spi: switch to managed controller allocation (part 2/3)

Johan Hovold <johan@kernel.org> says:

In preparation for fixing the SPI controller API so that it no longer
drops a reference when deregistering (non-managed) controllers (cf.
[1]), this series converts drivers using non-managed registration to use
managed allocation.

Included is also a related cleanup of a ti-qspi error path.

This second set will be followed by a third set of 12 patches for
drivers using managed registration.

That leaves us with 18 drivers using non-managed allocation, which is
few enough to be able to fix the API in tree-wide change.

Johan

[1] https://lore.kernel.org/lkml/20260325145319.1132072-1-johan@kernel.org/

Link: https://patch.msgid.link/20260505072909.618363-1-johan@kernel.org

23 files changed, 384 insertions, 95 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b4b703c90ca9..01e203964892 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3725,6 +3725,7 @@ extern const struct bpf_func_proto bpf_for_each_map_elem_proto;
 extern const struct bpf_func_proto bpf_btf_find_by_name_kind_proto;
 extern const struct bpf_func_proto bpf_sk_setsockopt_proto;
 extern const struct bpf_func_proto bpf_sk_getsockopt_proto;
+extern const struct bpf_func_proto bpf_sk_setsockopt_nodelay_proto;
 extern const struct bpf_func_proto bpf_unlocked_sk_setsockopt_proto;
 extern const struct bpf_func_proto bpf_unlocked_sk_getsockopt_proto;
 extern const struct bpf_func_proto bpf_find_vma_proto;
diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index f42563739d2e..50a784da7a81 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -611,8 +611,8 @@ struct cgroup {
 	/* used to wait for offlining of csses */
 	wait_queue_head_t offline_waitq;
 
-	/* used by cgroup_rmdir() to wait for dying tasks to leave */
-	wait_queue_head_t dying_populated_waitq;
+	/* defers killing csses after removal until cgroup is depopulated */
+	struct work_struct finish_destroy_work;
 
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index e52160e85af4..f6d037a30fd8 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -53,6 +53,7 @@ struct kernel_clone_args;
 enum css_task_iter_flags {
 	CSS_TASK_ITER_PROCS    = (1U << 0),  /* walk only threadgroup leaders */
 	CSS_TASK_ITER_THREADED = (1U << 1),  /* walk all threaded css_sets in the domain */
+	CSS_TASK_ITER_WITH_DEAD = (1U << 2),  /* include exiting tasks */
 	CSS_TASK_ITER_SKIPPED  = (1U << 16), /* internal flags */
 };
 
diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index 77c778d84d4c..a81b46af5118 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -146,6 +146,9 @@ struct xt_match {
 	/* Called when user tries to insert an entry of this type. */
 	int (*checkentry)(const struct xt_mtchk_param *);
 
+	/* Called to validate hooks based on the match configuration. */
+	int (*check_hooks)(const struct xt_mtchk_param *);
+
 	/* Called when entry of this type deleted. */
 	void (*destroy)(const struct xt_mtdtor_param *);
 #ifdef CONFIG_NETFILTER_XTABLES_COMPAT
@@ -187,6 +190,9 @@ struct xt_target {
 	/* Should return 0 on success or an error code otherwise (-Exxxx). */
 	int (*checkentry)(const struct xt_tgchk_param *);
 
+	/* Called to validate hooks based on the target configuration. */
+	int (*check_hooks)(const struct xt_tgchk_param *);
+
 	/* Called when entry of this type deleted. */
 	void (*destroy)(const struct xt_tgdtor_param *);
 #ifdef CONFIG_NETFILTER_XTABLES_COMPAT
@@ -279,8 +285,10 @@ bool xt_find_jump_offset(const unsigned int *offsets,
 
 int xt_check_proc_name(const char *name, unsigned int size);
 
+int xt_check_hooks_match(struct xt_mtchk_param *par);
 int xt_check_match(struct xt_mtchk_param *, unsigned int size, u16 proto,
 		   bool inv_proto);
+int xt_check_hooks_target(struct xt_tgchk_param *par);
 int xt_check_target(struct xt_tgchk_param *, unsigned int size, u16 proto,
 		    bool inv_proto);
 
diff --git a/include/linux/rseq.h b/include/linux/rseq.h
index b9d62fc2140d..7ef79b25e714 100644
--- a/include/linux/rseq.h
+++ b/include/linux/rseq.h
@@ -9,6 +9,11 @@
 
 void __rseq_handle_slowpath(struct pt_regs *regs);
 
+static __always_inline bool rseq_v2(struct task_struct *t)
+{
+	return IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY) && likely(t->rseq.event.has_rseq > 1);
+}
+
 /* Invoked from resume_user_mode_work() */
 static inline void rseq_handle_slowpath(struct pt_regs *regs)
 {
@@ -16,8 +21,7 @@ static inline void rseq_handle_slowpath(struct pt_regs *regs)
 		if (current->rseq.event.slowpath)
 			__rseq_handle_slowpath(regs);
 	} else {
-		/* '&' is intentional to spare one conditional branch */
-		if (current->rseq.event.sched_switch & current->rseq.event.has_rseq)
+		if (current->rseq.event.sched_switch && current->rseq.event.has_rseq)
 			__rseq_handle_slowpath(regs);
 	}
 }
@@ -30,9 +34,9 @@ void __rseq_signal_deliver(int sig, struct pt_regs *regs);
  */
 static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs)
 {
-	if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) {
-		/* '&' is intentional to spare one conditional branch */
-		if (current->rseq.event.has_rseq & current->rseq.event.user_irq)
+	if (rseq_v2(current)) {
+		/* has_rseq is implied in rseq_v2() */
+		if (current->rseq.event.user_irq)
 			__rseq_signal_deliver(ksig->sig, regs);
 	} else {
 		if (current->rseq.event.has_rseq)
@@ -50,15 +54,22 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t)
 {
 	struct rseq_event *ev = &t->rseq.event;
 
