From 7efa84b5cdd6d473c7e80912638fca9d7167f202 Mon Sep 17 00:00:00 2001
From: Nathan Chancellor <nathan@kernel.org>
Date: Fri, 4 Apr 2025 15:10:02 -0700
Subject: compiler-gcc.h: Introduce __diag_GCC_all

It is not possible disabling a diagnostic for all versions of GCC
without hard coding the minimum supported version at the site, as the
GCC specific macros require a minimum version to disable the warning
for:

    __diag_ignore(GCC, 5, ...);

__diag_ignore_all() does not solve this issue because it disables a
diagnostic for all versions of both GCC and clang, not just one or the
other.

Introduce __diag_GCC_all so that developers can write

    __diag_ignore(GCC, all, ...);

to disable a particular diagnostic for all versions of GCC, while not
affecting clang.

Closes: https://lore.kernel.org/r/CAHk-=wgfX9nBGE0Ap9GjhOy7Mn=RSy=rx0MvqfYFFDx31KJXqQ@mail.gmail.com
Signed-off-by: Nathan Chancellor <nathan@kernel.org>
Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Link: https://patch.msgid.link/20250404-vsprintf-convert-pragmas-to-__diag-v1-1-5d6c5c55b2bd@kernel.org
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 include/linux/compiler-gcc.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/compiler-gcc.h b/include/linux/compiler-gcc.h
index c9b58188ec61..c75a222880f9 100644
--- a/include/linux/compiler-gcc.h
+++ b/include/linux/compiler-gcc.h
@@ -127,6 +127,8 @@
 #define __diag_GCC_8(s)
 #endif
 
+#define __diag_GCC_all(s)	__diag(s)
+
 #define __diag_ignore_all(option, comment) \
 	__diag(__diag_GCC_ignore option)
 
-- 
cgit v1.2.3


From edfc4c8a1edffa6849e19ffade1be8dd824989d0 Mon Sep 17 00:00:00 2001
From: Michal Koutný <mkoutny@suse.com>
Date: Tue, 3 Jun 2025 17:45:27 +0200
Subject: cgroup: Drop sock_cgroup_classid() dummy implementation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The semantic of returning 0 is unclear when !CONFIG_CGROUP_NET_CLASSID.
Since there are no callers of sock_cgroup_classid() with that config
anymore we can undefine the helper at all and enforce all (future)
callers to handle cases when !CONFIG_CGROUP_NET_CLASSID.

Signed-off-by: Michal Koutný <mkoutny@suse.com>
Link: https://lore.kernel.org/r/Z_52r_v9-3JUzDT7@calendula/
Acked-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Waiman Long <longman@redhat.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup-defs.h | 10 ++++------
 1 file changed, 4 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index e61687d5e496..cd7f093e34cd 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -898,14 +898,12 @@ static inline u16 sock_cgroup_prioidx(const struct sock_cgroup_data *skcd)
 #endif
 }
 
+#ifdef CONFIG_CGROUP_NET_CLASSID
 static inline u32 sock_cgroup_classid(const struct sock_cgroup_data *skcd)
 {
-#ifdef CONFIG_CGROUP_NET_CLASSID
 	return READ_ONCE(skcd->classid);
-#else
-	return 0;
-#endif
 }
+#endif
 
 static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 					   u16 prioidx)
@@ -915,13 +913,13 @@ static inline void sock_cgroup_set_prioidx(struct sock_cgroup_data *skcd,
 #endif
 }
 
+#ifdef CONFIG_CGROUP_NET_CLASSID
 static inline void sock_cgroup_set_classid(struct sock_cgroup_data *skcd,
 					   u32 classid)
 {
-#ifdef CONFIG_CGROUP_NET_CLASSID
 	WRITE_ONCE(skcd->classid, classid);
-#endif
 }
+#endif
 
 #else	/* CONFIG_SOCK_CGROUP_DATA */
 
-- 
cgit v1.2.3


From 49b393af3130c7712c7e8f215f4126c9a8060fa6 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Wed, 4 Jun 2025 10:21:38 +0200
Subject: perf: Add comment to enum perf_event_state

Better describe the event states.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Leo Yan <leo.yan@arm.com>
Link: https://lkml.kernel.org/r/20250604135801.GK38114@noisy.programming.kicks-ass.net
---
 include/linux/perf_event.h | 42 ++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 40 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 52dc7cfab0e0..ec9d96025683 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -635,8 +635,46 @@ struct perf_addr_filter_range {
 	unsigned long			size;
 };
 
-/**
- * enum perf_event_state - the states of an event:
+/*
+ * The normal states are:
+ *
+ *            ACTIVE    --.
+ *               ^        |
+ *               |        |
+ *       sched_{in,out}() |
+ *               |        |
+ *               v        |
+ *      ,---> INACTIVE  --+ <-.
+ *      |                 |   |
+ *      |                {dis,en}able()
+ *   sched_in()           |   |
+ *      |       OFF    <--' --+
+ *      |                     |
+ *      `--->  ERROR    ------'
+ *
+ * That is:
+ *
+ * sched_in:       INACTIVE          -> {ACTIVE,ERROR}
+ * sched_out:      ACTIVE            -> INACTIVE
+ * disable:        {ACTIVE,INACTIVE} -> OFF
+ * enable:         {OFF,ERROR}       -> INACTIVE
+ *
+ * Where {OFF,ERROR} are disabled states.
+ *
+ * Then we have the {EXIT,REVOKED,DEAD} states which are various shades of
+ * defunct events:
+ *
+ *  - EXIT means task that the even was assigned to died, but child events
+ *    still live, and further children can still be created. But the event
+ *    itself will never be active again. It can only transition to
+ *    {REVOKED,DEAD};
+ *
+ *  - REVOKED means the PMU the event was associated with is gone; all
+ *    functionality is stopped but the event is still alive. Can only
+ *    transition to DEAD;
+ *
+ *  - DEAD event really is DYING tearing down state and freeing bits.
+ *
  */
 enum perf_event_state {
 	PERF_EVENT_STATE_DEAD		= -5,
-- 
cgit v1.2.3


From dc38441890ec0c54d032395ea9c365a4307185fa Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Fri, 16 May 2025 11:26:21 +0300
Subject: iio: backend: add support for filter config
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add backend support for digital filter type selection.

This setting can be adjusted within the IP cores interfacing devices.

The IP core can be configured based on the state of the actual
digital filter configuration of the part.

Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Link: https://patch.msgid.link/20250516082630.8236-2-antoniu.miclaus@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-backend.c | 18 ++++++++++++++++++
 include/linux/iio/backend.h        | 13 +++++++++++++
 2 files changed, 31 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c
index c1eb9ef9db08..e2d46c12c15f 100644
--- a/drivers/iio/industrialio-backend.c
+++ b/drivers/iio/industrialio-backend.c
@@ -808,6 +808,24 @@ static int __devm_iio_backend_get(struct device *dev, struct iio_backend *back)
 	return 0;
 }
 
+/**
+ * iio_backend_filter_type_set - Set filter type
+ * @back: Backend device
+ * @type: Filter type.
+ *
+ * RETURNS:
+ * 0 on success, negative error number on failure.
+ */
+int iio_backend_filter_type_set(struct iio_backend *back,
+				enum iio_backend_filter_type type)
+{
+	if (type >= IIO_BACKEND_FILTER_TYPE_MAX)
+		return -EINVAL;
+
+	return iio_backend_op_call(back, filter_type_set, type);
+}
+EXPORT_SYMBOL_NS_GPL(iio_backend_filter_type_set, "IIO_BACKEND");
+
 /**
  * iio_backend_ddr_enable - Enable interface DDR (Double Data Rate) mode
  * @back: Backend device
diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h
index e59d909cb659..8a1690f21318 100644
--- a/include/linux/iio/backend.h
+++ b/include/linux/iio/backend.h
@@ -76,6 +76,14 @@ enum iio_backend_interface_type {
 	IIO_BACKEND_INTERFACE_MAX
 };
 
+enum iio_backend_filter_type {
+	IIO_BACKEND_FILTER_TYPE_DISABLED,
+	IIO_BACKEND_FILTER_TYPE_SINC1,
+	IIO_BACKEND_FILTER_TYPE_SINC5,
+	IIO_BACKEND_FILTER_TYPE_SINC5_PLUS_COMP,
+	IIO_BACKEND_FILTER_TYPE_MAX
+};
+
 /**
  * struct iio_backend_ops - operations structure for an iio_backend
  * @enable: Enable backend.
@@ -101,6 +109,7 @@ enum iio_backend_interface_type {
  * @read_raw: Read a channel attribute from a backend device
  * @debugfs_print_chan_status: Print channel status into a buffer.
  * @debugfs_reg_access: Read or write register value of backend.
+ * @filter_type_set: Set filter type.
  * @ddr_enable: Enable interface DDR (Double Data Rate) mode.
  * @ddr_disable: Disable interface DDR (Double Data Rate) mode.
  * @data_stream_enable: Enable data stream.
@@ -153,6 +162,8 @@ struct iio_backend_ops {
 					 size_t len);
 	int (*debugfs_reg_access)(struct iio_backend *back, unsigned int reg,
 				  unsigned int writeval, unsigned int *readval);
+	int (*filter_type_set)(struct iio_backend *back,
+			       enum iio_backend_filter_type type);
 	int (*ddr_enable)(struct iio_backend *back);
 	int (*ddr_disable)(struct iio_backend *back);
 	int (*data_stream_enable)(struct iio_backend *back);
@@ -195,6 +206,8 @@ int iio_backend_data_sample_trigger(struct iio_backend *back,
 int devm_iio_backend_request_buffer(struct device *dev,
 				    struct iio_backend *back,
 				    struct iio_dev *indio_dev);
+int iio_backend_filter_type_set(struct iio_backend *back,
+				enum iio_backend_filter_type type);
 int iio_backend_ddr_enable(struct iio_backend *back);
 int iio_backend_ddr_disable(struct iio_backend *back);
 int iio_backend_data_stream_enable(struct iio_backend *back);
-- 
cgit v1.2.3


From 995fd6e002b0d1ac435faed68005585906467e92 Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Fri, 16 May 2025 11:26:22 +0300
Subject: iio: backend: add support for data alignment
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add backend support for staring the capture synchronization.
When activated, it initates a proccess that aligns the sample's most
significant bit (MSB) based solely on the captured data, without
considering any other external signals.

Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Link: https://patch.msgid.link/20250516082630.8236-3-antoniu.miclaus@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-backend.c | 23 +++++++++++++++++++++++
 include/linux/iio/backend.h        |  3 +++
 2 files changed, 26 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c
index e2d46c12c15f..1fd71b520691 100644
--- a/drivers/iio/industrialio-backend.c
+++ b/drivers/iio/industrialio-backend.c
@@ -826,6 +826,29 @@ int iio_backend_filter_type_set(struct iio_backend *back,
 }
 EXPORT_SYMBOL_NS_GPL(iio_backend_filter_type_set, "IIO_BACKEND");
 
+/**
+ * iio_backend_interface_data_align - Perform the data alignment process.
+ * @back: Backend device
+ * @timeout_us: Timeout value in us.
+ *
+ * When activated, it initates a proccess that aligns the sample's most
+ * significant bit (MSB) based solely on the captured data, without
+ * considering any other external signals.
+ *
+ * The timeout_us value must be greater than 0.
+ *
+ * RETURNS:
+ * 0 on success, negative error number on failure.
+ */
+int iio_backend_interface_data_align(struct iio_backend *back, u32 timeout_us)
+{
+	if (!timeout_us)
+		return -EINVAL;
+
+	return iio_backend_op_call(back, interface_data_align, timeout_us);
+}
+EXPORT_SYMBOL_NS_GPL(iio_backend_interface_data_align, "IIO_BACKEND");
+
 /**
  * iio_backend_ddr_enable - Enable interface DDR (Double Data Rate) mode
  * @back: Backend device
diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h
index 8a1690f21318..c579eb523466 100644
--- a/include/linux/iio/backend.h
+++ b/include/linux/iio/backend.h
@@ -110,6 +110,7 @@ enum iio_backend_filter_type {
  * @debugfs_print_chan_status: Print channel status into a buffer.
  * @debugfs_reg_access: Read or write register value of backend.
  * @filter_type_set: Set filter type.
+ * @interface_data_align: Perform the data alignment process.
  * @ddr_enable: Enable interface DDR (Double Data Rate) mode.
  * @ddr_disable: Disable interface DDR (Double Data Rate) mode.
  * @data_stream_enable: Enable data stream.
@@ -164,6 +165,7 @@ struct iio_backend_ops {
 				  unsigned int writeval, unsigned int *readval);
 	int (*filter_type_set)(struct iio_backend *back,
 			       enum iio_backend_filter_type type);
+	int (*interface_data_align)(struct iio_backend *back, u32 timeout_us);
 	int (*ddr_enable)(struct iio_backend *back);
 	int (*ddr_disable)(struct iio_backend *back);
 	int (*data_stream_enable)(struct iio_backend *back);
@@ -208,6 +210,7 @@ int devm_iio_backend_request_buffer(struct device *dev,
 				    struct iio_dev *indio_dev);
 int iio_backend_filter_type_set(struct iio_backend *back,
 				enum iio_backend_filter_type type);
+int iio_backend_interface_data_align(struct iio_backend *back, u32 timeout_us);
 int iio_backend_ddr_enable(struct iio_backend *back);
 int iio_backend_ddr_disable(struct iio_backend *back);
 int iio_backend_data_stream_enable(struct iio_backend *back);
-- 
cgit v1.2.3


From 5ef4cc6d2414d115cf09a6a33c3155f12e58a27d Mon Sep 17 00:00:00 2001
From: Antoniu Miclaus <antoniu.miclaus@analog.com>
Date: Fri, 16 May 2025 11:26:23 +0300
Subject: iio: backend: add support for number of lanes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add iio backend support for number of lanes to be enabled.

Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Signed-off-by: Antoniu Miclaus <antoniu.miclaus@analog.com>
Link: https://patch.msgid.link/20250516082630.8236-4-antoniu.miclaus@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-backend.c | 17 +++++++++++++++++
 include/linux/iio/backend.h        |  3 +++
 2 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c
index 1fd71b520691..6b2d3dac52b3 100644
--- a/drivers/iio/industrialio-backend.c
+++ b/drivers/iio/industrialio-backend.c
@@ -849,6 +849,23 @@ int iio_backend_interface_data_align(struct iio_backend *back, u32 timeout_us)
 }
 EXPORT_SYMBOL_NS_GPL(iio_backend_interface_data_align, "IIO_BACKEND");
 
+/**
+ * iio_backend_num_lanes_set - Number of lanes enabled.
+ * @back: Backend device
+ * @num_lanes: Number of lanes.
+ *
+ * RETURNS:
+ * 0 on success, negative error number on failure.
+ */
+int iio_backend_num_lanes_set(struct iio_backend *back, unsigned int num_lanes)
+{
+	if (!num_lanes)
+		return -EINVAL;
+
+	return iio_backend_op_call(back, num_lanes_set, num_lanes);
+}
+EXPORT_SYMBOL_NS_GPL(iio_backend_num_lanes_set, "IIO_BACKEND");
+
 /**
  * iio_backend_ddr_enable - Enable interface DDR (Double Data Rate) mode
  * @back: Backend device
diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h
index c579eb523466..1f528fbd9d11 100644
--- a/include/linux/iio/backend.h
+++ b/include/linux/iio/backend.h
@@ -111,6 +111,7 @@ enum iio_backend_filter_type {
  * @debugfs_reg_access: Read or write register value of backend.
  * @filter_type_set: Set filter type.
  * @interface_data_align: Perform the data alignment process.
+ * @num_lanes_set: Set the number of lanes enabled.
  * @ddr_enable: Enable interface DDR (Double Data Rate) mode.
  * @ddr_disable: Disable interface DDR (Double Data Rate) mode.
  * @data_stream_enable: Enable data stream.
@@ -166,6 +167,7 @@ struct iio_backend_ops {
 	int (*filter_type_set)(struct iio_backend *back,
 			       enum iio_backend_filter_type type);
 	int (*interface_data_align)(struct iio_backend *back, u32 timeout_us);
+	int (*num_lanes_set)(struct iio_backend *back, unsigned int num_lanes);
 	int (*ddr_enable)(struct iio_backend *back);
 	int (*ddr_disable)(struct iio_backend *back);
 	int (*data_stream_enable)(struct iio_backend *back);
@@ -211,6 +213,7 @@ int devm_iio_backend_request_buffer(struct device *dev,
 int iio_backend_filter_type_set(struct iio_backend *back,
 				enum iio_backend_filter_type type);
 int iio_backend_interface_data_align(struct iio_backend *back, u32 timeout_us);
+int iio_backend_num_lanes_set(struct iio_backend *back, unsigned int num_lanes);
 int iio_backend_ddr_enable(struct iio_backend *back);
 int iio_backend_ddr_disable(struct iio_backend *back);
 int iio_backend_data_stream_enable(struct iio_backend *back);
-- 
cgit v1.2.3


From 342c52dde2f031add61ddeaced9c100f88e04d09 Mon Sep 17 00:00:00 2001
From: Angelo Dureghello <adureghello@baylibre.com>
Date: Fri, 6 Jun 2025 16:19:17 +0200
Subject: iio: core: add ADC delay calibration definition

ADCs as ad7606 implement a phase calibration as a delay. Add such
definition, needed for ad7606.

Signed-off-by: Angelo Dureghello <adureghello@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20250606-wip-bl-ad7606-calibration-v9-2-6e014a1f92a2@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/industrialio-core.c | 1 +
 include/linux/iio/types.h       | 1 +
 2 files changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
index 178e99b111de..f13c3aa470d7 100644
--- a/drivers/iio/industrialio-core.c
+++ b/drivers/iio/industrialio-core.c
@@ -188,6 +188,7 @@ static const char * const iio_chan_info_postfix[] = {
 	[IIO_CHAN_INFO_CALIBAMBIENT] = "calibambient",
 	[IIO_CHAN_INFO_ZEROPOINT] = "zeropoint",
 	[IIO_CHAN_INFO_TROUGH] = "trough_raw",
+	[IIO_CHAN_INFO_CONVDELAY] = "convdelay",
 };
 /**
  * iio_device_id() - query the unique ID for the device
diff --git a/include/linux/iio/types.h b/include/linux/iio/types.h
index d89982c98368..ad2761efcc83 100644
--- a/include/linux/iio/types.h
+++ b/include/linux/iio/types.h
@@ -69,6 +69,7 @@ enum iio_chan_info_enum {
 	IIO_CHAN_INFO_CALIBAMBIENT,
 	IIO_CHAN_INFO_ZEROPOINT,
 	IIO_CHAN_INFO_TROUGH,
+	IIO_CHAN_INFO_CONVDELAY,
 };
 
 #endif /* _IIO_TYPES_H_ */
-- 
cgit v1.2.3


From 4c46a471be12216347ba707f8eadadbf5d68e698 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 3 Jun 2025 16:38:53 +0530
Subject: firmware: arm_ffa: Fix the missing entry in struct
 ffa_indirect_msg_hdr

As per the spec, one 32 bit reserved entry is missing here, add it.

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Fixes: 910cc1acc9b4 ("firmware: arm_ffa: Add support for passing UUID in FFA_MSG_SEND2")
Reviewed-by: Bertrand Marquis <bertrand.marquis@arm.com>
Message-Id: <28a624fbf416975de4fbe08cfbf7c2db89cb630e.1748948911.git.viresh.kumar@linaro.org>
Signed-off-by: Sudeep Holla <sudeep.holla@arm.com>
---
 include/linux/arm_ffa.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/arm_ffa.h b/include/linux/arm_ffa.h
index 5bded24dc24f..e1634897e159 100644
--- a/include/linux/arm_ffa.h
+++ b/include/linux/arm_ffa.h
@@ -283,6 +283,7 @@ struct ffa_indirect_msg_hdr {
 	u32 offset;
 	u32 send_recv_id;
 	u32 size;
+	u32 res1;
 	uuid_t uuid;
 };
 
-- 
cgit v1.2.3


From de1c831a7898f164c1c2703c6b2b9e4fb4bebefc Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Tue, 15 Apr 2025 10:02:33 -0700
Subject: slab: Decouple slab_debug and no_hash_pointers

Some system owners use slab_debug=FPZ (or similar) as a hardening option,
but do not want to be forced into having kernel addresses exposed due
to the implicit "no_hash_pointers" boot param setting.[1]

Introduce the "hash_pointers" boot param, which defaults to "auto"
(the current behavior), but also includes "always" (forcing on hashing
even when "slab_debug=..." is defined), and "never". The existing
"no_hash_pointers" boot param becomes an alias for "hash_pointers=never".

This makes it possible to boot with "slab_debug=FPZ hash_pointers=always".

Link: https://github.com/KSPP/linux/issues/368 [1]
Fixes: 792702911f58 ("slub: force on no_hash_pointers when slub_debug is enabled")
Co-developed-by: Sergio Perez Gonzalez <sperezglz@gmail.com>
Signed-off-by: Sergio Perez Gonzalez <sperezglz@gmail.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Rientjes <rientjes@google.com>
Reviewed-by: Bagas Sanjaya <bagasdotme@gmail.com>
Signed-off-by: Kees Cook <kees@kernel.org>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Acked-by: Rafael Aquini <raquini@redhat.com>
Tested-by: Petr Mladek <pmladek@suse.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Link: https://patch.msgid.link/20250415170232.it.467-kees@kernel.org
[kees@kernel.org: Add note about hash_pointers into slab_debug kernel parameter documentation.]
Signed-off-by: Petr Mladek <pmladek@suse.com>
---
 Documentation/admin-guide/kernel-parameters.txt | 38 ++++++++++-----
 include/linux/sprintf.h                         |  2 +-
 lib/vsprintf.c                                  | 61 +++++++++++++++++++++++--
 mm/slub.c                                       |  5 +-
 4 files changed, 86 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 3f35d5b8c296..0dd5cd17e87e 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1798,6 +1798,27 @@
 			backtraces on all cpus.
 			Format: 0 | 1
 
+	hash_pointers=
+			[KNL,EARLY]
+			By default, when pointers are printed to the console
+			or buffers via the %p format string, that pointer is
+			"hashed", i.e. obscured by hashing the pointer value.
+			This is a security feature that hides actual kernel
+			addresses from unprivileged users, but it also makes
+			debugging the kernel more difficult since unequal
+			pointers can no longer be compared. The choices are:
+			Format: { auto | always | never }
+			Default: auto
+
+			auto   - Hash pointers unless slab_debug is enabled.
+			always - Always hash pointers (even if slab_debug is
+				 enabled).
+			never  - Never hash pointers. This option should only
+				 be specified when debugging the kernel. Do
+				 not use on production kernels. The boot
+				 param "no_hash_pointers" is an alias for
+				 this mode.
+
 	hashdist=	[KNL,NUMA] Large hashes allocated during boot
 			are distributed across NUMA nodes.  Defaults on
 			for 64-bit NUMA, off otherwise.
@@ -4120,18 +4141,7 @@
 
 	no_hash_pointers
 			[KNL,EARLY]
-			Force pointers printed to the console or buffers to be
-			unhashed.  By default, when a pointer is printed via %p
-			format string, that pointer is "hashed", i.e. obscured
-			by hashing the pointer value.  This is a security feature
-			that hides actual kernel addresses from unprivileged
-			users, but it also makes debugging the kernel more
-			difficult since unequal pointers can no longer be
-			compared.  However, if this command-line option is
-			specified, then all normal pointers will have their true
-			value printed. This option should only be specified when
-			debugging the kernel.  Please do not use on production
-			kernels.
+			Alias for "hash_pointers=never".
 
 	nohibernate	[HIBERNATION] Disable hibernation and resume.
 
@@ -6481,6 +6491,10 @@
 			Documentation/mm/slub.rst.
 			(slub_debug legacy name also accepted for now)
 
+			Using this option implies the "no_hash_pointers"
+			option which can be undone by adding the
+			"hash_pointers=always" option.
+
 	slab_max_order= [MM]
 			Determines the maximum allowed order for slabs.
 			A high setting may cause OOMs due to memory
diff --git a/include/linux/sprintf.h b/include/linux/sprintf.h
index 51cab2def9ec..521bb2cd2648 100644
--- a/include/linux/sprintf.h
+++ b/include/linux/sprintf.h
@@ -22,7 +22,7 @@ __scanf(2, 0) int vsscanf(const char *, const char *, va_list);
 
 /* These are for specific cases, do not use without real need */
 extern bool no_hash_pointers;
-int no_hash_pointers_enable(char *str);
+void hash_pointers_finalize(bool slub_debug);
 
 /* Used for Rust formatting ('%pA') */
 char *rust_fmt_argument(char *buf, char *end, const void *ptr);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 01699852f30c..22cbd75266ef 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -60,6 +60,20 @@
 bool no_hash_pointers __ro_after_init;
 EXPORT_SYMBOL_GPL(no_hash_pointers);
 
+/*
+ * Hashed pointers policy selected by "hash_pointers=..." boot param
+ *
+ * `auto`   - Hashed pointers enabled unless disabled by slub_debug_enabled=true
+ * `always` - Hashed pointers enabled unconditionally
+ * `never`  - Hashed pointers disabled unconditionally
+ */
+enum hash_pointers_policy {
+	HASH_PTR_AUTO = 0,
+	HASH_PTR_ALWAYS,
+	HASH_PTR_NEVER
+};
+static enum hash_pointers_policy hash_pointers_mode __initdata;
+
 noinline
 static unsigned long long simple_strntoull(const char *startp, char **endp, unsigned int base, size_t max_chars)
 {
@@ -2271,12 +2285,23 @@ char *resource_or_range(const char *fmt, char *buf, char *end, void *ptr,
 	return resource_string(buf, end, ptr, spec, fmt);
 }
 
-int __init no_hash_pointers_enable(char *str)
+void __init hash_pointers_finalize(bool slub_debug)
 {
-	if (no_hash_pointers)
-		return 0;
+	switch (hash_pointers_mode) {
+	case HASH_PTR_ALWAYS:
+		no_hash_pointers = false;
+		break;
+	case HASH_PTR_NEVER:
+		no_hash_pointers = true;
+		break;
+	case HASH_PTR_AUTO:
+	default:
+		no_hash_pointers = slub_debug;
+		break;
+	}
 
-	no_hash_pointers = true;
+	if (!no_hash_pointers)
+		return;
 
 	pr_warn("**********************************************************\n");
 	pr_warn("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
@@ -2289,11 +2314,39 @@ int __init no_hash_pointers_enable(char *str)
 	pr_warn("** the kernel, report this immediately to your system   **\n");
 	pr_warn("** administrator!                                       **\n");
 	pr_warn("**                                                      **\n");
+	pr_warn("** Use hash_pointers=always to force this mode off      **\n");
+	pr_warn("**                                                      **\n");
 	pr_warn("**   NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE NOTICE   **\n");
 	pr_warn("**********************************************************\n");
+}
+
+static int __init hash_pointers_mode_parse(char *str)
+{
+	if (!str) {
+		pr_warn("Hash pointers mode empty; falling back to auto.\n");
+		hash_pointers_mode = HASH_PTR_AUTO;
+	} else if (strncmp(str, "auto", 4) == 0)   {
+		pr_info("Hash pointers mode set to auto.\n");
+		hash_pointers_mode = HASH_PTR_AUTO;
+	} else if (strncmp(str, "never", 5) == 0) {
+		pr_info("Hash pointers mode set to never.\n");
+		hash_pointers_mode = HASH_PTR_NEVER;
+	} else if (strncmp(str, "always", 6) == 0) {
+		pr_info("Hash pointers mode set to always.\n");
+		hash_pointers_mode = HASH_PTR_ALWAYS;
+	} else {
+		pr_warn("Unknown hash_pointers mode '%s' specified; assuming auto.\n", str);
+		hash_pointers_mode = HASH_PTR_AUTO;
+	}
 
 	return 0;
 }
+early_param("hash_pointers", hash_pointers_mode_parse);
+
+static int __init no_hash_pointers_enable(char *str)
+{
+	return hash_pointers_mode_parse("never");
+}
 early_param("no_hash_pointers", no_hash_pointers_enable);
 
 /*
diff --git a/mm/slub.c b/mm/slub.c
index b46f87662e71..f3d61b330a76 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -6314,9 +6314,8 @@ void __init kmem_cache_init(void)
 	if (debug_guardpage_minorder())
 		slub_max_order = 0;
 
-	/* Print slub debugging pointers without hashing */
-	if (__slub_debug_enabled())
-		no_hash_pointers_enable(NULL);
+	/* Inform pointer hashing choice about slub debugging state. */
+	hash_pointers_finalize(__slub_debug_enabled());
 
 	kmem_cache_node = &boot_kmem_cache_node;
 	kmem_cache = &boot_kmem_cache;
-- 
cgit v1.2.3


From 78b2d9908b42ea70e42f00af5db08ad514727a45 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Mon, 5 May 2025 13:14:22 -0700
Subject: net: intel: rename 'hena' to 'hashcfg' for clarity

i40e, ice, and iAVF all use 'hena' as a shorthand for the "hash enable"
configuration. This comes originally from the X710 datasheet 'xxQF_HENA'
registers. In the context of the registers the meaning is fairly clear.

However, on its own, hena is a weird name that can be more difficult to
understand. This is especially true in ice. The E810 hardware doesn't even
have registers with HENA in the name.

Replace the shorthand 'hena' with 'hashcfg'. This makes it clear the
variables deal with the Hash configuration, not just a single boolean
on/off for all hashing.

Do not update the register names. These come directly from the datasheet
for X710 and X722, and it is more important that the names can be searched.

Suggested-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_main.c        |  2 +-
 drivers/net/ethernet/intel/i40e/i40e_txrx.h        |  8 ++--
 drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c | 46 +++++++++++-----------
 drivers/net/ethernet/intel/iavf/iavf.h             | 10 ++---
 drivers/net/ethernet/intel/iavf/iavf_main.c        | 17 ++++----
 drivers/net/ethernet/intel/iavf/iavf_txrx.h        |  4 +-
 drivers/net/ethernet/intel/iavf/iavf_virtchnl.c    | 33 ++++++++--------
 drivers/net/ethernet/intel/ice/ice_flow.h          |  4 +-
 drivers/net/ethernet/intel/ice/ice_lib.c           |  2 +-
 drivers/net/ethernet/intel/ice/ice_virtchnl.c      | 44 ++++++++++-----------
 drivers/net/ethernet/intel/ice/ice_virtchnl.h      |  4 +-
 .../ethernet/intel/ice/ice_virtchnl_allowlist.c    |  2 +-
 include/linux/avf/virtchnl.h                       | 22 +++++------
 13 files changed, 101 insertions(+), 97 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 120d68654e3f..516e07b58161 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -12507,7 +12507,7 @@ static int i40e_pf_config_rss(struct i40e_pf *pf)
 	/* By default we enable TCP/UDP with IPv4/IPv6 ptypes */
 	hena = (u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(0)) |
 		((u64)i40e_read_rx_ctl(hw, I40E_PFQF_HENA(1)) << 32);
-	hena |= i40e_pf_get_default_rss_hena(pf);
+	hena |= i40e_pf_get_default_rss_hashcfg(pf);
 
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(0), (u32)hena);
 	i40e_write_rx_ctl(hw, I40E_PFQF_HENA(1), (u32)(hena >> 32));
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index 7c26c9a2bf65..b007a84268a7 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -71,7 +71,7 @@ enum i40e_dyn_idx {
 #define I40E_SW_ITR    I40E_IDX_ITR2
 
 /* Supported RSS offloads */
-#define I40E_DEFAULT_RSS_HENA ( \
+#define I40E_DEFAULT_RSS_HASHCFG ( \
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | \
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP) | \
@@ -84,7 +84,7 @@ enum i40e_dyn_idx {
 	BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6) | \
 	BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD))
 
-#define I40E_DEFAULT_RSS_HENA_EXPANDED (I40E_DEFAULT_RSS_HENA | \
+#define I40E_DEFAULT_RSS_HASHCFG_EXPANDED (I40E_DEFAULT_RSS_HASHCFG | \
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
@@ -92,9 +92,9 @@ enum i40e_dyn_idx {
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
 	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
-#define i40e_pf_get_default_rss_hena(pf) \
+#define i40e_pf_get_default_rss_hashcfg(pf) \
 	(test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE, (pf)->hw.caps) ? \
-	 I40E_DEFAULT_RSS_HENA_EXPANDED : I40E_DEFAULT_RSS_HENA)
+	 I40E_DEFAULT_RSS_HASHCFG_EXPANDED : I40E_DEFAULT_RSS_HASHCFG)
 
 /* Supported Rx Buffer Sizes (a multiple of 128) */
 #define I40E_RXBUFFER_256   256
diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
index 1120f8e4bb67..2d9b7e51bbe1 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c
@@ -812,7 +812,7 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx)
 	}
 
 	if (!idx) {
-		u64 hena = i40e_pf_get_default_rss_hena(pf);
+		u64 hashcfg = i40e_pf_get_default_rss_hashcfg(pf);
 		u8 broadcast[ETH_ALEN];
 
 		vf->lan_vsi_idx = vsi->idx;
@@ -841,8 +841,9 @@ static int i40e_alloc_vsi_res(struct i40e_vf *vf, u8 idx)
 			dev_info(&pf->pdev->dev,
 				 "Could not allocate VF broadcast filter\n");
 		spin_unlock_bh(&vsi->mac_filter_hash_lock);
-		wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hena);
-		wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id), (u32)(hena >> 32));
+		wr32(&pf->hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)hashcfg);
+		wr32(&pf->hw, I40E_VFQF_HENA1(1, vf->vf_id),
+		     (u32)(hashcfg >> 32));
 		/* program mac filter only for VF VSI */
 		ret = i40e_sync_vsi_filters(vsi);
 		if (ret)
@@ -3447,15 +3448,15 @@ err:
 }
 
 /**
- * i40e_vc_get_rss_hena
+ * i40e_vc_get_rss_hashcfg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
  *
- * Return the RSS HENA bits allowed by the hardware
+ * Return the RSS Hash configuration bits allowed by the hardware
  **/
-static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
+static int i40e_vc_get_rss_hashcfg(struct i40e_vf *vf, u8 *msg)
 {
-	struct virtchnl_rss_hena *vrh = NULL;
+	struct virtchnl_rss_hashcfg *vrh = NULL;
 	struct i40e_pf *pf = vf->pf;
 	int aq_ret = 0;
 	int len = 0;
@@ -3464,7 +3465,7 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
 		aq_ret = -EINVAL;
 		goto err;
 	}
-	len = sizeof(struct virtchnl_rss_hena);
+	len = sizeof(struct virtchnl_rss_hashcfg);
 
 	vrh = kzalloc(len, GFP_KERNEL);
 	if (!vrh) {
@@ -3472,26 +3473,26 @@ static int i40e_vc_get_rss_hena(struct i40e_vf *vf, u8 *msg)
 		len = 0;
 		goto err;
 	}
-	vrh->hena = i40e_pf_get_default_rss_hena(pf);
+	vrh->hashcfg = i40e_pf_get_default_rss_hashcfg(pf);
 err:
 	/* send the response back to the VF */
-	aq_ret = i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HENA_CAPS,
+	aq_ret = i40e_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS,
 					aq_ret, (u8 *)vrh, len);
 	kfree(vrh);
 	return aq_ret;
 }
 
 /**
- * i40e_vc_set_rss_hena
+ * i40e_vc_set_rss_hashcfg
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
  *
- * Set the RSS HENA bits for the VF
+ * Set the RSS Hash configuration bits for the VF
  **/
-static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg)
+static int i40e_vc_set_rss_hashcfg(struct i40e_vf *vf, u8 *msg)
 {
-	struct virtchnl_rss_hena *vrh =
-		(struct virtchnl_rss_hena *)msg;
+	struct virtchnl_rss_hashcfg *vrh =
+		(struct virtchnl_rss_hashcfg *)msg;
 	struct i40e_pf *pf = vf->pf;
 	struct i40e_hw *hw = &pf->hw;
 	int aq_ret = 0;
@@ -3500,13 +3501,14 @@ static int i40e_vc_set_rss_hena(struct i40e_vf *vf, u8 *msg)
 		aq_ret = -EINVAL;
 		goto err;
 	}
-	i40e_write_rx_ctl(hw, I40E_VFQF_HENA1(0, vf->vf_id), (u32)vrh->hena);
+	i40e_write_rx_ctl(hw, I40E_VFQF_HENA1(0, vf->vf_id),
+			  (u32)vrh->hashcfg);
 	i40e_write_rx_ctl(hw, I40E_VFQF_HENA1(1, vf->vf_id),
-			  (u32)(vrh->hena >> 32));
+			  (u32)(vrh->hashcfg >> 32));
 
 	/* send the response to the VF */
 err:
-	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_SET_RSS_HENA, aq_ret);
+	return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_SET_RSS_HASHCFG, aq_ret);
 }
 
 /**
@@ -4253,11 +4255,11 @@ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode,
 	case VIRTCHNL_OP_CONFIG_RSS_LUT:
 		ret = i40e_vc_config_rss_lut(vf, msg);
 		break;
-	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
-		ret = i40e_vc_get_rss_hena(vf, msg);
+	case VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS:
+		ret = i40e_vc_get_rss_hashcfg(vf, msg);
 		break;
-	case VIRTCHNL_OP_SET_RSS_HENA:
-		ret = i40e_vc_set_rss_hena(vf, msg);
+	case VIRTCHNL_OP_SET_RSS_HASHCFG:
+		ret = i40e_vc_set_rss_hashcfg(vf, msg);
 		break;
 	case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
 		ret = i40e_vc_enable_vlan_stripping(vf, msg);
diff --git a/drivers/net/ethernet/intel/iavf/iavf.h b/drivers/net/ethernet/intel/iavf/iavf.h
index f7a98ff43a57..eb86cca38be2 100644
--- a/drivers/net/ethernet/intel/iavf/iavf.h
+++ b/drivers/net/ethernet/intel/iavf/iavf.h
@@ -315,8 +315,8 @@ struct iavf_adapter {
 #define IAVF_FLAG_AQ_CONFIGURE_RSS		BIT_ULL(9) /* direct AQ config */
 #define IAVF_FLAG_AQ_GET_CONFIG			BIT_ULL(10)
 /* Newer style, RSS done by the PF so we can ignore hardware vagaries. */
-#define IAVF_FLAG_AQ_GET_HENA			BIT_ULL(11)
-#define IAVF_FLAG_AQ_SET_HENA			BIT_ULL(12)
+#define IAVF_FLAG_AQ_GET_RSS_HASHCFG		BIT_ULL(11)
+#define IAVF_FLAG_AQ_SET_RSS_HASHCFG		BIT_ULL(12)
 #define IAVF_FLAG_AQ_SET_RSS_KEY		BIT_ULL(13)
 #define IAVF_FLAG_AQ_SET_RSS_LUT		BIT_ULL(14)
 #define IAVF_FLAG_AQ_SET_RSS_HFUNC		BIT_ULL(15)
@@ -456,7 +456,7 @@ struct iavf_adapter {
 	u32 aq_wait_count;
 	/* RSS stuff */
 	enum virtchnl_rss_algorithm hfunc;
-	u64 hena;
+	u64 rss_hashcfg;
 	u16 rss_key_size;
 	u16 rss_lut_size;
 	u8 *rss_key;
@@ -600,8 +600,8 @@ void iavf_set_promiscuous(struct iavf_adapter *adapter);
 bool iavf_promiscuous_mode_changed(struct iavf_adapter *adapter);
 void iavf_request_stats(struct iavf_adapter *adapter);
 int iavf_request_reset(struct iavf_adapter *adapter);
-void iavf_get_hena(struct iavf_adapter *adapter);
-void iavf_set_hena(struct iavf_adapter *adapter);
+void iavf_get_rss_hashcfg(struct iavf_adapter *adapter);
+void iavf_set_rss_hashcfg(struct iavf_adapter *adapter);
 void iavf_set_rss_key(struct iavf_adapter *adapter);
 void iavf_set_rss_lut(struct iavf_adapter *adapter);
 void iavf_set_rss_hfunc(struct iavf_adapter *adapter);
diff --git a/drivers/net/ethernet/intel/iavf/iavf_main.c b/drivers/net/ethernet/intel/iavf/iavf_main.c
index 2c0bb41809a4..01e11ac5055b 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_main.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_main.c
@@ -1823,12 +1823,13 @@ static int iavf_init_rss(struct iavf_adapter *adapter)
 		/* Enable PCTYPES for RSS, TCP/UDP with IPv4/IPv6 */
 		if (adapter->vf_res->vf_cap_flags &
 		    VIRTCHNL_VF_OFFLOAD_RSS_PCTYPE_V2)
-			adapter->hena = IAVF_DEFAULT_RSS_HENA_EXPANDED;
+			adapter->rss_hashcfg =
+				IAVF_DEFAULT_RSS_HASHCFG_EXPANDED;
 		else
-			adapter->hena = IAVF_DEFAULT_RSS_HENA;
+			adapter->rss_hashcfg = IAVF_DEFAULT_RSS_HASHCFG;
 
-		wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->hena);
-		wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->hena >> 32));
+		wr32(hw, IAVF_VFQF_HENA(0), (u32)adapter->rss_hashcfg);
+		wr32(hw, IAVF_VFQF_HENA(1), (u32)(adapter->rss_hashcfg >> 32));
 	}
 
 	iavf_fill_rss_lut(adapter);
@@ -2195,12 +2196,12 @@ static int iavf_process_aq_command(struct iavf_adapter *adapter)
 		adapter->aq_required &= ~IAVF_FLAG_AQ_CONFIGURE_RSS;
 		return 0;
 	}
-	if (adapter->aq_required & IAVF_FLAG_AQ_GET_HENA) {
-		iavf_get_hena(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_GET_RSS_HASHCFG) {
+		iavf_get_rss_hashcfg(adapter);
 		return 0;
 	}
-	if (adapter->aq_required & IAVF_FLAG_AQ_SET_HENA) {
-		iavf_set_hena(adapter);
+	if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_HASHCFG) {
+		iavf_set_rss_hashcfg(adapter);
 		return 0;
 	}
 	if (adapter->aq_required & IAVF_FLAG_AQ_SET_RSS_KEY) {
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index 79ad554f2d53..94b324f212bd 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -59,7 +59,7 @@ enum iavf_dyn_idx_t {
 #define IAVF_PE_ITR    IAVF_IDX_ITR2
 
 /* Supported RSS offloads */
-#define IAVF_DEFAULT_RSS_HENA ( \
+#define IAVF_DEFAULT_RSS_HASHCFG ( \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_UDP) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP) | \
@@ -72,7 +72,7 @@ enum iavf_dyn_idx_t {
 	BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV6) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_L2_PAYLOAD))
 
-#define IAVF_DEFAULT_RSS_HENA_EXPANDED (IAVF_DEFAULT_RSS_HENA | \
+#define IAVF_DEFAULT_RSS_HASHCFG_EXPANDED (IAVF_DEFAULT_RSS_HASHCFG | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
 	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
diff --git a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
index a6f0e5990be2..1815cf3e28f4 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
+++ b/drivers/net/ethernet/intel/iavf/iavf_virtchnl.c
@@ -1128,12 +1128,12 @@ void iavf_request_stats(struct iavf_adapter *adapter)
 }
 
 /**
- * iavf_get_hena
+ * iavf_get_rss_hashcfg
  * @adapter: adapter structure
  *
- * Request hash enable capabilities from PF
+ * Request RSS Hash enable bits from PF
  **/
-void iavf_get_hena(struct iavf_adapter *adapter)
+void iavf_get_rss_hashcfg(struct iavf_adapter *adapter)
 {
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -1141,20 +1141,20 @@ void iavf_get_hena(struct iavf_adapter *adapter)
 			adapter->current_op);
 		return;
 	}
-	adapter->current_op = VIRTCHNL_OP_GET_RSS_HENA_CAPS;
-	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_HENA;
-	iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HENA_CAPS, NULL, 0);
+	adapter->current_op = VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_GET_RSS_HASHCFG;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS, NULL, 0);
 }
 
 /**
- * iavf_set_hena
+ * iavf_set_rss_hashcfg
  * @adapter: adapter structure
  *
  * Request the PF to set our RSS hash capabilities
  **/
-void iavf_set_hena(struct iavf_adapter *adapter)
+void iavf_set_rss_hashcfg(struct iavf_adapter *adapter)
 {
-	struct virtchnl_rss_hena vrh;
+	struct virtchnl_rss_hashcfg vrh;
 
 	if (adapter->current_op != VIRTCHNL_OP_UNKNOWN) {
 		/* bail because we already have a command pending */
@@ -1162,10 +1162,10 @@ void iavf_set_hena(struct iavf_adapter *adapter)
 			adapter->current_op);
 		return;
 	}
-	vrh.hena = adapter->hena;
-	adapter->current_op = VIRTCHNL_OP_SET_RSS_HENA;
-	adapter->aq_required &= ~IAVF_FLAG_AQ_SET_HENA;
-	iavf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HENA, (u8 *)&vrh,
+	vrh.hashcfg = adapter->rss_hashcfg;
+	adapter->current_op = VIRTCHNL_OP_SET_RSS_HASHCFG;
+	adapter->aq_required &= ~IAVF_FLAG_AQ_SET_RSS_HASHCFG;
+	iavf_send_pf_msg(adapter, VIRTCHNL_OP_SET_RSS_HASHCFG, (u8 *)&vrh,
 			 sizeof(vrh));
 }
 
@@ -2735,11 +2735,12 @@ void iavf_virtchnl_completion(struct iavf_adapter *adapter,
 		if (v_opcode != adapter->current_op)
 			return;
 		break;
-	case VIRTCHNL_OP_GET_RSS_HENA_CAPS: {
-		struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg;
+	case VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS: {
+		struct virtchnl_rss_hashcfg *vrh =
+			(struct virtchnl_rss_hashcfg *)msg;
 
 		if (msglen == sizeof(*vrh))
-			adapter->hena = vrh->hena;
+			adapter->rss_hashcfg = vrh->hashcfg;
 		else
 			dev_warn(&adapter->pdev->dev,
 				 "Invalid message %d from PF\n", v_opcode);
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index 6cb7bb879c98..b1313fb61677 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -295,10 +295,10 @@ enum ice_flow_avf_hdr_field {
 };
 
 /* Supported RSS offloads  This macro is defined to support
- * VIRTCHNL_OP_GET_RSS_HENA_CAPS ops. PF driver sends the RSS hardware
+ * VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS ops. PF driver sends the RSS hardware
  * capabilities to the caller of this ops.
  */
-#define ICE_DEFAULT_RSS_HENA ( \
+#define ICE_DEFAULT_RSS_HASHCFG ( \
 	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_UDP) | \
 	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP) | \
 	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP) | \
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 03bb16191237..2cc050db509f 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -1579,7 +1579,7 @@ static void ice_vsi_set_vf_rss_flow_fld(struct ice_vsi *vsi)
 		return;
 	}
 
-	status = ice_add_avf_rss_cfg(&pf->hw, vsi, ICE_DEFAULT_RSS_HENA);
+	status = ice_add_avf_rss_cfg(&pf->hw, vsi, ICE_DEFAULT_RSS_HASHCFG);
 	if (status)
 		dev_dbg(dev, "ice_add_avf_rss_cfg failed for vsi = %d, error = %d\n",
 			vsi->vsi_num, status);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index eeeb9968e477..24426dcd8aa2 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -2999,13 +2999,13 @@ error_param:
 }
 
 /**
- * ice_vc_get_rss_hena - return the RSS HENA bits allowed by the hardware
+ * ice_vc_get_rss_hashcfg - return the RSS Hash configuration
  * @vf: pointer to the VF info
  */
-static int ice_vc_get_rss_hena(struct ice_vf *vf)
+static int ice_vc_get_rss_hashcfg(struct ice_vf *vf)
 {
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
-	struct virtchnl_rss_hena *vrh = NULL;
+	struct virtchnl_rss_hashcfg *vrh = NULL;
 	int len = 0, ret;
 
 	if (!test_bit(ICE_VF_STATE_ACTIVE, vf->vf_states)) {
@@ -3019,7 +3019,7 @@ static int ice_vc_get_rss_hena(struct ice_vf *vf)
 		goto err;
 	}
 
-	len = sizeof(struct virtchnl_rss_hena);
+	len = sizeof(struct virtchnl_rss_hashcfg);
 	vrh = kzalloc(len, GFP_KERNEL);
 	if (!vrh) {
 		v_ret = VIRTCHNL_STATUS_ERR_NO_MEMORY;
@@ -3027,23 +3027,23 @@ static int ice_vc_get_rss_hena(struct ice_vf *vf)
 		goto err;
 	}
 
-	vrh->hena = ICE_DEFAULT_RSS_HENA;
+	vrh->hashcfg = ICE_DEFAULT_RSS_HASHCFG;
 err:
 	/* send the response back to the VF */
-	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HENA_CAPS, v_ret,
+	ret = ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS, v_ret,
 				    (u8 *)vrh, len);
 	kfree(vrh);
 	return ret;
 }
 
 /**
- * ice_vc_set_rss_hena - set RSS HENA bits for the VF
+ * ice_vc_set_rss_hashcfg - set RSS Hash configuration bits for the VF
  * @vf: pointer to the VF info
  * @msg: pointer to the msg buffer
  */
-static int ice_vc_set_rss_hena(struct ice_vf *vf, u8 *msg)
+static int ice_vc_set_rss_hashcfg(struct ice_vf *vf, u8 *msg)
 {
-	struct virtchnl_rss_hena *vrh = (struct virtchnl_rss_hena *)msg;
+	struct virtchnl_rss_hashcfg *vrh = (struct virtchnl_rss_hashcfg *)msg;
 	enum virtchnl_status_code v_ret = VIRTCHNL_STATUS_SUCCESS;
 	struct ice_pf *pf = vf->pf;
 	struct ice_vsi *vsi;
@@ -3074,9 +3074,9 @@ static int ice_vc_set_rss_hena(struct ice_vf *vf, u8 *msg)
 	 * disable RSS
 	 */
 	status = ice_rem_vsi_rss_cfg(&pf->hw, vsi->idx);
-	if (status && !vrh->hena) {
+	if (status && !vrh->hashcfg) {
 		/* only report failure to clear the current RSS configuration if
-		 * that was clearly the VF's intention (i.e. vrh->hena = 0)
+		 * that was clearly the VF's intention (i.e. vrh->hashcfg = 0)
 		 */
 		v_ret = ice_err_to_virt_err(status);
 		goto err;
@@ -3089,14 +3089,14 @@ static int ice_vc_set_rss_hena(struct ice_vf *vf, u8 *msg)
 			 vf->vf_id);
 	}
 
-	if (vrh->hena) {
-		status = ice_add_avf_rss_cfg(&pf->hw, vsi, vrh->hena);
+	if (vrh->hashcfg) {
+		status = ice_add_avf_rss_cfg(&pf->hw, vsi, vrh->hashcfg);
 		v_ret = ice_err_to_virt_err(status);
 	}
 
 	/* send the response to the VF */
 err:
-	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_SET_RSS_HENA, v_ret,
+	return ice_vc_send_msg_to_vf(vf, VIRTCHNL_OP_SET_RSS_HASHCFG, v_ret,
 				     NULL, 0);
 }
 
@@ -4243,8 +4243,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_dflt_ops = {
 	.add_vlan_msg = ice_vc_add_vlan_msg,
 	.remove_vlan_msg = ice_vc_remove_vlan_msg,
 	.query_rxdid = ice_vc_query_rxdid,
-	.get_rss_hena = ice_vc_get_rss_hena,
-	.set_rss_hena_msg = ice_vc_set_rss_hena,
+	.get_rss_hashcfg = ice_vc_get_rss_hashcfg,
+	.set_rss_hashcfg = ice_vc_set_rss_hashcfg,
 	.ena_vlan_stripping = ice_vc_ena_vlan_stripping,
 	.dis_vlan_stripping = ice_vc_dis_vlan_stripping,
 	.handle_rss_cfg_msg = ice_vc_handle_rss_cfg,
@@ -4380,8 +4380,8 @@ static const struct ice_virtchnl_ops ice_virtchnl_repr_ops = {
 	.add_vlan_msg = ice_vc_add_vlan_msg,
 	.remove_vlan_msg = ice_vc_remove_vlan_msg,
 	.query_rxdid = ice_vc_query_rxdid,
-	.get_rss_hena = ice_vc_get_rss_hena,
-	.set_rss_hena_msg = ice_vc_set_rss_hena,
+	.get_rss_hashcfg = ice_vc_get_rss_hashcfg,
+	.set_rss_hashcfg = ice_vc_set_rss_hashcfg,
 	.ena_vlan_stripping = ice_vc_ena_vlan_stripping,
 	.dis_vlan_stripping = ice_vc_dis_vlan_stripping,
 	.handle_rss_cfg_msg = ice_vc_handle_rss_cfg,
@@ -4582,11 +4582,11 @@ error_handler:
 	case VIRTCHNL_OP_GET_SUPPORTED_RXDIDS:
 		err = ops->query_rxdid(vf);
 		break;
-	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
-		err = ops->get_rss_hena(vf);
+	case VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS:
+		err = ops->get_rss_hashcfg(vf);
 		break;
-	case VIRTCHNL_OP_SET_RSS_HENA:
-		err = ops->set_rss_hena_msg(vf, msg);
+	case VIRTCHNL_OP_SET_RSS_HASHCFG:
+		err = ops->set_rss_hashcfg(vf, msg);
 		break;
 	case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
 		err = ops->ena_vlan_stripping(vf);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.h b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
index 222990f229d5..b3eece8c6780 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.h
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.h
@@ -57,8 +57,8 @@ struct ice_virtchnl_ops {
 	int (*add_vlan_msg)(struct ice_vf *vf, u8 *msg);
 	int (*remove_vlan_msg)(struct ice_vf *vf, u8 *msg);
 	int (*query_rxdid)(struct ice_vf *vf);
-	int (*get_rss_hena)(struct ice_vf *vf);
-	int (*set_rss_hena_msg)(struct ice_vf *vf, u8 *msg);
+	int (*get_rss_hashcfg)(struct ice_vf *vf);
+	int (*set_rss_hashcfg)(struct ice_vf *vf, u8 *msg);
 	int (*ena_vlan_stripping)(struct ice_vf *vf);
 	int (*dis_vlan_stripping)(struct ice_vf *vf);
 	int (*handle_rss_cfg_msg)(struct ice_vf *vf, u8 *msg, bool add);
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
index a3d1579a619a..4c2ec2337b38 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_allowlist.c
@@ -65,7 +65,7 @@ static const u32 vlan_v2_allowlist_opcodes[] = {
 /* VIRTCHNL_VF_OFFLOAD_RSS_PF */
 static const u32 rss_pf_allowlist_opcodes[] = {
 	VIRTCHNL_OP_CONFIG_RSS_KEY, VIRTCHNL_OP_CONFIG_RSS_LUT,
-	VIRTCHNL_OP_GET_RSS_HENA_CAPS, VIRTCHNL_OP_SET_RSS_HENA,
+	VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS, VIRTCHNL_OP_SET_RSS_HASHCFG,
 	VIRTCHNL_OP_CONFIG_RSS_HFUNC,
 };
 
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index cf0afa60e4a7..362d1cdc8cd8 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -132,8 +132,8 @@ enum virtchnl_ops {
 	VIRTCHNL_OP_RELEASE_RDMA_IRQ_MAP = VIRTCHNL_OP_RELEASE_IWARP_IRQ_MAP,
 	VIRTCHNL_OP_CONFIG_RSS_KEY = 23,
 	VIRTCHNL_OP_CONFIG_RSS_LUT = 24,
-	VIRTCHNL_OP_GET_RSS_HENA_CAPS = 25,
-	VIRTCHNL_OP_SET_RSS_HENA = 26,
+	VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS = 25,
+	VIRTCHNL_OP_SET_RSS_HASHCFG = 26,
 	VIRTCHNL_OP_ENABLE_VLAN_STRIPPING = 27,
 	VIRTCHNL_OP_DISABLE_VLAN_STRIPPING = 28,
 	VIRTCHNL_OP_REQUEST_QUEUES = 29,
@@ -974,18 +974,18 @@ struct virtchnl_rss_lut {
 VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_lut);
 #define virtchnl_rss_lut_LEGACY_SIZEOF	6
 
-/* VIRTCHNL_OP_GET_RSS_HENA_CAPS
- * VIRTCHNL_OP_SET_RSS_HENA
- * VF sends these messages to get and set the hash filter enable bits for RSS.
+/* VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS
+ * VIRTCHNL_OP_SET_RSS_HASHCFG
+ * VF sends these messages to get and set the hash filter configuration for RSS.
  * By default, the PF sets these to all possible traffic types that the
  * hardware supports. The VF can query this value if it wants to change the
  * traffic types that are hashed by the hardware.
  */
-struct virtchnl_rss_hena {
-	u64 hena;
+struct virtchnl_rss_hashcfg {
+	u64 hashcfg;
 };
 
-VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hena);
+VIRTCHNL_CHECK_STRUCT_LEN(8, virtchnl_rss_hashcfg);
 
 /* Type of RSS algorithm */
 enum virtchnl_rss_algorithm {
@@ -1779,10 +1779,10 @@ virtchnl_vc_validate_vf_msg(struct virtchnl_version_info *ver, u32 v_opcode,
 	case VIRTCHNL_OP_CONFIG_RSS_HFUNC:
 		valid_len = sizeof(struct virtchnl_rss_hfunc);
 		break;
-	case VIRTCHNL_OP_GET_RSS_HENA_CAPS:
+	case VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS:
 		break;
-	case VIRTCHNL_OP_SET_RSS_HENA:
-		valid_len = sizeof(struct virtchnl_rss_hena);
+	case VIRTCHNL_OP_SET_RSS_HASHCFG:
+		valid_len = sizeof(struct virtchnl_rss_hashcfg);
 		break;
 	case VIRTCHNL_OP_ENABLE_VLAN_STRIPPING:
 	case VIRTCHNL_OP_DISABLE_VLAN_STRIPPING:
-- 
cgit v1.2.3


From 141d0c9037ca57dac2d2c4e5d3c21521aa70ff12 Mon Sep 17 00:00:00 2001
From: Jacob Keller <jacob.e.keller@intel.com>
Date: Mon, 5 May 2025 13:14:23 -0700
Subject: net: intel: move RSS packet classifier types to libie

The Intel i40e, iavf, and ice drivers all include a definition of the
packet classifier filter types used to program RSS hash enable bits. For
i40e, these bits are used for both the PF and VF to configure the PFQF_HENA
and VFQF_HENA registers.

For ice and iAVF, these bits are used to communicate the desired hash
enable filter over virtchnl via its struct virtchnl_rss_hashena. The
virtchnl.h header makes no mention of where the bit definitions reside.

Maintaining a separate copy of these bits across three drivers is
cumbersome. Move the definition to libie as a new pctype.h header file.
Each driver can include this, and drop its own definition.

The ice implementation also defined a ICE_AVF_FLOW_FIELD_INVALID, intending
to use this to indicate when there were no hash enable bits set. This is
confusing, since the enumeration is using bit positions. A value of 0
*should* indicate the first bit. Instead, rewrite the code that uses
ICE_AVF_FLOW_FIELD_INVALID to just check if the avf_hash is zero. From
context this should be clear that we're checking if none of the bits are
set.

The values are kept as bit positions instead of encoding the BIT_ULL
directly into their value. While most users will simply use BIT_ULL
immediately, i40e uses the macros both with BIT_ULL and test_bit/set_bit
calls.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Jacob Keller <jacob.e.keller@intel.com>
Tested-by: Rafal Romanowski <rafal.romanowski@intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c | 81 +++++++++++++-------------
 drivers/net/ethernet/intel/i40e/i40e_main.c    | 23 ++++----
 drivers/net/ethernet/intel/i40e/i40e_txrx.c    | 25 ++++----
 drivers/net/ethernet/intel/i40e/i40e_txrx.h    | 35 +++++------
 drivers/net/ethernet/intel/i40e/i40e_type.h    | 32 ----------
 drivers/net/ethernet/intel/iavf/iavf_txrx.h    | 36 ++++++------
 drivers/net/ethernet/intel/iavf/iavf_type.h    | 32 ----------
 drivers/net/ethernet/intel/ice/ice_flow.c      | 45 +++++++-------
 drivers/net/ethernet/intel/ice/ice_flow.h      | 64 ++++++--------------
 include/linux/avf/virtchnl.h                   |  1 +
 include/linux/net/intel/libie/pctype.h         | 41 +++++++++++++
 11 files changed, 185 insertions(+), 230 deletions(-)
 create mode 100644 include/linux/net/intel/libie/pctype.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 8a7a83f83ee5..814e20325feb 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -3,6 +3,7 @@
 
 /* ethtool support for i40e */
 
+#include <linux/net/intel/libie/pctype.h>
 #include "i40e_devids.h"
 #include "i40e_diag.h"
 #include "i40e_txrx_common.h"
@@ -3146,16 +3147,16 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd)
 
 	switch (cmd->flow_type) {
 	case TCP_V4_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		flow_pctype = LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP;
 		break;
 	case UDP_V4_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		flow_pctype = LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP;
 		break;
 	case TCP_V6_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_TCP;
+		flow_pctype = LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP;
 		break;
 	case UDP_V6_FLOW:
-		flow_pctype = I40E_FILTER_PCTYPE_NONF_IPV6_UDP;
+		flow_pctype = LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP;
 		break;
 	case SCTP_V4_FLOW:
 	case AH_ESP_V4_FLOW:
@@ -3412,28 +3413,28 @@ static int i40e_get_ethtool_fdir_entry(struct i40e_pf *pf,
 
 	switch (rule->flow_type) {
 	case SCTP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP;
 		break;
 	case TCP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP;
 		break;
 	case UDP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP;
 		break;
 	case SCTP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_SCTP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP;
 		break;
 	case TCP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_TCP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP;
 		break;
 	case UDP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_UDP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP;
 		break;
 	case IP_USER_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER;
 		break;
 	case IPV6_USER_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_OTHER;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER;
 		break;
 	default:
 		/* If we have stored a filter with a flow type not listed here
@@ -3643,40 +3644,40 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 
 	switch (nfc->flow_type) {
 	case TCP_V4_FLOW:
-		set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes);
+		set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP, flow_pctypes);
 		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
 			     pf->hw.caps))
-			set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK,
 				flow_pctypes);
 		break;
 	case TCP_V6_FLOW:
-		set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes);
+		set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP, flow_pctypes);
 		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
 			     pf->hw.caps))
-			set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK,
 				flow_pctypes);
 		break;
 	case UDP_V4_FLOW:
-		set_bit(I40E_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes);
+		set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP, flow_pctypes);
 		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
 			     pf->hw.caps)) {
-			set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP,
 				flow_pctypes);
-			set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP,
 				flow_pctypes);
 		}
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4);
 		break;
 	case UDP_V6_FLOW:
-		set_bit(I40E_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes);
+		set_bit(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP, flow_pctypes);
 		if (test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE,
 			     pf->hw.caps)) {
-			set_bit(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP,
 				flow_pctypes);
-			set_bit(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP,
+			set_bit(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP,
 				flow_pctypes);
 		}
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6);
 		break;
 	case AH_ESP_V4_FLOW:
 	case AH_V4_FLOW:
@@ -3685,7 +3686,7 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 		if ((nfc->data & RXH_L4_B_0_1) ||
 		    (nfc->data & RXH_L4_B_2_3))
 			return -EINVAL;
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER);
 		break;
 	case AH_ESP_V6_FLOW:
 	case AH_V6_FLOW:
@@ -3694,15 +3695,15 @@ static int i40e_set_rss_hash_opt(struct i40e_pf *pf, struct ethtool_rxnfc *nfc)
 		if ((nfc->data & RXH_L4_B_0_1) ||
 		    (nfc->data & RXH_L4_B_2_3))
 			return -EINVAL;
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER);
 		break;
 	case IPV4_FLOW:
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) |
-			BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) |
+			BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4);
 		break;
 	case IPV6_FLOW:
-		hena |= BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) |
-			BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6);
+		hena |= BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) |
+			BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6);
 		break;
 	default:
 		return -EINVAL;
@@ -4312,36 +4313,36 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
 
 	switch (fsp->flow_type & ~FLOW_EXT) {
 	case SCTP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_SCTP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP;
 		fdir_filter_count = &pf->fd_sctp4_filter_cnt;
 		break;
 	case TCP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_TCP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP;
 		fdir_filter_count = &pf->fd_tcp4_filter_cnt;
 		break;
 	case UDP_V4_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_UDP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP;
 		fdir_filter_count = &pf->fd_udp4_filter_cnt;
 		break;
 	case SCTP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_SCTP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP;
 		fdir_filter_count = &pf->fd_sctp6_filter_cnt;
 		break;
 	case TCP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_TCP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP;
 		fdir_filter_count = &pf->fd_tcp6_filter_cnt;
 		break;
 	case UDP_V6_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_UDP;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP;
 		fdir_filter_count = &pf->fd_udp6_filter_cnt;
 		break;
 	case IP_USER_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER;
 		fdir_filter_count = &pf->fd_ip4_filter_cnt;
 		flex_l3 = true;
 		break;
 	case IPV6_USER_FLOW:
-		index = I40E_FILTER_PCTYPE_NONF_IPV6_OTHER;
+		index = LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER;
 		fdir_filter_count = &pf->fd_ip6_filter_cnt;
 		flex_l3 = true;
 		break;
@@ -4677,8 +4678,8 @@ static int i40e_check_fdir_input_set(struct i40e_vsi *vsi,
 	 * separate support, we'll always assume and enforce that the two flow
 	 * types must have matching input sets.
 	 */
-	if (index == I40E_FILTER_PCTYPE_NONF_IPV4_OTHER)
-		i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4,
+	if (index == LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER)
+		i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_FRAG_IPV4,
 					new_mask);
 
 	/* Add the new offset and update table, if necessary */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 516e07b58161..67faf5a8dcbf 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -3,6 +3,7 @@
 
 #include <generated/utsrelease.h>
 #include <linux/crash_dump.h>
+#include <linux/net/intel/libie/pctype.h>
 #include <linux/if_bridge.h>
 #include <linux/if_macvlan.h>
 #include <linux/module.h>
@@ -9188,47 +9189,47 @@ static void i40e_fdir_filter_exit(struct i40e_pf *pf)
 	i40e_reset_fdir_filter_cnt(pf);
 
 	/* Reprogram the default input set for TCP/IPv4 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for TCP/IPv6 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_TCP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP,
 				I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for UDP/IPv4 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_UDP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for UDP/IPv6 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_UDP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP,
 				I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for SCTP/IPv4 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_SCTP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for SCTP/IPv6 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_SCTP,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP,
 				I40E_L3_V6_SRC_MASK | I40E_L3_V6_DST_MASK |
 				I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
 	/* Reprogram the default input set for Other/IPv4 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_OTHER,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV4,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_FRAG_IPV4,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 
 	/* Reprogram the default input set for Other/IPv6 */
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV6_OTHER,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 
-	i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_FRAG_IPV6,
+	i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_FRAG_IPV6,
 				I40E_L3_SRC_MASK | I40E_L3_DST_MASK);
 }
 
@@ -9656,7 +9657,7 @@ static void i40e_reenable_fdir_atr(struct i40e_pf *pf)
 		 * settings. It is safe to restore the default input set
 		 * because there are no active TCPv4 filter rules.
 		 */
-		i40e_write_fd_input_set(pf, I40E_FILTER_PCTYPE_NONF_IPV4_TCP,
+		i40e_write_fd_input_set(pf, LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP,
 					I40E_L3_SRC_MASK | I40E_L3_DST_MASK |
 					I40E_L4_SRC_MASK | I40E_L4_DST_MASK);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
index c006f716a3bd..048c33039130 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c
@@ -2,6 +2,7 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/bpf_trace.h>
+#include <linux/net/intel/libie/pctype.h>
 #include <linux/net/intel/libie/rx.h>
 #include <linux/prefetch.h>
 #include <linux/sctp.h>
@@ -397,12 +398,12 @@ static int i40e_add_del_fdir_udp(struct i40e_vsi *vsi,
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_UDPIP_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV4_UDP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP);
 	else
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_UDPIP6_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV6_UDP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP);
 
 	if (ret) {
 		kfree(raw_packet);
@@ -444,12 +445,12 @@ static int i40e_add_del_fdir_tcp(struct i40e_vsi *vsi,
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_TCPIP_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV4_TCP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP);
 	else
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_TCPIP6_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV6_TCP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP);
 
 	if (ret) {
 		kfree(raw_packet);
@@ -499,12 +500,12 @@ static int i40e_add_del_fdir_sctp(struct i40e_vsi *vsi,
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_SCTPIP_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV4_SCTP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP);
 	else
 		ret = i40e_prepare_fdir_filter
 			(pf, fd_data, add, raw_packet,
 			 I40E_SCTPIP6_DUMMY_PACKET_LEN,
-			 I40E_FILTER_PCTYPE_NONF_IPV6_SCTP);
+			 LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP);
 
 	if (ret) {
 		kfree(raw_packet);
@@ -543,11 +544,11 @@ static int i40e_add_del_fdir_ip(struct i40e_vsi *vsi,
 	int i;
 
 	if (ipv4) {
-		iter_start = I40E_FILTER_PCTYPE_NONF_IPV4_OTHER;
-		iter_end = I40E_FILTER_PCTYPE_FRAG_IPV4;
+		iter_start = LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER;
+		iter_end = LIBIE_FILTER_PCTYPE_FRAG_IPV4;
 	} else {
-		iter_start = I40E_FILTER_PCTYPE_NONF_IPV6_OTHER;
-		iter_end = I40E_FILTER_PCTYPE_FRAG_IPV6;
+		iter_start = LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER;
+		iter_end = LIBIE_FILTER_PCTYPE_FRAG_IPV6;
 	}
 
 	for (i = iter_start; i <= iter_end; i++) {
@@ -2948,9 +2949,9 @@ static void i40e_atr(struct i40e_ring *tx_ring, struct sk_buff *skb,
 	flex_ptype = FIELD_PREP(I40E_TXD_FLTR_QW0_QINDEX_MASK,
 				tx_ring->queue_index);
 	flex_ptype |= (tx_flags & I40E_TX_FLAGS_IPV4) ?
-		      (I40E_FILTER_PCTYPE_NONF_IPV4_TCP <<
+		      (LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP <<
 		       I40E_TXD_FLTR_QW0_PCTYPE_SHIFT) :
-		      (I40E_FILTER_PCTYPE_NONF_IPV6_TCP <<
+		      (LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP <<
 		       I40E_TXD_FLTR_QW0_PCTYPE_SHIFT);
 
 	flex_ptype |= tx_ring->vsi->id << I40E_TXD_FLTR_QW0_DEST_VSI_SHIFT;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
index b007a84268a7..1e5fd63d47f4 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h
@@ -4,6 +4,7 @@
 #ifndef _I40E_TXRX_H_
 #define _I40E_TXRX_H_
 
+#include <linux/net/intel/libie/pctype.h>
 #include <net/xdp.h>
 #include "i40e_type.h"
 
@@ -72,25 +73,25 @@ enum i40e_dyn_idx {
 
 /* Supported RSS offloads */
 #define I40E_DEFAULT_RSS_HASHCFG ( \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV4) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_FRAG_IPV6) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_L2_PAYLOAD))
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_L2_PAYLOAD))
 
 #define I40E_DEFAULT_RSS_HASHCFG_EXPANDED (I40E_DEFAULT_RSS_HASHCFG | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
-	BIT_ULL(I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
 #define i40e_pf_get_default_rss_hashcfg(pf) \
 	(test_bit(I40E_HW_CAP_MULTI_TCP_UDP_RSS_PCTYPE, (pf)->hw.caps) ? \
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index 28568e126850..a09ed83835ff 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -929,38 +929,6 @@ struct i40e_filter_program_desc {
 #define I40E_TXD_FLTR_QW0_PCTYPE_MASK	(0x3FUL << \
 					 I40E_TXD_FLTR_QW0_PCTYPE_SHIFT)
 
-/* Packet Classifier Types for filters */
-enum i40e_filter_pctype {
-	/* Note: Values 0-28 are reserved for future use.
-	 * Value 29, 30, 32 are not supported on XL710 and X710.
-	 */
-	I40E_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP	= 29,
-	I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP	= 30,
-	I40E_FILTER_PCTYPE_NONF_IPV4_UDP		= 31,
-	I40E_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK	= 32,
-	I40E_FILTER_PCTYPE_NONF_IPV4_TCP		= 33,
-	I40E_FILTER_PCTYPE_NONF_IPV4_SCTP		= 34,
-	I40E_FILTER_PCTYPE_NONF_IPV4_OTHER		= 35,
-	I40E_FILTER_PCTYPE_FRAG_IPV4			= 36,
-	/* Note: Values 37-38 are reserved for future use.
-	 * Value 39, 40, 42 are not supported on XL710 and X710.
-	 */
-	I40E_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP	= 39,
-	I40E_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP	= 40,
-	I40E_FILTER_PCTYPE_NONF_IPV6_UDP		= 41,
-	I40E_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK	= 42,
-	I40E_FILTER_PCTYPE_NONF_IPV6_TCP		= 43,
-	I40E_FILTER_PCTYPE_NONF_IPV6_SCTP		= 44,
-	I40E_FILTER_PCTYPE_NONF_IPV6_OTHER		= 45,
-	I40E_FILTER_PCTYPE_FRAG_IPV6			= 46,
-	/* Note: Value 47 is reserved for future use */
-	I40E_FILTER_PCTYPE_FCOE_OX			= 48,
-	I40E_FILTER_PCTYPE_FCOE_RX			= 49,
-	I40E_FILTER_PCTYPE_FCOE_OTHER			= 50,
-	/* Note: Values 51-62 are reserved for future use */
-	I40E_FILTER_PCTYPE_L2_PAYLOAD			= 63,
-};
-
 enum i40e_filter_program_desc_dest {
 	I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET		= 0x0,
 	I40E_FILTER_PROGRAM_DESC_DEST_DIRECT_PACKET_QINDEX	= 0x1,
diff --git a/drivers/net/ethernet/intel/iavf/iavf_txrx.h b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
index 94b324f212bd..df49b0b1d54a 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_txrx.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_txrx.h
@@ -4,6 +4,8 @@
 #ifndef _IAVF_TXRX_H_
 #define _IAVF_TXRX_H_
 
+#include <linux/net/intel/libie/pctype.h>
+
 /* Interrupt Throttling and Rate Limiting Goodies */
 #define IAVF_DEFAULT_IRQ_WORK      256
 
@@ -60,25 +62,25 @@ enum iavf_dyn_idx_t {
 
 /* Supported RSS offloads */
 #define IAVF_DEFAULT_RSS_HASHCFG ( \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV4) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_FRAG_IPV6) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_L2_PAYLOAD))
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_L2_PAYLOAD))
 
 #define IAVF_DEFAULT_RSS_HASHCFG_EXPANDED (IAVF_DEFAULT_RSS_HASHCFG | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
-	BIT_ULL(IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
 /* How many Rx Buffers do we bundle into one write to the hardware ? */
 #define IAVF_RX_INCREMENT(r, i) \
diff --git a/drivers/net/ethernet/intel/iavf/iavf_type.h b/drivers/net/ethernet/intel/iavf/iavf_type.h
index f9e1319620f4..cb12e86ba4a6 100644
--- a/drivers/net/ethernet/intel/iavf/iavf_type.h
+++ b/drivers/net/ethernet/intel/iavf/iavf_type.h
@@ -463,38 +463,6 @@ enum iavf_tx_ctx_desc_cmd_bits {
 	IAVF_TX_CTX_DESC_SWPE		= 0x40
 };
 
-/* Packet Classifier Types for filters */
-enum iavf_filter_pctype {
-	/* Note: Values 0-28 are reserved for future use.
-	 * Value 29, 30, 32 are not supported on XL710 and X710.
-	 */
-	IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP	= 29,
-	IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP	= 30,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_UDP		= 31,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK	= 32,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_TCP		= 33,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_SCTP		= 34,
-	IAVF_FILTER_PCTYPE_NONF_IPV4_OTHER		= 35,
-	IAVF_FILTER_PCTYPE_FRAG_IPV4			= 36,
-	/* Note: Values 37-38 are reserved for future use.
-	 * Value 39, 40, 42 are not supported on XL710 and X710.
-	 */
-	IAVF_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP	= 39,
-	IAVF_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP	= 40,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_UDP		= 41,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK	= 42,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_TCP		= 43,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_SCTP		= 44,
-	IAVF_FILTER_PCTYPE_NONF_IPV6_OTHER		= 45,
-	IAVF_FILTER_PCTYPE_FRAG_IPV6			= 46,
-	/* Note: Value 47 is reserved for future use */
-	IAVF_FILTER_PCTYPE_FCOE_OX			= 48,
-	IAVF_FILTER_PCTYPE_FCOE_RX			= 49,
-	IAVF_FILTER_PCTYPE_FCOE_OTHER			= 50,
-	/* Note: Values 51-62 are reserved for future use */
-	IAVF_FILTER_PCTYPE_L2_PAYLOAD			= 63,
-};
-
 #define IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT	30
 #define IAVF_TXD_CTX_QW1_TSO_LEN_MASK	(0x3FFFFULL << \
 					 IAVF_TXD_CTX_QW1_TSO_LEN_SHIFT)
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.c b/drivers/net/ethernet/intel/ice/ice_flow.c
index d97b751052f2..278e57686274 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.c
+++ b/drivers/net/ethernet/intel/ice/ice_flow.c
@@ -2573,38 +2573,38 @@ ice_rem_rss_cfg(struct ice_hw *hw, u16 vsi_handle,
  * convert its values to their appropriate flow L3, L4 values.
  */
 #define ICE_FLOW_AVF_RSS_IPV4_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_OTHER) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV4))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4))
 #define ICE_FLOW_AVF_RSS_TCP_IPV4_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP))
 #define ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_UDP))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP))
 #define ICE_FLOW_AVF_RSS_ALL_IPV4_MASKS \
 	(ICE_FLOW_AVF_RSS_TCP_IPV4_MASKS | ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS | \
-	 ICE_FLOW_AVF_RSS_IPV4_MASKS | BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP))
+	 ICE_FLOW_AVF_RSS_IPV4_MASKS | BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP))
 
 #define ICE_FLOW_AVF_RSS_IPV6_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_OTHER) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV6))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6))
 #define ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_UDP))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP))
 #define ICE_FLOW_AVF_RSS_TCP_IPV6_MASKS \
-	(BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK) | \
-	 BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP))
+	(BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	 BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP))
 #define ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS \
 	(ICE_FLOW_AVF_RSS_TCP_IPV6_MASKS | ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS | \
-	 ICE_FLOW_AVF_RSS_IPV6_MASKS | BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP))
+	 ICE_FLOW_AVF_RSS_IPV6_MASKS | BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP))
 
 /**
  * ice_add_avf_rss_cfg - add an RSS configuration for AVF driver
  * @hw: pointer to the hardware structure
  * @vsi: VF's VSI
- * @avf_hash: hash bit fields (ICE_AVF_FLOW_FIELD_*) to configure
+ * @avf_hash: hash bit fields (LIBIE_FILTER_PCTYPE_*) to configure
  *
  * This function will take the hash bitmap provided by the AVF driver via a
  * message, convert it to ICE-compatible values, and configure RSS flow
@@ -2621,8 +2621,7 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, u64 avf_hash)
 		return -EINVAL;
 
 	vsi_handle = vsi->idx;
-	if (avf_hash == ICE_AVF_FLOW_FIELD_INVALID ||
-	    !ice_is_vsi_valid(hw, vsi_handle))
+	if (!avf_hash || !ice_is_vsi_valid(hw, vsi_handle))
 		return -EINVAL;
 
 	/* Make sure no unsupported bits are specified */
@@ -2658,11 +2657,11 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, u64 avf_hash)
 					ICE_FLOW_HASH_UDP_PORT;
 				hash_flds &= ~ICE_FLOW_AVF_RSS_UDP_IPV4_MASKS;
 			} else if (hash_flds &
-				   BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP)) {
+				   BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP)) {
 				rss_hash = ICE_FLOW_HASH_IPV4 |
 					ICE_FLOW_HASH_SCTP_PORT;
 				hash_flds &=
-					~BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP);
+					~BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP);
 			}
 		} else if (hash_flds & ICE_FLOW_AVF_RSS_ALL_IPV6_MASKS) {
 			if (hash_flds & ICE_FLOW_AVF_RSS_IPV6_MASKS) {
@@ -2679,11 +2678,11 @@ int ice_add_avf_rss_cfg(struct ice_hw *hw, struct ice_vsi *vsi, u64 avf_hash)
 					ICE_FLOW_HASH_UDP_PORT;
 				hash_flds &= ~ICE_FLOW_AVF_RSS_UDP_IPV6_MASKS;
 			} else if (hash_flds &
-				   BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP)) {
+				   BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP)) {
 				rss_hash = ICE_FLOW_HASH_IPV6 |
 					ICE_FLOW_HASH_SCTP_PORT;
 				hash_flds &=
-					~BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP);
+					~BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP);
 			}
 		}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_flow.h b/drivers/net/ethernet/intel/ice/ice_flow.h
index b1313fb61677..52f906d89eca 100644
--- a/drivers/net/ethernet/intel/ice/ice_flow.h
+++ b/drivers/net/ethernet/intel/ice/ice_flow.h
@@ -4,6 +4,8 @@
 #ifndef _ICE_FLOW_H_
 #define _ICE_FLOW_H_
 
+#include <linux/net/intel/libie/pctype.h>
+
 #include "ice_flex_type.h"
 #include "ice_parser.h"
 
@@ -264,57 +266,27 @@ enum ice_flow_field {
 #define ICE_FLOW_HASH_FLD_GTPU_DWN_TEID \
 	BIT_ULL(ICE_FLOW_FIELD_IDX_GTPU_DWN_TEID)
 
-/* Flow headers and fields for AVF support */
-enum ice_flow_avf_hdr_field {
-	/* Values 0 - 28 are reserved for future use */
-	ICE_AVF_FLOW_FIELD_INVALID		= 0,
-	ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP	= 29,
-	ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP,
-	ICE_AVF_FLOW_FIELD_IPV4_UDP,
-	ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK,
-	ICE_AVF_FLOW_FIELD_IPV4_TCP,
-	ICE_AVF_FLOW_FIELD_IPV4_SCTP,
-	ICE_AVF_FLOW_FIELD_IPV4_OTHER,
-	ICE_AVF_FLOW_FIELD_FRAG_IPV4,
-	/* Values 37-38 are reserved */
-	ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP	= 39,
-	ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP,
-	ICE_AVF_FLOW_FIELD_IPV6_UDP,
-	ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK,
-	ICE_AVF_FLOW_FIELD_IPV6_TCP,
-	ICE_AVF_FLOW_FIELD_IPV6_SCTP,
-	ICE_AVF_FLOW_FIELD_IPV6_OTHER,
-	ICE_AVF_FLOW_FIELD_FRAG_IPV6,
-	ICE_AVF_FLOW_FIELD_RSVD47,
-	ICE_AVF_FLOW_FIELD_FCOE_OX,
-	ICE_AVF_FLOW_FIELD_FCOE_RX,
-	ICE_AVF_FLOW_FIELD_FCOE_OTHER,
-	/* Values 51-62 are reserved */
-	ICE_AVF_FLOW_FIELD_L2_PAYLOAD		= 63,
-	ICE_AVF_FLOW_FIELD_MAX
-};
-
 /* Supported RSS offloads  This macro is defined to support
  * VIRTCHNL_OP_GET_RSS_HASHCFG_CAPS ops. PF driver sends the RSS hardware
  * capabilities to the caller of this ops.
  */
 #define ICE_DEFAULT_RSS_HASHCFG ( \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_SCTP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_OTHER) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV4) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_SCTP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_OTHER) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_FRAG_IPV6) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV4_TCP_SYN_NO_ACK) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV4_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV4_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_IPV6_TCP_SYN_NO_ACK) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_UNICAST_IPV6_UDP) | \
-	BIT_ULL(ICE_AVF_FLOW_FIELD_MULTICAST_IPV6_UDP))
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV4) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_FRAG_IPV6) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP) | \
+	BIT_ULL(LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP))
 
 enum ice_rss_cfg_hdr_type {
 	ICE_RSS_OUTER_HEADERS, /* take outer headers as inputset. */
diff --git a/include/linux/avf/virtchnl.h b/include/linux/avf/virtchnl.h
index 362d1cdc8cd8..5be1881abbb6 100644
--- a/include/linux/avf/virtchnl.h
+++ b/include/linux/avf/virtchnl.h
@@ -982,6 +982,7 @@ VIRTCHNL_CHECK_STRUCT_LEN(4, virtchnl_rss_lut);
  * traffic types that are hashed by the hardware.
  */
 struct virtchnl_rss_hashcfg {
+	/* Bits defined by enum libie_filter_pctype */
 	u64 hashcfg;
 };
 
diff --git a/include/linux/net/intel/libie/pctype.h b/include/linux/net/intel/libie/pctype.h
new file mode 100644
index 000000000000..d783417fbf36
--- /dev/null
+++ b/include/linux/net/intel/libie/pctype.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2025 Intel Corporation */
+
+#ifndef __LIBIE_PCTYPE_H
+#define __LIBIE_PCTYPE_H
+
+/* Packet Classifier Type indexes, used to set the xxQF_HENA registers. Also
+ * communicated over the virtchnl API as part of struct virtchnl_rss_hashena.
+ */
+enum libie_filter_pctype {
+	/* Note: Values 0-28 are reserved for future use.
+	 * Value 29, 30, 32 are not supported on XL710 and X710.
+	 */
+	LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV4_UDP	= 29,
+	LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV4_UDP	= 30,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_UDP		= 31,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP_SYN_NO_ACK	= 32,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_TCP		= 33,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_SCTP		= 34,
+	LIBIE_FILTER_PCTYPE_NONF_IPV4_OTHER		= 35,
+	LIBIE_FILTER_PCTYPE_FRAG_IPV4			= 36,
+	/* Note: Values 37-38 are reserved for future use.
+	 * Value 39, 40, 42 are not supported on XL710 and X710.
+	 */
+	LIBIE_FILTER_PCTYPE_NONF_UNICAST_IPV6_UDP	= 39,
+	LIBIE_FILTER_PCTYPE_NONF_MULTICAST_IPV6_UDP	= 40,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_UDP		= 41,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP_SYN_NO_ACK	= 42,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_TCP		= 43,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_SCTP		= 44,
+	LIBIE_FILTER_PCTYPE_NONF_IPV6_OTHER		= 45,
+	LIBIE_FILTER_PCTYPE_FRAG_IPV6			= 46,
+	/* Note: Value 47 is reserved for future use */
+	LIBIE_FILTER_PCTYPE_FCOE_OX			= 48,
+	LIBIE_FILTER_PCTYPE_FCOE_RX			= 49,
+	LIBIE_FILTER_PCTYPE_FCOE_OTHER			= 50,
+	/* Note: Values 51-62 are reserved for future use */
+	LIBIE_FILTER_PCTYPE_L2_PAYLOAD			= 63
+};
+
+#endif /* __LIBIE_PCTYPE_H */
-- 
cgit v1.2.3


From 9b8367b604c739947ec308874f087fe0eb80f412 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Fri, 6 Jun 2025 09:31:36 -0700
Subject: cgroup: Add bpf prog revisions to struct cgroup_bpf

One of key items in mprog API is revision for prog list. The revision
number will be increased if the prog list changed, e.g., attach, detach
or replace.

Add 'revisions' field to struct cgroup_bpf, representing revisions for
all cgroup related attachment types. The initial revision value is
set to 1, the same as kernel mprog implementations.

Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20250606163136.2428732-1-yonghong.song@linux.dev
---
 include/linux/bpf-cgroup-defs.h | 1 +
 kernel/cgroup/cgroup.c          | 5 +++++
 2 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup-defs.h b/include/linux/bpf-cgroup-defs.h
index 0985221d5478..c9e6b26abab6 100644
--- a/include/linux/bpf-cgroup-defs.h
+++ b/include/linux/bpf-cgroup-defs.h
@@ -63,6 +63,7 @@ struct cgroup_bpf {
 	 */
 	struct hlist_head progs[MAX_CGROUP_BPF_ATTACH_TYPE];
 	u8 flags[MAX_CGROUP_BPF_ATTACH_TYPE];
+	u64 revisions[MAX_CGROUP_BPF_ATTACH_TYPE];
 
 	/* list of cgroup shared storages */
 	struct list_head storages;
diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
index a723b7dc6e4e..312c6a8b55bb 100644
--- a/kernel/cgroup/cgroup.c
+++ b/kernel/cgroup/cgroup.c
@@ -2074,6 +2074,11 @@ static void init_cgroup_housekeeping(struct cgroup *cgrp)
 	for_each_subsys(ss, ssid)
 		INIT_LIST_HEAD(&cgrp->e_csets[ssid]);
 
+#ifdef CONFIG_CGROUP_BPF
+	for (int i = 0; i < ARRAY_SIZE(cgrp->bpf.revisions); i++)
+		cgrp->bpf.revisions[i] = 1;
+#endif
+
 	init_waitqueue_head(&cgrp->offline_waitq);
 	INIT_WORK(&cgrp->release_agent_work, cgroup1_release_agent);
 }
-- 
cgit v1.2.3


From 03c68a0f8c68936a0bb915b030693923784724cb Mon Sep 17 00:00:00 2001
From: Luis Gerhorst <luis.gerhorst@fau.de>
Date: Tue, 3 Jun 2025 23:13:18 +0200
Subject: bpf, arm64, powerpc: Add bpf_jit_bypass_spec_v1/v4()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

JITs can set bpf_jit_bypass_spec_v1/v4() if they want the verifier to
skip analysis/patching for the respective vulnerability. For v4, this
will reduce the number of barriers the verifier inserts. For v1, it
allows more programs to be accepted.

The primary motivation for this is to not regress unpriv BPF's
performance on ARM64 in a future commit where BPF_NOSPEC is also used
against Spectre v1.

This has the user-visible change that v1-induced rejections on
non-vulnerable PowerPC CPUs are avoided.

For now, this does not change the semantics of BPF_NOSPEC. It is still a
v4-only barrier and must not be implemented if bypass_spec_v4 is always
true for the arch. Changing it to a v1 AND v4-barrier is done in a
future commit.

As an alternative to bypass_spec_v1/v4, one could introduce NOSPEC_V1
AND NOSPEC_V4 instructions and allow backends to skip their lowering as
suggested by commit f5e81d111750 ("bpf: Introduce BPF nospec instruction
for mitigating Spectre v4"). Adding bpf_jit_bypass_spec_v1/v4() was
found to be preferable for the following reason:

* bypass_spec_v1/v4 benefits non-vulnerable CPUs: Always performing the
  same analysis (not taking into account whether the current CPU is
  vulnerable), needlessly restricts users of CPUs that are not
  vulnerable. The only use case for this would be portability-testing,
  but this can later be added easily when needed by allowing users to
  force bypass_spec_v1/v4 to false.

* Portability is still acceptable: Directly disabling the analysis
  instead of skipping the lowering of BPF_NOSPEC(_V1/V4) might allow
  programs on non-vulnerable CPUs to be accepted while the program will
  be rejected on vulnerable CPUs. With the fallback to speculation
  barriers for Spectre v1 implemented in a future commit, this will only
  affect programs that do variable stack-accesses or are very complex.

For PowerPC, the SEC_FTR checking in bpf_jit_bypass_spec_v4() is based
on the check that was previously located in the BPF_NOSPEC case.

For LoongArch, it would likely be safe to set both
bpf_jit_bypass_spec_v1() and _v4() according to
commit a6f6a95f2580 ("LoongArch, bpf: Fix jit to skip speculation
barrier opcode"). This is omitted here as I am unable to do any testing
for LoongArch.

Hari's ack concerns the PowerPC part only.

Signed-off-by: Luis Gerhorst <luis.gerhorst@fau.de>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
Cc: Henriette Herzog <henriette.herzog@rub.de>
Cc: Maximilian Ott <ott@cs.fau.de>
Cc: Milan Stephan <milan.stephan@fau.de>
Link: https://lore.kernel.org/r/20250603211318.337474-1-luis.gerhorst@fau.de
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arm64/net/bpf_jit_comp.c     | 21 ++++++++++++---------
 arch/powerpc/net/bpf_jit_comp64.c | 21 +++++++++++++++++----
 include/linux/bpf.h               | 11 +++++++++--
 kernel/bpf/core.c                 | 15 +++++++++++++++
 4 files changed, 53 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index da8b89dd2910..2cab9063f563 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1632,15 +1632,7 @@ emit_cond_jmp:
 
 	/* speculation barrier */
 	case BPF_ST | BPF_NOSPEC:
-		/*
-		 * Nothing required here.
-		 *
-		 * In case of arm64, we rely on the firmware mitigation of
-		 * Speculative Store Bypass as controlled via the ssbd kernel
-		 * parameter. Whenever the mitigation is enabled, it works
-		 * for all of the kernel code with no need to provide any
-		 * additional instructions.
-		 */
+		/* See bpf_jit_bypass_spec_v4() */
 		break;
 
 	/* ST: *(size *)(dst + off) = imm */
@@ -2911,6 +2903,17 @@ bool bpf_jit_supports_percpu_insn(void)
 	return true;
 }
 
+bool bpf_jit_bypass_spec_v4(void)
+{
+	/* In case of arm64, we rely on the firmware mitigation of Speculative
+	 * Store Bypass as controlled via the ssbd kernel parameter. Whenever
+	 * the mitigation is enabled, it works for all of the kernel code with
+	 * no need to provide any additional instructions. Therefore, skip
+	 * inserting nospec insns against Spectre v4.
+	 */
+	return true;
+}
+
 bool bpf_jit_inlines_helper_call(s32 imm)
 {
 	switch (imm) {
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index 5daa77aee7f7..a4335761b7f9 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -370,6 +370,23 @@ static int bpf_jit_emit_tail_call(u32 *image, struct codegen_context *ctx, u32 o
 	return 0;
 }
 
+bool bpf_jit_bypass_spec_v1(void)
+{
+#if defined(CONFIG_PPC_E500) || defined(CONFIG_PPC_BOOK3S_64)
+	return !(security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_BNDS_CHK_SPEC_BAR));
+#else
+	return true;
+#endif
+}
+
+bool bpf_jit_bypass_spec_v4(void)
+{
+	return !(security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) &&
+		 security_ftr_enabled(SEC_FTR_STF_BARRIER) &&
+		 stf_barrier_type_get() != STF_BARRIER_NONE);
+}
+
 /*
  * We spill into the redzone always, even if the bpf program has its own stackframe.
  * Offsets hardcoded based on BPF_PPC_STACK_SAVE -- see bpf_jit_stack_local()
@@ -791,10 +808,6 @@ emit_clear:
 		 * BPF_ST NOSPEC (speculation barrier)
 		 */
 		case BPF_ST | BPF_NOSPEC:
-			if (!security_ftr_enabled(SEC_FTR_FAVOUR_SECURITY) ||
-					!security_ftr_enabled(SEC_FTR_STF_BARRIER))
-				break;
-
 			switch (stf_barrier) {
 			case STF_BARRIER_EIEIO:
 				EMIT(PPC_RAW_EIEIO() | 0x02000000);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5b25d278409b..5dd556e89cce 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2288,6 +2288,9 @@ bpf_prog_run_array_uprobe(const struct bpf_prog_array *array,
 	return ret;
 }
 
+bool bpf_jit_bypass_spec_v1(void);
+bool bpf_jit_bypass_spec_v4(void);
+
 #ifdef CONFIG_BPF_SYSCALL
 DECLARE_PER_CPU(int, bpf_prog_active);
 extern struct mutex bpf_stats_enabled_mutex;
@@ -2475,12 +2478,16 @@ static inline bool bpf_allow_uninit_stack(const struct bpf_token *token)
 
 static inline bool bpf_bypass_spec_v1(const struct bpf_token *token)
 {
-	return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
+	return bpf_jit_bypass_spec_v1() ||
+		cpu_mitigations_off() ||
+		bpf_token_capable(token, CAP_PERFMON);
 }
 
 static inline bool bpf_bypass_spec_v4(const struct bpf_token *token)
 {
-	return cpu_mitigations_off() || bpf_token_capable(token, CAP_PERFMON);
+	return bpf_jit_bypass_spec_v4() ||
+		cpu_mitigations_off() ||
+		bpf_token_capable(token, CAP_PERFMON);
 }
 
 int bpf_map_new_fd(struct bpf_map *map, int flags);
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index c20babbf998f..f9bd9625438b 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -3034,6 +3034,21 @@ bool __weak bpf_jit_needs_zext(void)
 	return false;
 }
 
+/* By default, enable the verifier's mitigations against Spectre v1 and v4 for
+ * all archs. The value returned must not change at runtime as there is
+ * currently no support for reloading programs that were loaded without
+ * mitigations.
+ */
+bool __weak bpf_jit_bypass_spec_v1(void)
+{
+	return false;
+}
+
+bool __weak bpf_jit_bypass_spec_v4(void)
+{
+	return false;
+}
+
 /* Return true if the JIT inlines the call to the helper corresponding to
  * the imm.
  *
-- 
cgit v1.2.3


From dff883d9e93a7f2f2fa4e38a9444b2c79d6da91a Mon Sep 17 00:00:00 2001
From: Luis Gerhorst <luis.gerhorst@fau.de>
Date: Tue, 3 Jun 2025 23:17:03 +0200
Subject: bpf, arm64, powerpc: Change nospec to include v1 barrier
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This changes the semantics of BPF_NOSPEC (previously a v4-only barrier)
to always emit a speculation barrier that works against both Spectre v1
AND v4. If mitigation is not needed on an architecture, the backend
should set bpf_jit_bypass_spec_v4/v1().

As of now, this commit only has the user-visible implication that unpriv
BPF's performance on PowerPC is reduced. This is the case because we
have to emit additional v1 barrier instructions for BPF_NOSPEC now.

This commit is required for a future commit to allow us to rely on
BPF_NOSPEC for Spectre v1 mitigation. As of this commit, the feature
that nospec acts as a v1 barrier is unused.

Commit f5e81d111750 ("bpf: Introduce BPF nospec instruction for
mitigating Spectre v4") noted that mitigation instructions for v1 and v4
might be different on some archs. While this would potentially offer
improved performance on PowerPC, it was dismissed after the following
considerations:

* Only having one barrier simplifies the verifier and allows us to
  easily rely on v4-induced barriers for reducing the complexity of
  v1-induced speculative path verification.

* For the architectures that implemented BPF_NOSPEC, only PowerPC has
  distinct instructions for v1 and v4. Even there, some insns may be
  shared between the barriers for v1 and v4 (e.g., 'ori 31,31,0' and
  'sync'). If this is still found to impact performance in an
  unacceptable way, BPF_NOSPEC can be split into BPF_NOSPEC_V1 and
  BPF_NOSPEC_V4 later. As an optimization, we can already skip v1/v4
  insns from being emitted for PowerPC with this setup if
  bypass_spec_v1/v4 is set.

Vulnerability-status for BPF_NOSPEC-based Spectre mitigations (v4 as of
this commit, v1 in the future) is therefore:

* x86 (32-bit and 64-bit), ARM64, and PowerPC (64-bit): Mitigated - This
  patch implements BPF_NOSPEC for these architectures. The previous
  v4-only version was supported since commit f5e81d111750 ("bpf:
  Introduce BPF nospec instruction for mitigating Spectre v4") and
  commit b7540d625094 ("powerpc/bpf: Emit stf barrier instruction
  sequences for BPF_NOSPEC").

* LoongArch: Not Vulnerable - Commit a6f6a95f2580 ("LoongArch, bpf: Fix
  jit to skip speculation barrier opcode") is the only other past commit
  related to BPF_NOSPEC and indicates that the insn is not required
  there.

* MIPS: Vulnerable (if unprivileged BPF is enabled) -
  Commit a6f6a95f2580 ("LoongArch, bpf: Fix jit to skip speculation
  barrier opcode") indicates that it is not vulnerable, but this
  contradicts the kernel and Debian documentation. Therefore, I assume
  that there exist vulnerable MIPS CPUs (but maybe not from Loongson?).
  In the future, BPF_NOSPEC could be implemented for MIPS based on the
  GCC speculation_barrier [1]. For now, we rely on unprivileged BPF
  being disabled by default.

* Other: Unknown - To the best of my knowledge there is no definitive
  information available that indicates that any other arch is
  vulnerable. They are therefore left untouched (BPF_NOSPEC is not
  implemented, but bypass_spec_v1/v4 is also not set).

I did the following testing to ensure the insn encoding is correct:

* ARM64:
  * 'dsb nsh; isb' was successfully tested with the BPF CI in [2]
  * 'sb' locally using QEMU v7.2.15 -cpu max (emitted sb insn is
    executed for example with './test_progs -t verifier_array_access')

* PowerPC: The following configs were tested locally with ppc64le QEMU
  v8.2 '-machine pseries -cpu POWER9':
  * STF_BARRIER_EIEIO + CONFIG_PPC_BOOK32_64
  * STF_BARRIER_SYNC_ORI (forced on) + CONFIG_PPC_BOOK32_64
  * STF_BARRIER_FALLBACK (forced on) + CONFIG_PPC_BOOK32_64
  * CONFIG_PPC_E500 (forced on) + STF_BARRIER_EIEIO
  * CONFIG_PPC_E500 (forced on) + STF_BARRIER_SYNC_ORI (forced on)
  * CONFIG_PPC_E500 (forced on) + STF_BARRIER_FALLBACK (forced on)
  * CONFIG_PPC_E500 (forced on) + STF_BARRIER_NONE (forced on)
  Most of those cobinations should not occur in practice, but I was not
  able to get an PPC e6500 rootfs (for testing PPC_E500 without forcing
  it on). In any case, this should ensure that there are no unexpected
  conflicts between the insns when combined like this. Individual v1/v4
  barriers were already emitted elsewhere.

Hari's ack is for the PowerPC changes only.

[1] https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=29b74545531f6afbee9fc38c267524326dbfbedf
    ("MIPS: Add speculation_barrier support")
[2] https://github.com/kernel-patches/bpf/pull/8576

Signed-off-by: Luis Gerhorst <luis.gerhorst@fau.de>
Acked-by: Hari Bathini <hbathini@linux.ibm.com>
Cc: Henriette Herzog <henriette.herzog@rub.de>
Cc: Maximilian Ott <ott@cs.fau.de>
Cc: Milan Stephan <milan.stephan@fau.de>
Link: https://lore.kernel.org/r/20250603211703.337860-1-luis.gerhorst@fau.de
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/arm64/net/bpf_jit.h          |  5 ++++
 arch/arm64/net/bpf_jit_comp.c     |  9 ++++--
 arch/powerpc/net/bpf_jit_comp64.c | 59 ++++++++++++++++++++++++++++-----------
 include/linux/filter.h            |  2 +-
 kernel/bpf/core.c                 | 17 +++++------
 5 files changed, 65 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/net/bpf_jit.h b/arch/arm64/net/bpf_jit.h
index a3b0e693a125..bbea4f36f9f2 100644
--- a/arch/arm64/net/bpf_jit.h
+++ b/arch/arm64/net/bpf_jit.h
@@ -325,4 +325,9 @@
 #define A64_MRS_SP_EL0(Rt) \
 	aarch64_insn_gen_mrs(Rt, AARCH64_INSN_SYSREG_SP_EL0)
 
+/* Barriers */
+#define A64_SB aarch64_insn_get_sb_value()
+#define A64_DSB_NSH (aarch64_insn_get_dsb_base_value() | 0x7 << 8)
+#define A64_ISB aarch64_insn_get_isb_value()
+
 #endif /* _BPF_JIT_H */
diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
index 2cab9063f563..b6c42b5c9668 100644
--- a/arch/arm64/net/bpf_jit_comp.c
+++ b/arch/arm64/net/bpf_jit_comp.c
@@ -1630,9 +1630,14 @@ emit_cond_jmp:
 			return ret;
 		break;
 
-	/* speculation barrier */
+	/* speculation barrier against v1 and v4 */
 	case BPF_ST | BPF_NOSPEC:
-		/* See bpf_jit_bypass_spec_v4() */
+		if (alternative_has_cap_likely(ARM64_HAS_SB)) {
+			emit(A64_SB, ctx);
+		} else {
+			emit(A64_DSB_NSH, ctx);
+			emit(A64_ISB, ctx);
+		}
 		break;
 
 	/* ST: *(size *)(dst + off) = imm */
diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c
index a4335761b7f9..3665ff8bb4bc 100644
--- a/arch/powerpc/net/bpf_jit_comp64.c
+++ b/arch/powerpc/net/bpf_jit_comp64.c
@@ -414,6 +414,7 @@ int bpf_jit_build_body(struct bpf_prog *fp, u32 *image, u32 *fimage, struct code
 		       u32 *addrs, int pass, bool extra_pass)
 {
 	enum stf_barrier_type stf_barrier = stf_barrier_type_get();
+	bool sync_emitted, ori31_emitted;
 	const struct bpf_insn *insn = fp->insnsi;
 	int flen = fp->len;
 	int i, ret;
@@ -806,26 +807,52 @@ emit_clear:
 
 		/*
 		 * BPF_ST NOSPEC (speculation barrier)
+		 *
+		 * The following must act as a barrier against both Spectre v1
+		 * and v4 if we requested both mitigations. Therefore, also emit
+		 * 'isync; sync' on E500 or 'ori31' on BOOK3S_64 in addition to
+		 * the insns needed for a Spectre v4 barrier.
+		 *
+		 * If we requested only !bypass_spec_v1 OR only !bypass_spec_v4,
+		 * we can skip the respective other barrier type as an
+		 * optimization.
 		 */
 		case BPF_ST | BPF_NOSPEC:
-			switch (stf_barrier) {
-			case STF_BARRIER_EIEIO:
-				EMIT(PPC_RAW_EIEIO() | 0x02000000);
-				break;
-			case STF_BARRIER_SYNC_ORI:
+			sync_emitted = false;
+			ori31_emitted = false;
+#ifdef CONFIG_PPC_E500
+			if (!bpf_jit_bypass_spec_v1()) {
+				EMIT(PPC_RAW_ISYNC());
 				EMIT(PPC_RAW_SYNC());
-				EMIT(PPC_RAW_LD(tmp1_reg, _R13, 0));
-				EMIT(PPC_RAW_ORI(_R31, _R31, 0));
-				break;
-			case STF_BARRIER_FALLBACK:
-				ctx->seen |= SEEN_FUNC;
-				PPC_LI64(_R12, dereference_kernel_function_descriptor(bpf_stf_barrier));
-				EMIT(PPC_RAW_MTCTR(_R12));
-				EMIT(PPC_RAW_BCTRL());
-				break;
-			case STF_BARRIER_NONE:
-				break;
+				sync_emitted = true;
+			}
+#endif
+			if (!bpf_jit_bypass_spec_v4()) {
+				switch (stf_barrier) {
+				case STF_BARRIER_EIEIO:
+					EMIT(PPC_RAW_EIEIO() | 0x02000000);
+					break;
+				case STF_BARRIER_SYNC_ORI:
+					if (!sync_emitted)
+						EMIT(PPC_RAW_SYNC());
+					EMIT(PPC_RAW_LD(tmp1_reg, _R13, 0));
+					EMIT(PPC_RAW_ORI(_R31, _R31, 0));
+					ori31_emitted = true;
+					break;
+				case STF_BARRIER_FALLBACK:
+					ctx->seen |= SEEN_FUNC;
+					PPC_LI64(_R12, dereference_kernel_function_descriptor(bpf_stf_barrier));
+					EMIT(PPC_RAW_MTCTR(_R12));
+					EMIT(PPC_RAW_BCTRL());
+					break;
+				case STF_BARRIER_NONE:
+					break;
+				}
 			}
+#ifdef CONFIG_PPC_BOOK3S_64
+			if (!bpf_jit_bypass_spec_v1() && !ori31_emitted)
+				EMIT(PPC_RAW_ORI(_R31, _R31, 0));
+#endif
 			break;
 
 		/*
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f5cf4d35d83e..eca229752cbe 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -82,7 +82,7 @@ struct ctl_table_header;
 #define BPF_CALL_ARGS	0xe0
 
 /* unused opcode to mark speculation barrier for mitigating
- * Speculative Store Bypass
+ * Spectre v1 and v4
  */
 #define BPF_NOSPEC	0xc0
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f9bd9625438b..e536a34a32c8 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2102,14 +2102,15 @@ out:
 #undef COND_JMP
 	/* ST, STX and LDX*/
 	ST_NOSPEC:
-		/* Speculation barrier for mitigating Speculative Store Bypass.
-		 * In case of arm64, we rely on the firmware mitigation as
-		 * controlled via the ssbd kernel parameter. Whenever the
-		 * mitigation is enabled, it works for all of the kernel code
-		 * with no need to provide any additional instructions here.
-		 * In case of x86, we use 'lfence' insn for mitigation. We
-		 * reuse preexisting logic from Spectre v1 mitigation that
-		 * happens to produce the required code on x86 for v4 as well.
+		/* Speculation barrier for mitigating Speculative Store Bypass,
+		 * Bounds-Check Bypass and Type Confusion. In case of arm64, we
+		 * rely on the firmware mitigation as controlled via the ssbd
+		 * kernel parameter. Whenever the mitigation is enabled, it
+		 * works for all of the kernel code with no need to provide any
+		 * additional instructions here. In case of x86, we use 'lfence'
+		 * insn for mitigation. We reuse preexisting logic from Spectre
+		 * v1 mitigation that happens to produce the required code on
+		 * x86 for v4 as well.
 		 */
 		barrier_nospec();
 		CONT;
-- 
cgit v1.2.3


From 9124a4508007f146206a279f0c5e81dde314bda1 Mon Sep 17 00:00:00 2001
From: Luis Gerhorst <luis.gerhorst@fau.de>
Date: Tue, 3 Jun 2025 23:20:24 +0200
Subject: bpf: Rename sanitize_stack_spill to nospec_result

This is made to clarify that this flag will cause a nospec to be added
after this insn and can therefore be relied upon to reduce speculative
path analysis.

Signed-off-by: Luis Gerhorst <luis.gerhorst@fau.de>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Cc: Henriette Herzog <henriette.herzog@rub.de>
Cc: Maximilian Ott <ott@cs.fau.de>
Cc: Milan Stephan <milan.stephan@fau.de>
Link: https://lore.kernel.org/r/20250603212024.338154-1-luis.gerhorst@fau.de
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h | 2 +-
 kernel/bpf/verifier.c        | 4 ++--
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 256274acb1d8..2b0954202226 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -580,7 +580,7 @@ struct bpf_insn_aux_data {
 	u64 map_key_state; /* constant (32 bit) key tracking for maps */
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
 	u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
-	bool sanitize_stack_spill; /* subject to Spectre v4 sanitation */
+	bool nospec_result; /* result is unsafe under speculation, nospec must follow */
 	bool zext_dst; /* this insn zero extends dst reg */
 	bool needs_zext; /* alu op needs to clear upper bits */
 	bool storage_get_func_atomic; /* bpf_*_storage_get() with atomic memory alloc */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 04465e317f10..79ae0ee395b0 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -5027,7 +5027,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 		}
 
 		if (sanitize)
-			env->insn_aux_data[insn_idx].sanitize_stack_spill = true;
+			env->insn_aux_data[insn_idx].nospec_result = true;
 	}
 
 	err = destroy_if_dynptr_stack_slot(env, state, spi);
@@ -20930,7 +20930,7 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		}
 
 		if (type == BPF_WRITE &&
-		    env->insn_aux_data[i + delta].sanitize_stack_spill) {
+		    env->insn_aux_data[i + delta].nospec_result) {
 			struct bpf_insn patch[] = {
 				*insn,
 				BPF_ST_NOSPEC(),
-- 
cgit v1.2.3


From d6f1c85f22534d2d9fea9b32645da19c91ebe7d2 Mon Sep 17 00:00:00 2001
From: Luis Gerhorst <luis.gerhorst@fau.de>
Date: Tue, 3 Jun 2025 23:24:28 +0200
Subject: bpf: Fall back to nospec for Spectre v1
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This implements the core of the series and causes the verifier to fall
back to mitigating Spectre v1 using speculation barriers. The approach
was presented at LPC'24 [1] and RAID'24 [2].

If we find any forbidden behavior on a speculative path, we insert a
nospec (e.g., lfence speculation barrier on x86) before the instruction
and stop verifying the path. While verifying a speculative path, we can
furthermore stop verification of that path whenever we encounter a
nospec instruction.

A minimal example program would look as follows:

	A = true
	B = true
	if A goto e
	f()
	if B goto e
	unsafe()
e:	exit

There are the following speculative and non-speculative paths
(`cur->speculative` and `speculative` referring to the value of the
push_stack() parameters):

- A = true
- B = true
- if A goto e
  - A && !cur->speculative && !speculative
    - exit
  - !A && !cur->speculative && speculative
    - f()
    - if B goto e
      - B && cur->speculative && !speculative
        - exit
      - !B && cur->speculative && speculative
        - unsafe()

If f() contains any unsafe behavior under Spectre v1 and the unsafe
behavior matches `state->speculative &&
error_recoverable_with_nospec(err)`, do_check() will now add a nospec
before f() instead of rejecting the program:

	A = true
	B = true
	if A goto e
	nospec
	f()
	if B goto e
	unsafe()
e:	exit

Alternatively, the algorithm also takes advantage of nospec instructions
inserted for other reasons (e.g., Spectre v4). Taking the program above
as an example, speculative path exploration can stop before f() if a
nospec was inserted there because of Spectre v4 sanitization.

In this example, all instructions after the nospec are dead code (and
with the nospec they are also dead code speculatively).

For this, it relies on the fact that speculation barriers generally
prevent all later instructions from executing if the speculation was not
correct:

* On Intel x86_64, lfence acts as full speculation barrier, not only as
  a load fence [3]:

    An LFENCE instruction or a serializing instruction will ensure that
    no later instructions execute, even speculatively, until all prior
    instructions complete locally. [...] Inserting an LFENCE instruction
    after a bounds check prevents later operations from executing before
    the bound check completes.

  This was experimentally confirmed in [4].

* On AMD x86_64, lfence is dispatch-serializing [5] (requires MSR
  C001_1029[1] to be set if the MSR is supported, this happens in
  init_amd()). AMD further specifies "A dispatch serializing instruction
  forces the processor to retire the serializing instruction and all
  previous instructions before the next instruction is executed" [8]. As
  dispatch is not specific to memory loads or branches, lfence therefore
  also affects all instructions there. Also, if retiring a branch means
  it's PC change becomes architectural (should be), this means any
  "wrong" speculation is aborted as required for this series.

* ARM's SB speculation barrier instruction also affects "any instruction
  that appears later in the program order than the barrier" [6].

* PowerPC's barrier also affects all subsequent instructions [7]:

    [...] executing an ori R31,R31,0 instruction ensures that all
    instructions preceding the ori R31,R31,0 instruction have completed
    before the ori R31,R31,0 instruction completes, and that no
    subsequent instructions are initiated, even out-of-order, until
    after the ori R31,R31,0 instruction completes. The ori R31,R31,0
    instruction may complete before storage accesses associated with
    instructions preceding the ori R31,R31,0 instruction have been
    performed

Regarding the example, this implies that `if B goto e` will not execute
before `if A goto e` completes. Once `if A goto e` completes, the CPU
should find that the speculation was wrong and continue with `exit`.

If there is any other path that leads to `if B goto e` (and therefore
`unsafe()`) without going through `if A goto e`, then a nospec will
still be needed there. However, this patch assumes this other path will
be explored separately and therefore be discovered by the verifier even
if the exploration discussed here stops at the nospec.

This patch furthermore has the unfortunate consequence that Spectre v1
mitigations now only support architectures which implement BPF_NOSPEC.
Before this commit, Spectre v1 mitigations prevented exploits by
rejecting the programs on all architectures. Because some JITs do not
implement BPF_NOSPEC, this patch therefore may regress unpriv BPF's
security to a limited extent:

* The regression is limited to systems vulnerable to Spectre v1, have
  unprivileged BPF enabled, and do NOT emit insns for BPF_NOSPEC. The
  latter is not the case for x86 64- and 32-bit, arm64, and powerpc
  64-bit and they are therefore not affected by the regression.
  According to commit a6f6a95f2580 ("LoongArch, bpf: Fix jit to skip
  speculation barrier opcode"), LoongArch is not vulnerable to Spectre
  v1 and therefore also not affected by the regression.

* To the best of my knowledge this regression may therefore only affect
  MIPS. This is deemed acceptable because unpriv BPF is still disabled
  there by default. As stated in a previous commit, BPF_NOSPEC could be
  implemented for MIPS based on GCC's speculation_barrier
  implementation.

* It is unclear which other architectures (besides x86 64- and 32-bit,
  ARM64, PowerPC 64-bit, LoongArch, and MIPS) supported by the kernel
  are vulnerable to Spectre v1. Also, it is not clear if barriers are
  available on these architectures. Implementing BPF_NOSPEC on these
  architectures therefore is non-trivial. Searching GCC and the kernel
  for speculation barrier implementations for these architectures
  yielded no result.

* If any of those regressed systems is also vulnerable to Spectre v4,
  the system was already vulnerable to Spectre v4 attacks based on
  unpriv BPF before this patch and the impact is therefore further
  limited.

As an alternative to regressing security, one could still reject
programs if the architecture does not emit BPF_NOSPEC (e.g., by removing
the empty BPF_NOSPEC-case from all JITs except for LoongArch where it
appears justified). However, this will cause rejections on these archs
that are likely unfounded in the vast majority of cases.

In the tests, some are now successful where we previously had a
false-positive (i.e., rejection). Change them to reflect where the
nospec should be inserted (using __xlated_unpriv) and modify the error
message if the nospec is able to mitigate a problem that previously
shadowed another problem (in that case __xlated_unpriv does not work,
therefore just add a comment).

Define SPEC_V1 to avoid duplicating this ifdef whenever we check for
nospec insns using __xlated_unpriv, define it here once. This also
improves readability. PowerPC can probably also be added here. However,
omit it for now because the BPF CI currently does not include a test.

Limit it to EPERM, EACCES, and EINVAL (and not everything except for
EFAULT and ENOMEM) as it already has the desired effect for most
real-world programs. Briefly went through all the occurrences of EPERM,
EINVAL, and EACCESS in verifier.c to validate that catching them like
this makes sense.

Thanks to Dustin for their help in checking the vendor documentation.

[1] https://lpc.events/event/18/contributions/1954/ ("Mitigating
    Spectre-PHT using Speculation Barriers in Linux eBPF")
[2] https://arxiv.org/pdf/2405.00078 ("VeriFence: Lightweight and
    Precise Spectre Defenses for Untrusted Linux Kernel Extensions")
[3] https://www.intel.com/content/www/us/en/developer/articles/technical/software-security-guidance/technical-documentation/runtime-speculative-side-channel-mitigations.html
    ("Managed Runtime Speculative Execution Side Channel Mitigations")
[4] https://dl.acm.org/doi/pdf/10.1145/3359789.3359837 ("Speculator: a
    tool to analyze speculative execution attacks and mitigations" -
    Section 4.6 "Stopping Speculative Execution")
[5] https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/software-techniques-for-managing-speculation.pdf
    ("White Paper - SOFTWARE TECHNIQUES FOR MANAGING SPECULATION ON AMD
    PROCESSORS - REVISION 5.09.23")
[6] https://developer.arm.com/documentation/ddi0597/2020-12/Base-Instructions/SB--Speculation-Barrier-
    ("SB - Speculation Barrier - Arm Armv8-A A32/T32 Instruction Set
    Architecture (2020-12)")
[7] https://wiki.raptorcs.com/w/images/5/5f/OPF_PowerISA_v3.1C.pdf
    ("Power ISA™ - Version 3.1C - May 26, 2024 - Section 9.2.1 of Book
    III")
[8] https://www.amd.com/content/dam/amd/en/documents/processor-tech-docs/programmer-references/40332.pdf
    ("AMD64 Architecture Programmer’s Manual Volumes 1–5 - Revision 4.08
    - April 2024 - 7.6.4 Serializing Instructions")

Signed-off-by: Luis Gerhorst <luis.gerhorst@fau.de>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Acked-by: Henriette Herzog <henriette.herzog@rub.de>
Cc: Dustin Nguyen <nguyen@cs.fau.de>
Cc: Maximilian Ott <ott@cs.fau.de>
Cc: Milan Stephan <milan.stephan@fau.de>
Link: https://lore.kernel.org/r/20250603212428.338473-1-luis.gerhorst@fau.de
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h                       |  1 +
 kernel/bpf/verifier.c                              | 78 ++++++++++++++++++++--
 tools/testing/selftests/bpf/progs/bpf_misc.h       |  4 ++
 tools/testing/selftests/bpf/progs/verifier_and.c   |  8 ++-
 .../testing/selftests/bpf/progs/verifier_bounds.c  | 61 +++++++++++++----
 tools/testing/selftests/bpf/progs/verifier_movsx.c | 16 ++++-
 .../testing/selftests/bpf/progs/verifier_unpriv.c  |  8 ++-
 .../selftests/bpf/progs/verifier_value_ptr_arith.c | 16 +++--
 tools/testing/selftests/bpf/verifier/dead_code.c   |  3 +-
 tools/testing/selftests/bpf/verifier/jmp32.c       | 33 +++------
 tools/testing/selftests/bpf/verifier/jset.c        | 10 ++-
 11 files changed, 184 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 2b0954202226..e6c26393c029 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -580,6 +580,7 @@ struct bpf_insn_aux_data {
 	u64 map_key_state; /* constant (32 bit) key tracking for maps */
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
 	u32 seen; /* this insn was processed by the verifier at env->pass_cnt */
+	bool nospec; /* do not execute this instruction speculatively */
 	bool nospec_result; /* result is unsafe under speculation, nospec must follow */
 	bool zext_dst; /* this insn zero extends dst reg */
 	bool needs_zext; /* alu op needs to clear upper bits */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 79ae0ee395b0..b1f797616f20 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -2013,6 +2013,18 @@ static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
 	return 0;
 }
 
+static bool error_recoverable_with_nospec(int err)
+{
+	/* Should only return true for non-fatal errors that are allowed to
+	 * occur during speculative verification. For these we can insert a
+	 * nospec and the program might still be accepted. Do not include
+	 * something like ENOMEM because it is likely to re-occur for the next
+	 * architectural path once it has been recovered-from in all speculative
+	 * paths.
+	 */
+	return err == -EPERM || err == -EACCES || err == -EINVAL;
+}
+
 static struct bpf_verifier_state *push_stack(struct bpf_verifier_env *env,
 					     int insn_idx, int prev_insn_idx,
 					     bool speculative)
@@ -11147,7 +11159,7 @@ static int check_get_func_ip(struct bpf_verifier_env *env)
 	return -ENOTSUPP;
 }
 
-static struct bpf_insn_aux_data *cur_aux(struct bpf_verifier_env *env)
+static struct bpf_insn_aux_data *cur_aux(const struct bpf_verifier_env *env)
 {
 	return &env->insn_aux_data[env->insn_idx];
 }
@@ -14015,7 +14027,9 @@ static int retrieve_ptr_limit(const struct bpf_reg_state *ptr_reg,
 static bool can_skip_alu_sanitation(const struct bpf_verifier_env *env,
 				    const struct bpf_insn *insn)
 {
-	return env->bypass_spec_v1 || BPF_SRC(insn->code) == BPF_K;
+	return env->bypass_spec_v1 ||
+		BPF_SRC(insn->code) == BPF_K ||
+		cur_aux(env)->nospec;
 }
 
 static int update_alu_sanitation_state(struct bpf_insn_aux_data *aux,
@@ -19732,10 +19746,41 @@ static int do_check(struct bpf_verifier_env *env)
 		sanitize_mark_insn_seen(env);
 		prev_insn_idx = env->insn_idx;
 
+		/* Reduce verification complexity by stopping speculative path
+		 * verification when a nospec is encountered.
+		 */
+		if (state->speculative && cur_aux(env)->nospec)
+			goto process_bpf_exit;
+
 		err = do_check_insn(env, &do_print_state);
-		if (err < 0) {
+		if (state->speculative && error_recoverable_with_nospec(err)) {
+			/* Prevent this speculative path from ever reaching the
+			 * insn that would have been unsafe to execute.
+			 */
+			cur_aux(env)->nospec = true;
+			/* If it was an ADD/SUB insn, potentially remove any
+			 * markings for alu sanitization.
+			 */
+			cur_aux(env)->alu_state = 0;
+			goto process_bpf_exit;
+		} else if (err < 0) {
 			return err;
 		} else if (err == PROCESS_BPF_EXIT) {
+			goto process_bpf_exit;
+		}
+		WARN_ON_ONCE(err);
+
+		if (state->speculative && cur_aux(env)->nospec_result) {
+			/* If we are on a path that performed a jump-op, this
+			 * may skip a nospec patched-in after the jump. This can
+			 * currently never happen because nospec_result is only
+			 * used for the write-ops
+			 * `*(size*)(dst_reg+off)=src_reg|imm32` which must
+			 * never skip the following insn. Still, add a warning
+			 * to document this in case nospec_result is used
+			 * elsewhere in the future.
+			 */
+			WARN_ON_ONCE(env->insn_idx != prev_insn_idx + 1);
 process_bpf_exit:
 			mark_verifier_state_scratched(env);
 			update_branch_counts(env, env->cur_state);
@@ -19753,7 +19798,6 @@ process_bpf_exit:
 				continue;
 			}
 		}
-		WARN_ON_ONCE(err);
 	}
 
 	return 0;
@@ -20881,6 +20925,29 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 		bpf_convert_ctx_access_t convert_ctx_access;
 		u8 mode;
 
+		if (env->insn_aux_data[i + delta].nospec) {
+			WARN_ON_ONCE(env->insn_aux_data[i + delta].alu_state);
+			struct bpf_insn patch[] = {
+				BPF_ST_NOSPEC(),
+				*insn,
+			};
+
+			cnt = ARRAY_SIZE(patch);
+			new_prog = bpf_patch_insn_data(env, i + delta, patch, cnt);
+			if (!new_prog)
+				return -ENOMEM;
+
+			delta    += cnt - 1;
+			env->prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			/* This can not be easily merged with the
+			 * nospec_result-case, because an insn may require a
+			 * nospec before and after itself. Therefore also do not
+			 * 'continue' here but potentially apply further
+			 * patching to insn. *insn should equal patch[1] now.
+			 */
+		}
+
 		if (insn->code == (BPF_LDX | BPF_MEM | BPF_B) ||
 		    insn->code == (BPF_LDX | BPF_MEM | BPF_H) ||
 		    insn->code == (BPF_LDX | BPF_MEM | BPF_W) ||
@@ -20931,6 +20998,9 @@ static int convert_ctx_accesses(struct bpf_verifier_env *env)
 
 		if (type == BPF_WRITE &&
 		    env->insn_aux_data[i + delta].nospec_result) {
+			/* nospec_result is only used to mitigate Spectre v4 and
+			 * to limit verification-time for Spectre v1.
+			 */
 			struct bpf_insn patch[] = {
 				*insn,
 				BPF_ST_NOSPEC(),
diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
index 6e208e24ba3b..a678463e972c 100644
--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
+++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
@@ -231,4 +231,8 @@
 #define CAN_USE_LOAD_ACQ_STORE_REL
 #endif
 
+#if defined(__TARGET_ARCH_arm64) || defined(__TARGET_ARCH_x86)
+#define SPEC_V1
+#endif
+
 #endif
diff --git a/tools/testing/selftests/bpf/progs/verifier_and.c b/tools/testing/selftests/bpf/progs/verifier_and.c
index e97e518516b6..2b4fdca162be 100644
--- a/tools/testing/selftests/bpf/progs/verifier_and.c
+++ b/tools/testing/selftests/bpf/progs/verifier_and.c
@@ -85,8 +85,14 @@ l0_%=:	r0 = r0;					\
 
 SEC("socket")
 __description("check known subreg with unknown reg")
-__success __failure_unpriv __msg_unpriv("R1 !read_ok")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w0 < 0x1 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R1 !read_ok'` */
+__xlated_unpriv("goto pc-1") /* `r1 = *(u32*)(r1 + 512)`, sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
 __naked void known_subreg_with_unknown_reg(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds.c b/tools/testing/selftests/bpf/progs/verifier_bounds.c
index 0eb33bb801b5..30e16153fdf1 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds.c
@@ -620,8 +620,14 @@ l1_%=:	exit;						\
 
 SEC("socket")
 __description("bounds check mixed 32bit and 64bit arithmetic. test1")
-__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
 __naked void _32bit_and_64bit_arithmetic_test1(void)
 {
 	asm volatile ("					\
@@ -643,8 +649,14 @@ l1_%=:	exit;						\
 
 SEC("socket")
 __description("bounds check mixed 32bit and 64bit arithmetic. test2")
-__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
 __naked void _32bit_and_64bit_arithmetic_test2(void)
 {
 	asm volatile ("					\
@@ -691,9 +703,14 @@ l0_%=:	r0 = 0;						\
 
 SEC("socket")
 __description("bounds check for reg = 0, reg xor 1")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 != 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
 __naked void reg_0_reg_xor_1(void)
 {
 	asm volatile ("					\
@@ -719,9 +736,14 @@ l1_%=:	r0 = 0;						\
 
 SEC("socket")
 __description("bounds check for reg32 = 0, reg32 xor 1")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w1 != 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
 __naked void reg32_0_reg32_xor_1(void)
 {
 	asm volatile ("					\
@@ -747,9 +769,14 @@ l1_%=:	r0 = 0;						\
 
 SEC("socket")
 __description("bounds check for reg = 2, reg xor 3")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 > 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
 __naked void reg_2_reg_xor_3(void)
 {
 	asm volatile ("					\
@@ -829,9 +856,14 @@ l1_%=:	r0 = 0;						\
 
 SEC("socket")
 __description("bounds check for reg > 0, reg xor 3")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r1 >= 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
 __naked void reg_0_reg_xor_3(void)
 {
 	asm volatile ("					\
@@ -858,9 +890,14 @@ l1_%=:	r0 = 0;						\
 
 SEC("socket")
 __description("bounds check for reg32 > 0, reg32 xor 3")
-__success __failure_unpriv
-__msg_unpriv("R0 min value is outside of the allowed memory range")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if w1 >= 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 min value is outside of the allowed memory range` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("r0 = 0")
+#endif
 __naked void reg32_0_reg32_xor_3(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_movsx.c b/tools/testing/selftests/bpf/progs/verifier_movsx.c
index 994bbc346d25..a4d8814eb5ed 100644
--- a/tools/testing/selftests/bpf/progs/verifier_movsx.c
+++ b/tools/testing/selftests/bpf/progs/verifier_movsx.c
@@ -245,7 +245,13 @@ l0_%=:							\
 SEC("socket")
 __description("MOV32SX, S8, var_off not u32_max, positive after s8 extension")
 __success __retval(0)
-__failure_unpriv __msg_unpriv("frame pointer is read only")
+__success_unpriv
+#ifdef SPEC_V1
+__xlated_unpriv("w0 = 0")
+__xlated_unpriv("exit")
+__xlated_unpriv("nospec") /* inserted to prevent `frame pointer is read only` */
+__xlated_unpriv("goto pc-1")
+#endif
 __naked void mov64sx_s32_varoff_2(void)
 {
 	asm volatile ("					\
@@ -267,7 +273,13 @@ l0_%=:							\
 SEC("socket")
 __description("MOV32SX, S8, var_off not u32_max, negative after s8 extension")
 __success __retval(0)
-__failure_unpriv __msg_unpriv("frame pointer is read only")
+__success_unpriv
+#ifdef SPEC_V1
+__xlated_unpriv("w0 = 0")
+__xlated_unpriv("exit")
+__xlated_unpriv("nospec") /* inserted to prevent `frame pointer is read only` */
+__xlated_unpriv("goto pc-1")
+#endif
 __naked void mov64sx_s32_varoff_3(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_unpriv.c b/tools/testing/selftests/bpf/progs/verifier_unpriv.c
index db52ba66e880..9bd4aef72140 100644
--- a/tools/testing/selftests/bpf/progs/verifier_unpriv.c
+++ b/tools/testing/selftests/bpf/progs/verifier_unpriv.c
@@ -572,8 +572,14 @@ l0_%=:	exit;						\
 
 SEC("socket")
 __description("alu32: mov u32 const")
-__success __failure_unpriv __msg_unpriv("R7 invalid mem access 'scalar'")
+__success __success_unpriv
 __retval(0)
+#ifdef SPEC_V1
+__xlated_unpriv("if r0 == 0x0 goto pc+2")
+__xlated_unpriv("nospec") /* inserted to prevent `R7 invalid mem access 'scalar'` */
+__xlated_unpriv("goto pc-1") /* sanitized dead code */
+__xlated_unpriv("exit")
+#endif
 __naked void alu32_mov_u32_const(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
index 5ba6e53571c8..fcea9819e359 100644
--- a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
@@ -398,7 +398,8 @@ l2_%=:	r0 = 1;						\
 
 SEC("socket")
 __description("map access: mixing value pointer and scalar, 1")
-__success __failure_unpriv __msg_unpriv("R2 pointer comparison prohibited")
+__success __failure_unpriv
+__msg_unpriv("R2 tried to add from different maps, paths or scalars, pointer arithmetic with it prohibited for !root")
 __retval(0)
 __naked void value_pointer_and_scalar_1(void)
 {
@@ -433,6 +434,7 @@ l2_%=:	/* common instruction */			\
 l3_%=:	/* branch B */					\
 	r0 = 0x13371337;				\
 	/* verifier follows fall-through */		\
+	/* unpriv: nospec (inserted to prevent `R2 pointer comparison prohibited`) */\
 	if r2 != 0x100000 goto l4_%=;			\
 	r0 = 0;						\
 	exit;						\
@@ -450,7 +452,8 @@ l4_%=:	/* fake-dead code; targeted from branch A to	\
 
 SEC("socket")
 __description("map access: mixing value pointer and scalar, 2")
-__success __failure_unpriv __msg_unpriv("R0 invalid mem access 'scalar'")
+__success __failure_unpriv
+__msg_unpriv("R2 tried to add from different maps, paths or scalars, pointer arithmetic with it prohibited for !root")
 __retval(0)
 __naked void value_pointer_and_scalar_2(void)
 {
@@ -492,6 +495,7 @@ l4_%=:	/* fake-dead code; targeted from branch A to	\
 	 * prevent dead code sanitization, rejected	\
 	 * via branch B however				\
 	 */						\
+	/* unpriv: nospec (inserted to prevent `R0 invalid mem access 'scalar'`) */\
 	r0 = *(u8*)(r0 + 0);				\
 	r0 = 0;						\
 	exit;						\
@@ -1296,9 +1300,13 @@ l0_%=:	r0 = 1;						\
 
 SEC("socket")
 __description("map access: value_ptr -= unknown scalar, 2")
-__success __failure_unpriv
-__msg_unpriv("R0 pointer arithmetic of map value goes out of range")
+__success __success_unpriv
 __retval(1)
+#ifdef SPEC_V1
+__xlated_unpriv("r1 &= 7")
+__xlated_unpriv("nospec") /* inserted to prevent `R0 pointer arithmetic of map value goes out of range` */
+__xlated_unpriv("r0 -= r1")
+#endif
 __naked void value_ptr_unknown_scalar_2_2(void)
 {
 	asm volatile ("					\
diff --git a/tools/testing/selftests/bpf/verifier/dead_code.c b/tools/testing/selftests/bpf/verifier/dead_code.c
index ee454327e5c6..77207b498c6f 100644
--- a/tools/testing/selftests/bpf/verifier/dead_code.c
+++ b/tools/testing/selftests/bpf/verifier/dead_code.c
@@ -2,14 +2,13 @@
 	"dead code: start",
 	.insns = {
 	BPF_JMP_IMM(BPF_JA, 0, 0, 2),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_JMP_IMM(BPF_JA, 0, 0, 2),
 	BPF_MOV64_IMM(BPF_REG_0, 7),
 	BPF_JMP_IMM(BPF_JGE, BPF_REG_0, 10, -4),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 7,
 },
diff --git a/tools/testing/selftests/bpf/verifier/jmp32.c b/tools/testing/selftests/bpf/verifier/jmp32.c
index 43776f6f92f4..91d83e9cb148 100644
--- a/tools/testing/selftests/bpf/verifier/jmp32.c
+++ b/tools/testing/selftests/bpf/verifier/jmp32.c
@@ -84,11 +84,10 @@
 	BPF_JMP32_IMM(BPF_JSET, BPF_REG_7, 0x10, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JGE, BPF_REG_7, 0x10, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -149,11 +148,10 @@
 	BPF_JMP32_IMM(BPF_JEQ, BPF_REG_7, 0x10, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JSGE, BPF_REG_7, 0xf, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -214,11 +212,10 @@
 	BPF_JMP32_IMM(BPF_JNE, BPF_REG_7, 0x10, 1),
 	BPF_JMP_IMM(BPF_JNE, BPF_REG_7, 0x10, 1),
 	BPF_EXIT_INSN(),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -283,11 +280,10 @@
 	BPF_JMP32_REG(BPF_JGE, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JGE, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -354,11 +350,10 @@
 	BPF_JMP32_REG(BPF_JGT, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JGT, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -425,11 +420,10 @@
 	BPF_JMP32_REG(BPF_JLE, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JLE, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -496,11 +490,10 @@
 	BPF_JMP32_REG(BPF_JLT, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSLT, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -567,11 +560,10 @@
 	BPF_JMP32_REG(BPF_JSGE, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSGE, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -638,11 +630,10 @@
 	BPF_JMP32_REG(BPF_JSGT, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSGT, BPF_REG_7, -2, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -709,11 +700,10 @@
 	BPF_JMP32_REG(BPF_JSLE, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSLE, BPF_REG_7, 0x7ffffff0, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
@@ -780,11 +770,10 @@
 	BPF_JMP32_REG(BPF_JSLT, BPF_REG_7, BPF_REG_8, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP32_IMM(BPF_JSLT, BPF_REG_7, -1, 1),
+	/* unpriv: nospec (inserted to prevent "R0 invalid mem access 'scalar'") */
 	BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
-	.errstr_unpriv = "R0 invalid mem access 'scalar'",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 	.retval = 2,
 	.flags = F_NEEDS_EFFICIENT_UNALIGNED_ACCESS,
diff --git a/tools/testing/selftests/bpf/verifier/jset.c b/tools/testing/selftests/bpf/verifier/jset.c
index 11fc68da735e..e901eefd774a 100644
--- a/tools/testing/selftests/bpf/verifier/jset.c
+++ b/tools/testing/selftests/bpf/verifier/jset.c
@@ -78,12 +78,11 @@
 	.insns = {
 	BPF_MOV64_IMM(BPF_REG_0, 1),
 	BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 1, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.retval = 1,
 	.result = ACCEPT,
 },
@@ -136,13 +135,12 @@
 	BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, BPF_FUNC_get_prandom_u32),
 	BPF_ALU64_IMM(BPF_OR, BPF_REG_0, 2),
 	BPF_JMP_IMM(BPF_JSET, BPF_REG_0, 3, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_MOV64_IMM(BPF_REG_0, 0),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
 {
@@ -154,16 +152,16 @@
 	BPF_ALU64_IMM(BPF_AND, BPF_REG_1, 0xff),
 	BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0xf0, 3),
 	BPF_JMP_IMM(BPF_JLT, BPF_REG_1, 0x10, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JSET, BPF_REG_1, 0x10, 1),
 	BPF_EXIT_INSN(),
 	BPF_JMP_IMM(BPF_JGE, BPF_REG_1, 0x10, 1),
+	/* unpriv: nospec (inserted to prevent "R9 !read_ok") */
 	BPF_LDX_MEM(BPF_B, BPF_REG_8, BPF_REG_9, 0),
 	BPF_EXIT_INSN(),
 	},
 	.prog_type = BPF_PROG_TYPE_SOCKET_FILTER,
-	.errstr_unpriv = "R9 !read_ok",
-	.result_unpriv = REJECT,
 	.result = ACCEPT,
 },
-- 
cgit v1.2.3


From bee7e3322a2859a80a67077591128323bbc4052f Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Wed, 13 Nov 2024 01:50:18 +0900
Subject: can: bittiming: rename CAN_CTRLMODE_TDC_MASK into
 CAN_CTRLMODE_FD_TDC_MASK

With the introduction of CAN XL, a new CAN_CTRLMODE_XL_TDC_MASK will
be introduced later on. Because CAN_CTRLMODE_TDC_MASK is not part of
the uapi, rename it to CAN_CTRLMODE_FD_TDC_MASK to make it more
explicit that this mask is meant for CAN FD.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20241112165118.586613-10-mailhol.vincent@wanadoo.fr
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/calc_bittiming.c |  2 +-
 drivers/net/can/dev/netlink.c        | 12 ++++++------
 include/linux/can/bittiming.h        |  2 +-
 include/linux/can/dev.h              |  2 +-
 4 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/dev/calc_bittiming.c b/drivers/net/can/dev/calc_bittiming.c
index 3809c148fb88..a94bd67c670c 100644
--- a/drivers/net/can/dev/calc_bittiming.c
+++ b/drivers/net/can/dev/calc_bittiming.c
@@ -179,7 +179,7 @@ void can_calc_tdco(struct can_tdc *tdc, const struct can_tdc_const *tdc_const,
 	if (!tdc_const || !(ctrlmode_supported & CAN_CTRLMODE_TDC_AUTO))
 		return;
 
-	*ctrlmode &= ~CAN_CTRLMODE_TDC_MASK;
+	*ctrlmode &= ~CAN_CTRLMODE_FD_TDC_MASK;
 
 	/* As specified in ISO 11898-1 section 11.3.3 "Transmitter
 	 * delay compensation" (TDC) is only applicable if data BRP is
diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 4ebd5181aea9..08261cfcf6b2 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -67,12 +67,12 @@ static int can_validate(struct nlattr *tb[], struct nlattr *data[],
 
 	if (data[IFLA_CAN_CTRLMODE]) {
 		struct can_ctrlmode *cm = nla_data(data[IFLA_CAN_CTRLMODE]);
-		u32 tdc_flags = cm->flags & CAN_CTRLMODE_TDC_MASK;
+		u32 tdc_flags = cm->flags & CAN_CTRLMODE_FD_TDC_MASK;
 
 		is_can_fd = cm->flags & cm->mask & CAN_CTRLMODE_FD;
 
 		/* CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually exclusive */
-		if (tdc_flags == CAN_CTRLMODE_TDC_MASK)
+		if (tdc_flags == CAN_CTRLMODE_FD_TDC_MASK)
 			return -EOPNOTSUPP;
 		/* If one of the CAN_CTRLMODE_TDC_* flag is set then
 		 * TDC must be set and vice-versa
@@ -230,16 +230,16 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			dev->mtu = CAN_MTU;
 			memset(&priv->fd.data_bittiming, 0,
 			       sizeof(priv->fd.data_bittiming));
-			priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK;
+			priv->ctrlmode &= ~CAN_CTRLMODE_FD_TDC_MASK;
 			memset(&priv->fd.tdc, 0, sizeof(priv->fd.tdc));
 		}
 
-		tdc_mask = cm->mask & CAN_CTRLMODE_TDC_MASK;
+		tdc_mask = cm->mask & CAN_CTRLMODE_FD_TDC_MASK;
 		/* CAN_CTRLMODE_TDC_{AUTO,MANUAL} are mutually
 		 * exclusive: make sure to turn the other one off
 		 */
 		if (tdc_mask)
-			priv->ctrlmode &= cm->flags | ~CAN_CTRLMODE_TDC_MASK;
+			priv->ctrlmode &= cm->flags | ~CAN_CTRLMODE_FD_TDC_MASK;
 	}
 
 	if (data[IFLA_CAN_BITTIMING]) {
@@ -339,7 +339,7 @@ static int can_changelink(struct net_device *dev, struct nlattr *tb[],
 			err = can_tdc_changelink(priv, data[IFLA_CAN_TDC],
 						 extack);
 			if (err) {
-				priv->ctrlmode &= ~CAN_CTRLMODE_TDC_MASK;
+				priv->ctrlmode &= ~CAN_CTRLMODE_FD_TDC_MASK;
 				return err;
 			}
 		} else if (!tdc_mask) {
diff --git a/include/linux/can/bittiming.h b/include/linux/can/bittiming.h
index 9b8a9c39614b..5dfdbb63b1d5 100644
--- a/include/linux/can/bittiming.h
+++ b/include/linux/can/bittiming.h
@@ -14,7 +14,7 @@
 #define CAN_BITRATE_UNSET 0
 #define CAN_BITRATE_UNKNOWN (-1U)
 
-#define CAN_CTRLMODE_TDC_MASK					\
+#define CAN_CTRLMODE_FD_TDC_MASK				\
 	(CAN_CTRLMODE_TDC_AUTO | CAN_CTRLMODE_TDC_MANUAL)
 
 /*
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index 492d23bec7be..e492dfa8a472 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -93,7 +93,7 @@ struct can_priv {
 
 static inline bool can_tdc_is_enabled(const struct can_priv *priv)
 {
-	return !!(priv->ctrlmode & CAN_CTRLMODE_TDC_MASK);
+	return !!(priv->ctrlmode & CAN_CTRLMODE_FD_TDC_MASK);
 }
 
 /*
-- 
cgit v1.2.3


From 23c0dc95bfa86503eed9fa99423fa0bb39a3bcb0 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Wed, 13 Nov 2024 01:50:19 +0900
Subject: can: bittiming: rename can_tdc_is_enabled() into
 can_fd_tdc_is_enabled()

With the introduction of CAN XL, a new can_xl_tdc_is_enabled() helper
function will be introduced later on. Rename can_tdc_is_enabled() into
can_fd_tdc_is_enabled() to make it more explicit that this helper is
meant for CAN FD.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Link: https://patch.msgid.link/20241112165118.586613-11-mailhol.vincent@wanadoo.fr
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
---
 drivers/net/can/dev/netlink.c             | 6 +++---
 drivers/net/can/usb/etas_es58x/es58x_fd.c | 2 +-
 drivers/net/can/xilinx_can.c              | 2 +-
 include/linux/can/dev.h                   | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/can/dev/netlink.c b/drivers/net/can/dev/netlink.c
index 08261cfcf6b2..16b0f326c143 100644
--- a/drivers/net/can/dev/netlink.c
+++ b/drivers/net/can/dev/netlink.c
@@ -144,7 +144,7 @@ static int can_tdc_changelink(struct can_priv *priv, const struct nlattr *nla,
 	const struct can_tdc_const *tdc_const = priv->fd.tdc_const;
 	int err;
 
-	if (!tdc_const || !can_tdc_is_enabled(priv))
+	if (!tdc_const || !can_fd_tdc_is_enabled(priv))
 		return -EOPNOTSUPP;
 
 	err = nla_parse_nested(tb_tdc, IFLA_CAN_TDC_MAX, nla,
@@ -409,7 +409,7 @@ static size_t can_tdc_get_size(const struct net_device *dev)
 		size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCF_MAX */
 	}
 
-	if (can_tdc_is_enabled(priv)) {
+	if (can_fd_tdc_is_enabled(priv)) {
 		if (priv->ctrlmode & CAN_CTRLMODE_TDC_MANUAL ||
 		    priv->fd.do_get_auto_tdcv)
 			size += nla_total_size(sizeof(u32));	/* IFLA_CAN_TDCV */
@@ -490,7 +490,7 @@ static int can_tdc_fill_info(struct sk_buff *skb, const struct net_device *dev)
 	     nla_put_u32(skb, IFLA_CAN_TDC_TDCF_MAX, tdc_const->tdcf_max)))
 		goto err_cancel;
 
-	if (can_tdc_is_enabled(priv)) {
+	if (can_fd_tdc_is_enabled(priv)) {
 		u32 tdcv;
 		int err = -EINVAL;
 
diff --git a/drivers/net/can/usb/etas_es58x/es58x_fd.c b/drivers/net/can/usb/etas_es58x/es58x_fd.c
index d924b053677b..6476add1c105 100644
--- a/drivers/net/can/usb/etas_es58x/es58x_fd.c
+++ b/drivers/net/can/usb/etas_es58x/es58x_fd.c
@@ -429,7 +429,7 @@ static int es58x_fd_enable_channel(struct es58x_priv *priv)
 		es58x_fd_convert_bittiming(&tx_conf_msg.data_bittiming,
 					   &priv->can.fd.data_bittiming);
 
-		if (can_tdc_is_enabled(&priv->can)) {
+		if (can_fd_tdc_is_enabled(&priv->can)) {
 			tx_conf_msg.tdc_enabled = 1;
 			tx_conf_msg.tdco = cpu_to_le16(priv->can.fd.tdc.tdco);
 			tx_conf_msg.tdcf = cpu_to_le16(priv->can.fd.tdc.tdcf);
diff --git a/drivers/net/can/xilinx_can.c b/drivers/net/can/xilinx_can.c
index 3f2e378199ab..81baec8eb1e5 100644
--- a/drivers/net/can/xilinx_can.c
+++ b/drivers/net/can/xilinx_can.c
@@ -515,7 +515,7 @@ static int xcan_set_bittiming(struct net_device *ndev)
 	    priv->devtype.cantype == XAXI_CANFD_2_0) {
 		/* Setting Baud Rate prescaler value in F_BRPR Register */
 		btr0 = dbt->brp - 1;
-		if (can_tdc_is_enabled(&priv->can)) {
+		if (can_fd_tdc_is_enabled(&priv->can)) {
 			if (priv->devtype.cantype == XAXI_CANFD)
 				btr0 |= FIELD_PREP(XCAN_BRPR_TDCO_MASK, priv->can.fd.tdc.tdco) |
 					XCAN_BRPR_TDC_ENABLE;
diff --git a/include/linux/can/dev.h b/include/linux/can/dev.h
index e492dfa8a472..9a92cbe5b2cb 100644
--- a/include/linux/can/dev.h
+++ b/include/linux/can/dev.h
@@ -91,7 +91,7 @@ struct can_priv {
 				   struct can_berr_counter *bec);
 };
 
-static inline bool can_tdc_is_enabled(const struct can_priv *priv)
+static inline bool can_fd_tdc_is_enabled(const struct can_priv *priv)
 {
 	return !!(priv->ctrlmode & CAN_CTRLMODE_FD_TDC_MASK);
 }
-- 
cgit v1.2.3


From a5589313383074c48a1b3751d592a6e084ae0573 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Sun, 1 Jun 2025 00:21:39 +0300
Subject: gpiolib: Remove unused devm_gpio_request()

Remove devm_gpio_request() due to lack of users.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250531212331.3635269-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 Documentation/driver-api/driver-model/devres.rst |  1 -
 drivers/gpio/gpiolib-legacy.c                    | 38 ------------------------
 include/linux/gpio.h                             |  8 -----
 3 files changed, 47 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/driver-model/devres.rst b/Documentation/driver-api/driver-model/devres.rst
index 3d56f94ac2ee..2b36ebde9cec 100644
--- a/Documentation/driver-api/driver-model/devres.rst
+++ b/Documentation/driver-api/driver-model/devres.rst
@@ -275,7 +275,6 @@ GPIO
   devm_gpiod_put()
   devm_gpiod_unhinge()
   devm_gpiochip_add_data()
-  devm_gpio_request()
   devm_gpio_request_one()
 
 I2C
diff --git a/drivers/gpio/gpiolib-legacy.c b/drivers/gpio/gpiolib-legacy.c
index aeae6df8bec9..3bc93ccadb5b 100644
--- a/drivers/gpio/gpiolib-legacy.c
+++ b/drivers/gpio/gpiolib-legacy.c
@@ -85,44 +85,6 @@ static void devm_gpio_release(struct device *dev, void *res)
 	gpio_free(*gpio);
 }
 
-/**
- * devm_gpio_request - request a GPIO for a managed device
- * @dev: device to request the GPIO for
- * @gpio: GPIO to allocate
- * @label: the name of the requested GPIO
- *
- * Except for the extra @dev argument, this function takes the
- * same arguments and performs the same function as gpio_request().
- * GPIOs requested with this function will be automatically freed
- * on driver detach.
- *
- * **DEPRECATED** This function is deprecated and must not be used in new code.
- *
- * Returns:
- * 0 on success, or negative errno on failure.
- */
-int devm_gpio_request(struct device *dev, unsigned gpio, const char *label)
-{
-	unsigned *dr;
-	int rc;
-
-	dr = devres_alloc(devm_gpio_release, sizeof(unsigned), GFP_KERNEL);
-	if (!dr)
-		return -ENOMEM;
-
-	rc = gpio_request(gpio, label);
-	if (rc) {
-		devres_free(dr);
-		return rc;
-	}
-
-	*dr = gpio;
-	devres_add(dev, dr);
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(devm_gpio_request);
-
 /**
  * devm_gpio_request_one - request a single GPIO with initial setup
  * @dev: device to request for
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index c1ec62c11ed3..61e9f43c082a 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -110,7 +110,6 @@ static inline int gpio_to_irq(unsigned gpio)
 
 int gpio_request_one(unsigned gpio, unsigned long flags, const char *label);
 
-int devm_gpio_request(struct device *dev, unsigned gpio, const char *label);
 int devm_gpio_request_one(struct device *dev, unsigned gpio,
 			  unsigned long flags, const char *label);
 
@@ -188,13 +187,6 @@ static inline int gpio_to_irq(unsigned gpio)
 	return -EINVAL;
 }
 
-static inline int devm_gpio_request(struct device *dev, unsigned gpio,
-				    const char *label)
-{
-	WARN_ON(1);
-	return -EINVAL;
-}
-
 static inline int devm_gpio_request_one(struct device *dev, unsigned gpio,
 					unsigned long flags, const char *label)
 {
-- 
cgit v1.2.3


From 9b4d4c952e28f97c5e653c8b9453690f7e63cc5a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Sat, 31 May 2025 22:55:43 +0300
Subject: gpio: Remove unused 'struct gpio' definition

There is no user for the legacy 'struct gpio', remove it for good.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250531195801.3632110-2-andriy.shevchenko@linux.intel.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 include/linux/gpio.h | 12 ------------
 1 file changed, 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 61e9f43c082a..8697ab817898 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -21,18 +21,6 @@ struct device;
 #define GPIOF_OUT_INIT_LOW	((0 << 0) | (0 << 1))
 #define GPIOF_OUT_INIT_HIGH	((0 << 0) | (1 << 1))
 
-/**
- * struct gpio - a structure describing a GPIO with configuration
- * @gpio:	the GPIO number
- * @flags:	GPIO configuration as specified by GPIOF_*
- * @label:	a literal description string of this GPIO
- */
-struct gpio {
-	unsigned	gpio;
-	unsigned long	flags;
-	const char	*label;
-};
-
 #ifdef CONFIG_GPIOLIB
 
 #include <linux/gpio/consumer.h>
-- 
cgit v1.2.3


From 6595ea2761df191c2ec500d5f54b57592b969f5c Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Sat, 31 May 2025 22:55:44 +0300
Subject: gpiolib: Move GPIO_DYNAMIC_* constants to its only user

There is no need to export GPIO_DYNAMIC_* constants, especially via
legacy header which is subject to remove. Move the mentioned constants
to its only user, i.e. gpiolib.c.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250531195801.3632110-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c | 13 +++++++++++++
 include/linux/gpio.h   | 13 -------------
 2 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index fdafa0df1b43..5b0b4fc97543 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -74,6 +74,19 @@ static const struct bus_type gpio_bus_type = {
 	.match = gpio_bus_match,
 };
 
+/*
+ * At the end we want all GPIOs to be dynamically allocated from 0.
+ * However, some legacy drivers still perform fixed allocation.
+ * Until they are all fixed, leave 0-512 space for them.
+ */
+#define GPIO_DYNAMIC_BASE	512
+/*
+ * Define the maximum of the possible GPIO in the global numberspace.
+ * While the GPIO base and numbers are positive, we limit it with signed
+ * maximum as a lot of code is using negative values for special cases.
+ */
+#define GPIO_DYNAMIC_MAX	INT_MAX
+
 /*
  * Number of GPIOs to use for the fast path in set array
  */
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index 8697ab817898..ff99ed76fdc3 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -45,19 +45,6 @@ static inline bool gpio_is_valid(int number)
  * extra memory (for code and for per-GPIO table entries).
  */
 
-/*
- * At the end we want all GPIOs to be dynamically allocated from 0.
- * However, some legacy drivers still perform fixed allocation.
- * Until they are all fixed, leave 0-512 space for them.
- */
-#define GPIO_DYNAMIC_BASE	512
-/*
- * Define the maximum of the possible GPIO in the global numberspace.
- * While the GPIO base and numbers are positive, we limit it with signed
- * maximum as a lot of code is using negative values for special cases.
- */
-#define GPIO_DYNAMIC_MAX	INT_MAX
-
 /* Always use the library code for GPIO management calls,
  * or when sleeping may be involved.
  */
-- 
cgit v1.2.3


From d209f6e122950d9b6f329f3538b785dd709001e5 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Mon, 2 Jun 2025 07:58:54 -0400
Subject: filelock: add new locks_wake_up_waiter() helper

Currently the function that does this takes a struct file_lock, but
__locks_wake_up_blocks() deals with both locks and leases. Currently
this works because both file_lock and file_lease have the file_lock_core
at the beginning of the struct, but it's fragile to rely on that.

Add a new locks_wake_up_waiter() function and call that from
__locks_wake_up_blocks().

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/20250602-filelock-6-16-v1-1-7da5b2c930fd@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/locks.c               | 2 +-
 include/linux/filelock.h | 7 ++++++-
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/locks.c b/fs/locks.c
index 1619cddfa7a4..f96024feab17 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -712,7 +712,7 @@ static void __locks_wake_up_blocks(struct file_lock_core *blocker)
 		    fl->fl_lmops && fl->fl_lmops->lm_notify)
 			fl->fl_lmops->lm_notify(fl);
 		else
-			locks_wake_up(fl);
+			locks_wake_up_waiter(waiter);
 
 		/*
 		 * The setting of flc_blocker to NULL marks the "done"
diff --git a/include/linux/filelock.h b/include/linux/filelock.h
index c412ded9171e..c2ce8ba05d06 100644
--- a/include/linux/filelock.h
+++ b/include/linux/filelock.h
@@ -175,9 +175,14 @@ static inline bool lock_is_write(struct file_lock *fl)
 	return fl->c.flc_type == F_WRLCK;
 }
 
+static inline void locks_wake_up_waiter(struct file_lock_core *flc)
+{
+	wake_up(&flc->flc_wait);
+}
+
 static inline void locks_wake_up(struct file_lock *fl)
 {
-	wake_up(&fl->c.flc_wait);
+	locks_wake_up_waiter(&fl->c);
 }
 
 static inline bool locks_can_async_lock(const struct file_operations *fops)
-- 
cgit v1.2.3


From 33877220b8641b4cde474a4229ea92c0e3637883 Mon Sep 17 00:00:00 2001
From: Tasos Sahanidis <tasos@tasossah.com>
Date: Mon, 19 May 2025 11:56:55 +0300
Subject: ata: libata-acpi: Do not assume 40 wire cable if no devices are
 enabled

On at least an ASRock 990FX Extreme 4 with a VIA VT6330, the devices
have not yet been enabled by the first time ata_acpi_cbl_80wire() is
called. This means that the ata_for_each_dev loop is never entered,
and a 40 wire cable is assumed.

The VIA controller on this board does not report the cable in the PCI
config space, thus having to fall back to ACPI even though no SATA
bridge is present.

The _GTM values are correctly reported by the firmware through ACPI,
which has already set up faster transfer modes, but due to the above
the controller is forced down to a maximum of UDMA/33.

Resolve this by modifying ata_acpi_cbl_80wire() to directly return the
cable type. First, an unknown cable is assumed which preserves the mode
set by the firmware, and then on subsequent calls when the devices have
been enabled, an 80 wire cable is correctly detected.

Since the function now directly returns the cable type, it is renamed
to ata_acpi_cbl_pata_type().

Signed-off-by: Tasos Sahanidis <tasos@tasossah.com>
Link: https://lore.kernel.org/r/20250519085945.1399466-1-tasos@tasossah.com
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-acpi.c | 24 ++++++++++++++++--------
 drivers/ata/pata_via.c    |  6 ++----
 include/linux/libata.h    |  7 +++----
 3 files changed, 21 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-acpi.c b/drivers/ata/libata-acpi.c
index b7f0bf795521..f2140fc06ba0 100644
--- a/drivers/ata/libata-acpi.c
+++ b/drivers/ata/libata-acpi.c
@@ -514,15 +514,19 @@ unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 EXPORT_SYMBOL_GPL(ata_acpi_gtm_xfermask);
 
 /**
- * ata_acpi_cbl_80wire		-	Check for 80 wire cable
+ * ata_acpi_cbl_pata_type - Return PATA cable type
  * @ap: Port to check
- * @gtm: GTM data to use
  *
- * Return 1 if the @gtm indicates the BIOS selected an 80wire mode.
+ * Return ATA_CBL_PATA* according to the transfer mode selected by BIOS
  */
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
+int ata_acpi_cbl_pata_type(struct ata_port *ap)
 {
 	struct ata_device *dev;
+	int ret = ATA_CBL_PATA_UNK;
+	const struct ata_acpi_gtm *gtm = ata_acpi_init_gtm(ap);
+
+	if (!gtm)
+		return ATA_CBL_PATA40;
 
 	ata_for_each_dev(dev, &ap->link, ENABLED) {
 		unsigned int xfer_mask, udma_mask;
@@ -530,13 +534,17 @@ int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm)
 		xfer_mask = ata_acpi_gtm_xfermask(dev, gtm);
 		ata_unpack_xfermask(xfer_mask, NULL, NULL, &udma_mask);
 
-		if (udma_mask & ~ATA_UDMA_MASK_40C)
-			return 1;
+		ret = ATA_CBL_PATA40;
+
+		if (udma_mask & ~ATA_UDMA_MASK_40C) {
+			ret = ATA_CBL_PATA80;
+			break;
+		}
 	}
 
-	return 0;
+	return ret;
 }
-EXPORT_SYMBOL_GPL(ata_acpi_cbl_80wire);
+EXPORT_SYMBOL_GPL(ata_acpi_cbl_pata_type);
 
 static void ata_acpi_gtf_to_tf(struct ata_device *dev,
 			       const struct ata_acpi_gtf *gtf,
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index d82728a01832..bb80e7800dcb 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -201,11 +201,9 @@ static int via_cable_detect(struct ata_port *ap) {
 	   two drives */
 	if (ata66 & (0x10100000 >> (16 * ap->port_no)))
 		return ATA_CBL_PATA80;
+
 	/* Check with ACPI so we can spot BIOS reported SATA bridges */
-	if (ata_acpi_init_gtm(ap) &&
-	    ata_acpi_cbl_80wire(ap, ata_acpi_init_gtm(ap)))
-		return ATA_CBL_PATA80;
-	return ATA_CBL_PATA40;
+	return ata_acpi_cbl_pata_type(ap);
 }
 
 static int via_pre_reset(struct ata_link *link, unsigned long deadline)
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 31be45fd47a6..1e5aec839041 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1352,7 +1352,7 @@ int ata_acpi_stm(struct ata_port *ap, const struct ata_acpi_gtm *stm);
 int ata_acpi_gtm(struct ata_port *ap, struct ata_acpi_gtm *stm);
 unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 				   const struct ata_acpi_gtm *gtm);
-int ata_acpi_cbl_80wire(struct ata_port *ap, const struct ata_acpi_gtm *gtm);
+int ata_acpi_cbl_pata_type(struct ata_port *ap);
 #else
 static inline const struct ata_acpi_gtm *ata_acpi_init_gtm(struct ata_port *ap)
 {
@@ -1377,10 +1377,9 @@ static inline unsigned int ata_acpi_gtm_xfermask(struct ata_device *dev,
 	return 0;
 }
 
-static inline int ata_acpi_cbl_80wire(struct ata_port *ap,
-				      const struct ata_acpi_gtm *gtm)
+static inline int ata_acpi_cbl_pata_type(struct ata_port *ap)
 {
-	return 0;
+	return ATA_CBL_PATA40;
 }
 #endif
 
-- 
cgit v1.2.3


From 5943c611c47c9444e834555c867dec744158b7ad Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 22 Feb 2025 16:04:47 -0500
Subject: procfs: kill ->proc_dops

It has two possible values - one for "forced lookup" entries, another
for the normal ones.  We'd be better off with that as an explicit
flag anyway and in addition to that it opens some fun possibilities
with ->d_op and ->d_flags handling.

[moved PROC_ENTRY_FORCE_LOOKUP to include/linux/proc_fs.h, switched it
to an unused bit - there was a conflict]

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/proc/generic.c       | 8 +++++---
 fs/proc/internal.h      | 3 +--
 include/linux/proc_fs.h | 2 ++
 3 files changed, 8 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index a3e22803cddf..38ce45ce0eb6 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -254,7 +254,10 @@ struct dentry *proc_lookup_de(struct inode *dir, struct dentry *dentry,
 		inode = proc_get_inode(dir->i_sb, de);
 		if (!inode)
 			return ERR_PTR(-ENOMEM);
-		d_set_d_op(dentry, de->proc_dops);
+		if (de->flags & PROC_ENTRY_FORCE_LOOKUP)
+			d_set_d_op(dentry, &proc_net_dentry_ops);
+		else
+			d_set_d_op(dentry, &proc_misc_dentry_ops);
 		return d_splice_alias(inode, dentry);
 	}
 	read_unlock(&proc_subdir_lock);
@@ -448,9 +451,8 @@ static struct proc_dir_entry *__proc_create(struct proc_dir_entry **parent,
 	INIT_LIST_HEAD(&ent->pde_openers);
 	proc_set_user(ent, (*parent)->uid, (*parent)->gid);
 
-	ent->proc_dops = &proc_misc_dentry_ops;
 	/* Revalidate everything under /proc/${pid}/net */
-	if ((*parent)->proc_dops == &proc_net_dentry_ops)
+	if ((*parent)->flags & PROC_ENTRY_FORCE_LOOKUP)
 		pde_force_lookup(ent);
 
 out:
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 96122e91c645..a4054916f6da 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -44,7 +44,6 @@ struct proc_dir_entry {
 		const struct proc_ops *proc_ops;
 		const struct file_operations *proc_dir_ops;
 	};
-	const struct dentry_operations *proc_dops;
 	union {
 		const struct seq_operations *seq_ops;
 		int (*single_show)(struct seq_file *, void *);
@@ -403,7 +402,7 @@ extern const struct dentry_operations proc_net_dentry_ops;
 static inline void pde_force_lookup(struct proc_dir_entry *pde)
 {
 	/* /proc/net/ entries can be changed under us by setns(CLONE_NEWNET) */
-	pde->proc_dops = &proc_net_dentry_ops;
+	pde->flags |= PROC_ENTRY_FORCE_LOOKUP;
 }
 
 /*
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index ea62201c74c4..de1d24f19f76 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -27,6 +27,8 @@ enum {
 
 	PROC_ENTRY_proc_read_iter	= 1U << 1,
 	PROC_ENTRY_proc_compat_ioctl	= 1U << 2,
+
+	PROC_ENTRY_FORCE_LOOKUP		= 1U << 7,
 };
 
 struct proc_ops {
-- 
cgit v1.2.3


From 790fa81b8c43cda9fe25c1b564d0afe3ddeeb370 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 24 Feb 2025 12:46:49 -0500
Subject: new helper: d_splice_alias_ops()

Uses of d_set_d_op() on live dentry can be very dangerous; it is going
to be withdrawn and replaced with saner things.

The best way for a filesystem is to have the default dentry_operations
set at mount time and be done with that - __d_alloc() will use that.

Currently there are two cases when d_set_d_op() is used on a live dentry -
one is procfs, which has several genuinely different dentry_operations
instances (different ->d_revalidate(), etc.) and another is
simple_lookup(), where we would be better off without overriding ->d_op.

For procfs we have d_set_d_op() calls followed by d_splice_alias();
provide a new helper (d_splice_alias_ops(inode, dentry, d_ops)) that would
combine those two, and do the d_set_d_op() part while under ->d_lock.
That eliminates one of the places where ->d_flags had been modified
without holding ->d_lock; current behaviour is not racy, but the reasons
for that are far too brittle.  Better move to uniform locking rules and
simpler proof of correctness...

The next commit will convert procfs to use of that helper; it is not
exported and won't be until somebody comes up with convincing modular
user for it.

Again, the best approach is to have default ->d_op and let __d_alloc()
do the right thing; filesystem _may_ need non-uniform ->d_op (procfs
does), but there'd better be good reasons for that.

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c            | 63 ++++++++++++++++++++++++++++----------------------
 include/linux/dcache.h |  3 +++
 2 files changed, 39 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/fs/dcache.c b/fs/dcache.c
index 3c3cfb345233..bf550d438e40 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2667,7 +2667,8 @@ EXPORT_SYMBOL(__d_lookup_unhash_wake);
 
 /* inode->i_lock held if inode is non-NULL */
 
-static inline void __d_add(struct dentry *dentry, struct inode *inode)
+static inline void __d_add(struct dentry *dentry, struct inode *inode,
+			   const struct dentry_operations *ops)
 {
 	wait_queue_head_t *d_wait;
 	struct inode *dir = NULL;
@@ -2678,6 +2679,8 @@ static inline void __d_add(struct dentry *dentry, struct inode *inode)
 		n = start_dir_add(dir);
 		d_wait = __d_lookup_unhash(dentry);
 	}
+	if (unlikely(ops))
+		d_set_d_op(dentry, ops);
 	if (inode) {
 		unsigned add_flags = d_flags_for_inode(inode);
 		hlist_add_head(&dentry->d_u.d_alias, &inode->i_dentry);
@@ -2709,7 +2712,7 @@ void d_add(struct dentry *entry, struct inode *inode)
 		security_d_instantiate(entry, inode);
 		spin_lock(&inode->i_lock);
 	}
-	__d_add(entry, inode);
+	__d_add(entry, inode, NULL);
 }
 EXPORT_SYMBOL(d_add);
 
@@ -2961,30 +2964,8 @@ out_err:
 	return ret;
 }
 
-/**
- * d_splice_alias - splice a disconnected dentry into the tree if one exists
- * @inode:  the inode which may have a disconnected dentry
- * @dentry: a negative dentry which we want to point to the inode.
- *
- * If inode is a directory and has an IS_ROOT alias, then d_move that in
- * place of the given dentry and return it, else simply d_add the inode
- * to the dentry and return NULL.
- *
- * If a non-IS_ROOT directory is found, the filesystem is corrupt, and
- * we should error out: directories can't have multiple aliases.
- *
- * This is needed in the lookup routine of any filesystem that is exportable
- * (via knfsd) so that we can build dcache paths to directories effectively.
- *
- * If a dentry was found and moved, then it is returned.  Otherwise NULL
- * is returned.  This matches the expected return value of ->lookup.
- *
- * Cluster filesystems may call this function with a negative, hashed dentry.
- * In that case, we know that the inode will be a regular file, and also this
- * will only occur during atomic_open. So we need to check for the dentry
- * being already hashed only in the final case.
- */
-struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
+struct dentry *d_splice_alias_ops(struct inode *inode, struct dentry *dentry,
+				  const struct dentry_operations *ops)
 {
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
@@ -3030,9 +3011,37 @@ struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
 		}
 	}
 out:
-	__d_add(dentry, inode);
+	__d_add(dentry, inode, ops);
 	return NULL;
 }
+
+/**
+ * d_splice_alias - splice a disconnected dentry into the tree if one exists
+ * @inode:  the inode which may have a disconnected dentry
+ * @dentry: a negative dentry which we want to point to the inode.
+ *
+ * If inode is a directory and has an IS_ROOT alias, then d_move that in
+ * place of the given dentry and return it, else simply d_add the inode
+ * to the dentry and return NULL.
+ *
+ * If a non-IS_ROOT directory is found, the filesystem is corrupt, and
+ * we should error out: directories can't have multiple aliases.
+ *
+ * This is needed in the lookup routine of any filesystem that is exportable
+ * (via knfsd) so that we can build dcache paths to directories effectively.
+ *
+ * If a dentry was found and moved, then it is returned.  Otherwise NULL
+ * is returned.  This matches the expected return value of ->lookup.
+ *
+ * Cluster filesystems may call this function with a negative, hashed dentry.
+ * In that case, we know that the inode will be a regular file, and also this
+ * will only occur during atomic_open. So we need to check for the dentry
+ * being already hashed only in the final case.
+ */
+struct dentry *d_splice_alias(struct inode *inode, struct dentry *dentry)
+{
+	return d_splice_alias_ops(inode, dentry, NULL);
+}
 EXPORT_SYMBOL(d_splice_alias);
 
 /*
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index e29823c701ac..1993e6704552 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -245,6 +245,9 @@ extern struct dentry * d_alloc_anon(struct super_block *);
 extern struct dentry * d_alloc_parallel(struct dentry *, const struct qstr *,
 					wait_queue_head_t *);
 extern struct dentry * d_splice_alias(struct inode *, struct dentry *);
+/* weird procfs mess; *NOT* exported */
+extern struct dentry * d_splice_alias_ops(struct inode *, struct dentry *,
+					  const struct dentry_operations *);
 extern struct dentry * d_add_ci(struct dentry *, struct inode *, struct qstr *);
 extern bool d_same_name(const struct dentry *dentry, const struct dentry *parent,
 			const struct qstr *name);
-- 
cgit v1.2.3


From 05fb0e666495cda068c068a681ecbbf8e57324d0 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 23 Feb 2025 19:39:47 -0500
Subject: new helper: set_default_d_op()

... to be used instead of manually assigning to ->s_d_op.
All in-tree filesystem converted (and field itself is renamed,
so any out-of-tree ones in need of conversion will be caught
by compiler).

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/porting.rst |  7 +++++++
 fs/9p/vfs_super.c                     |  4 ++--
 fs/adfs/super.c                       |  2 +-
 fs/affs/super.c                       |  4 ++--
 fs/afs/super.c                        |  4 ++--
 fs/autofs/inode.c                     |  2 +-
 fs/btrfs/super.c                      |  2 +-
 fs/ceph/super.c                       |  2 +-
 fs/coda/inode.c                       |  2 +-
 fs/configfs/mount.c                   |  2 +-
 fs/dcache.c                           | 10 ++++++++--
 fs/debugfs/inode.c                    |  2 +-
 fs/devpts/inode.c                     |  2 +-
 fs/ecryptfs/main.c                    |  2 +-
 fs/efivarfs/super.c                   |  2 +-
 fs/exfat/super.c                      |  4 ++--
 fs/fat/namei_msdos.c                  |  2 +-
 fs/fat/namei_vfat.c                   |  4 ++--
 fs/fuse/inode.c                       |  4 ++--
 fs/gfs2/ops_fstype.c                  |  2 +-
 fs/hfs/super.c                        |  2 +-
 fs/hfsplus/super.c                    |  2 +-
 fs/hostfs/hostfs_kern.c               |  2 +-
 fs/hpfs/super.c                       |  2 +-
 fs/isofs/inode.c                      |  2 +-
 fs/jfs/super.c                        |  2 +-
 fs/kernfs/mount.c                     |  2 +-
 fs/libfs.c                            | 16 ++++++++--------
 fs/nfs/super.c                        |  2 +-
 fs/ntfs3/super.c                      |  3 ++-
 fs/ocfs2/super.c                      |  2 +-
 fs/orangefs/super.c                   |  2 +-
 fs/overlayfs/super.c                  |  2 +-
 fs/smb/client/cifsfs.c                |  4 ++--
 fs/tracefs/inode.c                    |  2 +-
 fs/vboxsf/super.c                     |  2 +-
 include/linux/dcache.h                |  2 ++
 include/linux/fs.h                    |  2 +-
 mm/shmem.c                            |  2 +-
 net/sunrpc/rpc_pipe.c                 |  2 +-
 40 files changed, 69 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 3616d7161dab..b16139e91942 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1249,3 +1249,10 @@ Using try_lookup_noperm() will require linux/namei.h to be included.
 
 Calling conventions for ->d_automount() have changed; we should *not* grab
 an extra reference to new mount - it should be returned with refcount 1.
+
+---
+
+**mandatory**
+
+If your filesystem sets the default dentry_operations, use set_default_d_op()
+rather than manually setting sb->s_d_op.
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index 489db161abc9..5c3dc3efb909 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -135,9 +135,9 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 		goto release_sb;
 
 	if (v9ses->cache & (CACHE_META|CACHE_LOOSE))
-		sb->s_d_op = &v9fs_cached_dentry_operations;
+		set_default_d_op(sb, &v9fs_cached_dentry_operations);
 	else
-		sb->s_d_op = &v9fs_dentry_operations;
+		set_default_d_op(sb, &v9fs_dentry_operations);
 
 	inode = v9fs_get_new_inode_from_fid(v9ses, fid, sb);
 	if (IS_ERR(inode)) {
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 017c48a80203..fdccdbbfc213 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -397,7 +397,7 @@ static int adfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (asb->s_ftsuffix)
 		asb->s_namelen += 4;
 
-	sb->s_d_op = &adfs_dentry_operations;
+	set_default_d_op(sb, &adfs_dentry_operations);
 	root = adfs_iget(sb, &root_obj);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
diff --git a/fs/affs/super.c b/fs/affs/super.c
index 2fa40337776d..44f8aa883100 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -500,9 +500,9 @@ got_root:
 		return PTR_ERR(root_inode);
 
 	if (affs_test_opt(AFFS_SB(sb)->s_flags, SF_INTL))
-		sb->s_d_op = &affs_intl_dentry_operations;
+		set_default_d_op(sb, &affs_intl_dentry_operations);
 	else
-		sb->s_d_op = &affs_dentry_operations;
+		set_default_d_op(sb, &affs_dentry_operations);
 
 	sb->s_root = d_make_root(root_inode);
 	if (!sb->s_root) {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index 25b306db6992..da407f2d6f0d 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -483,9 +483,9 @@ static int afs_fill_super(struct super_block *sb, struct afs_fs_context *ctx)
 		goto error;
 
 	if (as->dyn_root) {
-		sb->s_d_op = &afs_dynroot_dentry_operations;
+		set_default_d_op(sb, &afs_dynroot_dentry_operations);
 	} else {
-		sb->s_d_op = &afs_fs_dentry_operations;
+		set_default_d_op(sb, &afs_fs_dentry_operations);
 		rcu_assign_pointer(as->volume->sb, sb);
 	}
 
diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
index ee2edccaef70..f5c16ffba013 100644
--- a/fs/autofs/inode.c
+++ b/fs/autofs/inode.c
@@ -311,7 +311,7 @@ static int autofs_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_blocksize_bits = 10;
 	s->s_magic = AUTOFS_SUPER_MAGIC;
 	s->s_op = &autofs_sops;
-	s->s_d_op = &autofs_dentry_operations;
+	set_default_d_op(s, &autofs_dentry_operations);
 	s->s_time_gran = 1;
 
 	/*
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index a0c65adce1ab..ad75d9f8f404 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -950,7 +950,7 @@ static int btrfs_fill_super(struct super_block *sb,
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_magic = BTRFS_SUPER_MAGIC;
 	sb->s_op = &btrfs_super_ops;
-	sb->s_d_op = &btrfs_dentry_operations;
+	set_default_d_op(sb, &btrfs_dentry_operations);
 	sb->s_export_op = &btrfs_export_ops;
 #ifdef CONFIG_FS_VERITY
 	sb->s_vop = &btrfs_verityops;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 2b8438d8a324..c3eb651862c5 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -1219,7 +1219,7 @@ static int ceph_set_super(struct super_block *s, struct fs_context *fc)
 	fsc->max_file_size = 1ULL << 40; /* temp value until we get mdsmap */
 
 	s->s_op = &ceph_super_ops;
-	s->s_d_op = &ceph_dentry_ops;
+	set_default_d_op(s, &ceph_dentry_ops);
 	s->s_export_op = &ceph_export_ops;
 
 	s->s_time_gran = 1;
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 6896fce122e1..08450d006016 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -230,7 +230,7 @@ static int coda_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_blocksize_bits = 12;
 	sb->s_magic = CODA_SUPER_MAGIC;
 	sb->s_op = &coda_super_operations;
-	sb->s_d_op = &coda_dentry_operations;
+	set_default_d_op(sb, &coda_dentry_operations);
 	sb->s_time_gran = 1;
 	sb->s_time_min = S64_MIN;
 	sb->s_time_max = S64_MAX;
diff --git a/fs/configfs/mount.c b/fs/configfs/mount.c
index c2d820063ec4..20412eaca972 100644
--- a/fs/configfs/mount.c
+++ b/fs/configfs/mount.c
@@ -92,7 +92,7 @@ static int configfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	configfs_root_group.cg_item.ci_dentry = root;
 	root->d_fsdata = &configfs_root;
 	sb->s_root = root;
-	sb->s_d_op = &configfs_dentry_ops; /* the rest get that */
+	set_default_d_op(sb, &configfs_dentry_ops); /* the rest get that */
 	return 0;
 }
 
diff --git a/fs/dcache.c b/fs/dcache.c
index bf550d438e40..2ed875558ccc 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1738,7 +1738,7 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	INIT_HLIST_HEAD(&dentry->d_children);
 	INIT_HLIST_NODE(&dentry->d_u.d_alias);
 	INIT_HLIST_NODE(&dentry->d_sib);
-	d_set_d_op(dentry, dentry->d_sb->s_d_op);
+	d_set_d_op(dentry, dentry->d_sb->__s_d_op);
 
 	if (dentry->d_op && dentry->d_op->d_init) {
 		err = dentry->d_op->d_init(dentry);
@@ -1821,7 +1821,7 @@ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
 	struct dentry *dentry = __d_alloc(sb, name);
 	if (likely(dentry)) {
 		dentry->d_flags |= DCACHE_NORCU;
-		if (!sb->s_d_op)
+		if (!dentry->d_op)
 			d_set_d_op(dentry, &anon_ops);
 	}
 	return dentry;
@@ -1867,6 +1867,12 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 }
 EXPORT_SYMBOL(d_set_d_op);
 
+void set_default_d_op(struct super_block *s, const struct dentry_operations *ops)
+{
+	s->__s_d_op = ops;
+}
+EXPORT_SYMBOL(set_default_d_op);
+
 static unsigned d_flags_for_inode(struct inode *inode)
 {
 	unsigned add_flags = DCACHE_REGULAR_TYPE;
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 30c4944e1862..29c5ec382342 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -273,7 +273,7 @@ static int debugfs_fill_super(struct super_block *sb, struct fs_context *fc)
 		return err;
 
 	sb->s_op = &debugfs_super_operations;
-	sb->s_d_op = &debugfs_dops;
+	set_default_d_op(sb, &debugfs_dops);
 
 	debugfs_apply_options(sb);
 
diff --git a/fs/devpts/inode.c b/fs/devpts/inode.c
index 9c20d78e41f6..fd17992ee298 100644
--- a/fs/devpts/inode.c
+++ b/fs/devpts/inode.c
@@ -381,7 +381,7 @@ static int devpts_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_blocksize_bits = 10;
 	s->s_magic = DEVPTS_SUPER_MAGIC;
 	s->s_op = &devpts_sops;
-	s->s_d_op = &simple_dentry_operations;
+	set_default_d_op(s, &simple_dentry_operations);
 	s->s_time_gran = 1;
 	fsi->sb = s;
 
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 8dd1d7189c3b..45f9ca4465da 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -471,7 +471,7 @@ static int ecryptfs_get_tree(struct fs_context *fc)
 	sbi = NULL;
 	s->s_op = &ecryptfs_sops;
 	s->s_xattr = ecryptfs_xattr_handlers;
-	s->s_d_op = &ecryptfs_dops;
+	set_default_d_op(s, &ecryptfs_dops);
 
 	err = "Reading sb failed";
 	rc = kern_path(fc->source, LOOKUP_FOLLOW | LOOKUP_DIRECTORY, &path);
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index c900d98bf494..f76d8dfa646b 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -350,7 +350,7 @@ static int efivarfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_blocksize_bits    = PAGE_SHIFT;
 	sb->s_magic             = EFIVARFS_MAGIC;
 	sb->s_op                = &efivarfs_ops;
-	sb->s_d_op		= &efivarfs_d_ops;
+	set_default_d_op(sb, &efivarfs_d_ops);
 	sb->s_time_gran         = 1;
 
 	if (!efivar_supports_writes())
diff --git a/fs/exfat/super.c b/fs/exfat/super.c
index 7ed858937d45..ea5c1334a214 100644
--- a/fs/exfat/super.c
+++ b/fs/exfat/super.c
@@ -667,9 +667,9 @@ static int exfat_fill_super(struct super_block *sb, struct fs_context *fc)
 	}
 
 	if (sbi->options.utf8)
-		sb->s_d_op = &exfat_utf8_dentry_ops;
+		set_default_d_op(sb, &exfat_utf8_dentry_ops);
 	else
-		sb->s_d_op = &exfat_dentry_ops;
+		set_default_d_op(sb, &exfat_dentry_ops);
 
 	root_inode = new_inode(sb);
 	if (!root_inode) {
diff --git a/fs/fat/namei_msdos.c b/fs/fat/namei_msdos.c
index 23e9b9371ec3..0b920ee40a7f 100644
--- a/fs/fat/namei_msdos.c
+++ b/fs/fat/namei_msdos.c
@@ -646,7 +646,7 @@ static const struct inode_operations msdos_dir_inode_operations = {
 static void setup(struct super_block *sb)
 {
 	MSDOS_SB(sb)->dir_ops = &msdos_dir_inode_operations;
-	sb->s_d_op = &msdos_dentry_operations;
+	set_default_d_op(sb, &msdos_dentry_operations);
 	sb->s_flags |= SB_NOATIME;
 }
 
diff --git a/fs/fat/namei_vfat.c b/fs/fat/namei_vfat.c
index dd910edd2404..5dbc4cbb8fce 100644
--- a/fs/fat/namei_vfat.c
+++ b/fs/fat/namei_vfat.c
@@ -1187,9 +1187,9 @@ static void setup(struct super_block *sb)
 {
 	MSDOS_SB(sb)->dir_ops = &vfat_dir_inode_operations;
 	if (MSDOS_SB(sb)->options.name_check != 's')
-		sb->s_d_op = &vfat_ci_dentry_ops;
+		set_default_d_op(sb, &vfat_ci_dentry_ops);
 	else
-		sb->s_d_op = &vfat_dentry_ops;
+		set_default_d_op(sb, &vfat_dentry_ops);
 }
 
 static int vfat_fill_super(struct super_block *sb, struct fs_context *fc)
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index eb6177508598..0dd65c0e9e29 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -1715,7 +1715,7 @@ static int fuse_fill_super_submount(struct super_block *sb,
 	fi = get_fuse_inode(root);
 	fi->nlookup--;
 
-	sb->s_d_op = &fuse_dentry_operations;
+	set_default_d_op(sb, &fuse_dentry_operations);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root)
 		return -ENOMEM;
@@ -1850,7 +1850,7 @@ int fuse_fill_super_common(struct super_block *sb, struct fuse_fs_context *ctx)
 
 	err = -ENOMEM;
 	root = fuse_get_root_inode(sb, ctx->rootmode);
-	sb->s_d_op = &fuse_dentry_operations;
+	set_default_d_op(sb, &fuse_dentry_operations);
 	root_dentry = d_make_root(root);
 	if (!root_dentry)
 		goto err_dev_free;
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index 85c491fcf1a3..b568767dba46 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -1145,7 +1145,7 @@ static int gfs2_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_magic = GFS2_MAGIC;
 	sb->s_op = &gfs2_super_ops;
 
-	sb->s_d_op = &gfs2_dops;
+	set_default_d_op(sb, &gfs2_dops);
 	sb->s_export_op = &gfs2_export_ops;
 	sb->s_qcop = &gfs2_quotactl_ops;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index fe09c2093a93..388a318297ec 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -365,7 +365,7 @@ static int hfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (!root_inode)
 		goto bail_no_root;
 
-	sb->s_d_op = &hfs_dentry_operations;
+	set_default_d_op(sb, &hfs_dentry_operations);
 	res = -ENOMEM;
 	sb->s_root = d_make_root(root_inode);
 	if (!sb->s_root)
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index 948b8aaee33e..0caf7aa1c249 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -508,7 +508,7 @@ static int hfsplus_fill_super(struct super_block *sb, struct fs_context *fc)
 		goto out_put_alloc_file;
 	}
 
-	sb->s_d_op = &hfsplus_dentry_operations;
+	set_default_d_op(sb, &hfsplus_dentry_operations);
 	sb->s_root = d_make_root(root);
 	if (!sb->s_root) {
 		err = -ENOMEM;
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 702c41317589..1c0f5038e19c 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -933,7 +933,7 @@ static int hostfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_blocksize_bits = 10;
 	sb->s_magic = HOSTFS_SUPER_MAGIC;
 	sb->s_op = &hostfs_sbops;
-	sb->s_d_op = &simple_dentry_operations;
+	set_default_d_op(sb, &simple_dentry_operations);
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	err = super_setup_bdi(sb);
 	if (err)
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 27567920abe4..42b779b4d87f 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -554,7 +554,7 @@ static int hpfs_fill_super(struct super_block *s, struct fs_context *fc)
 	/* Fill superblock stuff */
 	s->s_magic = HPFS_SUPER_MAGIC;
 	s->s_op = &hpfs_sops;
-	s->s_d_op = &hpfs_dentry_operations;
+	set_default_d_op(s, &hpfs_dentry_operations);
 	s->s_time_min =  local_to_gmt(s, 0);
 	s->s_time_max =  local_to_gmt(s, U32_MAX);
 
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index d5da9817df9b..8624393c0d8c 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -939,7 +939,7 @@ root_found:
 	sbi->s_check = opt->check;
 
 	if (table)
-		s->s_d_op = &isofs_dentry_ops[table - 1];
+		set_default_d_op(s, &isofs_dentry_ops[table - 1]);
 
 	/* get the root dentry */
 	s->s_root = d_make_root(inode);
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 10368c188c5e..3cfb86c5a36e 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -542,7 +542,7 @@ static int jfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_magic = JFS_SUPER_MAGIC;
 
 	if (sbi->mntflag & JFS_OS2)
-		sb->s_d_op = &jfs_ci_dentry_operations;
+		set_default_d_op(sb, &jfs_ci_dentry_operations);
 
 	inode = jfs_iget(sb, ROOT_I);
 	if (IS_ERR(inode)) {
diff --git a/fs/kernfs/mount.c b/fs/kernfs/mount.c
index c1719b5778a1..e384a69fbece 100644
--- a/fs/kernfs/mount.c
+++ b/fs/kernfs/mount.c
@@ -318,7 +318,7 @@ static int kernfs_fill_super(struct super_block *sb, struct kernfs_fs_context *k
 		return -ENOMEM;
 	}
 	sb->s_root = root;
-	sb->s_d_op = &kernfs_dops;
+	set_default_d_op(sb, &kernfs_dops);
 	return 0;
 }
 
diff --git a/fs/libfs.c b/fs/libfs.c
index 9ea0ecc325a8..ab82de070310 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -75,7 +75,7 @@ struct dentry *simple_lookup(struct inode *dir, struct dentry *dentry, unsigned
 {
 	if (dentry->d_name.len > NAME_MAX)
 		return ERR_PTR(-ENAMETOOLONG);
-	if (!dentry->d_sb->s_d_op)
+	if (!dentry->d_op)
 		d_set_d_op(dentry, &simple_dentry_operations);
 
 	if (IS_ENABLED(CONFIG_UNICODE) && IS_CASEFOLDED(dir))
@@ -684,7 +684,7 @@ static int pseudo_fs_fill_super(struct super_block *s, struct fs_context *fc)
 	s->s_root = d_make_root(root);
 	if (!s->s_root)
 		return -ENOMEM;
-	s->s_d_op = ctx->dops;
+	set_default_d_op(s, ctx->dops);
 	return 0;
 }
 
@@ -1950,22 +1950,22 @@ static const struct dentry_operations generic_encrypted_dentry_ops = {
  * @sb: superblock to be configured
  *
  * Filesystems supporting casefolding and/or fscrypt can call this
- * helper at mount-time to configure sb->s_d_op to best set of dentry
- * operations required for the enabled features. The helper must be
- * called after these have been configured, but before the root dentry
- * is created.
+ * helper at mount-time to configure default dentry_operations to the
+ * best set of dentry operations required for the enabled features.
+ * The helper must be called after these have been configured, but
+ * before the root dentry is created.
  */
 void generic_set_sb_d_ops(struct super_block *sb)
 {
 #if IS_ENABLED(CONFIG_UNICODE)
 	if (sb->s_encoding) {
-		sb->s_d_op = &generic_ci_dentry_ops;
+		set_default_d_op(sb, &generic_ci_dentry_ops);
 		return;
 	}
 #endif
 #ifdef CONFIG_FS_ENCRYPTION
 	if (sb->s_cop) {
-		sb->s_d_op = &generic_encrypted_dentry_ops;
+		set_default_d_op(sb, &generic_encrypted_dentry_ops);
 		return;
 	}
 #endif
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 91b5503b6f74..72dee6f3050e 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -1183,7 +1183,7 @@ static int nfs_set_super(struct super_block *s, struct fs_context *fc)
 	struct nfs_server *server = fc->s_fs_info;
 	int ret;
 
-	s->s_d_op = server->nfs_client->rpc_ops->dentry_ops;
+	set_default_d_op(s, server->nfs_client->rpc_ops->dentry_ops);
 	ret = set_anon_super(s, server);
 	if (ret == 0)
 		server->s_dev = s->s_dev;
diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
index 920a1ab47b63..ddff94c091b8 100644
--- a/fs/ntfs3/super.c
+++ b/fs/ntfs3/super.c
@@ -1223,7 +1223,8 @@ static int ntfs_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_export_op = &ntfs_export_ops;
 	sb->s_time_gran = NTFS_TIME_GRAN; // 100 nsec
 	sb->s_xattr = ntfs_xattr_handlers;
-	sb->s_d_op = options->nocase ? &ntfs_dentry_ops : NULL;
+	if (options->nocase)
+		set_default_d_op(sb, &ntfs_dentry_ops);
 
 	options->nls = ntfs_load_nls(options->nls_name);
 	if (IS_ERR(options->nls)) {
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 3d2533950bae..53daa4482406 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -1962,7 +1962,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 
 	sb->s_fs_info = osb;
 	sb->s_op = &ocfs2_sops;
-	sb->s_d_op = &ocfs2_dentry_ops;
+	set_default_d_op(sb, &ocfs2_dentry_ops);
 	sb->s_export_op = &ocfs2_export_ops;
 	sb->s_qcop = &dquot_quotactl_sysfile_ops;
 	sb->dq_op = &ocfs2_quota_operations;
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index 64ca9498f550..f3da840758e7 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -416,7 +416,7 @@ static int orangefs_fill_sb(struct super_block *sb,
 	sb->s_xattr = orangefs_xattr_handlers;
 	sb->s_magic = ORANGEFS_SUPER_MAGIC;
 	sb->s_op = &orangefs_s_ops;
-	sb->s_d_op = &orangefs_dentry_operations;
+	set_default_d_op(sb, &orangefs_dentry_operations);
 
 	sb->s_blocksize = PAGE_SIZE;
 	sb->s_blocksize_bits = PAGE_SHIFT;
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index e19940d649ca..efbf0b291551 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -1322,7 +1322,7 @@ int ovl_fill_super(struct super_block *sb, struct fs_context *fc)
 	if (WARN_ON(fc->user_ns != current_user_ns()))
 		goto out_err;
 
-	sb->s_d_op = &ovl_dentry_operations;
+	set_default_d_op(sb, &ovl_dentry_operations);
 
 	err = -ENOMEM;
 	if (!ofs->creator_cred)
diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
index 0a5266ecfd15..d4ec73359922 100644
--- a/fs/smb/client/cifsfs.c
+++ b/fs/smb/client/cifsfs.c
@@ -260,9 +260,9 @@ cifs_read_super(struct super_block *sb)
 	}
 
 	if (tcon->nocase)
-		sb->s_d_op = &cifs_ci_dentry_ops;
+		set_default_d_op(sb, &cifs_ci_dentry_ops);
 	else
-		sb->s_d_op = &cifs_dentry_ops;
+		set_default_d_op(sb, &cifs_dentry_ops);
 
 	sb->s_root = d_make_root(inode);
 	if (!sb->s_root) {
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index a3fd3cc591bd..c8ca61777323 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -480,7 +480,7 @@ static int tracefs_fill_super(struct super_block *sb, struct fs_context *fc)
 		return err;
 
 	sb->s_op = &tracefs_super_operations;
-	sb->s_d_op = &tracefs_dentry_operations;
+	set_default_d_op(sb, &tracefs_dentry_operations);
 
 	return 0;
 }
diff --git a/fs/vboxsf/super.c b/fs/vboxsf/super.c
index 0bc96ab6580b..241647b060ee 100644
--- a/fs/vboxsf/super.c
+++ b/fs/vboxsf/super.c
@@ -189,7 +189,7 @@ static int vboxsf_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_blocksize = 1024;
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_op = &vboxsf_super_ops;
-	sb->s_d_op = &vboxsf_dentry_ops;
+	set_default_d_op(sb, &vboxsf_dentry_ops);
 
 	iroot = iget_locked(sb, 0);
 	if (!iroot) {
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index 1993e6704552..be7ae058fa90 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -607,4 +607,6 @@ static inline struct dentry *d_next_sibling(const struct dentry *dentry)
 	return hlist_entry_safe(dentry->d_sib.next, struct dentry, d_sib);
 }
 
+void set_default_d_op(struct super_block *, const struct dentry_operations *);
+
 #endif	/* __LINUX_DCACHE_H */
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..7cd8eaab4d4e 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1413,7 +1413,7 @@ struct super_block {
 	 */
 	const char *s_subtype;
 
-	const struct dentry_operations *s_d_op; /* default d_op for dentries */
+	const struct dentry_operations *__s_d_op; /* default d_op for dentries */
 
 	struct shrinker *s_shrink;	/* per-sb shrinker handle */
 
diff --git a/mm/shmem.c b/mm/shmem.c
index 0c5fb4ffa03a..3583508800fc 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -5028,7 +5028,7 @@ static int shmem_fill_super(struct super_block *sb, struct fs_context *fc)
 
 	if (ctx->encoding) {
 		sb->s_encoding = ctx->encoding;
-		sb->s_d_op = &shmem_ci_dentry_ops;
+		set_default_d_op(sb, &shmem_ci_dentry_ops);
 		if (ctx->strict_encoding)
 			sb->s_encoding_flags = SB_ENC_STRICT_MODE_FL;
 	}
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 98f78cd55905..f4e880383f67 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -1363,7 +1363,7 @@ rpc_fill_super(struct super_block *sb, struct fs_context *fc)
 	sb->s_blocksize_bits = PAGE_SHIFT;
 	sb->s_magic = RPCAUTH_GSSMAGIC;
 	sb->s_op = &s_ops;
-	sb->s_d_op = &simple_dentry_operations;
+	set_default_d_op(sb, &simple_dentry_operations);
 	sb->s_time_gran = 1;
 
 	inode = rpc_get_inode(sb, S_IFDIR | 0555);
-- 
cgit v1.2.3


From 4ccd065a69df163cd9fe0dd8e0f609f1eeb4723d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Wed, 4 Jun 2025 17:54:41 +0800
Subject: crypto: ahash - Add support for drivers with no fallback

Some drivers cannot have a fallback, e.g., because the key is held
in hardware.  Allow these to be used with ahash by adding the bit
CRYPTO_ALG_NO_FALLBACK.

Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Tested-by: Harald Freudenberger <freude@linux.ibm.com>
---
 crypto/ahash.c         | 10 +++++++++-
 include/linux/crypto.h |  3 +++
 2 files changed, 12 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/crypto/ahash.c b/crypto/ahash.c
index e10bc2659ae4..bd9e49950201 100644
--- a/crypto/ahash.c
+++ b/crypto/ahash.c
@@ -347,6 +347,9 @@ static int ahash_do_req_chain(struct ahash_request *req,
 	if (crypto_ahash_statesize(tfm) > HASH_MAX_STATESIZE)
 		return -ENOSYS;
 
+	if (!crypto_ahash_need_fallback(tfm))
+		return -ENOSYS;
+
 	{
 		u8 state[HASH_MAX_STATESIZE];
 
@@ -952,6 +955,10 @@ static int ahash_prepare_alg(struct ahash_alg *alg)
 	    base->cra_reqsize > MAX_SYNC_HASH_REQSIZE)
 		return -EINVAL;
 
+	if (base->cra_flags & CRYPTO_ALG_NEED_FALLBACK &&
+	    base->cra_flags & CRYPTO_ALG_NO_FALLBACK)
+		return -EINVAL;
+
 	err = hash_prepare_alg(&alg->halg);
 	if (err)
 		return err;
@@ -960,7 +967,8 @@ static int ahash_prepare_alg(struct ahash_alg *alg)
 	base->cra_flags |= CRYPTO_ALG_TYPE_AHASH;
 
 	if ((base->cra_flags ^ CRYPTO_ALG_REQ_VIRT) &
-	    (CRYPTO_ALG_ASYNC | CRYPTO_ALG_REQ_VIRT))
+	    (CRYPTO_ALG_ASYNC | CRYPTO_ALG_REQ_VIRT) &&
+	    !(base->cra_flags & CRYPTO_ALG_NO_FALLBACK))
 		base->cra_flags |= CRYPTO_ALG_NEED_FALLBACK;
 
 	if (!alg->setkey)
diff --git a/include/linux/crypto.h b/include/linux/crypto.h
index b50f1954d1bb..a2137e19be7d 100644
--- a/include/linux/crypto.h
+++ b/include/linux/crypto.h
@@ -136,6 +136,9 @@
 /* Set if the algorithm supports virtual addresses. */
 #define CRYPTO_ALG_REQ_VIRT		0x00040000
 
+/* Set if the algorithm cannot have a fallback (e.g., phmac). */
+#define CRYPTO_ALG_NO_FALLBACK		0x00080000
+
 /* The high bits 0xff000000 are reserved for type-specific flags. */
 
 /*
-- 
cgit v1.2.3


From 0b0cae7119a0ec9449d7261b5e672a5fed765068 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Tue, 3 Jun 2025 14:14:43 +0300
Subject: x86/its: move its_pages array to struct mod_arch_specific

The of pages with ITS thunks allocated for modules are tracked by an
array in 'struct module'.

Since this is very architecture specific data structure, move it to
'struct mod_arch_specific'.

No functional changes.

Fixes: 872df34d7c51 ("x86/its: Use dynamic thunks for indirect branches")
Suggested-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250603111446.2609381-4-rppt@kernel.org
---
 arch/x86/include/asm/module.h |  8 ++++++++
 arch/x86/kernel/alternative.c | 19 ++++++++++---------
 include/linux/module.h        |  5 -----
 3 files changed, 18 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/module.h b/arch/x86/include/asm/module.h
index e988bac0a4a1..3c2de4ce3b10 100644
--- a/arch/x86/include/asm/module.h
+++ b/arch/x86/include/asm/module.h
@@ -5,12 +5,20 @@
 #include <asm-generic/module.h>
 #include <asm/orc_types.h>
 
+struct its_array {
+#ifdef CONFIG_MITIGATION_ITS
+	void **pages;
+	int num;
+#endif
+};
+
 struct mod_arch_specific {
 #ifdef CONFIG_UNWINDER_ORC
 	unsigned int num_orcs;
 	int *orc_unwind_ip;
 	struct orc_entry *orc_unwind;
 #endif
+	struct its_array its_pages;
 };
 
 #endif /* _ASM_X86_MODULE_H */
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ecfe7b497cad..b50fe6ce4655 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -173,8 +173,8 @@ void its_fini_mod(struct module *mod)
 	its_page = NULL;
 	mutex_unlock(&text_mutex);
 
-	for (int i = 0; i < mod->its_num_pages; i++) {
-		void *page = mod->its_page_array[i];
+	for (int i = 0; i < mod->arch.its_pages.num; i++) {
+		void *page = mod->arch.its_pages.pages[i];
 		execmem_restore_rox(page, PAGE_SIZE);
 	}
 }
@@ -184,11 +184,11 @@ void its_free_mod(struct module *mod)
 	if (!cpu_feature_enabled(X86_FEATURE_INDIRECT_THUNK_ITS))
 		return;
 
-	for (int i = 0; i < mod->its_num_pages; i++) {
-		void *page = mod->its_page_array[i];
+	for (int i = 0; i < mod->arch.its_pages.num; i++) {
+		void *page = mod->arch.its_pages.pages[i];
 		execmem_free(page);
 	}
-	kfree(mod->its_page_array);
+	kfree(mod->arch.its_pages.pages);
 }
 #endif /* CONFIG_MODULES */
 
@@ -201,14 +201,15 @@ static void *its_alloc(void)
 
 #ifdef CONFIG_MODULES
 	if (its_mod) {
-		void *tmp = krealloc(its_mod->its_page_array,
-				     (its_mod->its_num_pages+1) * sizeof(void *),
+		struct its_array *pages = &its_mod->arch.its_pages;
+		void *tmp = krealloc(pages->pages,
+				     (pages->num+1) * sizeof(void *),
 				     GFP_KERNEL);
 		if (!tmp)
 			return NULL;
 
-		its_mod->its_page_array = tmp;
-		its_mod->its_page_array[its_mod->its_num_pages++] = page;
+		pages->pages = tmp;
+		pages->pages[pages->num++] = page;
 
 		execmem_make_temp_rw(page, PAGE_SIZE);
 	}
diff --git a/include/linux/module.h b/include/linux/module.h
index 92e1420fccdf..5faa1fb1f4b4 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -586,11 +586,6 @@ struct module {
 	atomic_t refcnt;
 #endif
 
-#ifdef CONFIG_MITIGATION_ITS
-	int its_num_pages;
-	void **its_page_array;
-#endif
-
 #ifdef CONFIG_CONSTRUCTORS
 	/* Constructor functions. */
 	ctor_fn_t *ctors;
-- 
cgit v1.2.3


From 7cd9a11dd0c3d1dd225795ed1b5b53132888e7b5 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Tue, 3 Jun 2025 14:14:45 +0300
Subject: Revert "mm/execmem: Unify early execmem_cache behaviour"

The commit d6d1e3e6580c ("mm/execmem: Unify early execmem_cache
behaviour") changed early behaviour of execemem ROX cache to allow its
usage in early x86 code that allocates text pages when
CONFIG_MITGATION_ITS is enabled.

The permission management of the pages allocated from execmem for ITS
mitigation is now completely contained in arch/x86/kernel/alternatives.c
and therefore there is no need to special case early allocations in
execmem.

This reverts commit d6d1e3e6580ca35071ad474381f053cbf1fb6414.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: stable@vger.kernel.org
Link: https://lkml.kernel.org/r/20250603111446.2609381-6-rppt@kernel.org
---
 arch/x86/mm/init_32.c   |  3 ---
 arch/x86/mm/init_64.c   |  3 ---
 include/linux/execmem.h |  8 +-------
 mm/execmem.c            | 40 +++-------------------------------------
 4 files changed, 4 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 607d6a2e66e2..8a34fff6ab2b 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -30,7 +30,6 @@
 #include <linux/initrd.h>
 #include <linux/cpumask.h>
 #include <linux/gfp.h>
-#include <linux/execmem.h>
 
 #include <asm/asm.h>
 #include <asm/bios_ebda.h>
@@ -749,8 +748,6 @@ void mark_rodata_ro(void)
 	pr_info("Write protecting kernel text and read-only data: %luk\n",
 		size >> 10);
 
-	execmem_cache_make_ro();
-
 	kernel_set_to_readonly = 1;
 
 #ifdef CONFIG_CPA_DEBUG
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ee66fae9ebcc..fdb6cab524f0 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -34,7 +34,6 @@
 #include <linux/gfp.h>
 #include <linux/kcore.h>
 #include <linux/bootmem_info.h>
-#include <linux/execmem.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
@@ -1392,8 +1391,6 @@ void mark_rodata_ro(void)
 	       (end - start) >> 10);
 	set_memory_ro(start, (end - start) >> PAGE_SHIFT);
 
-	execmem_cache_make_ro();
-
 	kernel_set_to_readonly = 1;
 
 	/*
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index ca42d5e46ccc..3be35680a54f 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -54,7 +54,7 @@ enum execmem_range_flags {
 	EXECMEM_ROX_CACHE	= (1 << 1),
 };
 
-#if defined(CONFIG_ARCH_HAS_EXECMEM_ROX) && defined(CONFIG_EXECMEM)
+#ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
 /**
  * execmem_fill_trapping_insns - set memory to contain instructions that
  *				 will trap
@@ -94,15 +94,9 @@ int execmem_make_temp_rw(void *ptr, size_t size);
  * Return: 0 on success or negative error code on failure.
  */
 int execmem_restore_rox(void *ptr, size_t size);
-
-/*
- * Called from mark_readonly(), where the system transitions to ROX.
- */
-void execmem_cache_make_ro(void);
 #else
 static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
 static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
-static inline void execmem_cache_make_ro(void) { }
 #endif
 
 /**
diff --git a/mm/execmem.c b/mm/execmem.c
index 9720ac2dfa41..2b683e7d864d 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -254,34 +254,6 @@ out_unlock:
 	return ptr;
 }
 
-static bool execmem_cache_rox = false;
-
-void execmem_cache_make_ro(void)
-{
-	struct maple_tree *free_areas = &execmem_cache.free_areas;
-	struct maple_tree *busy_areas = &execmem_cache.busy_areas;
-	MA_STATE(mas_free, free_areas, 0, ULONG_MAX);
-	MA_STATE(mas_busy, busy_areas, 0, ULONG_MAX);
-	struct mutex *mutex = &execmem_cache.mutex;
-	void *area;
-
-	execmem_cache_rox = true;
-
-	mutex_lock(mutex);
-
-	mas_for_each(&mas_free, area, ULONG_MAX) {
-		unsigned long pages = mas_range_len(&mas_free) >> PAGE_SHIFT;
-		set_memory_ro(mas_free.index, pages);
-	}
-
-	mas_for_each(&mas_busy, area, ULONG_MAX) {
-		unsigned long pages = mas_range_len(&mas_busy) >> PAGE_SHIFT;
-		set_memory_ro(mas_busy.index, pages);
-	}
-
-	mutex_unlock(mutex);
-}
-
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
 	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
@@ -302,15 +274,9 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 	/* fill memory with instructions that will trap */
 	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
 
-	if (execmem_cache_rox) {
-		err = set_memory_rox((unsigned long)p, vm->nr_pages);
-		if (err)
-			goto err_free_mem;
-	} else {
-		err = set_memory_x((unsigned long)p, vm->nr_pages);
-		if (err)
-			goto err_free_mem;
-	}
+	err = set_memory_rox((unsigned long)p, vm->nr_pages);
+	if (err)
+		goto err_free_mem;
 
 	err = execmem_cache_add(p, alloc_size);
 	if (err)
-- 
cgit v1.2.3


From 6a9e2fb1bab53b54d02714a2ee3c6612d19629ce Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Fri, 6 Jun 2025 11:45:07 +0200
Subject: nsfs: move root inode number to uapi

Userspace relies on the root inode numbers to identify the initial
namespaces. That's already a hard dependency. So we cannot change that
anymore. Move the initial inode numbers to a public header.

Link: https://github.com/systemd/systemd/commit/d293fade24b34ccc2f5716b0ff5513e9533cf0c4
Link: https://lore.kernel.org/20250606-work-nsfs-v1-1-b8749c9a8844@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/proc_ns.h   | 13 +++++++------
 include/uapi/linux/nsfs.h |  9 +++++++++
 2 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 5ea470eb4d76..e77a37b23ca7 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -6,6 +6,7 @@
 #define _LINUX_PROC_NS_H
 
 #include <linux/ns_common.h>
+#include <uapi/linux/nsfs.h>
 
 struct pid_namespace;
 struct nsset;
@@ -40,12 +41,12 @@ extern const struct proc_ns_operations timens_for_children_operations;
  */
 enum {
 	PROC_ROOT_INO		= 1,
-	PROC_IPC_INIT_INO	= 0xEFFFFFFFU,
-	PROC_UTS_INIT_INO	= 0xEFFFFFFEU,
-	PROC_USER_INIT_INO	= 0xEFFFFFFDU,
-	PROC_PID_INIT_INO	= 0xEFFFFFFCU,
-	PROC_CGROUP_INIT_INO	= 0xEFFFFFFBU,
-	PROC_TIME_INIT_INO	= 0xEFFFFFFAU,
+	PROC_IPC_INIT_INO	= IPC_NS_INIT_INO,
+	PROC_UTS_INIT_INO	= UTS_NS_INIT_INO,
+	PROC_USER_INIT_INO	= USER_NS_INIT_INO,
+	PROC_PID_INIT_INO	= PID_NS_INIT_INO,
+	PROC_CGROUP_INIT_INO	= CGROUP_NS_INIT_INO,
+	PROC_TIME_INIT_INO	= TIME_NS_INIT_INO,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h
index 34127653fd00..6683e7ca3996 100644
--- a/include/uapi/linux/nsfs.h
+++ b/include/uapi/linux/nsfs.h
@@ -42,4 +42,13 @@ struct mnt_ns_info {
 /* Get previous namespace. */
 #define NS_MNT_GET_PREV		_IOR(NSIO, 12, struct mnt_ns_info)
 
+enum init_ns_ino {
+	IPC_NS_INIT_INO		= 0xEFFFFFFFU,
+	UTS_NS_INIT_INO		= 0xEFFFFFFEU,
+	USER_NS_INIT_INO	= 0xEFFFFFFDU,
+	PID_NS_INIT_INO		= 0xEFFFFFFCU,
+	CGROUP_NS_INIT_INO	= 0xEFFFFFFBU,
+	TIME_NS_INIT_INO	= 0xEFFFFFFAU,
+};
+
 #endif /* __LINUX_NSFS_H */
-- 
cgit v1.2.3


From 9b0240b3ccc325c7a96cf362877180bc9e10d546 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Fri, 6 Jun 2025 11:45:08 +0200
Subject: netns: use stable inode number for initial mount ns

Apart from the network and mount namespace all other namespaces expose a
stable inode number and userspace has been relying on that for a very
long time now. It's very much heavily used API. Align the network
namespace and use a stable inode number from the reserved procfs inode
number space so this is consistent across all namespaces.

Link: https://lore.kernel.org/20250606-work-nsfs-v1-2-b8749c9a8844@kernel.org
Reviewed-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/proc_ns.h   | 1 +
 include/uapi/linux/nsfs.h | 1 +
 net/core/net_namespace.c  | 8 ++++++++
 3 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index e77a37b23ca7..3ff0bd381704 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -47,6 +47,7 @@ enum {
 	PROC_PID_INIT_INO	= PID_NS_INIT_INO,
 	PROC_CGROUP_INIT_INO	= CGROUP_NS_INIT_INO,
 	PROC_TIME_INIT_INO	= TIME_NS_INIT_INO,
+	PROC_NET_INIT_INO	= NET_NS_INIT_INO,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h
index 6683e7ca3996..393778489d85 100644
--- a/include/uapi/linux/nsfs.h
+++ b/include/uapi/linux/nsfs.h
@@ -49,6 +49,7 @@ enum init_ns_ino {
 	PID_NS_INIT_INO		= 0xEFFFFFFCU,
 	CGROUP_NS_INIT_INO	= 0xEFFFFFFBU,
 	TIME_NS_INIT_INO	= 0xEFFFFFFAU,
+	NET_NS_INIT_INO		= 0xEFFFFFF9U,
 };
 
 #endif /* __LINUX_NSFS_H */
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index ae54f26709ca..03cf87d3b380 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -796,11 +796,19 @@ static __net_init int net_ns_net_init(struct net *net)
 #ifdef CONFIG_NET_NS
 	net->ns.ops = &netns_operations;
 #endif
+	if (net == &init_net) {
+		net->ns.inum = PROC_NET_INIT_INO;
+		return 0;
+	}
 	return ns_alloc_inum(&net->ns);
 }
 
 static __net_exit void net_ns_net_exit(struct net *net)
 {
+	/*
+	 * Initial network namespace doesn't exit so we don't need any
+	 * special checks here.
+	 */
 	ns_free_inum(&net->ns);
 }
 
-- 
cgit v1.2.3


From 7f4f229195b73606ded77e56943f463b78adf635 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Fri, 6 Jun 2025 11:45:09 +0200
Subject: mntns: use stable inode number for initial mount ns

Apart from the network and mount namespace all other namespaces expose a
stable inode number and userspace has been relying on that for a very
long time now. It's very much heavily used API. Align the mount
namespace and use a stable inode number from the reserved procfs inode
number space so this is consistent across all namespaces.

Link: https://lore.kernel.org/20250606-work-nsfs-v1-3-b8749c9a8844@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/namespace.c            | 4 +++-
 include/linux/proc_ns.h   | 1 +
 include/uapi/linux/nsfs.h | 1 +
 3 files changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/namespace.c b/fs/namespace.c
index e13d9ab4f564..7ca4612c7ae9 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -6203,9 +6203,11 @@ static void __init init_mount_tree(void)
 	if (IS_ERR(mnt))
 		panic("Can't create rootfs");
 
-	ns = alloc_mnt_ns(&init_user_ns, false);
+	ns = alloc_mnt_ns(&init_user_ns, true);
 	if (IS_ERR(ns))
 		panic("Can't allocate initial namespace");
+	ns->seq = atomic64_inc_return(&mnt_ns_seq);
+	ns->ns.inum = PROC_MNT_INIT_INO;
 	m = real_mount(mnt);
 	ns->root = m;
 	ns->nr_mounts = 1;
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 3ff0bd381704..6258455e49a4 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -48,6 +48,7 @@ enum {
 	PROC_CGROUP_INIT_INO	= CGROUP_NS_INIT_INO,
 	PROC_TIME_INIT_INO	= TIME_NS_INIT_INO,
 	PROC_NET_INIT_INO	= NET_NS_INIT_INO,
+	PROC_MNT_INIT_INO	= MNT_NS_INIT_INO,
 };
 
 #ifdef CONFIG_PROC_FS
diff --git a/include/uapi/linux/nsfs.h b/include/uapi/linux/nsfs.h
index 393778489d85..97d8d80d139f 100644
--- a/include/uapi/linux/nsfs.h
+++ b/include/uapi/linux/nsfs.h
@@ -50,6 +50,7 @@ enum init_ns_ino {
 	CGROUP_NS_INIT_INO	= 0xEFFFFFFBU,
 	TIME_NS_INIT_INO	= 0xEFFFFFFAU,
 	NET_NS_INIT_INO		= 0xEFFFFFF9U,
+	MNT_NS_INIT_INO		= 0xEFFFFFF8U,
 };
 
 #endif /* __LINUX_NSFS_H */
-- 
cgit v1.2.3


From 6bdd3a01fe4627ad7a562ba38eb759eba715b671 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 10 Jun 2025 16:00:20 +0200
Subject: fs: add missing values to TRACE_IOCB_STRINGS

Make sure all values are covered.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250610140020.2227932-1-hch@lst.de
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..d27c402f1162 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -399,7 +399,9 @@ struct readahead_control;
 	{ IOCB_WAITQ,		"WAITQ" }, \
 	{ IOCB_NOIO,		"NOIO" }, \
 	{ IOCB_ALLOC_CACHE,	"ALLOC_CACHE" }, \
-	{ IOCB_DIO_CALLER_COMP,	"CALLER_COMP" }
+	{ IOCB_DIO_CALLER_COMP,	"CALLER_COMP" }, \
+	{ IOCB_AIO_RW,		"AIO_RW" }, \
+	{ IOCB_HAS_METADATA,	"AIO_HAS_METADATA" }
 
 struct kiocb {
 	struct file		*ki_filp;
-- 
cgit v1.2.3


From 2fa8bf42c50582c7302918474aae8c52b59e7910 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 23 Feb 2025 19:53:00 -0500
Subject: set_default_d_op(): calculate the matching value for ->d_flags

... and store it in ->s_d_flags, to be used by __d_alloc()

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/dcache.c        | 6 ++++--
 include/linux/fs.h | 1 +
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/dcache.c b/fs/dcache.c
index 27e6d2f36973..7519c5f66f79 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1731,14 +1731,14 @@ static struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	dentry->d_inode = NULL;
 	dentry->d_parent = dentry;
 	dentry->d_sb = sb;
-	dentry->d_op = NULL;
+	dentry->d_op = sb->__s_d_op;
+	dentry->d_flags = sb->s_d_flags;
 	dentry->d_fsdata = NULL;
 	INIT_HLIST_BL_NODE(&dentry->d_hash);
 	INIT_LIST_HEAD(&dentry->d_lru);
 	INIT_HLIST_HEAD(&dentry->d_children);
 	INIT_HLIST_NODE(&dentry->d_u.d_alias);
 	INIT_HLIST_NODE(&dentry->d_sib);
-	d_set_d_op(dentry, dentry->d_sb->__s_d_op);
 
 	if (dentry->d_op && dentry->d_op->d_init) {
 		err = dentry->d_op->d_init(dentry);
@@ -1877,7 +1877,9 @@ EXPORT_SYMBOL(d_set_d_op);
 
 void set_default_d_op(struct super_block *s, const struct dentry_operations *ops)
 {
+	unsigned int flags = d_op_flags(ops);
 	s->__s_d_op = ops;
+	s->s_d_flags = (s->s_d_flags & ~DCACHE_OP_FLAGS) | flags;
 }
 EXPORT_SYMBOL(set_default_d_op);
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 7cd8eaab4d4e..65548e70e596 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1400,6 +1400,7 @@ struct super_block {
 	char			s_sysfs_name[UUID_STRING_LEN + 1];
 
 	unsigned int		s_max_links;
+	unsigned int		s_d_flags;	/* default d_flags for dentries */
 
 	/*
 	 * The next field is for VFS *only*. No filesystems have any business
-- 
cgit v1.2.3


From 691fb82ca6ccdcdb9e60e754b55659271d5280e7 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 23 Feb 2025 20:18:15 -0500
Subject: make d_set_d_op() static

Convert the last user (d_alloc_pseudo()) and be done with that.
Any out-of-tree filesystem using it should switch to d_splice_alias_ops()
or, better yet, check whether it really needs to have ->d_op vary among
its dentries.

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/porting.rst | 11 +++++++++++
 fs/dcache.c                           |  6 +++---
 include/linux/dcache.h                |  1 -
 3 files changed, 14 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index b16139e91942..579f17df46cf 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1256,3 +1256,14 @@ an extra reference to new mount - it should be returned with refcount 1.
 
 If your filesystem sets the default dentry_operations, use set_default_d_op()
 rather than manually setting sb->s_d_op.
+
+---
+
+**mandatory**
+
+d_set_d_op() is no longer exported (or public, for that matter); _if_
+your filesystem really needed that, make use of d_splice_alias_ops()
+to have them set.  Better yet, think hard whether you need different
+->d_op for different dentries - if not, just use set_default_d_op()
+at mount time and be done with that.  Currently procfs is the only
+thing that really needs ->d_op varying between dentries.
diff --git a/fs/dcache.c b/fs/dcache.c
index 7519c5f66f79..4e6ab27471a4 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -1821,8 +1821,9 @@ struct dentry *d_alloc_pseudo(struct super_block *sb, const struct qstr *name)
 	struct dentry *dentry = __d_alloc(sb, name);
 	if (likely(dentry)) {
 		dentry->d_flags |= DCACHE_NORCU;
+		/* d_op_flags(&anon_ops) is 0 */
 		if (!dentry->d_op)
-			d_set_d_op(dentry, &anon_ops);
+			dentry->d_op = &anon_ops;
 	}
 	return dentry;
 }
@@ -1864,7 +1865,7 @@ static unsigned int d_op_flags(const struct dentry_operations *op)
 	return flags;
 }
 
-void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
+static void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 {
 	unsigned int flags = d_op_flags(op);
 	WARN_ON_ONCE(dentry->d_op);
@@ -1873,7 +1874,6 @@ void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op)
 	if (flags)
 		dentry->d_flags |= flags;
 }
-EXPORT_SYMBOL(d_set_d_op);
 
 void set_default_d_op(struct super_block *s, const struct dentry_operations *ops)
 {
diff --git a/include/linux/dcache.h b/include/linux/dcache.h
index be7ae058fa90..cc3e1c1a3454 100644
--- a/include/linux/dcache.h
+++ b/include/linux/dcache.h
@@ -237,7 +237,6 @@ extern void d_instantiate_new(struct dentry *, struct inode *);
 extern void __d_drop(struct dentry *dentry);
 extern void d_drop(struct dentry *dentry);
 extern void d_delete(struct dentry *);
-extern void d_set_d_op(struct dentry *dentry, const struct dentry_operations *op);
 
 /* allocate/de-allocate */
 extern struct dentry * d_alloc(struct dentry *, const struct qstr *);
-- 
cgit v1.2.3


From 0b136e7d18fa8bb1251ab06f4f30e883da780245 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 23 Feb 2025 20:59:01 -0500
Subject: kill simple_dentry_operations

No users left and anything that wants it would be better off just
setting DCACHE_DONTCACHE in their ->s_d_flags.

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/libfs.c         | 5 -----
 include/linux/fs.h | 1 -
 2 files changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/libfs.c b/fs/libfs.c
index 19cc12651708..3051211998b6 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -62,11 +62,6 @@ int always_delete_dentry(const struct dentry *dentry)
 }
 EXPORT_SYMBOL(always_delete_dentry);
 
-const struct dentry_operations simple_dentry_operations = {
-	.d_delete = always_delete_dentry,
-};
-EXPORT_SYMBOL(simple_dentry_operations);
-
 /*
  * Lookup the data. This is trivial - if the dentry didn't already
  * exist, we know it is negative.  Set d_op to delete negative dentries.
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 65548e70e596..d58bbb8262e8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3606,7 +3606,6 @@ extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
 extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
-extern const struct dentry_operations simple_dentry_operations;
 
 extern struct dentry *simple_lookup(struct inode *, struct dentry *, unsigned int flags);
 extern ssize_t generic_read_dir(struct file *, char __user *, size_t, loff_t *);
-- 
cgit v1.2.3


From 29d673b1508fcaa14be32e92679874f10a099bc8 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Mon, 13 May 2024 23:36:53 -0600
Subject: make securityfs_remove() remove the entire subtree

... and fix the mount leak when anything's mounted there.
securityfs_recursive_remove becomes an alias for securityfs_remove -
we'll probably need to remove it in a cycle or two.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/security.h |  3 ++-
 security/inode.c         | 47 ++++++++++-------------------------------------
 2 files changed, 12 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/security.h b/include/linux/security.h
index dba349629229..386463b5e848 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -2211,7 +2211,6 @@ struct dentry *securityfs_create_symlink(const char *name,
 					 const char *target,
 					 const struct inode_operations *iops);
 extern void securityfs_remove(struct dentry *dentry);
-extern void securityfs_recursive_remove(struct dentry *dentry);
 
 #else /* CONFIG_SECURITYFS */
 
@@ -2243,6 +2242,8 @@ static inline void securityfs_remove(struct dentry *dentry)
 
 #endif
 
+#define securityfs_recursive_remove securityfs_remove
+
 #ifdef CONFIG_BPF_SYSCALL
 union bpf_attr;
 struct bpf_map;
diff --git a/security/inode.c b/security/inode.c
index 1ecb8859c272..43382ef8896e 100644
--- a/security/inode.c
+++ b/security/inode.c
@@ -281,6 +281,12 @@ struct dentry *securityfs_create_symlink(const char *name,
 }
 EXPORT_SYMBOL_GPL(securityfs_create_symlink);
 
+static void remove_one(struct dentry *victim)
+{
+	if (victim->d_parent == victim->d_sb->s_root)
+		simple_release_fs(&mount, &mount_count);
+}
+
 /**
  * securityfs_remove - removes a file or directory from the securityfs filesystem
  *
@@ -293,44 +299,11 @@ EXPORT_SYMBOL_GPL(securityfs_create_symlink);
  * This function is required to be called in order for the file to be
  * removed. No automatic cleanup of files will happen when a module is
  * removed; you are responsible here.
- */
-void securityfs_remove(struct dentry *dentry)
-{
-	struct inode *dir;
-
-	if (IS_ERR_OR_NULL(dentry))
-		return;
-
-	dir = d_inode(dentry->d_parent);
-	inode_lock(dir);
-	if (simple_positive(dentry)) {
-		if (d_is_dir(dentry))
-			simple_rmdir(dir, dentry);
-		else
-			simple_unlink(dir, dentry);
-	}
-	inode_unlock(dir);
-	if (dir == dir->i_sb->s_root->d_inode)
-		simple_release_fs(&mount, &mount_count);
-}
-EXPORT_SYMBOL_GPL(securityfs_remove);
-
-static void remove_one(struct dentry *victim)
-{
-	if (victim->d_parent == victim->d_sb->s_root)
-		simple_release_fs(&mount, &mount_count);
-}
-
-/**
- * securityfs_recursive_remove - recursively removes a file or directory
- *
- * @dentry: a pointer to a the dentry of the file or directory to be removed.
  *
- * This function recursively removes a file or directory in securityfs that was
- * previously created with a call to another securityfs function (like
- * securityfs_create_file() or variants thereof.)
+ * AV: when applied to directory it will take all children out; no need to call
+ * it for descendents if ancestor is getting killed.
  */
-void securityfs_recursive_remove(struct dentry *dentry)
+void securityfs_remove(struct dentry *dentry)
 {
 	if (IS_ERR_OR_NULL(dentry))
 		return;
@@ -339,7 +312,7 @@ void securityfs_recursive_remove(struct dentry *dentry)
 	simple_recursive_removal(dentry, remove_one);
 	simple_release_fs(&mount, &mount_count);
 }
-EXPORT_SYMBOL_GPL(securityfs_recursive_remove);
+EXPORT_SYMBOL_GPL(securityfs_remove);
 
 #ifdef CONFIG_SECURITY
 static struct dentry *lsm_dentry;
-- 
cgit v1.2.3


From e1f4b1f167581a4932dd4f017c80a6e46d28761a Mon Sep 17 00:00:00 2001
From: Mohsin Bashir <mohsin.bashr@gmail.com>
Date: Tue, 10 Jun 2025 10:11:08 -0700
Subject: eth: Update rmon hist range

The fbnic driver reports up-to 11 ranges resulting in the drop of the
last range. This patch increment the value of ETHTOOL_RMON_HIST_MAX to
address this limitation.

Signed-off-by: Mohsin Bashir <mohsin.bashr@gmail.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250610171109.1481229-2-mohsin.bashr@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ethtool.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 5e0dd333ad1f..90da1aee6e56 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -536,7 +536,7 @@ struct ethtool_rmon_hist_range {
 	u16 high;
 };
 
-#define ETHTOOL_RMON_HIST_MAX	10
+#define ETHTOOL_RMON_HIST_MAX	11
 
 /**
  * struct ethtool_rmon_stats - selected RMON (RFC 2819) statistics
-- 
cgit v1.2.3


From baaebe0928bf321a1cd980d569e308dec66be94c Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Wed, 11 Jun 2025 13:08:26 -0700
Subject: Revert "bpf: use common instruction history across all states"

This reverts commit 96a30e469ca1d2b8cc7811b40911f8614b558241.
Next patches in the series modify propagate_precision() to allow
arbitrary starting state. Precision propagation requires access to
jump history, and arbitrary states represent history not belonging to
`env->cur_state`.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250611200836.4135542-1-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  19 ++++----
 kernel/bpf/verifier.c        | 109 ++++++++++++++++++++++---------------------
 2 files changed, 64 insertions(+), 64 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index e6c26393c029..3e77befdbc4b 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -344,7 +344,7 @@ struct bpf_func_state {
 
 #define MAX_CALL_FRAMES 8
 
-/* instruction history flags, used in bpf_insn_hist_entry.flags field */
+/* instruction history flags, used in bpf_jmp_history_entry.flags field */
 enum {
 	/* instruction references stack slot through PTR_TO_STACK register;
 	 * we also store stack's frame number in lower 3 bits (MAX_CALL_FRAMES is 8)
@@ -366,7 +366,7 @@ enum {
 static_assert(INSN_F_FRAMENO_MASK + 1 >= MAX_CALL_FRAMES);
 static_assert(INSN_F_SPI_MASK + 1 >= MAX_BPF_STACK / 8);
 
-struct bpf_insn_hist_entry {
+struct bpf_jmp_history_entry {
 	u32 idx;
 	/* insn idx can't be bigger than 1 million */
 	u32 prev_idx : 20;
@@ -459,14 +459,13 @@ struct bpf_verifier_state {
 	 * See get_loop_entry() for more information.
 	 */
 	struct bpf_verifier_state *loop_entry;
-	/* Sub-range of env->insn_hist[] corresponding to this state's
-	 * instruction history.
-	 * Backtracking is using it to go from last to first.
-	 * For most states instruction history is short, 0-3 instructions.
+	/* jmp history recorded from first to last.
+	 * backtracking is using it to go from last to first.
+	 * For most states jmp_history_cnt is [0-3].
 	 * For loops can go up to ~40.
 	 */
-	u32 insn_hist_start;
-	u32 insn_hist_end;
+	struct bpf_jmp_history_entry *jmp_history;
+	u32 jmp_history_cnt;
 	u32 dfs_depth;
 	u32 callback_unroll_depth;
 	u32 may_goto_depth;
@@ -776,9 +775,7 @@ struct bpf_verifier_env {
 		int cur_postorder;
 	} cfg;
 	struct backtrack_state bt;
-	struct bpf_insn_hist_entry *insn_hist;
-	struct bpf_insn_hist_entry *cur_hist_ent;
-	u32 insn_hist_cap;
+	struct bpf_jmp_history_entry *cur_hist_ent;
 	u32 pass_cnt; /* number of times do_check() was called */
 	u32 subprog_cnt;
 	/* number of instructions analyzed by the verifier */
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index b1f797616f20..92f2dad5f453 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1660,6 +1660,13 @@ static void free_func_state(struct bpf_func_state *state)
 	kfree(state);
 }
 
+static void clear_jmp_history(struct bpf_verifier_state *state)
+{
+	kfree(state->jmp_history);
+	state->jmp_history = NULL;
+	state->jmp_history_cnt = 0;
+}
+
 static void free_verifier_state(struct bpf_verifier_state *state,
 				bool free_self)
 {
@@ -1670,6 +1677,7 @@ static void free_verifier_state(struct bpf_verifier_state *state,
 		state->frame[i] = NULL;
 	}
 	kfree(state->refs);
+	clear_jmp_history(state);
 	if (free_self)
 		kfree(state);
 }
@@ -1734,6 +1742,13 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	struct bpf_func_state *dst;
 	int i, err;
 
+	dst_state->jmp_history = copy_array(dst_state->jmp_history, src->jmp_history,
+					  src->jmp_history_cnt, sizeof(*dst_state->jmp_history),
+					  GFP_USER);
+	if (!dst_state->jmp_history)
+		return -ENOMEM;
+	dst_state->jmp_history_cnt = src->jmp_history_cnt;
+
 	/* if dst has more stack frames then src frame, free them, this is also
 	 * necessary in case of exceptional exits using bpf_throw.
 	 */
@@ -1751,8 +1766,6 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	dst_state->parent = src->parent;
 	dst_state->first_insn_idx = src->first_insn_idx;
 	dst_state->last_insn_idx = src->last_insn_idx;
-	dst_state->insn_hist_start = src->insn_hist_start;
-	dst_state->insn_hist_end = src->insn_hist_end;
 	dst_state->dfs_depth = src->dfs_depth;
 	dst_state->callback_unroll_depth = src->callback_unroll_depth;
 	dst_state->used_as_loop_entry = src->used_as_loop_entry;
@@ -2820,14 +2833,9 @@ static struct bpf_verifier_state *push_async_cb(struct bpf_verifier_env *env,
 	 * The caller state doesn't matter.
 	 * This is async callback. It starts in a fresh stack.
 	 * Initialize it similar to do_check_common().
-	 * But we do need to make sure to not clobber insn_hist, so we keep
-	 * chaining insn_hist_start/insn_hist_end indices as for a normal
-	 * child state.
 	 */
 	elem->st.branches = 1;
 	elem->st.in_sleepable = is_sleepable;
-	elem->st.insn_hist_start = env->cur_state->insn_hist_end;
-	elem->st.insn_hist_end = elem->st.insn_hist_start;
 	frame = kzalloc(sizeof(*frame), GFP_KERNEL);
 	if (!frame)
 		goto err;
@@ -3856,10 +3864,11 @@ static void linked_regs_unpack(u64 val, struct linked_regs *s)
 }
 
 /* for any branch, call, exit record the history of jmps in the given state */
-static int push_insn_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
-			     int insn_flags, u64 linked_regs)
+static int push_jmp_history(struct bpf_verifier_env *env, struct bpf_verifier_state *cur,
+			    int insn_flags, u64 linked_regs)
 {
-	struct bpf_insn_hist_entry *p;
+	u32 cnt = cur->jmp_history_cnt;
+	struct bpf_jmp_history_entry *p;
 	size_t alloc_size;
 
 	/* combine instruction flags if we already recorded this instruction */
@@ -3879,32 +3888,29 @@ static int push_insn_history(struct bpf_verifier_env *env, struct bpf_verifier_s
 		return 0;
 	}
 
-	if (cur->insn_hist_end + 1 > env->insn_hist_cap) {
-		alloc_size = size_mul(cur->insn_hist_end + 1, sizeof(*p));
-		p = kvrealloc(env->insn_hist, alloc_size, GFP_USER);
-		if (!p)
-			return -ENOMEM;
-		env->insn_hist = p;
-		env->insn_hist_cap = alloc_size / sizeof(*p);
-	}
+	cnt++;
+	alloc_size = kmalloc_size_roundup(size_mul(cnt, sizeof(*p)));
+	p = krealloc(cur->jmp_history, alloc_size, GFP_USER);
+	if (!p)
+		return -ENOMEM;
+	cur->jmp_history = p;
 
-	p = &env->insn_hist[cur->insn_hist_end];
+	p = &cur->jmp_history[cnt - 1];
 	p->idx = env->insn_idx;
 	p->prev_idx = env->prev_insn_idx;
 	p->flags = insn_flags;
 	p->linked_regs = linked_regs;
-
-	cur->insn_hist_end++;
+	cur->jmp_history_cnt = cnt;
 	env->cur_hist_ent = p;
 
 	return 0;
 }
 
-static struct bpf_insn_hist_entry *get_insn_hist_entry(struct bpf_verifier_env *env,
-						       u32 hist_start, u32 hist_end, int insn_idx)
+static struct bpf_jmp_history_entry *get_jmp_hist_entry(struct bpf_verifier_state *st,
+						        u32 hist_end, int insn_idx)
 {
-	if (hist_end > hist_start && env->insn_hist[hist_end - 1].idx == insn_idx)
-		return &env->insn_hist[hist_end - 1];
+	if (hist_end > 0 && st->jmp_history[hist_end - 1].idx == insn_idx)
+		return &st->jmp_history[hist_end - 1];
 	return NULL;
 }
 
@@ -3921,26 +3927,25 @@ static struct bpf_insn_hist_entry *get_insn_hist_entry(struct bpf_verifier_env *
  * history entry recording a jump from last instruction of parent state and
  * first instruction of given state.
  */
-static int get_prev_insn_idx(const struct bpf_verifier_env *env,
-			     struct bpf_verifier_state *st,
-			     int insn_idx, u32 hist_start, u32 *hist_endp)
+static int get_prev_insn_idx(struct bpf_verifier_state *st, int i,
+			     u32 *history)
 {
-	u32 hist_end = *hist_endp;
-	u32 cnt = hist_end - hist_start;
+	u32 cnt = *history;
 
-	if (insn_idx == st->first_insn_idx) {
+	if (i == st->first_insn_idx) {
 		if (cnt == 0)
 			return -ENOENT;
-		if (cnt == 1 && env->insn_hist[hist_start].idx == insn_idx)
+		if (cnt == 1 && st->jmp_history[0].idx == i)
 			return -ENOENT;
 	}
 
-	if (cnt && env->insn_hist[hist_end - 1].idx == insn_idx) {
-		(*hist_endp)--;
-		return env->insn_hist[hist_end - 1].prev_idx;
+	if (cnt && st->jmp_history[cnt - 1].idx == i) {
+		i = st->jmp_history[cnt - 1].prev_idx;
+		(*history)--;
 	} else {
-		return insn_idx - 1;
+		i--;
 	}
+	return i;
 }
 
 static const char *disasm_kfunc_name(void *data, const struct bpf_insn *insn)
@@ -4121,7 +4126,7 @@ static void fmt_stack_mask(char *buf, ssize_t buf_sz, u64 stack_mask)
 /* If any register R in hist->linked_regs is marked as precise in bt,
  * do bt_set_frame_{reg,slot}(bt, R) for all registers in hist->linked_regs.
  */
-static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_insn_hist_entry *hist)
+static void bt_sync_linked_regs(struct backtrack_state *bt, struct bpf_jmp_history_entry *hist)
 {
 	struct linked_regs linked_regs;
 	bool some_precise = false;
@@ -4166,7 +4171,7 @@ static bool calls_callback(struct bpf_verifier_env *env, int insn_idx);
  *   - *was* processed previously during backtracking.
  */
 static int backtrack_insn(struct bpf_verifier_env *env, int idx, int subseq_idx,
-			  struct bpf_insn_hist_entry *hist, struct backtrack_state *bt)
+			  struct bpf_jmp_history_entry *hist, struct backtrack_state *bt)
 {
 	struct bpf_insn *insn = env->prog->insnsi + idx;
 	u8 class = BPF_CLASS(insn->code);
@@ -4584,7 +4589,7 @@ static void mark_all_scalars_imprecise(struct bpf_verifier_env *env, struct bpf_
  * SCALARS, as well as any other registers and slots that contribute to
  * a tracked state of given registers/stack slots, depending on specific BPF
  * assembly instructions (see backtrack_insns() for exact instruction handling
- * logic). This backtracking relies on recorded insn_hist and is able to
+ * logic). This backtracking relies on recorded jmp_history and is able to
  * traverse entire chain of parent states. This process ends only when all the
  * necessary registers/slots and their transitive dependencies are marked as
  * precise.
@@ -4701,9 +4706,8 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 
 	for (;;) {
 		DECLARE_BITMAP(mask, 64);
-		u32 hist_start = st->insn_hist_start;
-		u32 hist_end = st->insn_hist_end;
-		struct bpf_insn_hist_entry *hist;
+		u32 history = st->jmp_history_cnt;
+		struct bpf_jmp_history_entry *hist;
 
 		if (env->log.level & BPF_LOG_LEVEL2) {
 			verbose(env, "mark_precise: frame%d: last_idx %d first_idx %d subseq_idx %d \n",
@@ -4741,7 +4745,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				err = 0;
 				skip_first = false;
 			} else {
-				hist = get_insn_hist_entry(env, hist_start, hist_end, i);
+				hist = get_jmp_hist_entry(st, history, i);
 				err = backtrack_insn(env, i, subseq_idx, hist, bt);
 			}
 			if (err == -ENOTSUPP) {
@@ -4758,7 +4762,7 @@ static int __mark_chain_precision(struct bpf_verifier_env *env, int regno)
 				 */
 				return 0;
 			subseq_idx = i;
-			i = get_prev_insn_idx(env, st, i, hist_start, &hist_end);
+			i = get_prev_insn_idx(st, i, &history);
 			if (i == -ENOENT)
 				break;
 			if (i >= env->prog->len) {
@@ -5122,7 +5126,7 @@ static int check_stack_write_fixed_off(struct bpf_verifier_env *env,
 	}
 
 	if (insn_flags)
-		return push_insn_history(env, env->cur_state, insn_flags, 0);
+		return push_jmp_history(env, env->cur_state, insn_flags, 0);
 	return 0;
 }
 
@@ -5429,7 +5433,7 @@ static int check_stack_read_fixed_off(struct bpf_verifier_env *env,
 		insn_flags = 0; /* we are not restoring spilled register */
 	}
 	if (insn_flags)
-		return push_insn_history(env, env->cur_state, insn_flags, 0);
+		return push_jmp_history(env, env->cur_state, insn_flags, 0);
 	return 0;
 }
 
@@ -16496,7 +16500,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	}
 
 	if (insn_flags) {
-		err = push_insn_history(env, this_branch, insn_flags, 0);
+		err = push_jmp_history(env, this_branch, insn_flags, 0);
 		if (err)
 			return err;
 	}
@@ -16554,7 +16558,7 @@ static int check_cond_jmp_op(struct bpf_verifier_env *env,
 	if (dst_reg->type == SCALAR_VALUE && dst_reg->id)
 		collect_linked_regs(this_branch, dst_reg->id, &linked_regs);
 	if (linked_regs.cnt > 1) {
-		err = push_insn_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
+		err = push_jmp_history(env, this_branch, 0, linked_regs_pack(&linked_regs));
 		if (err)
 			return err;
 	}
@@ -19052,7 +19056,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 
 	force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) ||
 			  /* Avoid accumulating infinitely long jmp history */
-			  cur->insn_hist_end - cur->insn_hist_start > 40;
+			  cur->jmp_history_cnt > 40;
 
 	/* bpf progs typically have pruning point every 4 instructions
 	 * http://vger.kernel.org/bpfconf2019.html#session-1
@@ -19251,7 +19255,7 @@ hit:
 			 * the current state.
 			 */
 			if (is_jmp_point(env, env->insn_idx))
-				err = err ? : push_insn_history(env, cur, 0, 0);
+				err = err ? : push_jmp_history(env, cur, 0, 0);
 			err = err ? : propagate_precision(env, &sl->state);
 			if (err)
 				return err;
@@ -19333,8 +19337,8 @@ miss:
 
 	cur->parent = new;
 	cur->first_insn_idx = insn_idx;
-	cur->insn_hist_start = cur->insn_hist_end;
 	cur->dfs_depth = new->dfs_depth + 1;
+	clear_jmp_history(cur);
 	list_add(&new_sl->node, head);
 
 	/* connect new state to parentage chain. Current frame needs all
@@ -19704,7 +19708,7 @@ static int do_check(struct bpf_verifier_env *env)
 		}
 
 		if (is_jmp_point(env, env->insn_idx)) {
-			err = push_insn_history(env, state, 0, 0);
+			err = push_jmp_history(env, state, 0, 0);
 			if (err)
 				return err;
 		}
@@ -24291,7 +24295,6 @@ err_unlock:
 	if (!is_priv)
 		mutex_unlock(&bpf_verifier_lock);
 	vfree(env->insn_aux_data);
-	kvfree(env->insn_hist);
 err_free_env:
 	kvfree(env->cfg.insn_postorder);
 	kvfree(env);
-- 
cgit v1.2.3


From 96c6aa4c63af0bb0675c41b3e61a2fc7f6fed998 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Wed, 11 Jun 2025 13:08:27 -0700
Subject: bpf: compute SCCs in program control flow graph

Compute strongly connected components in the program CFG.
Assign an SCC number to each instruction, recorded in
env->insn_aux[*].scc. Use Tarjan's algorithm for SCC computation
adapted to run non-recursively.

For debug purposes print out computed SCCs as a part of full program
dump in compute_live_registers() at log level 2, e.g.:

  func#0 @0
  Live regs before insn:
        0: .......... (b4) w6 = 10
    2   1: ......6... (18) r1 = 0xffff88810bbb5565
    2   3: .1....6... (b4) w2 = 2
    2   4: .12...6... (85) call bpf_trace_printk#6
    2   5: ......6... (04) w6 += -1
    2   6: ......6... (56) if w6 != 0x0 goto pc-6
        7: .......... (b4) w6 = 5
    1   8: ......6... (18) r1 = 0xffff88810bbb5567
    1  10: .1....6... (b4) w2 = 2
    1  11: .12...6... (85) call bpf_trace_printk#6
    1  12: ......6... (04) w6 += -1
    1  13: ......6... (56) if w6 != 0x0 goto pc-6
       14: .......... (b4) w0 = 0
       15: 0......... (95) exit
   ^^^
  SCC number for the instruction

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250611200836.4135542-2-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |   5 ++
 kernel/bpf/verifier.c        | 182 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 187 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 3e77befdbc4b..95f5211610f4 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -609,6 +609,11 @@ struct bpf_insn_aux_data {
 	 * accepts callback function as a parameter.
 	 */
 	bool calls_callback;
+	/*
+	 * CFG strongly connected component this instruction belongs to,
+	 * zero if it is a singleton SCC.
+	 */
+	u32 scc;
 	/* registers alive before this instruction. */
 	u16 live_regs_before;
 };
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 92f2dad5f453..75e4f6544b2a 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -24013,6 +24013,10 @@ static int compute_live_registers(struct bpf_verifier_env *env)
 	if (env->log.level & BPF_LOG_LEVEL2) {
 		verbose(env, "Live regs before insn:\n");
 		for (i = 0; i < insn_cnt; ++i) {
+			if (env->insn_aux_data[i].scc)
+				verbose(env, "%3d ", env->insn_aux_data[i].scc);
+			else
+				verbose(env, "    ");
 			verbose(env, "%3d: ", i);
 			for (j = BPF_REG_0; j < BPF_REG_10; ++j)
 				if (insn_aux[i].live_regs_before & BIT(j))
@@ -24034,6 +24038,180 @@ out:
 	return err;
 }
 
+/*
+ * Compute strongly connected components (SCCs) on the CFG.
+ * Assign an SCC number to each instruction, recorded in env->insn_aux[*].scc.
+ * If instruction is a sole member of its SCC and there are no self edges,
+ * assign it SCC number of zero.
+ * Uses a non-recursive adaptation of Tarjan's algorithm for SCC computation.
+ */
+static int compute_scc(struct bpf_verifier_env *env)
+{
+	const u32 NOT_ON_STACK = U32_MAX;
+
+	struct bpf_insn_aux_data *aux = env->insn_aux_data;
+	const u32 insn_cnt = env->prog->len;
+	int stack_sz, dfs_sz, err = 0;
+	u32 *stack, *pre, *low, *dfs;
+	u32 succ_cnt, i, j, t, w;
+	u32 next_preorder_num;
+	u32 next_scc_id;
+	bool assign_scc;
+	u32 succ[2];
+
+	next_preorder_num = 1;
+	next_scc_id = 1;
+	/*
+	 * - 'stack' accumulates vertices in DFS order, see invariant comment below;
+	 * - 'pre[t] == p' => preorder number of vertex 't' is 'p';
+	 * - 'low[t] == n' => smallest preorder number of the vertex reachable from 't' is 'n';
+	 * - 'dfs' DFS traversal stack, used to emulate explicit recursion.
+	 */
+	stack = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	pre = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	low = kvcalloc(insn_cnt, sizeof(int), GFP_KERNEL);
+	dfs = kvcalloc(insn_cnt, sizeof(*dfs), GFP_KERNEL);
+	if (!stack || !pre || !low || !dfs) {
+		err = -ENOMEM;
+		goto exit;
+	}
+	/*
+	 * References:
+	 * [1] R. Tarjan "Depth-First Search and Linear Graph Algorithms"
+	 * [2] D. J. Pearce "A Space-Efficient Algorithm for Finding Strongly Connected Components"
+	 *
+	 * The algorithm maintains the following invariant:
+	 * - suppose there is a path 'u' ~> 'v', such that 'pre[v] < pre[u]';
+	 * - then, vertex 'u' remains on stack while vertex 'v' is on stack.
+	 *
+	 * Consequently:
+	 * - If 'low[v] < pre[v]', there is a path from 'v' to some vertex 'u',
+	 *   such that 'pre[u] == low[v]'; vertex 'u' is currently on the stack,
+	 *   and thus there is an SCC (loop) containing both 'u' and 'v'.
+	 * - If 'low[v] == pre[v]', loops containing 'v' have been explored,
+	 *   and 'v' can be considered the root of some SCC.
+	 *
+	 * Here is a pseudo-code for an explicitly recursive version of the algorithm:
+	 *
+	 *    NOT_ON_STACK = insn_cnt + 1
+	 *    pre = [0] * insn_cnt
+	 *    low = [0] * insn_cnt
+	 *    scc = [0] * insn_cnt
+	 *    stack = []
+	 *
+	 *    next_preorder_num = 1
+	 *    next_scc_id = 1
+	 *
+	 *    def recur(w):
+	 *        nonlocal next_preorder_num
+	 *        nonlocal next_scc_id
+	 *
+	 *        pre[w] = next_preorder_num
+	 *        low[w] = next_preorder_num
+	 *        next_preorder_num += 1
+	 *        stack.append(w)
+	 *        for s in successors(w):
+	 *            # Note: for classic algorithm the block below should look as:
+	 *            #
+	 *            # if pre[s] == 0:
+	 *            #     recur(s)
+	 *            #	    low[w] = min(low[w], low[s])
+	 *            # elif low[s] != NOT_ON_STACK:
+	 *            #     low[w] = min(low[w], pre[s])
+	 *            #
+	 *            # But replacing both 'min' instructions with 'low[w] = min(low[w], low[s])'
+	 *            # does not break the invariant and makes itartive version of the algorithm
+	 *            # simpler. See 'Algorithm #3' from [2].
+	 *
+	 *            # 's' not yet visited
+	 *            if pre[s] == 0:
+	 *                recur(s)
+	 *            # if 's' is on stack, pick lowest reachable preorder number from it;
+	 *            # if 's' is not on stack 'low[s] == NOT_ON_STACK > low[w]',
+	 *            # so 'min' would be a noop.
+	 *            low[w] = min(low[w], low[s])
+	 *
+	 *        if low[w] == pre[w]:
+	 *            # 'w' is the root of an SCC, pop all vertices
+	 *            # below 'w' on stack and assign same SCC to them.
+	 *            while True:
+	 *                t = stack.pop()
+	 *                low[t] = NOT_ON_STACK
+	 *                scc[t] = next_scc_id
+	 *                if t == w:
+	 *                    break
+	 *            next_scc_id += 1
+	 *
+	 *    for i in range(0, insn_cnt):
+	 *        if pre[i] == 0:
+	 *            recur(i)
+	 *
+	 * Below implementation replaces explicit recusion with array 'dfs'.
+	 */
+	for (i = 0; i < insn_cnt; i++) {
+		if (pre[i])
+			continue;
+		stack_sz = 0;
+		dfs_sz = 1;
+		dfs[0] = i;
+dfs_continue:
+		while (dfs_sz) {
+			w = dfs[dfs_sz - 1];
+			if (pre[w] == 0) {
+				low[w] = next_preorder_num;
+				pre[w] = next_preorder_num;
+				next_preorder_num++;
+				stack[stack_sz++] = w;
+			}
+			/* Visit 'w' successors */
+			succ_cnt = insn_successors(env->prog, w, succ);
+			for (j = 0; j < succ_cnt; ++j) {
+				if (pre[succ[j]]) {
+					low[w] = min(low[w], low[succ[j]]);
+				} else {
+					dfs[dfs_sz++] = succ[j];
+					goto dfs_continue;
+				}
+			}
+			/*
+			 * Preserve the invariant: if some vertex above in the stack
+			 * is reachable from 'w', keep 'w' on the stack.
+			 */
+			if (low[w] < pre[w]) {
+				dfs_sz--;
+				goto dfs_continue;
+			}
+			/*
+			 * Assign SCC number only if component has two or more elements,
+			 * or if component has a self reference.
+			 */
+			assign_scc = stack[stack_sz - 1] != w;
+			for (j = 0; j < succ_cnt; ++j) {
+				if (succ[j] == w) {
+					assign_scc = true;
+					break;
+				}
+			}
+			/* Pop component elements from stack */
+			do {
+				t = stack[--stack_sz];
+				low[t] = NOT_ON_STACK;
+				if (assign_scc)
+					aux[t].scc = next_scc_id;
+			} while (t != w);
+			if (assign_scc)
+				next_scc_id++;
+			dfs_sz--;
+		}
+	}
+exit:
+	kvfree(stack);
+	kvfree(pre);
+	kvfree(low);
+	kvfree(dfs);
+	return err;
+}
+
 int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u32 uattr_size)
 {
 	u64 start_time = ktime_get_ns();
@@ -24155,6 +24333,10 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr, bpfptr_t uattr, __u3
 	if (ret)
 		goto skip_full_check;
 
+	ret = compute_scc(env);
+	if (ret < 0)
+		goto skip_full_check;
+
 	ret = compute_live_registers(env);
 	if (ret < 0)
 		goto skip_full_check;
-- 
cgit v1.2.3


From c9e31900b54cadf5398dfb838c0a63effa1defec Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Wed, 11 Jun 2025 13:08:33 -0700
Subject: bpf: propagate read/precision marks over state graph backedges

Current loop_entry-based exact states comparison logic does not handle
the following case:

 .-> A --.  Assume the states are visited in the order A, B, C.
 |   |   |  Assume that state B reaches a state equivalent to state A.
 |   v   v  At this point, state C is not processed yet, so state A
 '-- B   C  has not received any read or precision marks from C.
            As a result, these marks won't be propagated to B.

If B has incomplete marks, it is unsafe to use it in states_equal()
checks.

This commit replaces the existing logic with the following:
- Strongly connected components (SCCs) are computed over the program's
  control flow graph (intraprocedurally).
- When a verifier state enters an SCC, that state is recorded as the
  SCC entry point.
- When a verifier state is found equivalent to another (e.g., B to A
  in the example), it is recorded as a states graph backedge.
  Backedges are accumulated per SCC.
- When an SCC entry state reaches `branches == 0`, read and precision
  marks are propagated through the backedges (e.g., from A to B, from
  C to A, and then again from A to B).

To support nested subprogram calls, the entry state and backedge list
are associated not with the SCC itself but with an object called
`bpf_scc_callchain`. A callchain is a tuple `(callsite*, scc_id)`,
where `callsite` is the index of a call instruction for each frame
except the last.

See the comments added in `is_state_visited()` and
`compute_scc_callchain()` for more details.

Fixes: 2a0992829ea3 ("bpf: correct loop detection for iterators convergence")
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250611200836.4135542-8-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  38 ++++
 kernel/bpf/verifier.c        | 452 ++++++++++++++++++++++++++++++++++++-------
 2 files changed, 422 insertions(+), 68 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 95f5211610f4..b0273f759589 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -459,6 +459,10 @@ struct bpf_verifier_state {
 	 * See get_loop_entry() for more information.
 	 */
 	struct bpf_verifier_state *loop_entry;
+	/* if this state is a backedge state then equal_state
+	 * records cached state to which this state is equal.
+	 */
+	struct bpf_verifier_state *equal_state;
 	/* jmp history recorded from first to last.
 	 * backtracking is using it to go from last to first.
 	 * For most states jmp_history_cnt is [0-3].
@@ -723,6 +727,37 @@ struct bpf_idset {
 	u32 ids[BPF_ID_MAP_SIZE];
 };
 
+/* see verifier.c:compute_scc_callchain() */
+struct bpf_scc_callchain {
+	/* call sites from bpf_verifier_state->frame[*]->callsite leading to this SCC */
+	u32 callsites[MAX_CALL_FRAMES - 1];
+	/* last frame in a chain is identified by SCC id */
+	u32 scc;
+};
+
+/* verifier state waiting for propagate_backedges() */
+struct bpf_scc_backedge {
+	struct bpf_scc_backedge *next;
+	struct bpf_verifier_state state;
+};
+
+struct bpf_scc_visit {
+	struct bpf_scc_callchain callchain;
+	/* first state in current verification path that entered SCC
+	 * identified by the callchain
+	 */
+	struct bpf_verifier_state *entry_state;
+	struct bpf_scc_backedge *backedges; /* list of backedges */
+};
+
+/* An array of bpf_scc_visit structs sharing tht same bpf_scc_callchain->scc
+ * but having different bpf_scc_callchain->callsites.
+ */
+struct bpf_scc_info {
+	u32 num_visits;
+	struct bpf_scc_visit visits[];
+};
+
 /* single container for all structs
  * one verifier_env per bpf_check() call
  */
@@ -819,6 +854,9 @@ struct bpf_verifier_env {
 	char tmp_str_buf[TMP_STR_BUF_LEN];
 	struct bpf_insn insn_buf[INSN_BUF_SIZE];
 	struct bpf_insn epilogue_buf[INSN_BUF_SIZE];
+	/* array of pointers to bpf_scc_info indexed by SCC id */
+	struct bpf_scc_info **scc_info;
+	u32 scc_cnt;
 };
 
 static inline struct bpf_func_info_aux *subprog_aux(struct bpf_verifier_env *env, int subprog)
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 90b3d1a0bd86..aa1bb4be7b8b 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1700,6 +1700,9 @@ static struct bpf_verifier_state_list *state_loop_entry_as_list(struct bpf_verif
 	return NULL;
 }
 
+static bool incomplete_read_marks(struct bpf_verifier_env *env,
+				  struct bpf_verifier_state *st);
+
 /* A state can be freed if it is no longer referenced:
  * - is in the env->free_list;
  * - has no children states;
@@ -1710,20 +1713,14 @@ static struct bpf_verifier_state_list *state_loop_entry_as_list(struct bpf_verif
 static void maybe_free_verifier_state(struct bpf_verifier_env *env,
 				      struct bpf_verifier_state_list *sl)
 {
-	struct bpf_verifier_state_list *loop_entry_sl;
-
-	while (sl && sl->in_free_list &&
-		     sl->state.branches == 0 &&
-		     sl->state.used_as_loop_entry == 0) {
-		loop_entry_sl = state_loop_entry_as_list(&sl->state);
-		if (loop_entry_sl)
-			loop_entry_sl->state.used_as_loop_entry--;
-		list_del(&sl->node);
-		free_verifier_state(&sl->state, false);
-		kfree(sl);
-		env->free_list_size--;
-		sl = loop_entry_sl;
-	}
+	if (!sl->in_free_list
+	    || sl->state.branches != 0
+	    || incomplete_read_marks(env, &sl->state))
+		return;
+	list_del(&sl->node);
+	free_verifier_state(&sl->state, false);
+	kfree(sl);
+	env->free_list_size--;
 }
 
 /* copy verifier state from src to dst growing dst stack space
@@ -1771,6 +1768,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	dst_state->used_as_loop_entry = src->used_as_loop_entry;
 	dst_state->may_goto_depth = src->may_goto_depth;
 	dst_state->loop_entry = src->loop_entry;
+	dst_state->equal_state = src->equal_state;
 	for (i = 0; i <= src->curframe; i++) {
 		dst = dst_state->frame[i];
 		if (!dst) {
@@ -1972,22 +1970,218 @@ static u32 frame_insn_idx(struct bpf_verifier_state *st, u32 frame)
 	       : st->frame[frame + 1]->callsite;
 }
 
-static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+/* For state @st look for a topmost frame with frame_insn_idx() in some SCC,
+ * if such frame exists form a corresponding @callchain as an array of
+ * call sites leading to this frame and SCC id.
+ * E.g.:
+ *
+ *    void foo()  { A: loop {... SCC#1 ...}; }
+ *    void bar()  { B: loop { C: foo(); ... SCC#2 ... }
+ *                  D: loop { E: foo(); ... SCC#3 ... } }
+ *    void main() { F: bar(); }
+ *
+ * @callchain at (A) would be either (F,SCC#2) or (F,SCC#3) depending
+ * on @st frame call sites being (F,C,A) or (F,E,A).
+ */
+static bool compute_scc_callchain(struct bpf_verifier_env *env,
+				  struct bpf_verifier_state *st,
+				  struct bpf_scc_callchain *callchain)
+{
+	u32 i, scc, insn_idx;
+
+	memset(callchain, 0, sizeof(*callchain));
+	for (i = 0; i <= st->curframe; i++) {
+		insn_idx = frame_insn_idx(st, i);
+		scc = env->insn_aux_data[insn_idx].scc;
+		if (scc) {
+			callchain->scc = scc;
+			break;
+		} else if (i < st->curframe) {
+			callchain->callsites[i] = insn_idx;
+		} else {
+			return false;
+		}
+	}
+	return true;
+}
+
+/* Check if bpf_scc_visit instance for @callchain exists. */
+static struct bpf_scc_visit *scc_visit_lookup(struct bpf_verifier_env *env,
+					      struct bpf_scc_callchain *callchain)
+{
+	struct bpf_scc_info *info = env->scc_info[callchain->scc];
+	struct bpf_scc_visit *visits = info->visits;
+	u32 i;
+
+	if (!info)
+		return NULL;
+	for (i = 0; i < info->num_visits; i++)
+		if (memcmp(callchain, &visits[i].callchain, sizeof(*callchain)) == 0)
+			return &visits[i];
+	return NULL;
+}
+
+/* Allocate a new bpf_scc_visit instance corresponding to @callchain.
+ * Allocated instances are alive for a duration of the do_check_common()
+ * call and are freed by free_states().
+ */
+static struct bpf_scc_visit *scc_visit_alloc(struct bpf_verifier_env *env,
+					     struct bpf_scc_callchain *callchain)
+{
+	struct bpf_scc_visit *visit;
+	struct bpf_scc_info *info;
+	u32 scc, num_visits;
+	u64 new_sz;
+
+	scc = callchain->scc;
+	info = env->scc_info[scc];
+	num_visits = info ? info->num_visits : 0;
+	new_sz = sizeof(*info) + sizeof(struct bpf_scc_visit) * (num_visits + 1);
+	info = kvrealloc(env->scc_info[scc], new_sz, GFP_KERNEL);
+	if (!info)
+		return NULL;
+	env->scc_info[scc] = info;
+	info->num_visits = num_visits + 1;
+	visit = &info->visits[num_visits];
+	memset(visit, 0, sizeof(*visit));
+	memcpy(&visit->callchain, callchain, sizeof(*callchain));
+	return visit;
+}
+
+/* Form a string '(callsite#1,callsite#2,...,scc)' in env->tmp_str_buf */
+static char *format_callchain(struct bpf_verifier_env *env, struct bpf_scc_callchain *callchain)
+{
+	char *buf = env->tmp_str_buf;
+	int i, delta = 0;
+
+	delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "(");
+	for (i = 0; i < ARRAY_SIZE(callchain->callsites); i++) {
+		if (!callchain->callsites[i])
+			break;
+		delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u,",
+				  callchain->callsites[i]);
+	}
+	delta += snprintf(buf + delta, TMP_STR_BUF_LEN - delta, "%u)", callchain->scc);
+	return env->tmp_str_buf;
+}
+
+/* If callchain for @st exists (@st is in some SCC), ensure that
+ * bpf_scc_visit instance for this callchain exists.
+ * If instance does not exist or is empty, assign visit->entry_state to @st.
+ */
+static int maybe_enter_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+	struct bpf_scc_callchain callchain;
+	struct bpf_scc_visit *visit;
+
+	if (!compute_scc_callchain(env, st, &callchain))
+		return 0;
+	visit = scc_visit_lookup(env, &callchain);
+	visit = visit ?: scc_visit_alloc(env, &callchain);
+	if (!visit)
+		return -ENOMEM;
+	if (!visit->entry_state) {
+		visit->entry_state = st;
+		if (env->log.level & BPF_LOG_LEVEL2)
+			verbose(env, "SCC enter %s\n", format_callchain(env, &callchain));
+	}
+	return 0;
+}
+
+static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit);
+
+/* If callchain for @st exists (@st is in some SCC), make it empty:
+ * - set visit->entry_state to NULL;
+ * - flush accumulated backedges.
+ */
+static int maybe_exit_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
+{
+	struct bpf_scc_callchain callchain;
+	struct bpf_scc_visit *visit;
+
+	if (!compute_scc_callchain(env, st, &callchain))
+		return 0;
+	visit = scc_visit_lookup(env, &callchain);
+	if (!visit) {
+		verifier_bug(env, "scc exit: no visit info for call chain %s",
+			     format_callchain(env, &callchain));
+		return -EFAULT;
+	}
+	if (visit->entry_state != st)
+		return 0;
+	if (env->log.level & BPF_LOG_LEVEL2)
+		verbose(env, "SCC exit %s\n", format_callchain(env, &callchain));
+	visit->entry_state = NULL;
+	return propagate_backedges(env, visit);
+}
+
+/* Lookup an bpf_scc_visit instance corresponding to @st callchain
+ * and add @backedge to visit->backedges. @st callchain must exist.
+ */
+static int add_scc_backedge(struct bpf_verifier_env *env,
+			    struct bpf_verifier_state *st,
+			    struct bpf_scc_backedge *backedge)
+{
+	struct bpf_scc_callchain callchain;
+	struct bpf_scc_visit *visit;
+
+	if (!compute_scc_callchain(env, st, &callchain)) {
+		verifier_bug(env, "add backedge: no SCC in verification path, insn_idx %d",
+			     st->insn_idx);
+		return -EFAULT;
+	}
+	visit = scc_visit_lookup(env, &callchain);
+	if (!visit) {
+		verifier_bug(env, "add backedge: no visit info for call chain %s",
+			     format_callchain(env, &callchain));
+		return -EFAULT;
+	}
+	if (env->log.level & BPF_LOG_LEVEL2)
+		verbose(env, "SCC backedge %s\n", format_callchain(env, &callchain));
+	backedge->next = visit->backedges;
+	visit->backedges = backedge;
+	return 0;
+}
+
+/* bpf_reg_state->live marks for registers in a state @st are incomplete,
+ * if state @st is in some SCC and not all execution paths starting at this
+ * SCC are fully explored.
+ */
+static bool incomplete_read_marks(struct bpf_verifier_env *env,
+				  struct bpf_verifier_state *st)
+{
+	struct bpf_scc_callchain callchain;
+	struct bpf_scc_visit *visit;
+
+	if (!compute_scc_callchain(env, st, &callchain))
+		return false;
+	visit = scc_visit_lookup(env, &callchain);
+	if (!visit)
+		return false;
+	return !!visit->backedges;
+}
+
+static void free_backedges(struct bpf_scc_visit *visit)
+{
+	struct bpf_scc_backedge *backedge, *next;
+
+	for (backedge = visit->backedges; backedge; backedge = next) {
+		free_verifier_state(&backedge->state, false);
+		next = backedge->next;
+		kvfree(backedge);
+	}
+	visit->backedges = NULL;
+}
+
+static int update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
 {
 	struct bpf_verifier_state_list *sl = NULL, *parent_sl;
 	struct bpf_verifier_state *parent;
+	int err;
 
 	while (st) {
 		u32 br = --st->branches;
 
-		/* br == 0 signals that DFS exploration for 'st' is finished,
-		 * thus it is necessary to update parent's loop entry if it
-		 * turned out that st is a part of some loop.
-		 * This is a part of 'case A' in get_loop_entry() comment.
-		 */
-		if (br == 0 && st->parent && st->loop_entry)
-			update_loop_entry(env, st->parent, st->loop_entry);
-
 		/* WARN_ON(br > 1) technically makes sense here,
 		 * but see comment in push_stack(), hence:
 		 */
@@ -1996,6 +2190,9 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi
 			  br);
 		if (br)
 			break;
+		err = maybe_exit_scc(env, st);
+		if (err)
+			return err;
 		parent = st->parent;
 		parent_sl = state_parent_as_list(st);
 		if (sl)
@@ -2003,6 +2200,7 @@ static void update_branch_counts(struct bpf_verifier_env *env, struct bpf_verifi
 		st = parent;
 		sl = parent_sl;
 	}
+	return 0;
 }
 
 static int pop_stack(struct bpf_verifier_env *env, int *prev_insn_idx,
@@ -18344,7 +18542,6 @@ static void clean_verifier_state(struct bpf_verifier_env *env,
 static void clean_live_states(struct bpf_verifier_env *env, int insn,
 			      struct bpf_verifier_state *cur)
 {
-	struct bpf_verifier_state *loop_entry;
 	struct bpf_verifier_state_list *sl;
 	struct list_head *pos, *head;
 
@@ -18353,15 +18550,14 @@ static void clean_live_states(struct bpf_verifier_env *env, int insn,
 		sl = container_of(pos, struct bpf_verifier_state_list, node);
 		if (sl->state.branches)
 			continue;
-		loop_entry = get_loop_entry(env, &sl->state);
-		if (!IS_ERR_OR_NULL(loop_entry) && loop_entry->branches)
-			continue;
 		if (sl->state.insn_idx != insn ||
 		    !same_callsites(&sl->state, cur))
 			continue;
 		if (sl->state.frame[0]->regs[0].live & REG_LIVE_DONE)
 			/* all regs in this state in all frames were already marked */
 			continue;
+		if (incomplete_read_marks(env, &sl->state))
+			continue;
 		clean_verifier_state(env, &sl->state);
 	}
 }
@@ -18963,6 +19159,46 @@ static int propagate_precision(struct bpf_verifier_env *env,
 	return 0;
 }
 
+#define MAX_BACKEDGE_ITERS 64
+
+/* Propagate read and precision marks from visit->backedges[*].state->equal_state
+ * to corresponding parent states of visit->backedges[*].state until fixed point is reached,
+ * then free visit->backedges.
+ * After execution of this function incomplete_read_marks() will return false
+ * for all states corresponding to @visit->callchain.
+ */
+static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visit *visit)
+{
+	struct bpf_scc_backedge *backedge;
+	struct bpf_verifier_state *st;
+	bool changed;
+	int i, err;
+
+	i = 0;
+	do {
+		if (i++ > MAX_BACKEDGE_ITERS) {
+			if (env->log.level & BPF_LOG_LEVEL2)
+				verbose(env, "%s: too many iterations\n", __func__);
+			for (backedge = visit->backedges; backedge; backedge = backedge->next)
+				mark_all_scalars_precise(env, &backedge->state);
+			break;
+		}
+		changed = false;
+		for (backedge = visit->backedges; backedge; backedge = backedge->next) {
+			st = &backedge->state;
+			err = propagate_liveness(env, st->equal_state, st, &changed);
+			if (err)
+				return err;
+			err = propagate_precision(env, st->equal_state, st, &changed);
+			if (err)
+				return err;
+		}
+	} while (changed);
+
+	free_backedges(visit);
+	return 0;
+}
+
 static bool states_maybe_looping(struct bpf_verifier_state *old,
 				 struct bpf_verifier_state *cur)
 {
@@ -19072,9 +19308,9 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 {
 	struct bpf_verifier_state_list *new_sl;
 	struct bpf_verifier_state_list *sl;
-	struct bpf_verifier_state *cur = env->cur_state, *new, *loop_entry;
+	struct bpf_verifier_state *cur = env->cur_state, *new;
+	bool force_new_state, add_new_state, loop;
 	int i, j, n, err, states_cnt = 0;
-	bool force_new_state, add_new_state, force_exact;
 	struct list_head *pos, *tmp, *head;
 
 	force_new_state = env->test_state_freq || is_force_checkpoint(env, insn_idx) ||
@@ -19096,6 +19332,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 
 	clean_live_states(env, insn_idx, cur);
 
+	loop = false;
 	head = explored_state(env, insn_idx);
 	list_for_each_safe(pos, tmp, head) {
 		sl = container_of(pos, struct bpf_verifier_state_list, node);
@@ -19175,7 +19412,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 					spi = __get_spi(iter_reg->off + iter_reg->var_off.value);
 					iter_state = &func(env, iter_reg)->stack[spi].spilled_ptr;
 					if (iter_state->iter.state == BPF_ITER_STATE_ACTIVE) {
-						update_loop_entry(env, cur, &sl->state);
+						loop = true;
 						goto hit;
 					}
 				}
@@ -19184,7 +19421,7 @@ static int is_state_visited(struct bpf_verifier_env *env, int insn_idx)
 			if (is_may_goto_insn_at(env, insn_idx)) {
 				if (sl->state.may_goto_depth != cur->may_goto_depth &&
 				    states_equal(env, &sl->state, cur, RANGE_WITHIN)) {
-					update_loop_entry(env, cur, &sl->state);
+					loop = true;
 					goto hit;
 				}
 			}
@@ -19226,38 +19463,9 @@ skip_inf_loop_check:
 				add_new_state = false;
 			goto miss;
 		}
-		/* If sl->state is a part of a loop and this loop's entry is a part of
-		 * current verification path then states have to be compared exactly.
-		 * 'force_exact' is needed to catch the following case:
-		 *
-		 *                initial     Here state 'succ' was processed first,
-		 *                  |         it was eventually tracked to produce a
-		 *                  V         state identical to 'hdr'.
-		 *     .---------> hdr        All branches from 'succ' had been explored
-		 *     |            |         and thus 'succ' has its .branches == 0.
-		 *     |            V
-		 *     |    .------...        Suppose states 'cur' and 'succ' correspond
-		 *     |    |       |         to the same instruction + callsites.
-		 *     |    V       V         In such case it is necessary to check
-		 *     |   ...     ...        if 'succ' and 'cur' are states_equal().
-		 *     |    |       |         If 'succ' and 'cur' are a part of the
-		 *     |    V       V         same loop exact flag has to be set.
-		 *     |   succ <- cur        To check if that is the case, verify
-		 *     |    |                 if loop entry of 'succ' is in current
-		 *     |    V                 DFS path.
-		 *     |   ...
-		 *     |    |
-		 *     '----'
-		 *
-		 * Additional details are in the comment before get_loop_entry().
-		 */
-		loop_entry = get_loop_entry(env, &sl->state);
-		if (IS_ERR(loop_entry))
-			return PTR_ERR(loop_entry);
-		force_exact = loop_entry && loop_entry->branches > 0;
-		if (states_equal(env, &sl->state, cur, force_exact ? RANGE_WITHIN : NOT_EXACT)) {
-			if (force_exact)
-				update_loop_entry(env, cur, loop_entry);
+		/* See comments for mark_all_regs_read_and_precise() */
+		loop = incomplete_read_marks(env, &sl->state);
+		if (states_equal(env, &sl->state, cur, loop ? RANGE_WITHIN : NOT_EXACT)) {
 hit:
 			sl->hit_cnt++;
 			/* reached equivalent register/stack state,
@@ -19282,6 +19490,94 @@ hit:
 			err = err ? : propagate_precision(env, &sl->state, cur, NULL);
 			if (err)
 				return err;
+			/* When processing iterator based loops above propagate_liveness and
+			 * propagate_precision calls are not sufficient to transfer all relevant
+			 * read and precision marks. E.g. consider the following case:
+			 *
+			 *  .-> A --.  Assume the states are visited in the order A, B, C.
+			 *  |   |   |  Assume that state B reaches a state equivalent to state A.
+			 *  |   v   v  At this point, state C is not processed yet, so state A
+			 *  '-- B   C  has not received any read or precision marks from C.
+			 *             Thus, marks propagated from A to B are incomplete.
+			 *
+			 * The verifier mitigates this by performing the following steps:
+			 *
+			 * - Prior to the main verification pass, strongly connected components
+			 *   (SCCs) are computed over the program's control flow graph,
+			 *   intraprocedurally.
+			 *
+			 * - During the main verification pass, `maybe_enter_scc()` checks
+			 *   whether the current verifier state is entering an SCC. If so, an
+			 *   instance of a `bpf_scc_visit` object is created, and the state
+			 *   entering the SCC is recorded as the entry state.
+			 *
+			 * - This instance is associated not with the SCC itself, but with a
+			 *   `bpf_scc_callchain`: a tuple consisting of the call sites leading to
+			 *   the SCC and the SCC id. See `compute_scc_callchain()`.
+			 *
+			 * - When a verification path encounters a `states_equal(...,
+			 *   RANGE_WITHIN)` condition, there exists a call chain describing the
+			 *   current state and a corresponding `bpf_scc_visit` instance. A copy
+			 *   of the current state is created and added to
+			 *   `bpf_scc_visit->backedges`.
+			 *
+			 * - When a verification path terminates, `maybe_exit_scc()` is called
+			 *   from `update_branch_counts()`. For states with `branches == 0`, it
+			 *   checks whether the state is the entry state of any `bpf_scc_visit`
+			 *   instance. If it is, this indicates that all paths originating from
+			 *   this SCC visit have been explored. `propagate_backedges()` is then
+			 *   called, which propagates read and precision marks through the
+			 *   backedges until a fixed point is reached.
+			 *   (In the earlier example, this would propagate marks from A to B,
+			 *    from C to A, and then again from A to B.)
+			 *
+			 * A note on callchains
+			 * --------------------
+			 *
+			 * Consider the following example:
+			 *
+			 *     void foo() { loop { ... SCC#1 ... } }
+			 *     void main() {
+			 *       A: foo();
+			 *       B: ...
+			 *       C: foo();
+			 *     }
+			 *
+			 * Here, there are two distinct callchains leading to SCC#1:
+			 * - (A, SCC#1)
+			 * - (C, SCC#1)
+			 *
+			 * Each callchain identifies a separate `bpf_scc_visit` instance that
+			 * accumulates backedge states. The `propagate_{liveness,precision}()`
+			 * functions traverse the parent state of each backedge state, which
+			 * means these parent states must remain valid (i.e., not freed) while
+			 * the corresponding `bpf_scc_visit` instance exists.
+			 *
+			 * Associating `bpf_scc_visit` instances directly with SCCs instead of
+			 * callchains would break this invariant:
+			 * - States explored during `C: foo()` would contribute backedges to
+			 *   SCC#1, but SCC#1 would only be exited once the exploration of
+			 *   `A: foo()` completes.
+			 * - By that time, the states explored between `A: foo()` and `C: foo()`
+			 *   (i.e., `B: ...`) may have already been freed, causing the parent
+			 *   links for states from `C: foo()` to become invalid.
+			 */
+			if (loop) {
+				struct bpf_scc_backedge *backedge;
+
+				backedge = kzalloc(sizeof(*backedge), GFP_KERNEL);
+				if (!backedge)
+					return -ENOMEM;
+				err = copy_verifier_state(&backedge->state, cur);
+				backedge->state.equal_state = &sl->state;
+				backedge->state.insn_idx = insn_idx;
+				err = err ?: add_scc_backedge(env, &sl->state, backedge);
+				if (err) {
+					free_verifier_state(&backedge->state, false);
+					kvfree(backedge);
+					return err;
+				}
+			}
 			return 1;
 		}
 miss:
@@ -19357,6 +19653,12 @@ miss:
 	new->insn_idx = insn_idx;
 	WARN_ONCE(new->branches != 1,
 		  "BUG is_state_visited:branches_to_explore=%d insn %d\n", new->branches, insn_idx);
+	err = maybe_enter_scc(env, new);
+	if (err) {
+		free_verifier_state(new, false);
+		kvfree(new_sl);
+		return err;
+	}
 
 	cur->parent = new;
 	cur->first_insn_idx = insn_idx;
@@ -19811,7 +20113,9 @@ static int do_check(struct bpf_verifier_env *env)
 			WARN_ON_ONCE(env->insn_idx != prev_insn_idx + 1);
 process_bpf_exit:
 			mark_verifier_state_scratched(env);
-			update_branch_counts(env, env->cur_state);
+			err = update_branch_counts(env, env->cur_state);
+			if (err)
+				return err;
 			err = pop_stack(env, &prev_insn_idx, &env->insn_idx,
 					pop_log);
 			if (err < 0) {
@@ -19819,9 +20123,6 @@ process_bpf_exit:
 					return err;
 				break;
 			} else {
-				if (verifier_bug_if(env->cur_state->loop_entry, env,
-						    "broken loop detection"))
-					return -EFAULT;
 				do_print_state = true;
 				continue;
 			}
@@ -22787,7 +23088,8 @@ static void free_states(struct bpf_verifier_env *env)
 {
 	struct bpf_verifier_state_list *sl;
 	struct list_head *head, *pos, *tmp;
-	int i;
+	struct bpf_scc_info *info;
+	int i, j;
 
 	list_for_each_safe(pos, tmp, &env->free_list) {
 		sl = container_of(pos, struct bpf_verifier_state_list, node);
@@ -22796,6 +23098,14 @@ static void free_states(struct bpf_verifier_env *env)
 	}
 	INIT_LIST_HEAD(&env->free_list);
 
+	for (i = 0; i < env->scc_cnt; ++i) {
+		info = env->scc_info[i];
+		for (j = 0; j < info->num_visits; j++)
+			free_backedges(&info->visits[j]);
+		kvfree(info);
+		env->scc_info[i] = NULL;
+	}
+
 	if (!env->explored_states)
 		return;
 
@@ -24228,6 +24538,11 @@ dfs_continue:
 			dfs_sz--;
 		}
 	}
+	env->scc_info = kvcalloc(next_scc_id, sizeof(*env->scc_info), GFP_KERNEL);
+	if (!env->scc_info) {
+		err = -ENOMEM;
+		goto exit;
+	}
 exit:
 	kvfree(stack);
 	kvfree(pre);
@@ -24503,6 +24818,7 @@ err_unlock:
 	vfree(env->insn_aux_data);
 err_free_env:
 	kvfree(env->cfg.insn_postorder);
+	kvfree(env->scc_info);
 	kvfree(env);
 	return ret;
 }
-- 
cgit v1.2.3


From 0e0da5f901f582b97bfeefbf1f36a27e9d427ff4 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Wed, 11 Jun 2025 13:08:34 -0700
Subject: bpf: remove {update,get}_loop_entry functions

The previous patch switched read and precision tracking for
iterator-based loops from state-graph-based loop tracking to
control-flow-graph-based loop tracking.

This patch removes the now-unused `update_loop_entry()` and
`get_loop_entry()` functions, which were part of the state-graph-based
logic.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250611200836.4135542-9-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  15 ----
 kernel/bpf/verifier.c        | 165 +------------------------------------------
 2 files changed, 1 insertion(+), 179 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index b0273f759589..1ae588679e20 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -449,16 +449,6 @@ struct bpf_verifier_state {
 	/* first and last insn idx of this verifier state */
 	u32 first_insn_idx;
 	u32 last_insn_idx;
-	/* If this state is a part of states loop this field points to some
-	 * parent of this state such that:
-	 * - it is also a member of the same states loop;
-	 * - DFS states traversal starting from initial state visits loop_entry
-	 *   state before this state.
-	 * Used to compute topmost loop entry for state loops.
-	 * State loops might appear because of open coded iterators logic.
-	 * See get_loop_entry() for more information.
-	 */
-	struct bpf_verifier_state *loop_entry;
 	/* if this state is a backedge state then equal_state
 	 * records cached state to which this state is equal.
 	 */
@@ -473,11 +463,6 @@ struct bpf_verifier_state {
 	u32 dfs_depth;
 	u32 callback_unroll_depth;
 	u32 may_goto_depth;
-	/* If this state was ever pointed-to by other state's loop_entry field
-	 * this flag would be set to true. Used to avoid freeing such states
-	 * while they are still in use.
-	 */
-	u32 used_as_loop_entry;
 };
 
 #define bpf_get_spilled_reg(slot, frame, mask)				\
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index aa1bb4be7b8b..48847f8da5b1 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1682,7 +1682,7 @@ static void free_verifier_state(struct bpf_verifier_state *state,
 		kfree(state);
 }
 
-/* struct bpf_verifier_state->{parent,loop_entry} refer to states
+/* struct bpf_verifier_state->parent refers to states
  * that are in either of env->{expored_states,free_list}.
  * In both cases the state is contained in struct bpf_verifier_state_list.
  */
@@ -1693,22 +1693,12 @@ static struct bpf_verifier_state_list *state_parent_as_list(struct bpf_verifier_
 	return NULL;
 }
 
-static struct bpf_verifier_state_list *state_loop_entry_as_list(struct bpf_verifier_state *st)
-{
-	if (st->loop_entry)
-		return container_of(st->loop_entry, struct bpf_verifier_state_list, state);
-	return NULL;
-}
-
 static bool incomplete_read_marks(struct bpf_verifier_env *env,
 				  struct bpf_verifier_state *st);
 
 /* A state can be freed if it is no longer referenced:
  * - is in the env->free_list;
  * - has no children states;
- * - is not used as loop_entry.
- *
- * Freeing a state can make it's loop_entry free-able.
  */
 static void maybe_free_verifier_state(struct bpf_verifier_env *env,
 				      struct bpf_verifier_state_list *sl)
@@ -1765,9 +1755,7 @@ static int copy_verifier_state(struct bpf_verifier_state *dst_state,
 	dst_state->last_insn_idx = src->last_insn_idx;
 	dst_state->dfs_depth = src->dfs_depth;
 	dst_state->callback_unroll_depth = src->callback_unroll_depth;
-	dst_state->used_as_loop_entry = src->used_as_loop_entry;
 	dst_state->may_goto_depth = src->may_goto_depth;
-	dst_state->loop_entry = src->loop_entry;
 	dst_state->equal_state = src->equal_state;
 	for (i = 0; i <= src->curframe; i++) {
 		dst = dst_state->frame[i];
@@ -1811,157 +1799,6 @@ static bool same_callsites(struct bpf_verifier_state *a, struct bpf_verifier_sta
 	return true;
 }
 
-/* Open coded iterators allow back-edges in the state graph in order to
- * check unbounded loops that iterators.
- *
- * In is_state_visited() it is necessary to know if explored states are
- * part of some loops in order to decide whether non-exact states
- * comparison could be used:
- * - non-exact states comparison establishes sub-state relation and uses
- *   read and precision marks to do so, these marks are propagated from
- *   children states and thus are not guaranteed to be final in a loop;
- * - exact states comparison just checks if current and explored states
- *   are identical (and thus form a back-edge).
- *
- * Paper "A New Algorithm for Identifying Loops in Decompilation"
- * by Tao Wei, Jian Mao, Wei Zou and Yu Chen [1] presents a convenient
- * algorithm for loop structure detection and gives an overview of
- * relevant terminology. It also has helpful illustrations.
- *
- * [1] https://api.semanticscholar.org/CorpusID:15784067
- *
- * We use a similar algorithm but because loop nested structure is
- * irrelevant for verifier ours is significantly simpler and resembles
- * strongly connected components algorithm from Sedgewick's textbook.
- *
- * Define topmost loop entry as a first node of the loop traversed in a
- * depth first search starting from initial state. The goal of the loop
- * tracking algorithm is to associate topmost loop entries with states
- * derived from these entries.
- *
- * For each step in the DFS states traversal algorithm needs to identify
- * the following situations:
- *
- *          initial                     initial                   initial
- *            |                           |                         |
- *            V                           V                         V
- *           ...                         ...           .---------> hdr
- *            |                           |            |            |
- *            V                           V            |            V
- *           cur                     .-> succ          |    .------...
- *            |                      |    |            |    |       |
- *            V                      |    V            |    V       V
- *           succ                    '-- cur           |   ...     ...
- *                                                     |    |       |
- *                                                     |    V       V
- *                                                     |   succ <- cur
- *                                                     |    |
- *                                                     |    V
- *                                                     |   ...
- *                                                     |    |
- *                                                     '----'
- *
- *  (A) successor state of cur   (B) successor state of cur or it's entry
- *      not yet traversed            are in current DFS path, thus cur and succ
- *                                   are members of the same outermost loop
- *
- *                      initial                  initial
- *                        |                        |
- *                        V                        V
- *                       ...                      ...
- *                        |                        |
- *                        V                        V
- *                .------...               .------...
- *                |       |                |       |
- *                V       V                V       V
- *           .-> hdr     ...              ...     ...
- *           |    |       |                |       |
- *           |    V       V                V       V
- *           |   succ <- cur              succ <- cur
- *           |    |                        |
- *           |    V                        V
- *           |   ...                      ...
- *           |    |                        |
- *           '----'                       exit
- *
- * (C) successor state of cur is a part of some loop but this loop
- *     does not include cur or successor state is not in a loop at all.
- *
- * Algorithm could be described as the following python code:
- *
- *     traversed = set()   # Set of traversed nodes
- *     entries = {}        # Mapping from node to loop entry
- *     depths = {}         # Depth level assigned to graph node
- *     path = set()        # Current DFS path
- *
- *     # Find outermost loop entry known for n
- *     def get_loop_entry(n):
- *         h = entries.get(n, None)
- *         while h in entries:
- *             h = entries[h]
- *         return h
- *
- *     # Update n's loop entry if h comes before n in current DFS path.
- *     def update_loop_entry(n, h):
- *         if h in path and depths[entries.get(n, n)] < depths[n]:
- *             entries[n] = h1
- *
- *     def dfs(n, depth):
- *         traversed.add(n)
- *         path.add(n)
- *         depths[n] = depth
- *         for succ in G.successors(n):
- *             if succ not in traversed:
- *                 # Case A: explore succ and update cur's loop entry
- *                 #         only if succ's entry is in current DFS path.
- *                 dfs(succ, depth + 1)
- *                 h = entries.get(succ, None)
- *                 update_loop_entry(n, h)
- *             else:
- *                 # Case B or C depending on `h1 in path` check in update_loop_entry().
- *                 update_loop_entry(n, succ)
- *         path.remove(n)
- *
- * To adapt this algorithm for use with verifier:
- * - use st->branch == 0 as a signal that DFS of succ had been finished
- *   and cur's loop entry has to be updated (case A), handle this in
- *   update_branch_counts();
- * - use st->branch > 0 as a signal that st is in the current DFS path;
- * - handle cases B and C in is_state_visited().
- */
-static struct bpf_verifier_state *get_loop_entry(struct bpf_verifier_env *env,
-						 struct bpf_verifier_state *st)
-{
-	struct bpf_verifier_state *topmost = st->loop_entry;
-	u32 steps = 0;
-
-	while (topmost && topmost->loop_entry) {
-		if (verifier_bug_if(steps++ > st->dfs_depth, env, "infinite loop"))
-			return ERR_PTR(-EFAULT);
-		topmost = topmost->loop_entry;
-	}
-	return topmost;
-}
-
-static void update_loop_entry(struct bpf_verifier_env *env,
-			      struct bpf_verifier_state *cur, struct bpf_verifier_state *hdr)
-{
-	/* The hdr->branches check decides between cases B and C in
-	 * comment for get_loop_entry(). If hdr->branches == 0 then
-	 * head's topmost loop entry is not in current DFS path,
-	 * hence 'cur' and 'hdr' are not in the same loop and there is
-	 * no need to update cur->loop_entry.
-	 */
-	if (hdr->branches && hdr->dfs_depth < (cur->loop_entry ?: cur)->dfs_depth) {
-		if (cur->loop_entry) {
-			cur->loop_entry->used_as_loop_entry--;
-			maybe_free_verifier_state(env, state_loop_entry_as_list(cur));
-		}
-		cur->loop_entry = hdr;
-		hdr->used_as_loop_entry++;
-	}
-}
-
 /* Return IP for a given frame in a call stack */
 static u32 frame_insn_idx(struct bpf_verifier_state *st, u32 frame)
 {
-- 
cgit v1.2.3


From 0f54ff54700315caa8ed3bea36fa0ff3ebc53f56 Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Wed, 11 Jun 2025 13:08:35 -0700
Subject: bpf: include backedges in peak_states stat

Count states accumulated in bpf_scc_visit->backedges in
env->peak_states.

Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250611200836.4135542-10-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h | 2 ++
 kernel/bpf/verifier.c        | 8 +++++++-
 2 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 1ae588679e20..7e459e839f8b 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -733,6 +733,7 @@ struct bpf_scc_visit {
 	 */
 	struct bpf_verifier_state *entry_state;
 	struct bpf_scc_backedge *backedges; /* list of backedges */
+	u32 num_backedges;
 };
 
 /* An array of bpf_scc_visit structs sharing tht same bpf_scc_callchain->scc
@@ -822,6 +823,7 @@ struct bpf_verifier_env {
 	u32 longest_mark_read_walk;
 	u32 free_list_size;
 	u32 explored_states_size;
+	u32 num_backedges;
 	bpfptr_t fd_array;
 
 	/* bit mask to keep track of whether a register has been accessed
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 48847f8da5b1..1d3277bf935e 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1648,7 +1648,7 @@ static void update_peak_states(struct bpf_verifier_env *env)
 {
 	u32 cur_states;
 
-	cur_states = env->explored_states_size + env->free_list_size;
+	cur_states = env->explored_states_size + env->free_list_size + env->num_backedges;
 	env->peak_states = max(env->peak_states, cur_states);
 }
 
@@ -1949,6 +1949,9 @@ static int maybe_exit_scc(struct bpf_verifier_env *env, struct bpf_verifier_stat
 	if (env->log.level & BPF_LOG_LEVEL2)
 		verbose(env, "SCC exit %s\n", format_callchain(env, &callchain));
 	visit->entry_state = NULL;
+	env->num_backedges -= visit->num_backedges;
+	visit->num_backedges = 0;
+	update_peak_states(env);
 	return propagate_backedges(env, visit);
 }
 
@@ -1977,6 +1980,9 @@ static int add_scc_backedge(struct bpf_verifier_env *env,
 		verbose(env, "SCC backedge %s\n", format_callchain(env, &callchain));
 	backedge->next = visit->backedges;
 	visit->backedges = backedge;
+	visit->num_backedges++;
+	env->num_backedges++;
+	update_peak_states(env);
 	return 0;
 }
 
-- 
cgit v1.2.3


From fac4b41741b5cd0826cf0fa5b14e177f70a6b509 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 11 Jun 2025 07:59:43 -0700
Subject: net: ethtool: require drivers to opt into the per-RSS ctx RXFH

RX Flow Hashing supports using different configuration for different
RSS contexts. Only two drivers seem to support it. Make sure we
uniformly error out for drivers which don't.

Reviewed-by: Joe Damato <joe@dama.to>
Link: https://patch.msgid.link/20250611145949.2674086-4-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c | 1 +
 drivers/net/ethernet/sfc/ethtool.c                   | 1 +
 include/linux/ethtool.h                              | 3 +++
 net/ethtool/ioctl.c                                  | 8 ++++++++
 4 files changed, 13 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
index 3cb8d3bf9044..8b9ee8bac674 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
@@ -2616,6 +2616,7 @@ static void mlx5e_get_ts_stats(struct net_device *netdev,
 const struct ethtool_ops mlx5e_ethtool_ops = {
 	.cap_link_lanes_supported = true,
 	.cap_rss_ctx_supported	= true,
+	.rxfh_per_ctx_fields	= true,
 	.rxfh_per_ctx_key	= true,
 	.supported_coalesce_params = ETHTOOL_COALESCE_USECS |
 				     ETHTOOL_COALESCE_MAX_FRAMES |
diff --git a/drivers/net/ethernet/sfc/ethtool.c b/drivers/net/ethernet/sfc/ethtool.c
index 83d715544f7f..afbedca63b29 100644
--- a/drivers/net/ethernet/sfc/ethtool.c
+++ b/drivers/net/ethernet/sfc/ethtool.c
@@ -262,6 +262,7 @@ const struct ethtool_ops efx_ethtool_ops = {
 	.set_rxnfc		= efx_ethtool_set_rxnfc,
 	.get_rxfh_indir_size	= efx_ethtool_get_rxfh_indir_size,
 	.get_rxfh_key_size	= efx_ethtool_get_rxfh_key_size,
+	.rxfh_per_ctx_fields	= true,
 	.rxfh_per_ctx_key	= true,
 	.cap_rss_rxnfc_adds	= true,
 	.rxfh_priv_size		= sizeof(struct efx_rss_context_priv),
diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 90da1aee6e56..1a6737721d7f 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -855,6 +855,8 @@ struct kernel_ethtool_ts_info {
  * @cap_rss_ctx_supported: indicates if the driver supports RSS
  *	contexts via legacy API, drivers implementing @create_rxfh_context
  *	do not have to set this bit.
+ * @rxfh_per_ctx_fields: device supports selecting different header fields
+ *	for Rx hash calculation and RSS for each additional context.
  * @rxfh_per_ctx_key: device supports setting different RSS key for each
  *	additional context. Netlink API should report hfunc, key, and input_xfrm
  *	for every context, not just context 0.
@@ -1084,6 +1086,7 @@ struct ethtool_ops {
 	u32     supported_input_xfrm:8;
 	u32     cap_link_lanes_supported:1;
 	u32     cap_rss_ctx_supported:1;
+	u32	rxfh_per_ctx_fields:1;
 	u32	rxfh_per_ctx_key:1;
 	u32	cap_rss_rxnfc_adds:1;
 	u32	rxfh_indir_space;
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 33892099cdad..1a1705e900b3 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1075,6 +1075,10 @@ ethtool_set_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr)
 	if (rc)
 		return rc;
 
+	if (info.flow_type & FLOW_RSS && info.rss_context &&
+	    !ops->rxfh_per_ctx_fields)
+		return -EINVAL;
+
 	if (ops->get_rxfh) {
 		struct ethtool_rxfh_param rxfh = {};
 
@@ -1105,6 +1109,10 @@ ethtool_get_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr)
 	if (ret)
 		return ret;
 
+	if (info.flow_type & FLOW_RSS && info.rss_context &&
+	    !ops->rxfh_per_ctx_fields)
+		return -EINVAL;
+
 	ret = ops->get_rxnfc(dev, &info, NULL);
 	if (ret < 0)
 		return ret;
-- 
cgit v1.2.3


From 9bb00786fc61e865e121aa20dd12aa4d1311a990 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 11 Jun 2025 07:59:44 -0700
Subject: net: ethtool: add dedicated callbacks for getting and setting rxfh
 fields

We mux multiple calls to the drivers via the .get_nfc and .set_nfc
callbacks. This is slightly inconvenient to the drivers as they
have to de-mux them back. It will also be awkward for netlink code
to construct struct ethtool_rxnfc when it wants to get info about
RX Flow Hash, from the RSS module.

Add dedicated driver callbacks. Create struct ethtool_rxfh_fields
which contains only data relevant to RXFH. Maintain the names of
the fields to avoid having to heavily modify the drivers.

For now support both callbacks, once all drivers are converted
ethtool_*et_rxfh_fields() will stop using the rxnfc callbacks.

Link: https://patch.msgid.link/20250611145949.2674086-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ethtool.h | 20 ++++++++++++++++++
 net/ethtool/ioctl.c     | 55 ++++++++++++++++++++++++++++++++++++++++---------
 2 files changed, 65 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 1a6737721d7f..59877fd2a1d3 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -825,6 +825,19 @@ struct ethtool_rxfh_param {
 	u8	input_xfrm;
 };
 
+/**
+ * struct ethtool_rxfh_fields - Rx Flow Hashing (RXFH) header field config
+ * @data: which header fields are used for hashing, bitmask of RXH_* defines
+ * @flow_type: L2-L4 network traffic flow type
+ * @rss_context: RSS context, will only be used if rxfh_per_ctx_fields is
+ *	set in struct ethtool_ops
+ */
+struct ethtool_rxfh_fields {
+	u32 data;
+	u32 flow_type;
+	u32 rss_context;
+};
+
 /**
  * struct kernel_ethtool_ts_info - kernel copy of struct ethtool_ts_info
  * @cmd: command number = %ETHTOOL_GET_TS_INFO
@@ -970,6 +983,8 @@ struct kernel_ethtool_ts_info {
  *	will remain unchanged.
  *	Returns a negative error code or zero. An error code must be returned
  *	if at least one unsupported change was requested.
+ * @get_rxfh_fields: Get header fields used for flow hashing.
+ * @set_rxfh_fields: Set header fields used for flow hashing.
  * @create_rxfh_context: Create a new RSS context with the specified RX flow
  *	hash indirection table, hash key, and hash function.
  *	The &struct ethtool_rxfh_context for this context is passed in @ctx;
@@ -1156,6 +1171,11 @@ struct ethtool_ops {
 	int	(*get_rxfh)(struct net_device *, struct ethtool_rxfh_param *);
 	int	(*set_rxfh)(struct net_device *, struct ethtool_rxfh_param *,
 			    struct netlink_ext_ack *extack);
+	int	(*get_rxfh_fields)(struct net_device *,
+				   struct ethtool_rxfh_fields *);
+	int	(*set_rxfh_fields)(struct net_device *,
+				   const struct ethtool_rxfh_fields *,
+				   struct netlink_ext_ack *extack);
 	int	(*create_rxfh_context)(struct net_device *,
 				       struct ethtool_rxfh_context *ctx,
 				       const struct ethtool_rxfh_param *rxfh,
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 1a1705e900b3..a14cf901c32d 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1048,9 +1048,20 @@ static int ethtool_check_flow_types(struct net_device *dev, u32 input_xfrm)
 			continue;
 
 		info.flow_type = i;
-		err = ops->get_rxnfc(dev, &info, NULL);
-		if (err)
-			continue;
+
+		if (ops->get_rxfh_fields) {
+			struct ethtool_rxfh_fields fields = {
+				.flow_type	= info.flow_type,
+			};
+
+			if (ops->get_rxfh_fields(dev, &fields))
+				continue;
+
+			info.data = fields.data;
+		} else {
+			if (ops->get_rxnfc(dev, &info, NULL))
+				continue;
+		}
 
 		err = ethtool_check_xfrm_rxfh(input_xfrm, info.data);
 		if (err)
@@ -1064,11 +1075,12 @@ static noinline_for_stack int
 ethtool_set_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr)
 {
 	const struct ethtool_ops *ops = dev->ethtool_ops;
+	struct ethtool_rxfh_fields fields = {};
 	struct ethtool_rxnfc info;
 	size_t info_size = sizeof(info);
 	int rc;
 
-	if (!ops->set_rxnfc)
+	if (!ops->set_rxnfc && !ops->set_rxfh_fields)
 		return -EOPNOTSUPP;
 
 	rc = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr);
@@ -1091,7 +1103,15 @@ ethtool_set_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr)
 			return rc;
 	}
 
-	return ops->set_rxnfc(dev, &info);
+	if (!ops->set_rxfh_fields)
+		return ops->set_rxnfc(dev, &info);
+
+	fields.data = info.data;
+	fields.flow_type = info.flow_type & ~FLOW_RSS;
+	if (info.flow_type & FLOW_RSS)
+		fields.rss_context = info.rss_context;
+
+	return ops->set_rxfh_fields(dev, &fields, NULL);
 }
 
 static noinline_for_stack int
@@ -1102,7 +1122,7 @@ ethtool_get_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr)
 	const struct ethtool_ops *ops = dev->ethtool_ops;
 	int ret;
 
-	if (!ops->get_rxnfc)
+	if (!ops->get_rxnfc && !ops->get_rxfh_fields)
 		return -EOPNOTSUPP;
 
 	ret = ethtool_rxnfc_copy_struct(cmd, &info, &info_size, useraddr);
@@ -1113,9 +1133,24 @@ ethtool_get_rxfh_fields(struct net_device *dev, u32 cmd, void __user *useraddr)
 	    !ops->rxfh_per_ctx_fields)
 		return -EINVAL;
 
-	ret = ops->get_rxnfc(dev, &info, NULL);
-	if (ret < 0)
-		return ret;
+	if (ops->get_rxfh_fields) {
+		struct ethtool_rxfh_fields fields = {
+			.flow_type	= info.flow_type & ~FLOW_RSS,
+		};
+
+		if (info.flow_type & FLOW_RSS)
+			fields.rss_context = info.rss_context;
+
+		ret = ops->get_rxfh_fields(dev, &fields);
+		if (ret < 0)
+			return ret;
+
+		info.data = fields.data;
+	} else {
+		ret = ops->get_rxnfc(dev, &info, NULL);
+		if (ret < 0)
+			return ret;
+	}
 
 	return ethtool_rxnfc_copy_to_user(useraddr, &info, info_size, NULL);
 }
@@ -1493,7 +1528,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	u8 *rss_config;
 	int ret;
 
-	if (!ops->get_rxnfc || !ops->set_rxfh)
+	if ((!ops->get_rxnfc && !ops->get_rxfh_fields) || !ops->set_rxfh)
 		return -EOPNOTSUPP;
 
 	if (ops->get_rxfh_indir_size)
-- 
cgit v1.2.3


From b1b36680107ede3a4ec7fa41d052971606d6b325 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 10 Jun 2025 08:03:43 +0200
Subject: net: phy: assign default match function for non-PHY MDIO devices

Make mdio_device_bus_match() the default match function for non-PHY
MDIO devices. Benefit is that we don't have to export this function
any longer. As long as mdiodev->modalias isn't set, there's no change
in behavior. mdiobus_create_device() is the only place where
mdiodev->modalias gets set, but this function sets
mdio_device_bus_match() as match function anyway.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/6c94e3d3-bfb0-4ddc-a518-6fddbc64e1d0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/mdio_bus_provider.c | 1 -
 drivers/net/phy/mdio_device.c       | 5 +++--
 include/linux/mdio.h                | 1 -
 3 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/mdio_bus_provider.c b/drivers/net/phy/mdio_bus_provider.c
index 65850e36284d..48dc4bf85125 100644
--- a/drivers/net/phy/mdio_bus_provider.c
+++ b/drivers/net/phy/mdio_bus_provider.c
@@ -152,7 +152,6 @@ static int mdiobus_create_device(struct mii_bus *bus,
 
 	strscpy(mdiodev->modalias, bi->modalias,
 		sizeof(mdiodev->modalias));
-	mdiodev->bus_match = mdio_device_bus_match;
 	mdiodev->dev.platform_data = (void *)bi->platform_data;
 
 	ret = mdio_device_register(mdiodev);
diff --git a/drivers/net/phy/mdio_device.c b/drivers/net/phy/mdio_device.c
index cce3f405d1a4..f64176e0e197 100644
--- a/drivers/net/phy/mdio_device.c
+++ b/drivers/net/phy/mdio_device.c
@@ -35,7 +35,8 @@ static void mdio_device_release(struct device *dev)
 	kfree(to_mdio_device(dev));
 }
 
-int mdio_device_bus_match(struct device *dev, const struct device_driver *drv)
+static int mdio_device_bus_match(struct device *dev,
+				 const struct device_driver *drv)
 {
 	struct mdio_device *mdiodev = to_mdio_device(dev);
 	const struct mdio_driver *mdiodrv = to_mdio_driver(drv);
@@ -45,7 +46,6 @@ int mdio_device_bus_match(struct device *dev, const struct device_driver *drv)
 
 	return strcmp(mdiodev->modalias, drv->name) == 0;
 }
-EXPORT_SYMBOL_GPL(mdio_device_bus_match);
 
 struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr)
 {
@@ -59,6 +59,7 @@ struct mdio_device *mdio_device_create(struct mii_bus *bus, int addr)
 	mdiodev->dev.release = mdio_device_release;
 	mdiodev->dev.parent = &bus->dev;
 	mdiodev->dev.bus = &mdio_bus_type;
+	mdiodev->bus_match = mdio_device_bus_match;
 	mdiodev->device_free = mdio_device_free;
 	mdiodev->device_remove = mdio_device_remove;
 	mdiodev->bus = bus;
diff --git a/include/linux/mdio.h b/include/linux/mdio.h
index e43ff9f980a4..c640ba44dd6e 100644
--- a/include/linux/mdio.h
+++ b/include/linux/mdio.h
@@ -95,7 +95,6 @@ void mdio_device_remove(struct mdio_device *mdiodev);
 void mdio_device_reset(struct mdio_device *mdiodev, int value);
 int mdio_driver_register(struct mdio_driver *drv);
 void mdio_driver_unregister(struct mdio_driver *drv);
-int mdio_device_bus_match(struct device *dev, const struct device_driver *drv);
 
 static inline void mdio_device_get(struct mdio_device *mdiodev)
 {
-- 
cgit v1.2.3


From 00ee2537255e25a14360288dbd94ff62c0db497d Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Tue, 10 Jun 2025 23:34:53 +0200
Subject: net: phy: move definition of genphy_c45_driver to phy_device.c

genphy_c45_read_status() is exported, so we can move definition of
genphy_c45_driver to phy_device.c and make it static. This helps
to clean up phy.h a little.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/ead3ab17-22d0-4cd3-901c-3d493ab851e6@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy-c45.c    | 7 -------
 drivers/net/phy/phy_device.c | 7 +++++++
 include/linux/phy.h          | 3 ---
 3 files changed, 7 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy-c45.c b/drivers/net/phy/phy-c45.c
index bdd70d424491..61670be0f095 100644
--- a/drivers/net/phy/phy-c45.c
+++ b/drivers/net/phy/phy-c45.c
@@ -1573,10 +1573,3 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev,
 	return ret;
 }
 EXPORT_SYMBOL(genphy_c45_ethtool_set_eee);
-
-struct phy_driver genphy_c45_driver = {
-	.phy_id         = 0xffffffff,
-	.phy_id_mask    = 0xffffffff,
-	.name           = "Generic Clause 45 PHY",
-	.read_status    = genphy_c45_read_status,
-};
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 73f9cb2e2844..2902193e12f2 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -59,6 +59,13 @@ struct phy_fixup {
 	int (*run)(struct phy_device *phydev);
 };
 
+static struct phy_driver genphy_c45_driver = {
+	.phy_id         = 0xffffffff,
+	.phy_id_mask    = 0xffffffff,
+	.name           = "Generic Clause 45 PHY",
+	.read_status    = genphy_c45_read_status,
+};
+
 __ETHTOOL_DECLARE_LINK_MODE_MASK(phy_basic_features) __ro_after_init;
 EXPORT_SYMBOL_GPL(phy_basic_features);
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index e194dad1623d..c021b351ab0d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1941,9 +1941,6 @@ int genphy_c45_ethtool_set_eee(struct phy_device *phydev,
 			       struct ethtool_keee *data);
 int genphy_c45_an_config_eee_aneg(struct phy_device *phydev);
 
-/* Generic C45 PHY driver */
-extern struct phy_driver genphy_c45_driver;
-
 /* The gen10g_* functions are the old Clause 45 stub */
 int gen10g_config_aneg(struct phy_device *phydev);
 
-- 
cgit v1.2.3


From c4688ff47fd719e2371b984d59759f9fa09dd6a2 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Wed, 11 Jun 2025 14:56:19 +0100
Subject: net: phy: simplify phy_get_internal_delay()

Simplify the arguments passed to phy_get_internal_delay() - the "dev"
argument is always &phydev->mdio.dev, and as the phydev is passed in,
there's no need to also pass in the struct device, especially when this
function is the only reason for the caller to have a local "dev"
variable.

Remove the redundant "dev" argument, and update the callers.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/E1uPLwB-003VzR-4C@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/dp83822.c        | 7 ++-----
 drivers/net/phy/dp83869.c        | 7 +++----
 drivers/net/phy/intel-xway.c     | 7 ++-----
 drivers/net/phy/mscc/mscc_main.c | 5 ++---
 drivers/net/phy/phy_device.c     | 6 +++---
 include/linux/phy.h              | 4 ++--
 6 files changed, 14 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
index 01255dada600..33db21251f2e 100644
--- a/drivers/net/phy/dp83822.c
+++ b/drivers/net/phy/dp83822.c
@@ -516,7 +516,6 @@ static int dp83822_config_init_leds(struct phy_device *phydev)
 static int dp83822_config_init(struct phy_device *phydev)
 {
 	struct dp83822_private *dp83822 = phydev->priv;
-	struct device *dev = &phydev->mdio.dev;
 	int rgmii_delay = 0;
 	s32 rx_int_delay;
 	s32 tx_int_delay;
@@ -549,15 +548,13 @@ static int dp83822_config_init(struct phy_device *phydev)
 		return err;
 
 	if (phy_interface_is_rgmii(phydev)) {
-		rx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0,
-						      true);
+		rx_int_delay = phy_get_internal_delay(phydev, NULL, 0, true);
 
 		/* Set DP83822_RX_CLK_SHIFT to enable rx clk internal delay */
 		if (rx_int_delay > 0)
 			rgmii_delay |= DP83822_RX_CLK_SHIFT;
 
-		tx_int_delay = phy_get_internal_delay(phydev, dev, NULL, 0,
-						      false);
+		tx_int_delay = phy_get_internal_delay(phydev, NULL, 0, false);
 
 		/* Set DP83822_TX_CLK_SHIFT to disable tx clk internal delay */
 		if (tx_int_delay <= 0)
diff --git a/drivers/net/phy/dp83869.c b/drivers/net/phy/dp83869.c
index a62cd838a9ea..a2cd1cc35cde 100644
--- a/drivers/net/phy/dp83869.c
+++ b/drivers/net/phy/dp83869.c
@@ -540,9 +540,8 @@ static const int dp83869_internal_delay[] = {250, 500, 750, 1000, 1250, 1500,
 
 static int dp83869_of_init(struct phy_device *phydev)
 {
+	struct device_node *of_node = phydev->mdio.dev.of_node;
 	struct dp83869_private *dp83869 = phydev->priv;
-	struct device *dev = &phydev->mdio.dev;
-	struct device_node *of_node = dev->of_node;
 	int delay_size = ARRAY_SIZE(dp83869_internal_delay);
 	int ret;
 
@@ -597,13 +596,13 @@ static int dp83869_of_init(struct phy_device *phydev)
 				 &dp83869->tx_fifo_depth))
 		dp83869->tx_fifo_depth = DP83869_PHYCR_FIFO_DEPTH_4_B_NIB;
 
-	dp83869->rx_int_delay = phy_get_internal_delay(phydev, dev,
+	dp83869->rx_int_delay = phy_get_internal_delay(phydev,
 						       &dp83869_internal_delay[0],
 						       delay_size, true);
 	if (dp83869->rx_int_delay < 0)
 		dp83869->rx_int_delay = DP83869_CLK_DELAY_DEF;
 
-	dp83869->tx_int_delay = phy_get_internal_delay(phydev, dev,
+	dp83869->tx_int_delay = phy_get_internal_delay(phydev,
 						       &dp83869_internal_delay[0],
 						       delay_size, false);
 	if (dp83869->tx_int_delay < 0)
diff --git a/drivers/net/phy/intel-xway.c b/drivers/net/phy/intel-xway.c
index a44771e8acdc..9766dd99afaa 100644
--- a/drivers/net/phy/intel-xway.c
+++ b/drivers/net/phy/intel-xway.c
@@ -174,7 +174,6 @@ static const int xway_internal_delay[] = {0, 500, 1000, 1500, 2000, 2500,
 
 static int xway_gphy_rgmii_init(struct phy_device *phydev)
 {
-	struct device *dev = &phydev->mdio.dev;
 	unsigned int delay_size = ARRAY_SIZE(xway_internal_delay);
 	s32 int_delay;
 	int val = 0;
@@ -207,8 +206,7 @@ static int xway_gphy_rgmii_init(struct phy_device *phydev)
 
 	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
 	    phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID) {
-		int_delay = phy_get_internal_delay(phydev, dev,
-						   xway_internal_delay,
+		int_delay = phy_get_internal_delay(phydev, xway_internal_delay,
 						   delay_size, true);
 
 		/* if rx-internal-delay-ps is missing, use default of 2.0 ns */
@@ -220,8 +218,7 @@ static int xway_gphy_rgmii_init(struct phy_device *phydev)
 
 	if (phydev->interface == PHY_INTERFACE_MODE_RGMII_ID ||
 	    phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID) {
-		int_delay = phy_get_internal_delay(phydev, dev,
-						   xway_internal_delay,
+		int_delay = phy_get_internal_delay(phydev, xway_internal_delay,
 						   delay_size, false);
 
 		/* if tx-internal-delay-ps is missing, use default of 2.0 ns */
diff --git a/drivers/net/phy/mscc/mscc_main.c b/drivers/net/phy/mscc/mscc_main.c
index 7ff975efd8e7..7ed6522fb0ef 100644
--- a/drivers/net/phy/mscc/mscc_main.c
+++ b/drivers/net/phy/mscc/mscc_main.c
@@ -530,7 +530,6 @@ static int vsc85xx_update_rgmii_cntl(struct phy_device *phydev, u32 rgmii_cntl,
 	u16 rgmii_rx_delay_pos = ffs(rgmii_rx_delay_mask) - 1;
 	u16 rgmii_tx_delay_pos = ffs(rgmii_tx_delay_mask) - 1;
 	int delay_size = ARRAY_SIZE(vsc85xx_internal_delay);
-	struct device *dev = &phydev->mdio.dev;
 	u16 reg_val = 0;
 	u16 mask = 0;
 	s32 rx_delay;
@@ -549,7 +548,7 @@ static int vsc85xx_update_rgmii_cntl(struct phy_device *phydev, u32 rgmii_cntl,
 	if (phy_interface_is_rgmii(phydev))
 		mask |= rgmii_rx_delay_mask | rgmii_tx_delay_mask;
 
-	rx_delay = phy_get_internal_delay(phydev, dev, vsc85xx_internal_delay,
+	rx_delay = phy_get_internal_delay(phydev, vsc85xx_internal_delay,
 					  delay_size, true);
 	if (rx_delay < 0) {
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_RXID ||
@@ -559,7 +558,7 @@ static int vsc85xx_update_rgmii_cntl(struct phy_device *phydev, u32 rgmii_cntl,
 			rx_delay = RGMII_CLK_DELAY_0_2_NS;
 	}
 
-	tx_delay = phy_get_internal_delay(phydev, dev, vsc85xx_internal_delay,
+	tx_delay = phy_get_internal_delay(phydev, vsc85xx_internal_delay,
 					  delay_size, false);
 	if (tx_delay < 0) {
 		if (phydev->interface == PHY_INTERFACE_MODE_RGMII_TXID ||
diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2902193e12f2..509078344020 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -2906,7 +2906,6 @@ static int phy_get_u32_property(struct device *dev, const char *name, u32 *val)
 /**
  * phy_get_internal_delay - returns the index of the internal delay
  * @phydev: phy_device struct
- * @dev: pointer to the devices device struct
  * @delay_values: array of delays the PHY supports
  * @size: the size of the delay array
  * @is_rx: boolean to indicate to get the rx internal delay
@@ -2919,9 +2918,10 @@ static int phy_get_u32_property(struct device *dev, const char *name, u32 *val)
  * array then size = 0 and the value of the delay property is returned.
  * Return -EINVAL if the delay is invalid or cannot be found.
  */
-s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
-			   const int *delay_values, int size, bool is_rx)
+s32 phy_get_internal_delay(struct phy_device *phydev, const int *delay_values,
+			   int size, bool is_rx)
 {
+	struct device *dev = &phydev->mdio.dev;
 	int i, ret;
 	u32 delay;
 
diff --git a/include/linux/phy.h b/include/linux/phy.h
index c021b351ab0d..c4d8f7c82627 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1994,8 +1994,8 @@ bool phy_validate_pause(struct phy_device *phydev,
 			struct ethtool_pauseparam *pp);
 void phy_get_pause(struct phy_device *phydev, bool *tx_pause, bool *rx_pause);
 
-s32 phy_get_internal_delay(struct phy_device *phydev, struct device *dev,
-			   const int *delay_values, int size, bool is_rx);
+s32 phy_get_internal_delay(struct phy_device *phydev, const int *delay_values,
+			   int size, bool is_rx);
 
 int phy_get_tx_amplitude_gain(struct phy_device *phydev, struct device *dev,
 			      enum ethtool_link_mode_bit_indices linkmode,
-- 
cgit v1.2.3


From 5202c25dd17c54cd4c21f266d9a51b644d7cd682 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 28 May 2025 10:09:00 +0200
Subject: sched/smp: Always define sched_domains_mutex_lock()/unlock(),
 def_root_domain and sched_domains_mutex

Simplify the scheduler by making CONFIG_SMP=y primitives and data
structures unconditional.

Unconditionally build kernel/sched/topology.c and the main sched-domains
locking primitives.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20250528080924.2273858-20-mingo@kernel.org
---
 include/linux/sched.h        | 5 -----
 kernel/sched/build_utility.c | 3 ++-
 kernel/sched/topology.c      | 4 ++++
 3 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52..aa54d75034ea 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -395,15 +395,10 @@ enum uclamp_id {
 	UCLAMP_CNT
 };
 
-#ifdef CONFIG_SMP
 extern struct root_domain def_root_domain;
 extern struct mutex sched_domains_mutex;
 extern void sched_domains_mutex_lock(void);
 extern void sched_domains_mutex_unlock(void);
-#else
-static inline void sched_domains_mutex_lock(void) { }
-static inline void sched_domains_mutex_unlock(void) { }
-#endif
 
 struct sched_param {
 	int sched_priority;
diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
index bf9d8db94b70..5c485b2dfb95 100644
--- a/kernel/sched/build_utility.c
+++ b/kernel/sched/build_utility.c
@@ -83,9 +83,10 @@
 #ifdef CONFIG_SMP
 # include "cpupri.c"
 # include "stop_task.c"
-# include "topology.c"
 #endif
 
+#include "topology.c"
+
 #ifdef CONFIG_SCHED_CORE
 # include "core_sched.c"
 #endif
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 2352caf4f942..ee347d9c5df4 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -17,6 +17,8 @@ void sched_domains_mutex_unlock(void)
 	mutex_unlock(&sched_domains_mutex);
 }
 
+#ifdef CONFIG_SMP
+
 /* Protected by sched_domains_mutex: */
 static cpumask_var_t sched_domains_tmpmask;
 static cpumask_var_t sched_domains_tmpmask2;
@@ -2842,3 +2844,5 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
 	sched_domains_mutex_unlock();
 }
+
+#endif /* CONFIG_SMP */
-- 
cgit v1.2.3


From cac5cefbade90ff0bb0b393d301fa3b5234cf056 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 28 May 2025 10:09:01 +0200
Subject: sched/smp: Make SMP unconditional

Simplify the scheduler by making CONFIG_SMP=y primitives and data
structures unconditional.

Introduce transitory wrappers for functionality not yet converted to SMP.

Note that this patch is pretty large, because there's no clear separation
between various aspects of the SMP scheduler, it's basically a huge block
of #ifdef CONFIG_SMP. A fair amount of it has to be switched on for it to
boot and work on UP systems.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20250528080924.2273858-21-mingo@kernel.org
---
 include/linux/preempt.h        |   9 ---
 include/linux/sched.h          |  42 --------------
 include/linux/sched/deadline.h |   4 --
 include/linux/sched/idle.h     |   4 --
 include/linux/sched/nohz.h     |   4 +-
 include/linux/sched/topology.h |  32 -----------
 kernel/sched/build_policy.c    |   6 +-
 kernel/sched/build_utility.c   |   6 +-
 kernel/sched/core.c            | 106 +++++-------------------------------
 kernel/sched/cpudeadline.h     |   2 -
 kernel/sched/cpupri.h          |   2 -
 kernel/sched/deadline.c        |  95 --------------------------------
 kernel/sched/debug.c           |  12 ----
 kernel/sched/fair.c            | 115 ---------------------------------------
 kernel/sched/pelt.h            |  52 ------------------
 kernel/sched/rt.c              |   6 +-
 kernel/sched/sched.h           | 121 +----------------------------------------
 kernel/sched/syscalls.c        |   2 -
 kernel/sched/topology.c        |  10 +---
 19 files changed, 31 insertions(+), 599 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/preempt.h b/include/linux/preempt.h
index b0af8d4ef6e6..1fad1c8a4c76 100644
--- a/include/linux/preempt.h
+++ b/include/linux/preempt.h
@@ -369,8 +369,6 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 
 #endif
 
-#ifdef CONFIG_SMP
-
 /*
  * Migrate-Disable and why it is undesired.
  *
@@ -429,13 +427,6 @@ static inline void preempt_notifier_init(struct preempt_notifier *notifier,
 extern void migrate_disable(void);
 extern void migrate_enable(void);
 
-#else
-
-static inline void migrate_disable(void) { }
-static inline void migrate_enable(void) { }
-
-#endif /* CONFIG_SMP */
-
 /**
  * preempt_disable_nested - Disable preemption inside a normally preempt disabled section
  *
diff --git a/include/linux/sched.h b/include/linux/sched.h
index aa54d75034ea..376befdec4b0 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -599,7 +599,6 @@ struct sched_entity {
 	unsigned long			runnable_weight;
 #endif
 
-#ifdef CONFIG_SMP
 	/*
 	 * Per entity load average tracking.
 	 *
@@ -607,7 +606,6 @@ struct sched_entity {
 	 * collide with read-mostly values above.
 	 */
 	struct sched_avg		avg;
-#endif
 };
 
 struct sched_rt_entity {
@@ -837,7 +835,6 @@ struct task_struct {
 	struct alloc_tag		*alloc_tag;
 #endif
 
-#ifdef CONFIG_SMP
 	int				on_cpu;
 	struct __call_single_node	wake_entry;
 	unsigned int			wakee_flips;
@@ -853,7 +850,6 @@ struct task_struct {
 	 */
 	int				recent_used_cpu;
 	int				wake_cpu;
-#endif
 	int				on_rq;
 
 	int				prio;
@@ -912,9 +908,7 @@ struct task_struct {
 	cpumask_t			*user_cpus_ptr;
 	cpumask_t			cpus_mask;
 	void				*migration_pending;
-#ifdef CONFIG_SMP
 	unsigned short			migration_disabled;
-#endif
 	unsigned short			migration_flags;
 
 #ifdef CONFIG_PREEMPT_RCU
@@ -946,10 +940,8 @@ struct task_struct {
 	struct sched_info		sched_info;
 
 	struct list_head		tasks;
-#ifdef CONFIG_SMP
 	struct plist_node		pushable_tasks;
 	struct rb_node			pushable_dl_tasks;
-#endif
 
 	struct mm_struct		*mm;
 	struct mm_struct		*active_mm;
@@ -1843,7 +1835,6 @@ extern int cpuset_cpumask_can_shrink(const struct cpumask *cur, const struct cpu
 extern int task_can_attach(struct task_struct *p);
 extern int dl_bw_alloc(int cpu, u64 dl_bw);
 extern void dl_bw_free(int cpu, u64 dl_bw);
-#ifdef CONFIG_SMP
 
 /* do_set_cpus_allowed() - consider using set_cpus_allowed_ptr() instead */
 extern void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask);
@@ -1861,33 +1852,6 @@ extern void release_user_cpus_ptr(struct task_struct *p);
 extern int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask);
 extern void force_compatible_cpus_allowed_ptr(struct task_struct *p);
 extern void relax_compatible_cpus_allowed_ptr(struct task_struct *p);
-#else
-static inline void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
-{
-}
-static inline int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
-{
-	/* Opencoded cpumask_test_cpu(0, new_mask) to avoid dependency on cpumask.h */
-	if ((*cpumask_bits(new_mask) & 1) == 0)
-		return -EINVAL;
-	return 0;
-}
-static inline int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src, int node)
-{
-	if (src->user_cpus_ptr)
-		return -EINVAL;
-	return 0;
-}
-static inline void release_user_cpus_ptr(struct task_struct *p)
-{
-	WARN_ON(p->user_cpus_ptr);
-}
-
-static inline int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
-{
-	return 0;
-}
-#endif
 
 extern int yield_to(struct task_struct *p, bool preempt);
 extern void set_user_nice(struct task_struct *p, long nice);
@@ -1976,11 +1940,7 @@ extern int wake_up_state(struct task_struct *tsk, unsigned int state);
 extern int wake_up_process(struct task_struct *tsk);
 extern void wake_up_new_task(struct task_struct *tsk);
 
-#ifdef CONFIG_SMP
 extern void kick_process(struct task_struct *tsk);
-#else
-static inline void kick_process(struct task_struct *tsk) { }
-#endif
 
 extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec);
 #define set_task_comm(tsk, from) ({			\
@@ -2225,7 +2185,6 @@ extern long sched_getaffinity(pid_t pid, struct cpumask *mask);
 #define TASK_SIZE_OF(tsk)	TASK_SIZE
 #endif
 
-#ifdef CONFIG_SMP
 static inline bool owner_on_cpu(struct task_struct *owner)
 {
 	/*
@@ -2237,7 +2196,6 @@ static inline bool owner_on_cpu(struct task_struct *owner)
 
 /* Returns effective CPU energy utilization, as seen by the scheduler */
 unsigned long sched_cpu_util(int cpu);
-#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_SCHED_CORE
 extern void sched_core_free(struct task_struct *tsk);
diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
index f9aabbc9d22e..c40115d4e34d 100644
--- a/include/linux/sched/deadline.h
+++ b/include/linux/sched/deadline.h
@@ -29,15 +29,11 @@ static inline bool dl_time_before(u64 a, u64 b)
 	return (s64)(a - b) < 0;
 }
 
-#ifdef CONFIG_SMP
-
 struct root_domain;
 extern void dl_add_task_root_domain(struct task_struct *p);
 extern void dl_clear_root_domain(struct root_domain *rd);
 extern void dl_clear_root_domain_cpu(int cpu);
 
-#endif /* CONFIG_SMP */
-
 extern u64 dl_cookie;
 extern bool dl_bw_visited(int cpu, u64 cookie);
 
diff --git a/include/linux/sched/idle.h b/include/linux/sched/idle.h
index 439f6029d3b9..8465ff1f20d1 100644
--- a/include/linux/sched/idle.h
+++ b/include/linux/sched/idle.h
@@ -11,11 +11,7 @@ enum cpu_idle_type {
 	CPU_MAX_IDLE_TYPES
 };
 
-#ifdef CONFIG_SMP
 extern void wake_up_if_idle(int cpu);
-#else
-static inline void wake_up_if_idle(int cpu) { }
-#endif
 
 /*
  * Idle thread specific functions to determine the need_resched
diff --git a/include/linux/sched/nohz.h b/include/linux/sched/nohz.h
index 6d67e9a5af6b..0db7f67935fe 100644
--- a/include/linux/sched/nohz.h
+++ b/include/linux/sched/nohz.h
@@ -6,7 +6,7 @@
  * This is the interface between the scheduler and nohz/dynticks:
  */
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#ifdef CONFIG_NO_HZ_COMMON
 extern void nohz_balance_enter_idle(int cpu);
 extern int get_nohz_timer_target(void);
 #else
@@ -23,7 +23,7 @@ static inline void calc_load_nohz_remote(struct rq *rq) { }
 static inline void calc_load_nohz_stop(void) { }
 #endif /* CONFIG_NO_HZ_COMMON */
 
-#if defined(CONFIG_NO_HZ_COMMON) && defined(CONFIG_SMP)
+#ifdef CONFIG_NO_HZ_COMMON
 extern void wake_up_nohz_cpu(int cpu);
 #else
 static inline void wake_up_nohz_cpu(int cpu) { }
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 198bb5cc1774..e54e7fa76ba6 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -9,7 +9,6 @@
 /*
  * sched-domains (multiprocessor balancing) declarations:
  */
-#ifdef CONFIG_SMP
 
 /* Generate SD flag indexes */
 #define SD_FLAG(name, mflags) __##name,
@@ -200,37 +199,6 @@ extern void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio);
 
 # define SD_INIT_NAME(type)		.name = #type
 
-#else /* CONFIG_SMP */
-
-struct sched_domain_attr;
-
-static inline void
-partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-			struct sched_domain_attr *dattr_new)
-{
-}
-
-static inline bool cpus_equal_capacity(int this_cpu, int that_cpu)
-{
-	return true;
-}
-
-static inline bool cpus_share_cache(int this_cpu, int that_cpu)
-{
-	return true;
-}
-
-static inline bool cpus_share_resources(int this_cpu, int that_cpu)
-{
-	return true;
-}
-
-static inline void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
-{
-}
-
-#endif	/* !CONFIG_SMP */
-
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 extern void rebuild_sched_domains_energy(void);
 #else
diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
index 72d97aa8b726..c4a488e67aa7 100644
--- a/kernel/sched/build_policy.c
+++ b/kernel/sched/build_policy.c
@@ -50,11 +50,9 @@
 #include "idle.c"
 
 #include "rt.c"
+#include "cpudeadline.c"
 
-#ifdef CONFIG_SMP
-# include "cpudeadline.c"
-# include "pelt.c"
-#endif
+#include "pelt.c"
 
 #include "cputime.c"
 #include "deadline.c"
diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
index 5c485b2dfb95..e2cf3b08d4e9 100644
--- a/kernel/sched/build_utility.c
+++ b/kernel/sched/build_utility.c
@@ -80,10 +80,8 @@
 #include "wait_bit.c"
 #include "wait.c"
 
-#ifdef CONFIG_SMP
-# include "cpupri.c"
-# include "stop_task.c"
-#endif
+#include "cpupri.c"
+#include "stop_task.c"
 
 #include "topology.c"
 
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f1ef6d29792c..9fc44f4b779a 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -650,7 +650,6 @@ void raw_spin_rq_unlock(struct rq *rq)
 	raw_spin_unlock(rq_lockp(rq));
 }
 
-#ifdef CONFIG_SMP
 /*
  * double_rq_lock - safely lock two runqueues
  */
@@ -667,7 +666,6 @@ void double_rq_lock(struct rq *rq1, struct rq *rq2)
 
 	double_rq_clock_clear_update(rq1, rq2);
 }
-#endif /* CONFIG_SMP */
 
 /*
  * __task_rq_lock - lock the rq @p resides on.
@@ -949,7 +947,7 @@ static inline void hrtick_rq_init(struct rq *rq)
 	_val;								\
 })
 
-#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
+#ifdef TIF_POLLING_NRFLAG
 /*
  * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
  * this avoids any races wrt polling state changes and thereby avoids
@@ -988,13 +986,11 @@ static inline bool set_nr_and_not_polling(struct thread_info *ti, int tif)
 	return true;
 }
 
-#ifdef CONFIG_SMP
 static inline bool set_nr_if_polling(struct task_struct *p)
 {
 	return false;
 }
 #endif
-#endif
 
 static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
 {
@@ -1167,7 +1163,6 @@ void resched_cpu(int cpu)
 	raw_spin_rq_unlock_irqrestore(rq, flags);
 }
 
-#ifdef CONFIG_SMP
 #ifdef CONFIG_NO_HZ_COMMON
 /*
  * In the semi idle case, use the nearest busy CPU for migrating timers
@@ -1374,10 +1369,8 @@ bool sched_can_stop_tick(struct rq *rq)
 	return true;
 }
 #endif /* CONFIG_NO_HZ_FULL */
-#endif /* CONFIG_SMP */
 
-#if defined(CONFIG_RT_GROUP_SCHED) || (defined(CONFIG_FAIR_GROUP_SCHED) && \
-			(defined(CONFIG_SMP) || defined(CONFIG_CFS_BANDWIDTH)))
+#if defined(CONFIG_RT_GROUP_SCHED) || defined(CONFIG_FAIR_GROUP_SCHED)
 /*
  * Iterate task_group tree rooted at *from, calling @down when first entering a
  * node and @up when leaving it for the final time.
@@ -2353,8 +2346,6 @@ unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state
 	return ncsw;
 }
 
-#ifdef CONFIG_SMP
-
 static void
 __do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx);
 
@@ -3305,6 +3296,8 @@ void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
 	WARN_ON_ONCE(ret);
 }
 
+#ifdef CONFIG_SMP
+
 void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 {
 	unsigned int state = READ_ONCE(p->__state);
@@ -3358,6 +3351,7 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 
 	__set_task_cpu(p, new_cpu);
 }
+#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
@@ -3661,17 +3655,6 @@ void sched_set_stop_task(int cpu, struct task_struct *stop)
 	}
 }
 
-#else /* !CONFIG_SMP: */
-
-static inline void migrate_disable_switch(struct rq *rq, struct task_struct *p) { }
-
-static inline bool rq_has_pinned_tasks(struct rq *rq)
-{
-	return false;
-}
-
-#endif /* !CONFIG_SMP */
-
 static void
 ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 {
@@ -3682,7 +3665,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 
 	rq = this_rq();
 
-#ifdef CONFIG_SMP
 	if (cpu == rq->cpu) {
 		__schedstat_inc(rq->ttwu_local);
 		__schedstat_inc(p->stats.nr_wakeups_local);
@@ -3702,7 +3684,6 @@ ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
 
 	if (wake_flags & WF_MIGRATED)
 		__schedstat_inc(p->stats.nr_wakeups_migrate);
-#endif /* CONFIG_SMP */
 
 	__schedstat_inc(rq->ttwu_count);
 	__schedstat_inc(p->stats.nr_wakeups);
@@ -3731,13 +3712,11 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 	if (p->sched_contributes_to_load)
 		rq->nr_uninterruptible--;
 
-#ifdef CONFIG_SMP
 	if (wake_flags & WF_RQ_SELECTED)
 		en_flags |= ENQUEUE_RQ_SELECTED;
 	if (wake_flags & WF_MIGRATED)
 		en_flags |= ENQUEUE_MIGRATED;
 	else
-#endif
 	if (p->in_iowait) {
 		delayacct_blkio_end(p);
 		atomic_dec(&task_rq(p)->nr_iowait);
@@ -3748,7 +3727,6 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 
 	ttwu_do_wakeup(p);
 
-#ifdef CONFIG_SMP
 	if (p->sched_class->task_woken) {
 		/*
 		 * Our task @p is fully woken up and running; so it's safe to
@@ -3770,7 +3748,6 @@ ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags,
 
 		rq->idle_stamp = 0;
 	}
-#endif /* CONFIG_SMP */
 }
 
 /*
@@ -3824,7 +3801,6 @@ static int ttwu_runnable(struct task_struct *p, int wake_flags)
 	return ret;
 }
 
-#ifdef CONFIG_SMP
 void sched_ttwu_pending(void *arg)
 {
 	struct llist_node *llist = arg;
@@ -3891,7 +3867,9 @@ static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags
 	p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
 
 	WRITE_ONCE(rq->ttwu_pending, 1);
+#ifdef CONFIG_SMP
 	__smp_call_single_queue(cpu, &p->wake_entry.llist);
+#endif
 }
 
 void wake_up_if_idle(int cpu)
@@ -3992,15 +3970,6 @@ static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
 	return false;
 }
 
-#else /* !CONFIG_SMP: */
-
-static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
-{
-	return false;
-}
-
-#endif /* !CONFIG_SMP */
-
 static void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
 {
 	struct rq *rq = cpu_rq(cpu);
@@ -4533,10 +4502,8 @@ static void __sched_fork(unsigned long clone_flags, struct task_struct *p)
 	p->capture_control = NULL;
 #endif
 	init_numa_balancing(clone_flags, p);
-#ifdef CONFIG_SMP
 	p->wake_entry.u_flags = CSD_TYPE_TTWU;
 	p->migration_pending = NULL;
-#endif
 	init_sched_mm_cid(p);
 }
 
@@ -4787,14 +4754,11 @@ int sched_fork(unsigned long clone_flags, struct task_struct *p)
 	if (likely(sched_info_on()))
 		memset(&p->sched_info, 0, sizeof(p->sched_info));
 #endif
-#ifdef CONFIG_SMP
 	p->on_cpu = 0;
-#endif
 	init_task_preempt_count(p);
-#ifdef CONFIG_SMP
 	plist_node_init(&p->pushable_tasks, MAX_PRIO);
 	RB_CLEAR_NODE(&p->pushable_dl_tasks);
-#endif
+
 	return 0;
 }
 
@@ -4871,7 +4835,6 @@ void wake_up_new_task(struct task_struct *p)
 
 	raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
 	WRITE_ONCE(p->__state, TASK_RUNNING);
-#ifdef CONFIG_SMP
 	/*
 	 * Fork balancing, do it here and not earlier because:
 	 *  - cpus_ptr can change in the fork path
@@ -4883,7 +4846,6 @@ void wake_up_new_task(struct task_struct *p)
 	p->recent_used_cpu = task_cpu(p);
 	rseq_migrate(p);
 	__set_task_cpu(p, select_task_rq(p, task_cpu(p), &wake_flags));
-#endif
 	rq = __task_rq_lock(p, &rf);
 	update_rq_clock(rq);
 	post_init_entity_util_avg(p);
@@ -4994,7 +4956,6 @@ fire_sched_out_preempt_notifiers(struct task_struct *curr,
 
 static inline void prepare_task(struct task_struct *next)
 {
-#ifdef CONFIG_SMP
 	/*
 	 * Claim the task as running, we do this before switching to it
 	 * such that any running task will have this set.
@@ -5003,12 +4964,10 @@ static inline void prepare_task(struct task_struct *next)
 	 * its ordering comment.
 	 */
 	WRITE_ONCE(next->on_cpu, 1);
-#endif
 }
 
 static inline void finish_task(struct task_struct *prev)
 {
-#ifdef CONFIG_SMP
 	/*
 	 * This must be the very last reference to @prev from this CPU. After
 	 * p->on_cpu is cleared, the task can be moved to a different CPU. We
@@ -5021,11 +4980,8 @@ static inline void finish_task(struct task_struct *prev)
 	 * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
 	 */
 	smp_store_release(&prev->on_cpu, 0);
-#endif
 }
 
-#ifdef CONFIG_SMP
-
 static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
 {
 	void (*func)(struct rq *rq);
@@ -5107,14 +5063,6 @@ void balance_callbacks(struct rq *rq, struct balance_callback *head)
 	}
 }
 
-#else /* !CONFIG_SMP: */
-
-static inline void __balance_callbacks(struct rq *rq)
-{
-}
-
-#endif /* !CONFIG_SMP */
-
 static inline void
 prepare_lock_switch(struct rq *rq, struct task_struct *next, struct rq_flags *rf)
 {
@@ -5563,7 +5511,7 @@ unsigned long long task_sched_runtime(struct task_struct *p)
 	struct rq *rq;
 	u64 ns;
 
-#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
+#ifdef CONFIG_64BIT
 	/*
 	 * 64-bit doesn't need locks to atomically read a 64-bit value.
 	 * So we have a optimization chance when the task's delta_exec is 0.
@@ -5690,12 +5638,10 @@ void sched_tick(void)
 	if (donor->flags & PF_WQ_WORKER)
 		wq_worker_tick(donor);
 
-#ifdef CONFIG_SMP
 	if (!scx_switched_all()) {
 		rq->idle_balance = idle_cpu(cpu);
 		sched_balance_trigger(rq);
 	}
-#endif
 }
 
 #ifdef CONFIG_NO_HZ_FULL
@@ -7819,12 +7765,10 @@ void show_state_filter(unsigned int state_filter)
  */
 void __init init_idle(struct task_struct *idle, int cpu)
 {
-#ifdef CONFIG_SMP
 	struct affinity_context ac = (struct affinity_context) {
 		.new_mask  = cpumask_of(cpu),
 		.flags     = 0,
 	};
-#endif
 	struct rq *rq = cpu_rq(cpu);
 	unsigned long flags;
 
@@ -7840,13 +7784,11 @@ void __init init_idle(struct task_struct *idle, int cpu)
 	idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY;
 	kthread_set_per_cpu(idle, cpu);
 
-#ifdef CONFIG_SMP
 	/*
 	 * No validation and serialization required at boot time and for
 	 * setting up the idle tasks of not yet online CPUs.
 	 */
 	set_cpus_allowed_common(idle, &ac);
-#endif
 	/*
 	 * We're having a chicken and egg problem, even though we are
 	 * holding rq->lock, the CPU isn't yet set to this CPU so the
@@ -7865,9 +7807,7 @@ void __init init_idle(struct task_struct *idle, int cpu)
 	rq_set_donor(rq, idle);
 	rcu_assign_pointer(rq->curr, idle);
 	idle->on_rq = TASK_ON_RQ_QUEUED;
-#ifdef CONFIG_SMP
 	idle->on_cpu = 1;
-#endif
 	raw_spin_rq_unlock(rq);
 	raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
 
@@ -7880,13 +7820,9 @@ void __init init_idle(struct task_struct *idle, int cpu)
 	idle->sched_class = &idle_sched_class;
 	ftrace_graph_init_idle_task(idle, cpu);
 	vtime_init_idle(idle, cpu);
-#ifdef CONFIG_SMP
 	sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
-#endif
 }
 
-#ifdef CONFIG_SMP
-
 int cpuset_cpumask_can_shrink(const struct cpumask *cur,
 			      const struct cpumask *trial)
 {
@@ -8480,13 +8416,6 @@ static int __init migration_init(void)
 }
 early_initcall(migration_init);
 
-#else /* !CONFIG_SMP: */
-void __init sched_init_smp(void)
-{
-	sched_init_granularity();
-}
-#endif /* !CONFIG_SMP */
-
 int in_sched_functions(unsigned long addr)
 {
 	return in_lock_functions(addr) ||
@@ -8512,9 +8441,7 @@ void __init sched_init(void)
 	int i;
 
 	/* Make sure the linker didn't screw up */
-#ifdef CONFIG_SMP
 	BUG_ON(!sched_class_above(&stop_sched_class, &dl_sched_class));
-#endif
 	BUG_ON(!sched_class_above(&dl_sched_class, &rt_sched_class));
 	BUG_ON(!sched_class_above(&rt_sched_class, &fair_sched_class));
 	BUG_ON(!sched_class_above(&fair_sched_class, &idle_sched_class));
@@ -8557,9 +8484,7 @@ void __init sched_init(void)
 #endif /* CONFIG_RT_GROUP_SCHED */
 	}
 
-#ifdef CONFIG_SMP
 	init_defrootdomain();
-#endif
 
 #ifdef CONFIG_RT_GROUP_SCHED
 	init_rt_bandwidth(&root_task_group.rt_bandwidth,
@@ -8620,7 +8545,6 @@ void __init sched_init(void)
 		rq->rt.rt_runtime = global_rt_runtime();
 		init_tg_rt_entry(&root_task_group, &rq->rt, NULL, i, NULL);
 #endif
-#ifdef CONFIG_SMP
 		rq->sd = NULL;
 		rq->rd = NULL;
 		rq->cpu_capacity = SCHED_CAPACITY_SCALE;
@@ -8637,16 +8561,15 @@ void __init sched_init(void)
 		INIT_LIST_HEAD(&rq->cfs_tasks);
 
 		rq_attach_root(rq, &def_root_domain);
-# ifdef CONFIG_NO_HZ_COMMON
+#ifdef CONFIG_NO_HZ_COMMON
 		rq->last_blocked_load_update_tick = jiffies;
 		atomic_set(&rq->nohz_flags, 0);
 
 		INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq);
-# endif
-# ifdef CONFIG_HOTPLUG_CPU
+#endif
+#ifdef CONFIG_HOTPLUG_CPU
 		rcuwait_init(&rq->hotplug_wait);
-# endif
-#endif /* CONFIG_SMP */
+#endif
 		hrtick_rq_init(rq);
 		atomic_set(&rq->nr_iowait, 0);
 		fair_server_init(rq);
@@ -8696,8 +8619,9 @@ void __init sched_init(void)
 
 #ifdef CONFIG_SMP
 	idle_thread_set_boot_cpu();
-	balance_push_set(smp_processor_id(), false);
 #endif
+
+	balance_push_set(smp_processor_id(), false);
 	init_sched_fair_class();
 	init_sched_ext_class();
 
diff --git a/kernel/sched/cpudeadline.h b/kernel/sched/cpudeadline.h
index 3f7c73d1d189..11c0f1faa7e1 100644
--- a/kernel/sched/cpudeadline.h
+++ b/kernel/sched/cpudeadline.h
@@ -17,7 +17,6 @@ struct cpudl {
 	struct cpudl_item	*elements;
 };
 
-#ifdef CONFIG_SMP
 int  cpudl_find(struct cpudl *cp, struct task_struct *p, struct cpumask *later_mask);
 void cpudl_set(struct cpudl *cp, int cpu, u64 dl);
 void cpudl_clear(struct cpudl *cp, int cpu);
@@ -25,4 +24,3 @@ int  cpudl_init(struct cpudl *cp);
 void cpudl_set_freecpu(struct cpudl *cp, int cpu);
 void cpudl_clear_freecpu(struct cpudl *cp, int cpu);
 void cpudl_cleanup(struct cpudl *cp);
-#endif /* CONFIG_SMP */
diff --git a/kernel/sched/cpupri.h b/kernel/sched/cpupri.h
index 24add19625ff..6f562088c056 100644
--- a/kernel/sched/cpupri.h
+++ b/kernel/sched/cpupri.h
@@ -20,7 +20,6 @@ struct cpupri {
 	int			*cpu_to_pri;
 };
 
-#ifdef CONFIG_SMP
 int  cpupri_find(struct cpupri *cp, struct task_struct *p,
 		 struct cpumask *lowest_mask);
 int  cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
@@ -29,4 +28,3 @@ int  cpupri_find_fitness(struct cpupri *cp, struct task_struct *p,
 void cpupri_set(struct cpupri *cp, int cpu, int pri);
 int  cpupri_init(struct cpupri *cp);
 void cpupri_cleanup(struct cpupri *cp);
-#endif /* CONFIG_SMP */
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index a2cea68b2198..bf9b70a3ff95 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -115,7 +115,6 @@ static inline bool is_dl_boosted(struct sched_dl_entity *dl_se)
 }
 #endif /* !CONFIG_RT_MUTEXES */
 
-#ifdef CONFIG_SMP
 static inline struct dl_bw *dl_bw_of(int i)
 {
 	RCU_LOCKDEP_WARN(!rcu_read_lock_sched_held(),
@@ -195,35 +194,6 @@ void __dl_update(struct dl_bw *dl_b, s64 bw)
 		rq->dl.extra_bw += bw;
 	}
 }
-#else /* !CONFIG_SMP: */
-static inline struct dl_bw *dl_bw_of(int i)
-{
-	return &cpu_rq(i)->dl.dl_bw;
-}
-
-static inline int dl_bw_cpus(int i)
-{
-	return 1;
-}
-
-static inline unsigned long dl_bw_capacity(int i)
-{
-	return SCHED_CAPACITY_SCALE;
-}
-
-bool dl_bw_visited(int cpu, u64 cookie)
-{
-	return false;
-}
-
-static inline
-void __dl_update(struct dl_bw *dl_b, s64 bw)
-{
-	struct dl_rq *dl = container_of(dl_b, struct dl_rq, dl_bw);
-
-	dl->extra_bw += bw;
-}
-#endif /* !CONFIG_SMP */
 
 static inline
 void __dl_sub(struct dl_bw *dl_b, u64 tsk_bw, int cpus)
@@ -556,23 +526,17 @@ void init_dl_rq(struct dl_rq *dl_rq)
 {
 	dl_rq->root = RB_ROOT_CACHED;
 
-#ifdef CONFIG_SMP
 	/* zero means no -deadline tasks */
 	dl_rq->earliest_dl.curr = dl_rq->earliest_dl.next = 0;
 
 	dl_rq->overloaded = 0;
 	dl_rq->pushable_dl_tasks_root = RB_ROOT_CACHED;
-#else
-	init_dl_bw(&dl_rq->dl_bw);
-#endif
 
 	dl_rq->running_bw = 0;
 	dl_rq->this_bw = 0;
 	init_dl_rq_bw_ratio(dl_rq);
 }
 
-#ifdef CONFIG_SMP
-
 static inline int dl_overloaded(struct rq *rq)
 {
 	return atomic_read(&rq->rd->dlo_count);
@@ -757,37 +721,6 @@ static struct rq *dl_task_offline_migration(struct rq *rq, struct task_struct *p
 	return later_rq;
 }
 
-#else /* !CONFIG_SMP: */
-
-static inline
-void enqueue_pushable_dl_task(struct rq *rq, struct task_struct *p)
-{
-}
-
-static inline
-void dequeue_pushable_dl_task(struct rq *rq, struct task_struct *p)
-{
-}
-
-static inline
-void inc_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
-{
-}
-
-static inline
-void dec_dl_migration(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
-{
-}
-
-static inline void deadline_queue_push_tasks(struct rq *rq)
-{
-}
-
-static inline void deadline_queue_pull_task(struct rq *rq)
-{
-}
-#endif /* !CONFIG_SMP */
-
 static void
 enqueue_dl_entity(struct sched_dl_entity *dl_se, int flags);
 static void enqueue_task_dl(struct rq *rq, struct task_struct *p, int flags);
@@ -1199,7 +1132,6 @@ static int start_dl_timer(struct sched_dl_entity *dl_se)
 
 static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
 {
-#ifdef CONFIG_SMP
 	/*
 	 * Queueing this task back might have overloaded rq, check if we need
 	 * to kick someone away.
@@ -1213,7 +1145,6 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
 		push_dl_task(rq);
 		rq_repin_lock(rq, rf);
 	}
-#endif /* CONFIG_SMP */
 }
 
 /* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
@@ -1343,7 +1274,6 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 		goto unlock;
 	}
 
-#ifdef CONFIG_SMP
 	if (unlikely(!rq->online)) {
 		/*
 		 * If the runqueue is no longer available, migrate the
@@ -1360,7 +1290,6 @@ static enum hrtimer_restart dl_task_timer(struct hrtimer *timer)
 		 * there.
 		 */
 	}
-#endif /* CONFIG_SMP */
 
 	enqueue_task_dl(rq, p, ENQUEUE_REPLENISH);
 	if (dl_task(rq->donor))
@@ -1848,8 +1777,6 @@ static void init_dl_inactive_task_timer(struct sched_dl_entity *dl_se)
 #define __node_2_dle(node) \
 	rb_entry((node), struct sched_dl_entity, rb_node)
 
-#ifdef CONFIG_SMP
-
 static void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 {
 	struct rq *rq = rq_of_dl_rq(dl_rq);
@@ -1885,13 +1812,6 @@ static void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline)
 	}
 }
 
-#else /* !CONFIG_SMP: */
-
-static inline void inc_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
-static inline void dec_dl_deadline(struct dl_rq *dl_rq, u64 deadline) {}
-
-#endif /* !CONFIG_SMP */
-
 static inline
 void inc_dl_tasks(struct sched_dl_entity *dl_se, struct dl_rq *dl_rq)
 {
@@ -2218,8 +2138,6 @@ static void yield_task_dl(struct rq *rq)
 	rq_clock_skip_update(rq);
 }
 
-#ifdef CONFIG_SMP
-
 static inline bool dl_task_is_earliest_deadline(struct task_struct *p,
 						 struct rq *rq)
 {
@@ -2349,7 +2267,6 @@ static int balance_dl(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
 
 	return sched_stop_runnable(rq) || sched_dl_runnable(rq);
 }
-#endif /* CONFIG_SMP */
 
 /*
  * Only called when both the current and waking task are -deadline
@@ -2363,7 +2280,6 @@ static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
 		return;
 	}
 
-#ifdef CONFIG_SMP
 	/*
 	 * In the unlikely case current and p have the same deadline
 	 * let us try to decide what's the best thing to do...
@@ -2371,7 +2287,6 @@ static void wakeup_preempt_dl(struct rq *rq, struct task_struct *p,
 	if ((p->dl.deadline == rq->donor->dl.deadline) &&
 	    !test_tsk_need_resched(rq->curr))
 		check_preempt_equal_dl(rq, p);
-#endif /* CONFIG_SMP */
 }
 
 #ifdef CONFIG_SCHED_HRTICK
@@ -2504,8 +2419,6 @@ static void task_fork_dl(struct task_struct *p)
 	 */
 }
 
-#ifdef CONFIG_SMP
-
 /* Only try algorithms three times */
 #define DL_MAX_TRIES 3
 
@@ -2999,8 +2912,6 @@ void dl_clear_root_domain_cpu(int cpu)
 	dl_clear_root_domain(cpu_rq(cpu)->rd);
 }
 
-#endif /* CONFIG_SMP */
-
 static void switched_from_dl(struct rq *rq, struct task_struct *p)
 {
 	/*
@@ -3073,10 +2984,8 @@ static void switched_to_dl(struct rq *rq, struct task_struct *p)
 	}
 
 	if (rq->donor != p) {
-#ifdef CONFIG_SMP
 		if (p->nr_cpus_allowed > 1 && rq->dl.overloaded)
 			deadline_queue_push_tasks(rq);
-#endif
 		if (dl_task(rq->donor))
 			wakeup_preempt_dl(rq, p, 0);
 		else
@@ -3153,7 +3062,6 @@ DEFINE_SCHED_CLASS(dl) = {
 	.put_prev_task		= put_prev_task_dl,
 	.set_next_task		= set_next_task_dl,
 
-#ifdef CONFIG_SMP
 	.balance		= balance_dl,
 	.select_task_rq		= select_task_rq_dl,
 	.migrate_task_rq	= migrate_task_rq_dl,
@@ -3162,7 +3070,6 @@ DEFINE_SCHED_CLASS(dl) = {
 	.rq_offline             = rq_offline_dl,
 	.task_woken		= task_woken_dl,
 	.find_lock_rq		= find_lock_later_rq,
-#endif /* CONFIG_SMP */
 
 	.task_tick		= task_tick_dl,
 	.task_fork              = task_fork_dl,
@@ -3462,7 +3369,6 @@ bool dl_param_changed(struct task_struct *p, const struct sched_attr *attr)
 	return false;
 }
 
-#ifdef CONFIG_SMP
 int dl_cpuset_cpumask_can_shrink(const struct cpumask *cur,
 				 const struct cpumask *trial)
 {
@@ -3574,7 +3480,6 @@ void dl_bw_free(int cpu, u64 dl_bw)
 {
 	dl_bw_manage(dl_bw_req_free, cpu, dl_bw);
 }
-#endif /* CONFIG_SMP */
 
 void print_dl_stats(struct seq_file *m, int cpu)
 {
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 748709c03214..04c0354f05e4 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -286,7 +286,6 @@ static const struct file_operations sched_dynamic_fops = {
 
 __read_mostly bool sched_debug_verbose;
 
-#ifdef CONFIG_SMP
 static struct dentry           *sd_dentry;
 
 
@@ -314,9 +313,6 @@ static ssize_t sched_verbose_write(struct file *filp, const char __user *ubuf,
 
 	return result;
 }
-#else /* !CONFIG_SMP: */
-# define sched_verbose_write debugfs_write_file_bool
-#endif /* !CONFIG_SMP */
 
 static const struct file_operations sched_verbose_fops = {
 	.read =         debugfs_read_file_bool,
@@ -543,8 +539,6 @@ static __init int sched_init_debug(void)
 }
 late_initcall(sched_init_debug);
 
-#ifdef CONFIG_SMP
-
 static cpumask_var_t		sd_sysctl_cpus;
 
 static int sd_flags_show(struct seq_file *m, void *v)
@@ -655,8 +649,6 @@ void dirty_sched_domain_sysctl(int cpu)
 		__cpumask_set_cpu(cpu, sd_sysctl_cpus);
 }
 
-#endif /* CONFIG_SMP */
-
 #ifdef CONFIG_FAIR_GROUP_SCHED
 static void print_cfs_group_stats(struct seq_file *m, int cpu, struct task_group *tg)
 {
@@ -932,11 +924,7 @@ void print_dl_rq(struct seq_file *m, int cpu, struct dl_rq *dl_rq)
 	SEQ_printf(m, "  .%-30s: %lu\n", #x, (unsigned long)(dl_rq->x))
 
 	PU(dl_nr_running);
-#ifdef CONFIG_SMP
 	dl_bw = &cpu_rq(cpu)->rd->dl_bw;
-#else
-	dl_bw = &dl_rq->dl_bw;
-#endif
 	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->bw", dl_bw->bw);
 	SEQ_printf(m, "  .%-30s: %lld\n", "dl_bw->total_bw", dl_bw->total_bw);
 
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 1fabbe01bf93..6b17d3da034a 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -88,7 +88,6 @@ static int __init setup_sched_thermal_decay_shift(char *str)
 }
 __setup("sched_thermal_decay_shift=", setup_sched_thermal_decay_shift);
 
-#ifdef CONFIG_SMP
 /*
  * For asym packing, by default the lower numbered CPU has higher priority.
  */
@@ -111,7 +110,6 @@ int __weak arch_asym_cpu_priority(int cpu)
  * (default: ~5%)
  */
 #define capacity_greater(cap1, cap2) ((cap1) * 1024 > (cap2) * 1078)
-#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_CFS_BANDWIDTH
 /*
@@ -996,7 +994,6 @@ struct sched_entity *__pick_last_entity(struct cfs_rq *cfs_rq)
 /**************************************************************
  * Scheduling class statistics methods:
  */
-#ifdef CONFIG_SMP
 int sched_update_scaling(void)
 {
 	unsigned int factor = get_update_sysctl_factor();
@@ -1008,7 +1005,6 @@ int sched_update_scaling(void)
 
 	return 0;
 }
-#endif /* CONFIG_SMP */
 
 static void clear_buddies(struct cfs_rq *cfs_rq, struct sched_entity *se);
 
@@ -1042,8 +1038,6 @@ static bool update_deadline(struct cfs_rq *cfs_rq, struct sched_entity *se)
 
 #include "pelt.h"
 
-#ifdef CONFIG_SMP
-
 static int select_idle_sibling(struct task_struct *p, int prev_cpu, int cpu);
 static unsigned long task_h_load(struct task_struct *p);
 static unsigned long capacity_of(int cpu);
@@ -1132,18 +1126,6 @@ void post_init_entity_util_avg(struct task_struct *p)
 	sa->runnable_avg = sa->util_avg;
 }
 
-#else /* !CONFIG_SMP: */
-void init_entity_runnable_average(struct sched_entity *se)
-{
-}
-void post_init_entity_util_avg(struct task_struct *p)
-{
-}
-static void update_tg_load_avg(struct cfs_rq *cfs_rq)
-{
-}
-#endif /* !CONFIG_SMP */
-
 static s64 update_curr_se(struct rq *rq, struct sched_entity *curr)
 {
 	u64 now = rq_clock_task(rq);
@@ -3698,14 +3680,12 @@ static void
 account_entity_enqueue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_add(&cfs_rq->load, se->load.weight);
-#ifdef CONFIG_SMP
 	if (entity_is_task(se)) {
 		struct rq *rq = rq_of(cfs_rq);
 
 		account_numa_enqueue(rq, task_of(se));
 		list_add(&se->group_node, &rq->cfs_tasks);
 	}
-#endif
 	cfs_rq->nr_queued++;
 }
 
@@ -3713,12 +3693,10 @@ static void
 account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
 	update_load_sub(&cfs_rq->load, se->load.weight);
-#ifdef CONFIG_SMP
 	if (entity_is_task(se)) {
 		account_numa_dequeue(rq_of(cfs_rq), task_of(se));
 		list_del_init(&se->group_node);
 	}
-#endif
 	cfs_rq->nr_queued--;
 }
 
@@ -3770,7 +3748,6 @@ account_entity_dequeue(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	*ptr -= min_t(typeof(*ptr), *ptr, _val);		\
 } while (0)
 
-#ifdef CONFIG_SMP
 static inline void
 enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 {
@@ -3787,12 +3764,6 @@ dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se)
 	cfs_rq->avg.load_sum = max_t(u32, cfs_rq->avg.load_sum,
 					  cfs_rq->avg.load_avg * PELT_MIN_DIVIDER);
 }
-#else /* !CONFIG_SMP: */
-static inline void
-enqueue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
-static inline void
-dequeue_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) { }
-#endif /* !CONFIG_SMP */
 
 static void place_entity(struct cfs_rq *cfs_rq, struct sched_entity *se, int flags);
 
@@ -3824,13 +3795,11 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
 
 	update_load_set(&se->load, weight);
 
-#ifdef CONFIG_SMP
 	do {
 		u32 divider = get_pelt_divider(&se->avg);
 
 		se->avg.load_avg = div_u64(se_weight(se) * se->avg.load_sum, divider);
 	} while (0);
-#endif
 
 	enqueue_load_avg(cfs_rq, se);
 	if (se->on_rq) {
@@ -3865,7 +3834,6 @@ static void reweight_task_fair(struct rq *rq, struct task_struct *p,
 static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
-#ifdef CONFIG_SMP
 /*
  * All this does is approximate the hierarchical proportion which includes that
  * global sum we all love to hate.
@@ -3972,7 +3940,6 @@ static long calc_group_shares(struct cfs_rq *cfs_rq)
 	 */
 	return clamp_t(long, shares, MIN_SHARES, tg_shares);
 }
-#endif /* CONFIG_SMP */
 
 /*
  * Recomputes the group entity based on the current state of its group
@@ -3993,11 +3960,7 @@ static void update_cfs_group(struct sched_entity *se)
 	if (throttled_hierarchy(gcfs_rq))
 		return;
 
-#ifndef CONFIG_SMP
-	shares = READ_ONCE(gcfs_rq->tg->shares);
-#else
 	shares = calc_group_shares(gcfs_rq);
-#endif
 	if (unlikely(se->load.weight != shares))
 		reweight_entity(cfs_rq_of(se), se, shares);
 }
@@ -4031,7 +3994,6 @@ static inline void cfs_rq_util_change(struct cfs_rq *cfs_rq, int flags)
 	}
 }
 
-#ifdef CONFIG_SMP
 static inline bool load_avg_is_decayed(struct sched_avg *sa)
 {
 	if (sa->load_sum)
@@ -5146,48 +5108,6 @@ static inline void update_misfit_status(struct task_struct *p, struct rq *rq)
 	rq->misfit_task_load = max_t(unsigned long, task_h_load(p), 1);
 }
 
-#else /* !CONFIG_SMP: */
-
-static inline bool cfs_rq_is_decayed(struct cfs_rq *cfs_rq)
-{
-	return !cfs_rq->nr_queued;
-}
-
-#define UPDATE_TG	0x0
-#define SKIP_AGE_LOAD	0x0
-#define DO_ATTACH	0x0
-#define DO_DETACH	0x0
-
-static inline void update_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se, int not_used1)
-{
-	cfs_rq_util_change(cfs_rq, 0);
-}
-
-static inline void remove_entity_load_avg(struct sched_entity *se) {}
-
-static inline void
-attach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
-static inline void
-detach_entity_load_avg(struct cfs_rq *cfs_rq, struct sched_entity *se) {}
-
-static inline int sched_balance_newidle(struct rq *rq, struct rq_flags *rf)
-{
-	return 0;
-}
-
-static inline void
-util_est_enqueue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
-
-static inline void
-util_est_dequeue(struct cfs_rq *cfs_rq, struct task_struct *p) {}
-
-static inline void
-util_est_update(struct cfs_rq *cfs_rq, struct task_struct *p,
-		bool task_sleep) {}
-static inline void update_misfit_status(struct task_struct *p, struct rq *rq) {}
-
-#endif /* !CONFIG_SMP */
-
 void __setparam_fair(struct task_struct *p, const struct sched_attr *attr)
 {
 	struct sched_entity *se = &p->se;
@@ -6090,7 +6010,6 @@ unthrottle_throttle:
 		resched_curr(rq);
 }
 
-#ifdef CONFIG_SMP
 static void __cfsb_csd_unthrottle(void *arg)
 {
 	struct cfs_rq *cursor, *tmp;
@@ -6149,12 +6068,6 @@ static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
 	if (first)
 		smp_call_function_single_async(cpu_of(rq), &rq->cfsb_csd);
 }
-#else /* !CONFIG_SMP: */
-static inline void __unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
-{
-	unthrottle_cfs_rq(cfs_rq);
-}
-#endif /* !CONFIG_SMP */
 
 static void unthrottle_cfs_rq_async(struct cfs_rq *cfs_rq)
 {
@@ -6610,7 +6523,6 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 	 * guaranteed at this point that no additional cfs_rq of this group can
 	 * join a CSD list.
 	 */
-#ifdef CONFIG_SMP
 	for_each_possible_cpu(i) {
 		struct rq *rq = cpu_rq(i);
 		unsigned long flags;
@@ -6622,7 +6534,6 @@ static void destroy_cfs_bandwidth(struct cfs_bandwidth *cfs_b)
 		__cfsb_csd_unthrottle(rq);
 		local_irq_restore(flags);
 	}
-#endif
 }
 
 /*
@@ -6835,7 +6746,6 @@ static inline void hrtick_update(struct rq *rq)
 }
 #endif /* !CONFIG_SCHED_HRTICK */
 
-#ifdef CONFIG_SMP
 static inline bool cpu_overutilized(int cpu)
 {
 	unsigned long  rq_util_min, rq_util_max;
@@ -6877,9 +6787,6 @@ static inline void check_update_overutilized_status(struct rq *rq)
 	if (!is_rd_overutilized(rq->rd) && cpu_overutilized(rq->cpu))
 		set_rd_overutilized(rq->rd, 1);
 }
-#else /* !CONFIG_SMP: */
-static inline void check_update_overutilized_status(struct rq *rq) { }
-#endif /* !CONFIG_SMP */
 
 /* Runqueue only has SCHED_IDLE tasks enqueued */
 static int sched_idle_rq(struct rq *rq)
@@ -6888,12 +6795,10 @@ static int sched_idle_rq(struct rq *rq)
 			rq->nr_running);
 }
 
-#ifdef CONFIG_SMP
 static int sched_idle_cpu(int cpu)
 {
 	return sched_idle_rq(cpu_rq(cpu));
 }
-#endif
 
 static void
 requeue_delayed_entity(struct sched_entity *se)
@@ -7208,8 +7113,6 @@ static inline unsigned int cfs_h_nr_delayed(struct rq *rq)
 	return (rq->cfs.h_nr_queued - rq->cfs.h_nr_runnable);
 }
 
-#ifdef CONFIG_SMP
-
 /* Working cpumask for: sched_balance_rq(), sched_balance_newidle(). */
 static DEFINE_PER_CPU(cpumask_var_t, load_balance_mask);
 static DEFINE_PER_CPU(cpumask_var_t, select_rq_mask);
@@ -8745,9 +8648,6 @@ balance_fair(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
 
 	return sched_balance_newidle(rq, rf) != 0;
 }
-#else /* !CONFIG_SMP: */
-static inline void set_task_max_allowed_capacity(struct task_struct *p) {}
-#endif /* !CONFIG_SMP */
 
 static void set_next_buddy(struct sched_entity *se)
 {
@@ -9057,7 +8957,6 @@ static bool yield_to_task_fair(struct rq *rq, struct task_struct *p)
 	return true;
 }
 
-#ifdef CONFIG_SMP
 /**************************************************
  * Fair scheduling class load-balancing methods.
  *
@@ -12980,8 +12879,6 @@ static void rq_offline_fair(struct rq *rq)
 	clear_tg_offline_cfs_rqs(rq);
 }
 
-#endif /* CONFIG_SMP */
-
 #ifdef CONFIG_SCHED_CORE
 static inline bool
 __entity_slice_used(struct sched_entity *se, int min_nr_tasks)
@@ -13209,7 +13106,6 @@ static void detach_entity_cfs_rq(struct sched_entity *se)
 {
 	struct cfs_rq *cfs_rq = cfs_rq_of(se);
 
-#ifdef CONFIG_SMP
 	/*
 	 * In case the task sched_avg hasn't been attached:
 	 * - A forked task which hasn't been woken up by wake_up_new_task().
@@ -13218,7 +13114,6 @@ static void detach_entity_cfs_rq(struct sched_entity *se)
 	 */
 	if (!se->avg.last_update_time)
 		return;
-#endif
 
 	/* Catch up with the cfs_rq and remove our load when we leave */
 	update_load_avg(cfs_rq, se, 0);
@@ -13282,7 +13177,6 @@ static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool firs
 {
 	struct sched_entity *se = &p->se;
 
-#ifdef CONFIG_SMP
 	if (task_on_rq_queued(p)) {
 		/*
 		 * Move the next running task to the front of the list, so our
@@ -13290,7 +13184,6 @@ static void __set_next_task_fair(struct rq *rq, struct task_struct *p, bool firs
 		 */
 		list_move(&se->group_node, &rq->cfs_tasks);
 	}
-#endif
 	if (!first)
 		return;
 
@@ -13328,9 +13221,7 @@ void init_cfs_rq(struct cfs_rq *cfs_rq)
 {
 	cfs_rq->tasks_timeline = RB_ROOT_CACHED;
 	cfs_rq->min_vruntime = (u64)(-(1LL << 20));
-#ifdef CONFIG_SMP
 	raw_spin_lock_init(&cfs_rq->removed.lock);
-#endif
 }
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
@@ -13345,10 +13236,8 @@ static void task_change_group_fair(struct task_struct *p)
 
 	detach_task_cfs_rq(p);
 
-#ifdef CONFIG_SMP
 	/* Tell se's cfs_rq has been changed -- migrated */
 	p->se.avg.last_update_time = 0;
-#endif
 	set_task_rq(p, task_cpu(p));
 	attach_task_cfs_rq(p);
 }
@@ -13644,7 +13533,6 @@ DEFINE_SCHED_CLASS(fair) = {
 	.put_prev_task		= put_prev_task_fair,
 	.set_next_task          = set_next_task_fair,
 
-#ifdef CONFIG_SMP
 	.balance		= balance_fair,
 	.select_task_rq		= select_task_rq_fair,
 	.migrate_task_rq	= migrate_task_rq_fair,
@@ -13654,7 +13542,6 @@ DEFINE_SCHED_CLASS(fair) = {
 
 	.task_dead		= task_dead_fair,
 	.set_cpus_allowed	= set_cpus_allowed_fair,
-#endif
 
 	.task_tick		= task_tick_fair,
 	.task_fork		= task_fork_fair,
@@ -13717,7 +13604,6 @@ void show_numa_stats(struct task_struct *p, struct seq_file *m)
 
 __init void init_sched_fair_class(void)
 {
-#ifdef CONFIG_SMP
 	int i;
 
 	for_each_possible_cpu(i) {
@@ -13739,5 +13625,4 @@ __init void init_sched_fair_class(void)
 	nohz.next_blocked = jiffies;
 	zalloc_cpumask_var(&nohz.idle_cpus_mask, GFP_NOWAIT);
 #endif
-#endif /* CONFIG_SMP */
 }
diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
index a5d4933e6b70..62c3fa543c0f 100644
--- a/kernel/sched/pelt.h
+++ b/kernel/sched/pelt.h
@@ -3,7 +3,6 @@
 #define _KERNEL_SCHED_PELT_H
 #include "sched.h"
 
-#ifdef CONFIG_SMP
 #include "sched-pelt.h"
 
 int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
@@ -187,55 +186,4 @@ static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
 }
 #endif /* !CONFIG_CFS_BANDWIDTH */
 
-#else /* !CONFIG_SMP: */
-
-static inline int
-update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
-{
-	return 0;
-}
-
-static inline int
-update_rt_rq_load_avg(u64 now, struct rq *rq, int running)
-{
-	return 0;
-}
-
-static inline int
-update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
-{
-	return 0;
-}
-
-static inline int
-update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
-{
-	return 0;
-}
-
-static inline u64 hw_load_avg(struct rq *rq)
-{
-	return 0;
-}
-
-static inline int
-update_irq_load_avg(struct rq *rq, u64 running)
-{
-	return 0;
-}
-
-static inline u64 rq_clock_pelt(struct rq *rq)
-{
-	return rq_clock_task(rq);
-}
-
-static inline void
-update_rq_clock_pelt(struct rq *rq, s64 delta) { }
-
-static inline void
-update_idle_rq_clock_pelt(struct rq *rq) { }
-
-static inline void update_idle_cfs_rq_clock_pelt(struct cfs_rq *cfs_rq) { }
-#endif /* !CONFIG_SMP */
-
 #endif /* _KERNEL_SCHED_PELT_H */
diff --git a/kernel/sched/rt.c b/kernel/sched/rt.c
index 7e8ed05d302a..ab211706b160 100644
--- a/kernel/sched/rt.c
+++ b/kernel/sched/rt.c
@@ -2454,7 +2454,11 @@ void __init init_sched_rt_class(void)
 					GFP_KERNEL, cpu_to_node(i));
 	}
 }
-#endif /* CONFIG_SMP */
+#else /* !CONFIG_SMP: */
+void __init init_sched_rt_class(void)
+{
+}
+#endif /* !CONFIG_SMP */
 
 /*
  * When switching a task to RT, we may overload the runqueue
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 2bf804b8c89b..7a7ebc2a3675 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -443,14 +443,12 @@ struct task_group {
 	/* runqueue "owned" by this group on each CPU */
 	struct cfs_rq		**cfs_rq;
 	unsigned long		shares;
-#ifdef CONFIG_SMP
 	/*
 	 * load_avg can be heavily contended at clock tick time, so put
 	 * it in its own cache-line separated from the fields above which
 	 * will also be accessed at each tick.
 	 */
 	atomic_long_t		load_avg ____cacheline_aligned;
-#endif /* CONFIG_SMP */
 #endif /* CONFIG_FAIR_GROUP_SCHED */
 
 #ifdef CONFIG_RT_GROUP_SCHED
@@ -574,13 +572,8 @@ extern int sched_group_set_shares(struct task_group *tg, unsigned long shares);
 
 extern int sched_group_set_idle(struct task_group *tg, long idle);
 
-#ifdef CONFIG_SMP
 extern void set_task_rq_fair(struct sched_entity *se,
 			     struct cfs_rq *prev, struct cfs_rq *next);
-#else /* !CONFIG_SMP: */
-static inline void set_task_rq_fair(struct sched_entity *se,
-			     struct cfs_rq *prev, struct cfs_rq *next) { }
-#endif /* !CONFIG_SMP */
 #else /* !CONFIG_FAIR_GROUP_SCHED: */
 static inline int sched_group_set_shares(struct task_group *tg, unsigned long shares) { return 0; }
 static inline int sched_group_set_idle(struct task_group *tg, long idle) { return 0; }
@@ -668,7 +661,6 @@ struct cfs_rq {
 	struct sched_entity	*curr;
 	struct sched_entity	*next;
 
-#ifdef CONFIG_SMP
 	/*
 	 * CFS load tracking
 	 */
@@ -700,7 +692,6 @@ struct cfs_rq {
 	u64			last_h_load_update;
 	struct sched_entity	*h_load_next;
 #endif /* CONFIG_FAIR_GROUP_SCHED */
-#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FAIR_GROUP_SCHED
 	struct rq		*rq;	/* CPU runqueue to which this cfs_rq is attached */
@@ -797,14 +788,10 @@ struct rt_rq {
 	struct rt_prio_array	active;
 	unsigned int		rt_nr_running;
 	unsigned int		rr_nr_running;
-#if defined CONFIG_SMP || defined CONFIG_RT_GROUP_SCHED
 	struct {
 		int		curr; /* highest queued rt task prio */
-#ifdef CONFIG_SMP
 		int		next; /* next highest */
-#endif
 	} highest_prio;
-#endif
 #ifdef CONFIG_SMP
 	bool			overloaded;
 	struct plist_head	pushable_tasks;
@@ -840,7 +827,6 @@ struct dl_rq {
 
 	unsigned int		dl_nr_running;
 
-#ifdef CONFIG_SMP
 	/*
 	 * Deadline values of the currently executing and the
 	 * earliest ready task on this rq. Caching these facilitates
@@ -860,9 +846,7 @@ struct dl_rq {
 	 * of the leftmost (earliest deadline) element.
 	 */
 	struct rb_root_cached	pushable_dl_tasks_root;
-#else /* !CONFIG_SMP: */
-	struct dl_bw		dl_bw;
-#endif /* !CONFIG_SMP */
+
 	/*
 	 * "Active utilization" for this runqueue: increased when a
 	 * task wakes up (becomes TASK_RUNNING) and decreased when a
@@ -933,7 +917,6 @@ static inline long se_runnable(struct sched_entity *se)
 
 #endif /* !CONFIG_FAIR_GROUP_SCHED */
 
-#ifdef CONFIG_SMP
 /*
  * XXX we want to get rid of these helpers and use the full load resolution.
  */
@@ -1044,7 +1027,6 @@ static inline void set_rd_overloaded(struct root_domain *rd, int status)
 #ifdef HAVE_RT_PUSH_IPI
 extern void rto_push_irq_work_func(struct irq_work *work);
 #endif
-#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_UCLAMP_TASK
 /*
@@ -1108,18 +1090,14 @@ struct rq {
 	unsigned int		numa_migrate_on;
 #endif
 #ifdef CONFIG_NO_HZ_COMMON
-#ifdef CONFIG_SMP
 	unsigned long		last_blocked_load_update_tick;
 	unsigned int		has_blocked_load;
 	call_single_data_t	nohz_csd;
-#endif /* CONFIG_SMP */
 	unsigned int		nohz_tick_stopped;
 	atomic_t		nohz_flags;
 #endif /* CONFIG_NO_HZ_COMMON */
 
-#ifdef CONFIG_SMP
 	unsigned int		ttwu_pending;
-#endif
 	u64			nr_switches;
 
 #ifdef CONFIG_UCLAMP_TASK
@@ -1184,7 +1162,6 @@ struct rq {
 	int membarrier_state;
 #endif
 
-#ifdef CONFIG_SMP
 	struct root_domain		*rd;
 	struct sched_domain __rcu	*sd;
 
@@ -1225,7 +1202,6 @@ struct rq {
 #ifdef CONFIG_HOTPLUG_CPU
 	struct rcuwait		hotplug_wait;
 #endif
-#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 	u64			prev_irq_time;
@@ -1272,9 +1248,7 @@ struct rq {
 	struct cpuidle_state	*idle_state;
 #endif
 
-#ifdef CONFIG_SMP
 	unsigned int		nr_pinned;
-#endif
 	unsigned int		push_busy;
 	struct cpu_stop_work	push_work;
 
@@ -1300,7 +1274,7 @@ struct rq {
 	/* Scratch cpumask to be temporarily used under rq_lock */
 	cpumask_var_t		scratch_mask;
 
-#if defined(CONFIG_CFS_BANDWIDTH) && defined(CONFIG_SMP)
+#ifdef CONFIG_CFS_BANDWIDTH
 	call_single_data_t	cfsb_csd;
 	struct list_head	cfsb_csd_list;
 #endif
@@ -1963,8 +1937,6 @@ init_numa_balancing(unsigned long clone_flags, struct task_struct *p)
 
 #endif /* !CONFIG_NUMA_BALANCING */
 
-#ifdef CONFIG_SMP
-
 static inline void
 queue_balance_callback(struct rq *rq,
 		       struct balance_callback *head,
@@ -2130,8 +2102,6 @@ static inline const struct cpumask *task_user_cpus(struct task_struct *p)
 	return p->user_cpus_ptr;
 }
 
-#endif /* CONFIG_SMP */
-
 #ifdef CONFIG_CGROUP_SCHED
 
 /*
@@ -2418,7 +2388,6 @@ struct sched_class {
 	void (*put_prev_task)(struct rq *rq, struct task_struct *p, struct task_struct *next);
 	void (*set_next_task)(struct rq *rq, struct task_struct *p, bool first);
 
-#ifdef CONFIG_SMP
 	int  (*select_task_rq)(struct task_struct *p, int task_cpu, int flags);
 
 	void (*migrate_task_rq)(struct task_struct *p, int new_cpu);
@@ -2431,7 +2400,6 @@ struct sched_class {
 	void (*rq_offline)(struct rq *rq);
 
 	struct rq *(*find_lock_rq)(struct task_struct *p, struct rq *rq);
-#endif /* CONFIG_SMP */
 
 	void (*task_tick)(struct rq *rq, struct task_struct *p, int queued);
 	void (*task_fork)(struct task_struct *p);
@@ -2583,8 +2551,6 @@ extern struct task_struct *pick_task_idle(struct rq *rq);
 #define SCA_MIGRATE_ENABLE	0x04
 #define SCA_USER		0x08
 
-#ifdef CONFIG_SMP
-
 extern void update_group_capacity(struct sched_domain *sd, int cpu);
 
 extern void sched_balance_trigger(struct rq *rq);
@@ -2636,26 +2602,6 @@ static inline struct task_struct *get_push_task(struct rq *rq)
 
 extern int push_cpu_stop(void *arg);
 
-#else /* !CONFIG_SMP: */
-
-static inline bool task_allowed_on_cpu(struct task_struct *p, int cpu)
-{
-	return true;
-}
-
-static inline int __set_cpus_allowed_ptr(struct task_struct *p,
-					 struct affinity_context *ctx)
-{
-	return set_cpus_allowed_ptr(p, ctx->new_mask);
-}
-
-static inline cpumask_t *alloc_user_cpus_ptr(int node)
-{
-	return NULL;
-}
-
-#endif /* !CONFIG_SMP */
-
 #ifdef CONFIG_CPU_IDLE
 
 static inline void idle_set_state(struct rq *rq,
@@ -2932,8 +2878,6 @@ static inline class_##name##_t class_##name##_constructor(type *lock, type *lock
 { class_##name##_t _t = { .lock = lock, .lock2 = lock2 }, *_T = &_t;			\
   _lock; return _t; }
 
-#ifdef CONFIG_SMP
-
 static inline bool rq_order_less(struct rq *rq1, struct rq *rq2)
 {
 #ifdef CONFIG_SCHED_CORE
@@ -3093,42 +3037,6 @@ extern void set_rq_offline(struct rq *rq);
 
 extern bool sched_smp_initialized;
 
-#else /* !CONFIG_SMP: */
-
-/*
- * double_rq_lock - safely lock two runqueues
- *
- * Note this does not disable interrupts like task_rq_lock,
- * you need to do so manually before calling.
- */
-static inline void double_rq_lock(struct rq *rq1, struct rq *rq2)
-	__acquires(rq1->lock)
-	__acquires(rq2->lock)
-{
-	WARN_ON_ONCE(!irqs_disabled());
-	WARN_ON_ONCE(rq1 != rq2);
-	raw_spin_rq_lock(rq1);
-	__acquire(rq2->lock);	/* Fake it out ;) */
-	double_rq_clock_clear_update(rq1, rq2);
-}
-
-/*
- * double_rq_unlock - safely unlock two runqueues
- *
- * Note this does not restore interrupts like task_rq_unlock,
- * you need to do so manually after calling.
- */
-static inline void double_rq_unlock(struct rq *rq1, struct rq *rq2)
-	__releases(rq1->lock)
-	__releases(rq2->lock)
-{
-	WARN_ON_ONCE(rq1 != rq2);
-	raw_spin_rq_unlock(rq1);
-	__release(rq2->lock);
-}
-
-#endif /* !CONFIG_SMP */
-
 DEFINE_LOCK_GUARD_2(double_rq_lock, struct rq,
 		    double_rq_lock(_T->lock, _T->lock2),
 		    double_rq_unlock(_T->lock, _T->lock2))
@@ -3187,7 +3095,7 @@ extern void nohz_balance_exit_idle(struct rq *rq);
 static inline void nohz_balance_exit_idle(struct rq *rq) { }
 #endif /* !CONFIG_NO_HZ_COMMON */
 
-#if defined(CONFIG_SMP) && defined(CONFIG_NO_HZ_COMMON)
+#ifdef CONFIG_NO_HZ_COMMON
 extern void nohz_run_idle_balance(int cpu);
 #else
 static inline void nohz_run_idle_balance(int cpu) { }
@@ -3313,8 +3221,6 @@ static inline void cpufreq_update_util(struct rq *rq, unsigned int flags) { }
 # define arch_scale_freq_invariant()	false
 #endif
 
-#ifdef CONFIG_SMP
-
 unsigned long effective_cpu_util(int cpu, unsigned long util_cfs,
 				 unsigned long *min,
 				 unsigned long *max);
@@ -3358,10 +3264,6 @@ static inline unsigned long cpu_util_rt(struct rq *rq)
 	return READ_ONCE(rq->avg_rt.util_avg);
 }
 
-#else /* !CONFIG_SMP: */
-static inline bool update_other_load_avgs(struct rq *rq) { return false; }
-#endif /* !CONFIG_SMP */
-
 #ifdef CONFIG_UCLAMP_TASK
 
 unsigned long uclamp_eff_value(struct task_struct *p, enum uclamp_id clamp_id);
@@ -3580,7 +3482,6 @@ static inline void membarrier_switch_mm(struct rq *rq,
 
 #endif /* !CONFIG_MEMBARRIER */
 
-#ifdef CONFIG_SMP
 static inline bool is_per_cpu_kthread(struct task_struct *p)
 {
 	if (!(p->flags & PF_KTHREAD))
@@ -3591,7 +3492,6 @@ static inline bool is_per_cpu_kthread(struct task_struct *p)
 
 	return true;
 }
-#endif /* CONFIG_SMP */
 
 extern void swake_up_all_locked(struct swait_queue_head *q);
 extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
@@ -3890,7 +3790,6 @@ static inline void init_sched_mm_cid(struct task_struct *t) { }
 
 extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
 extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
-#ifdef CONFIG_SMP
 static inline
 void move_queued_task_locked(struct rq *src_rq, struct rq *dst_rq, struct task_struct *task)
 {
@@ -3911,7 +3810,6 @@ bool task_is_pushable(struct rq *rq, struct task_struct *p, int cpu)
 
 	return false;
 }
-#endif /* CONFIG_SMP */
 
 #ifdef CONFIG_RT_MUTEXES
 
@@ -3952,21 +3850,8 @@ extern void check_class_changed(struct rq *rq, struct task_struct *p,
 				const struct sched_class *prev_class,
 				int oldprio);
 
-#ifdef CONFIG_SMP
 extern struct balance_callback *splice_balance_callbacks(struct rq *rq);
 extern void balance_callbacks(struct rq *rq, struct balance_callback *head);
-#else /* !CONFIG_SMP: */
-
-static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
-{
-	return NULL;
-}
-
-static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
-{
-}
-
-#endif /* !CONFIG_SMP */
 
 #ifdef CONFIG_SCHED_CLASS_EXT
 /*
diff --git a/kernel/sched/syscalls.c b/kernel/sched/syscalls.c
index 5cb5e9487f0d..d7fccf871c7d 100644
--- a/kernel/sched/syscalls.c
+++ b/kernel/sched/syscalls.c
@@ -1119,7 +1119,6 @@ SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
 	return copy_struct_to_user(uattr, usize, &kattr, sizeof(kattr), NULL);
 }
 
-#ifdef CONFIG_SMP
 int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 {
 	/*
@@ -1148,7 +1147,6 @@ int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
 
 	return 0;
 }
-#endif /* CONFIG_SMP */
 
 int __sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
 {
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index ee347d9c5df4..f2c10167f2bc 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -17,8 +17,6 @@ void sched_domains_mutex_unlock(void)
 	mutex_unlock(&sched_domains_mutex);
 }
 
-#ifdef CONFIG_SMP
-
 /* Protected by sched_domains_mutex: */
 static cpumask_var_t sched_domains_tmpmask;
 static cpumask_var_t sched_domains_tmpmask2;
@@ -1322,11 +1320,10 @@ next:
 	update_group_capacity(sd, cpu);
 }
 
-#ifdef CONFIG_SMP
-
 /* Update the "asym_prefer_cpu" when arch_asym_cpu_priority() changes. */
 void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
 {
+#ifdef CONFIG_SMP
 	int asym_prefer_cpu = cpu;
 	struct sched_domain *sd;
 
@@ -1376,9 +1373,8 @@ void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
 
 		WRITE_ONCE(sg->asym_prefer_cpu, asym_prefer_cpu);
 	}
-}
-
 #endif /* CONFIG_SMP */
+}
 
 /*
  * Set of available CPUs grouped by their corresponding capacities
@@ -2844,5 +2840,3 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
 	partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
 	sched_domains_mutex_unlock();
 }
-
-#endif /* CONFIG_SMP */
-- 
cgit v1.2.3


From 06ddd17521bf11a3e7f59dafdf5c148f29467d2c Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 28 May 2025 10:09:02 +0200
Subject: sched/smp: Always define is_percpu_thread() and scheduler_ipi()

Simplify the scheduler by making the CONFIG_SMP=y primitives
of is_percpu_thread() and scheduler_ipi() unconditional.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20250528080924.2273858-22-mingo@kernel.org
---
 include/linux/sched.h | 8 --------
 1 file changed, 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 376befdec4b0..eec6b225e9d1 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1765,12 +1765,8 @@ extern struct pid *cad_pid;
 
 static __always_inline bool is_percpu_thread(void)
 {
-#ifdef CONFIG_SMP
 	return (current->flags & PF_NO_SETAFFINITY) &&
 		(current->nr_cpus_allowed  == 1);
-#else
-	return true;
-#endif
 }
 
 /* Per-process atomic flags. */
@@ -1967,7 +1963,6 @@ extern void __set_task_comm(struct task_struct *tsk, const char *from, bool exec
 	buf;						\
 })
 
-#ifdef CONFIG_SMP
 static __always_inline void scheduler_ipi(void)
 {
 	/*
@@ -1977,9 +1972,6 @@ static __always_inline void scheduler_ipi(void)
 	 */
 	preempt_fold_need_resched();
 }
-#else
-static inline void scheduler_ipi(void) { }
-#endif
 
 extern unsigned long wait_task_inactive(struct task_struct *, unsigned int match_state);
 
-- 
cgit v1.2.3


From 1f25730e5a780b33f78e3ea23e64d3f75e0b2042 Mon Sep 17 00:00:00 2001
From: Ingo Molnar <mingo@kernel.org>
Date: Wed, 28 May 2025 10:09:07 +0200
Subject: sched/smp: Use the SMP version of sched_exec()

Simplify the scheduler making CONFIG_SMP=y sched_exec()
code unconditional.

Signed-off-by: Ingo Molnar <mingo@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Cc: Dietmar Eggemann <dietmar.eggemann@arm.com>
Cc: Juri Lelli <juri.lelli@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Shrikanth Hegde <sshegde@linux.ibm.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Valentin Schneider <vschneid@redhat.com>
Cc: Vincent Guittot <vincent.guittot@linaro.org>
Link: https://lore.kernel.org/r/20250528080924.2273858-27-mingo@kernel.org
---
 include/linux/sched/task.h | 4 ----
 kernel/sched/core.c        | 4 ----
 2 files changed, 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index ca1db4b92c32..c517dbc242f7 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -109,11 +109,7 @@ int kernel_wait(pid_t pid, int *stat);
 extern void free_task(struct task_struct *tsk);
 
 /* sched_exec is called by processes performing an exec */
-#ifdef CONFIG_SMP
 extern void sched_exec(void);
-#else
-#define sched_exec()   {}
-#endif
 
 static inline struct task_struct *get_task_struct(struct task_struct *t)
 {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c108b5c2e115..fa89006e05e9 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5419,8 +5419,6 @@ unsigned int nr_iowait(void)
 	return sum;
 }
 
-#ifdef CONFIG_SMP
-
 /*
  * sched_exec - execve() is a valuable balancing opportunity, because at
  * this point the task has the smallest effective memory and cache footprint.
@@ -5444,8 +5442,6 @@ void sched_exec(void)
 	stop_one_cpu(task_cpu(p), migration_cpu_stop, &arg);
 }
 
-#endif /* CONFIG_SMP */
-
 DEFINE_PER_CPU(struct kernel_stat, kstat);
 DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
 
-- 
cgit v1.2.3


From 71203f68c7749609d7fc8ae6ad054bdedeb24f91 Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Sat, 24 May 2025 20:32:20 +0800
Subject: padata: Fix pd UAF once and for all

There is a race condition/UAF in padata_reorder that goes back
to the initial commit.  A reference count is taken at the start
of the process in padata_do_parallel, and released at the end in
padata_serial_worker.