-	if (IS_ENABLED(CONFIG_GENERIC_IRQ_ENTRY)) {
+	/*
+	 * Only apply the user_irq optimization for RSEQ ABI V2 registrations.
+	 * Legacy users like TCMalloc rely on the original ABI V1 behaviour
+	 * which updates IDs on every context swtich.
+	 */
+	if (rseq_v2(t)) {
 		/*
-		 * Avoid a boat load of conditionals by using simple logic
-		 * to determine whether NOTIFY_RESUME needs to be raised.
+		 * Avoid a boat load of conditionals by using simple logic to
+		 * determine whether TIF_NOTIFY_RESUME or TIF_RSEQ needs to be
+		 * raised.
 		 *
-		 * It's required when the CPU or MM CID has changed or
-		 * the entry was from user space.
+		 * It's required when the CPU or MM CID has changed or the entry
+		 * was via interrupt from user space. ev->has_rseq does not have
+		 * to be evaluated here because rseq_v2() implies has_rseq.
 		 */
-		bool raise = (ev->user_irq | ev->ids_changed) & ev->has_rseq;
+		bool raise = ev->user_irq | ev->ids_changed;
 
 		if (raise) {
 			ev->sched_switch = true;
@@ -66,6 +77,7 @@ static __always_inline void rseq_sched_switch_event(struct task_struct *t)
 		}
 	} else {
 		if (ev->has_rseq) {
+			t->rseq.event.ids_changed = true;
 			t->rseq.event.sched_switch = true;
 			rseq_raise_notify_resume(t);
 		}
@@ -119,6 +131,8 @@ static inline void rseq_virt_userspace_exit(void)
 
 static inline void rseq_reset(struct task_struct *t)
 {
+	/* Protect against preemption and membarrier IPI */
+	guard(irqsave)();
 	memset(&t->rseq, 0, sizeof(t->rseq));
 	t->rseq.ids.cpu_id = RSEQ_CPU_ID_UNINITIALIZED;
 }
@@ -159,6 +173,7 @@ static inline unsigned int rseq_alloc_align(void)
 }
 
 #else /* CONFIG_RSEQ */
+static inline bool rseq_v2(struct task_struct *t) { return false; }
 static inline void rseq_handle_slowpath(struct pt_regs *regs) { }
 static inline void rseq_signal_deliver(struct ksignal *ksig, struct pt_regs *regs) { }
 static inline void rseq_sched_switch_event(struct task_struct *t) { }
diff --git a/include/linux/rseq_entry.h b/include/linux/rseq_entry.h
index f11ebd34f8b9..2d0295df5107 100644
--- a/include/linux/rseq_entry.h
+++ b/include/linux/rseq_entry.h
@@ -111,6 +111,20 @@ static __always_inline void rseq_slice_clear_grant(struct task_struct *t)
 	t->rseq.slice.state.granted = false;
 }
 
+/*
+ * Open coded, so it can be invoked within a user access region.
+ *
+ * This clears the user space state of the time slice extensions field only when
+ * the task has registered the optimized RSEQ_ABI V2. Some legacy registrations,
+ * e.g. TCMalloc, have conflicting non-ABI fields in struct RSEQ, which would be
+ * overwritten by an unconditional write.
+ */
+#define rseq_slice_clear_user(rseq, efault)				\
+do {									\
+	if (rseq_slice_extension_enabled())				\
+		unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);	\
+} while (0)
+
 static __always_inline bool __rseq_grant_slice_extension(bool work_pending)
 {
 	struct task_struct *curr = current;
@@ -230,10 +244,10 @@ static __always_inline bool rseq_slice_extension_enabled(void) { return false; }
 static __always_inline bool rseq_arm_slice_extension_timer(void) { return false; }
 static __always_inline void rseq_slice_clear_grant(struct task_struct *t) { }
 static __always_inline bool rseq_grant_slice_extension(unsigned long ti_work, unsigned long mask) { return false; }
+#define rseq_slice_clear_user(rseq, efault) do { } while (0)
 #endif /* !CONFIG_RSEQ_SLICE_EXTENSION */
 
 bool rseq_debug_update_user_cs(struct task_struct *t, struct pt_regs *regs, unsigned long csaddr);
-bool rseq_debug_validate_ids(struct task_struct *t);
 
 static __always_inline void rseq_note_user_irq_entry(void)
 {
@@ -353,43 +367,6 @@ efault:
 	return false;
 }
 
-/*
- * On debug kernels validate that user space did not mess with it if the
- * debug branch is enabled.
- */
-bool rseq_debug_validate_ids(struct task_struct *t)
-{
-	struct rseq __user *rseq = t->rseq.usrptr;
-	u32 cpu_id, uval, node_id;
-
-	/*
-	 * On the first exit after registering the rseq region CPU ID is
-	 * RSEQ_CPU_ID_UNINITIALIZED and node_id in user space is 0!
-	 */
-	node_id = t->rseq.ids.cpu_id != RSEQ_CPU_ID_UNINITIALIZED ?
-		  cpu_to_node(t->rseq.ids.cpu_id) : 0;
-
-	scoped_user_read_access(rseq, efault) {
-		unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault);
-		if (cpu_id != t->rseq.ids.cpu_id)
-			goto die;
-		unsafe_get_user(uval, &rseq->cpu_id, efault);
-		if (uval != cpu_id)
-			goto die;
-		unsafe_get_user(uval, &rseq->node_id, efault);
-		if (uval != node_id)
-			goto die;
-		unsafe_get_user(uval, &rseq->mm_cid, efault);
-		if (uval != t->rseq.ids.mm_cid)
-			goto die;
-	}
-	return true;
-die:
-	t->rseq.event.fatal = true;
-efault:
-	return false;
-}
-
 #endif /* RSEQ_BUILD_SLOW_PATH */
 
 /*
@@ -499,37 +476,50 @@ efault:
  * faults in task context are fatal too.
  */
 static rseq_inline
-bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids,
-			     u32 node_id, u64 *csaddr)
+bool rseq_set_ids_get_csaddr(struct task_struct *t, struct rseq_ids *ids, u64 *csaddr)
 {
 	struct rseq __user *rseq = t->rseq.usrptr;
 
-	if (static_branch_unlikely(&rseq_debug_enabled)) {
-		if (!rseq_debug_validate_ids(t))
-			return false;
-	}
-
 	scoped_user_rw_access(rseq, efault) {
+		/* Validate the R/O fields for debug and optimized mode */
+		if (static_branch_unlikely(&rseq_debug_enabled) || rseq_v2(t)) {
+			u32 cpu_id, uval;
+
+			unsafe_get_user(cpu_id, &rseq->cpu_id_start, efault);
+			if (cpu_id != t->rseq.ids.cpu_id)
+				goto die;
+			unsafe_get_user(uval, &rseq->cpu_id, efault);
+			if (uval != cpu_id)
+				goto die;
+			unsafe_get_user(uval, &rseq->node_id, efault);
+			if (uval != t->rseq.ids.node_id)
+				goto die;
+			unsafe_get_user(uval, &rseq->mm_cid, efault);
+			if (uval != t->rseq.ids.mm_cid)
+				goto die;
+		}
+
 		unsafe_put_user(ids->cpu_id, &rseq->cpu_id_start, efault);
 		unsafe_put_user(ids->cpu_id, &rseq->cpu_id, efault);
-		unsafe_put_user(node_id, &rseq->node_id, efault);
+		unsafe_put_user(ids->node_id, &rseq->node_id, efault);
 		unsafe_put_user(ids->mm_cid, &rseq->mm_cid, efault);
 		if (csaddr)
 			unsafe_get_user(*csaddr, &rseq->rseq_cs, efault);
 
-		/* Open coded, so it's in the same user access region */
-		if (rseq_slice_extension_enabled()) {
-			/* Unconditionally clear it, no point in conditionals */
-			unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
-		}
+		/* RSEQ ABI V2 only operations */
+		if (rseq_v2(t))
+			rseq_slice_clear_user(rseq, efault);
 	}
 
 	rseq_slice_clear_grant(t);
 	/* Cache the new values */
-	t->rseq.ids.cpu_cid = ids->cpu_cid;
+	t->rseq.ids = *ids;
 	rseq_stat_inc(rseq_stats.ids);
 	rseq_trace_update(t, ids);
 	return true;
+
+die:
+	t->rseq.event.fatal = true;
 efault:
 	return false;
 }
@@ -539,11 +529,11 @@ efault:
  * is in a critical section.
  */
 static rseq_inline bool rseq_update_usr(struct task_struct *t, struct pt_regs *regs,
-					struct rseq_ids *ids, u32 node_id)
+					struct rseq_ids *ids)
 {
 	u64 csaddr;
 
-	if (!rseq_set_ids_get_csaddr(t, ids, node_id, &csaddr))
+	if (!rseq_set_ids_get_csaddr(t, ids, &csaddr))
 		return false;
 
 	/*
@@ -612,6 +602,14 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t
 	 * interrupts disabled
 	 */
 	guard(pagefault)();
+	/*
+	 * This optimization is only valid when the task registered for the
+	 * optimized RSEQ_ABI_V2 variant. Some legacy users rely on the original
+	 * RSEQ implementation behaviour which unconditionally updated the IDs.
+	 * rseq_sched_switch_event() ensures that legacy registrations always
+	 * have both sched_switch and ids_changed set, which is compatible with
+	 * the historical TIF_NOTIFY_RESUME behaviour.
+	 */
 	if (likely(!t->rseq.event.ids_changed)) {
 		struct rseq __user *rseq = t->rseq.usrptr;
 		/*
@@ -623,11 +621,9 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t
 		scoped_user_rw_access(rseq, efault) {
 			unsafe_get_user(csaddr, &rseq->rseq_cs, efault);
 
-			/* Open coded, so it's in the same user access region */
-			if (rseq_slice_extension_enabled()) {
-				/* Unconditionally clear it, no point in conditionals */
-				unsafe_put_user(0U, &rseq->slice_ctrl.all, efault);
-			}
+			/* RSEQ ABI V2 only operations */
+			if (rseq_v2(t))
+				rseq_slice_clear_user(rseq, efault);
 		}
 
 		rseq_slice_clear_grant(t);
@@ -640,12 +636,12 @@ static __always_inline bool rseq_exit_user_update(struct pt_regs *regs, struct t
 	}
 
 	struct rseq_ids ids = {
-		.cpu_id = task_cpu(t),
-		.mm_cid = task_mm_cid(t),
+		.cpu_id	 = task_cpu(t),
+		.mm_cid	 = task_mm_cid(t),
+		.node_id = cpu_to_node(ids.cpu_id),
 	};
-	u32 node_id = cpu_to_node(ids.cpu_id);
 