This reference count is (and only is) required for padata_replace
to function correctly.  If padata_replace is never called then
there is no issue.

In the function padata_reorder which serves as the core of padata,
as soon as padata is added to queue->serial.list, and the associated
spin lock released, that padata may be processed and the reference
count on pd would go away.

Fix this by getting the next padata before the squeue->serial lock
is released.

In order to make this possible, simplify padata_reorder by only
calling it once the next padata arrives.

Fixes: 16295bec6398 ("padata: Generic parallelization/serialization interface")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/padata.h |   3 --
 kernel/padata.c        | 132 ++++++++++++++-----------------------------------
 2 files changed, 37 insertions(+), 98 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/padata.h b/include/linux/padata.h
index 0146daf34430..b486c7359de2 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -91,7 +91,6 @@ struct padata_cpumask {
  * @cpu: Next CPU to be processed.
  * @cpumask: The cpumasks in use for parallel and serial workers.
  * @reorder_work: work struct for reordering.
- * @lock: Reorder lock.
  */
 struct parallel_data {
 	struct padata_shell		*ps;
@@ -102,8 +101,6 @@ struct parallel_data {
 	unsigned int			processed;
 	int				cpu;
 	struct padata_cpumask		cpumask;
-	struct work_struct		reorder_work;
-	spinlock_t                      ____cacheline_aligned lock;
 };
 
 /**
diff --git a/kernel/padata.c b/kernel/padata.c
index 7eee94166357..25cd3406477a 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -261,20 +261,17 @@ EXPORT_SYMBOL(padata_do_parallel);
  *   be parallel processed by another cpu and is not yet present in
  *   the cpu's reorder queue.
  */
-static struct padata_priv *padata_find_next(struct parallel_data *pd,
-					    bool remove_object)
+static struct padata_priv *padata_find_next(struct parallel_data *pd, int cpu,
+					    unsigned int processed)
 {
 	struct padata_priv *padata;
 	struct padata_list *reorder;
-	int cpu = pd->cpu;
 
 	reorder = per_cpu_ptr(pd->reorder_list, cpu);
 
 	spin_lock(&reorder->lock);
-	if (list_empty(&reorder->list)) {
-		spin_unlock(&reorder->lock);
-		return NULL;
-	}
+	if (list_empty(&reorder->list))
+		goto notfound;
 
 	padata = list_entry(reorder->list.next, struct padata_priv, list);
 
@@ -282,97 +279,52 @@ static struct padata_priv *padata_find_next(struct parallel_data *pd,
 	 * Checks the rare case where two or more parallel jobs have hashed to
 	 * the same CPU and one of the later ones finishes first.
 	 */
-	if (padata->seq_nr != pd->processed) {
-		spin_unlock(&reorder->lock);
-		return NULL;
-	}
-
-	if (remove_object) {
-		list_del_init(&padata->list);
-		++pd->processed;
-		pd->cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu);
-	}
+	if (padata->seq_nr != processed)
+		goto notfound;
 
+	list_del_init(&padata->list);
 	spin_unlock(&reorder->lock);
 	return padata;
+
+notfound:
+	pd->processed = processed;
+	pd->cpu = cpu;
+	spin_unlock(&reorder->lock);
+	return NULL;
 }
 
-static void padata_reorder(struct parallel_data *pd)
+static void padata_reorder(struct padata_priv *padata)
 {
+	struct parallel_data *pd = padata->pd;
 	struct padata_instance *pinst = pd->ps->pinst;
-	int cb_cpu;
-	struct padata_priv *padata;
-	struct padata_serial_queue *squeue;
-	struct padata_list *reorder;
+	unsigned int processed;
+	int cpu;
 
-	/*
-	 * We need to ensure that only one cpu can work on dequeueing of
-	 * the reorder queue the time. Calculating in which percpu reorder
-	 * queue the next object will arrive takes some time. A spinlock
-	 * would be highly contended. Also it is not clear in which order
-	 * the objects arrive to the reorder queues. So a cpu could wait to
-	 * get the lock just to notice that there is nothing to do at the
-	 * moment. Therefore we use a trylock and let the holder of the lock
-	 * care for all the objects enqueued during the holdtime of the lock.
-	 */
-	if (!spin_trylock_bh(&pd->lock))
-		return;
+	processed = pd->processed;
+	cpu = pd->cpu;
 
-	while (1) {
-		padata = padata_find_next(pd, true);
+	do {
+		struct padata_serial_queue *squeue;
+		int cb_cpu;
 
-		/*
-		 * If the next object that needs serialization is parallel
-		 * processed by another cpu and is still on it's way to the
-		 * cpu's reorder queue, nothing to do for now.
-		 */
-		if (!padata)
-			break;
+		cpu = cpumask_next_wrap(cpu, pd->cpumask.pcpu);
+		processed++;
 
 		cb_cpu = padata->cb_cpu;
 		squeue = per_cpu_ptr(pd->squeue, cb_cpu);
 
 		spin_lock(&squeue->serial.lock);
 		list_add_tail(&padata->list, &squeue->serial.list);
-		spin_unlock(&squeue->serial.lock);
-
 		queue_work_on(cb_cpu, pinst->serial_wq, &squeue->work);
-	}
 
-	spin_unlock_bh(&pd->lock);
-
-	/*
-	 * The next object that needs serialization might have arrived to
-	 * the reorder queues in the meantime.
-	 *
-	 * Ensure reorder queue is read after pd->lock is dropped so we see
-	 * new objects from another task in padata_do_serial.  Pairs with
-	 * smp_mb in padata_do_serial.
-	 */
-	smp_mb();
-
-	reorder = per_cpu_ptr(pd->reorder_list, pd->cpu);
-	if (!list_empty(&reorder->list) && padata_find_next(pd, false)) {
 		/*
-		 * Other context(eg. the padata_serial_worker) can finish the request.
-		 * To avoid UAF issue, add pd ref here, and put pd ref after reorder_work finish.
+		 * If the next object that needs serialization is parallel
+		 * processed by another cpu and is still on it's way to the
+		 * cpu's reorder queue, end the loop.
 		 */
-		padata_get_pd(pd);
-		if (!queue_work(pinst->serial_wq, &pd->reorder_work))
-			padata_put_pd(pd);
-	}
-}
-
-static void invoke_padata_reorder(struct work_struct *work)
-{
-	struct parallel_data *pd;
-
-	local_bh_disable();
-	pd = container_of(work, struct parallel_data, reorder_work);
-	padata_reorder(pd);
-	local_bh_enable();
-	/* Pairs with putting the reorder_work in the serial_wq */
-	padata_put_pd(pd);
+		padata = padata_find_next(pd, cpu, processed);
+		spin_unlock(&squeue->serial.lock);
+	} while (padata);
 }
 
 static void padata_serial_worker(struct work_struct *serial_work)
@@ -423,6 +375,7 @@ void padata_do_serial(struct padata_priv *padata)
 	struct padata_list *reorder = per_cpu_ptr(pd->reorder_list, hashed_cpu);
 	struct padata_priv *cur;
 	struct list_head *pos;
+	bool gotit = true;
 
 	spin_lock(&reorder->lock);
 	/* Sort in ascending order of sequence number. */
@@ -432,17 +385,14 @@ void padata_do_serial(struct padata_priv *padata)
 		if ((signed int)(cur->seq_nr - padata->seq_nr) < 0)
 			break;
 	}
-	list_add(&padata->list, pos);
+	if (padata->seq_nr != pd->processed) {
+		gotit = false;
+		list_add(&padata->list, pos);
+	}
 	spin_unlock(&reorder->lock);
 
-	/*
-	 * Ensure the addition to the reorder list is ordered correctly
-	 * with the trylock of pd->lock in padata_reorder.  Pairs with smp_mb
-	 * in padata_reorder.
-	 */
-	smp_mb();
-
-	padata_reorder(pd);
+	if (gotit)
+		padata_reorder(padata);
 }
 EXPORT_SYMBOL(padata_do_serial);
 
@@ -632,9 +582,7 @@ static struct parallel_data *padata_alloc_pd(struct padata_shell *ps)
 	padata_init_squeues(pd);
 	pd->seq_nr = -1;
 	refcount_set(&pd->refcnt, 1);
-	spin_lock_init(&pd->lock);
 	pd->cpu = cpumask_first(pd->cpumask.pcpu);
-	INIT_WORK(&pd->reorder_work, invoke_padata_reorder);
 
 	return pd;
 
@@ -1144,12 +1092,6 @@ void padata_free_shell(struct padata_shell *ps)
 	if (!ps)
 		return;
 
-	/*
-	 * Wait for all _do_serial calls to finish to avoid touching
-	 * freed pd's and ps's.
-	 */
-	synchronize_rcu();
-
 	mutex_lock(&ps->pinst->lock);
 	list_del(&ps->list);
 	pd = rcu_dereference_protected(ps->pd, 1);
-- 
cgit v1.2.3


From 09735f0624b494c0959f3327af009283567af320 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Tue, 10 Jun 2025 13:27:13 +0530
Subject: smp: Fix typo in comment for raw_smp_processor_id()

The comment in `smp.h` incorrectly refers to `raw_processor_id()`
instead of the correct function name `raw_smp_processor_id()`.

Suggested-by: Boqun Feng <boqun.feng@gmail.com>
Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Boqun Feng <boqun.feng@gmail.com>
Link: https://lore.kernel.org/all/d096779819962c305b85cd12bda41b593e0981aa.1749536622.git.viresh.kumar@linaro.org
---
 include/linux/smp.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/smp.h b/include/linux/smp.h
index f1aa0952e8c3..bea8d2826e09 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -234,7 +234,7 @@ static inline int get_boot_cpu_id(void)
 #endif /* !SMP */
 
 /**
- * raw_processor_id() - get the current (unstable) CPU id
+ * raw_smp_processor_id() - get the current (unstable) CPU id
  *
  * For then you know what you are doing and need an unstable
  * CPU id.
-- 
cgit v1.2.3


From 91695b8592638c85dc78a15d59250c62b9c68891 Mon Sep 17 00:00:00 2001
From: "Russell King (Oracle)" <rmk+kernel@armlinux.org.uk>
Date: Thu, 12 Jun 2025 16:21:04 +0100
Subject: net: phy: improve rgmii_clock() documentation

Improve the rgmii_clock() documentation to indicate that it can also
be used for MII, GMII and RMII modes as well as RGMII as the required
clock rates are identical, but note that it won't error out for 1G
speeds for MII and RMII.

Signed-off-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/E1uPjjk-0049pI-MD@rmk-PC.armlinux.org.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index c4d8f7c82627..8e2e4fcd050e 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -269,8 +269,10 @@ static inline const char *phy_modes(phy_interface_t interface)
  * rgmii_clock - map link speed to the clock rate
  * @speed: link speed value
  *
- * Description: maps RGMII supported link speeds
- * into the clock rates.
+ * Description: maps RGMII supported link speeds into the clock rates.
+ * This can also be used for MII, GMII, and RMII interface modes as the
+ * clock rates are indentical, but the caller must be aware that errors
+ * for unsupported clock rates will not be signalled.
  *
  * Returns: clock rate or negative errno
  */
-- 
cgit v1.2.3


From 2952daf44a84670a6aa9e13edbc105bdab83ccba Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Thu, 12 Jun 2025 17:28:34 +0200
Subject: dpll: add phase_offset_monitor_get/set callback ops

Add new callback operations for a dpll device:
- phase_offset_monitor_get(..) - to obtain current state of phase offset
  monitor feature from dpll device,
- phase_offset_monitor_set(..) - to allow feature configuration.

Obtain the feature state value using the get callback and provide it to
the user if the device driver implements callbacks.

Execute the set callback upon user requests.

Reviewed-by: Milena Olech <milena.olech@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Acked-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250612152835.1703397-3-arkadiusz.kubalewski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/dpll_netlink.c | 69 +++++++++++++++++++++++++++++++++++++++++++--
 include/linux/dpll.h        |  8 ++++++
 2 files changed, 75 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index c130f87147fa..4619aaa18b9c 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -126,6 +126,26 @@ dpll_msg_add_mode_supported(struct sk_buff *msg, struct dpll_device *dpll,
 	return 0;
 }
 
+static int
+dpll_msg_add_phase_offset_monitor(struct sk_buff *msg, struct dpll_device *dpll,
+				  struct netlink_ext_ack *extack)
+{
+	const struct dpll_device_ops *ops = dpll_device_ops(dpll);
+	enum dpll_feature_state state;
+	int ret;
+
+	if (ops->phase_offset_monitor_set && ops->phase_offset_monitor_get) {
+		ret = ops->phase_offset_monitor_get(dpll, dpll_priv(dpll),
+						    &state, extack);
+		if (ret)
+			return ret;
+		if (nla_put_u32(msg, DPLL_A_PHASE_OFFSET_MONITOR, state))
+			return -EMSGSIZE;
+	}
+
+	return 0;
+}
+
 static int
 dpll_msg_add_lock_status(struct sk_buff *msg, struct dpll_device *dpll,
 			 struct netlink_ext_ack *extack)
@@ -591,6 +611,9 @@ dpll_device_get_one(struct dpll_device *dpll, struct sk_buff *msg,
 		return ret;
 	if (nla_put_u32(msg, DPLL_A_TYPE, dpll->type))
 		return -EMSGSIZE;
+	ret = dpll_msg_add_phase_offset_monitor(msg, dpll, extack);
+	if (ret)
+		return ret;
 
 	return 0;
 }
@@ -746,6 +769,31 @@ int dpll_pin_change_ntf(struct dpll_pin *pin)
 }
 EXPORT_SYMBOL_GPL(dpll_pin_change_ntf);
 
+static int
+dpll_phase_offset_monitor_set(struct dpll_device *dpll, struct nlattr *a,
+			      struct netlink_ext_ack *extack)
+{
+	const struct dpll_device_ops *ops = dpll_device_ops(dpll);
+	enum dpll_feature_state state = nla_get_u32(a), old_state;
+	int ret;
+
+	if (!(ops->phase_offset_monitor_set && ops->phase_offset_monitor_get)) {
+		NL_SET_ERR_MSG_ATTR(extack, a, "dpll device not capable of phase offset monitor");
+		return -EOPNOTSUPP;
+	}
+	ret = ops->phase_offset_monitor_get(dpll, dpll_priv(dpll), &old_state,
+					    extack);
+	if (ret) {
+		NL_SET_ERR_MSG(extack, "unable to get current state of phase offset monitor");
+		return ret;
+	}
+	if (state == old_state)
+		return 0;
+
+	return ops->phase_offset_monitor_set(dpll, dpll_priv(dpll), state,
+					     extack);
+}
+
 static int
 dpll_pin_freq_set(struct dpll_pin *pin, struct nlattr *a,
 		  struct netlink_ext_ack *extack)
@@ -1533,12 +1581,29 @@ int dpll_nl_device_get_doit(struct sk_buff *skb, struct genl_info *info)
 	return genlmsg_reply(msg, info);
 }
 
-int dpll_nl_device_set_doit(struct sk_buff *skb, struct genl_info *info)
+static int
+dpll_set_from_nlattr(struct dpll_device *dpll, struct genl_info *info)
 {
-	/* placeholder for set command */
+	int ret;
+
+	if (info->attrs[DPLL_A_PHASE_OFFSET_MONITOR]) {
+		struct nlattr *a = info->attrs[DPLL_A_PHASE_OFFSET_MONITOR];
+
+		ret = dpll_phase_offset_monitor_set(dpll, a, info->extack);
+		if (ret)
+			return ret;
+	}
+
 	return 0;
 }
 
+int dpll_nl_device_set_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct dpll_device *dpll = info->user_ptr[0];
+
+	return dpll_set_from_nlattr(dpll, info);
+}
+
 int dpll_nl_device_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
 {
 	struct dpll_dump_ctx *ctx = dpll_dump_context(cb);
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index 5e4f9ab1cf75..6ad6c2968a28 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -30,6 +30,14 @@ struct dpll_device_ops {
 				       void *dpll_priv,
 				       unsigned long *qls,
 				       struct netlink_ext_ack *extack);
+	int (*phase_offset_monitor_set)(const struct dpll_device *dpll,
+					void *dpll_priv,
+					enum dpll_feature_state state,
+					struct netlink_ext_ack *extack);
+	int (*phase_offset_monitor_get)(const struct dpll_device *dpll,
+					void *dpll_priv,
+					enum dpll_feature_state *state,
+					struct netlink_ext_ack *extack);
 };
 
 struct dpll_pin_ops {
-- 
cgit v1.2.3


From 385a766bed48c5bcf620061f24e864dafeca671a Mon Sep 17 00:00:00 2001
From: Igor Belwon <igor.belwon@mentallysanemainliners.org>
Date: Thu, 15 May 2025 16:43:02 +0200
Subject: phy: exynos5-usbdrd: Add support for the Exynos990 usbdrd phy

The Exynos990 usbdrd PHY is a combo PHY which supports USB SS, HS and
DisplayPort outputs. This commit adds support only for UTMI+ (USB HS).

Reviewed-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Signed-off-by: Igor Belwon <igor.belwon@mentallysanemainliners.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250515-usb-resends-may-15-v3-2-ad33a85b6cee@mentallysanemainliners.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/samsung/phy-exynos5-usbdrd.c    | 32 +++++++++++++++++++++++++++++
 include/linux/soc/samsung/exynos-regs-pmu.h |  3 +++
 2 files changed, 35 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/phy/samsung/phy-exynos5-usbdrd.c b/drivers/phy/samsung/phy-exynos5-usbdrd.c
index 917a76d584f0..dd660ebe8045 100644
--- a/drivers/phy/samsung/phy-exynos5-usbdrd.c
+++ b/drivers/phy/samsung/phy-exynos5-usbdrd.c
@@ -2025,6 +2025,35 @@ static const struct exynos5_usbdrd_phy_drvdata exynos850_usbdrd_phy = {
 	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
 };
 
+static const struct exynos5_usbdrd_phy_tuning exynos990_tunes_utmi_postinit[] = {
+	PHY_TUNING_ENTRY_PHY(EXYNOS850_DRD_HSPPARACON,
+			     (HSPPARACON_TXVREF |
+			      HSPPARACON_TXPREEMPAMP | HSPPARACON_SQRX |
+			      HSPPARACON_COMPDIS),
+			     (FIELD_PREP_CONST(HSPPARACON_TXVREF, 7) |
+			      FIELD_PREP_CONST(HSPPARACON_TXPREEMPAMP, 3) |
+			      FIELD_PREP_CONST(HSPPARACON_SQRX, 5) |
+			      FIELD_PREP_CONST(HSPPARACON_COMPDIS, 7))),
+	PHY_TUNING_ENTRY_LAST
+};
+
+static const struct exynos5_usbdrd_phy_tuning *exynos990_tunes[PTS_MAX] = {
+	[PTS_UTMI_POSTINIT] = exynos990_tunes_utmi_postinit,
+};
+
+static const struct exynos5_usbdrd_phy_drvdata exynos990_usbdrd_phy = {
+	.phy_cfg		= phy_cfg_exynos850,
+	.phy_ops		= &exynos850_usbdrd_phy_ops,
+	.phy_tunes		= exynos990_tunes,
+	.pmu_offset_usbdrd0_phy	= EXYNOS990_PHY_CTRL_USB20,
+	.clk_names		= exynos5_clk_names,
+	.n_clks			= ARRAY_SIZE(exynos5_clk_names),
+	.core_clk_names		= exynos5_core_clk_names,
+	.n_core_clks		= ARRAY_SIZE(exynos5_core_clk_names),
+	.regulator_names	= exynos5_regulator_names,
+	.n_regulators		= ARRAY_SIZE(exynos5_regulator_names),
+};
+
 static const struct exynos5_usbdrd_phy_config phy_cfg_gs101[] = {
 	{
 		.id		= EXYNOS5_DRDPHY_UTMI,
@@ -2228,6 +2257,9 @@ static const struct of_device_id exynos5_usbdrd_phy_of_match[] = {
 	}, {
 		.compatible = "samsung,exynos850-usbdrd-phy",
 		.data = &exynos850_usbdrd_phy
+	}, {
+		.compatible = "samsung,exynos990-usbdrd-phy",
+		.data = &exynos990_usbdrd_phy
 	},
 	{ },
 };
diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h
index 1a2c0e0838f9..7754697e5810 100644
--- a/include/linux/soc/samsung/exynos-regs-pmu.h
+++ b/include/linux/soc/samsung/exynos-regs-pmu.h
@@ -662,6 +662,9 @@
 #define EXYNOS5433_PAD_RETENTION_UFS_OPTION			(0x3268)
 #define EXYNOS5433_PAD_RETENTION_FSYSGENIO_OPTION		(0x32A8)
 
+/* For Exynos990 */
+#define EXYNOS990_PHY_CTRL_USB20				(0x72C)
+
 /* For Tensor GS101 */
 /* PMU ALIVE */
 #define GS101_SYSIP_DAT0					(0x810)
-- 
cgit v1.2.3


From 0c17270f9b920e4e1777488f1911bbfdaf2af3be Mon Sep 17 00:00:00 2001
From: Yajun Deng <yajun.deng@linux.dev>
Date: Thu, 12 Jun 2025 14:27:07 +0000
Subject: net: sysfs: Implement is_visible for phys_(port_id, port_name,
 switch_id)

phys_port_id_show, phys_port_name_show and phys_switch_id_show would
return -EOPNOTSUPP if the netdev didn't implement the corresponding
method.

There is no point in creating these files if they are unsupported.

Put these attributes in netdev_phys_group and implement the is_visible
method. make phys_(port_id, port_name, switch_id) invisible if the netdev
dosen't implement the corresponding method.

Signed-off-by: Yajun Deng <yajun.deng@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250612142707.4644-1-yajun.deng@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  2 +-
 net/core/net-sysfs.c      | 59 ++++++++++++++++++++++++++++-------------------
 2 files changed, 36 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index adb14db25798..9cbc4e54b7e4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2388,7 +2388,7 @@ struct net_device {
 	struct dm_hw_stat_delta __rcu *dm_private;
 #endif
 	struct device		dev;
-	const struct attribute_group *sysfs_groups[4];
+	const struct attribute_group *sysfs_groups[5];
 	const struct attribute_group *sysfs_rx_queue_group;
 
 	const struct rtnl_link_ops *rtnl_link_ops;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 1ace0cd01adc..c9b969386399 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -641,12 +641,6 @@ static ssize_t phys_port_id_show(struct device *dev,
 	struct netdev_phys_item_id ppid;
 	ssize_t ret;
 
-	/* The check is also done in dev_get_phys_port_id; this helps returning
-	 * early without hitting the locking section below.
-	 */
-	if (!netdev->netdev_ops->ndo_get_phys_port_id)
-		return -EOPNOTSUPP;
-
 	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
 	if (ret)
 		return ret;
@@ -668,13 +662,6 @@ static ssize_t phys_port_name_show(struct device *dev,
 	char name[IFNAMSIZ];
 	ssize_t ret;
 
-	/* The checks are also done in dev_get_phys_port_name; this helps
-	 * returning early without hitting the locking section below.
-	 */
-	if (!netdev->netdev_ops->ndo_get_phys_port_name &&
-	    !netdev->devlink_port)
-		return -EOPNOTSUPP;
-
 	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
 	if (ret)
 		return ret;
@@ -696,14 +683,6 @@ static ssize_t phys_switch_id_show(struct device *dev,
 	struct netdev_phys_item_id ppid = { };
 	ssize_t ret;
 
-	/* The checks are also done in dev_get_phys_port_name; this helps
-	 * returning early without hitting the locking section below. This works
-	 * because recurse is false when calling dev_get_port_parent_id.
-	 */
-	if (!netdev->netdev_ops->ndo_get_port_parent_id &&
-	    !netdev->devlink_port)
-		return -EOPNOTSUPP;
-
 	ret = sysfs_rtnl_lock(&dev->kobj, &attr->attr, netdev);
 	if (ret)
 		return ret;
@@ -718,6 +697,40 @@ static ssize_t phys_switch_id_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(phys_switch_id);
 
+static struct attribute *netdev_phys_attrs[] __ro_after_init = {
+	&dev_attr_phys_port_id.attr,
+	&dev_attr_phys_port_name.attr,
+	&dev_attr_phys_switch_id.attr,
+	NULL,
+};
+
+static umode_t netdev_phys_is_visible(struct kobject *kobj,
+				      struct attribute *attr, int index)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct net_device *netdev = to_net_dev(dev);
+
+	if (attr == &dev_attr_phys_port_id.attr) {
+		if (!netdev->netdev_ops->ndo_get_phys_port_id)
+			return 0;
+	} else if (attr == &dev_attr_phys_port_name.attr) {
+		if (!netdev->netdev_ops->ndo_get_phys_port_name &&
+		    !netdev->devlink_port)
+			return 0;
+	} else if (attr == &dev_attr_phys_switch_id.attr) {
+		if (!netdev->netdev_ops->ndo_get_port_parent_id &&
+		    !netdev->devlink_port)
+			return 0;
+	}
+
+	return attr->mode;
+}
+
+static const struct attribute_group netdev_phys_group = {
+	.attrs = netdev_phys_attrs,
+	.is_visible = netdev_phys_is_visible,
+};
+
 static ssize_t threaded_show(struct device *dev,
 			     struct device_attribute *attr, char *buf)
 {
@@ -783,9 +796,6 @@ static struct attribute *net_class_attrs[] __ro_after_init = {
 	&dev_attr_tx_queue_len.attr,
 	&dev_attr_gro_flush_timeout.attr,
 	&dev_attr_napi_defer_hard_irqs.attr,
-	&dev_attr_phys_port_id.attr,
-	&dev_attr_phys_port_name.attr,
-	&dev_attr_phys_switch_id.attr,
 	&dev_attr_proto_down.attr,
 	&dev_attr_carrier_up_count.attr,
 	&dev_attr_carrier_down_count.attr,
@@ -2328,6 +2338,7 @@ int netdev_register_kobject(struct net_device *ndev)
 		groups++;
 
 	*groups++ = &netstat_group;
+	*groups++ = &netdev_phys_group;
 
 	if (wireless_group_needed(ndev))
 		*groups++ = &wireless_group;
-- 
cgit v1.2.3


From 72bf1441231ab421a380771e37a5c595493db178 Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Sun, 15 Jun 2025 22:32:51 +0900
Subject: firewire: core: allocate workqueue for AR/AT request/response
 contexts

Some tasklets (softIRQs) are still used as bottom-halves to handle
events for 1394 OHCI AR/AT contexts. However, using softIRQs for IRQ
bottom halves is generally discouraged today.

This commit adds a per-fw_card workqueue to accommodate the behaviour
specified by the 1394 OHCI specification.

According to the 1394 OHCI specification, system memory pages are
reserved for each asynchronous DMA context. This allows concurrent
operation across contexts. In the 1394 OHCI PCI driver implementation,
the hardware generates IRQs either upon receiving asynchronous packets
from other nodes (incoming) or after completing transmission to them
(outgoing). These independent events can occur in the same transmission
cycle, therefore the max_active parameter for the workqueue is set to the
total number of AR/AT contexts (=4). The WQ_UNBOUND flag is used to
allow the work to be scheduled on any available core, since there is
little CPU cache affinity benefit for the data.

Each DMA context uses a circular descriptor list in system memory,
allowing deferred data processing in software as long as buffer overrun
are avoided. Since the overall operation is sleepable except for small
atomic regions, WQ_BH is not used. As the descriptors contain
timestamps, WQ_HIGHPRI is specified to support semi-real-time
processing.

The asynchronous context is also used by the SCSI over IEEE 1394
protocol implementation (sbp2), which can be part of memory reclaim paths.
Therefore, WQ_MEM_RECLAIM is required.

To allow uses to adjust CPU affinity according to workload, WQ_SYSFS is
specified so that workqueue attributes are exposed to user space.

Link: https://lore.kernel.org/r/20250615133253.433057-2-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/core-card.c | 48 +++++++++++++++++++++++++++++++-------------
 include/linux/firewire.h     |  1 +
 2 files changed, 35 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firewire/core-card.c b/drivers/firewire/core-card.c
index 2b6ad47b6d57..b3e48ca516fe 100644
--- a/drivers/firewire/core-card.c
+++ b/drivers/firewire/core-card.c
@@ -574,7 +574,6 @@ EXPORT_SYMBOL(fw_card_initialize);
 int fw_card_add(struct fw_card *card, u32 max_receive, u32 link_speed, u64 guid,
 		unsigned int supported_isoc_contexts)
 {
-	struct workqueue_struct *isoc_wq;
 	int ret;
 
 	// This workqueue should be:
@@ -589,29 +588,48 @@ int fw_card_add(struct fw_card *card, u32 max_receive, u32 link_speed, u64 guid,
 	//  * == WQ_SYSFS		Parameters are available via sysfs.
 	//  * max_active == n_it + n_ir	A hardIRQ could notify events for multiple isochronous
 	//				contexts if they are scheduled to the same cycle.
-	isoc_wq = alloc_workqueue("firewire-isoc-card%u",
-				  WQ_UNBOUND | WQ_FREEZABLE | WQ_HIGHPRI | WQ_SYSFS,
-				  supported_isoc_contexts, card->index);
-	if (!isoc_wq)
+	card->isoc_wq = alloc_workqueue("firewire-isoc-card%u",
+					WQ_UNBOUND | WQ_FREEZABLE | WQ_HIGHPRI | WQ_SYSFS,
+					supported_isoc_contexts, card->index);
+	if (!card->isoc_wq)
 		return -ENOMEM;
 
+	// This workqueue should be:
+	//  * != WQ_BH			Sleepable.
+	//  * == WQ_UNBOUND		Any core can process data for asynchronous context.
+	//  * == WQ_MEM_RECLAIM		Used for any backend of block device.
+	//  * == WQ_FREEZABLE		The target device would not be available when being freezed.
+	//  * == WQ_HIGHPRI		High priority to process semi-realtime timestamped data.
+	//  * == WQ_SYSFS		Parameters are available via sysfs.
+	//  * max_active == 4		A hardIRQ could notify events for a pair of requests and
+	//				response AR/AT contexts.
+	card->async_wq = alloc_workqueue("firewire-async-card%u",
+					 WQ_UNBOUND | WQ_MEM_RECLAIM | WQ_FREEZABLE | WQ_HIGHPRI | WQ_SYSFS,
+					 4, card->index);
+	if (!card->async_wq) {
+		ret = -ENOMEM;
+		goto err_isoc;
+	}
+
 	card->max_receive = max_receive;
 	card->link_speed = link_speed;
 	card->guid = guid;
 
-	guard(mutex)(&card_mutex);
+	scoped_guard(mutex, &card_mutex) {
+		generate_config_rom(card, tmp_config_rom);
+		ret = card->driver->enable(card, tmp_config_rom, config_rom_length);
+		if (ret < 0)
+			goto err_async;
 
-	generate_config_rom(card, tmp_config_rom);
-	ret = card->driver->enable(card, tmp_config_rom, config_rom_length);
-	if (ret < 0) {
-		destroy_workqueue(isoc_wq);
-		return ret;
+		list_add_tail(&card->link, &card_list);
 	}
 
-	card->isoc_wq = isoc_wq;
-	list_add_tail(&card->link, &card_list);
-
 	return 0;
+err_async:
+	destroy_workqueue(card->async_wq);
+err_isoc:
+	destroy_workqueue(card->isoc_wq);
+	return ret;
 }
 EXPORT_SYMBOL(fw_card_add);
 
@@ -744,6 +762,7 @@ void fw_core_remove_card(struct fw_card *card)
 	dummy_driver.stop_iso		= card->driver->stop_iso;
 	card->driver = &dummy_driver;
 	drain_workqueue(card->isoc_wq);
+	drain_workqueue(card->async_wq);
 
 	scoped_guard(spinlock_irqsave, &card->lock)
 		fw_destroy_nodes(card);
@@ -753,6 +772,7 @@ void fw_core_remove_card(struct fw_card *card)
 	wait_for_completion(&card->done);
 
 	destroy_workqueue(card->isoc_wq);
+	destroy_workqueue(card->async_wq);
 
 	WARN_ON(!list_empty(&card->transaction_list));
 }
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index b632eec3ab52..c55b8e30e700 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -136,6 +136,7 @@ struct fw_card {
 	__be32 maint_utility_register;
 
 	struct workqueue_struct *isoc_wq;
+	struct workqueue_struct *async_wq;
 };
 
 static inline struct fw_card *fw_card_get(struct fw_card *card)
-- 
cgit v1.2.3


From aef6bcc0f278eba408751f8b3e0beae992e9faec Mon Sep 17 00:00:00 2001
From: Takashi Sakamoto <o-takashi@sakamocchi.jp>
Date: Sun, 15 Jun 2025 22:32:53 +0900
Subject: firewire: ohci: use workqueue to handle events of AT request/response
 contexts

This commit adds a work item to handle events of 1394 OHCI AT
request/response contexts, and queues the item to the specific
workqueue. The call of struct fw_packet.callbaqck() is done in the
workqueue when receiving acknowledgement to the asynchronous packet
transferred to remote node.

Link: https://lore.kernel.org/r/20250615133253.433057-4-o-takashi@sakamocchi.jp
Signed-off-by: Takashi Sakamoto <o-takashi@sakamocchi.jp>
---
 drivers/firewire/net.c   |  4 ++--
 drivers/firewire/ohci.c  | 40 ++++++++++++++++++++++++----------------
 include/linux/firewire.h | 11 +++++++++--
 3 files changed, 35 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firewire/net.c b/drivers/firewire/net.c
index 1bf0e15c1540..6d6446713539 100644
--- a/drivers/firewire/net.c
+++ b/drivers/firewire/net.c
@@ -1007,7 +1007,7 @@ static int fwnet_send_packet(struct fwnet_packet_task *ptask)
 
 		spin_lock_irqsave(&dev->lock, flags);
 
-		/* If the AT tasklet already ran, we may be last user. */
+		/* If the AT work item already ran, we may be last user. */
 		free = (ptask->outstanding_pkts == 0 && !ptask->enqueued);
 		if (!free)
 			ptask->enqueued = true;
@@ -1026,7 +1026,7 @@ static int fwnet_send_packet(struct fwnet_packet_task *ptask)
 
 	spin_lock_irqsave(&dev->lock, flags);
 
-	/* If the AT tasklet already ran, we may be last user. */
+	/* If the AT work item already ran, we may be last user. */
 	free = (ptask->outstanding_pkts == 0 && !ptask->enqueued);
 	if (!free)
 		ptask->enqueued = true;
diff --git a/drivers/firewire/ohci.c b/drivers/firewire/ohci.c
index 68317b5a64a7..709a714fd5c8 100644
--- a/drivers/firewire/ohci.c
+++ b/drivers/firewire/ohci.c
@@ -158,7 +158,7 @@ struct context {
 
 	descriptor_callback_t callback;
 
-	struct tasklet_struct tasklet;
+	struct work_struct work;
 };
 
 struct iso_context {
@@ -1176,9 +1176,9 @@ static void context_retire_descriptors(struct context *ctx)
 	}
 }
 
-static void context_tasklet(unsigned long data)
+static void ohci_at_context_work(struct work_struct *work)
 {
-	struct context *ctx = (struct context *) data;
+	struct context *ctx = from_work(ctx, work, work);
 
 	context_retire_descriptors(ctx);
 }
@@ -1243,7 +1243,6 @@ static int context_init(struct context *ctx, struct fw_ohci *ohci,
 	ctx->buffer_tail = list_entry(ctx->buffer_list.next,
 			struct descriptor_buffer, list);
 
-	tasklet_init(&ctx->tasklet, context_tasklet, (unsigned long)ctx);
 	ctx->callback = callback;
 
 	/*
@@ -1524,13 +1523,17 @@ static int at_context_queue_packet(struct context *ctx,
 
 static void at_context_flush(struct context *ctx)
 {
-	tasklet_disable(&ctx->tasklet);
+	// Avoid dead lock due to programming mistake.
+	if (WARN_ON_ONCE(current_work() == &ctx->work))
+		return;
 
-	ctx->flushing = true;
-	context_tasklet((unsigned long)ctx);
-	ctx->flushing = false;
+	disable_work_sync(&ctx->work);
 
-	tasklet_enable(&ctx->tasklet);
+	WRITE_ONCE(ctx->flushing, true);
+	ohci_at_context_work(&ctx->work);
+	WRITE_ONCE(ctx->flushing, false);
+
+	enable_work(&ctx->work);
 }
 
 static int handle_at_packet(struct context *context,
@@ -1542,7 +1545,7 @@ static int handle_at_packet(struct context *context,
 	struct fw_ohci *ohci = context->ohci;
 	int evt;
 
-	if (last->transfer_status == 0 && !context->flushing)
+	if (last->transfer_status == 0 && !READ_ONCE(context->flushing))
 		/* This descriptor isn't done yet, stop iteration. */
 		return 0;
 
@@ -1576,7 +1579,7 @@ static int handle_at_packet(struct context *context,
 		break;
 
 	case OHCI1394_evt_missing_ack:
-		if (context->flushing)
+		if (READ_ONCE(context->flushing))
 			packet->ack = RCODE_GENERATION;
 		else {
 			/*
@@ -1598,7 +1601,7 @@ static int handle_at_packet(struct context *context,
 		break;
 
 	case OHCI1394_evt_no_status:
-		if (context->flushing) {
+		if (READ_ONCE(context->flushing)) {
 			packet->ack = RCODE_GENERATION;
 			break;
 		}
@@ -2239,10 +2242,10 @@ static irqreturn_t irq_handler(int irq, void *data)
 		queue_work(ohci->card.async_wq, &ohci->ar_response_ctx.work);
 
 	if (event & OHCI1394_reqTxComplete)
-		tasklet_schedule(&ohci->at_request_ctx.tasklet);
+		queue_work(ohci->card.async_wq, &ohci->at_request_ctx.work);
 
 	if (event & OHCI1394_respTxComplete)
-		tasklet_schedule(&ohci->at_response_ctx.tasklet);
+		queue_work(ohci->card.async_wq, &ohci->at_response_ctx.work);
 
 	if (event & OHCI1394_isochRx) {
 		iso_event = reg_read(ohci, OHCI1394_IsoRecvIntEventClear);
@@ -2684,7 +2687,10 @@ static int ohci_cancel_packet(struct fw_card *card, struct fw_packet *packet)
 	struct driver_data *driver_data = packet->driver_data;
 	int ret = -ENOENT;
 
-	tasklet_disable_in_atomic(&ctx->tasklet);
+	// Avoid dead lock due to programming mistake.
+	if (WARN_ON_ONCE(current_work() == &ctx->work))
+		return 0;
+	disable_work_sync(&ctx->work);
 
 	if (packet->ack != 0)
 		goto out;
@@ -2703,7 +2709,7 @@ static int ohci_cancel_packet(struct fw_card *card, struct fw_packet *packet)
 	packet->callback(packet, &ohci->card, packet->ack);
 	ret = 0;
  out:
-	tasklet_enable(&ctx->tasklet);
+	enable_work(&ctx->work);
 
 	return ret;
 }
@@ -3765,11 +3771,13 @@ static int pci_probe(struct pci_dev *dev,
 			   OHCI1394_AsReqTrContextControlSet, handle_at_packet);
 	if (err < 0)
 		return err;
+	INIT_WORK(&ohci->at_request_ctx.work, ohci_at_context_work);
 
 	err = context_init(&ohci->at_response_ctx, ohci,
 			   OHCI1394_AsRspTrContextControlSet, handle_at_packet);
 	if (err < 0)
 		return err;
+	INIT_WORK(&ohci->at_response_ctx.work, ohci_at_context_work);
 
 	reg_write(ohci, OHCI1394_IsoRecvIntMaskSet, ~0);
 	ohci->ir_context_channels = ~0ULL;
diff --git a/include/linux/firewire.h b/include/linux/firewire.h
index c55b8e30e700..cceb70415ed2 100644
--- a/include/linux/firewire.h
+++ b/include/linux/firewire.h
@@ -308,8 +308,7 @@ struct fw_packet {
 	 * For successful transmission, the status code is the ack received
 	 * from the destination.  Otherwise it is one of the juju-specific
 	 * rcodes:  RCODE_SEND_ERROR, _CANCELLED, _BUSY, _GENERATION, _NO_ACK.
-	 * The callback can be called from tasklet context and thus
-	 * must never block.
+	 * The callback can be called from workqueue and thus must never block.
 	 */
 	fw_packet_callback_t callback;
 	int ack;
@@ -382,6 +381,10 @@ void __fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode
  *
  * A variation of __fw_send_request() to generate callback for response subaction without time
  * stamp.
+ *
+ * The callback is invoked in the workqueue context in most cases. However, if an error is detected
+ * before queueing or the destination address refers to the local node, it is invoked in the
+ * current context instead.
  */
 static inline void fw_send_request(struct fw_card *card, struct fw_transaction *t, int tcode,
 				   int destination_id, int generation, int speed,
@@ -411,6 +414,10 @@ static inline void fw_send_request(struct fw_card *card, struct fw_transaction *
  * @callback_data:	data to be passed to the transaction completion callback
  *
  * A variation of __fw_send_request() to generate callback for response subaction with time stamp.
+ *
+ * The callback is invoked in the workqueue context in most cases. However, if an error is detected
+ * before queueing or the destination address refers to the local node, it is invoked in the current
+ * context instead.
  */
 static inline void fw_send_request_with_tstamp(struct fw_card *card, struct fw_transaction *t,
 	int tcode, int destination_id, int generation, int speed, unsigned long long offset,
-- 
cgit v1.2.3


From 543f5e314282c4c2e5114f88ddecc9aeaf0985e2 Mon Sep 17 00:00:00 2001
From: Kaustabh Chakraborty <kauschluss@disroot.org>
Date: Thu, 12 Jun 2025 20:39:30 +0530
Subject: phy: exynos-mipi-video: introduce support for exynos7870

Add support for Exynos7870 in the existing MIPI CSIS/DSIM driver. The
SoC has one DSIM phy and three CSIS phys.

Signed-off-by: Kaustabh Chakraborty <kauschluss@disroot.org>
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Link: https://lore.kernel.org/r/20250612-exynos7870-mipi-phy-v1-2-3fff0b62d9d3@disroot.org
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/samsung/phy-exynos-mipi-video.c | 52 +++++++++++++++++++++++++++++
 include/linux/soc/samsung/exynos-regs-pmu.h |  5 +++
 2 files changed, 57 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/phy/samsung/phy-exynos-mipi-video.c b/drivers/phy/samsung/phy-exynos-mipi-video.c
index f6756a609a9a..b184923b9b40 100644
--- a/drivers/phy/samsung/phy-exynos-mipi-video.c
+++ b/drivers/phy/samsung/phy-exynos-mipi-video.c
@@ -213,6 +213,55 @@ static const struct mipi_phy_device_desc exynos5433_mipi_phy = {
 	},
 };
 
+static const struct mipi_phy_device_desc exynos7870_mipi_phy = {
+	.num_regmaps = 3,
+	.regmap_names = {
+		"samsung,pmu-syscon",
+		"samsung,disp-sysreg",
+		"samsung,cam-sysreg"
+	},
+	.num_phys = 4,
+	.phys = {
+		{
+			/* EXYNOS_MIPI_PHY_ID_CSIS0 */
+			.coupled_phy_id = EXYNOS_MIPI_PHY_ID_DSIM0,
+			.enable_val = EXYNOS4_PHY_ENABLE,
+			.enable_reg = EXYNOS7870_MIPI_PHY_CONTROL0,
+			.enable_map = EXYNOS_MIPI_REGMAP_PMU,
+			.resetn_val = BIT(0),
+			.resetn_reg = 0,
+			.resetn_map = EXYNOS_MIPI_REGMAP_CAM0,
+		}, {
+			/* EXYNOS_MIPI_PHY_ID_DSIM0 */
+			.coupled_phy_id = EXYNOS_MIPI_PHY_ID_CSIS0,
+			.enable_val = EXYNOS4_PHY_ENABLE,
+			.enable_reg = EXYNOS7870_MIPI_PHY_CONTROL0,
+			.enable_map = EXYNOS_MIPI_REGMAP_PMU,
+			.resetn_val = BIT(0),
+			.resetn_reg = 0,
+			.resetn_map = EXYNOS_MIPI_REGMAP_DISP,
+		}, {
+			/* EXYNOS_MIPI_PHY_ID_CSIS1 */
+			.coupled_phy_id = EXYNOS_MIPI_PHY_ID_NONE,
+			.enable_val = EXYNOS4_PHY_ENABLE,
+			.enable_reg = EXYNOS7870_MIPI_PHY_CONTROL1,
+			.enable_map = EXYNOS_MIPI_REGMAP_PMU,
+			.resetn_val = BIT(1),
+			.resetn_reg = 0,
+			.resetn_map = EXYNOS_MIPI_REGMAP_CAM0,
+		}, {
+			/* EXYNOS_MIPI_PHY_ID_CSIS2 */
+			.coupled_phy_id = EXYNOS_MIPI_PHY_ID_NONE,
+			.enable_val = EXYNOS4_PHY_ENABLE,
+			.enable_reg = EXYNOS7870_MIPI_PHY_CONTROL2,
+			.enable_map = EXYNOS_MIPI_REGMAP_PMU,
+			.resetn_val = BIT(2),
+			.resetn_reg = 0,
+			.resetn_map = EXYNOS_MIPI_REGMAP_CAM0,
+		},
+	},
+};
+
 struct exynos_mipi_video_phy {
 	struct regmap *regmaps[EXYNOS_MIPI_REGMAPS_NUM];
 	int num_phys;
@@ -351,6 +400,9 @@ static const struct of_device_id exynos_mipi_video_phy_of_match[] = {
 	}, {
 		.compatible = "samsung,exynos5433-mipi-video-phy",
 		.data = &exynos5433_mipi_phy,
+	}, {
+		.compatible = "samsung,exynos7870-mipi-video-phy",
+		.data = &exynos7870_mipi_phy,
 	},
 	{ /* sentinel */ },
 };
diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h
index 7754697e5810..fa28a8784d65 100644
--- a/include/linux/soc/samsung/exynos-regs-pmu.h
+++ b/include/linux/soc/samsung/exynos-regs-pmu.h
@@ -665,6 +665,11 @@
 /* For Exynos990 */
 #define EXYNOS990_PHY_CTRL_USB20				(0x72C)
 
+/* For Exynos7870 */
+#define EXYNOS7870_MIPI_PHY_CONTROL0				(0x070c)
+#define EXYNOS7870_MIPI_PHY_CONTROL1				(0x0714)
+#define EXYNOS7870_MIPI_PHY_CONTROL2				(0x0734)
+
 /* For Tensor GS101 */
 /* PMU ALIVE */
 #define GS101_SYSIP_DAT0					(0x810)
-- 
cgit v1.2.3


From cf0233491b3a15933234a26efd9ecbc1c0764674 Mon Sep 17 00:00:00 2001
From: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Date: Thu, 5 Jun 2025 14:25:49 +0300
Subject: phy: use per-PHY lockdep keys

If the PHY driver uses another PHY internally (e.g. in case of eUSB2,
repeaters are represented as PHYs), then it would trigger the following
lockdep splat because all PHYs use a single static lockdep key and thus
lockdep can not identify whether there is a dependency or not and
reports a false positive.

Make PHY subsystem use dynamic lockdep keys, assigning each driver a
separate key. This way lockdep can correctly identify dependency graph
between mutexes.

 ============================================
 WARNING: possible recursive locking detected
 6.15.0-rc7-next-20250522-12896-g3932f283970c #3455 Not tainted
 --------------------------------------------
 kworker/u51:0/78 is trying to acquire lock:
 ffff0008116554f0 (&phy->mutex){+.+.}-{4:4}, at: phy_init+0x4c/0x12c

 but task is already holding lock:
 ffff000813c10cf0 (&phy->mutex){+.+.}-{4:4}, at: phy_init+0x4c/0x12c

 other info that might help us debug this:
  Possible unsafe locking scenario:

        CPU0
        ----
   lock(&phy->mutex);
   lock(&phy->mutex);

  *** DEADLOCK ***

  May be due to missing lock nesting notation

 4 locks held by kworker/u51:0/78:
  #0: ffff000800010948 ((wq_completion)events_unbound){+.+.}-{0:0}, at: process_one_work+0x18c/0x5ec
  #1: ffff80008036bdb0 (deferred_probe_work){+.+.}-{0:0}, at: process_one_work+0x1b4/0x5ec
  #2: ffff0008094ac8f8 (&dev->mutex){....}-{4:4}, at: __device_attach+0x38/0x188
  #3: ffff000813c10cf0 (&phy->mutex){+.+.}-{4:4}, at: phy_init+0x4c/0x12c

 stack backtrace:
 CPU: 0 UID: 0 PID: 78 Comm: kworker/u51:0 Not tainted 6.15.0-rc7-next-20250522-12896-g3932f283970c #3455 PREEMPT
 Hardware name: Qualcomm CRD, BIOS 6.0.240904.BOOT.MXF.2.4-00528.1-HAMOA-1 09/ 4/2024
 Workqueue: events_unbound deferred_probe_work_func
 Call trace:
  show_stack+0x18/0x24 (C)
  dump_stack_lvl+0x90/0xd0
  dump_stack+0x18/0x24
  print_deadlock_bug+0x258/0x348
  __lock_acquire+0x10fc/0x1f84
  lock_acquire+0x1c8/0x338
  __mutex_lock+0xb8/0x59c
  mutex_lock_nested+0x24/0x30
  phy_init+0x4c/0x12c
  snps_eusb2_hsphy_init+0x54/0x1a0
  phy_init+0xe0/0x12c
  dwc3_core_init+0x450/0x10b4
  dwc3_core_probe+0xce4/0x15fc
  dwc3_probe+0x64/0xb0
  platform_probe+0x68/0xc4
  really_probe+0xbc/0x298
  __driver_probe_device+0x78/0x12c
  driver_probe_device+0x3c/0x160
  __device_attach_driver+0xb8/0x138
  bus_for_each_drv+0x84/0xe0
  __device_attach+0x9c/0x188
  device_initial_probe+0x14/0x20
  bus_probe_device+0xac/0xb0
  deferred_probe_work_func+0x8c/0xc8
  process_one_work+0x208/0x5ec
  worker_thread+0x1c0/0x368
  kthread+0x14c/0x20c
  ret_from_fork+0x10/0x20

Fixes: 3584f6392f09 ("phy: qcom: phy-qcom-snps-eusb2: Add support for eUSB2 repeater")
Fixes: e2463559ff1d ("phy: amlogic: Add Amlogic AXG PCIE PHY Driver")
Reviewed-by: Neil Armstrong <neil.armstrong@linaro.org>
Reviewed-by: Abel Vesa <abel.vesa@linaro.org>
Reported-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://lore.kernel.org/lkml/ZnpoAVGJMG4Zu-Jw@hovoldconsulting.com/
Reviewed-by: Johan Hovold <johan+linaro@kernel.org>
Tested-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250605-phy-subinit-v3-1-1e1e849e10cd@oss.qualcomm.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/phy/phy-core.c  | 5 ++++-
 include/linux/phy/phy.h | 2 ++
 2 files changed, 6 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/phy/phy-core.c b/drivers/phy/phy-core.c
index 8e2daea81666..04a5a34e7a95 100644
--- a/drivers/phy/phy-core.c
+++ b/drivers/phy/phy-core.c
@@ -994,7 +994,8 @@ struct phy *phy_create(struct device *dev, struct device_node *node,
 	}
 
 	device_initialize(&phy->dev);
-	mutex_init(&phy->mutex);
+	lockdep_register_key(&phy->lockdep_key);
+	mutex_init_with_key(&phy->mutex, &phy->lockdep_key);
 
 	phy->dev.class = &phy_class;
 	phy->dev.parent = dev;
@@ -1259,6 +1260,8 @@ static void phy_release(struct device *dev)
 	dev_vdbg(dev, "releasing '%s'\n", dev_name(dev));
 	debugfs_remove_recursive(phy->debugfs);
 	regulator_put(phy->pwr);
+	mutex_destroy(&phy->mutex);
+	lockdep_unregister_key(&phy->lockdep_key);
 	ida_free(&phy_ida, phy->id);
 	kfree(phy);
 }
diff --git a/include/linux/phy/phy.h b/include/linux/phy/phy.h
index 437769e061b7..13add0c2c407 100644
--- a/include/linux/phy/phy.h
+++ b/include/linux/phy/phy.h
@@ -154,6 +154,7 @@ struct phy_attrs {
  * @id: id of the phy device
  * @ops: function pointers for performing phy operations
  * @mutex: mutex to protect phy_ops
+ * @lockdep_key: lockdep information for this mutex
  * @init_count: used to protect when the PHY is used by multiple consumers
  * @power_count: used to protect when the PHY is used by multiple consumers
  * @attrs: used to specify PHY specific attributes
@@ -165,6 +166,7 @@ struct phy {
 	int			id;
 	const struct phy_ops	*ops;
 	struct mutex		mutex;
+	struct lock_class_key	lockdep_key;
 	int			init_count;
 	int			power_count;
 	struct phy_attrs	attrs;
-- 
cgit v1.2.3


From e7af416aebb36e6681b9c6950d0f6352aee7c084 Mon Sep 17 00:00:00 2001
From: Richard Fitzgerald <rf@opensource.cirrus.com>
Date: Mon, 16 Jun 2025 11:30:52 +0100
Subject: firmware: cs_dsp: Remove unused struct list_head from
 cs_dsp_coeff_ctl

Remove two unused pointers from struct cs_dsp_coeff_ctl by taking the
struct list_head out of struct cs_dsp_alg_region. On a x86_64 build
this saves 16 bytes per control.

Each cs_dsp_coeff_ctl instance needs to keep information about the
algorithm region it refers to. This is done by embedding an instance
of struct cs_dsp_alg_region. But cs_dsp_alg_region was also used to
store entries in a list of algorithm regions, and so had a struct
list_head object for that purpose. This list_head object is not used
with the embedded object in struct cs_dsp_alg_region so was just
wasted bytes.

A new struct cs_dsp_alg_region_list_item has been defined for creating
the list of algorithm regions. It contains a struct cs_dsp_alg_region
and a struct list_head.

Signed-off-by: Richard Fitzgerald <rf@opensource.cirrus.com>
Link: https://patch.msgid.link/20250616103052.66537-1-rf@opensource.cirrus.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/firmware/cirrus/cs_dsp.c       | 45 +++++++++++++++++++---------------
 include/linux/firmware/cirrus/cs_dsp.h |  2 --
 2 files changed, 25 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c
index 560724ce21aa..f51047d8ea64 100644
--- a/drivers/firmware/cirrus/cs_dsp.c
+++ b/drivers/firmware/cirrus/cs_dsp.c
@@ -311,6 +311,11 @@ static const struct cs_dsp_ops cs_dsp_adsp2_ops[];
 static const struct cs_dsp_ops cs_dsp_halo_ops;
 static const struct cs_dsp_ops cs_dsp_halo_ao_ops;
 
+struct cs_dsp_alg_region_list_item {
+	struct list_head list;
+	struct cs_dsp_alg_region alg_region;
+};
+
 struct cs_dsp_buf {
 	struct list_head list;
 	void *buf;
@@ -1752,13 +1757,13 @@ static void *cs_dsp_read_algs(struct cs_dsp *dsp, size_t n_algs,
 struct cs_dsp_alg_region *cs_dsp_find_alg_region(struct cs_dsp *dsp,
 						 int type, unsigned int id)
 {
-	struct cs_dsp_alg_region *alg_region;
+	struct cs_dsp_alg_region_list_item *item;
 
 	lockdep_assert_held(&dsp->pwr_lock);
 
-	list_for_each_entry(alg_region, &dsp->alg_regions, list) {
-		if (id == alg_region->alg && type == alg_region->type)
-			return alg_region;
+	list_for_each_entry(item, &dsp->alg_regions, list) {
+		if (id == item->alg_region.alg && type == item->alg_region.type)
+			return &item->alg_region;
 	}
 
 	return NULL;
@@ -1769,35 +1774,35 @@ static struct cs_dsp_alg_region *cs_dsp_create_region(struct cs_dsp *dsp,
 						      int type, __be32 id,
 						      __be32 ver, __be32 base)
 {
-	struct cs_dsp_alg_region *alg_region;
+	struct cs_dsp_alg_region_list_item *item;
 
-	alg_region = kzalloc(sizeof(*alg_region), GFP_KERNEL);
-	if (!alg_region)
+	item = kzalloc(sizeof(*item), GFP_KERNEL);
+	if (!item)
 		return ERR_PTR(-ENOMEM);
 
-	alg_region->type = type;
-	alg_region->alg = be32_to_cpu(id);
-	alg_region->ver = be32_to_cpu(ver);
-	alg_region->base = be32_to_cpu(base);
+	item->alg_region.type = type;
+	item->alg_region.alg = be32_to_cpu(id);
+	item->alg_region.ver = be32_to_cpu(ver);
+	item->alg_region.base = be32_to_cpu(base);
 
-	list_add_tail(&alg_region->list, &dsp->alg_regions);
+	list_add_tail(&item->list, &dsp->alg_regions);
 
 	if (dsp->wmfw_ver > 0)
-		cs_dsp_ctl_fixup_base(dsp, alg_region);
+		cs_dsp_ctl_fixup_base(dsp, &item->alg_region);
 
-	return alg_region;
+	return &item->alg_region;
 }
 
 static void cs_dsp_free_alg_regions(struct cs_dsp *dsp)
 {
-	struct cs_dsp_alg_region *alg_region;
+	struct cs_dsp_alg_region_list_item *item;
 
 	while (!list_empty(&dsp->alg_regions)) {
-		alg_region = list_first_entry(&dsp->alg_regions,
-					      struct cs_dsp_alg_region,
-					      list);
-		list_del(&alg_region->list);
-		kfree(alg_region);
+		item = list_first_entry(&dsp->alg_regions,
+					struct cs_dsp_alg_region_list_item,
+					list);
+		list_del(&item->list);
+		kfree(item);
 	}
 }
 
diff --git a/include/linux/firmware/cirrus/cs_dsp.h b/include/linux/firmware/cirrus/cs_dsp.h
index 7cae703b3137..a66eb7624730 100644
--- a/include/linux/firmware/cirrus/cs_dsp.h
+++ b/include/linux/firmware/cirrus/cs_dsp.h
@@ -64,14 +64,12 @@ struct cs_dsp_region {
 
 /**
  * struct cs_dsp_alg_region - Describes a logical algorithm region in DSP address space
- * @list:	List node for internal use
  * @alg:	Algorithm id
  * @ver:	Expected algorithm version
  * @type:	Memory region type
  * @base:	Address of region
  */
 struct cs_dsp_alg_region {
-	struct list_head list;
 	unsigned int alg;
 	unsigned int ver;
 	int type;
-- 
cgit v1.2.3


From bc9241367aac08de44633fd957b2452a6da8e6d4 Mon Sep 17 00:00:00 2001
From: NeilBrown <neil@brown.name>
Date: Fri, 13 Jun 2025 09:28:10 +1000
Subject: VFS: change old_dir and new_dir in struct renamedata to dentrys

all users of 'struct renamedata' have the dentry for the old and new
directories, and often have no use for the inode except to store it in
the renamedata.

This patch changes struct renamedata to hold the dentry, rather than
the inode, for the old and new directories, and changes callers to
match.  The names are also changed from a _dir suffix to _parent.  This
is consistent with other usage in namei.c and elsewhere.

This results in the removal of several local variables and several
dereferences of ->d_inode at the cost of adding ->d_inode dereferences
to vfs_rename().

Acked-by: Miklos Szeredi <miklos@szeredi.hu>
Reviewed-by: Chuck Lever <chuck.lever@oracle.com>
Reviewed-by: Namjae Jeon <linkinjeon@kernel.org>
Signed-off-by: NeilBrown <neil@brown.name>
Link: https://lore.kernel.org/174977089072.608730.4244531834577097454@noble.neil.brown.name
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/cachefiles/namei.c    |  4 ++--
 fs/ecryptfs/inode.c      |  4 ++--
 fs/namei.c               |  7 ++++---
 fs/nfsd/vfs.c            |  7 ++-----
 fs/overlayfs/copy_up.c   |  6 +++---
 fs/overlayfs/dir.c       | 16 ++++++++--------
 fs/overlayfs/overlayfs.h | 16 ++++++++--------
 fs/overlayfs/readdir.c   |  2 +-
 fs/overlayfs/super.c     |  2 +-
 fs/overlayfs/util.c      |  2 +-
 fs/smb/server/vfs.c      |  4 ++--
 include/linux/fs.h       |  8 ++++----
 12 files changed, 38 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index aecfc5c37b49..91dfd0231877 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -388,10 +388,10 @@ try_again:
 	} else {
 		struct renamedata rd = {
 			.old_mnt_idmap	= &nop_mnt_idmap,
-			.old_dir	= d_inode(dir),
+			.old_parent	= dir,
 			.old_dentry	= rep,
 			.new_mnt_idmap	= &nop_mnt_idmap,
-			.new_dir	= d_inode(cache->graveyard),
+			.new_parent	= cache->graveyard,
 			.new_dentry	= grave,
 		};
 		trace_cachefiles_rename(object, d_inode(rep)->i_ino, why);
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 493d7f194956..bd317d943d62 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -635,10 +635,10 @@ ecryptfs_rename(struct mnt_idmap *idmap, struct inode *old_dir,
 	}
 
 	rd.old_mnt_idmap	= &nop_mnt_idmap;
-	rd.old_dir		= d_inode(lower_old_dir_dentry);
+	rd.old_parent		= lower_old_dir_dentry;
 	rd.old_dentry		= lower_old_dentry;
 	rd.new_mnt_idmap	= &nop_mnt_idmap;
-	rd.new_dir		= d_inode(lower_new_dir_dentry);
+	rd.new_parent		= lower_new_dir_dentry;
 	rd.new_dentry		= lower_new_dentry;
 	rc = vfs_rename(&rd);
 	if (rc)
diff --git a/fs/namei.c b/fs/namei.c
index 4bb889fc980b..981da44e1291 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -5007,7 +5007,8 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
 int vfs_rename(struct renamedata *rd)
 {
 	int error;
-	struct inode *old_dir = rd->old_dir, *new_dir = rd->new_dir;
+	struct inode *old_dir = d_inode(rd->old_parent);
+	struct inode *new_dir = d_inode(rd->new_parent);
 	struct dentry *old_dentry = rd->old_dentry;
 	struct dentry *new_dentry = rd->new_dentry;
 	struct inode **delegated_inode = rd->delegated_inode;
@@ -5266,10 +5267,10 @@ retry_deleg:
 	if (error)
 		goto exit5;
 
-	rd.old_dir	   = old_path.dentry->d_inode;
+	rd.old_parent	   = old_path.dentry;
 	rd.old_dentry	   = old_dentry;
 	rd.old_mnt_idmap   = mnt_idmap(old_path.mnt);
-	rd.new_dir	   = new_path.dentry->d_inode;
+	rd.new_parent	   = new_path.dentry;
 	rd.new_dentry	   = new_dentry;
 	rd.new_mnt_idmap   = mnt_idmap(new_path.mnt);
 	rd.delegated_inode = &delegated_inode;
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index cd689df2ca5d..7d522e426b2d 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -1864,7 +1864,6 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 			    struct svc_fh *tfhp, char *tname, int tlen)
 {
 	struct dentry	*fdentry, *tdentry, *odentry, *ndentry, *trap;
-	struct inode	*fdir, *tdir;
 	int		type = S_IFDIR;
 	__be32		err;
 	int		host_err;
@@ -1880,10 +1879,8 @@ nfsd_rename(struct svc_rqst *rqstp, struct svc_fh *ffhp, char *fname, int flen,
 		goto out;
 
 	fdentry = ffhp->fh_dentry;
-	fdir = d_inode(fdentry);
 
 	tdentry = tfhp->fh_dentry;
-	tdir = d_inode(tdentry);
 
 	err = nfserr_perm;
 	if (!flen || isdotent(fname, flen) || !tlen || isdotent(tname, tlen))
@@ -1944,10 +1941,10 @@ retry:
 	} else {
 		struct renamedata rd = {
 			.old_mnt_idmap	= &nop_mnt_idmap,
-			.old_dir	= fdir,
+			.old_parent	= fdentry,
 			.old_dentry	= odentry,
 			.new_mnt_idmap	= &nop_mnt_idmap,
-			.new_dir	= tdir,
+			.new_parent	= tdentry,
 			.new_dentry	= ndentry,
 		};
 		int retries;
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index d7310fcf3888..8a3c0d18ec2e 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -563,7 +563,7 @@ static int ovl_create_index(struct dentry *dentry, const struct ovl_fh *fh,
 	if (IS_ERR(index)) {
 		err = PTR_ERR(index);
 	} else {
-		err = ovl_do_rename(ofs, dir, temp, dir, index, 0);
+		err = ovl_do_rename(ofs, indexdir, temp, indexdir, index, 0);
 		dput(index);
 	}
 out:
@@ -762,7 +762,7 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
 {
 	struct ovl_fs *ofs = OVL_FS(c->dentry->d_sb);
 	struct inode *inode;
-	struct inode *udir = d_inode(c->destdir), *wdir = d_inode(c->workdir);
+	struct inode *wdir = d_inode(c->workdir);
 	struct path path = { .mnt = ovl_upper_mnt(ofs) };
 	struct dentry *temp, *upper, *trap;
 	struct ovl_cu_creds cc;
@@ -829,7 +829,7 @@ static int ovl_copy_up_workdir(struct ovl_copy_up_ctx *c)
 	if (IS_ERR(upper))
 		goto cleanup;
 
-	err = ovl_do_rename(ofs, wdir, temp, udir, upper, 0);
+	err = ovl_do_rename(ofs, c->workdir, temp, c->destdir, upper, 0);
 	dput(upper);
 	if (err)
 		goto cleanup;
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index fe493f3ed6b6..4fc221ea6480 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -107,7 +107,7 @@ out:
 }
 
 /* Caller must hold i_mutex on both workdir and dir */
-int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
+int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir,
 			     struct dentry *dentry)
 {
 	struct inode *wdir = ofs->workdir->d_inode;
@@ -123,7 +123,7 @@ int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
 	if (d_is_dir(dentry))
 		flags = RENAME_EXCHANGE;
 
-	err = ovl_do_rename(ofs, wdir, whiteout, dir, dentry, flags);
+	err = ovl_do_rename(ofs, ofs->workdir, whiteout, dir, dentry, flags);
 	if (err)
 		goto kill_whiteout;
 	if (flags)
@@ -384,7 +384,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_do_rename(ofs, wdir, opaquedir, udir, upper, RENAME_EXCHANGE);
+	err = ovl_do_rename(ofs, workdir, opaquedir, upperdir, upper, RENAME_EXCHANGE);
 	if (err)
 		goto out_cleanup;
 
@@ -491,14 +491,14 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 		if (err)
 			goto out_cleanup;
 
-		err = ovl_do_rename(ofs, wdir, newdentry, udir, upper,
+		err = ovl_do_rename(ofs, workdir, newdentry, upperdir, upper,
 				    RENAME_EXCHANGE);
 		if (err)
 			goto out_cleanup;
 
 		ovl_cleanup(ofs, wdir, upper);
 	} else {
-		err = ovl_do_rename(ofs, wdir, newdentry, udir, upper, 0);
+		err = ovl_do_rename(ofs, workdir, newdentry, upperdir, upper, 0);
 		if (err)
 			goto out_cleanup;
 	}
@@ -774,7 +774,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry,
 		goto out_dput_upper;
 	}
 
-	err = ovl_cleanup_and_whiteout(ofs, d_inode(upperdir), upper);
+	err = ovl_cleanup_and_whiteout(ofs, upperdir, upper);
 	if (err)
 		goto out_d_drop;
 
@@ -1246,8 +1246,8 @@ static int ovl_rename(struct mnt_idmap *idmap, struct inode *olddir,
 	if (err)
 		goto out_dput;
 
-	err = ovl_do_rename(ofs, old_upperdir->d_inode, olddentry,
-			    new_upperdir->d_inode, newdentry, flags);
+	err = ovl_do_rename(ofs, old_upperdir, olddentry,
+			    new_upperdir, newdentry, flags);
 	if (err)
 		goto out_dput;
 
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 8baaba0a3fe5..78deb89e16b5 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -353,19 +353,19 @@ static inline int ovl_do_remove_acl(struct ovl_fs *ofs, struct dentry *dentry,
 	return vfs_remove_acl(ovl_upper_mnt_idmap(ofs), dentry, acl_name);
 }
 
-static inline int ovl_do_rename(struct ovl_fs *ofs, struct inode *olddir,
-				struct dentry *olddentry, struct inode *newdir,
+static inline int ovl_do_rename(struct ovl_fs *ofs, struct dentry *olddir,
+				struct dentry *olddentry, struct dentry *newdir,
 				struct dentry *newdentry, unsigned int flags)
 {
 	int err;
 	struct renamedata rd = {
 		.old_mnt_idmap	= ovl_upper_mnt_idmap(ofs),
-		.old_dir 	= olddir,
-		.old_dentry 	= olddentry,
+		.old_parent	= olddir,
+		.old_dentry	= olddentry,
 		.new_mnt_idmap	= ovl_upper_mnt_idmap(ofs),
-		.new_dir 	= newdir,
-		.new_dentry 	= newdentry,
-		.flags 		= flags,
+		.new_parent	= newdir,
+		.new_dentry	= newdentry,
+		.flags		= flags,
 	};
 
 	pr_debug("rename(%pd2, %pd2, 0x%x)\n", olddentry, newdentry, flags);
@@ -826,7 +826,7 @@ static inline void ovl_copyflags(struct inode *from, struct inode *to)
 
 /* dir.c */
 extern const struct inode_operations ovl_dir_inode_operations;
-int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct inode *dir,
+int ovl_cleanup_and_whiteout(struct ovl_fs *ofs, struct dentry *dir,
 			     struct dentry *dentry);
 struct ovl_cattr {
 	dev_t rdev;
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index 474c80d210d1..68cca52ae2ac 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -1235,7 +1235,7 @@ int ovl_indexdir_cleanup(struct ovl_fs *ofs)
 			 * Whiteout orphan index to block future open by
 			 * handle after overlay nlink dropped to zero.
 			 */
-			err = ovl_cleanup_and_whiteout(ofs, dir, index);
+			err = ovl_cleanup_and_whiteout(ofs, indexdir, index);
 		} else {
 			/* Cleanup orphan index entries */
 			err = ovl_cleanup(ofs, dir, index);
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index e19940d649ca..cf99b276fdfb 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -580,7 +580,7 @@ static int ovl_check_rename_whiteout(struct ovl_fs *ofs)
 
 	/* Name is inline and stable - using snapshot as a copy helper */
 	take_dentry_name_snapshot(&name, temp);
-	err = ovl_do_rename(ofs, dir, temp, dir, dest, RENAME_WHITEOUT);
+	err = ovl_do_rename(ofs, workdir, temp, workdir, dest, RENAME_WHITEOUT);
 	if (err) {
 		if (err == -EINVAL)
 			err = 0;
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index dcccb4b4a66c..2b4754c645ee 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -1115,7 +1115,7 @@ static void ovl_cleanup_index(struct dentry *dentry)
 	} else if (ovl_index_all(dentry->d_sb)) {
 		/* Whiteout orphan index to block future open by handle */
 		err = ovl_cleanup_and_whiteout(OVL_FS(dentry->d_sb),
-					       dir, index);
+					       indexdir, index);
 	} else {
 		/* Cleanup orphan index entries */
 		err = ovl_cleanup(ofs, dir, index);
diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
index ba45e809555a..2f0171896e5d 100644
--- a/fs/smb/server/vfs.c
+++ b/fs/smb/server/vfs.c
@@ -764,10 +764,10 @@ retry:
 	}
 
 	rd.old_mnt_idmap	= mnt_idmap(old_path->mnt),
-	rd.old_dir		= d_inode(old_parent),
+	rd.old_parent		= old_parent,
 	rd.old_dentry		= old_child,
 	rd.new_mnt_idmap	= mnt_idmap(new_path.mnt),
-	rd.new_dir		= new_path.dentry->d_inode,
+	rd.new_parent		= new_path.dentry,
 	rd.new_dentry		= new_dentry,
 	rd.flags		= flags,
 	rd.delegated_inode	= NULL,
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..1d9586a78041 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2004,20 +2004,20 @@ int vfs_unlink(struct mnt_idmap *, struct inode *, struct dentry *,
 /**
  * struct renamedata - contains all information required for renaming
  * @old_mnt_idmap:     idmap of the old mount the inode was found from
- * @old_dir:           parent of source
+ * @old_parent:        parent of source
  * @old_dentry:                source
  * @new_mnt_idmap:     idmap of the new mount the inode was found from
- * @new_dir:           parent of destination
+ * @new_parent:        parent of destination
  * @new_dentry:                destination
  * @delegated_inode:   returns an inode needing a delegation break
  * @flags:             rename flags
  */
 struct renamedata {
 	struct mnt_idmap *old_mnt_idmap;
-	struct inode *old_dir;
+	struct dentry *old_parent;
 	struct dentry *old_dentry;
 	struct mnt_idmap *new_mnt_idmap;
-	struct inode *new_dir;
+	struct dentry *new_parent;
 	struct dentry *new_dentry;
 	struct inode **delegated_inode;
 	unsigned int flags;
-- 
cgit v1.2.3


From 0da3e3822cfabf062945e449f91ea3ca529eeaa4 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 12 Jun 2025 15:25:19 +0200
Subject: fs: move name_contains_dotdot() to header

Move the helper from the firmware specific code to a header so we can
reuse it for coredump sockets.

Link: https://lore.kernel.org/20250612-work-coredump-massage-v1-5-315c0c34ba94@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 drivers/base/firmware_loader/main.c | 31 +++++++++++--------------------
 include/linux/fs.h                  | 16 ++++++++++++++++
 2 files changed, 27 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
index 44486b2c7172..6942c62fa59d 100644
--- a/drivers/base/firmware_loader/main.c
+++ b/drivers/base/firmware_loader/main.c
@@ -822,26 +822,6 @@ static void fw_log_firmware_info(const struct firmware *fw, const char *name,
 {}
 #endif
 
-/*
- * Reject firmware file names with ".." path components.
- * There are drivers that construct firmware file names from device-supplied
- * strings, and we don't want some device to be able to tell us "I would like to
- * be sent my firmware from ../../../etc/shadow, please".
- *
- * Search for ".." surrounded by either '/' or start/end of string.
- *
- * This intentionally only looks at the firmware name, not at the firmware base
- * directory or at symlink contents.
- */
-static bool name_contains_dotdot(const char *name)
-{
-	size_t name_len = strlen(name);
-
-	return strcmp(name, "..") == 0 || strncmp(name, "../", 3) == 0 ||
-	       strstr(name, "/../") != NULL ||
-	       (name_len >= 3 && strcmp(name+name_len-3, "/..") == 0);
-}
-
 /* called from request_firmware() and request_firmware_work_func() */
 static int
 _request_firmware(const struct firmware **firmware_p, const char *name,
@@ -862,6 +842,17 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
 		goto out;
 	}
 
+
+	/*
+	 * Reject firmware file names with ".." path components.
+	 * There are drivers that construct firmware file names from
+	 * device-supplied strings, and we don't want some device to be
+	 * able to tell us "I would like to be sent my firmware from
+	 * ../../../etc/shadow, please".
+	 *
+	 * This intentionally only looks at the firmware name, not at
+	 * the firmware base directory or at symlink contents.
+	 */
 	if (name_contains_dotdot(name)) {
 		dev_warn(device,
 			 "Firmware load for '%s' refused, path contains '..' component\n",
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..18fdbd184eea 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3264,6 +3264,22 @@ static inline bool is_dot_dotdot(const char *name, size_t len)
 		(len == 1 || (len == 2 && name[1] == '.'));
 }
 
+/**
+ * name_contains_dotdot - check if a file name contains ".." path components
+ *
+ * Search for ".." surrounded by either '/' or start/end of string.
+ */
+static inline bool name_contains_dotdot(const char *name)
+{
+	size_t name_len;
+
+	name_len = strlen(name);
+	return strcmp(name, "..") == 0 ||
+	       strncmp(name, "../", 3) == 0 ||
+	       strstr(name, "/../") != NULL ||
+	       (name_len >= 3 && strcmp(name + name_len - 3, "/..") == 0);
+}
+
 #include <linux/err.h>
 
 /* needed for stackable file system support */
-- 
cgit v1.2.3


From 70e3ee31282d293c794fb5bbec8efe495c32044b Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 12 Jun 2025 15:25:23 +0200
Subject: coredump: rename do_coredump() to vfs_coredump()

Align the naming with the rest of our helpers exposed
outside of core vfs.

Link: https://lore.kernel.org/20250612-work-coredump-massage-v1-9-315c0c34ba94@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/security/credentials.rst                    | 2 +-
 Documentation/translations/zh_CN/security/credentials.rst | 2 +-
 fs/coredump.c                                             | 2 +-
 include/linux/coredump.h                                  | 4 ++--
 kernel/signal.c                                           | 2 +-
 5 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/security/credentials.rst b/Documentation/security/credentials.rst
index 2aa0791bcefe..d0191c8b8060 100644
--- a/Documentation/security/credentials.rst
+++ b/Documentation/security/credentials.rst
@@ -555,5 +555,5 @@ the VFS, and that can be done by calling into such as ``vfs_mkdir()`` with a
 different set of credentials.  This is done in the following places:
 
  * ``sys_faccessat()``.
- * ``do_coredump()``.
+ * ``vfs_coredump()``.
  * nfs4recover.c.
diff --git a/Documentation/translations/zh_CN/security/credentials.rst b/Documentation/translations/zh_CN/security/credentials.rst
index 91c353dfb622..88fcd9152ffe 100644
--- a/Documentation/translations/zh_CN/security/credentials.rst
+++ b/Documentation/translations/zh_CN/security/credentials.rst
@@ -475,5 +475,5 @@ const指针上操作，因此不需要进行类型转换，但需要临时放弃
 如 ``vfs_mkdir()`` 来实现。以下是一些进行此操作的位置:
 
  * ``sys_faccessat()``.
- * ``do_coredump()``.
+ * ``vfs_coredump()``.
  * nfs4recover.c.
diff --git a/fs/coredump.c b/fs/coredump.c
index 52efd1b34261..8a401eeee940 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -865,7 +865,7 @@ static inline void coredump_sock_wait(struct file *file) { }
 static inline void coredump_sock_shutdown(struct file *file) { }
 #endif
 
-void do_coredump(const kernel_siginfo_t *siginfo)
+void vfs_coredump(const kernel_siginfo_t *siginfo)
 {
 	struct core_state core_state;
 	struct core_name cn;
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 76e41805b92d..96e8a66da133 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -43,7 +43,7 @@ extern int dump_emit(struct coredump_params *cprm, const void *addr, int nr);
 extern int dump_align(struct coredump_params *cprm, int align);
 int dump_user_range(struct coredump_params *cprm, unsigned long start,
 		    unsigned long len);
-extern void do_coredump(const kernel_siginfo_t *siginfo);
+extern void vfs_coredump(const kernel_siginfo_t *siginfo);
 
 /*
  * Logging for the coredump code, ratelimited.
@@ -63,7 +63,7 @@ extern void do_coredump(const kernel_siginfo_t *siginfo);
 #define coredump_report_failure(fmt, ...) __COREDUMP_PRINTK(KERN_WARNING, fmt, ##__VA_ARGS__)
 
 #else
-static inline void do_coredump(const kernel_siginfo_t *siginfo) {}
+static inline void vfs_coredump(const kernel_siginfo_t *siginfo) {}
 
 #define coredump_report(...)
 #define coredump_report_failure(...)
diff --git a/kernel/signal.c b/kernel/signal.c
index 148082db9a55..e2c928de7d2c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -3016,7 +3016,7 @@ relock:
 			 * first and our do_group_exit call below will use
 			 * that value and ignore the one we pass it.
 			 */
-			do_coredump(&ksig->info);
+			vfs_coredump(&ksig->info);
 		}
 
 		/*
-- 
cgit v1.2.3


From fda6add9243867486f8cd456d7b05395d2132e0a Mon Sep 17 00:00:00 2001
From: Kent Overstreet <kent.overstreet@linux.dev>
Date: Mon, 16 Jun 2025 13:59:20 -0400
Subject: workqueue: Basic memory allocation profiling support

Hook alloc_workqueue and alloc_workqueue_attrs() so that they're
accounted to the callsite. Since we're doing allocations on behalf of
another subsystem, this helps when using memory allocation profiling to
check for leaks.

Cc: Tejun Heo <tj@kernel.org>
Cc: Lai Jiangshan <jiangshanlai@gmail.com>
Signed-off-by: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/workqueue.h | 12 ++++++++----
 kernel/workqueue.c        | 14 +++++++-------
 2 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 6e30f275da77..e907c9bb840c 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -6,6 +6,7 @@
 #ifndef _LINUX_WORKQUEUE_H
 #define _LINUX_WORKQUEUE_H
 
+#include <linux/alloc_tag.h>
 #include <linux/timer.h>
 #include <linux/linkage.h>
 #include <linux/bitops.h>
@@ -505,7 +506,8 @@ void workqueue_softirq_dead(unsigned int cpu);
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 __printf(1, 4) struct workqueue_struct *
-alloc_workqueue(const char *fmt, unsigned int flags, int max_active, ...);
+alloc_workqueue_noprof(const char *fmt, unsigned int flags, int max_active, ...);
+#define alloc_workqueue(...)	alloc_hooks(alloc_workqueue_noprof(__VA_ARGS__))
 
 #ifdef CONFIG_LOCKDEP
 /**
@@ -544,8 +546,8 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active,
  * Pointer to the allocated workqueue on success, %NULL on failure.
  */
 #define alloc_ordered_workqueue_lockdep_map(fmt, flags, lockdep_map, args...)	\
-	alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags),	\
-				    1, lockdep_map, ##args)
+	alloc_hooks(alloc_workqueue_lockdep_map(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags),\
+						1, lockdep_map, ##args))
 #endif
 
 /**
@@ -577,7 +579,9 @@ alloc_workqueue_lockdep_map(const char *fmt, unsigned int flags, int max_active,
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
-struct workqueue_attrs *alloc_workqueue_attrs(void);
+struct workqueue_attrs *alloc_workqueue_attrs_noprof(void);
+#define alloc_workqueue_attrs(...)	alloc_hooks(alloc_workqueue_attrs_noprof(__VA_ARGS__))
+
 void free_workqueue_attrs(struct workqueue_attrs *attrs);
 int apply_workqueue_attrs(struct workqueue_struct *wq,
 			  const struct workqueue_attrs *attrs);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index d9de0f2a2e00..c24844afaa98 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -4626,7 +4626,7 @@ void free_workqueue_attrs(struct workqueue_attrs *attrs)
  *
  * Return: The allocated new workqueue_attr on success. %NULL on failure.
  */
-struct workqueue_attrs *alloc_workqueue_attrs(void)
+struct workqueue_attrs *alloc_workqueue_attrs_noprof(void)
 {
 	struct workqueue_attrs *attrs;
 
@@ -5679,12 +5679,12 @@ static struct workqueue_struct *__alloc_workqueue(const char *fmt,
 	else
 		wq_size = sizeof(*wq);
 
-	wq = kzalloc(wq_size, GFP_KERNEL);
+	wq = kzalloc_noprof(wq_size, GFP_KERNEL);
 	if (!wq)
 		return NULL;
 
 	if (flags & WQ_UNBOUND) {
-		wq->unbound_attrs = alloc_workqueue_attrs();
+		wq->unbound_attrs = alloc_workqueue_attrs_noprof();
 		if (!wq->unbound_attrs)
 			goto err_free_wq;
 	}
@@ -5774,9 +5774,9 @@ err_destroy:
 }
 
 __printf(1, 4)
-struct workqueue_struct *alloc_workqueue(const char *fmt,
-					 unsigned int flags,
-					 int max_active, ...)
+struct workqueue_struct *alloc_workqueue_noprof(const char *fmt,
+						unsigned int flags,
+						int max_active, ...)
 {
 	struct workqueue_struct *wq;
 	va_list args;
@@ -5791,7 +5791,7 @@ struct workqueue_struct *alloc_workqueue(const char *fmt,
 
 	return wq;
 }
-EXPORT_SYMBOL_GPL(alloc_workqueue);
+EXPORT_SYMBOL_GPL(alloc_workqueue_noprof);
 
 #ifdef CONFIG_LOCKDEP
 __printf(1, 5)
-- 
cgit v1.2.3


From 49d63971f96349cdcff89d21786e3c804e7cd4c0 Mon Sep 17 00:00:00 2001
From: Andrea della Porta <andrea.porta@suse.com>
Date: Thu, 29 May 2025 15:50:44 +0200
Subject: misc: rp1: RaspberryPi RP1 misc driver

The RaspberryPi RP1 is a PCI multi function device containing
peripherals ranging from Ethernet to USB controller, I2C, SPI
and others.

Implement a bare minimum driver to operate the RP1, leveraging
actual OF based driver implementations for the on-board peripherals
by loading a devicetree overlay during driver probe if the RP1
node is not already present in the DT.

The peripherals are accessed by mapping MMIO registers starting
from PCI BAR1 region.

With the overlay approach we can achieve more generic and agnostic
approach to managing this chipset, being that it is a PCI endpoint
and could possibly be reused in other hw implementations. The
presented approach is also used by Bootlin's Microchip LAN966x
patchset (see link) as well, for a similar chipset.
In this case, the inclusion tree for the DT overlay is as follow
(the arrow points to the includer):

 rp1-pci.dtso <---- rp1-common.dtsi

On the other hand, to ensure compatibility with downstream, this
driver can also work with a DT already comprising the RP1 node, so
the dynamically loaded overlay will not be used if the DT is already
fully defined.

The reason why this driver is contained in drivers/misc has
been paved by Bootlin's LAN966X driver, which first used the
overlay approach to implement non discoverable peripherals behind a
PCI bus. For RP1, the same arguments apply: it's not used as an SoC
since the driver code is not running on-chip and is not like an MFD
since it does not really need all the MFD infrastructure (shared regs,
etc.). So, for this particular use, misc has been proposed and deemed
as a good choice. For further details about that please check the links.

This driver is heavily based on downstream code from RaspberryPi
Foundation, and the original author is Phil Elwell.

Link: https://datasheets.raspberrypi.com/rp1/rp1-peripherals.pdf
Link: https://lore.kernel.org/all/20240612140208.GC1504919@google.com/
Link: https://lore.kernel.org/all/83f7fa09-d0e6-4f36-a27d-cee08979be2a@app.fastmail.com/
Link: https://lore.kernel.org/all/2024081356-mutable-everyday-6f9d@gregkh/
Link: https://lore.kernel.org/all/20240808154658.247873-1-herve.codina@bootlin.com/

Signed-off-by: Andrea della Porta <andrea.porta@suse.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>   # quirks.c, pci_ids.h
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Link: https://lore.kernel.org/r/20250529135052.28398-7-andrea.porta@suse.com
Signed-off-by: Florian Fainelli <florian.fainelli@broadcom.com>
---
 drivers/misc/Kconfig          |   1 +
 drivers/misc/Makefile         |   1 +
 drivers/misc/rp1/Kconfig      |  20 +++
 drivers/misc/rp1/Makefile     |   3 +
 drivers/misc/rp1/rp1-pci.dtso |  25 ++++
 drivers/misc/rp1/rp1_pci.c    | 333 ++++++++++++++++++++++++++++++++++++++++++
 drivers/pci/quirks.c          |   1 +
 include/linux/pci_ids.h       |   3 +
 8 files changed, 387 insertions(+)
 create mode 100644 drivers/misc/rp1/Kconfig
 create mode 100644 drivers/misc/rp1/Makefile
 create mode 100644 drivers/misc/rp1/rp1-pci.dtso
 create mode 100644 drivers/misc/rp1/rp1_pci.c

(limited to 'include/linux')

diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index b9ca56930003..b9c11f67315f 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -660,4 +660,5 @@ source "drivers/misc/pvpanic/Kconfig"
 source "drivers/misc/mchp_pci1xxxx/Kconfig"
 source "drivers/misc/keba/Kconfig"
 source "drivers/misc/amd-sbi/Kconfig"
+source "drivers/misc/rp1/Kconfig"
 endmenu
diff --git a/drivers/misc/Makefile b/drivers/misc/Makefile
index 917b9a7183aa..e2e66f5f4fb8 100644
--- a/drivers/misc/Makefile
+++ b/drivers/misc/Makefile
@@ -75,3 +75,4 @@ lan966x-pci-objs		+= lan966x_pci.dtbo.o
 obj-$(CONFIG_MCHP_LAN966X_PCI)	+= lan966x-pci.o
 obj-y				+= keba/
 obj-y				+= amd-sbi/
+obj-$(CONFIG_MISC_RP1)		+= rp1/
diff --git a/drivers/misc/rp1/Kconfig b/drivers/misc/rp1/Kconfig
new file mode 100644
index 000000000000..5232e70d3079
--- /dev/null
+++ b/drivers/misc/rp1/Kconfig
@@ -0,0 +1,20 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# RaspberryPi RP1 misc device
+#
+
+config MISC_RP1
+	tristate "RaspberryPi RP1 misc device"
+	depends on OF_IRQ && OF_OVERLAY && PCI_MSI && PCI_QUIRKS
+	select PCI_DYNAMIC_OF_NODES
+	help
+	  Support the RP1 peripheral chip found on Raspberry Pi 5 board.
+
+	  This device supports several sub-devices including e.g. Ethernet
+	  controller, USB controller, I2C, SPI and UART.
+
+	  The driver is responsible for enabling the DT node once the PCIe
+	  endpoint has been configured, and handling interrupts.
+
+	  This driver uses an overlay to load other drivers to support for
+	  RP1 internal sub-devices.
diff --git a/drivers/misc/rp1/Makefile b/drivers/misc/rp1/Makefile
new file mode 100644
index 000000000000..508b4cb05627
--- /dev/null
+++ b/drivers/misc/rp1/Makefile
@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_MISC_RP1)		+= rp1-pci.o
+rp1-pci-objs			:= rp1_pci.o rp1-pci.dtbo.o
diff --git a/drivers/misc/rp1/rp1-pci.dtso b/drivers/misc/rp1/rp1-pci.dtso
new file mode 100644
index 000000000000..eea826b36e02
--- /dev/null
+++ b/drivers/misc/rp1/rp1-pci.dtso
@@ -0,0 +1,25 @@
+// SPDX-License-Identifier: (GPL-2.0 OR MIT)
+
+/*
+ * The dts overlay is included from the dts directory so
+ * it can be possible to check it with CHECK_DTBS while
+ * also compile it from the driver source directory.
+ */
+
+/dts-v1/;
+/plugin/;
+
+/ {
+	fragment@0 {
+		target-path="";
+		__overlay__ {
+			compatible = "pci1de4,1";
+			#address-cells = <3>;
+			#size-cells = <2>;
+			interrupt-controller;
+			#interrupt-cells = <2>;
+
+			#include "arm64/broadcom/rp1-common.dtsi"
+		};
+	};
+};
diff --git a/drivers/misc/rp1/rp1_pci.c b/drivers/misc/rp1/rp1_pci.c
new file mode 100644
index 000000000000..803832006ec8
--- /dev/null
+++ b/drivers/misc/rp1/rp1_pci.c
@@ -0,0 +1,333 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2018-2025 Raspberry Pi Ltd.
+ *
+ * All rights reserved.
+ */
+
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_platform.h>
+#include <linux/pci.h>
+#include <linux/platform_device.h>
+
+#define RP1_HW_IRQ_MASK		GENMASK(5, 0)
+
+#define REG_SET			0x800
+#define REG_CLR			0xc00
+
+/* MSI-X CFG registers start at 0x8 */
+#define MSIX_CFG(x) (0x8 + (4 * (x)))
+
+#define MSIX_CFG_IACK_EN        BIT(3)
+#define MSIX_CFG_IACK           BIT(2)
+#define MSIX_CFG_ENABLE         BIT(0)
+
+/* Address map */
+#define RP1_PCIE_APBS_BASE	0x108000
+
+/* Interrupts */
+#define RP1_INT_END		61
+
+/* Embedded dtbo symbols created by cmd_wrap_S_dtb in scripts/Makefile.lib */
+extern char __dtbo_rp1_pci_begin[];
+extern char __dtbo_rp1_pci_end[];
+
+struct rp1_dev {
+	struct pci_dev *pdev;
+	struct irq_domain *domain;
+	struct irq_data *pcie_irqds[64];
+	void __iomem *bar1;
+	int ovcs_id;	/* overlay changeset id */
+	bool level_triggered_irq[RP1_INT_END];
+};
+
+static void msix_cfg_set(struct rp1_dev *rp1, unsigned int hwirq, u32 value)
+{
+	iowrite32(value, rp1->bar1 + RP1_PCIE_APBS_BASE + REG_SET + MSIX_CFG(hwirq));
+}
+
+static void msix_cfg_clr(struct rp1_dev *rp1, unsigned int hwirq, u32 value)
+{
+	iowrite32(value, rp1->bar1 + RP1_PCIE_APBS_BASE + REG_CLR + MSIX_CFG(hwirq));
+}
+
+static void rp1_mask_irq(struct irq_data *irqd)
+{
+	struct rp1_dev *rp1 = irqd->domain->host_data;
+	struct irq_data *pcie_irqd = rp1->pcie_irqds[irqd->hwirq];
+
+	pci_msi_mask_irq(pcie_irqd);
+}
+
+static void rp1_unmask_irq(struct irq_data *irqd)
+{
+	struct rp1_dev *rp1 = irqd->domain->host_data;
+	struct irq_data *pcie_irqd = rp1->pcie_irqds[irqd->hwirq];
+
+	pci_msi_unmask_irq(pcie_irqd);
+}
+
+static int rp1_irq_set_type(struct irq_data *irqd, unsigned int type)
+{
+	struct rp1_dev *rp1 = irqd->domain->host_data;
+	unsigned int hwirq = (unsigned int)irqd->hwirq;
+
+	switch (type) {
+	case IRQ_TYPE_LEVEL_HIGH:
+		dev_dbg(&rp1->pdev->dev, "MSIX IACK EN for IRQ %u\n", hwirq);
+		msix_cfg_set(rp1, hwirq, MSIX_CFG_IACK_EN);
+		rp1->level_triggered_irq[hwirq] = true;
+	break;
+	case IRQ_TYPE_EDGE_RISING:
+		msix_cfg_clr(rp1, hwirq, MSIX_CFG_IACK_EN);
+		rp1->level_triggered_irq[hwirq] = false;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static struct irq_chip rp1_irq_chip = {
+	.name		= "rp1_irq_chip",
+	.irq_mask	= rp1_mask_irq,
+	.irq_unmask	= rp1_unmask_irq,
+	.irq_set_type	= rp1_irq_set_type,
+};
+
+static void rp1_chained_handle_irq(struct irq_desc *desc)
+{
+	unsigned int hwirq = desc->irq_data.hwirq & RP1_HW_IRQ_MASK;
+	struct rp1_dev *rp1 = irq_desc_get_handler_data(desc);
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+	unsigned int virq;
+
+	chained_irq_enter(chip, desc);
+
+	virq = irq_find_mapping(rp1->domain, hwirq);
+	generic_handle_irq(virq);
+	if (rp1->level_triggered_irq[hwirq])
+		msix_cfg_set(rp1, hwirq, MSIX_CFG_IACK);
+
+	chained_irq_exit(chip, desc);
+}
+
+static int rp1_irq_xlate(struct irq_domain *d, struct device_node *node,
+			 const u32 *intspec, unsigned int intsize,
+			 unsigned long *out_hwirq, unsigned int *out_type)
+{
+	struct rp1_dev *rp1 = d->host_data;
+	struct irq_data *pcie_irqd;
+	unsigned long hwirq;
+	int pcie_irq;
+	int ret;
+
+	ret = irq_domain_xlate_twocell(d, node, intspec, intsize,
+				       &hwirq, out_type);
+	if (ret)
+		return ret;
+
+	pcie_irq = pci_irq_vector(rp1->pdev, hwirq);
+	pcie_irqd = irq_get_irq_data(pcie_irq);
+	rp1->pcie_irqds[hwirq] = pcie_irqd;
+	*out_hwirq = hwirq;
+
+	return 0;
+}
+
+static int rp1_irq_activate(struct irq_domain *d, struct irq_data *irqd,
+			    bool reserve)
+{
+	struct rp1_dev *rp1 = d->host_data;
+
+	msix_cfg_set(rp1, (unsigned int)irqd->hwirq, MSIX_CFG_ENABLE);
+
+	return 0;
+}
+
+static void rp1_irq_deactivate(struct irq_domain *d, struct irq_data *irqd)
+{
+	struct rp1_dev *rp1 = d->host_data;
+
+	msix_cfg_clr(rp1, (unsigned int)irqd->hwirq, MSIX_CFG_ENABLE);
+}
+
+static const struct irq_domain_ops rp1_domain_ops = {
+	.xlate      = rp1_irq_xlate,
+	.activate   = rp1_irq_activate,
+	.deactivate = rp1_irq_deactivate,
+};
+
+static void rp1_unregister_interrupts(struct pci_dev *pdev)
+{
+	struct rp1_dev *rp1 = pci_get_drvdata(pdev);
+	int irq, i;
+
+	if (rp1->domain) {
+		for (i = 0; i < RP1_INT_END; i++) {
+			irq = irq_find_mapping(rp1->domain, i);
+			irq_dispose_mapping(irq);
+		}
+
+		irq_domain_remove(rp1->domain);
+	}
+
+	pci_free_irq_vectors(pdev);
+}
+
+static int rp1_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	u32 dtbo_size = __dtbo_rp1_pci_end - __dtbo_rp1_pci_begin;
+	void *dtbo_start = __dtbo_rp1_pci_begin;
+	struct device *dev = &pdev->dev;
+	struct device_node *rp1_node;
+	bool skip_ovl = true;
+	struct rp1_dev *rp1;
+	int err = 0;
+	int i;
+
+	/*
+	 * Either use rp1_nexus node if already present in DT, or
+	 * set a flag to load it from overlay at runtime
+	 */
+	rp1_node = of_find_node_by_name(NULL, "rp1_nexus");
+	if (!rp1_node) {
+		rp1_node = dev_of_node(dev);
+		skip_ovl = false;
+	}
+
+	if (!rp1_node) {
+		dev_err(dev, "Missing of_node for device\n");
+		err = -EINVAL;
+		goto err_put_node;
+	}
+
+	rp1 = devm_kzalloc(&pdev->dev, sizeof(*rp1), GFP_KERNEL);
+	if (!rp1) {
+		err = -ENOMEM;
+		goto err_put_node;
+	}
+
+	rp1->pdev = pdev;
+
+	if (pci_resource_len(pdev, 1) <= 0x10000) {
+		dev_err(&pdev->dev,
+			"Not initialized - is the firmware running?\n");
+		err = -EINVAL;
+		goto err_put_node;
+	}
+
+	err = pcim_enable_device(pdev);
+	if (err < 0) {
+		err = dev_err_probe(&pdev->dev, err,
+				    "Enabling PCI device has failed");
+		goto err_put_node;
+	}
+
+	rp1->bar1 = pcim_iomap(pdev, 1, 0);
+	if (!rp1->bar1) {
+		dev_err(&pdev->dev, "Cannot map PCI BAR\n");
+		err = -EIO;
+		goto err_put_node;
+	}
+
+	pci_set_master(pdev);
+
+	err = pci_alloc_irq_vectors(pdev, RP1_INT_END, RP1_INT_END,
+				    PCI_IRQ_MSIX);
+	if (err < 0) {
+		err = dev_err_probe(&pdev->dev, err,
+				    "Failed to allocate MSI-X vectors\n");
+		goto err_put_node;
+	} else if (err != RP1_INT_END) {
+		dev_err(&pdev->dev, "Cannot allocate enough interrupts\n");
+		err = -EINVAL;
+		goto err_put_node;
+	}
+
+	pci_set_drvdata(pdev, rp1);
+	rp1->domain = irq_domain_add_linear(rp1_node, RP1_INT_END,
+					    &rp1_domain_ops, rp1);
+	if (!rp1->domain) {
+		dev_err(&pdev->dev, "Error creating IRQ domain\n");
+		err = -ENOMEM;
+		goto err_unregister_interrupts;
+	}
+
+	for (i = 0; i < RP1_INT_END; i++) {
+		unsigned int irq = irq_create_mapping(rp1->domain, i);
+
+		if (!irq) {
+			dev_err(&pdev->dev, "Failed to create IRQ mapping\n");
+			err = -EINVAL;
+			goto err_unregister_interrupts;
+		}
+
+		irq_set_chip_and_handler(irq, &rp1_irq_chip, handle_level_irq);
+		irq_set_probe(irq);
+		irq_set_chained_handler_and_data(pci_irq_vector(pdev, i),
+						 rp1_chained_handle_irq, rp1);
+	}
+
+	if (!skip_ovl) {
+		err = of_overlay_fdt_apply(dtbo_start, dtbo_size, &rp1->ovcs_id,
+					   rp1_node);
+		if (err)
+			goto err_unregister_interrupts;
+	}
+
+	err = of_platform_default_populate(rp1_node, NULL, dev);
+	if (err) {
+		dev_err_probe(&pdev->dev, err, "Error populating devicetree\n");
+		goto err_unload_overlay;
+	}
+
+	return 0;
+
+err_unload_overlay:
+	of_overlay_remove(&rp1->ovcs_id);
+err_unregister_interrupts:
+	rp1_unregister_interrupts(pdev);
+err_put_node:
+	if (skip_ovl)
+		of_node_put(rp1_node);
+
+	return err;
+}
+
+static void rp1_remove(struct pci_dev *pdev)
+{
+	struct rp1_dev *rp1 = pci_get_drvdata(pdev);
+	struct device *dev = &pdev->dev;
+
+	of_platform_depopulate(dev);
+	of_overlay_remove(&rp1->ovcs_id);
+	rp1_unregister_interrupts(pdev);
+}
+
+static const struct pci_device_id dev_id_table[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_RPI, PCI_DEVICE_ID_RPI_RP1_C0), },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, dev_id_table);
+
+static struct pci_driver rp1_driver = {
+	.name		= KBUILD_MODNAME,
+	.id_table	= dev_id_table,
+	.probe		= rp1_probe,
+	.remove		= rp1_remove,
+};
+
+module_pci_driver(rp1_driver);
+
+MODULE_AUTHOR("Phil Elwell <phil@raspberrypi.com>");
+MODULE_AUTHOR("Andrea della Porta <andrea.porta@suse.com>");
+MODULE_DESCRIPTION("RaspberryPi RP1 misc device");
+MODULE_LICENSE("GPL");
diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
index d7f4ee634263..cf483d82572c 100644
--- a/drivers/pci/quirks.c
+++ b/drivers/pci/quirks.c
@@ -6303,6 +6303,7 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5020, of_pci_make_dev_node);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_XILINX, 0x5021, of_pci_make_dev_node);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_REDHAT, 0x0005, of_pci_make_dev_node);
 DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_EFAR, 0x9660, of_pci_make_dev_node);
+DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_RPI, PCI_DEVICE_ID_RPI_RP1_C0, of_pci_make_dev_node);
 
 /*
  * Devices known to require a longer delay before first config space access
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index e2d71b6fdd84..92ffc4373f6d 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -2624,6 +2624,9 @@
 #define PCI_VENDOR_ID_TEKRAM		0x1de1
 #define PCI_DEVICE_ID_TEKRAM_DC290	0xdc29
 
+#define PCI_VENDOR_ID_RPI		0x1de4
+#define PCI_DEVICE_ID_RPI_RP1_C0	0x0001
+
 #define PCI_VENDOR_ID_ALIBABA		0x1ded
 
 #define PCI_VENDOR_ID_CXL		0x1e98
-- 
cgit v1.2.3


From 594902c986e269660302f09df9ec4bf1cf017b77 Mon Sep 17 00:00:00 2001
From: Qinyun Tan <qinyuntan@linux.alibaba.com>
Date: Sat, 31 May 2025 02:20:53 +0800
Subject: x86,fs/resctrl: Remove inappropriate references to cacheinfo in the
 resctrl subsystem

In the resctrl subsystem's Sub-NUMA Cluster (SNC) mode, the rdt_mon_domain
structure representing a NUMA node relies on the cacheinfo interface
(rdt_mon_domain::ci) to store L3 cache information (e.g., shared_cpu_map)
for monitoring. The L3 cache information of a SNC NUMA node determines
which domains are summed for the "top level" L3-scoped events.

rdt_mon_domain::ci is initialized using the first online CPU of a NUMA
node. When this CPU goes offline, its shared_cpu_map is cleared to contain
only the offline CPU itself. Subsequently, attempting to read counters
via smp_call_on_cpu(offline_cpu) fails (and error ignored), returning
zero values for "top-level events" without any error indication.

Replace the cacheinfo references in struct rdt_mon_domain and struct
rmid_read with the cacheinfo ID (a unique identifier for the L3 cache).

rdt_domain_hdr::cpu_mask contains the online CPUs associated with that
domain. When reading "top-level events", select a CPU from
rdt_domain_hdr::cpu_mask and utilize its L3 shared_cpu_map to determine
valid CPUs for reading RMID counter via the MSR interface.

Considering all CPUs associated with the L3 cache improves the chances
of picking a housekeeping CPU on which the counter reading work can be
queued, avoiding an unnecessary IPI.

Fixes: 328ea68874642 ("x86/resctrl: Prepare for new Sub-NUMA Cluster (SNC) monitor files")
Signed-off-by: Qinyun Tan <qinyuntan@linux.alibaba.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>
Tested-by: Tony Luck <tony.luck@intel.com>
Link: https://lore.kernel.org/20250530182053.37502-2-qinyuntan@linux.alibaba.com
---
 arch/x86/kernel/cpu/resctrl/core.c |  6 ++++--
 fs/resctrl/ctrlmondata.c           | 13 +++++++++----
 fs/resctrl/internal.h              |  4 ++--
 fs/resctrl/monitor.c               |  6 ++++--
 fs/resctrl/rdtgroup.c              |  6 +++---
 include/linux/resctrl.h            |  4 ++--
 6 files changed, 24 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 7109cbfcad4f..187d527ef73b 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -498,6 +498,7 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	struct rdt_hw_mon_domain *hw_dom;
 	struct rdt_domain_hdr *hdr;
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	int err;
 
 	lockdep_assert_held(&domain_list_lock);
@@ -525,12 +526,13 @@ static void domain_add_cpu_mon(int cpu, struct rdt_resource *r)
 	d = &hw_dom->d_resctrl;
 	d->hdr.id = id;
 	d->hdr.type = RESCTRL_MON_DOMAIN;
-	d->ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
-	if (!d->ci) {
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci) {
 		pr_warn_once("Can't find L3 cache for CPU:%d resource %s\n", cpu, r->name);
 		mon_domain_free(hw_dom);
 		return;
 	}
+	d->ci_id = ci->id;
 	cpumask_set_cpu(cpu, &d->hdr.cpu_mask);
 
 	arch_mon_domain_online(r, d);
diff --git a/fs/resctrl/ctrlmondata.c b/fs/resctrl/ctrlmondata.c
index 6ed2dfd4dbbd..d98e0d2de09f 100644
--- a/fs/resctrl/ctrlmondata.c
+++ b/fs/resctrl/ctrlmondata.c
@@ -594,9 +594,10 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 	struct rmid_read rr = {0};
 	struct rdt_mon_domain *d;
 	struct rdtgroup *rdtgrp;
+	int domid, cpu, ret = 0;
 	struct rdt_resource *r;
+	struct cacheinfo *ci;
 	struct mon_data *md;
-	int domid, ret = 0;
 
 	rdtgrp = rdtgroup_kn_lock_live(of->kn);
 	if (!rdtgrp) {
@@ -623,10 +624,14 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 		 * one that matches this cache id.
 		 */
 		list_for_each_entry(d, &r->mon_domains, hdr.list) {
-			if (d->ci->id == domid) {
-				rr.ci = d->ci;
+			if (d->ci_id == domid) {
+				rr.ci_id = d->ci_id;
+				cpu = cpumask_any(&d->hdr.cpu_mask);
+				ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+				if (!ci)
+					continue;
 				mon_event_read(&rr, r, NULL, rdtgrp,
-					       &d->ci->shared_cpu_map, evtid, false);
+					       &ci->shared_cpu_map, evtid, false);
 				goto checkresult;
 			}
 		}
diff --git a/fs/resctrl/internal.h b/fs/resctrl/internal.h
index 9a8cf6f11151..0a1eedba2b03 100644
--- a/fs/resctrl/internal.h
+++ b/fs/resctrl/internal.h
@@ -98,7 +98,7 @@ struct mon_data {
  *	   domains in @r sharing L3 @ci.id
  * @evtid: Which monitor event to read.
  * @first: Initialize MBM counter when true.
- * @ci:    Cacheinfo for L3. Only set when @d is NULL. Used when summing domains.
+ * @ci_id: Cacheinfo id for L3. Only set when @d is NULL. Used when summing domains.
  * @err:   Error encountered when reading counter.
  * @val:   Returned value of event counter. If @rgrp is a parent resource group,
  *	   @val includes the sum of event counts from its child resource groups.
@@ -112,7 +112,7 @@ struct rmid_read {
 	struct rdt_mon_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
-	struct cacheinfo	*ci;
+	unsigned int		ci_id;
 	int			err;
 	u64			val;
 	void			*arch_mon_ctx;
diff --git a/fs/resctrl/monitor.c b/fs/resctrl/monitor.c
index bde2801289d3..f5637855c3ac 100644
--- a/fs/resctrl/monitor.c
+++ b/fs/resctrl/monitor.c
@@ -361,6 +361,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 {
 	int cpu = smp_processor_id();
 	struct rdt_mon_domain *d;
+	struct cacheinfo *ci;
 	struct mbm_state *m;
 	int err, ret;
 	u64 tval = 0;
@@ -388,7 +389,8 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	}
 
 	/* Summing domains that share a cache, must be on a CPU for that cache. */
-	if (!cpumask_test_cpu(cpu, &rr->ci->shared_cpu_map))
+	ci = get_cpu_cacheinfo_level(cpu, RESCTRL_L3_CACHE);
+	if (!ci || ci->id != rr->ci_id)
 		return -EINVAL;
 
 	/*
@@ -400,7 +402,7 @@ static int __mon_event_count(u32 closid, u32 rmid, struct rmid_read *rr)
 	 */
 	ret = -EINVAL;
 	list_for_each_entry(d, &rr->r->mon_domains, hdr.list) {
-		if (d->ci->id != rr->ci->id)
+		if (d->ci_id != rr->ci_id)
 			continue;
 		err = resctrl_arch_rmid_read(rr->r, d, closid, rmid,
 					     rr->evtid, &tval, rr->arch_mon_ctx);
diff --git a/fs/resctrl/rdtgroup.c b/fs/resctrl/rdtgroup.c
index 1beb124e25f6..77d08229d855 100644
--- a/fs/resctrl/rdtgroup.c
+++ b/fs/resctrl/rdtgroup.c
@@ -3036,7 +3036,7 @@ static void rmdir_mondata_subdir_allrdtgrp(struct rdt_resource *r,
 	char name[32];
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	if (snc_mode)
 		sprintf(subname, "mon_sub_%s_%02d", r->name, d->hdr.id);
 
@@ -3061,7 +3061,7 @@ static int mon_add_all_files(struct kernfs_node *kn, struct rdt_mon_domain *d,
 		return -EPERM;
 
 	list_for_each_entry(mevt, &r->evt_list, list) {
-		domid = do_sum ? d->ci->id : d->hdr.id;
+		domid = do_sum ? d->ci_id : d->hdr.id;
 		priv = mon_get_kn_priv(r->rid, domid, mevt, do_sum);
 		if (WARN_ON_ONCE(!priv))
 			return -EINVAL;
@@ -3089,7 +3089,7 @@ static int mkdir_mondata_subdir(struct kernfs_node *parent_kn,
 	lockdep_assert_held(&rdtgroup_mutex);
 
 	snc_mode = r->mon_scope == RESCTRL_L3_NODE;
-	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci->id : d->hdr.id);
+	sprintf(name, "mon_%s_%02d", r->name, snc_mode ? d->ci_id : d->hdr.id);
 	kn = kernfs_find_and_get(parent_kn, name);
 	if (kn) {
 		/*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 9ba771f2ddea..6fb4894b8cfd 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -159,7 +159,7 @@ struct rdt_ctrl_domain {
 /**
  * struct rdt_mon_domain - group of CPUs sharing a resctrl monitor resource
  * @hdr:		common header for different domain types
- * @ci:			cache info for this domain
+ * @ci_id:		cache info id for this domain
  * @rmid_busy_llc:	bitmap of which limbo RMIDs are above threshold
  * @mbm_total:		saved state for MBM total bandwidth
  * @mbm_local:		saved state for MBM local bandwidth
@@ -170,7 +170,7 @@ struct rdt_ctrl_domain {
  */
 struct rdt_mon_domain {
 	struct rdt_domain_hdr		hdr;
-	struct cacheinfo		*ci;
+	unsigned int			ci_id;
 	unsigned long			*rmid_busy_llc;
 	struct mbm_state		*mbm_total;
 	struct mbm_state		*mbm_local;
-- 
cgit v1.2.3


From ae1ae11fb277f1335d6bcd4935ba0ea985af3c32 Mon Sep 17 00:00:00 2001
From: Richard Guy Briggs <rgb@redhat.com>
Date: Fri, 13 Jun 2025 15:58:00 -0400
Subject: audit,module: restore audit logging in load failure case

The move of the module sanity check to earlier skipped the audit logging
call in the case of failure and to a place where the previously used
context is unavailable.

Add an audit logging call for the module loading failure case and get
the module name when possible.

Link: https://issues.redhat.com/browse/RHEL-52839
Fixes: 02da2cbab452 ("module: move check_modinfo() early to early_mod_check()")
Signed-off-by: Richard Guy Briggs <rgb@redhat.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/audit.h | 9 ++++-----
 kernel/audit.h        | 2 +-
 kernel/auditsc.c      | 2 +-
 kernel/module/main.c  | 6 ++++--
 4 files changed, 10 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/audit.h b/include/linux/audit.h
index 0050ef288ab3..a394614ccd0b 100644
--- a/include/linux/audit.h
+++ b/include/linux/audit.h
@@ -417,7 +417,7 @@ extern int __audit_log_bprm_fcaps(struct linux_binprm *bprm,
 extern void __audit_log_capset(const struct cred *new, const struct cred *old);
 extern void __audit_mmap_fd(int fd, int flags);
 extern void __audit_openat2_how(struct open_how *how);
-extern void __audit_log_kern_module(char *name);
+extern void __audit_log_kern_module(const char *name);
 extern void __audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar);
 extern void __audit_tk_injoffset(struct timespec64 offset);
 extern void __audit_ntp_log(const struct audit_ntp_data *ad);
@@ -519,7 +519,7 @@ static inline void audit_openat2_how(struct open_how *how)
 		__audit_openat2_how(how);
 }
 
-static inline void audit_log_kern_module(char *name)
+static inline void audit_log_kern_module(const char *name)
 {
 	if (!audit_dummy_context())
 		__audit_log_kern_module(name);
@@ -677,9 +677,8 @@ static inline void audit_mmap_fd(int fd, int flags)
 static inline void audit_openat2_how(struct open_how *how)
 { }
 
-static inline void audit_log_kern_module(char *name)
-{
-}
+static inline void audit_log_kern_module(const char *name)
+{ }
 
 static inline void audit_fanotify(u32 response, struct fanotify_response_info_audit_rule *friar)
 { }
diff --git a/kernel/audit.h b/kernel/audit.h
index 0211cb307d30..2a24d01c5fb0 100644
--- a/kernel/audit.h
+++ b/kernel/audit.h
@@ -200,7 +200,7 @@ struct audit_context {
 			int			argc;
 		} execve;
 		struct {
-			char			*name;
+			const char		*name;
 		} module;
 		struct {
 			struct audit_ntp_data	ntp_data;
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 78fd876a5473..eb98cd6fe91f 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -2864,7 +2864,7 @@ void __audit_openat2_how(struct open_how *how)
 	context->type = AUDIT_OPENAT2;
 }
 
-void __audit_log_kern_module(char *name)
+void __audit_log_kern_module(const char *name)
 {
 	struct audit_context *context = audit_context();
 
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 413ac6ea3702..1ac487d2f7c4 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -3368,7 +3368,7 @@ static int load_module(struct load_info *info, const char __user *uargs,
 
 	module_allocated = true;
 
-	audit_log_kern_module(mod->name);
+	audit_log_kern_module(info->name);
 
 	/* Reserve our place in the list. */
 	err = add_unformed_module(mod);
@@ -3532,8 +3532,10 @@ static int load_module(struct load_info *info, const char __user *uargs,
 	 * failures once the proper module was allocated and
 	 * before that.
 	 */
-	if (!module_allocated)
+	if (!module_allocated) {
+		audit_log_kern_module(info->name ? info->name : "?");
 		mod_stat_bump_becoming(info, flags);
+	}
 	free_copy(info, flags);
 	return err;
 }
-- 
cgit v1.2.3


From 260948993a9f99428f801dcb40654205e74aaa47 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 13 Jun 2025 04:31:30 -0700
Subject: netpoll: remove __netpoll_cleanup from exported API

Since commit 97714695ef90 ("net: netconsole: Defer netpoll cleanup to
avoid lock release during list traversal"), netconsole no longer uses
__netpoll_cleanup(). With no remaining users, remove this function
from the exported netpoll API.

The function remains available internally within netpoll for use by
netpoll_cleanup().

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250613-rework-v3-1-0752bf2e6912@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netpoll.h | 1 -
 net/core/netpoll.c      | 3 +--
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 0477208ed9ff..a637e5115254 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -69,7 +69,6 @@ void netpoll_print_options(struct netpoll *np);
 int netpoll_parse_options(struct netpoll *np, char *opt);
 int __netpoll_setup(struct netpoll *np, struct net_device *ndev);
 int netpoll_setup(struct netpoll *np);
-void __netpoll_cleanup(struct netpoll *np);
 void __netpoll_free(struct netpoll *np);
 void netpoll_cleanup(struct netpoll *np);
 void do_netpoll_cleanup(struct netpoll *np);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 4ddb7490df4b..a69c2773841a 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -863,7 +863,7 @@ static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
 	kfree(npinfo);
 }
 
-void __netpoll_cleanup(struct netpoll *np)
+static void __netpoll_cleanup(struct netpoll *np)
 {
 	struct netpoll_info *npinfo;
 
@@ -885,7 +885,6 @@ void __netpoll_cleanup(struct netpoll *np)
 
 	skb_pool_flush(np);
 }
-EXPORT_SYMBOL_GPL(__netpoll_cleanup);
 
 void __netpoll_free(struct netpoll *np)
 {
-- 
cgit v1.2.3


From afb023329c07af7a9144901a1dad3a80d9e177b1 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 13 Jun 2025 04:31:31 -0700
Subject: netpoll: expose netpoll logging macros in public header

Move np_info(), np_err(), and np_notice() macros from internal
implementation to the public netpoll header file to make them
available for use by netpoll consumers.

These logging macros provide consistent formatting for netpoll-related
messages by automatically prefixing log output with the netpoll instance
name.

The goal is to use the exact same format that is being displayed today,
instead of creating something netconsole-specific.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250613-rework-v3-2-0752bf2e6912@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netpoll.h | 7 +++++++
 net/core/netpoll.c      | 7 -------
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index a637e5115254..72086b8a3dec 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -42,6 +42,13 @@ struct netpoll {
 	struct work_struct refill_wq;
 };
 
+#define np_info(np, fmt, ...)				\
+	pr_info("%s: " fmt, np->name, ##__VA_ARGS__)
+#define np_err(np, fmt, ...)				\
+	pr_err("%s: " fmt, np->name, ##__VA_ARGS__)
+#define np_notice(np, fmt, ...)				\
+	pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
+
 struct netpoll_info {
 	refcount_t refcnt;
 
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index a69c2773841a..9e86026225a3 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -58,13 +58,6 @@ static void zap_completion_queue(void);
 static unsigned int carrier_timeout = 4;
 module_param(carrier_timeout, uint, 0644);
 
-#define np_info(np, fmt, ...)				\
-	pr_info("%s: " fmt, np->name, ##__VA_ARGS__)
-#define np_err(np, fmt, ...)				\
-	pr_err("%s: " fmt, np->name, ##__VA_ARGS__)
-#define np_notice(np, fmt, ...)				\
-	pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
-
 static netdev_tx_t netpoll_start_xmit(struct sk_buff *skb,
 				      struct net_device *dev,
 				      struct netdev_queue *txq)
-- 
cgit v1.2.3


From 5a34c9a8536511b6bd43d85bb0211077226c6fdb Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 13 Jun 2025 04:31:32 -0700
Subject: netpoll: relocate netconsole-specific functions to netconsole module

Move netpoll_parse_ip_addr() and netpoll_parse_options() from the generic
netpoll module to the netconsole module where they are actually used.

These functions were originally placed in netpoll but are only consumed by
netconsole. This refactoring improves code organization by:

 - Removing unnecessary exported symbols from netpoll
 - Making netpoll_parse_options() static (no longer needs global visibility)
 - Reducing coupling between netpoll and netconsole modules

The functions remain functionally identical - this is purely a code
reorganization to better reflect their actual usage patterns. Here are
the changes:

 1) Move both functions from netpoll to netconsole
 2) Add static to netpoll_parse_options()
 3) Removed the EXPORT_SYMBOL()

PS: This diff does not change the function format, so, it is easy to
review, but, checkpatch will not be happy. A follow-up patch will
address the current issues reported by checkpatch.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250613-rework-v3-3-0752bf2e6912@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 108 ++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/netpoll.h  |   1 -
 net/core/netpoll.c       | 109 -----------------------------------------------
 3 files changed, 108 insertions(+), 110 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index 1eb678e07dd0..bc145e4cf6e7 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -1659,6 +1659,114 @@ static void write_msg(struct console *con, const char *msg, unsigned int len)
 	spin_unlock_irqrestore(&target_list_lock, flags);
 }
 
+static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr)
+{
+	const char *end;
+
+	if (!strchr(str, ':') &&
+	    in4_pton(str, -1, (void *)addr, -1, &end) > 0) {
+		if (!*end)
+			return 0;
+	}
+	if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) {
+#if IS_ENABLED(CONFIG_IPV6)
+		if (!*end)
+			return 1;
+#else
+		return -1;
+#endif
+	}
+	return -1;
+}
+
+static int netpoll_parse_options(struct netpoll *np, char *opt)
+{
+	char *cur=opt, *delim;
+	int ipv6;
+	bool ipversion_set = false;
+
+	if (*cur != '@') {
+		if ((delim = strchr(cur, '@')) == NULL)
+			goto parse_failed;
+		*delim = 0;
+		if (kstrtou16(cur, 10, &np->local_port))
+			goto parse_failed;
+		cur = delim;
+	}
+	cur++;
+
+	if (*cur != '/') {
+		ipversion_set = true;
+		if ((delim = strchr(cur, '/')) == NULL)
+			goto parse_failed;
+		*delim = 0;
+		ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip);
+		if (ipv6 < 0)
+			goto parse_failed;
+		else
+			np->ipv6 = (bool)ipv6;
+		cur = delim;
+	}
+	cur++;
+
+	if (*cur != ',') {
+		/* parse out dev_name or dev_mac */
+		if ((delim = strchr(cur, ',')) == NULL)
+			goto parse_failed;
+		*delim = 0;
+
+		np->dev_name[0] = '\0';
+		eth_broadcast_addr(np->dev_mac);
+		if (!strchr(cur, ':'))
+			strscpy(np->dev_name, cur, sizeof(np->dev_name));
+		else if (!mac_pton(cur, np->dev_mac))
+			goto parse_failed;
+
+		cur = delim;
+	}
+	cur++;
+
+	if (*cur != '@') {
+		/* dst port */
+		if ((delim = strchr(cur, '@')) == NULL)
+			goto parse_failed;
+		*delim = 0;
+		if (*cur == ' ' || *cur == '\t')
+			np_info(np, "warning: whitespace is not allowed\n");
+		if (kstrtou16(cur, 10, &np->remote_port))
+			goto parse_failed;
+		cur = delim;
+	}
+	cur++;
+
+	/* dst ip */
+	if ((delim = strchr(cur, '/')) == NULL)
+		goto parse_failed;
+	*delim = 0;
+	ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
+	if (ipv6 < 0)
+		goto parse_failed;
+	else if (ipversion_set && np->ipv6 != (bool)ipv6)
+		goto parse_failed;
+	else
+		np->ipv6 = (bool)ipv6;
+	cur = delim + 1;
+
+	if (*cur != 0) {
+		/* MAC address */
+		if (!mac_pton(cur, np->remote_mac))
+			goto parse_failed;
+	}
+
+	netpoll_print_options(np);
+
+	return 0;
+
+ parse_failed:
+	np_info(np, "couldn't parse config at '%s'!\n", cur);
+	return -1;
+}
+
 /* Allocate new target (from boot/module param) and setup netpoll for it */
 static struct netconsole_target *alloc_param_target(char *target_config,
 						    int cmdline_count)
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 72086b8a3dec..1b8000954e52 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -73,7 +73,6 @@ static inline void netpoll_poll_enable(struct net_device *dev) { return; }
 
 int netpoll_send_udp(struct netpoll *np, const char *msg, int len);
 void netpoll_print_options(struct netpoll *np);
-int netpoll_parse_options(struct netpoll *np, char *opt);
 int __netpoll_setup(struct netpoll *np, struct net_device *ndev);
 int netpoll_setup(struct netpoll *np);
 void __netpoll_free(struct netpoll *np);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 9e86026225a3..d2965c916130 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -510,26 +510,6 @@ void netpoll_print_options(struct netpoll *np)
 }
 EXPORT_SYMBOL(netpoll_print_options);
 
-static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr)
-{
-	const char *end;
-
-	if (!strchr(str, ':') &&
-	    in4_pton(str, -1, (void *)addr, -1, &end) > 0) {
-		if (!*end)
-			return 0;
-	}
-	if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) {
-#if IS_ENABLED(CONFIG_IPV6)
-		if (!*end)
-			return 1;
-#else
-		return -1;
-#endif
-	}
-	return -1;
-}
-
 static void skb_pool_flush(struct netpoll *np)
 {
 	struct sk_buff_head *skb_pool;
@@ -539,95 +519,6 @@ static void skb_pool_flush(struct netpoll *np)
 	skb_queue_purge_reason(skb_pool, SKB_CONSUMED);
 }
 
-int netpoll_parse_options(struct netpoll *np, char *opt)
-{
-	char *cur=opt, *delim;
-	int ipv6;
-	bool ipversion_set = false;
-
-	if (*cur != '@') {
-		if ((delim = strchr(cur, '@')) == NULL)
-			goto parse_failed;
-		*delim = 0;
-		if (kstrtou16(cur, 10, &np->local_port))
-			goto parse_failed;
-		cur = delim;
-	}
-	cur++;
-
-	if (*cur != '/') {
-		ipversion_set = true;
-		if ((delim = strchr(cur, '/')) == NULL)
-			goto parse_failed;
-		*delim = 0;
-		ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip);
-		if (ipv6 < 0)
-			goto parse_failed;
-		else
-			np->ipv6 = (bool)ipv6;
-		cur = delim;
-	}
-	cur++;
-
-	if (*cur != ',') {
-		/* parse out dev_name or dev_mac */
-		if ((delim = strchr(cur, ',')) == NULL)
-			goto parse_failed;
-		*delim = 0;
-
-		np->dev_name[0] = '\0';
-		eth_broadcast_addr(np->dev_mac);
-		if (!strchr(cur, ':'))
-			strscpy(np->dev_name, cur, sizeof(np->dev_name));
-		else if (!mac_pton(cur, np->dev_mac))
-			goto parse_failed;
-
-		cur = delim;
-	}
-	cur++;
-
-	if (*cur != '@') {
-		/* dst port */
-		if ((delim = strchr(cur, '@')) == NULL)
-			goto parse_failed;
-		*delim = 0;
-		if (*cur == ' ' || *cur == '\t')
-			np_info(np, "warning: whitespace is not allowed\n");
-		if (kstrtou16(cur, 10, &np->remote_port))
-			goto parse_failed;
-		cur = delim;
-	}
-	cur++;
-
-	/* dst ip */
-	if ((delim = strchr(cur, '/')) == NULL)
-		goto parse_failed;
-	*delim = 0;
-	ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
-	if (ipv6 < 0)
-		goto parse_failed;
-	else if (ipversion_set && np->ipv6 != (bool)ipv6)
-		goto parse_failed;
-	else
-		np->ipv6 = (bool)ipv6;
-	cur = delim + 1;
-
-	if (*cur != 0) {
-		/* MAC address */
-		if (!mac_pton(cur, np->remote_mac))
-			goto parse_failed;
-	}
-
-	netpoll_print_options(np);
-
-	return 0;
-
- parse_failed:
-	np_info(np, "couldn't parse config at '%s'!\n", cur);
-	return -1;
-}
-EXPORT_SYMBOL(netpoll_parse_options);
-
 static void refill_skbs_work_handler(struct work_struct *work)
 {
 	struct netpoll *np =
-- 
cgit v1.2.3


From ccc7edf0ada83d395b634506eff9616360a99b5a Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Fri, 13 Jun 2025 04:31:33 -0700
Subject: netpoll: move netpoll_print_options to netconsole

Move netpoll_print_options() from net/core/netpoll.c to
drivers/net/netconsole.c and make it static. This function is only used
by netconsole, so there's no need to export it or keep it in the public
netpoll API.

This reduces the netpoll API surface and improves code locality
by keeping netconsole-specific functionality within the netconsole
driver.

Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250613-rework-v3-4-0752bf2e6912@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/netconsole.c | 17 +++++++++++++++++
 include/linux/netpoll.h  |  1 -
 net/core/netpoll.c       | 17 -----------------
 3 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
index bc145e4cf6e7..71522fb0eeee 100644
--- a/drivers/net/netconsole.c
+++ b/drivers/net/netconsole.c
@@ -278,6 +278,23 @@ static void netconsole_process_cleanups_core(void)
 	mutex_unlock(&target_cleanup_list_lock);
 }
 
+static void netpoll_print_options(struct netpoll *np)
+{
+	np_info(np, "local port %d\n", np->local_port);
+	if (np->ipv6)
+		np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
+	else
+		np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
+	np_info(np, "interface name '%s'\n", np->dev_name);
+	np_info(np, "local ethernet address '%pM'\n", np->dev_mac);
+	np_info(np, "remote port %d\n", np->remote_port);
+	if (np->ipv6)
+		np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
+	else
+		np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip);
+	np_info(np, "remote ethernet address %pM\n", np->remote_mac);
+}
+
 #ifdef	CONFIG_NETCONSOLE_DYNAMIC
 
 /*
diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 1b8000954e52..735e65c3cc11 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -72,7 +72,6 @@ static inline void netpoll_poll_enable(struct net_device *dev) { return; }
 #endif
 
 int netpoll_send_udp(struct netpoll *np, const char *msg, int len);
-void netpoll_print_options(struct netpoll *np);
 int __netpoll_setup(struct netpoll *np, struct net_device *ndev);
 int netpoll_setup(struct netpoll *np);
 void __netpoll_free(struct netpoll *np);
diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index d2965c916130..07c453864a7d 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -492,23 +492,6 @@ int netpoll_send_udp(struct netpoll *np, const char *msg, int len)
 }
 EXPORT_SYMBOL(netpoll_send_udp);
 
-void netpoll_print_options(struct netpoll *np)
-{
-	np_info(np, "local port %d\n", np->local_port);
-	if (np->ipv6)
-		np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
-	else
-		np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
-	np_info(np, "interface name '%s'\n", np->dev_name);
-	np_info(np, "local ethernet address '%pM'\n", np->dev_mac);
-	np_info(np, "remote port %d\n", np->remote_port);
-	if (np->ipv6)
-		np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
-	else
-		np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip);
-	np_info(np, "remote ethernet address %pM\n", np->remote_mac);
-}
-EXPORT_SYMBOL(netpoll_print_options);
 
 static void skb_pool_flush(struct netpoll *np)
 {
-- 
cgit v1.2.3


From 25d51ebf0f54f9c2424f28bb29125cf24f120df0 Mon Sep 17 00:00:00 2001
From: Subbaraya Sundeep <sbhatta@marvell.com>
Date: Wed, 11 Jun 2025 16:31:51 +0530
Subject: octeontx2: Set appropriate PF, VF masks and shifts based on silicon

Number of RVU PFs on CN20K silicon have increased to 96 from maximum
of 32 that were supported on earlier silicons. Every RVU PF and VF is
identified by HW using a 16bit PF_FUNC value. Due to the change in
Max number of PFs in CN20K, the bit encoding of this PF_FUNC has changed.

This patch handles the change by using helper functions(using silicon
check) to use PF,VF masks and shifts to support both new silicon CN20K,
OcteonTx series. These helper functions are used in different modules.

Also moved the NIX AF register offset macros to other files which
will be posted in coming patches.

Signed-off-by: Subbaraya Sundeep <sbhatta@marvell.com>
Signed-off-by: Sai Krishna <saikrishnag@marvell.com>
Signed-off-by: Sunil Kovvuri Goutham <sgoutham@marvell.com>
Link: https://patch.msgid.link/1749639716-13868-2-git-send-email-sbhatta@marvell.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/crypto/marvell/octeontx2/otx2_cpt_common.h |  5 +-
 drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c | 13 ++---
 .../crypto/marvell/octeontx2/otx2_cptpf_ucode.c    |  4 +-
 drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c |  6 +-
 .../net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c |  6 +-
 drivers/net/ethernet/marvell/octeontx2/af/rvu.c    | 30 ++++------
 drivers/net/ethernet/marvell/octeontx2/af/rvu.h    | 52 ++++++++++++++---
 .../net/ethernet/marvell/octeontx2/af/rvu_cgx.c    | 68 +++++++++++-----------
 .../net/ethernet/marvell/octeontx2/af/rvu_cn10k.c  |  4 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_cpt.c    |  4 +-
 .../ethernet/marvell/octeontx2/af/rvu_debugfs.c    | 22 +++----
 .../net/ethernet/marvell/octeontx2/af/rvu_nix.c    | 54 +++++++++--------
 .../net/ethernet/marvell/octeontx2/af/rvu_npc.c    |  8 ++-
 .../ethernet/marvell/octeontx2/af/rvu_npc_hash.c   | 16 ++---
 .../ethernet/marvell/octeontx2/af/rvu_npc_hash.h   |  4 +-
 .../net/ethernet/marvell/octeontx2/af/rvu_rep.c    | 13 ++---
 .../net/ethernet/marvell/octeontx2/af/rvu_sdp.c    | 10 ++--
 .../net/ethernet/marvell/octeontx2/af/rvu_switch.c |  8 +--
 .../ethernet/marvell/octeontx2/nic/cn10k_ipsec.c   |  2 +-
 .../ethernet/marvell/octeontx2/nic/cn10k_ipsec.h   |  2 +-
 .../ethernet/marvell/octeontx2/nic/otx2_common.h   | 11 +---
 .../net/ethernet/marvell/octeontx2/nic/otx2_pf.c   | 21 ++++---
 .../net/ethernet/marvell/octeontx2/nic/otx2_reg.h  | 30 ----------
 .../net/ethernet/marvell/octeontx2/nic/otx2_tc.c   |  3 +-
 drivers/net/ethernet/marvell/octeontx2/nic/rep.c   |  7 ++-
 include/linux/soc/marvell/silicons.h               | 25 ++++++++
 26 files changed, 225 insertions(+), 203 deletions(-)
 create mode 100644 include/linux/soc/marvell/silicons.h

(limited to 'include/linux')

diff --git a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h
index d529bcb03775..062def303dce 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h
+++ b/drivers/crypto/marvell/octeontx2/otx2_cpt_common.h
@@ -18,9 +18,8 @@
 #define OTX2_CPT_MAX_VFS_NUM 128
 #define OTX2_CPT_RVU_FUNC_ADDR_S(blk, slot, offs) \
 		(((blk) << 20) | ((slot) << 12) | (offs))
-#define OTX2_CPT_RVU_PFFUNC(pf, func)	\
-		((((pf) & RVU_PFVF_PF_MASK) << RVU_PFVF_PF_SHIFT) | \
-		(((func) & RVU_PFVF_FUNC_MASK) << RVU_PFVF_FUNC_SHIFT))
+
+#define OTX2_CPT_RVU_PFFUNC(pdev, pf, func) rvu_make_pcifunc(pdev, pf, func)
 
 #define OTX2_CPT_INVALID_CRYPTO_ENG_GRP 0xFF
 #define OTX2_CPT_NAME_LENGTH 64
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c
index 12c0e966fa65..b4b2d3d1cbc2 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_mbox.c
@@ -142,7 +142,7 @@ static int send_inline_ipsec_inbound_msg(struct otx2_cptpf_dev *cptpf,
 	memset(req, 0, sizeof(*req));
 	req->hdr.id = MBOX_MSG_CPT_INLINE_IPSEC_CFG;
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;
-	req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptpf->pf_id, 0);
+	req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptpf->pdev, cptpf->pf_id, 0);
 	req->dir = CPT_INLINE_INBOUND;
 	req->slot = slot;
 	req->sso_pf_func_ovrd = cptpf->sso_pf_func_ovrd;
@@ -184,7 +184,8 @@ static int rx_inline_ipsec_lf_cfg(struct otx2_cptpf_dev *cptpf, u8 egrp,
 		nix_req->gen_cfg.opcode = cpt_inline_rx_opcode(pdev);
 	nix_req->gen_cfg.param1 = req->param1;
 	nix_req->gen_cfg.param2 = req->param2;
-	nix_req->inst_qsel.cpt_pf_func = OTX2_CPT_RVU_PFFUNC(cptpf->pf_id, 0);
+	nix_req->inst_qsel.cpt_pf_func =
+		OTX2_CPT_RVU_PFFUNC(cptpf->pdev, cptpf->pf_id, 0);
 	nix_req->inst_qsel.cpt_slot = 0;
 	ret = otx2_cpt_send_mbox_msg(&cptpf->afpf_mbox, pdev);
 	if (ret)
@@ -392,9 +393,8 @@ void otx2_cptpf_vfpf_mbox_handler(struct work_struct *work)
 		msg = (struct mbox_msghdr *)(mdev->mbase + offset);
 
 		/* Set which VF sent this message based on mbox IRQ */
-		msg->pcifunc = ((u16)cptpf->pf_id << RVU_PFVF_PF_SHIFT) |
-				((vf->vf_id + 1) & RVU_PFVF_FUNC_MASK);
-
+		msg->pcifunc = rvu_make_pcifunc(cptpf->pdev, cptpf->pf_id,
+						(vf->vf_id + 1));
 		err = cptpf_handle_vf_req(cptpf, vf, msg,
 					  msg->next_msgoff - offset);
 		/*
@@ -469,8 +469,7 @@ static void process_afpf_mbox_msg(struct otx2_cptpf_dev *cptpf,
 
 	switch (msg->id) {
 	case MBOX_MSG_READY:
-		cptpf->pf_id = (msg->pcifunc >> RVU_PFVF_PF_SHIFT) &
-				RVU_PFVF_PF_MASK;
+		cptpf->pf_id = rvu_get_pf(cptpf->pdev, msg->pcifunc);
 		break;
 	case MBOX_MSG_MSIX_OFFSET:
 		rsp_msix = (struct msix_offset_rsp *) msg;
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
index 78367849c3d5..7180944ece50 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptpf_ucode.c
@@ -176,7 +176,9 @@ static int cptx_set_ucode_base(struct otx2_cpt_eng_grp_info *eng_grp,
 	/* Set PF number for microcode fetches */
 	ret = otx2_cpt_write_af_reg(&cptpf->afpf_mbox, cptpf->pdev,
 				    CPT_AF_PF_FUNC,
-				    cptpf->pf_id << RVU_PFVF_PF_SHIFT, blkaddr);
+				    rvu_make_pcifunc(cptpf->pdev,
+						     cptpf->pf_id, 0),
+				    blkaddr);
 	if (ret)
 		return ret;
 
diff --git a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c
index 931b72580fd9..92e49babd79a 100644
--- a/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c
+++ b/drivers/crypto/marvell/octeontx2/otx2_cptvf_mbox.c
@@ -189,7 +189,7 @@ int otx2_cptvf_send_eng_grp_num_msg(struct otx2_cptvf_dev *cptvf, int eng_type)
 	}
 	req->hdr.id = MBOX_MSG_GET_ENG_GRP_NUM;
 	req->hdr.sig = OTX2_MBOX_REQ_SIG;
-	req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0);
+	req->hdr.pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0);
 	req->eng_type = eng_type;
 
 	return otx2_cpt_send_mbox_msg(mbox, pdev);
@@ -210,7 +210,7 @@ int otx2_cptvf_send_kvf_limits_msg(struct otx2_cptvf_dev *cptvf)
 	}
 	req->id = MBOX_MSG_GET_KVF_LIMITS;
 	req->sig = OTX2_MBOX_REQ_SIG;
-	req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0);
+	req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0);
 
 	return otx2_cpt_send_mbox_msg(mbox, pdev);
 }
@@ -230,7 +230,7 @@ int otx2_cptvf_send_caps_msg(struct otx2_cptvf_dev *cptvf)
 	}
 	req->id = MBOX_MSG_GET_CAPS;
 	req->sig = OTX2_MBOX_REQ_SIG;
-	req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->vf_id, 0);
+	req->pcifunc = OTX2_CPT_RVU_PFFUNC(cptvf->pdev, cptvf->vf_id, 0);
 
 	return otx2_cpt_send_mbox_msg(mbox, pdev);
 }
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
index 0277d226293e..d7030dfa5dad 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/mcs_rvu_if.c
@@ -97,7 +97,7 @@ int mcs_add_intr_wq_entry(struct mcs *mcs, struct mcs_intr_event *event)
 	if (pcifunc & RVU_PFVF_FUNC_MASK)
 		pfvf = &mcs->vf[rvu_get_hwvf(rvu, pcifunc)];
 	else
-		pfvf = &mcs->pf[rvu_get_pf(pcifunc)];
+		pfvf = &mcs->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 
 	event->intr_mask &= pfvf->intr_mask;
 
@@ -123,7 +123,7 @@ static int mcs_notify_pfvf(struct mcs_intr_event *event, struct rvu *rvu)
 	struct mcs_intr_info *req;
 	int pf;
 
-	pf = rvu_get_pf(event->pcifunc);
+	pf = rvu_get_pf(rvu->pdev, event->pcifunc);
 
 	mutex_lock(&rvu->mbox_lock);
 
@@ -193,7 +193,7 @@ int rvu_mbox_handler_mcs_intr_cfg(struct rvu *rvu,
 	if (pcifunc & RVU_PFVF_FUNC_MASK)
 		pfvf = &mcs->vf[rvu_get_hwvf(rvu, pcifunc)];
 	else
-		pfvf = &mcs->pf[rvu_get_pf(pcifunc)];
+		pfvf = &mcs->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 
 	mcs->pf_map[0] = pcifunc;
 	pfvf->intr_mask = req->intr_mask;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
index 43eea74bf541..61d80a2277f0 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.c
@@ -294,7 +294,7 @@ int rvu_get_blkaddr(struct rvu *rvu, int blktype, u16 pcifunc)
 		devnum = rvu_get_hwvf(rvu, pcifunc);
 	} else {
 		is_pf = true;
-		devnum = rvu_get_pf(pcifunc);
+		devnum = rvu_get_pf(rvu->pdev, pcifunc);
 	}
 
 	/* Check if the 'pcifunc' has a NIX LF from 'BLKADDR_NIX0' or
@@ -359,7 +359,7 @@ static void rvu_update_rsrc_map(struct rvu *rvu, struct rvu_pfvf *pfvf,
 		devnum = rvu_get_hwvf(rvu, pcifunc);
 	} else {
 		is_pf = true;
-		devnum = rvu_get_pf(pcifunc);
+		devnum = rvu_get_pf(rvu->pdev, pcifunc);
 	}
 
 	block->fn_map[lf] = attach ? pcifunc : 0;
@@ -400,11 +400,6 @@ static void rvu_update_rsrc_map(struct rvu *rvu, struct rvu_pfvf *pfvf,
 	rvu_write64(rvu, BLKADDR_RVUM, reg | (devnum << 16), num_lfs);
 }
 
-inline int rvu_get_pf(u16 pcifunc)
-{
-	return (pcifunc >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
-}
-
 void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf)
 {
 	u64 cfg;
@@ -422,7 +417,7 @@ int rvu_get_hwvf(struct rvu *rvu, int pcifunc)
 	int pf, func;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	func = pcifunc & RVU_PFVF_FUNC_MASK;
 
 	/* Get first HWVF attached to this PF */
@@ -437,7 +432,7 @@ struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc)
 	if (pcifunc & RVU_PFVF_FUNC_MASK)
 		return &rvu->hwvf[rvu_get_hwvf(rvu, pcifunc)];
 	else
-		return &rvu->pf[rvu_get_pf(pcifunc)];
+		return &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 }
 
 static bool is_pf_func_valid(struct rvu *rvu, u16 pcifunc)
@@ -445,7 +440,7 @@ static bool is_pf_func_valid(struct rvu *rvu, u16 pcifunc)
 	int pf, vf, nvfs;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (pf >= rvu->hw->total_pfs)
 		return false;
 
@@ -1487,7 +1482,7 @@ int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
 	pf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
 
 	/* All CGX mapped PFs are set with assigned NIX block during init */
-	if (is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
+	if (is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) {
 		blkaddr = pf->nix_blkaddr;
 	} else if (is_lbk_vf(rvu, pcifunc)) {
 		vf = pcifunc - 1;
@@ -1501,7 +1496,7 @@ int rvu_get_nix_blkaddr(struct rvu *rvu, u16 pcifunc)
 	}
 
 	/* if SDP1 then the blkaddr is NIX1 */
-	if (is_sdp_pfvf(pcifunc) && pf->sdp_info->node_id == 1)
+	if (is_sdp_pfvf(rvu, pcifunc) && pf->sdp_info->node_id == 1)
 		blkaddr = BLKADDR_NIX1;
 
 	switch (blkaddr) {
@@ -2006,7 +2001,7 @@ int rvu_mbox_handler_vf_flr(struct rvu *rvu, struct msg_req *req,
 
 	vf = pcifunc & RVU_PFVF_FUNC_MASK;
 	cfg = rvu_read64(rvu, BLKADDR_RVUM,
-			 RVU_PRIV_PFX_CFG(rvu_get_pf(pcifunc)));
+			 RVU_PRIV_PFX_CFG(rvu_get_pf(rvu->pdev, pcifunc)));
 	numvfs = (cfg >> 12) & 0xFF;
 
 	if (vf && vf <= numvfs)
@@ -2229,9 +2224,8 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll)
 		/* Set which PF/VF sent this message based on mbox IRQ */
 		switch (type) {
 		case TYPE_AFPF:
-			msg->pcifunc &=
-				~(RVU_PFVF_PF_MASK << RVU_PFVF_PF_SHIFT);
-			msg->pcifunc |= (devid << RVU_PFVF_PF_SHIFT);
+			msg->pcifunc &= rvu_pcifunc_pf_mask(rvu->pdev);
+			msg->pcifunc |= rvu_make_pcifunc(rvu->pdev, devid, 0);
 			break;
 		case TYPE_AFVF:
 			msg->pcifunc &=
@@ -2249,7 +2243,7 @@ static void __rvu_mbox_handler(struct rvu_work *mwork, int type, bool poll)
 		if (msg->pcifunc & RVU_PFVF_FUNC_MASK)
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d:VF%d\n",
 				 err, otx2_mbox_id2name(msg->id),
-				 msg->id, rvu_get_pf(msg->pcifunc),
+				 msg->id, rvu_get_pf(rvu->pdev, msg->pcifunc),
 				 (msg->pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 		else
 			dev_warn(rvu->dev, "Error %d when processing message %s (0x%x) from PF%d\n",
@@ -2773,7 +2767,7 @@ static void rvu_flr_handler(struct work_struct *work)
 
 	cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
 	numvfs = (cfg >> 12) & 0xFF;
-	pcifunc  = pf << RVU_PFVF_PF_SHIFT;
+	pcifunc  = rvu_make_pcifunc(rvu->pdev, pf, 0);
 
 	for (vf = 0; vf < numvfs; vf++)
 		__rvu_flr_handler(rvu, (pcifunc | (vf + 1)));
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
index 48f66292ad5c..5c179df1f167 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
@@ -10,6 +10,7 @@
 
 #include <linux/pci.h>
 #include <net/devlink.h>
+#include <linux/soc/marvell/silicons.h>
 
 #include "rvu_struct.h"
 #include "rvu_devlink.h"
@@ -43,10 +44,34 @@
 #define MAX_CPT_BLKS				2
 
 /* PF_FUNC */
-#define RVU_PFVF_PF_SHIFT	10
-#define RVU_PFVF_PF_MASK	0x3F
-#define RVU_PFVF_FUNC_SHIFT	0
-#define RVU_PFVF_FUNC_MASK	0x3FF
+#define RVU_OTX2_PFVF_PF_SHIFT			10
+#define RVU_OTX2_PFVF_PF_MASK			0x3F
+#define RVU_PFVF_FUNC_SHIFT			0
+#define RVU_PFVF_FUNC_MASK			0x3FF
+#define RVU_CN20K_PFVF_PF_SHIFT			9
+#define RVU_CN20K_PFVF_PF_MASK			0x7F
+
+static inline u16 rvu_make_pcifunc(struct pci_dev *pdev, int pf, int func)
+{
+	if (is_cn20k(pdev))
+		return ((pf & RVU_CN20K_PFVF_PF_MASK) <<
+			RVU_CN20K_PFVF_PF_SHIFT) |
+			((func & RVU_PFVF_FUNC_MASK) <<
+			RVU_PFVF_FUNC_SHIFT);
+	else
+		return ((pf & RVU_OTX2_PFVF_PF_MASK) <<
+			RVU_OTX2_PFVF_PF_SHIFT) |
+			((func & RVU_PFVF_FUNC_MASK) <<
+			RVU_PFVF_FUNC_SHIFT);
+}
+
+static inline int rvu_pcifunc_pf_mask(struct pci_dev *pdev)
+{
+	if (is_cn20k(pdev))
+		return ~(RVU_CN20K_PFVF_PF_MASK << RVU_CN20K_PFVF_PF_SHIFT);
+	else
+		return ~(RVU_OTX2_PFVF_PF_MASK << RVU_OTX2_PFVF_PF_SHIFT);
+}
 
 #ifdef CONFIG_DEBUG_FS
 struct dump_ctx {
@@ -836,7 +861,6 @@ int rvu_alloc_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc);
 void rvu_free_rsrc_contig(struct rsrc_bmap *rsrc, int nrsrc, int start);
 bool rvu_rsrc_check_contig(struct rsrc_bmap *rsrc, int nrsrc);
 u16 rvu_get_rsrc_mapcount(struct rvu_pfvf *pfvf, int blkaddr);
-int rvu_get_pf(u16 pcifunc);
 struct rvu_pfvf *rvu_get_pfvf(struct rvu *rvu, int pcifunc);
 void rvu_get_pf_numvfs(struct rvu *rvu, int pf, int *numvfs, int *hwvf);
 bool is_block_implemented(struct rvu_hwinfo *hw, int blkaddr);
@@ -865,8 +889,8 @@ void rvu_aq_free(struct rvu *rvu, struct admin_queue *aq);
 
 /* SDP APIs */
 int rvu_sdp_init(struct rvu *rvu);
-bool is_sdp_pfvf(u16 pcifunc);
-bool is_sdp_pf(u16 pcifunc);
+bool is_sdp_pfvf(struct rvu *rvu, u16 pcifunc);
+bool is_sdp_pf(struct rvu *rvu, u16 pcifunc);
 bool is_sdp_vf(struct rvu *rvu, u16 pcifunc);
 
 static inline bool is_rep_dev(struct rvu *rvu, u16 pcifunc)
@@ -877,11 +901,21 @@ static inline bool is_rep_dev(struct rvu *rvu, u16 pcifunc)
 	return false;
 }
 
+static inline int rvu_get_pf(struct pci_dev *pdev, u16 pcifunc)
+{
+	if (is_cn20k(pdev))
+		return (pcifunc >> RVU_CN20K_PFVF_PF_SHIFT) &
+			RVU_CN20K_PFVF_PF_MASK;
+	else
+		return (pcifunc >> RVU_OTX2_PFVF_PF_SHIFT) &
+			RVU_OTX2_PFVF_PF_MASK;
+}
+
 /* CGX APIs */
 static inline bool is_pf_cgxmapped(struct rvu *rvu, u8 pf)
 {
 	return (pf >= PF_CGXMAP_BASE && pf <= rvu->cgx_mapped_pfs) &&
-		!is_sdp_pf(pf << RVU_PFVF_PF_SHIFT);
+		!is_sdp_pf(rvu, rvu_make_pcifunc(rvu->pdev, pf, 0));
 }
 
 static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id)
@@ -893,7 +927,7 @@ static inline void rvu_get_cgx_lmac_id(u8 map, u8 *cgx_id, u8 *lmac_id)
 static inline bool is_cgx_vf(struct rvu *rvu, u16 pcifunc)
 {
 	return ((pcifunc & RVU_PFVF_FUNC_MASK) &&
-		is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)));
+		is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)));
 }
 
 #define M(_name, _id, fn_name, req, rsp)				\
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
index d0331b0e0bfd..b79db887ab9b 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cgx.c
@@ -457,7 +457,7 @@ int rvu_cgx_exit(struct rvu *rvu)
 inline bool is_cgx_config_permitted(struct rvu *rvu, u16 pcifunc)
 {
 	if ((pcifunc & RVU_PFVF_FUNC_MASK) ||
-	    !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)))
+	    !is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)))
 		return false;
 	return true;
 }
@@ -484,7 +484,7 @@ void rvu_cgx_enadis_rx_bp(struct rvu *rvu, int pf, bool enable)
 
 int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	void *cgxd;
@@ -501,7 +501,7 @@ int rvu_cgx_config_rxtx(struct rvu *rvu, u16 pcifunc, bool start)
 
 int rvu_cgx_tx_enable(struct rvu *rvu, u16 pcifunc, bool enable)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	void *cgxd;
@@ -526,7 +526,7 @@ int rvu_cgx_config_tx(void *cgxd, int lmac_id, bool enable)
 
 void rvu_cgx_disable_dmac_entries(struct rvu *rvu, u16 pcifunc)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	int i = 0, lmac_count = 0;
 	struct mac_ops *mac_ops;
 	u8 max_dmac_filters;
@@ -577,7 +577,7 @@ int rvu_mbox_handler_cgx_stop_rxtx(struct rvu *rvu, struct msg_req *req,
 static int rvu_lmac_get_stats(struct rvu *rvu, struct msg_req *req,
 			      void *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct mac_ops *mac_ops;
 	int stat = 0, err = 0;
 	u64 tx_stat, rx_stat;
@@ -633,7 +633,7 @@ int rvu_mbox_handler_rpm_stats(struct rvu *rvu, struct msg_req *req,
 int rvu_mbox_handler_cgx_stats_rst(struct rvu *rvu, struct msg_req *req,
 				   struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct rvu_pfvf	*parent_pf;
 	struct mac_ops *mac_ops;
 	u8 cgx_idx, lmac;
@@ -663,7 +663,7 @@ int rvu_mbox_handler_cgx_fec_stats(struct rvu *rvu,
 				   struct msg_req *req,
 				   struct cgx_fec_stats_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_idx, lmac;
 	void *cgxd;
@@ -681,7 +681,7 @@ int rvu_mbox_handler_cgx_mac_addr_set(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -701,7 +701,7 @@ int rvu_mbox_handler_cgx_mac_addr_add(struct rvu *rvu,
 				      struct cgx_mac_addr_add_req *req,
 				      struct cgx_mac_addr_add_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 	int rc = 0;
 
@@ -725,7 +725,7 @@ int rvu_mbox_handler_cgx_mac_addr_del(struct rvu *rvu,
 				      struct cgx_mac_addr_del_req *req,
 				      struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -743,7 +743,7 @@ int rvu_mbox_handler_cgx_mac_max_entries_get(struct rvu *rvu,
 					     struct cgx_max_dmac_entries_get_rsp
 					     *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	/* If msg is received from PFs(which are not mapped to CGX LMACs)
@@ -769,7 +769,7 @@ int rvu_mbox_handler_cgx_mac_addr_get(struct rvu *rvu,
 				      struct cgx_mac_addr_set_or_get *req,
 				      struct cgx_mac_addr_set_or_get *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 	int rc = 0;
 	u64 cfg;
@@ -790,7 +790,7 @@ int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req,
 					struct msg_rsp *rsp)
 {
 	u16 pcifunc = req->hdr.pcifunc;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -809,7 +809,7 @@ int rvu_mbox_handler_cgx_promisc_enable(struct rvu *rvu, struct msg_req *req,
 int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req,
 					 struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -828,7 +828,7 @@ int rvu_mbox_handler_cgx_promisc_disable(struct rvu *rvu, struct msg_req *req,
 static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	void *cgxd;
@@ -864,7 +864,7 @@ static int rvu_cgx_ptp_rx_cfg(struct rvu *rvu, u16 pcifunc, bool enable)
 int rvu_mbox_handler_cgx_ptp_rx_enable(struct rvu *rvu, struct msg_req *req,
 				       struct msg_rsp *rsp)
 {
-	if (!is_pf_cgxmapped(rvu, rvu_get_pf(req->hdr.pcifunc)))
+	if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, req->hdr.pcifunc)))
 		return -EPERM;
 
 	return rvu_cgx_ptp_rx_cfg(rvu, req->hdr.pcifunc, true);
@@ -878,7 +878,7 @@ int rvu_mbox_handler_cgx_ptp_rx_disable(struct rvu *rvu, struct msg_req *req,
 
 static int rvu_cgx_config_linkevents(struct rvu *rvu, u16 pcifunc, bool en)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, pcifunc))
@@ -917,7 +917,7 @@ int rvu_mbox_handler_cgx_get_linkinfo(struct rvu *rvu, struct msg_req *req,
 	u8 cgx_id, lmac_id;
 	int pf, err;
 
-	pf = rvu_get_pf(req->hdr.pcifunc);
+	pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 
 	if (!is_pf_cgxmapped(rvu, pf))
 		return -ENODEV;
@@ -933,7 +933,7 @@ int rvu_mbox_handler_cgx_features_get(struct rvu *rvu,
 				      struct msg_req *req,
 				      struct cgx_features_info_msg *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_idx, lmac;
 	void *cgxd;
 
@@ -975,7 +975,7 @@ u32 rvu_cgx_get_lmac_fifolen(struct rvu *rvu, int cgx, int lmac)
 
 static int rvu_cgx_config_intlbk(struct rvu *rvu, u16 pcifunc, bool en)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 
@@ -1005,7 +1005,7 @@ int rvu_mbox_handler_cgx_intlbk_disable(struct rvu *rvu, struct msg_req *req,
 
 int rvu_cgx_cfg_pause_frm(struct rvu *rvu, u16 pcifunc, u8 tx_pause, u8 rx_pause)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 rx_pfc = 0, tx_pfc = 0;
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
@@ -1046,7 +1046,7 @@ int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu,
 				       struct cgx_pause_frm_cfg *req,
 				       struct cgx_pause_frm_cfg *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	int err = 0;
@@ -1073,7 +1073,7 @@ int rvu_mbox_handler_cgx_cfg_pause_frm(struct rvu *rvu,
 int rvu_mbox_handler_cgx_get_phy_fec_stats(struct rvu *rvu, struct msg_req *req,
 					   struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_pf_cgxmapped(rvu, pf))
@@ -1106,7 +1106,7 @@ int rvu_cgx_nix_cuml_stats(struct rvu *rvu, void *cgxd, int lmac_id,
 	/* Assumes LF of a PF and all of its VF belongs to the same
 	 * NIX block
 	 */
-	pcifunc = pf << RVU_PFVF_PF_SHIFT;
+	pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 	blkaddr = rvu_get_blkaddr(rvu, BLKTYPE_NIX, pcifunc);
 	if (blkaddr < 0)
 		return 0;
@@ -1133,10 +1133,10 @@ int rvu_cgx_start_stop_io(struct rvu *rvu, u16 pcifunc, bool start)
 	struct rvu_pfvf *parent_pf, *pfvf;
 	int cgx_users, err = 0;
 
-	if (!is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)))
+	if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)))
 		return 0;
 
-	parent_pf = &rvu->pf[rvu_get_pf(pcifunc)];
+	parent_pf = &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 	pfvf = rvu_get_pfvf(rvu, pcifunc);
 
 	mutex_lock(&rvu->cgx_cfg_lock);
@@ -1179,7 +1179,7 @@ int rvu_mbox_handler_cgx_set_fec_param(struct rvu *rvu,
 				       struct fec_mode *req,
 				       struct fec_mode *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_pf_cgxmapped(rvu, pf))
@@ -1195,7 +1195,7 @@ int rvu_mbox_handler_cgx_set_fec_param(struct rvu *rvu,
 int rvu_mbox_handler_cgx_get_aux_link_info(struct rvu *rvu, struct msg_req *req,
 					   struct cgx_fw_data *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!rvu->fwdata)
@@ -1222,7 +1222,7 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu,
 				       struct cgx_set_link_mode_req *req,
 				       struct cgx_set_link_mode_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_idx, lmac;
 	void *cgxd;
 
@@ -1238,7 +1238,7 @@ int rvu_mbox_handler_cgx_set_link_mode(struct rvu *rvu,
 int rvu_mbox_handler_cgx_mac_addr_reset(struct rvu *rvu, struct cgx_mac_addr_reset_req *req,
 					struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -1256,7 +1256,7 @@ int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu,
 					 struct cgx_mac_addr_update_req *req,
 					 struct cgx_mac_addr_update_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u8 cgx_id, lmac_id;
 
 	if (!is_cgx_config_permitted(rvu, req->hdr.pcifunc))
@@ -1272,7 +1272,7 @@ int rvu_mbox_handler_cgx_mac_addr_update(struct rvu *rvu,
 int rvu_cgx_prio_flow_ctrl_cfg(struct rvu *rvu, u16 pcifunc, u8 tx_pause,
 			       u8 rx_pause, u16 pfc_en)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 rx_8023 = 0, tx_8023 = 0;
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
@@ -1310,7 +1310,7 @@ int rvu_mbox_handler_cgx_prio_flow_ctrl_cfg(struct rvu *rvu,
 					    struct cgx_pfc_cfg *req,
 					    struct cgx_pfc_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	void *cgxd;
@@ -1335,7 +1335,7 @@ int rvu_mbox_handler_cgx_prio_flow_ctrl_cfg(struct rvu *rvu,
 
 void rvu_mac_reset(struct rvu *rvu, u16 pcifunc)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	struct cgx *cgxd;
 	u8 cgx, lmac;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
index 4a3370a40dd8..05adc54535eb 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cn10k.c
@@ -66,7 +66,7 @@ static int lmtst_map_table_ops(struct rvu *rvu, u32 index, u64 *val,
 #define LMT_MAP_TBL_W1_OFF  8
 static u32 rvu_get_lmtst_tbl_index(struct rvu *rvu, u16 pcifunc)
 {
-	return ((rvu_get_pf(pcifunc) * LMT_MAX_VFS) +
+	return ((rvu_get_pf(rvu->pdev, pcifunc) * LMT_MAX_VFS) +
 		(pcifunc & RVU_PFVF_FUNC_MASK)) * LMT_MAPTBL_ENTRY_SIZE;
 }
 
@@ -83,7 +83,7 @@ static int rvu_get_lmtaddr(struct rvu *rvu, u16 pcifunc,
 
 	mutex_lock(&rvu->rsrc_lock);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_ADDR_REQ, iova);
-	pf = rvu_get_pf(pcifunc) & RVU_PFVF_PF_MASK;
+	pf = rvu_get_pf(rvu->pdev, pcifunc) & RVU_OTX2_PFVF_PF_MASK;
 	val = BIT_ULL(63) | BIT_ULL(14) | BIT_ULL(13) | pf << 8 |
 	      ((pcifunc & RVU_PFVF_FUNC_MASK) & 0xFF);
 	rvu_write64(rvu, BLKADDR_RVUM, RVU_AF_SMMU_TXN_REQ, val);
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 3c5bbaf12e59..f404117bf6c8 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -410,7 +410,7 @@ static bool is_cpt_pf(struct rvu *rvu, u16 pcifunc)
 {
 	int cpt_pf_num = rvu->cpt_pf_num;
 
-	if (rvu_get_pf(pcifunc) != cpt_pf_num)
+	if (rvu_get_pf(rvu->pdev, pcifunc) != cpt_pf_num)
 		return false;
 	if (pcifunc & RVU_PFVF_FUNC_MASK)
 		return false;
@@ -422,7 +422,7 @@ static bool is_cpt_vf(struct rvu *rvu, u16 pcifunc)
 {
 	int cpt_pf_num = rvu->cpt_pf_num;
 
-	if (rvu_get_pf(pcifunc) != cpt_pf_num)
+	if (rvu_get_pf(rvu->pdev, pcifunc) != cpt_pf_num)
 		return false;
 	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
 		return false;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
index c827da626471..0c20642f81b9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_debugfs.c
@@ -688,7 +688,7 @@ static int get_max_column_width(struct rvu *rvu)
 
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
-			pcifunc = pf << 10 | vf;
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf);
 			if (!pcifunc)
 				continue;
 
@@ -759,7 +759,7 @@ static ssize_t rvu_dbg_rsrc_attach_status(struct file *filp,
 		for (vf = 0; vf <= rvu->hw->total_vfs; vf++) {
 			off = 0;
 			flag = 0;
-			pcifunc = pf << 10 | vf;
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf);
 			if (!pcifunc)
 				continue;
 
@@ -842,7 +842,7 @@ static int rvu_dbg_rvu_pf_cgx_map_display(struct seq_file *filp, void *unused)
 
 		cgx[0] = 0;
 		lmac[0] = 0;
-		pcifunc = pf << 10;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		pfvf = rvu_get_pfvf(rvu, pcifunc);
 
 		if (pfvf->nix_blkaddr == BLKADDR_NIX0)
@@ -2623,10 +2623,10 @@ static int rvu_dbg_nix_band_prof_ctx_display(struct seq_file *m, void *unused)
 			pcifunc = ipolicer->pfvf_map[idx];
 			if (!(pcifunc & RVU_PFVF_FUNC_MASK))
 				seq_printf(m, "Allocated to :: PF %d\n",
-					   rvu_get_pf(pcifunc));
+					   rvu_get_pf(rvu->pdev, pcifunc));
 			else
 				seq_printf(m, "Allocated to :: PF %d VF %d\n",
-					   rvu_get_pf(pcifunc),
+					   rvu_get_pf(rvu->pdev, pcifunc),
 					   (pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 			print_band_prof_ctx(m, &aq_rsp.prof);
 		}
@@ -2983,10 +2983,10 @@ static void rvu_print_npc_mcam_info(struct seq_file *s,
 
 	if (!(pcifunc & RVU_PFVF_FUNC_MASK))
 		seq_printf(s, "\n\t\t Device \t\t: PF%d\n",
-			   rvu_get_pf(pcifunc));
+			   rvu_get_pf(rvu->pdev, pcifunc));
 	else
 		seq_printf(s, "\n\t\t Device \t\t: PF%d VF%d\n",
-			   rvu_get_pf(pcifunc),
+			   rvu_get_pf(rvu->pdev, pcifunc),
 			   (pcifunc & RVU_PFVF_FUNC_MASK) - 1);
 
 	if (entry_acnt) {
@@ -3049,13 +3049,13 @@ static int rvu_dbg_npc_mcam_info_display(struct seq_file *filp, void *unsued)
 	seq_puts(filp, "\n\t\t Current allocation\n");
 	seq_puts(filp, "\t\t====================\n");
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
-		pcifunc = (pf << RVU_PFVF_PF_SHIFT);
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		rvu_print_npc_mcam_info(filp, pcifunc, blkaddr);
 
 		cfg = rvu_read64(rvu, BLKADDR_RVUM, RVU_PRIV_PFX_CFG(pf));
 		numvfs = (cfg >> 12) & 0xFF;
 		for (vf = 0; vf < numvfs; vf++) {
-			pcifunc = (pf << RVU_PFVF_PF_SHIFT) | (vf + 1);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1));
 			rvu_print_npc_mcam_info(filp, pcifunc, blkaddr);
 		}
 	}
@@ -3326,7 +3326,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused)
 
 	mutex_lock(&mcam->lock);
 	list_for_each_entry(iter, &mcam->mcam_rules, list) {
-		pf = (iter->owner >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
+		pf = rvu_get_pf(rvu->pdev, iter->owner);
 		seq_printf(s, "\n\tInstalled by: PF%d ", pf);
 
 		if (iter->owner & RVU_PFVF_FUNC_MASK) {
@@ -3344,7 +3344,7 @@ static int rvu_dbg_npc_mcam_show_rules(struct seq_file *s, void *unused)
 		rvu_dbg_npc_mcam_show_flows(s, iter);
 		if (is_npc_intf_rx(iter->intf)) {
 			target = iter->rx_action.pf_func;
-			pf = (target >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
+			pf = rvu_get_pf(rvu->pdev, target);
 			seq_printf(s, "\tForward to: PF%d ", pf);
 
 			if (target & RVU_PFVF_FUNC_MASK) {
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
index 613655fcd34f..bdf4d852c15d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
@@ -315,7 +315,8 @@ static bool is_valid_txschq(struct rvu *rvu, int blkaddr,
 	if (lvl >= hw->cap.nix_tx_aggr_lvl) {
 		if ((nix_get_tx_link(rvu, map_func) !=
 		     nix_get_tx_link(rvu, pcifunc)) &&
-		     (rvu_get_pf(map_func) != rvu_get_pf(pcifunc)))
+		     (rvu_get_pf(rvu->pdev, map_func) !=
+				rvu_get_pf(rvu->pdev, pcifunc)))
 			return false;
 		else
 			return true;
@@ -339,7 +340,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf,
 	bool from_vf;
 	int err;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK &&
 	    type != NIX_INTF_TYPE_SDP)
 		return 0;
@@ -416,7 +417,7 @@ static int nix_interface_init(struct rvu *rvu, u16 pcifunc, int type, int nixlf,
 		break;
 	case NIX_INTF_TYPE_SDP:
 		from_vf = !!(pcifunc & RVU_PFVF_FUNC_MASK);
-		parent_pf = &rvu->pf[rvu_get_pf(pcifunc)];
+		parent_pf = &rvu->pf[rvu_get_pf(rvu->pdev, pcifunc)];
 		sdp_info = parent_pf->sdp_info;
 		if (!sdp_info) {
 			dev_err(rvu->dev, "Invalid sdp_info pointer\n");
@@ -590,12 +591,12 @@ static int nix_bp_disable(struct rvu *rvu,
 	u16 chan_v;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	type = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
 	if (!is_pf_cgxmapped(rvu, pf) && type != NIX_INTF_TYPE_LBK)
 		return 0;
 
-	if (is_sdp_pfvf(pcifunc))
+	if (is_sdp_pfvf(rvu, pcifunc))
 		type = NIX_INTF_TYPE_SDP;
 
 	if (cpt_link && !rvu->hw->cpt_links)
@@ -736,9 +737,9 @@ static int nix_bp_enable(struct rvu *rvu,
 	u16 chan_v;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	type = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
-	if (is_sdp_pfvf(pcifunc))
+	if (is_sdp_pfvf(rvu, pcifunc))
 		type = NIX_INTF_TYPE_SDP;
 
 	/* Enable backpressure only for CGX mapped PFs and LBK/SDP interface */
@@ -1674,7 +1675,7 @@ int rvu_mbox_handler_nix_lf_alloc(struct rvu *rvu,
 	}
 
 	intf = is_lbk_vf(rvu, pcifunc) ? NIX_INTF_TYPE_LBK : NIX_INTF_TYPE_CGX;
-	if (is_sdp_pfvf(pcifunc))
+	if (is_sdp_pfvf(rvu, pcifunc))
 		intf = NIX_INTF_TYPE_SDP;
 
 	err = nix_interface_init(rvu, pcifunc, intf, nixlf, rsp,
@@ -1798,7 +1799,8 @@ int rvu_mbox_handler_nix_mark_format_cfg(struct rvu *rvu,
 	rc = rvu_nix_reserve_mark_format(rvu, nix_hw, blkaddr, cfg);
 	if (rc < 0) {
 		dev_err(rvu->dev, "No mark_format_ctl for (pf:%d, vf:%d)",
-			rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK);
+			rvu_get_pf(rvu->pdev,  pcifunc),
+				   pcifunc & RVU_PFVF_FUNC_MASK);
 		return NIX_AF_ERR_MARK_CFG_FAIL;
 	}
 
@@ -2050,7 +2052,7 @@ static void nix_clear_tx_xoff(struct rvu *rvu, int blkaddr,
 static int nix_get_tx_link(struct rvu *rvu, u16 pcifunc)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id = 0, lmac_id = 0;
 
 	if (is_lbk_vf(rvu, pcifunc)) {/* LBK links */
@@ -2068,7 +2070,7 @@ static void nix_get_txschq_range(struct rvu *rvu, u16 pcifunc,
 				 int link, int *start, int *end)
 {
 	struct rvu_hwinfo *hw = rvu->hw;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 
 	/* LBK links */
 	if (is_lbk_vf(rvu, pcifunc) || is_rep_dev(rvu, pcifunc)) {
@@ -2426,7 +2428,7 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr,
 {
 	struct nix_smq_flush_ctx *smq_flush_ctx;
 	int err, restore_tx_en = 0, i;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id = 0, lmac_id = 0;
 	u16 tl2_tl3_link_schq;
 	u8 link, link_level;
@@ -2820,7 +2822,7 @@ void rvu_nix_tx_tl2_cfg(struct rvu *rvu, int blkaddr, u16 pcifunc,
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	int lbk_link_start, lbk_links;
-	u8 pf = rvu_get_pf(pcifunc);
+	u8 pf = rvu_get_pf(rvu->pdev, pcifunc);
 	int schq;
 	u64 cfg;
 
@@ -3190,7 +3192,8 @@ static int nix_blk_setup_mce(struct rvu *rvu, struct nix_hw *nix_hw,
 	err = rvu_nix_blk_aq_enq_inst(rvu, nix_hw, &aq_req, NULL);
 	if (err) {
 		dev_err(rvu->dev, "Failed to setup Bcast MCE for PF%d:VF%d\n",
-			rvu_get_pf(pcifunc), pcifunc & RVU_PFVF_FUNC_MASK);
+			rvu_get_pf(rvu->pdev, pcifunc),
+				pcifunc & RVU_PFVF_FUNC_MASK);
 		return err;
 	}
 	return 0;
@@ -3458,7 +3461,7 @@ int nix_update_mce_list(struct rvu *rvu, u16 pcifunc,
 		dev_err(rvu->dev,
 			"%s: Idx %d > max MCE idx %d, for PF%d bcast list\n",
 			__func__, idx, mce_list->max,
-			pcifunc >> RVU_PFVF_PF_SHIFT);
+			rvu_get_pf(rvu->pdev, pcifunc));
 		return -EINVAL;
 	}
 
@@ -3510,7 +3513,8 @@ void nix_get_mce_list(struct rvu *rvu, u16 pcifunc, int type,
 	struct rvu_pfvf *pfvf;
 
 	if (!hw->cap.nix_rx_multicast ||
-	    !is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc & ~RVU_PFVF_FUNC_MASK))) {
+	    !is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev,
+			     pcifunc & ~RVU_PFVF_FUNC_MASK))) {
 		*mce_list = NULL;
 		*mce_idx = 0;
 		return;
@@ -3544,13 +3548,13 @@ static int nix_update_mce_rule(struct rvu *rvu, u16 pcifunc,
 	int pf;
 
 	/* skip multicast pkt replication for AF's VFs & SDP links */
-	if (is_lbk_vf(rvu, pcifunc) || is_sdp_pfvf(pcifunc))
+	if (is_lbk_vf(rvu, pcifunc) || is_sdp_pfvf(rvu, pcifunc))
 		return 0;
 
 	if (!hw->cap.nix_rx_multicast)
 		return 0;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (!is_pf_cgxmapped(rvu, pf))
 		return 0;
 
@@ -3619,7 +3623,7 @@ static int nix_setup_mce_tables(struct rvu *rvu, struct nix_hw *nix_hw)
 
 		for (idx = 0; idx < (numvfs + 1); idx++) {
 			/* idx-0 is for PF, followed by VFs */
-			pcifunc = (pf << RVU_PFVF_PF_SHIFT);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 			pcifunc |= idx;
 			/* Add dummy entries now, so that we don't have to check
 			 * for whether AQ_OP should be INIT/WRITE later on.
@@ -4554,7 +4558,7 @@ int rvu_mbox_handler_nix_set_rx_mode(struct rvu *rvu, struct nix_rx_mode *req,
 static void nix_find_link_frs(struct rvu *rvu,
 			      struct nix_frs_cfg *req, u16 pcifunc)
 {
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct rvu_pfvf *pfvf;
 	int maxlen, minlen;
 	int numvfs, hwvf;
@@ -4601,7 +4605,7 @@ int rvu_mbox_handler_nix_set_hw_frs(struct rvu *rvu, struct nix_frs_cfg *req,
 {
 	struct rvu_hwinfo *hw = rvu->hw;
 	u16 pcifunc = req->hdr.pcifunc;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	int blkaddr, link = -1;
 	struct nix_hw *nix_hw;
 	struct rvu_pfvf *pfvf;
@@ -5251,7 +5255,7 @@ int rvu_mbox_handler_nix_lf_start_rx(struct rvu *rvu, struct msg_req *req,
 
 	rvu_switch_update_rules(rvu, pcifunc, true);
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode)
 		rvu_rep_notify_pfvf_state(rvu, pcifunc, true);
 
@@ -5284,7 +5288,7 @@ int rvu_mbox_handler_nix_lf_stop_rx(struct rvu *rvu, struct msg_req *req,
 	rvu_switch_update_rules(rvu, pcifunc, false);
 	rvu_cgx_tx_enable(rvu, pcifunc, true);
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (is_pf_cgxmapped(rvu, pf) && rvu->rep_mode)
 		rvu_rep_notify_pfvf_state(rvu, pcifunc, false);
 	return 0;
@@ -5296,7 +5300,7 @@ void rvu_nix_lf_teardown(struct rvu *rvu, u16 pcifunc, int blkaddr, int nixlf)
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	struct hwctx_disable_req ctx_req;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	struct mac_ops *mac_ops;
 	u8 cgx_id, lmac_id;
 	u64 sa_base;
@@ -5385,7 +5389,7 @@ static int rvu_nix_lf_ptp_tx_cfg(struct rvu *rvu, u16 pcifunc, bool enable)
 	int nixlf;
 	u64 cfg;
 
-	pf = rvu_get_pf(pcifunc);
+	pf = rvu_get_pf(rvu->pdev, pcifunc);
 	if (!is_mac_feature_supported(rvu, pf, RVU_LMAC_FEAT_PTP))
 		return 0;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
index da15bb451178..c7c70429eb6c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc.c
@@ -147,7 +147,9 @@ static int npc_get_ucast_mcam_index(struct npc_mcam *mcam, u16 pcifunc,
 int npc_get_nixlf_mcam_index(struct npc_mcam *mcam,
 			     u16 pcifunc, int nixlf, int type)
 {
-	int pf = rvu_get_pf(pcifunc);
+	struct rvu_hwinfo *hw = container_of(mcam, struct rvu_hwinfo, mcam);
+	struct rvu *rvu = hw->rvu;
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	int index;
 
 	/* Check if this is for a PF */
@@ -698,7 +700,7 @@ void rvu_npc_install_promisc_entry(struct rvu *rvu, u16 pcifunc,
 
 	/* RX_ACTION set to MCAST for CGX PF's */
 	if (hw->cap.nix_rx_multicast && pfvf->use_mce_list &&
-	    is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc))) {
+	    is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc))) {
 		*(u64 *)&action = 0;
 		action.op = NIX_RX_ACTIONOP_MCAST;
 		pfvf = rvu_get_pfvf(rvu, pcifunc & ~RVU_PFVF_FUNC_MASK);
@@ -3434,7 +3436,7 @@ int rvu_npc_set_parse_mode(struct rvu *rvu, u16 pcifunc, u64 mode, u8 dir,
 {
 	struct rvu_pfvf *pfvf = rvu_get_pfvf(rvu, pcifunc);
 	int blkaddr, nixlf, rc, intf_mode;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u64 rxpkind, txpkind;
 	u8 cgx_id, lmac_id;
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
index d2661e7fabdb..999f6d93c7fe 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.c
@@ -1465,7 +1465,7 @@ static int rvu_npc_exact_update_table_entry(struct rvu *rvu, u8 cgx_id, u8 lmac_
 int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc)
 {
 	struct npc_exact_table *table;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id, lmac_id;
 	u32 drop_mcam_idx;
 	bool *promisc;
@@ -1512,7 +1512,7 @@ int rvu_npc_exact_promisc_disable(struct rvu *rvu, u16 pcifunc)
 int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc)
 {
 	struct npc_exact_table *table;
-	int pf = rvu_get_pf(pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u8 cgx_id, lmac_id;
 	u32 drop_mcam_idx;
 	bool *promisc;
@@ -1560,7 +1560,7 @@ int rvu_npc_exact_promisc_enable(struct rvu *rvu, u16 pcifunc)
 int rvu_npc_exact_mac_addr_reset(struct rvu *rvu, struct cgx_mac_addr_reset_req *req,
 				 struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u32 seq_id = req->index;
 	struct rvu_pfvf *pfvf;
 	u8 cgx_id, lmac_id;
@@ -1593,7 +1593,7 @@ int rvu_npc_exact_mac_addr_update(struct rvu *rvu,
 				  struct cgx_mac_addr_update_req *req,
 				  struct cgx_mac_addr_update_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct npc_exact_table_entry *entry;
 	struct npc_exact_table *table;
 	struct rvu_pfvf *pfvf;
@@ -1675,7 +1675,7 @@ int rvu_npc_exact_mac_addr_add(struct rvu *rvu,
 			       struct cgx_mac_addr_add_req *req,
 			       struct cgx_mac_addr_add_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	struct rvu_pfvf *pfvf;
 	u8 cgx_id, lmac_id;
 	int rc = 0;
@@ -1711,7 +1711,7 @@ int rvu_npc_exact_mac_addr_del(struct rvu *rvu,
 			       struct cgx_mac_addr_del_req *req,
 			       struct msg_rsp *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	int rc;
 
 	rc = rvu_npc_exact_del_table_entry_by_id(rvu, req->index);
@@ -1736,7 +1736,7 @@ int rvu_npc_exact_mac_addr_del(struct rvu *rvu,
 int rvu_npc_exact_mac_addr_set(struct rvu *rvu, struct cgx_mac_addr_set_or_get *req,
 			       struct cgx_mac_addr_set_or_get *rsp)
 {
-	int pf = rvu_get_pf(req->hdr.pcifunc);
+	int pf = rvu_get_pf(rvu->pdev, req->hdr.pcifunc);
 	u32 seq_id = req->index;
 	struct rvu_pfvf *pfvf;
 	u8 cgx_id, lmac_id;
@@ -2001,7 +2001,7 @@ int rvu_npc_exact_init(struct rvu *rvu)
 		}
 
 		/* Filter rules are only for PF */
-		pcifunc = RVU_PFFUNC(i, 0);
+		pcifunc = RVU_PFFUNC(rvu->pdev, i, 0);
 
 		dev_dbg(rvu->dev,
 			"%s:Drop rule cgx=%d lmac=%d chan(val=0x%llx, mask=0x%llx\n",
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h
index 57a09328d46b..cb25cf478f1f 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_npc_hash.h
@@ -139,9 +139,7 @@ static struct npc_mcam_kex_hash npc_mkex_hash_default __maybe_unused = {
 #define NPC_MCAM_DROP_RULE_MAX 30
 #define NPC_MCAM_SDP_DROP_RULE_IDX 0
 
-#define RVU_PFFUNC(pf, func)	\
-	((((pf) & RVU_PFVF_PF_MASK) << RVU_PFVF_PF_SHIFT) | \
-	(((func) & RVU_PFVF_FUNC_MASK) << RVU_PFVF_FUNC_SHIFT))
+#define RVU_PFFUNC(pdev, pf, func) rvu_make_pcifunc(pdev, pf, func)
 
 enum npc_exact_opc_type {
 	NPC_EXACT_OPC_MEM,
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
index 32953cca108c..03099bc570bd 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_rep.c
@@ -39,7 +39,7 @@ static int rvu_rep_up_notify(struct rvu *rvu, struct rep_event *event)
 	struct rep_event *msg;
 	int pf;
 
-	pf = rvu_get_pf(event->pcifunc);
+	pf = rvu_get_pf(rvu->pdev, event->pcifunc);
 
 	if (event->event & RVU_EVENT_MAC_ADDR_CHANGE)
 		ether_addr_copy(pfvf->mac_addr, event->evt_data.mac);
@@ -114,10 +114,10 @@ int rvu_rep_notify_pfvf_state(struct rvu *rvu, u16 pcifunc, bool enable)
 	struct rep_event *req;
 	int pf;
 
-	if (!is_pf_cgxmapped(rvu, rvu_get_pf(pcifunc)))
+	if (!is_pf_cgxmapped(rvu, rvu_get_pf(rvu->pdev, pcifunc)))
 		return 0;
 
-	pf = rvu_get_pf(rvu->rep_pcifunc);
+	pf = rvu_get_pf(rvu->pdev, rvu->rep_pcifunc);
 
 	mutex_lock(&rvu->mbox_lock);
 	req = otx2_mbox_alloc_msg_rep_event_up_notify(rvu, pf);
@@ -325,7 +325,7 @@ int rvu_rep_install_mcam_rules(struct rvu *rvu)
 		if (!is_pf_cgxmapped(rvu, pf))
 			continue;
 
-		pcifunc = pf << RVU_PFVF_PF_SHIFT;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		rvu_get_nix_blkaddr(rvu, pcifunc);
 		rep = true;
 		for (i = 0; i < 2; i++) {
@@ -345,8 +345,7 @@ int rvu_rep_install_mcam_rules(struct rvu *rvu)
 
 		rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
 		for (vf = 0; vf < numvfs; vf++) {
-			pcifunc = pf << RVU_PFVF_PF_SHIFT |
-				  ((vf + 1) & RVU_PFVF_FUNC_MASK);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, vf + 1);
 			rvu_get_nix_blkaddr(rvu, pcifunc);
 
 			/* Skip installimg rules if nixlf is not attached */
@@ -454,7 +453,7 @@ int rvu_mbox_handler_get_rep_cnt(struct rvu *rvu, struct msg_req *req,
 	for (pf = 0; pf < rvu->hw->total_pfs; pf++) {
 		if (!is_pf_cgxmapped(rvu, pf))
 			continue;
-		pcifunc = pf << RVU_PFVF_PF_SHIFT;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		rvu->rep2pfvf_map[rep] = pcifunc;
 		rsp->rep_pf_map[rep] = pcifunc;
 		rep++;
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c
index 38cfe148f4b7..e4a5f9fa6fd4 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_sdp.c
@@ -17,9 +17,9 @@
 /* SDP PF number */
 static int sdp_pf_num[MAX_SDP] = {-1, -1};
 
-bool is_sdp_pfvf(u16 pcifunc)
+bool is_sdp_pfvf(struct rvu *rvu, u16 pcifunc)
 {
-	u16 pf = rvu_get_pf(pcifunc);
+	u16 pf = rvu_get_pf(rvu->pdev, pcifunc);
 	u32 found = 0, i = 0;
 
 	while (i < MAX_SDP) {
@@ -34,9 +34,9 @@ bool is_sdp_pfvf(u16 pcifunc)
 	return true;
 }
 
-bool is_sdp_pf(u16 pcifunc)
+bool is_sdp_pf(struct rvu *rvu, u16 pcifunc)
 {
-	return (is_sdp_pfvf(pcifunc) &&
+	return (is_sdp_pfvf(rvu, pcifunc) &&
 		!(pcifunc & RVU_PFVF_FUNC_MASK));
 }
 
@@ -46,7 +46,7 @@ bool is_sdp_vf(struct rvu *rvu, u16 pcifunc)
 	if (!(pcifunc & ~RVU_PFVF_FUNC_MASK))
 		return (rvu->vf_devid == RVU_SDP_VF_DEVID);
 
-	return (is_sdp_pfvf(pcifunc) &&
+	return (is_sdp_pfvf(rvu, pcifunc) &&
 		!!(pcifunc & RVU_PFVF_FUNC_MASK));
 }
 
diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
index 268efb7c1c15..49ce38685a7e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_switch.c
@@ -93,7 +93,7 @@ static int rvu_switch_install_rules(struct rvu *rvu)
 		if (!is_pf_cgxmapped(rvu, pf))
 			continue;
 
-		pcifunc = pf << 10;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		/* rvu_get_nix_blkaddr sets up the corresponding NIX block
 		 * address and NIX RX and TX interfaces for a pcifunc.
 		 * Generally it is called during attach call of a pcifunc but it
@@ -126,7 +126,7 @@ static int rvu_switch_install_rules(struct rvu *rvu)
 
 		rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
 		for (vf = 0; vf < numvfs; vf++) {
-			pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1));
 			rvu_get_nix_blkaddr(rvu, pcifunc);
 
 			err = rvu_switch_install_rx_rule(rvu, pcifunc, 0x0);
@@ -236,7 +236,7 @@ void rvu_switch_disable(struct rvu *rvu)
 		if (!is_pf_cgxmapped(rvu, pf))
 			continue;
 
-		pcifunc = pf << 10;
+		pcifunc = rvu_make_pcifunc(rvu->pdev, pf, 0);
 		err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
 		if (err)
 			dev_err(rvu->dev,
@@ -248,7 +248,7 @@ void rvu_switch_disable(struct rvu *rvu)
 
 		rvu_get_pf_numvfs(rvu, pf, &numvfs, NULL);
 		for (vf = 0; vf < numvfs; vf++) {
-			pcifunc = pf << 10 | ((vf + 1) & 0x3FF);
+			pcifunc = rvu_make_pcifunc(rvu->pdev, pf, (vf + 1));
 			err = rvu_switch_install_rx_rule(rvu, pcifunc, 0xFFF);
 			if (err)
 				dev_err(rvu->dev,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
index a6500e3673f2..c691f0722154 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.c
@@ -481,7 +481,7 @@ static int cn10k_outb_write_sa(struct otx2_nic *pf, struct qmem *sa_info)
 		goto set_available;
 
 	/* Trigger CTX flush to write dirty data back to DRAM */
-	reg_val = FIELD_PREP(CPT_LF_CTX_FLUSH, sa_iova >> 7);
+	reg_val = FIELD_PREP(CPT_LF_CTX_FLUSH_CPTR, sa_iova >> 7);
 	otx2_write64(pf, CN10K_CPT_LF_CTX_FLUSH, reg_val);
 
 set_available:
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h
index 9965df0faa3e..43fbce0d6039 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/cn10k_ipsec.h
@@ -220,7 +220,7 @@ struct cpt_sg_s {
 #define CPT_LF_Q_SIZE_DIV40 GENMASK_ULL(14, 0)
 
 /* CPT LF CTX Flush Register */
-#define CPT_LF_CTX_FLUSH GENMASK_ULL(45, 0)
+#define CPT_LF_CTX_FLUSH_CPTR GENMASK_ULL(45, 0)
 
 #ifdef CONFIG_XFRM_OFFLOAD
 int cn10k_ipsec_init(struct net_device *netdev);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
index a2a7fc99695d..8ada34a868e9 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_common.h
@@ -28,6 +28,7 @@
 #include "otx2_reg.h"
 #include "otx2_txrx.h"
 #include "otx2_devlink.h"
+#include <rvu.h>
 #include <rvu_trace.h>
 #include "qos.h"
 #include "rep.h"
@@ -904,21 +905,11 @@ MBOX_UP_MCS_MESSAGES
 /* Time to wait before watchdog kicks off */
 #define OTX2_TX_TIMEOUT		(100 * HZ)
 
-#define	RVU_PFVF_PF_SHIFT	10
-#define	RVU_PFVF_PF_MASK	0x3F
-#define	RVU_PFVF_FUNC_SHIFT	0
-#define	RVU_PFVF_FUNC_MASK	0x3FF
-
 static inline bool is_otx2_vf(u16 pcifunc)
 {
 	return !!(pcifunc & RVU_PFVF_FUNC_MASK);
 }
 
-static inline int rvu_get_pf(u16 pcifunc)
-{
-	return (pcifunc >> RVU_PFVF_PF_SHIFT) & RVU_PFVF_PF_MASK;
-}
-
 static inline dma_addr_t otx2_dma_map_page(struct otx2_nic *pfvf,
 					   struct page *page,
 					   size_t offset, size_t size,
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
index 07da4d6dbbc9..1dc3e057f52d 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c
@@ -206,7 +206,8 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
 
 	/* Register ME interrupt handler*/
 	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFME0 * NAME_SIZE];
-	snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME0", rvu_get_pf(pf->pcifunc));
+	snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME0",
+		 rvu_get_pf(pf->pdev, pf->pcifunc));
 	ret = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFME0),
 			  otx2_pf_me_intr_handler, 0, irq_name, pf);
 	if (ret) {
@@ -216,7 +217,8 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
 
 	/* Register FLR interrupt handler */
 	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFFLR0 * NAME_SIZE];
-	snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR0", rvu_get_pf(pf->pcifunc));
+	snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR0",
+		 rvu_get_pf(pf->pdev, pf->pcifunc));
 	ret = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFFLR0),
 			  otx2_pf_flr_intr_handler, 0, irq_name, pf);
 	if (ret) {
@@ -228,7 +230,7 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
 	if (numvfs > 64) {
 		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFME1 * NAME_SIZE];
 		snprintf(irq_name, NAME_SIZE, "RVUPF%d_ME1",
-			 rvu_get_pf(pf->pcifunc));
+			 rvu_get_pf(pf->pdev, pf->pcifunc));
 		ret = request_irq(pci_irq_vector
 				  (pf->pdev, RVU_PF_INT_VEC_VFME1),
 				  otx2_pf_me_intr_handler, 0, irq_name, pf);
@@ -238,7 +240,7 @@ static int otx2_register_flr_me_intr(struct otx2_nic *pf, int numvfs)
 		}
 		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFFLR1 * NAME_SIZE];
 		snprintf(irq_name, NAME_SIZE, "RVUPF%d_FLR1",
-			 rvu_get_pf(pf->pcifunc));
+			 rvu_get_pf(pf->pdev, pf->pcifunc));
 		ret = request_irq(pci_irq_vector
 				  (pf->pdev, RVU_PF_INT_VEC_VFFLR1),
 				  otx2_pf_flr_intr_handler, 0, irq_name, pf);
@@ -700,7 +702,7 @@ static int otx2_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
 	irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFPF_MBOX0 * NAME_SIZE];
 	if (pf->pcifunc)
 		snprintf(irq_name, NAME_SIZE,
-			 "RVUPF%d_VF Mbox0", rvu_get_pf(pf->pcifunc));
+			 "RVUPF%d_VF Mbox0", rvu_get_pf(pf->pdev, pf->pcifunc));
 	else
 		snprintf(irq_name, NAME_SIZE, "RVUPF_VF Mbox0");
 	err = request_irq(pci_irq_vector(pf->pdev, RVU_PF_INT_VEC_VFPF_MBOX0),
@@ -716,7 +718,8 @@ static int otx2_register_pfvf_mbox_intr(struct otx2_nic *pf, int numvfs)
 		irq_name = &hw->irq_name[RVU_PF_INT_VEC_VFPF_MBOX1 * NAME_SIZE];
 		if (pf->pcifunc)
 			snprintf(irq_name, NAME_SIZE,
-				 "RVUPF%d_VF Mbox1", rvu_get_pf(pf->pcifunc));
+				 "RVUPF%d_VF Mbox1",
+				 rvu_get_pf(pf->pdev, pf->pcifunc));
 		else
 			snprintf(irq_name, NAME_SIZE, "RVUPF_VF Mbox1");
 		err = request_irq(pci_irq_vector(pf->pdev,
@@ -1971,7 +1974,7 @@ int otx2_open(struct net_device *netdev)
 	if (err) {
 		dev_err(pf->dev,
 			"RVUPF%d: IRQ registration failed for QERR\n",
-			rvu_get_pf(pf->pcifunc));
+			rvu_get_pf(pf->pdev, pf->pcifunc));
 		goto err_disable_napi;
 	}
 
@@ -1989,7 +1992,7 @@ int otx2_open(struct net_device *netdev)
 		if (name_len >= NAME_SIZE) {
 			dev_err(pf->dev,
 				"RVUPF%d: IRQ registration failed for CQ%d, irq name is too long\n",
-				rvu_get_pf(pf->pcifunc), qidx);
+				rvu_get_pf(pf->pdev, pf->pcifunc), qidx);
 			err = -EINVAL;
 			goto err_free_cints;
 		}
@@ -2000,7 +2003,7 @@ int otx2_open(struct net_device *netdev)
 		if (err) {
 			dev_err(pf->dev,
 				"RVUPF%d: IRQ registration failed for CQ%d\n",
-				rvu_get_pf(pf->pcifunc), qidx);
+				rvu_get_pf(pf->pdev, pf->pcifunc), qidx);
 			goto err_free_cints;
 		}
 		vec++;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
index e3aee6e36215..858f084b9d47 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_reg.h
@@ -138,36 +138,6 @@
 #define	NIX_LF_CINTX_ENA_W1S(a)		(NIX_LFBASE | 0xD40 | (a) << 12)
 #define	NIX_LF_CINTX_ENA_W1C(a)		(NIX_LFBASE | 0xD50 | (a) << 12)
 
-/* NIX AF transmit scheduler registers */
-#define NIX_AF_SMQX_CFG(a)		(0x700 | (u64)(a) << 16)
-#define NIX_AF_TL4X_SDP_LINK_CFG(a)	(0xB10 | (u64)(a) << 16)
-#define NIX_AF_TL1X_SCHEDULE(a)		(0xC00 | (u64)(a) << 16)
-#define NIX_AF_TL1X_CIR(a)		(0xC20 | (u64)(a) << 16)
-#define NIX_AF_TL1X_TOPOLOGY(a)		(0xC80 | (u64)(a) << 16)
-#define NIX_AF_TL2X_PARENT(a)		(0xE88 | (u64)(a) << 16)
-#define NIX_AF_TL2X_SCHEDULE(a)		(0xE00 | (u64)(a) << 16)
-#define NIX_AF_TL2X_TOPOLOGY(a)		(0xE80 | (u64)(a) << 16)
-#define NIX_AF_TL2X_CIR(a)		(0xE20 | (u64)(a) << 16)
-#define NIX_AF_TL2X_PIR(a)		(0xE30 | (u64)(a) << 16)
-#define NIX_AF_TL3X_PARENT(a)		(0x1088 | (u64)(a) << 16)
-#define NIX_AF_TL3X_SCHEDULE(a)		(0x1000 | (u64)(a) << 16)
-#define NIX_AF_TL3X_SHAPE(a)		(0x1010 | (u64)(a) << 16)
-#define NIX_AF_TL3X_CIR(a)		(0x1020 | (u64)(a) << 16)
-#define NIX_AF_TL3X_PIR(a)		(0x1030 | (u64)(a) << 16)
-#define NIX_AF_TL3X_TOPOLOGY(a)		(0x1080 | (u64)(a) << 16)
-#define NIX_AF_TL4X_PARENT(a)		(0x1288 | (u64)(a) << 16)
-#define NIX_AF_TL4X_SCHEDULE(a)		(0x1200 | (u64)(a) << 16)
-#define NIX_AF_TL4X_SHAPE(a)		(0x1210 | (u64)(a) << 16)
-#define NIX_AF_TL4X_CIR(a)		(0x1220 | (u64)(a) << 16)
-#define NIX_AF_TL4X_PIR(a)		(0x1230 | (u64)(a) << 16)
-#define NIX_AF_TL4X_TOPOLOGY(a)		(0x1280 | (u64)(a) << 16)
-#define NIX_AF_MDQX_SCHEDULE(a)		(0x1400 | (u64)(a) << 16)
-#define NIX_AF_MDQX_SHAPE(a)		(0x1410 | (u64)(a) << 16)
-#define NIX_AF_MDQX_CIR(a)		(0x1420 | (u64)(a) << 16)
-#define NIX_AF_MDQX_PIR(a)		(0x1430 | (u64)(a) << 16)
-#define NIX_AF_MDQX_PARENT(a)		(0x1480 | (u64)(a) << 16)
-#define NIX_AF_TL3_TL2X_LINKX_CFG(a, b)	(0x1700 | (u64)(a) << 16 | (b) << 3)
-
 /* LMT LF registers */
 #define LMT_LFBASE			BIT_ULL(RVU_FUNC_BLKADDR_SHIFT)
 #define LMT_LF_LMTLINEX(a)		(LMT_LFBASE | 0x000 | (a) << 12)
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
index 9a226ca74425..5f80b23c5335 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_tc.c
@@ -467,7 +467,8 @@ static int otx2_tc_parse_actions(struct otx2_nic *nic,
 			target = act->dev;
 			if (target->dev.parent) {
 				priv = netdev_priv(target);
-				if (rvu_get_pf(nic->pcifunc) != rvu_get_pf(priv->pcifunc)) {
+				if (rvu_get_pf(nic->pdev, nic->pcifunc) !=
+					rvu_get_pf(nic->pdev, priv->pcifunc)) {
 					NL_SET_ERR_MSG_MOD(extack,
 							   "can't redirect to other pf/vf");
 					return -EOPNOTSUPP;
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
index 2cd3da3b6843..25af98034e2e 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/rep.c
@@ -244,10 +244,10 @@ static int rvu_rep_devlink_port_register(struct rep_dev *rep)
 
 	if (!(rep->pcifunc & RVU_PFVF_FUNC_MASK)) {
 		attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-		attrs.phys.port_number = rvu_get_pf(rep->pcifunc);
+		attrs.phys.port_number = rvu_get_pf(priv->pdev, rep->pcifunc);
 	} else {
 		attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
-		attrs.pci_vf.pf = rvu_get_pf(rep->pcifunc);
+		attrs.pci_vf.pf = rvu_get_pf(priv->pdev, rep->pcifunc);
 		attrs.pci_vf.vf = rep->pcifunc & RVU_PFVF_FUNC_MASK;
 	}
 
@@ -672,7 +672,8 @@ int rvu_rep_create(struct otx2_nic *priv, struct netlink_ext_ack *extack)
 		rep->pcifunc = pcifunc;
 
 		snprintf(ndev->name, sizeof(ndev->name), "Rpf%dvf%d",
-			 rvu_get_pf(pcifunc), (pcifunc & RVU_PFVF_FUNC_MASK));
+			 rvu_get_pf(priv->pdev, pcifunc),
+			 (pcifunc & RVU_PFVF_FUNC_MASK));
 
 		ndev->hw_features = (NETIF_F_RXCSUM | NETIF_F_IP_CSUM |
 			       NETIF_F_IPV6_CSUM | NETIF_F_RXHASH |
diff --git a/include/linux/soc/marvell/silicons.h b/include/linux/soc/marvell/silicons.h
new file mode 100644
index 000000000000..66bb9bfaf17d
--- /dev/null
+++ b/include/linux/soc/marvell/silicons.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only
+ * Copyright (C) 2024 Marvell.
+ */
+
+#ifndef __SOC_SILICON_H
+#define __SOC_SILICON_H
+
+#include <linux/types.h>
+#include <linux/pci.h>
+
+#if defined(CONFIG_ARM64)
+
+#define CN20K_CHIPID	0x20
+/*
+ * Silicon check for CN20K family
+ */
+static inline bool is_cn20k(struct pci_dev *pdev)
+{
+	return (pdev->subsystem_device & 0xFF) == CN20K_CHIPID;
+}
+#else
+#define is_cn20k(pdev)		((void)(pdev), 0)
+#endif
+
+#endif /* __SOC_SILICON_H */
-- 
cgit v1.2.3


From 2796ff1e3dcae7a3568f8e428ec9d32a8ee2fb36 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 14 Jun 2025 22:30:43 +0200
Subject: net: phy: add flag is_genphy_driven to struct phy_device

In order to get rid of phy_driver_is_genphy() and
phy_driver_is_genphy_10g(), as first step add and use a flag
phydev->is_genphy_driven.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/3f3ad6dc-402e-4915-8d5a-2306b6d5562b@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 13 +++++++------
 include/linux/phy.h          |  2 ++
 2 files changed, 9 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 509078344020..2aae97b2ffd8 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1522,7 +1522,6 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	struct mii_bus *bus = phydev->mdio.bus;
 	struct device *d = &phydev->mdio.dev;
 	struct module *ndev_owner = NULL;
-	bool using_genphy = false;
 	int err;
 
 	/* For Ethernet device drivers that register their own MDIO bus, we
@@ -1548,7 +1547,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		else
 			d->driver = &genphy_driver.mdiodrv.driver;
 
-		using_genphy = true;
+		phydev->is_genphy_driven = 1;
 	}
 
 	if (!try_module_get(d->driver->owner)) {
@@ -1557,7 +1556,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 		goto error_put_device;
 	}
 
-	if (using_genphy) {
+	if (phydev->is_genphy_driven) {
 		err = d->driver->probe(d);
 		if (err >= 0)
 			err = device_bind_driver(d);
@@ -1627,7 +1626,7 @@ int phy_attach_direct(struct net_device *dev, struct phy_device *phydev,
 	 * the generic PHY driver we can't figure it out, thus set the old
 	 * legacy PORT_MII value.
 	 */
-	if (using_genphy)
+	if (phydev->is_genphy_driven)
 		phydev->port = PORT_MII;
 
 	/* Initial carrier state is off as the phy is about to be
@@ -1666,6 +1665,7 @@ error:
 
 error_module_put:
 	module_put(d->driver->owner);
+	phydev->is_genphy_driven = 0;
 	d->driver = NULL;
 error_put_device:
 	put_device(d);
@@ -1799,9 +1799,10 @@ void phy_detach(struct phy_device *phydev)
 	 * from the generic driver so that there's a chance a
 	 * real driver could be loaded
 	 */
-	if (phy_driver_is_genphy(phydev) ||
-	    phy_driver_is_genphy_10g(phydev))
+	if (phydev->is_genphy_driven) {
 		device_release_driver(&phydev->mdio.dev);
+		phydev->is_genphy_driven = 0;
+	}
 
 	/* Assert the reset signal */
 	phy_device_reset(phydev, 1);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 8e2e4fcd050e..32ed27f10639 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -528,6 +528,7 @@ struct macsec_ops;
  * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY
  * @wol_enabled: Set to true if the PHY or the attached MAC have Wake-on-LAN
  * 		 enabled.
+ * @is_genphy_driven: PHY is driven by one of the generic PHY drivers
  * @state: State of the PHY for management purposes
  * @dev_flags: Device-specific flags used by the PHY driver.
  *
@@ -631,6 +632,7 @@ struct phy_device {
 	unsigned is_on_sfp_module:1;
 	unsigned mac_managed_pm:1;
 	unsigned wol_enabled:1;
+	unsigned is_genphy_driven:1;
 
 	unsigned autoneg:1;
 	/* The most recently read link state */
-- 
cgit v1.2.3


From 59e74c92e67e2951d829f9b0d78c5dc1df7c4c88 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 14 Jun 2025 22:31:57 +0200
Subject: net: phy: improve phy_driver_is_genphy

Use new flag phydev->is_genphy_driven to simplify this function.
Note that this includes a minor functional change:
Now this function returns true if ANY of the genphy drivers
is bound to the PHY device.