-	return rseq_update_usr(t, regs, &ids, node_id);
+	return rseq_update_usr(t, regs, &ids);
 efault:
 	return false;
 }
diff --git a/include/linux/rseq_types.h b/include/linux/rseq_types.h
index 0b42045988db..85739a63e85e 100644
--- a/include/linux/rseq_types.h
+++ b/include/linux/rseq_types.h
@@ -9,6 +9,12 @@
 #ifdef CONFIG_RSEQ
 struct rseq;
 
+/*
+ * rseq_event::has_rseq contains the ABI version number so preserving it
+ * in AND operations requires a mask.
+ */
+#define RSEQ_HAS_RSEQ_VERSION_MASK	0xff
+
 /**
  * struct rseq_event - Storage for rseq related event management
  * @all:		Compound to initialize and clear the data efficiently
@@ -17,7 +23,8 @@ struct rseq;
  *			exit to user
  * @ids_changed:	Indicator that IDs need to be updated
  * @user_irq:		True on interrupt entry from user mode
- * @has_rseq:		True if the task has a rseq pointer installed
+ * @has_rseq:		Greater than 0 if the task has a rseq pointer installed.
+ *			Contains the RSEQ version number
  * @error:		Compound error code for the slow path to analyze
  * @fatal:		User space data corrupted or invalid
  * @slowpath:		Indicator that slow path processing via TIF_NOTIFY_RESUME
@@ -59,8 +66,9 @@ struct rseq_event {
  *		compiler emit a single compare on 64-bit
  * @cpu_id:	The CPU ID which was written last to user space
  * @mm_cid:	The MM CID which was written last to user space
+ * @node_id:	The node ID which was written last to user space
  *
- * @cpu_id and @mm_cid are updated when the data is written to user space.
+ * @cpu_id, @mm_cid and @node_id are updated when the data is written to user space.
  */
 struct rseq_ids {
 	union {
@@ -70,6 +78,7 @@ struct rseq_ids {
 			u32	mm_cid;
 		};
 	};
+	u32			node_id;
 };
 
 /**
diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 1a3af2ea2a79..adb9a4de068a 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -101,6 +101,7 @@ enum scx_ent_flags {
 	SCX_TASK_DEQD_FOR_SLEEP	= 1 << 3, /* last dequeue was for SLEEP */
 	SCX_TASK_SUB_INIT	= 1 << 4, /* task being initialized for a sub sched */
 	SCX_TASK_IMMED		= 1 << 5, /* task is on local DSQ with %SCX_ENQ_IMMED */
+	SCX_TASK_OFF_TASKS	= 1 << 6, /* removed from scx_tasks by sched_ext_dead() */
 
 	/*
 	 * Bits 8 and 9 are used to carry task state:
diff --git a/include/linux/sched/isolation.h b/include/linux/sched/isolation.h
index dc3975ff1b2e..cf0fd03dd7a2 100644
--- a/include/linux/sched/isolation.h
+++ b/include/linux/sched/isolation.h
@@ -21,6 +21,11 @@ enum hk_type {
 	HK_TYPE_MAX,
 
 	/*
+	 * HK_TYPE_KTHREAD is now an alias of HK_TYPE_DOMAIN
+	 */
+	HK_TYPE_KTHREAD = HK_TYPE_DOMAIN,
+
+	/*
 	 * The following housekeeping types are only set by the nohz_full
 	 * boot commandline option. So they can share the same value.
 	 */
@@ -29,7 +34,6 @@ enum hk_type {
 	HK_TYPE_RCU     = HK_TYPE_KERNEL_NOISE,
 	HK_TYPE_MISC    = HK_TYPE_KERNEL_NOISE,
 	HK_TYPE_WQ      = HK_TYPE_KERNEL_NOISE,
-	HK_TYPE_KTHREAD = HK_TYPE_KERNEL_NOISE
 };
 