We have only one user in DSA driver mt7530, and there the
functional change doesn't matter.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/c9ac3a7d-262a-425d-9153-97fe3ca6280a@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c |  7 -------
 include/linux/phy.h          | 12 +++++++++++-
 2 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index 2aae97b2ffd8..fa0890ebf2ea 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1729,13 +1729,6 @@ static bool phy_driver_is_genphy_kind(struct phy_device *phydev,
 	return ret;
 }
 
-bool phy_driver_is_genphy(struct phy_device *phydev)
-{
-	return phy_driver_is_genphy_kind(phydev,
-					 &genphy_driver.mdiodrv.driver);
-}
-EXPORT_SYMBOL_GPL(phy_driver_is_genphy);
-
 bool phy_driver_is_genphy_10g(struct phy_device *phydev)
 {
 	return phy_driver_is_genphy_kind(phydev,
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 32ed27f10639..97a09e5743ef 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -1295,6 +1295,17 @@ static inline bool phy_is_started(struct phy_device *phydev)
 	return phydev->state >= PHY_UP;
 }
 
+/**
+ * phy_driver_is_genphy - Convenience function to check whether PHY is driven
+ *                        by one of the generic PHY drivers
+ * @phydev: The phy_device struct
+ * Return: true if PHY is driven by one of the genphy drivers
+ */
+static inline bool phy_driver_is_genphy(struct phy_device *phydev)
+{
+	return phydev->is_genphy_driven;
+}
+
 /**
  * phy_disable_eee_mode - Don't advertise an EEE mode.
  * @phydev: The phy_device struct
@@ -2097,7 +2108,6 @@ module_exit(phy_module_exit)
 #define module_phy_driver(__phy_drivers)				\
 	phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers))
 
-bool phy_driver_is_genphy(struct phy_device *phydev);
 bool phy_driver_is_genphy_10g(struct phy_device *phydev);
 
 #endif /* __PHY_H */
-- 
cgit v1.2.3


From 42ed7f7e94da01391d3519ffb5747698d2be0a67 Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Sat, 14 Jun 2025 22:32:47 +0200
Subject: net: phy: remove phy_driver_is_genphy_10g

Remove now unused function phy_driver_is_genphy_10g().

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/49b0589a-9604-4ee9-add5-28fbbbe2c2f3@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/phy_device.c | 23 -----------------------
 include/linux/phy.h          |  2 --
 2 files changed, 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
index fa0890ebf2ea..1c3a27b73d7b 100644
--- a/drivers/net/phy/phy_device.c
+++ b/drivers/net/phy/phy_device.c
@@ -1713,29 +1713,6 @@ struct phy_device *phy_attach(struct net_device *dev, const char *bus_id,
 }
 EXPORT_SYMBOL(phy_attach);
 
-static bool phy_driver_is_genphy_kind(struct phy_device *phydev,
-				      struct device_driver *driver)
-{
-	struct device *d = &phydev->mdio.dev;
-	bool ret = false;
-
-	if (!phydev->drv)
-		return ret;
-
-	get_device(d);
-	ret = d->driver == driver;
-	put_device(d);
-
-	return ret;
-}
-
-bool phy_driver_is_genphy_10g(struct phy_device *phydev)
-{
-	return phy_driver_is_genphy_kind(phydev,
-					 &genphy_c45_driver.mdiodrv.driver);
-}
-EXPORT_SYMBOL_GPL(phy_driver_is_genphy_10g);
-
 /**
  * phy_detach - detach a PHY device from its network device
  * @phydev: target phy_device struct
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 97a09e5743ef..b037aab7b71d 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -2108,6 +2108,4 @@ module_exit(phy_module_exit)
 #define module_phy_driver(__phy_drivers)				\
 	phy_module_driver(__phy_drivers, ARRAY_SIZE(__phy_drivers))
 
-bool phy_driver_is_genphy_10g(struct phy_device *phydev);
-
 #endif /* __PHY_H */
-- 
cgit v1.2.3


From 5da8a8b8090b5f79a816ba016af3a70a9d7287bf Mon Sep 17 00:00:00 2001
From: Shradha Gupta <shradhagupta@linux.microsoft.com>
Date: Wed, 11 Jun 2025 07:10:01 -0700
Subject: PCI/MSI: Export pci_msix_prepare_desc() for dynamic MSI-X allocations

For supporting dynamic MSI-X vector allocation by PCI controllers, enabling
the flag MSI_FLAG_PCI_MSIX_ALLOC_DYN is not enough, msix_prepare_msi_desc()
to prepare the MSI descriptor is also needed.

Export pci_msix_prepare_desc() to allow PCI controllers to support dynamic
MSI-X vector allocation.

Signed-off-by: Shradha Gupta <shradhagupta@linux.microsoft.com>
Reviewed-by: Haiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Saurabh Sengar <ssengar@linux.microsoft.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
---
 drivers/pci/msi/irqdomain.c | 5 +++--
 include/linux/msi.h         | 2 ++
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index c05152733993..765312c92d9b 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -222,13 +222,14 @@ static void pci_irq_unmask_msix(struct irq_data *data)
 	pci_msix_unmask(irq_data_get_msi_desc(data));
 }
 
-static void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
-				  struct msi_desc *desc)
+void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+			   struct msi_desc *desc)
 {
 	/* Don't fiddle with preallocated MSI descriptors */
 	if (!desc->pci.mask_base)
 		msix_prepare_msi_desc(to_pci_dev(desc->dev), desc);
 }
+EXPORT_SYMBOL_GPL(pci_msix_prepare_desc);
 
 static const struct msi_domain_template pci_msix_template = {
 	.chip = {
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 6863540f4b71..7f254bde5426 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -706,6 +706,8 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct irq_domain *parent);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
 struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev);
+void pci_msix_prepare_desc(struct irq_domain *domain, msi_alloc_info_t *arg,
+			   struct msi_desc *desc);
 #else /* CONFIG_PCI_MSI */
 static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
 {
-- 
cgit v1.2.3


From b29929b819f35503024c6a7e6ad442f6e36c68a0 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Mon, 16 Jun 2025 20:16:21 +0200
Subject: driver core: Add device_link_test() for testing device link flags

To avoid coding mistakes like the one fixed by commit 3860cbe23963 ("PM:
sleep: Fix bit masking operation"), introduce device_link_test() for
testing device link flags and use it where applicable.

No intentional functional impact.

Signed-off-by: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Link: https://lore.kernel.org/r/2793309.mvXUDI8C0e@rjwysocki.net
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/base/core.c          | 73 ++++++++++++++++++++++----------------------
 drivers/base/power/main.c    |  2 +-
 drivers/base/power/runtime.c |  6 ++--
 include/linux/device.h       |  5 +++
 4 files changed, 45 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index cbc0099d8ef2..3809baed42f3 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -460,9 +460,9 @@ static ssize_t auto_remove_on_show(struct device *dev,
 	struct device_link *link = to_devlink(dev);
 	const char *output;
 
-	if (link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
+	if (device_link_test(link, DL_FLAG_AUTOREMOVE_SUPPLIER))
 		output = "supplier unbind";
-	else if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER)
+	else if (device_link_test(link, DL_FLAG_AUTOREMOVE_CONSUMER))
 		output = "consumer unbind";
 	else
 		output = "never";
@@ -476,7 +476,7 @@ static ssize_t runtime_pm_show(struct device *dev,
 {
 	struct device_link *link = to_devlink(dev);
 
-	return sysfs_emit(buf, "%d\n", !!(link->flags & DL_FLAG_PM_RUNTIME));
+	return sysfs_emit(buf, "%d\n", device_link_test(link, DL_FLAG_PM_RUNTIME));
 }
 static DEVICE_ATTR_RO(runtime_pm);
 
@@ -485,8 +485,7 @@ static ssize_t sync_state_only_show(struct device *dev,
 {
 	struct device_link *link = to_devlink(dev);
 
-	return sysfs_emit(buf, "%d\n",
-			  !!(link->flags & DL_FLAG_SYNC_STATE_ONLY));
+	return sysfs_emit(buf, "%d\n", device_link_test(link, DL_FLAG_SYNC_STATE_ONLY));
 }
 static DEVICE_ATTR_RO(sync_state_only);
 
@@ -792,12 +791,12 @@ struct device_link *device_link_add(struct device *consumer,
 		if (link->consumer != consumer)
 			continue;
 
-		if (link->flags & DL_FLAG_INFERRED &&
+		if (device_link_test(link, DL_FLAG_INFERRED) &&
 		    !(flags & DL_FLAG_INFERRED))
 			link->flags &= ~DL_FLAG_INFERRED;
 
 		if (flags & DL_FLAG_PM_RUNTIME) {
-			if (!(link->flags & DL_FLAG_PM_RUNTIME)) {
+			if (!device_link_test(link, DL_FLAG_PM_RUNTIME)) {
 				pm_runtime_new_link(consumer);
 				link->flags |= DL_FLAG_PM_RUNTIME;
 			}
@@ -807,8 +806,8 @@ struct device_link *device_link_add(struct device *consumer,
 
 		if (flags & DL_FLAG_STATELESS) {
 			kref_get(&link->kref);
-			if (link->flags & DL_FLAG_SYNC_STATE_ONLY &&
-			    !(link->flags & DL_FLAG_STATELESS)) {
+			if (device_link_test(link, DL_FLAG_SYNC_STATE_ONLY) &&
+			    !device_link_test(link, DL_FLAG_STATELESS)) {
 				link->flags |= DL_FLAG_STATELESS;
 				goto reorder;
 			} else {
@@ -823,7 +822,7 @@ struct device_link *device_link_add(struct device *consumer,
 		 * update the existing link to stay around longer.
 		 */
 		if (flags & DL_FLAG_AUTOREMOVE_SUPPLIER) {
-			if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) {
+			if (device_link_test(link, DL_FLAG_AUTOREMOVE_CONSUMER)) {
 				link->flags &= ~DL_FLAG_AUTOREMOVE_CONSUMER;
 				link->flags |= DL_FLAG_AUTOREMOVE_SUPPLIER;
 			}
@@ -831,12 +830,12 @@ struct device_link *device_link_add(struct device *consumer,
 			link->flags &= ~(DL_FLAG_AUTOREMOVE_CONSUMER |
 					 DL_FLAG_AUTOREMOVE_SUPPLIER);
 		}
-		if (!(link->flags & DL_FLAG_MANAGED)) {
+		if (!device_link_test(link, DL_FLAG_MANAGED)) {
 			kref_get(&link->kref);
 			link->flags |= DL_FLAG_MANAGED;
 			device_link_init_status(link, consumer, supplier);
 		}
-		if (link->flags & DL_FLAG_SYNC_STATE_ONLY &&
+		if (device_link_test(link, DL_FLAG_SYNC_STATE_ONLY) &&
 		    !(flags & DL_FLAG_SYNC_STATE_ONLY)) {
 			link->flags &= ~DL_FLAG_SYNC_STATE_ONLY;
 			goto reorder;
@@ -940,7 +939,7 @@ static void __device_link_del(struct kref *kref)
 
 static void device_link_put_kref(struct device_link *link)
 {
-	if (link->flags & DL_FLAG_STATELESS)
+	if (device_link_test(link, DL_FLAG_STATELESS))
 		kref_put(&link->kref, __device_link_del);
 	else if (!device_is_registered(link->consumer))
 		__device_link_del(&link->kref);
@@ -1004,7 +1003,7 @@ static void device_links_missing_supplier(struct device *dev)
 		if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) {
 			WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
 		} else {
-			WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY));
+			WARN_ON(!device_link_test(link, DL_FLAG_SYNC_STATE_ONLY));
 			WRITE_ONCE(link->status, DL_STATE_DORMANT);
 		}
 	}
@@ -1072,14 +1071,14 @@ int device_links_check_suppliers(struct device *dev)
 	device_links_write_lock();
 
 	list_for_each_entry(link, &dev->links.suppliers, c_node) {
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 
 		if (link->status != DL_STATE_AVAILABLE &&
-		    !(link->flags & DL_FLAG_SYNC_STATE_ONLY)) {
+		    !device_link_test(link, DL_FLAG_SYNC_STATE_ONLY)) {
 
 			if (dev_is_best_effort(dev) &&
-			    link->flags & DL_FLAG_INFERRED &&
+			    device_link_test(link, DL_FLAG_INFERRED) &&
 			    !link->supplier->can_match) {
 				ret = -EAGAIN;
 				continue;
@@ -1128,7 +1127,7 @@ static void __device_links_queue_sync_state(struct device *dev,
 		return;
 
 	list_for_each_entry(link, &dev->links.consumers, s_node) {
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 		if (link->status != DL_STATE_ACTIVE)
 			return;
@@ -1268,7 +1267,7 @@ void device_links_force_bind(struct device *dev)
 	device_links_write_lock();
 
 	list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) {
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 
 		if (link->status != DL_STATE_AVAILABLE) {
@@ -1329,7 +1328,7 @@ void device_links_driver_bound(struct device *dev)
 	device_links_write_lock();
 
 	list_for_each_entry(link, &dev->links.consumers, s_node) {
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 
 		/*
@@ -1345,7 +1344,7 @@ void device_links_driver_bound(struct device *dev)
 		WARN_ON(link->status != DL_STATE_DORMANT);
 		WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
 
-		if (link->flags & DL_FLAG_AUTOPROBE_CONSUMER)
+		if (device_link_test(link, DL_FLAG_AUTOPROBE_CONSUMER))
 			driver_deferred_probe_add(link->consumer);
 	}
 
@@ -1357,11 +1356,11 @@ void device_links_driver_bound(struct device *dev)
 	list_for_each_entry_safe(link, ln, &dev->links.suppliers, c_node) {
 		struct device *supplier;
 
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 
 		supplier = link->supplier;
-		if (link->flags & DL_FLAG_SYNC_STATE_ONLY) {
+		if (device_link_test(link, DL_FLAG_SYNC_STATE_ONLY)) {
 			/*
 			 * When DL_FLAG_SYNC_STATE_ONLY is set, it means no
 			 * other DL_MANAGED_LINK_FLAGS have been set. So, it's
@@ -1369,7 +1368,7 @@ void device_links_driver_bound(struct device *dev)
 			 */
 			device_link_drop_managed(link);
 		} else if (dev_is_best_effort(dev) &&
-			   link->flags & DL_FLAG_INFERRED &&
+			   device_link_test(link, DL_FLAG_INFERRED) &&
 			   link->status != DL_STATE_CONSUMER_PROBE &&
 			   !link->supplier->can_match) {
 			/*
@@ -1421,10 +1420,10 @@ static void __device_links_no_driver(struct device *dev)
 	struct device_link *link, *ln;
 
 	list_for_each_entry_safe_reverse(link, ln, &dev->links.suppliers, c_node) {
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 
-		if (link->flags & DL_FLAG_AUTOREMOVE_CONSUMER) {
+		if (device_link_test(link, DL_FLAG_AUTOREMOVE_CONSUMER)) {
 			device_link_drop_managed(link);
 			continue;
 		}
@@ -1436,7 +1435,7 @@ static void __device_links_no_driver(struct device *dev)
 		if (link->supplier->links.status == DL_DEV_DRIVER_BOUND) {
 			WRITE_ONCE(link->status, DL_STATE_AVAILABLE);
 		} else {
-			WARN_ON(!(link->flags & DL_FLAG_SYNC_STATE_ONLY));
+			WARN_ON(!device_link_test(link, DL_FLAG_SYNC_STATE_ONLY));
 			WRITE_ONCE(link->status, DL_STATE_DORMANT);
 		}
 	}
@@ -1461,7 +1460,7 @@ void device_links_no_driver(struct device *dev)
 	device_links_write_lock();
 
 	list_for_each_entry(link, &dev->links.consumers, s_node) {
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 
 		/*
@@ -1498,10 +1497,10 @@ void device_links_driver_cleanup(struct device *dev)
 	device_links_write_lock();
 
 	list_for_each_entry_safe(link, ln, &dev->links.consumers, s_node) {
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 
-		WARN_ON(link->flags & DL_FLAG_AUTOREMOVE_CONSUMER);
+		WARN_ON(device_link_test(link, DL_FLAG_AUTOREMOVE_CONSUMER));
 		WARN_ON(link->status != DL_STATE_SUPPLIER_UNBIND);
 
 		/*
@@ -1510,7 +1509,7 @@ void device_links_driver_cleanup(struct device *dev)
 		 * has moved to DL_STATE_SUPPLIER_UNBIND.
 		 */
 		if (link->status == DL_STATE_SUPPLIER_UNBIND &&
-		    link->flags & DL_FLAG_AUTOREMOVE_SUPPLIER)
+		    device_link_test(link, DL_FLAG_AUTOREMOVE_SUPPLIER))
 			device_link_drop_managed(link);
 
 		WRITE_ONCE(link->status, DL_STATE_DORMANT);
@@ -1544,7 +1543,7 @@ bool device_links_busy(struct device *dev)
 	device_links_write_lock();
 
 	list_for_each_entry(link, &dev->links.consumers, s_node) {
-		if (!(link->flags & DL_FLAG_MANAGED))
+		if (!device_link_test(link, DL_FLAG_MANAGED))
 			continue;
 
 		if (link->status == DL_STATE_CONSUMER_PROBE
@@ -1586,8 +1585,8 @@ void device_links_unbind_consumers(struct device *dev)
 	list_for_each_entry(link, &dev->links.consumers, s_node) {
 		enum device_link_state status;
 
-		if (!(link->flags & DL_FLAG_MANAGED) ||
-		    link->flags & DL_FLAG_SYNC_STATE_ONLY)
+		if (!device_link_test(link, DL_FLAG_MANAGED) ||
+		    device_link_test(link, DL_FLAG_SYNC_STATE_ONLY))
 			continue;
 
 		status = link->status;
@@ -1743,7 +1742,7 @@ static void fw_devlink_parse_fwtree(struct fwnode_handle *fwnode)
 
 static void fw_devlink_relax_link(struct device_link *link)
 {
-	if (!(link->flags & DL_FLAG_INFERRED))
+	if (!device_link_test(link, DL_FLAG_INFERRED))
 		return;
 
 	if (device_link_flag_is_sync_state_only(link->flags))
@@ -1779,7 +1778,7 @@ static int fw_devlink_dev_sync_state(struct device *dev, void *data)
 	struct device_link *link = to_devlink(dev);
 	struct device *sup = link->supplier;
 
-	if (!(link->flags & DL_FLAG_MANAGED) ||
+	if (!device_link_test(link, DL_FLAG_MANAGED) ||
 	    link->status == DL_STATE_ACTIVE || sup->state_synced ||
 	    !dev_has_sync_state(sup))
 		return 0;
@@ -2063,7 +2062,7 @@ static bool __fw_devlink_relax_cycles(struct fwnode_handle *con_handle,
 		 * such due to a cycle.
 		 */
 		if (device_link_flag_is_sync_state_only(dev_link->flags) &&
-		    !(dev_link->flags & DL_FLAG_CYCLE))
+		    !device_link_test(dev_link, DL_FLAG_CYCLE))
 			continue;
 
 		if (__fw_devlink_relax_cycles(con_handle,
diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index eebe699fdf4f..6c6f8ded6877 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1998,7 +1998,7 @@ static bool device_prepare_smart_suspend(struct device *dev)
 	idx = device_links_read_lock();
 
 	list_for_each_entry_rcu_locked(link, &dev->links.suppliers, c_node) {
-		if (!(link->flags & DL_FLAG_PM_RUNTIME))
+		if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
 			continue;
 
 		if (!dev_pm_smart_suspend(link->supplier) &&
diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index c55a7c70bc1a..c67e7a6b8ed0 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -290,7 +290,7 @@ static int rpm_get_suppliers(struct device *dev)
 				device_links_read_lock_held()) {
 		int retval;
 
-		if (!(link->flags & DL_FLAG_PM_RUNTIME))
+		if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
 			continue;
 
 		retval = pm_runtime_get_sync(link->supplier);
@@ -1879,7 +1879,7 @@ void pm_runtime_get_suppliers(struct device *dev)
 
 	list_for_each_entry_rcu(link, &dev->links.suppliers, c_node,
 				device_links_read_lock_held())
-		if (link->flags & DL_FLAG_PM_RUNTIME) {
+		if (device_link_test(link, DL_FLAG_PM_RUNTIME)) {
 			link->supplier_preactivated = true;
 			pm_runtime_get_sync(link->supplier);
 		}
@@ -1933,7 +1933,7 @@ static void pm_runtime_drop_link_count(struct device *dev)
  */
 void pm_runtime_drop_link(struct device_link *link)
 {
-	if (!(link->flags & DL_FLAG_PM_RUNTIME))
+	if (!device_link_test(link, DL_FLAG_PM_RUNTIME))
 		return;
 
 	pm_runtime_drop_link_count(link->consumer);
diff --git a/include/linux/device.h b/include/linux/device.h
index 4940db137fff..afdd4f7c0d94 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1162,6 +1162,11 @@ void device_links_supplier_sync_state_pause(void);
 void device_links_supplier_sync_state_resume(void);
 void device_link_wait_removal(void);
 
+static inline bool device_link_test(const struct device_link *link, u32 flags)
+{
+	return !!(link->flags & flags);
+}
+
 /* Create alias, so I can be autoloaded. */
 #define MODULE_ALIAS_CHARDEV(major,minor) \
 	MODULE_ALIAS("char-major-" __stringify(major) "-" __stringify(minor))
-- 
cgit v1.2.3


From 5660ee54e7982f9097ddc684e90f15bdcc7fef4b Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Mon, 2 Jun 2025 13:02:13 +0200
Subject: mm, slab: use frozen pages for large kmalloc

Since slab pages are now frozen, it makes sense to have large kmalloc()
objects behave same as small kmalloc(), as the choice between the two is
an implementation detail depending on allocation size.

Notably, increasing refcount on a slab page containing kmalloc() object
is not possible anymore, so it should be consistent for large kmalloc
pages.

Therefore, change large kmalloc to use the frozen pages API.

Because of some unexpected fallout in the slab pages case (see commit
b9c0e49abfca ("mm: decline to manipulate the refcount on a slab page"),
implement the same kind of checks and warnings as part of this change.

Notably, networking code using sendpage_ok() to determine whether the
page refcount can be manipulated in the network stack should continue
behaving correctly. Before this change, the function returns true for
large kmalloc pages and page refcount can be manipulated. After this
change, the function will return false.

Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Acked-by: Harry Yoo <harry.yoo@oracle.com>
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
---
 include/linux/mm.h | 4 +++-
 mm/slub.c          | 6 +++---
 2 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0ef2ba0c667a..a35d5958603f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1325,6 +1325,8 @@ static inline void get_page(struct page *page)
 	struct folio *folio = page_folio(page);
 	if (WARN_ON_ONCE(folio_test_slab(folio)))
 		return;
+	if (WARN_ON_ONCE(folio_test_large_kmalloc(folio)))
+		return;
 	folio_get(folio);
 }
 
@@ -1419,7 +1421,7 @@ static inline void put_page(struct page *page)
 {
 	struct folio *folio = page_folio(page);
 
-	if (folio_test_slab(folio))
+	if (folio_test_slab(folio) || folio_test_large_kmalloc(folio))
 		return;
 
 	folio_put(folio);
diff --git a/mm/slub.c b/mm/slub.c
index 06d64a5fb1bf..823042efbfc9 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -4271,9 +4271,9 @@ static void *___kmalloc_large_node(size_t size, gfp_t flags, int node)
 	flags |= __GFP_COMP;
 
 	if (node == NUMA_NO_NODE)
-		folio = (struct folio *)alloc_pages_noprof(flags, order);
+		folio = (struct folio *)alloc_frozen_pages_noprof(flags, order);
 	else
-		folio = (struct folio *)__alloc_pages_noprof(flags, order, node, NULL);
+		folio = (struct folio *)__alloc_frozen_pages_noprof(flags, order, node, NULL);
 
 	if (folio) {
 		ptr = folio_address(folio);
@@ -4770,7 +4770,7 @@ static void free_large_kmalloc(struct folio *folio, void *object)
 	lruvec_stat_mod_folio(folio, NR_SLAB_UNRECLAIMABLE_B,
 			      -(PAGE_SIZE << order));
 	__folio_clear_large_kmalloc(folio);
-	folio_put(folio);
+	free_frozen_pages(&folio->page, order);
 }
 
 /*
-- 
cgit v1.2.3


From 20ca475d9860e14cf389f5a7d5ba9c6437d74613 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Mon, 16 Jun 2025 20:33:20 +0100
Subject: mm: rename call_mmap/mmap_prepare to vfs_mmap/mmap_prepare

The call_mmap() function violates the existing convention in
include/linux/fs.h whereby invocations of virtual file system hooks is
performed by functions prefixed with vfs_xxx().

Correct this by renaming call_mmap() to vfs_mmap(). This also avoids
confusion as to the fact that f_op->mmap_prepare may be invoked here.

Also rename __call_mmap_prepare() function to vfs_mmap_prepare() and adjust
to accept a file parameter, this is useful later for nested file systems.

Finally, fix up the VMA userland tests and ensure the mmap_prepare -> mmap
shim is implemented there.

Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Link: https://lore.kernel.org/8d389f4994fa736aa8f9172bef8533c10a9e9011.1750099179.git.lorenzo.stoakes@oracle.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c |  2 +-
 fs/backing-file.c                          |  2 +-
 fs/coda/file.c                             |  4 ++--
 include/linux/fs.h                         |  5 ++---
 ipc/shm.c                                  |  2 +-
 mm/internal.h                              |  2 +-
 mm/vma.c                                   |  2 +-
 tools/testing/vma/vma_internal.h           | 32 ++++++++++++++++++++++++------
 8 files changed, 35 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
index 05e440643aa2..f4f1c979d1b9 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_dmabuf.c
@@ -105,7 +105,7 @@ static int i915_gem_dmabuf_mmap(struct dma_buf *dma_buf, struct vm_area_struct *
 	if (!obj->base.filp)
 		return -ENODEV;
 
-	ret = call_mmap(obj->base.filp, vma);
+	ret = vfs_mmap(obj->base.filp, vma);
 	if (ret)
 		return ret;
 
diff --git a/fs/backing-file.c b/fs/backing-file.c
index 763fbe9b72b2..04018679bf69 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -339,7 +339,7 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
 	vma_set_file(vma, file);
 
 	old_cred = override_creds(ctx->cred);
-	ret = call_mmap(vma->vm_file, vma);
+	ret = vfs_mmap(vma->vm_file, vma);
 	revert_creds(old_cred);
 
 	if (ctx->accessed)
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 148856a582a9..2e6ea9319b35 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -199,10 +199,10 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	spin_unlock(&cii->c_lock);
 
 	vma->vm_file = get_file(host_file);
-	ret = call_mmap(vma->vm_file, vma);
+	ret = vfs_mmap(vma->vm_file, vma);
 
 	if (ret) {
-		/* if call_mmap fails, our caller will put host_file so we
+		/* if vfs_mmap fails, our caller will put host_file so we
 		 * should drop the reference to the coda_file that we got.
 		 */
 		fput(coda_file);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4ec77da65f14..c66f235f9e4d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2276,7 +2276,7 @@ static inline bool file_has_valid_mmap_hooks(struct file *file)
 
 int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma);
 
-static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
+static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	if (file->f_op->mmap_prepare)
 		return compat_vma_mmap_prepare(file, vma);
@@ -2284,8 +2284,7 @@ static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
 	return file->f_op->mmap(file, vma);
 }
 
-static inline int __call_mmap_prepare(struct file *file,
-		struct vm_area_desc *desc)
+static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
 {
 	return file->f_op->mmap_prepare(desc);
 }
diff --git a/ipc/shm.c b/ipc/shm.c
index 492fcc699985..a9310b6dbbc3 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -602,7 +602,7 @@ static int shm_mmap(struct file *file, struct vm_area_struct *vma)
 	if (ret)
 		return ret;
 
-	ret = call_mmap(sfd->file, vma);
+	ret = vfs_mmap(sfd->file, vma);
 	if (ret) {
 		__shm_close(sfd);
 		return ret;
diff --git a/mm/internal.h b/mm/internal.h
index 6b8ed2017743..0f73ff13c212 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -164,7 +164,7 @@ static inline void *folio_raw_mapping(const struct folio *folio)
  */
 static inline int mmap_file(struct file *file, struct vm_area_struct *vma)
 {
-	int err = call_mmap(file, vma);
+	int err = vfs_mmap(file, vma);
 
 	if (likely(!err))
 		return 0;
diff --git a/mm/vma.c b/mm/vma.c
index fef67a66a095..535b138e26c1 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2569,7 +2569,7 @@ static int call_mmap_prepare(struct mmap_state *map)
 	};
 
 	/* Invoke the hook. */
-	err = __call_mmap_prepare(map->file, &desc);
+	err = vfs_mmap_prepare(map->file, &desc);
 	if (err)
 		return err;
 
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 14718ca23a05..7ab04700470f 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -1442,6 +1442,27 @@ static inline void free_anon_vma_name(struct vm_area_struct *vma)
 	(void)vma;
 }
 
+/* Declared in vma.h. */
+static inline void set_vma_from_desc(struct vm_area_struct *vma,
+		struct vm_area_desc *desc);
+
+static inline struct vm_area_desc *vma_to_desc(struct vm_area_struct *vma,
+		struct vm_area_desc *desc);
+
+static int compat_vma_mmap_prepare(struct file *file,
+		struct vm_area_struct *vma)
+{
+	struct vm_area_desc desc;
+	int err;
+
+	err = file->f_op->mmap_prepare(vma_to_desc(vma, &desc));
+	if (err)
+		return err;
+	set_vma_from_desc(vma, &desc);
+
+	return 0;
+}
+
 /* Did the driver provide valid mmap hook configuration? */
 static inline bool file_has_valid_mmap_hooks(struct file *file)
 {
@@ -1451,22 +1472,21 @@ static inline bool file_has_valid_mmap_hooks(struct file *file)
 	/* Hooks are mutually exclusive. */
 	if (WARN_ON_ONCE(has_mmap && has_mmap_prepare))
 		return false;
-	if (WARN_ON_ONCE(!has_mmap && !has_mmap_prepare))
+	if (!has_mmap && !has_mmap_prepare)
 		return false;
 
 	return true;
 }
 
-static inline int call_mmap(struct file *file, struct vm_area_struct *vma)
+static inline int vfs_mmap(struct file *file, struct vm_area_struct *vma)
 {
-	if (WARN_ON_ONCE(file->f_op->mmap_prepare))
-		return -EINVAL;
+	if (file->f_op->mmap_prepare)
+		return compat_vma_mmap_prepare(file, vma);
 
 	return file->f_op->mmap(file, vma);
 }
 
-static inline int __call_mmap_prepare(struct file *file,
-		struct vm_area_desc *desc)
+static inline int vfs_mmap_prepare(struct file *file, struct vm_area_desc *desc)
 {
 	return file->f_op->mmap_prepare(desc);
 }
-- 
cgit v1.2.3


From 2b5eac0f8c6e79bc152c8804f9f88d16717013ab Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 11 Jun 2025 12:02:47 +0200
Subject: tty: introduce and use tty_port_tty_vhangup() helper
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This code (tty_get -> vhangup -> tty_put) is repeated on few places.
Introduce a helper similar to tty_port_tty_hangup() (asynchronous) to
handle even vhangup (synchronous).

And use it on those places.

In fact, reuse the tty_port_tty_hangup()'s code and call tty_vhangup()
depending on a new bool parameter.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Karsten Keil <isdn@linux-pingi.de>
Cc: David Lin <dtwlin@gmail.com>
Cc: Johan Hovold <johan@kernel.org>
Cc: Alex Elder <elder@kernel.org>
Cc: Oliver Neukum <oneukum@suse.com>
Cc: Marcel Holtmann <marcel@holtmann.org>
Cc: Johan Hedberg <johan.hedberg@gmail.com>
Cc: Luiz Augusto von Dentz <luiz.dentz@gmail.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20250611100319.186924-2-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/isdn/capi/capi.c         |  8 +-------
 drivers/staging/greybus/uart.c   |  7 +------
 drivers/tty/serial/serial_core.c |  7 +------
 drivers/tty/tty_port.c           | 12 ++++++++----
 drivers/usb/class/cdc-acm.c      |  7 +------
 drivers/usb/serial/usb-serial.c  |  7 +------
 include/linux/tty_port.h         | 12 +++++++++++-
 net/bluetooth/rfcomm/tty.c       |  7 +------
 8 files changed, 25 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/isdn/capi/capi.c b/drivers/isdn/capi/capi.c
index 70dee9ad4bae..78e6e7748fb9 100644
--- a/drivers/isdn/capi/capi.c
+++ b/drivers/isdn/capi/capi.c
@@ -306,15 +306,9 @@ static void capincci_alloc_minor(struct capidev *cdev, struct capincci *np)
 static void capincci_free_minor(struct capincci *np)
 {
 	struct capiminor *mp = np->minorp;
-	struct tty_struct *tty;
 
 	if (mp) {
-		tty = tty_port_tty_get(&mp->port);
-		if (tty) {
-			tty_vhangup(tty);
-			tty_kref_put(tty);
-		}
-
+		tty_port_tty_vhangup(&mp->port);
 		capiminor_free(mp);
 	}
 }
diff --git a/drivers/staging/greybus/uart.c b/drivers/staging/greybus/uart.c
index 308ed1ca9947..10df5c37c83e 100644
--- a/drivers/staging/greybus/uart.c
+++ b/drivers/staging/greybus/uart.c
@@ -916,7 +916,6 @@ static void gb_uart_remove(struct gbphy_device *gbphy_dev)
 {
 	struct gb_tty *gb_tty = gb_gbphy_get_data(gbphy_dev);
 	struct gb_connection *connection = gb_tty->connection;
-	struct tty_struct *tty;
 	int ret;
 
 	ret = gbphy_runtime_get_sync(gbphy_dev);
@@ -929,11 +928,7 @@ static void gb_uart_remove(struct gbphy_device *gbphy_dev)
 	wake_up_all(&gb_tty->wioctl);
 	mutex_unlock(&gb_tty->mutex);
 
-	tty = tty_port_tty_get(&gb_tty->port);
-	if (tty) {
-		tty_vhangup(tty);
-		tty_kref_put(tty);
-	}
+	tty_port_tty_vhangup(&gb_tty->port);
 
 	gb_connection_disable_rx(connection);
 	tty_unregister_device(gb_tty_driver, gb_tty->minor);
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index 1f7708a91fc6..d6485714eb0f 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -3209,7 +3209,6 @@ static void serial_core_remove_one_port(struct uart_driver *drv,
 	struct uart_state *state = drv->state + uport->line;
 	struct tty_port *port = &state->port;
 	struct uart_port *uart_port;
-	struct tty_struct *tty;
 
 	mutex_lock(&port->mutex);
 	uart_port = uart_port_check(state);
@@ -3228,11 +3227,7 @@ static void serial_core_remove_one_port(struct uart_driver *drv,
 	 */
 	tty_port_unregister_device(port, drv->tty_driver, uport->line);
 
-	tty = tty_port_tty_get(port);
-	if (tty) {
-		tty_vhangup(port->tty);
-		tty_kref_put(tty);
-	}
+	tty_port_tty_vhangup(port);
 
 	/*
 	 * If the port is used as a console, unregister it
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 4af1fbf73f51..903eebdbe12d 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -396,15 +396,19 @@ EXPORT_SYMBOL(tty_port_hangup);
  * @port: tty port
  * @check_clocal: hang only ttys with %CLOCAL unset?
  */
-void tty_port_tty_hangup(struct tty_port *port, bool check_clocal)
+void __tty_port_tty_hangup(struct tty_port *port, bool check_clocal, bool async)
 {
 	struct tty_struct *tty = tty_port_tty_get(port);
 
-	if (tty && (!check_clocal || !C_CLOCAL(tty)))
-		tty_hangup(tty);
+	if (tty && (!check_clocal || !C_CLOCAL(tty))) {
+		if (async)
+			tty_hangup(tty);
+		else
+			tty_vhangup(tty);
+	}
 	tty_kref_put(tty);
 }
-EXPORT_SYMBOL_GPL(tty_port_tty_hangup);
+EXPORT_SYMBOL_GPL(__tty_port_tty_hangup);
 
 /**
  * tty_port_tty_wakeup - helper to wake up a tty
diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
index c2ecfa3c8349..f9171fbedf5c 100644
--- a/drivers/usb/class/cdc-acm.c
+++ b/drivers/usb/class/cdc-acm.c
@@ -1571,7 +1571,6 @@ err_put_port:
 static void acm_disconnect(struct usb_interface *intf)
 {
 	struct acm *acm = usb_get_intfdata(intf);
-	struct tty_struct *tty;
 	int i;
 
 	/* sibling interface is already cleaning up */
@@ -1598,11 +1597,7 @@ static void acm_disconnect(struct usb_interface *intf)
 	usb_set_intfdata(acm->data, NULL);
 	mutex_unlock(&acm->mutex);
 
-	tty = tty_port_tty_get(&acm->port);
-	if (tty) {
-		tty_vhangup(tty);
-		tty_kref_put(tty);
-	}
+	tty_port_tty_vhangup(&acm->port);
 
 	cancel_delayed_work_sync(&acm->dwork);
 
diff --git a/drivers/usb/serial/usb-serial.c b/drivers/usb/serial/usb-serial.c
index 7266558d823a..c78ff40b1e5f 100644
--- a/drivers/usb/serial/usb-serial.c
+++ b/drivers/usb/serial/usb-serial.c
@@ -1176,7 +1176,6 @@ static void usb_serial_disconnect(struct usb_interface *interface)
 	struct usb_serial *serial = usb_get_intfdata(interface);
 	struct device *dev = &interface->dev;
 	struct usb_serial_port *port;
-	struct tty_struct *tty;
 
 	/* sibling interface is cleaning up */
 	if (!serial)
@@ -1191,11 +1190,7 @@ static void usb_serial_disconnect(struct usb_interface *interface)
 
 	for (i = 0; i < serial->num_ports; ++i) {
 		port = serial->port[i];
-		tty = tty_port_tty_get(&port->port);
-		if (tty) {
-			tty_vhangup(tty);
-			tty_kref_put(tty);
-		}
+		tty_port_tty_vhangup(&port->port);
 		usb_serial_port_poison_urbs(port);
 		wake_up_interruptible(&port->port.delta_msr_wait);
 		cancel_work_sync(&port->work);
diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h
index 08f89a598366..021f9a8415c0 100644
--- a/include/linux/tty_port.h
+++ b/include/linux/tty_port.h
@@ -232,7 +232,7 @@ bool tty_port_carrier_raised(struct tty_port *port);
 void tty_port_raise_dtr_rts(struct tty_port *port);
 void tty_port_lower_dtr_rts(struct tty_port *port);
 void tty_port_hangup(struct tty_port *port);
-void tty_port_tty_hangup(struct tty_port *port, bool check_clocal);
+void __tty_port_tty_hangup(struct tty_port *port, bool check_clocal, bool async);
 void tty_port_tty_wakeup(struct tty_port *port);
 int tty_port_block_til_ready(struct tty_port *port, struct tty_struct *tty,
 		struct file *filp);
@@ -251,4 +251,14 @@ static inline int tty_port_users(struct tty_port *port)
 	return port->count + port->blocked_open;
 }
 
+static inline void tty_port_tty_hangup(struct tty_port *port, bool check_clocal)
+{
+	__tty_port_tty_hangup(port, check_clocal, true);
+}
+
+static inline void tty_port_tty_vhangup(struct tty_port *port)
+{
+	__tty_port_tty_hangup(port, false, false);
+}
+
 #endif
diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c
index 21a5b5535ebc..827dfbe66085 100644
--- a/net/bluetooth/rfcomm/tty.c
+++ b/net/bluetooth/rfcomm/tty.c
@@ -438,7 +438,6 @@ static int __rfcomm_release_dev(void __user *arg)
 {
 	struct rfcomm_dev_req req;
 	struct rfcomm_dev *dev;
-	struct tty_struct *tty;
 
 	if (copy_from_user(&req, arg, sizeof(req)))
 		return -EFAULT;
@@ -464,11 +463,7 @@ static int __rfcomm_release_dev(void __user *arg)
 		rfcomm_dlc_close(dev->dlc, 0);
 
 	/* Shut down TTY synchronously before freeing rfcomm_dev */
-	tty = tty_port_tty_get(&dev->port);
-	if (tty) {
-		tty_vhangup(tty);
-		tty_kref_put(tty);
-	}
+	tty_port_tty_vhangup(&dev->port);
 
 	if (!test_bit(RFCOMM_TTY_OWNED, &dev->status))
 		tty_port_put(&dev->port);
-- 
cgit v1.2.3


From fc9ceb501e38cc21066c1638993500b30eda8bdb Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Wed, 11 Jun 2025 12:02:54 +0200
Subject: serial: 8250: sanitize uart_port::serial_{in,out}() types
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

uart_port::{serial_in,serial_out} (and plat_serial8250_port::* likewise)
historically use:
* 'unsigned int' for 32-bit register values in reads and writes, and
* 'int' for offsets.

Make them sane such that:
* 'u32' is used for register values, and
* 'unsigned int' is used for offsets.

While at it, name hooks' parameters, so it is clear what is what.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Paul Cercueil <paul@crapouillou.net>
Cc: Vladimir Zapolskiy <vz@mleia.com>
Cc: Kunihiko Hayashi <hayashi.kunihiko@socionext.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250611100319.186924-9-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 arch/powerpc/kernel/legacy_serial.c     |  7 ++++---
 drivers/tty/serial/8250/8250_dw.c       | 34 ++++++++++++++++-----------------
 drivers/tty/serial/8250/8250_em.c       |  4 ++--
 drivers/tty/serial/8250/8250_ingenic.c  |  8 ++++----
 drivers/tty/serial/8250/8250_ioc3.c     |  4 ++--
 drivers/tty/serial/8250/8250_lpc18xx.c  |  2 +-
 drivers/tty/serial/8250/8250_pci.c      |  6 +++---
 drivers/tty/serial/8250/8250_port.c     | 30 ++++++++++++++---------------
 drivers/tty/serial/8250/8250_rt288x.c   |  4 ++--
 drivers/tty/serial/8250/8250_uniphier.c |  4 ++--
 include/linux/serial_8250.h             |  4 ++--
 include/linux/serial_core.h             |  4 ++--
 12 files changed, 56 insertions(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kernel/legacy_serial.c b/arch/powerpc/kernel/legacy_serial.c
index a874eb8e000b..ae1906bfe8a5 100644
--- a/arch/powerpc/kernel/legacy_serial.c
+++ b/arch/powerpc/kernel/legacy_serial.c
@@ -54,9 +54,10 @@ static int legacy_serial_console = -1;
 static const upf_t legacy_port_flags = UPF_BOOT_AUTOCONF | UPF_SKIP_TEST |
 	UPF_SHARE_IRQ | UPF_FIXED_PORT;
 
-static unsigned int tsi_serial_in(struct uart_port *p, int offset)
+static u32 tsi_serial_in(struct uart_port *p, unsigned int offset)
 {
-	unsigned int tmp;
+	u32 tmp;
+
 	offset = offset << p->regshift;
 	if (offset == UART_IIR) {
 		tmp = readl(p->membase + (UART_IIR & ~3));
@@ -65,7 +66,7 @@ static unsigned int tsi_serial_in(struct uart_port *p, int offset)
 		return readb(p->membase + offset);
 }
 
-static void tsi_serial_out(struct uart_port *p, int offset, int value)
+static void tsi_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	offset = offset << p->regshift;
 	if (!((offset == UART_IER) && (value & UART_IER_UUE)))
diff --git a/drivers/tty/serial/8250/8250_dw.c b/drivers/tty/serial/8250/8250_dw.c
index 1902f29444a1..0a22f0cb8896 100644
--- a/drivers/tty/serial/8250/8250_dw.c
+++ b/drivers/tty/serial/8250/8250_dw.c
@@ -67,8 +67,8 @@ struct dw8250_data {
 	struct dw8250_port_data	data;
 	const struct dw8250_platform_data *pdata;
 
-	int			msr_mask_on;
-	int			msr_mask_off;
+	u32			msr_mask_on;
+	u32			msr_mask_off;
 	struct clk		*clk;
 	struct clk		*pclk;
 	struct notifier_block	clk_notifier;
@@ -94,7 +94,7 @@ static inline struct dw8250_data *work_to_dw8250_data(struct work_struct *work)
 	return container_of(work, struct dw8250_data, clk_work);
 }
 
-static inline int dw8250_modify_msr(struct uart_port *p, int offset, int value)
+static inline u32 dw8250_modify_msr(struct uart_port *p, unsigned int offset, u32 value)
 {
 	struct dw8250_data *d = to_dw8250_data(p->private_data);
 
@@ -145,7 +145,7 @@ static void dw8250_force_idle(struct uart_port *p)
  * routine. Hence, it must not call serial_port_out() or serial_out()
  * against the modified registers here, i.e. LCR.
  */
-static void dw8250_check_lcr(struct uart_port *p, int offset, int value)
+static void dw8250_check_lcr(struct uart_port *p, unsigned int offset, u32 value)
 {
 	struct dw8250_data *d = to_dw8250_data(p->private_data);
 	void __iomem *addr = p->membase + (offset << p->regshift);
@@ -156,7 +156,7 @@ static void dw8250_check_lcr(struct uart_port *p, int offset, int value)
 
 	/* Make sure LCR write wasn't ignored */
 	while (tries--) {
-		unsigned int lcr = serial_port_in(p, offset);
+		u32 lcr = serial_port_in(p, offset);
 
 		if ((value & ~UART_LCR_SPAR) == (lcr & ~UART_LCR_SPAR))
 			return;
@@ -205,13 +205,13 @@ static void dw8250_tx_wait_empty(struct uart_port *p)
 	}
 }
 
-static void dw8250_serial_out(struct uart_port *p, int offset, int value)
+static void dw8250_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	writeb(value, p->membase + (offset << p->regshift));
 	dw8250_check_lcr(p, offset, value);
 }
 
-static void dw8250_serial_out38x(struct uart_port *p, int offset, int value)
+static void dw8250_serial_out38x(struct uart_port *p, unsigned int offset, u32 value)
 {
 	/* Allow the TX to drain before we reconfigure */
 	if (offset == UART_LCR)
@@ -220,22 +220,22 @@ static void dw8250_serial_out38x(struct uart_port *p, int offset, int value)
 	dw8250_serial_out(p, offset, value);
 }
 
-static unsigned int dw8250_serial_in(struct uart_port *p, int offset)
+static u32 dw8250_serial_in(struct uart_port *p, unsigned int offset)
 {
-	unsigned int value = readb(p->membase + (offset << p->regshift));
+	u32 value = readb(p->membase + (offset << p->regshift));
 
 	return dw8250_modify_msr(p, offset, value);
 }
 
 #ifdef CONFIG_64BIT
-static unsigned int dw8250_serial_inq(struct uart_port *p, int offset)
+static u32 dw8250_serial_inq(struct uart_port *p, unsigned int offset)
 {
 	u8 value = __raw_readq(p->membase + (offset << p->regshift));
 
 	return dw8250_modify_msr(p, offset, value);
 }
 
-static void dw8250_serial_outq(struct uart_port *p, int offset, int value)
+static void dw8250_serial_outq(struct uart_port *p, unsigned int offset, u32 value)
 {
 	value &= 0xff;
 	__raw_writeq(value, p->membase + (offset << p->regshift));
@@ -246,28 +246,28 @@ static void dw8250_serial_outq(struct uart_port *p, int offset, int value)
 }
 #endif /* CONFIG_64BIT */
 
-static void dw8250_serial_out32(struct uart_port *p, int offset, int value)
+static void dw8250_serial_out32(struct uart_port *p, unsigned int offset, u32 value)
 {
 	writel(value, p->membase + (offset << p->regshift));
 	dw8250_check_lcr(p, offset, value);
 }
 
-static unsigned int dw8250_serial_in32(struct uart_port *p, int offset)
+static u32 dw8250_serial_in32(struct uart_port *p, unsigned int offset)
 {
-	unsigned int value = readl(p->membase + (offset << p->regshift));
+	u32 value = readl(p->membase + (offset << p->regshift));
 
 	return dw8250_modify_msr(p, offset, value);
 }
 
-static void dw8250_serial_out32be(struct uart_port *p, int offset, int value)
+static void dw8250_serial_out32be(struct uart_port *p, unsigned int offset, u32 value)
 {
 	iowrite32be(value, p->membase + (offset << p->regshift));
 	dw8250_check_lcr(p, offset, value);
 }
 
-static unsigned int dw8250_serial_in32be(struct uart_port *p, int offset)
+static u32 dw8250_serial_in32be(struct uart_port *p, unsigned int offset)
 {
-       unsigned int value = ioread32be(p->membase + (offset << p->regshift));
+       u32 value = ioread32be(p->membase + (offset << p->regshift));
 
        return dw8250_modify_msr(p, offset, value);
 }
diff --git a/drivers/tty/serial/8250/8250_em.c b/drivers/tty/serial/8250/8250_em.c
index 35094f884492..e90c71494944 100644
--- a/drivers/tty/serial/8250/8250_em.c
+++ b/drivers/tty/serial/8250/8250_em.c
@@ -59,7 +59,7 @@ static void serial8250_em_serial_out_helper(struct uart_port *p, int offset,
 	}
 }
 
-static unsigned int serial8250_em_serial_in(struct uart_port *p, int offset)
+static u32 serial8250_em_serial_in(struct uart_port *p, unsigned int offset)
 {
 	switch (offset) {
 	case UART_RX: /* RX @ 0x00 */
@@ -119,7 +119,7 @@ static void serial8250_em_reg_update(struct uart_port *p, int off, int value)
 	serial8250_em_serial_out_helper(p, UART_HCR0_EM, hcr0);
 }
 
-static void serial8250_em_serial_out(struct uart_port *p, int offset, int value)
+static void serial8250_em_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	switch (offset) {
 	case UART_TX:
diff --git a/drivers/tty/serial/8250/8250_ingenic.c b/drivers/tty/serial/8250/8250_ingenic.c
index a73dd3773640..94542fc143c2 100644
--- a/drivers/tty/serial/8250/8250_ingenic.c
+++ b/drivers/tty/serial/8250/8250_ingenic.c
@@ -168,9 +168,9 @@ OF_EARLYCON_DECLARE(jz4780_uart, "ingenic,jz4780-uart",
 OF_EARLYCON_DECLARE(x1000_uart, "ingenic,x1000-uart",
 		    ingenic_early_console_setup);
 
-static void ingenic_uart_serial_out(struct uart_port *p, int offset, int value)
+static void ingenic_uart_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
-	int ier;
+	u32 ier;
 
 	switch (offset) {
 	case UART_FCR:
@@ -206,9 +206,9 @@ static void ingenic_uart_serial_out(struct uart_port *p, int offset, int value)
 	writeb(value, p->membase + (offset << p->regshift));
 }
 
-static unsigned int ingenic_uart_serial_in(struct uart_port *p, int offset)
+static u32 ingenic_uart_serial_in(struct uart_port *p, unsigned int offset)
 {
-	unsigned int value;
+	u8 value;
 
 	value = readb(p->membase + (offset << p->regshift));
 
diff --git a/drivers/tty/serial/8250/8250_ioc3.c b/drivers/tty/serial/8250/8250_ioc3.c
index 499e80aa4cf9..3ebda9a5d07d 100644
--- a/drivers/tty/serial/8250/8250_ioc3.c
+++ b/drivers/tty/serial/8250/8250_ioc3.c
@@ -21,12 +21,12 @@ struct ioc3_8250_data {
 	int line;
 };
 
-static unsigned int ioc3_serial_in(struct uart_port *p, int offset)
+static u32 ioc3_serial_in(struct uart_port *p, unsigned int offset)
 {
 	return readb(p->membase + (offset ^ 3));
 }
 
-static void ioc3_serial_out(struct uart_port *p, int offset, int value)
+static void ioc3_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	writeb(value, p->membase + (offset ^ 3));
 }
diff --git a/drivers/tty/serial/8250/8250_lpc18xx.c b/drivers/tty/serial/8250/8250_lpc18xx.c
index d52445948da0..6c0489c9c253 100644
--- a/drivers/tty/serial/8250/8250_lpc18xx.c
+++ b/drivers/tty/serial/8250/8250_lpc18xx.c
@@ -67,7 +67,7 @@ static int lpc18xx_rs485_config(struct uart_port *port, struct ktermios *termios
 	return 0;
 }
 
-static void lpc18xx_uart_serial_out(struct uart_port *p, int offset, int value)
+static void lpc18xx_uart_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	/*
 	 * For DMA mode one must ensure that the UART_FCR_DMA_SELECT
diff --git a/drivers/tty/serial/8250/8250_pci.c b/drivers/tty/serial/8250/8250_pci.c
index 73c200127b08..152f914c599d 100644
--- a/drivers/tty/serial/8250/8250_pci.c
+++ b/drivers/tty/serial/8250/8250_pci.c
@@ -1751,7 +1751,7 @@ static int pci_fintek_init(struct pci_dev *dev)
 	return max_port;
 }
 
-static void f815xxa_mem_serial_out(struct uart_port *p, int offset, int value)
+static void f815xxa_mem_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	struct f815xxa_data *data = p->private_data;
 	unsigned long flags;
@@ -1846,10 +1846,10 @@ static void kt_handle_break(struct uart_port *p)
 	serial8250_clear_and_reinit_fifos(up);
 }
 
-static unsigned int kt_serial_in(struct uart_port *p, int offset)
+static u32 kt_serial_in(struct uart_port *p, unsigned int offset)
 {
 	struct uart_8250_port *up = up_to_u8250p(p);
-	unsigned int val;
+	u32 val;
 
 	/*
 	 * When the Intel ME (management engine) gets reset its serial
diff --git a/drivers/tty/serial/8250/8250_port.c b/drivers/tty/serial/8250/8250_port.c
index 6d7b8c4667c9..f5407832e8a7 100644
--- a/drivers/tty/serial/8250/8250_port.c
+++ b/drivers/tty/serial/8250/8250_port.c
@@ -339,14 +339,14 @@ static void default_serial_dl_write(struct uart_8250_port *up, u32 value)
 }
 
 #ifdef CONFIG_HAS_IOPORT
-static unsigned int hub6_serial_in(struct uart_port *p, int offset)
+static u32 hub6_serial_in(struct uart_port *p, unsigned int offset)
 {
 	offset = offset << p->regshift;
 	outb(p->hub6 - 1 + offset, p->iobase);
 	return inb(p->iobase + 1);
 }
 
-static void hub6_serial_out(struct uart_port *p, int offset, int value)
+static void hub6_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	offset = offset << p->regshift;
 	outb(p->hub6 - 1 + offset, p->iobase);
@@ -354,73 +354,73 @@ static void hub6_serial_out(struct uart_port *p, int offset, int value)
 }
 #endif /* CONFIG_HAS_IOPORT */
 
-static unsigned int mem_serial_in(struct uart_port *p, int offset)
+static u32 mem_serial_in(struct uart_port *p, unsigned int offset)
 {
 	offset = offset << p->regshift;
 	return readb(p->membase + offset);
 }
 
-static void mem_serial_out(struct uart_port *p, int offset, int value)
+static void mem_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	offset = offset << p->regshift;
 	writeb(value, p->membase + offset);
 }
 
-static void mem16_serial_out(struct uart_port *p, int offset, int value)
+static void mem16_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	offset = offset << p->regshift;
 	writew(value, p->membase + offset);
 }
 
-static unsigned int mem16_serial_in(struct uart_port *p, int offset)
+static u32 mem16_serial_in(struct uart_port *p, unsigned int offset)
 {
 	offset = offset << p->regshift;
 	return readw(p->membase + offset);
 }
 
-static void mem32_serial_out(struct uart_port *p, int offset, int value)
+static void mem32_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	offset = offset << p->regshift;
 	writel(value, p->membase + offset);
 }
 
-static unsigned int mem32_serial_in(struct uart_port *p, int offset)
+static u32 mem32_serial_in(struct uart_port *p, unsigned int offset)
 {
 	offset = offset << p->regshift;
 	return readl(p->membase + offset);
 }
 
-static void mem32be_serial_out(struct uart_port *p, int offset, int value)
+static void mem32be_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	offset = offset << p->regshift;
 	iowrite32be(value, p->membase + offset);
 }
 
-static unsigned int mem32be_serial_in(struct uart_port *p, int offset)
+static u32 mem32be_serial_in(struct uart_port *p, unsigned int offset)
 {
 	offset = offset << p->regshift;
 	return ioread32be(p->membase + offset);
 }
 
 #ifdef CONFIG_HAS_IOPORT
-static unsigned int io_serial_in(struct uart_port *p, int offset)
+static u32 io_serial_in(struct uart_port *p, unsigned int offset)
 {
 	offset = offset << p->regshift;
 	return inb(p->iobase + offset);
 }
 
-static void io_serial_out(struct uart_port *p, int offset, int value)
+static void io_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	offset = offset << p->regshift;
 	outb(value, p->iobase + offset);
 }
 #endif
-static unsigned int no_serial_in(struct uart_port *p, int offset)
+static u32 no_serial_in(struct uart_port *p, unsigned int offset)
 {
-	return (unsigned int)-1;
+	return ~0U;
 }
 
-static void no_serial_out(struct uart_port *p, int offset, int value)
+static void no_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 }
 
diff --git a/drivers/tty/serial/8250/8250_rt288x.c b/drivers/tty/serial/8250/8250_rt288x.c
index 6415ca8d3adf..bf28b8a9a710 100644
--- a/drivers/tty/serial/8250/8250_rt288x.c
+++ b/drivers/tty/serial/8250/8250_rt288x.c
@@ -33,7 +33,7 @@ static const u8 au_io_out_map[5] = {
 	[UART_MCR]	= 6,
 };
 
-static unsigned int au_serial_in(struct uart_port *p, int offset)
+static u32 au_serial_in(struct uart_port *p, unsigned int offset)
 {
 	if (offset >= ARRAY_SIZE(au_io_in_map))
 		return UINT_MAX;
@@ -42,7 +42,7 @@ static unsigned int au_serial_in(struct uart_port *p, int offset)
 	return __raw_readl(p->membase + (offset << p->regshift));
 }
 
-static void au_serial_out(struct uart_port *p, int offset, int value)
+static void au_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	if (offset >= ARRAY_SIZE(au_io_out_map))
 		return;
diff --git a/drivers/tty/serial/8250/8250_uniphier.c b/drivers/tty/serial/8250/8250_uniphier.c
index 4874a9632db3..e3db60bf50c9 100644
--- a/drivers/tty/serial/8250/8250_uniphier.c
+++ b/drivers/tty/serial/8250/8250_uniphier.c
@@ -63,7 +63,7 @@ OF_EARLYCON_DECLARE(uniphier, "socionext,uniphier-uart",
  * The register map is slightly different from that of 8250.
  * IO callbacks must be overridden for correct access to FCR, LCR, MCR and SCR.
  */
-static unsigned int uniphier_serial_in(struct uart_port *p, int offset)
+static u32 uniphier_serial_in(struct uart_port *p, unsigned int offset)
 {
 	unsigned int valshift = 0;
 
@@ -92,7 +92,7 @@ static unsigned int uniphier_serial_in(struct uart_port *p, int offset)
 	return (readl(p->membase + offset) >> valshift) & 0xff;
 }
 
-static void uniphier_serial_out(struct uart_port *p, int offset, int value)
+static void uniphier_serial_out(struct uart_port *p, unsigned int offset, u32 value)
 {
 	unsigned int valshift = 0;
 	bool normal = false;
diff --git a/include/linux/serial_8250.h b/include/linux/serial_8250.h
index 144de7a7948d..01efdce0fda0 100644
--- a/include/linux/serial_8250.h
+++ b/include/linux/serial_8250.h
@@ -46,8 +46,8 @@ struct plat_serial8250_port {
 	unsigned int	type;		/* If UPF_FIXED_TYPE */
 	upf_t		flags;		/* UPF_* flags */
 	u16		bugs;		/* port bugs */
-	unsigned int	(*serial_in)(struct uart_port *, int);
-	void		(*serial_out)(struct uart_port *, int, int);
+	u32		(*serial_in)(struct uart_port *, unsigned int offset);
+	void		(*serial_out)(struct uart_port *, unsigned int offset, u32 val);
 	u32		(*dl_read)(struct uart_8250_port *up);
 	void		(*dl_write)(struct uart_8250_port *up, u32 value);
 	void		(*set_termios)(struct uart_port *,
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index 914b5e97e056..d65b15449cfe 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -443,8 +443,8 @@ struct uart_port {
 	spinlock_t		lock;			/* port lock */
 	unsigned long		iobase;			/* in/out[bwl] */
 	unsigned char __iomem	*membase;		/* read/write[bwl] */
-	unsigned int		(*serial_in)(struct uart_port *, int);
-	void			(*serial_out)(struct uart_port *, int, int);
+	u32			(*serial_in)(struct uart_port *, unsigned int offset);
+	void			(*serial_out)(struct uart_port *, unsigned int offset, u32 val);
 	void			(*set_termios)(struct uart_port *,
 				               struct ktermios *new,
 				               const struct ktermios *old);
-- 
cgit v1.2.3


From b013ed403197f3f8c30ddb3ce66fe05a632b3493 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Mon, 16 Jun 2025 20:33:22 +0100
Subject: fs: consistently use can_mmap_file() helper

Since commit c84bf6dd2b83 ("mm: introduce new .mmap_prepare() file
callback"), the f_op->mmap() hook has been deprecated in favour of
f_op->mmap_prepare().

Additionally, commit bb666b7c2707 ("mm: add mmap_prepare() compatibility
layer for nested file systems") permits the use of the .mmap_prepare() hook
even in nested filesystems like overlayfs.

There are a number of places where we check only for f_op->mmap - this is
incorrect now mmap_prepare exists, so update all of these to use the
general helper can_mmap_file().

Most notably, this updates the elf logic to allow for the ability to
execute binaries on filesystems which have the .mmap_prepare hook, but
additionally we update nested filesystems.

Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Link: https://lore.kernel.org/b68145b609532e62bab603dd9686faa6562046ec.1750099179.git.lorenzo.stoakes@oracle.com
Acked-by: Kees Cook <kees@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/backing-file.c                | 2 +-
 fs/binfmt_elf.c                  | 4 ++--
 fs/binfmt_elf_fdpic.c            | 2 +-
 fs/coda/file.c                   | 2 +-
 fs/ecryptfs/file.c               | 2 +-
 include/linux/fs.h               | 2 +-
 mm/mmap.c                        | 2 +-
 mm/nommu.c                       | 2 +-
 tools/testing/vma/vma_internal.h | 2 +-
 9 files changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/backing-file.c b/fs/backing-file.c
index 04018679bf69..29748953a851 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -333,7 +333,7 @@ int backing_file_mmap(struct file *file, struct vm_area_struct *vma,
 	if (WARN_ON_ONCE(!(file->f_mode & FMODE_BACKING)))
 		return -EIO;
 
-	if (!file->f_op->mmap)
+	if (!can_mmap_file(file))
 		return -ENODEV;
 
 	vma_set_file(vma, file);
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index a43363d593e5..e3b56b603192 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -646,7 +646,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 	if (!elf_check_arch(interp_elf_ex) ||
 	    elf_check_fdpic(interp_elf_ex))
 		goto out;
-	if (!interpreter->f_op->mmap)
+	if (!can_mmap_file(interpreter))
 		goto out;
 
 	total_size = total_mapping_size(interp_elf_phdata,
@@ -848,7 +848,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		goto out;
 	if (elf_check_fdpic(elf_ex))
 		goto out;
-	if (!bprm->file->f_op->mmap)
+	if (!can_mmap_file(bprm->file))
 		goto out;
 
 	elf_phdata = load_elf_phdrs(elf_ex, bprm->file);
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index 9133f3827f90..59b138062352 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -109,7 +109,7 @@ static int is_elf(struct elfhdr *hdr, struct file *file)
 		return 0;
 	if (!elf_check_arch(hdr))
 		return 0;
-	if (!file->f_op->mmap)
+	if (!can_mmap_file(file))
 		return 0;
 	return 1;
 }
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 2e6ea9319b35..a390b5d21196 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -160,7 +160,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	size_t count;
 	int ret;
 
-	if (!host_file->f_op->mmap)
+	if (!can_mmap_file(host_file))
 		return -ENODEV;
 
 	if (WARN_ON(coda_file != vma->vm_file))
diff --git a/fs/ecryptfs/file.c b/fs/ecryptfs/file.c
index ce0a3c5ed0ca..5f8f96da09fe 100644
--- a/fs/ecryptfs/file.c
+++ b/fs/ecryptfs/file.c
@@ -193,7 +193,7 @@ static int ecryptfs_mmap(struct file *file, struct vm_area_struct *vma)
 	 * natively.  If FILESYSTEM_MAX_STACK_DEPTH > 2 or ecryptfs
 	 * allows recursive mounting, this will need to be extended.
 	 */
-	if (!lower_file->f_op->mmap)
+	if (!can_mmap_file(lower_file))
 		return -ENODEV;
 	return generic_file_mmap(file, vma);
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index c66f235f9e4d..d4fa1cb0755a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2260,7 +2260,7 @@ struct inode_operations {
 } ____cacheline_aligned;
 
 /* Did the driver provide valid mmap hook configuration? */
-static inline bool file_has_valid_mmap_hooks(struct file *file)
+static inline bool can_mmap_file(struct file *file)
 {
 	bool has_mmap = file->f_op->mmap;
 	bool has_mmap_prepare = file->f_op->mmap_prepare;
diff --git a/mm/mmap.c b/mm/mmap.c
index 09c563c95112..12c1d060f104 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -475,7 +475,7 @@ unsigned long do_mmap(struct file *file, unsigned long addr,
 				vm_flags &= ~VM_MAYEXEC;
 			}
 
-			if (!file_has_valid_mmap_hooks(file))
+			if (!can_mmap_file(file))
 				return -ENODEV;
 			if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP))
 				return -EINVAL;
diff --git a/mm/nommu.c b/mm/nommu.c
index 38c22ea0a95c..56a53de10166 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -719,7 +719,7 @@ static int validate_mmap_request(struct file *file,
 
 	if (file) {
 		/* files must support mmap */
-		if (!file_has_valid_mmap_hooks(file))
+		if (!can_mmap_file(file))
 			return -ENODEV;
 
 		/* work out if what we've got could possibly be shared
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 7ab04700470f..816e7e057585 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -1464,7 +1464,7 @@ static int compat_vma_mmap_prepare(struct file *file,
 }
 
 /* Did the driver provide valid mmap hook configuration? */
-static inline bool file_has_valid_mmap_hooks(struct file *file)
+static inline bool can_mmap_file(struct file *file)
 {
 	bool has_mmap = file->f_op->mmap;
 	bool has_mmap_prepare = file->f_op->mmap_prepare;
-- 
cgit v1.2.3


From 0335f6afd3488d1101f3b15014095fa51b978253 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Mon, 16 Jun 2025 20:33:23 +0100
Subject: fs/dax: make it possible to check dev dax support without a VMA

This is a prerequisite for adapting those filesystems to use the
.mmap_prepare() hook for mmap()'ing which invoke this check as this hook
does not have access to a VMA pointer.

To effect this, change the signature of daxdev_mapping_supported() and
update its callers (ext4 and xfs mmap()'ing hook code).

Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Link: https://lore.kernel.org/b09de1e8544384074165d92d048e80058d971286.1750099179.git.lorenzo.stoakes@oracle.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/ext4/file.c      |  2 +-
 fs/xfs/xfs_file.c   |  3 ++-
 include/linux/dax.h | 16 +++++++++-------
 3 files changed, 12 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 21df81347147..5b8b95936a4c 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -821,7 +821,7 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 	 * We don't support synchronous mappings for non-DAX files and
 	 * for DAX files if underneath dax_device is not synchronous.
 	 */
-	if (!daxdev_mapping_supported(vma, dax_dev))
+	if (!daxdev_mapping_supported(vma->vm_flags, file_inode(vma->vm_file), dax_dev))
 		return -EOPNOTSUPP;
 
 	file_accessed(file);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 48254a72071b..1160eba8727f 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1924,7 +1924,8 @@ xfs_file_mmap(
 	 * We don't support synchronous mappings for non-DAX files and
 	 * for DAX files if underneath dax_device is not synchronous.
 	 */
-	if (!daxdev_mapping_supported(vma, target->bt_daxdev))
+	if (!daxdev_mapping_supported(vma->vm_flags, file_inode(vma->vm_file),
+				      target->bt_daxdev))
 		return -EOPNOTSUPP;
 
 	file_accessed(file);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index dcc9fcdf14e4..78891518291d 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -65,12 +65,13 @@ size_t dax_recovery_write(struct dax_device *dax_dev, pgoff_t pgoff,
 /*
  * Check if given mapping is supported by the file / underlying device.
  */
-static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
-					     struct dax_device *dax_dev)
+static inline bool daxdev_mapping_supported(vm_flags_t vm_flags,
+					    const struct inode *inode,
+					    struct dax_device *dax_dev)
 {
-	if (!(vma->vm_flags & VM_SYNC))
+	if (!(vm_flags & VM_SYNC))
 		return true;
-	if (!IS_DAX(file_inode(vma->vm_file)))
+	if (!IS_DAX(inode))
 		return false;
 	return dax_synchronous(dax_dev);
 }
@@ -110,10 +111,11 @@ static inline void set_dax_nomc(struct dax_device *dax_dev)
 static inline void set_dax_synchronous(struct dax_device *dax_dev)
 {
 }
-static inline bool daxdev_mapping_supported(struct vm_area_struct *vma,
-				struct dax_device *dax_dev)
+static inline bool daxdev_mapping_supported(vm_flags_t vm_flags,
+					    const struct inode *inode,
+					    struct dax_device *dax_dev)
 {
-	return !(vma->vm_flags & VM_SYNC);
+	return !(vm_flags & VM_SYNC);
 }
 static inline size_t dax_recovery_write(struct dax_device *dax_dev,
 		pgoff_t pgoff, void *addr, size_t bytes, struct iov_iter *i)
-- 
cgit v1.2.3


From 5b44297bcfa49ee197cdb8ca6164bef120c4e73c Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Mon, 16 Jun 2025 20:33:26 +0100
Subject: mm/filemap: introduce generic_file_*_mmap_prepare() helpers

Since commit c84bf6dd2b83 ("mm: introduce new .mmap_prepare() file
callback"), the f_op->mmap() hook has been deprecated in favour of
f_op->mmap_prepare().

The generic mmap handlers are very simple, so we can very easily convert
these in advance of converting file systems which use them.

This patch does so.

Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Link: https://lore.kernel.org/30622c1f0b98c66840bc8c02668bda276a810b70.1750099179.git.lorenzo.stoakes@oracle.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs.h |  6 ++++--
 mm/filemap.c       | 29 +++++++++++++++++++++++++++++
 2 files changed, 33 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index d4fa1cb0755a..fd5e7409489d 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3393,8 +3393,10 @@ extern void inode_add_lru(struct inode *inode);
 extern int sb_set_blocksize(struct super_block *, int);
 extern int sb_min_blocksize(struct super_block *, int);
 
-extern int generic_file_mmap(struct file *, struct vm_area_struct *);
-extern int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
+int generic_file_mmap(struct file *, struct vm_area_struct *);
+int generic_file_mmap_prepare(struct vm_area_desc *desc);
+int generic_file_readonly_mmap(struct file *, struct vm_area_struct *);
+int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc);
 extern ssize_t generic_write_checks(struct kiocb *, struct iov_iter *);
 int generic_write_checks_count(struct kiocb *iocb, loff_t *count);
 extern int generic_write_check_limits(struct file *file, loff_t pos,
diff --git a/mm/filemap.c b/mm/filemap.c
index bada249b9fb7..77e1bac30490 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3814,6 +3814,18 @@ int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+int generic_file_mmap_prepare(struct vm_area_desc *desc)
+{
+	struct file *file = desc->file;
+	struct address_space *mapping = file->f_mapping;
+
+	if (!mapping->a_ops->read_folio)
+		return -ENOEXEC;
+	file_accessed(file);
+	desc->vm_ops = &generic_file_vm_ops;
+	return 0;
+}
+
 /*
  * This is for filesystems which do not implement ->writepage.
  */
@@ -3823,6 +3835,13 @@ int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EINVAL;
 	return generic_file_mmap(file, vma);
 }
+
+int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc)
+{
+	if (is_shared_maywrite(desc->vm_flags))
+		return -EINVAL;
+	return generic_file_mmap_prepare(desc);
+}
 #else
 vm_fault_t filemap_page_mkwrite(struct vm_fault *vmf)
 {
@@ -3832,15 +3851,25 @@ int generic_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	return -ENOSYS;
 }
+int generic_file_mmap_prepare(struct vm_area_desc *desc)
+{
+	return -ENOSYS;
+}
 int generic_file_readonly_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	return -ENOSYS;
 }
+int generic_file_readonly_mmap_prepare(struct vm_area_desc *desc)
+{
+	return -ENOSYS;
+}
 #endif /* CONFIG_MMU */
 
 EXPORT_SYMBOL(filemap_page_mkwrite);
 EXPORT_SYMBOL(generic_file_mmap);
+EXPORT_SYMBOL(generic_file_mmap_prepare);
 EXPORT_SYMBOL(generic_file_readonly_mmap);
+EXPORT_SYMBOL(generic_file_readonly_mmap_prepare);
 
 static struct folio *do_read_cache_folio(struct address_space *mapping,
 		pgoff_t index, filler_t filler, struct file *file, gfp_t gfp)
-- 
cgit v1.2.3


From a85b8544d46390469b6ca72d6bfd3ecb7be985ff Mon Sep 17 00:00:00 2001
From: Johannes Berg <johannes.berg@intel.com>
Date: Sat, 14 Jun 2025 00:30:37 +0200
Subject: wifi: remove zero-length arrays

All of these are really meant to be variable-length, and
in the case of s1g_beacon it's actually accessed. Make that
one in particular, and a couple of others (that aren't used
as arrays now), actually variable.

Reported-by: syzbot+fd222bb38e916df26fa4@syzkaller.appspotmail.com
Fixes: 1e1f706fc2ce ("wifi: cfg80211/mac80211: correctly parse S1G beacon optional elements")
Link: https://patch.msgid.link/20250614003037.a3e82e882251.I2e8b58e56ff2a9f8b06c66f036578b7c1d4e4685@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index ce377f7fb912..22f39e5e2ff1 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -1278,7 +1278,7 @@ struct ieee80211_ext {
 			u8 sa[ETH_ALEN];
 			__le32 timestamp;
 			u8 change_seq;
-			u8 variable[0];
+			u8 variable[];
 		} __packed s1g_beacon;
 	} u;
 } __packed __aligned(2);
@@ -1536,7 +1536,7 @@ struct ieee80211_mgmt {
 					u8 action_code;
 					u8 dialog_token;
 					__le16 capability;
-					u8 variable[0];
+					u8 variable[];
 				} __packed tdls_discover_resp;
 				struct {
 					u8 action_code;
@@ -1721,35 +1721,35 @@ struct ieee80211_tdls_data {
 		struct {
 			u8 dialog_token;
 			__le16 capability;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_req;
 		struct {
 			__le16 status_code;
 			u8 dialog_token;
 			__le16 capability;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_resp;
 		struct {
 			__le16 status_code;
 			u8 dialog_token;
-			u8 variable[0];
+			u8 variable[];
 		} __packed setup_cfm;
 		struct {
 			__le16 reason_code;
-			u8 variable[0];
+			u8 variable[];
 		} __packed teardown;
 		struct {
 			u8 dialog_token;
-			u8 variable[0];
+			u8 variable[];
 		} __packed discover_req;
 		struct {
 			u8 target_channel;
 			u8 oper_class;
-			u8 variable[0];
+			u8 variable[];
 		} __packed chan_switch_req;
 		struct {
 			__le16 status_code;
-			u8 variable[0];
+			u8 variable[];
 		} __packed chan_switch_resp;
 	} u;
 } __packed;
-- 
cgit v1.2.3


From d8010d4ba43e9f790925375a7de100604a5e2dba Mon Sep 17 00:00:00 2001
From: "Borislav Petkov (AMD)" <bp@alien8.de>
Date: Wed, 11 Sep 2024 10:53:08 +0200
Subject: x86/bugs: Add a Transient Scheduler Attacks mitigation

Add the required features detection glue to bugs.c et all in order to
support the TSA mitigation.

Co-developed-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Reviewed-by: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
---
 Documentation/ABI/testing/sysfs-devices-system-cpu |   1 +
 Documentation/admin-guide/kernel-parameters.txt    |  13 +++
 arch/x86/Kconfig                                   |   9 ++
 arch/x86/include/asm/cpufeatures.h                 |   6 +-
 arch/x86/include/asm/mwait.h                       |   2 +-
 arch/x86/include/asm/nospec-branch.h               |  14 ++-
 arch/x86/kernel/cpu/amd.c                          |  44 ++++++++
 arch/x86/kernel/cpu/bugs.c                         | 124 +++++++++++++++++++++
 arch/x86/kernel/cpu/common.c                       |  14 ++-
 arch/x86/kernel/cpu/scattered.c                    |   2 +
 arch/x86/kvm/svm/vmenter.S                         |   6 +
 drivers/base/cpu.c                                 |   3 +
 include/linux/cpu.h                                |   1 +
 13 files changed, 232 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
index bf85f4de6862..ab8cd337f43a 100644
--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
+++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
@@ -584,6 +584,7 @@ What:		/sys/devices/system/cpu/vulnerabilities
 		/sys/devices/system/cpu/vulnerabilities/spectre_v1
 		/sys/devices/system/cpu/vulnerabilities/spectre_v2
 		/sys/devices/system/cpu/vulnerabilities/srbds
+		/sys/devices/system/cpu/vulnerabilities/tsa
 		/sys/devices/system/cpu/vulnerabilities/tsx_async_abort
 Date:		January 2018
 Contact:	Linux kernel mailing list <linux-kernel@vger.kernel.org>
diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index f1f2c0874da9..07e22ba5bfe3 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -7488,6 +7488,19 @@
 			having this key zero'ed is acceptable. E.g. in testing
 			scenarios.
 
+	tsa=		[X86] Control mitigation for Transient Scheduler
+			Attacks on AMD CPUs. Search the following in your
+			favourite search engine for more details:
+
+			"Technical guidance for mitigating transient scheduler
+			attacks".
+
+			off		- disable the mitigation
+			on		- enable the mitigation (default)
+			user		- mitigate only user/kernel transitions
+			vm		- mitigate only guest/host transitions
+
+
 	tsc=		Disable clocksource stability checks for TSC.
 			Format: <string>
 			[x86] reliable: mark tsc clocksource as reliable, this
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 340e5468980e..71dfe7d7c786 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -2695,6 +2695,15 @@ config MITIGATION_ITS
 	  disabled, mitigation cannot be enabled via cmdline.
 	  See <file:Documentation/admin-guide/hw-vuln/indirect-target-selection.rst>
 
+config MITIGATION_TSA
+	bool "Mitigate Transient Scheduler Attacks"
+	depends on CPU_SUP_AMD
+	default y
+	help
+	  Enable mitigation for Transient Scheduler Attacks. TSA is a hardware
+	  security vulnerability on AMD CPUs which can lead to forwarding of
+	  invalid info to subsequent instructions and thus can affect their
+	  timing and thereby cause a leakage.
 endif
 
 config ARCH_HAS_ADD_PAGES
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index ee176236c2be..286d509f9363 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -456,6 +456,7 @@
 #define X86_FEATURE_NO_NESTED_DATA_BP	(20*32+ 0) /* No Nested Data Breakpoints */
 #define X86_FEATURE_WRMSR_XX_BASE_NS	(20*32+ 1) /* WRMSR to {FS,GS,KERNEL_GS}_BASE is non-serializing */
 #define X86_FEATURE_LFENCE_RDTSC	(20*32+ 2) /* LFENCE always serializing / synchronizes RDTSC */
+#define X86_FEATURE_VERW_CLEAR		(20*32+ 5) /* The memory form of VERW mitigates TSA */
 #define X86_FEATURE_NULL_SEL_CLR_BASE	(20*32+ 6) /* Null Selector Clears Base */
 #define X86_FEATURE_AUTOIBRS		(20*32+ 8) /* Automatic IBRS */
 #define X86_FEATURE_NO_SMM_CTL_MSR	(20*32+ 9) /* SMM_CTL MSR is not present */
@@ -487,6 +488,9 @@
 #define X86_FEATURE_PREFER_YMM		(21*32+ 8) /* Avoid ZMM registers due to downclocking */
 #define X86_FEATURE_APX			(21*32+ 9) /* Advanced Performance Extensions */
 #define X86_FEATURE_INDIRECT_THUNK_ITS	(21*32+10) /* Use thunk for indirect branches in lower half of cacheline */
+#define X86_FEATURE_TSA_SQ_NO		(21*32+11) /* AMD CPU not vulnerable to TSA-SQ */
+#define X86_FEATURE_TSA_L1_NO		(21*32+12) /* AMD CPU not vulnerable to TSA-L1 */
+#define X86_FEATURE_CLEAR_CPU_BUF_VM	(21*32+13) /* Clear CPU buffers using VERW before VMRUN */
 
 /*
  * BUG word(s)
@@ -542,5 +546,5 @@
 #define X86_BUG_OLD_MICROCODE		X86_BUG( 1*32+ 6) /* "old_microcode" CPU has old microcode, it is surely vulnerable to something */
 #define X86_BUG_ITS			X86_BUG( 1*32+ 7) /* "its" CPU is affected by Indirect Target Selection */
 #define X86_BUG_ITS_NATIVE_ONLY		X86_BUG( 1*32+ 8) /* "its_native_only" CPU is affected by ITS, VMX is not affected */
-
+#define X86_BUG_TSA			X86_BUG( 1*32+ 9) /* "tsa" CPU is affected by Transient Scheduler Attacks */
 #endif /* _ASM_X86_CPUFEATURES_H */
diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index cc34c3fd197b..82bd9eb73b3c 100644
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -80,7 +80,7 @@ static __always_inline void __mwait(u32 eax, u32 ecx)
  */
 static __always_inline void __mwaitx(u32 eax, u32 ebx, u32 ecx)
 {
-	/* No MDS buffer clear as this is AMD/HYGON only */
+	/* No need for TSA buffer clearing on AMD */
 
 	/* "mwaitx %eax, %ebx, %ecx" */
 	asm volatile(".byte 0x0f, 0x01, 0xfb"
diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h
index 5dcd75bb5e0d..10f261678749 100644
--- a/arch/x86/include/asm/nospec-branch.h
+++ b/arch/x86/include/asm/nospec-branch.h
@@ -308,19 +308,25 @@
  * CFLAGS.ZF.
  * Note: Only the memory operand variant of VERW clears the CPU buffers.
  */
-.macro CLEAR_CPU_BUFFERS
+.macro __CLEAR_CPU_BUFFERS feature
 #ifdef CONFIG_X86_64
-	ALTERNATIVE "", "verw x86_verw_sel(%rip)", X86_FEATURE_CLEAR_CPU_BUF
+	ALTERNATIVE "", "verw x86_verw_sel(%rip)", \feature
 #else
 	/*
 	 * In 32bit mode, the memory operand must be a %cs reference. The data
 	 * segments may not be usable (vm86 mode), and the stack segment may not
 	 * be flat (ESPFIX32).
 	 */
-	ALTERNATIVE "", "verw %cs:x86_verw_sel", X86_FEATURE_CLEAR_CPU_BUF
+	ALTERNATIVE "", "verw %cs:x86_verw_sel", \feature
 #endif
 .endm
 
+#define CLEAR_CPU_BUFFERS \
+	__CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF
+
+#define VM_CLEAR_CPU_BUFFERS \
+	__CLEAR_CPU_BUFFERS X86_FEATURE_CLEAR_CPU_BUF_VM
+
 #ifdef CONFIG_X86_64
 .macro CLEAR_BRANCH_HISTORY
 	ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP
@@ -602,7 +608,7 @@ static __always_inline void x86_clear_cpu_buffers(void)
 
 /**
  * x86_idle_clear_cpu_buffers - Buffer clearing support in idle for the MDS
- * vulnerability
+ * and TSA vulnerabilities.
  *
  * Clear CPU buffers if the corresponding static key is enabled
  */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 93da466dfe2c..23c535871a7e 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -377,6 +377,47 @@ static void bsp_determine_snp(struct cpuinfo_x86 *c)
 #endif
 }
 
+#define ZEN_MODEL_STEP_UCODE(fam, model, step, ucode) \
+	X86_MATCH_VFM_STEPS(VFM_MAKE(X86_VENDOR_AMD, fam, model), \
+			    step, step, ucode)
+
+static const struct x86_cpu_id amd_tsa_microcode[] = {
+	ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x1, 0x0a0011d7),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x01, 0x2, 0x0a00123b),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x08, 0x2, 0x0a00820d),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x1, 0x0a10114c),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x11, 0x2, 0x0a10124c),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x18, 0x1, 0x0a108109),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x0, 0x0a20102e),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x21, 0x2, 0x0a201211),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x44, 0x1, 0x0a404108),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x50, 0x0, 0x0a500012),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x61, 0x2, 0x0a60120a),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x74, 0x1, 0x0a704108),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x75, 0x2, 0x0a705208),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x78, 0x0, 0x0a708008),
+	ZEN_MODEL_STEP_UCODE(0x19, 0x7c, 0x0, 0x0a70c008),
+	ZEN_MODEL_STEP_UCODE(0x19, 0xa0, 0x2, 0x0aa00216),
+	{},
+};
+
+static void tsa_init(struct cpuinfo_x86 *c)
+{
+	if (cpu_has(c, X86_FEATURE_HYPERVISOR))
+		return;
+
+	if (cpu_has(c, X86_FEATURE_ZEN3) ||
+	    cpu_has(c, X86_FEATURE_ZEN4)) {
+		if (x86_match_min_microcode_rev(amd_tsa_microcode))
+			setup_force_cpu_cap(X86_FEATURE_VERW_CLEAR);
+		else
+			pr_debug("%s: current revision: 0x%x\n", __func__, c->microcode);
+	} else {
+		setup_force_cpu_cap(X86_FEATURE_TSA_SQ_NO);
+		setup_force_cpu_cap(X86_FEATURE_TSA_L1_NO);
+	}
+}
+
 static void bsp_init_amd(struct cpuinfo_x86 *c)
 {
 	if (cpu_has(c, X86_FEATURE_CONSTANT_TSC)) {
@@ -489,6 +530,9 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
 	}
 
 	bsp_determine_snp(c);
+
+	tsa_init(c);
+
 	return;
 
 warn:
diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c
index 258ed3d2b6a9..f4d3abb12317 100644
--- a/arch/x86/kernel/cpu/bugs.c
+++ b/arch/x86/kernel/cpu/bugs.c
@@ -94,6 +94,8 @@ static void __init bhi_apply_mitigation(void);
 static void __init its_select_mitigation(void);
 static void __init its_update_mitigation(void);
 static void __init its_apply_mitigation(void);
+static void __init tsa_select_mitigation(void);
+static void __init tsa_apply_mitigation(void);
 
 /* The base value of the SPEC_CTRL MSR without task-specific bits set */
 u64 x86_spec_ctrl_base;
@@ -225,6 +227,7 @@ void __init cpu_select_mitigations(void)
 	gds_select_mitigation();
 	its_select_mitigation();
 	bhi_select_mitigation();
+	tsa_select_mitigation();
 
 	/*
 	 * After mitigations are selected, some may need to update their
@@ -272,6 +275,7 @@ void __init cpu_select_mitigations(void)
 	gds_apply_mitigation();
 	its_apply_mitigation();
 	bhi_apply_mitigation();
+	tsa_apply_mitigation();
 }
 
 /*
@@ -1487,6 +1491,94 @@ static void __init its_apply_mitigation(void)
 	set_return_thunk(its_return_thunk);
 }
 
+#undef pr_fmt
+#define pr_fmt(fmt)	"Transient Scheduler Attacks: " fmt
+
+enum tsa_mitigations {
+	TSA_MITIGATION_NONE,
+	TSA_MITIGATION_AUTO,
+	TSA_MITIGATION_UCODE_NEEDED,
+	TSA_MITIGATION_USER_KERNEL,
+	TSA_MITIGATION_VM,
+	TSA_MITIGATION_FULL,
+};
+
+static const char * const tsa_strings[] = {
+	[TSA_MITIGATION_NONE]		= "Vulnerable",
+	[TSA_MITIGATION_UCODE_NEEDED]	= "Vulnerable: No microcode",
+	[TSA_MITIGATION_USER_KERNEL]	= "Mitigation: Clear CPU buffers: user/kernel boundary",
+	[TSA_MITIGATION_VM]		= "Mitigation: Clear CPU buffers: VM",
+	[TSA_MITIGATION_FULL]		= "Mitigation: Clear CPU buffers",
+};
+
+static enum tsa_mitigations tsa_mitigation __ro_after_init =
+	IS_ENABLED(CONFIG_MITIGATION_TSA) ? TSA_MITIGATION_AUTO : TSA_MITIGATION_NONE;
+
+static int __init tsa_parse_cmdline(char *str)
+{
+	if (!str)
+		return -EINVAL;
+
+	if (!strcmp(str, "off"))
+		tsa_mitigation = TSA_MITIGATION_NONE;
+	else if (!strcmp(str, "on"))
+		tsa_mitigation = TSA_MITIGATION_FULL;
+	else if (!strcmp(str, "user"))
+		tsa_mitigation = TSA_MITIGATION_USER_KERNEL;
+	else if (!strcmp(str, "vm"))
+		tsa_mitigation = TSA_MITIGATION_VM;
+	else
+		pr_err("Ignoring unknown tsa=%s option.\n", str);
+
+	return 0;
+}
+early_param("tsa", tsa_parse_cmdline);
+
+static void __init tsa_select_mitigation(void)
+{
+	if (cpu_mitigations_off() || !boot_cpu_has_bug(X86_BUG_TSA)) {
+		tsa_mitigation = TSA_MITIGATION_NONE;
+		return;
+	}
+
+	if (tsa_mitigation == TSA_MITIGATION_NONE)
+		return;
+
+	if (!boot_cpu_has(X86_FEATURE_VERW_CLEAR)) {
+		tsa_mitigation = TSA_MITIGATION_UCODE_NEEDED;
+		goto out;
+	}
+
+	if (tsa_mitigation == TSA_MITIGATION_AUTO)
+		tsa_mitigation = TSA_MITIGATION_FULL;
+
+	/*
+	 * No need to set verw_clear_cpu_buf_mitigation_selected - it
+	 * doesn't fit all cases here and it is not needed because this
+	 * is the only VERW-based mitigation on AMD.
+	 */
+out:
+	pr_info("%s\n", tsa_strings[tsa_mitigation]);
+}
+
+static void __init tsa_apply_mitigation(void)
+{
+	switch (tsa_mitigation) {
+	case TSA_MITIGATION_USER_KERNEL:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+		break;
+	case TSA_MITIGATION_VM:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+		break;
+	case TSA_MITIGATION_FULL:
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF);
+		setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF_VM);
+		break;
+	default:
+		break;
+	}
+}
+
 #undef pr_fmt
 #define pr_fmt(fmt)     "Spectre V2 : " fmt
 
@@ -2316,6 +2408,25 @@ void cpu_bugs_smt_update(void)
 		break;
 	}
 
+	switch (tsa_mitigation) {
+	case TSA_MITIGATION_USER_KERNEL:
+	case TSA_MITIGATION_VM:
+	case TSA_MITIGATION_AUTO:
+	case TSA_MITIGATION_FULL:
+		/*
+		 * TSA-SQ can potentially lead to info leakage between
+		 * SMT threads.
+		 */
+		if (sched_smt_active())
+			static_branch_enable(&cpu_buf_idle_clear);
+		else
+			static_branch_disable(&cpu_buf_idle_clear);
+		break;
+	case TSA_MITIGATION_NONE:
+	case TSA_MITIGATION_UCODE_NEEDED:
+		break;
+	}
+
 	mutex_unlock(&spec_ctrl_mutex);
 }
 
@@ -3265,6 +3376,11 @@ static ssize_t gds_show_state(char *buf)
 	return sysfs_emit(buf, "%s\n", gds_strings[gds_mitigation]);
 }
 
+static ssize_t tsa_show_state(char *buf)
+{
+	return sysfs_emit(buf, "%s\n", tsa_strings[tsa_mitigation]);
+}
+
 static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr,
 			       char *buf, unsigned int bug)
 {
@@ -3328,6 +3444,9 @@ static ssize_t cpu_show_common(struct device *dev, struct device_attribute *attr
 	case X86_BUG_ITS:
 		return its_show_state(buf);
 
+	case X86_BUG_TSA:
+		return tsa_show_state(buf);
+
 	default:
 		break;
 	}
@@ -3414,6 +3533,11 @@ ssize_t cpu_show_indirect_target_selection(struct device *dev, struct device_att
 {
 	return cpu_show_common(dev, attr, buf, X86_BUG_ITS);
 }
+
+ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	return cpu_show_common(dev, attr, buf, X86_BUG_TSA);
+}
 #endif
 
 void __warn_thunk(void)
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index 8feb8fd2957a..f7b9fca82bda 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -1233,6 +1233,8 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = {
 #define ITS		BIT(8)
 /* CPU is affected by Indirect Target Selection, but guest-host isolation is not affected */
 #define ITS_NATIVE_ONLY	BIT(9)
+/* CPU is affected by Transient Scheduler Attacks */
+#define TSA		BIT(10)
 
 static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_INTEL_STEPS(INTEL_IVYBRIDGE,	     X86_STEP_MAX,	SRBDS),
@@ -1280,7 +1282,7 @@ static const struct x86_cpu_id cpu_vuln_blacklist[] __initconst = {
 	VULNBL_AMD(0x16, RETBLEED),
 	VULNBL_AMD(0x17, RETBLEED | SMT_RSB | SRSO),
 	VULNBL_HYGON(0x18, RETBLEED | SMT_RSB | SRSO),
-	VULNBL_AMD(0x19, SRSO),
+	VULNBL_AMD(0x19, SRSO | TSA),
 	VULNBL_AMD(0x1a, SRSO),
 	{}
 };
@@ -1530,6 +1532,16 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c)
 			setup_force_cpu_bug(X86_BUG_ITS_NATIVE_ONLY);
 	}
 
+	if (c->x86_vendor == X86_VENDOR_AMD) {
+		if (!cpu_has(c, X86_FEATURE_TSA_SQ_NO) ||
+		    !cpu_has(c, X86_FEATURE_TSA_L1_NO)) {
+			if (cpu_matches(cpu_vuln_blacklist, TSA) ||
+			    /* Enable bug on Zen guests to allow for live migration. */
+			    (cpu_has(c, X86_FEATURE_HYPERVISOR) && cpu_has(c, X86_FEATURE_ZEN)))
+				setup_force_cpu_bug(X86_BUG_TSA);
+		}
+	}
+
 	if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN))
 		return;
 
diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c
index dbf6d71bdf18..b4a1f6732a3a 100644
--- a/arch/x86/kernel/cpu/scattered.c
+++ b/arch/x86/kernel/cpu/scattered.c
@@ -50,6 +50,8 @@ static const struct cpuid_bit cpuid_bits[] = {
 	{ X86_FEATURE_MBA,			CPUID_EBX,  6, 0x80000008, 0 },
 	{ X86_FEATURE_SMBA,			CPUID_EBX,  2, 0x80000020, 0 },
 	{ X86_FEATURE_BMEC,			CPUID_EBX,  3, 0x80000020, 0 },
+	{ X86_FEATURE_TSA_SQ_NO,		CPUID_ECX,  1, 0x80000021, 0 },
+	{ X86_FEATURE_TSA_L1_NO,		CPUID_ECX,  2, 0x80000021, 0 },
 	{ X86_FEATURE_AMD_WORKLOAD_CLASS,	CPUID_EAX, 22, 0x80000021, 0 },
 	{ X86_FEATURE_PERFMON_V2,		CPUID_EAX,  0, 0x80000022, 0 },
 	{ X86_FEATURE_AMD_LBR_V2,		CPUID_EAX,  1, 0x80000022, 0 },
diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S
index 0c61153b275f..235c4af6b692 100644
--- a/arch/x86/kvm/svm/vmenter.S
+++ b/arch/x86/kvm/svm/vmenter.S
@@ -169,6 +169,9 @@ SYM_FUNC_START(__svm_vcpu_run)
 #endif
 	mov VCPU_RDI(%_ASM_DI), %_ASM_DI
 
+	/* Clobbers EFLAGS.ZF */
+	VM_CLEAR_CPU_BUFFERS
+
 	/* Enter guest mode */
 3:	vmrun %_ASM_AX
 4:
@@ -335,6 +338,9 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run)
 	mov SVM_current_vmcb(%rdi), %rax
 	mov KVM_VMCB_pa(%rax), %rax
 
+	/* Clobbers EFLAGS.ZF */
+	VM_CLEAR_CPU_BUFFERS
+
 	/* Enter guest mode */
 1:	vmrun %rax
 2:
diff --git a/drivers/base/cpu.c b/drivers/base/cpu.c
index 7779ab0ca7ce..efc575a00edd 100644
--- a/drivers/base/cpu.c
+++ b/drivers/base/cpu.c
@@ -602,6 +602,7 @@ CPU_SHOW_VULN_FALLBACK(reg_file_data_sampling);
 CPU_SHOW_VULN_FALLBACK(ghostwrite);
 CPU_SHOW_VULN_FALLBACK(old_microcode);
 CPU_SHOW_VULN_FALLBACK(indirect_target_selection);
+CPU_SHOW_VULN_FALLBACK(tsa);
 
 static DEVICE_ATTR(meltdown, 0444, cpu_show_meltdown, NULL);
 static DEVICE_ATTR(spectre_v1, 0444, cpu_show_spectre_v1, NULL);
@@ -620,6 +621,7 @@ static DEVICE_ATTR(reg_file_data_sampling, 0444, cpu_show_reg_file_data_sampling
 static DEVICE_ATTR(ghostwrite, 0444, cpu_show_ghostwrite, NULL);
 static DEVICE_ATTR(old_microcode, 0444, cpu_show_old_microcode, NULL);
 static DEVICE_ATTR(indirect_target_selection, 0444, cpu_show_indirect_target_selection, NULL);
+static DEVICE_ATTR(tsa, 0444, cpu_show_tsa, NULL);
 
 static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_meltdown.attr,
@@ -639,6 +641,7 @@ static struct attribute *cpu_root_vulnerabilities_attrs[] = {
 	&dev_attr_ghostwrite.attr,
 	&dev_attr_old_microcode.attr,
 	&dev_attr_indirect_target_selection.attr,
+	&dev_attr_tsa.attr,
 	NULL
 };
 
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 96a3a0d6a60e..6378370a952f 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -82,6 +82,7 @@ extern ssize_t cpu_show_old_microcode(struct device *dev,
 				      struct device_attribute *attr, char *buf);
 extern ssize_t cpu_show_indirect_target_selection(struct device *dev,
 						  struct device_attribute *attr, char *buf);
+extern ssize_t cpu_show_tsa(struct device *dev, struct device_attribute *attr, char *buf);
 
 extern __printf(4, 5)
 struct device *cpu_device_create(struct device *parent, void *drvdata,
-- 
cgit v1.2.3


From 128ea9f6ccfb6960293ae4212f4f97165e42222d Mon Sep 17 00:00:00 2001
From: Marco Crivellari <marco.crivellari@suse.com>
Date: Sat, 14 Jun 2025 15:35:29 +0200
Subject: workqueue: Add system_percpu_wq and system_dfl_wq

Currently, if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.

This lack of consistentcy cannot be addressed without refactoring the API.

system_wq is a per-CPU worqueue, yet nothing in its name tells about that
CPU affinity constraint, which is very often not required by users. Make it
clear by adding a system_percpu_wq.

system_unbound_wq should be the default workqueue so as not to enforce
locality constraints for random work whenever it's not required.

Adding system_dfl_wq to encourage its use when unbound work should be used.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/workqueue.h |  8 +++++---
 kernel/workqueue.c        | 13 +++++++++----
 2 files changed, 14 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index b0dc957c3e56..74b0042709cd 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -427,7 +427,7 @@ enum wq_consts {
 /*
  * System-wide workqueues which are always present.
  *
- * system_wq is the one used by schedule[_delayed]_work[_on]().
+ * system_percpu_wq is the one used by schedule[_delayed]_work[_on]().
  * Multi-CPU multi-threaded.  There are users which expect relatively
  * short queue flush time.  Don't queue works which can run for too
  * long.
@@ -438,7 +438,7 @@ enum wq_consts {
  * system_long_wq is similar to system_wq but may host long running
  * works.  Queue flushing might take relatively long.
  *
- * system_unbound_wq is unbound workqueue.  Workers are not bound to
+ * system_dfl_wq is unbound workqueue.  Workers are not bound to
  * any specific CPU, not concurrency managed, and all queued works are
  * executed immediately as long as max_active limit is not reached and
  * resources are available.
@@ -455,10 +455,12 @@ enum wq_consts {
  * system_bh[_highpri]_wq are convenience interface to softirq. BH work items
  * are executed in the queueing CPU's BH context in the queueing order.
  */
-extern struct workqueue_struct *system_wq;
+extern struct workqueue_struct *system_wq; /* use system_percpu_wq, this will be removed */
+extern struct workqueue_struct *system_percpu_wq;
 extern struct workqueue_struct *system_highpri_wq;
 extern struct workqueue_struct *system_long_wq;
 extern struct workqueue_struct *system_unbound_wq;
+extern struct workqueue_struct *system_dfl_wq;
 extern struct workqueue_struct *system_freezable_wq;
 extern struct workqueue_struct *system_power_efficient_wq;
 extern struct workqueue_struct *system_freezable_power_efficient_wq;
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index cf6203282737..71a4dd59977c 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -505,12 +505,16 @@ static struct kthread_worker *pwq_release_worker __ro_after_init;
 
 struct workqueue_struct *system_wq __ro_after_init;
 EXPORT_SYMBOL(system_wq);
+struct workqueue_struct *system_percpu_wq __ro_after_init;
+EXPORT_SYMBOL(system_percpu_wq);
 struct workqueue_struct *system_highpri_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_highpri_wq);
 struct workqueue_struct *system_long_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_long_wq);
 struct workqueue_struct *system_unbound_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_unbound_wq);
+struct workqueue_struct *system_dfl_wq __ro_after_init;
+EXPORT_SYMBOL_GPL(system_dfl_wq);
 struct workqueue_struct *system_freezable_wq __ro_after_init;
 EXPORT_SYMBOL_GPL(system_freezable_wq);
 struct workqueue_struct *system_power_efficient_wq __ro_after_init;
@@ -7816,10 +7820,11 @@ void __init workqueue_init_early(void)
 	}
 
 	system_wq = alloc_workqueue("events", 0, 0);
+	system_percpu_wq = alloc_workqueue("events", 0, 0);
 	system_highpri_wq = alloc_workqueue("events_highpri", WQ_HIGHPRI, 0);
 	system_long_wq = alloc_workqueue("events_long", 0, 0);
-	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND,
-					    WQ_MAX_ACTIVE);
+	system_unbound_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
+	system_dfl_wq = alloc_workqueue("events_unbound", WQ_UNBOUND, WQ_MAX_ACTIVE);
 	system_freezable_wq = alloc_workqueue("events_freezable",
 					      WQ_FREEZABLE, 0);
 	system_power_efficient_wq = alloc_workqueue("events_power_efficient",
@@ -7830,8 +7835,8 @@ void __init workqueue_init_early(void)
 	system_bh_wq = alloc_workqueue("events_bh", WQ_BH, 0);
 	system_bh_highpri_wq = alloc_workqueue("events_bh_highpri",
 					       WQ_BH | WQ_HIGHPRI, 0);
-	BUG_ON(!system_wq || !system_highpri_wq || !system_long_wq ||
-	       !system_unbound_wq || !system_freezable_wq ||
+	BUG_ON(!system_wq || !system_percpu_wq|| !system_highpri_wq || !system_long_wq ||
+	       !system_unbound_wq || !system_freezable_wq || !system_dfl_wq ||
 	       !system_power_efficient_wq ||
 	       !system_freezable_power_efficient_wq ||
 	       !system_bh_wq || !system_bh_highpri_wq);
-- 
cgit v1.2.3


From 930c2ea566aff59e962c50b2421d5fcc3b98b8be Mon Sep 17 00:00:00 2001
From: Marco Crivellari <marco.crivellari@suse.com>
Date: Sat, 14 Jun 2025 15:35:30 +0200
Subject: workqueue: Add new WQ_PERCPU flag

Currently if a user enqueue a work item using schedule_delayed_work() the
used wq is "system_wq" (per-cpu wq) while queue_delayed_work() use
WORK_CPU_UNBOUND (used when a cpu is not specified). The same applies to
schedule_work() that is using system_wq and queue_work(), that makes use
again of WORK_CPU_UNBOUND.
This lack of consistentcy cannot be addressed without refactoring the API.

This patch adds a new WQ_PERCPU flag to explicitly request the use of
the per-CPU behavior. Both flags coexist for one release cycle to allow
callers to transition their calls.

Once migration is complete, WQ_UNBOUND can be removed and unbound will
become the implicit default.

tj: Merged doc patch.

Suggested-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Marco Crivellari <marco.crivellari@suse.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 Documentation/core-api/workqueue.rst | 6 ++++++
 include/linux/workqueue.h            | 1 +
 2 files changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/core-api/workqueue.rst b/Documentation/core-api/workqueue.rst
index e295835fc116..165ca73e8351 100644
--- a/Documentation/core-api/workqueue.rst
+++ b/Documentation/core-api/workqueue.rst
@@ -183,6 +183,12 @@ resources, scheduled and executed.
   BH work items cannot sleep. All other features such as delayed queueing,
   flushing and canceling are supported.
 
+``WQ_PERCPU``
+  Work items queued to a per-cpu wq are bound to a specific CPU.
+  This flag is the right choice when cpu locality is important.
+
+  This flag is the complement of ``WQ_UNBOUND``.
+
 ``WQ_UNBOUND``
   Work items queued to an unbound wq are served by the special
   worker-pools which host workers which are not bound to any
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 74b0042709cd..f19072605faa 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -401,6 +401,7 @@ enum wq_flags {
 	 * http://thread.gmane.org/gmane.linux.kernel/1480396
 	 */
 	WQ_POWER_EFFICIENT	= 1 << 7,
+	WQ_PERCPU		= 1 << 8, /* bound to a specific cpu */
 
 	__WQ_DESTROYING		= 1 << 15, /* internal: workqueue is destroying */
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
-- 
cgit v1.2.3


From 1257b8786ac689a2ce5fe3e1741c65038035adc6 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeel.butt@linux.dev>
Date: Tue, 17 Jun 2025 12:57:22 -0700
Subject: cgroup: support to enable nmi-safe css_rstat_updated

Add necessary infrastructure to enable the nmi-safe execution of
css_rstat_updated(). Currently css_rstat_updated() takes a per-cpu
per-css raw spinlock to add the given css in the per-cpu per-css update
tree. However the kernel can not spin in nmi context, so we need to
remove the spinning on the raw spinlock in css_rstat_updated().

To support lockless css_rstat_updated(), let's add necessary data
structures in the css and ss structures.

Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Tested-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup-defs.h |  4 ++++
 kernel/cgroup/rstat.c       | 23 +++++++++++++++++++++--
 2 files changed, 25 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index cd7f093e34cd..04191d99228c 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -384,6 +384,9 @@ struct css_rstat_cpu {
 	 */
 	struct cgroup_subsys_state *updated_children;
 	struct cgroup_subsys_state *updated_next;	/* NULL if not on the list */
+
+	struct llist_node lnode;		/* lockless list for update */
+	struct cgroup_subsys_state *owner;	/* back pointer */
 };
 
 /*
@@ -822,6 +825,7 @@ struct cgroup_subsys {
 
 	spinlock_t rstat_ss_lock;
 	raw_spinlock_t __percpu *rstat_ss_cpu_lock;
+	struct llist_head __percpu *lhead; /* lockless update list head */
 };
 
 extern struct percpu_rw_semaphore cgroup_threadgroup_rwsem;
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index ce4752ab9e09..bfa6366d2325 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -11,6 +11,7 @@
 
 static DEFINE_SPINLOCK(rstat_base_lock);
 static DEFINE_PER_CPU(raw_spinlock_t, rstat_base_cpu_lock);
+static DEFINE_PER_CPU(struct llist_head, rstat_backlog_list);
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
 
@@ -45,6 +46,13 @@ static spinlock_t *ss_rstat_lock(struct cgroup_subsys *ss)
 	return &rstat_base_lock;
 }
 
+static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu)
+{
+	if (ss)
+		return per_cpu_ptr(ss->lhead, cpu);
+	return per_cpu_ptr(&rstat_backlog_list, cpu);
+}
+
 static raw_spinlock_t *ss_rstat_cpu_lock(struct cgroup_subsys *ss, int cpu)
 {
 	if (ss)
@@ -456,7 +464,8 @@ int css_rstat_init(struct cgroup_subsys_state *css)
 	for_each_possible_cpu(cpu) {
 		struct css_rstat_cpu *rstatc = css_rstat_cpu(css, cpu);
 
-		rstatc->updated_children = css;
+		rstatc->owner = rstatc->updated_children = css;
+		init_llist_node(&rstatc->lnode);
 
 		if (is_self) {
 			struct cgroup_rstat_base_cpu *rstatbc;
@@ -525,9 +534,19 @@ int __init ss_rstat_init(struct cgroup_subsys *ss)
 	}
 #endif
 
+	if (ss) {
+		ss->lhead = alloc_percpu(struct llist_head);
+		if (!ss->lhead) {
+			free_percpu(ss->rstat_ss_cpu_lock);
+			return -ENOMEM;
+		}
+	}
+
 	spin_lock_init(ss_rstat_lock(ss));
-	for_each_possible_cpu(cpu)
+	for_each_possible_cpu(cpu) {
 		raw_spin_lock_init(ss_rstat_cpu_lock(ss, cpu));
+		init_llist_head(ss_lhead_cpu(ss, cpu));
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 6af89c6ca71742e9227e6f8172a86ce1ee16aa85 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeel.butt@linux.dev>
Date: Tue, 17 Jun 2025 12:57:24 -0700
Subject: cgroup: remove per-cpu per-subsystem locks

The rstat update side used to insert the cgroup whose stats are updated
in the update tree and the read side flush the update tree to get the
latest uptodate stats. The per-cpu per-subsystem locks were used to
synchronize the update and flush side. However now the update side does
not access update tree but uses per-cpu lockless lists. So there is no
need for locks to synchronize update and flush side. Let's remove them.

Suggested-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Tested-by: JP Kobryn <inwardvessel@gmail.com>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/cgroup-defs.h   |   7 ---
 include/trace/events/cgroup.h |  47 --------------------
 kernel/cgroup/rstat.c         | 100 ++----------------------------------------
 3 files changed, 4 insertions(+), 150 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cgroup-defs.h b/include/linux/cgroup-defs.h
index 04191d99228c..6b93a64115fe 100644
--- a/include/linux/cgroup-defs.h
+++ b/include/linux/cgroup-defs.h
@@ -375,12 +375,6 @@ struct css_rstat_cpu {
 	 * Child cgroups with stat updates on this cpu since the last read
 	 * are linked on the parent's ->updated_children through
 	 * ->updated_next. updated_children is terminated by its container css.
-	 *
-	 * In addition to being more compact, singly-linked list pointing to
-	 * the css makes it unnecessary for each per-cpu struct to point back
-	 * to the associated css.
-	 *
-	 * Protected by per-cpu css->ss->rstat_ss_cpu_lock.
 	 */
 	struct cgroup_subsys_state *updated_children;
 	struct cgroup_subsys_state *updated_next;	/* NULL if not on the list */
@@ -824,7 +818,6 @@ struct cgroup_subsys {
 	unsigned int depends_on;
 
 	spinlock_t rstat_ss_lock;
-	raw_spinlock_t __percpu *rstat_ss_cpu_lock;
 	struct llist_head __percpu *lhead; /* lockless update list head */
 };
 
diff --git a/include/trace/events/cgroup.h b/include/trace/events/cgroup.h
index 7d332387be6c..ba9229af9a34 100644
--- a/include/trace/events/cgroup.h
+++ b/include/trace/events/cgroup.h
@@ -257,53 +257,6 @@ DEFINE_EVENT(cgroup_rstat, cgroup_rstat_unlock,
 	TP_ARGS(cgrp, cpu, contended)
 );
 
-/*
- * Related to per CPU locks:
- * global rstat_base_cpu_lock for base stats
- * cgroup_subsys::rstat_ss_cpu_lock for subsystem stats
- */
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_lock_contended_fastpath,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_locked_fastpath,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
-DEFINE_EVENT(cgroup_rstat, cgroup_rstat_cpu_unlock_fastpath,
-
-	TP_PROTO(struct cgroup *cgrp, int cpu, bool contended),
-
-	TP_ARGS(cgrp, cpu, contended)
-);
-
 #endif /* _TRACE_CGROUP_H */
 
 /* This part must be outside protection */
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index 823a4c7c3fea..c8a48cf83878 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -10,7 +10,6 @@
 #include <trace/events/cgroup.h>
 
 static DEFINE_SPINLOCK(rstat_base_lock);
-static DEFINE_PER_CPU(raw_spinlock_t, rstat_base_cpu_lock);
 static DEFINE_PER_CPU(struct llist_head, rstat_backlog_list);
 
 static void cgroup_base_stat_flush(struct cgroup *cgrp, int cpu);
@@ -53,74 +52,6 @@ static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu)
 	return per_cpu_ptr(&rstat_backlog_list, cpu);
 }
 
-static raw_spinlock_t *ss_rstat_cpu_lock(struct cgroup_subsys *ss, int cpu)
-{
-	if (ss)
-		return per_cpu_ptr(ss->rstat_ss_cpu_lock, cpu);
-
-	return per_cpu_ptr(&rstat_base_cpu_lock, cpu);
-}
-
-/*
- * Helper functions for rstat per CPU locks.
- *
- * This makes it easier to diagnose locking issues and contention in
- * production environments. The parameter @fast_path determine the
- * tracepoints being added, allowing us to diagnose "flush" related
- * operations without handling high-frequency fast-path "update" events.
- */
-static __always_inline
-unsigned long _css_rstat_cpu_lock(struct cgroup_subsys_state *css, int cpu,
-		const bool fast_path)
-{
-	struct cgroup *cgrp = css->cgroup;
-	raw_spinlock_t *cpu_lock;
-	unsigned long flags;
-	bool contended;
-
-	/*
-	 * The _irqsave() is needed because the locks used for flushing are
-	 * spinlock_t which is a sleeping lock on PREEMPT_RT. Acquiring this lock
-	 * with the _irq() suffix only disables interrupts on a non-PREEMPT_RT
-	 * kernel. The raw_spinlock_t below disables interrupts on both
-	 * configurations. The _irqsave() ensures that interrupts are always
-	 * disabled and later restored.
-	 */
-	cpu_lock = ss_rstat_cpu_lock(css->ss, cpu);
-	contended = !raw_spin_trylock_irqsave(cpu_lock, flags);
-	if (contended) {
-		if (fast_path)
-			trace_cgroup_rstat_cpu_lock_contended_fastpath(cgrp, cpu, contended);
-		else
-			trace_cgroup_rstat_cpu_lock_contended(cgrp, cpu, contended);
-
-		raw_spin_lock_irqsave(cpu_lock, flags);
-	}
-
-	if (fast_path)
-		trace_cgroup_rstat_cpu_locked_fastpath(cgrp, cpu, contended);
-	else
-		trace_cgroup_rstat_cpu_locked(cgrp, cpu, contended);
-
-	return flags;
-}
-
-static __always_inline
-void _css_rstat_cpu_unlock(struct cgroup_subsys_state *css, int cpu,
-		unsigned long flags, const bool fast_path)
-{
-	struct cgroup *cgrp = css->cgroup;
-	raw_spinlock_t *cpu_lock;
-
-	if (fast_path)
-		trace_cgroup_rstat_cpu_unlock_fastpath(cgrp, cpu, false);
-	else
-		trace_cgroup_rstat_cpu_unlock(cgrp, cpu, false);
-
-	cpu_lock = ss_rstat_cpu_lock(css->ss, cpu);
-	raw_spin_unlock_irqrestore(cpu_lock, flags);
-}
-
 /**
  * css_rstat_updated - keep track of updated rstat_cpu
  * @css: target cgroup subsystem state
@@ -323,15 +254,12 @@ static struct cgroup_subsys_state *css_rstat_updated_list(
 {
 	struct css_rstat_cpu *rstatc = css_rstat_cpu(root, cpu);
 	struct cgroup_subsys_state *head = NULL, *parent, *child;
-	unsigned long flags;
-
-	flags = _css_rstat_cpu_lock(root, cpu, false);
 
 	css_process_update_tree(root->ss, cpu);
 
 	/* Return NULL if this subtree is not on-list */
 	if (!rstatc->updated_next)
-		goto unlock_ret;
+		return NULL;
 
 	/*
 	 * Unlink @root from its parent. As the updated_children list is
@@ -363,8 +291,7 @@ static struct cgroup_subsys_state *css_rstat_updated_list(
 	rstatc->updated_children = root;
 	if (child != root)
 		head = css_rstat_push_children(head, child, cpu);
-unlock_ret:
-	_css_rstat_cpu_unlock(root, cpu, flags, false);
+
 	return head;
 }
 
@@ -560,34 +487,15 @@ int __init ss_rstat_init(struct cgroup_subsys *ss)
 {
 	int cpu;
 
-#ifdef CONFIG_SMP
-	/*
-	 * On uniprocessor machines, arch_spinlock_t is defined as an empty
-	 * struct. Avoid allocating a size of zero by having this block
-	 * excluded in this case. It's acceptable to leave the subsystem locks
-	 * unitialized since the associated lock functions are no-ops in the
-	 * non-smp case.
-	 */
-	if (ss) {
-		ss->rstat_ss_cpu_lock = alloc_percpu(raw_spinlock_t);
-		if (!ss->rstat_ss_cpu_lock)
-			return -ENOMEM;
-	}
-#endif
-
 	if (ss) {
 		ss->lhead = alloc_percpu(struct llist_head);
-		if (!ss->lhead) {
-			free_percpu(ss->rstat_ss_cpu_lock);
+		if (!ss->lhead)
 			return -ENOMEM;
-		}
 	}
 
 	spin_lock_init(ss_rstat_lock(ss));
-	for_each_possible_cpu(cpu) {
-		raw_spin_lock_init(ss_rstat_cpu_lock(ss, cpu));
+	for_each_possible_cpu(cpu)
 		init_llist_head(ss_lhead_cpu(ss, cpu));
-	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 07a4688833b237331e5045f90fc546c085b28c86 Mon Sep 17 00:00:00 2001
From: Alexander Wilhelm <alexander.wilhelm@westermo.com>
Date: Thu, 22 May 2025 16:35:30 +0200
Subject: soc: qcom: fix endianness for QMI header

The members of QMI header have to be swapped on big endian platforms. Use
__le16 types instead of u16 ones.

Signed-off-by: Alexander Wilhelm <alexander.wilhelm@westermo.com>
Fixes: 9b8a11e82615 ("soc: qcom: Introduce QMI encoder/decoder")
Fixes: 3830d0771ef6 ("soc: qcom: Introduce QMI helpers")
Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250522143530.3623809-3-alexander.wilhelm@westermo.com
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/soc/qcom/qmi_encdec.c    | 6 +++---
 drivers/soc/qcom/qmi_interface.c | 6 +++---
 include/linux/soc/qcom/qmi.h     | 6 +++---
 3 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/soc/qcom/qmi_encdec.c b/drivers/soc/qcom/qmi_encdec.c
index dafe0a4c202e..7660a960fb45 100644
--- a/drivers/soc/qcom/qmi_encdec.c
+++ b/drivers/soc/qcom/qmi_encdec.c
@@ -776,9 +776,9 @@ void *qmi_encode_message(int type, unsigned int msg_id, size_t *len,
 
 	hdr = msg;
 	hdr->type = type;
-	hdr->txn_id = txn_id;
-	hdr->msg_id = msg_id;
-	hdr->msg_len = msglen;
+	hdr->txn_id = cpu_to_le16(txn_id);
+	hdr->msg_id = cpu_to_le16(msg_id);
+	hdr->msg_len = cpu_to_le16(msglen);
 
 	*len = sizeof(*hdr) + msglen;
 
diff --git a/drivers/soc/qcom/qmi_interface.c b/drivers/soc/qcom/qmi_interface.c
index bc6d6379d8b1..6500f863aae5 100644
--- a/drivers/soc/qcom/qmi_interface.c
+++ b/drivers/soc/qcom/qmi_interface.c
@@ -400,7 +400,7 @@ static void qmi_invoke_handler(struct qmi_handle *qmi, struct sockaddr_qrtr *sq,
 
 	for (handler = qmi->handlers; handler->fn; handler++) {
 		if (handler->type == hdr->type &&
-		    handler->msg_id == hdr->msg_id)
+		    handler->msg_id == le16_to_cpu(hdr->msg_id))
 			break;
 	}
 
@@ -488,7 +488,7 @@ static void qmi_handle_message(struct qmi_handle *qmi,
 	/* If this is a response, find the matching transaction handle */
 	if (hdr->type == QMI_RESPONSE) {
 		mutex_lock(&qmi->txn_lock);
-		txn = idr_find(&qmi->txns, hdr->txn_id);
+		txn = idr_find(&qmi->txns, le16_to_cpu(hdr->txn_id));
 
 		/* Ignore unexpected responses */
 		if (!txn) {
@@ -514,7 +514,7 @@ static void qmi_handle_message(struct qmi_handle *qmi,
 	} else {
 		/* Create a txn based on the txn_id of the incoming message */
 		memset(&tmp_txn, 0, sizeof(tmp_txn));
-		tmp_txn.id = hdr->txn_id;
+		tmp_txn.id = le16_to_cpu(hdr->txn_id);
 
 		qmi_invoke_handler(qmi, sq, &tmp_txn, buf, len);
 	}
diff --git a/include/linux/soc/qcom/qmi.h b/include/linux/soc/qcom/qmi.h
index 469e02d2aa0d..291cdc7ef49c 100644
--- a/include/linux/soc/qcom/qmi.h
+++ b/include/linux/soc/qcom/qmi.h
@@ -24,9 +24,9 @@ struct socket;
  */
 struct qmi_header {
 	u8 type;
-	u16 txn_id;
-	u16 msg_id;
-	u16 msg_len;
+	__le16 txn_id;
+	__le16 msg_id;
+	__le16 msg_len;
 } __packed;
 
 #define QMI_REQUEST	0
-- 
cgit v1.2.3


From f42b8d78dee77107245ec5beee3eb01915bcae7f Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 11 Jun 2025 19:40:04 -0400
Subject: tpm: don't bother with removal of files in directory we'll be
 removing

FWIW, there is a reliable indication of removal - ->i_nlink going to 0 ;-)

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/char/tpm/eventlog/common.c | 46 ++++++++++----------------------------
 include/linux/tpm.h                |  2 +-
 2 files changed, 13 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c
index 4c0bbba64ee5..691813d2a5a2 100644
--- a/drivers/char/tpm/eventlog/common.c
+++ b/drivers/char/tpm/eventlog/common.c
@@ -32,7 +32,7 @@ static int tpm_bios_measurements_open(struct inode *inode,
 	struct tpm_chip *chip;
 
 	inode_lock(inode);
-	if (!inode->i_private) {
+	if (!inode->i_nlink) {
 		inode_unlock(inode);
 		return -ENODEV;
 	}
@@ -105,7 +105,7 @@ static int tpm_read_log(struct tpm_chip *chip)
 void tpm_bios_log_setup(struct tpm_chip *chip)
 {
 	const char *name = dev_name(&chip->dev);
-	unsigned int cnt;
+	struct dentry *dentry;
 	int log_version;
 	int rc = 0;
 
@@ -117,14 +117,12 @@ void tpm_bios_log_setup(struct tpm_chip *chip)
 		return;
 	log_version = rc;
 
-	cnt = 0;
-	chip->bios_dir[cnt] = securityfs_create_dir(name, NULL);
+	chip->bios_dir = securityfs_create_dir(name, NULL);
 	/* NOTE: securityfs_create_dir can return ENODEV if securityfs is
 	 * compiled out. The caller should ignore the ENODEV return code.
 	 */
-	if (IS_ERR(chip->bios_dir[cnt]))
-		goto err;
-	cnt++;
+	if (IS_ERR(chip->bios_dir))
+		return;
 
 	chip->bin_log_seqops.chip = chip;
 	if (log_version == EFI_TCG2_EVENT_LOG_FORMAT_TCG_2)
@@ -135,14 +133,13 @@ void tpm_bios_log_setup(struct tpm_chip *chip)
 			&tpm1_binary_b_measurements_seqops;
 
 
-	chip->bios_dir[cnt] =
+	dentry =
 	    securityfs_create_file("binary_bios_measurements",
-				   0440, chip->bios_dir[0],
+				   0440, chip->bios_dir,
 				   (void *)&chip->bin_log_seqops,
 				   &tpm_bios_measurements_ops);
-	if (IS_ERR(chip->bios_dir[cnt]))
+	if (IS_ERR(dentry))
 		goto err;
-	cnt++;
 
 	if (!(chip->flags & TPM_CHIP_FLAG_TPM2)) {
 
@@ -150,42 +147,23 @@ void tpm_bios_log_setup(struct tpm_chip *chip)
 		chip->ascii_log_seqops.seqops =
 			&tpm1_ascii_b_measurements_seqops;
 
-		chip->bios_dir[cnt] =
+		dentry =
 			securityfs_create_file("ascii_bios_measurements",
-					       0440, chip->bios_dir[0],
+					       0440, chip->bios_dir,
 					       (void *)&chip->ascii_log_seqops,
 					       &tpm_bios_measurements_ops);
-		if (IS_ERR(chip->bios_dir[cnt]))
+		if (IS_ERR(dentry))
 			goto err;
-		cnt++;
 	}
 
 	return;
 
 err:
-	chip->bios_dir[cnt] = NULL;
 	tpm_bios_log_teardown(chip);
 	return;
 }
 
 void tpm_bios_log_teardown(struct tpm_chip *chip)
 {
-	int i;
-	struct inode *inode;
-
-	/* securityfs_remove currently doesn't take care of handling sync
-	 * between removal and opening of pseudo files. To handle this, a
-	 * workaround is added by making i_private = NULL here during removal
-	 * and to check it during open(), both within inode_lock()/unlock().
-	 * This design ensures that open() either safely gets kref or fails.
-	 */
-	for (i = (TPM_NUM_EVENT_LOG_FILES - 1); i >= 0; i--) {
-		if (chip->bios_dir[i]) {
-			inode = d_inode(chip->bios_dir[i]);
-			inode_lock(inode);
-			inode->i_private = NULL;
-			inode_unlock(inode);
-			securityfs_remove(chip->bios_dir[i]);
-		}
-	}
+	securityfs_remove(chip->bios_dir);
 }
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index a3d8305e88a5..9894c104dc93 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -182,7 +182,7 @@ struct tpm_chip {
 	unsigned long duration[TPM_NUM_DURATIONS]; /* jiffies */
 	bool duration_adjusted;
 
-	struct dentry *bios_dir[TPM_NUM_EVENT_LOG_FILES];
+	struct dentry *bios_dir;
 
 	const struct attribute_group *groups[3 + TPM_MAX_HASHES];
 	unsigned int groups_cnt;
-- 
cgit v1.2.3


From ba4618885b23372c45bb1566ed8e3f1c191ff22d Mon Sep 17 00:00:00 2001
From: Neal Cardwell <ncardwell@google.com>
Date: Sat, 14 Jun 2025 20:14:34 -0400
Subject: tcp: remove RFC3517/RFC6675 hint state: lost_skb_hint, lost_cnt_hint

Now that obsolete RFC3517/RFC6675 TCP loss detection has been removed,
we can remove the somewhat complex and intrusive code to maintain its
hint state: lost_skb_hint and lost_cnt_hint.

This commit makes tcp_clear_retrans_hints_partial() empty. We will
remove tcp_clear_retrans_hints_partial() and its call sites in the
next commit.

Suggested-by: Yuchung Cheng <ycheng@google.com>
Signed-off-by: Neal Cardwell <ncardwell@google.com>
Reviewed-by: Yuchung Cheng <ycheng@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250615001435.2390793-3-ncardwell.sw@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/net_cachelines/tcp_sock.rst |  2 --
 include/linux/tcp.h                                  |  3 ---
 include/net/tcp.h                                    |  1 -
 net/ipv4/tcp.c                                       |  3 +--
 net/ipv4/tcp_input.c                                 | 19 -------------------
 net/ipv4/tcp_output.c                                |  5 -----
 6 files changed, 1 insertion(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/net_cachelines/tcp_sock.rst b/Documentation/networking/net_cachelines/tcp_sock.rst
index bc9b2131bf7a..7bbda5944ee2 100644
--- a/Documentation/networking/net_cachelines/tcp_sock.rst
+++ b/Documentation/networking/net_cachelines/tcp_sock.rst
@@ -115,7 +115,6 @@ u32                           lost_out                read_mostly         read_m
 u32                           sacked_out              read_mostly         read_mostly         tcp_left_out(tx);tcp_packets_in_flight(tx/rx);tcp_clean_rtx_queue(rx)
 struct hrtimer                pacing_timer
 struct hrtimer                compressed_ack_timer
-struct sk_buff*               lost_skb_hint           read_mostly                             tcp_clean_rtx_queue
 struct sk_buff*               retransmit_skb_hint     read_mostly                             tcp_clean_rtx_queue
 struct rb_root                out_of_order_queue                          read_mostly         tcp_data_queue,tcp_fast_path_check
 struct sk_buff*               ooo_last_skb
@@ -123,7 +122,6 @@ struct tcp_sack_block[1]      duplicate_sack
 struct tcp_sack_block[4]      selective_acks
 struct tcp_sack_block[4]      recv_sack_cache
 struct sk_buff*               highest_sack            read_write                              tcp_event_new_data_sent
-int                           lost_cnt_hint
 u32                           prior_ssthresh
 u32                           high_seq
 u32                           retrans_stamp
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 29f59d50dc73..1a5737b3753d 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -208,7 +208,6 @@ struct tcp_sock {
 	u32	notsent_lowat;	/* TCP_NOTSENT_LOWAT */
 	u16	gso_segs;	/* Max number of segs per GSO packet	*/
 	/* from STCP, retrans queue hinting */
-	struct sk_buff *lost_skb_hint;
 	struct sk_buff *retransmit_skb_hint;
 	__cacheline_group_end(tcp_sock_read_tx);
 
@@ -419,8 +418,6 @@ struct tcp_sock {
 
 	struct tcp_sack_block recv_sack_cache[4];
 
-	int     lost_cnt_hint;
-
 	u32	prior_ssthresh; /* ssthresh saved at recovery start	*/
 	u32	high_seq;	/* snd_nxt at onset of congestion	*/
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5078ad868fee..f57d12183794 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1813,7 +1813,6 @@ static inline void tcp_mib_init(struct net *net)
 /* from STCP */
 static inline void tcp_clear_retrans_hints_partial(struct tcp_sock *tp)
 {
-	tp->lost_skb_hint = NULL;
 }
 
 static inline void tcp_clear_all_retrans_hints(struct tcp_sock *tp)
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index f64f8276a73c..27d3ef83ce7b 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -5053,9 +5053,8 @@ static void __init tcp_struct_check(void)
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, reordering);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, notsent_lowat);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, gso_segs);
-	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, lost_skb_hint);
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_tx, retransmit_skb_hint);
-	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 40);
+	CACHELINE_ASSERT_GROUP_SIZE(struct tcp_sock, tcp_sock_read_tx, 32);
 
 	/* TXRX read-mostly hotpath cache lines */
 	CACHELINE_ASSERT_GROUP_MEMBER(struct tcp_sock, tcp_sock_read_txrx, tsoffset);
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index dc234d3854aa..e8e130e946f1 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -1451,11 +1451,6 @@ static u8 tcp_sacktag_one(struct sock *sk,
 		tp->sacked_out += pcount;
 		/* Out-of-order packets delivered */
 		state->sack_delivered += pcount;
-
-		/* Lost marker hint past SACKed? Tweak RFC3517 cnt */
-		if (tp->lost_skb_hint &&
-		    before(start_seq, TCP_SKB_CB(tp->lost_skb_hint)->seq))
-			tp->lost_cnt_hint += pcount;
 	}
 
 	/* D-SACK. We can detect redundant retransmission in S|R and plain R
@@ -1496,9 +1491,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
 			tcp_skb_timestamp_us(skb));
 	tcp_rate_skb_delivered(sk, skb, state->rate);
 
-	if (skb == tp->lost_skb_hint)
-		tp->lost_cnt_hint += pcount;
-
 	TCP_SKB_CB(prev)->end_seq += shifted;
 	TCP_SKB_CB(skb)->seq += shifted;
 
@@ -1531,10 +1523,6 @@ static bool tcp_shifted_skb(struct sock *sk, struct sk_buff *prev,
 
 	if (skb == tp->retransmit_skb_hint)
 		tp->retransmit_skb_hint = prev;
-	if (skb == tp->lost_skb_hint) {
-		tp->lost_skb_hint = prev;
-		tp->lost_cnt_hint -= tcp_skb_pcount(prev);
-	}
 
 	TCP_SKB_CB(prev)->tcp_flags |= TCP_SKB_CB(skb)->tcp_flags;
 	TCP_SKB_CB(prev)->eor = TCP_SKB_CB(skb)->eor;
@@ -3318,8 +3306,6 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb,
 		next = skb_rb_next(skb);
 		if (unlikely(skb == tp->retransmit_skb_hint))
 			tp->retransmit_skb_hint = NULL;
-		if (unlikely(skb == tp->lost_skb_hint))
-			tp->lost_skb_hint = NULL;
 		tcp_highest_sack_replace(sk, skb, next);
 		tcp_rtx_queue_unlink_and_free(skb, sk);
 	}
@@ -3377,14 +3363,9 @@ static int tcp_clean_rtx_queue(struct sock *sk, const struct sk_buff *ack_skb,
 			if (flag & FLAG_RETRANS_DATA_ACKED)
 				flag &= ~FLAG_ORIG_SACK_ACKED;
 		} else {
-			int delta;
-
 			/* Non-retransmitted hole got filled? That's reordering */
 			if (before(reord, prior_fack))
 				tcp_check_sack_reordering(sk, reord, 0);
-
-			delta = prior_sacked - tp->sacked_out;
-			tp->lost_cnt_hint -= min(tp->lost_cnt_hint, delta);
 		}
 	} else if (skb && rtt_update && sack_rtt_us >= 0 &&
 		   sack_rtt_us > tcp_stamp_us_delta(tp->tcp_mstamp,
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 3ac8d2d17e1f..b0ffefe604b4 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -1554,11 +1554,6 @@ static void tcp_adjust_pcount(struct sock *sk, const struct sk_buff *skb, int de
 	if (tcp_is_reno(tp) && decr > 0)
 		tp->sacked_out -= min_t(u32, tp->sacked_out, decr);
 
-	if (tp->lost_skb_hint &&
-	    before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
-	    (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED))
-		tp->lost_cnt_hint -= decr;
-
 	tcp_verify_left_out(tp);
 }
 
-- 
cgit v1.2.3


From 2de1ba0887e5d3bf02d7c212f380039b34e10aa3 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 16 Jun 2025 16:26:24 +0300
Subject: net: vlan: Make is_vlan_dev() a stub when VLAN is not configured

Add a stub implementation of is_vlan_dev() that returns false when
VLAN support is not compiled in (CONFIG_VLAN_8021Q=n).

This allows us to compile-out VLAN-dependent dead code when it is not
needed.

This also resolves the following compilation error when:
* CONFIG_VLAN_8021Q=n
* CONFIG_OBJTOOL=y
* CONFIG_OBJTOOL_WERROR=y

drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.o: error: objtool: parse_mirred.isra.0+0x370: mlx5e_tc_act_vlan_add_push_action() missing __noreturn in .c/.h or NORETURN() in noreturns.h

The error occurs because objtool cannot determine that unreachable BUG()
(which doesn't return) calls in VLAN code paths are actually dead code
when VLAN support is disabled.

Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20250616132626.1749331-2-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/if_vlan.h | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 38456b42cdb5..618a973ff8ee 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -79,11 +79,6 @@ static inline struct vlan_ethhdr *skb_vlan_eth_hdr(const struct sk_buff *skb)
 /* found in socket.c */
 extern void vlan_ioctl_set(int (*hook)(struct net *, void __user *));
 
-static inline bool is_vlan_dev(const struct net_device *dev)
-{
-        return dev->priv_flags & IFF_802_1Q_VLAN;
-}
-
 #define skb_vlan_tag_present(__skb)	(!!(__skb)->vlan_all)
 #define skb_vlan_tag_get(__skb)		((__skb)->vlan_tci)
 #define skb_vlan_tag_get_id(__skb)	((__skb)->vlan_tci & VLAN_VID_MASK)
@@ -200,6 +195,11 @@ struct vlan_dev_priv {
 #endif
 };
 
+static inline bool is_vlan_dev(const struct net_device *dev)
+{
+	return dev->priv_flags & IFF_802_1Q_VLAN;
+}
+
 static inline struct vlan_dev_priv *vlan_dev_priv(const struct net_device *dev)
 {
 	return netdev_priv(dev);
@@ -237,6 +237,11 @@ extern void vlan_vids_del_by_dev(struct net_device *dev,
 extern bool vlan_uses_dev(const struct net_device *dev);
 
 #else
+static inline bool is_vlan_dev(const struct net_device *dev)
+{
+	return false;
+}
+
 static inline struct net_device *
 __vlan_find_dev_deep_rcu(struct net_device *real_dev,
 		     __be16 vlan_proto, u16 vlan_id)
-- 
cgit v1.2.3


From 60a8b1a5d0824afda869f18dc0ecfe72f8dfda42 Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 16 Jun 2025 16:26:25 +0300
Subject: net: vlan: Replace BUG() with WARN_ON_ONCE() in vlan_dev_* stubs

When CONFIG_VLAN_8021Q=n, a set of stub helpers are used, three of these
helpers use BUG() unconditionally.

This code should not be reached, as callers of these functions should
always check for is_vlan_dev() first, but the usage of BUG() is not
recommended, replace it with WARN_ON() instead.

Reviewed-by: Alex Lazar <alazar@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20250616132626.1749331-3-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/if_vlan.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index 618a973ff8ee..b9f699799cf6 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -259,19 +259,19 @@ vlan_for_each(struct net_device *dev,
 
 static inline struct net_device *vlan_dev_real_dev(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return NULL;
 }
 
 static inline u16 vlan_dev_vlan_id(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return 0;
 }
 
 static inline __be16 vlan_dev_vlan_proto(const struct net_device *dev)
 {
-	BUG();
+	WARN_ON_ONCE(1);
 	return 0;
 }
 
-- 
cgit v1.2.3


From 9c5f5a5bf0da5cee2044b93907ac6d8d9af0492b Mon Sep 17 00:00:00 2001
From: Gal Pressman <gal@nvidia.com>
Date: Mon, 16 Jun 2025 16:26:26 +0300
Subject: net: vlan: Use IS_ENABLED() helper for CONFIG_VLAN_8021Q guard
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The header currently tests the VLAN core with an explicit pair of 'if
defined' checks:
    #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)

Instead, use IS_ENABLED() which is the kernel way to test whether an
option is configured as builtin/module.

This is purely cosmetic – no functional changes.

Reviewed-by: Alex Lazar <alazar@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Gal Pressman <gal@nvidia.com>
Link: https://patch.msgid.link/20250616132626.1749331-4-gal@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/if_vlan.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h
index b9f699799cf6..15e01935d3fa 100644
--- a/include/linux/if_vlan.h
+++ b/include/linux/if_vlan.h
@@ -131,7 +131,7 @@ struct vlan_pcpu_stats {
 	u32			tx_dropped;
 };
 
-#if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE)
+#if IS_ENABLED(CONFIG_VLAN_8021Q)
 
 extern struct net_device *__vlan_find_dev_deep_rcu(struct net_device *real_dev,
 					       __be16 vlan_proto, u16 vlan_id);
-- 
cgit v1.2.3


From 96e8f5a9fe2d91b9f9eb8b45cc13ce1ca6a8af82 Mon Sep 17 00:00:00 2001
From: Petr Machata <petrm@nvidia.com>
Date: Tue, 17 Jun 2025 00:44:18 +0200
Subject: net: ipv6: Add ip6_mr_output()

Multicast routing is today handled in the input path. Locally generated MC
packets don't hit the IPMR code today. Thus if a VXLAN remote address is
multicast, the driver needs to set an OIF during route lookup. Thus MC
routing configuration needs to be kept in sync with the VXLAN FDB and MDB.
Ideally, the VXLAN packets would be routed by the MC routing code instead.

To that end, this patch adds support to route locally generated multicast
packets. The newly-added routines do largely what ip6_mr_input() and
ip6_mr_forward() do: make an MR cache lookup to find where to send the
packets, and use ip6_output() to send each of them. When no cache entry is
found, the packet is punted to the daemon for resolution.

Similarly to the IPv4 case in a previous patch, the new logic is contingent
on a newly-added IP6CB flag being set.

Signed-off-by: Petr Machata <petrm@nvidia.com>
Link: https://patch.msgid.link/3bcc034a3ab4d3c291072fff38f78d7fbbeef4e6.1750113335.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ipv6.h    |   1 +
 include/linux/mroute6.h |   7 +++
 net/ipv6/ip6mr.c        | 118 ++++++++++++++++++++++++++++++++++++++++++++++++
 net/ipv6/route.c        |   1 +
 4 files changed, 127 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index 5aeeed22f35b..db0eb0d86b64 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -156,6 +156,7 @@ struct inet6_skb_parm {
 #define IP6SKB_SEG6	      256
 #define IP6SKB_FAKEJUMBO      512
 #define IP6SKB_MULTIPATH      1024
+#define IP6SKB_MCROUTE        2048
 };
 
 #if defined(CONFIG_NET_L3_MASTER_DEV)
diff --git a/include/linux/mroute6.h b/include/linux/mroute6.h
index 63ef5191cc57..fddafdc168f7 100644
--- a/include/linux/mroute6.h
+++ b/include/linux/mroute6.h
@@ -31,6 +31,7 @@ extern int ip6_mroute_getsockopt(struct sock *, int, sockptr_t, sockptr_t);
 extern int ip6_mr_input(struct sk_buff *skb);
 extern int ip6mr_compat_ioctl(struct sock *sk, unsigned int cmd, void __user *arg);
 extern int ip6_mr_init(void);
+extern int ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb);
 extern void ip6_mr_cleanup(void);
 int ip6mr_ioctl(struct sock *sk, int cmd, void *arg);
 #else
@@ -58,6 +59,12 @@ static inline int ip6_mr_init(void)
 	return 0;
 }
 
+static inline int
+ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	return ip6_output(net, sk, skb);
+}
+
 static inline void ip6_mr_cleanup(void)
 {
 	return;
diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c
index bd964564160d..a35f4f1c6589 100644
--- a/net/ipv6/ip6mr.c
+++ b/net/ipv6/ip6mr.c
@@ -2119,6 +2119,19 @@ out_free:
 	kfree_skb(skb);
 }
 
+static void ip6mr_output2(struct net *net, struct mr_table *mrt,
+			  struct sk_buff *skb, int vifi)
+{
+	if (ip6mr_prepare_xmit(net, mrt, skb, vifi))
+		goto out_free;
+
+	ip6_output(net, NULL, skb);
+	return;
+
+out_free:
+	kfree_skb(skb);
+}
+
 /* Called with rcu_read_lock() */
 static int ip6mr_find_vif(struct mr_table *mrt, struct net_device *dev)
 {
@@ -2231,6 +2244,56 @@ dont_forward:
 	kfree_skb(skb);
 }
 
+/* Called under rcu_read_lock() */
+static void ip6_mr_output_finish(struct net *net, struct mr_table *mrt,
+				 struct net_device *dev, struct sk_buff *skb,
+				 struct mfc6_cache *c)
+{
+	int psend = -1;
+	int ct;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	atomic_long_inc(&c->_c.mfc_un.res.pkt);
+	atomic_long_add(skb->len, &c->_c.mfc_un.res.bytes);
+	WRITE_ONCE(c->_c.mfc_un.res.lastuse, jiffies);
+
+	/* Forward the frame */
+	if (ipv6_addr_any(&c->mf6c_origin) &&
+	    ipv6_addr_any(&c->mf6c_mcastgrp)) {
+		if (ipv6_hdr(skb)->hop_limit >
+		    c->_c.mfc_un.res.ttls[c->_c.mfc_parent]) {
+			/* It's an (*,*) entry and the packet is not coming from
+			 * the upstream: forward the packet to the upstream
+			 * only.
+			 */
+			psend = c->_c.mfc_parent;
+			goto last_forward;
+		}
+		goto dont_forward;
+	}
+	for (ct = c->_c.mfc_un.res.maxvif - 1;
+	     ct >= c->_c.mfc_un.res.minvif; ct--) {
+		if (ipv6_hdr(skb)->hop_limit > c->_c.mfc_un.res.ttls[ct]) {
+			if (psend != -1) {
+				struct sk_buff *skb2;
+
+				skb2 = skb_clone(skb, GFP_ATOMIC);
+				if (skb2)
+					ip6mr_output2(net, mrt, skb2, psend);
+			}
+			psend = ct;
+		}
+	}
+last_forward:
+	if (psend != -1) {
+		ip6mr_output2(net, mrt, skb, psend);
+		return;
+	}
+
+dont_forward:
+	kfree_skb(skb);
+}
 
 /*
  *	Multicast packets for forwarding arrive here
@@ -2298,6 +2361,61 @@ int ip6_mr_input(struct sk_buff *skb)
 	return 0;
 }
 
+int ip6_mr_output(struct net *net, struct sock *sk, struct sk_buff *skb)
+{
+	struct net_device *dev = skb_dst(skb)->dev;
+	struct flowi6 fl6 = (struct flowi6) {
+		.flowi6_iif = LOOPBACK_IFINDEX,
+		.flowi6_mark = skb->mark,
+	};
+	struct mfc6_cache *cache;
+	struct mr_table *mrt;
+	int err;
+	int vif;
+
+	WARN_ON_ONCE(!rcu_read_lock_held());
+
+	if (IP6CB(skb)->flags & IP6SKB_FORWARDED)
+		goto ip6_output;
+	if (!(IP6CB(skb)->flags & IP6SKB_MCROUTE))
+		goto ip6_output;
+
+	err = ip6mr_fib_lookup(net, &fl6, &mrt);
+	if (err < 0) {
+		kfree_skb(skb);
+		return err;
+	}
+
+	cache = ip6mr_cache_find(mrt,
+				 &ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr);
+	if (!cache) {
+		vif = ip6mr_find_vif(mrt, dev);
+		if (vif >= 0)
+			cache = ip6mr_cache_find_any(mrt,
+						     &ipv6_hdr(skb)->daddr,
+						     vif);
+	}
+
+	/* No usable cache entry */
+	if (!cache) {
+		vif = ip6mr_find_vif(mrt, dev);
+		if (vif >= 0)
+			return ip6mr_cache_unresolved(mrt, vif, skb, dev);
+		goto ip6_output;
+	}
+
+	/* Wrong interface */
+	vif = cache->_c.mfc_parent;
+	if (rcu_access_pointer(mrt->vif_table[vif].dev) != dev)
+		goto ip6_output;
+
+	ip6_mr_output_finish(net, mrt, dev, skb, cache);
+	return 0;
+
+ip6_output:
+	return ip6_output(net, sk, skb);
+}
+
 int ip6mr_get_route(struct net *net, struct sk_buff *skb, struct rtmsg *rtm,
 		    u32 portid)
 {
diff --git a/net/ipv6/route.c b/net/ipv6/route.c
index 79c8f1acf8a3..df0caffefb38 100644
--- a/net/ipv6/route.c
+++ b/net/ipv6/route.c
@@ -1145,6 +1145,7 @@ static void ip6_rt_init_dst(struct rt6_info *rt, const struct fib6_result *res)
 		rt->dst.input = ip6_input;
 	} else if (ipv6_addr_type(&f6i->fib6_dst.addr) & IPV6_ADDR_MULTICAST) {
 		rt->dst.input = ip6_mc_input;
+		rt->dst.output = ip6_mr_output;
 	} else {
 		rt->dst.input = ip6_forward;
 	}
-- 
cgit v1.2.3


From 1cbb49f85b4095af798f1a421db2e08894d0606c Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Mon, 16 Jun 2025 17:14:31 +0300
Subject: net: Add skb_can_coalesce for netmem

Allow drivers that have moved over to netmem to do fragment coalescing.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Cosmin Ratiu <cratiu@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Reviewed-by: Mina Almasry <almasrymina@google.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250616141441.1243044-3-mbloch@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 12 +++++++++---
 1 file changed, 9 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 5520524c93bf..9508968cb300 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3873,20 +3873,26 @@ static inline int __must_check skb_put_padto(struct sk_buff *skb, unsigned int l
 bool csum_and_copy_from_iter_full(void *addr, size_t bytes, __wsum *csum, struct iov_iter *i)
 	__must_check;
 
-static inline bool skb_can_coalesce(struct sk_buff *skb, int i,
-				    const struct page *page, int off)
+static inline bool skb_can_coalesce_netmem(struct sk_buff *skb, int i,
+					   netmem_ref netmem, int off)
 {
 	if (skb_zcopy(skb))
 		return false;
 	if (i) {
 		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i - 1];
 
-		return page == skb_frag_page(frag) &&
+		return netmem == skb_frag_netmem(frag) &&
 		       off == skb_frag_off(frag) + skb_frag_size(frag);
 	}
 	return false;
 }
 
+static inline bool skb_can_coalesce(struct sk_buff *skb, int i,
+				    const struct page *page, int off)
+{
+	return skb_can_coalesce_netmem(skb, i, page_to_netmem(page), off);
+}
+
 static inline int __skb_linearize(struct sk_buff *skb)
 {
 	return __pskb_pull_tail(skb, skb->data_len) ? 0 : -ENOMEM;
-- 
cgit v1.2.3


From 7851263998d4269125fd6cb3fdbfc7c6db853859 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Mon, 16 Jun 2025 11:21:15 -0700
Subject: atm: Revert atm_account_tx() if copy_from_iter_full() fails.

In vcc_sendmsg(), we account skb->truesize to sk->sk_wmem_alloc by
atm_account_tx().

It is expected to be reverted by atm_pop_raw() later called by
vcc->dev->ops->send(vcc, skb).

However, vcc_sendmsg() misses the same revert when copy_from_iter_full()
fails, and then we will leak a socket.

Let's factorise the revert part as atm_return_tx() and call it in
the failure path.

Note that the corresponding sk_wmem_alloc operation can be found in
alloc_tx() as of the blamed commit.

  $ git blame -L:alloc_tx net/atm/common.c c55fa3cccbc2c~

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-by: Simon Horman <horms@kernel.org>
Closes: https://lore.kernel.org/netdev/20250614161959.GR414686@horms.kernel.org/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Link: https://patch.msgid.link/20250616182147.963333-3-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/atmdev.h | 6 ++++++
 net/atm/common.c       | 1 +
 net/atm/raw.c          | 2 +-
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/atmdev.h b/include/linux/atmdev.h
index 9b02961d65ee..45f2f278b50a 100644
--- a/include/linux/atmdev.h
+++ b/include/linux/atmdev.h
@@ -249,6 +249,12 @@ static inline void atm_account_tx(struct atm_vcc *vcc, struct sk_buff *skb)
 	ATM_SKB(skb)->atm_options = vcc->atm_options;
 }
 
+static inline void atm_return_tx(struct atm_vcc *vcc, struct sk_buff *skb)
+{
+	WARN_ON_ONCE(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize,
+					   &sk_atm(vcc)->sk_wmem_alloc));
+}
+
 static inline void atm_force_charge(struct atm_vcc *vcc,int truesize)
 {
 	atomic_add(truesize, &sk_atm(vcc)->sk_rmem_alloc);
diff --git a/net/atm/common.c b/net/atm/common.c
index 9b75699992ff..d7f7976ea13a 100644
--- a/net/atm/common.c
+++ b/net/atm/common.c
@@ -635,6 +635,7 @@ int vcc_sendmsg(struct socket *sock, struct msghdr *m, size_t size)
 
 	skb->dev = NULL; /* for paths shared with net_device interfaces */
 	if (!copy_from_iter_full(skb_put(skb, size), size, &m->msg_iter)) {
+		atm_return_tx(vcc, skb);
 		kfree_skb(skb);
 		error = -EFAULT;
 		goto out;
diff --git a/net/atm/raw.c b/net/atm/raw.c
index 2b5f78a7ec3e..1e6511ec842c 100644
--- a/net/atm/raw.c
+++ b/net/atm/raw.c
@@ -36,7 +36,7 @@ static void atm_pop_raw(struct atm_vcc *vcc, struct sk_buff *skb)
 
 	pr_debug("(%d) %d -= %d\n",
 		 vcc->vci, sk_wmem_alloc_get(sk), ATM_SKB(skb)->acct_truesize);
-	WARN_ON(refcount_sub_and_test(ATM_SKB(skb)->acct_truesize, &sk->sk_wmem_alloc));
+	atm_return_tx(vcc, skb);
 	dev_kfree_skb_any(skb);
 	sk->sk_write_space(sk);
 }
-- 
cgit v1.2.3


From 635e118317ffa773f6d25ec6a71b7927d7e8886a Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 10:54:44 +0200
Subject: Revert "mtd: core: always create master device"

The idea behind this patch was to always let a "master" mtd device
available to anchor runtime PM. Historically, there was no mtd device
representing the whole storage as soon as partitions were coming into
play. The introduction of CONFIG_MTD_PARTITIONED_MASTER allowed to keep
this "master" device, but was not enabled by default to avoid breaking
existing users (otherwise the mtd device numbering would be totally
messed up with an off by 1, at least).

The approach of adding an mtd_master class on top of partitioned mtd
devices is breaking the mtd core in many creative ways, so better think
again this approach and revert the faulty changes for now.

This reverts commit 0aa7b390fc40a871267a2328bbbefca8b37ad307.

Fixes: 0aa7b390fc40 ("mtd: core: always create master device")
Tested-by: Guenter Roeck <linux@roeck-us.net>
Acked-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/mtdchar.c          |   2 +-
 drivers/mtd/mtdcore.c          | 152 +++++++++++------------------------------
 drivers/mtd/mtdcore.h          |   2 +-
 drivers/mtd/mtdpart.c          |  16 ++---
 include/linux/mtd/partitions.h |   2 +-
 5 files changed, 51 insertions(+), 123 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/mtdchar.c b/drivers/mtd/mtdchar.c
index 391d81ad960c..8dc4f5c493fc 100644
--- a/drivers/mtd/mtdchar.c
+++ b/drivers/mtd/mtdchar.c
@@ -559,7 +559,7 @@ static int mtdchar_blkpg_ioctl(struct mtd_info *mtd,
 		/* Sanitize user input */
 		p.devname[BLKPG_DEVNAMELTH - 1] = '\0';
 
-		return mtd_add_partition(mtd, p.devname, p.start, p.length, NULL);
+		return mtd_add_partition(mtd, p.devname, p.start, p.length);
 
 	case BLKPG_DEL_PARTITION:
 
diff --git a/drivers/mtd/mtdcore.c b/drivers/mtd/mtdcore.c
index 429d8c16baf0..5ba9a741f5ac 100644
--- a/drivers/mtd/mtdcore.c
+++ b/drivers/mtd/mtdcore.c
@@ -68,13 +68,7 @@ static struct class mtd_class = {
 	.pm = MTD_CLS_PM_OPS,
 };
 
-static struct class mtd_master_class = {
-	.name = "mtd_master",
-	.pm = MTD_CLS_PM_OPS,
-};
-
 static DEFINE_IDR(mtd_idr);
-static DEFINE_IDR(mtd_master_idr);
 
 /* These are exported solely for the purpose of mtd_blkdevs.c. You
    should not use them for _anything_ else */
@@ -89,9 +83,8 @@ EXPORT_SYMBOL_GPL(__mtd_next_device);
 
 static LIST_HEAD(mtd_notifiers);
 
-#define MTD_MASTER_DEVS 255
+
 #define MTD_DEVT(index) MKDEV(MTD_CHAR_MAJOR, (index)*2)
-static dev_t mtd_master_devt;
 
 /* REVISIT once MTD uses the driver model better, whoever allocates
  * the mtd_info will probably want to use the release() hook...
@@ -111,17 +104,6 @@ static void mtd_release(struct device *dev)
 	device_destroy(&mtd_class, index + 1);
 }
 
-static void mtd_master_release(struct device *dev)
-{
-	struct mtd_info *mtd = dev_get_drvdata(dev);
-
-	idr_remove(&mtd_master_idr, mtd->index);
-	of_node_put(mtd_get_of_node(mtd));
-
-	if (mtd_is_partition(mtd))
-		release_mtd_partition(mtd);
-}
-
 static void mtd_device_release(struct kref *kref)
 {
 	struct mtd_info *mtd = container_of(kref, struct mtd_info, refcnt);
@@ -385,11 +367,6 @@ static const struct device_type mtd_devtype = {
 	.release	= mtd_release,
 };
 
-static const struct device_type mtd_master_devtype = {
-	.name		= "mtd_master",
-	.release	= mtd_master_release,
-};
-
 static bool mtd_expert_analysis_mode;
 
 #ifdef CONFIG_DEBUG_FS
@@ -657,13 +634,13 @@ exit_parent:
 /**
  *	add_mtd_device - register an MTD device
  *	@mtd: pointer to new MTD device info structure
- *	@partitioned: create partitioned device
  *
  *	Add a device to the list of MTD devices present in the system, and
  *	notify each currently active MTD 'user' of its arrival. Returns
  *	zero on success or non-zero on failure.
  */
-int add_mtd_device(struct mtd_info *mtd, bool partitioned)
+
+int add_mtd_device(struct mtd_info *mtd)
 {
 	struct device_node *np = mtd_get_of_node(mtd);
 	struct mtd_info *master = mtd_get_master(mtd);
@@ -710,17 +687,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 	ofidx = -1;
 	if (np)
 		ofidx = of_alias_get_id(np, "mtd");
-	if (partitioned) {
-		if (ofidx >= 0)
-			i = idr_alloc(&mtd_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
-		else
-			i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL);
-	} else {
-		if (ofidx >= 0)
-			i = idr_alloc(&mtd_master_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
-		else
-			i = idr_alloc(&mtd_master_idr, mtd, 0, 0, GFP_KERNEL);
-	}
+	if (ofidx >= 0)
+		i = idr_alloc(&mtd_idr, mtd, ofidx, ofidx + 1, GFP_KERNEL);
+	else
+		i = idr_alloc(&mtd_idr, mtd, 0, 0, GFP_KERNEL);
 	if (i < 0) {
 		error = i;
 		goto fail_locked;
@@ -768,18 +738,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 	/* Caller should have set dev.parent to match the
 	 * physical device, if appropriate.
 	 */
-	if (partitioned) {
-		mtd->dev.type = &mtd_devtype;
-		mtd->dev.class = &mtd_class;
-		mtd->dev.devt = MTD_DEVT(i);
-		dev_set_name(&mtd->dev, "mtd%d", i);
-		error = dev_set_name(&mtd->dev, "mtd%d", i);
-	} else {
-		mtd->dev.type = &mtd_master_devtype;
-		mtd->dev.class = &mtd_master_class;
-		mtd->dev.devt = MKDEV(MAJOR(mtd_master_devt), i);
-		error = dev_set_name(&mtd->dev, "mtd_master%d", i);
-	}
+	mtd->dev.type = &mtd_devtype;
+	mtd->dev.class = &mtd_class;
+	mtd->dev.devt = MTD_DEVT(i);
+	error = dev_set_name(&mtd->dev, "mtd%d", i);
 	if (error)
 		goto fail_devname;
 	dev_set_drvdata(&mtd->dev, mtd);
@@ -787,7 +749,6 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 	of_node_get(mtd_get_of_node(mtd));
 	error = device_register(&mtd->dev);
 	if (error) {
-		pr_err("mtd: %s device_register fail %d\n", mtd->name, error);
 		put_device(&mtd->dev);
 		goto fail_added;
 	}
@@ -799,13 +760,10 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 
 	mtd_debugfs_populate(mtd);
 
-	if (partitioned) {
-		device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
-			      "mtd%dro", i);
-	}
+	device_create(&mtd_class, mtd->dev.parent, MTD_DEVT(i) + 1, NULL,
+		      "mtd%dro", i);
 
-	pr_debug("mtd: Giving out %spartitioned device %d to %s\n",
-		 partitioned ? "" : "un-", i, mtd->name);
+	pr_debug("mtd: Giving out device %d to %s\n", i, mtd->name);
 	/* No need to get a refcount on the module containing
 	   the notifier, since we hold the mtd_table_mutex */
 	list_for_each_entry(not, &mtd_notifiers, list)
@@ -813,16 +771,13 @@ int add_mtd_device(struct mtd_info *mtd, bool partitioned)
 
 	mutex_unlock(&mtd_table_mutex);
 
-	if (partitioned) {
-		if (of_property_read_bool(mtd_get_of_node(mtd), "linux,rootfs")) {
-			if (IS_BUILTIN(CONFIG_MTD)) {
-				pr_info("mtd: setting mtd%d (%s) as root device\n",
-					mtd->index, mtd->name);
-				ROOT_DEV = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
-			} else {
-				pr_warn("mtd: can't set mtd%d (%s) as root device - mtd must be builtin\n",
-					mtd->index, mtd->name);
-			}
+	if (of_property_read_bool(mtd_get_of_node(mtd), "linux,rootfs")) {
+		if (IS_BUILTIN(CONFIG_MTD)) {
+			pr_info("mtd: setting mtd%d (%s) as root device\n", mtd->index, mtd->name);
+			ROOT_DEV = MKDEV(MTD_BLOCK_MAJOR, mtd->index);
+		} else {
+			pr_warn("mtd: can't set mtd%d (%s) as root device - mtd must be builtin\n",
+				mtd->index, mtd->name);
 		}
 	}
 
@@ -838,10 +793,7 @@ fail_nvmem_add:
 fail_added:
 	of_node_put(mtd_get_of_node(mtd));
 fail_devname:
-	if (partitioned)
-		idr_remove(&mtd_idr, i);
-	else
-		idr_remove(&mtd_master_idr, i);
+	idr_remove(&mtd_idr, i);
 fail_locked:
 	mutex_unlock(&mtd_table_mutex);
 	return error;
@@ -859,14 +811,12 @@ fail_locked:
 
 int del_mtd_device(struct mtd_info *mtd)
 {
-	struct mtd_notifier *not;
-	struct idr *idr;
 	int ret;
+	struct mtd_notifier *not;
 
 	mutex_lock(&mtd_table_mutex);
 
-	idr = mtd->dev.class == &mtd_class ? &mtd_idr : &mtd_master_idr;
-	if (idr_find(idr, mtd->index) != mtd) {
+	if (idr_find(&mtd_idr, mtd->index) != mtd) {
 		ret = -ENODEV;
 		goto out_error;
 	}
@@ -1106,7 +1056,6 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
 			      const struct mtd_partition *parts,
 			      int nr_parts)
 {
-	struct mtd_info *parent;
 	int ret, err;
 
 	mtd_set_dev_defaults(mtd);
@@ -1115,30 +1064,25 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
 	if (ret)
 		goto out;
 
-	ret = add_mtd_device(mtd, false);
-	if (ret)
-		goto out;
-
 	if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER)) {
-		ret = mtd_add_partition(mtd, mtd->name, 0, MTDPART_SIZ_FULL, &parent);
+		ret = add_mtd_device(mtd);
 		if (ret)
 			goto out;
-
-	} else {
-		parent = mtd;
 	}
 
 	/* Prefer parsed partitions over driver-provided fallback */
-	ret = parse_mtd_partitions(parent, types, parser_data);
+	ret = parse_mtd_partitions(mtd, types, parser_data);
 	if (ret == -EPROBE_DEFER)
 		goto out;
 
 	if (ret > 0)
 		ret = 0;
 	else if (nr_parts)
-		ret = add_mtd_partitions(parent, parts, nr_parts);
-	else if (!IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
-		ret = mtd_add_partition(parent, mtd->name, 0, MTDPART_SIZ_FULL, NULL);
+		ret = add_mtd_partitions(mtd, parts, nr_parts);
+	else if (!device_is_registered(&mtd->dev))
+		ret = add_mtd_device(mtd);
+	else
+		ret = 0;
 
 	if (ret)
 		goto out;
@@ -1158,14 +1102,13 @@ int mtd_device_parse_register(struct mtd_info *mtd, const char * const *types,
 		register_reboot_notifier(&mtd->reboot_notifier);
 	}
 
-	return 0;
 out:
-	nvmem_unregister(mtd->otp_user_nvmem);
-	nvmem_unregister(mtd->otp_factory_nvmem);
-
-	del_mtd_partitions(mtd);
+	if (ret) {
+		nvmem_unregister(mtd->otp_user_nvmem);
+		nvmem_unregister(mtd->otp_factory_nvmem);
+	}
 
-	if (device_is_registered(&mtd->dev)) {
+	if (ret && device_is_registered(&mtd->dev)) {
 		err = del_mtd_device(mtd);
 		if (err)
 			pr_err("Error when deleting MTD device (%d)\n", err);
@@ -1324,7 +1267,8 @@ int __get_mtd_device(struct mtd_info *mtd)
 		mtd = mtd->parent;
 	}
 
-	kref_get(&master->refcnt);
+	if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
+		kref_get(&master->refcnt);
 
 	return 0;
 }
@@ -1418,7 +1362,8 @@ void __put_mtd_device(struct mtd_info *mtd)
 		mtd = parent;
 	}
 
-	kref_put(&master->refcnt, mtd_device_release);
+	if (IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER))
+		kref_put(&master->refcnt, mtd_device_release);
 
 	module_put(master->owner);
 
@@ -2585,16 +2530,6 @@ static int __init init_mtd(void)
 	if (ret)
 		goto err_reg;
 
-	ret = class_register(&mtd_master_class);
-	if (ret)
-		goto err_reg2;
-
-	ret = alloc_chrdev_region(&mtd_master_devt, 0, MTD_MASTER_DEVS, "mtd_master");
-	if (ret < 0) {
-		pr_err("unable to allocate char dev region\n");
-		goto err_chrdev;
-	}
-
 	mtd_bdi = mtd_bdi_init("mtd");
 	if (IS_ERR(mtd_bdi)) {
 		ret = PTR_ERR(mtd_bdi);
@@ -2619,10 +2554,6 @@ out_procfs:
 	bdi_unregister(mtd_bdi);
 	bdi_put(mtd_bdi);
 err_bdi:
-	unregister_chrdev_region(mtd_master_devt, MTD_MASTER_DEVS);
-err_chrdev:
-	class_unregister(&mtd_master_class);
-err_reg2:
 	class_unregister(&mtd_class);
 err_reg:
 	pr_err("Error registering mtd class or bdi: %d\n", ret);
@@ -2636,12 +2567,9 @@ static void __exit cleanup_mtd(void)
 	if (proc_mtd)
 		remove_proc_entry("mtd", NULL);
 	class_unregister(&mtd_class);
-	class_unregister(&mtd_master_class);
-	unregister_chrdev_region(mtd_master_devt, MTD_MASTER_DEVS);
 	bdi_unregister(mtd_bdi);
 	bdi_put(mtd_bdi);
 	idr_destroy(&mtd_idr);
-	idr_destroy(&mtd_master_idr);
 }
 
 module_init(init_mtd);
diff --git a/drivers/mtd/mtdcore.h b/drivers/mtd/mtdcore.h
index 2258d31c5aa6..b014861a06a6 100644
--- a/drivers/mtd/mtdcore.h
+++ b/drivers/mtd/mtdcore.h
@@ -8,7 +8,7 @@ extern struct mutex mtd_table_mutex;
 extern struct backing_dev_info *mtd_bdi;
 
 struct mtd_info *__mtd_next_device(int i);
-int __must_check add_mtd_device(struct mtd_info *mtd, bool partitioned);
+int __must_check add_mtd_device(struct mtd_info *mtd);
 int del_mtd_device(struct mtd_info *mtd);
 int add_mtd_partitions(struct mtd_info *, const struct mtd_partition *, int);
 int del_mtd_partitions(struct mtd_info *);
diff --git a/drivers/mtd/mtdpart.c b/drivers/mtd/mtdpart.c
index 5a3db36d734e..994e8c51e674 100644
--- a/drivers/mtd/mtdpart.c
+++ b/drivers/mtd/mtdpart.c
@@ -86,7 +86,8 @@ static struct mtd_info *allocate_partition(struct mtd_info *parent,
 	 * parent conditional on that option. Note, this is a way to
 	 * distinguish between the parent and its partitions in sysfs.
 	 */
-	child->dev.parent = &parent->dev;
+	child->dev.parent = IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) || mtd_is_partition(parent) ?
+			    &parent->dev : parent->dev.parent;
 	child->dev.of_node = part->of_node;
 	child->parent = parent;
 	child->part.offset = part->offset;
@@ -242,7 +243,7 @@ static int mtd_add_partition_attrs(struct mtd_info *new)
 }
 
 int mtd_add_partition(struct mtd_info *parent, const char *name,
-		      long long offset, long long length, struct mtd_info **out)
+		      long long offset, long long length)
 {
 	struct mtd_info *master = mtd_get_master(parent);
 	u64 parent_size = mtd_is_partition(parent) ?
@@ -275,15 +276,12 @@ int mtd_add_partition(struct mtd_info *parent, const char *name,
 	list_add_tail(&child->part.node, &parent->partitions);
 	mutex_unlock(&master->master.partitions_lock);
 
-	ret = add_mtd_device(child, true);
+	ret = add_mtd_device(child);
 	if (ret)
 		goto err_remove_part;
 
 	mtd_add_partition_attrs(child);
 
-	if (out)
-		*out = child;
-
 	return 0;
 
 err_remove_part:
@@ -415,7 +413,7 @@ int add_mtd_partitions(struct mtd_info *parent,
 		list_add_tail(&child->part.node, &parent->partitions);
 		mutex_unlock(&master->master.partitions_lock);
 
-		ret = add_mtd_device(child, true);
+		ret = add_mtd_device(child);
 		if (ret) {
 			mutex_lock(&master->master.partitions_lock);
 			list_del(&child->part.node);
@@ -592,6 +590,9 @@ static int mtd_part_of_parse(struct mtd_info *master,
 	int ret, err = 0;
 
 	dev = &master->dev;
+	/* Use parent device (controller) if the top level MTD is not registered */
+	if (!IS_ENABLED(CONFIG_MTD_PARTITIONED_MASTER) && !mtd_is_partition(master))
+		dev = master->dev.parent;
 
 	np = mtd_get_of_node(master);
 	if (mtd_is_partition(master))
@@ -710,7 +711,6 @@ int parse_mtd_partitions(struct mtd_info *master, const char *const *types,
 		if (ret < 0 && !err)
 			err = ret;
 	}
-
 	return err;
 }
 
diff --git a/include/linux/mtd/partitions.h b/include/linux/mtd/partitions.h
index 5daf80df9e89..b74a539ec581 100644
--- a/include/linux/mtd/partitions.h
+++ b/include/linux/mtd/partitions.h
@@ -108,7 +108,7 @@ extern void deregister_mtd_parser(struct mtd_part_parser *parser);
 		      deregister_mtd_parser)
 
 int mtd_add_partition(struct mtd_info *master, const char *name,
-		      long long offset, long long length, struct mtd_info **part);
+		      long long offset, long long length);
 int mtd_del_partition(struct mtd_info *master, int partno);
 uint64_t mtd_get_device_size(const struct mtd_info *mtd);
 
-- 
cgit v1.2.3


From dba90f5a79c13936de4273a19e67908a0c296afe Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 10:48:00 +0200
Subject: mtd: spinand: winbond: Prevent unsupported frequencies on dual/quad
 I/O variants

Dual and quad capable chips natively support dual and quad I/O variants
at up to 104MHz (1-2-2 and 1-4-4 operations). Reaching the maximum speed
of 166MHz is theoretically possible (while still unsupported in the
field) by adding a few more dummy cycles. Let's be accurate and clearly
state this limit.

Setting a maximum frequency implies adding the frequency parameter to
the macro, which is done using a variadic argument to avoid impacting
all the other drivers which already make use of this macro.

Fixes: 1ea808b4d15b ("mtd: spinand: winbond: Update the *JW chip definitions")
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/winbond.c |  4 ++--
 include/linux/mtd/spinand.h    | 10 ++++++----
 2 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index 0756966b4e3c..b7a28f001a38 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -42,11 +42,11 @@ static SPINAND_OP_VARIANTS(update_cache_octal_variants,
 static SPINAND_OP_VARIANTS(read_cache_dual_quad_dtr_variants,
 		SPINAND_PAGE_READ_FROM_CACHE_1S_4D_4D_OP(0, 8, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_4D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 104 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_2D_2D_OP(0, 4, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_2D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 104 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_1D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 811a0f356315..15eaa09da998 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -113,11 +113,12 @@
 		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 2),			\
 		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len, ...) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 2),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_2S_2S_OP(addr, ndummy, buf, len) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
@@ -151,11 +152,12 @@
 		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 4),			\
 		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len, ...) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 4),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_4S_4S_OP(addr, ndummy, buf, len) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
-- 
cgit v1.2.3


From ffaf1bf3737f706e4e9be876de4bc3c8fc578091 Mon Sep 17 00:00:00 2001
From: RubenKelevra <rubenkelevra@gmail.com>
Date: Wed, 18 Jun 2025 01:09:27 +0200
Subject: fs_context: fix parameter name in infofc() macro
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The macro takes a parameter called "p" but references "fc" internally.
This happens to compile as long as callers pass a variable named fc,
but breaks otherwise. Rename the first parameter to “fc” to match the
usage and to be consistent with warnfc() / errorfc().

Fixes: a3ff937b33d9 ("prefix-handling analogues of errorf() and friends")
Signed-off-by: RubenKelevra <rubenkelevra@gmail.com>
Link: https://lore.kernel.org/20250617230927.1790401-1-rubenkelevra@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/fs_context.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fs_context.h b/include/linux/fs_context.h
index a19e4bd32e4d..7773eb870039 100644
--- a/include/linux/fs_context.h
+++ b/include/linux/fs_context.h
@@ -200,7 +200,7 @@ void logfc(struct fc_log *log, const char *prefix, char level, const char *fmt,
  */
 #define infof(fc, fmt, ...) __logfc(fc, 'i', fmt, ## __VA_ARGS__)
 #define info_plog(p, fmt, ...) __plog(p, 'i', fmt, ## __VA_ARGS__)
-#define infofc(p, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__)
+#define infofc(fc, fmt, ...) __plog((&(fc)->log), 'i', fmt, ## __VA_ARGS__)
 
 /**
  * warnf - Store supplementary warning message
-- 
cgit v1.2.3


From 82a0302e7167d0b7c6cde56613db3748f8dd806d Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 16 Jun 2025 16:38:49 +0800
Subject: padata: Remove comment for reorder_work

Remove comment for reorder_work which no longer exists.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Fixes: 71203f68c774 ("padata: Fix pd UAF once and for all")
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 include/linux/padata.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/padata.h b/include/linux/padata.h
index b486c7359de2..765f2778e264 100644
--- a/include/linux/padata.h
+++ b/include/linux/padata.h
@@ -90,7 +90,6 @@ struct padata_cpumask {
  * @processed: Number of already processed objects.
  * @cpu: Next CPU to be processed.
  * @cpumask: The cpumasks in use for parallel and serial workers.
- * @reorder_work: work struct for reordering.
  */
 struct parallel_data {
 	struct padata_shell		*ps;
-- 
cgit v1.2.3


From 9724e6f1953644cc9a5d102605d624bc79609038 Mon Sep 17 00:00:00 2001
From: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Date: Wed, 11 Jun 2025 08:13:36 +0200
Subject: pinctrl: Constify pointers to 'pinctrl_desc'

Pin controller core code only stores the pointer to
'struct pinctrl_desc' and does not modify it anywhere.  The pointer can
be changed to pointer to const which makes the code safer, explicit and
later allows constifying 'pinctrl_desc' allocations in individual
drivers.

Reviewed-by: Geert Uytterhoeven <geert+renesas@glider.be>
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
Link: https://lore.kernel.org/20250611-pinctrl-const-desc-v2-4-b11c1d650384@linaro.org
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
---
 drivers/pinctrl/core.c          | 13 +++++++------
 drivers/pinctrl/core.h          |  2 +-
 include/linux/pinctrl/pinctrl.h |  8 ++++----
 3 files changed, 12 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
index 9046292d1360..73b78d6eac67 100644
--- a/drivers/pinctrl/core.c
+++ b/drivers/pinctrl/core.c
@@ -2062,7 +2062,7 @@ static int pinctrl_check_ops(struct pinctrl_dev *pctldev)
  * @driver_data: private pin controller data for this pin controller
  */
 static struct pinctrl_dev *
-pinctrl_init_controller(struct pinctrl_desc *pctldesc, struct device *dev,
+pinctrl_init_controller(const struct pinctrl_desc *pctldesc, struct device *dev,
 			void *driver_data)
 {
 	struct pinctrl_dev *pctldev;
@@ -2132,7 +2132,8 @@ out_err:
 	return ERR_PTR(ret);
 }
 
-static void pinctrl_uninit_controller(struct pinctrl_dev *pctldev, struct pinctrl_desc *pctldesc)
+static void pinctrl_uninit_controller(struct pinctrl_dev *pctldev,
+				      const struct pinctrl_desc *pctldesc)
 {
 	pinctrl_free_pindescs(pctldev, pctldesc->pins,
 			      pctldesc->npins);
@@ -2209,7 +2210,7 @@ EXPORT_SYMBOL_GPL(pinctrl_enable);
  * struct pinctrl_dev handle. To avoid issues later on, please use the
  * new pinctrl_register_and_init() below instead.
  */
-struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc,
+struct pinctrl_dev *pinctrl_register(const struct pinctrl_desc *pctldesc,
 				    struct device *dev, void *driver_data)
 {
 	struct pinctrl_dev *pctldev;
@@ -2239,7 +2240,7 @@ EXPORT_SYMBOL_GPL(pinctrl_register);
  * Note that pinctrl_enable() still needs to be manually called after
  * this once the driver is ready.
  */
-int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
+int pinctrl_register_and_init(const struct pinctrl_desc *pctldesc,
 			      struct device *dev, void *driver_data,
 			      struct pinctrl_dev **pctldev)
 {
@@ -2330,7 +2331,7 @@ static int devm_pinctrl_dev_match(struct device *dev, void *res, void *data)
  * The pinctrl device will be automatically released when the device is unbound.
  */
 struct pinctrl_dev *devm_pinctrl_register(struct device *dev,
-					  struct pinctrl_desc *pctldesc,
+					  const struct pinctrl_desc *pctldesc,
 					  void *driver_data)
 {
 	struct pinctrl_dev **ptr, *pctldev;
@@ -2364,7 +2365,7 @@ EXPORT_SYMBOL_GPL(devm_pinctrl_register);
  * The pinctrl device will be automatically released when the device is unbound.
  */
 int devm_pinctrl_register_and_init(struct device *dev,
-				   struct pinctrl_desc *pctldesc,
+				   const struct pinctrl_desc *pctldesc,
 				   void *driver_data,
 				   struct pinctrl_dev **pctldev)
 {
diff --git a/drivers/pinctrl/core.h b/drivers/pinctrl/core.h
index d6c24978e708..fc513a9cdd4f 100644
--- a/drivers/pinctrl/core.h
+++ b/drivers/pinctrl/core.h
@@ -51,7 +51,7 @@ struct pinctrl_state;
  */
 struct pinctrl_dev {
 	struct list_head node;
-	struct pinctrl_desc *desc;
+	const struct pinctrl_desc *desc;
 	struct radix_tree_root pin_desc_tree;
 #ifdef CONFIG_GENERIC_PINCTRL_GROUPS
 	struct radix_tree_root pin_group_tree;
diff --git a/include/linux/pinctrl/pinctrl.h b/include/linux/pinctrl/pinctrl.h
index 9a8189ffd0f2..d138e1815645 100644
--- a/include/linux/pinctrl/pinctrl.h
+++ b/include/linux/pinctrl/pinctrl.h
@@ -165,25 +165,25 @@ struct pinctrl_desc {
 
 /* External interface to pin controller */
 
-extern int pinctrl_register_and_init(struct pinctrl_desc *pctldesc,
+extern int pinctrl_register_and_init(const struct pinctrl_desc *pctldesc,
 				     struct device *dev, void *driver_data,
 				     struct pinctrl_dev **pctldev);
 extern int pinctrl_enable(struct pinctrl_dev *pctldev);
 
 /* Please use pinctrl_register_and_init() and pinctrl_enable() instead */
-extern struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc,
+extern struct pinctrl_dev *pinctrl_register(const struct pinctrl_desc *pctldesc,
 				struct device *dev, void *driver_data);
 
 extern void pinctrl_unregister(struct pinctrl_dev *pctldev);
 
 extern int devm_pinctrl_register_and_init(struct device *dev,
-				struct pinctrl_desc *pctldesc,
+				const struct pinctrl_desc *pctldesc,
 				void *driver_data,
 				struct pinctrl_dev **pctldev);
 
 /* Please use devm_pinctrl_register_and_init() instead */
 extern struct pinctrl_dev *devm_pinctrl_register(struct device *dev,
-				struct pinctrl_desc *pctldesc,
+				const struct pinctrl_desc *pctldesc,
 				void *driver_data);
 
 extern void devm_pinctrl_unregister(struct device *dev,
-- 
cgit v1.2.3


From 271ff96d6066347cd267ac3bcd6021bd4d38913d Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 16 Jun 2025 09:12:07 +0300
Subject: PM: runtime: Document return values of suspend-related API functions

Document return values for device suspend and idle related API
functions.

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Link: https://patch.msgid.link/20250616061212.2286741-2-sakari.ailus@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm_runtime.h | 147 ++++++++++++++++++++++++++++++++++++++++++---
 1 file changed, 138 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index e7cb70fcc0af..9dd2e4031a27 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -337,6 +337,20 @@ static inline void pm_runtime_release_supplier(struct device_link *link) {}
  * Invoke the "idle check" callback of @dev and, depending on its return value,
  * set up autosuspend of @dev or suspend it (depending on whether or not
  * autosuspend has been enabled for it).
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero, Runtime PM status change ongoing
+ *            or device not in %RPM_ACTIVE state.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -EINPROGRESS: Suspend already in progress.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
+ * Other values and conditions for the above values are possible as returned by
+ * Runtime PM idle and suspend callbacks.
  */
 static inline int pm_runtime_idle(struct device *dev)
 {
@@ -346,6 +360,18 @@ static inline int pm_runtime_idle(struct device *dev)
 /**
  * pm_runtime_suspend - Suspend a device synchronously.
  * @dev: Target device.
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
+ * Other values and conditions for the above values are possible as returned by
+ * Runtime PM suspend callbacks.
  */
 static inline int pm_runtime_suspend(struct device *dev)
 {
@@ -358,6 +384,18 @@ static inline int pm_runtime_suspend(struct device *dev)
  *
  * Set up autosuspend of @dev or suspend it (depending on whether or not
  * autosuspend is enabled for it) without engaging its "idle check" callback.
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
+ * Other values and conditions for the above values are possible as returned by
+ * Runtime PM suspend callbacks.
  */
 static inline int pm_runtime_autosuspend(struct device *dev)
 {
@@ -379,6 +417,18 @@ static inline int pm_runtime_resume(struct device *dev)
  *
  * Queue up a work item to run an equivalent of pm_runtime_idle() for @dev
  * asynchronously.
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero, Runtime PM status change ongoing
+ *            or device not in %RPM_ACTIVE state.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -EINPROGRESS: Suspend already in progress.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
  */
 static inline int pm_request_idle(struct device *dev)
 {
@@ -400,6 +450,17 @@ static inline int pm_request_resume(struct device *dev)
  *
  * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev
  * asynchronously.
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -EINPROGRESS: Suspend already in progress.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
  */
 static inline int pm_request_autosuspend(struct device *dev)
 {
@@ -464,6 +525,17 @@ static inline int pm_runtime_resume_and_get(struct device *dev)
  *
  * Decrement the runtime PM usage counter of @dev and if it turns out to be
  * equal to 0, queue up a work item for @dev like in pm_request_idle().
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -EINPROGRESS: Suspend already in progress.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
  */
 static inline int pm_runtime_put(struct device *dev)
 {
@@ -478,6 +550,17 @@ DEFINE_FREE(pm_runtime_put, struct device *, if (_T) pm_runtime_put(_T))
  *
  * Decrement the runtime PM usage counter of @dev and if it turns out to be
  * equal to 0, queue up a work item for @dev like in pm_request_autosuspend().
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -EINPROGRESS: Suspend already in progress.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
  */
 static inline int __pm_runtime_put_autosuspend(struct device *dev)
 {
@@ -490,6 +573,17 @@ static inline int __pm_runtime_put_autosuspend(struct device *dev)
  *
  * Decrement the runtime PM usage counter of @dev and if it turns out to be
  * equal to 0, queue up a work item for @dev like in pm_request_autosuspend().
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -EINPROGRESS: Suspend already in progress.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
  */
 static inline int pm_runtime_put_autosuspend(struct device *dev)
 {
@@ -506,9 +600,20 @@ static inline int pm_runtime_put_autosuspend(struct device *dev)
  * return value, set up autosuspend of @dev or suspend it (depending on whether
  * or not autosuspend has been enabled for it).
  *
- * The possible return values of this function are the same as for
- * pm_runtime_idle() and the runtime PM usage counter of @dev remains
- * decremented in all cases, even if it returns an error code.
+ * The runtime PM usage counter of @dev remains decremented in all cases, even
+ * if it returns an error code.
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
+ * Other values and conditions for the above values are possible as returned by
+ * Runtime PM suspend callbacks.
  */
 static inline int pm_runtime_put_sync(struct device *dev)
 {
@@ -522,9 +627,21 @@ static inline int pm_runtime_put_sync(struct device *dev)
  * Decrement the runtime PM usage counter of @dev and if it turns out to be
  * equal to 0, carry out runtime-suspend of @dev synchronously.
  *
- * The possible return values of this function are the same as for
- * pm_runtime_suspend() and the runtime PM usage counter of @dev remains
- * decremented in all cases, even if it returns an error code.
+ * The runtime PM usage counter of @dev remains decremented in all cases, even
+ * if it returns an error code.
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EAGAIN: usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
+ * Other values and conditions for the above values are possible as returned by
+ * Runtime PM suspend callbacks.
  */
 static inline int pm_runtime_put_sync_suspend(struct device *dev)
 {
@@ -539,9 +656,21 @@ static inline int pm_runtime_put_sync_suspend(struct device *dev)
  * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending
  * on whether or not autosuspend has been enabled for it).
  *
- * The possible return values of this function are the same as for
- * pm_runtime_autosuspend() and the runtime PM usage counter of @dev remains
- * decremented in all cases, even if it returns an error code.
+ * The runtime PM usage counter of @dev remains decremented in all cases, even
+ * if it returns an error code.
+ *
+ * Return:
+ * * 0: Success.
+ * * -EINVAL: Runtime PM error.
+ * * -EACCES: Runtime PM disabled.
+ * * -EAGAIN: Runtime PM usage_count non-zero or Runtime PM status change ongoing.
+ * * -EBUSY: Runtime PM child_count non-zero.
+ * * -EPERM: Device PM QoS resume latency 0.
+ * * -EINPROGRESS: Suspend already in progress.
+ * * -ENOSYS: CONFIG_PM not enabled.
+ * * 1: Device already suspended.
+ * Other values and conditions for the above values are possible as returned by
+ * Runtime PM suspend callbacks.
  */
 static inline int pm_runtime_put_sync_autosuspend(struct device *dev)
 {
-- 
cgit v1.2.3


From b3db492e8335417dfd66c1fa2ea08e1d2f7b6736 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 16 Jun 2025 09:12:08 +0300
Subject: PM: runtime: Mark last busy stamp in pm_runtime_put_autosuspend()

Set device's last busy timestamp to current time in
pm_runtime_put_autosuspend(). Callers wishing not to do that will need to
use __pm_runtime_put_autosuspend().

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://patch.msgid.link/20250616061212.2286741-3-sakari.ailus@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/runtime_pm.rst | 23 ++++++++++-------------
 include/linux/pm_runtime.h         | 12 +++++++-----
 2 files changed, 17 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst
index 63344bea8393..e7bbdc66d64c 100644
--- a/Documentation/power/runtime_pm.rst
+++ b/Documentation/power/runtime_pm.rst
@@ -411,8 +411,9 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       pm_request_idle(dev) and return its result
 
   `int pm_runtime_put_autosuspend(struct device *dev);`
-    - does the same as __pm_runtime_put_autosuspend() for now, but in the
-      future, will also call pm_runtime_mark_last_busy() as well, DO NOT USE!
+    - set the power.last_busy field to the current time and decrement the
+      device's usage counter; if the result is 0 then run
+      pm_request_autosuspend(dev) and return its result
 
   `int __pm_runtime_put_autosuspend(struct device *dev);`
     - decrement the device's usage counter; if the result is 0 then run
@@ -870,11 +871,9 @@ device is automatically suspended (the subsystem or driver still has to call
 the appropriate PM routines); rather it means that runtime suspends will
 automatically be delayed until the desired period of inactivity has elapsed.
 
-Inactivity is determined based on the power.last_busy field.  Drivers should
-call pm_runtime_mark_last_busy() to update this field after carrying out I/O,
-typically just before calling __pm_runtime_put_autosuspend().  The desired
-length of the inactivity period is a matter of policy.  Subsystems can set this
-length initially by calling pm_runtime_set_autosuspend_delay(), but after device
+Inactivity is determined based on the power.last_busy field. The desired length
+of the inactivity period is a matter of policy.  Subsystems can set this length
+initially by calling pm_runtime_set_autosuspend_delay(), but after device
 registration the length should be controlled by user space, using the
 /sys/devices/.../power/autosuspend_delay_ms attribute.
 
@@ -885,7 +884,7 @@ instead of the non-autosuspend counterparts::
 
 	Instead of: pm_runtime_suspend    use: pm_runtime_autosuspend;
 	Instead of: pm_schedule_suspend   use: pm_request_autosuspend;
-	Instead of: pm_runtime_put        use: __pm_runtime_put_autosuspend;
+	Instead of: pm_runtime_put        use: pm_runtime_put_autosuspend;
 	Instead of: pm_runtime_put_sync   use: pm_runtime_put_sync_autosuspend.
 
 Drivers may also continue to use the non-autosuspend helper functions; they
@@ -922,12 +921,10 @@ Here is a schematic pseudo-code example::
 	foo_io_completion(struct foo_priv *foo, void *req)
 	{
 		lock(&foo->private_lock);
-		if (--foo->num_pending_requests == 0) {
-			pm_runtime_mark_last_busy(&foo->dev);
-			__pm_runtime_put_autosuspend(&foo->dev);
-		} else {
+		if (--foo->num_pending_requests == 0)
+			pm_runtime_put_autosuspend(&foo->dev);
+		else
 			foo_process_next_request(foo);
-		}
 		unlock(&foo->private_lock);
 		/* Send req result back to the user ... */
 	}
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 9dd2e4031a27..14ca7be96686 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -568,11 +568,13 @@ static inline int __pm_runtime_put_autosuspend(struct device *dev)
 }
 
 /**
- * pm_runtime_put_autosuspend - Drop device usage counter and queue autosuspend if 0.
+ * pm_runtime_put_autosuspend - Update the last access time of a device, drop
+ * its usage counter and queue autosuspend if the usage counter becomes 0.
  * @dev: Target device.
  *
- * Decrement the runtime PM usage counter of @dev and if it turns out to be
- * equal to 0, queue up a work item for @dev like in pm_request_autosuspend().
+ * Update the last access time of @dev, decrement runtime PM usage counter of
+ * @dev and if it turns out to be equal to 0, queue up a work item for @dev like
+ * in pm_request_autosuspend().
  *
  * Return:
  * * 0: Success.
@@ -587,8 +589,8 @@ static inline int __pm_runtime_put_autosuspend(struct device *dev)
  */
 static inline int pm_runtime_put_autosuspend(struct device *dev)
 {
-	return __pm_runtime_suspend(dev,
-	    RPM_GET_PUT | RPM_ASYNC | RPM_AUTO);
+	pm_runtime_mark_last_busy(dev);
+	return __pm_runtime_put_autosuspend(dev);
 }
 
 /**
-- 
cgit v1.2.3


From e24e0630b5ba13e83f65905becde9945518efa0b Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 16 Jun 2025 09:12:09 +0300
Subject: PM: runtime: Mark last busy stamp in
 pm_runtime_put_sync_autosuspend()

Set device's last busy timestamp to current time in
pm_runtime_put_sync_autosuspend().

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://patch.msgid.link/20250616061212.2286741-4-sakari.ailus@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/runtime_pm.rst |  3 ++-
 include/linux/pm_runtime.h         | 11 +++++++----
 2 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst
index e7bbdc66d64c..9c21c913f9cf 100644
--- a/Documentation/power/runtime_pm.rst
+++ b/Documentation/power/runtime_pm.rst
@@ -428,7 +428,8 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       pm_runtime_suspend(dev) and return its result
 
   `int pm_runtime_put_sync_autosuspend(struct device *dev);`
-    - decrement the device's usage counter; if the result is 0 then run
+    - set the power.last_busy field to the current time and decrement the
+      device's usage counter; if the result is 0 then run
       pm_runtime_autosuspend(dev) and return its result
 
   `void pm_runtime_enable(struct device *dev);`
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 14ca7be96686..3a0d5f0ea471 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -651,12 +651,14 @@ static inline int pm_runtime_put_sync_suspend(struct device *dev)
 }
 
 /**
- * pm_runtime_put_sync_autosuspend - Drop device usage counter and autosuspend if 0.
+ * pm_runtime_put_sync_autosuspend - Update the last access time of a device,
+ * drop device usage counter and autosuspend if 0.
  * @dev: Target device.
  *
- * Decrement the runtime PM usage counter of @dev and if it turns out to be
- * equal to 0, set up autosuspend of @dev or suspend it synchronously (depending
- * on whether or not autosuspend has been enabled for it).
+ * Update the last access time of @dev, decrement the runtime PM usage counter
+ * of @dev and if it turns out to be equal to 0, set up autosuspend of @dev or
+ * suspend it synchronously (depending on whether or not autosuspend has been
+ * enabled for it).
  *
  * The runtime PM usage counter of @dev remains decremented in all cases, even
  * if it returns an error code.
@@ -676,6 +678,7 @@ static inline int pm_runtime_put_sync_suspend(struct device *dev)
  */
 static inline int pm_runtime_put_sync_autosuspend(struct device *dev)
 {
+	pm_runtime_mark_last_busy(dev);
 	return __pm_runtime_suspend(dev, RPM_GET_PUT | RPM_AUTO);
 }
 
-- 
cgit v1.2.3


From 08071e64cb642ae19ebd6ffeb13b4f3d130b5860 Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 16 Jun 2025 09:12:10 +0300
Subject: PM: runtime: Mark last busy stamp in pm_runtime_autosuspend()

Set device's last busy timestamp to current time in
pm_runtime_autosuspend().

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://patch.msgid.link/20250616061212.2286741-5-sakari.ailus@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/runtime_pm.rst | 15 ++++++---------
 include/linux/pm_runtime.h         |  9 ++++++---
 2 files changed, 12 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst
index 9c21c913f9cf..39a0b62f6648 100644
--- a/Documentation/power/runtime_pm.rst
+++ b/Documentation/power/runtime_pm.rst
@@ -154,11 +154,9 @@ suspending the device are satisfied) and to queue up a suspend request for the
 device in that case.  If there is no idle callback, or if the callback returns
 0, then the PM core will attempt to carry out a runtime suspend of the device,
 also respecting devices configured for autosuspend.  In essence this means a
-call to pm_runtime_autosuspend() (do note that drivers needs to update the
-device last busy mark, pm_runtime_mark_last_busy(), to control the delay under
-this circumstance).  To prevent this (for example, if the callback routine has
-started a delayed suspend), the routine must return a non-zero value.  Negative
-error return codes are ignored by the PM core.
+call to pm_runtime_autosuspend(). To prevent this (for example, if the callback
+routine has started a delayed suspend), the routine must return a non-zero
+value.  Negative error return codes are ignored by the PM core.
 
 The helper functions provided by the PM core, described in Section 4, guarantee
 that the following constraints are met with respect to runtime PM callbacks for
@@ -330,10 +328,9 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       'power.disable_depth' is different from 0
 
   `int pm_runtime_autosuspend(struct device *dev);`
-    - same as pm_runtime_suspend() except that the autosuspend delay is taken
-      `into account;` if pm_runtime_autosuspend_expiration() says the delay has
-      not yet expired then an autosuspend is scheduled for the appropriate time
-      and 0 is returned
+    - same as pm_runtime_suspend() except that a call to
+      pm_runtime_mark_last_busy() is made and an autosuspend is scheduled for
+      the appropriate time and 0 is returned
 
   `int pm_runtime_resume(struct device *dev);`
     - execute the subsystem-level resume callback for the device; returns 0 on
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 3a0d5f0ea471..566a07b60f63 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -379,11 +379,13 @@ static inline int pm_runtime_suspend(struct device *dev)
 }
 
 /**
- * pm_runtime_autosuspend - Set up autosuspend of a device or suspend it.
+ * pm_runtime_autosuspend - Update the last access time and set up autosuspend
+ * of a device.
  * @dev: Target device.
  *
- * Set up autosuspend of @dev or suspend it (depending on whether or not
- * autosuspend is enabled for it) without engaging its "idle check" callback.
+ * First update the last access time, then set up autosuspend of @dev or suspend
+ * it (depending on whether or not autosuspend is enabled for it) without
+ * engaging its "idle check" callback.
  *
  * Return:
  * * 0: Success.
@@ -399,6 +401,7 @@ static inline int pm_runtime_suspend(struct device *dev)
  */
 static inline int pm_runtime_autosuspend(struct device *dev)
 {
+	pm_runtime_mark_last_busy(dev);
 	return __pm_runtime_suspend(dev, RPM_AUTO);
 }
 
-- 
cgit v1.2.3


From 18c1fe53d186867243f4cf17f4eef60737a16c4c Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Mon, 16 Jun 2025 09:12:11 +0300
Subject: PM: runtime: Mark last busy stamp in pm_request_autosuspend()

Set device's last busy timestamp to current time in
pm_request_autosuspend().

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Laurent Pinchart <laurent.pinchart@ideasonboard.com>
Link: https://patch.msgid.link/20250616061212.2286741-6-sakari.ailus@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 Documentation/power/runtime_pm.rst | 6 +++---
 include/linux/pm_runtime.h         | 8 +++++---
 2 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/power/runtime_pm.rst b/Documentation/power/runtime_pm.rst
index 39a0b62f6648..91bc93422262 100644
--- a/Documentation/power/runtime_pm.rst
+++ b/Documentation/power/runtime_pm.rst
@@ -354,9 +354,9 @@ drivers/base/power/runtime.c and include/linux/pm_runtime.h:
       success or error code if the request has not been queued up
 
   `int pm_request_autosuspend(struct device *dev);`
-    - schedule the execution of the subsystem-level suspend callback for the
-      device when the autosuspend delay has expired; if the delay has already
-      expired then the work item is queued up immediately
+    - Call pm_runtime_mark_last_busy() and schedule the execution of the
+      subsystem-level suspend callback for the device when the autosuspend delay
+      expires
 
   `int pm_schedule_suspend(struct device *dev, unsigned int delay);`
     - schedule the execution of the subsystem-level suspend callback for the
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index 566a07b60f63..778d5988f35e 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -448,11 +448,12 @@ static inline int pm_request_resume(struct device *dev)
 }
 
 /**
- * pm_request_autosuspend - Queue up autosuspend of a device.
+ * pm_request_autosuspend - Update the last access time and queue up autosuspend
+ * of a device.
  * @dev: Target device.
  *
- * Queue up a work item to run an equivalent pm_runtime_autosuspend() for @dev
- * asynchronously.
+ * Update the last access time of a device and queue up a work item to run an
+ * equivalent pm_runtime_autosuspend() for @dev asynchronously.
  *
  * Return:
  * * 0: Success.
@@ -467,6 +468,7 @@ static inline int pm_request_resume(struct device *dev)
  */
 static inline int pm_request_autosuspend(struct device *dev)
 {
+	pm_runtime_mark_last_busy(dev);
 	return __pm_runtime_suspend(dev, RPM_ASYNC | RPM_AUTO);
 }
 
-- 
cgit v1.2.3


From 4bfbc2691de8c869339090e851703209b17ba378 Mon Sep 17 00:00:00 2001
From: Thorsten Blum <thorsten.blum@linux.dev>
Date: Tue, 10 Jun 2025 12:40:59 +0200
Subject: mux: Convert mux_control_ops to a flex array member in mux_chip

Convert mux_control_ops to a flexible array member at the end of the
mux_chip struct and add the __counted_by() compiler attribute to
improve access bounds-checking via CONFIG_UBSAN_BOUNDS and
CONFIG_FORTIFY_SOURCE.

Use struct_size() to calculate the number of bytes to allocate for a new
mux chip and to remove the following Coccinelle/coccicheck warning:

  WARNING: Use struct_size

Use size_add() to safely add any extra bytes.

No functional changes intended.

Link: https://github.com/KSPP/linux/issues/83
Signed-off-by: Thorsten Blum <thorsten.blum@linux.dev>
Link: https://lore.kernel.org/r/20250610104106.1948-2-thorsten.blum@linux.dev
Signed-off-by: Kees Cook <kees@kernel.org>
---
 drivers/mux/core.c         | 7 +++----
 include/linux/mux/driver.h | 4 ++--
 2 files changed, 5 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mux/core.c b/drivers/mux/core.c
index 02be4ba37257..a3840fe0995f 100644
--- a/drivers/mux/core.c
+++ b/drivers/mux/core.c
@@ -98,13 +98,12 @@ struct mux_chip *mux_chip_alloc(struct device *dev,
 	if (WARN_ON(!dev || !controllers))
 		return ERR_PTR(-EINVAL);
 
-	mux_chip = kzalloc(sizeof(*mux_chip) +
-			   controllers * sizeof(*mux_chip->mux) +
-			   sizeof_priv, GFP_KERNEL);
+	mux_chip = kzalloc(size_add(struct_size(mux_chip, mux, controllers),
+				    sizeof_priv),
+			   GFP_KERNEL);
 	if (!mux_chip)
 		return ERR_PTR(-ENOMEM);
 
-	mux_chip->mux = (struct mux_control *)(mux_chip + 1);
 	mux_chip->dev.class = &mux_class;
 	mux_chip->dev.type = &mux_type;
 	mux_chip->dev.parent = dev;
diff --git a/include/linux/mux/driver.h b/include/linux/mux/driver.h
index 18824064f8c0..e58e59354e23 100644
--- a/include/linux/mux/driver.h
+++ b/include/linux/mux/driver.h
@@ -56,18 +56,18 @@ struct mux_control {
 /**
  * struct mux_chip -	Represents a chip holding mux controllers.
  * @controllers:	Number of mux controllers handled by the chip.
- * @mux:		Array of mux controllers that are handled.
  * @dev:		Device structure.
  * @id:			Used to identify the device internally.
  * @ops:		Mux controller operations.
+ * @mux:		Array of mux controllers that are handled.
  */
 struct mux_chip {
 	unsigned int controllers;
-	struct mux_control *mux;
 	struct device dev;
 	int id;
 
 	const struct mux_control_ops *ops;
+	struct mux_control mux[] __counted_by(controllers);
 };
 
 #define to_mux_chip(x) container_of((x), struct mux_chip, dev)
-- 
cgit v1.2.3


From 29bb79e9dbf1ba100125e39deb7147acd490903f Mon Sep 17 00:00:00 2001
From: "Gustavo A. R. Silva" <gustavoars@kernel.org>
Date: Tue, 17 Jun 2025 13:05:36 -0600
Subject: stddef: Introduce TRAILING_OVERLAP() helper macro

Add new TRAILING_OVERLAP() helper macro to create a union between
a flexible-array member (FAM) and a set of members that would
otherwise follow it. This overlays the trailing members onto the
FAM while preserving the original memory layout.

Co-developed-by: Kees Cook <kees@kernel.org>
Signed-off-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/aFG8gEwKXAWWIvX0@kspp
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/stddef.h | 20 ++++++++++++++++++++
 1 file changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/stddef.h b/include/linux/stddef.h
index 929d67710cc5..dab49e2ec8c0 100644
--- a/include/linux/stddef.h
+++ b/include/linux/stddef.h
@@ -93,4 +93,24 @@ enum {
 #define DECLARE_FLEX_ARRAY(TYPE, NAME) \
 	__DECLARE_FLEX_ARRAY(TYPE, NAME)
 
+/**
+ * TRAILING_OVERLAP() - Overlap a flexible-array member with trailing members.
+ *
+ * Creates a union between a flexible-array member (FAM) in a struct and a set
+ * of additional members that would otherwise follow it.
+ *
+ * @TYPE: Flexible structure type name, including "struct" keyword.
+ * @NAME: Name for a variable to define.
+ * @FAM: The flexible-array member within @TYPE
+ * @MEMBERS: Trailing overlapping members.
+ */
+#define TRAILING_OVERLAP(TYPE, NAME, FAM, MEMBERS)				\
+	union {									\
+		TYPE NAME;							\
+		struct {							\
+			unsigned char __offset_to_##FAM[offsetof(TYPE, FAM)];	\
+			MEMBERS							\
+		};								\
+	}
+
 #endif
-- 
cgit v1.2.3


From fa2f0454174c2f33005f5a6e6f70c7160a15b2a1 Mon Sep 17 00:00:00 2001
From: "Kory Maincent (Dent Project)" <kory.maincent@bootlin.com>
Date: Tue, 17 Jun 2025 14:12:00 +0200
Subject: net: pse-pd: Introduce attached_phydev to pse control

In preparation for reporting PSE events via ethtool notifications,
introduce an attached_phydev field in the pse_control structure.
This field stores the phy_device associated with the PSE PI,
ensuring that notifications are sent to the correct network
interface.

The attached_phydev pointer is directly tied to the PHY lifecycle. It
is set when the PHY is registered and cleared when the PHY is removed.
There is no need to use a refcount, as doing so could interfere with
the PHY removal process.

Signed-off-by: Kory Maincent (Dent Project) <kory.maincent@bootlin.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250617-feature_poe_port_prio-v14-1-78a1a645e2ee@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/mdio/fwnode_mdio.c | 26 ++++++++++++++------------
 drivers/net/pse-pd/pse_core.c  | 11 ++++++++---
 include/linux/pse-pd/pse.h     |  6 ++++--
 3 files changed, 26 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/mdio/fwnode_mdio.c b/drivers/net/mdio/fwnode_mdio.c
index aea0f0357568..9b41d4697a40 100644
--- a/drivers/net/mdio/fwnode_mdio.c
+++ b/drivers/net/mdio/fwnode_mdio.c
@@ -18,7 +18,8 @@ MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("FWNODE MDIO bus (Ethernet PHY) accessors");
 
 static struct pse_control *
-fwnode_find_pse_control(struct fwnode_handle *fwnode)
+fwnode_find_pse_control(struct fwnode_handle *fwnode,
+			struct phy_device *phydev)
 {
 	struct pse_control *psec;
 	struct device_node *np;
@@ -30,7 +31,7 @@ fwnode_find_pse_control(struct fwnode_handle *fwnode)
 	if (!np)
 		return NULL;
 
-	psec = of_pse_control_get(np);
+	psec = of_pse_control_get(np, phydev);
 	if (PTR_ERR(psec) == -ENOENT)
 		return NULL;
 
@@ -128,15 +129,9 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus,
 	u32 phy_id;
 	int rc;
 
-	psec = fwnode_find_pse_control(child);
-	if (IS_ERR(psec))
-		return PTR_ERR(psec);
-
 	mii_ts = fwnode_find_mii_timestamper(child);
-	if (IS_ERR(mii_ts)) {
-		rc = PTR_ERR(mii_ts);
-		goto clean_pse;
-	}
+	if (IS_ERR(mii_ts))
+		return PTR_ERR(mii_ts);
 
 	is_c45 = fwnode_device_is_compatible(child, "ethernet-phy-ieee802.3-c45");
 	if (is_c45 || fwnode_get_phy_id(child, &phy_id))
@@ -169,6 +164,12 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus,
 			goto clean_phy;
 	}
 
+	psec = fwnode_find_pse_control(child, phy);
+	if (IS_ERR(psec)) {
+		rc = PTR_ERR(psec);
+		goto unregister_phy;
+	}
+
 	phy->psec = psec;
 
 	/* phy->mii_ts may already be defined by the PHY driver. A
@@ -180,12 +181,13 @@ int fwnode_mdiobus_register_phy(struct mii_bus *bus,
 
 	return 0;
 
+unregister_phy:
+	if (is_acpi_node(child) || is_of_node(child))
+		phy_device_remove(phy);
 clean_phy:
 	phy_device_free(phy);
 clean_mii_ts:
 	unregister_mii_timestamper(mii_ts);
-clean_pse:
-	pse_control_put(psec);
 
 	return rc;
 }
diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
index 4602e26eb8c8..4610c1f0ddd6 100644
--- a/drivers/net/pse-pd/pse_core.c
+++ b/drivers/net/pse-pd/pse_core.c
@@ -23,6 +23,7 @@ static LIST_HEAD(pse_controller_list);
  * @list: list entry for the pcdev's PSE controller list
  * @id: ID of the PSE line in the PSE controller device
  * @refcnt: Number of gets of this pse_control
+ * @attached_phydev: PHY device pointer attached by the PSE control
  */
 struct pse_control {
 	struct pse_controller_dev *pcdev;
@@ -30,6 +31,7 @@ struct pse_control {
 	struct list_head list;
 	unsigned int id;
 	struct kref refcnt;
+	struct phy_device *attached_phydev;
 };
 
 static int of_load_single_pse_pi_pairset(struct device_node *node,
@@ -599,7 +601,8 @@ void pse_control_put(struct pse_control *psec)
 EXPORT_SYMBOL_GPL(pse_control_put);
 
 static struct pse_control *
-pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index)
+pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index,
+			 struct phy_device *phydev)
 {
 	struct pse_control *psec;
 	int ret;
@@ -638,6 +641,7 @@ pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index)
 	psec->pcdev = pcdev;
 	list_add(&psec->list, &pcdev->pse_control_head);
 	psec->id = index;
+	psec->attached_phydev = phydev;
 	kref_init(&psec->refcnt);
 
 	return psec;
@@ -693,7 +697,8 @@ static int psec_id_xlate(struct pse_controller_dev *pcdev,
 	return pse_spec->args[0];
 }
 
-struct pse_control *of_pse_control_get(struct device_node *node)
+struct pse_control *of_pse_control_get(struct device_node *node,
+				       struct phy_device *phydev)
 {
 	struct pse_controller_dev *r, *pcdev;
 	struct of_phandle_args args;
@@ -743,7 +748,7 @@ struct pse_control *of_pse_control_get(struct device_node *node)
 	}
 
 	/* pse_list_mutex also protects the pcdev's pse_control list */
-	psec = pse_control_get_internal(pcdev, psec_id);
+	psec = pse_control_get_internal(pcdev, psec_id, phydev);
 
 out:
 	mutex_unlock(&pse_list_mutex);
diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h
index c773eeb92d04..8b0866fad2ad 100644
--- a/include/linux/pse-pd/pse.h
+++ b/include/linux/pse-pd/pse.h
@@ -250,7 +250,8 @@ struct device;
 int devm_pse_controller_register(struct device *dev,
 				 struct pse_controller_dev *pcdev);
 
-struct pse_control *of_pse_control_get(struct device_node *node);
+struct pse_control *of_pse_control_get(struct device_node *node,
+				       struct phy_device *phydev);
 void pse_control_put(struct pse_control *psec);
 
 int pse_ethtool_get_status(struct pse_control *psec,
@@ -268,7 +269,8 @@ bool pse_has_c33(struct pse_control *psec);
 
 #else
 
-static inline struct pse_control *of_pse_control_get(struct device_node *node)
+static inline struct pse_control *of_pse_control_get(struct device_node *node,
+						     struct phy_device *phydev)
 {
 	return ERR_PTR(-ENOENT);
 }
-- 
cgit v1.2.3


From fc0e6db30941a66e284b8516b82356f97f31061d Mon Sep 17 00:00:00 2001
From: "Kory Maincent (Dent Project)" <kory.maincent@bootlin.com>
Date: Tue, 17 Jun 2025 14:12:01 +0200
Subject: net: pse-pd: Add support for reporting events

Add support for devm_pse_irq_helper() to register PSE interrupts and report
events such as over-current or over-temperature conditions. This follows a
similar approach to the regulator API but also sends notifications using a
dedicated PSE ethtool netlink socket.

Signed-off-by: Kory Maincent (Dent Project) <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20250617-feature_poe_port_prio-v14-2-78a1a645e2ee@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml       |  34 +++++
 Documentation/networking/ethtool-netlink.rst   |  19 +++
 drivers/net/pse-pd/pse_core.c                  | 179 +++++++++++++++++++++++++
 include/linux/ethtool_netlink.h                |   7 +
 include/linux/pse-pd/pse.h                     |  20 +++
 include/uapi/linux/ethtool_netlink_generated.h |  19 +++
 net/ethtool/pse-pd.c                           |  39 ++++++
 7 files changed, 317 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index ed9bcdec01cc..92b34a19f308 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -118,6 +118,17 @@ definitions:
         doc: |
           Hardware timestamp comes from one PHY device
           of the network topology
+  -
+    name: pse-event
+    doc: PSE event list for the PSE controller
+    type: flags
+    entries:
+      -
+        name: over-current
+        doc: PSE output current is too high
+      -
+        name: over-temp
+        doc: PSE in over temperature state
 
 attribute-sets:
   -
@@ -1555,6 +1566,19 @@ attribute-sets:
         name: hwtstamp-flags
         type: nest
         nested-attributes: bitset
+  -
+    name: pse-ntf
+    attr-cnt-name: --ethtool-a-pse-ntf-cnt
+    attributes:
+      -
+        name: header
+        type: nest
+        nested-attributes: header
+      -
+        name: events
+        type: uint
+        enum: pse-event
+        doc: List of events reported by the PSE controller
 
 operations:
   enum-model: directional
@@ -2413,3 +2437,13 @@ operations:
           attributes: *tsconfig
         reply:
           attributes: *tsconfig
+    -
+      name: pse-ntf
+      doc: Notification for PSE events.
+
+      attribute-set: pse-ntf
+
+      event:
+        attributes:
+          - header
+          - events
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index b6e9af4d0f1b..433737865bc2 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -290,6 +290,7 @@ Kernel to userspace:
   ``ETHTOOL_MSG_PHY_NTF``                  Ethernet PHY information change
   ``ETHTOOL_MSG_TSCONFIG_GET_REPLY``       hw timestamping configuration
   ``ETHTOOL_MSG_TSCONFIG_SET_REPLY``       new hw timestamping configuration
+  ``ETHTOOL_MSG_PSE_NTF``                  PSE events notification
   ======================================== =================================
 
 ``GET`` requests are sent by userspace applications to retrieve device
@@ -1896,6 +1897,24 @@ various existing products that document power consumption in watts rather than
 classes. If power limit configuration based on classes is needed, the
 conversion can be done in user space, for example by ethtool.
 
+PSE_NTF
+=======
+
+Notify PSE events.
+
+Notification contents:
+
+  ===============================  ======  ========================
+  ``ETHTOOL_A_PSE_HEADER``         nested  request header
+  ``ETHTOOL_A_PSE_EVENTS``         bitset  PSE events
+  ===============================  ======  ========================
+
+When set, the optional ``ETHTOOL_A_PSE_EVENTS`` attribute identifies the
+PSE events.
+
+.. kernel-doc:: include/uapi/linux/ethtool_netlink_generated.h
+    :identifiers: ethtool_pse_event
+
 RSS_GET
 =======
 
diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
index 4610c1f0ddd6..16cc1dc07246 100644
--- a/drivers/net/pse-pd/pse_core.c
+++ b/drivers/net/pse-pd/pse_core.c
@@ -7,10 +7,14 @@
 
 #include <linux/device.h>
 #include <linux/ethtool.h>
+#include <linux/ethtool_netlink.h>
 #include <linux/of.h>
+#include <linux/phy.h>
 #include <linux/pse-pd/pse.h>
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
+#include <linux/rtnetlink.h>
+#include <net/net_trackers.h>
 
 static DEFINE_MUTEX(pse_list_mutex);
 static LIST_HEAD(pse_controller_list);
@@ -210,6 +214,48 @@ out:
 	return ret;
 }
 
+/**
+ * pse_control_find_net_by_id - Find net attached to the pse control id
+ * @pcdev: a pointer to the PSE
+ * @id: index of the PSE control
+ *
+ * Return: pse_control pointer or NULL. The device returned has had a
+ *	   reference added and the pointer is safe until the user calls
+ *	   pse_control_put() to indicate they have finished with it.
+ */
+static struct pse_control *
+pse_control_find_by_id(struct pse_controller_dev *pcdev, int id)
+{
+	struct pse_control *psec;
+
+	mutex_lock(&pse_list_mutex);
+	list_for_each_entry(psec, &pcdev->pse_control_head, list) {
+		if (psec->id == id) {
+			kref_get(&psec->refcnt);
+			mutex_unlock(&pse_list_mutex);
+			return psec;
+		}
+	}
+	mutex_unlock(&pse_list_mutex);
+	return NULL;
+}
+
+/**
+ * pse_control_get_netdev - Return netdev associated to a PSE control
+ * @psec: PSE control pointer
+ *
+ * Return: netdev pointer or NULL
+ */
+static struct net_device *pse_control_get_netdev(struct pse_control *psec)
+{
+	ASSERT_RTNL();
+
+	if (!psec || !psec->attached_phydev)
+		return NULL;
+
+	return psec->attached_phydev->attached_dev;
+}
+
 static int pse_pi_is_enabled(struct regulator_dev *rdev)
 {
 	struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev);
@@ -559,6 +605,139 @@ int devm_pse_controller_register(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_pse_controller_register);
 
+struct pse_irq {
+	struct pse_controller_dev *pcdev;
+	struct pse_irq_desc desc;
+	unsigned long *notifs;
+};
+
+/**
+ * pse_to_regulator_notifs - Convert PSE notifications to Regulator
+ *			     notifications
+ * @notifs: PSE notifications
+ *
+ * Return: Regulator notifications
+ */
+static unsigned long pse_to_regulator_notifs(unsigned long notifs)
+{
+	unsigned long rnotifs = 0;
+
+	if (notifs & ETHTOOL_PSE_EVENT_OVER_CURRENT)
+		rnotifs |= REGULATOR_EVENT_OVER_CURRENT;
+	if (notifs & ETHTOOL_PSE_EVENT_OVER_TEMP)
+		rnotifs |= REGULATOR_EVENT_OVER_TEMP;
+
+	return rnotifs;
+}
+
+/**
+ * pse_isr - IRQ handler for PSE
+ * @irq: irq number
+ * @data: pointer to user interrupt structure
+ *
+ * Return: irqreturn_t - status of IRQ
+ */
+static irqreturn_t pse_isr(int irq, void *data)
+{
+	struct pse_controller_dev *pcdev;
+	unsigned long notifs_mask = 0;
+	struct pse_irq_desc *desc;
+	struct pse_irq *h = data;
+	int ret, i;
+
+	desc = &h->desc;
+	pcdev = h->pcdev;
+
+	/* Clear notifs mask */
+	memset(h->notifs, 0, pcdev->nr_lines * sizeof(*h->notifs));
+	mutex_lock(&pcdev->lock);
+	ret = desc->map_event(irq, pcdev, h->notifs, &notifs_mask);
+	mutex_unlock(&pcdev->lock);
+	if (ret || !notifs_mask)
+		return IRQ_NONE;
+
+	for_each_set_bit(i, &notifs_mask, pcdev->nr_lines) {
+		unsigned long notifs, rnotifs;
+		struct net_device *netdev;
+		struct pse_control *psec;
+
+		/* Do nothing PI not described */
+		if (!pcdev->pi[i].rdev)
+			continue;
+
+		notifs = h->notifs[i];
+		dev_dbg(h->pcdev->dev,
+			"Sending PSE notification EVT 0x%lx\n", notifs);
+
+		psec = pse_control_find_by_id(pcdev, i);
+		rtnl_lock();
+		netdev = pse_control_get_netdev(psec);
+		if (netdev)
+			ethnl_pse_send_ntf(netdev, notifs);
+		rtnl_unlock();
+		pse_control_put(psec);
+
+		rnotifs = pse_to_regulator_notifs(notifs);
+		regulator_notifier_call_chain(pcdev->pi[i].rdev, rnotifs,
+					      NULL);
+	}
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * devm_pse_irq_helper - Register IRQ based PSE event notifier
+ * @pcdev: a pointer to the PSE
+ * @irq: the irq value to be passed to request_irq
+ * @irq_flags: the flags to be passed to request_irq
+ * @d: PSE interrupt description
+ *
+ * Return: 0 on success and errno on failure
+ */
+int devm_pse_irq_helper(struct pse_controller_dev *pcdev, int irq,
+			int irq_flags, const struct pse_irq_desc *d)
+{
+	struct device *dev = pcdev->dev;
+	size_t irq_name_len;
+	struct pse_irq *h;
+	char *irq_name;
+	int ret;
+
+	if (!d || !d->map_event || !d->name)
+		return -EINVAL;
+
+	h = devm_kzalloc(dev, sizeof(*h), GFP_KERNEL);
+	if (!h)
+		return -ENOMEM;
+
+	h->pcdev = pcdev;
+	h->desc = *d;
+
+	/* IRQ name len is pcdev dev name + 5 char + irq desc name + 1 */
+	irq_name_len = strlen(dev_name(pcdev->dev)) + 5 + strlen(d->name) + 1;
+	irq_name = devm_kzalloc(dev, irq_name_len, GFP_KERNEL);
+	if (!irq_name)
+		return -ENOMEM;
+
+	snprintf(irq_name, irq_name_len, "pse-%s:%s", dev_name(pcdev->dev),
+		 d->name);
+
+	h->notifs = devm_kcalloc(dev, pcdev->nr_lines,
+				 sizeof(*h->notifs), GFP_KERNEL);
+	if (!h->notifs)
+		return -ENOMEM;
+
+	ret = devm_request_threaded_irq(dev, irq, NULL, pse_isr,
+					IRQF_ONESHOT | irq_flags,
+					irq_name, h);
+	if (ret)
+		dev_err(pcdev->dev, "Failed to request IRQ %d\n", irq);
+
+	pcdev->irq = irq;
+	return ret;
+}
+EXPORT_SYMBOL_GPL(devm_pse_irq_helper);
+
 /* PSE control section */
 
 static void __pse_control_release(struct kref *kref)
diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h
index aba91335273a..1dcc4059b5ab 100644
--- a/include/linux/ethtool_netlink.h
+++ b/include/linux/ethtool_netlink.h
@@ -43,6 +43,8 @@ void ethtool_aggregate_rmon_stats(struct net_device *dev,
 				  struct ethtool_rmon_stats *rmon_stats);
 bool ethtool_dev_mm_supported(struct net_device *dev);
 
+void ethnl_pse_send_ntf(struct net_device *netdev, unsigned long notif);
+
 #else
 static inline int ethnl_cable_test_alloc(struct phy_device *phydev, u8 cmd)
 {
@@ -120,6 +122,11 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev)
 	return false;
 }
 
+static inline void ethnl_pse_send_ntf(struct phy_device *phydev,
+				      unsigned long notif)
+{
+}
+
 #endif /* IS_ENABLED(CONFIG_ETHTOOL_NETLINK) */
 
 static inline int ethnl_cable_test_result(struct phy_device *phydev, u8 pair,
diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h
index 8b0866fad2ad..6eb064722aa8 100644
--- a/include/linux/pse-pd/pse.h
+++ b/include/linux/pse-pd/pse.h
@@ -7,12 +7,15 @@
 
 #include <linux/list.h>
 #include <uapi/linux/ethtool.h>
+#include <uapi/linux/ethtool_netlink_generated.h>
+#include <linux/regulator/driver.h>
 
 /* Maximum current in uA according to IEEE 802.3-2022 Table 145-1 */
 #define MAX_PI_CURRENT 1920000
 /* Maximum power in mW according to IEEE 802.3-2022 Table 145-16 */
 #define MAX_PI_PW 99900
 
+struct net_device;
 struct phy_device;
 struct pse_controller_dev;
 struct netlink_ext_ack;
@@ -37,6 +40,19 @@ struct ethtool_c33_pse_pw_limit_range {
 	u32 max;
 };
 
+/**
+ * struct pse_irq_desc - notification sender description for IRQ based events.
+ *
+ * @name: the visible name for the IRQ
+ * @map_event: driver callback to map IRQ status into PSE devices with events.
+ */
+struct pse_irq_desc {
+	const char *name;
+	int (*map_event)(int irq, struct pse_controller_dev *pcdev,
+			 unsigned long *notifs,
+			 unsigned long *notifs_mask);
+};
+
 /**
  * struct pse_control_config - PSE control/channel configuration.
  *
@@ -228,6 +244,7 @@ struct pse_pi {
  * @types: types of the PSE controller
  * @pi: table of PSE PIs described in this controller device
  * @no_of_pse_pi: flag set if the pse_pis devicetree node is not used
+ * @irq: PSE interrupt
  */
 struct pse_controller_dev {
 	const struct pse_controller_ops *ops;
@@ -241,6 +258,7 @@ struct pse_controller_dev {
 	enum ethtool_pse_types types;
 	struct pse_pi *pi;
 	bool no_of_pse_pi;
+	int irq;
 };
 
 #if IS_ENABLED(CONFIG_PSE_CONTROLLER)
@@ -249,6 +267,8 @@ void pse_controller_unregister(struct pse_controller_dev *pcdev);
 struct device;
 int devm_pse_controller_register(struct device *dev,
 				 struct pse_controller_dev *pcdev);
+int devm_pse_irq_helper(struct pse_controller_dev *pcdev, int irq,
+			int irq_flags, const struct pse_irq_desc *d);
 
 struct pse_control *of_pse_control_get(struct device_node *node,
 				       struct phy_device *phydev);
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index 9a02f579de22..3864aa0de8c7 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -49,6 +49,16 @@ enum hwtstamp_source {
 	HWTSTAMP_SOURCE_PHYLIB,
 };
 
+/**
+ * enum ethtool_pse_event - PSE event list for the PSE controller
+ * @ETHTOOL_PSE_EVENT_OVER_CURRENT: PSE output current is too high
+ * @ETHTOOL_PSE_EVENT_OVER_TEMP: PSE in over temperature state
+ */
+enum ethtool_pse_event {
+	ETHTOOL_PSE_EVENT_OVER_CURRENT = 1,
+	ETHTOOL_PSE_EVENT_OVER_TEMP = 2,
+};
+
 enum {
 	ETHTOOL_A_HEADER_UNSPEC,
 	ETHTOOL_A_HEADER_DEV_INDEX,
@@ -718,6 +728,14 @@ enum {
 	ETHTOOL_A_TSCONFIG_MAX = (__ETHTOOL_A_TSCONFIG_CNT - 1)
 };
 
+enum {
+	ETHTOOL_A_PSE_NTF_HEADER = 1,
+	ETHTOOL_A_PSE_NTF_EVENTS,
+
+	__ETHTOOL_A_PSE_NTF_CNT,
+	ETHTOOL_A_PSE_NTF_MAX = (__ETHTOOL_A_PSE_NTF_CNT - 1)
+};
+
 enum {
 	ETHTOOL_MSG_USER_NONE = 0,
 	ETHTOOL_MSG_STRSET_GET = 1,
@@ -822,6 +840,7 @@ enum {
 	ETHTOOL_MSG_PHY_NTF,
 	ETHTOOL_MSG_TSCONFIG_GET_REPLY,
 	ETHTOOL_MSG_TSCONFIG_SET_REPLY,
+	ETHTOOL_MSG_PSE_NTF,
 
 	__ETHTOOL_MSG_KERNEL_CNT,
 	ETHTOOL_MSG_KERNEL_MAX = (__ETHTOOL_MSG_KERNEL_CNT - 1)
diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 4f6b99eab2a6..5443b4e0065a 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -315,3 +315,42 @@ const struct ethnl_request_ops ethnl_pse_request_ops = {
 	.set			= ethnl_set_pse,
 	/* PSE has no notification */
 };
+
+void ethnl_pse_send_ntf(struct net_device *netdev, unsigned long notifs)
+{
+	void *reply_payload;
+	struct sk_buff *skb;
+	int reply_len;
+	int ret;
+
+	ASSERT_RTNL();
+
+	if (!netdev || !notifs)
+		return;
+
+	reply_len = ethnl_reply_header_size() +
+		    nla_total_size(sizeof(u32)); /* _PSE_NTF_EVENTS */
+
+	skb = genlmsg_new(reply_len, GFP_KERNEL);
+	if (!skb)
+		return;
+
+	reply_payload = ethnl_bcastmsg_put(skb, ETHTOOL_MSG_PSE_NTF);
+	if (!reply_payload)
+		goto err_skb;
+
+	ret = ethnl_fill_reply_header(skb, netdev, ETHTOOL_A_PSE_NTF_HEADER);
+	if (ret < 0)
+		goto err_skb;
+
+	if (nla_put_uint(skb, ETHTOOL_A_PSE_NTF_EVENTS, notifs))
+		goto err_skb;
+
+	genlmsg_end(skb, reply_payload);
+	ethnl_multicast(skb, netdev);
+	return;
+
+err_skb:
+	nlmsg_free(skb);
+}
+EXPORT_SYMBOL_GPL(ethnl_pse_send_ntf);
-- 
cgit v1.2.3


From 50f8b341d26826aa5fdccb8f497fbff2500934b3 Mon Sep 17 00:00:00 2001
From: "Kory Maincent (Dent Project)" <kory.maincent@bootlin.com>
Date: Tue, 17 Jun 2025 14:12:03 +0200
Subject: net: pse-pd: Add support for PSE power domains

Introduce PSE power domain support as groundwork for upcoming port
priority features. Multiple PSE PIs can now be grouped under a single
PSE power domain, enabling future enhancements like defining available
power budgets, port priority modes, and disconnection policies. This
setup will allow the system to assess whether activating a port would
exceed the available power budget, preventing over-budget states
proactively.

Signed-off-by: Kory Maincent (Dent Project) <kory.maincent@bootlin.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250617-feature_poe_port_prio-v14-4-78a1a645e2ee@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/pse-pd/pse_core.c | 140 ++++++++++++++++++++++++++++++++++++++++++
 include/linux/pse-pd/pse.h    |   2 +
 2 files changed, 142 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
index 16cc1dc07246..f2fb7ccbc4c2 100644
--- a/drivers/net/pse-pd/pse_core.c
+++ b/drivers/net/pse-pd/pse_core.c
@@ -16,8 +16,12 @@
 #include <linux/rtnetlink.h>
 #include <net/net_trackers.h>
 
+#define PSE_PW_D_LIMIT INT_MAX
+
 static DEFINE_MUTEX(pse_list_mutex);
 static LIST_HEAD(pse_controller_list);
+static DEFINE_XARRAY_ALLOC(pse_pw_d_map);
+static DEFINE_MUTEX(pse_pw_d_mutex);
 
 /**
  * struct pse_control - a PSE control
@@ -38,6 +42,18 @@ struct pse_control {
 	struct phy_device *attached_phydev;
 };
 
+/**
+ * struct pse_power_domain - a PSE power domain
+ * @id: ID of the power domain
+ * @supply: Power supply the Power Domain
+ * @refcnt: Number of gets of this pse_power_domain
+ */
+struct pse_power_domain {
+	int id;
+	struct regulator *supply;
+	struct kref refcnt;
+};
+
 static int of_load_single_pse_pi_pairset(struct device_node *node,
 					 struct pse_pi *pi,
 					 int pairset_num)
@@ -485,6 +501,125 @@ devm_pse_pi_regulator_register(struct pse_controller_dev *pcdev,
 	return 0;
 }
 
+static void __pse_pw_d_release(struct kref *kref)
+{
+	struct pse_power_domain *pw_d = container_of(kref,
+						     struct pse_power_domain,
+						     refcnt);
+
+	regulator_put(pw_d->supply);
+	xa_erase(&pse_pw_d_map, pw_d->id);
+	mutex_unlock(&pse_pw_d_mutex);
+}
+
+/**
+ * pse_flush_pw_ds - flush all PSE power domains of a PSE
+ * @pcdev: a pointer to the initialized PSE controller device
+ */
+static void pse_flush_pw_ds(struct pse_controller_dev *pcdev)
+{
+	struct pse_power_domain *pw_d;
+	int i;
+
+	for (i = 0; i < pcdev->nr_lines; i++) {
+		if (!pcdev->pi[i].pw_d)
+			continue;
+
+		pw_d = xa_load(&pse_pw_d_map, pcdev->pi[i].pw_d->id);
+		if (!pw_d)
+			continue;
+
+		kref_put_mutex(&pw_d->refcnt, __pse_pw_d_release,
+			       &pse_pw_d_mutex);
+	}
+}
+
+/**
+ * devm_pse_alloc_pw_d - allocate a new PSE power domain for a device
+ * @dev: device that is registering this PSE power domain
+ *
+ * Return: Pointer to the newly allocated PSE power domain or error pointers
+ */
+static struct pse_power_domain *devm_pse_alloc_pw_d(struct device *dev)
+{
+	struct pse_power_domain *pw_d;
+	int index, ret;
+
+	pw_d = devm_kzalloc(dev, sizeof(*pw_d), GFP_KERNEL);
+	if (!pw_d)
+		return ERR_PTR(-ENOMEM);
+
+	ret = xa_alloc(&pse_pw_d_map, &index, pw_d, XA_LIMIT(1, PSE_PW_D_LIMIT),
+		       GFP_KERNEL);
+	if (ret)
+		return ERR_PTR(ret);
+
+	kref_init(&pw_d->refcnt);
+	pw_d->id = index;
+	return pw_d;
+}
+
+/**
+ * pse_register_pw_ds - register the PSE power domains for a PSE
+ * @pcdev: a pointer to the PSE controller device
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int pse_register_pw_ds(struct pse_controller_dev *pcdev)
+{
+	int i, ret = 0;
+
+	mutex_lock(&pse_pw_d_mutex);
+	for (i = 0; i < pcdev->nr_lines; i++) {
+		struct regulator_dev *rdev = pcdev->pi[i].rdev;
+		struct pse_power_domain *pw_d;
+		struct regulator *supply;
+		bool present = false;
+		unsigned long index;
+
+		/* No regulator or regulator parent supply registered.
+		 * We need a regulator parent to register a PSE power domain
+		 */
+		if (!rdev || !rdev->supply)
+			continue;
+
+		xa_for_each(&pse_pw_d_map, index, pw_d) {
+			/* Power supply already registered as a PSE power
+			 * domain.
+			 */
+			if (regulator_is_equal(pw_d->supply, rdev->supply)) {
+				present = true;
+				pcdev->pi[i].pw_d = pw_d;
+				break;
+			}
+		}
+		if (present) {
+			kref_get(&pw_d->refcnt);
+			continue;
+		}
+
+		pw_d = devm_pse_alloc_pw_d(pcdev->dev);
+		if (IS_ERR(pw_d)) {
+			ret = PTR_ERR(pw_d);
+			goto out;
+		}
+
+		supply = regulator_get(&rdev->dev, rdev->supply_name);
+		if (IS_ERR(supply)) {
+			xa_erase(&pse_pw_d_map, pw_d->id);
+			ret = PTR_ERR(supply);
+			goto out;
+		}
+
+		pw_d->supply = supply;
+		pcdev->pi[i].pw_d = pw_d;
+	}
+
+out:
+	mutex_unlock(&pse_pw_d_mutex);
+	return ret;
+}
+
 /**
  * pse_controller_register - register a PSE controller device
  * @pcdev: a pointer to the initialized PSE controller device
@@ -544,6 +679,10 @@ int pse_controller_register(struct pse_controller_dev *pcdev)
 			return ret;
 	}
 
+	ret = pse_register_pw_ds(pcdev);
+	if (ret)
+		return ret;
+
 	mutex_lock(&pse_list_mutex);
 	list_add(&pcdev->list, &pse_controller_list);
 	mutex_unlock(&pse_list_mutex);
@@ -558,6 +697,7 @@ EXPORT_SYMBOL_GPL(pse_controller_register);
  */
 void pse_controller_unregister(struct pse_controller_dev *pcdev)
 {
+	pse_flush_pw_ds(pcdev);
 	pse_release_pis(pcdev);
 	mutex_lock(&pse_list_mutex);
 	list_del(&pcdev->list);
diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h
index 6eb064722aa8..f736b1677ea5 100644
--- a/include/linux/pse-pd/pse.h
+++ b/include/linux/pse-pd/pse.h
@@ -222,12 +222,14 @@ struct pse_pi_pairset {
  * @np: device node pointer of the PSE PI node
  * @rdev: regulator represented by the PSE PI
  * @admin_state_enabled: PI enabled state
+ * @pw_d: Power domain of the PSE PI
  */
 struct pse_pi {
 	struct pse_pi_pairset pairset[2];
 	struct device_node *np;
 	struct regulator_dev *rdev;
 	bool admin_state_enabled;
+	struct pse_power_domain *pw_d;
 };
 
 /**
-- 
cgit v1.2.3


From 1176978ed851952652ddea3685e2f71a0e5d61ff Mon Sep 17 00:00:00 2001
From: "Kory Maincent (Dent Project)" <kory.maincent@bootlin.com>
Date: Tue, 17 Jun 2025 14:12:04 +0200
Subject: net: ethtool: Add support for new power domains index description

Report the index of the newly introduced PSE power domain to the user,
enabling improved management of the power budget for PSE devices.

Signed-off-by: Kory Maincent (Dent Project) <kory.maincent@bootlin.com>
Reviewed-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250617-feature_poe_port_prio-v14-5-78a1a645e2ee@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml       | 5 +++++
 Documentation/networking/ethtool-netlink.rst   | 4 ++++
 drivers/net/pse-pd/pse_core.c                  | 3 +++
 include/linux/pse-pd/pse.h                     | 2 ++
 include/uapi/linux/ethtool_netlink_generated.h | 1 +
 net/ethtool/pse-pd.c                           | 7 +++++++
 6 files changed, 22 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index 92b34a19f308..dfd9b842a4e7 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -1406,6 +1406,10 @@ attribute-sets:
         type: nest
         multi-attr: true
         nested-attributes: c33-pse-pw-limit
+      -
+        name: pse-pw-d-id
+        type: u32
+        name-prefix: ethtool-a-
   -
     name: rss
     attr-cnt-name: __ethtool-a-rss-cnt
@@ -2229,6 +2233,7 @@ operations:
             - c33-pse-ext-substate
             - c33-pse-avail-pw-limit
             - c33-pse-pw-limit-ranges
+            - pse-pw-d-id
       dump: *pse-get-op
     -
       name: pse-set
diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
index 433737865bc2..e9af8e58564c 100644
--- a/Documentation/networking/ethtool-netlink.rst
+++ b/Documentation/networking/ethtool-netlink.rst
@@ -1789,6 +1789,7 @@ Kernel response contents:
                                                       limit of the PoE PSE.
   ``ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES``       nested  Supported power limit
                                                       configuration ranges.
+  ``ETHTOOL_A_PSE_PW_D_ID``                      u32  Index of the PSE power domain
   ==========================================  ======  =============================
 
 When set, the optional ``ETHTOOL_A_PODL_PSE_ADMIN_STATE`` attribute identifies
@@ -1862,6 +1863,9 @@ identifies the C33 PSE power limit ranges through
 If the controller works with fixed classes, the min and max values will be
 equal.
 
+The ``ETHTOOL_A_PSE_PW_D_ID`` attribute identifies the index of PSE power
+domain.
+
 PSE_SET
 =======
 
diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
index f2fb7ccbc4c2..7d424c22225e 100644
--- a/drivers/net/pse-pd/pse_core.c
+++ b/drivers/net/pse-pd/pse_core.c
@@ -1098,6 +1098,9 @@ int pse_ethtool_get_status(struct pse_control *psec,
 	pcdev = psec->pcdev;
 	ops = pcdev->ops;
 	mutex_lock(&pcdev->lock);
+	if (pcdev->pi[psec->id].pw_d)
+		status->pw_d_id = pcdev->pi[psec->id].pw_d->id;
+
 	ret = ops->pi_get_admin_state(pcdev, psec->id, &admin_state);
 	if (ret)
 		goto out;
diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h
index f736b1677ea5..2f8ecfd87d43 100644
--- a/include/linux/pse-pd/pse.h
+++ b/include/linux/pse-pd/pse.h
@@ -114,6 +114,7 @@ struct pse_pw_limit_ranges {
 /**
  * struct ethtool_pse_control_status - PSE control/channel status.
  *
+ * @pw_d_id: PSE power domain index.
  * @podl_admin_state: operational state of the PoDL PSE
  *	functions. IEEE 802.3-2018 30.15.1.1.2 aPoDLPSEAdminState
  * @podl_pw_status: power detection status of the PoDL PSE.
@@ -135,6 +136,7 @@ struct pse_pw_limit_ranges {
  *	ranges
  */
 struct ethtool_pse_control_status {
+	u32 pw_d_id;
 	enum ethtool_podl_pse_admin_state podl_admin_state;
 	enum ethtool_podl_pse_pw_d_status podl_pw_status;
 	enum ethtool_c33_pse_admin_state c33_admin_state;
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index 3864aa0de8c7..ed344c8533eb 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -652,6 +652,7 @@ enum {
 	ETHTOOL_A_C33_PSE_EXT_SUBSTATE,
 	ETHTOOL_A_C33_PSE_AVAIL_PW_LIMIT,
 	ETHTOOL_A_C33_PSE_PW_LIMIT_RANGES,
+	ETHTOOL_A_PSE_PW_D_ID,
 
 	__ETHTOOL_A_PSE_CNT,
 	ETHTOOL_A_PSE_MAX = (__ETHTOOL_A_PSE_CNT - 1)
diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
index 5443b4e0065a..6a978a55959e 100644
--- a/net/ethtool/pse-pd.c
+++ b/net/ethtool/pse-pd.c
@@ -83,6 +83,8 @@ static int pse_reply_size(const struct ethnl_req_info *req_base,
 	const struct ethtool_pse_control_status *st = &data->status;
 	int len = 0;
 
+	if (st->pw_d_id)
+		len += nla_total_size(sizeof(u32)); /* _PSE_PW_D_ID */
 	if (st->podl_admin_state > 0)
 		len += nla_total_size(sizeof(u32)); /* _PODL_PSE_ADMIN_STATE */
 	if (st->podl_pw_status > 0)
@@ -148,6 +150,11 @@ static int pse_fill_reply(struct sk_buff *skb,
 	const struct pse_reply_data *data = PSE_REPDATA(reply_base);
 	const struct ethtool_pse_control_status *st = &data->status;
 
+	if (st->pw_d_id &&
+	    nla_put_u32(skb, ETHTOOL_A_PSE_PW_D_ID,
+			st->pw_d_id))
+		return -EMSGSIZE;
+
 	if (st->podl_admin_state > 0 &&
 	    nla_put_u32(skb, ETHTOOL_A_PODL_PSE_ADMIN_STATE,
 			st->podl_admin_state))
-- 
cgit v1.2.3


From ffef61d6d27374542f1bce4452200d9bdd2e1edd Mon Sep 17 00:00:00 2001
From: "Kory Maincent (Dent Project)" <kory.maincent@bootlin.com>
Date: Tue, 17 Jun 2025 14:12:06 +0200
Subject: net: pse-pd: Add support for budget evaluation strategies
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch introduces the ability to configure the PSE PI budget evaluation
strategies. Budget evaluation strategies is utilized by PSE controllers to
determine which ports to turn off first in scenarios such as power budget
exceedance.

The pis_prio_max value is used to define the maximum priority level
supported by the controller. Both the current priority and the maximum
priority are exposed to the user through the pse_ethtool_get_status call.

This patch add support for two mode of budget evaluation strategies.
1. Static Method:

   This method involves distributing power based on PD classification.
   It’s straightforward and stable, the PSE core keeping track of the
   budget and subtracting the power requested by each PD’s class.

   Advantages: Every PD gets its promised power at any time, which
   guarantees reliability.

   Disadvantages: PD classification steps are large, meaning devices
   request much more power than they actually need. As a result, the power
   supply may only operate at, say, 50% capacity, which is inefficient and
   wastes money.

   Priority max value is matching the number of PSE PIs within the PSE.

2. Dynamic Method:

   To address the inefficiencies of the static method, vendors like
   Microchip have introduced dynamic power budgeting, as seen in the
   PD692x0 firmware. This method monitors the current consumption per port
   and subtracts it from the available power budget. When the budget is
   exceeded, lower-priority ports are shut down.

   Advantages: This method optimizes resource utilization, saving costs.

   Disadvantages: Low-priority devices may experience instability.

   Priority max value is set by the PSE controller driver.

For now, budget evaluation methods are not configurable and cannot be
mixed. They are hardcoded in the PSE driver itself, as no current PSE
controller supports both methods.

Signed-off-by: Kory Maincent (Dent Project) <kory.maincent@bootlin.com>
Acked-by: Oleksij Rempel <o.rempel@pengutronix.de>
Link: https://patch.msgid.link/20250617-feature_poe_port_prio-v14-7-78a1a645e2ee@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/ethtool.yaml       |  30 +-
 drivers/net/pse-pd/pse_core.c                  | 731 +++++++++++++++++++++++--
 include/linux/pse-pd/pse.h                     |  76 +++
 include/uapi/linux/ethtool_netlink_generated.h |  18 +
 4 files changed, 815 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
index dfd9b842a4e7..7a9a857370e2 100644
--- a/Documentation/netlink/specs/ethtool.yaml
+++ b/Documentation/netlink/specs/ethtool.yaml
@@ -122,13 +122,39 @@ definitions:
     name: pse-event
     doc: PSE event list for the PSE controller
     type: flags
+    name-prefix: ethtool-
     entries:
       -
-        name: over-current
+        name: pse-event-over-current
         doc: PSE output current is too high
       -
-        name: over-temp
+        name: pse-event-over-temp
         doc: PSE in over temperature state
+      -
+        name: c33-pse-event-detection
+        doc: |
+          detection process occur on the PSE. IEEE 802.3-2022 33.2.5 and
+          145.2.6 PSE detection of PDs. IEEE 802.3-202 30.9.1.1.5
+          aPSEPowerDetectionStatus
+      -
+        name: c33-pse-event-classification
+        doc: |
+          classification process occur on the PSE. IEEE 802.3-2022 33.2.6
+          and 145.2.8 classification of PDs mutual identification.
+          IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification.
+      -
+        name: c33-pse-event-disconnection
+        doc: |
+          PD has been disconnected on the PSE. IEEE 802.3-2022 33.3.8
+          and 145.3.9 PD Maintain Power Signature. IEEE 802.3-2022
+          33.5.1.2.9 MPS Absent. IEEE 802.3-2022 30.9.1.1.20
+          aPSEMPSAbsentCounter.
+      -
+        name: pse-event-over-budget
+        doc: PSE turned off due to over budget situation
+      -
+        name: pse-event-sw-pw-control-error
+        doc: PSE faced an error managing the power control from software
 
 attribute-sets:
   -
diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
index 495d72f98029..23eb3c9d0bcd 100644
--- a/drivers/net/pse-pd/pse_core.c
+++ b/drivers/net/pse-pd/pse_core.c
@@ -47,11 +47,14 @@ struct pse_control {
  * @id: ID of the power domain
  * @supply: Power supply the Power Domain
  * @refcnt: Number of gets of this pse_power_domain
+ * @budget_eval_strategy: Current power budget evaluation strategy of the
+ *			  power domain
  */
 struct pse_power_domain {
 	int id;
 	struct regulator *supply;
 	struct kref refcnt;
+	u32 budget_eval_strategy;
 };
 
 static int of_load_single_pse_pi_pairset(struct device_node *node,
@@ -297,6 +300,115 @@ static int pse_pi_is_hw_enabled(struct pse_controller_dev *pcdev, int id)
 	return 0;
 }
 
+/**
+ * pse_pi_is_admin_enable_pending - Check if PI is in admin enable pending state
+ *				    which mean the power is not yet being
+ *				    delivered
+ * @pcdev: a pointer to the PSE controller device
+ * @id: Index of the PI
+ *
+ * Detects if a PI is enabled in software with a PD detected, but the hardware
+ * admin state hasn't been applied yet.
+ *
+ * This function is used in the power delivery and retry mechanisms to determine
+ * which PIs need to have power delivery attempted again.
+ *
+ * Return: true if the PI has admin enable flag set in software but not yet
+ *	   reflected in the hardware admin state, false otherwise.
+ */
+static bool
+pse_pi_is_admin_enable_pending(struct pse_controller_dev *pcdev, int id)
+{
+	int ret;
+
+	/* PI not enabled or nothing is plugged */
+	if (!pcdev->pi[id].admin_state_enabled ||
+	    !pcdev->pi[id].isr_pd_detected)
+		return false;
+
+	ret = pse_pi_is_hw_enabled(pcdev, id);
+	/* PSE PI is already enabled at hardware level */
+	if (ret == 1)
+		return false;
+
+	return true;
+}
+
+static int _pse_pi_delivery_power_sw_pw_ctrl(struct pse_controller_dev *pcdev,
+					     int id,
+					     struct netlink_ext_ack *extack);
+
+/**
+ * pse_pw_d_retry_power_delivery - Retry power delivery for pending ports in a
+ *				   PSE power domain
+ * @pcdev: a pointer to the PSE controller device
+ * @pw_d: a pointer to the PSE power domain
+ *
+ * Scans all ports in the specified power domain and attempts to enable power
+ * delivery to any ports that have admin enable state set but don't yet have
+ * hardware power enabled. Used when there are changes in connection status,
+ * admin state, or priority that might allow previously unpowered ports to
+ * receive power, especially in over-budget conditions.
+ */
+static void pse_pw_d_retry_power_delivery(struct pse_controller_dev *pcdev,
+					  struct pse_power_domain *pw_d)
+{
+	int i, ret = 0;
+
+	for (i = 0; i < pcdev->nr_lines; i++) {
+		int prio_max = pcdev->nr_lines;
+		struct netlink_ext_ack extack;
+
+		if (pcdev->pi[i].pw_d != pw_d)
+			continue;
+
+		if (!pse_pi_is_admin_enable_pending(pcdev, i))
+			continue;
+
+		/* Do not try to enable PI with a lower prio (higher value)
+		 * than one which already can't be enabled.
+		 */
+		if (pcdev->pi[i].prio > prio_max)
+			continue;
+
+		ret = _pse_pi_delivery_power_sw_pw_ctrl(pcdev, i, &extack);
+		if (ret == -ERANGE)
+			prio_max = pcdev->pi[i].prio;
+	}
+}
+
+/**
+ * pse_pw_d_is_sw_pw_control - Determine if power control is software managed
+ * @pcdev: a pointer to the PSE controller device
+ * @pw_d: a pointer to the PSE power domain
+ *
+ * This function determines whether the power control for a specific power
+ * domain is managed by software in the interrupt handler rather than directly
+ * by hardware.
+ *
+ * Software power control is active in the following cases:
+ * - When the budget evaluation strategy is set to static
+ * - When the budget evaluation strategy is disabled but the PSE controller
+ *   has an interrupt handler that can report if a Powered Device is connected
+ *
+ * Return: true if the power control of the power domain is managed by software,
+ *         false otherwise
+ */
+static bool pse_pw_d_is_sw_pw_control(struct pse_controller_dev *pcdev,
+				      struct pse_power_domain *pw_d)
+{
+	if (!pw_d)
+		return false;
+
+	if (pw_d->budget_eval_strategy == PSE_BUDGET_EVAL_STRAT_STATIC)
+		return true;
+	if (pw_d->budget_eval_strategy == PSE_BUDGET_EVAL_STRAT_DISABLED &&
+	    pcdev->ops->pi_enable && pcdev->irq)
+		return true;
+
+	return false;
+}
+
 static int pse_pi_is_enabled(struct regulator_dev *rdev)
 {
 	struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev);
@@ -309,17 +421,252 @@ static int pse_pi_is_enabled(struct regulator_dev *rdev)
 
 	id = rdev_get_id(rdev);
 	mutex_lock(&pcdev->lock);
+	if (pse_pw_d_is_sw_pw_control(pcdev, pcdev->pi[id].pw_d)) {
+		ret = pcdev->pi[id].admin_state_enabled;
+		goto out;
+	}
+
 	ret = pse_pi_is_hw_enabled(pcdev, id);
+
+out:
 	mutex_unlock(&pcdev->lock);
 
 	return ret;
 }
 
+/**
+ * pse_pi_deallocate_pw_budget - Deallocate power budget of the PI
+ * @pi: a pointer to the PSE PI
+ */
+static void pse_pi_deallocate_pw_budget(struct pse_pi *pi)
+{
+	if (!pi->pw_d || !pi->pw_allocated_mW)
+		return;
+
+	regulator_free_power_budget(pi->pw_d->supply, pi->pw_allocated_mW);
+	pi->pw_allocated_mW = 0;
+}
+
+/**
+ * _pse_pi_disable - Call disable operation. Assumes the PSE lock has been
+ *		     acquired.
+ * @pcdev: a pointer to the PSE
+ * @id: index of the PSE control
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int _pse_pi_disable(struct pse_controller_dev *pcdev, int id)
+{
+	const struct pse_controller_ops *ops = pcdev->ops;
+	int ret;
+
+	if (!ops->pi_disable)
+		return -EOPNOTSUPP;
+
+	ret = ops->pi_disable(pcdev, id);
+	if (ret)
+		return ret;
+
+	pse_pi_deallocate_pw_budget(&pcdev->pi[id]);
+
+	if (pse_pw_d_is_sw_pw_control(pcdev, pcdev->pi[id].pw_d))
+		pse_pw_d_retry_power_delivery(pcdev, pcdev->pi[id].pw_d);
+
+	return 0;
+}
+
+/**
+ * pse_disable_pi_pol - Disable a PI on a power budget policy
+ * @pcdev: a pointer to the PSE
+ * @id: index of the PSE PI
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int pse_disable_pi_pol(struct pse_controller_dev *pcdev, int id)
+{
+	unsigned long notifs = ETHTOOL_PSE_EVENT_OVER_BUDGET;
+	struct pse_ntf ntf = {};
+	int ret;
+
+	dev_dbg(pcdev->dev, "Disabling PI %d to free power budget\n", id);
+
+	ret = _pse_pi_disable(pcdev, id);
+	if (ret)
+		notifs |= ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR;
+
+	ntf.notifs = notifs;
+	ntf.id = id;
+	kfifo_in_spinlocked(&pcdev->ntf_fifo, &ntf, 1, &pcdev->ntf_fifo_lock);
+	schedule_work(&pcdev->ntf_work);
+
+	return ret;
+}
+
+/**
+ * pse_disable_pi_prio - Disable all PIs of a given priority inside a PSE
+ *			 power domain
+ * @pcdev: a pointer to the PSE
+ * @pw_d: a pointer to the PSE power domain
+ * @prio: priority
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int pse_disable_pi_prio(struct pse_controller_dev *pcdev,
+			       struct pse_power_domain *pw_d,
+			       int prio)
+{
+	int i;
+
+	for (i = 0; i < pcdev->nr_lines; i++) {
+		int ret;
+
+		if (pcdev->pi[i].prio != prio ||
+		    pcdev->pi[i].pw_d != pw_d ||
+		    pse_pi_is_hw_enabled(pcdev, i) <= 0)
+			continue;
+
+		ret = pse_disable_pi_pol(pcdev, i);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+/**
+ * pse_pi_allocate_pw_budget_static_prio - Allocate power budget for the PI
+ *					   when the budget eval strategy is
+ *					   static
+ * @pcdev: a pointer to the PSE
+ * @id: index of the PSE control
+ * @pw_req: power requested in mW
+ * @extack: extack for error reporting
+ *
+ * Allocates power using static budget evaluation strategy, where allocation
+ * is based on PD classification. When insufficient budget is available,
+ * lower-priority ports (higher priority numbers) are turned off first.
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int
+pse_pi_allocate_pw_budget_static_prio(struct pse_controller_dev *pcdev, int id,
+				      int pw_req, struct netlink_ext_ack *extack)
+{
+	struct pse_pi *pi = &pcdev->pi[id];
+	int ret, _prio;
+
+	_prio = pcdev->nr_lines;
+	while (regulator_request_power_budget(pi->pw_d->supply, pw_req) == -ERANGE) {
+		if (_prio <= pi->prio) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "PI %d: not enough power budget available",
+					   id);
+			return -ERANGE;
+		}
+
+		ret = pse_disable_pi_prio(pcdev, pi->pw_d, _prio);
+		if (ret < 0)
+			return ret;
+
+		_prio--;
+	}
+
+	pi->pw_allocated_mW = pw_req;
+	return 0;
+}
+
+/**
+ * pse_pi_allocate_pw_budget - Allocate power budget for the PI
+ * @pcdev: a pointer to the PSE
+ * @id: index of the PSE control
+ * @pw_req: power requested in mW
+ * @extack: extack for error reporting
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int pse_pi_allocate_pw_budget(struct pse_controller_dev *pcdev, int id,
+				     int pw_req, struct netlink_ext_ack *extack)
+{
+	struct pse_pi *pi = &pcdev->pi[id];
+
+	if (!pi->pw_d)
+		return 0;
+
+	/* PSE_BUDGET_EVAL_STRAT_STATIC */
+	if (pi->pw_d->budget_eval_strategy == PSE_BUDGET_EVAL_STRAT_STATIC)
+		return pse_pi_allocate_pw_budget_static_prio(pcdev, id, pw_req,
+							     extack);
+
+	return 0;
+}
+
+/**
+ * _pse_pi_delivery_power_sw_pw_ctrl - Enable PSE PI in case of software power
+ *				       control. Assumes the PSE lock has been
+ *				       acquired.
+ * @pcdev: a pointer to the PSE
+ * @id: index of the PSE control
+ * @extack: extack for error reporting
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int _pse_pi_delivery_power_sw_pw_ctrl(struct pse_controller_dev *pcdev,
+					     int id,
+					     struct netlink_ext_ack *extack)
+{
+	const struct pse_controller_ops *ops = pcdev->ops;
+	struct pse_pi *pi = &pcdev->pi[id];
+	int ret, pw_req;
+
+	if (!ops->pi_get_pw_req) {
+		/* No power allocation management */
+		ret = ops->pi_enable(pcdev, id);
+		if (ret)
+			NL_SET_ERR_MSG_FMT(extack,
+					   "PI %d: enable error %d",
+					   id, ret);
+		return ret;
+	}
+
+	ret = ops->pi_get_pw_req(pcdev, id);
+	if (ret < 0)
+		return ret;
+
+	pw_req = ret;
+
+	/* Compare requested power with port power limit and use the lowest
+	 * one.
+	 */
+	if (ops->pi_get_pw_limit) {
+		ret = ops->pi_get_pw_limit(pcdev, id);
+		if (ret < 0)
+			return ret;
+
+		if (ret < pw_req)
+			pw_req = ret;
+	}
+
+	ret = pse_pi_allocate_pw_budget(pcdev, id, pw_req, extack);
+	if (ret)
+		return ret;
+
+	ret = ops->pi_enable(pcdev, id);
+	if (ret) {
+		pse_pi_deallocate_pw_budget(pi);
+		NL_SET_ERR_MSG_FMT(extack,
+				   "PI %d: enable error %d",
+				   id, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
 static int pse_pi_enable(struct regulator_dev *rdev)
 {
 	struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev);
 	const struct pse_controller_ops *ops;
-	int id, ret;
+	int id, ret = 0;
 
 	ops = pcdev->ops;
 	if (!ops->pi_enable)
@@ -327,6 +674,23 @@ static int pse_pi_enable(struct regulator_dev *rdev)
 
 	id = rdev_get_id(rdev);
 	mutex_lock(&pcdev->lock);
+	if (pse_pw_d_is_sw_pw_control(pcdev, pcdev->pi[id].pw_d)) {
+		/* Manage enabled status by software.
+		 * Real enable process will happen if a port is connected.
+		 */
+		if (pcdev->pi[id].isr_pd_detected) {
+			struct netlink_ext_ack extack;
+
+			ret = _pse_pi_delivery_power_sw_pw_ctrl(pcdev, id, &extack);
+		}
+		if (!ret || ret == -ERANGE) {
+			pcdev->pi[id].admin_state_enabled = 1;
+			ret = 0;
+		}
+		mutex_unlock(&pcdev->lock);
+		return ret;
+	}
+
 	ret = ops->pi_enable(pcdev, id);
 	if (!ret)
 		pcdev->pi[id].admin_state_enabled = 1;
@@ -338,21 +702,18 @@ static int pse_pi_enable(struct regulator_dev *rdev)
 static int pse_pi_disable(struct regulator_dev *rdev)
 {
 	struct pse_controller_dev *pcdev = rdev_get_drvdata(rdev);
-	const struct pse_controller_ops *ops;
+	struct pse_pi *pi;
 	int id, ret;
 
-	ops = pcdev->ops;
-	if (!ops->pi_disable)
-		return -EOPNOTSUPP;
-
 	id = rdev_get_id(rdev);
+	pi = &pcdev->pi[id];
 	mutex_lock(&pcdev->lock);
-	ret = ops->pi_disable(pcdev, id);
+	ret = _pse_pi_disable(pcdev, id);
 	if (!ret)
-		pcdev->pi[id].admin_state_enabled = 0;
-	mutex_unlock(&pcdev->lock);
+		pi->admin_state_enabled = 0;
 
-	return ret;
+	mutex_unlock(&pcdev->lock);
+	return 0;
 }
 
 static int _pse_pi_get_voltage(struct regulator_dev *rdev)
@@ -628,6 +989,11 @@ static int pse_register_pw_ds(struct pse_controller_dev *pcdev)
 		}
 
 		pw_d->supply = supply;
+		if (pcdev->supp_budget_eval_strategies)
+			pw_d->budget_eval_strategy = pcdev->supp_budget_eval_strategies;
+		else
+			pw_d->budget_eval_strategy = PSE_BUDGET_EVAL_STRAT_DISABLED;
+		kref_init(&pw_d->refcnt);
 		pcdev->pi[i].pw_d = pw_d;
 	}
 
@@ -636,6 +1002,34 @@ out:
 	return ret;
 }
 
+/**
+ * pse_send_ntf_worker - Worker to send PSE notifications
+ * @work: work object
+ *
+ * Manage and send PSE netlink notifications using a workqueue to avoid
+ * deadlock between pcdev_lock and pse_list_mutex.
+ */
+static void pse_send_ntf_worker(struct work_struct *work)
+{
+	struct pse_controller_dev *pcdev;
+	struct pse_ntf ntf;
+
+	pcdev = container_of(work, struct pse_controller_dev, ntf_work);
+
+	while (kfifo_out(&pcdev->ntf_fifo, &ntf, 1)) {
+		struct net_device *netdev;
+		struct pse_control *psec;
+
+		psec = pse_control_find_by_id(pcdev, ntf.id);
+		rtnl_lock();
+		netdev = pse_control_get_netdev(psec);
+		if (netdev)
+			ethnl_pse_send_ntf(netdev, ntf.notifs);
+		rtnl_unlock();
+		pse_control_put(psec);
+	}
+}
+
 /**
  * pse_controller_register - register a PSE controller device
  * @pcdev: a pointer to the initialized PSE controller device
@@ -649,6 +1043,13 @@ int pse_controller_register(struct pse_controller_dev *pcdev)
 
 	mutex_init(&pcdev->lock);
 	INIT_LIST_HEAD(&pcdev->pse_control_head);
+	spin_lock_init(&pcdev->ntf_fifo_lock);
+	ret = kfifo_alloc(&pcdev->ntf_fifo, pcdev->nr_lines, GFP_KERNEL);
+	if (ret) {
+		dev_err(pcdev->dev, "failed to allocate kfifo notifications\n");
+		return ret;
+	}
+	INIT_WORK(&pcdev->ntf_work, pse_send_ntf_worker);
 
 	if (!pcdev->nr_lines)
 		pcdev->nr_lines = 1;
@@ -715,6 +1116,10 @@ void pse_controller_unregister(struct pse_controller_dev *pcdev)
 {
 	pse_flush_pw_ds(pcdev);
 	pse_release_pis(pcdev);
+	if (pcdev->irq)
+		disable_irq(pcdev->irq);
+	cancel_work_sync(&pcdev->ntf_work);
+	kfifo_free(&pcdev->ntf_fifo);
 	mutex_lock(&pse_list_mutex);
 	list_del(&pcdev->list);
 	mutex_unlock(&pse_list_mutex);
@@ -786,6 +1191,52 @@ static unsigned long pse_to_regulator_notifs(unsigned long notifs)
 	return rnotifs;
 }
 
+/**
+ * pse_set_config_isr - Set PSE control config according to the PSE
+ *			notifications
+ * @pcdev: a pointer to the PSE
+ * @id: index of the PSE control
+ * @notifs: PSE event notifications
+ *
+ * Return: 0 on success and failure value on error
+ */
+static int pse_set_config_isr(struct pse_controller_dev *pcdev, int id,
+			      unsigned long notifs)
+{
+	int ret = 0;
+
+	if (notifs & PSE_BUDGET_EVAL_STRAT_DYNAMIC)
+		return 0;
+
+	if ((notifs & ETHTOOL_C33_PSE_EVENT_DISCONNECTION) &&
+	    ((notifs & ETHTOOL_C33_PSE_EVENT_DETECTION) ||
+	     (notifs & ETHTOOL_C33_PSE_EVENT_CLASSIFICATION))) {
+		dev_dbg(pcdev->dev,
+			"PI %d: error, connection and disconnection reported simultaneously",
+			id);
+		return -EINVAL;
+	}
+
+	if (notifs & ETHTOOL_C33_PSE_EVENT_CLASSIFICATION) {
+		struct netlink_ext_ack extack;
+
+		pcdev->pi[id].isr_pd_detected = true;
+		if (pcdev->pi[id].admin_state_enabled) {
+			ret = _pse_pi_delivery_power_sw_pw_ctrl(pcdev, id,
+								&extack);
+			if (ret == -ERANGE)
+				ret = 0;
+		}
+	} else if (notifs & ETHTOOL_C33_PSE_EVENT_DISCONNECTION) {
+		if (pcdev->pi[id].admin_state_enabled &&
+		    pcdev->pi[id].isr_pd_detected)
+			ret = _pse_pi_disable(pcdev, id);
+		pcdev->pi[id].isr_pd_detected = false;
+	}
+
+	return ret;
+}
+
 /**
  * pse_isr - IRQ handler for PSE
  * @irq: irq number
@@ -808,36 +1259,42 @@ static irqreturn_t pse_isr(int irq, void *data)
 	memset(h->notifs, 0, pcdev->nr_lines * sizeof(*h->notifs));
 	mutex_lock(&pcdev->lock);
 	ret = desc->map_event(irq, pcdev, h->notifs, &notifs_mask);
-	mutex_unlock(&pcdev->lock);
-	if (ret || !notifs_mask)
+	if (ret || !notifs_mask) {
+		mutex_unlock(&pcdev->lock);
 		return IRQ_NONE;
+	}
 
 	for_each_set_bit(i, &notifs_mask, pcdev->nr_lines) {
 		unsigned long notifs, rnotifs;
-		struct net_device *netdev;
-		struct pse_control *psec;
+		struct pse_ntf ntf = {};
 
 		/* Do nothing PI not described */
 		if (!pcdev->pi[i].rdev)
 			continue;
 
 		notifs = h->notifs[i];
+		if (pse_pw_d_is_sw_pw_control(pcdev, pcdev->pi[i].pw_d)) {
+			ret = pse_set_config_isr(pcdev, i, notifs);
+			if (ret)
+				notifs |= ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR;
+		}
+
 		dev_dbg(h->pcdev->dev,
 			"Sending PSE notification EVT 0x%lx\n", notifs);
 
-		psec = pse_control_find_by_id(pcdev, i);
-		rtnl_lock();
-		netdev = pse_control_get_netdev(psec);
-		if (netdev)
-			ethnl_pse_send_ntf(netdev, notifs);
-		rtnl_unlock();
-		pse_control_put(psec);
+		ntf.notifs = notifs;
+		ntf.id = i;
+		kfifo_in_spinlocked(&pcdev->ntf_fifo, &ntf, 1,
+				    &pcdev->ntf_fifo_lock);
+		schedule_work(&pcdev->ntf_work);
 
 		rnotifs = pse_to_regulator_notifs(notifs);
 		regulator_notifier_call_chain(pcdev->pi[i].rdev, rnotifs,
 					      NULL);
 	}
 
+	mutex_unlock(&pcdev->lock);
+
 	return IRQ_HANDLED;
 }
 
@@ -960,6 +1417,20 @@ pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index,
 		goto free_psec;
 	}
 
+	if (!pcdev->ops->pi_get_admin_state) {
+		ret = -EOPNOTSUPP;
+		goto free_psec;
+	}
+
+	/* Initialize admin_state_enabled before the regulator_get. This
+	 * aims to have the right value reported in the first is_enabled
+	 * call in case of control managed by software.
+	 */
+	ret = pse_pi_is_hw_enabled(pcdev, index);
+	if (ret < 0)
+		goto free_psec;
+
+	pcdev->pi[index].admin_state_enabled = ret;
 	psec->ps = devm_regulator_get_exclusive(pcdev->dev,
 						rdev_get_name(pcdev->pi[index].rdev));
 	if (IS_ERR(psec->ps)) {
@@ -967,12 +1438,6 @@ pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index,
 		goto put_module;
 	}
 
-	ret = regulator_is_enabled(psec->ps);
-	if (ret < 0)
-		goto regulator_put;
-
-	pcdev->pi[index].admin_state_enabled = ret;
-
 	psec->pcdev = pcdev;
 	list_add(&psec->list, &pcdev->pse_control_head);
 	psec->id = index;
@@ -981,8 +1446,6 @@ pse_control_get_internal(struct pse_controller_dev *pcdev, unsigned int index,
 
 	return psec;
 
-regulator_put:
-	devm_regulator_put(psec->ps);
 put_module:
 	module_put(pcdev->owner);
 free_psec:
@@ -1093,6 +1556,35 @@ out:
 }
 EXPORT_SYMBOL_GPL(of_pse_control_get);
 
+/**
+ * pse_get_sw_admin_state - Convert the software admin state to c33 or podl
+ *			    admin state value used in the standard
+ * @psec: PSE control pointer
+ * @admin_state: a pointer to the admin_state structure
+ */
+static void pse_get_sw_admin_state(struct pse_control *psec,
+				   struct pse_admin_state *admin_state)
+{
+	struct pse_pi *pi = &psec->pcdev->pi[psec->id];
+
+	if (pse_has_podl(psec)) {
+		if (pi->admin_state_enabled)
+			admin_state->podl_admin_state =
+				ETHTOOL_PODL_PSE_ADMIN_STATE_ENABLED;
+		else
+			admin_state->podl_admin_state =
+				ETHTOOL_PODL_PSE_ADMIN_STATE_DISABLED;
+	}
+	if (pse_has_c33(psec)) {
+		if (pi->admin_state_enabled)
+			admin_state->c33_admin_state =
+				ETHTOOL_C33_PSE_ADMIN_STATE_ENABLED;
+		else
+			admin_state->c33_admin_state =
+				ETHTOOL_C33_PSE_ADMIN_STATE_DISABLED;
+	}
+}
+
 /**
  * pse_ethtool_get_status - get status of PSE control
  * @psec: PSE control pointer
@@ -1109,19 +1601,46 @@ int pse_ethtool_get_status(struct pse_control *psec,
 	struct pse_pw_status pw_status = {0};
 	const struct pse_controller_ops *ops;
 	struct pse_controller_dev *pcdev;
+	struct pse_pi *pi;
 	int ret;
 
 	pcdev = psec->pcdev;
 	ops = pcdev->ops;
+
+	pi = &pcdev->pi[psec->id];
 	mutex_lock(&pcdev->lock);
-	if (pcdev->pi[psec->id].pw_d)
-		status->pw_d_id = pcdev->pi[psec->id].pw_d->id;
+	if (pi->pw_d) {
+		status->pw_d_id = pi->pw_d->id;
+		if (pse_pw_d_is_sw_pw_control(pcdev, pi->pw_d)) {
+			pse_get_sw_admin_state(psec, &admin_state);
+		} else {
+			ret = ops->pi_get_admin_state(pcdev, psec->id,
+						      &admin_state);
+			if (ret)
+				goto out;
+		}
+		status->podl_admin_state = admin_state.podl_admin_state;
+		status->c33_admin_state = admin_state.c33_admin_state;
 
-	ret = ops->pi_get_admin_state(pcdev, psec->id, &admin_state);
-	if (ret)
-		goto out;
-	status->podl_admin_state = admin_state.podl_admin_state;
-	status->c33_admin_state = admin_state.c33_admin_state;
+		switch (pi->pw_d->budget_eval_strategy) {
+		case PSE_BUDGET_EVAL_STRAT_STATIC:
+			status->prio_max = pcdev->nr_lines - 1;
+			status->prio = pi->prio;
+			break;
+		case PSE_BUDGET_EVAL_STRAT_DYNAMIC:
+			status->prio_max = pcdev->pis_prio_max;
+			if (ops->pi_get_prio) {
+				ret = ops->pi_get_prio(pcdev, psec->id);
+				if (ret < 0)
+					goto out;
+
+				status->prio = ret;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	ret = ops->pi_get_pw_status(pcdev, psec->id, &pw_status);
 	if (ret)
@@ -1270,6 +1789,52 @@ int pse_ethtool_set_config(struct pse_control *psec,
 }
 EXPORT_SYMBOL_GPL(pse_ethtool_set_config);
 
+/**
+ * pse_pi_update_pw_budget - Update PSE power budget allocated with new
+ *			     power in mW
+ * @pcdev: a pointer to the PSE controller device
+ * @id: index of the PSE PI
+ * @pw_req: power requested
+ * @extack: extack for reporting useful error messages
+ *
+ * Return: Previous power allocated on success and failure value on error
+ */
+static int pse_pi_update_pw_budget(struct pse_controller_dev *pcdev, int id,
+				   const unsigned int pw_req,
+				   struct netlink_ext_ack *extack)
+{
+	struct pse_pi *pi = &pcdev->pi[id];
+	int previous_pw_allocated;
+	int pw_diff, ret = 0;
+
+	/* We don't want pw_allocated_mW value change in the middle of an
+	 * power budget update
+	 */
+	mutex_lock(&pcdev->lock);
+	previous_pw_allocated = pi->pw_allocated_mW;
+	pw_diff = pw_req - previous_pw_allocated;
+	if (!pw_diff) {
+		goto out;
+	} else if (pw_diff > 0) {
+		ret = regulator_request_power_budget(pi->pw_d->supply, pw_diff);
+		if (ret) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "PI %d: not enough power budget available",
+					   id);
+			goto out;
+		}
+
+	} else {
+		regulator_free_power_budget(pi->pw_d->supply, -pw_diff);
+	}
+	pi->pw_allocated_mW = pw_req;
+	ret = previous_pw_allocated;
+
+out:
+	mutex_unlock(&pcdev->lock);
+	return ret;
+}
+
 /**
  * pse_ethtool_set_pw_limit - set PSE control power limit
  * @psec: PSE control pointer
@@ -1282,7 +1847,7 @@ int pse_ethtool_set_pw_limit(struct pse_control *psec,
 			     struct netlink_ext_ack *extack,
 			     const unsigned int pw_limit)
 {
-	int uV, uA, ret;
+	int uV, uA, ret, previous_pw_allocated = 0;
 	s64 tmp_64;
 
 	if (pw_limit > MAX_PI_PW)
@@ -1306,10 +1871,100 @@ int pse_ethtool_set_pw_limit(struct pse_control *psec,
 	/* uA = mW * 1000000000 / uV */
 	uA = DIV_ROUND_CLOSEST_ULL(tmp_64, uV);
 
-	return regulator_set_current_limit(psec->ps, 0, uA);
+	/* Update power budget only in software power control case and
+	 * if a Power Device is powered.
+	 */
+	if (pse_pw_d_is_sw_pw_control(psec->pcdev,
+				      psec->pcdev->pi[psec->id].pw_d) &&
+	    psec->pcdev->pi[psec->id].admin_state_enabled &&
+	    psec->pcdev->pi[psec->id].isr_pd_detected) {
+		ret = pse_pi_update_pw_budget(psec->pcdev, psec->id,
+					      pw_limit, extack);
+		if (ret < 0)
+			return ret;
+		previous_pw_allocated = ret;
+	}
+
+	ret = regulator_set_current_limit(psec->ps, 0, uA);
+	if (ret < 0 && previous_pw_allocated) {
+		pse_pi_update_pw_budget(psec->pcdev, psec->id,
+					previous_pw_allocated, extack);
+	}
+
+	return ret;
 }
 EXPORT_SYMBOL_GPL(pse_ethtool_set_pw_limit);
 
+/**
+ * pse_ethtool_set_prio - Set PSE PI priority according to the budget
+ *			  evaluation strategy
+ * @psec: PSE control pointer
+ * @extack: extack for reporting useful error messages
+ * @prio: priovity value
+ *
+ * Return: 0 on success and failure value on error
+ */
+int pse_ethtool_set_prio(struct pse_control *psec,
+			 struct netlink_ext_ack *extack,
+			 unsigned int prio)
+{
+	struct pse_controller_dev *pcdev = psec->pcdev;
+	const struct pse_controller_ops *ops;
+	int ret = 0;
+
+	if (!pcdev->pi[psec->id].pw_d) {
+		NL_SET_ERR_MSG(extack, "no power domain attached");
+		return -EOPNOTSUPP;
+	}
+
+	/* We don't want priority change in the middle of an
+	 * enable/disable call or a priority mode change
+	 */
+	mutex_lock(&pcdev->lock);
+	switch (pcdev->pi[psec->id].pw_d->budget_eval_strategy) {
+	case PSE_BUDGET_EVAL_STRAT_STATIC:
+		if (prio >= pcdev->nr_lines) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "priority %d exceed priority max %d",
+					   prio, pcdev->nr_lines);
+			ret = -ERANGE;
+			goto out;
+		}
+
+		pcdev->pi[psec->id].prio = prio;
+		pse_pw_d_retry_power_delivery(pcdev, pcdev->pi[psec->id].pw_d);
+		break;
+
+	case PSE_BUDGET_EVAL_STRAT_DYNAMIC:
+		ops = psec->pcdev->ops;
+		if (!ops->pi_set_prio) {
+			NL_SET_ERR_MSG(extack,
+				       "pse driver does not support setting port priority");
+			ret = -EOPNOTSUPP;
+			goto out;
+		}
+
+		if (prio > pcdev->pis_prio_max) {
+			NL_SET_ERR_MSG_FMT(extack,
+					   "priority %d exceed priority max %d",
+					   prio, pcdev->pis_prio_max);
+			ret = -ERANGE;
+			goto out;
+		}
+
+		ret = ops->pi_set_prio(pcdev, psec->id, prio);
+		break;
+
+	default:
+		ret = -EOPNOTSUPP;
+	}
+
+out:
+	mutex_unlock(&pcdev->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pse_ethtool_set_prio);
+
 bool pse_has_podl(struct pse_control *psec)
 {
 	return psec->pcdev->types & ETHTOOL_PSE_PODL;
diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h
index 2f8ecfd87d43..e5f305cef82e 100644
--- a/include/linux/pse-pd/pse.h
+++ b/include/linux/pse-pd/pse.h
@@ -6,6 +6,8 @@
 #define _LINUX_PSE_CONTROLLER_H
 
 #include <linux/list.h>
+#include <linux/netlink.h>
+#include <linux/kfifo.h>
 #include <uapi/linux/ethtool.h>
 #include <uapi/linux/ethtool_netlink_generated.h>
 #include <linux/regulator/driver.h>
@@ -134,6 +136,9 @@ struct pse_pw_limit_ranges {
  *	is in charge of the memory allocation
  * @c33_pw_limit_nb_ranges: number of supported power limit configuration
  *	ranges
+ * @prio_max: max priority allowed for the c33_prio variable value.
+ * @prio: priority of the PSE. Managed by PSE core in case of static budget
+ *	evaluation strategy.
  */
 struct ethtool_pse_control_status {
 	u32 pw_d_id;
@@ -147,6 +152,8 @@ struct ethtool_pse_control_status {
 	u32 c33_avail_pw_limit;
 	struct ethtool_c33_pse_pw_limit_range *c33_pw_limit_ranges;
 	u32 c33_pw_limit_nb_ranges;
+	u32 prio_max;
+	u32 prio;
 };
 
 /**
@@ -170,6 +177,11 @@ struct ethtool_pse_control_status {
  *			    range. The driver is in charge of the memory
  *			    allocation and should return the number of
  *			    ranges.
+ * @pi_get_prio: Get the PSE PI priority.
+ * @pi_set_prio: Configure the PSE PI priority.
+ * @pi_get_pw_req: Get the power requested by a PD before enabling the PSE PI.
+ *		   This is only relevant when an interrupt is registered using
+ *		   devm_pse_irq_helper helper.
  */
 struct pse_controller_ops {
 	int (*setup_pi_matrix)(struct pse_controller_dev *pcdev);
@@ -190,6 +202,10 @@ struct pse_controller_ops {
 			       int id, int max_mW);
 	int (*pi_get_pw_limit_ranges)(struct pse_controller_dev *pcdev, int id,
 				      struct pse_pw_limit_ranges *pw_limit_ranges);
+	int (*pi_get_prio)(struct pse_controller_dev *pcdev, int id);
+	int (*pi_set_prio)(struct pse_controller_dev *pcdev, int id,
+			   unsigned int prio);
+	int (*pi_get_pw_req)(struct pse_controller_dev *pcdev, int id);
 };
 
 struct module;
@@ -225,6 +241,13 @@ struct pse_pi_pairset {
  * @rdev: regulator represented by the PSE PI
  * @admin_state_enabled: PI enabled state
  * @pw_d: Power domain of the PSE PI
+ * @prio: Priority of the PSE PI. Used in static budget evaluation strategy
+ * @isr_pd_detected: PSE PI detection status managed by the interruption
+ *		     handler. This variable is relevant when the power enabled
+ *		     management is managed in software like the static
+ *		     budget evaluation strategy.
+ * @pw_allocated_mW: Power allocated to a PSE PI to manage power budget in
+ *		     static budget evaluation strategy.
  */
 struct pse_pi {
 	struct pse_pi_pairset pairset[2];
@@ -232,6 +255,20 @@ struct pse_pi {
 	struct regulator_dev *rdev;
 	bool admin_state_enabled;
 	struct pse_power_domain *pw_d;
+	int prio;
+	bool isr_pd_detected;
+	int pw_allocated_mW;
+};
+
+/**
+ * struct pse_ntf - PSE notification element
+ *
+ * @id: ID of the PSE control
+ * @notifs: PSE notifications to be reported
+ */
+struct pse_ntf {
+	int id;
+	unsigned long notifs;
 };
 
 /**
@@ -249,6 +286,12 @@ struct pse_pi {
  * @pi: table of PSE PIs described in this controller device
  * @no_of_pse_pi: flag set if the pse_pis devicetree node is not used
  * @irq: PSE interrupt
+ * @pis_prio_max: Maximum value allowed for the PSE PIs priority
+ * @supp_budget_eval_strategies: budget evaluation strategies supported
+ *				 by the PSE
+ * @ntf_work: workqueue for PSE notification management
+ * @ntf_fifo: PSE notifications FIFO
+ * @ntf_fifo_lock: protect @ntf_fifo writer
  */
 struct pse_controller_dev {
 	const struct pse_controller_ops *ops;
@@ -263,6 +306,29 @@ struct pse_controller_dev {
 	struct pse_pi *pi;
 	bool no_of_pse_pi;
 	int irq;
+	unsigned int pis_prio_max;
+	u32 supp_budget_eval_strategies;
+	struct work_struct ntf_work;
+	DECLARE_KFIFO_PTR(ntf_fifo, struct pse_ntf);
+	spinlock_t ntf_fifo_lock; /* Protect @ntf_fifo writer */
+};
+
+/**
+ * enum pse_budget_eval_strategies - PSE budget evaluation strategies.
+ * @PSE_BUDGET_EVAL_STRAT_DISABLED: Budget evaluation strategy disabled.
+ * @PSE_BUDGET_EVAL_STRAT_STATIC: PSE static budget evaluation strategy.
+ *	Budget evaluation strategy based on the power requested during PD
+ *	classification. This strategy is managed by the PSE core.
+ * @PSE_BUDGET_EVAL_STRAT_DYNAMIC: PSE dynamic budget evaluation
+ *	strategy. Budget evaluation strategy based on the current consumption
+ *	per ports compared to the total	power budget. This mode is managed by
+ *	the PSE controller.
+ */
+
+enum pse_budget_eval_strategies {
+	PSE_BUDGET_EVAL_STRAT_DISABLED	= 1 << 0,
+	PSE_BUDGET_EVAL_STRAT_STATIC	= 1 << 1,
+	PSE_BUDGET_EVAL_STRAT_DYNAMIC	= 1 << 2,
 };
 
 #if IS_ENABLED(CONFIG_PSE_CONTROLLER)
@@ -287,6 +353,9 @@ int pse_ethtool_set_config(struct pse_control *psec,
 int pse_ethtool_set_pw_limit(struct pse_control *psec,
 			     struct netlink_ext_ack *extack,
 			     const unsigned int pw_limit);
+int pse_ethtool_set_prio(struct pse_control *psec,
+			 struct netlink_ext_ack *extack,
+			 unsigned int prio);
 
 bool pse_has_podl(struct pse_control *psec);
 bool pse_has_c33(struct pse_control *psec);
@@ -324,6 +393,13 @@ static inline int pse_ethtool_set_pw_limit(struct pse_control *psec,
 	return -EOPNOTSUPP;
 }
 
+static inline int pse_ethtool_set_prio(struct pse_control *psec,
+				       struct netlink_ext_ack *extack,
+				       unsigned int prio)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline bool pse_has_podl(struct pse_control *psec)
 {
 	return false;
diff --git a/include/uapi/linux/ethtool_netlink_generated.h b/include/uapi/linux/ethtool_netlink_generated.h
index ed344c8533eb..c6a95224be25 100644
--- a/include/uapi/linux/ethtool_netlink_generated.h
+++ b/include/uapi/linux/ethtool_netlink_generated.h
@@ -53,10 +53,28 @@ enum hwtstamp_source {
  * enum ethtool_pse_event - PSE event list for the PSE controller
  * @ETHTOOL_PSE_EVENT_OVER_CURRENT: PSE output current is too high
  * @ETHTOOL_PSE_EVENT_OVER_TEMP: PSE in over temperature state
+ * @ETHTOOL_C33_PSE_EVENT_DETECTION: detection process occur on the PSE. IEEE
+ *   802.3-2022 33.2.5 and 145.2.6 PSE detection of PDs. IEEE 802.3-202
+ *   30.9.1.1.5 aPSEPowerDetectionStatus
+ * @ETHTOOL_C33_PSE_EVENT_CLASSIFICATION: classification process occur on the
+ *   PSE. IEEE 802.3-2022 33.2.6 and 145.2.8 classification of PDs mutual
+ *   identification. IEEE 802.3-2022 30.9.1.1.8 aPSEPowerClassification.
+ * @ETHTOOL_C33_PSE_EVENT_DISCONNECTION: PD has been disconnected on the PSE.
+ *   IEEE 802.3-2022 33.3.8 and 145.3.9 PD Maintain Power Signature. IEEE
+ *   802.3-2022 33.5.1.2.9 MPS Absent. IEEE 802.3-2022 30.9.1.1.20
+ *   aPSEMPSAbsentCounter.
+ * @ETHTOOL_PSE_EVENT_OVER_BUDGET: PSE turned off due to over budget situation
+ * @ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR: PSE faced an error managing the
+ *   power control from software
  */
 enum ethtool_pse_event {
 	ETHTOOL_PSE_EVENT_OVER_CURRENT = 1,
 	ETHTOOL_PSE_EVENT_OVER_TEMP = 2,
+	ETHTOOL_C33_PSE_EVENT_DETECTION = 4,
+	ETHTOOL_C33_PSE_EVENT_CLASSIFICATION = 8,
+	ETHTOOL_C33_PSE_EVENT_DISCONNECTION = 16,
+	ETHTOOL_PSE_EVENT_OVER_BUDGET = 32,
+	ETHTOOL_PSE_EVENT_SW_PW_CONTROL_ERROR = 64,
 };
 
 enum {
-- 
cgit v1.2.3


From deefc7083414de81aad102b60f0390f600d7eb79 Mon Sep 17 00:00:00 2001
From: Clément Le Goffic <clement.legoffic@foss.st.com>
Date: Fri, 13 Jun 2025 12:14:12 +0200
Subject: gpio: mmio: add BGPIOF_NO_INPUT flag for GPO gpiochip
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

When using bgpio_init with a gpiochip acting as a GPO (output only), the
gpiochip ops `direction_input` was set to `bgpio_simple_dir_in` by
default but we have no input ability.

Adding this flag allows to set a valid ops for the `direction_output`
ops without setting a valid ops for `direction_input` by default.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Clément Le Goffic <clement.legoffic@foss.st.com>
Link: https://lore.kernel.org/r/20250613-hdp-upstream-v5-1-6fd6f0dc527c@foss.st.com
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-mmio.c    | 11 ++++++++++-
 include/linux/gpio/driver.h |  1 +
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c
index 4841e4ebe7a6..09b9e1275e7e 100644
--- a/drivers/gpio/gpio-mmio.c
+++ b/drivers/gpio/gpio-mmio.c
@@ -335,6 +335,11 @@ static int bgpio_dir_return(struct gpio_chip *gc, unsigned int gpio, bool dir_ou
 		return pinctrl_gpio_direction_input(gc, gpio);
 }
 
+static int bgpio_dir_in_err(struct gpio_chip *gc, unsigned int gpio)
+{
+	return -EINVAL;
+}
+
 static int bgpio_simple_dir_in(struct gpio_chip *gc, unsigned int gpio)
 {
 	return bgpio_dir_return(gc, gpio, false);
@@ -566,7 +571,11 @@ static int bgpio_setup_direction(struct gpio_chip *gc,
 			gc->direction_output = bgpio_dir_out_err;
 		else
 			gc->direction_output = bgpio_simple_dir_out;
-		gc->direction_input = bgpio_simple_dir_in;
+
+		if (flags & BGPIOF_NO_INPUT)
+			gc->direction_input = bgpio_dir_in_err;
+		else
+			gc->direction_input = bgpio_simple_dir_in;
 	}
 
 	return 0;
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index b53233051bee..97cc75623261 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -750,6 +750,7 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev,
 #define BGPIOF_NO_OUTPUT		BIT(5) /* only input */
 #define BGPIOF_NO_SET_ON_INPUT		BIT(6)
 #define BGPIOF_PINCTRL_BACKEND		BIT(7) /* Call pinctrl direction setters */
+#define BGPIOF_NO_INPUT			BIT(8) /* only output */
 
 #ifdef CONFIG_GPIOLIB_IRQCHIP
 int gpiochip_irqchip_add_domain(struct gpio_chip *gc,
-- 
cgit v1.2.3


From 6012ce6b30567aa8ec8dc5b648b7841f9f74ca7c Mon Sep 17 00:00:00 2001
From: Richard Leitner <richard.leitner@linux.dev>
Date: Tue, 17 Jun 2025 09:31:37 +0200
Subject: leds: led-class-flash:: Fix flash_timeout comment

The comment for the flash_timeout setter mentioned it is the "flash
duration". Fix this by changing it to "flash timeout".

Signed-off-by: Richard Leitner <richard.leitner@linux.dev>
Link: https://lore.kernel.org/r/20250617-ov9282-flash-strobe-v5-3-9762da74d065@linux.dev
Signed-off-by: Lee Jones <lee@kernel.org>
---
 include/linux/led-class-flash.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/led-class-flash.h b/include/linux/led-class-flash.h
index 21ec856c36bc..775a96217518 100644
--- a/include/linux/led-class-flash.h
+++ b/include/linux/led-class-flash.h
@@ -197,7 +197,7 @@ int led_update_flash_brightness(struct led_classdev_flash *fled_cdev);
  * @fled_cdev: the flash LED to set
  * @timeout: the flash timeout to set it to
  *
- * Set the flash strobe duration.
+ * Set the flash strobe timeout.
  *
  * Returns: 0 on success or negative error value on failure
  */
-- 
cgit v1.2.3


From bc9a0c68f2583e42ace81a9c229c158b7cdcb45b Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 3 Jun 2025 21:39:05 +0100
Subject: usb: phy: tegra: Remove unused functions

tegra_ehci_phy_restore_start() and tegra_ehci_phy_restore_end()
last use was removed in 2013 by
commit a4faa54e3aa2 ("USB: EHCI: tegra: remove all power management")

tegra_usb_phy_preresume() and tegra_usb_phy_postresume() last
use was removed in 2020 by
commit c3590c7656fb ("usb: host: ehci-tegra: Remove the driver")
(Although that one makes me wonder how much of the rest of the file
is actually used)

Remove both sets.

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Link: https://lore.kernel.org/r/20250603203905.279307-1-linux@treblig.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/phy/phy-tegra-usb.c   | 89 ---------------------------------------
 include/linux/usb/tegra_usb_phy.h |  9 ----
 2 files changed, 98 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/phy/phy-tegra-usb.c b/drivers/usb/phy/phy-tegra-usb.c
index bee222967f6b..fb9031628d39 100644
--- a/drivers/usb/phy/phy-tegra-usb.c
+++ b/drivers/usb/phy/phy-tegra-usb.c
@@ -711,58 +711,6 @@ static int utmi_phy_power_off(struct tegra_usb_phy *phy)
 	return utmip_pad_power_off(phy);
 }
 
-static void utmi_phy_preresume(struct tegra_usb_phy *phy)
-{
-	void __iomem *base = phy->regs;
-	u32 val;
-
-	val = readl_relaxed(base + UTMIP_TX_CFG0);
-	val |= UTMIP_HS_DISCON_DISABLE;
-	writel_relaxed(val, base + UTMIP_TX_CFG0);
-}
-
-static void utmi_phy_postresume(struct tegra_usb_phy *phy)
-{
-	void __iomem *base = phy->regs;
-	u32 val;
-
-	val = readl_relaxed(base + UTMIP_TX_CFG0);
-	val &= ~UTMIP_HS_DISCON_DISABLE;
-	writel_relaxed(val, base + UTMIP_TX_CFG0);
-}
-
-static void utmi_phy_restore_start(struct tegra_usb_phy *phy,
-				   enum tegra_usb_phy_port_speed port_speed)
-{
-	void __iomem *base = phy->regs;
-	u32 val;
-
-	val = readl_relaxed(base + UTMIP_MISC_CFG0);
-	val &= ~UTMIP_DPDM_OBSERVE_SEL(~0);
-	if (port_speed == TEGRA_USB_PHY_PORT_SPEED_LOW)
-		val |= UTMIP_DPDM_OBSERVE_SEL_FS_K;
-	else
-		val |= UTMIP_DPDM_OBSERVE_SEL_FS_J;
-	writel_relaxed(val, base + UTMIP_MISC_CFG0);
-	usleep_range(1, 10);
-
-	val = readl_relaxed(base + UTMIP_MISC_CFG0);
-	val |= UTMIP_DPDM_OBSERVE;
-	writel_relaxed(val, base + UTMIP_MISC_CFG0);
-	usleep_range(10, 100);
-}
-
-static void utmi_phy_restore_end(struct tegra_usb_phy *phy)
-{
-	void __iomem *base = phy->regs;
-	u32 val;
-
-	val = readl_relaxed(base + UTMIP_MISC_CFG0);
-	val &= ~UTMIP_DPDM_OBSERVE;
-	writel_relaxed(val, base + UTMIP_MISC_CFG0);
-	usleep_range(10, 100);
-}
-
 static int ulpi_phy_power_on(struct tegra_usb_phy *phy)
 {
 	void __iomem *base = phy->regs;
@@ -1123,43 +1071,6 @@ disable_clk:
 	return err;
 }
 
-void tegra_usb_phy_preresume(struct usb_phy *u_phy)
-{
-	struct tegra_usb_phy *phy = to_tegra_usb_phy(u_phy);
-
-	if (!phy->is_ulpi_phy)
-		utmi_phy_preresume(phy);
-}
-EXPORT_SYMBOL_GPL(tegra_usb_phy_preresume);
-
-void tegra_usb_phy_postresume(struct usb_phy *u_phy)
-{
-	struct tegra_usb_phy *phy = to_tegra_usb_phy(u_phy);
-
-	if (!phy->is_ulpi_phy)
-		utmi_phy_postresume(phy);
-}
-EXPORT_SYMBOL_GPL(tegra_usb_phy_postresume);
-
-void tegra_ehci_phy_restore_start(struct usb_phy *u_phy,
-				  enum tegra_usb_phy_port_speed port_speed)
-{
-	struct tegra_usb_phy *phy = to_tegra_usb_phy(u_phy);
-
-	if (!phy->is_ulpi_phy)
-		utmi_phy_restore_start(phy, port_speed);
-}
-EXPORT_SYMBOL_GPL(tegra_ehci_phy_restore_start);
-
-void tegra_ehci_phy_restore_end(struct usb_phy *u_phy)
-{
-	struct tegra_usb_phy *phy = to_tegra_usb_phy(u_phy);
-
-	if (!phy->is_ulpi_phy)
-		utmi_phy_restore_end(phy);
-}
-EXPORT_SYMBOL_GPL(tegra_ehci_phy_restore_end);
-
 static int read_utmi_param(struct platform_device *pdev, const char *param,
 			   u8 *dest)
 {
diff --git a/include/linux/usb/tegra_usb_phy.h b/include/linux/usb/tegra_usb_phy.h
index e6c14f2b1f9b..40afcee8b4f5 100644
--- a/include/linux/usb/tegra_usb_phy.h
+++ b/include/linux/usb/tegra_usb_phy.h
@@ -80,13 +80,4 @@ struct tegra_usb_phy {
 	bool powered_on;
 };
 
-void tegra_usb_phy_preresume(struct usb_phy *phy);
-
-void tegra_usb_phy_postresume(struct usb_phy *phy);
-
-void tegra_ehci_phy_restore_start(struct usb_phy *phy,
-				 enum tegra_usb_phy_port_speed port_speed);
-
-void tegra_ehci_phy_restore_end(struct usb_phy *phy);
-
 #endif /* __TEGRA_USB_PHY_H */
-- 
cgit v1.2.3


From efec475e5e20c594e10d42f73cf6803805ae14c9 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 9 Jun 2025 00:33:37 +0100
Subject: usb: gadget: config: Remove unused usb_gadget_config_buf

usb_gadget_config_buf() has been unused since 2012's
commit fa06920a3ece ("usb: gadget: Remove File-backed Storage Gadget
(g_file_storage).")

Remove it.

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Link: https://lore.kernel.org/r/20250608233338.179894-2-linux@treblig.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/config.c | 53 ---------------------------------------------
 include/linux/usb/gadget.h  |  4 ----
 2 files changed, 57 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/gadget/config.c b/drivers/usb/gadget/config.c
index 95f144a54ed9..256364d4b941 100644
--- a/drivers/usb/gadget/config.c
+++ b/drivers/usb/gadget/config.c
@@ -53,59 +53,6 @@ usb_descriptor_fillbuf(void *buf, unsigned buflen,
 }
 EXPORT_SYMBOL_GPL(usb_descriptor_fillbuf);
 
-/**
- * usb_gadget_config_buf - builts a complete configuration descriptor
- * @config: Header for the descriptor, including characteristics such
- *	as power requirements and number of interfaces.
- * @buf: Buffer for the resulting configuration descriptor.
- * @length: Length of buffer.  If this is not big enough to hold the
- *	entire configuration descriptor, an error code will be returned.
- * @desc: Null-terminated vector of pointers to the descriptors (interface,
- *	endpoint, etc) defining all functions in this device configuration.
- *
- * This copies descriptors into the response buffer, building a descriptor
- * for that configuration.  It returns the buffer length or a negative
- * status code.  The config.wTotalLength field is set to match the length
- * of the result, but other descriptor fields (including power usage and
- * interface count) must be set by the caller.
- *
- * Gadget drivers could use this when constructing a config descriptor
- * in response to USB_REQ_GET_DESCRIPTOR.  They will need to patch the
- * resulting bDescriptorType value if USB_DT_OTHER_SPEED_CONFIG is needed.
- */
-int usb_gadget_config_buf(
-	const struct usb_config_descriptor	*config,
-	void					*buf,
-	unsigned				length,
-	const struct usb_descriptor_header	**desc
-)
-{
-	struct usb_config_descriptor		*cp = buf;
-	int					len;
-
-	/* config descriptor first */
-	if (length < USB_DT_CONFIG_SIZE || !desc)
-		return -EINVAL;
-	*cp = *config;
-
-	/* then interface/endpoint/class/vendor/... */
-	len = usb_descriptor_fillbuf(USB_DT_CONFIG_SIZE + (u8 *)buf,
-			length - USB_DT_CONFIG_SIZE, desc);
-	if (len < 0)
-		return len;
-	len += USB_DT_CONFIG_SIZE;
-	if (len > 0xffff)
-		return -EINVAL;
-
-	/* patch up the config descriptor */
-	cp->bLength = USB_DT_CONFIG_SIZE;
-	cp->bDescriptorType = USB_DT_CONFIG;
-	cp->wTotalLength = cpu_to_le16(len);
-	cp->bmAttributes |= USB_CONFIG_ATT_ONE;
-	return len;
-}
-EXPORT_SYMBOL_GPL(usb_gadget_config_buf);
-
 /**
  * usb_copy_descriptors - copy a vector of USB descriptors
  * @src: null-terminated vector to copy
diff --git a/include/linux/usb/gadget.h b/include/linux/usb/gadget.h
index df33333650a0..0f28c5512fcb 100644
--- a/include/linux/usb/gadget.h
+++ b/include/linux/usb/gadget.h
@@ -860,10 +860,6 @@ container_of(str_item, struct gadget_string, item)
 int usb_descriptor_fillbuf(void *, unsigned,
 		const struct usb_descriptor_header **);
 
-/* build config descriptor from single descriptor vector */
-int usb_gadget_config_buf(const struct usb_config_descriptor *config,
-	void *buf, unsigned buflen, const struct usb_descriptor_header **desc);
-
 /* copy a NULL-terminated vector of descriptors */
 struct usb_descriptor_header **usb_copy_descriptors(
 		struct usb_descriptor_header **);
-- 
cgit v1.2.3


From 227280ad66ac50287a3ea8b8fd43b7c7a6eb09ac Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 9 Jun 2025 00:33:38 +0100
Subject: usb: gadget: Remove unused usb_remove_config

usb_remove_config() was added in 2012's
commit Fixes: 51cce6fc155c ("usb: gadget: composite: Add
usb_remove_config")
but has remained unused.

I see there was a use in drivers/staging/cch that
was removed by
commit 515e6dd20b3f ("Staging: ccg: delete it from the tree")
but it had it's own copy of usb_remove_config()

Remove it.

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Link: https://lore.kernel.org/r/20250608233338.179894-3-linux@treblig.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/gadget/composite.c | 24 ------------------------
 include/linux/usb/composite.h  |  3 ---
 2 files changed, 27 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/gadget/composite.c b/drivers/usb/gadget/composite.c
index 12634f0b45a8..0f649c747584 100644
--- a/drivers/usb/gadget/composite.c
+++ b/drivers/usb/gadget/composite.c
@@ -1194,30 +1194,6 @@ static void remove_config(struct usb_composite_dev *cdev,
 	}
 }
 
-/**
- * usb_remove_config() - remove a configuration from a device.
- * @cdev: wraps the USB gadget
- * @config: the configuration
- *
- * Drivers must call usb_gadget_disconnect before calling this function
- * to disconnect the device from the host and make sure the host will not
- * try to enumerate the device while we are changing the config list.
- */
-void usb_remove_config(struct usb_composite_dev *cdev,
-		      struct usb_configuration *config)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cdev->lock, flags);
-
-	if (cdev->config == config)
-		reset_config(cdev);
-
-	spin_unlock_irqrestore(&cdev->lock, flags);
-
-	remove_config(cdev, config);
-}
-
 /*-------------------------------------------------------------------------*/
 
 /* We support strings in multiple languages ... string descriptor zero
diff --git a/include/linux/usb/composite.h b/include/linux/usb/composite.h
index d8c4e9f73839..c18041fafa52 100644
--- a/include/linux/usb/composite.h
+++ b/include/linux/usb/composite.h
@@ -339,9 +339,6 @@ int usb_add_config(struct usb_composite_dev *,
 		struct usb_configuration *,
 		int (*)(struct usb_configuration *));
 
-void usb_remove_config(struct usb_composite_dev *,
-		struct usb_configuration *);
-
 /* predefined index for usb_composite_driver */
 enum {
 	USB_GADGET_MANUFACTURER_IDX	= 0,
-- 
cgit v1.2.3


From 47c83f95f3e293a9e924a1ba41d782bb059bb954 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 9 Jun 2025 00:56:17 +0100
Subject: usb: core: Remove unused usb_unlink_anchored_urbs

usb_unlink_anchored_urbs() has been unused since it's last use was
removed in 2009 by
commit 9b9c5aaeedfd ("ar9170: xmit code revamp")

Remove it.

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20250608235617.200731-1-linux@treblig.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/driver-api/usb/anchors.rst | 11 -----------
 drivers/usb/core/urb.c                   | 29 +++--------------------------
 include/linux/usb.h                      |  1 -
 3 files changed, 3 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/usb/anchors.rst b/Documentation/driver-api/usb/anchors.rst
index 4b248e691bd6..5a93d171e76c 100644
--- a/Documentation/driver-api/usb/anchors.rst
+++ b/Documentation/driver-api/usb/anchors.rst
@@ -45,17 +45,6 @@ This function kills all URBs associated with an anchor. The URBs
 are called in the reverse temporal order they were submitted.
 This way no data can be reordered.
 
-:c:func:`usb_unlink_anchored_urbs`
-----------------------------------
-
-
-This function unlinks all URBs associated with an anchor. The URBs
-are processed in the reverse temporal order they were submitted.
-This is similar to :c:func:`usb_kill_anchored_urbs`, but it will not sleep.
-Therefore no guarantee is made that the URBs have been unlinked when
-the call returns. They may be unlinked later but will be unlinked in
-finite time.
-
 :c:func:`usb_scuttle_anchored_urbs`
 -----------------------------------
 
diff --git a/drivers/usb/core/urb.c b/drivers/usb/core/urb.c
index 5e52a35486af..0e58a8531d6e 100644
--- a/drivers/usb/core/urb.c
+++ b/drivers/usb/core/urb.c
@@ -597,10 +597,9 @@ EXPORT_SYMBOL_GPL(usb_submit_urb);
  * code).
  *
  * Drivers should not call this routine or related routines, such as
- * usb_kill_urb() or usb_unlink_anchored_urbs(), after their disconnect
- * method has returned.  The disconnect function should synchronize with
- * a driver's I/O routines to insure that all URB-related activity has
- * completed before it returns.
+ * usb_kill_urb(), after their disconnect method has returned. The
+ * disconnect function should synchronize with a driver's I/O routines
+ * to insure that all URB-related activity has completed before it returns.
  *
  * This request is asynchronous, however the HCD might call the ->complete()
  * callback during unlink. Therefore when drivers call usb_unlink_urb(), they
@@ -890,28 +889,6 @@ void usb_unpoison_anchored_urbs(struct usb_anchor *anchor)
 	spin_unlock_irqrestore(&anchor->lock, flags);
 }
 EXPORT_SYMBOL_GPL(usb_unpoison_anchored_urbs);
-/**
- * usb_unlink_anchored_urbs - asynchronously cancel transfer requests en masse
- * @anchor: anchor the requests are bound to
- *
- * this allows all outstanding URBs to be unlinked starting
- * from the back of the queue. This function is asynchronous.
- * The unlinking is just triggered. It may happen after this
- * function has returned.
- *
- * This routine should not be called by a driver after its disconnect
- * method has returned.
- */
-void usb_unlink_anchored_urbs(struct usb_anchor *anchor)
-{
-	struct urb *victim;
-
-	while ((victim = usb_get_from_anchor(anchor)) != NULL) {
-		usb_unlink_urb(victim);
-		usb_put_urb(victim);
-	}
-}
-EXPORT_SYMBOL_GPL(usb_unlink_anchored_urbs);
 
 /**
  * usb_anchor_suspend_wakeups
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 1b2545b4363b..e8662843e68c 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1780,7 +1780,6 @@ extern void usb_block_urb(struct urb *urb);
 extern void usb_kill_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_poison_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_unpoison_anchored_urbs(struct usb_anchor *anchor);
-extern void usb_unlink_anchored_urbs(struct usb_anchor *anchor);
 extern void usb_anchor_suspend_wakeups(struct usb_anchor *anchor);
 extern void usb_anchor_resume_wakeups(struct usb_anchor *anchor);
 extern void usb_anchor_urb(struct urb *urb, struct usb_anchor *anchor);
-- 
cgit v1.2.3


From 78c76554c6b94dfa5e101b870f0c57b6c230503e Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Sat, 14 Jun 2025 20:56:43 +0800
Subject: usb: chipidea: udc: add CI_HDRC_CONTROLLER_PULLUP_EVENT event

The device controller will send CI_HDRC_CONTROLLER_PULLUP_EVENT event
when it's going to pullup or pulldown data line.

Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Acked-by: Peter Chen <peter.chen@kernel.org>
Link: https://lore.kernel.org/r/20250614125645.207732-2-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/chipidea/udc.c   | 5 +++++
 include/linux/usb/chipidea.h | 1 +
 2 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/usb/chipidea/udc.c b/drivers/usb/chipidea/udc.c
index 8a9b31fd5c89..8ec9817d3311 100644
--- a/drivers/usb/chipidea/udc.c
+++ b/drivers/usb/chipidea/udc.c
@@ -1970,6 +1970,11 @@ static int ci_udc_pullup(struct usb_gadget *_gadget, int is_on)
 		hw_write(ci, OP_USBCMD, USBCMD_RS, USBCMD_RS);
 	else
 		hw_write(ci, OP_USBCMD, USBCMD_RS, 0);
+
+	if (ci->platdata->notify_event) {
+		_gadget->connected = is_on;
+		ci->platdata->notify_event(ci, CI_HDRC_CONTROLLER_PULLUP_EVENT);
+	}
 	pm_runtime_put_sync(ci->dev);
 
 	return 0;
diff --git a/include/linux/usb/chipidea.h b/include/linux/usb/chipidea.h
index ebdfef124b2b..e17ebeee24e3 100644
--- a/include/linux/usb/chipidea.h
+++ b/include/linux/usb/chipidea.h
@@ -72,6 +72,7 @@ struct ci_hdrc_platform_data {
 #define CI_HDRC_IMX_HSIC_ACTIVE_EVENT		2
 #define CI_HDRC_IMX_HSIC_SUSPEND_EVENT		3
 #define CI_HDRC_CONTROLLER_VBUS_EVENT		4
+#define CI_HDRC_CONTROLLER_PULLUP_EVENT		5
 	int	(*notify_event) (struct ci_hdrc *ci, unsigned event);
 	struct regulator	*reg_vbus;
 	struct usb_otg_caps	ci_otg_caps;
-- 
cgit v1.2.3


From 48ea23115887c12e53335ca2eddc0d0e3d99e5d9 Mon Sep 17 00:00:00 2001
From: RubenKelevra <rubenkelevra@gmail.com>
Date: Wed, 18 Jun 2025 18:47:43 +0200
Subject: include: fsl_devices.h: drop unused, misspelled
 FLS_USB2_WORKAROUND_ENGCM09152

The macro was introduced in commit 69cb1ec4ce4d ("mxc_udc: add
workaround for ENGcm09152 for i.MX35") on 2010-10-15, but its prefix was
misspelled as **FLS_** instead of the usual **FSL_**.

Its last in-tree user disappeared with commit a390bef7db1f ("usb:
gadget: fsl_mxc_udc: Remove the driver") on 2020-12-10, so the macro has
been completely unused since then.

Remove the dead and wrongly named definition.

Signed-off-by: RubenKelevra <rubenkelevra@gmail.com>
Link: https://lore.kernel.org/r/20250618164743.1916838-1-rubenkelevra@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/fsl_devices.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fsl_devices.h b/include/linux/fsl_devices.h
index 5d231ce8709b..49f20c2f99bf 100644
--- a/include/linux/fsl_devices.h
+++ b/include/linux/fsl_devices.h
@@ -118,7 +118,6 @@ struct fsl_usb2_platform_data {
 #define FSL_USB2_PORT0_ENABLED	0x00000001
 #define FSL_USB2_PORT1_ENABLED	0x00000002
 
-#define FLS_USB2_WORKAROUND_ENGCM09152	(1 << 0)
 
 struct spi_device;
 
-- 
cgit v1.2.3


From 3b18405763c1ebb1efc15feef5563c9cdb2cc3a7 Mon Sep 17 00:00:00 2001
From: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Date: Wed, 11 Jun 2025 14:14:15 +0300
Subject: usb: acpi: fix device link removal

The device link to the USB4 host interface has to be removed
manually since it's no longer auto removed.

Fixes: 623dae3e7084 ("usb: acpi: fix boot hang due to early incorrect 'tunneled' USB3 device links")
Cc: stable <stable@kernel.org>
Signed-off-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Reviewed-by: Mika Westerberg <mika.westerberg@linux.intel.com>
Link: https://lore.kernel.org/r/20250611111415.2707865-1-heikki.krogerus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hub.c      | 3 +++
 drivers/usb/core/usb-acpi.c | 4 +++-
 include/linux/usb.h         | 2 ++
 3 files changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/hub.c b/drivers/usb/core/hub.c
index 5c12dfdef569..6bb6e92cb0a4 100644
--- a/drivers/usb/core/hub.c
+++ b/drivers/usb/core/hub.c
@@ -2368,6 +2368,9 @@ void usb_disconnect(struct usb_device **pdev)
 	usb_remove_ep_devs(&udev->ep0);
 	usb_unlock_device(udev);
 
+	if (udev->usb4_link)
+		device_link_del(udev->usb4_link);
+
 	/* Unregister the device.  The device driver is responsible
 	 * for de-configuring the device and invoking the remove-device
 	 * notifier chain (used by usbfs and possibly others).
diff --git a/drivers/usb/core/usb-acpi.c b/drivers/usb/core/usb-acpi.c
index ea1ce8beb0cb..489dbdc96f94 100644
--- a/drivers/usb/core/usb-acpi.c
+++ b/drivers/usb/core/usb-acpi.c
@@ -157,7 +157,7 @@ EXPORT_SYMBOL_GPL(usb_acpi_set_power_state);
  */
 static int usb_acpi_add_usb4_devlink(struct usb_device *udev)
 {
-	const struct device_link *link;
+	struct device_link *link;
 	struct usb_port *port_dev;
 	struct usb_hub *hub;
 
@@ -188,6 +188,8 @@ static int usb_acpi_add_usb4_devlink(struct usb_device *udev)
 	dev_dbg(&port_dev->dev, "Created device link from %s to %s\n",
 		dev_name(&port_dev->child->dev), dev_name(nhi_fwnode->dev));
 
+	udev->usb4_link = link;
+
 	return 0;
 }
 
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 1b2545b4363b..92c752f5446f 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -614,6 +614,7 @@ struct usb3_lpm_parameters {
  *	FIXME -- complete doc
  * @authenticated: Crypto authentication passed
  * @tunnel_mode: Connection native or tunneled over USB4
+ * @usb4_link: device link to the USB4 host interface
  * @lpm_capable: device supports LPM
  * @lpm_devinit_allow: Allow USB3 device initiated LPM, exit latency is in range
  * @usb2_hw_lpm_capable: device can perform USB2 hardware LPM
@@ -724,6 +725,7 @@ struct usb_device {
 	unsigned reset_resume:1;
 	unsigned port_is_suspended:1;
 	enum usb_link_tunnel_mode tunnel_mode;
+	struct device_link *usb4_link;
 
 	int slot_id;
 	struct usb2_lpm_parameters l1_params;
-- 
cgit v1.2.3


From d574c5dc8cfe1fd1ddda6edb435f3b3f39155c52 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 8 Jun 2025 16:46:54 +0100
Subject: serial: Remove unused uart_get_console

uart_get_console() has been unused since 2019's
commit bd0d9d159988 ("serial: remove ks8695 driver")

Remove it, and it's associated docs.

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Jiri Slaby <jirislaby@kernel.org>
Link: https://lore.kernel.org/r/20250608154654.73994-1-linux@treblig.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/driver-api/serial/driver.rst |  7 +++----
 drivers/tty/serial/serial_core.c           | 27 ---------------------------
 include/linux/serial_core.h                |  2 --
 3 files changed, 3 insertions(+), 33 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/serial/driver.rst b/Documentation/driver-api/serial/driver.rst
index fa1ebfcd4472..c1db6a1a67c4 100644
--- a/Documentation/driver-api/serial/driver.rst
+++ b/Documentation/driver-api/serial/driver.rst
@@ -24,9 +24,8 @@ console support.
 Console Support
 ---------------
 
-The serial core provides a few helper functions.  This includes identifying
-the correct port structure (via uart_get_console()) and decoding command line
-arguments (uart_parse_options()).
+The serial core provides a few helper functions.  This includes
+decoding command line arguments (uart_parse_options()).
 
 There is also a helper function (uart_console_write()) which performs a
 character by character write, translating newlines to CRLF sequences.
@@ -76,7 +75,7 @@ Other functions
            uart_add_one_port uart_remove_one_port uart_console_write
            uart_parse_earlycon uart_parse_options uart_set_options
            uart_get_lsr_info uart_handle_dcd_change uart_handle_cts_change
-           uart_try_toggle_sysrq uart_get_console
+           uart_try_toggle_sysrq
 
 .. kernel-doc:: include/linux/serial_core.h
    :identifiers: uart_port_tx_limited uart_port_tx
diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
index d6485714eb0f..de23e45f55e5 100644
--- a/drivers/tty/serial/serial_core.c
+++ b/drivers/tty/serial/serial_core.c
@@ -2131,33 +2131,6 @@ void uart_console_write(struct uart_port *port, const char *s,
 }
 EXPORT_SYMBOL_GPL(uart_console_write);
 
-/**
- * uart_get_console - get uart port for console
- * @ports: ports to search in
- * @nr: number of @ports
- * @co: console to search for
- * Returns: uart_port for the console @co
- *
- * Check whether an invalid uart number has been specified (as @co->index), and
- * if so, search for the first available port that does have console support.
- */
-struct uart_port * __init
-uart_get_console(struct uart_port *ports, int nr, struct console *co)
-{
-	int idx = co->index;
-
-	if (idx < 0 || idx >= nr || (ports[idx].iobase == 0 &&
-				     ports[idx].membase == NULL))
-		for (idx = 0; idx < nr; idx++)
-			if (ports[idx].iobase != 0 ||
-			    ports[idx].membase != NULL)
-				break;
-
-	co->index = idx;
-
-	return ports + idx;
-}
-
 /**
  * uart_parse_earlycon - Parse earlycon options
  * @p:	     ptr to 2nd field (ie., just beyond '<name>,')
diff --git a/include/linux/serial_core.h b/include/linux/serial_core.h
index d65b15449cfe..84b4648ead7e 100644
--- a/include/linux/serial_core.h
+++ b/include/linux/serial_core.h
@@ -1101,8 +1101,6 @@ static inline bool uart_console_registered(struct uart_port *port)
 	return uart_console(port) && console_is_registered(port->cons);
 }
 
-struct uart_port *uart_get_console(struct uart_port *ports, int nr,
-				   struct console *c);
 int uart_parse_earlycon(char *p, enum uart_iotype *iotype,
 			resource_size_t *addr, char **options);
 void uart_parse_options(const char *options, int *baud, int *parity, int *bits,
-- 
cgit v1.2.3


From f12b45862c4dcb9c2937b83ed730e473b9a76cbf Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 19 May 2025 10:33:19 +0200
Subject: timekeeping: Introduce timekeeper ID

As long as there is only a single timekeeper, there is no need to clarify
which timekeeper is used. But with the upcoming reusage of the timekeeper
infrastructure for auxiliary clock timekeepers, an ID is required to
differentiate.

Introduce an enum for timekeeper IDs, introduce a field in struct tk_data
to store this timekeeper id and add also initialization. The id struct
field is added at the end of the second cachline, as there is a 4 byte hole
anyway.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/all/20250519083025.842476378@linutronix.de
---
 include/linux/timekeeper_internal.h | 14 +++++++++++++-
 kernel/time/timekeeping.c           |  5 +++--
 2 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 785048a3b3e6..bfcecad0e279 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -11,6 +11,16 @@
 #include <linux/jiffies.h>
 #include <linux/time.h>
 
+/**
+ * timekeeper_ids - IDs for various time keepers in the kernel
+ * @TIMEKEEPER_CORE:	The central core timekeeper managing system time
+ * @TIMEKEEPERS_MAX:	The maximum number of timekeepers managed
+ */
+enum timekeeper_ids {
+	TIMEKEEPER_CORE,
+	TIMEKEEPERS_MAX,
+};
+
 /**
  * struct tk_read_base - base structure for timekeeping readout
  * @clock:	Current clocksource used for timekeeping.
@@ -52,6 +62,7 @@ struct tk_read_base {
  * @offs_boot:			Offset clock monotonic -> clock boottime
  * @offs_tai:			Offset clock monotonic -> clock tai
  * @coarse_nsec:		The nanoseconds part for coarse time getters
+ * @id:				The timekeeper ID
  * @tkr_raw:			The readout base structure for CLOCK_MONOTONIC_RAW
  * @raw_sec:			CLOCK_MONOTONIC_RAW  time in seconds
  * @clock_was_set_seq:		The sequence number of clock was set events
@@ -101,7 +112,7 @@ struct tk_read_base {
  * which results in the following cacheline layout:
  *
  * 0:	seqcount, tkr_mono
- * 1:	xtime_sec ... coarse_nsec
+ * 1:	xtime_sec ... id
  * 2:	tkr_raw, raw_sec
  * 3,4: Internal variables
  *
@@ -123,6 +134,7 @@ struct timekeeper {
 	ktime_t			offs_boot;
 	ktime_t			offs_tai;
 	u32			coarse_nsec;
+	enum timekeeper_ids	id;
 
 	/* Cacheline 2: */
 	struct tk_read_base	tkr_raw;
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index fb1da87a92f1..f4692fc2ea6b 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1663,10 +1663,11 @@ read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
 	*boot_offset = ns_to_timespec64(local_clock());
 }
 
-static __init void tkd_basic_setup(struct tk_data *tkd)
+static __init void tkd_basic_setup(struct tk_data *tkd, enum timekeeper_ids tk_id)
 {
 	raw_spin_lock_init(&tkd->lock);
 	seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock);
+	tkd->timekeeper.id = tkd->shadow_timekeeper.id = tk_id;
 }
 
 /*
@@ -1696,7 +1697,7 @@ void __init timekeeping_init(void)
 	struct timekeeper *tks = &tk_core.shadow_timekeeper;
 	struct clocksource *clock;
 
-	tkd_basic_setup(&tk_core);
+	tkd_basic_setup(&tk_core, TIMEKEEPER_CORE);
 
 	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
 	if (timespec64_valid_settod(&wall_time) &&
-- 
cgit v1.2.3


From 9094c72c3d81bf2416b7c79d12c8494ab8fbac20 Mon Sep 17 00:00:00 2001
From: Anna-Maria Behnsen <anna-maria@linutronix.de>
Date: Mon, 19 May 2025 10:33:20 +0200
Subject: time: Introduce auxiliary POSIX clocks

To support auxiliary timekeeping and the related user space interfaces,
it's required to define a clock ID range for them.

Reserve 8 auxiliary clock IDs after the regular timekeeping clock ID space.

This is the maximum number of auxiliary clocks the kernel can support. The actual
number of supported clocks depends obviously on the presence of related devices
and might be constraint by the available VDSO space.

Add the corresponding timekeeper IDs as well.

Signed-off-by: Anna-Maria Behnsen <anna-maria@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/all/20250519083025.905800695@linutronix.de
---
 include/linux/timekeeper_internal.h | 10 ++++++++--
 include/uapi/linux/time.h           | 11 +++++++++++
 kernel/time/Kconfig                 | 15 +++++++++++++--
 3 files changed, 32 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index bfcecad0e279..4201ae818f57 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -13,11 +13,17 @@
 
 /**
  * timekeeper_ids - IDs for various time keepers in the kernel
- * @TIMEKEEPER_CORE:	The central core timekeeper managing system time
- * @TIMEKEEPERS_MAX:	The maximum number of timekeepers managed
+ * @TIMEKEEPER_CORE:		The central core timekeeper managing system time
+ * @TIMEKEEPER_AUX_FIRST:	The first AUX timekeeper
+ * @TIMEKEEPER_AUX_LAST:	The last AUX timekeeper
+ * @TIMEKEEPERS_MAX:		The maximum number of timekeepers managed
  */
 enum timekeeper_ids {
 	TIMEKEEPER_CORE,
+#ifdef CONFIG_POSIX_AUX_CLOCKS
+	TIMEKEEPER_AUX_FIRST,
+	TIMEKEEPER_AUX_LAST = TIMEKEEPER_AUX_FIRST + MAX_AUX_CLOCKS - 1,
+#endif
 	TIMEKEEPERS_MAX,
 };
 
diff --git a/include/uapi/linux/time.h b/include/uapi/linux/time.h
index 4f4b6e48e01c..16ca1ac206fd 100644
--- a/include/uapi/linux/time.h
+++ b/include/uapi/linux/time.h
@@ -64,6 +64,17 @@ struct timezone {
 #define CLOCK_TAI			11
 
 #define MAX_CLOCKS			16
+
+/*
+ * AUX clock support. AUXiliary clocks are dynamically configured by
+ * enabling a clock ID. These clock can be steered independently of the
+ * core timekeeper. The kernel can support up to 8 auxiliary clocks, but
+ * the actual limit depends on eventual architecture constraints vs. VDSO.
+ */
+#define CLOCK_AUX			MAX_CLOCKS
+#define MAX_AUX_CLOCKS			8
+#define CLOCK_AUX_LAST			(CLOCK_AUX + MAX_AUX_CLOCKS - 1)
+
 #define CLOCKS_MASK			(CLOCK_REALTIME | CLOCK_MONOTONIC)
 #define CLOCKS_MONO			CLOCK_MONOTONIC
 
diff --git a/kernel/time/Kconfig b/kernel/time/Kconfig
index b0b97a60aaa6..7c6a52f7836c 100644
--- a/kernel/time/Kconfig
+++ b/kernel/time/Kconfig
@@ -82,9 +82,9 @@ config CONTEXT_TRACKING_IDLE
 	help
 	  Tracks idle state on behalf of RCU.
 
-if GENERIC_CLOCKEVENTS
 menu "Timers subsystem"
 
+if GENERIC_CLOCKEVENTS
 # Core internal switch. Selected by NO_HZ_COMMON / HIGH_RES_TIMERS. This is
 # only related to the tick functionality. Oneshot clockevent devices
 # are supported independent of this.
@@ -208,6 +208,17 @@ config CLOCKSOURCE_WATCHDOG_MAX_SKEW_US
 	  interval and NTP's maximum frequency drift of 500 parts
 	  per million.	If the clocksource is good enough for NTP,
 	  it is good enough for the clocksource watchdog!
+endif
+
+config POSIX_AUX_CLOCKS
+	bool "Enable auxiliary POSIX clocks"
+	depends on POSIX_TIMERS
+	help
+	  Auxiliary POSIX clocks are clocks which can be steered
+	  independently of the core timekeeper, which controls the
+	  MONOTONIC, REALTIME, BOOTTIME and TAI clocks.  They are useful to
+	  provide e.g. lockless time accessors to independent PTP clocks
+	  and other clock domains, which are not correlated to the TAI/NTP
+	  notion of time.
 
 endmenu
-endif
-- 
cgit v1.2.3


From 6168024604236cb2bb1004ea8459c8ece2c4ef5f Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 19 May 2025 10:33:27 +0200
Subject: timekeeping: Add clock_valid flag to timekeeper

In preparation for supporting independent auxiliary timekeepers, add a
clock valid field and set it to true for the system timekeeper.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/all/20250519083026.287145536@linutronix.de
---
 include/linux/timekeeper_internal.h | 2 ++
 kernel/time/timekeeping.c           | 5 +++--
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 4201ae818f57..1690eda1c7c3 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -73,6 +73,7 @@ struct tk_read_base {
  * @raw_sec:			CLOCK_MONOTONIC_RAW  time in seconds
  * @clock_was_set_seq:		The sequence number of clock was set events
  * @cs_was_changed_seq:		The sequence number of clocksource change events
+ * @clock_valid:		Indicator for valid clock
  * @monotonic_to_boot:		CLOCK_MONOTONIC to CLOCK_BOOTTIME offset
  * @cycle_interval:		Number of clock cycles in one NTP interval
  * @xtime_interval:		Number of clock shifted nano seconds in one NTP
@@ -149,6 +150,7 @@ struct timekeeper {
 	/* Cachline 3 and 4 (timekeeping internal variables): */
 	unsigned int		clock_was_set_seq;
 	u8			cs_was_changed_seq;
+	u8			clock_valid;
 
 	struct timespec64	monotonic_to_boot;
 
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index e3c1a1c1d8c5..bf59bacc97db 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1665,11 +1665,12 @@ read_persistent_wall_and_boot_offset(struct timespec64 *wall_time,
 	*boot_offset = ns_to_timespec64(local_clock());
 }
 
-static __init void tkd_basic_setup(struct tk_data *tkd, enum timekeeper_ids tk_id)
+static __init void tkd_basic_setup(struct tk_data *tkd, enum timekeeper_ids tk_id, bool valid)
 {
 	raw_spin_lock_init(&tkd->lock);
 	seqcount_raw_spinlock_init(&tkd->seq, &tkd->lock);
 	tkd->timekeeper.id = tkd->shadow_timekeeper.id = tk_id;
+	tkd->timekeeper.clock_valid = tkd->shadow_timekeeper.clock_valid = valid;
 }
 
 /*
@@ -1699,7 +1700,7 @@ void __init timekeeping_init(void)
 	struct timekeeper *tks = &tk_core.shadow_timekeeper;
 	struct clocksource *clock;
 
-	tkd_basic_setup(&tk_core, TIMEKEEPER_CORE);
+	tkd_basic_setup(&tk_core, TIMEKEEPER_CORE, true);
 
 	read_persistent_wall_and_boot_offset(&wall_time, &boot_offset);
 	if (timespec64_valid_settod(&wall_time) &&
-- 
cgit v1.2.3


From 75215c972581d3934e76a57690cf838d7ceab399 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 18 Jun 2025 22:53:38 +0200
Subject: pidfs: move to anonymous struct

Move the pidfs entries to an anonymous struct.

Link: https://lore.kernel.org/20250618-work-pidfs-persistent-v2-4-98f3456fd552@kernel.org
Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/pid.h | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pid.h b/include/linux/pid.h
index 453ae6d8a68d..00646a692dd4 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -52,14 +52,15 @@ struct upid {
 	struct pid_namespace *ns;
 };
 
-struct pid
-{
+struct pid {
 	refcount_t count;
 	unsigned int level;
 	spinlock_t lock;
-	struct dentry *stashed;
-	u64 ino;
-	struct rb_node pidfs_node;
+	struct {
+		u64 ino;
+		struct rb_node pidfs_node;
+		struct dentry *stashed;
+	};
 	/* lists of tasks that use this pid */
 	struct hlist_head tasks[PIDTYPE_MAX];
 	struct hlist_head inodes;
-- 
cgit v1.2.3


From 8ec7c826d97b390879df2a03dfb035c70af86779 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 18 Jun 2025 22:53:39 +0200
Subject: pidfs: persist information

Persist exit and coredump information independent of whether anyone
currently holds a pidfd for the struct pid.

The current scheme allocated pidfs dentries on-demand repeatedly.
This scheme is reaching it's limits as it makes it impossible to pin
information that needs to be available after the task has exited or
coredumped and that should not be lost simply because the pidfd got
closed temporarily. The next opener should still see the stashed
information.

This is also a prerequisite for supporting extended attributes on
pidfds to allow attaching meta information to them.

If someone opens a pidfd for a struct pid a pidfs dentry is allocated
and stashed in pid->stashed. Once the last pidfd for the struct pid is
closed the pidfs dentry is released and removed from pid->stashed.

So if 10 callers create a pidfs dentry for the same struct pid
sequentially, i.e., each closing the pidfd before the other creates a
new one then a new pidfs dentry is allocated every time.

Because multiple tasks acquiring and releasing a pidfd for the same
struct pid can race with each another a task may still find a valid
pidfs entry from the previous task in pid->stashed and reuse it. Or it
might find a dead dentry in there and fail to reuse it and so stashes a
new pidfs dentry. Multiple tasks may race to stash a new pidfs dentry
but only one will succeed, the other ones will put their dentry.

The current scheme aims to ensure that a pidfs dentry for a struct pid
can only be created if the task is still alive or if a pidfs dentry
already existed before the task was reaped and so exit information has
been was stashed in the pidfs inode.

That's great except that it's buggy. If a pidfs dentry is stashed in
pid->stashed after pidfs_exit() but before __unhash_process() is called
we will return a pidfd for a reaped task without exit information being
available.

The pidfds_pid_valid() check does not guard against this race as it
doens't sync at all with pidfs_exit(). The pid_has_task() check might be
successful simply because we're before __unhash_process() but after
pidfs_exit().

Introduce a new scheme where the lifetime of information associated with
a pidfs entry (coredump and exit information) isn't bound to the
lifetime of the pidfs inode but the struct pid itself.

The first time a pidfs dentry is allocated for a struct pid a struct
pidfs_attr will be allocated which will be used to store exit and
coredump information.

If all pidfs for the pidfs dentry are closed the dentry and inode can be
cleaned up but the struct pidfs_attr will stick until the struct pid
itself is freed. This will ensure minimal memory usage while persisting
relevant information.

The new scheme has various advantages. First, it allows to close the
race where we end up handing out a pidfd for a reaped task for which no
exit information is available. Second, it minimizes memory usage.
Third, it allows to remove complex lifetime tracking via dentries when
registering a struct pid with pidfs. There's no need to get or put a
reference. Instead, the lifetime of exit and coredump information
associated with a struct pid is bound to the lifetime of struct pid
itself.

Link: https://lore.kernel.org/20250618-work-pidfs-persistent-v2-5-98f3456fd552@kernel.org
Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/pidfs.c            | 212 ++++++++++++++++++++++++++++++++++----------------
 include/linux/pid.h   |   3 +
 include/linux/pidfs.h |   1 +
 kernel/pid.c          |   2 +-
 4 files changed, 151 insertions(+), 67 deletions(-)

(limited to 'include/linux')

diff --git a/fs/pidfs.c b/fs/pidfs.c
index ff2560b34ed1..6a907457b1fe 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -25,7 +25,10 @@
 #include "internal.h"
 #include "mount.h"
 
+#define PIDFS_PID_DEAD ERR_PTR(-ESRCH)
+
 static struct kmem_cache *pidfs_cachep __ro_after_init;
+static struct kmem_cache *pidfs_attr_cachep __ro_after_init;
 
 /*
  * Stashes information that userspace needs to access even after the
@@ -37,6 +40,11 @@ struct pidfs_exit_info {
 	__u32 coredump_mask;
 };
 
+struct pidfs_attr {
+	struct pidfs_exit_info __pei;
+	struct pidfs_exit_info *exit_info;
+};
+
 struct pidfs_inode {
 	struct pidfs_exit_info __pei;
 	struct pidfs_exit_info *exit_info;
@@ -125,6 +133,7 @@ void pidfs_add_pid(struct pid *pid)
 
 	pid->ino = pidfs_ino_nr;
 	pid->stashed = NULL;
+	pid->attr = NULL;
 	pidfs_ino_nr++;
 
 	write_seqcount_begin(&pidmap_lock_seq);
@@ -139,6 +148,18 @@ void pidfs_remove_pid(struct pid *pid)
 	write_seqcount_end(&pidmap_lock_seq);
 }
 
+void pidfs_free_pid(struct pid *pid)
+{
+	/*
+	 * Any dentry must've been wiped from the pid by now.
+	 * Otherwise there's a reference count bug.
+	 */
+	VFS_WARN_ON_ONCE(pid->stashed);
+
+	if (!IS_ERR(pid->attr))
+		kfree(pid->attr);
+}
+
 #ifdef CONFIG_PROC_FS
 /**
  * pidfd_show_fdinfo - print information about a pidfd
@@ -261,13 +282,13 @@ static __u32 pidfs_coredump_mask(unsigned long mm_flags)
 static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 {
 	struct pidfd_info __user *uinfo = (struct pidfd_info __user *)arg;
-	struct inode *inode = file_inode(file);
 	struct pid *pid = pidfd_pid(file);
 	size_t usize = _IOC_SIZE(cmd);
 	struct pidfd_info kinfo = {};
 	struct pidfs_exit_info *exit_info;
 	struct user_namespace *user_ns;
 	struct task_struct *task;
+	struct pidfs_attr *attr;
 	const struct cred *c;
 	__u64 mask;
 
@@ -286,8 +307,9 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 	if (!pid_in_current_pidns(pid))
 		return -ESRCH;
 
+	attr = READ_ONCE(pid->attr);
 	if (mask & PIDFD_INFO_EXIT) {
-		exit_info = READ_ONCE(pidfs_i(inode)->exit_info);
+		exit_info = READ_ONCE(attr->exit_info);
 		if (exit_info) {
 			kinfo.mask |= PIDFD_INFO_EXIT;
 #ifdef CONFIG_CGROUPS
@@ -300,7 +322,7 @@ static long pidfd_info(struct file *file, unsigned int cmd, unsigned long arg)
 
 	if (mask & PIDFD_INFO_COREDUMP) {
 		kinfo.mask |= PIDFD_INFO_COREDUMP;
-		kinfo.coredump_mask = READ_ONCE(pidfs_i(inode)->__pei.coredump_mask);
+		kinfo.coredump_mask = READ_ONCE(attr->__pei.coredump_mask);
 	}
 
 	task = get_pid_task(pid, PIDTYPE_PID);
@@ -552,41 +574,61 @@ struct pid *pidfd_pid(const struct file *file)
  * task has been reaped which cannot happen until we're out of
  * release_task().
  *
- * If this struct pid is referred to by a pidfd then
- * stashed_dentry_get() will return the dentry and inode for that struct
- * pid. Since we've taken a reference on it there's now an additional
- * reference from the exit path on it. Which is fine. We're going to put
- * it again in a second and we know that the pid is kept alive anyway.
+ * If this struct pid has at least once been referred to by a pidfd then
+ * pid->attr will be allocated. If not we mark the struct pid as dead so
+ * anyone who is trying to register it with pidfs will fail to do so.
+ * Otherwise we would hand out pidfs for reaped tasks without having
+ * exit information available.
  *
- * Worst case is that we've filled in the info and immediately free the
- * dentry and inode afterwards since the pidfd has been closed. Since
+ * Worst case is that we've filled in the info and the pid gets freed
+ * right away in free_pid() when no one holds a pidfd anymore. Since
  * pidfs_exit() currently is placed after exit_task_work() we know that
- * it cannot be us aka the exiting task holding a pidfd to ourselves.
+ * it cannot be us aka the exiting task holding a pidfd to itself.
  */
 void pidfs_exit(struct task_struct *tsk)
 {
-	struct dentry *dentry;
+	struct pid *pid = task_pid(tsk);
+	struct pidfs_attr *attr;
+	struct pidfs_exit_info *exit_info;
+#ifdef CONFIG_CGROUPS
+	struct cgroup *cgrp;
+#endif
 
 	might_sleep();
 
-	dentry = stashed_dentry_get(&task_pid(tsk)->stashed);
-	if (dentry) {
-		struct inode *inode = d_inode(dentry);
-		struct pidfs_exit_info *exit_info = &pidfs_i(inode)->__pei;
-#ifdef CONFIG_CGROUPS
-		struct cgroup *cgrp;
+	guard(spinlock_irq)(&pid->wait_pidfd.lock);
+	attr = pid->attr;
+	if (!attr) {
+		/*
+		 * No one ever held a pidfd for this struct pid.
+		 * Mark it as dead so no one can add a pidfs
+		 * entry anymore. We're about to be reaped and
+		 * so no exit information would be available.
+		 */
+		pid->attr = PIDFS_PID_DEAD;
+		return;
+	}
 
-		rcu_read_lock();
-		cgrp = task_dfl_cgroup(tsk);
-		exit_info->cgroupid = cgroup_id(cgrp);
-		rcu_read_unlock();
+	/*
+	 * If @pid->attr is set someone might still legitimately hold a
+	 * pidfd to @pid or someone might concurrently still be getting
+	 * a reference to an already stashed dentry from @pid->stashed.
+	 * So defer cleaning @pid->attr until the last reference to @pid
+	 * is put
+	 */
+
+	exit_info = &attr->__pei;
+
+#ifdef CONFIG_CGROUPS
+	rcu_read_lock();
+	cgrp = task_dfl_cgroup(tsk);
+	exit_info->cgroupid = cgroup_id(cgrp);
+	rcu_read_unlock();
 #endif
-		exit_info->exit_code = tsk->exit_code;
+	exit_info->exit_code = tsk->exit_code;
 
-		/* Ensure that PIDFD_GET_INFO sees either all or nothing. */
-		smp_store_release(&pidfs_i(inode)->exit_info, &pidfs_i(inode)->__pei);
-		dput(dentry);
-	}
+	/* Ensure that PIDFD_GET_INFO sees either all or nothing. */
+	smp_store_release(&attr->exit_info, &attr->__pei);
 }
 
 #ifdef CONFIG_COREDUMP
@@ -594,16 +636,15 @@ void pidfs_coredump(const struct coredump_params *cprm)
 {
 	struct pid *pid = cprm->pid;
 	struct pidfs_exit_info *exit_info;
-	struct dentry *dentry;
-	struct inode *inode;
+	struct pidfs_attr *attr;
 	__u32 coredump_mask = 0;
 
-	dentry = pid->stashed;
-	if (WARN_ON_ONCE(!dentry))
-		return;
+	attr = READ_ONCE(pid->attr);
 
-	inode = d_inode(dentry);
-	exit_info = &pidfs_i(inode)->__pei;
+	VFS_WARN_ON_ONCE(!attr);
+	VFS_WARN_ON_ONCE(attr == PIDFS_PID_DEAD);
+
+	exit_info = &attr->__pei;
 	/* Note how we were coredumped. */
 	coredump_mask = pidfs_coredump_mask(cprm->mm_flags);
 	/* Note that we actually did coredump. */
@@ -663,7 +704,7 @@ static struct inode *pidfs_alloc_inode(struct super_block *sb)
 
 static void pidfs_free_inode(struct inode *inode)
 {
-	kmem_cache_free(pidfs_cachep, pidfs_i(inode));
+	kfree(pidfs_i(inode));
 }
 
 static const struct super_operations pidfs_sops = {
@@ -831,8 +872,13 @@ static inline bool pidfs_pid_valid(struct pid *pid, const struct path *path,
 	 * recorded and published can be handled correctly.
 	 */
 	if (unlikely(!pid_has_task(pid, type))) {
-		struct inode *inode = d_inode(path->dentry);
-		return !!READ_ONCE(pidfs_i(inode)->exit_info);
+		struct pidfs_attr *attr;
+
+		attr = READ_ONCE(pid->attr);
+		if (!attr)
+			return false;
+		if (!READ_ONCE(attr->exit_info))
+			return false;
 	}
 
 	return true;
@@ -878,9 +924,67 @@ static void pidfs_put_data(void *data)
 	put_pid(pid);
 }
 
+/**
+ * pidfs_register_pid - register a struct pid in pidfs
+ * @pid: pid to pin
+ *
+ * Register a struct pid in pidfs. Needs to be paired with
+ * pidfs_put_pid() to not risk leaking the pidfs dentry and inode.
+ *
+ * Return: On success zero, on error a negative error code is returned.
+ */
+int pidfs_register_pid(struct pid *pid)
+{
+	struct pidfs_attr *new_attr __free(kfree) = NULL;
+	struct pidfs_attr *attr;
+
+	might_sleep();
+
+	if (!pid)
+		return 0;
+
+	attr = READ_ONCE(pid->attr);
+	if (unlikely(attr == PIDFS_PID_DEAD))
+		return PTR_ERR(PIDFS_PID_DEAD);
+	if (attr)
+		return 0;
+
+	new_attr = kmem_cache_zalloc(pidfs_attr_cachep, GFP_KERNEL);
+	if (!new_attr)
+		return -ENOMEM;
+
+	/* Synchronize with pidfs_exit(). */
+	guard(spinlock_irq)(&pid->wait_pidfd.lock);
+
+	attr = pid->attr;
+	if (unlikely(attr == PIDFS_PID_DEAD))
+		return PTR_ERR(PIDFS_PID_DEAD);
+	if (unlikely(attr))
+		return 0;
+
+	pid->attr = no_free_ptr(new_attr);
+	return 0;
+}
+
+static struct dentry *pidfs_stash_dentry(struct dentry **stashed,
+					 struct dentry *dentry)
+{
+	int ret;
+	struct pid *pid = d_inode(dentry)->i_private;
+
+	VFS_WARN_ON_ONCE(stashed != &pid->stashed);
+
+	ret = pidfs_register_pid(pid);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return stash_dentry(stashed, dentry);
+}
+
 static const struct stashed_operations pidfs_stashed_ops = {
-	.init_inode = pidfs_init_inode,
-	.put_data = pidfs_put_data,
+	.stash_dentry	= pidfs_stash_dentry,
+	.init_inode	= pidfs_init_inode,
+	.put_data	= pidfs_put_data,
 };
 
 static int pidfs_init_fs_context(struct fs_context *fc)
@@ -936,33 +1040,6 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
 	return pidfd_file;
 }
 
-/**
- * pidfs_register_pid - register a struct pid in pidfs
- * @pid: pid to pin
- *
- * Register a struct pid in pidfs. Needs to be paired with
- * pidfs_put_pid() to not risk leaking the pidfs dentry and inode.
- *
- * Return: On success zero, on error a negative error code is returned.
- */
-int pidfs_register_pid(struct pid *pid)
-{
-	struct path path __free(path_put) = {};
-	int ret;
-
-	might_sleep();
-
-	if (!pid)
-		return 0;
-
-	ret = path_from_stashed(&pid->stashed, pidfs_mnt, get_pid(pid), &path);
-	if (unlikely(ret))
-		return ret;
-	/* Keep the dentry and only put the reference to the mount. */
-	path.dentry = NULL;
-	return 0;
-}
-
 /**
  * pidfs_get_pid - pin a struct pid through pidfs
  * @pid: pid to pin
@@ -1008,6 +1085,9 @@ void __init pidfs_init(void)
 					 (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT |
 					  SLAB_ACCOUNT | SLAB_PANIC),
 					 pidfs_inode_init_once);
+	pidfs_attr_cachep = kmem_cache_create("pidfs_attr_cache", sizeof(struct pidfs_attr), 0,
+					 (SLAB_HWCACHE_ALIGN | SLAB_RECLAIM_ACCOUNT |
+					  SLAB_ACCOUNT | SLAB_PANIC), NULL);
 	pidfs_mnt = kern_mount(&pidfs_type);
 	if (IS_ERR(pidfs_mnt))
 		panic("Failed to mount pidfs pseudo filesystem");
diff --git a/include/linux/pid.h b/include/linux/pid.h
index 00646a692dd4..003a1027d219 100644
--- a/include/linux/pid.h
+++ b/include/linux/pid.h
@@ -47,6 +47,8 @@
 
 #define RESERVED_PIDS 300
 
+struct pidfs_attr;
+
 struct upid {
 	int nr;
 	struct pid_namespace *ns;
@@ -60,6 +62,7 @@ struct pid {
 		u64 ino;
 		struct rb_node pidfs_node;
 		struct dentry *stashed;
+		struct pidfs_attr *attr;
 	};
 	/* lists of tasks that use this pid */
 	struct hlist_head tasks[PIDTYPE_MAX];
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
index 77e7db194914..8f6ed59bb3fb 100644
--- a/include/linux/pidfs.h
+++ b/include/linux/pidfs.h
@@ -16,5 +16,6 @@ extern const struct dentry_operations pidfs_dentry_operations;
 int pidfs_register_pid(struct pid *pid);
 void pidfs_get_pid(struct pid *pid);
 void pidfs_put_pid(struct pid *pid);
+void pidfs_free_pid(struct pid *pid);
 
 #endif /* _LINUX_PID_FS_H */
diff --git a/kernel/pid.c b/kernel/pid.c
index 8317bcbc7cf7..07db7d8d066c 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -100,7 +100,7 @@ void put_pid(struct pid *pid)
 
 	ns = pid->numbers[pid->level].ns;
 	if (refcount_dec_and_test(&pid->count)) {
-		WARN_ON_ONCE(pid->stashed);
+		pidfs_free_pid(pid);
 		kmem_cache_free(ns->pid_cachep, pid);
 		put_pid_ns(ns);
 	}
-- 
cgit v1.2.3


From 804d6794497e6f3992d156e07d01e22b037ce09e Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Wed, 18 Jun 2025 22:53:42 +0200
Subject: pidfs: remove pidfs_{get,put}_pid()

Now that we stash persistent information in struct pid there's no need
to play volatile games with pinning struct pid via dentries in pidfs.

Link: https://lore.kernel.org/20250618-work-pidfs-persistent-v2-8-98f3456fd552@kernel.org
Reviewed-by: Alexander Mikhalitsyn <aleksandr.mikhalitsyn@canonical.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/coredump.c         |  6 ------
 fs/pidfs.c            | 35 +----------------------------------
 include/linux/pidfs.h |  2 --
 net/unix/af_unix.c    |  5 -----
 4 files changed, 1 insertion(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/fs/coredump.c b/fs/coredump.c
index f217ebf2b3b6..55d6a713a0fb 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -898,12 +898,6 @@ void do_coredump(const kernel_siginfo_t *siginfo)
 		retval = kernel_connect(socket, (struct sockaddr *)(&addr),
 					addr_len, O_NONBLOCK | SOCK_COREDUMP);
 
-		/*
-		 * ... Make sure to only put our reference after connect() took
-		 * its own reference keeping the pidfs entry alive ...
-		 */
-		pidfs_put_pid(cprm.pid);
-
 		if (retval) {
 			if (retval == -EAGAIN)
 				coredump_report_failure("Coredump socket %s receive queue full", addr.sun_path);
diff --git a/fs/pidfs.c b/fs/pidfs.c
index c49c53d6ae51..bc2342cf4492 100644
--- a/fs/pidfs.c
+++ b/fs/pidfs.c
@@ -895,8 +895,7 @@ static void pidfs_put_data(void *data)
  * pidfs_register_pid - register a struct pid in pidfs
  * @pid: pid to pin
  *
- * Register a struct pid in pidfs. Needs to be paired with
- * pidfs_put_pid() to not risk leaking the pidfs dentry and inode.
+ * Register a struct pid in pidfs.
  *
  * Return: On success zero, on error a negative error code is returned.
  */
@@ -1007,38 +1006,6 @@ struct file *pidfs_alloc_file(struct pid *pid, unsigned int flags)
 	return pidfd_file;
 }
 
-/**
- * pidfs_get_pid - pin a struct pid through pidfs
- * @pid: pid to pin
- *
- * Similar to pidfs_register_pid() but only valid if the caller knows
- * there's a reference to the @pid through a dentry already that can't
- * go away.
- */
-void pidfs_get_pid(struct pid *pid)
-{
-	if (!pid)
-		return;
-	WARN_ON_ONCE(!stashed_dentry_get(&pid->stashed));
-}
-
-/**
- * pidfs_put_pid - drop a pidfs reference
- * @pid: pid to drop
- *
- * Drop a reference to @pid via pidfs. This is only safe if the
- * reference has been taken via pidfs_get_pid().
- */
-void pidfs_put_pid(struct pid *pid)
-{
-	might_sleep();
-
-	if (!pid)
-		return;
-	VFS_WARN_ON_ONCE(!pid->stashed);
-	dput(pid->stashed);
-}
-
 void __init pidfs_init(void)
 {
 	pidfs_attr_cachep = kmem_cache_create("pidfs_attr_cache", sizeof(struct pidfs_attr), 0,
diff --git a/include/linux/pidfs.h b/include/linux/pidfs.h
index 8f6ed59bb3fb..3e08c33da2df 100644
--- a/include/linux/pidfs.h
+++ b/include/linux/pidfs.h
@@ -14,8 +14,6 @@ void pidfs_coredump(const struct coredump_params *cprm);
 #endif
 extern const struct dentry_operations pidfs_dentry_operations;
 int pidfs_register_pid(struct pid *pid);
-void pidfs_get_pid(struct pid *pid);
-void pidfs_put_pid(struct pid *pid);
 void pidfs_free_pid(struct pid *pid);
 
 #endif /* _LINUX_PID_FS_H */
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 2e2e9997a68e..129388c309b0 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -646,9 +646,6 @@ static void unix_sock_destructor(struct sock *sk)
 		return;
 	}
 
-	if (sk->sk_peer_pid)
-		pidfs_put_pid(sk->sk_peer_pid);
-
 	if (u->addr)
 		unix_release_addr(u->addr);
 
@@ -769,7 +766,6 @@ static void drop_peercred(struct unix_peercred *peercred)
 	swap(peercred->peer_pid, pid);
 	swap(peercred->peer_cred, cred);
 
-	pidfs_put_pid(pid);
 	put_pid(pid);
 	put_cred(cred);
 }
@@ -802,7 +798,6 @@ static void copy_peercred(struct sock *sk, struct sock *peersk)
 
 	spin_lock(&sk->sk_peer_lock);
 	sk->sk_peer_pid = get_pid(peersk->sk_peer_pid);
-	pidfs_get_pid(sk->sk_peer_pid);
 	sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
 	spin_unlock(&sk->sk_peer_lock);
 }
-- 
cgit v1.2.3


From 180d8b4ce91fe0cf7a9cb236bb01f14587ba4bf0 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Mon, 19 May 2025 10:33:32 +0200
Subject: timekeeping: Add AUX offset to struct timekeeper

This offset will be used in the time getters of auxiliary clocks. It is
added to the "monotonic" clock readout.

As auxiliary clocks do not utilize the offset fields of the core time
keeper, this is just an alias for offs_tai, so that the cache line layout
stays the same.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/all/20250519083026.533486349@linutronix.de
---
 include/linux/timekeeper_internal.h | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index 1690eda1c7c3..ca79938b62f3 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -67,6 +67,7 @@ struct tk_read_base {
  * @offs_real:			Offset clock monotonic -> clock realtime
  * @offs_boot:			Offset clock monotonic -> clock boottime
  * @offs_tai:			Offset clock monotonic -> clock tai
+ * @offs_aux:			Offset clock monotonic -> clock AUX
  * @coarse_nsec:		The nanoseconds part for coarse time getters
  * @id:				The timekeeper ID
  * @tkr_raw:			The readout base structure for CLOCK_MONOTONIC_RAW
@@ -113,6 +114,9 @@ struct tk_read_base {
  * @monotonic_to_boottime is a timespec64 representation of @offs_boot to
  * accelerate the VDSO update for CLOCK_BOOTTIME.
  *
+ * @offs_aux is used by the auxiliary timekeepers which do not utilize any
+ * of the regular timekeeper offset fields.
+ *
  * The cacheline ordering of the structure is optimized for in kernel usage of
  * the ktime_get() and ktime_get_ts64() family of time accessors. Struct
  * timekeeper is prepended in the core timekeeping code with a sequence count,
@@ -139,7 +143,10 @@ struct timekeeper {
 	struct timespec64	wall_to_monotonic;
 	ktime_t			offs_real;
 	ktime_t			offs_boot;
-	ktime_t			offs_tai;
+	union {
+		ktime_t		offs_tai;
+		ktime_t		offs_aux;
+	};
 	u32			coarse_nsec;
 	enum timekeeper_ids	id;
 
-- 
cgit v1.2.3


From ea92128fe7f6eef6ee5fcaaed521b1b2b5ab7c9a Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Fri, 13 Jun 2025 23:35:13 -0700
Subject: iommufd: Apply obvious cosmetic fixes

Run clang-format but exclude those not so obvious ones, which leaves us:
 - Align indentations
 - Add missing spaces
 - Remove unnecessary spaces
 - Remove unnecessary line wrappings

Link: https://patch.msgid.link/r/9132e1ab45690ab1959c66bbb51ac5536a635388.1749882255.git.nicolinc@nvidia.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/device.c          |  3 +--
 drivers/iommu/iommufd/hw_pagetable.c    |  6 ++----
 drivers/iommu/iommufd/io_pagetable.c    |  3 +--
 drivers/iommu/iommufd/io_pagetable.h    |  2 +-
 drivers/iommu/iommufd/iommufd_private.h |  6 ++----
 drivers/iommu/iommufd/iova_bitmap.c     |  1 -
 drivers/iommu/iommufd/main.c            |  6 ++----
 drivers/iommu/iommufd/pages.c           |  9 ++++-----
 drivers/iommu/iommufd/selftest.c        | 24 +++++++++++-------------
 include/linux/iommufd.h                 |  5 +++--
 10 files changed, 27 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 86244403b532..ed0dc539d490 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -485,8 +485,7 @@ iommufd_device_get_attach_handle(struct iommufd_device *idev, ioasid_t pasid)
 
 	lockdep_assert_held(&idev->igroup->lock);
 
-	handle =
-		iommu_attach_handle_get(idev->igroup->group, pasid, 0);
+	handle = iommu_attach_handle_get(idev->igroup->group, pasid, 0);
 	if (IS_ERR(handle))
 		return NULL;
 	return to_iommufd_handle(handle);
diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
index 487779470261..8565a6f596b2 100644
--- a/drivers/iommu/iommufd/hw_pagetable.c
+++ b/drivers/iommu/iommufd/hw_pagetable.c
@@ -309,10 +309,8 @@ iommufd_viommu_alloc_hwpt_nested(struct iommufd_viommu *viommu, u32 flags,
 	refcount_inc(&viommu->obj.users);
 	hwpt_nested->parent = viommu->hwpt;
 
-	hwpt->domain =
-		viommu->ops->alloc_domain_nested(viommu,
-				flags & ~IOMMU_HWPT_FAULT_ID_VALID,
-				user_data);
+	hwpt->domain = viommu->ops->alloc_domain_nested(
+		viommu, flags & ~IOMMU_HWPT_FAULT_ID_VALID, user_data);
 	if (IS_ERR(hwpt->domain)) {
 		rc = PTR_ERR(hwpt->domain);
 		hwpt->domain = NULL;
diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
index 8a790e597e12..13d010f19ed1 100644
--- a/drivers/iommu/iommufd/io_pagetable.c
+++ b/drivers/iommu/iommufd/io_pagetable.c
@@ -1410,8 +1410,7 @@ out_unlock:
 }
 
 void iopt_remove_access(struct io_pagetable *iopt,
-			struct iommufd_access *access,
-			u32 iopt_access_list_id)
+			struct iommufd_access *access, u32 iopt_access_list_id)
 {
 	down_write(&iopt->domains_rwsem);
 	down_write(&iopt->iova_rwsem);
diff --git a/drivers/iommu/iommufd/io_pagetable.h b/drivers/iommu/iommufd/io_pagetable.h
index 10c928a9a463..c115a51d9384 100644
--- a/drivers/iommu/iommufd/io_pagetable.h
+++ b/drivers/iommu/iommufd/io_pagetable.h
@@ -240,7 +240,7 @@ int iopt_area_add_access(struct iopt_area *area, unsigned long start,
 			 unsigned long last, struct page **out_pages,
 			 unsigned int flags);
 void iopt_area_remove_access(struct iopt_area *area, unsigned long start,
-			    unsigned long last);
+			     unsigned long last);
 int iopt_pages_rw_access(struct iopt_pages *pages, unsigned long start_byte,
 			 void *data, unsigned long length, unsigned int flags);
 
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 9ccc83341f32..190ceb5dada3 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -266,8 +266,7 @@ struct iommufd_ioas {
 static inline struct iommufd_ioas *iommufd_get_ioas(struct iommufd_ctx *ictx,
 						    u32 id)
 {
-	return container_of(iommufd_get_object(ictx, id,
-					       IOMMUFD_OBJ_IOAS),
+	return container_of(iommufd_get_object(ictx, id, IOMMUFD_OBJ_IOAS),
 			    struct iommufd_ioas, obj);
 }
 
@@ -452,8 +451,7 @@ struct iommufd_access {
 
 int iopt_add_access(struct io_pagetable *iopt, struct iommufd_access *access);
 void iopt_remove_access(struct io_pagetable *iopt,
-			struct iommufd_access *access,
-			u32 iopt_access_list_id);
+			struct iommufd_access *access, u32 iopt_access_list_id);
 void iommufd_access_destroy_object(struct iommufd_object *obj);
 
 struct iommufd_eventq {
diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c
index 39a86a4a1d3a..4514575818fc 100644
--- a/drivers/iommu/iommufd/iova_bitmap.c
+++ b/drivers/iommu/iommufd/iova_bitmap.c
@@ -407,7 +407,6 @@ void iova_bitmap_set(struct iova_bitmap *bitmap,
 
 update_indexes:
 	if (unlikely(!iova_bitmap_mapped_range(mapped, iova, length))) {
-
 		/*
 		 * The attempt to advance the base index to @iova
 		 * may fail if it's out of bounds, or pinning the pages
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 3df468f64e7d..347c56ef44d8 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -102,9 +102,8 @@ static int iommufd_object_dec_wait_shortterm(struct iommufd_ctx *ictx,
 		return 0;
 
 	if (wait_event_timeout(ictx->destroy_wait,
-				refcount_read(&to_destroy->shortterm_users) ==
-					0,
-				msecs_to_jiffies(60000)))
+			       refcount_read(&to_destroy->shortterm_users) == 0,
+			       msecs_to_jiffies(60000)))
 		return 0;
 
 	pr_crit("Time out waiting for iommufd object to become free\n");
@@ -539,7 +538,6 @@ static struct miscdevice iommu_misc_dev = {
 	.mode = 0660,
 };
 
-
 static struct miscdevice vfio_misc_dev = {
 	.minor = VFIO_MINOR,
 	.name = "vfio",
diff --git a/drivers/iommu/iommufd/pages.c b/drivers/iommu/iommufd/pages.c
index 3427749bc5ce..cbdde642d2af 100644
--- a/drivers/iommu/iommufd/pages.c
+++ b/drivers/iommu/iommufd/pages.c
@@ -1287,8 +1287,7 @@ static int pfn_reader_first(struct pfn_reader *pfns, struct iopt_pages *pages,
 }
 
 static struct iopt_pages *iopt_alloc_pages(unsigned long start_byte,
-					   unsigned long length,
-					   bool writable)
+					   unsigned long length, bool writable)
 {
 	struct iopt_pages *pages;
 
@@ -1328,7 +1327,7 @@ struct iopt_pages *iopt_alloc_user_pages(void __user *uptr,
 	struct iopt_pages *pages;
 	unsigned long end;
 	void __user *uptr_down =
-		(void __user *) ALIGN_DOWN((uintptr_t)uptr, PAGE_SIZE);
+		(void __user *)ALIGN_DOWN((uintptr_t)uptr, PAGE_SIZE);
 
 	if (check_add_overflow((unsigned long)uptr, length, &end))
 		return ERR_PTR(-EOVERFLOW);
@@ -2111,8 +2110,8 @@ iopt_pages_get_exact_access(struct iopt_pages *pages, unsigned long index,
  * This should be undone through a matching call to iopt_area_remove_access()
  */
 int iopt_area_add_access(struct iopt_area *area, unsigned long start_index,
-			  unsigned long last_index, struct page **out_pages,
-			  unsigned int flags)
+			 unsigned long last_index, struct page **out_pages,
+			 unsigned int flags)
 {
 	struct iopt_pages *pages = area->pages;
 	struct iopt_pages_access *access;
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 6bd0abf9a641..4d5dca8027b1 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -1216,9 +1216,8 @@ static int iommufd_test_md_check_refs(struct iommufd_ucmd *ucmd,
 	return 0;
 }
 
-static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd,
-				       u32 mockpt_id, unsigned int iotlb_id,
-				       u32 iotlb)
+static int iommufd_test_md_check_iotlb(struct iommufd_ucmd *ucmd, u32 mockpt_id,
+				       unsigned int iotlb_id, u32 iotlb)
 {
 	struct mock_iommu_domain_nested *mock_nested;
 	struct iommufd_hw_pagetable *hwpt;
@@ -1491,7 +1490,7 @@ static int iommufd_test_access_pages(struct iommufd_ucmd *ucmd,
 	int rc;
 
 	/* Prevent syzkaller from triggering a WARN_ON in kvzalloc() */
-	if (length > 16*1024*1024)
+	if (length > 16 * 1024 * 1024)
 		return -ENOMEM;
 
 	if (flags & ~(MOCK_FLAGS_ACCESS_WRITE | MOCK_FLAGS_ACCESS_SYZ))
@@ -1508,7 +1507,7 @@ static int iommufd_test_access_pages(struct iommufd_ucmd *ucmd,
 
 	if (flags & MOCK_FLAGS_ACCESS_SYZ)
 		iova = iommufd_test_syz_conv_iova(staccess->access,
-					&cmd->access_pages.iova);
+						  &cmd->access_pages.iova);
 
 	npages = (ALIGN(iova + length, PAGE_SIZE) -
 		  ALIGN_DOWN(iova, PAGE_SIZE)) /
@@ -1584,7 +1583,7 @@ static int iommufd_test_access_rw(struct iommufd_ucmd *ucmd,
 	int rc;
 
 	/* Prevent syzkaller from triggering a WARN_ON in kvzalloc() */
-	if (length > 16*1024*1024)
+	if (length > 16 * 1024 * 1024)
 		return -ENOMEM;
 
 	if (flags & ~(MOCK_ACCESS_RW_WRITE | MOCK_ACCESS_RW_SLOW_PATH |
@@ -1610,7 +1609,7 @@ static int iommufd_test_access_rw(struct iommufd_ucmd *ucmd,
 
 	if (flags & MOCK_FLAGS_ACCESS_SYZ)
 		iova = iommufd_test_syz_conv_iova(staccess->access,
-				&cmd->access_rw.iova);
+						  &cmd->access_rw.iova);
 
 	rc = iommufd_access_rw(staccess->access, iova, tmp, length, flags);
 	if (rc)
@@ -1665,7 +1664,7 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
 		goto out_put;
 	}
 
-	if (copy_from_user(tmp, uptr,DIV_ROUND_UP(max, BITS_PER_BYTE))) {
+	if (copy_from_user(tmp, uptr, DIV_ROUND_UP(max, BITS_PER_BYTE))) {
 		rc = -EFAULT;
 		goto out_free;
 	}
@@ -1701,7 +1700,7 @@ out_put:
 static int iommufd_test_trigger_iopf(struct iommufd_ucmd *ucmd,
 				     struct iommu_test_cmd *cmd)
 {
-	struct iopf_fault event = { };
+	struct iopf_fault event = {};
 	struct iommufd_device *idev;
 
 	idev = iommufd_get_device(ucmd, cmd->trigger_iopf.dev_id);
@@ -1832,8 +1831,7 @@ static int iommufd_test_pasid_attach(struct iommufd_ucmd *ucmd,
 
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 	if (rc)
-		iommufd_device_detach(sobj->idev.idev,
-				      cmd->pasid_attach.pasid);
+		iommufd_device_detach(sobj->idev.idev, cmd->pasid_attach.pasid);
 
 out_sobj:
 	iommufd_put_object(ucmd->ictx, &sobj->obj);
@@ -2004,8 +2002,8 @@ int __init iommufd_test_init(void)
 		goto err_bus;
 
 	rc = iommu_device_register_bus(&mock_iommu.iommu_dev, &mock_ops,
-				  &iommufd_mock_bus_type.bus,
-				  &iommufd_mock_bus_type.nb);
+				       &iommufd_mock_bus_type.bus,
+				       &iommufd_mock_bus_type.nb);
 	if (rc)
 		goto err_sysfs;
 
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 34b6e6ca4bfa..498c9a768506 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -171,8 +171,9 @@ static inline void iommufd_access_unpin_pages(struct iommufd_access *access,
 {
 }
 
-static inline int iommufd_access_rw(struct iommufd_access *access, unsigned long iova,
-		      void *data, size_t len, unsigned int flags)
+static inline int iommufd_access_rw(struct iommufd_access *access,
+				    unsigned long iova, void *data, size_t len,
+				    unsigned int flags)
 {
 	return -EOPNOTSUPP;
 }
-- 
cgit v1.2.3


From fc9c40e3a4faa09dbd643ae1bdaf8ad006c3bc28 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Fri, 13 Jun 2025 23:35:15 -0700
Subject: iommufd: Use enum iommu_viommu_type for type in struct iommufd_viommu

Replace unsigned int, to make it clear. No functional changes.

The viommu_alloc iommu op will be deprecated, so don't change that.

Link: https://patch.msgid.link/r/6c6ba5c0cd381594f17ae74355872d78d7a022c0.1749882255.git.nicolinc@nvidia.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/iommufd.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 498c9a768506..ac98e49e44fe 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -101,7 +101,7 @@ struct iommufd_viommu {
 	struct list_head veventqs;
 	struct rw_semaphore veventqs_rwsem;
 
-	unsigned int type;
+	enum iommu_viommu_type type;
 };
 
 /**
-- 
cgit v1.2.3


From 187f146d5de65d50d90a4f49157d381d8ae32939 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Fri, 13 Jun 2025 23:35:18 -0700
Subject: iommu: Introduce get_viommu_size and viommu_init ops

So far, a vIOMMU object has been allocated by IOMMU driver and initialized
with the driver-level structure, before it returns to the iommufd core for
core-level structure initialization. It has been requiring iommufd core to
expose some core structure/helpers in its driver.c file, which result in a
size increase of this driver module.

Meanwhile, IOMMU drivers are now requiring more vIOMMU-base structures for
some advanced feature, such as the existing vDEVICE and a future HW_QUEUE.
Initializing a core-structure later than driver-structure gives for-driver
helpers some trouble, when they are used by IOMMU driver assuming that the
new structure (including core) are fully initialized, for example:

core:	viommu = ops->viommu_alloc();
driver:	// my_viommu is successfully allocated
driver:	my_viommu = iommufd_viommu_alloc(...);
driver:	// This may crash if it reads viommu->ictx
driver:	new = iommufd_new_viommu_helper(my_viommu->core ...);
core:	viommu->ictx = ucmd->ictx;
core:	...

To ease such a condition, allow the IOMMU driver to report the size of its
vIOMMU structure, let the core allocate a vIOMMU object and initialize the
core-level structure first, and then hand it over the driver to initialize
its driver-level structure.

Thus, this requires two new iommu ops, get_viommu_size and viommu_init, so
iommufd core can communicate with drivers to replace the viommu_alloc op:

core:	viommu = ops->get_viommu_size();
driver:	return VIOMMU_STRUCT_SIZE();
core:	viommu->ictx = ucmd->ictx; // and others
core:	rc = ops->viommu_init();
driver:	// This is safe now as viommu->ictx is inited
driver:	new = iommufd_new_viommu_helper(my_viommu->core ...);
core:	...

This also adds a VIOMMU_STRUCT_SIZE macro, for drivers to use, which would
statically sanitize the driver structure.

Link: https://patch.msgid.link/r/3ab52c5b622dad476c43b1b1f1636c8b902f1692.1749882255.git.nicolinc@nvidia.com
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/iommu.h   | 15 +++++++++++++++
 include/linux/iommufd.h |  6 ++++++
 2 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 156732807994..9be4ff370f1e 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -14,6 +14,7 @@
 #include <linux/err.h>
 #include <linux/of.h>
 #include <linux/iova_bitmap.h>
+#include <uapi/linux/iommufd.h>
 
 #define IOMMU_READ	(1 << 0)
 #define IOMMU_WRITE	(1 << 1)
@@ -596,6 +597,16 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
  *		- IOMMU_DOMAIN_DMA: must use a dma domain
  *		- 0: use the default setting
  * @default_domain_ops: the default ops for domains
+ * @get_viommu_size: Get the size of a driver-level vIOMMU structure for a given
+ *                   @dev corresponding to @viommu_type. Driver should return 0
+ *                   if vIOMMU isn't supported accordingly. It is required for
+ *                   driver to use the VIOMMU_STRUCT_SIZE macro to sanitize the
+ *                   driver-level vIOMMU structure related to the core one
+ * @viommu_init: Init the driver-level struct of an iommufd_viommu on a physical
+ *               IOMMU instance @viommu->iommu_dev, as the set of virtualization
+ *               resources shared/passed to user space IOMMU instance. Associate
+ *               it with a nesting @parent_domain. It is required for driver to
+ *               set @viommu->ops pointing to its own viommu_ops
  * @viommu_alloc: Allocate an iommufd_viommu on a physical IOMMU instance behind
  *                the @dev, as the set of virtualization resources shared/passed
  *                to user space IOMMU instance. And associate it with a nesting
@@ -654,6 +665,10 @@ struct iommu_ops {
 
 	int (*def_domain_type)(struct device *dev);
 
+	size_t (*get_viommu_size)(struct device *dev,
+				  enum iommu_viommu_type viommu_type);
+	int (*viommu_init)(struct iommufd_viommu *viommu,
+			   struct iommu_domain *parent_domain);
 	struct iommufd_viommu *(*viommu_alloc)(
 		struct device *dev, struct iommu_domain *parent_domain,
 		struct iommufd_ctx *ictx, unsigned int viommu_type);
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index ac98e49e44fe..423e08963d90 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -229,6 +229,12 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 }
 #endif /* CONFIG_IOMMUFD_DRIVER_CORE */
 
+#define VIOMMU_STRUCT_SIZE(drv_struct, member)                                 \
+	(sizeof(drv_struct) +                                                  \
+	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
+	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_viommu,                 \
+					((drv_struct *)NULL)->member)))
+
 /*
  * Helpers for IOMMU driver to allocate driver structures that will be freed by
  * the iommufd core. The free op will be called prior to freeing the memory.
-- 
cgit v1.2.3


From f842ea208e43066c43e5e91e20fe8ce600df7055 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Fri, 13 Jun 2025 23:35:23 -0700
Subject: iommu: Deprecate viommu_alloc op

To ease the for-driver iommufd APIs, get_viommu_size and viommu_init ops
are introduced. Now, those existing vIOMMU supported drivers implemented
these two ops, replacing the viommu_alloc one. So, there is no use of it.

Remove it from the headers and the viommu core.

Link: https://patch.msgid.link/r/5b32d4499d7ed02a63e57a293c11b642d226ef8d.1749882255.git.nicolinc@nvidia.com
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/viommu.c | 20 +++++---------------
 include/linux/iommu.h          | 11 -----------
 include/linux/iommufd.h        | 18 ------------------
 3 files changed, 5 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index 27a39f524840..044e3ef06e0f 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -33,8 +33,6 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd)
 
 	ops = dev_iommu_ops(idev->dev);
 	if (!ops->get_viommu_size || !ops->viommu_init) {
-		if (ops->viommu_alloc)
-			goto get_hwpt_paging;
 		rc = -EOPNOTSUPP;
 		goto out_put_idev;
 	}
@@ -54,7 +52,6 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd)
 		goto out_put_idev;
 	}
 
-get_hwpt_paging:
 	hwpt_paging = iommufd_get_hwpt_paging(ucmd, cmd->hwpt_id);
 	if (IS_ERR(hwpt_paging)) {
 		rc = PTR_ERR(hwpt_paging);
@@ -66,13 +63,8 @@ get_hwpt_paging:
 		goto out_put_hwpt;
 	}
 
-	if (ops->viommu_alloc)
-		viommu = ops->viommu_alloc(idev->dev,
-					   hwpt_paging->common.domain,
-					   ucmd->ictx, cmd->type);
-	else
-		viommu = (struct iommufd_viommu *)_iommufd_object_alloc(
-			ucmd->ictx, viommu_size, IOMMUFD_OBJ_VIOMMU);
+	viommu = (struct iommufd_viommu *)_iommufd_object_alloc(
+		ucmd->ictx, viommu_size, IOMMUFD_OBJ_VIOMMU);
 	if (IS_ERR(viommu)) {
 		rc = PTR_ERR(viommu);
 		goto out_put_hwpt;
@@ -92,11 +84,9 @@ get_hwpt_paging:
 	 */
 	viommu->iommu_dev = __iommu_get_iommu_dev(idev->dev);
 
-	if (!ops->viommu_alloc) {
-		rc = ops->viommu_init(viommu, hwpt_paging->common.domain);
-		if (rc)
-			goto out_abort;
-	}
+	rc = ops->viommu_init(viommu, hwpt_paging->common.domain);
+	if (rc)
+		goto out_abort;
 
 	/* It is a driver bug that viommu->ops isn't filled */
 	if (WARN_ON_ONCE(!viommu->ops)) {
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 9be4ff370f1e..04548b18df28 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -607,14 +607,6 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
  *               resources shared/passed to user space IOMMU instance. Associate
  *               it with a nesting @parent_domain. It is required for driver to
  *               set @viommu->ops pointing to its own viommu_ops
- * @viommu_alloc: Allocate an iommufd_viommu on a physical IOMMU instance behind
- *                the @dev, as the set of virtualization resources shared/passed
- *                to user space IOMMU instance. And associate it with a nesting
- *                @parent_domain. The @viommu_type must be defined in the header
- *                include/uapi/linux/iommufd.h
- *                It is required to call iommufd_viommu_alloc() helper for
- *                a bundled allocation of the core and the driver structures,
- *                using the given @ictx pointer.
  * @pgsize_bitmap: bitmap of all possible supported page sizes
  * @owner: Driver module providing these ops
  * @identity_domain: An always available, always attachable identity
@@ -669,9 +661,6 @@ struct iommu_ops {
 				  enum iommu_viommu_type viommu_type);
 	int (*viommu_init)(struct iommufd_viommu *viommu,
 			   struct iommu_domain *parent_domain);
-	struct iommufd_viommu *(*viommu_alloc)(
-		struct device *dev, struct iommu_domain *parent_domain,
-		struct iommufd_ctx *ictx, unsigned int viommu_type);
 
 	const struct iommu_domain_ops *default_domain_ops;
 	unsigned long pgsize_bitmap;
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 423e08963d90..bf41b242b9f6 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -234,22 +234,4 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
 	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_viommu,                 \
 					((drv_struct *)NULL)->member)))
-
-/*
- * Helpers for IOMMU driver to allocate driver structures that will be freed by
- * the iommufd core. The free op will be called prior to freeing the memory.
- */
-#define iommufd_viommu_alloc(ictx, drv_struct, member, viommu_ops)             \
-	({                                                                     \
-		drv_struct *ret;                                               \
-									       \
-		static_assert(__same_type(struct iommufd_viommu,               \
-					  ((drv_struct *)NULL)->member));      \
-		static_assert(offsetof(drv_struct, member.obj) == 0);          \
-		ret = (drv_struct *)_iommufd_object_alloc(                     \
-			ictx, sizeof(drv_struct), IOMMUFD_OBJ_VIOMMU);         \
-		if (!IS_ERR(ret))                                              \
-			ret->member.ops = viommu_ops;                          \
-		ret;                                                           \
-	})
 #endif
-- 
cgit v1.2.3


From 17a93473a552fc0ffdfb04e69a26946afd4a046a Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Fri, 13 Jun 2025 23:35:24 -0700
Subject: iommufd: Move _iommufd_object_alloc out of driver.c

Now, all driver structures will be allocated by the core, i.e. no longer a
need of driver calling _iommufd_object_alloc. Thus, move it back.

Before:
   text	   data	    bss	    dec	    hex	filename
   3024	    180	      0	   3204	    c84	drivers/iommu/iommufd/driver.o
   9074	    610	     64	   9748	   2614	drivers/iommu/iommufd/main.o
After:
   text	   data	    bss	    dec	    hex	filename
   2665	    164	      0	   2829	    b0d	drivers/iommu/iommufd/driver.o
   9410	    618	     64	  10092	   276c	drivers/iommu/iommufd/main.o

Link: https://patch.msgid.link/r/79e630c7b911930cf36e3c8a775a04e66c528d65.1749882255.git.nicolinc@nvidia.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/driver.c          | 33 ---------------------------------
 drivers/iommu/iommufd/iommufd_private.h |  4 ++++
 drivers/iommu/iommufd/main.c            | 32 ++++++++++++++++++++++++++++++++
 include/linux/iommufd.h                 | 10 ----------
 4 files changed, 36 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c
index 922cd1fe7ec2..2fee399a148e 100644
--- a/drivers/iommu/iommufd/driver.c
+++ b/drivers/iommu/iommufd/driver.c
@@ -3,39 +3,6 @@
  */
 #include "iommufd_private.h"
 
-struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
-					     size_t size,
-					     enum iommufd_object_type type)
-{
-	struct iommufd_object *obj;
-	int rc;
-
-	obj = kzalloc(size, GFP_KERNEL_ACCOUNT);
-	if (!obj)
-		return ERR_PTR(-ENOMEM);
-	obj->type = type;
-	/* Starts out bias'd by 1 until it is removed from the xarray */
-	refcount_set(&obj->shortterm_users, 1);
-	refcount_set(&obj->users, 1);
-
-	/*
-	 * Reserve an ID in the xarray but do not publish the pointer yet since
-	 * the caller hasn't initialized it yet. Once the pointer is published
-	 * in the xarray and visible to other threads we can't reliably destroy
-	 * it anymore, so the caller must complete all errorable operations
-	 * before calling iommufd_object_finalize().
-	 */
-	rc = xa_alloc(&ictx->objects, &obj->id, XA_ZERO_ENTRY, xa_limit_31b,
-		      GFP_KERNEL_ACCOUNT);
-	if (rc)
-		goto out_free;
-	return obj;
-out_free:
-	kfree(obj);
-	return ERR_PTR(rc);
-}
-EXPORT_SYMBOL_NS_GPL(_iommufd_object_alloc, "IOMMUFD");
-
 /* Caller should xa_lock(&viommu->vdevs) to protect the return value */
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id)
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 32f0631368e1..ec5b499d139c 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -230,6 +230,10 @@ iommufd_object_put_and_try_destroy(struct iommufd_ctx *ictx,
 	iommufd_object_remove(ictx, obj, obj->id, 0);
 }
 
+struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
+					     size_t size,
+					     enum iommufd_object_type type);
+
 #define __iommufd_object_alloc(ictx, ptr, type, obj)                           \
 	container_of(_iommufd_object_alloc(                                    \
 			     ictx,                                             \
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 347c56ef44d8..85ad2853da0b 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -29,6 +29,38 @@ struct iommufd_object_ops {
 static const struct iommufd_object_ops iommufd_object_ops[];
 static struct miscdevice vfio_misc_dev;
 
+struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
+					     size_t size,
+					     enum iommufd_object_type type)
+{
+	struct iommufd_object *obj;
+	int rc;
+
+	obj = kzalloc(size, GFP_KERNEL_ACCOUNT);
+	if (!obj)
+		return ERR_PTR(-ENOMEM);
+	obj->type = type;
+	/* Starts out bias'd by 1 until it is removed from the xarray */
+	refcount_set(&obj->shortterm_users, 1);
+	refcount_set(&obj->users, 1);
+
+	/*
+	 * Reserve an ID in the xarray but do not publish the pointer yet since
+	 * the caller hasn't initialized it yet. Once the pointer is published
+	 * in the xarray and visible to other threads we can't reliably destroy
+	 * it anymore, so the caller must complete all errorable operations
+	 * before calling iommufd_object_finalize().
+	 */
+	rc = xa_alloc(&ictx->objects, &obj->id, XA_ZERO_ENTRY, xa_limit_31b,
+		      GFP_KERNEL_ACCOUNT);
+	if (rc)
+		goto out_free;
+	return obj;
+out_free:
+	kfree(obj);
+	return ERR_PTR(rc);
+}
+
 /*
  * Allow concurrent access to the object.
  *
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index bf41b242b9f6..2d1bf2f97ee3 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -190,9 +190,6 @@ static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx)
 #endif /* CONFIG_IOMMUFD */
 
 #if IS_ENABLED(CONFIG_IOMMUFD_DRIVER_CORE)
-struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
-					     size_t size,
-					     enum iommufd_object_type type);
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id);
 int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
@@ -201,13 +198,6 @@ int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 				enum iommu_veventq_type type, void *event_data,
 				size_t data_len);
 #else /* !CONFIG_IOMMUFD_DRIVER_CORE */
-static inline struct iommufd_object *
-_iommufd_object_alloc(struct iommufd_ctx *ictx, size_t size,
-		      enum iommufd_object_type type)
-{
-	return ERR_PTR(-EOPNOTSUPP);
-}
-
 static inline struct device *
 iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)
 {
-- 
cgit v1.2.3


From 2c04d279e857e6c441593c282f978cebc5583fd9 Mon Sep 17 00:00:00 2001
From: Jun Miao <jun.miao@intel.com>
Date: Wed, 18 Jun 2025 13:39:23 -0400
Subject: net: usb: Convert tasklet API to new bottom half workqueue mechanism

Migrate tasklet APIs to the new bottom half workqueue mechanism. It
replaces all occurrences of tasklet usage with the appropriate workqueue
APIs throughout the usbnet driver. This transition ensures compatibility
with the latest design and enhances performance.