 #ifdef CONFIG_CPU_ISOLATION
diff --git a/include/linux/smbdirect.h b/include/linux/smbdirect.h
new file mode 100644
index 000000000000..97f5ba730fa7
--- /dev/null
+++ b/include/linux/smbdirect.h
@@ -0,0 +1,186 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *   Copyright (C) 2025, Stefan Metzmacher
+ */
+
+#ifndef __LINUX_SMBDIRECT_H__
+#define __LINUX_SMBDIRECT_H__
+
+#include <linux/types.h>
+
+/* SMB-DIRECT buffer descriptor V1 structure [MS-SMBD] 2.2.3.1 */
+struct smbdirect_buffer_descriptor_v1 {
+	__le64 offset;
+	__le32 token;
+	__le32 length;
+} __packed;
+
+/*
+ * Connection parameters mostly from [MS-SMBD] 3.1.1.1
+ *
+ * These are setup and negotiated at the beginning of a
+ * connection and remain constant unless explicitly changed.
+ *
+ * Some values are important for the upper layer.
+ */
+struct smbdirect_socket_parameters {
+	__u64 flags;
+#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB ((__u64)0x1)
+#define SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW ((__u64)0x2)
+	__u32 resolve_addr_timeout_msec;
+	__u32 resolve_route_timeout_msec;
+	__u32 rdma_connect_timeout_msec;
+	__u32 negotiate_timeout_msec;
+	__u16 initiator_depth;     /* limited to U8_MAX */
+	__u16 responder_resources; /* limited to U8_MAX */
+	__u16 recv_credit_max;
+	__u16 send_credit_target;
+	__u32 max_send_size;
+	__u32 max_fragmented_send_size;
+	__u32 max_recv_size;
+	__u32 max_fragmented_recv_size;
+	__u32 max_read_write_size;
+	__u32 max_frmr_depth;
+	__u32 keepalive_interval_msec;
+	__u32 keepalive_timeout_msec;
+} __packed;
+
+#define SMBDIRECT_FLAG_PORT_RANGE_MASK ( \
+		SMBDIRECT_FLAG_PORT_RANGE_ONLY_IB | \
+		SMBDIRECT_FLAG_PORT_RANGE_ONLY_IW)
+
+struct smbdirect_socket;
+struct smbdirect_send_batch;
+struct smbdirect_mr_io;
+
+#include <rdma/rw.h>
+
+u8 smbdirect_netdev_rdma_capable_node_type(struct net_device *netdev);
+
+bool smbdirect_frwr_is_supported(const struct ib_device_attr *attrs);
+
+int smbdirect_socket_create_kern(struct net *net, struct smbdirect_socket **_sc);
+
+int smbdirect_socket_create_accepting(struct rdma_cm_id *id, struct smbdirect_socket **_sc);
+
+int smbdirect_socket_set_initial_parameters(struct smbdirect_socket *sc,
+					    const struct smbdirect_socket_parameters *sp);
+
+const struct smbdirect_socket_parameters *
+smbdirect_socket_get_current_parameters(struct smbdirect_socket *sc);
+
+int smbdirect_socket_set_kernel_settings(struct smbdirect_socket *sc,
+					 enum ib_poll_context poll_ctx,
+					 gfp_t gfp_mask);
+
+#define SMBDIRECT_LOG_ERR		0x0
+#define SMBDIRECT_LOG_INFO		0x1
+
+#define SMBDIRECT_LOG_OUTGOING			0x1
+#define SMBDIRECT_LOG_INCOMING			0x2
+#define SMBDIRECT_LOG_READ			0x4
+#define SMBDIRECT_LOG_WRITE			0x8
+#define SMBDIRECT_LOG_RDMA_SEND			0x10
+#define SMBDIRECT_LOG_RDMA_RECV			0x20
+#define SMBDIRECT_LOG_KEEP_ALIVE		0x40
+#define SMBDIRECT_LOG_RDMA_EVENT		0x80
+#define SMBDIRECT_LOG_RDMA_MR			0x100
+#define SMBDIRECT_LOG_RDMA_RW			0x200
+#define SMBDIRECT_LOG_NEGOTIATE			0x400
+void smbdirect_socket_set_logging(struct smbdirect_socket *sc,
+				  void *private_ptr,
+				  bool (*needed)(struct smbdirect_socket *sc,
+						 void *private_ptr,
+						 unsigned int lvl,
+						 unsigned int cls),
+				  void (*vaprintf)(struct smbdirect_socket *sc,
+						   const char *func,
+						   unsigned int line,
+						   void *private_ptr,
+						   unsigned int lvl,
+						   unsigned int cls,
+						   struct va_format *vaf));
+
+bool smbdirect_connection_is_connected(struct smbdirect_socket *sc);
+
+int smbdirect_connection_wait_for_connected(struct smbdirect_socket *sc);
+
+int smbdirect_socket_bind(struct smbdirect_socket *sc, struct sockaddr *addr);
+
+void smbdirect_socket_shutdown(struct smbdirect_socket *sc);
+
+void smbdirect_socket_release(struct smbdirect_socket *sc);
+
+int smbdirect_connection_send_batch_flush(struct smbdirect_socket *sc,
+					  struct smbdirect_send_batch *batch,
+					  bool is_last);
+
+/*
+ * This is only temporary and only needed
+ * as long as the client still requires
+ * to use smbdirect_connection_send_single_iter()
+ */
+struct smbdirect_send_batch_storage {
+	union {
+		struct list_head __msg_list;
+		__aligned_u64 __space[5];
+	};
+};
+
+struct smbdirect_send_batch *
+smbdirect_init_send_batch_storage(struct smbdirect_send_batch_storage *storage,
+				  bool need_invalidate_rkey,
+				  unsigned int remote_key);
+
+int smbdirect_connection_send_single_iter(struct smbdirect_socket *sc,
+					  struct smbdirect_send_batch *batch,
+					  struct iov_iter *iter,
+					  unsigned int flags,
+					  u32 remaining_data_length);
+
+int smbdirect_connection_send_wait_zero_pending(struct smbdirect_socket *sc);
+
+int smbdirect_connection_send_iter(struct smbdirect_socket *sc,
+				   struct iov_iter *iter,
+				   unsigned int flags,
+				   bool need_invalidate,
+				   unsigned int remote_key);
+
+int smbdirect_connection_recvmsg(struct smbdirect_socket *sc,
+				 struct msghdr *msg,
+				 unsigned int flags);
+
+int smbdirect_connect(struct smbdirect_socket *sc,
+		      const struct sockaddr *dst);
+
+int smbdirect_connect_sync(struct smbdirect_socket *sc,
+			   const struct sockaddr *dst);
+
+int smbdirect_socket_listen(struct smbdirect_socket *sc, int backlog);
+
+struct smbdirect_socket *smbdirect_socket_accept(struct smbdirect_socket *lsc,
+						 long timeo,
+						 struct proto_accept_arg *arg);
+
+int smbdirect_connection_rdma_xmit(struct smbdirect_socket *sc,
+				   void *buf, size_t buf_len,
+				   struct smbdirect_buffer_descriptor_v1 *desc,
+				   size_t desc_len,
+				   bool is_read);
+
+struct smbdirect_mr_io *
+smbdirect_connection_register_mr_io(struct smbdirect_socket *sc,
+				    struct iov_iter *iter,
+				    bool writing,
+				    bool need_invalidate);
+
+void smbdirect_mr_io_fill_buffer_descriptor(struct smbdirect_mr_io *mr,
+					    struct smbdirect_buffer_descriptor_v1 *v1);
+
+void smbdirect_connection_deregister_mr_io(struct smbdirect_mr_io *mr);
+
+void smbdirect_connection_legacy_debug_proc_show(struct smbdirect_socket *sc,
+						 unsigned int rdma_readwrite_threshold,
+						 struct seq_file *m);
+
+#endif /* __LINUX_SMBDIRECT_H__ */
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index ab6cb70ca1a5..6177624539b3 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -534,8 +534,10 @@ alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...)
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 __printf(2, 5) struct workqueue_struct *
-devm_alloc_workqueue(struct device *dev, const char *fmt, unsigned int flags,
-		     int max_active, ...);
+devm_alloc_workqueue_noprof(struct device *dev, const char *fmt,
+			    unsigned int flags, int max_active, ...);
+#define devm_alloc_workqueue(...)	\
+	alloc_hooks(devm_alloc_workqueue_noprof(__VA_ARGS__))
 
 #ifdef CONFIG_LOCKDEP
 /**
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index a7bffb908c1e..aa600fbf9a53 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -2495,7 +2495,7 @@ void mgmt_adv_monitor_device_lost(struct hci_dev *hdev, u16 handle,
 				  bdaddr_t *bdaddr, u8 addr_type);
 
 int hci_abort_conn(struct hci_conn *conn, u8 reason);
-u8 hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency,
+void hci_le_conn_update(struct hci_conn *conn, u16 min, u16 max, u16 latency,
 		      u16 to_multiplier);
 void hci_le_start_enc(struct hci_conn *conn, __le16 ediv, __le64 rand,
 		      __u8 ltk[16], __u8 key_size);
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index e0ca3904ff8e..2f312d1f67d6 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -99,6 +99,7 @@
 	FN(FRAG_TOO_FAR)		\
 	FN(TCP_MINTTL)			\
 	FN(IPV6_BAD_EXTHDR)		\
+	FN(IPV6_TOO_MANY_EXTHDRS)	\
 	FN(IPV6_NDISC_FRAG)		\
 	FN(IPV6_NDISC_HOP_LIMIT)	\
 	FN(IPV6_NDISC_BAD_CODE)		\
@@ -494,6 +495,11 @@ enum skb_drop_reason {
 	SKB_DROP_REASON_TCP_MINTTL,
 	/** @SKB_DROP_REASON_IPV6_BAD_EXTHDR: Bad IPv6 extension header. */
 	SKB_DROP_REASON_IPV6_BAD_EXTHDR,
+	/**
+	 * @SKB_DROP_REASON_IPV6_TOO_MANY_EXTHDRS: Number of IPv6 extension
+	 * headers in the packet exceeds IP6_MAX_EXT_HDRS_CNT.
+	 */
+	SKB_DROP_REASON_IPV6_TOO_MANY_EXTHDRS,
 	/** @SKB_DROP_REASON_IPV6_NDISC_FRAG: invalid frag (suppress_frag_ndisc). */
 	SKB_DROP_REASON_IPV6_NDISC_FRAG,
 	/** @SKB_DROP_REASON_IPV6_NDISC_HOP_LIMIT: invalid hop limit. */
diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h
index 72d325c81313..02762ce73a0c 100644
--- a/include/net/ip_vs.h
+++ b/include/net/ip_vs.h
@@ -491,6 +491,7 @@ struct ip_vs_est_kt_data {
 	DECLARE_BITMAP(avail, IPVS_EST_NTICKS);	/* tick has space for ests */
 	unsigned long		est_timer;	/* estimation timer (jiffies) */
 	struct ip_vs_stats	*calc_stats;	/* Used for calculation */
+	int			needed;		/* task is needed */
 	int			tick_len[IPVS_EST_NTICKS];	/* est count */
 	int			id;		/* ktid per netns */
 	int			chain_max;	/* max ests per tick chain */
@@ -1411,7 +1412,7 @@ static inline int sysctl_run_estimation(struct netns_ipvs *ipvs)
 	return ipvs->sysctl_run_estimation;
 }
 
-static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs)
+static inline const struct cpumask *__sysctl_est_cpulist(struct netns_ipvs *ipvs)
 {
 	if (ipvs->est_cpulist_valid)
 		return ipvs->sysctl_est_cpulist;
@@ -1529,7 +1530,7 @@ static inline int sysctl_run_estimation(struct netns_ipvs *ipvs)
 	return 1;
 }
 
-static inline const struct cpumask *sysctl_est_cpulist(struct netns_ipvs *ipvs)
+static inline const struct cpumask *__sysctl_est_cpulist(struct netns_ipvs *ipvs)
 {
 	return housekeeping_cpumask(HK_TYPE_KTHREAD);
 }
@@ -1564,6 +1565,18 @@ static inline int sysctl_svc_lfactor(struct netns_ipvs *ipvs)
 	return READ_ONCE(ipvs->sysctl_svc_lfactor);
 }
 
+static inline bool sysctl_est_cpulist_empty(struct netns_ipvs *ipvs)
+{
+	guard(rcu)();
+	return cpumask_empty(__sysctl_est_cpulist(ipvs));
+}
+
+static inline unsigned int sysctl_est_cpulist_weight(struct netns_ipvs *ipvs)
+{
+	guard(rcu)();
+	return cpumask_weight(__sysctl_est_cpulist(ipvs));
+}
+
 /* IPVS core functions
  * (from ip_vs_core.c)
  */
@@ -1884,18 +1897,26 @@ int ip_vs_start_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
 void ip_vs_stop_estimator(struct netns_ipvs *ipvs, struct ip_vs_stats *stats);
 void ip_vs_zero_estimator(struct ip_vs_stats *stats);
 void ip_vs_read_estimator(struct ip_vs_kstats *dst, struct ip_vs_stats *stats);
-void ip_vs_est_reload_start(struct netns_ipvs *ipvs);
+void ip_vs_est_reload_start(struct netns_ipvs *ipvs, bool restart);
 int ip_vs_est_kthread_start(struct netns_ipvs *ipvs,
 			    struct ip_vs_est_kt_data *kd);
 void ip_vs_est_kthread_stop(struct ip_vs_est_kt_data *kd);
 