Signed-off-by: Jun Miao <jun.miao@intel.com>
Link: https://patch.msgid.link/20250618173923.950510-1-jun.miao@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/usbnet.c   | 36 ++++++++++++++++++------------------
 include/linux/usb/usbnet.h |  2 +-
 2 files changed, 19 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index c04e715a4c2a..9564478a79cc 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -461,7 +461,7 @@ static enum skb_state defer_bh(struct usbnet *dev, struct sk_buff *skb,
 
 	__skb_queue_tail(&dev->done, skb);
 	if (dev->done.qlen == 1)
-		tasklet_schedule(&dev->bh);
+		queue_work(system_bh_wq, &dev->bh_work);
 	spin_unlock(&dev->done.lock);
 	spin_unlock_irqrestore(&list->lock, flags);
 	return old_state;
@@ -549,7 +549,7 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
 		default:
 			netif_dbg(dev, rx_err, dev->net,
 				  "rx submit, %d\n", retval);
-			tasklet_schedule (&dev->bh);
+			queue_work(system_bh_wq, &dev->bh_work);
 			break;
 		case 0:
 			__usbnet_queue_skb(&dev->rxq, skb, rx_start);
@@ -709,7 +709,7 @@ void usbnet_resume_rx(struct usbnet *dev)
 		num++;
 	}
 
-	tasklet_schedule(&dev->bh);
+	queue_work(system_bh_wq, &dev->bh_work);
 
 	netif_dbg(dev, rx_status, dev->net,
 		  "paused rx queue disabled, %d skbs requeued\n", num);
@@ -778,7 +778,7 @@ void usbnet_unlink_rx_urbs(struct usbnet *dev)
 {
 	if (netif_running(dev->net)) {
 		(void) unlink_urbs (dev, &dev->rxq);
-		tasklet_schedule(&dev->bh);
+		queue_work(system_bh_wq, &dev->bh_work);
 	}
 }
 EXPORT_SYMBOL_GPL(usbnet_unlink_rx_urbs);
@@ -861,14 +861,14 @@ int usbnet_stop (struct net_device *net)
 	/* deferred work (timer, softirq, task) must also stop */
 	dev->flags = 0;
 	timer_delete_sync(&dev->delay);
-	tasklet_kill(&dev->bh);
+	disable_work_sync(&dev->bh_work);
 	cancel_work_sync(&dev->kevent);
 
 	/* We have cyclic dependencies. Those calls are needed
 	 * to break a cycle. We cannot fall into the gaps because
 	 * we have a flag
 	 */
-	tasklet_kill(&dev->bh);
+	disable_work_sync(&dev->bh_work);
 	timer_delete_sync(&dev->delay);
 	cancel_work_sync(&dev->kevent);
 
@@ -955,7 +955,7 @@ int usbnet_open (struct net_device *net)
 	clear_bit(EVENT_RX_KILL, &dev->flags);
 
 	// delay posting reads until we're fully open
-	tasklet_schedule (&dev->bh);
+	queue_work(system_bh_wq, &dev->bh_work);
 	if (info->manage_power) {
 		retval = info->manage_power(dev, 1);
 		if (retval < 0) {
@@ -1123,7 +1123,7 @@ static void __handle_link_change(struct usbnet *dev)
 		 */
 	} else {
 		/* submitting URBs for reading packets */
-		tasklet_schedule(&dev->bh);
+		queue_work(system_bh_wq, &dev->bh_work);
 	}
 
 	/* hard_mtu or rx_urb_size may change during link change */
@@ -1198,11 +1198,11 @@ fail_halt:
 		} else {
 			clear_bit (EVENT_RX_HALT, &dev->flags);
 			if (!usbnet_going_away(dev))
-				tasklet_schedule(&dev->bh);
+				queue_work(system_bh_wq, &dev->bh_work);
 		}
 	}
 
-	/* tasklet could resubmit itself forever if memory is tight */
+	/* work could resubmit itself forever if memory is tight */
 	if (test_bit (EVENT_RX_MEMORY, &dev->flags)) {
 		struct urb	*urb = NULL;
 		int resched = 1;
@@ -1224,7 +1224,7 @@ fail_halt:
 fail_lowmem:
 			if (resched)
 				if (!usbnet_going_away(dev))
-					tasklet_schedule(&dev->bh);
+					queue_work(system_bh_wq, &dev->bh_work);
 		}
 	}
 
@@ -1325,7 +1325,7 @@ void usbnet_tx_timeout (struct net_device *net, unsigned int txqueue)
 	struct usbnet		*dev = netdev_priv(net);
 
 	unlink_urbs (dev, &dev->txq);
-	tasklet_schedule (&dev->bh);
+	queue_work(system_bh_wq, &dev->bh_work);
 	/* this needs to be handled individually because the generic layer
 	 * doesn't know what is sufficient and could not restore private
 	 * information if a remedy of an unconditional reset were used.
@@ -1547,7 +1547,7 @@ static inline void usb_free_skb(struct sk_buff *skb)
 
 /*-------------------------------------------------------------------------*/
 
-// tasklet (work deferred from completions, in_irq) or timer
+// work (work deferred from completions, in_irq) or timer
 
 static void usbnet_bh (struct timer_list *t)
 {
@@ -1601,16 +1601,16 @@ static void usbnet_bh (struct timer_list *t)
 					  "rxqlen %d --> %d\n",
 					  temp, dev->rxq.qlen);
 			if (dev->rxq.qlen < RX_QLEN(dev))
-				tasklet_schedule (&dev->bh);
+				queue_work(system_bh_wq, &dev->bh_work);
 		}
 		if (dev->txq.qlen < TX_QLEN (dev))
 			netif_wake_queue (dev->net);
 	}
 }
 
-static void usbnet_bh_tasklet(struct tasklet_struct *t)
+static void usbnet_bh_work(struct work_struct *work)
 {
-	struct usbnet *dev = from_tasklet(dev, t, bh);
+	struct usbnet *dev = from_work(dev, work, bh_work);
 
 	usbnet_bh(&dev->delay);
 }
@@ -1742,7 +1742,7 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
 	skb_queue_head_init (&dev->txq);
 	skb_queue_head_init (&dev->done);
 	skb_queue_head_init(&dev->rxq_pause);
-	tasklet_setup(&dev->bh, usbnet_bh_tasklet);
+	INIT_WORK(&dev->bh_work, usbnet_bh_work);
 	INIT_WORK (&dev->kevent, usbnet_deferred_kevent);
 	init_usb_anchor(&dev->deferred);
 	timer_setup(&dev->delay, usbnet_bh, 0);
@@ -1971,7 +1971,7 @@ int usbnet_resume (struct usb_interface *intf)
 
 			if (!(dev->txq.qlen >= TX_QLEN(dev)))
 				netif_tx_wake_all_queues(dev->net);
-			tasklet_schedule (&dev->bh);
+			queue_work(system_bh_wq, &dev->bh_work);
 		}
 	}
 
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 0b9f1e598e3a..208682f77179 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -58,7 +58,7 @@ struct usbnet {
 	unsigned		interrupt_count;
 	struct mutex		interrupt_mutex;
 	struct usb_anchor	deferred;
-	struct tasklet_struct	bh;
+	struct work_struct	bh_work;
 
 	struct work_struct	kevent;
 	unsigned long		flags;
-- 
cgit v1.2.3


From 27480a7c8f0274f8f2fc6c40e4522f38e52bd05f Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 18 Jun 2025 01:32:44 -0700
Subject: net: add dev_dstats_rx_dropped_add() helper

Introduce the dev_dstats_rx_dropped_add() helper to allow incrementing
the rx_drops per-CPU statistic by an arbitrary value, rather than just
one. This is useful for drivers or code paths that need to account for
multiple dropped packets at once, such as when dropping entire queues.

Reviewed-by: Joe Damato <joe@dama.to>
Signed-off-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20250618-netdevsim_stat-v4-3-19fe0d35e28e@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 9cbc4e54b7e4..03c26bb0fbbe 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3016,6 +3016,16 @@ static inline void dev_dstats_rx_dropped(struct net_device *dev)
 	u64_stats_update_end(&dstats->syncp);
 }
 
+static inline void dev_dstats_rx_dropped_add(struct net_device *dev,
+					     unsigned int packets)
+{
+	struct pcpu_dstats *dstats = this_cpu_ptr(dev->dstats);
+
+	u64_stats_update_begin(&dstats->syncp);
+	u64_stats_add(&dstats->rx_drops, packets);
+	u64_stats_update_end(&dstats->syncp);
+}
+
 static inline void dev_dstats_tx_add(struct net_device *dev,
 				     unsigned int len)
 {
-- 
cgit v1.2.3


From 49c94af071fc6c9f5e1db52b3031dec28daa90c3 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 18 Jun 2025 10:24:16 -0400
Subject: ref_tracker: have callers pass output function to pr_ostream()

In a later patch, we'll be adding a 3rd mechanism for outputting
ref_tracker info via seq_file. Instead of a conditional, have the caller
set a pointer to an output function in struct ostream. As part of this,
the log prefix must be explicitly passed in, as it's too late for the
pr_fmt macro.

Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20250618-reftrack-dbgfs-v15-3-24fc37ead144@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ref_tracker.h |  2 ++
 lib/ref_tracker.c           | 52 ++++++++++++++++++++++++++++++++-------------
 2 files changed, 39 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h
index 8eac4f3d5254..a0a1ee43724f 100644
--- a/include/linux/ref_tracker.h
+++ b/include/linux/ref_tracker.h
@@ -6,6 +6,8 @@
 #include <linux/spinlock.h>
 #include <linux/stackdepot.h>
 
+#define __ostream_printf __printf(2, 3)
+
 struct ref_tracker;
 
 struct ref_tracker_dir {
diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index d374e5273e14..42872f406b2a 100644
--- a/lib/ref_tracker.c
+++ b/lib/ref_tracker.c
@@ -63,21 +63,38 @@ ref_tracker_get_stats(struct ref_tracker_dir *dir, unsigned int limit)
 }
 
 struct ostream {
+	void __ostream_printf (*func)(struct ostream *stream, char *fmt, ...);
+	char *prefix;
 	char *buf;
 	int size, used;
 };
 
+static void __ostream_printf pr_ostream_log(struct ostream *stream, char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vprintk(fmt, args);
+	va_end(args);
+}
+
+static void __ostream_printf pr_ostream_buf(struct ostream *stream, char *fmt, ...)
+{
+	int ret, len = stream->size - stream->used;
+	va_list args;
+
+	va_start(args, fmt);
+	ret = vsnprintf(stream->buf + stream->used, len, fmt, args);
+	va_end(args);
+	if (ret > 0)
+		stream->used += min(ret, len);
+}
+
 #define pr_ostream(stream, fmt, args...) \
 ({ \
 	struct ostream *_s = (stream); \
 \
-	if (!_s->buf) { \
-		pr_err(fmt, ##args); \
-	} else { \
-		int ret, len = _s->size - _s->used; \
-		ret = snprintf(_s->buf + _s->used, len, pr_fmt(fmt), ##args); \
-		_s->used += min(ret, len); \
-	} \
+	_s->func(_s, fmt, ##args); \
 })
 
 static void
@@ -96,8 +113,8 @@ __ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir,
 
 	stats = ref_tracker_get_stats(dir, display_limit);
 	if (IS_ERR(stats)) {
-		pr_ostream(s, "%s@%p: couldn't get stats, error %pe\n",
-			   dir->name, dir, stats);
+		pr_ostream(s, "%s%s@%p: couldn't get stats, error %pe\n",
+			   s->prefix, dir->name, dir, stats);
 		return;
 	}
 
@@ -107,14 +124,15 @@ __ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir,
 		stack = stats->stacks[i].stack_handle;
 		if (sbuf && !stack_depot_snprint(stack, sbuf, STACK_BUF_SIZE, 4))
 			sbuf[0] = 0;
-		pr_ostream(s, "%s@%p has %d/%d users at\n%s\n", dir->name, dir,
-			   stats->stacks[i].count, stats->total, sbuf);
+		pr_ostream(s, "%s%s@%p has %d/%d users at\n%s\n", s->prefix,
+			   dir->name, dir, stats->stacks[i].count,
+			   stats->total, sbuf);
 		skipped -= stats->stacks[i].count;
 	}
 
 	if (skipped)
-		pr_ostream(s, "%s@%p skipped reports about %d/%d users.\n",
-			   dir->name, dir, skipped, stats->total);
+		pr_ostream(s, "%s%s@%p skipped reports about %d/%d users.\n",
+			   s->prefix, dir->name, dir, skipped, stats->total);
 
 	kfree(sbuf);
 
@@ -124,7 +142,8 @@ __ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir,
 void ref_tracker_dir_print_locked(struct ref_tracker_dir *dir,
 				  unsigned int display_limit)
 {
-	struct ostream os = {};
+	struct ostream os = { .func = pr_ostream_log,
+			      .prefix = "ref_tracker: " };
 
 	__ref_tracker_dir_pr_ostream(dir, display_limit, &os);
 }
@@ -143,7 +162,10 @@ EXPORT_SYMBOL(ref_tracker_dir_print);
 
 int ref_tracker_dir_snprint(struct ref_tracker_dir *dir, char *buf, size_t size)
 {
-	struct ostream os = { .buf = buf, .size = size };
+	struct ostream os = { .func = pr_ostream_buf,
+			      .prefix = "ref_tracker: ",
+			      .buf = buf,
+			      .size = size };
 	unsigned long flags;
 
 	spin_lock_irqsave(&dir->lock, flags);
-- 
cgit v1.2.3


From aa7d26c3c3497258b712fb97221e775733a710b7 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 18 Jun 2025 10:24:17 -0400
Subject: ref_tracker: add a static classname string to each ref_tracker_dir

A later patch in the series will be adding debugfs files for each
ref_tracker that get created in ref_tracker_dir_init(). The format will
be "class@%px". The current "name" string can vary between
ref_tracker_dir objects of the same type, so it's not suitable for this
purpose.

Add a new "class" string to the ref_tracker dir that describes the
the type of object (sans any individual info for that object).

Also, in the i915 driver, gate the creation of debugfs files on whether
the dentry pointer is still set to NULL. CI has shown that the
ref_tracker_dir can be initialized more than once.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20250618-reftrack-dbgfs-v15-4-24fc37ead144@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/gpu/drm/display/drm_dp_tunnel.c | 2 +-
 drivers/gpu/drm/i915/intel_runtime_pm.c | 4 +++-
 drivers/gpu/drm/i915/intel_wakeref.c    | 3 ++-
 include/linux/ref_tracker.h             | 4 ++++
 lib/test_ref_tracker.c                  | 2 +-
 net/core/dev.c                          | 2 +-
 net/core/net_namespace.c                | 4 ++--
 7 files changed, 14 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/display/drm_dp_tunnel.c b/drivers/gpu/drm/display/drm_dp_tunnel.c
index 076edf161048..b9c12b8bf2a3 100644
--- a/drivers/gpu/drm/display/drm_dp_tunnel.c
+++ b/drivers/gpu/drm/display/drm_dp_tunnel.c
@@ -1920,7 +1920,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count)
 	}
 
 #ifdef CONFIG_DRM_DISPLAY_DP_TUNNEL_STATE_DEBUG
-	ref_tracker_dir_init(&mgr->ref_tracker, 16, "dptun");
+	ref_tracker_dir_init(&mgr->ref_tracker, 16, "drm_dptun", "dptun");
 #endif
 
 	for (i = 0; i < max_group_count; i++) {
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 8d9f4c410546..90d90145a189 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -59,7 +59,9 @@ static struct drm_i915_private *rpm_to_i915(struct intel_runtime_pm *rpm)
 
 static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
 {
-	ref_tracker_dir_init(&rpm->debug, INTEL_REFTRACK_DEAD_COUNT, dev_name(rpm->kdev));
+	if (!rpm->debug.class)
+		ref_tracker_dir_init(&rpm->debug, INTEL_REFTRACK_DEAD_COUNT,
+				     "intel_runtime_pm", dev_name(rpm->kdev));
 }
 
 static intel_wakeref_t
diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c
index 51561b190b93..7e74c58862c1 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.c
+++ b/drivers/gpu/drm/i915/intel_wakeref.c
@@ -114,7 +114,8 @@ void __intel_wakeref_init(struct intel_wakeref *wf,
 			 "wakeref.work", &key->work, 0);
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_WAKEREF)
-	ref_tracker_dir_init(&wf->debug, INTEL_REFTRACK_DEAD_COUNT, name);
+	if (!wf->debug.class)
+		ref_tracker_dir_init(&wf->debug, INTEL_REFTRACK_DEAD_COUNT, "intel_wakeref", name);
 #endif
 }
 
diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h
index a0a1ee43724f..3968f993db81 100644
--- a/include/linux/ref_tracker.h
+++ b/include/linux/ref_tracker.h
@@ -19,6 +19,7 @@ struct ref_tracker_dir {
 	bool			dead;
 	struct list_head	list; /* List of active trackers */
 	struct list_head	quarantine; /* List of dead trackers */
+	const char		*class; /* object classname */
 	char			name[32];
 #endif
 };
@@ -27,6 +28,7 @@ struct ref_tracker_dir {
 
 static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 					unsigned int quarantine_count,
+					const char *class,
 					const char *name)
 {
 	INIT_LIST_HEAD(&dir->list);
@@ -36,6 +38,7 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 	dir->dead = false;
 	refcount_set(&dir->untracked, 1);
 	refcount_set(&dir->no_tracker, 1);
+	dir->class = class;
 	strscpy(dir->name, name, sizeof(dir->name));
 	stack_depot_init();
 }
@@ -60,6 +63,7 @@ int ref_tracker_free(struct ref_tracker_dir *dir,
 
 static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 					unsigned int quarantine_count,
+					const char *class,
 					const char *name)
 {
 }
diff --git a/lib/test_ref_tracker.c b/lib/test_ref_tracker.c
index b983ceb12afc..d263502a4c1d 100644
--- a/lib/test_ref_tracker.c
+++ b/lib/test_ref_tracker.c
@@ -64,7 +64,7 @@ static int __init test_ref_tracker_init(void)
 {
 	int i;
 
-	ref_tracker_dir_init(&ref_dir, 100, "selftest");
+	ref_tracker_dir_init(&ref_dir, 100, "selftest", "selftest");
 
 	timer_setup(&test_ref_tracker_timer, test_ref_tracker_timer_func, 0);
 	mod_timer(&test_ref_tracker_timer, jiffies + 1);
diff --git a/net/core/dev.c b/net/core/dev.c
index be97c440ecd5..12cf4e5ae9c5 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11715,7 +11715,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->priv_len = sizeof_priv;
 
-	ref_tracker_dir_init(&dev->refcnt_tracker, 128, name);
+	ref_tracker_dir_init(&dev->refcnt_tracker, 128, "netdev", name);
 #ifdef CONFIG_PCPU_DEV_REFCNT
 	dev->pcpu_refcnt = alloc_percpu(int);
 	if (!dev->pcpu_refcnt)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index ae54f26709ca..aa1e34181ed6 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -403,8 +403,8 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_
 {
 	refcount_set(&net->passive, 1);
 	refcount_set(&net->ns.count, 1);
-	ref_tracker_dir_init(&net->refcnt_tracker, 128, "net refcnt");
-	ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net notrefcnt");
+	ref_tracker_dir_init(&net->refcnt_tracker, 128, "net_refcnt", "net_refcnt");
+	ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net_notrefcnt", "net_notrefcnt");
 
 	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;
-- 
cgit v1.2.3


From 65b584f5361163ba539d2c7122ca792c3cc87997 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 18 Jun 2025 10:24:19 -0400
Subject: ref_tracker: automatically register a file in debugfs for a
 ref_tracker_dir

Currently, there is no convenient way to see the info that the
ref_tracking infrastructure collects. Attempt to create a file in
debugfs when called from ref_tracker_dir_init().

The file is given the name "class@%px", as having the unmodified address
is helpful for debugging. This should be safe since this directory is only
accessible by root

While ref_tracker_dir_init() is generally called from a context where
sleeping is OK, ref_tracker_dir_exit() can be called from anywhere.
Thus, dentry cleanup must be handled asynchronously.

Add a new global xarray that has entries with the ref_tracker_dir
pointer as the index and the corresponding debugfs dentry pointer as the
value. Instead of removing the debugfs dentry, have
ref_tracker_dir_exit() set a mark on the xarray entry and schedule a
workqueue job. The workqueue job then walks the xarray looking for
marked entries, and removes their xarray entries and the debugfs
dentries.

Because of this, the debugfs dentry can outlive the corresponding
ref_tracker_dir. Have ref_tracker_debugfs_show() take extra care to
ensure that it's safe to dereference the dir pointer before using it.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20250618-reftrack-dbgfs-v15-6-24fc37ead144@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ref_tracker.h |  17 +++++
 lib/ref_tracker.c           | 152 ++++++++++++++++++++++++++++++++++++++++++--
 2 files changed, 164 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h
index 3968f993db81..28bbf436a8f4 100644
--- a/include/linux/ref_tracker.h
+++ b/include/linux/ref_tracker.h
@@ -26,6 +26,18 @@ struct ref_tracker_dir {
 
 #ifdef CONFIG_REF_TRACKER
 
+#ifdef CONFIG_DEBUG_FS
+
+void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir);
+
+#else /* CONFIG_DEBUG_FS */
+
+static inline void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir)
+{
+}
+
+#endif /* CONFIG_DEBUG_FS */
+
 static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 					unsigned int quarantine_count,
 					const char *class,
@@ -40,6 +52,7 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 	refcount_set(&dir->no_tracker, 1);
 	dir->class = class;
 	strscpy(dir->name, name, sizeof(dir->name));
+	ref_tracker_dir_debugfs(dir);
 	stack_depot_init();
 }
 
@@ -68,6 +81,10 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 {
 }
 
+static inline void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir)
+{
+}
+
 static inline void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
 {
 }
diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index 73b606570cce..c938ef56954b 100644
--- a/lib/ref_tracker.c
+++ b/lib/ref_tracker.c
@@ -29,6 +29,40 @@ struct ref_tracker_dir_stats {
 	} stacks[];
 };
 
+#ifdef CONFIG_DEBUG_FS
+#include <linux/xarray.h>
+
+/*
+ * ref_tracker_dir_init() is usually called in allocation-safe contexts, but
+ * the same is not true of ref_tracker_dir_exit() which can be called from
+ * anywhere an object is freed. Removing debugfs dentries is a blocking
+ * operation, so we defer that work to the debugfs_reap_worker.
+ *
+ * Each dentry is tracked in the appropriate xarray.  When
+ * ref_tracker_dir_exit() is called, its entries in the xarrays are marked and
+ * the workqueue job is scheduled. The worker then runs and deletes any marked
+ * dentries asynchronously.
+ */
+static struct xarray		debugfs_dentries;
+static struct work_struct	debugfs_reap_worker;
+
+#define REF_TRACKER_DIR_DEAD	XA_MARK_0
+static inline void ref_tracker_debugfs_mark(struct ref_tracker_dir *dir)
+{
+	unsigned long flags;
+
+	xa_lock_irqsave(&debugfs_dentries, flags);
+	__xa_set_mark(&debugfs_dentries, (unsigned long)dir, REF_TRACKER_DIR_DEAD);
+	xa_unlock_irqrestore(&debugfs_dentries, flags);
+
+	schedule_work(&debugfs_reap_worker);
+}
+#else
+static inline void ref_tracker_debugfs_mark(struct ref_tracker_dir *dir)
+{
+}
+#endif
+
 static struct ref_tracker_dir_stats *
 ref_tracker_get_stats(struct ref_tracker_dir *dir, unsigned int limit)
 {
@@ -185,6 +219,11 @@ void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
 	bool leak = false;
 
 	dir->dead = true;
+	/*
+	 * The xarray entries must be marked before the dir->lock is taken to
+	 * protect simultaneous debugfs readers.
+	 */
+	ref_tracker_debugfs_mark(dir);
 	spin_lock_irqsave(&dir->lock, flags);
 	list_for_each_entry_safe(tracker, n, &dir->quarantine, head) {
 		list_del(&tracker->head);
@@ -312,23 +351,126 @@ static void __ostream_printf pr_ostream_seq(struct ostream *stream, char *fmt, .
 	va_end(args);
 }
 
-static __maybe_unused int
-ref_tracker_dir_seq_print(struct ref_tracker_dir *dir, struct seq_file *seq)
+static int ref_tracker_dir_seq_print(struct ref_tracker_dir *dir, struct seq_file *seq)
 {
 	struct ostream os = { .func = pr_ostream_seq,
 			      .prefix = "",
 			      .seq = seq };
-	unsigned long flags;
 
-	spin_lock_irqsave(&dir->lock, flags);
 	__ref_tracker_dir_pr_ostream(dir, 16, &os);
-	spin_unlock_irqrestore(&dir->lock, flags);
 
 	return os.used;
 }
 
+static int ref_tracker_debugfs_show(struct seq_file *f, void *v)
+{
+	struct ref_tracker_dir *dir = f->private;
+	unsigned long index = (unsigned long)dir;
+	unsigned long flags;
+	int ret;
+
+	/*
+	 * "dir" may not exist at this point if ref_tracker_dir_exit() has
+	 * already been called. Take care not to dereference it until its
+	 * legitimacy is established.
+	 *
+	 * The xa_lock is necessary to ensure that "dir" doesn't disappear
+	 * before its lock can be taken. If it's in the hash and not marked
+	 * dead, then it's safe to take dir->lock which prevents
+	 * ref_tracker_dir_exit() from completing. Once the dir->lock is
+	 * acquired, the xa_lock can be released. All of this must be IRQ-safe.
+	 */
+	xa_lock_irqsave(&debugfs_dentries, flags);
+	if (!xa_load(&debugfs_dentries, index) ||
+	    xa_get_mark(&debugfs_dentries, index, REF_TRACKER_DIR_DEAD)) {
+		xa_unlock_irqrestore(&debugfs_dentries, flags);
+		return -ENODATA;
+	}
+
+	spin_lock(&dir->lock);
+	xa_unlock(&debugfs_dentries);
+	ret = ref_tracker_dir_seq_print(dir, f);
+	spin_unlock_irqrestore(&dir->lock, flags);
+	return ret;
+}
+
+static int ref_tracker_debugfs_open(struct inode *inode, struct file *filp)
+{
+	struct ref_tracker_dir *dir = inode->i_private;
+
+	return single_open(filp, ref_tracker_debugfs_show, dir);
+}
+
+static const struct file_operations ref_tracker_debugfs_fops = {
+	.owner		= THIS_MODULE,
+	.open		= ref_tracker_debugfs_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= single_release,
+};
+
+/**
+ * ref_tracker_dir_debugfs - create debugfs file for ref_tracker_dir
+ * @dir: ref_tracker_dir to be associated with debugfs file
+ *
+ * In most cases, a debugfs file will be created automatically for every
+ * ref_tracker_dir. If the object was created before debugfs is brought up
+ * then that may fail. In those cases, it is safe to call this at a later
+ * time to create the file.
+ */
+void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir)
+{
+	char name[NAME_MAX + 1];
+	struct dentry *dentry;
+	int ret;
+
+	/* No-op if already created */
+	dentry = xa_load(&debugfs_dentries, (unsigned long)dir);
+	if (dentry && !xa_is_err(dentry))
+		return;
+
+	ret = snprintf(name, sizeof(name), "%s@%px", dir->class, dir);
+	name[sizeof(name) - 1] = '\0';
+
+	if (ret < sizeof(name)) {
+		dentry = debugfs_create_file(name, S_IFREG | 0400,
+					     ref_tracker_debug_dir, dir,
+					     &ref_tracker_debugfs_fops);
+		if (!IS_ERR(dentry)) {
+			void *old;
+
+			old = xa_store_irq(&debugfs_dentries, (unsigned long)dir,
+					   dentry, GFP_KERNEL);
+
+			if (xa_is_err(old))
+				debugfs_remove(dentry);
+			else
+				WARN_ON_ONCE(old);
+		}
+	}
+}
+EXPORT_SYMBOL(ref_tracker_dir_debugfs);
+
+static void debugfs_reap_work(struct work_struct *work)
+{
+	struct dentry *dentry;
+	unsigned long index;
+	bool reaped;
+
+	do {
+		reaped = false;
+		xa_for_each_marked(&debugfs_dentries, index, dentry, REF_TRACKER_DIR_DEAD) {
+			xa_erase_irq(&debugfs_dentries, index);
+			debugfs_remove(dentry);
+			reaped = true;
+		}
+	} while (reaped);
+}
+
 static int __init ref_tracker_debugfs_init(void)
 {
+	INIT_WORK(&debugfs_reap_worker, debugfs_reap_work);
+	xa_init_flags(&debugfs_dentries, XA_FLAGS_LOCK_IRQ);
 	ref_tracker_debug_dir = debugfs_create_dir("ref_tracker", NULL);
 	return 0;
 }
-- 
cgit v1.2.3


From d04992dc86a6c77b7d39a1ee10013aed7111e855 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 18 Jun 2025 10:24:20 -0400
Subject: ref_tracker: add a way to create a symlink to the ref_tracker_dir
 debugfs file

Add the ability for a subsystem to add a user-friendly symlink that
points to a ref_tracker_dir's debugfs file. Add a separate
debugfs_symlinks xarray and use that to track symlinks. The reaper
workqueue job will remove symlinks before their corresponding dentries.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20250618-reftrack-dbgfs-v15-7-24fc37ead144@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ref_tracker.h | 11 ++++++++++
 lib/ref_tracker.c           | 50 +++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 61 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h
index 28bbf436a8f4..e1323de93bf6 100644
--- a/include/linux/ref_tracker.h
+++ b/include/linux/ref_tracker.h
@@ -29,6 +29,7 @@ struct ref_tracker_dir {
 #ifdef CONFIG_DEBUG_FS
 
 void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir);
+void ref_tracker_dir_symlink(struct ref_tracker_dir *dir, const char *fmt, ...);
 
 #else /* CONFIG_DEBUG_FS */
 
@@ -36,6 +37,11 @@ static inline void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir)
 {
 }
 
+static inline __ostream_printf
+void ref_tracker_dir_symlink(struct ref_tracker_dir *dir, const char *fmt, ...)
+{
+}
+
 #endif /* CONFIG_DEBUG_FS */
 
 static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
@@ -85,6 +91,11 @@ static inline void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir)
 {
 }
 
+static inline __ostream_printf
+void ref_tracker_dir_symlink(struct ref_tracker_dir *dir, const char *fmt, ...)
+{
+}
+
 static inline void ref_tracker_dir_exit(struct ref_tracker_dir *dir)
 {
 }
diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index c938ef56954b..6608520d6118 100644
--- a/lib/ref_tracker.c
+++ b/lib/ref_tracker.c
@@ -44,6 +44,7 @@ struct ref_tracker_dir_stats {
  * dentries asynchronously.
  */
 static struct xarray		debugfs_dentries;
+static struct xarray		debugfs_symlinks;
 static struct work_struct	debugfs_reap_worker;
 
 #define REF_TRACKER_DIR_DEAD	XA_MARK_0
@@ -55,6 +56,10 @@ static inline void ref_tracker_debugfs_mark(struct ref_tracker_dir *dir)
 	__xa_set_mark(&debugfs_dentries, (unsigned long)dir, REF_TRACKER_DIR_DEAD);
 	xa_unlock_irqrestore(&debugfs_dentries, flags);
 
+	xa_lock_irqsave(&debugfs_symlinks, flags);
+	__xa_set_mark(&debugfs_symlinks, (unsigned long)dir, REF_TRACKER_DIR_DEAD);
+	xa_unlock_irqrestore(&debugfs_symlinks, flags);
+
 	schedule_work(&debugfs_reap_worker);
 }
 #else
@@ -451,6 +456,45 @@ void ref_tracker_dir_debugfs(struct ref_tracker_dir *dir)
 }
 EXPORT_SYMBOL(ref_tracker_dir_debugfs);
 
+void __ostream_printf ref_tracker_dir_symlink(struct ref_tracker_dir *dir, const char *fmt, ...)
+{
+	char name[NAME_MAX + 1];
+	struct dentry *symlink, *dentry;
+	va_list args;
+	int ret;
+
+	symlink = xa_load(&debugfs_symlinks, (unsigned long)dir);
+	dentry = xa_load(&debugfs_dentries, (unsigned long)dir);
+
+	/* Already created?*/
+	if (symlink && !xa_is_err(symlink))
+		return;
+
+	if (!dentry || xa_is_err(dentry))
+		return;
+
+	va_start(args, fmt);
+	ret = vsnprintf(name, sizeof(name), fmt, args);
+	va_end(args);
+	name[sizeof(name) - 1] = '\0';
+
+	if (ret < sizeof(name)) {
+		symlink = debugfs_create_symlink(name, ref_tracker_debug_dir,
+						 dentry->d_name.name);
+		if (!IS_ERR(symlink)) {
+			void *old;
+
+			old = xa_store_irq(&debugfs_symlinks, (unsigned long)dir,
+					   symlink, GFP_KERNEL);
+			if (xa_is_err(old))
+				debugfs_remove(symlink);
+			else
+				WARN_ON_ONCE(old);
+		}
+	}
+}
+EXPORT_SYMBOL(ref_tracker_dir_symlink);
+
 static void debugfs_reap_work(struct work_struct *work)
 {
 	struct dentry *dentry;
@@ -459,6 +503,11 @@ static void debugfs_reap_work(struct work_struct *work)
 
 	do {
 		reaped = false;
+		xa_for_each_marked(&debugfs_symlinks, index, dentry, REF_TRACKER_DIR_DEAD) {
+			xa_erase_irq(&debugfs_symlinks, index);
+			debugfs_remove(dentry);
+			reaped = true;
+		}
 		xa_for_each_marked(&debugfs_dentries, index, dentry, REF_TRACKER_DIR_DEAD) {
 			xa_erase_irq(&debugfs_dentries, index);
 			debugfs_remove(dentry);
@@ -471,6 +520,7 @@ static int __init ref_tracker_debugfs_init(void)
 {
 	INIT_WORK(&debugfs_reap_worker, debugfs_reap_work);
 	xa_init_flags(&debugfs_dentries, XA_FLAGS_LOCK_IRQ);
+	xa_init_flags(&debugfs_symlinks, XA_FLAGS_LOCK_IRQ);
 	ref_tracker_debug_dir = debugfs_create_dir("ref_tracker", NULL);
 	return 0;
 }
-- 
cgit v1.2.3


From 707bd05be75f65749c3f1695f4e362a89b3fcc7b Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Wed, 18 Jun 2025 10:24:22 -0400
Subject: ref_tracker: eliminate the ref_tracker_dir name field

Now that we have dentries and the ability to create meaningful symlinks
to them, don't keep a name string in each tracker. Switch the output
format to print "class@address", and drop the name field.

Also, add a kerneldoc header for ref_tracker_dir_init().

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Link: https://patch.msgid.link/20250618-reftrack-dbgfs-v15-9-24fc37ead144@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/gpu/drm/display/drm_dp_tunnel.c |  2 +-
 drivers/gpu/drm/i915/intel_runtime_pm.c |  2 +-
 drivers/gpu/drm/i915/intel_wakeref.c    |  2 +-
 include/linux/ref_tracker.h             | 20 ++++++++++++++------
 lib/ref_tracker.c                       |  6 +++---
 lib/test_ref_tracker.c                  |  2 +-
 net/core/dev.c                          |  2 +-
 net/core/net_namespace.c                |  4 ++--
 8 files changed, 24 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/display/drm_dp_tunnel.c b/drivers/gpu/drm/display/drm_dp_tunnel.c
index b9c12b8bf2a3..1205a4432eb4 100644
--- a/drivers/gpu/drm/display/drm_dp_tunnel.c
+++ b/drivers/gpu/drm/display/drm_dp_tunnel.c
@@ -1920,7 +1920,7 @@ drm_dp_tunnel_mgr_create(struct drm_device *dev, int max_group_count)
 	}
 
 #ifdef CONFIG_DRM_DISPLAY_DP_TUNNEL_STATE_DEBUG
-	ref_tracker_dir_init(&mgr->ref_tracker, 16, "drm_dptun", "dptun");
+	ref_tracker_dir_init(&mgr->ref_tracker, 16, "drm_dptun");
 #endif
 
 	for (i = 0; i < max_group_count; i++) {
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 90d90145a189..7ce3e6de0c19 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -61,7 +61,7 @@ static void init_intel_runtime_pm_wakeref(struct intel_runtime_pm *rpm)
 {
 	if (!rpm->debug.class)
 		ref_tracker_dir_init(&rpm->debug, INTEL_REFTRACK_DEAD_COUNT,
-				     "intel_runtime_pm", dev_name(rpm->kdev));
+				     "intel_runtime_pm");
 }
 
 static intel_wakeref_t
diff --git a/drivers/gpu/drm/i915/intel_wakeref.c b/drivers/gpu/drm/i915/intel_wakeref.c
index 7e74c58862c1..7fa194de5d35 100644
--- a/drivers/gpu/drm/i915/intel_wakeref.c
+++ b/drivers/gpu/drm/i915/intel_wakeref.c
@@ -115,7 +115,7 @@ void __intel_wakeref_init(struct intel_wakeref *wf,
 
 #if IS_ENABLED(CONFIG_DRM_I915_DEBUG_WAKEREF)
 	if (!wf->debug.class)
-		ref_tracker_dir_init(&wf->debug, INTEL_REFTRACK_DEAD_COUNT, "intel_wakeref", name);
+		ref_tracker_dir_init(&wf->debug, INTEL_REFTRACK_DEAD_COUNT, "intel_wakeref");
 #endif
 }
 
diff --git a/include/linux/ref_tracker.h b/include/linux/ref_tracker.h
index e1323de93bf6..d10563afd91c 100644
--- a/include/linux/ref_tracker.h
+++ b/include/linux/ref_tracker.h
@@ -20,7 +20,6 @@ struct ref_tracker_dir {
 	struct list_head	list; /* List of active trackers */
 	struct list_head	quarantine; /* List of dead trackers */
 	const char		*class; /* object classname */
-	char			name[32];
 #endif
 };
 
@@ -44,10 +43,21 @@ void ref_tracker_dir_symlink(struct ref_tracker_dir *dir, const char *fmt, ...)
 
 #endif /* CONFIG_DEBUG_FS */
 
+/**
+ * ref_tracker_dir_init - initialize a ref_tracker dir
+ * @dir: ref_tracker_dir to be initialized
+ * @quarantine_count: max number of entries to be tracked
+ * @class: pointer to static string that describes object type
+ *
+ * Initialize a ref_tracker_dir. If debugfs is configured, then a file
+ * will also be created for it under the top-level ref_tracker debugfs
+ * directory.
+ *
+ * Note that @class must point to a static string.
+ */
 static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 					unsigned int quarantine_count,
-					const char *class,
-					const char *name)
+					const char *class)
 {
 	INIT_LIST_HEAD(&dir->list);
 	INIT_LIST_HEAD(&dir->quarantine);
@@ -57,7 +67,6 @@ static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 	refcount_set(&dir->untracked, 1);
 	refcount_set(&dir->no_tracker, 1);
 	dir->class = class;
-	strscpy(dir->name, name, sizeof(dir->name));
 	ref_tracker_dir_debugfs(dir);
 	stack_depot_init();
 }
@@ -82,8 +91,7 @@ int ref_tracker_free(struct ref_tracker_dir *dir,
 
 static inline void ref_tracker_dir_init(struct ref_tracker_dir *dir,
 					unsigned int quarantine_count,
-					const char *class,
-					const char *name)
+					const char *class)
 {
 }
 
diff --git a/lib/ref_tracker.c b/lib/ref_tracker.c
index 6608520d6118..dcf923a1edf5 100644
--- a/lib/ref_tracker.c
+++ b/lib/ref_tracker.c
@@ -155,7 +155,7 @@ __ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir,
 	stats = ref_tracker_get_stats(dir, display_limit);
 	if (IS_ERR(stats)) {
 		pr_ostream(s, "%s%s@%p: couldn't get stats, error %pe\n",
-			   s->prefix, dir->name, dir, stats);
+			   s->prefix, dir->class, dir, stats);
 		return;
 	}
 
@@ -166,14 +166,14 @@ __ref_tracker_dir_pr_ostream(struct ref_tracker_dir *dir,
 		if (sbuf && !stack_depot_snprint(stack, sbuf, STACK_BUF_SIZE, 4))
 			sbuf[0] = 0;
 		pr_ostream(s, "%s%s@%p has %d/%d users at\n%s\n", s->prefix,
-			   dir->name, dir, stats->stacks[i].count,
+			   dir->class, dir, stats->stacks[i].count,
 			   stats->total, sbuf);
 		skipped -= stats->stacks[i].count;
 	}
 
 	if (skipped)
 		pr_ostream(s, "%s%s@%p skipped reports about %d/%d users.\n",
-			   s->prefix, dir->name, dir, skipped, stats->total);
+			   s->prefix, dir->class, dir, skipped, stats->total);
 
 	kfree(sbuf);
 
diff --git a/lib/test_ref_tracker.c b/lib/test_ref_tracker.c
index d263502a4c1d..b983ceb12afc 100644
--- a/lib/test_ref_tracker.c
+++ b/lib/test_ref_tracker.c
@@ -64,7 +64,7 @@ static int __init test_ref_tracker_init(void)
 {
 	int i;
 
-	ref_tracker_dir_init(&ref_dir, 100, "selftest", "selftest");
+	ref_tracker_dir_init(&ref_dir, 100, "selftest");
 
 	timer_setup(&test_ref_tracker_timer, test_ref_tracker_timer_func, 0);
 	mod_timer(&test_ref_tracker_timer, jiffies + 1);
diff --git a/net/core/dev.c b/net/core/dev.c
index 12cf4e5ae9c5..92a830162dd8 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11715,7 +11715,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name,
 
 	dev->priv_len = sizeof_priv;
 
-	ref_tracker_dir_init(&dev->refcnt_tracker, 128, "netdev", name);
+	ref_tracker_dir_init(&dev->refcnt_tracker, 128, "netdev");
 #ifdef CONFIG_PCPU_DEV_REFCNT
 	dev->pcpu_refcnt = alloc_percpu(int);
 	if (!dev->pcpu_refcnt)
diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c
index 45de05d8f087..d0f607507ee8 100644
--- a/net/core/net_namespace.c
+++ b/net/core/net_namespace.c
@@ -403,8 +403,8 @@ static __net_init void preinit_net(struct net *net, struct user_namespace *user_
 {
 	refcount_set(&net->passive, 1);
 	refcount_set(&net->ns.count, 1);
-	ref_tracker_dir_init(&net->refcnt_tracker, 128, "net_refcnt", "net_refcnt");
-	ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net_notrefcnt", "net_notrefcnt");
+	ref_tracker_dir_init(&net->refcnt_tracker, 128, "net_refcnt");
+	ref_tracker_dir_init(&net->notrefcnt_tracker, 128, "net_notrefcnt");
 
 	get_random_bytes(&net->hash_mix, sizeof(u32));
 	net->dev_base_seq = 1;
-- 
cgit v1.2.3


From 5f4081d6fafec6c9dca9e7990e783b70db854a5c Mon Sep 17 00:00:00 2001
From: Jerome Brunet <jbrunet@baylibre.com>
Date: Thu, 17 Apr 2025 15:44:22 +0200
Subject: clk: add a clk_hw helpers to get the clock device or device_node

Add helpers to get the device or device_node associated with clk_hw.

This can be used by clock drivers to access various device related
functionality such as devres, dev_ prints, etc ...

Signed-off-by: Jerome Brunet <jbrunet@baylibre.com>
Link: https://lore.kernel.org/r/20250417-clk-hw-get-helpers-v1-1-7743e509612a@baylibre.com
Reviewed-by: Brian Masney <bmasney@redhat.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/clk/clk.c            | 12 ++++++++++++
 include/linux/clk-provider.h | 26 ++++++++++++++++++++++++++
 2 files changed, 38 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/clk/clk.c b/drivers/clk/clk.c
index 0565c87656cf..b821b2cdb155 100644
--- a/drivers/clk/clk.c
+++ b/drivers/clk/clk.c
@@ -365,6 +365,18 @@ const char *clk_hw_get_name(const struct clk_hw *hw)
 }
 EXPORT_SYMBOL_GPL(clk_hw_get_name);
 
+struct device *clk_hw_get_dev(const struct clk_hw *hw)
+{
+	return hw->core->dev;
+}
+EXPORT_SYMBOL_GPL(clk_hw_get_dev);
+
+struct device_node *clk_hw_get_of_node(const struct clk_hw *hw)
+{
+	return hw->core->of_node;
+}
+EXPORT_SYMBOL_GPL(clk_hw_get_of_node);
+
 struct clk_hw *__clk_get_hw(struct clk *clk)
 {
 	return !clk ? NULL : clk->core->hw;
diff --git a/include/linux/clk-provider.h b/include/linux/clk-provider.h
index 2e6e603b7493..630705a47129 100644
--- a/include/linux/clk-provider.h
+++ b/include/linux/clk-provider.h
@@ -1360,6 +1360,32 @@ void clk_hw_unregister(struct clk_hw *hw);
 /* helper functions */
 const char *__clk_get_name(const struct clk *clk);
 const char *clk_hw_get_name(const struct clk_hw *hw);
+
+/**
+ * clk_hw_get_dev() - get device from an hardware clock.
+ * @hw: the clk_hw pointer to get the struct device from
+ *
+ * This is a helper to get the struct device associated with a hardware
+ * clock. Some clock controllers, such as the one registered with
+ * CLK_OF_DECLARE(), may have not provided a device pointer while
+ * registering the clock.
+ *
+ * Return: the struct device associated with the clock, or NULL if there
+ * is none.
+ */
+struct device *clk_hw_get_dev(const struct clk_hw *hw);
+
+/**
+ * clk_hw_get_of_node() - get device_node from a hardware clock.
+ * @hw: the clk_hw pointer to get the struct device_node from
+ *
+ * This is a helper to get the struct device_node associated with a
+ * hardware clock.
+ *
+ * Return: the struct device_node associated with the clock, or NULL
+ * if there is none.
+ */
+struct device_node *clk_hw_get_of_node(const struct clk_hw *hw);
 #ifdef CONFIG_COMMON_CLK
 struct clk_hw *__clk_get_hw(struct clk *clk);
 #else
-- 
cgit v1.2.3


From aa34ecc42a2138af76642b68b53a5a07cb12fe43 Mon Sep 17 00:00:00 2001
From: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Date: Wed, 28 May 2025 09:09:47 +0530
Subject: wifi: ieee80211: add Radio Measurement action fields

Drivers that support Tx power insertion could examine the outgoing Radio
measurement packet and depending on the packet type, the driver can
insert specific data fields in it. These action field values will help
drivers classify the action code within the Radio Measurement action
packet.

These action fields are defined in IEEE 802.11-2024 - Table 9-470, Radio
Measurement Action field values.

Signed-off-by: Aditya Kumar Singh <aditya.kumar.singh@oss.qualcomm.com>
Link: https://patch.msgid.link/20250528-add_rrm_action_code-v1-1-6b7c78b5bbaf@oss.qualcomm.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 10 ++++++++++
 1 file changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 22f39e5e2ff1..120de474a8bf 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -4007,6 +4007,16 @@ enum ieee80211_s1g_actioncode {
 	WLAN_S1G_TWT_INFORMATION = 11,
 };
 
+/* Radio measurement action codes as defined in IEEE 802.11-2024 - Table 9-470 */
+enum ieee80211_radio_measurement_actioncode {
+	WLAN_RM_ACTION_RADIO_MEASUREMENT_REQUEST = 0,
+	WLAN_RM_ACTION_RADIO_MEASUREMENT_REPORT  = 1,
+	WLAN_RM_ACTION_LINK_MEASUREMENT_REQUEST  = 2,
+	WLAN_RM_ACTION_LINK_MEASUREMENT_REPORT   = 3,
+	WLAN_RM_ACTION_NEIGHBOR_REPORT_REQUEST   = 4,
+	WLAN_RM_ACTION_NEIGHBOR_REPORT_RESPONSE  = 5,
+};
+
 #define IEEE80211_WEP_IV_LEN		4
 #define IEEE80211_WEP_ICV_LEN		4
 #define IEEE80211_CCMP_HDR_LEN		8
-- 
cgit v1.2.3


From 4051ead99888f101be92c7ce90d2de09aac6fd1c Mon Sep 17 00:00:00 2001
From: Li Chen <chenl311@chinatelecom.cn>
Date: Fri, 20 Jun 2025 20:02:31 +0800
Subject: HID: rate-limit hid_warn to prevent log flooding

Syzkaller can create many uhid devices that trigger
repeated warnings like:

  "hid-generic xxxx: unknown main item tag 0x0"

These messages can flood the system log, especially if a crash occurs
(e.g., with a slow UART console, leading to soft lockups). To mitigate
this, convert `hid_warn()` to use `dev_warn_ratelimited()`.

This helps reduce log noise and improves system stability under fuzzing
or faulty device scenarios.

Signed-off-by: Li Chen <chenl311@chinatelecom.cn>
Signed-off-by: Jiri Kosina <jkosina@suse.com>
---
 drivers/hid/hid-core.c | 4 ++--
 include/linux/hid.h    | 2 ++
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 4a00bd4a4224..ef1f79951d9b 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -659,9 +659,9 @@ static int hid_parser_main(struct hid_parser *parser, struct hid_item *item)
 	default:
 		if (item->tag >= HID_MAIN_ITEM_TAG_RESERVED_MIN &&
 			item->tag <= HID_MAIN_ITEM_TAG_RESERVED_MAX)
-			hid_warn(parser->device, "reserved main item tag 0x%x\n", item->tag);
+			hid_warn_ratelimited(parser->device, "reserved main item tag 0x%x\n", item->tag);
 		else
-			hid_warn(parser->device, "unknown main item tag 0x%x\n", item->tag);
+			hid_warn_ratelimited(parser->device, "unknown main item tag 0x%x\n", item->tag);
 		ret = 0;
 	}
 
diff --git a/include/linux/hid.h b/include/linux/hid.h
index 568a9d8c749b..7f260e0e2049 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -1239,6 +1239,8 @@ void hid_quirks_exit(__u16 bus);
 	dev_notice(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_warn(hid, fmt, ...)				\
 	dev_warn(&(hid)->dev, fmt, ##__VA_ARGS__)
+#define hid_warn_ratelimited(hid, fmt, ...)				\
+	dev_warn_ratelimited(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_info(hid, fmt, ...)				\
 	dev_info(&(hid)->dev, fmt, ##__VA_ARGS__)
 #define hid_dbg(hid, fmt, ...)				\
-- 
cgit v1.2.3


From 530a8ba71b4c3b7fcee323dd997f4bab1be1a6ba Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 16 May 2025 14:35:35 -0700
Subject: KVM: Bound the number of dirty ring entries in a single reset at
 INT_MAX

Cap the number of ring entries that are reset in a single ioctl to INT_MAX
to ensure userspace isn't confused by a wrap into negative space, and so
that, in a truly pathological scenario, KVM doesn't miss a TLB flush due
to the count wrapping to zero.  While the size of the ring is fixed at
0x10000 entries and KVM (currently) supports at most 4096, userspace is
allowed to harvest entries from the ring while the reset is in-progress,
i.e. it's possible for the ring to always have harvested entries.

Opportunistically return an actual error code from the helper so that a
future fix to handle pending signals can gracefully return -EINTR.  Drop
the function comment now that the return code is a stanard 0/-errno (and
because a future commit will add a proper lockdep assertion).

Opportunistically drop a similarly stale comment for kvm_dirty_ring_push().

Cc: Peter Xu <peterx@redhat.com>
Cc: Yan Zhao <yan.y.zhao@intel.com>
Cc: Maxim Levitsky <mlevitsk@redhat.com>
Cc: Binbin Wu <binbin.wu@linux.intel.com>
Fixes: fb04a1eddb1a ("KVM: X86: Implement ring-based dirty memory tracking")
Reviewed-by: James Houghton <jthoughton@google.com>
Reviewed-by: Binbin Wu <binbin.wu@linux.intel.com>
Reviewed-by: Yan Zhao <yan.y.zhao@intel.com>
Reviewed-by: Peter Xu <peterx@redhat.com>
Link: https://lore.kernel.org/r/20250516213540.2546077-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/kvm_dirty_ring.h | 18 +++++-------------
 virt/kvm/dirty_ring.c          | 10 +++++-----
 virt/kvm/kvm_main.c            |  9 ++++++---
 3 files changed, 16 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kvm_dirty_ring.h b/include/linux/kvm_dirty_ring.h
index da4d9b5f58f1..eb10d87adf7d 100644
--- a/include/linux/kvm_dirty_ring.h
+++ b/include/linux/kvm_dirty_ring.h
@@ -49,9 +49,10 @@ static inline int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *r
 }
 
 static inline int kvm_dirty_ring_reset(struct kvm *kvm,
-				       struct kvm_dirty_ring *ring)
+				       struct kvm_dirty_ring *ring,
+				       int *nr_entries_reset)
 {
-	return 0;
+	return -ENOENT;
 }
 
 static inline void kvm_dirty_ring_push(struct kvm_vcpu *vcpu,
@@ -77,17 +78,8 @@ bool kvm_arch_allow_write_without_running_vcpu(struct kvm *kvm);
 u32 kvm_dirty_ring_get_rsvd_entries(struct kvm *kvm);
 int kvm_dirty_ring_alloc(struct kvm *kvm, struct kvm_dirty_ring *ring,
 			 int index, u32 size);
-
-/*
- * called with kvm->slots_lock held, returns the number of
- * processed pages.
- */
-int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring);
-
-/*
- * returns =0: successfully pushed
- *         <0: unable to push, need to wait
- */
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring,
+			 int *nr_entries_reset);
 void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset);
 
 bool kvm_dirty_ring_check_request(struct kvm_vcpu *vcpu);
diff --git a/virt/kvm/dirty_ring.c b/virt/kvm/dirty_ring.c
index d14ffc7513ee..77986f34eff8 100644
--- a/virt/kvm/dirty_ring.c
+++ b/virt/kvm/dirty_ring.c
@@ -105,19 +105,19 @@ static inline bool kvm_dirty_gfn_harvested(struct kvm_dirty_gfn *gfn)
 	return smp_load_acquire(&gfn->flags) & KVM_DIRTY_GFN_F_RESET;
 }
 
-int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
+int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring,
+			 int *nr_entries_reset)
 {
 	u32 cur_slot, next_slot;
 	u64 cur_offset, next_offset;
 	unsigned long mask;
-	int count = 0;
 	struct kvm_dirty_gfn *entry;
 	bool first_round = true;
 
 	/* This is only needed to make compilers happy */
 	cur_slot = cur_offset = mask = 0;
 
-	while (true) {
+	while (likely((*nr_entries_reset) < INT_MAX)) {
 		entry = &ring->dirty_gfns[ring->reset_index & (ring->size - 1)];
 
 		if (!kvm_dirty_gfn_harvested(entry))
@@ -130,7 +130,7 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
 		kvm_dirty_gfn_set_invalid(entry);
 
 		ring->reset_index++;
-		count++;
+		(*nr_entries_reset)++;
 		/*
 		 * Try to coalesce the reset operations when the guest is
 		 * scanning pages in the same slot.
@@ -167,7 +167,7 @@ int kvm_dirty_ring_reset(struct kvm *kvm, struct kvm_dirty_ring *ring)
 
 	trace_kvm_dirty_ring_reset(ring);
 
-	return count;
+	return 0;
 }
 
 void kvm_dirty_ring_push(struct kvm_vcpu *vcpu, u32 slot, u64 offset)
diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
index eec82775c5bf..c784b6708708 100644
--- a/virt/kvm/kvm_main.c
+++ b/virt/kvm/kvm_main.c
@@ -4962,15 +4962,18 @@ static int kvm_vm_ioctl_reset_dirty_pages(struct kvm *kvm)
 {
 	unsigned long i;
 	struct kvm_vcpu *vcpu;
-	int cleared = 0;
+	int cleared = 0, r;
 
 	if (!kvm->dirty_ring_size)
 		return -EINVAL;
 
 	mutex_lock(&kvm->slots_lock);
 
-	kvm_for_each_vcpu(i, vcpu, kvm)
-		cleared += kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring);
+	kvm_for_each_vcpu(i, vcpu, kvm) {
+		r = kvm_dirty_ring_reset(vcpu->kvm, &vcpu->dirty_ring, &cleared);
+		if (r)
+			break;
+	}
 
 	mutex_unlock(&kvm->slots_lock);
 
-- 
cgit v1.2.3


From cd4178d19420359554e3da6fd77ecfd0f58067ce Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 12 Jun 2025 16:51:47 -0700
Subject: KVM: arm64: WARN if unmapping a vLPI fails in any path

When unmapping a vLPI, WARN if nullifying vCPU affinity fails, not just if
failure occurs when freeing an ITE.  If undoing vCPU affinity fails, then
odds are very good that vLPI state tracking has has gotten out of whack,
i.e. that KVM and the GIC disagree on the state of an IRQ/vLPI.  At best,
inconsistent state means there is a lurking bug/flaw somewhere.  At worst,
the inconsistency could eventually be fatal to the host, e.g. if an ITS
command fails because KVM's view of things doesn't match reality/hardware.

Note, only the call from kvm_arch_irq_bypass_del_producer() by way of
kvm_vgic_v4_unset_forwarding() doesn't already WARN.  Common KVM's
kvm_irq_routing_update() WARNs if kvm_arch_update_irqfd_routing() fails.
For that path, if its_unmap_vlpi() fails in kvm_vgic_v4_unset_forwarding(),
the only possible causes are that the GIC doesn't have a v4 ITS (from
its_irq_set_vcpu_affinity()):

        /* Need a v4 ITS */
        if (!is_v4(its_dev->its))
                return -EINVAL;

        guard(raw_spinlock)(&its_dev->event_map.vlpi_lock);

        /* Unmap request? */
        if (!info)
                return its_vlpi_unmap(d);

or that KVM has gotten out of sync with the GIC/ITS (from its_vlpi_unmap()):

        if (!its_dev->event_map.vm || !irqd_is_forwarded_to_vcpu(d))
                return -EINVAL;

All of the above failure scenarios are warnable offences, as they should
never occur absent a kernel/KVM bug.

Acked-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/all/aFWY2LTVIxz5rfhh@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/vgic/vgic-its.c     | 2 +-
 arch/arm64/kvm/vgic/vgic-v4.c      | 4 ++--
 drivers/irqchip/irq-gic-v4.c       | 4 ++--
 include/linux/irqchip/arm-gic-v4.h | 2 +-
 4 files changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kvm/vgic/vgic-its.c b/arch/arm64/kvm/vgic/vgic-its.c
index 534049c7c94b..98630dae910d 100644
--- a/arch/arm64/kvm/vgic/vgic-its.c
+++ b/arch/arm64/kvm/vgic/vgic-its.c
@@ -758,7 +758,7 @@ static void its_free_ite(struct kvm *kvm, struct its_ite *ite)
 	if (irq) {
 		scoped_guard(raw_spinlock_irqsave, &irq->irq_lock) {
 			if (irq->hw)
-				WARN_ON(its_unmap_vlpi(ite->irq->host_irq));
+				its_unmap_vlpi(ite->irq->host_irq);
 
 			irq->hw = false;
 		}
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index 193946108192..911170d4a9c8 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -545,10 +545,10 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq)
 	if (irq->hw) {
 		atomic_dec(&irq->target_vcpu->arch.vgic_cpu.vgic_v3.its_vpe.vlpi_count);
 		irq->hw = false;
-		ret = its_unmap_vlpi(host_irq);
+		its_unmap_vlpi(host_irq);
 	}
 
 	raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 	vgic_put_irq(kvm, irq);
-	return ret;
+	return 0;
 }
diff --git a/drivers/irqchip/irq-gic-v4.c b/drivers/irqchip/irq-gic-v4.c
index 58c28895f8c4..8455b4a5fbb0 100644
--- a/drivers/irqchip/irq-gic-v4.c
+++ b/drivers/irqchip/irq-gic-v4.c
@@ -342,10 +342,10 @@ int its_get_vlpi(int irq, struct its_vlpi_map *map)
 	return irq_set_vcpu_affinity(irq, &info);
 }
 
-int its_unmap_vlpi(int irq)
+void its_unmap_vlpi(int irq)
 {
 	irq_clear_status_flags(irq, IRQ_DISABLE_UNLAZY);
-	return irq_set_vcpu_affinity(irq, NULL);
+	WARN_ON_ONCE(irq_set_vcpu_affinity(irq, NULL));
 }
 
 int its_prop_update_vlpi(int irq, u8 config, bool inv)
diff --git a/include/linux/irqchip/arm-gic-v4.h b/include/linux/irqchip/arm-gic-v4.h
index 7f1f11a5e4e4..0b0887099fd7 100644
--- a/include/linux/irqchip/arm-gic-v4.h
+++ b/include/linux/irqchip/arm-gic-v4.h
@@ -146,7 +146,7 @@ int its_commit_vpe(struct its_vpe *vpe);
 int its_invall_vpe(struct its_vpe *vpe);
 int its_map_vlpi(int irq, struct its_vlpi_map *map);
 int its_get_vlpi(int irq, struct its_vlpi_map *map);
-int its_unmap_vlpi(int irq);
+void its_unmap_vlpi(int irq);
 int its_prop_update_vlpi(int irq, u8 config, bool inv);
 int its_prop_update_vsgi(int irq, u8 priority, bool group);
 
-- 
cgit v1.2.3


From 2b521d86ee80a436a92445b8206d38d75aeb39ea Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 16 May 2025 16:07:29 -0700
Subject: irqbypass: Take ownership of producer/consumer token tracking

Move ownership of IRQ bypass token tracking into irqbypass.ko, and
explicitly require callers to pass an eventfd_ctx structure instead of a
completely opaque token.  Relying on producers and consumers to set the
token appropriately is error prone, and hiding the fact that the token must
be an eventfd_ctx pointer (for all intents and purposes) unnecessarily
obfuscates the code and makes it more brittle.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/r/20250516230734.2564775-4-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/x86.c                |  4 ++--
 drivers/vfio/pci/vfio_pci_intrs.c |  9 +++-----
 drivers/vhost/vdpa.c              |  8 +++----
 include/linux/irqbypass.h         | 35 +++++++++++++++++--------------
 virt/kvm/eventfd.c                |  7 +++----
 virt/lib/irqbypass.c              | 44 +++++++++++++++++++++++++--------------
 6 files changed, 58 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index b58a74c1722d..3dc93e2d4777 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13669,8 +13669,8 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
 					   prod->irq, irqfd->gsi, 0);
 	if (ret)
-		printk(KERN_INFO "irq bypass consumer (token %p) unregistration"
-		       " fails: %d\n", irqfd->consumer.token, ret);
+		printk(KERN_INFO "irq bypass consumer (eventfd %p) unregistration"
+		       " fails: %d\n", irqfd->consumer.eventfd, ret);
 
 	spin_unlock_irq(&kvm->irqfds.lock);
 
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 565966351dfa..d87fe116762a 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -505,15 +505,12 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_core_device *vdev,
 	if (ret)
 		goto out_put_eventfd_ctx;
 
-	ctx->producer.token = trigger;
 	ctx->producer.irq = irq;
-	ret = irq_bypass_register_producer(&ctx->producer);
+	ret = irq_bypass_register_producer(&ctx->producer, trigger);
 	if (unlikely(ret)) {
 		dev_info(&pdev->dev,
-		"irq bypass producer (token %p) registration fails: %d\n",
-		ctx->producer.token, ret);
-
-		ctx->producer.token = NULL;
+		"irq bypass producer (eventfd %p) registration fails: %d\n",
+		trigger, ret);
 	}
 	ctx->trigger = trigger;
 
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 5a49b5a6d496..7b265ffda697 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -213,10 +213,10 @@ static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid)
 		return;
 
 	vq->call_ctx.producer.irq = irq;
-	ret = irq_bypass_register_producer(&vq->call_ctx.producer);
+	ret = irq_bypass_register_producer(&vq->call_ctx.producer, vq->call_ctx.ctx);
 	if (unlikely(ret))
-		dev_info(&v->dev, "vq %u, irq bypass producer (token %p) registration fails, ret =  %d\n",
-			 qid, vq->call_ctx.producer.token, ret);
+		dev_info(&v->dev, "vq %u, irq bypass producer (eventfd %p) registration fails, ret =  %d\n",
+			 qid, vq->call_ctx.ctx, ret);
 }
 
 static void vhost_vdpa_unsetup_vq_irq(struct vhost_vdpa *v, u16 qid)
@@ -712,7 +712,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 			if (ops->get_status(vdpa) &
 			    VIRTIO_CONFIG_S_DRIVER_OK)
 				vhost_vdpa_unsetup_vq_irq(v, idx);
-			vq->call_ctx.producer.token = NULL;
 		}
 		break;
 	}
@@ -753,7 +752,6 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
 			cb.callback = vhost_vdpa_virtqueue_cb;
 			cb.private = vq;
 			cb.trigger = vq->call_ctx.ctx;
-			vq->call_ctx.producer.token = vq->call_ctx.ctx;
 			if (ops->get_status(vdpa) &
 			    VIRTIO_CONFIG_S_DRIVER_OK)
 				vhost_vdpa_setup_vq_irq(v, idx);
diff --git a/include/linux/irqbypass.h b/include/linux/irqbypass.h
index 9bdb2a781841..1b57d15ac4cf 100644
--- a/include/linux/irqbypass.h
+++ b/include/linux/irqbypass.h
@@ -10,6 +10,7 @@
 
 #include <linux/list.h>
 
+struct eventfd_ctx;
 struct irq_bypass_consumer;
 
 /*
@@ -18,20 +19,20 @@ struct irq_bypass_consumer;
  * The IRQ bypass manager is a simple set of lists and callbacks that allows
  * IRQ producers (ex. physical interrupt sources) to be matched to IRQ
  * consumers (ex. virtualization hardware that allows IRQ bypass or offload)
- * via a shared token (ex. eventfd_ctx).  Producers and consumers register
- * independently.  When a token match is found, the optional @stop callback
- * will be called for each participant.  The pair will then be connected via
- * the @add_* callbacks, and finally the optional @start callback will allow
- * any final coordination.  When either participant is unregistered, the
- * process is repeated using the @del_* callbacks in place of the @add_*
- * callbacks.  Match tokens must be unique per producer/consumer, 1:N pairings
- * are not supported.
+ * via a shared eventfd_ctx.  Producers and consumers register independently.
+ * When a producer and consumer are paired, i.e. an eventfd match is found, the
+ * optional @stop callback will be called for each participant.  The pair will
+ * then be connected via the @add_* callbacks, and finally the optional @start
+ * callback will allow any final coordination.  When either participant is
+ * unregistered, the process is repeated using the @del_* callbacks in place of
+ * the @add_* callbacks.  eventfds must be unique per producer/consumer, 1:N
+ * pairings are not supported.
  */
 
 /**
  * struct irq_bypass_producer - IRQ bypass producer definition
  * @node: IRQ bypass manager private list management
- * @token: opaque token to match between producer and consumer (non-NULL)
+ * @eventfd: eventfd context used to match producers and consumers
  * @irq: Linux IRQ number for the producer device
  * @add_consumer: Connect the IRQ producer to an IRQ consumer (optional)
  * @del_consumer: Disconnect the IRQ producer from an IRQ consumer (optional)
@@ -44,7 +45,7 @@ struct irq_bypass_consumer;
  */
 struct irq_bypass_producer {
 	struct list_head node;
-	void *token;
+	struct eventfd_ctx *eventfd;
 	int irq;
 	int (*add_consumer)(struct irq_bypass_producer *,
 			    struct irq_bypass_consumer *);
@@ -57,7 +58,7 @@ struct irq_bypass_producer {
 /**
  * struct irq_bypass_consumer - IRQ bypass consumer definition
  * @node: IRQ bypass manager private list management
- * @token: opaque token to match between producer and consumer (non-NULL)
+ * @eventfd: eventfd context used to match producers and consumers
  * @add_producer: Connect the IRQ consumer to an IRQ producer
  * @del_producer: Disconnect the IRQ consumer from an IRQ producer
  * @stop: Perform any quiesce operations necessary prior to add/del (optional)
@@ -70,7 +71,7 @@ struct irq_bypass_producer {
  */
 struct irq_bypass_consumer {
 	struct list_head node;
-	void *token;
+	struct eventfd_ctx *eventfd;
 	int (*add_producer)(struct irq_bypass_consumer *,
 			    struct irq_bypass_producer *);
 	void (*del_producer)(struct irq_bypass_consumer *,
@@ -79,9 +80,11 @@ struct irq_bypass_consumer {
 	void (*start)(struct irq_bypass_consumer *);
 };
 
-int irq_bypass_register_producer(struct irq_bypass_producer *);
-void irq_bypass_unregister_producer(struct irq_bypass_producer *);
-int irq_bypass_register_consumer(struct irq_bypass_consumer *);
-void irq_bypass_unregister_consumer(struct irq_bypass_consumer *);
+int irq_bypass_register_producer(struct irq_bypass_producer *producer,
+				 struct eventfd_ctx *eventfd);
+void irq_bypass_unregister_producer(struct irq_bypass_producer *producer);
+int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer,
+				 struct eventfd_ctx *eventfd);
+void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer);
 
 #endif /* IRQBYPASS_H */
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 11e5d1e3f12e..5bc6abe30748 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -426,15 +426,14 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 
 #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
 	if (kvm_arch_has_irq_bypass()) {
-		irqfd->consumer.token = (void *)irqfd->eventfd;
 		irqfd->consumer.add_producer = kvm_arch_irq_bypass_add_producer;
 		irqfd->consumer.del_producer = kvm_arch_irq_bypass_del_producer;
 		irqfd->consumer.stop = kvm_arch_irq_bypass_stop;
 		irqfd->consumer.start = kvm_arch_irq_bypass_start;
-		ret = irq_bypass_register_consumer(&irqfd->consumer);
+		ret = irq_bypass_register_consumer(&irqfd->consumer, irqfd->eventfd);
 		if (ret)
-			pr_info("irq bypass consumer (token %p) registration fails: %d\n",
-				irqfd->consumer.token, ret);
+			pr_info("irq bypass consumer (eventfd %p) registration fails: %d\n",
+				irqfd->eventfd, ret);
 	}
 #endif
 
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
index 28a4d933569a..e8d7c420db52 100644
--- a/virt/lib/irqbypass.c
+++ b/virt/lib/irqbypass.c
@@ -77,30 +77,32 @@ static void __disconnect(struct irq_bypass_producer *prod,
 /**
  * irq_bypass_register_producer - register IRQ bypass producer
  * @producer: pointer to producer structure
+ * @eventfd: pointer to the eventfd context associated with the producer
  *
  * Add the provided IRQ producer to the list of producers and connect
- * with any matching token found on the IRQ consumers list.
+ * with any matching eventfd found on the IRQ consumers list.
  */
-int irq_bypass_register_producer(struct irq_bypass_producer *producer)
+int irq_bypass_register_producer(struct irq_bypass_producer *producer,
+				 struct eventfd_ctx *eventfd)
 {
 	struct irq_bypass_producer *tmp;
 	struct irq_bypass_consumer *consumer;
 	int ret;
 
-	if (!producer->token)
+	if (WARN_ON_ONCE(producer->eventfd))
 		return -EINVAL;
 
 	mutex_lock(&lock);
 
 	list_for_each_entry(tmp, &producers, node) {
-		if (tmp->token == producer->token) {
+		if (tmp->eventfd == eventfd) {
 			ret = -EBUSY;
 			goto out_err;
 		}
 	}
 
 	list_for_each_entry(consumer, &consumers, node) {
-		if (consumer->token == producer->token) {
+		if (consumer->eventfd == eventfd) {
 			ret = __connect(producer, consumer);
 			if (ret)
 				goto out_err;
@@ -108,6 +110,7 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer)
 		}
 	}
 
+	producer->eventfd = eventfd;
 	list_add(&producer->node, &producers);
 
 	mutex_unlock(&lock);
@@ -131,26 +134,28 @@ void irq_bypass_unregister_producer(struct irq_bypass_producer *producer)
 	struct irq_bypass_producer *tmp;
 	struct irq_bypass_consumer *consumer;
 
-	if (!producer->token)
+	if (!producer->eventfd)
 		return;
 
 	mutex_lock(&lock);
 
 	list_for_each_entry(tmp, &producers, node) {
-		if (tmp->token != producer->token)
+		if (tmp->eventfd != producer->eventfd)
 			continue;
 
 		list_for_each_entry(consumer, &consumers, node) {
-			if (consumer->token == producer->token) {
+			if (consumer->eventfd == producer->eventfd) {
 				__disconnect(producer, consumer);
 				break;
 			}
 		}
 
+		producer->eventfd = NULL;
 		list_del(&producer->node);
 		break;
 	}
 
+	WARN_ON_ONCE(producer->eventfd);
 	mutex_unlock(&lock);
 }
 EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer);
@@ -158,31 +163,35 @@ EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer);
 /**
  * irq_bypass_register_consumer - register IRQ bypass consumer
  * @consumer: pointer to consumer structure
+ * @eventfd: pointer to the eventfd context associated with the consumer
  *
  * Add the provided IRQ consumer to the list of consumers and connect
- * with any matching token found on the IRQ producer list.
+ * with any matching eventfd found on the IRQ producer list.
  */
-int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
+int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer,
+				 struct eventfd_ctx *eventfd)
 {
 	struct irq_bypass_consumer *tmp;
 	struct irq_bypass_producer *producer;
 	int ret;
 
-	if (!consumer->token ||
-	    !consumer->add_producer || !consumer->del_producer)
+	if (WARN_ON_ONCE(consumer->eventfd))
+		return -EINVAL;
+
+	if (!consumer->add_producer || !consumer->del_producer)
 		return -EINVAL;
 
 	mutex_lock(&lock);
 
 	list_for_each_entry(tmp, &consumers, node) {
-		if (tmp->token == consumer->token || tmp == consumer) {
+		if (tmp->eventfd == eventfd) {
 			ret = -EBUSY;
 			goto out_err;
 		}
 	}
 
 	list_for_each_entry(producer, &producers, node) {
-		if (producer->token == consumer->token) {
+		if (producer->eventfd == eventfd) {
 			ret = __connect(producer, consumer);
 			if (ret)
 				goto out_err;
@@ -190,6 +199,7 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer)
 		}
 	}
 
+	consumer->eventfd = eventfd;
 	list_add(&consumer->node, &consumers);
 
 	mutex_unlock(&lock);
@@ -213,7 +223,7 @@ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
 	struct irq_bypass_consumer *tmp;
 	struct irq_bypass_producer *producer;
 
-	if (!consumer->token)
+	if (!consumer->eventfd)
 		return;
 
 	mutex_lock(&lock);
@@ -223,16 +233,18 @@ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
 			continue;
 
 		list_for_each_entry(producer, &producers, node) {
-			if (producer->token == consumer->token) {
+			if (producer->eventfd == consumer->eventfd) {
 				__disconnect(producer, consumer);
 				break;
 			}
 		}
 
+		consumer->eventfd = NULL;
 		list_del(&consumer->node);
 		break;
 	}
 
+	WARN_ON_ONCE(consumer->eventfd);
 	mutex_unlock(&lock);
 }
 EXPORT_SYMBOL_GPL(irq_bypass_unregister_consumer);
-- 
cgit v1.2.3


From add57f493e0893ac0fb4acbdc441918d3e800f10 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 16 May 2025 16:07:30 -0700
Subject: irqbypass: Explicitly track producer and consumer bindings

Explicitly track IRQ bypass producer:consumer bindings.  This will allow
making removal an O(1) operation; searching through the list to find
information that is trivially tracked (and useful for debug) is wasteful.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/r/20250516230734.2564775-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/irqbypass.h | 7 +++++++
 virt/lib/irqbypass.c      | 9 +++++++++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/irqbypass.h b/include/linux/irqbypass.h
index 1b57d15ac4cf..b28197c87483 100644
--- a/include/linux/irqbypass.h
+++ b/include/linux/irqbypass.h
@@ -29,10 +29,13 @@ struct irq_bypass_consumer;
  * pairings are not supported.
  */
 
+struct irq_bypass_consumer;
+
 /**
  * struct irq_bypass_producer - IRQ bypass producer definition
  * @node: IRQ bypass manager private list management
  * @eventfd: eventfd context used to match producers and consumers
+ * @consumer: The connected consumer (NULL if no connection)
  * @irq: Linux IRQ number for the producer device
  * @add_consumer: Connect the IRQ producer to an IRQ consumer (optional)
  * @del_consumer: Disconnect the IRQ producer from an IRQ consumer (optional)
@@ -46,6 +49,7 @@ struct irq_bypass_consumer;
 struct irq_bypass_producer {
 	struct list_head node;
 	struct eventfd_ctx *eventfd;
+	struct irq_bypass_consumer *consumer;
 	int irq;
 	int (*add_consumer)(struct irq_bypass_producer *,
 			    struct irq_bypass_consumer *);
@@ -59,6 +63,7 @@ struct irq_bypass_producer {
  * struct irq_bypass_consumer - IRQ bypass consumer definition
  * @node: IRQ bypass manager private list management
  * @eventfd: eventfd context used to match producers and consumers
+ * @producer: The connected producer (NULL if no connection)
  * @add_producer: Connect the IRQ consumer to an IRQ producer
  * @del_producer: Disconnect the IRQ consumer from an IRQ producer
  * @stop: Perform any quiesce operations necessary prior to add/del (optional)
@@ -72,6 +77,8 @@ struct irq_bypass_producer {
 struct irq_bypass_consumer {
 	struct list_head node;
 	struct eventfd_ctx *eventfd;
+	struct irq_bypass_producer *producer;
+
 	int (*add_producer)(struct irq_bypass_consumer *,
 			    struct irq_bypass_producer *);
 	void (*del_producer)(struct irq_bypass_consumer *,
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
index e8d7c420db52..fdbf7ecc0c21 100644
--- a/virt/lib/irqbypass.c
+++ b/virt/lib/irqbypass.c
@@ -51,6 +51,10 @@ static int __connect(struct irq_bypass_producer *prod,
 	if (prod->start)
 		prod->start(prod);
 
+	if (!ret) {
+		prod->consumer = cons;
+		cons->producer = prod;
+	}
 	return ret;
 }
 
@@ -72,6 +76,9 @@ static void __disconnect(struct irq_bypass_producer *prod,
 		cons->start(cons);
 	if (prod->start)
 		prod->start(prod);
+
+	prod->consumer = NULL;
+	cons->producer = NULL;
 }
 
 /**
@@ -145,6 +152,7 @@ void irq_bypass_unregister_producer(struct irq_bypass_producer *producer)
 
 		list_for_each_entry(consumer, &consumers, node) {
 			if (consumer->eventfd == producer->eventfd) {
+				WARN_ON_ONCE(producer->consumer != consumer);
 				__disconnect(producer, consumer);
 				break;
 			}
@@ -234,6 +242,7 @@ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
 
 		list_for_each_entry(producer, &producers, node) {
 			if (producer->eventfd == consumer->eventfd) {
+				WARN_ON_ONCE(consumer->producer != producer);
 				__disconnect(producer, consumer);
 				break;
 			}
-- 
cgit v1.2.3


From 8394b32faecd9c63b3c436e78e62519e9548e530 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 16 May 2025 16:07:33 -0700
Subject: irqbypass: Use xarray to track producers and consumers

Track IRQ bypass producers and consumers using an xarray to avoid the O(2n)
insertion time associated with walking a list to check for duplicate
entries, and to search for an partner.

At low (tens or few hundreds) total producer/consumer counts, using a list
is faster due to the need to allocate backing storage for xarray.  But as
count creeps into the thousands, xarray wins easily, and can provide
several orders of magnitude better latency at high counts.  E.g. hundreds
of nanoseconds vs. hundreds of milliseconds.

Cc: Oliver Upton <oliver.upton@linux.dev>
Cc: David Matlack <dmatlack@google.com>
Cc: Like Xu <like.xu.linux@gmail.com>
Cc: Binbin Wu <binbin.wu@linux.intel.com>
Reported-by: Yong He <alexyonghe@tencent.com>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=217379
Link: https://lore.kernel.org/all/20230801115646.33990-1-likexu@tencent.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Link: https://lore.kernel.org/r/20250516230734.2564775-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/irqbypass.h |  4 ---
 virt/lib/irqbypass.c      | 74 ++++++++++++++++++++++++-----------------------
 2 files changed, 38 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/irqbypass.h b/include/linux/irqbypass.h
index b28197c87483..cd64fcaa88fe 100644
--- a/include/linux/irqbypass.h
+++ b/include/linux/irqbypass.h
@@ -33,7 +33,6 @@ struct irq_bypass_consumer;
 
 /**
  * struct irq_bypass_producer - IRQ bypass producer definition
- * @node: IRQ bypass manager private list management
  * @eventfd: eventfd context used to match producers and consumers
  * @consumer: The connected consumer (NULL if no connection)
  * @irq: Linux IRQ number for the producer device
@@ -47,7 +46,6 @@ struct irq_bypass_consumer;
  * for a physical device assigned to a VM.
  */
 struct irq_bypass_producer {
-	struct list_head node;
 	struct eventfd_ctx *eventfd;
 	struct irq_bypass_consumer *consumer;
 	int irq;
@@ -61,7 +59,6 @@ struct irq_bypass_producer {
 
 /**
  * struct irq_bypass_consumer - IRQ bypass consumer definition
- * @node: IRQ bypass manager private list management
  * @eventfd: eventfd context used to match producers and consumers
  * @producer: The connected producer (NULL if no connection)
  * @add_producer: Connect the IRQ consumer to an IRQ producer
@@ -75,7 +72,6 @@ struct irq_bypass_producer {
  * portions of the interrupt handling to the VM.
  */
 struct irq_bypass_consumer {
-	struct list_head node;
 	struct eventfd_ctx *eventfd;
 	struct irq_bypass_producer *producer;
 
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
index 828556c081f5..ea888b9203d2 100644
--- a/virt/lib/irqbypass.c
+++ b/virt/lib/irqbypass.c
@@ -22,8 +22,8 @@
 MODULE_LICENSE("GPL v2");
 MODULE_DESCRIPTION("IRQ bypass manager utility module");
 
-static LIST_HEAD(producers);
-static LIST_HEAD(consumers);
+static DEFINE_XARRAY(producers);
+static DEFINE_XARRAY(consumers);
 static DEFINE_MUTEX(lock);
 
 /* @lock must be held when calling connect */
@@ -86,13 +86,13 @@ static void __disconnect(struct irq_bypass_producer *prod,
  * @producer: pointer to producer structure
  * @eventfd: pointer to the eventfd context associated with the producer
  *
- * Add the provided IRQ producer to the list of producers and connect
- * with any matching eventfd found on the IRQ consumers list.
+ * Add the provided IRQ producer to the set of producers and connect with the
+ * consumer with a matching eventfd, if one exists.
  */
 int irq_bypass_register_producer(struct irq_bypass_producer *producer,
 				 struct eventfd_ctx *eventfd)
 {
-	struct irq_bypass_producer *tmp;
+	unsigned long index = (unsigned long)eventfd;
 	struct irq_bypass_consumer *consumer;
 	int ret;
 
@@ -101,22 +101,20 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer,
 
 	guard(mutex)(&lock);
 
-	list_for_each_entry(tmp, &producers, node) {
-		if (tmp->eventfd == eventfd)
-			return -EBUSY;
-	}
+	ret = xa_insert(&producers, index, producer, GFP_KERNEL);
+	if (ret)
+		return ret;
 
-	list_for_each_entry(consumer, &consumers, node) {
-		if (consumer->eventfd == eventfd) {
-			ret = __connect(producer, consumer);
-			if (ret)
-				return ret;
-			break;
+	consumer = xa_load(&consumers, index);
+	if (consumer) {
+		ret = __connect(producer, consumer);
+		if (ret) {
+			WARN_ON_ONCE(xa_erase(&producers, index) != producer);
+			return ret;
 		}
 	}
 
 	producer->eventfd = eventfd;
-	list_add(&producer->node, &producers);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(irq_bypass_register_producer);
@@ -125,11 +123,14 @@ EXPORT_SYMBOL_GPL(irq_bypass_register_producer);
  * irq_bypass_unregister_producer - unregister IRQ bypass producer
  * @producer: pointer to producer structure
  *
- * Remove a previously registered IRQ producer from the list of producers
- * and disconnect it from any connected IRQ consumer.
+ * Remove a previously registered IRQ producer (note, it's safe to call this
+ * even if registration was unsuccessful).  Disconnect from the associated
+ * consumer, if one exists.
  */
 void irq_bypass_unregister_producer(struct irq_bypass_producer *producer)
 {
+	unsigned long index = (unsigned long)producer->eventfd;
+
 	if (!producer->eventfd)
 		return;
 
@@ -138,8 +139,8 @@ void irq_bypass_unregister_producer(struct irq_bypass_producer *producer)
 	if (producer->consumer)
 		__disconnect(producer, producer->consumer);
 
+	WARN_ON_ONCE(xa_erase(&producers, index) != producer);
 	producer->eventfd = NULL;
-	list_del(&producer->node);
 }
 EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer);
 
@@ -148,13 +149,13 @@ EXPORT_SYMBOL_GPL(irq_bypass_unregister_producer);
  * @consumer: pointer to consumer structure
  * @eventfd: pointer to the eventfd context associated with the consumer
  *
- * Add the provided IRQ consumer to the list of consumers and connect
- * with any matching eventfd found on the IRQ producer list.
+ * Add the provided IRQ consumer to the set of consumers and connect with the
+ * producer with a matching eventfd, if one exists.
  */
 int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer,
 				 struct eventfd_ctx *eventfd)
 {
-	struct irq_bypass_consumer *tmp;
+	unsigned long index = (unsigned long)eventfd;
 	struct irq_bypass_producer *producer;
 	int ret;
 
@@ -166,22 +167,20 @@ int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer,
 
 	guard(mutex)(&lock);
 
-	list_for_each_entry(tmp, &consumers, node) {
-		if (tmp->eventfd == eventfd)
-			return -EBUSY;
-	}
+	ret = xa_insert(&consumers, index, consumer, GFP_KERNEL);
+	if (ret)
+		return ret;
 
-	list_for_each_entry(producer, &producers, node) {
-		if (producer->eventfd == eventfd) {
-			ret = __connect(producer, consumer);
-			if (ret)
-				return ret;
-			break;
+	producer = xa_load(&producers, index);
+	if (producer) {
+		ret = __connect(producer, consumer);
+		if (ret) {
+			WARN_ON_ONCE(xa_erase(&consumers, index) != consumer);
+			return ret;
 		}
 	}
 
 	consumer->eventfd = eventfd;
-	list_add(&consumer->node, &consumers);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(irq_bypass_register_consumer);
@@ -190,11 +189,14 @@ EXPORT_SYMBOL_GPL(irq_bypass_register_consumer);
  * irq_bypass_unregister_consumer - unregister IRQ bypass consumer
  * @consumer: pointer to consumer structure
  *
- * Remove a previously registered IRQ consumer from the list of consumers
- * and disconnect it from any connected IRQ producer.
+ * Remove a previously registered IRQ consumer (note, it's safe to call this
+ * even if registration was unsuccessful).  Disconnect from the associated
+ * producer, if one exists.
  */
 void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
 {
+	unsigned long index = (unsigned long)consumer->eventfd;
+
 	if (!consumer->eventfd)
 		return;
 
@@ -203,7 +205,7 @@ void irq_bypass_unregister_consumer(struct irq_bypass_consumer *consumer)
 	if (consumer->producer)
 		__disconnect(consumer->producer, consumer);
 
+	WARN_ON_ONCE(xa_erase(&consumers, index) != consumer);
 	consumer->eventfd = NULL;
-	list_del(&consumer->node);
 }
 EXPORT_SYMBOL_GPL(irq_bypass_unregister_consumer);
-- 
cgit v1.2.3


From 23b54381cee2928e8b5622e654ca4516f30d2f1a Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Fri, 16 May 2025 16:07:34 -0700
Subject: irqbypass: Require producers to pass in Linux IRQ number during
 registration

Pass in the Linux IRQ associated with an IRQ bypass producer instead of
relying on the caller to set the field prior to registration, as there's
no benefit to relying on callers to do the right thing.

Take care to set producer->irq before __connect(), as KVM expects the IRQ
to be valid as soon as a connection is possible.

Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Alex Williamson <alex.williamson@redhat.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Link: https://lore.kernel.org/r/20250516230734.2564775-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 drivers/vfio/pci/vfio_pci_intrs.c | 3 +--
 drivers/vhost/vdpa.c              | 4 ++--
 include/linux/irqbypass.h         | 2 +-
 virt/lib/irqbypass.c              | 5 ++++-
 4 files changed, 8 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index d87fe116762a..123298a4dc8f 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -505,8 +505,7 @@ static int vfio_msi_set_vector_signal(struct vfio_pci_core_device *vdev,
 	if (ret)
 		goto out_put_eventfd_ctx;
 
-	ctx->producer.irq = irq;
-	ret = irq_bypass_register_producer(&ctx->producer, trigger);
+	ret = irq_bypass_register_producer(&ctx->producer, trigger, irq);
 	if (unlikely(ret)) {
 		dev_info(&pdev->dev,
 		"irq bypass producer (eventfd %p) registration fails: %d\n",
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 7b265ffda697..af1e1fdfd9ed 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -212,8 +212,8 @@ static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid)
 	if (!vq->call_ctx.ctx)
 		return;
 
-	vq->call_ctx.producer.irq = irq;
-	ret = irq_bypass_register_producer(&vq->call_ctx.producer, vq->call_ctx.ctx);
+	ret = irq_bypass_register_producer(&vq->call_ctx.producer,
+					   vq->call_ctx.ctx, irq);
 	if (unlikely(ret))
 		dev_info(&v->dev, "vq %u, irq bypass producer (eventfd %p) registration fails, ret =  %d\n",
 			 qid, vq->call_ctx.ctx, ret);
diff --git a/include/linux/irqbypass.h b/include/linux/irqbypass.h
index cd64fcaa88fe..ede1fa938152 100644
--- a/include/linux/irqbypass.h
+++ b/include/linux/irqbypass.h
@@ -84,7 +84,7 @@ struct irq_bypass_consumer {
 };
 
 int irq_bypass_register_producer(struct irq_bypass_producer *producer,
-				 struct eventfd_ctx *eventfd);
+				 struct eventfd_ctx *eventfd, int irq);
 void irq_bypass_unregister_producer(struct irq_bypass_producer *producer);
 int irq_bypass_register_consumer(struct irq_bypass_consumer *consumer,
 				 struct eventfd_ctx *eventfd);
diff --git a/virt/lib/irqbypass.c b/virt/lib/irqbypass.c
index ea888b9203d2..62c160200be9 100644
--- a/virt/lib/irqbypass.c
+++ b/virt/lib/irqbypass.c
@@ -85,12 +85,13 @@ static void __disconnect(struct irq_bypass_producer *prod,
  * irq_bypass_register_producer - register IRQ bypass producer
  * @producer: pointer to producer structure
  * @eventfd: pointer to the eventfd context associated with the producer
+ * @irq: Linux IRQ number of the underlying producer device
  *
  * Add the provided IRQ producer to the set of producers and connect with the
  * consumer with a matching eventfd, if one exists.
  */
 int irq_bypass_register_producer(struct irq_bypass_producer *producer,
-				 struct eventfd_ctx *eventfd)
+				 struct eventfd_ctx *eventfd, int irq)
 {
 	unsigned long index = (unsigned long)eventfd;
 	struct irq_bypass_consumer *consumer;
@@ -99,6 +100,8 @@ int irq_bypass_register_producer(struct irq_bypass_producer *producer,
 	if (WARN_ON_ONCE(producer->eventfd))
 		return -EINVAL;
 
+	producer->irq = irq;
+
 	guard(mutex)(&lock);
 
 	ret = xa_insert(&producers, index, producer, GFP_KERNEL);
-- 
cgit v1.2.3


From e295d2e7fbe69ddec772c951c466dfbfc1c96818 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 14:35:40 -0700
Subject: KVM: x86: Trigger I/O APIC route rescan in
 kvm_arch_irq_routing_update()

Trigger the I/O APIC route rescan that's performed for a split IRQ chip
after userspace updates IRQ routes in kvm_arch_irq_routing_update(), i.e.
before dropping kvm->irq_lock.  Calling kvm_make_all_cpus_request() under
a mutex is perfectly safe, and the smp_wmb()+smp_mb__after_atomic() pair
in __kvm_make_request()+kvm_check_request() ensures the new routing is
visible to vCPUs prior to the request being visible to vCPUs.

In all likelihood, commit b053b2aef25d ("KVM: x86: Add EOI exit bitmap
inference") somewhat arbitrarily made the request outside of irq_lock to
avoid holding irq_lock any longer than is strictly necessary.  And then
commit abdb080f7ac8 ("kvm/irqchip: kvm_arch_irq_routing_update renaming
split") took the easy route of adding another arch hook instead of risking
a functional change.

Note, the call to synchronize_srcu_expedited() does NOT provide ordering
guarantees with respect to vCPUs scanning the new routing; as above, the
request infrastructure provides the necessary ordering.  I.e. there's no
need to wait for kvm_scan_ioapic_routes() to complete if it's actively
running, because regardless of whether it grabs the old or new table, the
vCPU will have another KVM_REQ_SCAN_IOAPIC pending, i.e. will rescan again
and see the new mappings.

Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20250611213557.294358-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/irq_comm.c  | 10 +++-------
 include/linux/kvm_host.h |  4 ----
 virt/kvm/irqchip.c       |  2 --
 3 files changed, 3 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index d6d792b5d1bd..e2ae62ff9cc2 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -395,13 +395,6 @@ int kvm_setup_default_irq_routing(struct kvm *kvm)
 				   ARRAY_SIZE(default_routing), 0);
 }
 
-void kvm_arch_post_irq_routing_update(struct kvm *kvm)
-{
-	if (!irqchip_split(kvm))
-		return;
-	kvm_make_scan_ioapic_request(kvm);
-}
-
 void kvm_scan_ioapic_irq(struct kvm_vcpu *vcpu, u32 dest_id, u16 dest_mode,
 			 u8 vector, unsigned long *ioapic_handled_vectors)
 {
@@ -466,4 +459,7 @@ void kvm_arch_irq_routing_update(struct kvm *kvm)
 #ifdef CONFIG_KVM_HYPERV
 	kvm_hv_irq_routing_update(kvm);
 #endif
+
+	if (irqchip_split(kvm))
+		kvm_make_scan_ioapic_request(kvm);
 }
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3bde4fb5c6aa..9461517b4e62 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1024,14 +1024,10 @@ void vcpu_put(struct kvm_vcpu *vcpu);
 
 #ifdef __KVM_HAVE_IOAPIC
 void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm);
-void kvm_arch_post_irq_routing_update(struct kvm *kvm);
 #else
 static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm)
 {
 }
-static inline void kvm_arch_post_irq_routing_update(struct kvm *kvm)
-{
-}
 #endif
 
 #ifdef CONFIG_HAVE_KVM_IRQCHIP
diff --git a/virt/kvm/irqchip.c b/virt/kvm/irqchip.c
index 162d8ed889f2..6ccabfd32287 100644
--- a/virt/kvm/irqchip.c
+++ b/virt/kvm/irqchip.c
@@ -222,8 +222,6 @@ int kvm_set_irq_routing(struct kvm *kvm,
 	kvm_arch_irq_routing_update(kvm);
 	mutex_unlock(&kvm->irq_lock);
 
-	kvm_arch_post_irq_routing_update(kvm);
-
 	synchronize_srcu_expedited(&kvm->irq_srcu);
 
 	new = old;
-- 
cgit v1.2.3


From 77a74b8ff41ae620f5a5d727d596b670b7b9994e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 14:35:48 -0700
Subject: KVM: x86: Move kvm_{request,free}_irq_source_id() to i8254.c (PIT)

Move kvm_{request,free}_irq_source_id() to i8254.c, i.e. the dedicated PIT
emulation file, in anticipation of removing them entirely in favor of
hardcoding the PIT's "requested" source ID (the source ID can only ever be
'2', and the request can never fail).

No functional change intended.

Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20250611213557.294358-10-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/i8254.c     | 44 ++++++++++++++++++++++++++++++++++++++++++++
 arch/x86/kvm/irq_comm.c  | 44 --------------------------------------------
 include/linux/kvm_host.h |  2 --
 3 files changed, 44 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 59f956f35f4c..2bb223bf0dac 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -641,6 +641,50 @@ static void kvm_pit_reset(struct kvm_pit *pit)
 	kvm_pit_reset_reinject(pit);
 }
 
+static int kvm_request_irq_source_id(struct kvm *kvm)
+{
+	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
+	int irq_source_id;
+
+	mutex_lock(&kvm->irq_lock);
+	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
+
+	if (irq_source_id >= BITS_PER_LONG) {
+		pr_warn("exhausted allocatable IRQ sources!\n");
+		irq_source_id = -EFAULT;
+		goto unlock;
+	}
+
+	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+	set_bit(irq_source_id, bitmap);
+unlock:
+	mutex_unlock(&kvm->irq_lock);
+
+	return irq_source_id;
+}
+
+static void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
+{
+	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
+	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
+
+	mutex_lock(&kvm->irq_lock);
+	if (irq_source_id < 0 ||
+	    irq_source_id >= BITS_PER_LONG) {
+		pr_err("IRQ source ID out of range!\n");
+		goto unlock;
+	}
+	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
+	if (!irqchip_full(kvm))
+		goto unlock;
+
+	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
+	kvm_pic_clear_all(kvm->arch.vpic, irq_source_id);
+unlock:
+	mutex_unlock(&kvm->irq_lock);
+}
+
 static void pit_mask_notifer(struct kvm_irq_mask_notifier *kimn, bool mask)
 {
 	struct kvm_pit *pit = container_of(kimn, struct kvm_pit, mask_notifier);
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 99c521bd9db5..138c675dc24b 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -165,50 +165,6 @@ int kvm_arch_set_irq_inatomic(struct kvm_kernel_irq_routing_entry *e,
 	return -EWOULDBLOCK;
 }
 
-int kvm_request_irq_source_id(struct kvm *kvm)
-{
-	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
-	int irq_source_id;
-
-	mutex_lock(&kvm->irq_lock);
-	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
-
-	if (irq_source_id >= BITS_PER_LONG) {
-		pr_warn("exhausted allocatable IRQ sources!\n");
-		irq_source_id = -EFAULT;
-		goto unlock;
-	}
-
-	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
-	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
-	set_bit(irq_source_id, bitmap);
-unlock:
-	mutex_unlock(&kvm->irq_lock);
-
-	return irq_source_id;
-}
-
-void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
-{
-	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
-	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
-
-	mutex_lock(&kvm->irq_lock);
-	if (irq_source_id < 0 ||
-	    irq_source_id >= BITS_PER_LONG) {
-		pr_err("IRQ source ID out of range!\n");
-		goto unlock;
-	}
-	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
-	if (!irqchip_full(kvm))
-		goto unlock;
-
-	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
-	kvm_pic_clear_all(kvm->arch.vpic, irq_source_id);
-unlock:
-	mutex_unlock(&kvm->irq_lock);
-}
-
 void kvm_register_irq_mask_notifier(struct kvm *kvm, int irq,
 				    struct kvm_irq_mask_notifier *kimn)
 {
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 9461517b4e62..cba8fc4529e8 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1784,8 +1784,6 @@ void kvm_register_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);
 void kvm_unregister_irq_ack_notifier(struct kvm *kvm,
 				   struct kvm_irq_ack_notifier *kian);
-int kvm_request_irq_source_id(struct kvm *kvm);
-void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id);
 bool kvm_arch_irqfd_allowed(struct kvm *kvm, struct kvm_irqfd *args);
 
 /*
-- 
cgit v1.2.3


From 61423c413a746fd5fe5b0d865ea722e11b01105e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 14:35:49 -0700
Subject: KVM: x86: Hardcode the PIT IRQ source ID to '2'

Hardcode the PIT's source IRQ ID to '2' instead of "finding" that bit 2
is always the first available bit in irq_sources_bitmap.  Bits 0 and 1 are
set/reserved by kvm_arch_init_vm(), i.e. long before kvm_create_pit() can
be invoked, and KVM allows at most one in-kernel PIT instance, i.e. it's
impossible for the PIT to find a different free bit (there are no other
users of kvm_request_irq_source_id().

Delete the now-defunct irq_sources_bitmap and all its associated code.

Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20250611213557.294358-11-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h |  1 -
 arch/x86/kvm/i8254.c            | 55 ++++++-----------------------------------
 arch/x86/kvm/i8254.h            |  1 -
 arch/x86/kvm/x86.c              |  6 -----
 include/linux/kvm_host.h        |  1 +
 5 files changed, 8 insertions(+), 56 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index bf4459d637cc..4d68680f7051 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1397,7 +1397,6 @@ struct kvm_arch {
 	bool pause_in_guest;
 	bool cstate_in_guest;
 
-	unsigned long irq_sources_bitmap;
 	s64 kvmclock_offset;
 
 	/*
diff --git a/arch/x86/kvm/i8254.c b/arch/x86/kvm/i8254.c
index 2bb223bf0dac..fa8187608cfc 100644
--- a/arch/x86/kvm/i8254.c
+++ b/arch/x86/kvm/i8254.c
@@ -248,8 +248,8 @@ static void pit_do_work(struct kthread_work *work)
 	if (atomic_read(&ps->reinject) && !atomic_xchg(&ps->irq_ack, 0))
 		return;
 
-	kvm_set_irq(kvm, pit->irq_source_id, 0, 1, false);
-	kvm_set_irq(kvm, pit->irq_source_id, 0, 0, false);
+	kvm_set_irq(kvm, KVM_PIT_IRQ_SOURCE_ID, 0, 1, false);
+	kvm_set_irq(kvm, KVM_PIT_IRQ_SOURCE_ID, 0, 0, false);
 
 	/*
 	 * Provides NMI watchdog support via Virtual Wire mode.
@@ -641,47 +641,11 @@ static void kvm_pit_reset(struct kvm_pit *pit)
 	kvm_pit_reset_reinject(pit);
 }
 
-static int kvm_request_irq_source_id(struct kvm *kvm)
+static void kvm_pit_clear_all(struct kvm *kvm)
 {
-	unsigned long *bitmap = &kvm->arch.irq_sources_bitmap;
-	int irq_source_id;
-
-	mutex_lock(&kvm->irq_lock);
-	irq_source_id = find_first_zero_bit(bitmap, BITS_PER_LONG);
-
-	if (irq_source_id >= BITS_PER_LONG) {
-		pr_warn("exhausted allocatable IRQ sources!\n");
-		irq_source_id = -EFAULT;
-		goto unlock;
-	}
-
-	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
-	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
-	set_bit(irq_source_id, bitmap);
-unlock:
-	mutex_unlock(&kvm->irq_lock);
-
-	return irq_source_id;
-}
-
-static void kvm_free_irq_source_id(struct kvm *kvm, int irq_source_id)
-{
-	ASSERT(irq_source_id != KVM_USERSPACE_IRQ_SOURCE_ID);
-	ASSERT(irq_source_id != KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID);
-
 	mutex_lock(&kvm->irq_lock);
-	if (irq_source_id < 0 ||
-	    irq_source_id >= BITS_PER_LONG) {
-		pr_err("IRQ source ID out of range!\n");
-		goto unlock;
-	}
-	clear_bit(irq_source_id, &kvm->arch.irq_sources_bitmap);
-	if (!irqchip_full(kvm))
-		goto unlock;
-
-	kvm_ioapic_clear_all(kvm->arch.vioapic, irq_source_id);
-	kvm_pic_clear_all(kvm->arch.vpic, irq_source_id);
-unlock:
+	kvm_ioapic_clear_all(kvm->arch.vioapic, KVM_PIT_IRQ_SOURCE_ID);
+	kvm_pic_clear_all(kvm->arch.vpic, KVM_PIT_IRQ_SOURCE_ID);
 	mutex_unlock(&kvm->irq_lock);
 }
 
@@ -788,10 +752,6 @@ struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags)
 	if (!pit)
 		return NULL;
 
-	pit->irq_source_id = kvm_request_irq_source_id(kvm);
-	if (pit->irq_source_id < 0)
-		goto fail_request;
-
 	mutex_init(&pit->pit_state.lock);
 
 	pid = get_pid(task_tgid(current));
@@ -843,8 +803,7 @@ fail_register_pit:
 	kvm_pit_set_reinject(pit, false);
 	kthread_destroy_worker(pit->worker);
 fail_kthread:
-	kvm_free_irq_source_id(kvm, pit->irq_source_id);
-fail_request:
+	kvm_pit_clear_all(kvm);
 	kfree(pit);
 	return NULL;
 }
@@ -861,7 +820,7 @@ void kvm_free_pit(struct kvm *kvm)
 		kvm_pit_set_reinject(pit, false);
 		hrtimer_cancel(&pit->pit_state.timer);
 		kthread_destroy_worker(pit->worker);
-		kvm_free_irq_source_id(kvm, pit->irq_source_id);
+		kvm_pit_clear_all(kvm);
 		kfree(pit);
 	}
 }
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index 338095829ec8..b9c1feb379a7 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -44,7 +44,6 @@ struct kvm_pit {
 	struct kvm_io_device speaker_dev;
 	struct kvm *kvm;
 	struct kvm_kpit_state pit_state;
-	int irq_source_id;
 	struct kvm_irq_mask_notifier mask_notifier;
 	struct kthread_worker *worker;
 	struct kthread_work expired;
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 53f2ce2d40de..1d744730985e 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -12669,12 +12669,6 @@ int kvm_arch_init_vm(struct kvm *kvm, unsigned long type)
 	INIT_HLIST_HEAD(&kvm->arch.mask_notifier_list);
 	atomic_set(&kvm->arch.noncoherent_dma_count, 0);
 
-	/* Reserve bit 0 of irq_sources_bitmap for userspace irq source */
-	set_bit(KVM_USERSPACE_IRQ_SOURCE_ID, &kvm->arch.irq_sources_bitmap);
-	/* Reserve bit 1 of irq_sources_bitmap for irqfd-resampler */
-	set_bit(KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID,
-		&kvm->arch.irq_sources_bitmap);
-
 	raw_spin_lock_init(&kvm->arch.tsc_write_lock);
 	mutex_init(&kvm->arch.apic_map_lock);
 	seqcount_raw_spinlock_init(&kvm->arch.pvclock_sc, &kvm->arch.tsc_write_lock);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index cba8fc4529e8..4ff5ea29e343 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -190,6 +190,7 @@ bool kvm_make_all_cpus_request(struct kvm *kvm, unsigned int req);
 
 #define KVM_USERSPACE_IRQ_SOURCE_ID		0
 #define KVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID	1
+#define KVM_PIT_IRQ_SOURCE_ID			2
 
 extern struct mutex kvm_lock;
 extern struct list_head vm_list;
-- 
cgit v1.2.3


From 628a27731e3f36de7ddce226f7e09ee70e40ed66 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 14:35:53 -0700
Subject: KVM: x86: Add CONFIG_KVM_IOAPIC to allow disabling in-kernel I/O APIC

Add a Kconfig to allow building KVM without support for emulating a I/O
APIC, PIC, and PIT, which is desirable for deployments that effectively
don't support a fully in-kernel IRQ chip, i.e. never expect any VMM to
create an in-kernel I/O APIC.  E.g. compiling out support eliminates a few
thousand lines of guest-facing code and gives security folks warm fuzzies.

As a bonus, wrapping relevant paths with CONFIG_KVM_IOAPIC #ifdefs makes
it much easier for readers to understand which bits and pieces exist
specifically for fully in-kernel IRQ chips.

Opportunistically convert all two in-kernel uses of __KVM_HAVE_IOAPIC to
CONFIG_KVM_IOAPIC, e.g. rather than add a second #ifdef to generate a stub
for kvm_arch_post_irq_routing_update().

Acked-by: Kai Huang <kai.huang@intel.com>
Link: https://lore.kernel.org/r/20250611213557.294358-15-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h |  2 ++
 arch/x86/kvm/Kconfig            | 10 ++++++++++
 arch/x86/kvm/Makefile           |  5 +++--
 arch/x86/kvm/i8254.h            |  2 ++
 arch/x86/kvm/irq.c              |  8 ++++++++
 arch/x86/kvm/irq.h              |  9 +++++++++
 arch/x86/kvm/irq_comm.c         |  2 ++
 arch/x86/kvm/lapic.c            |  7 ++++++-
 arch/x86/kvm/trace.h            |  2 ++
 arch/x86/kvm/x86.c              | 22 ++++++++++++++++++----
 include/linux/kvm_host.h        |  2 +-
 include/trace/events/kvm.h      |  4 ++--
 12 files changed, 65 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index a4649a234f05..8d511eb03933 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1375,9 +1375,11 @@ struct kvm_arch {
 	atomic_t noncoherent_dma_count;
 #define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
 	atomic_t assigned_device_count;
+#ifdef CONFIG_KVM_IOAPIC
 	struct kvm_pic *vpic;
 	struct kvm_ioapic *vioapic;
 	struct kvm_pit *vpit;
+#endif
 	atomic_t vapics_in_nmi_mode;
 	struct mutex apic_map_lock;
 	struct kvm_apic_map __rcu *apic_map;
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index 2eeffcec5382..2c86673155c9 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -166,6 +166,16 @@ config KVM_AMD_SEV
 	  Encrypted State (SEV-ES), and Secure Encrypted Virtualization with
 	  Secure Nested Paging (SEV-SNP) technologies on AMD processors.
 
+config KVM_IOAPIC
+	bool "I/O APIC, PIC, and PIT emulation"
+	default y
+	depends on KVM
+	help
+	  Provides support for KVM to emulate an I/O APIC, PIC, and PIT, i.e.
+	  for full in-kernel APIC emulation.
+
+	  If unsure, say Y.
+
 config KVM_SMM
 	bool "System Management Mode emulation"
 	default y
diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile
index a5d362c7b504..92c737257789 100644
--- a/arch/x86/kvm/Makefile
+++ b/arch/x86/kvm/Makefile
@@ -5,12 +5,13 @@ ccflags-$(CONFIG_KVM_WERROR) += -Werror
 
 include $(srctree)/virt/kvm/Makefile.kvm
 
-kvm-y			+= x86.o emulate.o i8259.o irq.o lapic.o \
-			   i8254.o ioapic.o irq_comm.o cpuid.o pmu.o mtrr.o \
+kvm-y			+= x86.o emulate.o irq.o lapic.o \
+			   irq_comm.o cpuid.o pmu.o mtrr.o \
 			   debugfs.o mmu/mmu.o mmu/page_track.o \
 			   mmu/spte.o
 
 kvm-$(CONFIG_X86_64) += mmu/tdp_iter.o mmu/tdp_mmu.o
+kvm-$(CONFIG_KVM_IOAPIC) += i8259.o i8254.o ioapic.o
 kvm-$(CONFIG_KVM_HYPERV) += hyperv.o
 kvm-$(CONFIG_KVM_XEN)	+= xen.o
 kvm-$(CONFIG_KVM_SMM)	+= smm.o
diff --git a/arch/x86/kvm/i8254.h b/arch/x86/kvm/i8254.h
index b9c1feb379a7..e8bd59ad8a7c 100644
--- a/arch/x86/kvm/i8254.h
+++ b/arch/x86/kvm/i8254.h
@@ -8,6 +8,7 @@
 
 #include <uapi/asm/kvm.h>
 
+#ifdef CONFIG_KVM_IOAPIC
 struct kvm_kpit_channel_state {
 	u32 count; /* can be 65536 */
 	u16 latched_count;
@@ -64,5 +65,6 @@ int kvm_vm_ioctl_reinject(struct kvm *kvm, struct kvm_reinject_control *control)
 
 struct kvm_pit *kvm_create_pit(struct kvm *kvm, u32 flags);
 void kvm_free_pit(struct kvm *kvm);
+#endif /* CONFIG_KVM_IOAPIC */
 
 #endif
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index fb3bad0f4965..4c219e9f52b0 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -76,8 +76,10 @@ int kvm_cpu_has_extint(struct kvm_vcpu *v)
 	if (!kvm_apic_accept_pic_intr(v))
 		return 0;
 
+#ifdef CONFIG_KVM_IOAPIC
 	if (pic_in_kernel(v->kvm))
 		return v->kvm->arch.vpic->output;
+#endif
 
 	WARN_ON_ONCE(!irqchip_split(v->kvm));
 	return pending_userspace_extint(v);
@@ -136,8 +138,10 @@ int kvm_cpu_get_extint(struct kvm_vcpu *v)
 		return v->kvm->arch.xen.upcall_vector;
 #endif
 
+#ifdef CONFIG_KVM_IOAPIC
 	if (pic_in_kernel(v->kvm))
 		return kvm_pic_read_irq(v->kvm); /* PIC */
+#endif
 
 	WARN_ON_ONCE(!irqchip_split(v->kvm));
 	return get_userspace_extint(v);
@@ -171,7 +175,9 @@ void kvm_inject_pending_timer_irqs(struct kvm_vcpu *vcpu)
 void __kvm_migrate_timers(struct kvm_vcpu *vcpu)
 {
 	__kvm_migrate_apic_timer(vcpu);
+#ifdef CONFIG_KVM_IOAPIC
 	__kvm_migrate_pit_timer(vcpu);
+#endif
 	kvm_x86_call(migrate_timers)(vcpu);
 }
 
@@ -187,6 +193,7 @@ bool kvm_arch_irqchip_in_kernel(struct kvm *kvm)
 	return irqchip_in_kernel(kvm);
 }
 
+#ifdef CONFIG_KVM_IOAPIC
 #define IOAPIC_ROUTING_ENTRY(irq) \
 	{ .gsi = irq, .type = KVM_IRQ_ROUTING_IRQCHIP,	\
 	  .u.irqchip = { .irqchip = KVM_IRQCHIP_IOAPIC, .pin = (irq) } }
@@ -273,3 +280,4 @@ int kvm_vm_ioctl_set_irqchip(struct kvm *kvm, struct kvm_irqchip *chip)
 	kvm_pic_update_irq(pic);
 	return r;
 }
+#endif
diff --git a/arch/x86/kvm/irq.h b/arch/x86/kvm/irq.h
index 7b8b54462f95..5e62c1f79ce6 100644
--- a/arch/x86/kvm/irq.h
+++ b/arch/x86/kvm/irq.h
@@ -18,6 +18,8 @@
 #include <kvm/iodev.h>
 #include "lapic.h"
 
+#ifdef CONFIG_KVM_IOAPIC
+
 #define PIC_NUM_PINS 16
 #define SELECT_PIC(irq) \
 	((irq) < 8 ? KVM_IRQCHIP_PIC_MASTER : KVM_IRQCHIP_PIC_SLAVE)
@@ -79,12 +81,19 @@ static inline int irqchip_full(struct kvm *kvm)
 	smp_rmb();
 	return mode == KVM_IRQCHIP_KERNEL;
 }
+#else /* CONFIG_KVM_IOAPIC */
+static __always_inline int irqchip_full(struct kvm *kvm)
+{
+	return false;
+}
+#endif
 
 static inline int pic_in_kernel(struct kvm *kvm)
 {
 	return irqchip_full(kvm);
 }
 
+
 static inline int irqchip_split(struct kvm *kvm)
 {
 	int mode = kvm->arch.irqchip_mode;
diff --git a/arch/x86/kvm/irq_comm.c b/arch/x86/kvm/irq_comm.c
index 13d84c25e503..14fc8db0206c 100644
--- a/arch/x86/kvm/irq_comm.c
+++ b/arch/x86/kvm/irq_comm.c
@@ -208,6 +208,7 @@ int kvm_set_routing_entry(struct kvm *kvm,
 	 * check kvm_arch_can_set_irq_routing() before calling this function.
 	 */
 	switch (ue->type) {
+#ifdef CONFIG_KVM_IOAPIC
 	case KVM_IRQ_ROUTING_IRQCHIP:
 		if (irqchip_split(kvm))
 			return -EINVAL;
@@ -231,6 +232,7 @@ int kvm_set_routing_entry(struct kvm *kvm,
 		}
 		e->irqchip.irqchip = ue->u.irqchip.irqchip;
 		break;
+#endif
 	case KVM_IRQ_ROUTING_MSI:
 		e->set = kvm_set_msi;
 		e->msi.address_lo = ue->u.msi.address_lo;
diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
index 73418dc0ebb2..4cf8c1f753d3 100644
--- a/arch/x86/kvm/lapic.c
+++ b/arch/x86/kvm/lapic.c
@@ -1455,7 +1455,7 @@ static bool kvm_ioapic_handles_vector(struct kvm_lapic *apic, int vector)
 
 static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 {
-	int trigger_mode;
+	int __maybe_unused trigger_mode;
 
 	/* Eoi the ioapic only if the ioapic doesn't own the vector. */
 	if (!kvm_ioapic_handles_vector(apic, vector))
@@ -1476,12 +1476,14 @@ static void kvm_ioapic_send_eoi(struct kvm_lapic *apic, int vector)
 		return;
 	}
 
+#ifdef CONFIG_KVM_IOAPIC
 	if (apic_test_vector(vector, apic->regs + APIC_TMR))
 		trigger_mode = IOAPIC_LEVEL_TRIG;
 	else
 		trigger_mode = IOAPIC_EDGE_TRIG;
 
 	kvm_ioapic_update_eoi(apic->vcpu, vector, trigger_mode);
+#endif
 }
 
 static int apic_set_eoi(struct kvm_lapic *apic)
@@ -3146,8 +3148,11 @@ int kvm_apic_set_state(struct kvm_vcpu *vcpu, struct kvm_lapic_state *s)
 		kvm_x86_call(hwapic_isr_update)(vcpu, apic_find_highest_isr(apic));
 	}
 	kvm_make_request(KVM_REQ_EVENT, vcpu);
+
+#ifdef CONFIG_KVM_IOAPIC
 	if (ioapic_in_kernel(vcpu->kvm))
 		kvm_rtc_eoi_tracking_restore_one(vcpu);
+#endif
 
 	vcpu->arch.apic_arb_prio = 0;
 
diff --git a/arch/x86/kvm/trace.h b/arch/x86/kvm/trace.h
index 4ef17990574d..ababdba2c186 100644
--- a/arch/x86/kvm/trace.h
+++ b/arch/x86/kvm/trace.h
@@ -270,6 +270,7 @@ TRACE_EVENT(kvm_cpuid,
 	{0x6, "SIPI"},			\
 	{0x7, "ExtINT"}
 
+#ifdef CONFIG_KVM_IOAPIC
 TRACE_EVENT(kvm_ioapic_set_irq,
 	    TP_PROTO(__u64 e, int pin, bool coalesced),
 	    TP_ARGS(e, pin, coalesced),
@@ -314,6 +315,7 @@ TRACE_EVENT(kvm_ioapic_delayed_eoi_inj,
 		  (__entry->e & (1<<15)) ? "level" : "edge",
 		  (__entry->e & (1<<16)) ? "|masked" : "")
 );
+#endif
 
 TRACE_EVENT(kvm_msi_set_irq,
 	    TP_PROTO(__u64 address, __u64 data),
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1d744730985e..78dfa6c1cb01 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4632,17 +4632,20 @@ int kvm_vm_ioctl_check_extension(struct kvm *kvm, long ext)
 	case KVM_CAP_EXT_CPUID:
 	case KVM_CAP_EXT_EMUL_CPUID:
 	case KVM_CAP_CLOCKSOURCE:
+#ifdef CONFIG_KVM_IOAPIC
 	case KVM_CAP_PIT:
+	case KVM_CAP_PIT2:
+	case KVM_CAP_PIT_STATE2:
+	case KVM_CAP_REINJECT_CONTROL:
+#endif
 	case KVM_CAP_NOP_IO_DELAY:
 	case KVM_CAP_MP_STATE:
 	case KVM_CAP_SYNC_MMU:
 	case KVM_CAP_USER_NMI:
-	case KVM_CAP_REINJECT_CONTROL:
 	case KVM_CAP_IRQ_INJECT_STATUS:
 	case KVM_CAP_IOEVENTFD:
 	case KVM_CAP_IOEVENTFD_NO_LENGTH:
-	case KVM_CAP_PIT2:
-	case KVM_CAP_PIT_STATE2:
+
 	case KVM_CAP_SET_IDENTITY_MAP_ADDR:
 	case KVM_CAP_VCPU_EVENTS:
 #ifdef CONFIG_KVM_HYPERV
@@ -6937,9 +6940,11 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 	struct kvm *kvm = filp->private_data;
 	void __user *argp = (void __user *)arg;
 	int r = -ENOTTY;
+
+#ifdef CONFIG_KVM_IOAPIC
 	/*
 	 * This union makes it completely explicit to gcc-3.x
-	 * that these two variables' stack usage should be
+	 * that these three variables' stack usage should be
 	 * combined, not added together.
 	 */
 	union {
@@ -6947,6 +6952,7 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		struct kvm_pit_state2 ps2;
 		struct kvm_pit_config pit_config;
 	} u;
+#endif
 
 	switch (ioctl) {
 	case KVM_SET_TSS_ADDR:
@@ -6970,6 +6976,7 @@ set_identity_unlock:
 	case KVM_SET_NR_MMU_PAGES:
 		r = kvm_vm_ioctl_set_nr_mmu_pages(kvm, arg);
 		break;
+#ifdef CONFIG_KVM_IOAPIC
 	case KVM_CREATE_IRQCHIP: {
 		mutex_lock(&kvm->lock);
 
@@ -7136,6 +7143,7 @@ set_pit2_out:
 		r = kvm_vm_ioctl_reinject(kvm, &control);
 		break;
 	}
+#endif
 	case KVM_SET_BOOT_CPU_ID:
 		r = 0;
 		mutex_lock(&kvm->lock);
@@ -10595,8 +10603,10 @@ static void vcpu_scan_ioapic(struct kvm_vcpu *vcpu)
 
 	if (irqchip_split(vcpu->kvm))
 		kvm_scan_ioapic_routes(vcpu, vcpu->arch.ioapic_handled_vectors);
+#ifdef CONFIG_KVM_IOAPIC
 	else if (ioapic_in_kernel(vcpu->kvm))
 		kvm_ioapic_scan_entry(vcpu, vcpu->arch.ioapic_handled_vectors);
+#endif
 
 	if (is_guest_mode(vcpu))
 		vcpu->arch.load_eoi_exitmap_pending = true;
@@ -12799,7 +12809,9 @@ void kvm_arch_pre_destroy_vm(struct kvm *kvm)
 	cancel_delayed_work_sync(&kvm->arch.kvmclock_sync_work);
 	cancel_delayed_work_sync(&kvm->arch.kvmclock_update_work);
 
+#ifdef CONFIG_KVM_IOAPIC
 	kvm_free_pit(kvm);
+#endif
 
 	kvm_mmu_pre_destroy_vm(kvm);
 	static_call_cond(kvm_x86_vm_pre_destroy)(kvm);
@@ -12823,8 +12835,10 @@ void kvm_arch_destroy_vm(struct kvm *kvm)
 	}
 	kvm_destroy_vcpus(kvm);
 	kvm_free_msr_filter(srcu_dereference_check(kvm->arch.msr_filter, &kvm->srcu, 1));
+#ifdef CONFIG_KVM_IOAPIC
 	kvm_pic_destroy(kvm);
 	kvm_ioapic_destroy(kvm);
+#endif
 	kvfree(rcu_dereference_check(kvm->arch.apic_map, 1));
 	kfree(srcu_dereference_check(kvm->arch.pmu_event_filter, &kvm->srcu, 1));
 	kvm_mmu_uninit_vm(kvm);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 4ff5ea29e343..3b5575d0b574 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1023,7 +1023,7 @@ void kvm_unlock_all_vcpus(struct kvm *kvm);
 void vcpu_load(struct kvm_vcpu *vcpu);
 void vcpu_put(struct kvm_vcpu *vcpu);
 
-#ifdef __KVM_HAVE_IOAPIC
+#ifdef CONFIG_KVM_IOAPIC
 void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm);
 #else
 static inline void kvm_arch_post_irq_ack_notifier_list_update(struct kvm *kvm)
diff --git a/include/trace/events/kvm.h b/include/trace/events/kvm.h
index 96e581900c8e..1065a81ca57f 100644
--- a/include/trace/events/kvm.h
+++ b/include/trace/events/kvm.h
@@ -84,14 +84,14 @@ TRACE_EVENT(kvm_set_irq,
 );
 #endif /* defined(CONFIG_HAVE_KVM_IRQCHIP) */
 
-#if defined(__KVM_HAVE_IOAPIC)
+#ifdef CONFIG_KVM_IOAPIC
 
 #define kvm_irqchips						\
 	{KVM_IRQCHIP_PIC_MASTER,	"PIC master"},		\
 	{KVM_IRQCHIP_PIC_SLAVE,		"PIC slave"},		\
 	{KVM_IRQCHIP_IOAPIC,		"IOAPIC"}
 
-#endif /* defined(__KVM_HAVE_IOAPIC) */
+#endif /* CONFIG_KVM_IOAPIC */
 
 #if defined(CONFIG_HAVE_KVM_IRQCHIP)
 
-- 
cgit v1.2.3


From cb210737675ef4c1ad88721e84558eeb2f199312 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:06 -0700
Subject: KVM: Pass new routing entries and irqfd when updating IRTEs

When updating IRTEs in response to a GSI routing or IRQ bypass change,
pass the new/current routing information along with the associated irqfd.
This will allow KVM x86 to harden, simplify, and deduplicate its code.

Since adding/removing a bypass producer is now conveniently protected with
irqfds.lock, i.e. can't run concurrently with kvm_irq_routing_update(),
use the routing information cached in the irqfd instead of looking up
the information in the current GSI routing tables.

Opportunistically convert an existing printk() to pr_info() and put its
string onto a single line (old code that strictly adhered to 80 chars).

Link: https://lore.kernel.org/r/20250611224604.313496-5-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/arm.c            |  7 ++++---
 arch/x86/include/asm/kvm_host.h |  6 ++++--
 arch/x86/kvm/svm/avic.c         | 18 +++++++-----------
 arch/x86/kvm/svm/svm.h          |  5 +++--
 arch/x86/kvm/vmx/posted_intr.c  | 19 ++++++++-----------
 arch/x86/kvm/vmx/posted_intr.h  |  8 ++++++--
 arch/x86/kvm/x86.c              | 36 ++++++++++++++++++++----------------
 include/linux/kvm_host.h        |  7 +++++--
 virt/kvm/eventfd.c              | 11 +++++------
 9 files changed, 62 insertions(+), 55 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 38a91bb5d4c7..a9a39e0375f7 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2771,8 +2771,9 @@ bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
 	return memcmp(&old->msi, &new->msi, sizeof(new->msi));
 }
 
-int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
-				  uint32_t guest_irq, bool set)
+int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+				  struct kvm_kernel_irq_routing_entry *old,
+				  struct kvm_kernel_irq_routing_entry *new)
 {
 	/*
 	 * Remapping the vLPI requires taking the its_lock mutex to resolve
@@ -2781,7 +2782,7 @@ int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
 	 *
 	 * Unmap the vLPI and fall back to software LPI injection.
 	 */
-	return kvm_vgic_v4_unset_forwarding(kvm, host_irq);
+	return kvm_vgic_v4_unset_forwarding(irqfd->kvm, irqfd->producer->irq);
 }
 
 void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *cons)
diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 44fd9ccc0624..2a14564dd08a 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -297,6 +297,7 @@ enum x86_intercept_stage;
  */
 #define KVM_APIC_PV_EOI_PENDING	1
 
+struct kvm_kernel_irqfd;
 struct kvm_kernel_irq_routing_entry;
 
 /*
@@ -1845,8 +1846,9 @@ struct kvm_x86_ops {
 	void (*vcpu_blocking)(struct kvm_vcpu *vcpu);
 	void (*vcpu_unblocking)(struct kvm_vcpu *vcpu);
 
-	int (*pi_update_irte)(struct kvm *kvm, unsigned int host_irq,
-			      uint32_t guest_irq, bool set);
+	int (*pi_update_irte)(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+			      unsigned int host_irq, uint32_t guest_irq,
+			      struct kvm_kernel_irq_routing_entry *new);
 	void (*pi_start_assignment)(struct kvm *kvm);
 	void (*apicv_pre_state_restore)(struct kvm_vcpu *vcpu);
 	void (*apicv_post_state_restore)(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 067f8e3f5a0d..49b73907de92 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -18,6 +18,7 @@
 #include <linux/hashtable.h>
 #include <linux/amd-iommu.h>
 #include <linux/kvm_host.h>
+#include <linux/kvm_irqfd.h>
 
 #include <asm/irq_remapping.h>
 #include <asm/msr.h>
@@ -886,21 +887,14 @@ get_pi_vcpu_info(struct kvm *kvm, struct kvm_kernel_irq_routing_entry *e,
 	return 0;
 }
 
-/*
- * avic_pi_update_irte - set IRTE for Posted-Interrupts
- *
- * @kvm: kvm
- * @host_irq: host irq of the interrupt
- * @guest_irq: gsi of the interrupt
- * @set: set or unset PI
- * returns 0 on success, < 0 on failure
- */
-int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
-			uint32_t guest_irq, bool set)
+int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+			unsigned int host_irq, uint32_t guest_irq,
+			struct kvm_kernel_irq_routing_entry *new)
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
 	bool enable_remapped_mode = true;
+	bool set = !!new;
 	int idx, ret = 0;
 
 	if (!kvm_arch_has_assigned_device(kvm) || !kvm_arch_has_irq_bypass())
@@ -926,6 +920,8 @@ int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 		if (e->type != KVM_IRQ_ROUTING_MSI)
 			continue;
 
+		WARN_ON_ONCE(new && memcmp(e, new, sizeof(*new)));
+
 		/**
 		 * Here, we setup with legacy mode in the following cases:
 		 * 1. When cannot target interrupt to a specific vcpu.
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index e6f3c6a153a0..b35fce30d923 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -736,8 +736,9 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu);
 void avic_vcpu_put(struct kvm_vcpu *vcpu);
 void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu);
 void avic_refresh_apicv_exec_ctrl(struct kvm_vcpu *vcpu);
-int avic_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
-			uint32_t guest_irq, bool set);
+int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+			unsigned int host_irq, uint32_t guest_irq,
+			struct kvm_kernel_irq_routing_entry *new);
 void avic_vcpu_blocking(struct kvm_vcpu *vcpu);
 void avic_vcpu_unblocking(struct kvm_vcpu *vcpu);
 void avic_ring_doorbell(struct kvm_vcpu *vcpu);
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 5c615e5845bf..110fb19848ab 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -2,6 +2,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/kvm_host.h>
+#include <linux/kvm_irqfd.h>
 
 #include <asm/irq_remapping.h>
 #include <asm/cpu.h>
@@ -294,17 +295,9 @@ void vmx_pi_start_assignment(struct kvm *kvm)
 	kvm_make_all_cpus_request(kvm, KVM_REQ_UNBLOCK);
 }
 
-/*
- * vmx_pi_update_irte - set IRTE for Posted-Interrupts
- *
- * @kvm: kvm
- * @host_irq: host irq of the interrupt
- * @guest_irq: gsi of the interrupt
- * @set: set or unset PI
- * returns 0 on success, < 0 on failure
- */
-int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
-		       uint32_t guest_irq, bool set)
+int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+		       unsigned int host_irq, uint32_t guest_irq,
+		       struct kvm_kernel_irq_routing_entry *new)
 {
 	struct kvm_kernel_irq_routing_entry *e;
 	struct kvm_irq_routing_table *irq_rt;
@@ -312,6 +305,7 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 	struct kvm_lapic_irq irq;
 	struct kvm_vcpu *vcpu;
 	struct vcpu_data vcpu_info;
+	bool set = !!new;
 	int idx, ret = 0;
 
 	if (!vmx_can_use_vtd_pi(kvm))
@@ -329,6 +323,9 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
 	hlist_for_each_entry(e, &irq_rt->map[guest_irq], link) {
 		if (e->type != KVM_IRQ_ROUTING_MSI)
 			continue;
+
+		WARN_ON_ONCE(new && memcmp(e, new, sizeof(*new)));
+
 		/*
 		 * VT-d PI cannot support posting multicast/broadcast
 		 * interrupts to a vCPU, we still use interrupt remapping
diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
index 80499ea0e674..a94afcb55f7f 100644
--- a/arch/x86/kvm/vmx/posted_intr.h
+++ b/arch/x86/kvm/vmx/posted_intr.h
@@ -3,6 +3,9 @@
 #define __KVM_X86_VMX_POSTED_INTR_H
 
 #include <linux/bitmap.h>
+#include <linux/find.h>
+#include <linux/kvm_host.h>
+
 #include <asm/posted_intr.h>
 
 void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
@@ -11,8 +14,9 @@ void pi_wakeup_handler(void);
 void __init pi_init_cpu(int cpu);
 void pi_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
 bool pi_has_pending_interrupt(struct kvm_vcpu *vcpu);
-int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
-		       uint32_t guest_irq, bool set);
+int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
+		       unsigned int host_irq, uint32_t guest_irq,
+		       struct kvm_kernel_irq_routing_entry *new);
 void vmx_pi_start_assignment(struct kvm *kvm);
 
 static inline int pi_find_highest_vector(struct pi_desc *pi_desc)
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 02237dbb7f32..e1304b002062 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13507,31 +13507,31 @@ int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *cons,
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
 	struct kvm *kvm = irqfd->kvm;
-	int ret;
+	int ret = 0;
 
 	kvm_arch_start_assignment(irqfd->kvm);
 
 	spin_lock_irq(&kvm->irqfds.lock);
 	irqfd->producer = prod;
 
-	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
-					   prod->irq, irqfd->gsi, 1);
-	if (ret)
-		kvm_arch_end_assignment(irqfd->kvm);
-
+	if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) {
+		ret = kvm_x86_call(pi_update_irte)(irqfd, irqfd->kvm, prod->irq,
+						   irqfd->gsi, &irqfd->irq_entry);
+		if (ret)
+			kvm_arch_end_assignment(irqfd->kvm);
+	}
 	spin_unlock_irq(&kvm->irqfds.lock);
 
-
 	return ret;
 }
 
 void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 				      struct irq_bypass_producer *prod)
 {
-	int ret;
 	struct kvm_kernel_irqfd *irqfd =
 		container_of(cons, struct kvm_kernel_irqfd, consumer);
 	struct kvm *kvm = irqfd->kvm;
+	int ret;
 
 	WARN_ON(irqfd->producer != prod);
 
@@ -13544,11 +13544,13 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	spin_lock_irq(&kvm->irqfds.lock);
 	irqfd->producer = NULL;
 
-	ret = kvm_x86_call(pi_update_irte)(irqfd->kvm,
-					   prod->irq, irqfd->gsi, 0);
-	if (ret)
-		printk(KERN_INFO "irq bypass consumer (eventfd %p) unregistration"
-		       " fails: %d\n", irqfd->consumer.eventfd, ret);
+	if (irqfd->irq_entry.type == KVM_IRQ_ROUTING_MSI) {
+		ret = kvm_x86_call(pi_update_irte)(irqfd, irqfd->kvm, prod->irq,
+						   irqfd->gsi, NULL);
+		if (ret)
+			pr_info("irq bypass consumer (eventfd %p) unregistration fails: %d\n",
+				irqfd->consumer.eventfd, ret);
+	}
 
 	spin_unlock_irq(&kvm->irqfds.lock);
 
@@ -13556,10 +13558,12 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	kvm_arch_end_assignment(irqfd->kvm);
 }
 
-int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
-				   uint32_t guest_irq, bool set)
+int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+				  struct kvm_kernel_irq_routing_entry *old,
+				  struct kvm_kernel_irq_routing_entry *new)
 {
-	return kvm_x86_call(pi_update_irte)(kvm, host_irq, guest_irq, set);
+	return kvm_x86_call(pi_update_irte)(irqfd, irqfd->kvm, irqfd->producer->irq,
+					    irqfd->gsi, new);
 }
 
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 3b5575d0b574..a4160c1c0c6b 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2401,6 +2401,8 @@ struct kvm_vcpu *kvm_get_running_vcpu(void);
 struct kvm_vcpu * __percpu *kvm_get_running_vcpus(void);
 
 #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
+struct kvm_kernel_irqfd;
+
 bool kvm_arch_has_irq_bypass(void);
 int kvm_arch_irq_bypass_add_producer(struct irq_bypass_consumer *,
 			   struct irq_bypass_producer *);
@@ -2408,8 +2410,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *,
 			   struct irq_bypass_producer *);
 void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *);
 void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *);
-int kvm_arch_update_irqfd_routing(struct kvm *kvm, unsigned int host_irq,
-				  uint32_t guest_irq, bool set);
+int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+				  struct kvm_kernel_irq_routing_entry *old,
+				  struct kvm_kernel_irq_routing_entry *new);
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *,
 				  struct kvm_kernel_irq_routing_entry *);
 #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 5bc6abe30748..bd1766da6895 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -285,9 +285,9 @@ void __attribute__((weak)) kvm_arch_irq_bypass_start(
 {
 }
 
-int  __attribute__((weak)) kvm_arch_update_irqfd_routing(
-				struct kvm *kvm, unsigned int host_irq,
-				uint32_t guest_irq, bool set)
+int __weak kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+					 struct kvm_kernel_irq_routing_entry *old,
+					 struct kvm_kernel_irq_routing_entry *new)
 {
 	return 0;
 }
@@ -618,9 +618,8 @@ void kvm_irq_routing_update(struct kvm *kvm)
 #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
 		if (irqfd->producer &&
 		    kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry)) {
-			int ret = kvm_arch_update_irqfd_routing(
-					irqfd->kvm, irqfd->producer->irq,
-					irqfd->gsi, 1);
+			int ret = kvm_arch_update_irqfd_routing(irqfd, &old, &irqfd->irq_entry);
+
 			WARN_ON(ret);
 		}
 #endif
-- 
cgit v1.2.3


From 05c5e23657e1d61c271c2f4a3a21d4d630b18a9b Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:07 -0700
Subject: KVM: SVM: Track per-vCPU IRTEs using kvm_kernel_irqfd structure

Track the IRTEs that are posting to an SVM vCPU via the associated irqfd
structure and GSI routing instead of dynamically allocating a separate
data structure.  In addition to eliminating an atomic allocation, this
will allow hoisting much of the IRTE update logic to common x86.

Cc: Sairaj Kodilkar <sarunkod@amd.com>
Link: https://lore.kernel.org/r/20250611224604.313496-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/avic.c   | 71 ++++++++++++++++++-----------------------------
 arch/x86/kvm/svm/svm.h    | 10 ++++---
 include/linux/kvm_irqfd.h |  3 ++
 3 files changed, 36 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 49b73907de92..accc36958a75 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -76,14 +76,6 @@ static bool next_vm_id_wrapped = 0;
 static DEFINE_SPINLOCK(svm_vm_data_hash_lock);
 bool x2avic_enabled;
 
-/*
- * This is a wrapper of struct amd_iommu_ir_data.
- */
-struct amd_svm_iommu_ir {
-	struct list_head node;	/* Used by SVM for per-vcpu ir_list */
-	void *data;		/* Storing pointer to struct amd_ir_data */
-};
-
 static void avic_activate_vmcb(struct vcpu_svm *svm)
 {
 	struct vmcb *vmcb = svm->vmcb01.ptr;
@@ -747,8 +739,8 @@ static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 {
 	int ret = 0;
 	unsigned long flags;
-	struct amd_svm_iommu_ir *ir;
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_kernel_irqfd *irqfd;
 
 	if (!kvm_arch_has_assigned_device(vcpu->kvm))
 		return 0;
@@ -762,11 +754,11 @@ static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 	if (list_empty(&svm->ir_list))
 		goto out;
 
-	list_for_each_entry(ir, &svm->ir_list, node) {
+	list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
 		if (activate)
-			ret = amd_iommu_activate_guest_mode(ir->data);
+			ret = amd_iommu_activate_guest_mode(irqfd->irq_bypass_data);
 		else
-			ret = amd_iommu_deactivate_guest_mode(ir->data);
+			ret = amd_iommu_deactivate_guest_mode(irqfd->irq_bypass_data);
 		if (ret)
 			break;
 	}
@@ -775,27 +767,30 @@ out:
 	return ret;
 }
 
-static void svm_ir_list_del(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+static void svm_ir_list_del(struct vcpu_svm *svm,
+			    struct kvm_kernel_irqfd *irqfd,
+			    struct amd_iommu_pi_data *pi)
 {
 	unsigned long flags;
-	struct amd_svm_iommu_ir *cur;
+	struct kvm_kernel_irqfd *cur;
 
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
-	list_for_each_entry(cur, &svm->ir_list, node) {
-		if (cur->data != pi->ir_data)
+	list_for_each_entry(cur, &svm->ir_list, vcpu_list) {
+		if (cur->irq_bypass_data != pi->ir_data)
+			continue;
+		if (WARN_ON_ONCE(cur != irqfd))
 			continue;
-		list_del(&cur->node);
-		kfree(cur);
+		list_del(&irqfd->vcpu_list);
 		break;
 	}
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
 
-static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
+static int svm_ir_list_add(struct vcpu_svm *svm,
+			   struct kvm_kernel_irqfd *irqfd,
+			   struct amd_iommu_pi_data *pi)
 {
-	int ret = 0;
 	unsigned long flags;
-	struct amd_svm_iommu_ir *ir;
 	u64 entry;
 
 	if (WARN_ON_ONCE(!pi->ir_data))
@@ -812,25 +807,14 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
 		struct vcpu_svm *prev_svm;
 
-		if (!prev_vcpu) {
-			ret = -EINVAL;
-			goto out;
-		}
+		if (!prev_vcpu)
+			return -EINVAL;
 
 		prev_svm = to_svm(prev_vcpu);
-		svm_ir_list_del(prev_svm, pi);
+		svm_ir_list_del(prev_svm, irqfd, pi);
 	}
 
-	/**
-	 * Allocating new amd_iommu_pi_data, which will get
-	 * add to the per-vcpu ir_list.
-	 */
-	ir = kzalloc(sizeof(struct amd_svm_iommu_ir), GFP_ATOMIC | __GFP_ACCOUNT);
-	if (!ir) {
-		ret = -ENOMEM;
-		goto out;
-	}
-	ir->data = pi->ir_data;
+	irqfd->irq_bypass_data = pi->ir_data;
 
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
@@ -845,10 +829,9 @@ static int svm_ir_list_add(struct vcpu_svm *svm, struct amd_iommu_pi_data *pi)
 		amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
 				    true, pi->ir_data);
 
-	list_add(&ir->node, &svm->ir_list);
+	list_add(&irqfd->vcpu_list, &svm->ir_list);
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
-out:
-	return ret;
+	return 0;
 }
 
 /*
@@ -952,7 +935,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 			 * scheduling information in IOMMU irte.
 			 */
 			if (!ret && pi.is_guest_mode)
-				svm_ir_list_add(svm, &pi);
+				svm_ir_list_add(svm, irqfd, &pi);
 		}
 
 		if (!ret && svm) {
@@ -993,7 +976,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 
 			vcpu = kvm_get_vcpu_by_id(kvm, id);
 			if (vcpu)
-				svm_ir_list_del(to_svm(vcpu), &pi);
+				svm_ir_list_del(to_svm(vcpu), irqfd, &pi);
 		}
 	}
 out:
@@ -1005,8 +988,8 @@ static inline int
 avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 {
 	int ret = 0;
-	struct amd_svm_iommu_ir *ir;
 	struct vcpu_svm *svm = to_svm(vcpu);
+	struct kvm_kernel_irqfd *irqfd;
 
 	lockdep_assert_held(&svm->ir_list_lock);
 
@@ -1020,8 +1003,8 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 	if (list_empty(&svm->ir_list))
 		return 0;
 
-	list_for_each_entry(ir, &svm->ir_list, node) {
-		ret = amd_iommu_update_ga(cpu, r, ir->data);
+	list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
+		ret = amd_iommu_update_ga(cpu, r, irqfd->irq_bypass_data);
 		if (ret)
 			return ret;
 	}
diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h
index b35fce30d923..cc27877d69ae 100644
--- a/arch/x86/kvm/svm/svm.h
+++ b/arch/x86/kvm/svm/svm.h
@@ -310,10 +310,12 @@ struct vcpu_svm {
 	u64 *avic_physical_id_cache;
 
 	/*
-	 * Per-vcpu list of struct amd_svm_iommu_ir:
-	 * This is used mainly to store interrupt remapping information used
-	 * when update the vcpu affinity. This avoids the need to scan for
-	 * IRTE and try to match ga_tag in the IOMMU driver.
+	 * Per-vCPU list of irqfds that are eligible to post IRQs directly to
+	 * the vCPU (a.k.a. device posted IRQs, a.k.a. IRQ bypass).  The list
+	 * is used to reconfigure IRTEs when the vCPU is loaded/put (to set the
+	 * target pCPU), when AVIC is toggled on/off (to (de)activate bypass),
+	 * and if the irqfd becomes ineligible for posting (to put the IRTE
+	 * back into remapped mode).
 	 */
 	struct list_head ir_list;
 	spinlock_t ir_list_lock;
diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index 8ad43692e3bb..6510a48e62aa 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -59,6 +59,9 @@ struct kvm_kernel_irqfd {
 	struct work_struct shutdown;
 	struct irq_bypass_consumer consumer;
 	struct irq_bypass_producer *producer;
+
+	struct list_head vcpu_list;
+	void *irq_bypass_data;
 };
 
 #endif /* __LINUX_KVM_IRQFD_H */
-- 
cgit v1.2.3


From 0a917e9d4b7070fafcbf7a8ec32d2aa444b4e757 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:08 -0700
Subject: KVM: SVM: Delete IRTE link from previous vCPU before setting new IRTE

Delete the previous per-vCPU IRTE link prior to modifying the IRTE.  If
forcing the IRTE back to remapped mode fails, the IRQ is already broken;
keeping stale metadata won't change that, and the IOMMU should be
sufficiently paranoid to sanitize the IRTE when the IRQ is freed and
reallocated.

This will allow hoisting the vCPU tracking to common x86, which in turn
will allow most of the IRTE update code to be deduplicated.

Tested-by: Sairaj Kodilkar <sarunkod@amd.com>
Link: https://lore.kernel.org/r/20250611224604.313496-7-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/avic.c   | 60 ++++++++++-------------------------------------
 include/linux/kvm_irqfd.h |  1 +
 2 files changed, 14 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index accc36958a75..7f7af8ff627d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -767,23 +767,19 @@ out:
 	return ret;
 }
 
-static void svm_ir_list_del(struct vcpu_svm *svm,
-			    struct kvm_kernel_irqfd *irqfd,
-			    struct amd_iommu_pi_data *pi)
+static void svm_ir_list_del(struct kvm_kernel_irqfd *irqfd)
 {
+	struct kvm_vcpu *vcpu = irqfd->irq_bypass_vcpu;
 	unsigned long flags;
-	struct kvm_kernel_irqfd *cur;
 
-	spin_lock_irqsave(&svm->ir_list_lock, flags);
-	list_for_each_entry(cur, &svm->ir_list, vcpu_list) {
-		if (cur->irq_bypass_data != pi->ir_data)
-			continue;
-		if (WARN_ON_ONCE(cur != irqfd))
-			continue;
-		list_del(&irqfd->vcpu_list);
-		break;
-	}
-	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
+	if (!vcpu)
+		return;
+
+	spin_lock_irqsave(&to_svm(vcpu)->ir_list_lock, flags);
+	list_del(&irqfd->vcpu_list);
+	spin_unlock_irqrestore(&to_svm(vcpu)->ir_list_lock, flags);
+
+	irqfd->irq_bypass_vcpu = NULL;
 }
 
 static int svm_ir_list_add(struct vcpu_svm *svm,
@@ -796,24 +792,7 @@ static int svm_ir_list_add(struct vcpu_svm *svm,
 	if (WARN_ON_ONCE(!pi->ir_data))
 		return -EINVAL;
 
-	/**
-	 * In some cases, the existing irte is updated and re-set,
-	 * so we need to check here if it's already been * added
-	 * to the ir_list.
-	 */
-	if (pi->prev_ga_tag) {
-		struct kvm *kvm = svm->vcpu.kvm;
-		u32 vcpu_id = AVIC_GATAG_TO_VCPUID(pi->prev_ga_tag);
-		struct kvm_vcpu *prev_vcpu = kvm_get_vcpu_by_id(kvm, vcpu_id);
-		struct vcpu_svm *prev_svm;
-
-		if (!prev_vcpu)
-			return -EINVAL;
-
-		prev_svm = to_svm(prev_vcpu);
-		svm_ir_list_del(prev_svm, irqfd, pi);
-	}
-
+	irqfd->irq_bypass_vcpu = &svm->vcpu;
 	irqfd->irq_bypass_data = pi->ir_data;
 
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
@@ -905,6 +884,8 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 
 		WARN_ON_ONCE(new && memcmp(e, new, sizeof(*new)));
 
+		svm_ir_list_del(irqfd);
+
 		/**
 		 * Here, we setup with legacy mode in the following cases:
 		 * 1. When cannot target interrupt to a specific vcpu.
@@ -963,21 +944,6 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		pi.prev_ga_tag = 0;
 		pi.is_guest_mode = false;
 		ret = irq_set_vcpu_affinity(host_irq, &pi);
-
-		/**
-		 * Check if the posted interrupt was previously
-		 * setup with the guest_mode by checking if the ga_tag
-		 * was cached. If so, we need to clean up the per-vcpu
-		 * ir_list.
-		 */
-		if (!ret && pi.prev_ga_tag) {
-			int id = AVIC_GATAG_TO_VCPUID(pi.prev_ga_tag);
-			struct kvm_vcpu *vcpu;
-
-			vcpu = kvm_get_vcpu_by_id(kvm, id);
-			if (vcpu)
-				svm_ir_list_del(to_svm(vcpu), irqfd, &pi);
-		}
 	}
 out:
 	srcu_read_unlock(&kvm->irq_srcu, idx);
diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index 6510a48e62aa..361c07f4466d 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -60,6 +60,7 @@ struct kvm_kernel_irqfd {
 	struct irq_bypass_consumer consumer;
 	struct irq_bypass_producer *producer;
 
+	struct kvm_vcpu *irq_bypass_vcpu;
 	struct list_head vcpu_list;
 	void *irq_bypass_data;
 };
-- 
cgit v1.2.3


From 1da19c5ce0533796179d9e1b55e64bf78478c4c1 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:09 -0700
Subject: iommu/amd: KVM: SVM: Delete now-unused cached/previous GA tag fields

Delete the amd_ir_data.prev_ga_tag field now that all usage is
superfluous.

Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Tested-by: Sairaj Kodilkar <sarunkod@amd.com>
Link: https://lore.kernel.org/r/20250611224604.313496-8-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/avic.c             |  2 --
 drivers/iommu/amd/amd_iommu_types.h |  1 -
 drivers/iommu/amd/iommu.c           | 10 ----------
 include/linux/amd-iommu.h           |  2 +-
 4 files changed, 1 insertion(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 7f7af8ff627d..38cdfb052a3a 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -939,9 +939,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		/**
 		 * Here, pi is used to:
 		 * - Tell IOMMU to use legacy mode for this interrupt.
-		 * - Retrieve ga_tag of prior interrupt remapping data.
 		 */
-		pi.prev_ga_tag = 0;
 		pi.is_guest_mode = false;
 		ret = irq_set_vcpu_affinity(host_irq, &pi);
 	}
diff --git a/drivers/iommu/amd/amd_iommu_types.h b/drivers/iommu/amd/amd_iommu_types.h
index ccbab3a4811a..053a0f05768c 100644
--- a/drivers/iommu/amd/amd_iommu_types.h
+++ b/drivers/iommu/amd/amd_iommu_types.h
@@ -1054,7 +1054,6 @@ struct irq_2_irte {
 };
 
 struct amd_ir_data {
-	u32 cached_ga_tag;
 	struct amd_iommu *iommu;
 	struct irq_2_irte irq_2_irte;
 	struct msi_msg msi_entry;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 3117d99cf83d..ed96050d4933 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3887,23 +3887,13 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	ir_data->cfg = irqd_cfg(data);
 	pi_data->ir_data = ir_data;
 
-	pi_data->prev_ga_tag = ir_data->cached_ga_tag;
 	if (pi_data->is_guest_mode) {
 		ir_data->ga_root_ptr = (pi_data->base >> 12);
 		ir_data->ga_vector = vcpu_pi_info->vector;
 		ir_data->ga_tag = pi_data->ga_tag;
 		ret = amd_iommu_activate_guest_mode(ir_data);
-		if (!ret)
-			ir_data->cached_ga_tag = pi_data->ga_tag;
 	} else {
 		ret = amd_iommu_deactivate_guest_mode(ir_data);
-
-		/*
-		 * This communicates the ga_tag back to the caller
-		 * so that it can do all the necessary clean up.
-		 */
-		if (!ret)
-			ir_data->cached_ga_tag = 0;
 	}
 
 	return ret;
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 062fbd4c9b77..1f9b13d803c5 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -19,8 +19,8 @@ struct amd_iommu;
  */
 struct amd_iommu_pi_data {
 	u32 ga_tag;
-	u32 prev_ga_tag;
 	u64 base;
+
 	bool is_guest_mode;
 	struct vcpu_data *vcpu_data;
 	void *ir_data;
-- 
cgit v1.2.3


From 6e6558a6bc418f1478c5dc8609d03805364e0cb9 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 13 Jun 2025 15:33:10 -1000
Subject: sched_ext, sched/core: Factor out struct scx_task_group

More sched_ext fields will be added to struct task_group. In preparation,
factor out sched_ext fields into struct scx_task_group to reduce clutter in
the common header. No functional changes.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/sched/ext.h |  8 ++++++++
 kernel/sched/ext.c        | 32 ++++++++++++++++----------------
 kernel/sched/sched.h      |  5 +----
 3 files changed, 25 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index f7545430a548..eda89acdb7ab 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -214,4 +214,12 @@ static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}
 static inline void scx_softlockup(u32 dur_s) {}
 
 #endif	/* CONFIG_SCHED_CLASS_EXT */
+
+struct scx_task_group {
+#ifdef CONFIG_EXT_GROUP_SCHED
+	u32			flags;		/* SCX_TG_* */
+	u32			weight;
+#endif
+};
+
 #endif	/* _LINUX_SCHED_EXT_H */
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 4db51e708f86..6732e50e0679 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4058,7 +4058,7 @@ static bool scx_cgroup_enabled;
 
 void scx_tg_init(struct task_group *tg)
 {
-	tg->scx_weight = CGROUP_WEIGHT_DFL;
+	tg->scx.weight = CGROUP_WEIGHT_DFL;
 }
 
 int scx_tg_online(struct task_group *tg)
@@ -4066,14 +4066,14 @@ int scx_tg_online(struct task_group *tg)
 	struct scx_sched *sch = scx_root;
 	int ret = 0;
 
-	WARN_ON_ONCE(tg->scx_flags & (SCX_TG_ONLINE | SCX_TG_INITED));
+	WARN_ON_ONCE(tg->scx.flags & (SCX_TG_ONLINE | SCX_TG_INITED));
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
 	if (scx_cgroup_enabled) {
 		if (SCX_HAS_OP(sch, cgroup_init)) {
 			struct scx_cgroup_init_args args =
-				{ .weight = tg->scx_weight };
+				{ .weight = tg->scx.weight };
 
 			ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init,
 					      NULL, tg->css.cgroup, &args);
@@ -4081,9 +4081,9 @@ int scx_tg_online(struct task_group *tg)
 				ret = ops_sanitize_err(sch, "cgroup_init", ret);
 		}
 		if (ret == 0)
-			tg->scx_flags |= SCX_TG_ONLINE | SCX_TG_INITED;
+			tg->scx.flags |= SCX_TG_ONLINE | SCX_TG_INITED;
 	} else {
-		tg->scx_flags |= SCX_TG_ONLINE;
+		tg->scx.flags |= SCX_TG_ONLINE;
 	}
 
 	percpu_up_read(&scx_cgroup_rwsem);
@@ -4094,15 +4094,15 @@ void scx_tg_offline(struct task_group *tg)
 {
 	struct scx_sched *sch = scx_root;
 
-	WARN_ON_ONCE(!(tg->scx_flags & SCX_TG_ONLINE));
+	WARN_ON_ONCE(!(tg->scx.flags & SCX_TG_ONLINE));
 
 	percpu_down_read(&scx_cgroup_rwsem);
 
 	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_exit) &&
-	    (tg->scx_flags & SCX_TG_INITED))
+	    (tg->scx.flags & SCX_TG_INITED))
 		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_exit, NULL,
 			    tg->css.cgroup);
-	tg->scx_flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED);
+	tg->scx.flags &= ~(SCX_TG_ONLINE | SCX_TG_INITED);
 
 	percpu_up_read(&scx_cgroup_rwsem);
 }
@@ -4211,11 +4211,11 @@ void scx_group_set_weight(struct task_group *tg, unsigned long weight)
 	percpu_down_read(&scx_cgroup_rwsem);
 
 	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_weight) &&
-	    tg->scx_weight != weight)
+	    tg->scx.weight != weight)
 		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_weight, NULL,
 			    tg_cgrp(tg), weight);
 
-	tg->scx_weight = weight;
+	tg->scx.weight = weight;
 
 	percpu_up_read(&scx_cgroup_rwsem);
 }
@@ -4366,9 +4366,9 @@ static void scx_cgroup_exit(struct scx_sched *sch)
 	css_for_each_descendant_post(css, &root_task_group.css) {
 		struct task_group *tg = css_tg(css);
 
-		if (!(tg->scx_flags & SCX_TG_INITED))
+		if (!(tg->scx.flags & SCX_TG_INITED))
 			continue;
-		tg->scx_flags &= ~SCX_TG_INITED;
+		tg->scx.flags &= ~SCX_TG_INITED;
 
 		if (!sch->ops.cgroup_exit)
 			continue;
@@ -4400,14 +4400,14 @@ static int scx_cgroup_init(struct scx_sched *sch)
 	rcu_read_lock();
 	css_for_each_descendant_pre(css, &root_task_group.css) {
 		struct task_group *tg = css_tg(css);
-		struct scx_cgroup_init_args args = { .weight = tg->scx_weight };
+		struct scx_cgroup_init_args args = { .weight = tg->scx.weight };
 
-		if ((tg->scx_flags &
+		if ((tg->scx.flags &
 		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
 			continue;
 
 		if (!sch->ops.cgroup_init) {
-			tg->scx_flags |= SCX_TG_INITED;
+			tg->scx.flags |= SCX_TG_INITED;
 			continue;
 		}
 
@@ -4422,7 +4422,7 @@ static int scx_cgroup_init(struct scx_sched *sch)
 			scx_error(sch, "ops.cgroup_init() failed (%d)", ret);
 			return ret;
 		}
-		tg->scx_flags |= SCX_TG_INITED;
+		tg->scx.flags |= SCX_TG_INITED;
 
 		rcu_read_lock();
 		css_put(css);
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 105190b18020..fdf5f52b54a3 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -471,10 +471,7 @@ struct task_group {
 	struct rt_bandwidth	rt_bandwidth;
 #endif
 
-#ifdef CONFIG_EXT_GROUP_SCHED
-	u32			scx_flags;	/* SCX_TG_* */
-	u32			scx_weight;
-#endif
+	struct scx_task_group	scx;
 
 	struct rcu_head		rcu;
 	struct list_head	list;
-- 
cgit v1.2.3


From ddceadce63d9cb752c2472e220ded05cabaf7971 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 13 Jun 2025 15:34:22 -1000
Subject: sched_ext: Add support for cgroup bandwidth control interface

From 077814f57f8acce13f91dc34bbd2b7e4911fbf25 Mon Sep 17 00:00:00 2001
From: Tejun Heo <tj@kernel.org>
Date: Fri, 13 Jun 2025 15:06:47 -1000

- Add CONFIG_GROUP_SCHED_BANDWIDTH which is selected by both
  CONFIG_CFS_BANDWIDTH and EXT_GROUP_SCHED.

- Put bandwidth control interface files for both cgroup v1 and v2 under
  CONFIG_GROUP_SCHED_BANDWIDTH.

- Update tg_bandwidth() to fetch configuration parameters from fair if
  CONFIG_CFS_BANDWIDTH, SCX otherwise.

- Update tg_set_bandwidth() to update the parameters for both fair and SCX.

- Add bandwidth control parameters to struct scx_cgroup_init_args.

- Add sched_ext_ops.cgroup_set_bandwidth() which is invoked on bandwidth
  control parameter updates.

- Update scx_qmap and maximal selftest to test the new feature.

Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/sched/ext.h                       |  3 ++
 init/Kconfig                                    |  5 ++
 kernel/sched/core.c                             | 29 +++++++++--
 kernel/sched/ext.c                              | 66 +++++++++++++++++++++++--
 kernel/sched/ext.h                              |  2 +
 kernel/sched/sched.h                            |  4 +-
 tools/sched_ext/scx_qmap.bpf.c                  | 23 +++++++++
 tools/testing/selftests/sched_ext/maximal.bpf.c |  5 ++
 8 files changed, 127 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index eda89acdb7ab..8b92842776cb 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -219,6 +219,9 @@ struct scx_task_group {
 #ifdef CONFIG_EXT_GROUP_SCHED
 	u32			flags;		/* SCX_TG_* */
 	u32			weight;
+	u64			bw_period_us;
+	u64			bw_quota_us;
+	u64			bw_burst_us;
 #endif
 };
 
diff --git a/init/Kconfig b/init/Kconfig
index af4c2f085455..baf59d2a20a2 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1065,6 +1065,9 @@ if CGROUP_SCHED
 config GROUP_SCHED_WEIGHT
 	def_bool n
 
+config GROUP_SCHED_BANDWIDTH
+        def_bool n
+
 config FAIR_GROUP_SCHED
 	bool "Group scheduling for SCHED_OTHER"
 	depends on CGROUP_SCHED
@@ -1074,6 +1077,7 @@ config FAIR_GROUP_SCHED
 config CFS_BANDWIDTH
 	bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
 	depends on FAIR_GROUP_SCHED
+	select GROUP_SCHED_BANDWIDTH
 	default n
 	help
 	  This option allows users to define CPU bandwidth rates (limits) for
@@ -1108,6 +1112,7 @@ config EXT_GROUP_SCHED
 	bool
 	depends on SCHED_CLASS_EXT && CGROUP_SCHED
 	select GROUP_SCHED_WEIGHT
+	select GROUP_SCHED_BANDWIDTH
 	default y
 
 endif #CGROUP_SCHED
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index 0e3a00e2a2cc..91845d00a1cd 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -9545,7 +9545,9 @@ static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
 
 	return 0;
 }
+#endif /* CONFIG_CFS_BANDWIDTH */
 
+#ifdef CONFIG_GROUP_SCHED_BANDWIDTH
 const u64 max_bw_quota_period_us = 1 * USEC_PER_SEC; /* 1s */
 static const u64 min_bw_quota_period_us = 1 * USEC_PER_MSEC; /* 1ms */
 /* More than 203 days if BW_SHIFT equals 20. */
@@ -9554,12 +9556,21 @@ static const u64 max_bw_runtime_us = MAX_BW;
 static void tg_bandwidth(struct task_group *tg,
 			 u64 *period_us_p, u64 *quota_us_p, u64 *burst_us_p)
 {
+#ifdef CONFIG_CFS_BANDWIDTH
 	if (period_us_p)
 		*period_us_p = tg_get_cfs_period(tg);
 	if (quota_us_p)
 		*quota_us_p = tg_get_cfs_quota(tg);
 	if (burst_us_p)
 		*burst_us_p = tg_get_cfs_burst(tg);
+#else /* !CONFIG_CFS_BANDWIDTH */
+	if (period_us_p)
+		*period_us_p = tg->scx.bw_period_us;
+	if (quota_us_p)
+		*quota_us_p = tg->scx.bw_quota_us;
+	if (burst_us_p)
+		*burst_us_p = tg->scx.bw_burst_us;
+#endif /* CONFIG_CFS_BANDWIDTH */
 }
 
 static u64 cpu_period_read_u64(struct cgroup_subsys_state *css,
@@ -9575,6 +9586,7 @@ static int tg_set_bandwidth(struct task_group *tg,
 			    u64 period_us, u64 quota_us, u64 burst_us)
 {
 	const u64 max_usec = U64_MAX / NSEC_PER_USEC;
+	int ret = 0;
 
 	if (tg == &root_task_group)
 		return -EINVAL;
@@ -9612,7 +9624,12 @@ static int tg_set_bandwidth(struct task_group *tg,
 					burst_us + quota_us > max_bw_runtime_us))
 		return -EINVAL;
 
-	return tg_set_cfs_bandwidth(tg, period_us, quota_us, burst_us);
+#ifdef CONFIG_CFS_BANDWIDTH
+	ret = tg_set_cfs_bandwidth(tg, period_us, quota_us, burst_us);
+#endif /* CONFIG_CFS_BANDWIDTH */
+	if (!ret)
+		scx_group_set_bandwidth(tg, period_us, quota_us, burst_us);
+	return ret;
 }
 
 static s64 cpu_quota_read_s64(struct cgroup_subsys_state *css,
@@ -9665,7 +9682,7 @@ static int cpu_burst_write_u64(struct cgroup_subsys_state *css,
 	tg_bandwidth(tg, &period_us, &quota_us, NULL);
 	return tg_set_bandwidth(tg, period_us, quota_us, burst_us);
 }
-#endif /* CONFIG_CFS_BANDWIDTH */
+#endif /* CONFIG_GROUP_SCHED_BANDWIDTH */
 
 #ifdef CONFIG_RT_GROUP_SCHED
 static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
@@ -9725,7 +9742,7 @@ static struct cftype cpu_legacy_files[] = {
 		.write_s64 = cpu_idle_write_s64,
 	},
 #endif
-#ifdef CONFIG_CFS_BANDWIDTH
+#ifdef CONFIG_GROUP_SCHED_BANDWIDTH
 	{
 		.name = "cfs_period_us",
 		.read_u64 = cpu_period_read_u64,
@@ -9741,6 +9758,8 @@ static struct cftype cpu_legacy_files[] = {
 		.read_u64 = cpu_burst_read_u64,
 		.write_u64 = cpu_burst_write_u64,
 	},
+#endif
+#ifdef CONFIG_CFS_BANDWIDTH
 	{
 		.name = "stat",
 		.seq_show = cpu_cfs_stat_show,
@@ -9954,7 +9973,7 @@ static int __maybe_unused cpu_period_quota_parse(char *buf, u64 *period_us_p,
 	return 0;
 }
 
-#ifdef CONFIG_CFS_BANDWIDTH
+#ifdef CONFIG_GROUP_SCHED_BANDWIDTH
 static int cpu_max_show(struct seq_file *sf, void *v)
 {
 	struct task_group *tg = css_tg(seq_css(sf));
@@ -10001,7 +10020,7 @@ static struct cftype cpu_files[] = {
 		.write_s64 = cpu_idle_write_s64,
 	},
 #endif
-#ifdef CONFIG_CFS_BANDWIDTH
+#ifdef CONFIG_GROUP_SCHED_BANDWIDTH
 	{
 		.name = "max",
 		.flags = CFTYPE_NOT_ON_ROOT,
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index 6732e50e0679..39cba11688a9 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -203,6 +203,11 @@ struct scx_exit_task_args {
 struct scx_cgroup_init_args {
 	/* the weight of the cgroup [1..10000] */
 	u32			weight;
+
+	/* bandwidth control parameters from cpu.max and cpu.max.burst */
+	u64			bw_period_us;
+	u64			bw_quota_us;
+	u64			bw_burst_us;
 };
 
 enum scx_cpu_preempt_reason {
@@ -664,9 +669,31 @@ struct sched_ext_ops {
 	 * @cgrp: cgroup whose weight is being updated
 	 * @weight: new weight [1..10000]
 	 *
-	 * Update @tg's weight to @weight.
+	 * Update @cgrp's weight to @weight.
 	 */
 	void (*cgroup_set_weight)(struct cgroup *cgrp, u32 weight);
+
+	/**
+	 * @cgroup_set_bandwidth: A cgroup's bandwidth is being changed
+	 * @cgrp: cgroup whose bandwidth is being updated
+	 * @period_us: bandwidth control period
+	 * @quota_us: bandwidth control quota
+	 * @burst_us: bandwidth control burst
+	 *
+	 * Update @cgrp's bandwidth control parameters. This is from the cpu.max
+	 * cgroup interface.
+	 *
+	 * @quota_us / @period_us determines the CPU bandwidth @cgrp is entitled
+	 * to. For example, if @period_us is 1_000_000 and @quota_us is
+	 * 2_500_000. @cgrp is entitled to 2.5 CPUs. @burst_us can be
+	 * interpreted in the same fashion and specifies how much @cgrp can
+	 * burst temporarily. The specific control mechanism and thus the
+	 * interpretation of @period_us and burstiness is upto to the BPF
+	 * scheduler.
+	 */
+	void (*cgroup_set_bandwidth)(struct cgroup *cgrp,
+				     u64 period_us, u64 quota_us, u64 burst_us);
+
 #endif	/* CONFIG_EXT_GROUP_SCHED */
 
 	/*
@@ -4059,6 +4086,8 @@ static bool scx_cgroup_enabled;
 void scx_tg_init(struct task_group *tg)
 {
 	tg->scx.weight = CGROUP_WEIGHT_DFL;
+	tg->scx.bw_period_us = default_bw_period_us();
+	tg->scx.bw_quota_us = RUNTIME_INF;
 }
 
 int scx_tg_online(struct task_group *tg)
@@ -4073,7 +4102,10 @@ int scx_tg_online(struct task_group *tg)
 	if (scx_cgroup_enabled) {
 		if (SCX_HAS_OP(sch, cgroup_init)) {
 			struct scx_cgroup_init_args args =
-				{ .weight = tg->scx.weight };
+				{ .weight = tg->scx.weight,
+				  .bw_period_us = tg->scx.bw_period_us,
+				  .bw_quota_us = tg->scx.bw_quota_us,
+				  .bw_burst_us = tg->scx.bw_burst_us };
 
 			ret = SCX_CALL_OP_RET(sch, SCX_KF_UNLOCKED, cgroup_init,
 					      NULL, tg->css.cgroup, &args);
@@ -4225,6 +4257,27 @@ void scx_group_set_idle(struct task_group *tg, bool idle)
 	/* TODO: Implement ops->cgroup_set_idle() */
 }
 
+void scx_group_set_bandwidth(struct task_group *tg,
+			     u64 period_us, u64 quota_us, u64 burst_us)
+{
+	struct scx_sched *sch = scx_root;
+
+	percpu_down_read(&scx_cgroup_rwsem);
+
+	if (scx_cgroup_enabled && SCX_HAS_OP(sch, cgroup_set_bandwidth) &&
+	    (tg->scx.bw_period_us != period_us ||
+	     tg->scx.bw_quota_us != quota_us ||
+	     tg->scx.bw_burst_us != burst_us))
+		SCX_CALL_OP(sch, SCX_KF_UNLOCKED, cgroup_set_bandwidth, NULL,
+			    tg_cgrp(tg), period_us, quota_us, burst_us);
+
+	tg->scx.bw_period_us = period_us;
+	tg->scx.bw_quota_us = quota_us;
+	tg->scx.bw_burst_us = burst_us;
+
+	percpu_up_read(&scx_cgroup_rwsem);
+}
+
 static void scx_cgroup_lock(void)
 {
 	percpu_down_write(&scx_cgroup_rwsem);
@@ -4400,7 +4453,12 @@ static int scx_cgroup_init(struct scx_sched *sch)
 	rcu_read_lock();
 	css_for_each_descendant_pre(css, &root_task_group.css) {
 		struct task_group *tg = css_tg(css);
-		struct scx_cgroup_init_args args = { .weight = tg->scx.weight };
+		struct scx_cgroup_init_args args = {
+			.weight = tg->scx.weight,
+			.bw_period_us = tg->scx.bw_period_us,
+			.bw_quota_us = tg->scx.bw_quota_us,
+			.bw_burst_us = tg->scx.bw_burst_us,
+		};
 
 		if ((tg->scx.flags &
 		     (SCX_TG_ONLINE | SCX_TG_INITED)) != SCX_TG_ONLINE)
@@ -5902,6 +5960,7 @@ static s32 sched_ext_ops__cgroup_prep_move(struct task_struct *p, struct cgroup
 static void sched_ext_ops__cgroup_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
 static void sched_ext_ops__cgroup_cancel_move(struct task_struct *p, struct cgroup *from, struct cgroup *to) {}
 static void sched_ext_ops__cgroup_set_weight(struct cgroup *cgrp, u32 weight) {}
+static void sched_ext_ops__cgroup_set_bandwidth(struct cgroup *cgrp, u64 period_us, u64 quota_us, u64 burst_us) {}
 #endif
 static void sched_ext_ops__cpu_online(s32 cpu) {}
 static void sched_ext_ops__cpu_offline(s32 cpu) {}
@@ -5939,6 +5998,7 @@ static struct sched_ext_ops __bpf_ops_sched_ext_ops = {
 	.cgroup_move		= sched_ext_ops__cgroup_move,
 	.cgroup_cancel_move	= sched_ext_ops__cgroup_cancel_move,
 	.cgroup_set_weight	= sched_ext_ops__cgroup_set_weight,
+	.cgroup_set_bandwidth	= sched_ext_ops__cgroup_set_bandwidth,
 #endif
 	.cpu_online		= sched_ext_ops__cpu_online,
 	.cpu_offline		= sched_ext_ops__cpu_offline,
diff --git a/kernel/sched/ext.h b/kernel/sched/ext.h
index e7bcaa02ea56..292bb41a242e 100644
--- a/kernel/sched/ext.h
+++ b/kernel/sched/ext.h
@@ -104,6 +104,7 @@ void scx_cgroup_finish_attach(void);
 void scx_cgroup_cancel_attach(struct cgroup_taskset *tset);
 void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight);
 void scx_group_set_idle(struct task_group *tg, bool idle);
+void scx_group_set_bandwidth(struct task_group *tg, u64 period_us, u64 quota_us, u64 burst_us);
 #else	/* CONFIG_EXT_GROUP_SCHED */
 static inline void scx_tg_init(struct task_group *tg) {}
 static inline int scx_tg_online(struct task_group *tg) { return 0; }
@@ -114,5 +115,6 @@ static inline void scx_cgroup_finish_attach(void) {}
 static inline void scx_cgroup_cancel_attach(struct cgroup_taskset *tset) {}
 static inline void scx_group_set_weight(struct task_group *tg, unsigned long cgrp_weight) {}
 static inline void scx_group_set_idle(struct task_group *tg, bool idle) {}
+static inline void scx_group_set_bandwidth(struct task_group *tg, u64 period_us, u64 quota_us, u64 burst_us) {}
 #endif	/* CONFIG_EXT_GROUP_SCHED */
 #endif	/* CONFIG_CGROUP_SCHED */
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index fdf5f52b54a3..06767a210717 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -402,7 +402,7 @@ static inline bool dl_server_active(struct sched_dl_entity *dl_se)
 
 extern struct list_head task_groups;
 
-#ifdef CONFIG_CFS_BANDWIDTH
+#ifdef CONFIG_GROUP_SCHED_BANDWIDTH
 extern const u64 max_bw_quota_period_us;
 
 /*
@@ -413,7 +413,7 @@ static inline u64 default_bw_period_us(void)
 {
 	return 100000ULL;
 }
-#endif /* CONFIG_CFS_BANDWIDTH */
+#endif /* CONFIG_GROUP_SCHED_BANDWIDTH */
 
 struct cfs_bandwidth {
 #ifdef CONFIG_CFS_BANDWIDTH
diff --git a/tools/sched_ext/scx_qmap.bpf.c b/tools/sched_ext/scx_qmap.bpf.c
index c3cd9a17d48e..69d877501cb7 100644
--- a/tools/sched_ext/scx_qmap.bpf.c
+++ b/tools/sched_ext/scx_qmap.bpf.c
@@ -615,6 +615,26 @@ void BPF_STRUCT_OPS(qmap_dump_task, struct scx_dump_ctx *dctx, struct task_struc
 		     taskc->force_local, taskc->core_sched_seq);
 }
 
+s32 BPF_STRUCT_OPS(qmap_cgroup_init, struct cgroup *cgrp, struct scx_cgroup_init_args *args)
+{
+	bpf_printk("CGRP INIT %llu weight=%u period=%lu quota=%ld burst=%lu",
+		   cgrp->kn->id, args->weight, args->bw_period_us,
+		   args->bw_quota_us, args->bw_burst_us);
+	return 0;
+}
+
+void BPF_STRUCT_OPS(qmap_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
+{
+	bpf_printk("CGRP SET %llu weight=%u", cgrp->kn->id, weight);
+}
+
+void BPF_STRUCT_OPS(qmap_cgroup_set_bandwidth, struct cgroup *cgrp,
+		    u64 period_us, u64 quota_us, u64 burst_us)
+{
+	bpf_printk("CGRP SET %llu period=%lu quota=%ld burst=%lu", cgrp->kn->id,
+		   period_us, quota_us, burst_us);
+}
+
 /*
  * Print out the online and possible CPU map using bpf_printk() as a
  * demonstration of using the cpumask kfuncs and ops.cpu_on/offline().
@@ -840,6 +860,9 @@ SCX_OPS_DEFINE(qmap_ops,
 	       .dump			= (void *)qmap_dump,
 	       .dump_cpu		= (void *)qmap_dump_cpu,
 	       .dump_task		= (void *)qmap_dump_task,
+	       .cgroup_init		= (void *)qmap_cgroup_init,
+	       .cgroup_set_weight	= (void *)qmap_cgroup_set_weight,
+	       .cgroup_set_bandwidth	= (void *)qmap_cgroup_set_bandwidth,
 	       .cpu_online		= (void *)qmap_cpu_online,
 	       .cpu_offline		= (void *)qmap_cpu_offline,
 	       .init			= (void *)qmap_init,
diff --git a/tools/testing/selftests/sched_ext/maximal.bpf.c b/tools/testing/selftests/sched_ext/maximal.bpf.c
index 430f5e13bf55..01cf4f3da4e0 100644
--- a/tools/testing/selftests/sched_ext/maximal.bpf.c
+++ b/tools/testing/selftests/sched_ext/maximal.bpf.c
@@ -123,6 +123,10 @@ void BPF_STRUCT_OPS(maximal_cgroup_cancel_move, struct task_struct *p,
 void BPF_STRUCT_OPS(maximal_cgroup_set_weight, struct cgroup *cgrp, u32 weight)
 {}
 
+void BPF_STRUCT_OPS(maximal_cgroup_set_bandwidth, struct cgroup *cgrp,
+		    u64 period_us, u64 quota_us, u64 burst_us)
+{}
+
 s32 BPF_STRUCT_OPS_SLEEPABLE(maximal_init)
 {
 	return scx_bpf_create_dsq(DSQ_ID, -1);
@@ -160,6 +164,7 @@ struct sched_ext_ops maximal_ops = {
 	.cgroup_move		= (void *) maximal_cgroup_move,
 	.cgroup_cancel_move	= (void *) maximal_cgroup_cancel_move,
 	.cgroup_set_weight	= (void *) maximal_cgroup_set_weight,
+	.cgroup_set_bandwidth	= (void *) maximal_cgroup_set_bandwidth,
 	.init			= (void *) maximal_init,
 	.exit			= (void *) maximal_exit,
 	.name			= "maximal",
-- 
cgit v1.2.3


From 4672aec56d2e8edabcb74c3e2320301d106a377e Mon Sep 17 00:00:00 2001
From: Mina Almasry <almasrymina@google.com>
Date: Thu, 19 Jun 2025 17:52:38 +0000
Subject: netmem: fix skb_frag_address_safe with unreadable skbs

skb_frag_address_safe() needs a check that the
skb_frag_page exists check similar to skb_frag_address().

Cc: ap420073@gmail.com

Signed-off-by: Mina Almasry <almasrymina@google.com>
Acked-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250619175239.3039329-1-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 9508968cb300..4f6dcb37bae8 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3665,7 +3665,13 @@ static inline void *skb_frag_address(const skb_frag_t *frag)
  */
 static inline void *skb_frag_address_safe(const skb_frag_t *frag)
 {
-	void *ptr = page_address(skb_frag_page(frag));
+	struct page *page = skb_frag_page(frag);
+	void *ptr;
+
+	if (!page)
+		return NULL;
+
+	ptr = page_address(page);
 	if (unlikely(!ptr))
 		return NULL;
 
-- 
cgit v1.2.3


From 99aa0bbb082e7c0660751832acca897493c3082c Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Fri, 20 Jun 2025 11:16:41 +0200
Subject: net: pse-pd: Fix ethnl_pse_send_ntf() stub parameter type

The ethnl_pse_send_ntf() stub function has incorrect parameter type when
CONFIG_ETHTOOL_NETLINK is disabled. The function should take a net_device
pointer instead of phy_device pointer to match the actual implementation.

Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202506200355.TqFiYUbN-lkp@intel.com/
Fixes: fc0e6db30941 ("net: pse-pd: Add support for reporting events")
Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250620091641.2098028-1-kory.maincent@bootlin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ethtool_netlink.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ethtool_netlink.h b/include/linux/ethtool_netlink.h
index 1dcc4059b5ab..39254b2726c0 100644
--- a/include/linux/ethtool_netlink.h
+++ b/include/linux/ethtool_netlink.h
@@ -122,7 +122,7 @@ static inline bool ethtool_dev_mm_supported(struct net_device *dev)
 	return false;
 }
 
-static inline void ethnl_pse_send_ntf(struct phy_device *phydev,
+static inline void ethnl_pse_send_ntf(struct net_device *netdev,
 				      unsigned long notif)
 {
 }
-- 
cgit v1.2.3


From 520c790c83e9e4c915a8e3fc9f2152ece39b6511 Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Sun, 8 Jun 2025 22:40:02 +0200
Subject: power: supply: core: remove of_node from power_supply_config

All drivers have been migrated from .of_node to .fwnode,
so let's kill the former.

Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Link: https://lore.kernel.org/r/20250430-psy-core-convert-to-fwnode-v2-2-f9643b958677@collabora.com
Reviewed-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/power_supply_core.c | 3 +--
 include/linux/power_supply.h             | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 33a5bfce4604..89947f1fe610 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1529,10 +1529,9 @@ __power_supply_register(struct device *parent,
 	dev_set_drvdata(dev, psy);
 	psy->desc = desc;
 	if (cfg) {
+		device_set_node(dev, cfg->fwnode);
 		dev->groups = cfg->attr_grp;
 		psy->drv_data = cfg->drv_data;
-		dev->of_node =
-			cfg->fwnode ? to_of_node(cfg->fwnode) : cfg->of_node;
 		psy->supplied_to = cfg->supplied_to;
 		psy->num_supplicants = cfg->num_supplicants;
 	}
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 7803edaa8ff8..72012141656e 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -232,7 +232,6 @@ struct power_supply;
 
 /* Run-time specific power supply configuration */
 struct power_supply_config {
-	struct device_node *of_node;
 	struct fwnode_handle *fwnode;
 
 	/* Driver private data */
-- 
cgit v1.2.3


From f368f87b22dab8e97c5f447b00a0cae79fefbdcb Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Sun, 8 Jun 2025 22:40:06 +0200
Subject: power: supply: core: convert to fwnnode

Replace any DT specific code with fwnode in the power-supply
core.

Reviewed-by: AngeloGioacchino Del Regno <angelogioacchino.delregno@collabora.com>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250430-psy-core-convert-to-fwnode-v2-4-f9643b958677@collabora.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/power/supply/bq2415x_charger.c   |  2 +-
 drivers/power/supply/power_supply_core.c | 65 ++++++++++++++++----------------
 include/linux/power_supply.h             |  2 +-
 3 files changed, 34 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c
index 9e3b9181ee76..1ecbca510bba 100644
--- a/drivers/power/supply/bq2415x_charger.c
+++ b/drivers/power/supply/bq2415x_charger.c
@@ -1674,7 +1674,7 @@ static int bq2415x_probe(struct i2c_client *client)
 	/* Query for initial reported_mode and set it */
 	if (bq->nb.notifier_call) {
 		if (np) {
-			notify_psy = power_supply_get_by_phandle(np,
+			notify_psy = power_supply_get_by_phandle(of_fwnode_handle(np),
 						"ti,usb-charger-detection");
 			if (IS_ERR(notify_psy))
 				notify_psy = NULL;
diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index f2c79f15838d..2d83bb125a48 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -18,7 +18,6 @@
 #include <linux/device.h>
 #include <linux/notifier.h>
 #include <linux/err.h>
-#include <linux/of.h>
 #include <linux/power_supply.h>
 #include <linux/property.h>
 #include <linux/thermal.h>
@@ -196,24 +195,24 @@ static int __power_supply_populate_supplied_from(struct power_supply *epsy,
 						 void *data)
 {
 	struct power_supply *psy = data;
-	struct device_node *np;
+	struct fwnode_handle *np;
 	int i = 0;
 
 	do {
-		np = of_parse_phandle(psy->dev.of_node, "power-supplies", i++);
-		if (!np)
+		np = fwnode_find_reference(psy->dev.fwnode, "power-supplies", i++);
+		if (IS_ERR(np))
 			break;
 
-		if (np == epsy->dev.of_node) {
+		if (np == epsy->dev.fwnode) {
 			dev_dbg(&psy->dev, "%s: Found supply : %s\n",
 				psy->desc->name, epsy->desc->name);
 			psy->supplied_from[i-1] = (char *)epsy->desc->name;
 			psy->num_supplies++;
-			of_node_put(np);
+			fwnode_handle_put(np);
 			break;
 		}
-		of_node_put(np);
-	} while (np);
+		fwnode_handle_put(np);
+	} while (!IS_ERR(np));
 
 	return 0;
 }
@@ -232,16 +231,16 @@ static int power_supply_populate_supplied_from(struct power_supply *psy)
 static int  __power_supply_find_supply_from_node(struct power_supply *epsy,
 						 void *data)
 {
-	struct device_node *np = data;
+	struct fwnode_handle *fwnode = data;
 
 	/* returning non-zero breaks out of power_supply_for_each_psy loop */
-	if (epsy->dev.of_node == np)
+	if (epsy->dev.fwnode == fwnode)
 		return 1;
 
 	return 0;
 }
 
-static int power_supply_find_supply_from_node(struct device_node *supply_node)
+static int power_supply_find_supply_from_fwnode(struct fwnode_handle *supply_node)
 {
 	int error;
 
@@ -249,7 +248,7 @@ static int power_supply_find_supply_from_node(struct device_node *supply_node)
 	 * power_supply_for_each_psy() either returns its own errors or values
 	 * returned by __power_supply_find_supply_from_node().
 	 *
-	 * __power_supply_find_supply_from_node() will return 0 (no match)
+	 * __power_supply_find_supply_from_fwnode() will return 0 (no match)
 	 * or 1 (match).
 	 *
 	 * We return 0 if power_supply_for_each_psy() returned 1, -EPROBE_DEFER if
@@ -262,7 +261,7 @@ static int power_supply_find_supply_from_node(struct device_node *supply_node)
 
 static int power_supply_check_supplies(struct power_supply *psy)
 {
-	struct device_node *np;
+	struct fwnode_handle *np;
 	int cnt = 0;
 
 	/* If there is already a list honor it */
@@ -270,24 +269,24 @@ static int power_supply_check_supplies(struct power_supply *psy)
 		return 0;
 
 	/* No device node found, nothing to do */
-	if (!psy->dev.of_node)
+	if (!psy->dev.fwnode)
 		return 0;
 
 	do {
 		int ret;
 
-		np = of_parse_phandle(psy->dev.of_node, "power-supplies", cnt++);
-		if (!np)
+		np = fwnode_find_reference(psy->dev.fwnode, "power-supplies", cnt++);
+		if (IS_ERR(np))
 			break;
 
-		ret = power_supply_find_supply_from_node(np);
-		of_node_put(np);
+		ret = power_supply_find_supply_from_fwnode(np);
+		fwnode_handle_put(np);
 
 		if (ret) {
 			dev_dbg(&psy->dev, "Failed to find supply!\n");
 			return ret;
 		}
-	} while (np);
+	} while (!IS_ERR(np));
 
 	/* Missing valid "power-supplies" entries */
 	if (cnt == 1)
@@ -498,14 +497,14 @@ void power_supply_put(struct power_supply *psy)
 EXPORT_SYMBOL_GPL(power_supply_put);
 
 #ifdef CONFIG_OF
-static int power_supply_match_device_node(struct device *dev, const void *data)
+static int power_supply_match_device_fwnode(struct device *dev, const void *data)
 {
-	return dev->parent && dev->parent->of_node == data;
+	return dev->parent && dev_fwnode(dev->parent) == data;
 }
 
 /**
  * power_supply_get_by_phandle() - Search for a power supply and returns its ref
- * @np: Pointer to device node holding phandle property
+ * @fwnode: Pointer to fwnode holding phandle property
  * @property: Name of property holding a power supply name
  *
  * If power supply was found, it increases reference count for the
@@ -515,21 +514,21 @@ static int power_supply_match_device_node(struct device *dev, const void *data)
  * Return: On success returns a reference to a power supply with
  * matching name equals to value under @property, NULL or ERR_PTR otherwise.
  */
-struct power_supply *power_supply_get_by_phandle(struct device_node *np,
-							const char *property)
+struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode,
+						 const char *property)
 {
-	struct device_node *power_supply_np;
+	struct fwnode_handle *power_supply_fwnode;
 	struct power_supply *psy = NULL;
 	struct device *dev;
 
-	power_supply_np = of_parse_phandle(np, property, 0);
-	if (!power_supply_np)
-		return ERR_PTR(-ENODEV);
+	power_supply_fwnode = fwnode_find_reference(fwnode, property, 0);
+	if (IS_ERR(power_supply_fwnode))
+		return ERR_CAST(power_supply_fwnode);
 
-	dev = class_find_device(&power_supply_class, NULL, power_supply_np,
-				power_supply_match_device_node);
+	dev = class_find_device(&power_supply_class, NULL, power_supply_fwnode,
+				power_supply_match_device_fwnode);
 
-	of_node_put(power_supply_np);
+	fwnode_handle_put(power_supply_fwnode);
 
 	if (dev) {
 		psy = dev_to_psy(dev);
@@ -561,14 +560,14 @@ struct power_supply *devm_power_supply_get_by_phandle(struct device *dev,
 {
 	struct power_supply **ptr, *psy;
 
-	if (!dev->of_node)
+	if (!dev_fwnode(dev))
 		return ERR_PTR(-ENODEV);
 
 	ptr = devres_alloc(devm_power_supply_put, sizeof(*ptr), GFP_KERNEL);
 	if (!ptr)
 		return ERR_PTR(-ENOMEM);
 
-	psy = power_supply_get_by_phandle(dev->of_node, property);
+	psy = power_supply_get_by_phandle(dev_fwnode(dev), property);
 	if (IS_ERR_OR_NULL(psy)) {
 		devres_free(ptr);
 	} else {
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 72012141656e..d90ac7b73755 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -808,7 +808,7 @@ static inline struct power_supply *power_supply_get_by_name(const char *name)
 { return NULL; }
 #endif
 #ifdef CONFIG_OF
-extern struct power_supply *power_supply_get_by_phandle(struct device_node *np,
+extern struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode,
 							const char *property);
 extern struct power_supply *devm_power_supply_get_by_phandle(
 				    struct device *dev, const char *property);
-- 
cgit v1.2.3


From 370643f45aad93476b6489238ccb45a77b94da3f Mon Sep 17 00:00:00 2001
From: Sebastian Reichel <sebastian.reichel@collabora.com>
Date: Sun, 8 Jun 2025 22:40:07 +0200
Subject: power: supply: core: rename power_supply_get_by_phandle to
 power_supply_get_by_reference

(devm_)power_supply_get_by_phandle now internally uses fwnode and are no
longer DT specific. Thus drop the ifdef check for CONFIG_OF and rename
to (devm_)power_supply_get_by_reference to avoid the DT terminology.

Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250430-psy-core-convert-to-fwnode-v2-5-f9643b958677@collabora.com
Signed-off-by: Sebastian Reichel <sebastian.reichel@collabora.com>
---
 drivers/phy/allwinner/phy-sun4i-usb.c    |  2 +-
 drivers/power/supply/bq2415x_charger.c   |  2 +-
 drivers/power/supply/power_supply_core.c | 22 ++++++++++------------
 include/linux/power_supply.h             | 15 +++------------
 4 files changed, 15 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/phy/allwinner/phy-sun4i-usb.c b/drivers/phy/allwinner/phy-sun4i-usb.c
index 29b8fd4b9351..8873aed3a52a 100644
--- a/drivers/phy/allwinner/phy-sun4i-usb.c
+++ b/drivers/phy/allwinner/phy-sun4i-usb.c
@@ -754,7 +754,7 @@ static int sun4i_usb_phy_probe(struct platform_device *pdev)
 	}
 
 	if (of_property_present(np, "usb0_vbus_power-supply")) {
-		data->vbus_power_supply = devm_power_supply_get_by_phandle(dev,
+		data->vbus_power_supply = devm_power_supply_get_by_reference(dev,
 						     "usb0_vbus_power-supply");
 		if (IS_ERR(data->vbus_power_supply)) {
 			dev_err(dev, "Couldn't get the VBUS power supply\n");
diff --git a/drivers/power/supply/bq2415x_charger.c b/drivers/power/supply/bq2415x_charger.c
index 1ecbca510bba..917c26ee56bc 100644
--- a/drivers/power/supply/bq2415x_charger.c
+++ b/drivers/power/supply/bq2415x_charger.c
@@ -1674,7 +1674,7 @@ static int bq2415x_probe(struct i2c_client *client)
 	/* Query for initial reported_mode and set it */
 	if (bq->nb.notifier_call) {
 		if (np) {
-			notify_psy = power_supply_get_by_phandle(of_fwnode_handle(np),
+			notify_psy = power_supply_get_by_reference(of_fwnode_handle(np),
 						"ti,usb-charger-detection");
 			if (IS_ERR(notify_psy))
 				notify_psy = NULL;
diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 2d83bb125a48..aedb20c1d276 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -496,14 +496,13 @@ void power_supply_put(struct power_supply *psy)
 }
 EXPORT_SYMBOL_GPL(power_supply_put);
 
-#ifdef CONFIG_OF
 static int power_supply_match_device_fwnode(struct device *dev, const void *data)
 {
 	return dev->parent && dev_fwnode(dev->parent) == data;
 }
 
 /**
- * power_supply_get_by_phandle() - Search for a power supply and returns its ref
+ * power_supply_get_by_reference() - Search for a power supply and returns its ref
  * @fwnode: Pointer to fwnode holding phandle property
  * @property: Name of property holding a power supply name
  *
@@ -514,8 +513,8 @@ static int power_supply_match_device_fwnode(struct device *dev, const void *data
  * Return: On success returns a reference to a power supply with
  * matching name equals to value under @property, NULL or ERR_PTR otherwise.
  */
-struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode,
-						 const char *property)
+struct power_supply *power_supply_get_by_reference(struct fwnode_handle *fwnode,
+						   const char *property)
 {
 	struct fwnode_handle *power_supply_fwnode;
 	struct power_supply *psy = NULL;
@@ -537,7 +536,7 @@ struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode,
 
 	return psy;
 }
-EXPORT_SYMBOL_GPL(power_supply_get_by_phandle);
+EXPORT_SYMBOL_GPL(power_supply_get_by_reference);
 
 static void devm_power_supply_put(struct device *dev, void *res)
 {
@@ -547,16 +546,16 @@ static void devm_power_supply_put(struct device *dev, void *res)
 }
 
 /**
- * devm_power_supply_get_by_phandle() - Resource managed version of
- *  power_supply_get_by_phandle()
+ * devm_power_supply_get_by_reference() - Resource managed version of
+ *  power_supply_get_by_reference()
  * @dev: Pointer to device holding phandle property
  * @property: Name of property holding a power supply phandle
  *
  * Return: On success returns a reference to a power supply with
  * matching name equals to value under @property, NULL or ERR_PTR otherwise.
  */
-struct power_supply *devm_power_supply_get_by_phandle(struct device *dev,
-						      const char *property)
+struct power_supply *devm_power_supply_get_by_reference(struct device *dev,
+							const char *property)
 {
 	struct power_supply **ptr, *psy;
 
@@ -567,7 +566,7 @@ struct power_supply *devm_power_supply_get_by_phandle(struct device *dev,
 	if (!ptr)
 		return ERR_PTR(-ENOMEM);
 
-	psy = power_supply_get_by_phandle(dev_fwnode(dev), property);
+	psy = power_supply_get_by_reference(dev_fwnode(dev), property);
 	if (IS_ERR_OR_NULL(psy)) {
 		devres_free(ptr);
 	} else {
@@ -576,8 +575,7 @@ struct power_supply *devm_power_supply_get_by_phandle(struct device *dev,
 	}
 	return psy;
 }
-EXPORT_SYMBOL_GPL(devm_power_supply_get_by_phandle);
-#endif /* CONFIG_OF */
+EXPORT_SYMBOL_GPL(devm_power_supply_get_by_reference);
 
 int power_supply_get_battery_info(struct power_supply *psy,
 				  struct power_supply_battery_info **info_out)
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index d90ac7b73755..45468959dd98 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -807,19 +807,10 @@ static inline void power_supply_put(struct power_supply *psy) {}
 static inline struct power_supply *power_supply_get_by_name(const char *name)
 { return NULL; }
 #endif
-#ifdef CONFIG_OF
-extern struct power_supply *power_supply_get_by_phandle(struct fwnode_handle *fwnode,
-							const char *property);
-extern struct power_supply *devm_power_supply_get_by_phandle(
+extern struct power_supply *power_supply_get_by_reference(struct fwnode_handle *fwnode,
+							  const char *property);
+extern struct power_supply *devm_power_supply_get_by_reference(
 				    struct device *dev, const char *property);
-#else /* !CONFIG_OF */
-static inline struct power_supply *
-power_supply_get_by_phandle(struct device_node *np, const char *property)
-{ return NULL; }
-static inline struct power_supply *
-devm_power_supply_get_by_phandle(struct device *dev, const char *property)
-{ return NULL; }
-#endif /* CONFIG_OF */
 
 extern const enum power_supply_property power_supply_battery_info_properties[];
 extern const size_t power_supply_battery_info_properties_size;
-- 
cgit v1.2.3


From 2566de3e06a35b6517bcab11fd25b65ef90fd180 Mon Sep 17 00:00:00 2001
From: Zenghui Yu <yuzenghui@huawei.com>
Date: Wed, 18 Jun 2025 18:00:26 +0800
Subject: crypto: hisilicon - Use fine grained DMA mapping direction

The following splat was triggered when booting the kernel built with
arm64's defconfig + CRYPTO_SELFTESTS + DMA_API_DEBUG.

 ------------[ cut here ]------------
 DMA-API: hisi_sec2 0000:75:00.0: cacheline tracking EEXIST, overlapping mappings aren't supported
 WARNING: CPU: 24 PID: 1273 at kernel/dma/debug.c:596 add_dma_entry+0x248/0x308

 Call trace:
  add_dma_entry+0x248/0x308 (P)
  debug_dma_map_sg+0x208/0x3e4
  __dma_map_sg_attrs+0xbc/0x118
  dma_map_sg_attrs+0x10/0x24
  hisi_acc_sg_buf_map_to_hw_sgl+0x80/0x218 [hisi_qm]
  sec_cipher_map+0xc4/0x338 [hisi_sec2]
  sec_aead_sgl_map+0x18/0x24 [hisi_sec2]
  sec_process+0xb8/0x36c [hisi_sec2]
  sec_aead_crypto+0xe4/0x264 [hisi_sec2]
  sec_aead_encrypt+0x14/0x20 [hisi_sec2]
  crypto_aead_encrypt+0x24/0x38
  test_aead_vec_cfg+0x480/0x7e4
  test_aead_vec+0x84/0x1b8
  alg_test_aead+0xc0/0x498
  alg_test.part.0+0x518/0x524
  alg_test+0x20/0x64
  cryptomgr_test+0x24/0x44
  kthread+0x130/0x1fc
  ret_from_fork+0x10/0x20
 ---[ end trace 0000000000000000 ]---
 DMA-API: Mapped at:
  debug_dma_map_sg+0x234/0x3e4
  __dma_map_sg_attrs+0xbc/0x118
  dma_map_sg_attrs+0x10/0x24
  hisi_acc_sg_buf_map_to_hw_sgl+0x80/0x218 [hisi_qm]
  sec_cipher_map+0xc4/0x338 [hisi_sec2]

This occurs in selftests where the input and the output scatterlist point
to the same underlying memory (e.g., when tested with INPLACE_TWO_SGLISTS
mode).

The problem is that the hisi_sec2 driver maps these two different
scatterlists using the DMA_BIDIRECTIONAL flag which leads to overlapped
write mappings which are not supported by the DMA layer.

Fix it by using the fine grained and correct DMA mapping directions. While
at it, switch the DMA directions used by the hisi_zip driver too.