+static inline void ip_vs_stop_estimator_tot_stats(struct netns_ipvs *ipvs)
+{
+#ifdef CONFIG_SYSCTL
+	ip_vs_stop_estimator(ipvs, &ipvs->tot_stats->s);
+	ipvs->tot_stats->s.est.ktid = -2;
+#endif
+}
+
 static inline void ip_vs_est_stopped_recalc(struct netns_ipvs *ipvs)
 {
 #ifdef CONFIG_SYSCTL
 	/* Stop tasks while cpulist is empty or if disabled with flag */
 	ipvs->est_stopped = !sysctl_run_estimation(ipvs) ||
 			    (ipvs->est_cpulist_valid &&
-			     cpumask_empty(sysctl_est_cpulist(ipvs)));
+			     sysctl_est_cpulist_empty(ipvs));
 #endif
 }
 
@@ -1911,7 +1932,7 @@ static inline bool ip_vs_est_stopped(struct netns_ipvs *ipvs)
 static inline int ip_vs_est_max_threads(struct netns_ipvs *ipvs)
 {
 	unsigned int limit = IPVS_EST_CPU_KTHREADS *
-			     cpumask_weight(sysctl_est_cpulist(ipvs));
+			     sysctl_est_cpulist_weight(ipvs);
 
 	return max(1U, limit);
 }
diff --git a/include/net/ipv6.h b/include/net/ipv6.h
index d042afe7a245..1dec81faff28 100644
--- a/include/net/ipv6.h
+++ b/include/net/ipv6.h
@@ -90,6 +90,9 @@ struct ip_tunnel_info;
 #define IP6_DEFAULT_MAX_DST_OPTS_LEN	 INT_MAX /* No limit */
 #define IP6_DEFAULT_MAX_HBH_OPTS_LEN	 INT_MAX /* No limit */
 
+/* Hard limit on traversed IPv6 extension headers */
+#define IP6_MAX_EXT_HDRS_CNT		 12
+
 /*
  *	Addr type
  *	
diff --git a/include/net/mana/shm_channel.h b/include/net/mana/shm_channel.h
index 5199b41497ff..dbabcfb95daf 100644
--- a/include/net/mana/shm_channel.h
+++ b/include/net/mana/shm_channel.h
@@ -4,6 +4,12 @@
 #ifndef _SHM_CHANNEL_H
 #define _SHM_CHANNEL_H
 
+#define SMC_APERTURE_BITS 256
+#define SMC_BASIC_UNIT (sizeof(u32))
+#define SMC_APERTURE_DWORDS (SMC_APERTURE_BITS / (SMC_BASIC_UNIT * 8))
+#define SMC_LAST_DWORD (SMC_APERTURE_DWORDS - 1)
+#define SMC_APERTURE_SIZE  (SMC_APERTURE_BITS / 8)
+
 struct shm_channel {
 	struct device *dev;
 	void __iomem *base;
diff --git a/include/net/netfilter/nf_dup_netdev.h b/include/net/netfilter/nf_dup_netdev.h
index b175d271aec9..609bcf422a9b 100644
--- a/include/net/netfilter/nf_dup_netdev.h
+++ b/include/net/netfilter/nf_dup_netdev.h
@@ -3,10 +3,23 @@
 #define _NF_DUP_NETDEV_H_
 
 #include <net/netfilter/nf_tables.h>
+#include <linux/netdevice.h>
+#include <linux/sched.h>
 
 void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif);
 
+#define NF_RECURSION_LIMIT	2
+
+static inline u8 *nf_get_nf_dup_skb_recursion(void)
+{
+#ifndef CONFIG_PREEMPT_RT
+	return this_cpu_ptr(&softnet_data.xmit.nf_dup_skb_recursion);
+#else
+	return &current->net_xmit.nf_dup_skb_recursion;
+#endif
+}
+
 struct nft_offload_ctx;
 struct nft_flow_rule;
 
diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h
index b09c11c048d5..7b23b245a5a8 100644
--- a/include/net/netfilter/nf_flow_table.h
+++ b/include/net/netfilter/nf_flow_table.h
@@ -148,9 +148,10 @@ struct flow_offload_tuple {
 	/* All members above are keys for lookups, see flow_offload_hash(). */
 	struct { }			__hash;
 
-	u8				dir:2,
+	u16				dir:2,
 					xmit_type:3,
 					encap_num:2,
+					needs_gso_segment:1,
 					tun_num:2,
 					in_vlan_ingress:2;
 	u16				mtu;
@@ -232,6 +233,7 @@ struct nf_flow_route {
 			u32			hw_ifindex;
 			u8			h_source[ETH_ALEN];
 			u8			h_dest[ETH_ALEN];
+			u8			needs_gso_segment:1;
 		} out;
 		enum flow_offload_xmit_type	xmit_type;
 	} tuple[FLOW_OFFLOAD_DIR_MAX];
diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h
index 80ccd4dda8e0..6e27c56514df 100644
--- a/include/net/netns/ipv4.h
+++ b/include/net/netns/ipv4.h
@@ -275,7 +275,7 @@ struct netns_ipv4 {
 