Signed-off-by: Zenghui Yu <yuzenghui@huawei.com>
Reviewed-by: Longfang Liu <liulongfang@huawei.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
---
 drivers/crypto/hisilicon/sec2/sec_crypto.c | 21 +++++++++++++--------
 drivers/crypto/hisilicon/sgl.c             | 15 ++++++++-------
 drivers/crypto/hisilicon/zip/zip_crypto.c  | 13 +++++++------
 include/linux/hisi_acc_qm.h                |  4 ++--
 4 files changed, 30 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/crypto/hisilicon/sec2/sec_crypto.c b/drivers/crypto/hisilicon/sec2/sec_crypto.c
index 8ea5305bc320..7d04e770a8c2 100644
--- a/drivers/crypto/hisilicon/sec2/sec_crypto.c
+++ b/drivers/crypto/hisilicon/sec2/sec_crypto.c
@@ -965,6 +965,7 @@ static int sec_cipher_map(struct sec_ctx *ctx, struct sec_req *req,
 	struct sec_qp_ctx *qp_ctx = req->qp_ctx;
 	struct sec_alg_res *res = &qp_ctx->res[req->req_id];
 	struct device *dev = ctx->dev;
+	enum dma_data_direction src_direction;
 	int ret;
 
 	if (req->use_pbuf) {
@@ -990,10 +991,11 @@ static int sec_cipher_map(struct sec_ctx *ctx, struct sec_req *req,
 		a_req->out_mac_dma = res->out_mac_dma;
 	}
 
+	src_direction = dst == src ? DMA_BIDIRECTIONAL : DMA_TO_DEVICE;
 	req->in = hisi_acc_sg_buf_map_to_hw_sgl(dev, src,
 						qp_ctx->c_in_pool,
 						req->req_id,
-						&req->in_dma);
+						&req->in_dma, src_direction);
 	if (IS_ERR(req->in)) {
 		dev_err(dev, "fail to dma map input sgl buffers!\n");
 		return PTR_ERR(req->in);
@@ -1003,7 +1005,7 @@ static int sec_cipher_map(struct sec_ctx *ctx, struct sec_req *req,
 		ret = sec_aead_mac_init(a_req);
 		if (unlikely(ret)) {
 			dev_err(dev, "fail to init mac data for ICV!\n");
-			hisi_acc_sg_buf_unmap(dev, src, req->in);
+			hisi_acc_sg_buf_unmap(dev, src, req->in, src_direction);
 			return ret;
 		}
 	}
@@ -1015,11 +1017,12 @@ static int sec_cipher_map(struct sec_ctx *ctx, struct sec_req *req,
 		c_req->c_out = hisi_acc_sg_buf_map_to_hw_sgl(dev, dst,
 							     qp_ctx->c_out_pool,
 							     req->req_id,
-							     &c_req->c_out_dma);
+							     &c_req->c_out_dma,
+							     DMA_FROM_DEVICE);
 
 		if (IS_ERR(c_req->c_out)) {
 			dev_err(dev, "fail to dma map output sgl buffers!\n");
-			hisi_acc_sg_buf_unmap(dev, src, req->in);
+			hisi_acc_sg_buf_unmap(dev, src, req->in, src_direction);
 			return PTR_ERR(c_req->c_out);
 		}
 	}
@@ -1036,10 +1039,12 @@ static void sec_cipher_unmap(struct sec_ctx *ctx, struct sec_req *req,
 	if (req->use_pbuf) {
 		sec_cipher_pbuf_unmap(ctx, req, dst);
 	} else {
-		if (dst != src)
-			hisi_acc_sg_buf_unmap(dev, src, req->in);
-
-		hisi_acc_sg_buf_unmap(dev, dst, c_req->c_out);
+		if (dst != src) {
+			hisi_acc_sg_buf_unmap(dev, dst, c_req->c_out, DMA_FROM_DEVICE);
+			hisi_acc_sg_buf_unmap(dev, src, req->in, DMA_TO_DEVICE);
+		} else {
+			hisi_acc_sg_buf_unmap(dev, src, req->in, DMA_BIDIRECTIONAL);
+		}
 	}
 }
 
diff --git a/drivers/crypto/hisilicon/sgl.c b/drivers/crypto/hisilicon/sgl.c
index c974f95cd126..7a9ef2a9972a 100644
--- a/drivers/crypto/hisilicon/sgl.c
+++ b/drivers/crypto/hisilicon/sgl.c
@@ -210,15 +210,15 @@ static void clear_hw_sgl_sge(struct hisi_acc_hw_sgl *hw_sgl)
  * @pool: Pool which hw sgl memory will be allocated in.
  * @index: Index of hisi_acc_hw_sgl in pool.
  * @hw_sgl_dma: The dma address of allocated hw sgl.
+ * @dir: DMA direction.
  *
  * This function builds hw sgl according input sgl, user can use hw_sgl_dma
  * as src/dst in its BD. Only support single hw sgl currently.
  */
 struct hisi_acc_hw_sgl *
-hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
-			      struct scatterlist *sgl,
-			      struct hisi_acc_sgl_pool *pool,
-			      u32 index, dma_addr_t *hw_sgl_dma)
+hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev, struct scatterlist *sgl,
+			      struct hisi_acc_sgl_pool *pool, u32 index,
+			      dma_addr_t *hw_sgl_dma, enum dma_data_direction dir)
 {
 	struct hisi_acc_hw_sgl *curr_hw_sgl;
 	unsigned int i, sg_n_mapped;
@@ -232,7 +232,7 @@ hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
 
 	sg_n = sg_nents(sgl);
 
-	sg_n_mapped = dma_map_sg(dev, sgl, sg_n, DMA_BIDIRECTIONAL);
+	sg_n_mapped = dma_map_sg(dev, sgl, sg_n, dir);
 	if (!sg_n_mapped) {
 		dev_err(dev, "DMA mapping for SG error!\n");
 		return ERR_PTR(-EINVAL);
@@ -276,16 +276,17 @@ EXPORT_SYMBOL_GPL(hisi_acc_sg_buf_map_to_hw_sgl);
  * @dev: The device which hw sgl belongs to.
  * @sgl: Related scatterlist.
  * @hw_sgl: Virtual address of hw sgl.
+ * @dir: DMA direction.
  *
  * This function unmaps allocated hw sgl.
  */
 void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl,
-			   struct hisi_acc_hw_sgl *hw_sgl)
+			   struct hisi_acc_hw_sgl *hw_sgl, enum dma_data_direction dir)
 {
 	if (!dev || !sgl || !hw_sgl)
 		return;
 
-	dma_unmap_sg(dev, sgl, sg_nents(sgl), DMA_BIDIRECTIONAL);
+	dma_unmap_sg(dev, sgl, sg_nents(sgl), dir);
 	clear_hw_sgl_sge(hw_sgl);
 	hw_sgl->entry_sum_in_chain = 0;
 	hw_sgl->entry_sum_in_sgl = 0;
diff --git a/drivers/crypto/hisilicon/zip/zip_crypto.c b/drivers/crypto/hisilicon/zip/zip_crypto.c
index 7327f8f29b01..b97513981a3b 100644
--- a/drivers/crypto/hisilicon/zip/zip_crypto.c
+++ b/drivers/crypto/hisilicon/zip/zip_crypto.c
@@ -224,7 +224,8 @@ static int hisi_zip_do_work(struct hisi_zip_qp_ctx *qp_ctx,
 		return -EINVAL;
 
 	req->hw_src = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->src, pool,
-						    req->req_id << 1, &req->dma_src);
+						    req->req_id << 1, &req->dma_src,
+						    DMA_TO_DEVICE);
 	if (IS_ERR(req->hw_src)) {
 		dev_err(dev, "failed to map the src buffer to hw sgl (%ld)!\n",
 			PTR_ERR(req->hw_src));
@@ -233,7 +234,7 @@ static int hisi_zip_do_work(struct hisi_zip_qp_ctx *qp_ctx,
 
 	req->hw_dst = hisi_acc_sg_buf_map_to_hw_sgl(dev, a_req->dst, pool,
 						    (req->req_id << 1) + 1,
-						    &req->dma_dst);
+						    &req->dma_dst, DMA_FROM_DEVICE);
 	if (IS_ERR(req->hw_dst)) {
 		ret = PTR_ERR(req->hw_dst);
 		dev_err(dev, "failed to map the dst buffer to hw slg (%d)!\n",
@@ -258,9 +259,9 @@ static int hisi_zip_do_work(struct hisi_zip_qp_ctx *qp_ctx,
 	return -EINPROGRESS;
 
 err_unmap_output:
-	hisi_acc_sg_buf_unmap(dev, a_req->dst, req->hw_dst);
+	hisi_acc_sg_buf_unmap(dev, a_req->dst, req->hw_dst, DMA_FROM_DEVICE);
 err_unmap_input:
-	hisi_acc_sg_buf_unmap(dev, a_req->src, req->hw_src);
+	hisi_acc_sg_buf_unmap(dev, a_req->src, req->hw_src, DMA_TO_DEVICE);
 	return ret;
 }
 
@@ -303,8 +304,8 @@ static void hisi_zip_acomp_cb(struct hisi_qp *qp, void *data)
 		err = -EIO;
 	}
 
-	hisi_acc_sg_buf_unmap(dev, acomp_req->src, req->hw_src);
-	hisi_acc_sg_buf_unmap(dev, acomp_req->dst, req->hw_dst);
+	hisi_acc_sg_buf_unmap(dev, acomp_req->dst, req->hw_dst, DMA_FROM_DEVICE);
+	hisi_acc_sg_buf_unmap(dev, acomp_req->src, req->hw_src, DMA_TO_DEVICE);
 
 	acomp_req->dlen = ops->get_dstlen(sqe);
 
diff --git a/include/linux/hisi_acc_qm.h b/include/linux/hisi_acc_qm.h
index 99fcf65d575f..0c4c84b8c3be 100644
--- a/include/linux/hisi_acc_qm.h
+++ b/include/linux/hisi_acc_qm.h
@@ -556,9 +556,9 @@ int hisi_qm_mb(struct hisi_qm *qm, u8 cmd, dma_addr_t dma_addr, u16 queue,
 struct hisi_acc_sgl_pool;
 struct hisi_acc_hw_sgl *hisi_acc_sg_buf_map_to_hw_sgl(struct device *dev,
 	struct scatterlist *sgl, struct hisi_acc_sgl_pool *pool,
-	u32 index, dma_addr_t *hw_sgl_dma);
+	u32 index, dma_addr_t *hw_sgl_dma, enum dma_data_direction dir);
 void hisi_acc_sg_buf_unmap(struct device *dev, struct scatterlist *sgl,
-			   struct hisi_acc_hw_sgl *hw_sgl);
+			   struct hisi_acc_hw_sgl *hw_sgl, enum dma_data_direction dir);
 struct hisi_acc_sgl_pool *hisi_acc_create_sgl_pool(struct device *dev,
 						   u32 count, u32 sge_nr);
 void hisi_acc_free_sgl_pool(struct device *dev,
-- 
cgit v1.2.3


From 2773d282cd56464f62e9b4703c41d2f733a67842 Mon Sep 17 00:00:00 2001
From: Junxuan Liao <ljx@cs.wisc.edu>
Date: Sun, 22 Jun 2025 23:01:32 -0500
Subject: docs/vfs: update references to i_mutex to i_rwsem

VFS has switched to i_rwsem for ten years now (9902af79c01a: parallel
lookups actual switch to rwsem), but the VFS documentation and comments
still has references to i_mutex.

Signed-off-by: Junxuan Liao <ljx@cs.wisc.edu>
Link: https://lore.kernel.org/72223729-5471-474a-af3c-f366691fba82@cs.wisc.edu
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/vfs.rst |  5 +++--
 fs/attr.c                         | 10 +++++-----
 fs/buffer.c                       |  2 +-
 fs/dcache.c                       | 10 +++++-----
 fs/direct-io.c                    |  8 ++++----
 fs/inode.c                        |  9 ++++-----
 fs/libfs.c                        |  5 +++--
 fs/locks.c                        |  2 +-
 fs/namei.c                        | 22 +++++++++++-----------
 fs/namespace.c                    |  2 +-
 fs/stack.c                        |  4 ++--
 fs/xattr.c                        |  2 +-
 include/linux/exportfs.h          |  4 ++--
 include/linux/fs.h                |  6 +++---
 include/linux/fs_stack.h          |  2 +-
 include/linux/quotaops.h          |  2 +-
 16 files changed, 48 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index fd32a9a17bfb..dd9da7e04a99 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -758,8 +758,9 @@ process is more complicated and uses write_begin/write_end or
 dirty_folio to write data into the address_space, and
 writepages to writeback data to storage.
 
-Adding and removing pages to/from an address_space is protected by the
-inode's i_mutex.
+Removing pages from an address_space requires holding the inode's i_rwsem
+exclusively, while adding pages to the address_space requires holding the
+inode's i_mapping->invalidate_lock exclusively.
 
 When data is written to a page, the PG_Dirty flag should be set.  It
 typically remains set until writepages asks for it to be written.  This
diff --git a/fs/attr.c b/fs/attr.c
index 9caf63d20d03..5425c1dbbff9 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -230,7 +230,7 @@ EXPORT_SYMBOL(setattr_prepare);
  * @inode:	the inode to be truncated
  * @offset:	the new size to assign to the inode
  *
- * inode_newsize_ok must be called with i_mutex held.
+ * inode_newsize_ok must be called with i_rwsem held exclusively.
  *
  * inode_newsize_ok will check filesystem limits and ulimits to check that the
  * new inode size is within limits. inode_newsize_ok will also send SIGXFSZ
@@ -318,7 +318,7 @@ static void setattr_copy_mgtime(struct inode *inode, const struct iattr *attr)
  * @inode:	the inode to be updated
  * @attr:	the new attributes
  *
- * setattr_copy must be called with i_mutex held.
+ * setattr_copy must be called with i_rwsem held exclusively.
  *
  * setattr_copy updates the inode's metadata with that specified
  * in attr on idmapped mounts. Necessary permission checks to determine
@@ -403,13 +403,13 @@ EXPORT_SYMBOL(may_setattr);
  * @attr:	new attributes
  * @delegated_inode: returns inode, if the inode is delegated
  *
- * The caller must hold the i_mutex on the affected object.
+ * The caller must hold the i_rwsem exclusively on the affected object.
  *
  * If notify_change discovers a delegation in need of breaking,
  * it will return -EWOULDBLOCK and return a reference to the inode in
  * delegated_inode.  The caller should then break the delegation and
  * retry.  Because breaking a delegation may take a long time, the
- * caller should drop the i_mutex before doing so.
+ * caller should drop the i_rwsem before doing so.
  *
  * Alternatively, a caller may pass NULL for delegated_inode.  This may
  * be appropriate for callers that expect the underlying filesystem not
@@ -456,7 +456,7 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
 		if (S_ISLNK(inode->i_mode))
 			return -EOPNOTSUPP;
 
-		/* Flag setting protected by i_mutex */
+		/* Flag setting protected by i_rwsem */
 		if (is_sxid(attr->ia_mode))
 			inode->i_flags &= ~S_NOSEC;
 	}
diff --git a/fs/buffer.c b/fs/buffer.c
index a14d281c6a74..1d34200f69c8 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2609,7 +2609,7 @@ EXPORT_SYMBOL(cont_write_begin);
  * holes and correct delalloc and unwritten extent mapping on filesystems that
  * support these features.
  *
- * We are not allowed to take the i_mutex here so we have to play games to
+ * We are not allowed to take the i_rwsem here so we have to play games to
  * protect against truncate races as the page could now be beyond EOF.  Because
  * truncate writes the inode size before removing pages, once we have the
  * page lock we can determine safely if the page is beyond EOF. If it is not
diff --git a/fs/dcache.c b/fs/dcache.c
index 03d58b2d4fa3..ab8465ae9cad 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -2774,10 +2774,10 @@ static void copy_name(struct dentry *dentry, struct dentry *target)
  * @target: new dentry
  * @exchange: exchange the two dentries
  *
- * Update the dcache to reflect the move of a file name. Negative
- * dcache entries should not be moved in this way. Caller must hold
- * rename_lock, the i_mutex of the source and target directories,
- * and the sb->s_vfs_rename_mutex if they differ. See lock_rename().
+ * Update the dcache to reflect the move of a file name. Negative dcache
+ * entries should not be moved in this way. Caller must hold rename_lock, the
+ * i_rwsem of the source and target directories (exclusively), and the sb->
+ * s_vfs_rename_mutex if they differ. See lock_rename().
  */
 static void __d_move(struct dentry *dentry, struct dentry *target,
 		     bool exchange)
@@ -2923,7 +2923,7 @@ struct dentry *d_ancestor(struct dentry *p1, struct dentry *p2)
  * This helper attempts to cope with remotely renamed directories
  *
  * It assumes that the caller is already holding
- * dentry->d_parent->d_inode->i_mutex, and rename_lock
+ * dentry->d_parent->d_inode->i_rwsem, and rename_lock
  *
  * Note: If ever the locking in lock_rename() changes, then please
  * remember to update this too...
diff --git a/fs/direct-io.c b/fs/direct-io.c
index bbd05f1a2145..1694ee9a9382 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -1083,8 +1083,8 @@ static inline int drop_refcount(struct dio *dio)
  * The locking rules are governed by the flags parameter:
  *  - if the flags value contains DIO_LOCKING we use a fancy locking
  *    scheme for dumb filesystems.
- *    For writes this function is called under i_mutex and returns with
- *    i_mutex held, for reads, i_mutex is not held on entry, but it is
+ *    For writes this function is called under i_rwsem and returns with
+ *    i_rwsem held, for reads, i_rwsem is not held on entry, but it is
  *    taken and dropped again before returning.
  *  - if the flags value does NOT contain DIO_LOCKING we don't use any
  *    internal locking but rather rely on the filesystem to synchronize
@@ -1094,7 +1094,7 @@ static inline int drop_refcount(struct dio *dio)
  * counter before starting direct I/O, and decrement it once we are done.
  * Truncate can wait for it to reach zero to provide exclusion.  It is
  * expected that filesystem provide exclusion between new direct I/O
- * and truncates.  For DIO_LOCKING filesystems this is done by i_mutex,
+ * and truncates.  For DIO_LOCKING filesystems this is done by i_rwsem,
  * but other filesystems need to take care of this on their own.
  *
  * NOTE: if you pass "sdio" to anything by pointer make sure that function
@@ -1279,7 +1279,7 @@ ssize_t __blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 
 	/*
 	 * All block lookups have been performed. For READ requests
-	 * we can let i_mutex go now that its achieved its purpose
+	 * we can let i_rwsem go now that its achieved its purpose
 	 * of protecting us from looking up uninitialized blocks.
 	 */
 	if (iov_iter_rw(iter) == READ && (dio->flags & DIO_LOCKING))
diff --git a/fs/inode.c b/fs/inode.c
index 99318b157a9a..a0150e2ef22a 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -1158,9 +1158,8 @@ void lockdep_annotate_inode_mutex_key(struct inode *inode)
 		/* Set new key only if filesystem hasn't already changed it */
 		if (lockdep_match_class(&inode->i_rwsem, &type->i_mutex_key)) {
 			/*
-			 * ensure nobody is actually holding i_mutex
+			 * ensure nobody is actually holding i_rwsem
 			 */
-			// mutex_destroy(&inode->i_mutex);
 			init_rwsem(&inode->i_rwsem);
 			lockdep_set_class(&inode->i_rwsem,
 					  &type->i_mutex_dir_key);
@@ -2615,7 +2614,7 @@ EXPORT_SYMBOL(inode_dio_finished);
  * proceed with a truncate or equivalent operation.
  *
  * Must be called under a lock that serializes taking new references
- * to i_dio_count, usually by inode->i_mutex.
+ * to i_dio_count, usually by inode->i_rwsem.
  */
 void inode_dio_wait(struct inode *inode)
 {
@@ -2633,7 +2632,7 @@ EXPORT_SYMBOL(inode_dio_wait_interruptible);
 /*
  * inode_set_flags - atomically set some inode flags
  *
- * Note: the caller should be holding i_mutex, or else be sure that
+ * Note: the caller should be holding i_rwsem exclusively, or else be sure that
  * they have exclusive access to the inode structure (i.e., while the
  * inode is being instantiated).  The reason for the cmpxchg() loop
  * --- which wouldn't be necessary if all code paths which modify
@@ -2641,7 +2640,7 @@ EXPORT_SYMBOL(inode_dio_wait_interruptible);
  * code path which doesn't today so we use cmpxchg() out of an abundance
  * of caution.
  *
- * In the long run, i_mutex is overkill, and we should probably look
+ * In the long run, i_rwsem is overkill, and we should probably look
  * at using the i_lock spinlock to protect i_flags, and then make sure
  * it is so documented in include/linux/fs.h and that all code follows
  * the locking convention!!
diff --git a/fs/libfs.c b/fs/libfs.c
index 9ea0ecc325a8..4d1862f589e8 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -946,7 +946,8 @@ EXPORT_SYMBOL(simple_write_begin);
  * simple_write_end does the minimum needed for updating a folio after
  * writing is done. It has the same API signature as the .write_end of
  * address_space_operations vector. So it can just be set onto .write_end for
- * FSes that don't need any other processing. i_mutex is assumed to be held.
+ * FSes that don't need any other processing. i_rwsem is assumed to be held
+ * exclusively.
  * Block based filesystems should use generic_write_end().
  * NOTE: Even though i_size might get updated by this function, mark_inode_dirty
  * is not called, so a filesystem that actually does store data in .write_inode
@@ -973,7 +974,7 @@ static int simple_write_end(struct file *file, struct address_space *mapping,
 	}
 	/*
 	 * No need to use i_size_read() here, the i_size
-	 * cannot change under us because we hold the i_mutex.
+	 * cannot change under us because we hold the i_rwsem.
 	 */
 	if (last_pos > inode->i_size)
 		i_size_write(inode, last_pos);
diff --git a/fs/locks.c b/fs/locks.c
index f96024feab17..559f02aa4172 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1794,7 +1794,7 @@ generic_add_lease(struct file *filp, int arg, struct file_lease **flp, void **pr
 
 	/*
 	 * In the delegation case we need mutual exclusion with
-	 * a number of operations that take the i_mutex.  We trylock
+	 * a number of operations that take the i_rwsem.  We trylock
 	 * because delegations are an optional optimization, and if
 	 * there's some chance of a conflict--we'd rather not
 	 * bother, maybe that's a sign this just isn't a good file to
diff --git a/fs/namei.c b/fs/namei.c
index 981da44e1291..f5c157290ce2 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1469,7 +1469,7 @@ static int __traverse_mounts(struct path *path, unsigned flags, bool *jumped,
 	int ret = 0;
 
 	while (flags & DCACHE_MANAGED_DENTRY) {
-		/* Allow the filesystem to manage the transit without i_mutex
+		/* Allow the filesystem to manage the transit without i_rwsem
 		 * being held. */
 		if (flags & DCACHE_MANAGE_TRANSIT) {
 			ret = path->dentry->d_op->d_manage(path, false);
@@ -2945,7 +2945,7 @@ EXPORT_SYMBOL(try_lookup_noperm);
  * Note that this routine is purely a helper for filesystem usage and should
  * not be called by generic code.  It does no permission checking.
  *
- * The caller must hold base->i_mutex.
+ * The caller must hold base->i_rwsem.
  */
 struct dentry *lookup_noperm(struct qstr *name, struct dentry *base)
 {
@@ -2971,7 +2971,7 @@ EXPORT_SYMBOL(lookup_noperm);
  *
  * This can be used for in-kernel filesystem clients such as file servers.
  *
- * The caller must hold base->i_mutex.
+ * The caller must hold base->i_rwsem.
  */
 struct dentry *lookup_one(struct mnt_idmap *idmap, struct qstr *name,
 			  struct dentry *base)
@@ -4542,13 +4542,13 @@ SYSCALL_DEFINE1(rmdir, const char __user *, pathname)
  * @dentry:	victim
  * @delegated_inode: returns victim inode, if the inode is delegated.
  *
- * The caller must hold dir->i_mutex.
+ * The caller must hold dir->i_rwsem exclusively.
  *
  * If vfs_unlink discovers a delegation, it will return -EWOULDBLOCK and
  * return a reference to the inode in delegated_inode.  The caller
  * should then break the delegation on that inode and retry.  Because
  * breaking a delegation may take a long time, the caller should drop
- * dir->i_mutex before doing so.
+ * dir->i_rwsem before doing so.
  *
  * Alternatively, a caller may pass NULL for delegated_inode.  This may
  * be appropriate for callers that expect the underlying filesystem not
@@ -4607,7 +4607,7 @@ EXPORT_SYMBOL(vfs_unlink);
 
 /*
  * Make sure that the actual truncation of the file will occur outside its
- * directory's i_mutex.  Truncate can take a long time if there is a lot of
+ * directory's i_rwsem.  Truncate can take a long time if there is a lot of
  * writeout happening, and we don't want to prevent access to the directory
  * while waiting on the I/O.
  */
@@ -4785,13 +4785,13 @@ SYSCALL_DEFINE2(symlink, const char __user *, oldname, const char __user *, newn
  * @new_dentry:	where to create the new link
  * @delegated_inode: returns inode needing a delegation break
  *
- * The caller must hold dir->i_mutex
+ * The caller must hold dir->i_rwsem exclusively.
  *
  * If vfs_link discovers a delegation on the to-be-linked file in need
  * of breaking, it will return -EWOULDBLOCK and return a reference to the
  * inode in delegated_inode.  The caller should then break the delegation
  * and retry.  Because breaking a delegation may take a long time, the
- * caller should drop the i_mutex before doing so.
+ * caller should drop the i_rwsem before doing so.
  *
  * Alternatively, a caller may pass NULL for delegated_inode.  This may
  * be appropriate for callers that expect the underlying filesystem not
@@ -4987,7 +4987,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *	c) we may have to lock up to _four_ objects - parents and victim (if it exists),
  *	   and source (if it's a non-directory or a subdirectory that moves to
  *	   different parent).
- *	   And that - after we got ->i_mutex on parents (until then we don't know
+ *	   And that - after we got ->i_rwsem on parents (until then we don't know
  *	   whether the target exists).  Solution: try to be smart with locking
  *	   order for inodes.  We rely on the fact that tree topology may change
  *	   only under ->s_vfs_rename_mutex _and_ that parent of the object we
@@ -4999,9 +4999,9 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  *	   has no more than 1 dentry.  If "hybrid" objects will ever appear,
  *	   we'd better make sure that there's no link(2) for them.
  *	d) conversion from fhandle to dentry may come in the wrong moment - when
- *	   we are removing the target. Solution: we will have to grab ->i_mutex
+ *	   we are removing the target. Solution: we will have to grab ->i_rwsem
  *	   in the fhandle_to_dentry code. [FIXME - current nfsfh.c relies on
- *	   ->i_mutex on parents, which works but leads to some truly excessive
+ *	   ->i_rwsem on parents, which works but leads to some truly excessive
  *	   locking].
  */
 int vfs_rename(struct renamedata *rd)
diff --git a/fs/namespace.c b/fs/namespace.c
index e13d9ab4f564..8a1bfdf862f8 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2053,7 +2053,7 @@ out:
  * detach_mounts allows lazily unmounting those mounts instead of
  * leaking them.
  *
- * The caller may hold dentry->d_inode->i_mutex.
+ * The caller may hold dentry->d_inode->i_rwsem.
  */
 void __detach_mounts(struct dentry *dentry)
 {
diff --git a/fs/stack.c b/fs/stack.c
index f18920119944..d8c782e064e3 100644
--- a/fs/stack.c
+++ b/fs/stack.c
@@ -3,7 +3,7 @@
 #include <linux/fs.h>
 #include <linux/fs_stack.h>
 
-/* does _NOT_ require i_mutex to be held.
+/* does _NOT_ require i_rwsem to be held.
  *
  * This function cannot be inlined since i_size_{read,write} is rather
  * heavy-weight on 32-bit systems
@@ -41,7 +41,7 @@ void fsstack_copy_inode_size(struct inode *dst, struct inode *src)
 	 * If CONFIG_SMP or CONFIG_PREEMPTION on 32-bit, it's vital for
 	 * fsstack_copy_inode_size() to hold some lock around
 	 * i_size_write(), otherwise i_size_read() may spin forever (see
-	 * include/linux/fs.h).  We don't necessarily hold i_mutex when this
+	 * include/linux/fs.h).  We don't necessarily hold i_rwsem when this
 	 * is called, so take i_lock for that case.
 	 *
 	 * And if on 32-bit, continue our effort to keep the two halves of
diff --git a/fs/xattr.c b/fs/xattr.c
index 8ec5b0204bfd..c32e7d56a5d3 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -215,7 +215,7 @@ EXPORT_SYMBOL(__vfs_setxattr);
  *
  *  returns the result of the internal setxattr or setsecurity operations.
  *
- *  This function requires the caller to lock the inode's i_mutex before it
+ *  This function requires the caller to lock the inode's i_rwsem before it
  *  is executed. It also assumes that the caller will make the appropriate
  *  permission checks.
  */
diff --git a/include/linux/exportfs.h b/include/linux/exportfs.h
index 25c4a5afbd44..cfb0dd1ea49c 100644
--- a/include/linux/exportfs.h
+++ b/include/linux/exportfs.h
@@ -230,7 +230,7 @@ struct handle_to_path_ctx {
  *    directory.  The name should be stored in the @name (with the
  *    understanding that it is already pointing to a %NAME_MAX+1 sized
  *    buffer.   get_name() should return %0 on success, a negative error code
- *    or error.  @get_name will be called without @parent->i_mutex held.
+ *    or error.  @get_name will be called without @parent->i_rwsem held.
  *
  * get_parent:
  *    @get_parent should find the parent directory for the given @child which
@@ -247,7 +247,7 @@ struct handle_to_path_ctx {
  *    @commit_metadata should commit metadata changes to stable storage.
  *
  * Locking rules:
- *    get_parent is called with child->d_inode->i_mutex down
+ *    get_parent is called with child->d_inode->i_rwsem down
  *    get_name is not (which is possibly inconsistent)
  */
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1d9586a78041..09e3e80b0528 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -837,7 +837,7 @@ static inline void inode_fake_hash(struct inode *inode)
 }
 
 /*
- * inode->i_mutex nesting subclasses for the lock validator:
+ * inode->i_rwsem nesting subclasses for the lock validator:
  *
  * 0: the object of the current VFS operation
  * 1: parent
@@ -989,7 +989,7 @@ static inline loff_t i_size_read(const struct inode *inode)
 
 /*
  * NOTE: unlike i_size_read(), i_size_write() does need locking around it
- * (normally i_mutex), otherwise on 32bit/SMP an update of i_size_seqcount
+ * (normally i_rwsem), otherwise on 32bit/SMP an update of i_size_seqcount
  * can be lost, resulting in subsequent i_size_read() calls spinning forever.
  */
 static inline void i_size_write(struct inode *inode, loff_t i_size)
@@ -1921,7 +1921,7 @@ static inline void sb_end_intwrite(struct super_block *sb)
  * freeze protection should be the outermost lock. In particular, we have:
  *
  * sb_start_write
- *   -> i_mutex			(write path, truncate, directory ops, ...)
+ *   -> i_rwsem			(write path, truncate, directory ops, ...)
  *   -> s_umount		(freeze_super, thaw_super)
  */
 static inline void sb_start_write(struct super_block *sb)
diff --git a/include/linux/fs_stack.h b/include/linux/fs_stack.h
index 2b1f74b24070..0cc2fa283305 100644
--- a/include/linux/fs_stack.h
+++ b/include/linux/fs_stack.h
@@ -3,7 +3,7 @@
 #define _LINUX_FS_STACK_H
 
 /* This file defines generic functions used primarily by stackable
- * filesystems; none of these functions require i_mutex to be held.
+ * filesystems; none of these functions require i_rwsem to be held.
  */
 
 #include <linux/fs.h>
diff --git a/include/linux/quotaops.h b/include/linux/quotaops.h
index 06cc8888199e..c334f82ed385 100644
--- a/include/linux/quotaops.h
+++ b/include/linux/quotaops.h
@@ -19,7 +19,7 @@ static inline struct quota_info *sb_dqopt(struct super_block *sb)
 	return &sb->s_dquot;
 }
 
-/* i_mutex must being held */
+/* i_rwsem must being held */
 static inline bool is_quota_modification(struct mnt_idmap *idmap,
 					 struct inode *inode, struct iattr *ia)
 {
-- 
cgit v1.2.3


From cbe4134ea4bc493239786220bd69cb8a13493190 Mon Sep 17 00:00:00 2001
From: Shivank Garg <shivankg@amd.com>
Date: Fri, 20 Jun 2025 07:03:30 +0000
Subject: fs: export anon_inode_make_secure_inode() and fix secretmem LSM
 bypass

Export anon_inode_make_secure_inode() to allow KVM guest_memfd to create
anonymous inodes with proper security context. This replaces the current
pattern of calling alloc_anon_inode() followed by
inode_init_security_anon() for creating security context manually.

This change also fixes a security regression in secretmem where the
S_PRIVATE flag was not cleared after alloc_anon_inode(), causing
LSM/SELinux checks to be bypassed for secretmem file descriptors.

As guest_memfd currently resides in the KVM module, we need to export this
symbol for use outside the core kernel. In the future, guest_memfd might be
moved to core-mm, at which point the symbols no longer would have to be
exported. When/if that happens is still unclear.

Fixes: 2bfe15c52612 ("mm: create security context for memfd_secret inodes")
Suggested-by: David Hildenbrand <david@redhat.com>
Suggested-by: Mike Rapoport <rppt@kernel.org>
Signed-off-by: Shivank Garg <shivankg@amd.com>
Link: https://lore.kernel.org/20250620070328.803704-3-shivankg@amd.com
Acked-by: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/anon_inodes.c   | 23 ++++++++++++++++++-----
 include/linux/fs.h |  2 ++
 mm/secretmem.c     |  9 +--------
 3 files changed, 21 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/fs/anon_inodes.c b/fs/anon_inodes.c
index e51e7d88980a..1d847a939f29 100644
--- a/fs/anon_inodes.c
+++ b/fs/anon_inodes.c
@@ -98,14 +98,25 @@ static struct file_system_type anon_inode_fs_type = {
 	.kill_sb	= kill_anon_super,
 };
 
-static struct inode *anon_inode_make_secure_inode(
-	const char *name,
-	const struct inode *context_inode)
+/**
+ * anon_inode_make_secure_inode - allocate an anonymous inode with security context
+ * @sb:		[in]	Superblock to allocate from
+ * @name:	[in]	Name of the class of the newfile (e.g., "secretmem")
+ * @context_inode:
+ *		[in]	Optional parent inode for security inheritance
+ *
+ * The function ensures proper security initialization through the LSM hook
+ * security_inode_init_security_anon().
+ *
+ * Return:	Pointer to new inode on success, ERR_PTR on failure.
+ */
+struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name,
+					   const struct inode *context_inode)
 {
 	struct inode *inode;
 	int error;
 
-	inode = alloc_anon_inode(anon_inode_mnt->mnt_sb);
+	inode = alloc_anon_inode(sb);
 	if (IS_ERR(inode))
 		return inode;
 	inode->i_flags &= ~S_PRIVATE;
@@ -118,6 +129,7 @@ static struct inode *anon_inode_make_secure_inode(
 	}
 	return inode;
 }
+EXPORT_SYMBOL_GPL_FOR_MODULES(anon_inode_make_secure_inode, "kvm");
 
 static struct file *__anon_inode_getfile(const char *name,
 					 const struct file_operations *fops,
@@ -132,7 +144,8 @@ static struct file *__anon_inode_getfile(const char *name,
 		return ERR_PTR(-ENOENT);
 
 	if (make_inode) {
-		inode =	anon_inode_make_secure_inode(name, context_inode);
+		inode =	anon_inode_make_secure_inode(anon_inode_mnt->mnt_sb,
+						     name, context_inode);
 		if (IS_ERR(inode)) {
 			file = ERR_CAST(inode);
 			goto err;
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 4ec77da65f14..3a8e643c4279 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3606,6 +3606,8 @@ extern int simple_write_begin(struct file *file, struct address_space *mapping,
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
+struct inode *anon_inode_make_secure_inode(struct super_block *sb, const char *name,
+					   const struct inode *context_inode);
 extern int simple_nosetlease(struct file *, int, struct file_lease **, void **);
 extern const struct dentry_operations simple_dentry_operations;
 
diff --git a/mm/secretmem.c b/mm/secretmem.c
index 589b26c2d553..9a11a38a6770 100644
--- a/mm/secretmem.c
+++ b/mm/secretmem.c
@@ -195,18 +195,11 @@ static struct file *secretmem_file_create(unsigned long flags)
 	struct file *file;
 	struct inode *inode;
 	const char *anon_name = "[secretmem]";
-	int err;
 
-	inode = alloc_anon_inode(secretmem_mnt->mnt_sb);
+	inode = anon_inode_make_secure_inode(secretmem_mnt->mnt_sb, anon_name, NULL);
 	if (IS_ERR(inode))
 		return ERR_CAST(inode);
 
-	err = security_inode_init_security_anon(inode, &QSTR(anon_name), NULL);
-	if (err) {
-		file = ERR_PTR(err);
-		goto err_free_inode;
-	}
-
 	file = alloc_file_pseudo(inode, secretmem_mnt, "secretmem",
 				 O_RDWR, &secretmem_fops);
 	if (IS_ERR(file))
-- 
cgit v1.2.3


From 0c40d7cb5ef3af260e8c7f88e0e5d7ae15d6ce57 Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Thu, 19 Jun 2025 19:17:58 +0800
Subject: block: introduce max_{hw|user}_wzeroes_unmap_sectors to queue limits

Currently, disks primarily implement the write zeroes command (aka
REQ_OP_WRITE_ZEROES) through two mechanisms: the first involves
physically writing zeros to the disk media (e.g., HDDs), while the
second performs an unmap operation on the logical blocks, effectively
putting them into a deallocated state (e.g., SSDs). The first method is
generally slow, while the second method is typically very fast.

For example, on certain NVMe SSDs that support NVME_NS_DEAC, submitting
REQ_OP_WRITE_ZEROES requests with the NVME_WZ_DEAC bit can accelerate
the write zeros operation by placing disk blocks into a deallocated
state, which opportunistically avoids writing zeroes to media while
still guaranteeing that subsequent reads from the specified block range
will return zeroed data. This is a best-effort optimization, not a
mandatory requirement, some devices may partially fall back to writing
physical zeroes due to factors such as misalignment or being asked to
clear a block range smaller than the device's internal allocation unit.
Therefore, the speed of this operation is not guaranteed.

It is difficult to determine whether the storage device supports unmap
write zeroes operation. We cannot determine this by only querying
bdev_limits(bdev)->max_write_zeroes_sectors. Therefore, first, add a new
hardware queue limit parameters, max_hw_wzeroes_unmap_sectors, to
indicate whether a device supports this unmap write zeroes operation.
Then, add two new counterpart software queue limits,
max_wzeroes_unmap_sectors and max_user_wzeroes_unmap_sectors, which
allow users to disable this operation if the speed is very slow on some
sepcial devices.

Finally, for the stacked devices cases, initialize these two parameters
to UINT_MAX. This operation should be enabled by both the stacking
driver and all underlying devices.

Thanks to Martin K. Petersen for optimizing the documentation of the
write_zeroes_unmap sysfs interface.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Link: https://lore.kernel.org/20250619111806.3546162-2-yi.zhang@huaweicloud.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Martin K. Petersen" <martin.petersen@oracle.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/ABI/stable/sysfs-block | 33 +++++++++++++++++++++++++++++++++
 block/blk-settings.c                 | 20 ++++++++++++++++++--
 block/blk-sysfs.c                    | 26 ++++++++++++++++++++++++++
 include/linux/blkdev.h               | 10 ++++++++++
 4 files changed, 87 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/stable/sysfs-block b/Documentation/ABI/stable/sysfs-block
index 4ba771b56b3b..803f578dc023 100644
--- a/Documentation/ABI/stable/sysfs-block
+++ b/Documentation/ABI/stable/sysfs-block
@@ -778,6 +778,39 @@ Description:
 		0, write zeroes is not supported by the device.
 
 
+What:		/sys/block/<disk>/queue/write_zeroes_unmap_max_hw_bytes
+Date:		January 2025
+Contact:	Zhang Yi <yi.zhang@huawei.com>
+Description:
+		[RO] This file indicates whether a device supports zeroing data
+		in a specified block range without incurring the cost of
+		physically writing zeroes to the media for each individual
+		block. If this parameter is set to write_zeroes_max_bytes, the
+		device implements a zeroing operation which opportunistically
+		avoids writing zeroes to media while still guaranteeing that
+		subsequent reads from the specified block range will return
+		zeroed data. This operation is a best-effort optimization, a
+		device may fall back to physically writing zeroes to the media
+		due to other factors such as misalignment or being asked to
+		clear a block range smaller than the device's internal
+		allocation unit. If this parameter is set to 0, the device may
+		have to write each logical block media during a zeroing
+		operation.
+
+
+What:		/sys/block/<disk>/queue/write_zeroes_unmap_max_bytes
+Date:		January 2025
+Contact:	Zhang Yi <yi.zhang@huawei.com>
+Description:
+		[RW] While write_zeroes_unmap_max_hw_bytes is the hardware limit
+		for the device, this setting is the software limit. Since the
+		unmap write zeroes operation is a best-effort optimization, some
+		devices may still physically writing zeroes to media. So the
+		speed of this operation is not guaranteed. Writing a value of
+		'0' to this file disables this operation. Otherwise, this
+		parameter should be equal to write_zeroes_unmap_max_hw_bytes.
+
+
 What:		/sys/block/<disk>/queue/zone_append_max_bytes
 Date:		May 2020
 Contact:	linux-block@vger.kernel.org
diff --git a/block/blk-settings.c b/block/blk-settings.c
index a000daafbfb4..b5c75f0ac3e9 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -50,6 +50,8 @@ void blk_set_stacking_limits(struct queue_limits *lim)
 	lim->max_sectors = UINT_MAX;
 	lim->max_dev_sectors = UINT_MAX;
 	lim->max_write_zeroes_sectors = UINT_MAX;
+	lim->max_hw_wzeroes_unmap_sectors = UINT_MAX;
+	lim->max_user_wzeroes_unmap_sectors = UINT_MAX;
 	lim->max_hw_zone_append_sectors = UINT_MAX;
 	lim->max_user_discard_sectors = UINT_MAX;
 }
@@ -333,6 +335,12 @@ int blk_validate_limits(struct queue_limits *lim)
 	if (!lim->max_segments)
 		lim->max_segments = BLK_MAX_SEGMENTS;
 
+	if (lim->max_hw_wzeroes_unmap_sectors &&
+	    lim->max_hw_wzeroes_unmap_sectors != lim->max_write_zeroes_sectors)
+		return -EINVAL;
+	lim->max_wzeroes_unmap_sectors = min(lim->max_hw_wzeroes_unmap_sectors,
+			lim->max_user_wzeroes_unmap_sectors);
+
 	lim->max_discard_sectors =
 		min(lim->max_hw_discard_sectors, lim->max_user_discard_sectors);
 
@@ -418,10 +426,11 @@ int blk_set_default_limits(struct queue_limits *lim)
 {
 	/*
 	 * Most defaults are set by capping the bounds in blk_validate_limits,
-	 * but max_user_discard_sectors is special and needs an explicit
-	 * initialization to the max value here.
+	 * but these limits are special and need an explicit initialization to
+	 * the max value here.
 	 */
 	lim->max_user_discard_sectors = UINT_MAX;
+	lim->max_user_wzeroes_unmap_sectors = UINT_MAX;
 	return blk_validate_limits(lim);
 }
 
@@ -708,6 +717,13 @@ int blk_stack_limits(struct queue_limits *t, struct queue_limits *b,
 	t->max_dev_sectors = min_not_zero(t->max_dev_sectors, b->max_dev_sectors);
 	t->max_write_zeroes_sectors = min(t->max_write_zeroes_sectors,
 					b->max_write_zeroes_sectors);
+	t->max_user_wzeroes_unmap_sectors =
+			min(t->max_user_wzeroes_unmap_sectors,
+			    b->max_user_wzeroes_unmap_sectors);
+	t->max_hw_wzeroes_unmap_sectors =
+			min(t->max_hw_wzeroes_unmap_sectors,
+			    b->max_hw_wzeroes_unmap_sectors);
+
 	t->max_hw_zone_append_sectors = min(t->max_hw_zone_append_sectors,
 					b->max_hw_zone_append_sectors);
 
diff --git a/block/blk-sysfs.c b/block/blk-sysfs.c
index b2b9b89d6967..48c7ecbb531f 100644
--- a/block/blk-sysfs.c
+++ b/block/blk-sysfs.c
@@ -161,6 +161,8 @@ static ssize_t queue_##_field##_show(struct gendisk *disk, char *page)	\
 QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_discard_sectors)
 QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_hw_discard_sectors)
 QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_write_zeroes_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_hw_wzeroes_unmap_sectors)
+QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_wzeroes_unmap_sectors)
 QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_max_sectors)
 QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(atomic_write_boundary_sectors)
 QUEUE_SYSFS_LIMIT_SHOW_SECTORS_TO_BYTES(max_zone_append_sectors)
@@ -205,6 +207,24 @@ static int queue_max_discard_sectors_store(struct gendisk *disk,
 	return 0;
 }
 
+static int queue_max_wzeroes_unmap_sectors_store(struct gendisk *disk,
+		const char *page, size_t count, struct queue_limits *lim)
+{
+	unsigned long max_zeroes_bytes, max_hw_zeroes_bytes;
+	ssize_t ret;
+
+	ret = queue_var_store(&max_zeroes_bytes, page, count);
+	if (ret < 0)
+		return ret;
+
+	max_hw_zeroes_bytes = lim->max_hw_wzeroes_unmap_sectors << SECTOR_SHIFT;
+	if (max_zeroes_bytes != 0 && max_zeroes_bytes != max_hw_zeroes_bytes)
+		return -EINVAL;
+
+	lim->max_user_wzeroes_unmap_sectors = max_zeroes_bytes >> SECTOR_SHIFT;
+	return 0;
+}
+
 static int
 queue_max_sectors_store(struct gendisk *disk, const char *page, size_t count,
 		struct queue_limits *lim)
@@ -514,6 +534,10 @@ QUEUE_LIM_RO_ENTRY(queue_atomic_write_unit_min, "atomic_write_unit_min_bytes");
 
 QUEUE_RO_ENTRY(queue_write_same_max, "write_same_max_bytes");
 QUEUE_LIM_RO_ENTRY(queue_max_write_zeroes_sectors, "write_zeroes_max_bytes");
+QUEUE_LIM_RO_ENTRY(queue_max_hw_wzeroes_unmap_sectors,
+		"write_zeroes_unmap_max_hw_bytes");
+QUEUE_LIM_RW_ENTRY(queue_max_wzeroes_unmap_sectors,
+		"write_zeroes_unmap_max_bytes");
 QUEUE_LIM_RO_ENTRY(queue_max_zone_append_sectors, "zone_append_max_bytes");
 QUEUE_LIM_RO_ENTRY(queue_zone_write_granularity, "zone_write_granularity");
 
@@ -662,6 +686,8 @@ static struct attribute *queue_attrs[] = {
 	&queue_atomic_write_unit_min_entry.attr,
 	&queue_atomic_write_unit_max_entry.attr,
 	&queue_max_write_zeroes_sectors_entry.attr,
+	&queue_max_hw_wzeroes_unmap_sectors_entry.attr,
+	&queue_max_wzeroes_unmap_sectors_entry.attr,
 	&queue_max_zone_append_sectors_entry.attr,
 	&queue_zone_write_granularity_entry.attr,
 	&queue_rotational_entry.attr,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a59880c809c7..1a5725c1f93d 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -383,6 +383,9 @@ struct queue_limits {
 	unsigned int		max_user_discard_sectors;
 	unsigned int		max_secure_erase_sectors;
 	unsigned int		max_write_zeroes_sectors;
+	unsigned int		max_wzeroes_unmap_sectors;
+	unsigned int		max_hw_wzeroes_unmap_sectors;
+	unsigned int		max_user_wzeroes_unmap_sectors;
 	unsigned int		max_hw_zone_append_sectors;
 	unsigned int		max_zone_append_sectors;
 	unsigned int		discard_granularity;
@@ -1042,6 +1045,7 @@ static inline void blk_queue_disable_secure_erase(struct request_queue *q)
 static inline void blk_queue_disable_write_zeroes(struct request_queue *q)
 {
 	q->limits.max_write_zeroes_sectors = 0;
+	q->limits.max_wzeroes_unmap_sectors = 0;
 }
 
 /*
@@ -1378,6 +1382,12 @@ static inline unsigned int bdev_write_zeroes_sectors(struct block_device *bdev)
 	return bdev_limits(bdev)->max_write_zeroes_sectors;
 }
 
+static inline unsigned int
+bdev_write_zeroes_unmap_sectors(struct block_device *bdev)
+{
+	return bdev_limits(bdev)->max_wzeroes_unmap_sectors;
+}
+
 static inline bool bdev_nonrot(struct block_device *bdev)
 {
 	return blk_queue_nonrot(bdev_get_queue(bdev));
-- 
cgit v1.2.3


From 7bd43cc79cab3850f34da0a31d5b042b701590ef Mon Sep 17 00:00:00 2001
From: Zhang Yi <yi.zhang@huawei.com>
Date: Thu, 19 Jun 2025 19:18:03 +0800
Subject: fs: introduce FALLOC_FL_WRITE_ZEROES to fallocate

With the development of flash-based storage devices, we can quickly
write zeros to SSDs using the WRITE_ZERO command if the devices do not
actually write physical zeroes to the media. Therefore, we can use this
command to quickly preallocate a real all-zero file with written
extents. This approach should be beneficial for subsequent pure
overwriting within this file, as it can save on block allocation and,
consequently, significant metadata changes, which should greatly improve
overwrite performance on certain filesystems.

Therefore, introduce a new operation FALLOC_FL_WRITE_ZEROES to
fallocate. This flag is used to convert a specified range of a file to
zeros by issuing a zeroing operation. Blocks should be allocated for the
regions that span holes in the file, and the entire range is converted
to written extents. If the underlying device supports the actual offload
write zeroes command, the process of zeroing out operation can be
accelerated. If it does not, we currently don't prevent the file system
from writing actual zeros to the device. This provides users with a new
method to quickly generate a zeroed file, users no longer need to write
zero data to create a file with written extents.

Users can determine whether a disk supports the unmap write zeroes
feature through querying this sysfs interface:

    /sys/block/<disk>/queue/write_zeroes_unmap_max_hw_bytes

Users can also enable or disable the unmap write zeroes operation
through this sysfs interface:

    /sys/block/<disk>/queue/write_zeroes_unmap_max_bytes

Finally, this flag cannot be specified in conjunction with the
FALLOC_FL_KEEP_SIZE since allocating written extents beyond file EOF is
not permitted. In addition, filesystems that always require out-of-place
writes should not support this flag since they still need to allocated
new blocks during subsequent overwrites.

Signed-off-by: Zhang Yi <yi.zhang@huawei.com>
Link: https://lore.kernel.org/20250619111806.3546162-7-yi.zhang@huaweicloud.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: "Martin K. Petersen" <martin.petersen@oracle.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/open.c                   |  1 +
 include/linux/falloc.h      |  3 ++-
 include/uapi/linux/falloc.h | 17 +++++++++++++++++
 3 files changed, 20 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/open.c b/fs/open.c
index 7828234a7caa..b777e11e5522 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -281,6 +281,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 		break;
 	case FALLOC_FL_COLLAPSE_RANGE:
 	case FALLOC_FL_INSERT_RANGE:
+	case FALLOC_FL_WRITE_ZEROES:
 		if (mode & FALLOC_FL_KEEP_SIZE)
 			return -EOPNOTSUPP;
 		break;
diff --git a/include/linux/falloc.h b/include/linux/falloc.h
index 3f49f3df6af5..7c38c6b76b60 100644
--- a/include/linux/falloc.h
+++ b/include/linux/falloc.h
@@ -36,7 +36,8 @@ struct space_resv {
 				 FALLOC_FL_COLLAPSE_RANGE |	\
 				 FALLOC_FL_ZERO_RANGE |		\
 				 FALLOC_FL_INSERT_RANGE |	\
-				 FALLOC_FL_UNSHARE_RANGE)
+				 FALLOC_FL_UNSHARE_RANGE |	\
+				 FALLOC_FL_WRITE_ZEROES)
 
 /* on ia32 l_start is on a 32-bit boundary */
 #if defined(CONFIG_X86_64)
diff --git a/include/uapi/linux/falloc.h b/include/uapi/linux/falloc.h
index 5810371ed72b..1f9ca757d02d 100644
--- a/include/uapi/linux/falloc.h
+++ b/include/uapi/linux/falloc.h
@@ -78,4 +78,21 @@
  */
 #define FALLOC_FL_UNSHARE_RANGE		0x40
 
+/*
+ * FALLOC_FL_WRITE_ZEROES zeroes a specified file range in such a way that
+ * subsequent writes to that range do not require further changes to the file
+ * mapping metadata. This flag is beneficial for subsequent pure overwriting
+ * within this range, as it can save on block allocation and, consequently,
+ * significant metadata changes. Therefore, filesystems that always require
+ * out-of-place writes should not support this flag.
+ *
+ * Different filesystems may implement different limitations on the
+ * granularity of the zeroing operation. Most will preferably be accelerated
+ * by submitting write zeroes command if the backing storage supports, which
+ * may not physically write zeros to the media.
+ *
+ * This flag cannot be specified in conjunction with the FALLOC_FL_KEEP_SIZE.
+ */
+#define FALLOC_FL_WRITE_ZEROES		0x80
+
 #endif /* _UAPI_FALLOC_H_ */
-- 
cgit v1.2.3


From a24cc6ce1933eade12aa2b9859de0fcd2dac2c06 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 23 Jun 2025 10:34:08 +0200
Subject: futex: Initialize futex_phash_new during fork().

During a hash resize operation the new private hash is stored in
mm_struct::futex_phash_new if the current hash can not be immediately
replaced.

The new hash must not be copied during fork() into the new task. Doing
so will lead to a double-free of the memory by the two tasks.

Initialize the mm_struct::futex_phash_new during fork().

Closes: https://lore.kernel.org/all/aFBQ8CBKmRzEqIfS@mozart.vkv.me/
Fixes: bd54df5ea7cad ("futex: Allow to resize the private local hash")
Reported-by: Calvin Owens <calvin@wbinvd.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: Calvin Owens <calvin@wbinvd.org>
Link: https://lkml.kernel.org/r/20250623083408.jTiJiC6_@linutronix.de
---
 include/linux/futex.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/futex.h b/include/linux/futex.h
index 005b040c4791..b37193653e6b 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -89,6 +89,7 @@ void futex_hash_free(struct mm_struct *mm);
 static inline void futex_mm_init(struct mm_struct *mm)
 {
 	RCU_INIT_POINTER(mm->futex_phash, NULL);
+	mm->futex_phash_new = NULL;
 	mutex_init(&mm->futex_hash_lock);
 }
 
-- 
cgit v1.2.3


From 4d811e395bbe54ba2febb3940d4b6c4741f360a6 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 5 Jun 2025 11:48:33 -0600
Subject: io_uring: add IO_URING_F_INLINE issue flag

Set when the execution of the request is done inline from the system
call itself. Any deferred issue will never have this flag set.

Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |  2 ++
 io_uring/io_uring.c            | 12 +++++++-----
 2 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 2922635986f5..054c43c02c96 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -26,6 +26,8 @@ enum io_uring_cmd_flags {
 	IO_URING_F_MULTISHOT		= 4,
 	/* executed by io-wq */
 	IO_URING_F_IOWQ			= 8,
+	/* executed inline from syscall */
+	IO_URING_F_INLINE		= 16,
 	/* int's last bit, sign checks are usually faster than a bit test */
 	IO_URING_F_NONBLOCK		= INT_MIN,
 
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index 5111ec040c53..c60d1c286c87 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -147,7 +147,7 @@ static bool io_uring_try_cancel_requests(struct io_ring_ctx *ctx,
 					 bool cancel_all,
 					 bool is_sqpoll_thread);
 
-static void io_queue_sqe(struct io_kiocb *req);
+static void io_queue_sqe(struct io_kiocb *req, unsigned int extra_flags);
 static void __io_req_caches_free(struct io_ring_ctx *ctx);
 
 static __read_mostly DEFINE_STATIC_KEY_FALSE(io_key_has_sqarray);
@@ -1377,7 +1377,7 @@ void io_req_task_submit(struct io_kiocb *req, io_tw_token_t tw)
 	else if (req->flags & REQ_F_FORCE_ASYNC)
 		io_queue_iowq(req);
 	else
-		io_queue_sqe(req);
+		io_queue_sqe(req, 0);
 }
 
 void io_req_task_queue_fail(struct io_kiocb *req, int ret)
@@ -1960,12 +1960,14 @@ static void io_queue_async(struct io_kiocb *req, int ret)
 	}
 }
 
-static inline void io_queue_sqe(struct io_kiocb *req)
+static inline void io_queue_sqe(struct io_kiocb *req, unsigned int extra_flags)
 	__must_hold(&req->ctx->uring_lock)
 {
+	unsigned int issue_flags = IO_URING_F_NONBLOCK |
+				   IO_URING_F_COMPLETE_DEFER | extra_flags;
 	int ret;
 
-	ret = io_issue_sqe(req, IO_URING_F_NONBLOCK|IO_URING_F_COMPLETE_DEFER);
+	ret = io_issue_sqe(req, issue_flags);
 
 	/*
 	 * We async punt it if the file wasn't marked NOWAIT, or if the file
@@ -2221,7 +2223,7 @@ fallback:
 		return 0;
 	}
 
-	io_queue_sqe(req);
+	io_queue_sqe(req, IO_URING_F_INLINE);
 	return 0;
 }
 
-- 
cgit v1.2.3


From af19388a973877b2349df46c4487a789cd3148ed Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Thu, 5 Jun 2025 11:33:52 -0600
Subject: io_uring: add struct io_cold_def->sqe_copy() method

Will be called by the core of io_uring, if inline issue is not going
to be tried for a request. Opcodes can define this handler to defer
copying of SQE data that should remain stable.

Only called if IO_URING_F_INLINE is set. If it isn't set, then there's a
bug in the core handling of this, and -EFAULT will be returned instead
to terminate the request. This will trigger a WARN_ON_ONCE(). Don't
expect this to ever trigger, and down the line this can be removed.

Reviewed-by: Caleb Sander Mateos <csander@purestorage.com>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h |  3 +++
 io_uring/io_uring.c            | 27 +++++++++++++++++++++++++--
 io_uring/opdef.h               |  1 +
 3 files changed, 29 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 054c43c02c96..4ab3bdc103f2 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -504,6 +504,7 @@ enum {
 	REQ_F_BUF_NODE_BIT,
 	REQ_F_HAS_METADATA_BIT,
 	REQ_F_IMPORT_BUFFER_BIT,
+	REQ_F_SQE_COPIED_BIT,
 
 	/* not a real bit, just to check we're not overflowing the space */
 	__REQ_F_LAST_BIT,
@@ -593,6 +594,8 @@ enum {
 	 * For SEND_ZC, whether to import buffers (i.e. the first issue).
 	 */
 	REQ_F_IMPORT_BUFFER	= IO_REQ_FLAG(REQ_F_IMPORT_BUFFER_BIT),
+	/* ->sqe_copy() has been called, if necessary */
+	REQ_F_SQE_COPIED	= IO_REQ_FLAG(REQ_F_SQE_COPIED_BIT),
 };
 
 typedef void (*io_req_tw_func_t)(struct io_kiocb *req, io_tw_token_t tw);
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index c60d1c286c87..3a23c8713f1b 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -1938,14 +1938,34 @@ struct file *io_file_get_normal(struct io_kiocb *req, int fd)
 	return file;
 }
 
-static void io_queue_async(struct io_kiocb *req, int ret)
+static int io_req_sqe_copy(struct io_kiocb *req, unsigned int issue_flags)
+{
+	const struct io_cold_def *def = &io_cold_defs[req->opcode];
+
+	if (req->flags & REQ_F_SQE_COPIED)
+		return 0;
+	req->flags |= REQ_F_SQE_COPIED;
+	if (!def->sqe_copy)
+		return 0;
+	if (WARN_ON_ONCE(!(issue_flags & IO_URING_F_INLINE)))
+		return -EFAULT;
+	def->sqe_copy(req);
+	return 0;
+}
+
+static void io_queue_async(struct io_kiocb *req, unsigned int issue_flags, int ret)
 	__must_hold(&req->ctx->uring_lock)
 {
 	if (ret != -EAGAIN || (req->flags & REQ_F_NOWAIT)) {
+fail:
 		io_req_defer_failed(req, ret);
 		return;
 	}
 
+	ret = io_req_sqe_copy(req, issue_flags);
+	if (unlikely(ret))
+		goto fail;
+
 	switch (io_arm_poll_handler(req, 0)) {
 	case IO_APOLL_READY:
 		io_kbuf_recycle(req, 0);
@@ -1974,7 +1994,7 @@ static inline void io_queue_sqe(struct io_kiocb *req, unsigned int extra_flags)
 	 * doesn't support non-blocking read/write attempts
 	 */
 	if (unlikely(ret))
-		io_queue_async(req, ret);
+		io_queue_async(req, issue_flags, ret);
 }
 
 static void io_queue_sqe_fallback(struct io_kiocb *req)
@@ -1989,6 +2009,8 @@ static void io_queue_sqe_fallback(struct io_kiocb *req)
 		req->flags |= REQ_F_LINK;
 		io_req_defer_failed(req, req->cqe.res);
 	} else {
+		/* can't fail with IO_URING_F_INLINE */
+		io_req_sqe_copy(req, IO_URING_F_INLINE);
 		if (unlikely(req->ctx->drain_active))
 			io_drain_req(req);
 		else
@@ -2200,6 +2222,7 @@ static inline int io_submit_sqe(struct io_ring_ctx *ctx, struct io_kiocb *req,
 	 */
 	if (unlikely(link->head)) {
 		trace_io_uring_link(req, link->last);
+		io_req_sqe_copy(req, IO_URING_F_INLINE);
 		link->last->link = req;
 		link->last = req;
 
diff --git a/io_uring/opdef.h b/io_uring/opdef.h
index 719a52104abe..c2f0907ed78c 100644
--- a/io_uring/opdef.h
+++ b/io_uring/opdef.h
@@ -38,6 +38,7 @@ struct io_issue_def {
 struct io_cold_def {
 	const char		*name;
 
+	void (*sqe_copy)(struct io_kiocb *);
 	void (*cleanup)(struct io_kiocb *);
 	void (*fail)(struct io_kiocb *);
 };
-- 
cgit v1.2.3


From c4cdbaf9d81c8387da8b9b91567d4b0eb1b8a549 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:24 -0700
Subject: iommu/amd: KVM: SVM: Use pi_desc_addr to derive ga_root_ptr

Use vcpu_data.pi_desc_addr instead of amd_iommu_pi_data.base to get the
GA root pointer.  KVM is the only source of amd_iommu_pi_data.base, and
KVM's one and only path for writing amd_iommu_pi_data.base computes the
exact same value for vcpu_data.pi_desc_addr and amd_iommu_pi_data.base,
and fills amd_iommu_pi_data.base if and only if vcpu_data.pi_desc_addr is
valid, i.e. amd_iommu_pi_data.base is fully redundant.

Cc: Maxim Levitsky <mlevitsk@redhat.com>
Reviewed-by: Joao Martins <joao.m.martins@oracle.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Tested-by: Sairaj Kodilkar <sarunkod@amd.com>
Link: https://lore.kernel.org/r/20250611224604.313496-23-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/avic.c   | 7 +++++--
 drivers/iommu/amd/iommu.c | 2 +-
 include/linux/amd-iommu.h | 2 --
 3 files changed, 6 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 375a29022000..d95742faae11 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -894,8 +894,11 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 
 			enable_remapped_mode = false;
 
-			/* Try to enable guest_mode in IRTE */
-			pi.base = avic_get_backing_page_address(svm);
+			/*
+			 * Try to enable guest_mode in IRTE.  Note, the address
+			 * of the vCPU's AVIC backing page is passed to the
+			 * IOMMU via vcpu_info->pi_desc_addr.
+			 */
 			pi.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
 						     svm->vcpu.vcpu_id);
 			pi.is_guest_mode = true;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index ed96050d4933..bdfb57af7111 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3888,7 +3888,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	pi_data->ir_data = ir_data;
 
 	if (pi_data->is_guest_mode) {
-		ir_data->ga_root_ptr = (pi_data->base >> 12);
+		ir_data->ga_root_ptr = (vcpu_pi_info->pi_desc_addr >> 12);
 		ir_data->ga_vector = vcpu_pi_info->vector;
 		ir_data->ga_tag = pi_data->ga_tag;
 		ret = amd_iommu_activate_guest_mode(ir_data);
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 1f9b13d803c5..deeefc92a5cf 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -19,8 +19,6 @@ struct amd_iommu;
  */
 struct amd_iommu_pi_data {
 	u32 ga_tag;
-	u64 base;
-
 	bool is_guest_mode;
 	struct vcpu_data *vcpu_data;
 	void *ir_data;
-- 
cgit v1.2.3


From 53527ea1b70224d16d29edbd5c850456469f00ec Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:34 -0700
Subject: iommu: KVM: Split "struct vcpu_data" into separate AMD vs. Intel
 structs

Split the vcpu_data structure that serves as a handoff from KVM to IOMMU
drivers into vendor specific structures.  Overloading a single structure
makes the code hard to read and maintain, is *very* misleading as it
suggests that mixing vendors is actually supported, and bastardizing
Intel's posted interrupt descriptor address when AMD's IOMMU already has
its own structure is quite unnecessary.

Tested-by: Sairaj Kodilkar <sarunkod@amd.com>
Link: https://lore.kernel.org/r/20250611224604.313496-33-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/irq_remapping.h | 15 ++++++++++++++-
 arch/x86/kvm/svm/avic.c              | 21 ++++++++-------------
 arch/x86/kvm/vmx/posted_intr.c       |  4 ++--
 drivers/iommu/amd/iommu.c            | 12 ++++--------
 drivers/iommu/intel/irq_remapping.c  | 10 +++++-----
 include/linux/amd-iommu.h            | 12 ------------
 6 files changed, 33 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 5036f13ab69f..2dbc9cb61c2f 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -26,7 +26,20 @@ enum {
 	IRQ_REMAP_X2APIC_MODE,
 };
 
-struct vcpu_data {
+/*
+ * This is mainly used to communicate information back-and-forth
+ * between SVM and IOMMU for setting up and tearing down posted
+ * interrupt
+ */
+struct amd_iommu_pi_data {
+	u64 vapic_addr;		/* Physical address of the vCPU's vAPIC. */
+	u32 ga_tag;
+	u32 vector;		/* Guest vector of the interrupt */
+	bool is_guest_mode;
+	void *ir_data;
+};
+
+struct intel_iommu_pi_data {
 	u64 pi_desc_addr;	/* Physical address of PI Descriptor */
 	u32 vector;		/* Guest vector of the interrupt */
 };
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index eed5c58ac07f..dc1526fef18d 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -823,23 +823,18 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 	 */
 	if (vcpu && kvm_vcpu_apicv_active(vcpu)) {
 		/*
-		 * Try to enable guest_mode in IRTE.  Note, the address
-		 * of the vCPU's AVIC backing page is passed to the
-		 * IOMMU via vcpu_info->pi_desc_addr.
+		 * Try to enable guest_mode in IRTE.
 		 */
-		struct vcpu_data vcpu_info = {
-			.pi_desc_addr = avic_get_backing_page_address(to_svm(vcpu)),
-			.vector = vector,
-		};
-
-		struct amd_iommu_pi_data pi = {
-			.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id, vcpu->vcpu_id),
+		struct amd_iommu_pi_data pi_data = {
+			.ga_tag = AVIC_GATAG(to_kvm_svm(kvm)->avic_vm_id,
+					     vcpu->vcpu_id),
 			.is_guest_mode = true,
-			.vcpu_data = &vcpu_info,
+			.vapic_addr = avic_get_backing_page_address(to_svm(vcpu)),
+			.vector = vector,
 		};
 		int ret;
 
-		ret = irq_set_vcpu_affinity(host_irq, &pi);
+		ret = irq_set_vcpu_affinity(host_irq, &pi_data);
 		if (ret)
 			return ret;
 
@@ -850,7 +845,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		 * we can reference to them directly when we update vcpu
 		 * scheduling information in IOMMU irte.
 		 */
-		return svm_ir_list_add(to_svm(vcpu), irqfd, &pi);
+		return svm_ir_list_add(to_svm(vcpu), irqfd, &pi_data);
 	}
 	return irq_set_vcpu_affinity(host_irq, NULL);
 }
diff --git a/arch/x86/kvm/vmx/posted_intr.c b/arch/x86/kvm/vmx/posted_intr.c
index 687ffde3b61c..3a23c30f73cb 100644
--- a/arch/x86/kvm/vmx/posted_intr.c
+++ b/arch/x86/kvm/vmx/posted_intr.c
@@ -303,12 +303,12 @@ int vmx_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		       struct kvm_vcpu *vcpu, u32 vector)
 {
 	if (vcpu) {
-		struct vcpu_data vcpu_info = {
+		struct intel_iommu_pi_data pi_data = {
 			.pi_desc_addr = __pa(vcpu_to_pi_desc(vcpu)),
 			.vector = vector,
 		};
 
-		return irq_set_vcpu_affinity(host_irq, &vcpu_info);
+		return irq_set_vcpu_affinity(host_irq, &pi_data);
 	} else {
 		return irq_set_vcpu_affinity(host_irq, NULL);
 	}
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index e8e259c07265..8366d32252cd 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3860,10 +3860,10 @@ int amd_iommu_deactivate_guest_mode(void *data)
 }
 EXPORT_SYMBOL(amd_iommu_deactivate_guest_mode);
 
-static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
+static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 {
 	int ret;
-	struct amd_iommu_pi_data *pi_data = vcpu_info;
+	struct amd_iommu_pi_data *pi_data = info;
 	struct amd_ir_data *ir_data = data->chip_data;
 	struct irq_2_irte *irte_info = &ir_data->irq_2_irte;
 	struct iommu_dev_data *dev_data;
@@ -3886,14 +3886,10 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *vcpu_info)
 	ir_data->cfg = irqd_cfg(data);
 
 	if (pi_data) {
-		struct vcpu_data *vcpu_pi_info = pi_data->vcpu_data;
-
 		pi_data->ir_data = ir_data;
 
-		WARN_ON_ONCE(!pi_data->is_guest_mode);
-
-		ir_data->ga_root_ptr = (vcpu_pi_info->pi_desc_addr >> 12);
-		ir_data->ga_vector = vcpu_pi_info->vector;
+		ir_data->ga_root_ptr = (pi_data->vapic_addr >> 12);
+		ir_data->ga_vector = pi_data->vector;
 		ir_data->ga_tag = pi_data->ga_tag;
 		ret = amd_iommu_activate_guest_mode(ir_data);
 	} else {
diff --git a/drivers/iommu/intel/irq_remapping.c b/drivers/iommu/intel/irq_remapping.c
index cf7b6882ec75..2fc451253dc3 100644
--- a/drivers/iommu/intel/irq_remapping.c
+++ b/drivers/iommu/intel/irq_remapping.c
@@ -1244,10 +1244,10 @@ static void intel_ir_compose_msi_msg(struct irq_data *irq_data,
 static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 {
 	struct intel_ir_data *ir_data = data->chip_data;
-	struct vcpu_data *vcpu_pi_info = info;
+	struct intel_iommu_pi_data *pi_data = info;
 
 	/* stop posting interrupts, back to the default mode */
-	if (!vcpu_pi_info) {
+	if (!pi_data) {
 		__intel_ir_reconfigure_irte(data, true);
 	} else {
 		struct irte irte_pi;
@@ -1265,10 +1265,10 @@ static int intel_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 		/* Update the posted mode fields */
 		irte_pi.p_pst = 1;
 		irte_pi.p_urgent = 0;
-		irte_pi.p_vector = vcpu_pi_info->vector;
-		irte_pi.pda_l = (vcpu_pi_info->pi_desc_addr >>
+		irte_pi.p_vector = pi_data->vector;
+		irte_pi.pda_l = (pi_data->pi_desc_addr >>
 				(32 - PDA_LOW_BIT)) & ~(-1UL << PDA_LOW_BIT);
-		irte_pi.pda_h = (vcpu_pi_info->pi_desc_addr >> 32) &
+		irte_pi.pda_h = (pi_data->pi_desc_addr >> 32) &
 				~(-1UL << PDA_HIGH_BIT);
 
 		ir_data->irq_2_iommu.posted_vcpu = true;
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index deeefc92a5cf..99b4fa9a0296 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -12,18 +12,6 @@
 
 struct amd_iommu;
 
-/*
- * This is mainly used to communicate information back-and-forth
- * between SVM and IOMMU for setting up and tearing down posted
- * interrupt
- */
-struct amd_iommu_pi_data {
-	u32 ga_tag;
-	bool is_guest_mode;
-	struct vcpu_data *vcpu_data;
-	void *ir_data;
-};
-
 #ifdef CONFIG_AMD_IOMMU
 
 struct task_struct;
-- 
cgit v1.2.3


From b33252b9d17238a4a9fa5a29af6e6a2922a6c2b0 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:35 -0700
Subject: KVM: Don't WARN if updating IRQ bypass route fails

Don't bother WARNing if updating an IRTE route fails now that vendor code
provides much more precise WARNs.  The generic WARN doesn't provide enough
information to actually debug the problem, and has obviously done nothing
to surface the myriad bugs in KVM x86's implementation.

Drop all of the associated return code plumbing that existed just so that
common KVM could WARN.

Link: https://lore.kernel.org/r/20250611224604.313496-34-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/arm.c          |  6 +++---
 arch/arm64/kvm/vgic/vgic-v4.c |  8 +++-----
 arch/x86/kvm/irq.c            |  8 ++++----
 include/kvm/arm_vgic.h        |  2 +-
 include/linux/kvm_host.h      |  6 +++---
 virt/kvm/eventfd.c            | 15 ++++++---------
 6 files changed, 20 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index a9a39e0375f7..94fb2f096a20 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2771,9 +2771,9 @@ bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
 	return memcmp(&old->msi, &new->msi, sizeof(new->msi));
 }
 
-int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
-				  struct kvm_kernel_irq_routing_entry *old,
-				  struct kvm_kernel_irq_routing_entry *new)
+void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+				   struct kvm_kernel_irq_routing_entry *old,
+				   struct kvm_kernel_irq_routing_entry *new)
 {
 	/*
 	 * Remapping the vLPI requires taking the its_lock mutex to resolve
diff --git a/arch/arm64/kvm/vgic/vgic-v4.c b/arch/arm64/kvm/vgic/vgic-v4.c
index 911170d4a9c8..ef3481963122 100644
--- a/arch/arm64/kvm/vgic/vgic-v4.c
+++ b/arch/arm64/kvm/vgic/vgic-v4.c
@@ -527,18 +527,17 @@ static struct vgic_irq *__vgic_host_irq_get_vlpi(struct kvm *kvm, int host_irq)
 	return NULL;
 }
 
-int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq)
+void kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq)
 {
 	struct vgic_irq *irq;
 	unsigned long flags;
-	int ret = 0;
 
 	if (!vgic_supports_direct_msis(kvm))
-		return 0;
+		return;
 
 	irq = __vgic_host_irq_get_vlpi(kvm, host_irq);
 	if (!irq)
-		return 0;
+		return;
 
 	raw_spin_lock_irqsave(&irq->irq_lock, flags);
 	WARN_ON(irq->hw && irq->host_irq != host_irq);
@@ -550,5 +549,4 @@ int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq)
 
 	raw_spin_unlock_irqrestore(&irq->irq_lock, flags);
 	vgic_put_irq(kvm, irq);
-	return 0;
 }
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index cd9b56c6a5c3..b7b0fbc218b8 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -606,11 +606,11 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	kvm_arch_end_assignment(irqfd->kvm);
 }
 
-int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
-				  struct kvm_kernel_irq_routing_entry *old,
-				  struct kvm_kernel_irq_routing_entry *new)
+void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+				   struct kvm_kernel_irq_routing_entry *old,
+				   struct kvm_kernel_irq_routing_entry *new)
 {
-	return kvm_pi_update_irte(irqfd, new);
+	kvm_pi_update_irte(irqfd, new);
 }
 
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h
index 4a34f7f0a864..b2a04481de1a 100644
--- a/include/kvm/arm_vgic.h
+++ b/include/kvm/arm_vgic.h
@@ -434,7 +434,7 @@ struct kvm_kernel_irq_routing_entry;
 int kvm_vgic_v4_set_forwarding(struct kvm *kvm, int irq,
 			       struct kvm_kernel_irq_routing_entry *irq_entry);
 
-int kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq);
+void kvm_vgic_v4_unset_forwarding(struct kvm *kvm, int host_irq);
 
 int vgic_v4_load(struct kvm_vcpu *vcpu);
 void vgic_v4_commit(struct kvm_vcpu *vcpu);
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index a4160c1c0c6b..8e74ac0f90b1 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2410,9 +2410,9 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *,
 			   struct irq_bypass_producer *);
 void kvm_arch_irq_bypass_stop(struct irq_bypass_consumer *);
 void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *);
-int kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
-				  struct kvm_kernel_irq_routing_entry *old,
-				  struct kvm_kernel_irq_routing_entry *new);
+void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+				   struct kvm_kernel_irq_routing_entry *old,
+				   struct kvm_kernel_irq_routing_entry *new);
 bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *,
 				  struct kvm_kernel_irq_routing_entry *);
 #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index bd1766da6895..719b242fc935 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -285,11 +285,11 @@ void __attribute__((weak)) kvm_arch_irq_bypass_start(
 {
 }
 
-int __weak kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
-					 struct kvm_kernel_irq_routing_entry *old,
-					 struct kvm_kernel_irq_routing_entry *new)
+void __weak kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
+					  struct kvm_kernel_irq_routing_entry *old,
+					  struct kvm_kernel_irq_routing_entry *new)
 {
-	return 0;
+
 }
 
 bool __attribute__((weak)) kvm_arch_irqfd_route_changed(
@@ -617,11 +617,8 @@ void kvm_irq_routing_update(struct kvm *kvm)
 
 #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
 		if (irqfd->producer &&
-		    kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry)) {
-			int ret = kvm_arch_update_irqfd_routing(irqfd, &old, &irqfd->irq_entry);
-
-			WARN_ON(ret);
-		}
+		    kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry))
+			kvm_arch_update_irqfd_routing(irqfd, &old, &irqfd->irq_entry);
 #endif
 	}
 
-- 
cgit v1.2.3


From 77bb184ab880171a1cedfbed9ab05977e6ae2258 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:36 -0700
Subject: KVM: Fold kvm_arch_irqfd_route_changed() into
 kvm_arch_update_irqfd_routing()

Fold kvm_arch_irqfd_route_changed() into kvm_arch_update_irqfd_routing().
Calling arch code to know whether or not to call arch code is absurd.

Reviewed-by: Oliver Upton <oliver.upton@linux.dev>
Link: https://lore.kernel.org/r/20250611224604.313496-35-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/arm64/kvm/arm.c     | 15 +++++----------
 arch/x86/kvm/irq.c       | 15 +++++----------
 include/linux/kvm_host.h |  2 --
 virt/kvm/eventfd.c       | 10 +---------
 4 files changed, 11 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/kvm/arm.c b/arch/arm64/kvm/arm.c
index 94fb2f096a20..04f2116927b1 100644
--- a/arch/arm64/kvm/arm.c
+++ b/arch/arm64/kvm/arm.c
@@ -2761,20 +2761,15 @@ void kvm_arch_irq_bypass_del_producer(struct irq_bypass_consumer *cons,
 	kvm_vgic_v4_unset_forwarding(irqfd->kvm, prod->irq);
 }
 
-bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
-				  struct kvm_kernel_irq_routing_entry *new)
-{
-	if (old->type != KVM_IRQ_ROUTING_MSI ||
-	    new->type != KVM_IRQ_ROUTING_MSI)
-		return true;
-
-	return memcmp(&old->msi, &new->msi, sizeof(new->msi));
-}
-
 void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
 				   struct kvm_kernel_irq_routing_entry *old,
 				   struct kvm_kernel_irq_routing_entry *new)
 {
+	if (old->type == KVM_IRQ_ROUTING_MSI &&
+	    new->type == KVM_IRQ_ROUTING_MSI &&
+	    !memcmp(&old->msi, &new->msi, sizeof(new->msi)))
+		return;
+
 	/*
 	 * Remapping the vLPI requires taking the its_lock mutex to resolve
 	 * the new translation. We're in spinlock land at this point, so no
diff --git a/arch/x86/kvm/irq.c b/arch/x86/kvm/irq.c
index b7b0fbc218b8..23e0acc07cb6 100644
--- a/arch/x86/kvm/irq.c
+++ b/arch/x86/kvm/irq.c
@@ -610,17 +610,12 @@ void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
 				   struct kvm_kernel_irq_routing_entry *old,
 				   struct kvm_kernel_irq_routing_entry *new)
 {
-	kvm_pi_update_irte(irqfd, new);
-}
-
-bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *old,
-				  struct kvm_kernel_irq_routing_entry *new)
-{
-	if (old->type != KVM_IRQ_ROUTING_MSI ||
-	    new->type != KVM_IRQ_ROUTING_MSI)
-		return true;
+	if (old->type == KVM_IRQ_ROUTING_MSI &&
+	    new->type == KVM_IRQ_ROUTING_MSI &&
+	    !memcmp(&old->msi, &new->msi, sizeof(new->msi)))
+		return;
 
-	return !!memcmp(&old->msi, &new->msi, sizeof(new->msi));
+	kvm_pi_update_irte(irqfd, new);
 }
 
 #ifdef CONFIG_KVM_IOAPIC
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index 8e74ac0f90b1..fb9ec06aa807 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -2413,8 +2413,6 @@ void kvm_arch_irq_bypass_start(struct irq_bypass_consumer *);
 void kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
 				   struct kvm_kernel_irq_routing_entry *old,
 				   struct kvm_kernel_irq_routing_entry *new);
-bool kvm_arch_irqfd_route_changed(struct kvm_kernel_irq_routing_entry *,
-				  struct kvm_kernel_irq_routing_entry *);
 #endif /* CONFIG_HAVE_KVM_IRQ_BYPASS */
 
 #ifdef CONFIG_HAVE_KVM_INVALID_WAKEUPS
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 719b242fc935..59b1e64697f1 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -291,13 +291,6 @@ void __weak kvm_arch_update_irqfd_routing(struct kvm_kernel_irqfd *irqfd,
 {
 
 }
-
-bool __attribute__((weak)) kvm_arch_irqfd_route_changed(
-				struct kvm_kernel_irq_routing_entry *old,
-				struct kvm_kernel_irq_routing_entry *new)
-{
-	return true;
-}
 #endif
 
 static int
@@ -616,8 +609,7 @@ void kvm_irq_routing_update(struct kvm *kvm)
 		irqfd_update(kvm, irqfd);
 
 #if IS_ENABLED(CONFIG_HAVE_KVM_IRQ_BYPASS)
-		if (irqfd->producer &&
-		    kvm_arch_irqfd_route_changed(&old, &irqfd->irq_entry))
+		if (irqfd->producer)
 			kvm_arch_update_irqfd_routing(irqfd, &old, &irqfd->irq_entry);
 #endif
 	}
-- 
cgit v1.2.3


From 08d9ccdd1a5c75d7aca7ac3af56f723d780dd6ac Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:43 -0700
Subject: iommu/amd: KVM: SVM: Infer IsRun from validity of pCPU destination

Infer whether or not a vCPU should be marked running from the validity of
the pCPU on which it is running.  amd_iommu_update_ga() already skips the
IRTE update if the pCPU is invalid, i.e. passing %true for is_run with an
invalid pCPU would be a blatant and egregrious KVM bug.

Tested-by: Sairaj Kodilkar <sarunkod@amd.com>
Link: https://lore.kernel.org/r/20250611224604.313496-42-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/kvm/svm/avic.c   | 11 +++++------
 drivers/iommu/amd/iommu.c | 14 +++++++++-----
 include/linux/amd-iommu.h |  6 ++----
 3 files changed, 16 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 42fd1868c32f..1960bb06c4b9 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -833,7 +833,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		entry = svm->avic_physical_id_entry;
 		if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
 			amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
-					    true, pi_data.ir_data);
+					    pi_data.ir_data);
 
 		irqfd->irq_bypass_data = pi_data.ir_data;
 		list_add(&irqfd->vcpu_list, &svm->ir_list);
@@ -842,8 +842,7 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 	return irq_set_vcpu_affinity(host_irq, NULL);
 }
 
-static inline int
-avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
+static inline int avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu)
 {
 	int ret = 0;
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -862,7 +861,7 @@ avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu, bool r)
 		return 0;
 
 	list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
-		ret = amd_iommu_update_ga(cpu, r, irqfd->irq_bypass_data);
+		ret = amd_iommu_update_ga(cpu, irqfd->irq_bypass_data);
 		if (ret)
 			return ret;
 	}
@@ -924,7 +923,7 @@ void avic_vcpu_load(struct kvm_vcpu *vcpu, int cpu)
 
 	WRITE_ONCE(kvm_svm->avic_physical_id_table[vcpu->vcpu_id], entry);
 
-	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id, true);
+	avic_update_iommu_vcpu_affinity(vcpu, h_physical_id);
 
 	spin_unlock_irqrestore(&svm->ir_list_lock, flags);
 }
@@ -964,7 +963,7 @@ void avic_vcpu_put(struct kvm_vcpu *vcpu)
 	 */
 	spin_lock_irqsave(&svm->ir_list_lock, flags);
 
-	avic_update_iommu_vcpu_affinity(vcpu, -1, 0);
+	avic_update_iommu_vcpu_affinity(vcpu, -1);
 
 	entry &= ~AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK;
 	svm->avic_physical_id_entry = entry;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 0a0d73483195..3c4c81eb201b 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3990,15 +3990,17 @@ int amd_iommu_create_irq_domain(struct amd_iommu *iommu)
  * Update the pCPU information for an IRTE that is configured to post IRQs to
  * a vCPU, without issuing an IOMMU invalidation for the IRTE.
  *
- * This API is intended to be used when a vCPU is scheduled in/out (or stops
- * running for any reason), to do a fast update of IsRun and (conditionally)
- * Destination.
+ * If the vCPU is associated with a pCPU (@cpu >= 0), configure the Destination
+ * with the pCPU's APIC ID and set IsRun, else clear IsRun.  I.e. treat vCPUs
+ * that are associated with a pCPU as running.  This API is intended to be used
+ * when a vCPU is scheduled in/out (or stops running for any reason), to do a
+ * fast update of IsRun and (conditionally) Destination.
  *
  * Per the IOMMU spec, the Destination, IsRun, and GATag fields are not cached
  * and thus don't require an invalidation to ensure the IOMMU consumes fresh
  * information.
  */
-int amd_iommu_update_ga(int cpu, bool is_run, void *data)
+int amd_iommu_update_ga(int cpu, void *data)
 {
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -4015,8 +4017,10 @@ int amd_iommu_update_ga(int cpu, bool is_run, void *data)
 					APICID_TO_IRTE_DEST_LO(cpu);
 		entry->hi.fields.destination =
 					APICID_TO_IRTE_DEST_HI(cpu);
+		entry->lo.fields_vapic.is_run = true;
+	} else {
+		entry->lo.fields_vapic.is_run = false;
 	}
-	entry->lo.fields_vapic.is_run = is_run;
 
 	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
 				ir_data->irq_2_irte.index, entry);
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index 99b4fa9a0296..fe0e16ffe0e5 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -30,8 +30,7 @@ static inline void amd_iommu_detect(void) { }
 /* IOMMU AVIC Function */
 extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32));
 
-extern int
-amd_iommu_update_ga(int cpu, bool is_run, void *data);
+extern int amd_iommu_update_ga(int cpu, void *data);
 
 extern int amd_iommu_activate_guest_mode(void *data);
 extern int amd_iommu_deactivate_guest_mode(void *data);
@@ -44,8 +43,7 @@ amd_iommu_register_ga_log_notifier(int (*notifier)(u32))
 	return 0;
 }
 
-static inline int
-amd_iommu_update_ga(int cpu, bool is_run, void *data)
+static inline int amd_iommu_update_ga(int cpu, void *data)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From f965255dc5033387ac7858787c6c792fd789ac34 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:45:45 -0700
Subject: iommu/amd: KVM: SVM: Set pCPU info in IRTE when setting vCPU affinity

Now that setting vCPU affinity is guarded with ir_list_lock, i.e. now that
avic_physical_id_entry can be safely accessed, set the pCPU info
straight-away when setting vCPU affinity.  Putting the IRTE into posted
mode, and then immediately updating the IRTE a second time if the target
vCPU is running is wasteful and confusing.

This also fixes a flaw where a posted IRQ that arrives between putting
the IRTE into guest_mode and setting the correct destination could cause
the IOMMU to ring the doorbell on the wrong pCPU.

Link: https://lore.kernel.org/r/20250611224604.313496-44-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/irq_remapping.h |  1 +
 arch/x86/kvm/svm/avic.c              | 26 ++++++++++++++------------
 drivers/iommu/amd/iommu.c            |  6 ++++--
 include/linux/amd-iommu.h            |  4 ++--
 4 files changed, 21 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 2dbc9cb61c2f..4c75a17632f6 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -35,6 +35,7 @@ struct amd_iommu_pi_data {
 	u64 vapic_addr;		/* Physical address of the vCPU's vAPIC. */
 	u32 ga_tag;
 	u32 vector;		/* Guest vector of the interrupt */
+	int cpu;
 	bool is_guest_mode;
 	void *ir_data;
 };
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 1960bb06c4b9..35c5fb831c28 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -727,6 +727,7 @@ void avic_apicv_post_state_restore(struct kvm_vcpu *vcpu)
 
 static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 {
+	int apic_id = kvm_cpu_get_apicid(vcpu->cpu);
 	int ret = 0;
 	unsigned long flags;
 	struct vcpu_svm *svm = to_svm(vcpu);
@@ -746,7 +747,7 @@ static int avic_set_pi_irte_mode(struct kvm_vcpu *vcpu, bool activate)
 
 	list_for_each_entry(irqfd, &svm->ir_list, vcpu_list) {
 		if (activate)
-			ret = amd_iommu_activate_guest_mode(irqfd->irq_bypass_data);
+			ret = amd_iommu_activate_guest_mode(irqfd->irq_bypass_data, apic_id);
 		else
 			ret = amd_iommu_deactivate_guest_mode(irqfd->irq_bypass_data);
 		if (ret)
@@ -810,6 +811,18 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		 */
 		guard(spinlock_irqsave)(&svm->ir_list_lock);
 
+		/*
+		 * Update the target pCPU for IOMMU doorbells if the vCPU is
+		 * running.  If the vCPU is NOT running, i.e. is blocking or
+		 * scheduled out, KVM will update the pCPU info when the vCPU
+		 * is awakened and/or scheduled in.  See also avic_vcpu_load().
+		 */
+		entry = svm->avic_physical_id_entry;
+		if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+			pi_data.cpu = entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
+		else
+			pi_data.cpu = -1;
+
 		ret = irq_set_vcpu_affinity(host_irq, &pi_data);
 		if (ret)
 			return ret;
@@ -824,17 +837,6 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 			return -EIO;
 		}
 
-		/*
-		 * Update the target pCPU for IOMMU doorbells if the vCPU is
-		 * running.  If the vCPU is NOT running, i.e. is blocking or
-		 * scheduled out, KVM will update the pCPU info when the vCPU
-		 * is awakened and/or scheduled in.  See also avic_vcpu_load().
-		 */
-		entry = svm->avic_physical_id_entry;
-		if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
-			amd_iommu_update_ga(entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK,
-					    pi_data.ir_data);
-
 		irqfd->irq_bypass_data = pi_data.ir_data;
 		list_add(&irqfd->vcpu_list, &svm->ir_list);
 		return 0;
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 2eaba64be68a..6352930ad011 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3850,7 +3850,7 @@ int amd_iommu_update_ga(int cpu, void *data)
 }
 EXPORT_SYMBOL(amd_iommu_update_ga);
 
-int amd_iommu_activate_guest_mode(void *data)
+int amd_iommu_activate_guest_mode(void *data, int cpu)
 {
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -3871,6 +3871,8 @@ int amd_iommu_activate_guest_mode(void *data)
 	entry->hi.fields.vector            = ir_data->ga_vector;
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
+	__amd_iommu_update_ga(entry, cpu);
+
 	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
 			      ir_data->irq_2_irte.index, entry);
 }
@@ -3937,7 +3939,7 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 		ir_data->ga_root_ptr = (pi_data->vapic_addr >> 12);
 		ir_data->ga_vector = pi_data->vector;
 		ir_data->ga_tag = pi_data->ga_tag;
-		ret = amd_iommu_activate_guest_mode(ir_data);
+		ret = amd_iommu_activate_guest_mode(ir_data, pi_data->cpu);
 	} else {
 		ret = amd_iommu_deactivate_guest_mode(ir_data);
 	}
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index fe0e16ffe0e5..c9f2df0c4596 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -32,7 +32,7 @@ extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32));
 
 extern int amd_iommu_update_ga(int cpu, void *data);
 
-extern int amd_iommu_activate_guest_mode(void *data);
+extern int amd_iommu_activate_guest_mode(void *data, int cpu);
 extern int amd_iommu_deactivate_guest_mode(void *data);
 
 #else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */
@@ -48,7 +48,7 @@ static inline int amd_iommu_update_ga(int cpu, void *data)
 	return 0;
 }
 
-static inline int amd_iommu_activate_guest_mode(void *data)
+static inline int amd_iommu_activate_guest_mode(void *data, int cpu)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From b9e53f9ff4a88f01b22524878c9a381a6c5f65ff Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Wed, 11 Jun 2025 15:46:03 -0700
Subject: iommu/amd: KVM: SVM: Allow KVM to control need for GA log interrupts

Add plumbing to the AMD IOMMU driver to allow KVM to control whether or
not an IRTE is configured to generate GA log interrupts.  KVM only needs a
notification if the target vCPU is blocking, so the vCPU can be awakened.
If a vCPU is preempted or exits to userspace, KVM clears is_run, but will
set the vCPU back to running when userspace does KVM_RUN and/or the vCPU
task is scheduled back in, i.e. KVM doesn't need a notification.

Unconditionally pass "true" in all KVM paths to isolate the IOMMU changes
from the KVM changes insofar as possible.

Opportunistically swap the ordering of parameters for amd_iommu_update_ga()
so that the match amd_iommu_activate_guest_mode().

Note, as of this writing, the AMD IOMMU manual doesn't list GALogIntr as
a non-cached field, but per AMD hardware architects, it's not cached and
can be safely updated without an invalidation.

Link: https://lore.kernel.org/all/b29b8c22-2fd4-4b5e-b755-9198874157c7@amd.com
Cc: Vasant Hegde <vasant.hegde@amd.com>
Cc: Joao Martins <joao.m.martins@oracle.com>
Link: https://lore.kernel.org/r/20250611224604.313496-62-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/irq_remapping.h |  1 +
 arch/x86/kvm/svm/avic.c              | 10 ++++++----
 drivers/iommu/amd/iommu.c            | 28 +++++++++++++++++-----------
 include/linux/amd-iommu.h            |  9 ++++-----
 4 files changed, 28 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/irq_remapping.h b/arch/x86/include/asm/irq_remapping.h
index 4c75a17632f6..5a0d42464d44 100644
--- a/arch/x86/include/asm/irq_remapping.h
+++ b/arch/x86/include/asm/irq_remapping.h
@@ -36,6 +36,7 @@ struct amd_iommu_pi_data {
 	u32 ga_tag;
 	u32 vector;		/* Guest vector of the interrupt */
 	int cpu;
+	bool ga_log_intr;
 	bool is_guest_mode;
 	void *ir_data;
 };
diff --git a/arch/x86/kvm/svm/avic.c b/arch/x86/kvm/svm/avic.c
index 5803f778999f..02f266901bfe 100644
--- a/arch/x86/kvm/svm/avic.c
+++ b/arch/x86/kvm/svm/avic.c
@@ -785,10 +785,12 @@ int avic_pi_update_irte(struct kvm_kernel_irqfd *irqfd, struct kvm *kvm,
 		 * is awakened and/or scheduled in.  See also avic_vcpu_load().
 		 */
 		entry = svm->avic_physical_id_entry;
-		if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK)
+		if (entry & AVIC_PHYSICAL_ID_ENTRY_IS_RUNNING_MASK) {
 			pi_data.cpu = entry & AVIC_PHYSICAL_ID_ENTRY_HOST_PHYSICAL_ID_MASK;
-		else
+		} else {
 			pi_data.cpu = -1;
+			pi_data.ga_log_intr = true;
+		}
 
 		ret = irq_set_vcpu_affinity(host_irq, &pi_data);
 		if (ret)
@@ -850,9 +852,9 @@ static void avic_update_iommu_vcpu_affinity(struct kvm_vcpu *vcpu, int cpu,
 		void *data = irqfd->irq_bypass_data;
 
 		if (!(action & AVIC_TOGGLE_ON_OFF))
-			WARN_ON_ONCE(amd_iommu_update_ga(cpu, data));
+			WARN_ON_ONCE(amd_iommu_update_ga(data, cpu, true));
 		else if (cpu >= 0)
-			WARN_ON_ONCE(amd_iommu_activate_guest_mode(data, cpu));
+			WARN_ON_ONCE(amd_iommu_activate_guest_mode(data, cpu, true));
 		else
 			WARN_ON_ONCE(amd_iommu_deactivate_guest_mode(data));
 	}
diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
index 4b0cc249771f..c50d4a8a51be 100644
--- a/drivers/iommu/amd/iommu.c
+++ b/drivers/iommu/amd/iommu.c
@@ -3804,7 +3804,8 @@ static const struct irq_domain_ops amd_ir_domain_ops = {
 	.deactivate = irq_remapping_deactivate,
 };
 
-static void __amd_iommu_update_ga(struct irte_ga *entry, int cpu)
+static void __amd_iommu_update_ga(struct irte_ga *entry, int cpu,
+				  bool ga_log_intr)
 {
 	if (cpu >= 0) {
 		entry->lo.fields_vapic.destination =
@@ -3812,8 +3813,10 @@ static void __amd_iommu_update_ga(struct irte_ga *entry, int cpu)
 		entry->hi.fields.destination =
 					APICID_TO_IRTE_DEST_HI(cpu);
 		entry->lo.fields_vapic.is_run = true;
+		entry->lo.fields_vapic.ga_log_intr = false;
 	} else {
 		entry->lo.fields_vapic.is_run = false;
+		entry->lo.fields_vapic.ga_log_intr = ga_log_intr;
 	}
 }
 
@@ -3822,16 +3825,19 @@ static void __amd_iommu_update_ga(struct irte_ga *entry, int cpu)
  * a vCPU, without issuing an IOMMU invalidation for the IRTE.
  *
  * If the vCPU is associated with a pCPU (@cpu >= 0), configure the Destination
- * with the pCPU's APIC ID and set IsRun, else clear IsRun.  I.e. treat vCPUs
- * that are associated with a pCPU as running.  This API is intended to be used
- * when a vCPU is scheduled in/out (or stops running for any reason), to do a
- * fast update of IsRun and (conditionally) Destination.
+ * with the pCPU's APIC ID, set IsRun, and clear GALogIntr.  If the vCPU isn't
+ * associated with a pCPU (@cpu < 0), clear IsRun and set/clear GALogIntr based
+ * on input from the caller (e.g. KVM only requests GALogIntr when the vCPU is
+ * blocking and requires a notification wake event).  I.e. treat vCPUs that are
+ * associated with a pCPU as running.  This API is intended to be used when a
+ * vCPU is scheduled in/out (or stops running for any reason), to do a fast
+ * update of IsRun, GALogIntr, and (conditionally) Destination.
  *
  * Per the IOMMU spec, the Destination, IsRun, and GATag fields are not cached
  * and thus don't require an invalidation to ensure the IOMMU consumes fresh
  * information.
  */
-int amd_iommu_update_ga(int cpu, void *data)
+int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr)
 {
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -3845,14 +3851,14 @@ int amd_iommu_update_ga(int cpu, void *data)
 	if (!ir_data->iommu)
 		return -ENODEV;
 
-	__amd_iommu_update_ga(entry, cpu);
+	__amd_iommu_update_ga(entry, cpu, ga_log_intr);
 
 	return __modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
 				ir_data->irq_2_irte.index, entry);
 }
 EXPORT_SYMBOL(amd_iommu_update_ga);
 
-int amd_iommu_activate_guest_mode(void *data, int cpu)
+int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr)
 {
 	struct amd_ir_data *ir_data = (struct amd_ir_data *)data;
 	struct irte_ga *entry = (struct irte_ga *) ir_data->entry;
@@ -3871,12 +3877,11 @@ int amd_iommu_activate_guest_mode(void *data, int cpu)
 
 	entry->lo.fields_vapic.valid       = valid;
 	entry->lo.fields_vapic.guest_mode  = 1;
-	entry->lo.fields_vapic.ga_log_intr = 1;
 	entry->hi.fields.ga_root_ptr       = ir_data->ga_root_ptr;
 	entry->hi.fields.vector            = ir_data->ga_vector;
 	entry->lo.fields_vapic.ga_tag      = ir_data->ga_tag;
 
-	__amd_iommu_update_ga(entry, cpu);
+	__amd_iommu_update_ga(entry, cpu, ga_log_intr);
 
 	return modify_irte_ga(ir_data->iommu, ir_data->irq_2_irte.devid,
 			      ir_data->irq_2_irte.index, entry);
@@ -3947,7 +3952,8 @@ static int amd_ir_set_vcpu_affinity(struct irq_data *data, void *info)
 		ir_data->ga_vector = pi_data->vector;
 		ir_data->ga_tag = pi_data->ga_tag;
 		if (pi_data->is_guest_mode)
-			ret = amd_iommu_activate_guest_mode(ir_data, pi_data->cpu);
+			ret = amd_iommu_activate_guest_mode(ir_data, pi_data->cpu,
+							    pi_data->ga_log_intr);
 		else
 			ret = amd_iommu_deactivate_guest_mode(ir_data);
 	} else {
diff --git a/include/linux/amd-iommu.h b/include/linux/amd-iommu.h
index c9f2df0c4596..8cced632ecd0 100644
--- a/include/linux/amd-iommu.h
+++ b/include/linux/amd-iommu.h
@@ -30,9 +30,8 @@ static inline void amd_iommu_detect(void) { }
 /* IOMMU AVIC Function */
 extern int amd_iommu_register_ga_log_notifier(int (*notifier)(u32));
 
-extern int amd_iommu_update_ga(int cpu, void *data);
-
-extern int amd_iommu_activate_guest_mode(void *data, int cpu);
+extern int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr);
+extern int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr);
 extern int amd_iommu_deactivate_guest_mode(void *data);
 
 #else /* defined(CONFIG_AMD_IOMMU) && defined(CONFIG_IRQ_REMAP) */
@@ -43,12 +42,12 @@ amd_iommu_register_ga_log_notifier(int (*notifier)(u32))
 	return 0;
 }
 
-static inline int amd_iommu_update_ga(int cpu, void *data)
+static inline int amd_iommu_update_ga(void *data, int cpu, bool ga_log_intr)
 {
 	return 0;
 }
 
-static inline int amd_iommu_activate_guest_mode(void *data, int cpu)
+static inline int amd_iommu_activate_guest_mode(void *data, int cpu, bool ga_log_intr)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From 283ed5001d6852f85c09ed2522331b2b197ba937 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 22 May 2025 16:52:11 -0700
Subject: KVM: Use a local struct to do the initial vfs_poll() on an irqfd

Use a function-local struct for the poll_table passed to vfs_poll(), as
nothing in the vfs_poll() callchain grabs a long-term reference to the
structure, i.e. its lifetime doesn't need to be tied to the irqfd.  Using
a local structure will also allow propagating failures out of the polling
callback without further polluting kvm_kernel_irqfd.

Opportunstically rename irqfd_ptable_queue_proc() to kvm_irqfd_register()
to capture what it actually does.

Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250522235223.3178519-2-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/kvm_irqfd.h |  1 -
 virt/kvm/eventfd.c        | 26 +++++++++++++++++---------
 2 files changed, 17 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kvm_irqfd.h b/include/linux/kvm_irqfd.h
index 361c07f4466d..ef8c134ded8a 100644
--- a/include/linux/kvm_irqfd.h
+++ b/include/linux/kvm_irqfd.h
@@ -55,7 +55,6 @@ struct kvm_kernel_irqfd {
 	/* Used for setup/shutdown */
 	struct eventfd_ctx *eventfd;
 	struct list_head list;
-	poll_table pt;
 	struct work_struct shutdown;
 	struct irq_bypass_consumer consumer;
 	struct irq_bypass_producer *producer;
diff --git a/virt/kvm/eventfd.c b/virt/kvm/eventfd.c
index 59b1e64697f1..0b655376734e 100644
--- a/virt/kvm/eventfd.c
+++ b/virt/kvm/eventfd.c
@@ -245,12 +245,17 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 	return ret;
 }
 
-static void
-irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *wqh,
-			poll_table *pt)
+struct kvm_irqfd_pt {
+	struct kvm_kernel_irqfd *irqfd;
+	poll_table pt;
+};
+
+static void kvm_irqfd_register(struct file *file, wait_queue_head_t *wqh,
+			       poll_table *pt)
 {
-	struct kvm_kernel_irqfd *irqfd =
-		container_of(pt, struct kvm_kernel_irqfd, pt);
+	struct kvm_irqfd_pt *p = container_of(pt, struct kvm_irqfd_pt, pt);
+	struct kvm_kernel_irqfd *irqfd = p->irqfd;
+
 	add_wait_queue_priority(wqh, &irqfd->wait);
 }
 
@@ -298,6 +303,7 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 {
 	struct kvm_kernel_irqfd *irqfd, *tmp;
 	struct eventfd_ctx *eventfd = NULL, *resamplefd = NULL;
+	struct kvm_irqfd_pt irqfd_pt;
 	int ret;
 	__poll_t events;
 	int idx;
@@ -387,7 +393,6 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	 * a callback whenever someone signals the underlying eventfd
 	 */
 	init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup);
-	init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc);
 
 	spin_lock_irq(&kvm->irqfds.lock);
 
@@ -409,11 +414,14 @@ kvm_irqfd_assign(struct kvm *kvm, struct kvm_irqfd *args)
 	spin_unlock_irq(&kvm->irqfds.lock);
 
 	/*
-	 * Check if there was an event already pending on the eventfd
-	 * before we registered, and trigger it as if we didn't miss it.
+	 * Register the irqfd with the eventfd by polling on the eventfd.  If
+	 * there was en event pending on the eventfd prior to registering,
+	 * manually trigger IRQ injection.
 	 */
-	events = vfs_poll(fd_file(f), &irqfd->pt);
+	irqfd_pt.irqfd = irqfd;
+	init_poll_funcptr(&irqfd_pt.pt, kvm_irqfd_register);
 
+	events = vfs_poll(fd_file(f), &irqfd_pt.pt);
 	if (events & EPOLLIN)
 		schedule_work(&irqfd->inject);
 
-- 
cgit v1.2.3


From 0d09582b3a607436fd91d6ce813048a048ecbf10 Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 22 May 2025 16:52:18 -0700
Subject: sched/wait: Add a waitqueue helper for fully exclusive priority
 waiters

Add a waitqueue helper to add a priority waiter that requires exclusive
wakeups, i.e. that requires that it be the _only_ priority waiter.  The
API will be used by KVM to ensure that at most one of KVM's irqfds is
bound to a single eventfd (across the entire kernel).

Open code the helper instead of using __add_wait_queue() so that the
common path doesn't need to "handle" impossible failures.

Cc: K Prateek Nayak <kprateek.nayak@amd.com>
Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250522235223.3178519-9-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/wait.h |  2 ++
 kernel/sched/wait.c  | 18 ++++++++++++++++++
 2 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/wait.h b/include/linux/wait.h
index 965a19809c7e..09855d819418 100644
--- a/include/linux/wait.h
+++ b/include/linux/wait.h
@@ -164,6 +164,8 @@ static inline bool wq_has_sleeper(struct wait_queue_head *wq_head)
 extern void add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void add_wait_queue_exclusive(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 extern void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
+extern int add_wait_queue_priority_exclusive(struct wait_queue_head *wq_head,
+					     struct wait_queue_entry *wq_entry);
 extern void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry);
 
 static inline void __add_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
diff --git a/kernel/sched/wait.c b/kernel/sched/wait.c
index 4ab3ab195277..15632c89c4f2 100644
--- a/kernel/sched/wait.c
+++ b/kernel/sched/wait.c
@@ -47,6 +47,24 @@ void add_wait_queue_priority(struct wait_queue_head *wq_head, struct wait_queue_
 }
 EXPORT_SYMBOL_GPL(add_wait_queue_priority);
 
+int add_wait_queue_priority_exclusive(struct wait_queue_head *wq_head,
+				      struct wait_queue_entry *wq_entry)
+{
+	struct list_head *head = &wq_head->head;
+
+	wq_entry->flags |= WQ_FLAG_EXCLUSIVE | WQ_FLAG_PRIORITY;
+
+	guard(spinlock_irqsave)(&wq_head->lock);
+
+	if (!list_empty(head) &&
+	    (list_first_entry(head, typeof(*wq_entry), entry)->flags & WQ_FLAG_PRIORITY))
+		return -EBUSY;
+
+	list_add(&wq_entry->entry, head);
+	return 0;
+}
+EXPORT_SYMBOL_GPL(add_wait_queue_priority_exclusive);
+
 void remove_wait_queue(struct wait_queue_head *wq_head, struct wait_queue_entry *wq_entry)
 {
 	unsigned long flags;
-- 
cgit v1.2.3


From 7484e15dbb016d9d40f8c6e0475810212ae181db Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 17 Jun 2025 00:09:51 -0400
Subject: replace collect_mounts()/drop_collected_mounts() with a safer variant

collect_mounts() has several problems - one can't iterate over the results
directly, so it has to be done with callback passed to iterate_mounts();
it has an oopsable race with d_invalidate(); it creates temporary clones
of mounts invisibly for sync umount (IOW, you can have non-lazy umount
succeed leaving filesystem not mounted anywhere and yet still busy).

A saner approach is to give caller an array of struct path that would pin
every mount in a subtree, without cloning any mounts.

        * collect_mounts()/drop_collected_mounts()/iterate_mounts() is gone
        * collect_paths(where, preallocated, size) gives either ERR_PTR(-E...) or
a pointer to array of struct path, one for each chunk of tree visible under
'where' (i.e. the first element is a copy of where, followed by (mount,root)
for everything mounted under it - the same set collect_mounts() would give).
Unlike collect_mounts(), the mounts are *not* cloned - we just get pinning
references to the roots of subtrees in the caller's namespace.
        Array is terminated by {NULL, NULL} struct path.  If it fits into
preallocated array (on-stack, normally), that's where it goes; otherwise
it's allocated by kmalloc_array().  Passing 0 as size means that 'preallocated'
is ignored (and expected to be NULL).
        * drop_collected_paths(paths, preallocated) is given the array returned
by an earlier call of collect_paths() and the preallocated array passed to that
call.  All mount/dentry references are dropped and array is kfree'd if it's not
equal to 'preallocated'.
        * instead of iterate_mounts(), users should just iterate over array
of struct path - nothing exotic is needed for that.  Existing users (all in
audit_tree.c) are converted.

[folded a fix for braino reported by Venkat Rao Bagalkote <venkat88@linux.ibm.com>]

Fixes: 80b5dce8c59b0 ("vfs: Add a function to lazily unmount all mounts from any dentry")
Tested-by: Venkat Rao Bagalkote <venkat88@linux.ibm.com>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/porting.rst |  9 ++++
 fs/namespace.c                        | 97 +++++++++++++++++++++--------------
 fs/pnode.h                            |  2 -
 include/linux/mount.h                 |  6 +--
 kernel/audit_tree.c                   | 63 ++++++++++++-----------
 5 files changed, 104 insertions(+), 73 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/porting.rst b/Documentation/filesystems/porting.rst
index 3616d7161dab..a5734bdd1cc7 100644
--- a/Documentation/filesystems/porting.rst
+++ b/Documentation/filesystems/porting.rst
@@ -1249,3 +1249,12 @@ Using try_lookup_noperm() will require linux/namei.h to be included.
 
 Calling conventions for ->d_automount() have changed; we should *not* grab
 an extra reference to new mount - it should be returned with refcount 1.
+
+---
+
+collect_mounts()/drop_collected_mounts()/iterate_mounts() are gone now.
+Replacement is collect_paths()/drop_collected_path(), with no special
+iterator needed.  Instead of a cloned mount tree, the new interface returns
+an array of struct path, one for each mount collect_mounts() would've
+created.  These struct path point to locations in the caller's namespace
+that would be roots of the cloned mounts.
diff --git a/fs/namespace.c b/fs/namespace.c
index e13d9ab4f564..14601ec4c2c5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2310,21 +2310,62 @@ out:
 	return dst_mnt;
 }
 
-/* Caller should check returned pointer for errors */
+static inline bool extend_array(struct path **res, struct path **to_free,
+				unsigned n, unsigned *count, unsigned new_count)
+{
+	struct path *p;
+
+	if (likely(n < *count))
+		return true;
+	p = kmalloc_array(new_count, sizeof(struct path), GFP_KERNEL);
+	if (p && *count)
+		memcpy(p, *res, *count * sizeof(struct path));
+	*count = new_count;
+	kfree(*to_free);
+	*to_free = *res = p;
+	return p;
+}
 
-struct vfsmount *collect_mounts(const struct path *path)
+struct path *collect_paths(const struct path *path,
+			      struct path *prealloc, unsigned count)
 {
-	struct mount *tree;
-	namespace_lock();
-	if (!check_mnt(real_mount(path->mnt)))
-		tree = ERR_PTR(-EINVAL);
-	else
-		tree = copy_tree(real_mount(path->mnt), path->dentry,
-				 CL_COPY_ALL | CL_PRIVATE);
-	namespace_unlock();
-	if (IS_ERR(tree))
-		return ERR_CAST(tree);
-	return &tree->mnt;
+	struct mount *root = real_mount(path->mnt);
+	struct mount *child;
+	struct path *res = prealloc, *to_free = NULL;
+	unsigned n = 0;
+
+	guard(rwsem_read)(&namespace_sem);
+
+	if (!check_mnt(root))
+		return ERR_PTR(-EINVAL);
+	if (!extend_array(&res, &to_free, 0, &count, 32))
+		return ERR_PTR(-ENOMEM);
+	res[n++] = *path;
+	list_for_each_entry(child, &root->mnt_mounts, mnt_child) {
+		if (!is_subdir(child->mnt_mountpoint, path->dentry))
+			continue;
+		for (struct mount *m = child; m; m = next_mnt(m, child)) {
+			if (!extend_array(&res, &to_free, n, &count, 2 * count))
+				return ERR_PTR(-ENOMEM);
+			res[n].mnt = &m->mnt;
+			res[n].dentry = m->mnt.mnt_root;
+			n++;
+		}
+	}
+	if (!extend_array(&res, &to_free, n, &count, count + 1))
+		return ERR_PTR(-ENOMEM);
+	memset(res + n, 0, (count - n) * sizeof(struct path));
+	for (struct path *p = res; p->mnt; p++)
+		path_get(p);
+	return res;
+}
+
+void drop_collected_paths(struct path *paths, struct path *prealloc)
+{
+	for (struct path *p = paths; p->mnt; p++)
+		path_put(p);
+	if (paths != prealloc)
+		kfree(paths);
 }
 
 static void free_mnt_ns(struct mnt_namespace *);
@@ -2401,15 +2442,6 @@ void dissolve_on_fput(struct vfsmount *mnt)
 	free_mnt_ns(ns);
 }
 
-void drop_collected_mounts(struct vfsmount *mnt)
-{
-	namespace_lock();
-	lock_mount_hash();
-	umount_tree(real_mount(mnt), 0);
-	unlock_mount_hash();
-	namespace_unlock();
-}
-
 static bool __has_locked_children(struct mount *mnt, struct dentry *dentry)
 {
 	struct mount *child;
@@ -2511,21 +2543,6 @@ struct vfsmount *clone_private_mount(const struct path *path)
 }
 EXPORT_SYMBOL_GPL(clone_private_mount);
 
-int iterate_mounts(int (*f)(struct vfsmount *, void *), void *arg,
-		   struct vfsmount *root)
-{
-	struct mount *mnt;
-	int res = f(root, arg);
-	if (res)
-		return res;
-	list_for_each_entry(mnt, &real_mount(root)->mnt_list, mnt_list) {
-		res = f(&mnt->mnt, arg);
-		if (res)
-			return res;
-	}
-	return 0;
-}
-
 static void lock_mnt_tree(struct mount *mnt)
 {
 	struct mount *p;
@@ -6262,7 +6279,11 @@ void put_mnt_ns(struct mnt_namespace *ns)
 {
 	if (!refcount_dec_and_test(&ns->ns.count))
 		return;
-	drop_collected_mounts(&ns->root->mnt);
+	namespace_lock();
+	lock_mount_hash();
+	umount_tree(ns->root, 0);
+	unlock_mount_hash();
+	namespace_unlock();
 	free_mnt_ns(ns);
 }
 
diff --git a/fs/pnode.h b/fs/pnode.h
index 34b6247af01d..2d026fb98b18 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -28,8 +28,6 @@
 #define CL_SHARED_TO_SLAVE	0x20
 #define CL_COPY_MNT_NS_FILE	0x40
 
-#define CL_COPY_ALL		(CL_COPY_UNBINDABLE | CL_COPY_MNT_NS_FILE)
-
 static inline void set_mnt_shared(struct mount *mnt)
 {
 	mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 4880f434c021..1a508beba446 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -116,10 +116,8 @@ extern int may_umount_tree(struct vfsmount *);
 extern int may_umount(struct vfsmount *);
 int do_mount(const char *, const char __user *,
 		     const char *, unsigned long, void *);
-extern struct vfsmount *collect_mounts(const struct path *);
-extern void drop_collected_mounts(struct vfsmount *);
-extern int iterate_mounts(int (*)(struct vfsmount *, void *), void *,
-			  struct vfsmount *);
+extern struct path *collect_paths(const struct path *, struct path *, unsigned);
+extern void drop_collected_paths(struct path *, struct path *);
 extern void kern_unmount_array(struct vfsmount *mnt[], unsigned int num);
 
 extern int cifs_root_data(char **dev, char **opts);
diff --git a/kernel/audit_tree.c b/kernel/audit_tree.c
index f2f38903b2fe..b0eae2a3c895 100644
--- a/kernel/audit_tree.c
+++ b/kernel/audit_tree.c
@@ -668,12 +668,6 @@ int audit_remove_tree_rule(struct audit_krule *rule)
 	return 0;
 }
 
-static int compare_root(struct vfsmount *mnt, void *arg)
-{
-	return inode_to_key(d_backing_inode(mnt->mnt_root)) ==
-	       (unsigned long)arg;
-}
-
 void audit_trim_trees(void)
 {
 	struct list_head cursor;
@@ -683,8 +677,9 @@ void audit_trim_trees(void)
 	while (cursor.next != &tree_list) {
 		struct audit_tree *tree;
 		struct path path;
-		struct vfsmount *root_mnt;
 		struct audit_node *node;
+		struct path *paths;
+		struct path array[16];
 		int err;
 
 		tree = container_of(cursor.next, struct audit_tree, list);
@@ -696,9 +691,9 @@ void audit_trim_trees(void)
 		if (err)
 			goto skip_it;
 
-		root_mnt = collect_mounts(&path);
+		paths = collect_paths(&path, array, 16);
 		path_put(&path);
-		if (IS_ERR(root_mnt))
+		if (IS_ERR(paths))
 			goto skip_it;
 
 		spin_lock(&hash_lock);
@@ -706,14 +701,17 @@ void audit_trim_trees(void)
 			struct audit_chunk *chunk = find_chunk(node);
 			/* this could be NULL if the watch is dying else where... */
 			node->index |= 1U<<31;
-			if (iterate_mounts(compare_root,
-					   (void *)(chunk->key),
-					   root_mnt))
-				node->index &= ~(1U<<31);
+			for (struct path *p = paths; p->dentry; p++) {
+				struct inode *inode = p->dentry->d_inode;
+				if (inode_to_key(inode) == chunk->key) {
+					node->index &= ~(1U<<31);
+					break;
+				}
+			}
 		}
 		spin_unlock(&hash_lock);
 		trim_marked(tree);
-		drop_collected_mounts(root_mnt);
+		drop_collected_paths(paths, array);
 skip_it:
 		put_tree(tree);
 		mutex_lock(&audit_filter_mutex);
@@ -742,9 +740,14 @@ void audit_put_tree(struct audit_tree *tree)
 	put_tree(tree);
 }
 
-static int tag_mount(struct vfsmount *mnt, void *arg)
+static int tag_mounts(struct path *paths, struct audit_tree *tree)
 {
-	return tag_chunk(d_backing_inode(mnt->mnt_root), arg);
+	for (struct path *p = paths; p->dentry; p++) {
+		int err = tag_chunk(p->dentry->d_inode, tree);
+		if (err)
+			return err;
+	}
+	return 0;
 }
 
 /*
@@ -801,7 +804,8 @@ int audit_add_tree_rule(struct audit_krule *rule)
 {
 	struct audit_tree *seed = rule->tree, *tree;
 	struct path path;
-	struct vfsmount *mnt;
+	struct path array[16];
+	struct path *paths;
 	int err;
 
 	rule->tree = NULL;
@@ -828,16 +832,16 @@ int audit_add_tree_rule(struct audit_krule *rule)
 	err = kern_path(tree->pathname, 0, &path);
 	if (err)
 		goto Err;
-	mnt = collect_mounts(&path);
+	paths = collect_paths(&path, array, 16);
 	path_put(&path);
-	if (IS_ERR(mnt)) {
-		err = PTR_ERR(mnt);
+	if (IS_ERR(paths)) {
+		err = PTR_ERR(paths);
 		goto Err;
 	}
 
 	get_tree(tree);
-	err = iterate_mounts(tag_mount, tree, mnt);
-	drop_collected_mounts(mnt);
+	err = tag_mounts(paths, tree);
+	drop_collected_paths(paths, array);
 
 	if (!err) {
 		struct audit_node *node;
@@ -872,20 +876,21 @@ int audit_tag_tree(char *old, char *new)
 	struct list_head cursor, barrier;
 	int failed = 0;
 	struct path path1, path2;
-	struct vfsmount *tagged;
+	struct path array[16];
+	struct path *paths;
 	int err;
 
 	err = kern_path(new, 0, &path2);
 	if (err)
 		return err;
-	tagged = collect_mounts(&path2);
+	paths = collect_paths(&path2, array, 16);
 	path_put(&path2);
-	if (IS_ERR(tagged))
-		return PTR_ERR(tagged);
+	if (IS_ERR(paths))
+		return PTR_ERR(paths);
 
 	err = kern_path(old, 0, &path1);
 	if (err) {
-		drop_collected_mounts(tagged);
+		drop_collected_paths(paths, array);
 		return err;
 	}
 
@@ -914,7 +919,7 @@ int audit_tag_tree(char *old, char *new)
 			continue;
 		}
 
-		failed = iterate_mounts(tag_mount, tree, tagged);
+		failed = tag_mounts(paths, tree);
 		if (failed) {
 			put_tree(tree);
 			mutex_lock(&audit_filter_mutex);
@@ -955,7 +960,7 @@ int audit_tag_tree(char *old, char *new)
 	list_del(&cursor);
 	mutex_unlock(&audit_filter_mutex);
 	path_put(&path1);
-	drop_collected_mounts(tagged);
+	drop_collected_paths(paths, array);
 	return failed;
 }
 
-- 
cgit v1.2.3


From fc2898ea793a48bc4b74b61cde2d8656f20efdf4 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Mon, 23 Jun 2025 01:30:49 +0100
Subject: workqueue: Remove unused work_on_cpu_safe

The last use of the work_on_cpu_safe() macro was removed recently by
commit 9cda46babdfe ("crypto: n2 - remove Niagara2 SPU driver")

Remove it, and the work_on_cpu_safe_key() function it calls.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/workqueue.h | 13 -------------
 kernel/workqueue.c        | 25 -------------------------
 2 files changed, 38 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 83d158bb2791..45d5dd470ff6 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -847,19 +847,6 @@ long work_on_cpu_key(int cpu, long (*fn)(void *),
 	work_on_cpu_key(_cpu, _fn, _arg, &__key);	\
 })
 
-long work_on_cpu_safe_key(int cpu, long (*fn)(void *),
-			  void *arg, struct lock_class_key *key);
-
-/*
- * A new key is defined for each caller to make sure the work
- * associated with the function doesn't share its locking class.
- */
-#define work_on_cpu_safe(_cpu, _fn, _arg)		\
-({							\
-	static struct lock_class_key __key;		\
-							\
-	work_on_cpu_safe_key(_cpu, _fn, _arg, &__key);	\
-})
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FREEZER
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 086452e339c4..12c3080332bd 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -6771,31 +6771,6 @@ long work_on_cpu_key(int cpu, long (*fn)(void *),
 	return wfc.ret;
 }
 EXPORT_SYMBOL_GPL(work_on_cpu_key);
-
-/**
- * work_on_cpu_safe_key - run a function in thread context on a particular cpu
- * @cpu: the cpu to run on
- * @fn:  the function to run
- * @arg: the function argument
- * @key: The lock class key for lock debugging purposes
- *
- * Disables CPU hotplug and calls work_on_cpu(). The caller must not hold
- * any locks which would prevent @fn from completing.
- *
- * Return: The value @fn returns.
- */
-long work_on_cpu_safe_key(int cpu, long (*fn)(void *),
-			  void *arg, struct lock_class_key *key)
-{
-	long ret = -ENODEV;
-
-	cpus_read_lock();
-	if (cpu_online(cpu))
-		ret = work_on_cpu_key(cpu, fn, arg, key);
-	cpus_read_unlock();
-	return ret;
-}
-EXPORT_SYMBOL_GPL(work_on_cpu_safe_key);
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_FREEZER
-- 
cgit v1.2.3


From 3aa54d162490f14d1f1fdf3b3d1170b2ea50276b Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 18 Jun 2025 11:11:29 +0200
Subject: PCI/pwrctrl: Fix the kerneldoc tag for private fields

The correct tag for marking private fields in kerneldoc is "private:", not
capitalized "Private:". Fix the pwrctl struct to silence the following
warnings:

  Warning: include/linux/pci-pwrctrl.h:45 struct member 'nb' not described in 'pci_pwrctrl'
  Warning: include/linux/pci-pwrctrl.h:45 struct member 'link' not described in 'pci_pwrctrl'
  Warning: include/linux/pci-pwrctrl.h:45 struct member 'work' not described in 'pci_pwrctrl'

Fixes: 4565d2652a37 ("PCI/pwrctl: Add PCI power control core code")
Reported-by: Bjorn Helgaas <helgaas@kernel.org>
Closes: https://lore.kernel.org/all/20250617233539.GA1177120@bhelgaas/
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/20250618091129.44810-1-brgl@bgdev.pl
---
 include/linux/pci-pwrctrl.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/pci-pwrctrl.h b/include/linux/pci-pwrctrl.h
index 7d439b0675e9..4aefc7901cd1 100644
--- a/include/linux/pci-pwrctrl.h
+++ b/include/linux/pci-pwrctrl.h
@@ -39,7 +39,7 @@ struct device_link;
 struct pci_pwrctrl {
 	struct device *dev;
 
-	/* Private: don't use. */
+	/* private: internal use only */
 	struct notifier_block nb;
 	struct device_link *link;
 	struct work_struct work;
-- 
cgit v1.2.3


From bbb7d478d91ac4d5c288e226cc8744daf3820798 Mon Sep 17 00:00:00 2001
From: Alexander Duyck <alexanderduyck@fb.com>
Date: Wed, 18 Jun 2025 15:07:22 -0700
Subject: net: phy: Add interface types for 50G and 100G

Add support for 802.3cd based interface types 50GBASE-R and 100GBASE-P.
This choice in naming is based on section 135 of the 802.3-2022 IEEE
Standard.

In addition it is adding support for what I am referring to as LAUI
which is based on annex 135C of the IEEE Standard, and shares many
similarities with the 25/50G consortium. The main difference between the
two is that IEEE spec refers to LAUI as the AUI before the RS(544/514) FEC,
whereas the 25/50G use this lane and frequency combination after going
through RS(528/514), Base-R or no FEC at all.

Signed-off-by: Alexander Duyck <alexanderduyck@fb.com>
Link: https://patch.msgid.link/175028444205.625704.4191700324472974116.stgit@ahduyck-xeon-server.home.arpa
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/phy-core.c |  3 +++
 drivers/net/phy/phy_caps.c |  9 +++++++++
 drivers/net/phy/phylink.c  | 13 +++++++++++++
 include/linux/phy.h        | 12 ++++++++++++
 4 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index 27f1833563ab..c480bb40fa73 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -142,6 +142,9 @@ int phy_interface_num_ports(phy_interface_t interface)
 	case PHY_INTERFACE_MODE_RXAUI:
 	case PHY_INTERFACE_MODE_XAUI:
 	case PHY_INTERFACE_MODE_1000BASEKX:
+	case PHY_INTERFACE_MODE_50GBASER:
+	case PHY_INTERFACE_MODE_LAUI:
+	case PHY_INTERFACE_MODE_100GBASEP:
 		return 1;
 	case PHY_INTERFACE_MODE_QSGMII:
 	case PHY_INTERFACE_MODE_QUSGMII:
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index 38417e288611..d11ce1c7e712 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -351,6 +351,15 @@ unsigned long phy_caps_from_interface(phy_interface_t interface)
 		link_caps |= BIT(LINK_CAPA_40000FD);
 		break;
 
+	case PHY_INTERFACE_MODE_50GBASER:
+	case PHY_INTERFACE_MODE_LAUI:
+		link_caps |= BIT(LINK_CAPA_50000FD);
+		break;
+
+	case PHY_INTERFACE_MODE_100GBASEP:
+		link_caps |= BIT(LINK_CAPA_100000FD);
+		break;
+
 	case PHY_INTERFACE_MODE_INTERNAL:
 		link_caps |= LINK_CAPA_ALL;
 		break;
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index 0faa3d97e06b..67218d278ce6 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -127,6 +127,9 @@ do {									\
 #endif
 
 static const phy_interface_t phylink_sfp_interface_preference[] = {
+	PHY_INTERFACE_MODE_100GBASEP,
+	PHY_INTERFACE_MODE_50GBASER,
+	PHY_INTERFACE_MODE_LAUI,
 	PHY_INTERFACE_MODE_25GBASER,
 	PHY_INTERFACE_MODE_USXGMII,
 	PHY_INTERFACE_MODE_10GBASER,
@@ -274,6 +277,13 @@ static int phylink_interface_max_speed(phy_interface_t interface)
 	case PHY_INTERFACE_MODE_XLGMII:
 		return SPEED_40000;
 
+	case PHY_INTERFACE_MODE_50GBASER:
+	case PHY_INTERFACE_MODE_LAUI:
+		return SPEED_50000;
+
+	case PHY_INTERFACE_MODE_100GBASEP:
+		return SPEED_100000;
+
 	case PHY_INTERFACE_MODE_INTERNAL:
 	case PHY_INTERFACE_MODE_NA:
 	case PHY_INTERFACE_MODE_MAX:
@@ -798,6 +808,9 @@ static int phylink_parse_mode(struct phylink *pl,
 		case PHY_INTERFACE_MODE_10GKR:
 		case PHY_INTERFACE_MODE_10GBASER:
 		case PHY_INTERFACE_MODE_XLGMII:
+		case PHY_INTERFACE_MODE_50GBASER:
+		case PHY_INTERFACE_MODE_LAUI:
+		case PHY_INTERFACE_MODE_100GBASEP:
 			caps = ~(MAC_SYM_PAUSE | MAC_ASYM_PAUSE);
 			caps = phylink_get_capabilities(pl->link_config.interface, caps,
 							RATE_MATCH_NONE);
diff --git a/include/linux/phy.h b/include/linux/phy.h
index b037aab7b71d..74c1bcf64b3c 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -103,6 +103,9 @@ extern const int phy_basic_ports_array[3];
  * @PHY_INTERFACE_MODE_QUSGMII: Quad Universal SGMII
  * @PHY_INTERFACE_MODE_1000BASEKX: 1000Base-KX - with Clause 73 AN
  * @PHY_INTERFACE_MODE_10G_QXGMII: 10G-QXGMII - 4 ports over 10G USXGMII
+ * @PHY_INTERFACE_MODE_50GBASER: 50GBase-R - with Clause 134 FEC
+ * @PHY_INTERFACE_MODE_LAUI: 50 Gigabit Attachment Unit Interface
+ * @PHY_INTERFACE_MODE_100GBASEP: 100GBase-P - with Clause 134 FEC
  * @PHY_INTERFACE_MODE_MAX: Book keeping
  *
  * Describes the interface between the MAC and PHY.
@@ -144,6 +147,9 @@ typedef enum {
 	PHY_INTERFACE_MODE_QUSGMII,
 	PHY_INTERFACE_MODE_1000BASEKX,
 	PHY_INTERFACE_MODE_10G_QXGMII,
+	PHY_INTERFACE_MODE_50GBASER,
+	PHY_INTERFACE_MODE_LAUI,
+	PHY_INTERFACE_MODE_100GBASEP,
 	PHY_INTERFACE_MODE_MAX,
 } phy_interface_t;
 
@@ -260,6 +266,12 @@ static inline const char *phy_modes(phy_interface_t interface)
 		return "qusgmii";
 	case PHY_INTERFACE_MODE_10G_QXGMII:
 		return "10g-qxgmii";
+	case PHY_INTERFACE_MODE_50GBASER:
+		return "50gbase-r";
+	case PHY_INTERFACE_MODE_LAUI:
+		return "laui";
+	case PHY_INTERFACE_MODE_100GBASEP:
+		return "100gbase-p";
 	default:
 		return "unknown";
 	}
-- 
cgit v1.2.3


From dad51ea09040f9ac2ea2a0f694e5e3ed5cf167b9 Mon Sep 17 00:00:00 2001
From: Kory Maincent <kory.maincent@bootlin.com>
Date: Fri, 20 Jun 2025 12:02:40 +0200
Subject: net: pse-pd: tps23881: Clarify setup_pi_matrix callback documentation

Improve the setup_pi_matrix callback documentation to clarify its purpose
and usage. The enhanced description explains that PSE PI devicetree nodes
are pre-parsed before this callback is invoked, and drivers should utilize
pcdev->pi[x]->pairset[y].np to map PSE controller hardware ports to their
corresponding Power Interfaces.

This clarification helps driver implementers understand the callback's
role in establishing the hardware-to-PI relationship mapping.

Signed-off-by: Kory Maincent <kory.maincent@bootlin.com>
Link: https://patch.msgid.link/20250620-poe_doc_improve-v1-2-96357bb95d52@bootlin.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/pse-pd/pse.h | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/pse-pd/pse.h b/include/linux/pse-pd/pse.h
index e5f305cef82e..4e5696cfade7 100644
--- a/include/linux/pse-pd/pse.h
+++ b/include/linux/pse-pd/pse.h
@@ -159,7 +159,13 @@ struct ethtool_pse_control_status {
 /**
  * struct pse_controller_ops - PSE controller driver callbacks
  *
- * @setup_pi_matrix: setup PI matrix of the PSE controller
+ * @setup_pi_matrix: Setup PI matrix of the PSE controller.
+ *		     The PSE PIs devicetree nodes have already been parsed by
+ *		     of_load_pse_pis() and the pcdev->pi[x]->pairset[y].np
+ *		     populated. This callback should establish the
+ *		     relationship between the PSE controller hardware ports
+ *		     and the PSE Power Interfaces, either through software
+ *		     mapping or hardware configuration.
  * @pi_get_admin_state: Get the operational state of the PSE PI. This ops
  *			is mandatory.
  * @pi_get_pw_status: Get the power detection status of the PSE PI. This
-- 
cgit v1.2.3


From 7934a8dd8692b56714ce9b36421e316445d94a77 Mon Sep 17 00:00:00 2001
From: Masahiro Yamada <masahiroy@kernel.org>
Date: Fri, 6 Jun 2025 13:10:23 +0900
Subject: module: remove meaningless 'name' parameter from __MODULE_INFO()

The symbol names in the .modinfo section are never used and already
randomized by the __UNIQUE_ID() macro.

Therefore, the second parameter of  __MODULE_INFO() is meaningless
and can be removed to simplify the code.

With this change, the symbol names in the .modinfo section will be
prefixed with __UNIQUE_ID_modinfo, making it clearer that they
originate from MODULE_INFO().

[Before]

  $ objcopy  -j .modinfo vmlinux.o modinfo.o
  $ nm -n modinfo.o | head -n10
  0000000000000000 r __UNIQUE_ID_license560
  0000000000000011 r __UNIQUE_ID_file559
  0000000000000030 r __UNIQUE_ID_description558
  0000000000000074 r __UNIQUE_ID_license580
  000000000000008e r __UNIQUE_ID_file579
  00000000000000bd r __UNIQUE_ID_description578
  00000000000000e6 r __UNIQUE_ID_license581
  00000000000000ff r __UNIQUE_ID_file580
  0000000000000134 r __UNIQUE_ID_description579
  0000000000000179 r __UNIQUE_ID_uncore_no_discover578

[After]

  $ objcopy  -j .modinfo vmlinux.o modinfo.o
  $ nm -n modinfo.o | head -n10
  0000000000000000 r __UNIQUE_ID_modinfo560
  0000000000000011 r __UNIQUE_ID_modinfo559
  0000000000000030 r __UNIQUE_ID_modinfo558
  0000000000000074 r __UNIQUE_ID_modinfo580
  000000000000008e r __UNIQUE_ID_modinfo579
  00000000000000bd r __UNIQUE_ID_modinfo578
  00000000000000e6 r __UNIQUE_ID_modinfo581
  00000000000000ff r __UNIQUE_ID_modinfo580
  0000000000000134 r __UNIQUE_ID_modinfo579
  0000000000000179 r __UNIQUE_ID_modinfo578

Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
---
 include/crypto/algapi.h     | 4 ++--
 include/linux/module.h      | 3 ---
 include/linux/moduleparam.h | 9 +++++----
 include/net/tcp.h           | 4 ++--
 4 files changed, 9 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index 188eface0a11..fc4574940636 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -43,8 +43,8 @@
  * alias.
  */
 #define MODULE_ALIAS_CRYPTO(name)	\
-		__MODULE_INFO(alias, alias_userspace, name);	\
-		__MODULE_INFO(alias, alias_crypto, "crypto-" name)
+		MODULE_INFO(alias, name);	\
+		MODULE_INFO(alias, "crypto-" name)
 
 struct crypto_aead;
 struct crypto_instance;
diff --git a/include/linux/module.h b/include/linux/module.h
index 92e1420fccdf..81b41cc6a19e 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -164,9 +164,6 @@ extern void cleanup_module(void);
 
 struct module_kobject *lookup_or_create_module_kobject(const char *name);
 
-/* Generic info of form tag = "info" */
-#define MODULE_INFO(tag, info) __MODULE_INFO(tag, tag, info)
-
 /* For userspace: you can also call me... */
 #define MODULE_ALIAS(_alias) MODULE_INFO(alias, _alias)
 
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index bfb85fd13e1f..00166f747e27 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -20,18 +20,19 @@
 /* Chosen so that structs with an unsigned long line up. */
 #define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long))
 
-#define __MODULE_INFO(tag, name, info)					  \
-	static const char __UNIQUE_ID(name)[]				  \
+/* Generic info of form tag = "info" */
+#define MODULE_INFO(tag, info)					  \
+	static const char __UNIQUE_ID(modinfo)[]			  \
 		__used __section(".modinfo") __aligned(1)		  \
 		= __MODULE_INFO_PREFIX __stringify(tag) "=" info
 
 #define __MODULE_PARM_TYPE(name, _type)					  \
-	__MODULE_INFO(parmtype, name##type, #name ":" _type)
+	MODULE_INFO(parmtype, #name ":" _type)
 
 /* One for each parameter, describing how to use it.  Some files do
    multiple of these per line, so can't just use MODULE_INFO. */
 #define MODULE_PARM_DESC(_parm, desc) \
-	__MODULE_INFO(parm, _parm, #_parm ":" desc)
+	MODULE_INFO(parm, #_parm ":" desc)
 
 struct kernel_param;
 
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 5078ad868fee..9b39ef630c92 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -2662,8 +2662,8 @@ void tcp_update_ulp(struct sock *sk, struct proto *p,
 		    void (*write_space)(struct sock *sk));
 
 #define MODULE_ALIAS_TCP_ULP(name)				\
-	__MODULE_INFO(alias, alias_userspace, name);		\
-	__MODULE_INFO(alias, alias_tcp_ulp, "tcp-ulp-" name)
+	MODULE_INFO(alias, name);		\
+	MODULE_INFO(alias, "tcp-ulp-" name)
 
 #ifdef CONFIG_NET_SOCK_MSG
 struct sk_msg;
-- 
cgit v1.2.3


From b39f7d75dc41b5f5d028192cd5d66cff71179f35 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 24 Jun 2025 14:21:27 +0100
Subject: fs: Remove three arguments from block_write_end()

block_write_end() looks like it can be used as a ->write_end()
implementation.  However, it can't as it does not unlock nor put
the folio.  Since it does not use the 'file', 'mapping' nor 'fsdata'
arguments, remove them.

Signed-off-by: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Link: https://lore.kernel.org/20250624132130.1590285-1-willy@infradead.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/fops.c                | 2 +-
 fs/buffer.c                 | 7 +++----
 fs/ext2/dir.c               | 2 +-
 fs/ext4/inode.c             | 5 ++---
 fs/iomap/buffered-io.c      | 3 +--
 fs/minix/dir.c              | 2 +-
 fs/nilfs2/dir.c             | 2 +-
 fs/nilfs2/recovery.c        | 3 +--
 fs/ufs/dir.c                | 2 +-
 include/linux/buffer_head.h | 4 +---
 10 files changed, 13 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/block/fops.c b/block/fops.c
index 1309861d4c2c..35cea0cb304d 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -507,7 +507,7 @@ static int blkdev_write_end(struct file *file, struct address_space *mapping,
 		void *fsdata)
 {
 	int ret;
-	ret = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = block_write_end(pos, len, copied, folio);
 
 	folio_unlock(folio);
 	folio_put(folio);
diff --git a/fs/buffer.c b/fs/buffer.c
index 1d34200f69c8..d61073143127 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2270,9 +2270,8 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 }
 EXPORT_SYMBOL(block_write_begin);
 
-int block_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+int block_write_end(loff_t pos, unsigned len, unsigned copied,
+		struct folio *folio)
 {
 	size_t start = pos - folio_pos(folio);
 
@@ -2311,7 +2310,7 @@ int generic_write_end(struct file *file, struct address_space *mapping,
 	loff_t old_size = inode->i_size;
 	bool i_size_changed = false;
 
-	copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	copied = block_write_end(pos, len, copied, folio);
 
 	/*
 	 * No need to use i_size_read() here, the i_size cannot change under us
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index 402fecf90a44..b07b3b369710 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -87,7 +87,7 @@ static void ext2_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
 	struct inode *dir = mapping->host;
 
 	inode_inc_iversion(dir);
-	block_write_end(NULL, mapping, pos, len, len, folio, NULL);
+	block_write_end(pos, len, len, folio);
 
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index be9a4cba35fd..e6aa7ca6d842 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1424,7 +1424,7 @@ static int ext4_write_end(struct file *file,
 		return ext4_write_inline_data_end(inode, pos, len, copied,
 						  folio);
 
-	copied = block_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	copied = block_write_end(pos, len, copied, folio);
 	/*
 	 * it's important to update i_size while still holding folio lock:
 	 * page writeout could otherwise come in and zero beyond i_size.
@@ -3144,8 +3144,7 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	 * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
 	 * flag, which all that's needed to trigger page writeback.
 	 */
-	copied = block_write_end(NULL, mapping, pos, len, copied,
-			folio, NULL);
+	copied = block_write_end(pos, len, copied, folio);
 	new_i_size = pos + copied;
 
 	/*
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 3729391a18f3..775e8f1f0286 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -923,8 +923,7 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
 	if (srcmap->flags & IOMAP_F_BUFFER_HEAD) {
 		size_t bh_written;
 
-		bh_written = block_write_end(NULL, iter->inode->i_mapping, pos,
-					len, copied, folio, NULL);
+		bh_written = block_write_end(pos, len, copied, folio);
 		WARN_ON_ONCE(bh_written != copied && bh_written != 0);
 		return bh_written == copied;
 	}
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index dd2a425b41f0..19052fc47e9e 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -45,7 +45,7 @@ static void dir_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
 	struct address_space *mapping = folio->mapping;
 	struct inode *dir = mapping->host;
 
-	block_write_end(NULL, mapping, pos, len, len, folio, NULL);
+	block_write_end(pos, len, len, folio);
 
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
diff --git a/fs/nilfs2/dir.c b/fs/nilfs2/dir.c
index 9b7f8e9655a2..6ca3d74be1e1 100644
--- a/fs/nilfs2/dir.c
+++ b/fs/nilfs2/dir.c
@@ -96,7 +96,7 @@ static void nilfs_commit_chunk(struct folio *folio,
 	int err;
 
 	nr_dirty = nilfs_page_count_clean_buffers(folio, from, to);
-	copied = block_write_end(NULL, mapping, pos, len, len, folio, NULL);
+	copied = block_write_end(pos, len, len, folio);
 	if (pos + copied > dir->i_size)
 		i_size_write(dir, pos + copied);
 	if (IS_DIRSYNC(dir))
diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
index 22aecf6e2344..a9c61d0492cb 100644
--- a/fs/nilfs2/recovery.c
+++ b/fs/nilfs2/recovery.c
@@ -560,8 +560,7 @@ static int nilfs_recover_dsync_blocks(struct the_nilfs *nilfs,
 		if (unlikely(err))
 			goto failed_folio;
 
-		block_write_end(NULL, inode->i_mapping, pos, blocksize,
-				blocksize, folio, NULL);
+		block_write_end(pos, blocksize, blocksize, folio);
 
 		folio_unlock(folio);
 		folio_put(folio);
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index 88d0062cfdb9..0388a1bae326 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -48,7 +48,7 @@ static void ufs_commit_chunk(struct folio *folio, loff_t pos, unsigned len)
 	struct inode *dir = mapping->host;
 
 	inode_inc_iversion(dir);
-	block_write_end(NULL, mapping, pos, len, len, folio, NULL);
+	block_write_end(pos, len, len, folio);
 	if (pos+len > dir->i_size) {
 		i_size_write(dir, pos+len);
 		mark_inode_dirty(dir);
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 0029ff880e27..178eb90e9cf3 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -262,9 +262,7 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 		struct folio **foliop, get_block_t *get_block);
 int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block);
-int block_write_end(struct file *, struct address_space *,
-				loff_t, unsigned len, unsigned copied,
-				struct folio *, void *);
+int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *);
 int generic_write_end(struct file *, struct address_space *,
 				loff_t, unsigned len, unsigned copied,
 				struct folio *, void *);
-- 
cgit v1.2.3


From 6241b49540a65a6d5274fa938fd3eb4cbfe2e076 Mon Sep 17 00:00:00 2001
From: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Date: Tue, 24 Jun 2025 10:06:41 +0200
Subject: tty: fix tty_port_tty_*hangup() kernel-doc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The commit below added a new helper, but omitted to move (and add) the
corressponding kernel-doc. Do it now.

Signed-off-by: "Jiri Slaby (SUSE)" <jirislaby@kernel.org>
Fixes: 2b5eac0f8c6e ("tty: introduce and use tty_port_tty_vhangup() helper")
Link: https://lore.kernel.org/all/b23d566c-09dc-7374-cc87-0ad4660e8b2e@linux.intel.com/
Reported-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: linux-doc@vger.kernel.org
Link: https://lore.kernel.org/r/20250624080641.509959-6-jirislaby@kernel.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 Documentation/driver-api/tty/tty_port.rst | 5 +++--
 drivers/tty/tty_port.c                    | 5 -----
 include/linux/tty_port.h                  | 9 +++++++++
 3 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/driver-api/tty/tty_port.rst b/Documentation/driver-api/tty/tty_port.rst
index 5cb90e954fcf..504a353f2682 100644
--- a/Documentation/driver-api/tty/tty_port.rst
+++ b/Documentation/driver-api/tty/tty_port.rst
@@ -42,9 +42,10 @@ TTY Refcounting
 TTY Helpers
 -----------
 
+.. kernel-doc::  include/linux/tty_port.h
+   :identifiers: tty_port_tty_hangup tty_port_tty_vhangup
 .. kernel-doc::  drivers/tty/tty_port.c
-   :identifiers: tty_port_tty_hangup tty_port_tty_wakeup
-
+   :identifiers: tty_port_tty_wakeup
 
 Modem Signals
 -------------
diff --git a/drivers/tty/tty_port.c b/drivers/tty/tty_port.c
index 903eebdbe12d..5b4d5fb99a59 100644
--- a/drivers/tty/tty_port.c
+++ b/drivers/tty/tty_port.c
@@ -391,11 +391,6 @@ void tty_port_hangup(struct tty_port *port)
 }
 EXPORT_SYMBOL(tty_port_hangup);
 
-/**
- * tty_port_tty_hangup - helper to hang up a tty
- * @port: tty port
- * @check_clocal: hang only ttys with %CLOCAL unset?
- */
 void __tty_port_tty_hangup(struct tty_port *port, bool check_clocal, bool async)
 {
 	struct tty_struct *tty = tty_port_tty_get(port);
diff --git a/include/linux/tty_port.h b/include/linux/tty_port.h
index 021f9a8415c0..332ddb93603e 100644
--- a/include/linux/tty_port.h
+++ b/include/linux/tty_port.h
@@ -251,11 +251,20 @@ static inline int tty_port_users(struct tty_port *port)
 	return port->count + port->blocked_open;
 }
 
+/**
+ * tty_port_tty_hangup - helper to hang up a tty asynchronously
+ * @port: tty port
+ * @check_clocal: hang only ttys with %CLOCAL unset?
+ */
 static inline void tty_port_tty_hangup(struct tty_port *port, bool check_clocal)
 {
 	__tty_port_tty_hangup(port, check_clocal, true);
 }
 
+/**
+ * tty_port_tty_vhangup - helper to hang up a tty synchronously
+ * @port: tty port
+ */
 static inline void tty_port_tty_vhangup(struct tty_port *port)
 {
 	__tty_port_tty_hangup(port, false, false);
-- 
cgit v1.2.3


From af4db5a35a4ef7a68046883bfd12468007db38f1 Mon Sep 17 00:00:00 2001
From: RD Babiera <rdbabiera@google.com>
Date: Wed, 18 Jun 2025 22:49:42 +0000
Subject: usb: typec: altmodes/displayport: do not index invalid
 pin_assignments

A poorly implemented DisplayPort Alt Mode port partner can indicate
that its pin assignment capabilities are greater than the maximum
value, DP_PIN_ASSIGN_F. In this case, calls to pin_assignment_show
will cause a BRK exception due to an out of bounds array access.

Prevent for loop in pin_assignment_show from accessing
invalid values in pin_assignments by adding DP_PIN_ASSIGN_MAX
value in typec_dp.h and using i < DP_PIN_ASSIGN_MAX as a loop
condition.

Fixes: 0e3bb7d6894d ("usb: typec: Add driver for DisplayPort alternate mode")
Cc: stable <stable@kernel.org>
Signed-off-by: RD Babiera <rdbabiera@google.com>
Reviewed-by: Badhri Jagan Sridharan <badhri@google.com>
Reviewed-by: Heikki Krogerus <heikki.krogerus@linux.intel.com>
Link: https://lore.kernel.org/r/20250618224943.3263103-2-rdbabiera@google.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/typec/altmodes/displayport.c | 2 +-
 include/linux/usb/typec_dp.h             | 1 +
 2 files changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/usb/typec/altmodes/displayport.c b/drivers/usb/typec/altmodes/displayport.c
index b09b58d7311d..773786129dfb 100644
--- a/drivers/usb/typec/altmodes/displayport.c
+++ b/drivers/usb/typec/altmodes/displayport.c
@@ -677,7 +677,7 @@ static ssize_t pin_assignment_show(struct device *dev,
 
 	assignments = get_current_pin_assignments(dp);
 
-	for (i = 0; assignments; assignments >>= 1, i++) {
+	for (i = 0; assignments && i < DP_PIN_ASSIGN_MAX; assignments >>= 1, i++) {
 		if (assignments & 1) {
 			if (i == cur)
 				len += sprintf(buf + len, "[%s] ",
diff --git a/include/linux/usb/typec_dp.h b/include/linux/usb/typec_dp.h
index f2da264d9c14..acb0ad03bdac 100644
--- a/include/linux/usb/typec_dp.h
+++ b/include/linux/usb/typec_dp.h
@@ -57,6 +57,7 @@ enum {
 	DP_PIN_ASSIGN_D,
 	DP_PIN_ASSIGN_E,
 	DP_PIN_ASSIGN_F, /* Not supported after v1.0b */
+	DP_PIN_ASSIGN_MAX,
 };
 
 /* DisplayPort alt mode specific commands */
-- 
cgit v1.2.3


From a02fd05661d73a8507dd70dd820e9b984490c545 Mon Sep 17 00:00:00 2001
From: Huacai Chen <chenhuacai@loongson.cn>
Date: Tue, 24 Jun 2025 14:29:27 +0800
Subject: PCI: Extend isolated function probing to LoongArch

Like s390 and the jailhouse hypervisor, LoongArch's PCI architecture allows
passing isolated PCI functions to a guest OS instance. So it is possible
that there is a multi-function device without function 0 for the host or
guest.

Allow probing such functions by adding a IS_ENABLED(CONFIG_LOONGARCH) case
in the hypervisor_isolated_pci_functions() helper.

This is similar to commit 189c6c33ff42 ("PCI: Extend isolated function
probing to s390").

Signed-off-by: Huacai Chen <chenhuacai@loongson.cn>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Cc: stable@vger.kernel.org
Link: https://patch.msgid.link/20250624062927.4037734-1-chenhuacai@loongson.cn
---
 include/linux/hypervisor.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/hypervisor.h b/include/linux/hypervisor.h
index 9efbc54e35e5..be5417303ecf 100644
--- a/include/linux/hypervisor.h
+++ b/include/linux/hypervisor.h
@@ -37,6 +37,9 @@ static inline bool hypervisor_isolated_pci_functions(void)
 	if (IS_ENABLED(CONFIG_S390))
 		return true;
 
+	if (IS_ENABLED(CONFIG_LOONGARCH))
+		return true;
+
 	return jailhouse_paravirt();
 }
 
-- 
cgit v1.2.3


From 2ce80bc11ff91913bc6eb31a5876621f090cf5cc Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sat, 14 Jun 2025 02:03:43 +0100
Subject: misc: vmw_vmci: Remove unused vmci_doorbell_notify

vmci_doorbell_notify() was added in 2013 by
commit 83e2ec765be0 ("VMCI: doorbell implementation.")

but has remained unused.

Remove it.

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Link: https://lore.kernel.org/r/20250614010344.636076-3-linux@treblig.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/vmw_vmci/vmci_doorbell.c | 53 -----------------------------------
 include/linux/vmw_vmci_api.h          |  1 -
 2 files changed, 54 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/vmw_vmci/vmci_doorbell.c b/drivers/misc/vmw_vmci/vmci_doorbell.c
index fa8a7fce4481..53eeb9e6cb56 100644
--- a/drivers/misc/vmw_vmci/vmci_doorbell.c
+++ b/drivers/misc/vmw_vmci/vmci_doorbell.c
@@ -257,23 +257,6 @@ static int dbell_unlink(struct vmci_handle handle)
 	return vmci_send_datagram(&unlink_msg.hdr);
 }
 
-/*
- * Notify another guest or the host.  We send a datagram down to the
- * host via the hypervisor with the notification info.
- */
-static int dbell_notify_as_guest(struct vmci_handle handle, u32 priv_flags)
-{
-	struct vmci_doorbell_notify_msg notify_msg;
-
-	notify_msg.hdr.dst = vmci_make_handle(VMCI_HYPERVISOR_CONTEXT_ID,
-					      VMCI_DOORBELL_NOTIFY);
-	notify_msg.hdr.src = VMCI_ANON_SRC_HANDLE;
-	notify_msg.hdr.payload_size = sizeof(notify_msg) - VMCI_DG_HEADERSIZE;
-	notify_msg.handle = handle;
-
-	return vmci_send_datagram(&notify_msg.hdr);
-}
-
 /*
  * Calls the specified callback in a delayed context.
  */
@@ -566,39 +549,3 @@ int vmci_doorbell_destroy(struct vmci_handle handle)
 	return VMCI_SUCCESS;
 }
 EXPORT_SYMBOL_GPL(vmci_doorbell_destroy);
-
-/*
- * vmci_doorbell_notify() - Ring the doorbell (and hide in the bushes).
- * @dst:        The handlle identifying the doorbell resource
- * @priv_flags: Priviledge flags.
- *
- * Generates a notification on the doorbell identified by the
- * handle. For host side generation of notifications, the caller
- * can specify what the privilege of the calling side is.
- */
-int vmci_doorbell_notify(struct vmci_handle dst, u32 priv_flags)
-{
-	int retval;
-	enum vmci_route route;
-	struct vmci_handle src;
-
-	if (vmci_handle_is_invalid(dst) ||
-	    (priv_flags & ~VMCI_PRIVILEGE_ALL_FLAGS))
-		return VMCI_ERROR_INVALID_ARGS;
-
-	src = VMCI_INVALID_HANDLE;
-	retval = vmci_route(&src, &dst, false, &route);
-	if (retval < VMCI_SUCCESS)
-		return retval;
-
-	if (VMCI_ROUTE_AS_HOST == route)
-		return vmci_ctx_notify_dbell(VMCI_HOST_CONTEXT_ID,
-					     dst, priv_flags);
-
-	if (VMCI_ROUTE_AS_GUEST == route)
-		return dbell_notify_as_guest(dst, priv_flags);
-
-	pr_warn("Unknown route (%d) for doorbell\n", route);
-	return VMCI_ERROR_DST_UNREACHABLE;
-}
-EXPORT_SYMBOL_GPL(vmci_doorbell_notify);
diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h
index f28907345c80..28a3b6a9e1ca 100644
--- a/include/linux/vmw_vmci_api.h
+++ b/include/linux/vmw_vmci_api.h
@@ -35,7 +35,6 @@ int vmci_doorbell_create(struct vmci_handle *handle, u32 flags,
 			 u32 priv_flags,
 			 vmci_callback notify_cb, void *client_data);
 int vmci_doorbell_destroy(struct vmci_handle handle);
-int vmci_doorbell_notify(struct vmci_handle handle, u32 priv_flags);
 u32 vmci_get_context_id(void);
 bool vmci_is_context_owner(u32 context_id, kuid_t uid);
 int vmci_register_vsock_callback(vmci_vsock_cb callback);
-- 
cgit v1.2.3


From ea6895f021c0716a280eff576d3f64f549187faa Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sat, 14 Jun 2025 02:03:44 +0100
Subject: misc: vmw_vmci: Remove unused qpair functions

vmci_qpair_dequeue(), vmci_qpair_enqueue() and vmci_qpair_peek()
were added in 2013 by
commit 06164d2b72aa ("VMCI: queue pairs implementation.")

but have remained unused.

Remove them.

(The iov version of those functions is used)

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Link: https://lore.kernel.org/r/20250614010344.636076-4-linux@treblig.org
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/misc/vmw_vmci/vmci_queue_pair.c | 133 --------------------------------
 include/linux/vmw_vmci_api.h            |   6 --
 2 files changed, 139 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/misc/vmw_vmci/vmci_queue_pair.c b/drivers/misc/vmw_vmci/vmci_queue_pair.c
index 73d71c4ec139..b88ac144ad32 100644
--- a/drivers/misc/vmw_vmci/vmci_queue_pair.c
+++ b/drivers/misc/vmw_vmci/vmci_queue_pair.c
@@ -3022,139 +3022,6 @@ s64 vmci_qpair_consume_buf_ready(const struct vmci_qp *qpair)
 }
 EXPORT_SYMBOL_GPL(vmci_qpair_consume_buf_ready);
 
-/*
- * vmci_qpair_enqueue() - Throw data on the queue.
- * @qpair:      Pointer to the queue pair struct.
- * @buf:        Pointer to buffer containing data
- * @buf_size:   Length of buffer.
- * @buf_type:   Buffer type (Unused).
- *
- * This is the client interface for enqueueing data into the queue.
- * Returns number of bytes enqueued or < 0 on error.
- */
-ssize_t vmci_qpair_enqueue(struct vmci_qp *qpair,
-			   const void *buf,
-			   size_t buf_size,
-			   int buf_type)
-{
-	ssize_t result;
-	struct iov_iter from;
-	struct kvec v = {.iov_base = (void *)buf, .iov_len = buf_size};
-
-	if (!qpair || !buf)
-		return VMCI_ERROR_INVALID_ARGS;
-
-	iov_iter_kvec(&from, ITER_SOURCE, &v, 1, buf_size);
-
-	qp_lock(qpair);
-
-	do {
-		result = qp_enqueue_locked(qpair->produce_q,
-					   qpair->consume_q,
-					   qpair->produce_q_size,
-					   &from);
-
-		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
-		    !qp_wait_for_ready_queue(qpair))
-			result = VMCI_ERROR_WOULD_BLOCK;
-
-	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);
-
-	qp_unlock(qpair);
-
-	return result;
-}
-EXPORT_SYMBOL_GPL(vmci_qpair_enqueue);
-
-/*
- * vmci_qpair_dequeue() - Get data from the queue.
- * @qpair:      Pointer to the queue pair struct.
- * @buf:        Pointer to buffer for the data
- * @buf_size:   Length of buffer.
- * @buf_type:   Buffer type (Unused).
- *
- * This is the client interface for dequeueing data from the queue.
- * Returns number of bytes dequeued or < 0 on error.
- */
-ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair,
-			   void *buf,
-			   size_t buf_size,
-			   int buf_type)
-{
-	ssize_t result;
-	struct iov_iter to;
-	struct kvec v = {.iov_base = buf, .iov_len = buf_size};
-
-	if (!qpair || !buf)
-		return VMCI_ERROR_INVALID_ARGS;
-
-	iov_iter_kvec(&to, ITER_DEST, &v, 1, buf_size);
-
-	qp_lock(qpair);
-
-	do {
-		result = qp_dequeue_locked(qpair->produce_q,
-					   qpair->consume_q,
-					   qpair->consume_q_size,
-					   &to, true);
-
-		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
-		    !qp_wait_for_ready_queue(qpair))
-			result = VMCI_ERROR_WOULD_BLOCK;
-
-	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);
-
-	qp_unlock(qpair);
-
-	return result;
-}
-EXPORT_SYMBOL_GPL(vmci_qpair_dequeue);
-
-/*
- * vmci_qpair_peek() - Peek at the data in the queue.
- * @qpair:      Pointer to the queue pair struct.
- * @buf:        Pointer to buffer for the data
- * @buf_size:   Length of buffer.
- * @buf_type:   Buffer type (Unused on Linux).
- *
- * This is the client interface for peeking into a queue.  (I.e.,
- * copy data from the queue without updating the head pointer.)
- * Returns number of bytes dequeued or < 0 on error.
- */
-ssize_t vmci_qpair_peek(struct vmci_qp *qpair,
-			void *buf,
-			size_t buf_size,
-			int buf_type)
-{
-	struct iov_iter to;
-	struct kvec v = {.iov_base = buf, .iov_len = buf_size};
-	ssize_t result;
-
-	if (!qpair || !buf)
-		return VMCI_ERROR_INVALID_ARGS;
-
-	iov_iter_kvec(&to, ITER_DEST, &v, 1, buf_size);
-
-	qp_lock(qpair);
-
-	do {
-		result = qp_dequeue_locked(qpair->produce_q,
-					   qpair->consume_q,
-					   qpair->consume_q_size,
-					   &to, false);
-
-		if (result == VMCI_ERROR_QUEUEPAIR_NOT_READY &&
-		    !qp_wait_for_ready_queue(qpair))
-			result = VMCI_ERROR_WOULD_BLOCK;
-
-	} while (result == VMCI_ERROR_QUEUEPAIR_NOT_READY);
-
-	qp_unlock(qpair);
-
-	return result;
-}
-EXPORT_SYMBOL_GPL(vmci_qpair_peek);
-
 /*
  * vmci_qpair_enquev() - Throw data on the queue using iov.
  * @qpair:      Pointer to the queue pair struct.
diff --git a/include/linux/vmw_vmci_api.h b/include/linux/vmw_vmci_api.h
index 28a3b6a9e1ca..41764a684423 100644
--- a/include/linux/vmw_vmci_api.h
+++ b/include/linux/vmw_vmci_api.h
@@ -60,12 +60,6 @@ s64 vmci_qpair_produce_free_space(const struct vmci_qp *qpair);
 s64 vmci_qpair_produce_buf_ready(const struct vmci_qp *qpair);
 s64 vmci_qpair_consume_free_space(const struct vmci_qp *qpair);
 s64 vmci_qpair_consume_buf_ready(const struct vmci_qp *qpair);
-ssize_t vmci_qpair_enqueue(struct vmci_qp *qpair,
-			   const void *buf, size_t buf_size, int mode);
-ssize_t vmci_qpair_dequeue(struct vmci_qp *qpair,
-			   void *buf, size_t buf_size, int mode);
-ssize_t vmci_qpair_peek(struct vmci_qp *qpair, void *buf, size_t buf_size,
-			int mode);
 ssize_t vmci_qpair_enquev(struct vmci_qp *qpair,
 			  struct msghdr *msg, size_t iov_size, int mode);
 ssize_t vmci_qpair_dequev(struct vmci_qp *qpair,
-- 
cgit v1.2.3


From 7aecbbdf86d3288576a84df360f96b93ceec7ee2 Mon Sep 17 00:00:00 2001
From: Zijun Hu <zijun.hu@oss.qualcomm.com>
Date: Fri, 20 Jun 2025 22:35:18 +0800
Subject: char: misc: Remove redundant forward declarations

Header miscdevice.h includes linux/device.h which has definations for
below two forward declarations directly or indirectly:

struct device;
struct attribute_group;

Remove these redundant forward declarations from miscdevice.h

Signed-off-by: Zijun Hu <zijun.hu@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250620-fix_mischar-v1-1-6c2716bbf1fa@oss.qualcomm.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/miscdevice.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index 69e110c2b86a..3e6deb00fc85 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -73,9 +73,6 @@
 #define RFKILL_MINOR		242
 #define MISC_DYNAMIC_MINOR	255
 
-struct device;
-struct attribute_group;
-
 struct miscdevice {
 	int minor;
 	const char *name;
-- 
cgit v1.2.3


From cb444006a625c60e6d4dd3753863c3c74f96aac3 Mon Sep 17 00:00:00 2001
From: David Dai <david.dai@linux.dev>
Date: Tue, 24 Jun 2025 15:49:06 -0700
Subject: sched_ext, rcu: Eject BPF scheduler on RCU CPU stall panic

For systems using a sched_ext scheduler and has panic_on_rcu_stall
enabled, try kicking out the current scheduler before issuing a panic.

While there are numerous reasons for RCU CPU stalls that are not
directly attributed to the scheduler, deferring the panic gives
sched_ext an opportunity to provide additional debug info when ejecting
the current scheduler. Also, handling the event more gracefully allows
us to potentially recover the system instead of incurring additional
down time.

Suggested-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Signed-off-by: David Dai <david.dai@linux.dev>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/sched/ext.h |  2 ++
 kernel/rcu/tree_stall.h   |  7 +++++++
 kernel/sched/ext.c        | 35 +++++++++++++++++++++++++++++++++++
 3 files changed, 44 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 8b92842776cb..0cf0915572c9 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -206,12 +206,14 @@ struct sched_ext_entity {
 void sched_ext_free(struct task_struct *p);
 void print_scx_info(const char *log_lvl, struct task_struct *p);
 void scx_softlockup(u32 dur_s);
+bool scx_rcu_cpu_stall(void);
 
 #else	/* !CONFIG_SCHED_CLASS_EXT */
 
 static inline void sched_ext_free(struct task_struct *p) {}
 static inline void print_scx_info(const char *log_lvl, struct task_struct *p) {}
 static inline void scx_softlockup(u32 dur_s) {}
+static inline bool scx_rcu_cpu_stall(void) { return false; }
 
 #endif	/* CONFIG_SCHED_CLASS_EXT */
 
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 486c00536207..af61b2d0d311 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -134,6 +134,13 @@ static void panic_on_rcu_stall(void)
 {
 	static int cpu_stall;
 
+	/*
+	 * Attempt to kick out the BPF scheduler if it's installed and defer
+	 * the panic to give the system a chance to recover.
+	 */
+	if (scx_rcu_cpu_stall())
+		return;
+
 	if (++cpu_stall < sysctl_max_rcu_stall_to_panic)
 		return;
 
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index bee98fdcdd01..df5b2c952cf7 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -4672,6 +4672,41 @@ bool scx_allow_ttwu_queue(const struct task_struct *p)
 		p->sched_class != &ext_sched_class;
 }
 
+/**
+ * scx_rcu_cpu_stall - sched_ext RCU CPU stall handler
+ *
+ * While there are various reasons why RCU CPU stalls can occur on a system
+ * that may not be caused by the current BPF scheduler, try kicking out the
+ * current scheduler in an attempt to recover the system to a good state before
+ * issuing panics.
+ */
+bool scx_rcu_cpu_stall(void)
+{
+	struct scx_sched *sch;
+
+	rcu_read_lock();
+
+	sch = rcu_dereference(scx_root);
+	if (unlikely(!sch)) {
+		rcu_read_unlock();
+		return false;
+	}
+
+	switch (scx_enable_state()) {
+	case SCX_ENABLING:
+	case SCX_ENABLED:
+		break;
+	default:
+		rcu_read_unlock();
+		return false;
+	}
+
+	scx_error(sch, "RCU CPU stall detected!");
+	rcu_read_unlock();
+
+	return true;
+}
+
 /**
  * scx_softlockup - sched_ext softlockup handler
  * @dur_s: number of seconds of CPU stuck due to soft lockup
-- 
cgit v1.2.3


From f3128dd6762d71ec92ae888bf582a5f751c3f2e0 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 24 Jun 2025 09:41:08 +0800
Subject: security: Remove unused declaration cap_mmap_file()

Commit 3f4f1f8a1ab7 ("capabilities: remove cap_mmap_file()")
removed the implementation but leave declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Serge Hallyn <serge@hallyn.com>
Signed-off-by: Paul Moore <paul@paul-moore.com>
---
 include/linux/security.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/security.h b/include/linux/security.h
index dba349629229..e8d9f6069f0c 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -193,8 +193,6 @@ int cap_inode_getsecurity(struct mnt_idmap *idmap,
 			  struct inode *inode, const char *name, void **buffer,
 			  bool alloc);
 extern int cap_mmap_addr(unsigned long addr);
-extern int cap_mmap_file(struct file *file, unsigned long reqprot,
-			 unsigned long prot, unsigned long flags);
 extern int cap_task_fix_setuid(struct cred *new, const struct cred *old, int flags);
 extern int cap_task_prctl(int option, unsigned long arg2, unsigned long arg3,
 			  unsigned long arg4, unsigned long arg5);
-- 
cgit v1.2.3


From 52931f55159ea5c27ad4fe66fc0cb8ad75ab795b Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Tue, 17 Jun 2025 11:19:15 +0300
Subject: net/mlx5: fs, add multiple prios to RDMA TRANSPORT steering domain

RDMA TRANSPORT domains were initially limited to a single priority.
This change allows the domains to have multiple priorities, making
it possible to add several rules and control the order in which
they're evaluated.

Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Reviewed-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/b299cbb4c8678a33da6e6b6988b5bf6145c54b88.1750148083.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/fs_core.c | 30 +++++++++++++++++------
 include/linux/mlx5/fs.h                           |  2 +-
 2 files changed, 23 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
index a8046200d376..7f5608081ea0 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c
@@ -3245,34 +3245,48 @@ static int
 init_rdma_transport_rx_root_ns_one(struct mlx5_flow_steering *steering,
 				   int vport_idx)
 {
+	struct mlx5_flow_root_namespace *root_ns;
 	struct fs_prio *prio;
+	int i;
 
 	steering->rdma_transport_rx_root_ns[vport_idx] =
 		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_RX);
 	if (!steering->rdma_transport_rx_root_ns[vport_idx])
 		return -ENOMEM;
 
-	/* create 1 prio*/
-	prio = fs_create_prio(&steering->rdma_transport_rx_root_ns[vport_idx]->ns,
-			      MLX5_RDMA_TRANSPORT_BYPASS_PRIO, 1);
-	return PTR_ERR_OR_ZERO(prio);
+	root_ns = steering->rdma_transport_rx_root_ns[vport_idx];
+
+	for (i = 0; i < MLX5_RDMA_TRANSPORT_BYPASS_PRIO; i++) {
+		prio = fs_create_prio(&root_ns->ns, i, 1);
+		if (IS_ERR(prio))
+			return PTR_ERR(prio);
+	}
+	set_prio_attrs(root_ns);
+	return 0;
 }
 
 static int
 init_rdma_transport_tx_root_ns_one(struct mlx5_flow_steering *steering,
 				   int vport_idx)
 {
+	struct mlx5_flow_root_namespace *root_ns;
 	struct fs_prio *prio;
+	int i;
 
 	steering->rdma_transport_tx_root_ns[vport_idx] =
 		create_root_ns(steering, FS_FT_RDMA_TRANSPORT_TX);
 	if (!steering->rdma_transport_tx_root_ns[vport_idx])
 		return -ENOMEM;
 
-	/* create 1 prio*/
-	prio = fs_create_prio(&steering->rdma_transport_tx_root_ns[vport_idx]->ns,
-			      MLX5_RDMA_TRANSPORT_BYPASS_PRIO, 1);
-	return PTR_ERR_OR_ZERO(prio);
+	root_ns = steering->rdma_transport_tx_root_ns[vport_idx];
+
+	for (i = 0; i < MLX5_RDMA_TRANSPORT_BYPASS_PRIO; i++) {
+		prio = fs_create_prio(&root_ns->ns, i, 1);
+		if (IS_ERR(prio))
+			return PTR_ERR(prio);
+	}
+	set_prio_attrs(root_ns);
+	return 0;
 }
 
 static int init_rdma_transport_rx_root_ns(struct mlx5_flow_steering *steering)
diff --git a/include/linux/mlx5/fs.h b/include/linux/mlx5/fs.h
index 939e58c2f386..86055d55836d 100644
--- a/include/linux/mlx5/fs.h
+++ b/include/linux/mlx5/fs.h
@@ -40,7 +40,7 @@
 
 #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v)
 
-#define MLX5_RDMA_TRANSPORT_BYPASS_PRIO 0
+#define MLX5_RDMA_TRANSPORT_BYPASS_PRIO 16
 #define MLX5_FS_MAX_POOL_SIZE BIT(30)
 
 enum mlx5_flow_destination_type {
-- 
cgit v1.2.3


From ebf8d47121b6ef3f38425a343a72f37c60fd6dbc Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 19 Jun 2025 14:37:17 +0300
Subject: net/mlx5: Small refactor for general object capabilities

Make enum for capability bits of general object types depend on
the type definitions themselves.

Make sure that capabilities in the [64,127] bit range are
properly calculated (type id - 64).

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250619113721.60201-2-mbloch@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 27 ++++++++++++++++-----------
 1 file changed, 16 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 2c09df4ee574..5c8f75605eac 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -12501,17 +12501,6 @@ struct mlx5_ifc_affiliated_event_header_bits {
 	u8         obj_id[0x20];
 };
 
-enum {
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = BIT_ULL(0xc),
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC = BIT_ULL(0x13),
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER = BIT_ULL(0x20),
-	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO = BIT_ULL(0x24),
-};
-
-enum {
-	MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL = BIT_ULL(0x13),
-};
-
 enum {
 	MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY = 0xc,
 	MLX5_GENERAL_OBJECT_TYPES_IPSEC = 0x13,
@@ -12523,6 +12512,22 @@ enum {
 	MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS = 0xff15,
 };
 
+enum {
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_ENCRYPTION_KEY),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_IPSEC =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_IPSEC),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_SAMPLER =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_SAMPLER),
+	MLX5_HCA_CAP_GENERAL_OBJECT_TYPES_FLOW_METER_ASO =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_FLOW_METER_ASO),
+};
+
+enum {
+	MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_RDMA_CTRL - 0x40),
+};
+
 enum {
 	MLX5_IPSEC_OBJECT_ICV_LEN_16B,
 };
-- 
cgit v1.2.3


From 1f6da56679d33c733aaee929fd9af962ad66edbd Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 19 Jun 2025 14:37:18 +0300
Subject: net/mlx5: Add IFC bits for PCIe Congestion Event object

Add definitions for the PCIe Congestion Event object
and the relevant FW command structures.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Reviewed-by: Tariq Toukan <tariqt@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Link: https://patch.msgid.link/20250619113721.60201-3-mbloch@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 5c8f75605eac..0e93f342be09 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -12509,6 +12509,7 @@ enum {
 	MLX5_GENERAL_OBJECT_TYPES_MACSEC = 0x27,
 	MLX5_GENERAL_OBJECT_TYPES_INT_KEK = 0x47,
 	MLX5_GENERAL_OBJECT_TYPES_RDMA_CTRL = 0x53,
+	MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT = 0x58,
 	MLX5_GENERAL_OBJECT_TYPES_FLOW_TABLE_ALIAS = 0xff15,
 };
 
@@ -12526,6 +12527,8 @@ enum {
 enum {
 	MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_RDMA_CTRL =
 		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_RDMA_CTRL - 0x40),
+	MLX5_HCA_CAP_2_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT =
+		BIT_ULL(MLX5_GENERAL_OBJECT_TYPES_PCIE_CONG_EVENT - 0x40),
 };
 
 enum {
@@ -13284,4 +13287,41 @@ struct mlx5_ifc_mrtcq_reg_bits {
 	u8         reserved_at_80[0x180];
 };
 
+struct mlx5_ifc_pcie_cong_event_obj_bits {
+	u8         modify_select_field[0x40];
+
+	u8         inbound_event_en[0x1];
+	u8         outbound_event_en[0x1];
+	u8         reserved_at_42[0x1e];
+
+	u8         reserved_at_60[0x1];
+	u8         inbound_cong_state[0x3];
+	u8         reserved_at_64[0x1];
+	u8         outbound_cong_state[0x3];
+	u8         reserved_at_68[0x18];
+
+	u8         inbound_cong_low_threshold[0x10];
+	u8         inbound_cong_high_threshold[0x10];
+
+	u8         outbound_cong_low_threshold[0x10];
+	u8         outbound_cong_high_threshold[0x10];
+
+	u8         reserved_at_e0[0x340];
+};
+
+struct mlx5_ifc_pcie_cong_event_cmd_in_bits {
+	struct mlx5_ifc_general_obj_in_cmd_hdr_bits hdr;
+	struct mlx5_ifc_pcie_cong_event_obj_bits cong_obj;
+};
+
+struct mlx5_ifc_pcie_cong_event_cmd_out_bits {
+	struct mlx5_ifc_general_obj_out_cmd_hdr_bits hdr;
+	struct mlx5_ifc_pcie_cong_event_obj_bits cong_obj;
+};
+
+enum mlx5e_pcie_cong_event_mod_field {
+	MLX5_PCIE_CONG_EVENT_MOD_EVENT_EN = BIT(0),
+	MLX5_PCIE_CONG_EVENT_MOD_THRESH   = BIT(2),
+};
+
 #endif /* MLX5_IFC_H */
-- 
cgit v1.2.3


From 2642f55d44ce563f227dd9c620eda0dec8d882be Mon Sep 17 00:00:00 2001
From: Peter Griffin <peter.griffin@linaro.org>
Date: Thu, 19 Jun 2025 12:18:16 +0100
Subject: pinctrl: samsung: add support for gs101 wakeup mask programming

gs101 differs to other currently supported SoCs in that it has 3 wakeup
mask registers for the 67 external wakeup interrupt pins in alive and
far_alive.

EINT_WAKEUP_MASK  0x3A80 EINT[31:0]
EINT_WAKEUP_MASK2 0x3A84 EINT[63:32]
EINT_WAKEUP_MASK3 0x3A88 EINT[66:64]

Add gs101 specific callbacks and a dedicated gs101_wkup_irq_chip struct to
handle these differences.

The current wakeup mask with upstream is programmed as
WAKEUP_MASK0[0x3A80] value[0xFFFFFFFF]
WAKEUP_MASK1[0x3A84] value[0xF2FFEFFF]
WAKEUP_MASK2[0x3A88] value[0xFFFFFFFF]

Which corresponds to the following wakeup sources:
gpa7-3  vol down
gpa8-1  vol up
gpa10-1 power
gpa8-2  typec-int

Signed-off-by: Peter Griffin <peter.griffin@linaro.org>
Link: https://lore.kernel.org/r/20250619-gs101-eint-mask-v1-2-89438cfd7499@linaro.org
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski@linaro.org>
---
 drivers/pinctrl/samsung/pinctrl-exynos.c    | 100 ++++++++++++++++++++++++----
 drivers/pinctrl/samsung/pinctrl-samsung.h   |   4 ++
 include/linux/soc/samsung/exynos-regs-pmu.h |   1 +
 3 files changed, 91 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pinctrl/samsung/pinctrl-exynos.c b/drivers/pinctrl/samsung/pinctrl-exynos.c
index f3e1c11abe55..5554768d465f 100644
--- a/drivers/pinctrl/samsung/pinctrl-exynos.c
+++ b/drivers/pinctrl/samsung/pinctrl-exynos.c
@@ -32,18 +32,24 @@
 #include "pinctrl-samsung.h"
 #include "pinctrl-exynos.h"
 
+#define MAX_WAKEUP_REG 3
+
 struct exynos_irq_chip {
 	struct irq_chip chip;
 
 	u32 eint_con;
 	u32 eint_mask;
 	u32 eint_pend;
-	u32 *eint_wake_mask_value;
+	u32 eint_num_wakeup_reg;
 	u32 eint_wake_mask_reg;
 	void (*set_eint_wakeup_mask)(struct samsung_pinctrl_drv_data *drvdata,
 				     struct exynos_irq_chip *irq_chip);
 };
 
+static u32 eint_wake_mask_values[MAX_WAKEUP_REG] = { EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+						     EXYNOS_EINT_WAKEUP_MASK_DISABLED,
+						     EXYNOS_EINT_WAKEUP_MASK_DISABLED};
+
 static inline struct exynos_irq_chip *to_exynos_irq_chip(struct irq_chip *chip)
 {
 	return container_of(chip, struct exynos_irq_chip, chip);
@@ -307,7 +313,7 @@ static const struct exynos_irq_chip exynos_gpio_irq_chip __initconst = {
 	.eint_con = EXYNOS_GPIO_ECON_OFFSET,
 	.eint_mask = EXYNOS_GPIO_EMASK_OFFSET,
 	.eint_pend = EXYNOS_GPIO_EPEND_OFFSET,
-	/* eint_wake_mask_value not used */
+	/* eint_wake_mask_values not used */
 };
 
 static int exynos_eint_irq_map(struct irq_domain *h, unsigned int virq,
@@ -467,10 +473,55 @@ err_domains:
 	return ret;
 }
 
+#define BITS_PER_U32 32
+static int gs101_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
+{
+	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
+	struct samsung_pinctrl_drv_data *d = bank->drvdata;
+	u32 bit, wakeup_reg, shift;
+
+	bit = bank->eint_num + irqd->hwirq;
+	wakeup_reg = bit / BITS_PER_U32;
+	shift = bit - (wakeup_reg * BITS_PER_U32);
+
+	if (!on)
+		eint_wake_mask_values[wakeup_reg] |= BIT_U32(shift);
+	else
+		eint_wake_mask_values[wakeup_reg] &= ~BIT_U32(shift);
+
+	dev_info(d->dev, "wake %s for irq %d\n", str_enabled_disabled(on),
+		 irqd->irq);
+
+	return 0;
+}
+
+static void
+gs101_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
+				   struct exynos_irq_chip *irq_chip)
+{
+	struct regmap *pmu_regs;
+
+	if (!drvdata->retention_ctrl || !drvdata->retention_ctrl->priv) {
+		dev_warn(drvdata->dev,
+			 "No PMU syscon available. Wake-up mask will not be set.\n");
+		return;
+	}
+
+	pmu_regs = drvdata->retention_ctrl->priv;
+
+	dev_dbg(drvdata->dev, "Setting external wakeup interrupt mask:\n");
+
+	for (int i = 0; i < irq_chip->eint_num_wakeup_reg; i++) {
+		dev_dbg(drvdata->dev, "\tWAKEUP_MASK%d[0x%X] value[0x%X]\n",
+			i, irq_chip->eint_wake_mask_reg + i * 4,
+			eint_wake_mask_values[i]);
+		regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg + i * 4,
+			     eint_wake_mask_values[i]);
+	}
+}
+
 static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 {
-	struct irq_chip *chip = irq_data_get_irq_chip(irqd);
-	struct exynos_irq_chip *our_chip = to_exynos_irq_chip(chip);
 	struct samsung_pin_bank *bank = irq_data_get_irq_chip_data(irqd);
 	unsigned long bit = 1UL << (2 * bank->eint_offset + irqd->hwirq);
 
@@ -478,9 +529,9 @@ static int exynos_wkup_irq_set_wake(struct irq_data *irqd, unsigned int on)
 		irqd->irq, bank->name, irqd->hwirq);
 
 	if (!on)
-		*our_chip->eint_wake_mask_value |= bit;
+		eint_wake_mask_values[0] |= bit;
 	else
-		*our_chip->eint_wake_mask_value &= ~bit;
+		eint_wake_mask_values[0] &= ~bit;
 
 	return 0;
 }
@@ -500,10 +551,10 @@ exynos_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
 	pmu_regs = drvdata->retention_ctrl->priv;
 	dev_info(drvdata->dev,
 		 "Setting external wakeup interrupt mask: 0x%x\n",
-		 *irq_chip->eint_wake_mask_value);
+		 eint_wake_mask_values[0]);
 
 	regmap_write(pmu_regs, irq_chip->eint_wake_mask_reg,
-		     *irq_chip->eint_wake_mask_value);
+		     eint_wake_mask_values[0]);
 }
 
 static void
@@ -522,11 +573,10 @@ s5pv210_pinctrl_set_eint_wakeup_mask(struct samsung_pinctrl_drv_data *drvdata,
 
 	clk_base = (void __iomem *) drvdata->retention_ctrl->priv;
 
-	__raw_writel(*irq_chip->eint_wake_mask_value,
+	__raw_writel(eint_wake_mask_values[0],
 		     clk_base + irq_chip->eint_wake_mask_reg);
 }
 
-static u32 eint_wake_mask_value = EXYNOS_EINT_WAKEUP_MASK_DISABLED;
 /*
  * irq_chip for wakeup interrupts
  */
@@ -544,7 +594,7 @@ static const struct exynos_irq_chip s5pv210_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
-	.eint_wake_mask_value = &eint_wake_mask_value,
+	.eint_num_wakeup_reg = 1,
 	/* Only differences with exynos4210_wkup_irq_chip: */
 	.eint_wake_mask_reg = S5PV210_EINT_WAKEUP_MASK,
 	.set_eint_wakeup_mask = s5pv210_pinctrl_set_eint_wakeup_mask,
@@ -564,7 +614,7 @@ static const struct exynos_irq_chip exynos4210_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS_WKUP_EPEND_OFFSET,
-	.eint_wake_mask_value = &eint_wake_mask_value,
+	.eint_num_wakeup_reg = 1,
 	.eint_wake_mask_reg = EXYNOS_EINT_WAKEUP_MASK,
 	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
 };
@@ -583,7 +633,7 @@ static const struct exynos_irq_chip exynos7_wkup_irq_chip __initconst = {
 	.eint_con = EXYNOS7_WKUP_ECON_OFFSET,
 	.eint_mask = EXYNOS7_WKUP_EMASK_OFFSET,
 	.eint_pend = EXYNOS7_WKUP_EPEND_OFFSET,
-	.eint_wake_mask_value = &eint_wake_mask_value,
+	.eint_num_wakeup_reg = 1,
 	.eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK,
 	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
 };
@@ -599,13 +649,31 @@ static const struct exynos_irq_chip exynosautov920_wkup_irq_chip __initconst = {
 		.irq_request_resources = exynos_irq_request_resources,
 		.irq_release_resources = exynos_irq_release_resources,
 	},
-	.eint_wake_mask_value = &eint_wake_mask_value,
+	.eint_num_wakeup_reg = 1,
 	.eint_wake_mask_reg = EXYNOS5433_EINT_WAKEUP_MASK,
 	.set_eint_wakeup_mask = exynos_pinctrl_set_eint_wakeup_mask,
 };
 
+static const struct exynos_irq_chip gs101_wkup_irq_chip __initconst = {
+	.chip = {
+		.name = "gs101_wkup_irq_chip",
+		.irq_unmask = exynos_irq_unmask,
+		.irq_mask = exynos_irq_mask,
+		.irq_ack = exynos_irq_ack,
+		.irq_set_type = exynos_irq_set_type,
+		.irq_set_wake = gs101_wkup_irq_set_wake,
+		.irq_request_resources = exynos_irq_request_resources,
+		.irq_release_resources = exynos_irq_release_resources,
+	},
+	.eint_num_wakeup_reg = 3,
+	.eint_wake_mask_reg = GS101_EINT_WAKEUP_MASK,
+	.set_eint_wakeup_mask = gs101_pinctrl_set_eint_wakeup_mask,
+};
+
 /* list of external wakeup controllers supported */
 static const struct of_device_id exynos_wkup_irq_ids[] = {
+	{ .compatible = "google,gs101-wakeup-eint",
+			.data = &gs101_wkup_irq_chip },
 	{ .compatible = "samsung,s5pv210-wakeup-eint",
 			.data = &s5pv210_wkup_irq_chip },
 	{ .compatible = "samsung,exynos4210-wakeup-eint",
@@ -688,6 +756,7 @@ out:
 	chained_irq_exit(chip, desc);
 }
 
+static int eint_num;
 /*
  * exynos_eint_wkup_init() - setup handling of external wakeup interrupts.
  * @d: driver data of samsung pinctrl driver.
@@ -736,6 +805,9 @@ __init int exynos_eint_wkup_init(struct samsung_pinctrl_drv_data *d)
 			return -ENXIO;
 		}
 
+		bank->eint_num = eint_num;
+		eint_num = eint_num + bank->nr_pins;
+
 		if (!fwnode_property_present(bank->fwnode, "interrupts")) {
 			bank->eint_type = EINT_TYPE_WKUP_MUX;
 			++muxed_banks;
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.h b/drivers/pinctrl/samsung/pinctrl-samsung.h
index fcc57c244d16..1cabcbe1401a 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.h
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.h
@@ -141,6 +141,7 @@ struct samsung_pin_bank_type {
  * @eint_type: type of the external interrupt supported by the bank.
  * @eint_mask: bit mask of pins which support EINT function.
  * @eint_offset: SoC-specific EINT register or interrupt offset of bank.
+ * @eint_num: total number of eint pins.
  * @eint_con_offset: ExynosAuto SoC-specific EINT control register offset of bank.
  * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank.
  * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank.
@@ -156,6 +157,7 @@ struct samsung_pin_bank_data {
 	enum eint_type	eint_type;
 	u32		eint_mask;
 	u32		eint_offset;
+	u32		eint_num;
 	u32		eint_con_offset;
 	u32		eint_mask_offset;
 	u32		eint_pend_offset;
@@ -174,6 +176,7 @@ struct samsung_pin_bank_data {
  * @eint_type: type of the external interrupt supported by the bank.
  * @eint_mask: bit mask of pins which support EINT function.
  * @eint_offset: SoC-specific EINT register or interrupt offset of bank.
+ * @eint_num: total number of eint pins.
  * @eint_con_offset: ExynosAuto SoC-specific EINT register or interrupt offset of bank.
  * @eint_mask_offset: ExynosAuto SoC-specific EINT mask register offset of bank.
  * @eint_pend_offset: ExynosAuto SoC-specific EINT pend register offset of bank.
@@ -201,6 +204,7 @@ struct samsung_pin_bank {
 	enum eint_type	eint_type;
 	u32		eint_mask;
 	u32		eint_offset;
+	u32		eint_num;
 	u32		eint_con_offset;
 	u32		eint_mask_offset;
 	u32		eint_pend_offset;
diff --git a/include/linux/soc/samsung/exynos-regs-pmu.h b/include/linux/soc/samsung/exynos-regs-pmu.h
index 1a2c0e0838f9..938c6db235fb 100644
--- a/include/linux/soc/samsung/exynos-regs-pmu.h
+++ b/include/linux/soc/samsung/exynos-regs-pmu.h
@@ -669,6 +669,7 @@
 #define GS101_CPU_INFORM(cpu)	\
 			(GS101_CPU0_INFORM + (cpu*4))
 #define GS101_SYSTEM_CONFIGURATION				(0x3A00)
+#define GS101_EINT_WAKEUP_MASK					(0x3A80)
 #define GS101_PHY_CTRL_USB20					(0x3EB0)
 #define GS101_PHY_CTRL_USBDP					(0x3EB4)
 
-- 
cgit v1.2.3


From 51a4273dcab39dd1e850870945ccec664352d383 Mon Sep 17 00:00:00 2001
From: Nikunj A Dadhania <nikunj@amd.com>
Date: Tue, 8 Apr 2025 15:02:11 +0530
Subject: KVM: SVM: Add missing member in SNP_LAUNCH_START command structure

The sev_data_snp_launch_start structure should include a 4-byte
desired_tsc_khz field before the gosvw field, which was missed in the
initial implementation. As a result, the structure is 4 bytes shorter than
expected by the firmware, causing the gosvw field to start 4 bytes early.
Fix this by adding the missing 4-byte member for the desired TSC frequency.

Fixes: 3a45dc2b419e ("crypto: ccp: Define the SEV-SNP commands")
Cc: stable@vger.kernel.org
Suggested-by: Tom Lendacky <thomas.lendacky@amd.com>
Reviewed-by: Tom Lendacky <thomas.lendacky@amd.com>
Tested-by: Vaishali Thakkar <vaishali.thakkar@suse.com>
Signed-off-by: Nikunj A Dadhania <nikunj@amd.com>
Link: https://lore.kernel.org/r/20250408093213.57962-3-nikunj@amd.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 include/linux/psp-sev.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/psp-sev.h b/include/linux/psp-sev.h
index 0b3a36bdaa90..0f5f94137f6d 100644
--- a/include/linux/psp-sev.h
+++ b/include/linux/psp-sev.h
@@ -594,6 +594,7 @@ struct sev_data_snp_addr {
  * @imi_en: launch flow is launching an IMI (Incoming Migration Image) for the
  *          purpose of guest-assisted migration.
  * @rsvd: reserved
+ * @desired_tsc_khz: hypervisor desired mean TSC freq in kHz of the guest
  * @gosvw: guest OS-visible workarounds, as defined by hypervisor
  */
 struct sev_data_snp_launch_start {
@@ -603,6 +604,7 @@ struct sev_data_snp_launch_start {
 	u32 ma_en:1;				/* In */
 	u32 imi_en:1;				/* In */
 	u32 rsvd:30;
+	u32 desired_tsc_khz;			/* In */
 	u8 gosvw[16];				/* In */
 } __packed;
 
-- 
cgit v1.2.3


From bbc13ae593e0ea47357ff6e4740c533c16c2ae1e Mon Sep 17 00:00:00 2001
From: Sean Christopherson <seanjc@google.com>
Date: Thu, 22 May 2025 18:17:56 -0700
Subject: VFIO: KVM: x86: Drop kvm_arch_{start,end}_assignment()

Drop kvm_arch_{start,end}_assignment() and all associated code now that
KVM x86 no longer consumes assigned_device_count.  Tracking whether or not
a VFIO-assigned device is formally associated with a VM is fundamentally
flawed, as such an association is optional for general usage, i.e. is prone
to false negatives.  E.g. prior to commit 2edd9cb79fb3 ("kvm: detect
assigned device via irqbypass manager"), device passthrough via VFIO would
fail to enable IRQ bypass if userspace omitted the formal VFIO<=>KVM
binding.

And device drivers that *need* the VFIO<=>KVM connection, e.g. KVM-GT,
shouldn't be relying on generic x86 tracking infrastructure.

Cc: Jim Mattson <jmattson@google.com>
Link: https://lore.kernel.org/r/20250523011756.3243624-6-seanjc@google.com
Signed-off-by: Sean Christopherson <seanjc@google.com>
---
 arch/x86/include/asm/kvm_host.h |  2 --
 arch/x86/kvm/x86.c              | 18 ------------------
 include/linux/kvm_host.h        | 18 ------------------
 virt/kvm/vfio.c                 |  3 ---
 4 files changed, 41 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
index 7262bb11032e..c8ffb23d8441 100644
--- a/arch/x86/include/asm/kvm_host.h
+++ b/arch/x86/include/asm/kvm_host.h
@@ -1381,8 +1381,6 @@ struct kvm_arch {
 
 #define __KVM_HAVE_ARCH_NONCOHERENT_DMA
 	atomic_t noncoherent_dma_count;
-#define __KVM_HAVE_ARCH_ASSIGNED_DEVICE
-	atomic_t assigned_device_count;
 	unsigned long nr_possible_bypass_irqs;
 
 #ifdef CONFIG_KVM_IOAPIC
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index 1508b77622b9..d898b8082e15 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -13438,24 +13438,6 @@ bool kvm_arch_can_dequeue_async_page_present(struct kvm_vcpu *vcpu)
 		return kvm_lapic_enabled(vcpu) && apf_pageready_slot_free(vcpu);
 }
 
-void kvm_arch_start_assignment(struct kvm *kvm)
-{
-	atomic_inc(&kvm->arch.assigned_device_count);
-}
-EXPORT_SYMBOL_GPL(kvm_arch_start_assignment);
-
-void kvm_arch_end_assignment(struct kvm *kvm)
-{
-	atomic_dec(&kvm->arch.assigned_device_count);
-}
-EXPORT_SYMBOL_GPL(kvm_arch_end_assignment);
-
-bool noinstr kvm_arch_has_assigned_device(struct kvm *kvm)
-{
-	return raw_atomic_read(&kvm->arch.assigned_device_count);
-}
-EXPORT_SYMBOL_GPL(kvm_arch_has_assigned_device);
-
 static void kvm_noncoherent_dma_assignment_start_or_stop(struct kvm *kvm)
 {
 	/*
diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h
index fb9ec06aa807..15656b7fba6c 100644
--- a/include/linux/kvm_host.h
+++ b/include/linux/kvm_host.h
@@ -1690,24 +1690,6 @@ static inline bool kvm_arch_has_noncoherent_dma(struct kvm *kvm)
 	return false;
 }
 #endif
-#ifdef __KVM_HAVE_ARCH_ASSIGNED_DEVICE
-void kvm_arch_start_assignment(struct kvm *kvm);
-void kvm_arch_end_assignment(struct kvm *kvm);
-bool kvm_arch_has_assigned_device(struct kvm *kvm);
-#else
-static inline void kvm_arch_start_assignment(struct kvm *kvm)
-{
-}
-
-static inline void kvm_arch_end_assignment(struct kvm *kvm)
-{
-}
-
-static __always_inline bool kvm_arch_has_assigned_device(struct kvm *kvm)
-{
-	return false;
-}
-#endif
 
 static inline struct rcuwait *kvm_arch_vcpu_get_wait(struct kvm_vcpu *vcpu)
 {
diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c
index 196a102e34fb..be50514bbd11 100644
--- a/virt/kvm/vfio.c
+++ b/virt/kvm/vfio.c
@@ -175,7 +175,6 @@ static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd)
 	kvf->file = get_file(filp);
 	list_add_tail(&kvf->node, &kv->file_list);
 
-	kvm_arch_start_assignment(dev->kvm);
 	kvm_vfio_file_set_kvm(kvf->file, dev->kvm);
 	kvm_vfio_update_coherency(dev);
 
@@ -205,7 +204,6 @@ static int kvm_vfio_file_del(struct kvm_device *dev, unsigned int fd)
 			continue;
 
 		list_del(&kvf->node);
-		kvm_arch_end_assignment(dev->kvm);
 #ifdef CONFIG_SPAPR_TCE_IOMMU
 		kvm_spapr_tce_release_vfio_group(dev->kvm, kvf);
 #endif
@@ -336,7 +334,6 @@ static void kvm_vfio_release(struct kvm_device *dev)
 		fput(kvf->file);
 		list_del(&kvf->node);
 		kfree(kvf);
-		kvm_arch_end_assignment(dev->kvm);
 	}
 
 	kvm_vfio_update_coherency(dev);
-- 
cgit v1.2.3


From c8dc579169738a3546f57ecb38e62d3872a3cc04 Mon Sep 17 00:00:00 2001
From: Pratap Nirujogi <pratap.nirujogi@amd.com>
Date: Mon, 9 Jun 2025 11:53:56 -0400
Subject: i2c: amd-isp: Initialize unique adapter name

Initialize unique name for amdisp i2c adapter, which is used
in the platform driver to detect the matching adapter for
i2c_client creation.