 #ifdef CONFIG_IP_MROUTE
 #ifndef CONFIG_IP_MROUTE_MULTIPLE_TABLES
-	struct mr_table		*mrt;
+	struct mr_table __rcu	*mrt;
 #else
 	struct list_head	mr_tables;
 	struct fib_rules_ops	*mr_rules_ops;
diff --git a/include/uapi/linux/rseq.h b/include/uapi/linux/rseq.h
index f69344fe6c08..ca6fe1f9d05e 100644
--- a/include/uapi/linux/rseq.h
+++ b/include/uapi/linux/rseq.h
@@ -28,7 +28,7 @@ enum rseq_cs_flags_bit {
 	RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT_BIT	= 0,
 	RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL_BIT	= 1,
 	RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE_BIT	= 2,
-	/* (3) Intentional gap to put new bits into a separate byte */
+	/* (3) Intentional gap to keep new bits separate */
 
 	/* User read only feature flags */
 	RSEQ_CS_FLAG_SLICE_EXT_AVAILABLE_BIT	= 4,
@@ -161,6 +161,9 @@ struct rseq {
 	 *	- RSEQ_CS_FLAG_NO_RESTART_ON_PREEMPT
 	 *	- RSEQ_CS_FLAG_NO_RESTART_ON_SIGNAL
 	 *	- RSEQ_CS_FLAG_NO_RESTART_ON_MIGRATE
+	 *
+	 * It is now used for feature status advertisement by the kernel.
+	 * See: enum rseq_cs_flags_bit for further information.
 	 */
 	__u32 flags;
 
diff --git a/include/ufs/unipro.h b/include/ufs/unipro.h
index f849a2a101ae..9c168703b104 100644
--- a/include/ufs/unipro.h
+++ b/include/ufs/unipro.h
@@ -333,6 +333,11 @@ enum ufs_eom_eye_mask {
 #define DME_LocalTC0ReplayTimeOutVal		0xD042
 #define DME_LocalAFC0ReqTimeOutVal		0xD043
 
+enum ufs_op_mode {
+	LS_MODE = 1,
+	HS_MODE = 2,
+};
+
 /* PA power modes */
 enum ufs_pa_pwr_mode {
 	FAST_MODE	= 1,
diff --git a/include/video/imx-ipu-image-convert.h b/include/video/imx-ipu-image-convert.h
index 003b3927ede5..6b77968a6a15 100644
--- a/include/video/imx-ipu-image-convert.h
+++ b/include/video/imx-ipu-image-convert.h
@@ -27,12 +27,13 @@ struct ipu_image_convert_run {
 
 	int status;
 
+	/* private: */
 	/* internal to image converter, callers don't touch */
 	struct list_head list;
 };
 
 /**
- * ipu_image_convert_cb_t - conversion callback function prototype
+ * typedef ipu_image_convert_cb_t - conversion callback function prototype
  *
  * @run:	the completed conversion run pointer
  * @ctx:	a private context pointer for the callback
@@ -60,7 +61,7 @@ void ipu_image_convert_adjust(struct ipu_image *in, struct ipu_image *out,
  * @out:	output image format
  * @rot_mode:	rotation mode
  *
- * Returns 0 if the formats and rotation mode meet IPU restrictions,
+ * Returns: 0 if the formats and rotation mode meet IPU restrictions,
  * -EINVAL otherwise.
  */
 int ipu_image_convert_verify(struct ipu_image *in, struct ipu_image *out,
@@ -77,11 +78,11 @@ int ipu_image_convert_verify(struct ipu_image *in, struct ipu_image *out,
  * @complete:	run completion callback
  * @complete_context:	a context pointer for the completion callback
  *
- * Returns an opaque conversion context pointer on success, error pointer
+ * In V4L2, drivers should call ipu_image_convert_prepare() at streamon.
+ *
+ * Returns: an opaque conversion context pointer on success, error pointer
  * on failure. The input/output formats and rotation mode must already meet
  * IPU retrictions.
- *
- * In V4L2, drivers should call ipu_image_convert_prepare() at streamon.
  */
 struct ipu_image_convert_ctx *
 ipu_image_convert_prepare(struct ipu_soc *ipu, enum ipu_ic_task ic_task,
@@ -122,6 +123,8 @@ void ipu_image_convert_unprepare(struct ipu_image_convert_ctx *ctx);
  * In V4L2, drivers should call ipu_image_convert_queue() while
  * streaming to queue the conversion of a received input buffer.
  * For example mem2mem devices this would be called in .device_run.
+ *
+ * Returns: 0 on success or -errno on error.
  */
 int ipu_image_convert_queue(struct ipu_image_convert_run *run);
 
@@ -155,6 +158,9 @@ void ipu_image_convert_abort(struct ipu_image_convert_ctx *ctx);
  * On successful return the caller can queue more run requests if needed, using
  * the prepared context in run->ctx. The caller is responsible for unpreparing
  * the context when no more conversion requests are needed.
+ *
+ * Returns: pointer to the created &struct ipu_image_convert_run that has
+ * been queued on success; an ERR_PTR(errno) on error.
  */
 struct ipu_image_convert_run *
 ipu_image_convert(struct ipu_soc *ipu, enum ipu_ic_task ic_task,
diff --git a/include/video/udlfb.h b/include/video/udlfb.h
index 58fb5732831a..ab34790d57ec 100644
--- a/include/video/udlfb.h
+++ b/include/video/udlfb.h
@@ -56,6 +56,7 @@ struct dlfb_data {
 	spinlock_t damage_lock;
 	struct work_struct damage_work;
 	struct fb_ops ops;
+	atomic_t mmap_count;
 	/* blit-only rendering path metrics, exposed through sysfs */
 	atomic_t bytes_rendered; /* raw pixel-bytes driver asked to render */
 	atomic_t bytes_identical; /* saved effort with backbuffer comparison */