Add definition of amdisp i2c adapter name in a new header file
(include/linux/soc/amd/isp4_misc.h) as it is referred in different
driver modules.

Tested-by: Randy Dunlap <rdunlap@infradead.org>
Signed-off-by: Pratap Nirujogi <pratap.nirujogi@amd.com>
Signed-off-by: Andi Shyti <andi.shyti@kernel.org>
Link: https://lore.kernel.org/r/20250609155601.1477055-3-pratap.nirujogi@amd.com
---
 MAINTAINERS                                |  1 +
 drivers/i2c/busses/i2c-designware-amdisp.c |  2 ++
 include/linux/soc/amd/isp4_misc.h          | 12 ++++++++++++
 3 files changed, 15 insertions(+)
 create mode 100644 include/linux/soc/amd/isp4_misc.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index c3f7fbd0d67a..8719f097aae3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24063,6 +24063,7 @@ M:	Bin Du <bin.du@amd.com>
 L:	linux-i2c@vger.kernel.org
 S:	Maintained
 F:	drivers/i2c/busses/i2c-designware-amdisp.c
+F:	include/linux/soc/amd/isp4_misc.h
 
 SYNOPSYS DESIGNWARE MMC/SD/SDIO DRIVER
 M:	Jaehoon Chung <jh80.chung@samsung.com>
diff --git a/drivers/i2c/busses/i2c-designware-amdisp.c b/drivers/i2c/busses/i2c-designware-amdisp.c
index ad6f08338124..450793d5f839 100644
--- a/drivers/i2c/busses/i2c-designware-amdisp.c
+++ b/drivers/i2c/busses/i2c-designware-amdisp.c
@@ -8,6 +8,7 @@
 #include <linux/module.h>
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
+#include <linux/soc/amd/isp4_misc.h>
 
 #include "i2c-designware-core.h"
 
@@ -62,6 +63,7 @@ static int amd_isp_dw_i2c_plat_probe(struct platform_device *pdev)
 
 	adap = &isp_i2c_dev->adapter;
 	adap->owner = THIS_MODULE;
+	scnprintf(adap->name, sizeof(adap->name), AMDISP_I2C_ADAP_NAME);
 	ACPI_COMPANION_SET(&adap->dev, ACPI_COMPANION(&pdev->dev));
 	adap->dev.of_node = pdev->dev.of_node;
 	/* use dynamically allocated adapter id */
diff --git a/include/linux/soc/amd/isp4_misc.h b/include/linux/soc/amd/isp4_misc.h
new file mode 100644
index 000000000000..6738796986a7
--- /dev/null
+++ b/include/linux/soc/amd/isp4_misc.h
@@ -0,0 +1,12 @@
+// SPDX-License-Identifier: GPL-2.0+
+
+/*
+ * Copyright (C) 2025 Advanced Micro Devices, Inc.
+ */
+
+#ifndef __SOC_ISP4_MISC_H
+#define __SOC_ISP4_MISC_H
+
+#define AMDISP_I2C_ADAP_NAME "AMDISP DesignWare I2C adapter"
+
+#endif
-- 
cgit v1.2.3


From aced132599b3c8884c050218d4c48eef203678f6 Mon Sep 17 00:00:00 2001
From: Song Liu <song@kernel.org>
Date: Wed, 25 Jun 2025 09:40:24 -0700
Subject: bpf: Add range tracking for BPF_NEG

Add range tracking for instruction BPF_NEG. Without this logic, a trivial
program like the following will fail

    volatile bool found_value_b;
    SEC("lsm.s/socket_connect")
    int BPF_PROG(test_socket_connect)
    {
        if (!found_value_b)
                return -1;
        return 0;
    }

with verifier log:

"At program exit the register R0 has smin=0 smax=4294967295 should have
been in [-4095, 0]".

This is because range information is lost in BPF_NEG:

0: R1=ctx() R10=fp0
; if (!found_value_b) @ xxxx.c:24
0: (18) r1 = 0xffa00000011e7048       ; R1_w=map_value(...)
2: (71) r0 = *(u8 *)(r1 +0)           ; R0_w=scalar(smin32=0,smax=255)
3: (a4) w0 ^= 1                       ; R0_w=scalar(smin32=0,smax=255)
4: (84) w0 = -w0                      ; R0_w=scalar(range info lost)

Note that, the log above is manually modified to highlight relevant bits.

Fix this by maintaining proper range information with BPF_NEG, so that
the verifier will know:

4: (84) w0 = -w0                      ; R0_w=scalar(smin32=-255,smax=0)

Also updated selftests based on the expected behavior.

Signed-off-by: Song Liu <song@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250625164025.3310203-2-song@kernel.org
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/tnum.h                               |  2 ++
 kernel/bpf/tnum.c                                  |  5 +++++
 kernel/bpf/verifier.c                              | 17 ++++++++++++++++-
 .../bpf/progs/verifier_bounds_deduction.c          | 11 +++++++----
 .../selftests/bpf/progs/verifier_value_ptr_arith.c | 22 ++++++++++++++++------
 5 files changed, 46 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index 3c13240077b8..57ed3035cc30 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -40,6 +40,8 @@ struct tnum tnum_arshift(struct tnum a, u8 min_shift, u8 insn_bitness);
 struct tnum tnum_add(struct tnum a, struct tnum b);
 /* Subtract two tnums, return @a - @b */
 struct tnum tnum_sub(struct tnum a, struct tnum b);
+/* Neg of a tnum, return  0 - @a */
+struct tnum tnum_neg(struct tnum a);
 /* Bitwise-AND, return @a & @b */
 struct tnum tnum_and(struct tnum a, struct tnum b);
 /* Bitwise-OR, return @a | @b */
diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c
index 9dbc31b25e3d..fa353c5d550f 100644
--- a/kernel/bpf/tnum.c
+++ b/kernel/bpf/tnum.c
@@ -83,6 +83,11 @@ struct tnum tnum_sub(struct tnum a, struct tnum b)
 	return TNUM(dv & ~mu, mu);
 }
 
+struct tnum tnum_neg(struct tnum a)
+{
+	return tnum_sub(TNUM(0, 0), a);
+}
+
 struct tnum tnum_and(struct tnum a, struct tnum b)
 {
 	u64 alpha, beta, v;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index f403524bd215..2ff22ef42348 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -15182,6 +15182,7 @@ static bool is_safe_to_compute_dst_reg_range(struct bpf_insn *insn,
 	switch (BPF_OP(insn->code)) {
 	case BPF_ADD:
 	case BPF_SUB:
+	case BPF_NEG:
 	case BPF_AND:
 	case BPF_XOR:
 	case BPF_OR:
@@ -15250,6 +15251,13 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env,
 		scalar_min_max_sub(dst_reg, &src_reg);
 		dst_reg->var_off = tnum_sub(dst_reg->var_off, src_reg.var_off);
 		break;
+	case BPF_NEG:
+		env->fake_reg[0] = *dst_reg;
+		__mark_reg_known(dst_reg, 0);
+		scalar32_min_max_sub(dst_reg, &env->fake_reg[0]);
+		scalar_min_max_sub(dst_reg, &env->fake_reg[0]);
+		dst_reg->var_off = tnum_neg(env->fake_reg[0].var_off);
+		break;
 	case BPF_MUL:
 		dst_reg->var_off = tnum_mul(dst_reg->var_off, src_reg.var_off);
 		scalar32_min_max_mul(dst_reg, &src_reg);
@@ -15473,7 +15481,14 @@ static int check_alu_op(struct bpf_verifier_env *env, struct bpf_insn *insn)
 		}
 
 		/* check dest operand */
-		err = check_reg_arg(env, insn->dst_reg, DST_OP);
+		if (opcode == BPF_NEG) {
+			err = check_reg_arg(env, insn->dst_reg, DST_OP_NO_MARK);
+			err = err ?: adjust_scalar_min_max_vals(env, insn,
+							 &regs[insn->dst_reg],
+							 regs[insn->dst_reg]);
+		} else {
+			err = check_reg_arg(env, insn->dst_reg, DST_OP);
+		}
 		if (err)
 			return err;
 
diff --git a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c
index c506afbdd936..260a6df264e3 100644
--- a/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c
+++ b/tools/testing/selftests/bpf/progs/verifier_bounds_deduction.c
@@ -159,13 +159,16 @@ __failure_unpriv
 __naked void deducing_bounds_from_const_10(void)
 {
 	asm volatile ("					\
+	r6 = r1;					\
 	r0 = 0;						\
 	if r0 s<= 0 goto l0_%=;				\
-l0_%=:	/* Marks reg as unknown. */			\
-	r0 = -r0;					\
-	r0 -= r1;					\
+l0_%=: /* Marks r0 as unknown. */			\
+	call %[bpf_get_prandom_u32];			\
+	r0 -= r6;					\
 	exit;						\
-"	::: __clobber_all);
+"	:
+	: __imm(bpf_get_prandom_u32)
+	: __clobber_all);
 }
 
 char _license[] SEC("license") = "GPL";
diff --git a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
index fcea9819e359..af7938ce56cb 100644
--- a/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
+++ b/tools/testing/selftests/bpf/progs/verifier_value_ptr_arith.c
@@ -231,6 +231,10 @@ __retval(1)
 __naked void ptr_unknown_vs_unknown_lt(void)
 {
 	asm volatile ("					\
+	r8 = r1;					\
+	call %[bpf_get_prandom_u32];			\
+	r9 = r0;					\
+	r1 = r8;					\
 	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
 	r1 = 0;						\
 	*(u64*)(r10 - 8) = r1;				\
@@ -245,11 +249,11 @@ l1_%=:	call %[bpf_map_lookup_elem];			\
 	r4 = *(u8*)(r0 + 0);				\
 	if r4 == 1 goto l3_%=;				\
 	r1 = 6;						\
-	r1 = -r1;					\
+	r1 = r9;					\
 	r1 &= 0x3;					\
 	goto l4_%=;					\
 l3_%=:	r1 = 6;						\
-	r1 = -r1;					\
+	r1 = r9;					\
 	r1 &= 0x7;					\
 l4_%=:	r1 += r0;					\
 	r0 = *(u8*)(r1 + 0);				\
@@ -259,7 +263,8 @@ l2_%=:	r0 = 1;						\
 	: __imm(bpf_map_lookup_elem),
 	  __imm_addr(map_array_48b),
 	  __imm_addr(map_hash_16b),
-	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)),
+	  __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
 
@@ -271,6 +276,10 @@ __retval(1)
 __naked void ptr_unknown_vs_unknown_gt(void)
 {
 	asm volatile ("					\
+	r8 = r1;					\
+	call %[bpf_get_prandom_u32];			\
+	r9 = r0;					\
+	r1 = r8;					\
 	r0 = *(u32*)(r1 + %[__sk_buff_len]);		\
 	r1 = 0;						\
 	*(u64*)(r10 - 8) = r1;				\
@@ -285,11 +294,11 @@ l1_%=:	call %[bpf_map_lookup_elem];			\
 	r4 = *(u8*)(r0 + 0);				\
 	if r4 == 1 goto l3_%=;				\
 	r1 = 6;						\
-	r1 = -r1;					\
+	r1 = r9;					\
 	r1 &= 0x7;					\
 	goto l4_%=;					\
 l3_%=:	r1 = 6;						\
-	r1 = -r1;					\
+	r1 = r9;					\
 	r1 &= 0x3;					\
 l4_%=:	r1 += r0;					\
 	r0 = *(u8*)(r1 + 0);				\
@@ -299,7 +308,8 @@ l2_%=:	r0 = 1;						\
 	: __imm(bpf_map_lookup_elem),
 	  __imm_addr(map_array_48b),
 	  __imm_addr(map_hash_16b),
-	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len))
+	  __imm_const(__sk_buff_len, offsetof(struct __sk_buff, len)),
+	  __imm(bpf_get_prandom_u32)
 	: __clobber_all);
 }
 
-- 
cgit v1.2.3


From d83caf7c8dad96051267c18786b7bc446b537f3c Mon Sep 17 00:00:00 2001
From: Anton Protopopov <a.s.protopopov@gmail.com>
Date: Wed, 25 Jun 2025 15:16:21 +0000
Subject: bpf: add btf_type_is_i{32,64} helpers

There are places in BPF code which check if a BTF type is an integer
of particular size. This code can be made simpler by using helpers.
Add new btf_type_is_i{32,64} helpers, and simplify code in a few
files. (Suggested by Eduard for a patch which copy-pasted such a
check [1].)

  v1 -> v2:
    * export less generic helpers (Eduard)
    * make subject less generic than in [v1] (Eduard)

[1] https://lore.kernel.org/bpf/7edb47e73baa46705119a23c6bf4af26517a640f.camel@gmail.com/
[v1] https://lore.kernel.org/bpf/20250624193655.733050-1-a.s.protopopov@gmail.com/

Suggested-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Anton Protopopov <a.s.protopopov@gmail.com>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250625151621.1000584-1-a.s.protopopov@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h            |  2 ++
 kernel/bpf/arraymap.c          | 11 +++--------
 kernel/bpf/bpf_local_storage.c |  8 +-------
 kernel/bpf/btf.c               | 41 ++++++++++++++++++++++++++---------------
 kernel/bpf/local_storage.c     |  9 +--------
 5 files changed, 33 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index b2983706292f..a40beb9cf160 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -221,6 +221,8 @@ bool btf_is_vmlinux(const struct btf *btf);
 struct module *btf_try_get_module(const struct btf *btf);
 u32 btf_nr_types(const struct btf *btf);
 struct btf *btf_base_btf(const struct btf *btf);
+bool btf_type_is_i32(const struct btf_type *t);
+bool btf_type_is_i64(const struct btf_type *t);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index eb28c0f219ee..3d080916faf9 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -530,8 +530,6 @@ static int array_map_check_btf(const struct bpf_map *map,
 			       const struct btf_type *key_type,
 			       const struct btf_type *value_type)
 {
-	u32 int_data;
-
 	/* One exception for keyless BTF: .bss/.data/.rodata map */
 	if (btf_type_is_void(key_type)) {
 		if (map->map_type != BPF_MAP_TYPE_ARRAY ||
@@ -544,14 +542,11 @@ static int array_map_check_btf(const struct bpf_map *map,
 		return 0;
 	}
 
-	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
-		return -EINVAL;
-
-	int_data = *(u32 *)(key_type + 1);
-	/* bpf array can only take a u32 key. This check makes sure
+	/*
+	 * Bpf array can only take a u32 key. This check makes sure
 	 * that the btf matches the attr used during map_create.
 	 */
-	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+	if (!btf_type_is_i32(key_type))
 		return -EINVAL;
 
 	return 0;
diff --git a/kernel/bpf/bpf_local_storage.c b/kernel/bpf/bpf_local_storage.c
index fa56c30833ff..b931fbceb54d 100644
--- a/kernel/bpf/bpf_local_storage.c
+++ b/kernel/bpf/bpf_local_storage.c
@@ -722,13 +722,7 @@ int bpf_local_storage_map_check_btf(const struct bpf_map *map,
 				    const struct btf_type *key_type,
 				    const struct btf_type *value_type)
 {
-	u32 int_data;
-
-	if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
-		return -EINVAL;
-
-	int_data = *(u32 *)(key_type + 1);
-	if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data))
+	if (!btf_type_is_i32(key_type))
 		return -EINVAL;
 
 	return 0;
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 682acb1ed234..05fd64a371af 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -858,26 +858,37 @@ const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id)
 EXPORT_SYMBOL_GPL(btf_type_by_id);
 
 /*
- * Regular int is not a bit field and it must be either
- * u8/u16/u32/u64 or __int128.
+ * Check that the type @t is a regular int. This means that @t is not
+ * a bit field and it has the same size as either of u8/u16/u32/u64
+ * or __int128. If @expected_size is not zero, then size of @t should
+ * be the same. A caller should already have checked that the type @t
+ * is an integer.
  */
+static bool __btf_type_int_is_regular(const struct btf_type *t, size_t expected_size)
+{
+	u32 int_data = btf_type_int(t);
+	u8 nr_bits = BTF_INT_BITS(int_data);
+	u8 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
+
+	return BITS_PER_BYTE_MASKED(nr_bits) == 0 &&
+	       BTF_INT_OFFSET(int_data) == 0 &&
+	       (nr_bytes <= 16 && is_power_of_2(nr_bytes)) &&
+	       (expected_size == 0 || nr_bytes == expected_size);
+}
+
 static bool btf_type_int_is_regular(const struct btf_type *t)
 {
-	u8 nr_bits, nr_bytes;
-	u32 int_data;
+	return __btf_type_int_is_regular(t, 0);
+}
 
-	int_data = btf_type_int(t);
-	nr_bits = BTF_INT_BITS(int_data);
-	nr_bytes = BITS_ROUNDUP_BYTES(nr_bits);
-	if (BITS_PER_BYTE_MASKED(nr_bits) ||
-	    BTF_INT_OFFSET(int_data) ||
-	    (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) &&
-	     nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64) &&
-	     nr_bytes != (2 * sizeof(u64)))) {
-		return false;
-	}
+bool btf_type_is_i32(const struct btf_type *t)
+{
+	return btf_type_is_int(t) && __btf_type_int_is_regular(t, 4);
+}
 
-	return true;
+bool btf_type_is_i64(const struct btf_type *t)
+{
+	return btf_type_is_int(t) && __btf_type_int_is_regular(t, 8);
 }
 
 /*
diff --git a/kernel/bpf/local_storage.c b/kernel/bpf/local_storage.c
index 3969eb0382af..632d51b05fe9 100644
--- a/kernel/bpf/local_storage.c
+++ b/kernel/bpf/local_storage.c
@@ -394,17 +394,10 @@ static int cgroup_storage_check_btf(const struct bpf_map *map,
 		if (!btf_member_is_reg_int(btf, key_type, m, offset, size))
 			return -EINVAL;
 	} else {
-		u32 int_data;
-
 		/*
 		 * Key is expected to be u64, which stores the cgroup_inode_id
 		 */
-
-		if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT)
-			return -EINVAL;
-
-		int_data = *(u32 *)(key_type + 1);
-		if (BTF_INT_BITS(int_data) != 64 || BTF_INT_OFFSET(int_data))
+		if (!btf_type_is_i64(key_type))
 			return -EINVAL;
 	}
 
-- 
cgit v1.2.3


From bfb4fb77f9a8ce33ce357224569eae5564eec573 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Mon, 23 Jun 2025 08:31:47 -0700
Subject: team: replace team lock with rtnl lock

syszbot reports various ordering issues for lower instance locks and
team lock. Switch to using rtnl lock for protecting team device,
similar to bonding. Based on the patch by Tetsuo Handa.

Cc: Jiri Pirko <jiri@resnulli.us>
Cc: Tetsuo Handa <penguin-kernel@I-love.SAKURA.ne.jp>
Reported-by: syzbot+705c61d60b091ef42c04@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=705c61d60b091ef42c04
Reported-by: syzbot+71fd22ae4b81631e22fd@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=71fd22ae4b81631e22fd
Fixes: 6b1d3c5f675c ("team: grab team lock during team_change_rx_flags")
Link: https://lkml.kernel.org/r/ZoZ2RH9BcahEB9Sb@nanopsycho.orion
Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250623153147.3413631-1-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/team/team_core.c              | 96 ++++++++++++++-----------------
 drivers/net/team/team_mode_activebackup.c |  3 +-
 drivers/net/team/team_mode_loadbalance.c  | 13 ++---
 include/linux/if_team.h                   |  3 -
 4 files changed, 50 insertions(+), 65 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/team/team_core.c b/drivers/net/team/team_core.c
index 8bc56186b2a3..17f07eb0ee52 100644
--- a/drivers/net/team/team_core.c
+++ b/drivers/net/team/team_core.c
@@ -933,7 +933,7 @@ static bool team_port_find(const struct team *team,
  * Enable/disable port by adding to enabled port hashlist and setting
  * port->index (Might be racy so reader could see incorrect ifindex when
  * processing a flying packet, but that is not a problem). Write guarded
- * by team->lock.
+ * by RTNL.
  */
 static void team_port_enable(struct team *team,
 			     struct team_port *port)
@@ -1660,8 +1660,6 @@ static int team_init(struct net_device *dev)
 		goto err_options_register;
 	netif_carrier_off(dev);
 
-	lockdep_register_key(&team->team_lock_key);
-	__mutex_init(&team->lock, "team->team_lock_key", &team->team_lock_key);
 	netdev_lockdep_set_classes(dev);
 
 	return 0;
@@ -1682,7 +1680,8 @@ static void team_uninit(struct net_device *dev)
 	struct team_port *port;
 	struct team_port *tmp;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry_safe(port, tmp, &team->port_list, list)
 		team_port_del(team, port->dev);
 
@@ -1691,9 +1690,7 @@ static void team_uninit(struct net_device *dev)
 	team_mcast_rejoin_fini(team);
 	team_notify_peers_fini(team);
 	team_queue_override_fini(team);
-	mutex_unlock(&team->lock);
 	netdev_change_features(dev);
-	lockdep_unregister_key(&team->team_lock_key);
 }
 
 static void team_destructor(struct net_device *dev)
@@ -1778,7 +1775,8 @@ static void team_change_rx_flags(struct net_device *dev, int change)
 	struct team_port *port;
 	int inc;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry(port, &team->port_list, list) {
 		if (change & IFF_PROMISC) {
 			inc = dev->flags & IFF_PROMISC ? 1 : -1;
@@ -1789,7 +1787,6 @@ static void team_change_rx_flags(struct net_device *dev, int change)
 			dev_set_allmulti(port->dev, inc);
 		}
 	}
-	mutex_unlock(&team->lock);
 }
 
 static void team_set_rx_mode(struct net_device *dev)
@@ -1811,14 +1808,14 @@ static int team_set_mac_address(struct net_device *dev, void *p)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
+	ASSERT_RTNL();
+
 	if (dev->type == ARPHRD_ETHER && !is_valid_ether_addr(addr->sa_data))
 		return -EADDRNOTAVAIL;
 	dev_addr_set(dev, addr->sa_data);
-	mutex_lock(&team->lock);
 	list_for_each_entry(port, &team->port_list, list)
 		if (team->ops.port_change_dev_addr)
 			team->ops.port_change_dev_addr(team, port);
-	mutex_unlock(&team->lock);
 	return 0;
 }
 
@@ -1828,11 +1825,8 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 	struct team_port *port;
 	int err;
 
-	/*
-	 * Alhough this is reader, it's guarded by team lock. It's not possible
-	 * to traverse list in reverse under rcu_read_lock
-	 */
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	team->port_mtu_change_allowed = true;
 	list_for_each_entry(port, &team->port_list, list) {
 		err = dev_set_mtu(port->dev, new_mtu);
@@ -1843,7 +1837,6 @@ static int team_change_mtu(struct net_device *dev, int new_mtu)
 		}
 	}
 	team->port_mtu_change_allowed = false;
-	mutex_unlock(&team->lock);
 
 	WRITE_ONCE(dev->mtu, new_mtu);
 
@@ -1853,7 +1846,6 @@ unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		dev_set_mtu(port->dev, dev->mtu);
 	team->port_mtu_change_allowed = false;
-	mutex_unlock(&team->lock);
 
 	return err;
 }
@@ -1903,24 +1895,19 @@ static int team_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team_port *port;
 	int err;
 
-	/*
-	 * Alhough this is reader, it's guarded by team lock. It's not possible
-	 * to traverse list in reverse under rcu_read_lock
-	 */
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry(port, &team->port_list, list) {
 		err = vlan_vid_add(port->dev, proto, vid);
 		if (err)
 			goto unwind;
 	}
-	mutex_unlock(&team->lock);
 
 	return 0;
 
 unwind:
 	list_for_each_entry_continue_reverse(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	mutex_unlock(&team->lock);
 
 	return err;
 }
@@ -1930,10 +1917,10 @@ static int team_vlan_rx_kill_vid(struct net_device *dev, __be16 proto, u16 vid)
 	struct team *team = netdev_priv(dev);
 	struct team_port *port;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry(port, &team->port_list, list)
 		vlan_vid_del(port->dev, proto, vid);
-	mutex_unlock(&team->lock);
 
 	return 0;
 }
@@ -1955,9 +1942,9 @@ static void team_netpoll_cleanup(struct net_device *dev)
 {
 	struct team *team = netdev_priv(dev);
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	__team_netpoll_cleanup(team);
-	mutex_unlock(&team->lock);
 }
 
 static int team_netpoll_setup(struct net_device *dev)
@@ -1966,7 +1953,8 @@ static int team_netpoll_setup(struct net_device *dev)
 	struct team_port *port;
 	int err = 0;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	list_for_each_entry(port, &team->port_list, list) {
 		err = __team_port_enable_netpoll(port);
 		if (err) {
@@ -1974,7 +1962,6 @@ static int team_netpoll_setup(struct net_device *dev)
 			break;
 		}
 	}
-	mutex_unlock(&team->lock);
 	return err;
 }
 #endif
@@ -1985,9 +1972,9 @@ static int team_add_slave(struct net_device *dev, struct net_device *port_dev,
 	struct team *team = netdev_priv(dev);
 	int err;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	err = team_port_add(team, port_dev, extack);
-	mutex_unlock(&team->lock);
 
 	if (!err)
 		netdev_change_features(dev);
@@ -2000,18 +1987,13 @@ static int team_del_slave(struct net_device *dev, struct net_device *port_dev)
 	struct team *team = netdev_priv(dev);
 	int err;
 
-	mutex_lock(&team->lock);
+	ASSERT_RTNL();
+
 	err = team_port_del(team, port_dev);
-	mutex_unlock(&team->lock);
 
 	if (err)
 		return err;
 
-	if (netif_is_team_master(port_dev)) {
-		lockdep_unregister_key(&team->team_lock_key);
-		lockdep_register_key(&team->team_lock_key);
-		lockdep_set_class(&team->lock, &team->team_lock_key);
-	}
 	netdev_change_features(dev);
 
 	return err;
@@ -2304,9 +2286,10 @@ err_msg_put:
 static struct team *team_nl_team_get(struct genl_info *info)
 {
 	struct net *net = genl_info_net(info);
-	int ifindex;
 	struct net_device *dev;
-	struct team *team;
+	int ifindex;
+
+	ASSERT_RTNL();
 
 	if (!info->attrs[TEAM_ATTR_TEAM_IFINDEX])
 		return NULL;
@@ -2318,14 +2301,11 @@ static struct team *team_nl_team_get(struct genl_info *info)
 		return NULL;
 	}
 
-	team = netdev_priv(dev);
-	mutex_lock(&team->lock);
-	return team;
+	return netdev_priv(dev);
 }
 
 static void team_nl_team_put(struct team *team)
 {
-	mutex_unlock(&team->lock);
 	dev_put(team->dev);
 }
 
@@ -2515,9 +2495,13 @@ int team_nl_options_get_doit(struct sk_buff *skb, struct genl_info *info)
 	int err;
 	LIST_HEAD(sel_opt_inst_list);
 
+	rtnl_lock();
+
 	team = team_nl_team_get(info);
-	if (!team)
-		return -EINVAL;
+	if (!team) {
+		err = -EINVAL;
+		goto rtnl_unlock;
+	}
 
 	list_for_each_entry(opt_inst, &team->option_inst_list, list)
 		list_add_tail(&opt_inst->tmp_list, &sel_opt_inst_list);
@@ -2527,6 +2511,9 @@ int team_nl_options_get_doit(struct sk_buff *skb, struct genl_info *info)
 
 	team_nl_team_put(team);
 
+rtnl_unlock:
+	rtnl_unlock();
+
 	return err;
 }
 
@@ -2805,15 +2792,22 @@ int team_nl_port_list_get_doit(struct sk_buff *skb,
 	struct team *team;
 	int err;
 
+	rtnl_lock();
+
 	team = team_nl_team_get(info);
-	if (!team)
-		return -EINVAL;
+	if (!team) {
+		err = -EINVAL;
+		goto rtnl_unlock;
+	}
 
 	err = team_nl_send_port_list_get(team, info->snd_portid, info->snd_seq,
 					 NLM_F_ACK, team_nl_send_unicast, NULL);
 
 	team_nl_team_put(team);
 
+rtnl_unlock:
+	rtnl_unlock();
+
 	return err;
 }
 
@@ -2961,11 +2955,9 @@ static void __team_port_change_port_removed(struct team_port *port)
 
 static void team_port_change_check(struct team_port *port, bool linkup)
 {
-	struct team *team = port->team;
+	ASSERT_RTNL();
 
-	mutex_lock(&team->lock);
 	__team_port_change_check(port, linkup);
-	mutex_unlock(&team->lock);
 }
 
 
diff --git a/drivers/net/team/team_mode_activebackup.c b/drivers/net/team/team_mode_activebackup.c
index e0f599e2a51d..1c3336c7a1b2 100644
--- a/drivers/net/team/team_mode_activebackup.c
+++ b/drivers/net/team/team_mode_activebackup.c
@@ -67,8 +67,7 @@ static void ab_active_port_get(struct team *team, struct team_gsetter_ctx *ctx)
 {
 	struct team_port *active_port;
 
-	active_port = rcu_dereference_protected(ab_priv(team)->active_port,
-						lockdep_is_held(&team->lock));
+	active_port = rtnl_dereference(ab_priv(team)->active_port);
 	if (active_port)
 		ctx->data.u32_val = active_port->dev->ifindex;
 	else
diff --git a/drivers/net/team/team_mode_loadbalance.c b/drivers/net/team/team_mode_loadbalance.c
index 00f8989c29c0..b14538bde2f8 100644
--- a/drivers/net/team/team_mode_loadbalance.c
+++ b/drivers/net/team/team_mode_loadbalance.c
@@ -301,8 +301,7 @@ static int lb_bpf_func_set(struct team *team, struct team_gsetter_ctx *ctx)
 	if (lb_priv->ex->orig_fprog) {
 		/* Clear old filter data */
 		__fprog_destroy(lb_priv->ex->orig_fprog);
-		orig_fp = rcu_dereference_protected(lb_priv->fp,
-						lockdep_is_held(&team->lock));
+		orig_fp = rtnl_dereference(lb_priv->fp);
 	}
 
 	rcu_assign_pointer(lb_priv->fp, fp);
@@ -324,8 +323,7 @@ static void lb_bpf_func_free(struct team *team)
 		return;
 
 	__fprog_destroy(lb_priv->ex->orig_fprog);
-	fp = rcu_dereference_protected(lb_priv->fp,
-				       lockdep_is_held(&team->lock));
+	fp = rtnl_dereference(lb_priv->fp);
 	bpf_prog_destroy(fp);
 }
 
@@ -335,8 +333,7 @@ static void lb_tx_method_get(struct team *team, struct team_gsetter_ctx *ctx)
 	lb_select_tx_port_func_t *func;
 	char *name;
 
-	func = rcu_dereference_protected(lb_priv->select_tx_port_func,
-					 lockdep_is_held(&team->lock));
+	func = rtnl_dereference(lb_priv->select_tx_port_func);
 	name = lb_select_tx_port_get_name(func);
 	BUG_ON(!name);
 	ctx->data.str_val = name;
@@ -478,7 +475,7 @@ static void lb_stats_refresh(struct work_struct *work)
 	team = lb_priv_ex->team;
 	lb_priv = get_lb_priv(team);
 
-	if (!mutex_trylock(&team->lock)) {
+	if (!rtnl_trylock()) {
 		schedule_delayed_work(&lb_priv_ex->stats.refresh_dw, 0);
 		return;
 	}
@@ -515,7 +512,7 @@ static void lb_stats_refresh(struct work_struct *work)
 	schedule_delayed_work(&lb_priv_ex->stats.refresh_dw,
 			      (lb_priv_ex->stats.refresh_interval * HZ) / 10);
 
-	mutex_unlock(&team->lock);
+	rtnl_unlock();
 }
 
 static void lb_stats_refresh_interval_get(struct team *team,
diff --git a/include/linux/if_team.h b/include/linux/if_team.h
index cdc684e04a2f..ce97d891cf72 100644
--- a/include/linux/if_team.h
+++ b/include/linux/if_team.h
@@ -191,8 +191,6 @@ struct team {
 
 	const struct header_ops *header_ops_cache;
 
-	struct mutex lock; /* used for overall locking, e.g. port lists write */
-
 	/*
 	 * List of enabled ports and their count
 	 */
@@ -223,7 +221,6 @@ struct team {
 		atomic_t count_pending;
 		struct delayed_work dw;
 	} mcast_rejoin;
-	struct lock_class_key team_lock_key;
 	long mode_priv[TEAM_MODE_PRIV_LONGS];
 };
 
-- 
cgit v1.2.3


From f9dc3e52d821dc1f9afeec43fb1c18ac94bd587a Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 23 Jun 2025 16:17:16 -0700
Subject: net: ethtool: remove the data argument from ethtool_notify()

ethtool_notify() takes a const void *data argument, which presumably
was intended to pass information from the call site to the subcommand
handler. This argument currently has no users.

Expecting the data to be subcommand-specific has two complications.

Complication #1 is that its not plumbed thru any of the standardized
callbacks. It gets propagated to ethnl_default_notify() where it
remains unused. Coming from the ethnl_default_set_doit() side we pass
in NULL, because how could we have a command specific attribute in
a generic handler.

Complication #2 is that we expect the ethtool_notify() callers to
know what attribute type to pass in. Again, the data pointer is
untyped.

RSS will need to pass the context ID to the notifications.
I think it's a better design if the "subcommand" exports its own
typed interface and constructs the appropriate argument struct
(which will be req_info). Remove the unused data argument from
ethtool_notify() but retain it in a new internal helper which
subcommands can use to build a typed interface.

Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Tested-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Link: https://patch.msgid.link/20250623231720.3124717-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  5 ++---
 net/ethtool/ioctl.c       | 24 ++++++++++++------------
 net/ethtool/netlink.c     | 11 ++++++++---
 net/ethtool/netlink.h     |  1 +
 4 files changed, 23 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 03c26bb0fbbe..db5bfd4e7ec8 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -5138,10 +5138,9 @@ void netdev_bonding_info_change(struct net_device *dev,
 				struct netdev_bonding_info *bonding_info);
 
 #if IS_ENABLED(CONFIG_ETHTOOL_NETLINK)
-void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data);
+void ethtool_notify(struct net_device *dev, unsigned int cmd);
 #else
-static inline void ethtool_notify(struct net_device *dev, unsigned int cmd,
-				  const void *data)
+static inline void ethtool_notify(struct net_device *dev, unsigned int cmd)
 {
 }
 #endif
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index 82cde640aa87..96da9d18789b 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -617,8 +617,8 @@ static int ethtool_set_link_ksettings(struct net_device *dev,
 
 	err = dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings);
 	if (err >= 0) {
-		ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL);
-		ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF, NULL);
+		ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF);
+		ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF);
 	}
 	return err;
 }
@@ -708,8 +708,8 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr)
 		__ETHTOOL_LINK_MODE_MASK_NU32;
 	ret = dev->ethtool_ops->set_link_ksettings(dev, &link_ksettings);
 	if (ret >= 0) {
-		ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF, NULL);
-		ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF, NULL);
+		ethtool_notify(dev, ETHTOOL_MSG_LINKINFO_NTF);
+		ethtool_notify(dev, ETHTOOL_MSG_LINKMODES_NTF);
 	}
 	return ret;
 }
@@ -1868,7 +1868,7 @@ static int ethtool_set_wol(struct net_device *dev, char __user *useraddr)
 		return ret;
 
 	dev->ethtool->wol_enabled = !!wol.wolopts;
-	ethtool_notify(dev, ETHTOOL_MSG_WOL_NTF, NULL);
+	ethtool_notify(dev, ETHTOOL_MSG_WOL_NTF);
 
 	return 0;
 }
@@ -1944,7 +1944,7 @@ static int ethtool_set_eee(struct net_device *dev, char __user *useraddr)
 	eee_to_keee(&keee, &eee);
 	ret = dev->ethtool_ops->set_eee(dev, &keee);
 	if (!ret)
-		ethtool_notify(dev, ETHTOOL_MSG_EEE_NTF, NULL);
+		ethtool_notify(dev, ETHTOOL_MSG_EEE_NTF);
 	return ret;
 }
 
@@ -2184,7 +2184,7 @@ static noinline_for_stack int ethtool_set_coalesce(struct net_device *dev,
 	ret = dev->ethtool_ops->set_coalesce(dev, &coalesce, &kernel_coalesce,
 					     NULL);
 	if (!ret)
-		ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF, NULL);
+		ethtool_notify(dev, ETHTOOL_MSG_COALESCE_NTF);
 	return ret;
 }
 
@@ -2228,7 +2228,7 @@ static int ethtool_set_ringparam(struct net_device *dev, void __user *useraddr)
 	ret = dev->ethtool_ops->set_ringparam(dev, &ringparam,
 					      &kernel_ringparam, NULL);
 	if (!ret)
-		ethtool_notify(dev, ETHTOOL_MSG_RINGS_NTF, NULL);
+		ethtool_notify(dev, ETHTOOL_MSG_RINGS_NTF);
 	return ret;
 }
 
@@ -2295,7 +2295,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
 
 	ret = dev->ethtool_ops->set_channels(dev, &channels);
 	if (!ret)
-		ethtool_notify(dev, ETHTOOL_MSG_CHANNELS_NTF, NULL);
+		ethtool_notify(dev, ETHTOOL_MSG_CHANNELS_NTF);
 	return ret;
 }
 
@@ -2326,7 +2326,7 @@ static int ethtool_set_pauseparam(struct net_device *dev, void __user *useraddr)
 
 	ret = dev->ethtool_ops->set_pauseparam(dev, &pauseparam);
 	if (!ret)
-		ethtool_notify(dev, ETHTOOL_MSG_PAUSE_NTF, NULL);
+		ethtool_notify(dev, ETHTOOL_MSG_PAUSE_NTF);
 	return ret;
 }
 
@@ -3328,7 +3328,7 @@ __dev_ethtool(struct net *net, struct ifreq *ifr, void __user *useraddr,
 		rc = ethtool_set_value_void(dev, useraddr,
 				       dev->ethtool_ops->set_msglevel);
 		if (!rc)
-			ethtool_notify(dev, ETHTOOL_MSG_DEBUG_NTF, NULL);
+			ethtool_notify(dev, ETHTOOL_MSG_DEBUG_NTF);
 		break;
 	case ETHTOOL_GEEE:
 		rc = ethtool_get_eee(dev, useraddr);
@@ -3392,7 +3392,7 @@ __dev_ethtool(struct net *net, struct ifreq *ifr, void __user *useraddr,
 		rc = ethtool_get_value(dev, useraddr, ethcmd,
 				       dev->ethtool_ops->get_priv_flags);
 		if (!rc)
-			ethtool_notify(dev, ETHTOOL_MSG_PRIVFLAGS_NTF, NULL);
+			ethtool_notify(dev, ETHTOOL_MSG_PRIVFLAGS_NTF);
 		break;
 	case ETHTOOL_SPFLAGS:
 		rc = ethtool_set_value(dev, useraddr,
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index c5ec3c82ab2e..129f9d56ac65 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -911,7 +911,7 @@ static int ethnl_default_set_doit(struct sk_buff *skb, struct genl_info *info)
 	swap(dev->cfg, dev->cfg_pending);
 	if (!ret)
 		goto out_ops;
-	ethtool_notify(dev, ops->set_ntf_cmd, NULL);
+	ethtool_notify(dev, ops->set_ntf_cmd);
 
 	ret = 0;
 out_ops:
@@ -1049,7 +1049,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = {
 	[ETHTOOL_MSG_MM_NTF]		= ethnl_default_notify,
 };
 
-void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data)
+void ethnl_notify(struct net_device *dev, unsigned int cmd, const void *data)
 {
 	if (unlikely(!ethnl_ok))
 		return;
@@ -1062,13 +1062,18 @@ void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data)
 		WARN_ONCE(1, "notification %u not implemented (dev=%s)\n",
 			  cmd, netdev_name(dev));
 }
+
+void ethtool_notify(struct net_device *dev, unsigned int cmd)
+{
+	ethnl_notify(dev, cmd, NULL);
+}
 EXPORT_SYMBOL(ethtool_notify);
 
 static void ethnl_notify_features(struct netdev_notifier_info *info)
 {
 	struct net_device *dev = netdev_notifier_info_to_dev(info);
 
-	ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF, NULL);
+	ethtool_notify(dev, ETHTOOL_MSG_FEATURES_NTF);
 }
 
 static int ethnl_netdev_event(struct notifier_block *this, unsigned long event,
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index 91b953924af3..4a061944a3aa 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -23,6 +23,7 @@ void *ethnl_dump_put(struct sk_buff *skb, struct netlink_callback *cb, u8 cmd);
 void *ethnl_bcastmsg_put(struct sk_buff *skb, u8 cmd);
 void *ethnl_unicast_put(struct sk_buff *skb, u32 portid, u32 seq, u8 cmd);
 int ethnl_multicast(struct sk_buff *skb, struct net_device *dev);
+void ethnl_notify(struct net_device *dev, unsigned int cmd, const void *data);
 
 /**
  * ethnl_strz_size() - calculate attribute length for fixed size string
-- 
cgit v1.2.3


From 8bd0af3154b2206ce19f8b1410339f7a2a56d0c3 Mon Sep 17 00:00:00 2001
From: Nathan Lynch <nathan.lynch@amd.com>
Date: Tue, 24 Jun 2025 08:50:44 -0500
Subject: lib: packing: Include necessary headers

packing.h uses ARRAY_SIZE(), BUILD_BUG_ON_MSG(), min(), max(), and
sizeof_field() without including the headers where they are defined,
potentially causing build failures.

Fix this in packing.h and sort the result.

Signed-off-by: Nathan Lynch <nathan.lynch@amd.com>
Reviewed-by: Vladimir Oltean <olteanv@gmail.com>
Link: https://patch.msgid.link/20250624-packing-includes-v1-1-c23c81fab508@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/packing.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/packing.h b/include/linux/packing.h
index 0589d70bbe04..20ae4d452c7b 100644
--- a/include/linux/packing.h
+++ b/include/linux/packing.h
@@ -5,8 +5,12 @@
 #ifndef _LINUX_PACKING_H
 #define _LINUX_PACKING_H
 
-#include <linux/types.h>
+#include <linux/array_size.h>
 #include <linux/bitops.h>
+#include <linux/build_bug.h>
+#include <linux/minmax.h>
+#include <linux/stddef.h>
+#include <linux/types.h>
 
 #define GEN_PACKED_FIELD_STRUCT(__type) \
 	struct packed_field_ ## __type { \
-- 
cgit v1.2.3


From f5769359c5b241978e6933672bb78b3adc36aa18 Mon Sep 17 00:00:00 2001
From: Hao Ge <gehao@kylinos.cn>
Date: Fri, 20 Jun 2025 02:31:54 +0800
Subject: mm/alloc_tag: fix the kmemleak false positive issue in the allocation
 of the percpu variable tag->counters

When loading a module, as long as the module has memory allocation
operations, kmemleak produces a false positive report that resembles the
following:

unreferenced object (percpu) 0x7dfd232a1650 (size 16):
  comm "modprobe", pid 1301, jiffies 4294940249
  hex dump (first 16 bytes on cpu 2):
    00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00  ................
  backtrace (crc 0):
    kmemleak_alloc_percpu+0xb4/0xd0
    pcpu_alloc_noprof+0x700/0x1098
    load_module+0xd4/0x348
    codetag_module_init+0x20c/0x450
    codetag_load_module+0x70/0xb8
    load_module+0xef8/0x1608
    init_module_from_file+0xec/0x158
    idempotent_init_module+0x354/0x608
    __arm64_sys_finit_module+0xbc/0x150
    invoke_syscall+0xd4/0x258
    el0_svc_common.constprop.0+0xb4/0x240
    do_el0_svc+0x48/0x68
    el0_svc+0x40/0xf8
    el0t_64_sync_handler+0x10c/0x138
    el0t_64_sync+0x1ac/0x1b0

This is because the module can only indirectly reference
alloc_tag_counters through the alloc_tag section, which misleads kmemleak.

However, we don't have a kmemleak ignore interface for percpu allocations
yet.  So let's create one and invoke it for tag->counters.

[gehao@kylinos.cn: fix build error when CONFIG_DEBUG_KMEMLEAK=n, s/igonore/ignore/]
  Link: https://lkml.kernel.org/r/20250620093102.2416767-1-hao.ge@linux.dev
Link: https://lkml.kernel.org/r/20250619183154.2122608-1-hao.ge@linux.dev
Fixes: 12ca42c23775 ("alloc_tag: allocate percpu counters for module tags dynamically")
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Suren Baghdasaryan <surenb@google.com>	[lib/alloc_tag.c]
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/kmemleak.h |  4 ++++
 lib/alloc_tag.c          |  8 +++++++-
 mm/kmemleak.c            | 14 ++++++++++++++
 3 files changed, 25 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/kmemleak.h b/include/linux/kmemleak.h
index 93a73c076d16..fbd424b2abb1 100644
--- a/include/linux/kmemleak.h
+++ b/include/linux/kmemleak.h
@@ -28,6 +28,7 @@ extern void kmemleak_update_trace(const void *ptr) __ref;
 extern void kmemleak_not_leak(const void *ptr) __ref;
 extern void kmemleak_transient_leak(const void *ptr) __ref;
 extern void kmemleak_ignore(const void *ptr) __ref;
+extern void kmemleak_ignore_percpu(const void __percpu *ptr) __ref;
 extern void kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp) __ref;
 extern void kmemleak_no_scan(const void *ptr) __ref;
 extern void kmemleak_alloc_phys(phys_addr_t phys, size_t size,
@@ -97,6 +98,9 @@ static inline void kmemleak_not_leak(const void *ptr)
 static inline void kmemleak_transient_leak(const void *ptr)
 {
 }
+static inline void kmemleak_ignore_percpu(const void __percpu *ptr)
+{
+}
 static inline void kmemleak_ignore(const void *ptr)
 {
 }
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index d48b80f3f007..3a74d63a959e 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -10,6 +10,7 @@
 #include <linux/seq_buf.h>
 #include <linux/seq_file.h>
 #include <linux/vmalloc.h>
+#include <linux/kmemleak.h>
 
 #define ALLOCINFO_FILE_NAME		"allocinfo"
 #define MODULE_ALLOC_TAG_VMAP_SIZE	(100000UL * sizeof(struct alloc_tag))
@@ -632,8 +633,13 @@ static int load_module(struct module *mod, struct codetag *start, struct codetag
 			       mod->name);
 			return -ENOMEM;
 		}
-	}
 
+		/*
+		 * Avoid a kmemleak false positive. The pointer to the counters is stored
+		 * in the alloc_tag section of the module and cannot be directly accessed.
+		 */
+		kmemleak_ignore_percpu(tag->counters);
+	}
 	return 0;
 }
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index da9cee34ee1b..8d588e685311 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1246,6 +1246,20 @@ void __ref kmemleak_transient_leak(const void *ptr)
 }
 EXPORT_SYMBOL(kmemleak_transient_leak);
 
+/**
+ * kmemleak_ignore_percpu - similar to kmemleak_ignore but taking a percpu
+ *			    address argument
+ * @ptr:	percpu address of the object
+ */
+void __ref kmemleak_ignore_percpu(const void __percpu *ptr)
+{
+	pr_debug("%s(0x%px)\n", __func__, ptr);
+
+	if (kmemleak_enabled && ptr && !IS_ERR_PCPU(ptr))
+		make_black_object((unsigned long)ptr, OBJECT_PERCPU);
+}
+EXPORT_SYMBOL_GPL(kmemleak_ignore_percpu);
+
 /**
  * kmemleak_ignore - ignore an allocated object
  * @ptr:	pointer to beginning of the object
-- 
cgit v1.2.3


From 4ecf83741401c70d4420588ee1f3b1ca04ef58d5 Mon Sep 17 00:00:00 2001
From: Jake Hillion <jake@hillion.co.uk>
Date: Wed, 25 Jun 2025 18:05:46 +0100
Subject: sched_ext: Drop kfuncs marked for removal in 6.15

sched_ext performed a kfunc renaming pass in 6.13 and kept the old names
around for compatibility with old binaries. These were scheduled for
cleanup in 6.15 but were missed. Submitting for cleanup in for-next.

Removed the kfuncs, their flags, and any references I could find to them
in doc comments. Left the entries in include/scx/compat.bpf.h as they're
still useful to make new binaries compatible with old kernels.

Tested by applying to my kernel. It builds and a modern version of
scx_lavd loads fine.

Signed-off-by: Jake Hillion <jake@hillion.co.uk>
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/sched/ext.h | 10 +++----
 kernel/sched/ext.c        | 71 ++---------------------------------------------
 2 files changed, 7 insertions(+), 74 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/ext.h b/include/linux/sched/ext.h
index 0cf0915572c9..7047101dbf58 100644
--- a/include/linux/sched/ext.h
+++ b/include/linux/sched/ext.h
@@ -164,7 +164,7 @@ struct sched_ext_entity {
 
 	/*
 	 * Runtime budget in nsecs. This is usually set through
-	 * scx_bpf_dispatch() but can also be modified directly by the BPF
+	 * scx_bpf_dsq_insert() but can also be modified directly by the BPF
 	 * scheduler. Automatically decreased by SCX as the task executes. On
 	 * depletion, a scheduling event is triggered.
 	 *
@@ -176,10 +176,10 @@ struct sched_ext_entity {
 
 	/*
 	 * Used to order tasks when dispatching to the vtime-ordered priority
-	 * queue of a dsq. This is usually set through scx_bpf_dispatch_vtime()
-	 * but can also be modified directly by the BPF scheduler. Modifying it
-	 * while a task is queued on a dsq may mangle the ordering and is not
-	 * recommended.
+	 * queue of a dsq. This is usually set through
+	 * scx_bpf_dsq_insert_vtime() but can also be modified directly by the
+	 * BPF scheduler. Modifying it while a task is queued on a dsq may
+	 * mangle the ordering and is not recommended.
 	 */
 	u64			dsq_vtime;
 
diff --git a/kernel/sched/ext.c b/kernel/sched/ext.c
index df5b2c952cf7..512474eabea6 100644
--- a/kernel/sched/ext.c
+++ b/kernel/sched/ext.c
@@ -6391,7 +6391,8 @@ __bpf_kfunc_start_defs();
  * When called from ops.dispatch(), there are no restrictions on @p or @dsq_id
  * and this function can be called upto ops.dispatch_max_batch times to insert
  * multiple tasks. scx_bpf_dispatch_nr_slots() returns the number of the
- * remaining slots. scx_bpf_consume() flushes the batch and resets the counter.
+ * remaining slots. scx_bpf_dsq_move_to_local() flushes the batch and resets the
+ * counter.
  *
  * This function doesn't have any locking restrictions and may be called under
  * BPF locks (in the future when BPF introduces more flexible locking).
@@ -6415,14 +6416,6 @@ __bpf_kfunc void scx_bpf_dsq_insert(struct task_struct *p, u64 dsq_id, u64 slice
 	scx_dsq_insert_commit(p, dsq_id, enq_flags);
 }
 
-/* for backward compatibility, will be removed in v6.15 */
-__bpf_kfunc void scx_bpf_dispatch(struct task_struct *p, u64 dsq_id, u64 slice,
-				  u64 enq_flags)
-{
-	printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch() renamed to scx_bpf_dsq_insert()");
-	scx_bpf_dsq_insert(p, dsq_id, slice, enq_flags);
-}
-
 /**
  * scx_bpf_dsq_insert_vtime - Insert a task into the vtime priority queue of a DSQ
  * @p: task_struct to insert
@@ -6460,21 +6453,11 @@ __bpf_kfunc void scx_bpf_dsq_insert_vtime(struct task_struct *p, u64 dsq_id,
 	scx_dsq_insert_commit(p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ);
 }
 
-/* for backward compatibility, will be removed in v6.15 */
-__bpf_kfunc void scx_bpf_dispatch_vtime(struct task_struct *p, u64 dsq_id,
-					u64 slice, u64 vtime, u64 enq_flags)
-{
-	printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_vtime() renamed to scx_bpf_dsq_insert_vtime()");
-	scx_bpf_dsq_insert_vtime(p, dsq_id, slice, vtime, enq_flags);
-}
-
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(scx_kfunc_ids_enqueue_dispatch)
 BTF_ID_FLAGS(func, scx_bpf_dsq_insert, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_dsq_insert_vtime, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_dispatch, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime, KF_RCU)
 BTF_KFUNCS_END(scx_kfunc_ids_enqueue_dispatch)
 
 static const struct btf_kfunc_id_set scx_kfunc_set_enqueue_dispatch = {
@@ -6647,13 +6630,6 @@ __bpf_kfunc bool scx_bpf_dsq_move_to_local(u64 dsq_id)
 	}
 }
 
-/* for backward compatibility, will be removed in v6.15 */
-__bpf_kfunc bool scx_bpf_consume(u64 dsq_id)
-{
-	printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_consume() renamed to scx_bpf_dsq_move_to_local()");
-	return scx_bpf_dsq_move_to_local(dsq_id);
-}
-
 /**
  * scx_bpf_dsq_move_set_slice - Override slice when moving between DSQs
  * @it__iter: DSQ iterator in progress
@@ -6672,14 +6648,6 @@ __bpf_kfunc void scx_bpf_dsq_move_set_slice(struct bpf_iter_scx_dsq *it__iter,
 	kit->cursor.flags |= __SCX_DSQ_ITER_HAS_SLICE;
 }
 
-/* for backward compatibility, will be removed in v6.15 */
-__bpf_kfunc void scx_bpf_dispatch_from_dsq_set_slice(
-			struct bpf_iter_scx_dsq *it__iter, u64 slice)
-{
-	printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_from_dsq_set_slice() renamed to scx_bpf_dsq_move_set_slice()");
-	scx_bpf_dsq_move_set_slice(it__iter, slice);
-}
-
 /**
  * scx_bpf_dsq_move_set_vtime - Override vtime when moving between DSQs
  * @it__iter: DSQ iterator in progress
@@ -6699,14 +6667,6 @@ __bpf_kfunc void scx_bpf_dsq_move_set_vtime(struct bpf_iter_scx_dsq *it__iter,
 	kit->cursor.flags |= __SCX_DSQ_ITER_HAS_VTIME;
 }
 
-/* for backward compatibility, will be removed in v6.15 */
-__bpf_kfunc void scx_bpf_dispatch_from_dsq_set_vtime(
-			struct bpf_iter_scx_dsq *it__iter, u64 vtime)
-{
-	printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_from_dsq_set_vtime() renamed to scx_bpf_dsq_move_set_vtime()");
-	scx_bpf_dsq_move_set_vtime(it__iter, vtime);
-}
-
 /**
  * scx_bpf_dsq_move - Move a task from DSQ iteration to a DSQ
  * @it__iter: DSQ iterator in progress
@@ -6739,15 +6699,6 @@ __bpf_kfunc bool scx_bpf_dsq_move(struct bpf_iter_scx_dsq *it__iter,
 			    p, dsq_id, enq_flags);
 }
 
-/* for backward compatibility, will be removed in v6.15 */
-__bpf_kfunc bool scx_bpf_dispatch_from_dsq(struct bpf_iter_scx_dsq *it__iter,
-					   struct task_struct *p, u64 dsq_id,
-					   u64 enq_flags)
-{
-	printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_from_dsq() renamed to scx_bpf_dsq_move()");
-	return scx_bpf_dsq_move(it__iter, p, dsq_id, enq_flags);
-}
-
 /**
  * scx_bpf_dsq_move_vtime - Move a task from DSQ iteration to a PRIQ DSQ
  * @it__iter: DSQ iterator in progress
@@ -6773,30 +6724,16 @@ __bpf_kfunc bool scx_bpf_dsq_move_vtime(struct bpf_iter_scx_dsq *it__iter,
 			    p, dsq_id, enq_flags | SCX_ENQ_DSQ_PRIQ);
 }
 
-/* for backward compatibility, will be removed in v6.15 */
-__bpf_kfunc bool scx_bpf_dispatch_vtime_from_dsq(struct bpf_iter_scx_dsq *it__iter,
-						 struct task_struct *p, u64 dsq_id,
-						 u64 enq_flags)
-{
-	printk_deferred_once(KERN_WARNING "sched_ext: scx_bpf_dispatch_from_dsq_vtime() renamed to scx_bpf_dsq_move_vtime()");
-	return scx_bpf_dsq_move_vtime(it__iter, p, dsq_id, enq_flags);
-}
-
 __bpf_kfunc_end_defs();
 
 BTF_KFUNCS_START(scx_kfunc_ids_dispatch)
 BTF_ID_FLAGS(func, scx_bpf_dispatch_nr_slots)
 BTF_ID_FLAGS(func, scx_bpf_dispatch_cancel)
 BTF_ID_FLAGS(func, scx_bpf_dsq_move_to_local)
-BTF_ID_FLAGS(func, scx_bpf_consume)
 BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_slice)
 BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_vtime)
 BTF_ID_FLAGS(func, scx_bpf_dsq_move, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_dsq_move_vtime, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_slice)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_vtime)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime_from_dsq, KF_RCU)
 BTF_KFUNCS_END(scx_kfunc_ids_dispatch)
 
 static const struct btf_kfunc_id_set scx_kfunc_set_dispatch = {
@@ -6927,10 +6864,6 @@ BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_slice)
 BTF_ID_FLAGS(func, scx_bpf_dsq_move_set_vtime)
 BTF_ID_FLAGS(func, scx_bpf_dsq_move, KF_RCU)
 BTF_ID_FLAGS(func, scx_bpf_dsq_move_vtime, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_slice)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq_set_vtime)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_from_dsq, KF_RCU)
-BTF_ID_FLAGS(func, scx_bpf_dispatch_vtime_from_dsq, KF_RCU)
 BTF_KFUNCS_END(scx_kfunc_ids_unlocked)
 
 static const struct btf_kfunc_id_set scx_kfunc_set_unlocked = {
-- 
cgit v1.2.3


From 16e2707cf15e09234445d40ddd76f11240be8767 Mon Sep 17 00:00:00 2001
From: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
Date: Wed, 4 Jun 2025 15:39:37 -0400
Subject: cpumask: add cpumask_clear_cpus()

When user wants to clear a range in cpumask, the only option the API
provides now is a for-loop, like:

	for_each_cpu_from(cpu, mask) {
		if (cpu >= ncpus)
			break;
		__cpumask_clear_cpu(cpu, mask);
	}

In the bitmap API we have bitmap_clear() for that, which is
significantly faster than a for-loop. Propagate it to cpumasks.

Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
Link: https://patch.msgid.link/20250604193947.11834-2-yury.norov@gmail.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/cpumask.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 7ae80a7ca81e..ede95bbe8b80 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -609,6 +609,18 @@ void __cpumask_set_cpu(unsigned int cpu, struct cpumask *dstp)
 	__set_bit(cpumask_check(cpu), cpumask_bits(dstp));
 }
 
+/**
+ * cpumask_clear_cpus - clear cpus in a cpumask
+ * @dstp:  the cpumask pointer
+ * @cpu:   cpu number (< nr_cpu_ids)
+ * @ncpus: number of cpus to clear (< nr_cpu_ids)
+ */
+static __always_inline void cpumask_clear_cpus(struct cpumask *dstp,
+						unsigned int cpu, unsigned int ncpus)
+{
+	cpumask_check(cpu + ncpus - 1);
+	bitmap_clear(cpumask_bits(dstp), cpumask_check(cpu), ncpus);
+}
 
 /**
  * cpumask_clear_cpu - clear a cpu in a cpumask
-- 
cgit v1.2.3


From 611d08207d313500d010d8792424346ce70d0cfb Mon Sep 17 00:00:00 2001
From: Mark Bloch <mbloch@nvidia.com>
Date: Tue, 17 Jun 2025 11:44:02 +0300
Subject: RDMA/mlx5: Allocate IB device with net namespace supplied from core
 dev

Use the new ib_alloc_device_with_net() API to allocate the IB device
so that it is properly bound to the network namespace obtained via
mlx5_core_net(). This change ensures correct namespace association
(e.g., for containerized setups).

Additionally, expose mlx5_core_net so that RDMA driver can use it.

Signed-off-by: Shay Drory <shayd@nvidia.com>
Signed-off-by: Mark Bloch <mbloch@nvidia.com>
Reviewed-by: Parav Pandit <parav@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
---
 drivers/infiniband/hw/mlx5/ib_rep.c                | 3 ++-
 drivers/infiniband/hw/mlx5/main.c                  | 6 ++++--
 drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h | 5 -----
 include/linux/mlx5/driver.h                        | 5 +++++
 4 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/ib_rep.c b/drivers/infiniband/hw/mlx5/ib_rep.c
index 49af1cfbe6d1..cc8859d3c2f5 100644
--- a/drivers/infiniband/hw/mlx5/ib_rep.c
+++ b/drivers/infiniband/hw/mlx5/ib_rep.c
@@ -88,7 +88,8 @@ mlx5_ib_vport_rep_load(struct mlx5_core_dev *dev, struct mlx5_eswitch_rep *rep)
 	else
 		return mlx5_ib_set_vport_rep(lag_master, rep, vport_index);
 
-	ibdev = ib_alloc_device(mlx5_ib_dev, ib_dev);
+	ibdev = ib_alloc_device_with_net(mlx5_ib_dev, ib_dev,
+					 mlx5_core_net(lag_master));
 	if (!ibdev)
 		return -ENOMEM;
 
diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index efea3ffd9715..c521bce2eeff 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -4793,7 +4793,8 @@ static struct ib_device *mlx5_ib_add_sub_dev(struct ib_device *parent,
 	    !MLX5_CAP_GEN_2(mparent->mdev, multiplane_qp_ud))
 		return ERR_PTR(-EOPNOTSUPP);
 
-	mplane = ib_alloc_device(mlx5_ib_dev, ib_dev);
+	mplane = ib_alloc_device_with_net(mlx5_ib_dev, ib_dev,
+					  mlx5_core_net(mparent->mdev));
 	if (!mplane)
 		return ERR_PTR(-ENOMEM);
 
@@ -4907,7 +4908,8 @@ static int mlx5r_probe(struct auxiliary_device *adev,
 
 	num_ports = max(MLX5_CAP_GEN(mdev, num_ports),
 			MLX5_CAP_GEN(mdev, num_vhca_ports));
-	dev = ib_alloc_device(mlx5_ib_dev, ib_dev);
+	dev = ib_alloc_device_with_net(mlx5_ib_dev, ib_dev,
+				       mlx5_core_net(mdev));
 	if (!dev)
 		return -ENOMEM;
 
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
index 37d5f445598c..b111ccd03b02 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/mlx5.h
@@ -45,11 +45,6 @@ int mlx5_crdump_enable(struct mlx5_core_dev *dev);
 void mlx5_crdump_disable(struct mlx5_core_dev *dev);
 int mlx5_crdump_collect(struct mlx5_core_dev *dev, u32 *cr_data);
 
-static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
-{
-	return devlink_net(priv_to_devlink(dev));
-}
-
 static inline struct net_device *mlx5_uplink_netdev_get(struct mlx5_core_dev *mdev)
 {
 	return mdev->mlx5e_res.uplink_netdev;
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e6ba8f4f4bd1..3475d33c75f4 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -1349,4 +1349,9 @@ enum {
 };
 
 bool mlx5_wc_support_get(struct mlx5_core_dev *mdev);
+
+static inline struct net *mlx5_core_net(struct mlx5_core_dev *dev)
+{
+	return devlink_net(priv_to_devlink(dev));
+}
 #endif /* MLX5_DRIVER_H */
-- 
cgit v1.2.3


From df0f030ee7e444c55341f4210124115878284125 Mon Sep 17 00:00:00 2001
From: Vladimir Kondratiev <vladimir.kondratiev@mobileye.com>
Date: Thu, 12 Jun 2025 17:39:08 +0300
Subject: irqchip/thead-c900-aclint-sswi: Generalize aclint-sswi driver and add
 MIPS P800 support

Refactor the Thead specific implementation of the ACLINT-SSWI irqchip:

 - Rename the source file and related details to reflect the generic nature
   of the driver

 - Factor out the generic code that serves both Thead and MIPS variants.
   This generic part is compliant with the RISC-V draft spec [1]

 - Provide generic and Thead specific initialization functions

Signed-off-by: Vladimir Kondratiev <vladimir.kondratiev@mobileye.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250612143911.3224046-5-vladimir.kondratiev@mobileye.com
Link: https://github.com/riscvarchive/riscv-aclint [1]
---
 drivers/irqchip/Kconfig                      |  15 +-
 drivers/irqchip/Makefile                     |   2 +-
 drivers/irqchip/irq-aclint-sswi.c            | 208 +++++++++++++++++++++++++++
 drivers/irqchip/irq-thead-c900-aclint-sswi.c | 176 -----------------------
 include/linux/cpuhotplug.h                   |   2 +-
 5 files changed, 221 insertions(+), 182 deletions(-)
 create mode 100644 drivers/irqchip/irq-aclint-sswi.c
 delete mode 100644 drivers/irqchip/irq-thead-c900-aclint-sswi.c

(limited to 'include/linux')

diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 0d196e447142..39f6f421fc75 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -634,18 +634,25 @@ config STARFIVE_JH8100_INTC
 
 	  If you don't know what to do here, say Y.
 
-config THEAD_C900_ACLINT_SSWI
-	bool "THEAD C9XX ACLINT S-mode IPI Interrupt Controller"
+config ACLINT_SSWI
+	bool "RISC-V ACLINT S-mode IPI Interrupt Controller"
 	depends on RISCV
 	depends on SMP
 	select IRQ_DOMAIN_HIERARCHY
 	select GENERIC_IRQ_IPI_MUX
 	help
-	  This enables support for T-HEAD specific ACLINT SSWI device
-	  support.
+	  This enables support for variants of the RISC-V ACLINT-SSWI device.
+	  Supported variants are:
+	  - T-HEAD, with compatible "thead,c900-aclint-sswi"
+	  - MIPS P8700, with compatible "mips,p8700-aclint-sswi"
 
 	  If you don't know what to do here, say Y.
 
+# Backwards compatibility so oldconfig does not drop it.
+config THEAD_C900_ACLINT_SSWI
+	bool
+	select ACLINT_SSWI
+
 config EXYNOS_IRQ_COMBINER
 	bool "Samsung Exynos IRQ combiner support" if COMPILE_TEST
 	depends on (ARCH_EXYNOS && ARM) || COMPILE_TEST
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 23ca4959e6ce..0458d6c5d161 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -105,7 +105,7 @@ obj-$(CONFIG_RISCV_APLIC_MSI)		+= irq-riscv-aplic-msi.o
 obj-$(CONFIG_RISCV_IMSIC)		+= irq-riscv-imsic-state.o irq-riscv-imsic-early.o irq-riscv-imsic-platform.o
 obj-$(CONFIG_SIFIVE_PLIC)		+= irq-sifive-plic.o
 obj-$(CONFIG_STARFIVE_JH8100_INTC)	+= irq-starfive-jh8100-intc.o
-obj-$(CONFIG_THEAD_C900_ACLINT_SSWI)	+= irq-thead-c900-aclint-sswi.o
+obj-$(CONFIG_ACLINT_SSWI)		+= irq-aclint-sswi.o
 obj-$(CONFIG_IMX_IRQSTEER)		+= irq-imx-irqsteer.o
 obj-$(CONFIG_IMX_INTMUX)		+= irq-imx-intmux.o
 obj-$(CONFIG_IMX_MU_MSI)		+= irq-imx-mu-msi.o
diff --git a/drivers/irqchip/irq-aclint-sswi.c b/drivers/irqchip/irq-aclint-sswi.c
new file mode 100644
index 000000000000..0131194d4847
--- /dev/null
+++ b/drivers/irqchip/irq-aclint-sswi.c
@@ -0,0 +1,208 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2024 Inochi Amaoto <inochiama@gmail.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/cpu.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/irq.h>
+#include <linux/irqchip.h>
+#include <linux/irqchip/chained_irq.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/pci.h>
+#include <linux/spinlock.h>
+#include <linux/smp.h>
+#include <linux/string_choices.h>
+#include <asm/sbi.h>
+#include <asm/vendorid_list.h>
+
+static int sswi_ipi_virq __ro_after_init;
+static DEFINE_PER_CPU(void __iomem *, sswi_cpu_regs);
+
+static void aclint_sswi_ipi_send(unsigned int cpu)
+{
+	writel(0x1, per_cpu(sswi_cpu_regs, cpu));
+}
+
+static void aclint_sswi_ipi_clear(void)
+{
+	writel_relaxed(0x0, this_cpu_read(sswi_cpu_regs));
+}
+
+static void aclint_sswi_ipi_handle(struct irq_desc *desc)
+{
+	struct irq_chip *chip = irq_desc_get_chip(desc);
+
+	chained_irq_enter(chip, desc);
+
+	csr_clear(CSR_IP, IE_SIE);
+	aclint_sswi_ipi_clear();
+
+	ipi_mux_process();
+
+	chained_irq_exit(chip, desc);
+}
+
+static int aclint_sswi_starting_cpu(unsigned int cpu)
+{
+	enable_percpu_irq(sswi_ipi_virq, irq_get_trigger_type(sswi_ipi_virq));
+
+	return 0;
+}
+
+static int aclint_sswi_dying_cpu(unsigned int cpu)
+{
+	aclint_sswi_ipi_clear();
+
+	disable_percpu_irq(sswi_ipi_virq);
+
+	return 0;
+}
+
+static int __init aclint_sswi_parse_irq(struct fwnode_handle *fwnode, void __iomem *reg)
+{
+	struct of_phandle_args parent;
+	unsigned long hartid;
+	u32 contexts, i;
+	int rc, cpu;
+
+	contexts = of_irq_count(to_of_node(fwnode));
+	if (!(contexts)) {
+		pr_err("%pfwP: no ACLINT SSWI context available\n", fwnode);
+		return -EINVAL;
+	}
+
+	for (i = 0; i < contexts; i++) {
+		rc = of_irq_parse_one(to_of_node(fwnode), i, &parent);
+		if (rc)
+			return rc;
+
+		rc = riscv_of_parent_hartid(parent.np, &hartid);
+		if (rc)
+			return rc;
+
+		if (parent.args[0] != RV_IRQ_SOFT)
+			return -ENOTSUPP;
+
+		cpu = riscv_hartid_to_cpuid(hartid);
+
+		per_cpu(sswi_cpu_regs, cpu) = reg + hart_index * 4;
+	}
+
+	pr_info("%pfwP: register %u CPU%s\n", fwnode, contexts, str_plural(contexts));
+
+	return 0;
+}
+
+static int __init aclint_sswi_probe(struct fwnode_handle *fwnode)
+{
+	struct irq_domain *domain;
+	void __iomem *reg;
+	int virq, rc;
+
+	if (!is_of_node(fwnode))
+		return -EINVAL;
+
+	reg = of_iomap(to_of_node(fwnode), 0);
+	if (!reg)
+		return -ENOMEM;
+
+	/* Parse SSWI setting */
+	rc = aclint_sswi_parse_irq(fwnode, reg);
+	if (rc < 0)
+		return rc;
+
+	/* If mulitple SSWI devices are present, do not register irq again */
+	if (sswi_ipi_virq)
+		return 0;
+
+	/* Find riscv intc domain and create IPI irq mapping */
+	domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), DOMAIN_BUS_ANY);
+	if (!domain) {
+		pr_err("%pfwP: Failed to find INTC domain\n", fwnode);
+		return -ENOENT;
+	}
+
+	sswi_ipi_virq = irq_create_mapping(domain, RV_IRQ_SOFT);
+	if (!sswi_ipi_virq) {
+		pr_err("unable to create ACLINT SSWI IRQ mapping\n");
+		return -ENOMEM;
+	}
+
+	/* Register SSWI irq and handler */
+	virq = ipi_mux_create(BITS_PER_BYTE, aclint_sswi_ipi_send);
+	if (virq <= 0) {
+		pr_err("unable to create muxed IPIs\n");
+		irq_dispose_mapping(sswi_ipi_virq);
+		return virq < 0 ? virq : -ENOMEM;
+	}
+
+	irq_set_chained_handler(sswi_ipi_virq, aclint_sswi_ipi_handle);
+
+	cpuhp_setup_state(CPUHP_AP_IRQ_ACLINT_SSWI_STARTING,
+			  "irqchip/aclint-sswi:starting",
+			  aclint_sswi_starting_cpu,
+			  aclint_sswi_dying_cpu);
+
+	riscv_ipi_set_virq_range(virq, BITS_PER_BYTE);
+
+	return 0;
+}
+
+/* generic/MIPS variant */
+static int __init generic_aclint_sswi_probe(struct fwnode_handle *fwnode)
+{
+	int rc;
+
+	rc = aclint_sswi_probe(fwnode);
+	if (rc)
+		return rc;
+
+	/* Announce that SSWI is providing IPIs */
+	pr_info("providing IPIs using ACLINT SSWI\n");
+
+	return 0;
+}
+
+static int __init generic_aclint_sswi_early_probe(struct device_node *node,
+						  struct device_node *parent)
+{
+	return generic_aclint_sswi_probe(&node->fwnode);
+}
+IRQCHIP_DECLARE(generic_aclint_sswi, "mips,p8700-aclint-sswi", generic_aclint_sswi_early_probe);
+
+/* THEAD variant */
+#define THEAD_C9XX_CSR_SXSTATUS			0x5c0
+#define THEAD_C9XX_SXSTATUS_CLINTEE		BIT(17)
+
+static int __init thead_aclint_sswi_probe(struct fwnode_handle *fwnode)
+{
+	int rc;
+
+	/* If it is T-HEAD CPU, check whether SSWI is enabled */
+	if (riscv_cached_mvendorid(0) == THEAD_VENDOR_ID &&
+	    !(csr_read(THEAD_C9XX_CSR_SXSTATUS) & THEAD_C9XX_SXSTATUS_CLINTEE))
+		return -ENOTSUPP;
+
+	rc = aclint_sswi_probe(fwnode);
+	if (rc)
+		return rc;
+
+	/* Announce that SSWI is providing IPIs */
+	pr_info("providing IPIs using THEAD ACLINT SSWI\n");
+
+	return 0;
+}
+
+static int __init thead_aclint_sswi_early_probe(struct device_node *node,
+						struct device_node *parent)
+{
+	return thead_aclint_sswi_probe(&node->fwnode);
+}
+IRQCHIP_DECLARE(thead_aclint_sswi, "thead,c900-aclint-sswi", thead_aclint_sswi_early_probe);
diff --git a/drivers/irqchip/irq-thead-c900-aclint-sswi.c b/drivers/irqchip/irq-thead-c900-aclint-sswi.c
deleted file mode 100644
index 8ff6e7a1363b..000000000000
--- a/drivers/irqchip/irq-thead-c900-aclint-sswi.c
+++ /dev/null
@@ -1,176 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Copyright (C) 2024 Inochi Amaoto <inochiama@gmail.com>
- */
-
-#define pr_fmt(fmt) "thead-c900-aclint-sswi: " fmt
-#include <linux/cpu.h>
-#include <linux/interrupt.h>
-#include <linux/io.h>
-#include <linux/irq.h>
-#include <linux/irqchip.h>
-#include <linux/irqchip/chained_irq.h>
-#include <linux/module.h>
-#include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_irq.h>
-#include <linux/pci.h>
-#include <linux/spinlock.h>
-#include <linux/smp.h>
-#include <linux/string_choices.h>
-#include <asm/sbi.h>
-#include <asm/vendorid_list.h>
-
-#define THEAD_ACLINT_xSWI_REGISTER_SIZE		4
-
-#define THEAD_C9XX_CSR_SXSTATUS			0x5c0
-#define THEAD_C9XX_SXSTATUS_CLINTEE		BIT(17)
-
-static int sswi_ipi_virq __ro_after_init;
-static DEFINE_PER_CPU(void __iomem *, sswi_cpu_regs);
-
-static void thead_aclint_sswi_ipi_send(unsigned int cpu)
-{
-	writel(0x1, per_cpu(sswi_cpu_regs, cpu));
-}
-
-static void thead_aclint_sswi_ipi_clear(void)
-{
-	writel_relaxed(0x0, this_cpu_read(sswi_cpu_regs));
-}
-
-static void thead_aclint_sswi_ipi_handle(struct irq_desc *desc)
-{
-	struct irq_chip *chip = irq_desc_get_chip(desc);
-
-	chained_irq_enter(chip, desc);
-
-	csr_clear(CSR_IP, IE_SIE);
-	thead_aclint_sswi_ipi_clear();
-
-	ipi_mux_process();
-
-	chained_irq_exit(chip, desc);
-}
-
-static int thead_aclint_sswi_starting_cpu(unsigned int cpu)
-{
-	enable_percpu_irq(sswi_ipi_virq, irq_get_trigger_type(sswi_ipi_virq));
-
-	return 0;
-}
-
-static int thead_aclint_sswi_dying_cpu(unsigned int cpu)
-{
-	thead_aclint_sswi_ipi_clear();
-
-	disable_percpu_irq(sswi_ipi_virq);
-
-	return 0;
-}
-
-static int __init thead_aclint_sswi_parse_irq(struct fwnode_handle *fwnode,
-					      void __iomem *reg)
-{
-	struct of_phandle_args parent;
-	unsigned long hartid;
-	u32 contexts, i;
-	int rc, cpu;
-
-	contexts = of_irq_count(to_of_node(fwnode));
-	if (!(contexts)) {
-		pr_err("%pfwP: no ACLINT SSWI context available\n", fwnode);
-		return -EINVAL;
-	}
-
-	for (i = 0; i < contexts; i++) {
-		rc = of_irq_parse_one(to_of_node(fwnode), i, &parent);
-		if (rc)
-			return rc;
-
-		rc = riscv_of_parent_hartid(parent.np, &hartid);
-		if (rc)
-			return rc;
-
-		if (parent.args[0] != RV_IRQ_SOFT)
-			return -ENOTSUPP;
-
-		cpu = riscv_hartid_to_cpuid(hartid);
-
-		per_cpu(sswi_cpu_regs, cpu) = reg + i * THEAD_ACLINT_xSWI_REGISTER_SIZE;
-	}
-
-	pr_info("%pfwP: register %u CPU%s\n", fwnode, contexts, str_plural(contexts));
-
-	return 0;
-}
-
-static int __init thead_aclint_sswi_probe(struct fwnode_handle *fwnode)
-{
-	struct irq_domain *domain;
-	void __iomem *reg;
-	int virq, rc;
-
-	/* If it is T-HEAD CPU, check whether SSWI is enabled */
-	if (riscv_cached_mvendorid(0) == THEAD_VENDOR_ID &&
-	    !(csr_read(THEAD_C9XX_CSR_SXSTATUS) & THEAD_C9XX_SXSTATUS_CLINTEE))
-		return -ENOTSUPP;
-
-	if (!is_of_node(fwnode))
-		return -EINVAL;
-
-	reg = of_iomap(to_of_node(fwnode), 0);
-	if (!reg)
-		return -ENOMEM;
-
-	/* Parse SSWI setting */
-	rc = thead_aclint_sswi_parse_irq(fwnode, reg);
-	if (rc < 0)
-		return rc;
-
-	/* If mulitple SSWI devices are present, do not register irq again */
-	if (sswi_ipi_virq)
-		return 0;
-
-	/* Find riscv intc domain and create IPI irq mapping */
-	domain = irq_find_matching_fwnode(riscv_get_intc_hwnode(), DOMAIN_BUS_ANY);
-	if (!domain) {
-		pr_err("%pfwP: Failed to find INTC domain\n", fwnode);
-		return -ENOENT;
-	}
-
-	sswi_ipi_virq = irq_create_mapping(domain, RV_IRQ_SOFT);
-	if (!sswi_ipi_virq) {
-		pr_err("unable to create ACLINT SSWI IRQ mapping\n");
-		return -ENOMEM;
-	}
-
-	/* Register SSWI irq and handler */
-	virq = ipi_mux_create(BITS_PER_BYTE, thead_aclint_sswi_ipi_send);
-	if (virq <= 0) {
-		pr_err("unable to create muxed IPIs\n");
-		irq_dispose_mapping(sswi_ipi_virq);
-		return virq < 0 ? virq : -ENOMEM;
-	}
-
-	irq_set_chained_handler(sswi_ipi_virq, thead_aclint_sswi_ipi_handle);
-
-	cpuhp_setup_state(CPUHP_AP_IRQ_THEAD_ACLINT_SSWI_STARTING,
-			  "irqchip/thead-aclint-sswi:starting",
-			  thead_aclint_sswi_starting_cpu,
-			  thead_aclint_sswi_dying_cpu);
-
-	riscv_ipi_set_virq_range(virq, BITS_PER_BYTE);
-
-	/* Announce that SSWI is providing IPIs */
-	pr_info("providing IPIs using THEAD ACLINT SSWI\n");
-
-	return 0;
-}
-
-static int __init thead_aclint_sswi_early_probe(struct device_node *node,
-						struct device_node *parent)
-{
-	return thead_aclint_sswi_probe(&node->fwnode);
-}
-IRQCHIP_DECLARE(thead_aclint_sswi, "thead,c900-aclint-sswi", thead_aclint_sswi_early_probe);
diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index df366ee15456..d381420bbd5f 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -145,7 +145,7 @@ enum cpuhp_state {
 	CPUHP_AP_IRQ_EIOINTC_STARTING,
 	CPUHP_AP_IRQ_AVECINTC_STARTING,
 	CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
-	CPUHP_AP_IRQ_THEAD_ACLINT_SSWI_STARTING,
+	CPUHP_AP_IRQ_ACLINT_SSWI_STARTING,
 	CPUHP_AP_IRQ_RISCV_IMSIC_STARTING,
 	CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING,
 	CPUHP_AP_ARM_MVEBU_COHERENCY,
-- 
cgit v1.2.3


From 3a95a561f2763e3854e207de3ea821e795a1f1e0 Mon Sep 17 00:00:00 2001
From: Viktor Malik <vmalik@redhat.com>
Date: Thu, 26 Jun 2025 08:08:28 +0200
Subject: uaccess: Define pagefault lock guard

Define a pagefault lock guard which allows to simplify functions that
need to disable page faults.

Signed-off-by: Viktor Malik <vmalik@redhat.com>
Link: https://lore.kernel.org/r/8a01beb0b671923976f08297d81242bb2129881d.1750917800.git.vmalik@redhat.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/uaccess.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/uaccess.h b/include/linux/uaccess.h
index 7c06f4795670..1beb5b395d81 100644
--- a/include/linux/uaccess.h
+++ b/include/linux/uaccess.h
@@ -296,6 +296,8 @@ static inline bool pagefault_disabled(void)
  */
 #define faulthandler_disabled() (pagefault_disabled() || in_atomic())
 
+DEFINE_LOCK_GUARD_0(pagefault, pagefault_disable(), pagefault_enable())
+
 #ifndef CONFIG_ARCH_HAS_SUBPAGE_FAULTS
 
 /**
-- 
cgit v1.2.3


From c430955d0cb87fb7c6b186e457cb3beca4a9c89a Mon Sep 17 00:00:00 2001
From: Gwendal Grignou <gwendal@chromium.org>
Date: Tue, 3 Jun 2025 22:39:03 -0700
Subject: iio: cros_ec_sensors: add cros_ec_activity driver

ChromeOS EC can report activity information derived from the
accelerometer:
- Reports on-body/off-body as a proximity event.
- Reports significant motion as an activity event.

This new sensor is a virtual sensor, included only when the EC firmware
is compiled with the appropriate module.

Signed-off-by: Gwendal Grignou <gwendal@google.com>
Reviewed-by: Tzung-Bi Shih <tzungbi@kernel.org>
Link: https://patch.msgid.link/20250604053903.1376465-1-gwendal@google.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/common/cros_ec_sensors/Kconfig         |   9 +
 drivers/iio/common/cros_ec_sensors/Makefile        |   1 +
 .../iio/common/cros_ec_sensors/cros_ec_activity.c  | 307 +++++++++++++++++++++
 .../common/cros_ec_sensors/cros_ec_sensors_core.c  |  10 +
 include/linux/iio/common/cros_ec_sensors_core.h    |   1 +
 include/linux/platform_data/cros_ec_commands.h     |  26 +-
 6 files changed, 352 insertions(+), 2 deletions(-)
 create mode 100644 drivers/iio/common/cros_ec_sensors/cros_ec_activity.c

(limited to 'include/linux')

diff --git a/drivers/iio/common/cros_ec_sensors/Kconfig b/drivers/iio/common/cros_ec_sensors/Kconfig
index fefad9572790..394e319c9c97 100644
--- a/drivers/iio/common/cros_ec_sensors/Kconfig
+++ b/drivers/iio/common/cros_ec_sensors/Kconfig
@@ -30,3 +30,12 @@ config IIO_CROS_EC_SENSORS_LID_ANGLE
 	  convertible devices.
 	  This module is loaded when the EC can calculate the angle between the base
 	  and the lid.
+
+config IIO_CROS_EC_ACTIVITY
+	tristate "ChromeOS EC Activity Sensors"
+	depends on IIO_CROS_EC_SENSORS_CORE
+	help
+	  Module to handle activity events presented by the ChromeOS EC sensor hub.
+	  Activities can be a proximity detector (on body/off body detection)
+	  or a significant motion detector.
+	  Creates an IIO device to manage all activities.
diff --git a/drivers/iio/common/cros_ec_sensors/Makefile b/drivers/iio/common/cros_ec_sensors/Makefile
index c358fa0328ab..a7dfb5794cae 100644
--- a/drivers/iio/common/cros_ec_sensors/Makefile
+++ b/drivers/iio/common/cros_ec_sensors/Makefile
@@ -7,3 +7,4 @@ cros-ec-sensors-core-objs += cros_ec_sensors_core.o cros_ec_sensors_trace.o
 obj-$(CONFIG_IIO_CROS_EC_SENSORS_CORE) += cros-ec-sensors-core.o
 obj-$(CONFIG_IIO_CROS_EC_SENSORS) += cros_ec_sensors.o
 obj-$(CONFIG_IIO_CROS_EC_SENSORS_LID_ANGLE) += cros_ec_lid_angle.o
+obj-$(CONFIG_IIO_CROS_EC_ACTIVITY) += cros_ec_activity.o
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_activity.c b/drivers/iio/common/cros_ec_sensors/cros_ec_activity.c
new file mode 100644
index 000000000000..6e38d115b6fe
--- /dev/null
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_activity.c
@@ -0,0 +1,307 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * cros_ec_activity - Driver for activities/gesture recognition.
+ *
+ * Copyright 2025 Google, Inc
+ *
+ * This driver uses the cros-ec interface to communicate with the ChromeOS
+ * EC about activity data.
+ */
+
+#include <linux/bits.h>
+#include <linux/cleanup.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/platform_device.h>
+#include <linux/types.h>
+
+#include <linux/platform_data/cros_ec_commands.h>
+#include <linux/platform_data/cros_ec_proto.h>
+
+#include <linux/iio/common/cros_ec_sensors_core.h>
+#include <linux/iio/events.h>
+#include <linux/iio/iio.h>
+#include <linux/iio/trigger_consumer.h>
+
+#define DRV_NAME "cros-ec-activity"
+
+/* state data for ec_sensors iio driver. */
+struct cros_ec_sensors_state {
+	/* Shared by all sensors */
+	struct cros_ec_sensors_core_state core;
+
+	struct iio_chan_spec *channels;
+
+	int body_detection_channel_index;
+	int sig_motion_channel_index;
+};
+
+static const struct iio_event_spec cros_ec_activity_single_shot[] = {
+	{
+		.type = IIO_EV_TYPE_CHANGE,
+		/* significant motion trigger when we get out of still. */
+		.dir = IIO_EV_DIR_FALLING,
+		.mask_separate = BIT(IIO_EV_INFO_ENABLE),
+	},
+};
+
+static const struct iio_event_spec cros_ec_body_detect_events[] = {
+	{
+		.type = IIO_EV_TYPE_CHANGE,
+		.dir = IIO_EV_DIR_EITHER,
+		.mask_separate = BIT(IIO_EV_INFO_ENABLE),
+	},
+};
+
+static int cros_ec_activity_sensors_read_raw(struct iio_dev *indio_dev,
+					     struct iio_chan_spec const *chan,
+					     int *val, int *val2, long mask)
+{
+	struct cros_ec_sensors_state *st = iio_priv(indio_dev);
+	int ret;
+
+	if (chan->type != IIO_PROXIMITY || mask != IIO_CHAN_INFO_RAW)
+		return -EINVAL;
+
+	guard(mutex)(&st->core.cmd_lock);
+	st->core.param.cmd = MOTIONSENSE_CMD_GET_ACTIVITY;
+	st->core.param.get_activity.activity =
+		MOTIONSENSE_ACTIVITY_BODY_DETECTION;
+	ret = cros_ec_motion_send_host_cmd(&st->core, 0);
+	if (ret)
+		return ret;
+
+	/*
+	 * EC actually report if a body is near (1) or far (0).
+	 * Units for proximity sensor after scale is in meter,
+	 * so invert the result to return 0m when near and 1m when far.
+	 */
+	*val = !st->core.resp->get_activity.state;
+	return IIO_VAL_INT;
+}
+
+static int cros_ec_activity_read_event_config(struct iio_dev *indio_dev,
+					      const struct iio_chan_spec *chan,
+					      enum iio_event_type type,
+					      enum iio_event_direction dir)
+{
+	struct cros_ec_sensors_state *st = iio_priv(indio_dev);
+	int ret;
+
+	if (chan->type != IIO_ACTIVITY && chan->type != IIO_PROXIMITY)
+		return -EINVAL;
+
+	guard(mutex)(&st->core.cmd_lock);
+	st->core.param.cmd = MOTIONSENSE_CMD_LIST_ACTIVITIES;
+	ret = cros_ec_motion_send_host_cmd(&st->core, 0);
+	if (ret)
+		return ret;
+
+	switch (chan->type) {
+	case IIO_PROXIMITY:
+		return !!(st->core.resp->list_activities.enabled &
+			 (1 << MOTIONSENSE_ACTIVITY_BODY_DETECTION));
+	case IIO_ACTIVITY:
+		if (chan->channel2 == IIO_MOD_STILL) {
+			return !!(st->core.resp->list_activities.enabled &
+				 (1 << MOTIONSENSE_ACTIVITY_SIG_MOTION));
+		}
+
+		dev_warn(&indio_dev->dev, "Unknown activity: %d\n",
+			 chan->channel2);
+		return -EINVAL;
+	default:
+		dev_warn(&indio_dev->dev, "Unknown channel type: %d\n",
+			 chan->type);
+		return -EINVAL;
+	}
+}
+
+static int cros_ec_activity_write_event_config(struct iio_dev *indio_dev,
+					       const struct iio_chan_spec *chan,
+					       enum iio_event_type type,
+					       enum iio_event_direction dir,
+					       bool state)
+{
+	struct cros_ec_sensors_state *st = iio_priv(indio_dev);
+
+	guard(mutex)(&st->core.cmd_lock);
+	st->core.param.cmd = MOTIONSENSE_CMD_SET_ACTIVITY;
+	switch (chan->type) {
+	case IIO_PROXIMITY:
+		st->core.param.set_activity.activity =
+			MOTIONSENSE_ACTIVITY_BODY_DETECTION;
+		break;
+	case IIO_ACTIVITY:
+		if (chan->channel2 == IIO_MOD_STILL) {
+			st->core.param.set_activity.activity =
+				MOTIONSENSE_ACTIVITY_SIG_MOTION;
+			break;
+		}
+		dev_warn(&indio_dev->dev, "Unknown activity: %d\n",
+			 chan->channel2);
+		return -EINVAL;
+	default:
+		dev_warn(&indio_dev->dev, "Unknown channel type: %d\n",
+			 chan->type);
+		return -EINVAL;
+	}
+	st->core.param.set_activity.enable = state;
+	return cros_ec_motion_send_host_cmd(&st->core, 0);
+}
+
+static int cros_ec_activity_push_data(struct iio_dev *indio_dev,
+				      s16 *data, s64 timestamp)
+{
+	struct ec_response_activity_data *activity_data =
+			(struct ec_response_activity_data *)data;
+	enum motionsensor_activity activity = activity_data->activity;
+	u8 state = activity_data->state;
+	const struct cros_ec_sensors_state *st = iio_priv(indio_dev);
+	const struct iio_chan_spec *chan;
+	enum iio_event_direction dir;
+	int index;
+
+	switch (activity) {
+	case MOTIONSENSE_ACTIVITY_BODY_DETECTION:
+		index = st->body_detection_channel_index;
+		dir = state ? IIO_EV_DIR_FALLING : IIO_EV_DIR_RISING;
+		break;
+	case MOTIONSENSE_ACTIVITY_SIG_MOTION:
+		index = st->sig_motion_channel_index;
+		dir = IIO_EV_DIR_FALLING;
+		break;
+	default:
+		dev_warn(&indio_dev->dev, "Unknown activity: %d\n", activity);
+		return 0;
+	}
+	chan = &st->channels[index];
+	iio_push_event(indio_dev,
+		       IIO_UNMOD_EVENT_CODE(chan->type, index, chan->event_spec[0].type, dir),
+		       timestamp);
+	return 0;
+}
+
+static irqreturn_t cros_ec_activity_capture(int irq, void *p)
+{
+	struct iio_poll_func *pf = p;
+	struct iio_dev *indio_dev = pf->indio_dev;
+
+	/*
+	 * This callback would be called when a software trigger is
+	 * used. But when this virtual sensor is present, it is guaranteed
+	 * the sensor hub is advanced enough to not need a software trigger.
+	 */
+	dev_warn(&indio_dev->dev, "%s: Not Expected\n", __func__);
+	return IRQ_NONE;
+}
+
+static const struct iio_info ec_sensors_info = {
+	.read_raw = &cros_ec_activity_sensors_read_raw,
+	.read_event_config = cros_ec_activity_read_event_config,
+	.write_event_config = cros_ec_activity_write_event_config,
+};
+
+static int cros_ec_sensors_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct cros_ec_device *ec_device = dev_get_drvdata(dev->parent);
+	struct iio_dev *indio_dev;
+	struct cros_ec_sensors_state *st;
+	struct iio_chan_spec *channel;
+	unsigned long activities;
+	int i, index, ret, nb_activities;
+
+	if (!ec_device) {
+		dev_warn(dev, "No CROS EC device found.\n");
+		return -EINVAL;
+	}
+
+	indio_dev = devm_iio_device_alloc(dev, sizeof(*st));
+	if (!indio_dev)
+		return -ENOMEM;
+
+	ret = cros_ec_sensors_core_init(pdev, indio_dev, true,
+					cros_ec_activity_capture);
+	if (ret)
+		return ret;
+
+	indio_dev->info = &ec_sensors_info;
+	st = iio_priv(indio_dev);
+	st->core.type = st->core.resp->info.type;
+	st->core.read_ec_sensors_data = cros_ec_sensors_read_cmd;
+
+	st->core.param.cmd = MOTIONSENSE_CMD_LIST_ACTIVITIES;
+	ret = cros_ec_motion_send_host_cmd(&st->core, 0);
+	if (ret)
+		return ret;
+
+	activities = st->core.resp->list_activities.enabled |
+		     st->core.resp->list_activities.disabled;
+	if (!activities)
+		return -ENODEV;
+
+	/* Allocate a channel per activity and one for timestamp */
+	nb_activities = hweight_long(activities) + 1;
+	st->channels = devm_kcalloc(dev, nb_activities,
+				    sizeof(*st->channels), GFP_KERNEL);
+	if (!st->channels)
+		return -ENOMEM;
+
+	channel = &st->channels[0];
+	index = 0;
+	for_each_set_bit(i, &activities, BITS_PER_LONG) {
+		/* List all available triggers */
+		if (i == MOTIONSENSE_ACTIVITY_BODY_DETECTION) {
+			channel->type = IIO_PROXIMITY;
+			channel->info_mask_separate = BIT(IIO_CHAN_INFO_RAW);
+			channel->event_spec = cros_ec_body_detect_events;
+			channel->num_event_specs =
+				ARRAY_SIZE(cros_ec_body_detect_events);
+			st->body_detection_channel_index = index;
+		} else {
+			channel->type = IIO_ACTIVITY;
+			channel->modified = 1;
+			channel->event_spec = cros_ec_activity_single_shot;
+			channel->num_event_specs =
+				ARRAY_SIZE(cros_ec_activity_single_shot);
+			if (i == MOTIONSENSE_ACTIVITY_SIG_MOTION) {
+				channel->channel2 = IIO_MOD_STILL;
+				st->sig_motion_channel_index = index;
+			} else {
+				dev_warn(dev, "Unknown activity: %d\n", i);
+				continue;
+			}
+		}
+		channel->ext_info = cros_ec_sensors_limited_info;
+		channel->scan_index = index++;
+		channel++;
+	}
+
+	/* Timestamp */
+	channel->scan_index = index;
+	channel->type = IIO_TIMESTAMP;
+	channel->channel = -1;
+	channel->scan_type.sign = 's';
+	channel->scan_type.realbits = 64;
+	channel->scan_type.storagebits = 64;
+
+	indio_dev->channels = st->channels;
+	indio_dev->num_channels = index + 1;
+
+	return cros_ec_sensors_core_register(dev, indio_dev,
+					     cros_ec_activity_push_data);
+}
+
+static struct platform_driver cros_ec_sensors_platform_driver = {
+	.driver = {
+		.name	= DRV_NAME,
+	},
+	.probe		= cros_ec_sensors_probe,
+};
+module_platform_driver(cros_ec_sensors_platform_driver);
+
+MODULE_DESCRIPTION("ChromeOS EC activity sensors driver");
+MODULE_ALIAS("platform:" DRV_NAME);
+MODULE_LICENSE("GPL v2");
diff --git a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
index 700ebcd68ff4..9ac80e4b7d75 100644
--- a/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
+++ b/drivers/iio/common/cros_ec_sensors/cros_ec_sensors_core.c
@@ -486,6 +486,16 @@ const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[] = {
 };
 EXPORT_SYMBOL_GPL(cros_ec_sensors_ext_info);
 
+const struct iio_chan_spec_ext_info cros_ec_sensors_limited_info[] = {
+	{
+		.name = "id",
+		.shared = IIO_SHARED_BY_ALL,
+		.read = cros_ec_sensors_id
+	},
+	{ }
+};
+EXPORT_SYMBOL_GPL(cros_ec_sensors_limited_info);
+
 /**
  * cros_ec_sensors_idx_to_reg - convert index into offset in shared memory
  * @st:		pointer to state information for device
diff --git a/include/linux/iio/common/cros_ec_sensors_core.h b/include/linux/iio/common/cros_ec_sensors_core.h
index e72167b96d27..bb966abcde53 100644
--- a/include/linux/iio/common/cros_ec_sensors_core.h
+++ b/include/linux/iio/common/cros_ec_sensors_core.h
@@ -126,5 +126,6 @@ extern const struct dev_pm_ops cros_ec_sensors_pm_ops;
 
 /* List of extended channel specification for all sensors. */
 extern const struct iio_chan_spec_ext_info cros_ec_sensors_ext_info[];
+extern const struct iio_chan_spec_ext_info cros_ec_sensors_limited_info[];
 
 #endif  /* __CROS_EC_SENSORS_CORE_H */
diff --git a/include/linux/platform_data/cros_ec_commands.h b/include/linux/platform_data/cros_ec_commands.h
index 1f4e4f2b89bb..c19b404e3d8d 100644
--- a/include/linux/platform_data/cros_ec_commands.h
+++ b/include/linux/platform_data/cros_ec_commands.h
@@ -2388,6 +2388,12 @@ enum motionsense_command {
 	 */
 	MOTIONSENSE_CMD_SENSOR_SCALE = 18,
 
+	/*
+	 * Activity management
+	 * Retrieve current status of given activity.
+	 */
+	MOTIONSENSE_CMD_GET_ACTIVITY = 20,
+
 	/* Number of motionsense sub-commands. */
 	MOTIONSENSE_NUM_CMDS
 };
@@ -2447,6 +2453,11 @@ enum motionsensor_orientation {
 	MOTIONSENSE_ORIENTATION_UNKNOWN = 4,
 };
 
+struct ec_response_activity_data {
+	uint8_t activity; /* motionsensor_activity */
+	uint8_t state;
+} __ec_todo_packed;
+
 struct ec_response_motion_sensor_data {
 	/* Flags for each sensor. */
 	uint8_t flags;
@@ -2460,8 +2471,7 @@ struct ec_response_motion_sensor_data {
 			uint32_t    timestamp;
 		};
 		struct __ec_todo_unpacked {
-			uint8_t     activity; /* motionsensor_activity */
-			uint8_t     state;
+			struct ec_response_activity_data activity_data;
 			int16_t     add_info[2];
 		};
 	};
@@ -2494,6 +2504,7 @@ enum motionsensor_activity {
 	MOTIONSENSE_ACTIVITY_SIG_MOTION = 1,
 	MOTIONSENSE_ACTIVITY_DOUBLE_TAP = 2,
 	MOTIONSENSE_ACTIVITY_ORIENTATION = 3,
+	MOTIONSENSE_ACTIVITY_BODY_DETECTION = 4,
 };
 
 struct ec_motion_sense_activity {
@@ -2671,6 +2682,7 @@ struct ec_params_motion_sense {
 			uint32_t max_data_vector;
 		} fifo_read;
 
+		/* Used for MOTIONSENSE_CMD_SET_ACTIVITY */
 		struct ec_motion_sense_activity set_activity;
 
 		/* Used for MOTIONSENSE_CMD_LID_ANGLE */
@@ -2716,6 +2728,12 @@ struct ec_params_motion_sense {
 			 */
 			int16_t hys_degree;
 		} tablet_mode_threshold;
+
+		/* Used for MOTIONSENSE_CMD_GET_ACTIVITY */
+		struct __ec_todo_unpacked {
+			uint8_t sensor_num;
+			uint8_t activity;  /* enum motionsensor_activity */
+		} get_activity;
 	};
 } __ec_todo_packed;
 
@@ -2833,6 +2851,10 @@ struct ec_response_motion_sense {
 			uint16_t hys_degree;
 		} tablet_mode_threshold;
 
+		/* USED for MOTIONSENSE_CMD_GET_ACTIVITY. */
+		struct __ec_todo_unpacked {
+			uint8_t     state;
+		} get_activity;
 	};
 } __ec_todo_packed;
 
-- 
cgit v1.2.3


From 97e6882ed1a16cd22184127abf2bc9b8202f37e0 Mon Sep 17 00:00:00 2001
From: Pop Ioan Daniel <pop.ioan-daniel@analog.com>
Date: Thu, 5 Jun 2025 18:09:40 +0300
Subject: iio: backend: update iio_backend_oversampling_ratio_set
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add chan parameter to iio_backend_oversampling_ratio_set() to allow
for contexts where the channel must be specified. Modify all
existing users.

Reviewed-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Signed-off-by: Pop Ioan Daniel <pop.ioan-daniel@analog.com>
Link: https://patch.msgid.link/20250605150948.3091827-3-pop.ioan-daniel@analog.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad4851.c           | 3 ++-
 drivers/iio/adc/adi-axi-adc.c      | 3 ++-
 drivers/iio/industrialio-backend.c | 3 ++-
 include/linux/iio/backend.h        | 3 ++-
 4 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad4851.c b/drivers/iio/adc/ad4851.c
index 1751f601e7f7..31e1e02c0ce3 100644
--- a/drivers/iio/adc/ad4851.c
+++ b/drivers/iio/adc/ad4851.c
@@ -320,7 +320,8 @@ static int ad4851_set_oversampling_ratio(struct iio_dev *indio_dev,
 			return ret;
 	}
 
-	ret = iio_backend_oversampling_ratio_set(st->back, osr);
+	/* Channel is ignored by the backend being used here */
+	ret = iio_backend_oversampling_ratio_set(st->back, 0, osr);
 	if (ret)
 		return ret;
 
diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c
index ec08a62f0ef7..d0ad318d5400 100644
--- a/drivers/iio/adc/adi-axi-adc.c
+++ b/drivers/iio/adc/adi-axi-adc.c
@@ -387,7 +387,8 @@ static int axi_adc_ad485x_data_size_set(struct iio_backend *back,
 }
 
 static int axi_adc_ad485x_oversampling_ratio_set(struct iio_backend *back,
-					  unsigned int ratio)
+						 unsigned int chan,
+						 unsigned int ratio)
 {
 	struct adi_axi_adc_state *st = iio_backend_get_priv(back);
 
diff --git a/drivers/iio/industrialio-backend.c b/drivers/iio/industrialio-backend.c
index 6b2d3dac52b3..decd74caf305 100644
--- a/drivers/iio/industrialio-backend.c
+++ b/drivers/iio/industrialio-backend.c
@@ -720,9 +720,10 @@ EXPORT_SYMBOL_NS_GPL(iio_backend_data_size_set, "IIO_BACKEND");
  * 0 on success, negative error number on failure.
  */
 int iio_backend_oversampling_ratio_set(struct iio_backend *back,
+				       unsigned int chan,
 				       unsigned int ratio)
 {
-	return iio_backend_op_call(back, oversampling_ratio_set, ratio);
+	return iio_backend_op_call(back, oversampling_ratio_set, chan, ratio);
 }
 EXPORT_SYMBOL_NS_GPL(iio_backend_oversampling_ratio_set, "IIO_BACKEND");
 
diff --git a/include/linux/iio/backend.h b/include/linux/iio/backend.h
index 1f528fbd9d11..7f815f3fed6a 100644
--- a/include/linux/iio/backend.h
+++ b/include/linux/iio/backend.h
@@ -155,7 +155,7 @@ struct iio_backend_ops {
 				  enum iio_backend_interface_type *type);
 	int (*data_size_set)(struct iio_backend *back, unsigned int size);
 	int (*oversampling_ratio_set)(struct iio_backend *back,
-				      unsigned int ratio);
+				      unsigned int chan, unsigned int ratio);
 	int (*read_raw)(struct iio_backend *back,
 			struct iio_chan_spec const *chan, int *val, int *val2,
 			long mask);
@@ -228,6 +228,7 @@ int iio_backend_interface_type_get(struct iio_backend *back,
 				   enum iio_backend_interface_type *type);
 int iio_backend_data_size_set(struct iio_backend *back, unsigned int size);
 int iio_backend_oversampling_ratio_set(struct iio_backend *back,
+				       unsigned int chan,
 				       unsigned int ratio);
 int iio_backend_read_raw(struct iio_backend *back,
 			 struct iio_chan_spec const *chan, int *val, int *val2,
-- 
cgit v1.2.3


From 12ffc3b1513ebc1f11ae77d053948504a94a68a6 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Fri, 13 Jun 2025 16:43:44 -0500
Subject: PM: Restrict swap use to later in the suspend sequence

Currently swap is restricted before drivers have had a chance to do
their prepare() PM callbacks. Restricting swap this early means that if
a driver needs to evict some content from memory into sawp in it's
prepare callback, it won't be able to.

On AMD dGPUs this can lead to failed suspends under memory pressure
situations as all VRAM must be evicted to system memory or swap.

Move the swap restriction to right after all devices have had a chance
to do the prepare() callback.  If there is any problem with the sequence,
restore swap in the appropriate dpm resume callbacks or error handling
paths.

Closes: https://github.com/ROCm/ROCK-Kernel-Driver/issues/174
Closes: https://gitlab.freedesktop.org/drm/amd/-/issues/2362
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Tested-by: Nat Wittstock <nat@fardog.io>
Tested-by: Lucian Langa <lucilanga@7pot.org>
Link: https://patch.msgid.link/20250613214413.4127087-1-superm1@kernel.org
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/power/main.c | 5 ++++-
 include/linux/suspend.h   | 5 +++++
 kernel/kexec_core.c       | 1 +
 kernel/power/hibernate.c  | 3 ---
 kernel/power/power.h      | 5 -----
 kernel/power/suspend.c    | 3 +--
 6 files changed, 11 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index eebe699fdf4f..bf77d28e959f 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -1236,6 +1236,7 @@ void dpm_complete(pm_message_t state)
  */
 void dpm_resume_end(pm_message_t state)
 {
+	pm_restore_gfp_mask();
 	dpm_resume(state);
 	dpm_complete(state);
 }
@@ -2176,8 +2177,10 @@ int dpm_suspend_start(pm_message_t state)
 	error = dpm_prepare(state);
 	if (error)
 		dpm_save_failed_step(SUSPEND_PREPARE);
-	else
+	else {
+		pm_restrict_gfp_mask();
 		error = dpm_suspend(state);
+	}
 
 	dpm_show_time(starttime, state, error, "start");
 	return error;
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index b1c76c8f2c82..6a3f92098872 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -446,6 +446,8 @@ extern int unregister_pm_notifier(struct notifier_block *nb);
 extern void ksys_sync_helper(void);
 extern void pm_report_hw_sleep_time(u64 t);
 extern void pm_report_max_hw_sleep(u64 t);
+void pm_restrict_gfp_mask(void);
+void pm_restore_gfp_mask(void);
 
 #define pm_notifier(fn, pri) {				\
 	static struct notifier_block fn##_nb =			\
@@ -492,6 +494,9 @@ static inline int unregister_pm_notifier(struct notifier_block *nb)
 static inline void pm_report_hw_sleep_time(u64 t) {};
 static inline void pm_report_max_hw_sleep(u64 t) {};
 
+static inline void pm_restrict_gfp_mask(void) {}
+static inline void pm_restore_gfp_mask(void) {}
+
 static inline void ksys_sync_helper(void) {}
 
 #define pm_notifier(fn, pri)	do { (void)(fn); } while (0)
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 9c59fa480b0b..3a9a9f240dbc 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -1136,6 +1136,7 @@ int kernel_kexec(void)
  Resume_devices:
 		dpm_resume_end(PMSG_RESTORE);
  Resume_console:
+		pm_restore_gfp_mask();
 		console_resume_all();
 		thaw_processes();
  Restore_console:
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 519fb09de5e0..9216e3b91d3b 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -423,7 +423,6 @@ int hibernation_snapshot(int platform_mode)
 	}
 
 	console_suspend_all();
-	pm_restrict_gfp_mask();
 
 	error = dpm_suspend(PMSG_FREEZE);
 
@@ -559,7 +558,6 @@ int hibernation_restore(int platform_mode)
 
 	pm_prepare_console();
 	console_suspend_all();
-	pm_restrict_gfp_mask();
 	error = dpm_suspend_start(PMSG_QUIESCE);
 	if (!error) {
 		error = resume_target_kernel(platform_mode);
@@ -571,7 +569,6 @@ int hibernation_restore(int platform_mode)
 		BUG_ON(!error);
 	}
 	dpm_resume_end(PMSG_RECOVER);
-	pm_restore_gfp_mask();
 	console_resume_all();
 	pm_restore_console();
 	return error;
diff --git a/kernel/power/power.h b/kernel/power/power.h
index cb1d71562002..7ccd709af93f 100644
--- a/kernel/power/power.h
+++ b/kernel/power/power.h
@@ -239,11 +239,6 @@ static inline void suspend_test_finish(const char *label) {}
 /* kernel/power/main.c */
 extern int pm_notifier_call_chain_robust(unsigned long val_up, unsigned long val_down);
 extern int pm_notifier_call_chain(unsigned long val);
-void pm_restrict_gfp_mask(void);
-void pm_restore_gfp_mask(void);
-#else
-static inline void pm_restrict_gfp_mask(void) {}
-static inline void pm_restore_gfp_mask(void) {}
 #endif
 
 #ifdef CONFIG_HIGHMEM
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 76b141b9aac0..bb608b68fb30 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -540,6 +540,7 @@ int suspend_devices_and_enter(suspend_state_t state)
 	return error;
 
  Recover_platform:
+	pm_restore_gfp_mask();
 	platform_recover(state);
 	goto Resume_devices;
 }
@@ -606,9 +607,7 @@ static int enter_state(suspend_state_t state)
 
 	trace_suspend_resume(TPS("suspend_enter"), state, false);
 	pm_pr_dbg("Suspending system (%s)\n", mem_sleep_labels[state]);
-	pm_restrict_gfp_mask();
 	error = suspend_devices_and_enter(state);
-	pm_restore_gfp_mask();
 
  Finish:
 	events_check_enabled = false;
-- 
cgit v1.2.3


From 08bf1663c21a3e815eda28fa242d84c945ca3b94 Mon Sep 17 00:00:00 2001
From: Bence Csókás <csokas.bence@prolan.hu>
Date: Tue, 10 Jun 2025 10:22:53 +0200
Subject: dmaengine: Add devm_dma_request_chan()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Expand the arsenal of devm functions for DMA devices, this time for
requesting channels.

Signed-off-by: Bence Csókás <csokas.bence@prolan.hu>
Link: https://lore.kernel.org/r/20250610082256.400492-2-csokas.bence@prolan.hu
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/dma/dmaengine.c   | 30 ++++++++++++++++++++++++++++++
 include/linux/dmaengine.h |  7 +++++++
 2 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 758fcd0546d8..ca13cd39330b 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -926,6 +926,36 @@ void dma_release_channel(struct dma_chan *chan)
 }
 EXPORT_SYMBOL_GPL(dma_release_channel);
 
+static void dmaenginem_release_channel(void *chan)
+{
+	dma_release_channel(chan);
+}
+
+/**
+ * devm_dma_request_chan - try to allocate an exclusive slave channel
+ * @dev:	pointer to client device structure
+ * @name:	slave channel name
+ *
+ * Returns pointer to appropriate DMA channel on success or an error pointer.
+ *
+ * The operation is managed and will be undone on driver detach.
+ */
+
+struct dma_chan *devm_dma_request_chan(struct device *dev, const char *name)
+{
+	struct dma_chan *chan = dma_request_chan(dev, name);
+	int ret = 0;
+
+	if (!IS_ERR(chan))
+		ret = devm_add_action_or_reset(dev, dmaenginem_release_channel, chan);
+
+	if (ret)
+		return ERR_PTR(ret);
+
+	return chan;
+}
+EXPORT_SYMBOL_GPL(devm_dma_request_chan);
+
 /**
  * dmaengine_get - register interest in dma_channels
  */
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index bb146c5ac3e4..6de7c05d6bd8 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -1524,6 +1524,7 @@ struct dma_chan *__dma_request_channel(const dma_cap_mask_t *mask,
 
 struct dma_chan *dma_request_chan(struct device *dev, const char *name);
 struct dma_chan *dma_request_chan_by_mask(const dma_cap_mask_t *mask);
+struct dma_chan *devm_dma_request_chan(struct device *dev, const char *name);
 
 void dma_release_channel(struct dma_chan *chan);
 int dma_get_slave_caps(struct dma_chan *chan, struct dma_slave_caps *caps);
@@ -1560,6 +1561,12 @@ static inline struct dma_chan *dma_request_chan_by_mask(
 {
 	return ERR_PTR(-ENODEV);
 }
+
+static inline struct dma_chan *devm_dma_request_chan(struct device *dev, const char *name)
+{
+	return ERR_PTR(-ENODEV);
+}
+
 static inline void dma_release_channel(struct dma_chan *chan)
 {
 }
-- 
cgit v1.2.3


From ce57bc9771411d6d27f2ca7b40396cbd7d684ba9 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 26 Jun 2025 18:23:07 +0300
Subject: regulator: core: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20250626152307.322627-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regulator/coupler.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/regulator/coupler.h b/include/linux/regulator/coupler.h
index 73291f280a23..5e314a4294fb 100644
--- a/include/linux/regulator/coupler.h
+++ b/include/linux/regulator/coupler.h
@@ -8,7 +8,8 @@
 #ifndef __LINUX_REGULATOR_COUPLER_H_
 #define __LINUX_REGULATOR_COUPLER_H_
 
-#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/types.h>
 #include <linux/suspend.h>
 
 struct regulator_coupler;
-- 
cgit v1.2.3


From 040ae95a984f04afa5d300a97d11643a1577aa72 Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 25 Jun 2025 18:21:55 +0800
Subject: net: Remove unused function first_net_device_rcu()

This is unused since commit f04565ddf52e ("dev: use name hash for
dev_seq_ops")

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250625102155.483570-1-yuehaibing@huawei.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h | 7 -------
 1 file changed, 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index db5bfd4e7ec8..5847c20994d3 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3316,13 +3316,6 @@ static inline struct net_device *first_net_device(struct net *net)
 		net_device_entry(net->dev_base_head.next);
 }
 
-static inline struct net_device *first_net_device_rcu(struct net *net)
-{
-	struct list_head *lh = rcu_dereference(list_next_rcu(&net->dev_base_head));
-
-	return lh == &net->dev_base_head ? NULL : net_device_entry(lh);
-}
-
 int netdev_boot_setup_check(struct net_device *dev);
 struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type,
 				   const char *hwaddr);
-- 
cgit v1.2.3


From 017a6f7e7e25017eef9c30946cb0e7c803cb3f35 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 27 Jun 2025 13:34:15 +0300
Subject: firmware: sysfb: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Reviewed-by: Javier Martinez Canillas <javierm@redhat.com>
Reviewed-by: Thomas Zimmermann <tzimmermann@suse.de>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250627103454.702606-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Javier Martinez Canillas <javierm@redhat.com>
---
 include/linux/sysfb.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h
index 07cbab516942..b449665c686a 100644
--- a/include/linux/sysfb.h
+++ b/include/linux/sysfb.h
@@ -7,9 +7,13 @@
  * Copyright (c) 2012-2013 David Herrmann <dh.herrmann@gmail.com>
  */
 
-#include <linux/kernel.h>
+#include <linux/err.h>
+#include <linux/types.h>
+
 #include <linux/platform_data/simplefb.h>
 
+struct device;
+struct platform_device;
 struct screen_info;
 
 enum {
-- 
cgit v1.2.3


From 792ea7b6cafa46f8e6d6f40c557e614358a89520 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 9 Jun 2025 17:41:31 -0300
Subject: iommu: Remove ops->pgsize_bitmap

No driver uses it now, remove the core code.

Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Link: https://lore.kernel.org/r/7-v2-68a2e1ba507c+1fb-iommu_rm_ops_pgsize_jgg@nvidia.com
Signed-off-by: Joerg Roedel <joerg.roedel@amd.com>
---
 drivers/iommu/iommu.c | 7 -------
 include/linux/iommu.h | 2 --
 2 files changed, 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index a4b606c591da..060ebe330ee1 100644
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -2002,13 +2002,6 @@ static void iommu_domain_init(struct iommu_domain *domain, unsigned int type,
 	domain->owner = ops;
 	if (!domain->ops)
 		domain->ops = ops->default_domain_ops;
-
-	/*
-	 * If not already set, assume all sizes by default; the driver
-	 * may override this later
-	 */
-	if (!domain->pgsize_bitmap)
-		domain->pgsize_bitmap = ops->pgsize_bitmap;
 }
 
 static struct iommu_domain *
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 156732807994..7073be1d8841 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -604,7 +604,6 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
  *                It is required to call iommufd_viommu_alloc() helper for
  *                a bundled allocation of the core and the driver structures,
  *                using the given @ictx pointer.
- * @pgsize_bitmap: bitmap of all possible supported page sizes
  * @owner: Driver module providing these ops
  * @identity_domain: An always available, always attachable identity
  *                   translation.
@@ -659,7 +658,6 @@ struct iommu_ops {
 		struct iommufd_ctx *ictx, unsigned int viommu_type);
 
 	const struct iommu_domain_ops *default_domain_ops;
-	unsigned long pgsize_bitmap;
 	struct module *owner;
 	struct iommu_domain *identity_domain;
 	struct iommu_domain *blocked_domain;
-- 
cgit v1.2.3


From 05bc6e6290f91d2d40086ab4ef52da21c14ec4b6 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Wed, 25 Jun 2025 20:38:31 +0200
Subject: timekeeping: Provide time getters for auxiliary clocks

Provide interfaces similar to the ktime_get*() family which provide access
to the auxiliary clocks.

These interfaces have a boolean return value, which indicates whether the
accessed clock is valid or not.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/all/20250625183757.868342628@linutronix.de
---
 include/linux/posix-timers.h |  5 ++++
 include/linux/timekeeping.h  | 11 ++++++++
 kernel/time/timekeeping.c    | 65 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 81 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/posix-timers.h b/include/linux/posix-timers.h
index dd48c64b605e..4d3dbcef379e 100644
--- a/include/linux/posix-timers.h
+++ b/include/linux/posix-timers.h
@@ -37,6 +37,11 @@ static inline int clockid_to_fd(const clockid_t clk)
 	return ~(clk >> 3);
 }
 
+static inline bool clockid_aux_valid(clockid_t id)
+{
+	return IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS) && id >= CLOCK_AUX && id <= CLOCK_AUX_LAST;
+}
+
 #ifdef CONFIG_POSIX_TIMERS
 
 #include <linux/signal_types.h>
diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 542773650200..de9a3b7d7d0d 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -263,6 +263,17 @@ extern bool timekeeping_rtc_skipresume(void);
 
 extern void timekeeping_inject_sleeptime64(const struct timespec64 *delta);
 
+/*
+ * Auxiliary clock interfaces
+ */
+#ifdef CONFIG_POSIX_AUX_CLOCKS
+extern bool ktime_get_aux(clockid_t id, ktime_t *kt);
+extern bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt);
+#else
+static inline bool ktime_get_aux(clockid_t id, ktime_t *kt) { return false; }
+static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { return false; }
+#endif
+
 /**
  * struct system_time_snapshot - simultaneous raw/real time capture with
  *				 counter value
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index ee9757018341..c7d2913e68c3 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -2664,6 +2664,18 @@ EXPORT_SYMBOL(hardpps);
  */
 static unsigned long aux_timekeepers;
 
+static inline unsigned int clockid_to_tkid(unsigned int id)
+{
+	return TIMEKEEPER_AUX_FIRST + id - CLOCK_AUX;
+}
+
+static inline struct tk_data *aux_get_tk_data(clockid_t id)
+{
+	if (!clockid_aux_valid(id))
+		return NULL;
+	return &timekeeper_data[clockid_to_tkid(id)];
+}
+
 /* Invoked from timekeeping after a clocksource change */
 static void tk_aux_update_clocksource(void)
 {
@@ -2684,6 +2696,59 @@ static void tk_aux_update_clocksource(void)
 	}
 }
 
+/**
+ * ktime_get_aux - Get time for a AUX clock
+ * @id:	ID of the clock to read (CLOCK_AUX...)
+ * @kt:	Pointer to ktime_t to store the time stamp
+ *
+ * Returns: True if the timestamp is valid, false otherwise
+ */
+bool ktime_get_aux(clockid_t id, ktime_t *kt)
+{
+	struct tk_data *aux_tkd = aux_get_tk_data(id);
+	struct timekeeper *aux_tk;
+	unsigned int seq;
+	ktime_t base;
+	u64 nsecs;
+
+	WARN_ON(timekeeping_suspended);
+
+	if (!aux_tkd)
+		return false;
+
+	aux_tk = &aux_tkd->timekeeper;
+	do {
+		seq = read_seqcount_begin(&aux_tkd->seq);
+		if (!aux_tk->clock_valid)
+			return false;
+
+		base = ktime_add(aux_tk->tkr_mono.base, aux_tk->offs_aux);
+		nsecs = timekeeping_get_ns(&aux_tk->tkr_mono);
+	} while (read_seqcount_retry(&aux_tkd->seq, seq));
+
+	*kt = ktime_add_ns(base, nsecs);
+	return true;
+}
+EXPORT_SYMBOL_GPL(ktime_get_aux);
+
+/**
+ * ktime_get_aux_ts64 - Get time for a AUX clock
+ * @id:	ID of the clock to read (CLOCK_AUX...)
+ * @ts:	Pointer to timespec64 to store the time stamp
+ *
+ * Returns: True if the timestamp is valid, false otherwise
+ */
+bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *ts)
+{
+	ktime_t now;
+
+	if (!ktime_get_aux(id, &now))
+		return false;
+	*ts = ktime_to_timespec64(now);
+	return true;
+}
+EXPORT_SYMBOL_GPL(ktime_get_aux_ts64);
+
 static __init void tk_aux_setup(void)
 {
 	for (int i = TIMEKEEPER_AUX_FIRST; i <= TIMEKEEPER_AUX_LAST; i++)
-- 
cgit v1.2.3


From c5b60592886f97b01503c1bb553f88d6a7df42ea Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Fri, 27 Jun 2025 09:58:54 +0200
Subject: interconnect: avoid memory allocation when 'icc_bw_lock' is held

The 'icc_bw_lock' mutex is introduced in commit af42269c3523
("interconnect: Fix locking for runpm vs reclaim") in order to decouple
serialization of bw aggregation from codepaths that require memory
allocation.

However commit d30f83d278a9 ("interconnect: core: Add dynamic id
allocation support") added a devm_kasprintf() call into a path protected
by the 'icc_bw_lock' which causes the following lockdep warning on
machines like the Lenovo ThinkPad X13s:

    ======================================================
    WARNING: possible circular locking dependency detected
    6.16.0-rc3 #15 Not tainted
    ------------------------------------------------------
    (udev-worker)/342 is trying to acquire lock:
    ffffb973f7ec4638 (fs_reclaim){+.+.}-{0:0}, at: __kmalloc_node_track_caller_noprof+0xa0/0x3e0

    but task is already holding lock:
    ffffb973f7f7f0e8 (icc_bw_lock){+.+.}-{4:4}, at: icc_node_add+0x44/0x154

    which lock already depends on the new lock.

    the existing dependency chain (in reverse order) is:

    -> #1 (icc_bw_lock){+.+.}-{4:4}:
           icc_init+0x48/0x108
           do_one_initcall+0x64/0x30c
           kernel_init_freeable+0x27c/0x500
           kernel_init+0x20/0x1d8
           ret_from_fork+0x10/0x20

    -> #0 (fs_reclaim){+.+.}-{0:0}:
           __lock_acquire+0x136c/0x2114
           lock_acquire+0x1c8/0x354
           fs_reclaim_acquire+0x74/0xa8
           __kmalloc_node_track_caller_noprof+0xa0/0x3e0
           devm_kmalloc+0x54/0x124
           devm_kvasprintf+0x74/0xd4
           devm_kasprintf+0x58/0x80
           icc_node_add+0xb4/0x154
           qcom_osm_l3_probe+0x20c/0x314 [icc_osm_l3]
           platform_probe+0x68/0xd8
           really_probe+0xc0/0x38c
           __driver_probe_device+0x7c/0x160
           driver_probe_device+0x40/0x110
           __driver_attach+0xfc/0x208
           bus_for_each_dev+0x74/0xd0
           driver_attach+0x24/0x30
           bus_add_driver+0x110/0x234
           driver_register+0x60/0x128
           __platform_driver_register+0x24/0x30
           osm_l3_driver_init+0x20/0x1000 [icc_osm_l3]
           do_one_initcall+0x64/0x30c
           do_init_module+0x58/0x23c
           load_module+0x1df8/0x1f70
           init_module_from_file+0x88/0xc4
           idempotent_init_module+0x188/0x280
           __arm64_sys_finit_module+0x6c/0xd8
           invoke_syscall+0x48/0x110
           el0_svc_common.constprop.0+0xc0/0xe0
           do_el0_svc+0x1c/0x28
           el0_svc+0x4c/0x158
           el0t_64_sync_handler+0xc8/0xcc
           el0t_64_sync+0x198/0x19c

    other info that might help us debug this:

     Possible unsafe locking scenario:

           CPU0                    CPU1
           ----                    ----
      lock(icc_bw_lock);
                                   lock(fs_reclaim);
                                   lock(icc_bw_lock);
      lock(fs_reclaim);

     *** DEADLOCK ***

The icc_node_add() functions is not designed to fail, and as such it
should not do any memory allocation. In order to avoid this, add a new
helper function for the name generation to be called by drivers which
are using the new dynamic id feature.

Fixes: d30f83d278a9 ("interconnect: core: Add dynamic id allocation support")
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Link: https://lore.kernel.org/r/20250625-icc-bw-lockdep-v3-1-2b8f8b8987c4@gmail.com
Co-developed-by: Johan Hovold <johan+linaro@kernel.org>
Signed-off-by: Johan Hovold <johan+linaro@kernel.org>
Link: https://lore.kernel.org/r/20250627075854.26943-1-johan+linaro@kernel.org
Signed-off-by: Georgi Djakov <djakov@kernel.org>
---
 drivers/interconnect/core.c           | 29 +++++++++++++++++++++++++----
 drivers/interconnect/qcom/icc-rpmh.c  |  7 ++++++-
 drivers/interconnect/qcom/osm-l3.c    |  7 ++++++-
 include/linux/interconnect-provider.h |  7 +++++++
 4 files changed, 44 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/interconnect/core.c b/drivers/interconnect/core.c
index 3a41b2717edd..3ebf37ddfc18 100644
--- a/drivers/interconnect/core.c
+++ b/drivers/interconnect/core.c
@@ -909,10 +909,35 @@ void icc_node_destroy(int id)
 		return;
 
 	kfree(node->links);
+	if (node->id >= ICC_DYN_ID_START)
+		kfree(node->name);
 	kfree(node);
 }
 EXPORT_SYMBOL_GPL(icc_node_destroy);
 
+/**
+ * icc_node_set_name() - set node name
+ * @node: node
+ * @provider: node provider
+ * @name: node name
+ *
+ * Return: 0 on success, or -ENOMEM on allocation failure
+ */
+int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, const char *name)
+{
+	if (node->id >= ICC_DYN_ID_START) {
+		node->name = kasprintf(GFP_KERNEL, "%s@%s", name,
+				       dev_name(provider->dev));
+		if (!node->name)
+			return -ENOMEM;
+	} else {
+		node->name = name;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(icc_node_set_name);
+
 /**
  * icc_link_nodes() - create link between two nodes
  * @src_node: source node
@@ -1041,10 +1066,6 @@ void icc_node_add(struct icc_node *node, struct icc_provider *provider)
 	node->avg_bw = node->init_avg;
 	node->peak_bw = node->init_peak;
 
-	if (node->id >= ICC_DYN_ID_START)
-		node->name = devm_kasprintf(provider->dev, GFP_KERNEL, "%s@%s",
-					    node->name, dev_name(provider->dev));
-
 	if (node->avg_bw || node->peak_bw) {
 		if (provider->pre_aggregate)
 			provider->pre_aggregate(node);
diff --git a/drivers/interconnect/qcom/icc-rpmh.c b/drivers/interconnect/qcom/icc-rpmh.c
index 41bfc6e7ee1d..001404e91041 100644
--- a/drivers/interconnect/qcom/icc-rpmh.c
+++ b/drivers/interconnect/qcom/icc-rpmh.c
@@ -293,7 +293,12 @@ int qcom_icc_rpmh_probe(struct platform_device *pdev)
 			goto err_remove_nodes;
 		}
 
-		node->name = qn->name;
+		ret = icc_node_set_name(node, provider, qn->name);
+		if (ret) {
+			icc_node_destroy(node->id);
+			goto err_remove_nodes;
+		}
+
 		node->data = qn;
 		icc_node_add(node, provider);
 
diff --git a/drivers/interconnect/qcom/osm-l3.c b/drivers/interconnect/qcom/osm-l3.c
index baecbf2533f7..b33f00da1880 100644
--- a/drivers/interconnect/qcom/osm-l3.c
+++ b/drivers/interconnect/qcom/osm-l3.c
@@ -236,7 +236,12 @@ static int qcom_osm_l3_probe(struct platform_device *pdev)
 			goto err;
 		}
 
-		node->name = qnodes[i]->name;
+		ret = icc_node_set_name(node, provider, qnodes[i]->name);
+		if (ret) {
+			icc_node_destroy(node->id);
+			goto err;
+		}
+
 		/* Cast away const and add it back in qcom_osm_l3_set() */
 		node->data = (void *)qnodes[i];
 		icc_node_add(node, provider);
diff --git a/include/linux/interconnect-provider.h b/include/linux/interconnect-provider.h
index 55cfebc658e6..8a2f652a05ff 100644
--- a/include/linux/interconnect-provider.h
+++ b/include/linux/interconnect-provider.h
@@ -119,6 +119,7 @@ int icc_std_aggregate(struct icc_node *node, u32 tag, u32 avg_bw,
 struct icc_node *icc_node_create_dyn(void);
 struct icc_node *icc_node_create(int id);
 void icc_node_destroy(int id);
+int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider, const char *name);
 int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node);
 int icc_link_create(struct icc_node *node, const int dst_id);
 void icc_node_add(struct icc_node *node, struct icc_provider *provider);
@@ -152,6 +153,12 @@ static inline void icc_node_destroy(int id)
 {
 }
 
+static inline int icc_node_set_name(struct icc_node *node, const struct icc_provider *provider,
+				    const char *name)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline int icc_link_nodes(struct icc_node *src_node, struct icc_node **dst_node)
 {
 	return -EOPNOTSUPP;
-- 
cgit v1.2.3


From 58256a26bfb37a94738dd65618b1f31f460f8d91 Mon Sep 17 00:00:00 2001
From: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Date: Thu, 26 Jun 2025 15:52:18 +0200
Subject: dpll: add reference sync get/set

Define function for reference sync pin registration and callback ops to
set/get current feature state.

Implement netlink handler to fill netlink messages with reference sync
pin configuration of capable pins (pin-get).

Implement netlink handler to call proper ops and configure reference
sync pin state (pin-set).

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Milena Olech <milena.olech@intel.com>
Reviewed-by: Jiri Pirko <jiri@nvidia.com>
Signed-off-by: Arkadiusz Kubalewski <arkadiusz.kubalewski@intel.com>
Link: https://patch.msgid.link/20250626135219.1769350-3-arkadiusz.kubalewski@intel.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/dpll/dpll_core.c    |  45 +++++++++++
 drivers/dpll/dpll_core.h    |   2 +
 drivers/dpll/dpll_netlink.c | 190 +++++++++++++++++++++++++++++++++++++++-----
 drivers/dpll/dpll_netlink.h |   2 +
 include/linux/dpll.h        |  13 +++
 5 files changed, 233 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/dpll/dpll_core.c b/drivers/dpll/dpll_core.c
index 20bdc52f63a5..a461095efd8a 100644
--- a/drivers/dpll/dpll_core.c
+++ b/drivers/dpll/dpll_core.c
@@ -506,6 +506,7 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 	refcount_set(&pin->refcount, 1);
 	xa_init_flags(&pin->dpll_refs, XA_FLAGS_ALLOC);
 	xa_init_flags(&pin->parent_refs, XA_FLAGS_ALLOC);
+	xa_init_flags(&pin->ref_sync_pins, XA_FLAGS_ALLOC);
 	ret = xa_alloc_cyclic(&dpll_pin_xa, &pin->id, pin, xa_limit_32b,
 			      &dpll_pin_xa_id, GFP_KERNEL);
 	if (ret < 0)
@@ -514,6 +515,7 @@ dpll_pin_alloc(u64 clock_id, u32 pin_idx, struct module *module,
 err_xa_alloc:
 	xa_destroy(&pin->dpll_refs);
 	xa_destroy(&pin->parent_refs);
+	xa_destroy(&pin->ref_sync_pins);
 	dpll_pin_prop_free(&pin->prop);
 err_pin_prop:
 	kfree(pin);
@@ -595,6 +597,7 @@ void dpll_pin_put(struct dpll_pin *pin)
 		xa_erase(&dpll_pin_xa, pin->id);
 		xa_destroy(&pin->dpll_refs);
 		xa_destroy(&pin->parent_refs);
+		xa_destroy(&pin->ref_sync_pins);
 		dpll_pin_prop_free(&pin->prop);
 		kfree_rcu(pin, rcu);
 	}
@@ -659,11 +662,26 @@ dpll_pin_register(struct dpll_device *dpll, struct dpll_pin *pin,
 }
 EXPORT_SYMBOL_GPL(dpll_pin_register);
 
+static void dpll_pin_ref_sync_pair_del(u32 ref_sync_pin_id)
+{
+	struct dpll_pin *pin, *ref_sync_pin;
+	unsigned long i;
+
+	xa_for_each(&dpll_pin_xa, i, pin) {
+		ref_sync_pin = xa_load(&pin->ref_sync_pins, ref_sync_pin_id);
+		if (ref_sync_pin) {
+			xa_erase(&pin->ref_sync_pins, ref_sync_pin_id);
+			__dpll_pin_change_ntf(pin);
+		}
+	}
+}
+
 static void
 __dpll_pin_unregister(struct dpll_device *dpll, struct dpll_pin *pin,
 		      const struct dpll_pin_ops *ops, void *priv, void *cookie)
 {
 	ASSERT_DPLL_PIN_REGISTERED(pin);
+	dpll_pin_ref_sync_pair_del(pin->id);
 	dpll_xa_ref_pin_del(&dpll->pin_refs, pin, ops, priv, cookie);
 	dpll_xa_ref_dpll_del(&pin->dpll_refs, dpll, ops, priv, cookie);
 	if (xa_empty(&pin->dpll_refs))
@@ -783,6 +801,33 @@ void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin,
 }
 EXPORT_SYMBOL_GPL(dpll_pin_on_pin_unregister);
 
+/**
+ * dpll_pin_ref_sync_pair_add - create a reference sync signal pin pair
+ * @pin: pin which produces the base frequency
+ * @ref_sync_pin: pin which produces the sync signal
+ *
+ * Once pins are paired, the user-space configuration of reference sync pair
+ * is possible.
+ * Context: Acquires a lock (dpll_lock)
+ * Return:
+ * * 0 on success
+ * * negative - error value
+ */
+int dpll_pin_ref_sync_pair_add(struct dpll_pin *pin,
+			       struct dpll_pin *ref_sync_pin)
+{
+	int ret;
+
+	mutex_lock(&dpll_lock);
+	ret = xa_insert(&pin->ref_sync_pins, ref_sync_pin->id,
+			ref_sync_pin, GFP_KERNEL);
+	__dpll_pin_change_ntf(pin);
+	mutex_unlock(&dpll_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(dpll_pin_ref_sync_pair_add);
+
 static struct dpll_device_registration *
 dpll_device_registration_first(struct dpll_device *dpll)
 {
diff --git a/drivers/dpll/dpll_core.h b/drivers/dpll/dpll_core.h
index 9b11e637397b..8ce969bbeb64 100644
--- a/drivers/dpll/dpll_core.h
+++ b/drivers/dpll/dpll_core.h
@@ -44,6 +44,7 @@ struct dpll_device {
  * @module:		module of creator
  * @dpll_refs:		hold referencees to dplls pin was registered with
  * @parent_refs:	hold references to parent pins pin was registered with
+ * @ref_sync_pins:	hold references to pins for Reference SYNC feature
  * @prop:		pin properties copied from the registerer
  * @refcount:		refcount
  * @rcu:		rcu_head for kfree_rcu()
@@ -55,6 +56,7 @@ struct dpll_pin {
 	struct module *module;
 	struct xarray dpll_refs;
 	struct xarray parent_refs;
+	struct xarray ref_sync_pins;
 	struct dpll_pin_properties prop;
 	refcount_t refcount;
 	struct rcu_head rcu;
diff --git a/drivers/dpll/dpll_netlink.c b/drivers/dpll/dpll_netlink.c
index 4619aaa18b9c..036f21cac0a9 100644
--- a/drivers/dpll/dpll_netlink.c
+++ b/drivers/dpll/dpll_netlink.c
@@ -48,6 +48,24 @@ dpll_msg_add_dev_parent_handle(struct sk_buff *msg, u32 id)
 	return 0;
 }
 
+static bool dpll_pin_available(struct dpll_pin *pin)
+{
+	struct dpll_pin_ref *par_ref;
+	unsigned long i;
+
+	if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED))
+		return false;
+	xa_for_each(&pin->parent_refs, i, par_ref)
+		if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id,
+				DPLL_REGISTERED))
+			return true;
+	xa_for_each(&pin->dpll_refs, i, par_ref)
+		if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id,
+				DPLL_REGISTERED))
+			return true;
+	return false;
+}
+
 /**
  * dpll_msg_add_pin_handle - attach pin handle attribute to a given message
  * @msg: pointer to sk_buff message to attach a pin handle
@@ -428,6 +446,47 @@ nest_cancel:
 	return -EMSGSIZE;
 }
 
+static int
+dpll_msg_add_pin_ref_sync(struct sk_buff *msg, struct dpll_pin *pin,
+			  struct dpll_pin_ref *ref,
+			  struct netlink_ext_ack *extack)
+{
+	const struct dpll_pin_ops *ops = dpll_pin_ops(ref);
+	struct dpll_device *dpll = ref->dpll;
+	void *pin_priv, *ref_sync_pin_priv;
+	struct dpll_pin *ref_sync_pin;
+	enum dpll_pin_state state;
+	struct nlattr *nest;
+	unsigned long index;
+	int ret;
+
+	pin_priv = dpll_pin_on_dpll_priv(dpll, pin);
+	xa_for_each(&pin->ref_sync_pins, index, ref_sync_pin) {
+		if (!dpll_pin_available(ref_sync_pin))
+			continue;
+		ref_sync_pin_priv = dpll_pin_on_dpll_priv(dpll, ref_sync_pin);
+		if (WARN_ON(!ops->ref_sync_get))
+			return -EOPNOTSUPP;
+		ret = ops->ref_sync_get(pin, pin_priv, ref_sync_pin,
+					ref_sync_pin_priv, &state, extack);
+		if (ret)
+			return ret;
+		nest = nla_nest_start(msg, DPLL_A_PIN_REFERENCE_SYNC);
+		if (!nest)
+			return -EMSGSIZE;
+		if (nla_put_s32(msg, DPLL_A_PIN_ID, ref_sync_pin->id))
+			goto nest_cancel;
+		if (nla_put_s32(msg, DPLL_A_PIN_STATE, state))
+			goto nest_cancel;
+		nla_nest_end(msg, nest);
+	}
+	return 0;
+
+nest_cancel:
+	nla_nest_cancel(msg, nest);
+	return -EMSGSIZE;
+}
+
 static bool dpll_pin_is_freq_supported(struct dpll_pin *pin, u32 freq)
 {
 	int fs;
@@ -570,6 +629,10 @@ dpll_cmd_pin_get_one(struct sk_buff *msg, struct dpll_pin *pin,
 	if (ret)
 		return ret;
 	ret = dpll_msg_add_pin_esync(msg, pin, ref, extack);
+	if (ret)
+		return ret;
+	if (!xa_empty(&pin->ref_sync_pins))
+		ret = dpll_msg_add_pin_ref_sync(msg, pin, ref, extack);
 	if (ret)
 		return ret;
 	if (xa_empty(&pin->parent_refs))
@@ -665,24 +728,6 @@ __dpll_device_change_ntf(struct dpll_device *dpll)
 	return dpll_device_event_send(DPLL_CMD_DEVICE_CHANGE_NTF, dpll);
 }
 
-static bool dpll_pin_available(struct dpll_pin *pin)
-{
-	struct dpll_pin_ref *par_ref;
-	unsigned long i;
-
-	if (!xa_get_mark(&dpll_pin_xa, pin->id, DPLL_REGISTERED))
-		return false;
-	xa_for_each(&pin->parent_refs, i, par_ref)
-		if (xa_get_mark(&dpll_pin_xa, par_ref->pin->id,
-				DPLL_REGISTERED))
-			return true;
-	xa_for_each(&pin->dpll_refs, i, par_ref)
-		if (xa_get_mark(&dpll_device_xa, par_ref->dpll->id,
-				DPLL_REGISTERED))
-			return true;
-	return false;
-}
-
 /**
  * dpll_device_change_ntf - notify that the dpll device has been changed
  * @dpll: registered dpll pointer
@@ -745,7 +790,7 @@ int dpll_pin_delete_ntf(struct dpll_pin *pin)
 	return dpll_pin_event_send(DPLL_CMD_PIN_DELETE_NTF, pin);
 }
 
-static int __dpll_pin_change_ntf(struct dpll_pin *pin)
+int __dpll_pin_change_ntf(struct dpll_pin *pin)
 {
 	return dpll_pin_event_send(DPLL_CMD_PIN_CHANGE_NTF, pin);
 }
@@ -935,6 +980,108 @@ rollback:
 	return ret;
 }
 
+static int
+dpll_pin_ref_sync_state_set(struct dpll_pin *pin,
+			    unsigned long ref_sync_pin_idx,
+			    const enum dpll_pin_state state,
+			    struct netlink_ext_ack *extack)
+
+{
+	struct dpll_pin_ref *ref, *failed;
+	const struct dpll_pin_ops *ops;
+	enum dpll_pin_state old_state;
+	struct dpll_pin *ref_sync_pin;
+	struct dpll_device *dpll;
+	unsigned long i;
+	int ret;
+
+	ref_sync_pin = xa_find(&pin->ref_sync_pins, &ref_sync_pin_idx,
+			       ULONG_MAX, XA_PRESENT);
+	if (!ref_sync_pin) {
+		NL_SET_ERR_MSG(extack, "reference sync pin not found");
+		return -EINVAL;
+	}
+	if (!dpll_pin_available(ref_sync_pin)) {
+		NL_SET_ERR_MSG(extack, "reference sync pin not available");
+		return -EINVAL;
+	}
+	ref = dpll_xa_ref_dpll_first(&pin->dpll_refs);
+	ASSERT_NOT_NULL(ref);
+	ops = dpll_pin_ops(ref);
+	if (!ops->ref_sync_set || !ops->ref_sync_get) {
+		NL_SET_ERR_MSG(extack, "reference sync not supported by this pin");
+		return -EOPNOTSUPP;
+	}
+	dpll = ref->dpll;
+	ret = ops->ref_sync_get(pin, dpll_pin_on_dpll_priv(dpll, pin),
+				ref_sync_pin,
+				dpll_pin_on_dpll_priv(dpll, ref_sync_pin),
+				&old_state, extack);
+	if (ret) {
+		NL_SET_ERR_MSG(extack, "unable to get old reference sync state");
+		return ret;
+	}
+	if (state == old_state)
+		return 0;
+	xa_for_each(&pin->dpll_refs, i, ref) {
+		ops = dpll_pin_ops(ref);
+		dpll = ref->dpll;
+		ret = ops->ref_sync_set(pin, dpll_pin_on_dpll_priv(dpll, pin),
+					ref_sync_pin,
+					dpll_pin_on_dpll_priv(dpll,
+							      ref_sync_pin),
+					state, extack);
+		if (ret) {
+			failed = ref;
+			NL_SET_ERR_MSG_FMT(extack, "reference sync set failed for dpll_id:%u",
+					   dpll->id);
+			goto rollback;
+		}
+	}
+	__dpll_pin_change_ntf(pin);
+
+	return 0;
+
+rollback:
+	xa_for_each(&pin->dpll_refs, i, ref) {
+		if (ref == failed)
+			break;
+		ops = dpll_pin_ops(ref);
+		dpll = ref->dpll;
+		if (ops->ref_sync_set(pin, dpll_pin_on_dpll_priv(dpll, pin),
+				      ref_sync_pin,
+				      dpll_pin_on_dpll_priv(dpll, ref_sync_pin),
+				      old_state, extack))
+			NL_SET_ERR_MSG(extack, "set reference sync rollback failed");
+	}
+	return ret;
+}
+
+static int
+dpll_pin_ref_sync_set(struct dpll_pin *pin, struct nlattr *nest,
+		      struct netlink_ext_ack *extack)
+{
+	struct nlattr *tb[DPLL_A_PIN_MAX + 1];
+	enum dpll_pin_state state;
+	u32 sync_pin_id;
+
+	nla_parse_nested(tb, DPLL_A_PIN_MAX, nest,
+			 dpll_reference_sync_nl_policy, extack);
+	if (!tb[DPLL_A_PIN_ID]) {
+		NL_SET_ERR_MSG(extack, "sync pin id expected");
+		return -EINVAL;
+	}
+	sync_pin_id = nla_get_u32(tb[DPLL_A_PIN_ID]);
+
+	if (!tb[DPLL_A_PIN_STATE]) {
+		NL_SET_ERR_MSG(extack, "sync pin state expected");
+		return -EINVAL;
+	}
+	state = nla_get_u32(tb[DPLL_A_PIN_STATE]);
+
+	return dpll_pin_ref_sync_state_set(pin, sync_pin_id, state, extack);
+}
+
 static int
 dpll_pin_on_pin_state_set(struct dpll_pin *pin, u32 parent_idx,
 			  enum dpll_pin_state state,
@@ -1241,6 +1388,11 @@ dpll_pin_set_from_nlattr(struct dpll_pin *pin, struct genl_info *info)
 			if (ret)
 				return ret;
 			break;
+		case DPLL_A_PIN_REFERENCE_SYNC:
+			ret = dpll_pin_ref_sync_set(pin, a, info->extack);
+			if (ret)
+				return ret;
+			break;
 		}
 	}
 
diff --git a/drivers/dpll/dpll_netlink.h b/drivers/dpll/dpll_netlink.h
index a9cfd55f57fc..dd28b56d27c5 100644
--- a/drivers/dpll/dpll_netlink.h
+++ b/drivers/dpll/dpll_netlink.h
@@ -11,3 +11,5 @@ int dpll_device_delete_ntf(struct dpll_device *dpll);
 int dpll_pin_create_ntf(struct dpll_pin *pin);
 
 int dpll_pin_delete_ntf(struct dpll_pin *pin);
+
+int __dpll_pin_change_ntf(struct dpll_pin *pin);
diff --git a/include/linux/dpll.h b/include/linux/dpll.h
index 6ad6c2968a28..fa1e76920d0e 100644
--- a/include/linux/dpll.h
+++ b/include/linux/dpll.h
@@ -103,6 +103,16 @@ struct dpll_pin_ops {
 			 const struct dpll_device *dpll, void *dpll_priv,
 			 struct dpll_pin_esync *esync,
 			 struct netlink_ext_ack *extack);
+	int (*ref_sync_set)(const struct dpll_pin *pin, void *pin_priv,
+			    const struct dpll_pin *ref_sync_pin,
+			    void *ref_sync_pin_priv,
+			    const enum dpll_pin_state state,
+			    struct netlink_ext_ack *extack);
+	int (*ref_sync_get)(const struct dpll_pin *pin, void *pin_priv,
+			    const struct dpll_pin *ref_sync_pin,
+			    void *ref_sync_pin_priv,
+			    enum dpll_pin_state *state,
+			    struct netlink_ext_ack *extack);
 };
 
 struct dpll_pin_frequency {
@@ -202,6 +212,9 @@ int dpll_pin_on_pin_register(struct dpll_pin *parent, struct dpll_pin *pin,
 void dpll_pin_on_pin_unregister(struct dpll_pin *parent, struct dpll_pin *pin,
 				const struct dpll_pin_ops *ops, void *priv);
 
+int dpll_pin_ref_sync_pair_add(struct dpll_pin *pin,
+			       struct dpll_pin *ref_sync_pin);
+
 int dpll_device_change_ntf(struct dpll_device *dpll);
 
 int dpll_pin_change_ntf(struct dpll_pin *pin);
-- 
cgit v1.2.3


From ddaad4ad774d4ae02047ef873a8e38f62a4b7b01 Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Wed, 18 Jun 2025 22:22:50 +0200
Subject: mtd: nand: qpic_common: prevent out of bounds access of BAM arrays

The common QPIC code does not do any boundary checking when it handles
the command elements and scatter gater list arrays of a BAM transaction,
thus it allows to access out of bounds elements in those.

Although it is the responsibility of the given driver to allocate enough
space for all possible BAM transaction variations, however there can be
mistakes in the driver code which can lead to hidden memory corruption
issues which are hard to debug.

This kind of problem has been observed during testing the 'spi-qpic-snand'
driver. Although the driver has been fixed with a preceding patch, but it
still makes sense to reduce the chance of having such errors again later.

In order to prevent such errors, change the qcom_alloc_bam_transaction()
function to store the number of elements of the arrays in the
'bam_transaction' strucutre during allocation. Also, add sanity checks to
the qcom_prep_bam_dma_desc_{cmd,data}() functions to avoid using out of
bounds indices for the arrays.

Tested-by: Lakshmi Sowjanya D <quic_laksd@quicinc.com>     # on SDX75
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Link: https://patch.msgid.link/20250618-qpic-snand-avoid-mem-corruption-v3-2-319c71296cda@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/mtd/nand/qpic_common.c       | 30 ++++++++++++++++++++++++++----
 include/linux/mtd/nand-qpic-common.h |  8 ++++++++
 2 files changed, 34 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/qpic_common.c b/drivers/mtd/nand/qpic_common.c
index 4dc4d65e7d32..8e604cc22ca3 100644
--- a/drivers/mtd/nand/qpic_common.c
+++ b/drivers/mtd/nand/qpic_common.c
@@ -57,14 +57,15 @@ qcom_alloc_bam_transaction(struct qcom_nand_controller *nandc)
 	bam_txn_buf += sizeof(*bam_txn);
 
 	bam_txn->bam_ce = bam_txn_buf;
-	bam_txn_buf +=
-		sizeof(*bam_txn->bam_ce) * QPIC_PER_CW_CMD_ELEMENTS * num_cw;
+	bam_txn->bam_ce_nitems = QPIC_PER_CW_CMD_ELEMENTS * num_cw;
+	bam_txn_buf += sizeof(*bam_txn->bam_ce) * bam_txn->bam_ce_nitems;
 
 	bam_txn->cmd_sgl = bam_txn_buf;
-	bam_txn_buf +=
-		sizeof(*bam_txn->cmd_sgl) * QPIC_PER_CW_CMD_SGL * num_cw;
+	bam_txn->cmd_sgl_nitems = QPIC_PER_CW_CMD_SGL * num_cw;
+	bam_txn_buf += sizeof(*bam_txn->cmd_sgl) * bam_txn->cmd_sgl_nitems;
 
 	bam_txn->data_sgl = bam_txn_buf;
+	bam_txn->data_sgl_nitems = QPIC_PER_CW_DATA_SGL * num_cw;
 
 	init_completion(&bam_txn->txn_done);
 
@@ -238,6 +239,11 @@ int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read,
 	struct bam_transaction *bam_txn = nandc->bam_txn;
 	u32 offset;
 
+	if (bam_txn->bam_ce_pos + size > bam_txn->bam_ce_nitems) {
+		dev_err(nandc->dev, "BAM %s array is full\n", "CE");
+		return -EINVAL;
+	}
+
 	bam_ce_buffer = &bam_txn->bam_ce[bam_txn->bam_ce_pos];
 
 	/* fill the command desc */
@@ -258,6 +264,12 @@ int qcom_prep_bam_dma_desc_cmd(struct qcom_nand_controller *nandc, bool read,
 
 	/* use the separate sgl after this command */
 	if (flags & NAND_BAM_NEXT_SGL) {
+		if (bam_txn->cmd_sgl_pos >= bam_txn->cmd_sgl_nitems) {
+			dev_err(nandc->dev, "BAM %s array is full\n",
+				"CMD sgl");
+			return -EINVAL;
+		}
+
 		bam_ce_buffer = &bam_txn->bam_ce[bam_txn->bam_ce_start];
 		bam_ce_size = (bam_txn->bam_ce_pos -
 				bam_txn->bam_ce_start) *
@@ -297,10 +309,20 @@ int qcom_prep_bam_dma_desc_data(struct qcom_nand_controller *nandc, bool read,
 	struct bam_transaction *bam_txn = nandc->bam_txn;
 
 	if (read) {
+		if (bam_txn->rx_sgl_pos >= bam_txn->data_sgl_nitems) {
+			dev_err(nandc->dev, "BAM %s array is full\n", "RX sgl");
+			return -EINVAL;
+		}
+
 		sg_set_buf(&bam_txn->data_sgl[bam_txn->rx_sgl_pos],
 			   vaddr, size);
 		bam_txn->rx_sgl_pos++;
 	} else {
+		if (bam_txn->tx_sgl_pos >= bam_txn->data_sgl_nitems) {
+			dev_err(nandc->dev, "BAM %s array is full\n", "TX sgl");
+			return -EINVAL;
+		}
+
 		sg_set_buf(&bam_txn->data_sgl[bam_txn->tx_sgl_pos],
 			   vaddr, size);
 		bam_txn->tx_sgl_pos++;
diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h
index e8462deda6db..f0aa098a395f 100644
--- a/include/linux/mtd/nand-qpic-common.h
+++ b/include/linux/mtd/nand-qpic-common.h
@@ -237,6 +237,9 @@
  * @last_data_desc - last DMA desc in data channel (tx/rx).
  * @last_cmd_desc - last DMA desc in command channel.
  * @txn_done - completion for NAND transfer.
+ * @bam_ce_nitems - the number of elements in the @bam_ce array
+ * @cmd_sgl_nitems - the number of elements in the @cmd_sgl array
+ * @data_sgl_nitems - the number of elements in the @data_sgl array
  * @bam_ce_pos - the index in bam_ce which is available for next sgl
  * @bam_ce_start - the index in bam_ce which marks the start position ce
  *		   for current sgl. It will be used for size calculation
@@ -255,6 +258,11 @@ struct bam_transaction {
 	struct dma_async_tx_descriptor *last_data_desc;
 	struct dma_async_tx_descriptor *last_cmd_desc;
 	struct completion txn_done;
+
+	unsigned int bam_ce_nitems;
+	unsigned int cmd_sgl_nitems;
+	unsigned int data_sgl_nitems;
+
 	struct_group(bam_positions,
 		u32 bam_ce_pos;
 		u32 bam_ce_start;
-- 
cgit v1.2.3


From 96893cdd4760ad94a438c1523cc5ca2470e04670 Mon Sep 17 00:00:00 2001
From: Marc Kleine-Budde <mkl@pengutronix.de>
Date: Sun, 29 Jun 2025 18:15:32 +0200
Subject: spi: Raise limit on number of chip selects to 24

We have a system which uses 24 SPI chip selects, raise the hard coded
limit accordingly.

Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Link: https://patch.msgid.link/20250629-spi-increase-number-of-cs-v2-1-85a0a09bab32@pengutronix.de
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/spi/spi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/spi/spi.h b/include/linux/spi/spi.h
index 4789f91dae94..e9ea43234d9a 100644
--- a/include/linux/spi/spi.h
+++ b/include/linux/spi/spi.h
@@ -21,7 +21,7 @@
 #include <uapi/linux/spi/spi.h>
 
 /* Max no. of CS supported per spi device */
-#define SPI_CS_CNT_MAX 16
+#define SPI_CS_CNT_MAX 24
 
 struct dma_chan;
 struct software_node;
-- 
cgit v1.2.3


From 24368a744bafce7daf1eafd6a163871925ee5892 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Fri, 2 May 2025 21:32:01 -0400
Subject: sanitize handling of long-term internal mounts

Original rationale for those had been the reduced cost of mntput()
for the stuff that is mounted somewhere.  Mount refcount increments and
decrements are frequent; what's worse, they tend to concentrate on the
same instances and cacheline pingpong is quite noticable.

As the result, mount refcounts are per-cpu; that allows a very cheap
increment.  Plain decrement would be just as easy, but decrement-and-test
is anything but (we need to add the components up, with exclusion against
possible increment-from-zero, etc.).

Fortunately, there is a very common case where we can tell that decrement
won't be the final one - if the thing we are dropping is currently
mounted somewhere.  We have an RCU delay between the removal from mount
tree and dropping the reference that used to pin it there, so we can
just take rcu_read_lock() and check if the victim is mounted somewhere.
If it is, we can go ahead and decrement without and further checks -
the reference we are dropping is not the last one.  If it isn't, we
get all the fun with locking, carefully adding up components, etc.,
but the majority of refcount decrements end up taking the fast path.

There is a major exception, though - pipes and sockets.  Those live
on the internal filesystems that are not going to be mounted anywhere.
They are not going to be _un_mounted, of course, so having to take the
slow path every time a pipe or socket gets closed is really obnoxious.
Solution had been to mark them as long-lived ones - essentially faking
"they are mounted somewhere" indicator.

With minor modification that works even for ones that do eventually get
dropped - all it takes is making sure we have an RCU delay between
clearing the "mounted somewhere" indicator and dropping the reference.

There are some additional twists (if you want to drop a dozen of such
internal mounts, you'd be better off with clearing the indicator on
all of them, doing an RCU delay once, then dropping the references),
but in the basic form it had been
	* use kern_mount() if you want your internal mount to be
a long-term one.
	* use kern_unmount() to undo that.

Unfortunately, the things did rot a bit during the mount API reshuffling.
In several cases we have lost the "fake the indicator" part; kern_unmount()
on the unmount side remained (it doesn't warn if you use it on a mount
without the indicator), but all benefits regaring mntput() cost had been
lost.

To get rid of that bitrot, let's add a new helper that would work
with fs_context-based API: fc_mount_longterm().  It's a counterpart
of fc_mount() that does, on success, mark its result as long-term.
It must be paired with kern_unmount() or equivalents.

Converted:
	1) mqueue (it used to use kern_mount_data() and the umount side
is still as it used to be)
	2) hugetlbfs (used to use kern_mount_data(), internal mount is
never unmounted in this one)
	3) i915 gemfs (used to be kern_mount() + manual remount to set
options, still uses kern_unmount() on umount side)
	4) v3d gemfs (copied from i915)

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 drivers/gpu/drm/i915/gem/i915_gemfs.c | 21 ++++++++++++++++++---
 drivers/gpu/drm/v3d/v3d_gemfs.c       | 21 ++++++++++++++++++---
 fs/hugetlbfs/inode.c                  |  2 +-
 fs/namespace.c                        |  9 +++++++++
 include/linux/mount.h                 |  1 +
 ipc/mqueue.c                          |  2 +-
 6 files changed, 48 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gem/i915_gemfs.c b/drivers/gpu/drm/i915/gem/i915_gemfs.c
index 65d84a93c525..a09e2eb47175 100644
--- a/drivers/gpu/drm/i915/gem/i915_gemfs.c
+++ b/drivers/gpu/drm/i915/gem/i915_gemfs.c
@@ -5,16 +5,23 @@
 
 #include <linux/fs.h>
 #include <linux/mount.h>
+#include <linux/fs_context.h>
 
 #include "i915_drv.h"
 #include "i915_gemfs.h"
 #include "i915_utils.h"
 
+static int add_param(struct fs_context *fc, const char *key, const char *val)
+{
+	return vfs_parse_fs_string(fc, key, val, strlen(val));
+}
+
 void i915_gemfs_init(struct drm_i915_private *i915)
 {
-	char huge_opt[] = "huge=within_size"; /* r/w */
 	struct file_system_type *type;
+	struct fs_context *fc;
 	struct vfsmount *gemfs;
+	int ret;
 
 	/*
 	 * By creating our own shmemfs mountpoint, we can pass in
@@ -38,8 +45,16 @@ void i915_gemfs_init(struct drm_i915_private *i915)
 	if (!type)
 		goto err;
 
-	gemfs = vfs_kern_mount(type, SB_KERNMOUNT, type->name, huge_opt);
-	if (IS_ERR(gemfs))
+	fc = fs_context_for_mount(type, SB_KERNMOUNT);
+	if (IS_ERR(fc))
+		goto err;
+	ret = add_param(fc, "source", "tmpfs");
+	if (!ret)
+		ret = add_param(fc, "huge", "within_size");
+	if (!ret)
+		gemfs = fc_mount_longterm(fc);
+	put_fs_context(fc);
+	if (ret)
 		goto err;
 
 	i915->mm.gemfs = gemfs;
diff --git a/drivers/gpu/drm/v3d/v3d_gemfs.c b/drivers/gpu/drm/v3d/v3d_gemfs.c
index 4c5e18590a5c..8ec6ed82b3d9 100644
--- a/drivers/gpu/drm/v3d/v3d_gemfs.c
+++ b/drivers/gpu/drm/v3d/v3d_gemfs.c
@@ -3,14 +3,21 @@
 
 #include <linux/fs.h>
 #include <linux/mount.h>
+#include <linux/fs_context.h>
 
 #include "v3d_drv.h"
 
+static int add_param(struct fs_context *fc, const char *key, const char *val)
+{
+	return vfs_parse_fs_string(fc, key, val, strlen(val));
+}
+
 void v3d_gemfs_init(struct v3d_dev *v3d)
 {
-	char huge_opt[] = "huge=within_size";
 	struct file_system_type *type;
+	struct fs_context *fc;
 	struct vfsmount *gemfs;
+	int ret;
 
 	/*
 	 * By creating our own shmemfs mountpoint, we can pass in
@@ -28,8 +35,16 @@ void v3d_gemfs_init(struct v3d_dev *v3d)
 	if (!type)
 		goto err;
 
-	gemfs = vfs_kern_mount(type, SB_KERNMOUNT, type->name, huge_opt);
-	if (IS_ERR(gemfs))
+	fc = fs_context_for_mount(type, SB_KERNMOUNT);
+	if (IS_ERR(fc))
+		goto err;
+	ret = add_param(fc, "source", "tmpfs");
+	if (!ret)
+		ret = add_param(fc, "huge", "within_size");
+	if (!ret)
+		gemfs = fc_mount_longterm(fc);
+	put_fs_context(fc);
+	if (ret)
 		goto err;
 
 	v3d->gemfs = gemfs;
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index e4de5425838d..4e0397775167 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -1587,7 +1587,7 @@ static struct vfsmount *__init mount_one_hugetlbfs(struct hstate *h)
 	} else {
 		struct hugetlbfs_fs_context *ctx = fc->fs_private;
 		ctx->hstate = h;
-		mnt = fc_mount(fc);
+		mnt = fc_mount_longterm(fc);
 		put_fs_context(fc);
 	}
 	if (IS_ERR(mnt))
diff --git a/fs/namespace.c b/fs/namespace.c
index 57b0974a5d1e..6a0697eeda74 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -1260,6 +1260,15 @@ struct vfsmount *fc_mount(struct fs_context *fc)
 }
 EXPORT_SYMBOL(fc_mount);
 
+struct vfsmount *fc_mount_longterm(struct fs_context *fc)
+{
+	struct vfsmount *mnt = fc_mount(fc);
+	if (!IS_ERR(mnt))
+		real_mount(mnt)->mnt_ns = MNT_NS_INTERNAL;
+	return mnt;
+}
+EXPORT_SYMBOL(fc_mount_longterm);
+
 struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				int flags, const char *name,
 				void *data)
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 1a508beba446..c145820fcbbf 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -98,6 +98,7 @@ int mnt_get_write_access(struct vfsmount *mnt);
 void mnt_put_write_access(struct vfsmount *mnt);
 
 extern struct vfsmount *fc_mount(struct fs_context *fc);
+extern struct vfsmount *fc_mount_longterm(struct fs_context *fc);
 extern struct vfsmount *vfs_create_mount(struct fs_context *fc);
 extern struct vfsmount *vfs_kern_mount(struct file_system_type *type,
 				      int flags, const char *name,
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index 82ed2d3c9846..de7432efbf4a 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -482,7 +482,7 @@ static struct vfsmount *mq_create_mount(struct ipc_namespace *ns)
 	put_user_ns(fc->user_ns);
 	fc->user_ns = get_user_ns(ctx->ipc_ns->user_ns);
 
-	mnt = fc_mount(fc);
+	mnt = fc_mount_longterm(fc);
 	put_fs_context(fc);
 	return mnt;
 }
-- 
cgit v1.2.3


From f0d0ba19985d23a3e83d654318ccb6e9c5f1b095 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 14 May 2025 20:50:06 -0400
Subject: Rewrite of propagate_umount()

The variant currently in the tree has problems; trying to prove
correctness has caught at least one class of bugs (reparenting
that ends up moving the visible location of reparented mount, due
to not excluding some of the counterparts on propagation that
should've been included).

I tried to prove that it's the only bug there; I'm still not sure
whether it is.  If anyone can reconstruct and write down an analysis
of the mainline implementation, I'll gladly review it; as it is,
I ended up doing a different implementation.  Candidate collection
phase is similar, but trimming the set down until it satisfies the
constraints turned out pretty different.

I hoped to do transformation as a massage series, but that turns out
to be too convoluted.  So it's a single patch replacing propagate_umount()
and friends in one go, with notes and analysis in D/f/propagate_umount.txt
(in addition to inline comments).

As far I can tell, it is provably correct and provably linear by the number
of mounts we need to look at in order to decide what should be unmounted.
It even builds and seems to survive testing...

Another nice thing that fell out of that is that ->mnt_umounting is no longer
needed.

Compared to the first version:
	* explicit MNT_UMOUNT_CANDIDATE flag for is_candidate()
	* trim_ancestors() only clears that flag, leaving the suckers on list
	* trim_one() and handle_locked() take the stuff with flag cleared off
the list.  That allows to iterate with list_for_each_entry_safe() when calling
trim_one() - it removes at most one element from the list now.
	* no globals - I didn't bother with any kind of context, not worth it.

	* Notes updated accordingly; I have not touch the terms yet.

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/propagate_umount.txt | 484 +++++++++++++++++++++++++
 fs/mount.h                                     |   1 -
 fs/namespace.c                                 |   1 -
 fs/pnode.c                                     | 362 +++++++++---------
 fs/pnode.h                                     |   2 +-
 include/linux/mount.h                          |   3 +-
 6 files changed, 685 insertions(+), 168 deletions(-)
 create mode 100644 Documentation/filesystems/propagate_umount.txt

(limited to 'include/linux')

diff --git a/Documentation/filesystems/propagate_umount.txt b/Documentation/filesystems/propagate_umount.txt
new file mode 100644
index 000000000000..6906903a8aa2
--- /dev/null
+++ b/Documentation/filesystems/propagate_umount.txt
@@ -0,0 +1,484 @@
+	Notes on propagate_umount()
+
+Umount propagation starts with a set of mounts we are already going to
+take out.  Ideally, we would like to add all downstream cognates to
+that set - anything with the same mountpoint as one of the removed
+mounts and with parent that would receive events from the parent of that
+mount.  However, there are some constraints the resulting set must
+satisfy.
+
+It is convenient to define several properties of sets of mounts:
+
+1) A set S of mounts is non-shifting if for any mount X belonging
+to S all subtrees mounted strictly inside of X (i.e. not overmounting
+the root of X) contain only elements of S.
+
+2) A set S is non-revealing if all locked mounts that belong to S have
+parents that also belong to S.
+
+3) A set S is closed if it contains all children of its elements.
+
+The set of mounts taken out by umount(2) must be non-shifting and
+non-revealing; the first constraint is what allows to reparent
+any remaining mounts and the second is what prevents the exposure
+of any concealed mountpoints.
+
+propagate_umount() takes the original set as an argument and tries to
+extend that set.  The original set is a full subtree and its root is
+unlocked; what matters is that it's closed and non-revealing.
+Resulting set may not be closed; there might still be mounts outside
+of that set, but only on top of stacks of root-overmounting elements
+of set.  They can be reparented to the place where the bottom of
+stack is attached to a mount that will survive.  NOTE: doing that
+will violate a constraint on having no more than one mount with
+the same parent/mountpoint pair; however, the caller (umount_tree())
+will immediately remedy that - it may keep unmounted element attached
+to parent, but only if the parent itself is unmounted.  Since all
+conflicts created by reparenting have common parent *not* in the
+set and one side of the conflict (bottom of the stack of overmounts)
+is in the set, it will be resolved.  However, we rely upon umount_tree()
+doing that pretty much immediately after the call of propagate_umount().
+
+Algorithm is based on two statements:
+	1) for any set S, there is a maximal non-shifting subset of S
+and it can be calculated in O(#S) time.
+	2) for any non-shifting set S, there is a maximal non-revealing
+subset of S.  That subset is also non-shifting and it can be calculated
+in O(#S) time.
+
+		Finding candidates.
+
+We are given a closed set U and we want to find all mounts that have
+the same mountpoint as some mount m in U *and* whose parent receives
+propagation from the parent of the same mount m.  Naive implementation
+would be
+	S = {}
+	for each m in U
+		add m to S
+		p = parent(m)
+		for each q in Propagation(p) - {p}
+			child = look_up(q, mountpoint(m))
+			if child
+				add child to S
+but that can lead to excessive work - there might be propagation among the
+subtrees of U, in which case we'd end up examining the same candidates
+many times.  Since propagation is transitive, the same will happen to
+everything downstream of that candidate and it's not hard to construct
+cases where the approach above leads to the time quadratic by the actual
+number of candidates.
+
+Note that if we run into a candidate we'd already seen, it must've been
+added on an earlier iteration of the outer loop - all additions made
+during one iteration of the outer loop have different parents.  So
+if we find a child already added to the set, we know that everything
+in Propagation(parent(child)) with the same mountpoint has been already
+added.
+	S = {}
+	for each m in U
+		if m in S
+			continue
+		add m to S
+		p = parent(m)
+		q = propagation_next(p, p)
+		while q
+			child = look_up(q, mountpoint(m))
+			if child
+				if child in S
+					q = skip_them(q, p)
+					continue;
+				add child to S
+			q = propagation_next(q, p)
+where
+skip_them(q, p)
+	keep walking Propagation(p) from q until we find something
+	not in Propagation(q)
+
+would get rid of that problem, but we need a sane implementation of
+skip_them().  That's not hard to do - split propagation_next() into
+"down into mnt_slave_list" and "forward-and-up" parts, with the
+skip_them() being "repeat the forward-and-up part until we get NULL
+or something that isn't a peer of the one we are skipping".
+
+Note that there can be no absolute roots among the extra candidates -
+they all come from mount lookups.  Absolute root among the original
+set is _currently_ impossible, but it might be worth protecting
+against.
+
+		Maximal non-shifting subsets.
+
+Let's call a mount m in a set S forbidden in that set if there is a
+subtree mounted strictly inside m and containing mounts that do not
+belong to S.
+
+The set is non-shifting when none of its elements are forbidden in it.
+
+If mount m is forbidden in a set S, it is forbidden in any subset S' it
+belongs to.  In other words, it can't belong to any of the non-shifting
+subsets of S.  If we had a way to find a forbidden mount or show that
+there's none, we could use it to find the maximal non-shifting subset
+simply by finding and removing them until none remain.
+
+Suppose mount m is forbidden in S; then any mounts forbidden in S - {m}
+must have been forbidden in S itself.  Indeed, since m has descendents
+that do not belong to S, any subtree that fits into S will fit into
+S - {m} as well.
+
+So in principle we could go through elements of S, checking if they
+are forbidden in S and removing the ones that are.  Removals will
+not invalidate the checks done for earlier mounts - if they were not
+forbidden at the time we checked, they won't become forbidden later.
+It's too costly to be practical, but there is a similar approach that
+is linear by size of S.
+
+Let's say that mount x in a set S is forbidden by mount y, if
+	* both x and y belong to S.
+	* there is a chain of mounts starting at x and leaving S
+	  immediately after passing through y, with the first
+	  mountpoint strictly inside x.
+Note 1: x may be equal to y - that's the case when something not
+belonging to S is mounted strictly inside x.
+Note 2: if y does not belong to S, it can't forbid anything in S.
+Note 3: if y has no children outside of S, it can't forbid anything in S.
+
+It's easy to show that mount x is forbidden in S if and only if x is
+forbidden in S by some mount y.  And it's easy to find all mounts in S
+forbidden by a given mount.
+
+Consider the following operation:
+	Trim(S, m) = S - {x : x is forbidden by m in S}
+
+Note that if m does not belong to S or has no children outside of S we
+are guaranteed that Trim(S, m) is equal to S.
+
+The following is true: if x is forbidden by y in Trim(S, m), it was
+already forbidden by y in S.
+
+Proof: Suppose x is forbidden by y in Trim(S, m).  Then there is a
+chain of mounts (x_0 = x, ..., x_k = y, x_{k+1} = r), such that x_{k+1}
+is the first element that doesn't belong to Trim(S, m) and the
+mountpoint of x_1 is strictly inside x.  If mount r belongs to S, it must
+have been removed by Trim(S, m), i.e. it was forbidden in S by m.
+Then there was a mount chain from r to some child of m that stayed in
+S all the way until m, but that's impossible since x belongs to Trim(S, m)
+and prepending (x_0, ..., x_k) to that chain demonstrates that x is also
+forbidden in S by m, and thus can't belong to Trim(S, m).
+Therefore r can not belong to S and our chain demonstrates that
+x is forbidden by y in S.  QED.
+
+Corollary: no mount is forbidden by m in Trim(S, m).  Indeed, any
+such mount would have been forbidden by m in S and thus would have been
+in the part of S removed in Trim(S, m).
+
+Corollary: no mount is forbidden by m in Trim(Trim(S, m), n).  Indeed,
+any such would have to have been forbidden by m in Trim(S, m), which
+is impossible.
+
+Corollary: after
+	S = Trim(S, x_1)
+	S = Trim(S, x_2)
+	...
+	S = Trim(S, x_k)
+no mount remaining in S will be forbidden by either of x_1,...,x_k.
+
+The following will reduce S to its maximal non-shifting subset:
+	visited = {}
+	while S contains elements not belonging to visited
+		let m be an arbitrary such element of S
+		S = Trim(S, m)
+		add m to visited
+
+S never grows, so the number of elements of S not belonging to visited
+decreases at least by one on each iteration.  When the loop terminates,
+all mounts remaining in S belong to visited.  It's easy to see that at
+the beginning of each iteration no mount remaining in S will be forbidden
+by any element of visited.  In other words, no mount remaining in S will
+be forbidden, i.e. final value of S will be non-shifting.  It will be
+the maximal non-shifting subset, since we were removing only forbidden
+elements.
+
+	There are two difficulties in implementing the above in linear
+time, both due to the fact that Trim() might need to remove more than one
+element.  Naive implementation of Trim() is vulnerable to running into a
+long chain of mounts, each mounted on top of parent's root.  Nothing in
+that chain is forbidden, so nothing gets removed from it.  We need to
+recognize such chains and avoid walking them again on subsequent calls of
+Trim(), otherwise we will end up with worst-case time being quadratic by
+the number of elements in S.  Another difficulty is in implementing the
+outer loop - we need to iterate through all elements of a shrinking set.
+That would be trivial if we never removed more than one element at a time
+(linked list, with list_for_each_entry_safe for iterator), but we may
+need to remove more than one entry, possibly including the ones we have
+already visited.
+
+	Let's start with naive algorithm for Trim():
+
+Trim_one(m)
+	found = false
+	for each n in children(m)
+		if n not in S
+			found = true
+			if (mountpoint(n) != root(m))
+				remove m from S
+				break
+	if found
+		Trim_ancestors(m)
+
+Trim_ancestors(m)
+	for (; parent(m) in S; m = parent(m)) {
+		if (mountpoint(m) != root(parent(m)))
+			remove parent(m) from S
+	}
+
+If m belongs to S, Trim_one(m) will replace S with Trim(S, m).
+Proof:
+	Consider the chains excluding elements from Trim(S, m).  The last
+two elements in such chain are m and some child of m that does not belong
+to S.  If m has no such children, Trim(S, m) is equal to S.
+	m itself is removed if and only if the chain has exactly two
+elements, i.e. when the last element does not overmount the root of m.
+In other words, that happens when m has a child not in S that does not
+overmount the root of m.
+	All other elements to remove will be ancestors of m, such that
+the entire descent chain from them to m is contained in S.  Let
+(x_0, x_1, ..., x_k = m) be the longest such chain.  x_i needs to be
+removed if and only if x_{i+1} does not overmount its root.  It's easy
+to see that Trim_ancestors(m) will iterate through that chain from
+x_k to x_1 and that it will remove exactly the elements that need to be
+removed.
+
+	Note that if the loop in Trim_ancestors() walks into an already
+visited element, we are guaranteed that remaining iterations will see
+only elements that had already been visited and remove none of them.
+That's the weakness that makes it vulnerable to long chains of full
+overmounts.
+
+	It's easy to deal with, if we can afford setting marks on
+elements of S; we would mark all elements already visited by
+Trim_ancestors() and have it bail out as soon as it sees an already
+marked element.
+
+	The problems with iterating through the set can be dealt with in
+several ways, depending upon the representation we choose for our set.
+One useful observation is that we are given a closed subset in S - the
+original set passed to propagate_umount().  Its elements can neither
+forbid anything nor be forbidden by anything - all their descendents
+belong to S, so they can not occur anywhere in any excluding chain.
+In other words, the elements of that subset will remain in S until
+the end and Trim_one(S, m) is a no-op for all m from that subset.
+
+	That suggests keeping S as a disjoint union of a closed set U
+('will be unmounted, no matter what') and the set of all elements of
+S that do not belong to U.  That set ('candidates') is all we need
+to iterate through.  Let's represent it as a subset in a cyclic list,
+consisting of all list elements that are marked as candidates (initially -
+all of them).  Then we could have Trim_ancestors() only remove the mark,
+leaving the elements on the list.  Then Trim_one() would never remove
+anything other than its argument from the containing list, allowing to
+use list_for_each_entry_safe() as iterator.
+
+	Assuming that representation we get the following:
+
+	list_for_each_entry_safe(m, ..., Candidates, ...)
+		Trim_one(m)
+where
+Trim_one(m)
+	if (m is not marked as a candidate)
+		strip the "seen by Trim_ancestors" mark from m
+		remove m from the Candidates list
+		return
+		
+	remove_this = false
+	found = false
+	for each n in children(m)
+		if n not in S
+			found = true
+			if (mountpoint(n) != root(m))
+				remove_this = true
+				break
+	if found
+		Trim_ancestors(m)
+	if remove_this
+		strip the "seen by Trim_ancestors" mark from m
+		strip the "candidate" mark from m
+		remove m from the Candidate list
+
+Trim_ancestors(m)
+	for (p = parent(m); p is marked as candidate ; m = p, p = parent(p)) {
+		if m is marked as seen by Trim_ancestors
+			return
+		mark m as seen by Trim_ancestors
+		if (mountpoint(m) != root(p))
+			strip the "candidate" mark from p
+	}
+
+	Terminating condition in the loop in Trim_ancestors() is correct,
+since that that loop will never run into p belonging to U - p is always
+an ancestor of argument of Trim_one() and since U is closed, the argument
+of Trim_one() would also have to belong to U.  But Trim_one() is never
+called for elements of U.  In other words, p belongs to S if and only
+if it belongs to candidates.
+
+	Time complexity:
+* we get no more than O(#S) calls of Trim_one()
+* the loop over children in Trim_one() never looks at the same child
+twice through all the calls.
+* iterations of that loop for children in S are no more than O(#S)
+in the worst case
+* at most two children that are not elements of S are considered per
+call of Trim_one().
+* the loop in Trim_ancestors() sets its mark once per iteration and
+no element of S has is set more than once.
+
+	In the end we may have some elements excluded from S by
+Trim_ancestors() still stuck on the list.  We could do a separate
+loop removing them from the list (also no worse than O(#S) time),
+but it's easier to leave that until the next phase - there we will
+iterate through the candidates anyway.
+
+	The caller has already removed all elements of U from their parents'
+lists of children, which means that checking if child belongs to S is
+equivalent to checking if it's marked as a candidate; we'll never see
+the elements of U in the loop over children in Trim_one().
+
+	What's more, if we see that children(m) is empty and m is not
+locked, we can immediately move m into the committed subset (remove
+from the parent's list of children, etc.).  That's one fewer mount we'll
+have to look into when we check the list of children of its parent *and*
+when we get to building the non-revealing subset.
+
+		Maximal non-revealing subsets
+
+If S is not a non-revealing subset, there is a locked element x in S
+such that parent of x is not in S.
+
+Obviously, no non-revealing subset of S may contain x.  Removing such
+elements one by one will obviously end with the maximal non-revealing
+subset (possibly empty one).  Note that removal of an element will
+require removal of all its locked children, etc.
+
+If the set had been non-shifting, it will remain non-shifting after
+such removals.
+Proof: suppose S was non-shifting, x is a locked element of S, parent of x
+is not in S and S - {x} is not non-shifting.  Then there is an element m
+in S - {x} and a subtree mounted strictly inside m, such that m contains
+an element not in in S - {x}.  Since S is non-shifting, everything in
+that subtree must belong to S.  But that means that this subtree must
+contain x somewhere *and* that parent of x either belongs that subtree
+or is equal to m.  Either way it must belong to S.  Contradiction.
+
+// same representation as for finding maximal non-shifting subsets:
+// S is a disjoint union of a non-revealing set U (the ones we are committed
+// to unmount) and a set of candidates, represented as a subset of list
+// elements that have "is a candidate" mark on them.
+// Elements of U are removed from their parents' lists of children.
+// In the end candidates becomes empty and maximal non-revealing non-shifting
+// subset of S is now in U
+	while (Candidates list is non-empty)
+		handle_locked(first(Candidates))
+
+handle_locked(m)
+	if m is not marked as a candidate
+		strip the "seen by Trim_ancestors" mark from m
+		remove m from the list
+		return
+	cutoff = m
+	for (p = m; p in candidates; p = parent(p)) {
+		strip the "seen by Trim_ancestors" mark from p
+		strip the "candidate" mark from p
+		remove p from the Candidates list
+		if (!locked(p))
+			cutoff = parent(p)
+	}
+	if p in U
+		cutoff = p
+	while m != cutoff
+		remove m from children(parent(m))
+		add m to U
+		m = parent(m)
+
+Let (x_0, ..., x_n = m) be the maximal chain of descent of m within S.
+* If it contains some elements of U, let x_k be the last one of those.
+Then union of U with {x_{k+1}, ..., x_n} is obviously non-revealing.
+* otherwise if all its elements are locked, then none of {x_0, ..., x_n}
+may be elements of a non-revealing subset of S.
+* otherwise let x_k be the first unlocked element of the chain.  Then none
+of {x_0, ..., x_{k-1}} may be an element of a non-revealing subset of
+S and union of U and {x_k, ..., x_n} is non-revealing.
+
+handle_locked(m) finds which of these cases applies and adjusts Candidates
+and U accordingly.  U remains non-revealing, union of Candidates and
+U still contains any non-revealing subset of S and after the call of
+handle_locked(m) m is guaranteed to be not in Candidates list.  So having
+it called for each element of S would suffice to empty Candidates,
+leaving U the maximal non-revealing subset of S.
+
+However, handle_locked(m) is a no-op when m belongs to U, so it's enough
+to have it called for elements of Candidates list until none remain.
+
+Time complexity: number of calls of handle_locked() is limited by
+#Candidates, each iteration of the first loop in handle_locked() removes
+an element from the list, so their total number of executions is also
+limited by #Candidates; number of iterations in the second loop is no
+greater than the number of iterations of the first loop.
+
+
+		Reparenting
+
+After we'd calculated the final set, we still need to deal with
+reparenting - if an element of the final set has a child not in it,
+we need to reparent such child.
+
+Such children can only be root-overmounting (otherwise the set wouldn't
+be non-shifting) and their parents can not belong to the original set,
+since the original is guaranteed to be closed.
+
+
+		Putting all of that together
+
+The plan is to
+	* find all candidates
+	* trim down to maximal non-shifting subset
+	* trim down to maximal non-revealing subset
+	* reparent anything that needs to be reparented
+	* return the resulting set to the caller
+
+For the 2nd and 3rd steps we want to separate the set into growing
+non-revealing subset, initially containing the original set ("U" in
+terms of the pseudocode above) and everything we are still not sure about
+("candidates").  It means that for the output of the 1st step we'd like
+the extra candidates separated from the stuff already in the original set.
+For the 4th step we would like the additions to U separate from the
+original set.
+
+So let's go for
+	* original set ("set").  Linkage via mnt_list
+	* undecided candidates ("candidates").  Subset of a list,
+consisting of all its elements marked with a new flag (MNT_UMOUNT_CANDIDATE).
+Initially all elements of the list will be marked that way; in the
+end the list will become empty and no mounts will remain marked with
+that flag.
+	* Reuse MNT_MARKED for "has been already seen by trim_ancestors()".
+	* anything in U that hadn't been in the original set - elements of
+candidates will gradually be either discarded or moved there.  In other
+words, it's the candidates we have already decided to unmount.	Its role
+is reasonably close to the old "to_umount", so let's use that name.
+Linkage via mnt_list.
+
+For gather_candidates() we'll need to maintain both candidates (S -
+set) and intersection of S with set.  Use MNT_UMOUNT_CANDIDATE for
+all elements we encounter, putting the ones not already in the original
+set into the list of candidates.  When we are done, strip that flag from
+all elements of the original set.  That gives a cheap way to check
+if element belongs to S (in gather_candidates) and to candidates
+itself (at later stages).  Call that predicate is_candidate(); it would
+be m->mnt_flags & MNT_UMOUNT_CANDIDATE.
+
+All elements of the original set are marked with MNT_UMOUNT and we'll
+need the same for elements added when joining the contents of to_umount
+to set in the end.  Let's set MNT_UMOUNT at the time we add an element
+to to_umount; that's close to what the old 'umount_one' is doing, so
+let's keep that name.  It also gives us another predicate we need -
+"belongs to union of set and to_umount"; will_be_unmounted() for now.
+
+Removals from the candidates list should strip both MNT_MARKED and
+MNT_UMOUNT_CANDIDATE; call it remove_from_candidates_list().
diff --git a/fs/mount.h b/fs/mount.h
index f20e6ed845fe..fb93d3e16724 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -79,7 +79,6 @@ struct mount {
 		struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
 		struct hlist_node mnt_umount;
 	};
-	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
 	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
diff --git a/fs/namespace.c b/fs/namespace.c
index 6a0697eeda74..f64895d47d70 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -383,7 +383,6 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
-		INIT_LIST_HEAD(&mnt->mnt_umounting);
 		INIT_HLIST_HEAD(&mnt->mnt_stuck_children);
 		RB_CLEAR_NODE(&mnt->mnt_node);
 		mnt->mnt.mnt_idmap = &nop_mnt_idmap;
diff --git a/fs/pnode.c b/fs/pnode.c
index aa187144e389..901d40946d34 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -24,11 +24,6 @@ static inline struct mount *first_slave(struct mount *p)
 	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
 }
 
-static inline struct mount *last_slave(struct mount *p)
-{
-	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
-}
-
 static inline struct mount *next_slave(struct mount *p)
 {
 	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
@@ -136,6 +131,23 @@ void change_mnt_propagation(struct mount *mnt, int type)
 	}
 }
 
+static struct mount *__propagation_next(struct mount *m,
+					 struct mount *origin)
+{
+	while (1) {
+		struct mount *master = m->mnt_master;
+
+		if (master == origin->mnt_master) {
+			struct mount *next = next_peer(m);
+			return (next == origin) ? NULL : next;
+		} else if (m->mnt_slave.next != &master->mnt_slave_list)
+			return next_slave(m);
+
+		/* back at master */
+		m = master;
+	}
+}
+
 /*
  * get the next mount in the propagation tree.
  * @m: the mount seen last
@@ -153,31 +165,21 @@ static struct mount *propagation_next(struct mount *m,
 	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
 		return first_slave(m);
 
-	while (1) {
-		struct mount *master = m->mnt_master;
-
-		if (master == origin->mnt_master) {
-			struct mount *next = next_peer(m);
-			return (next == origin) ? NULL : next;
-		} else if (m->mnt_slave.next != &master->mnt_slave_list)
-			return next_slave(m);
-
-		/* back at master */
-		m = master;
-	}
+	return __propagation_next(m, origin);
 }
 
 static struct mount *skip_propagation_subtree(struct mount *m,
 						struct mount *origin)
 {
 	/*
-	 * Advance m such that propagation_next will not return
-	 * the slaves of m.
+	 * Advance m past everything that gets propagation from it.
 	 */
-	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
-		m = last_slave(m);
+	struct mount *p = __propagation_next(m, origin);
+
+	while (p && peers(m, p))
+		p = __propagation_next(p, origin);
 
-	return m;
+	return p;
 }
 
 static struct mount *next_group(struct mount *m, struct mount *origin)
@@ -458,181 +460,213 @@ void propagate_mount_unlock(struct mount *mnt)
 	}
 }
 
-static void umount_one(struct mount *mnt, struct list_head *to_umount)
+static inline bool is_candidate(struct mount *m)
 {
-	CLEAR_MNT_MARK(mnt);
-	mnt->mnt.mnt_flags |= MNT_UMOUNT;
-	list_del_init(&mnt->mnt_child);
-	list_del_init(&mnt->mnt_umounting);
-	move_from_ns(mnt, to_umount);
+	return m->mnt.mnt_flags & MNT_UMOUNT_CANDIDATE;
 }
 
-/*
- * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
- * parent propagates to.
- */
-static bool __propagate_umount(struct mount *mnt,
-			       struct list_head *to_umount,
-			       struct list_head *to_restore)
+static inline bool will_be_unmounted(struct mount *m)
 {
-	bool progress = false;
-	struct mount *child;
+	return m->mnt.mnt_flags & MNT_UMOUNT;
+}
 
-	/*
-	 * The state of the parent won't change if this mount is
-	 * already unmounted or marked as without children.
-	 */
-	if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
-		goto out;
+static void umount_one(struct mount *m, struct list_head *to_umount)
+{
+	m->mnt.mnt_flags |= MNT_UMOUNT;
+	list_del_init(&m->mnt_child);
+	move_from_ns(m, to_umount);
+}
 
-	/* Verify topper is the only grandchild that has not been
-	 * speculatively unmounted.
-	 */
-	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
-		if (child->mnt_mountpoint == mnt->mnt.mnt_root)
-			continue;
-		if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
-			continue;
-		/* Found a mounted child */
-		goto children;
-	}
+static void remove_from_candidate_list(struct mount *m)
+{
+	m->mnt.mnt_flags &= ~(MNT_MARKED | MNT_UMOUNT_CANDIDATE);
+	list_del_init(&m->mnt_list);
+}
 
-	/* Mark mounts that can be unmounted if not locked */
-	SET_MNT_MARK(mnt);
-	progress = true;
+static void gather_candidates(struct list_head *set,
+			      struct list_head *candidates)
+{
+	struct mount *m, *p, *q;
 
-	/* If a mount is without children and not locked umount it. */
-	if (!IS_MNT_LOCKED(mnt)) {
-		umount_one(mnt, to_umount);
-	} else {
-children:
-		list_move_tail(&mnt->mnt_umounting, to_restore);
+	list_for_each_entry(m, set, mnt_list) {
+		if (is_candidate(m))
+			continue;
+		m->mnt.mnt_flags |= MNT_UMOUNT_CANDIDATE;
+		p = m->mnt_parent;
+		q = propagation_next(p, p);
+		while (q) {
+			struct mount *child = __lookup_mnt(&q->mnt,
+							   m->mnt_mountpoint);
+			if (child) {
+				/*
+				 * We might've already run into this one.  That
+				 * must've happened on earlier iteration of the
+				 * outer loop; in that case we can skip those
+				 * parents that get propagation from q - there
+				 * will be nothing new on those as well.
+				 */
+				if (is_candidate(child)) {
+					q = skip_propagation_subtree(q, p);
+					continue;
+				}
+				child->mnt.mnt_flags |= MNT_UMOUNT_CANDIDATE;
+				if (!will_be_unmounted(child))
+					list_add(&child->mnt_list, candidates);
+			}
+			q = propagation_next(q, p);
+		}
 	}
-out:
-	return progress;
+	list_for_each_entry(m, set, mnt_list)
+		m->mnt.mnt_flags &= ~MNT_UMOUNT_CANDIDATE;
 }
 
-static void umount_list(struct list_head *to_umount,
-			struct list_head *to_restore)
+/*
+ * We know that some child of @m can't be unmounted.  In all places where the
+ * chain of descent of @m has child not overmounting the root of parent,
+ * the parent can't be unmounted either.
+ */
+static void trim_ancestors(struct mount *m)
 {
-	struct mount *mnt, *child, *tmp;
-	list_for_each_entry(mnt, to_umount, mnt_list) {
-		list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
-			/* topper? */
-			if (child->mnt_mountpoint == mnt->mnt.mnt_root)
-				list_move_tail(&child->mnt_umounting, to_restore);
-			else
-				umount_one(child, to_umount);
-		}
+	struct mount *p;
+
+	for (p = m->mnt_parent; is_candidate(p); m = p, p = p->mnt_parent) {
+		if (IS_MNT_MARKED(m))	// all candidates beneath are overmounts
+			return;
+		SET_MNT_MARK(m);
+		if (m != p->overmount)
+			p->mnt.mnt_flags &= ~MNT_UMOUNT_CANDIDATE;
 	}
 }
 
-static void restore_mounts(struct list_head *to_restore)
+/*
+ * Find and exclude all umount candidates forbidden by @m
+ * (see Documentation/filesystems/propagate_umount.txt)
+ * If we can immediately tell that @m is OK to unmount (unlocked
+ * and all children are already committed to unmounting) commit
+ * to unmounting it.
+ * Only @m itself might be taken from the candidates list;
+ * anything found by trim_ancestors() is marked non-candidate
+ * and left on the list.
+ */
+static void trim_one(struct mount *m, struct list_head *to_umount)
 {
-	/* Restore mounts to a clean working state */
-	while (!list_empty(to_restore)) {
-		struct mount *mnt, *parent;
-		struct mountpoint *mp;
-
-		mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
-		CLEAR_MNT_MARK(mnt);
-		list_del_init(&mnt->mnt_umounting);
-
-		/* Should this mount be reparented? */
-		mp = mnt->mnt_mp;
-		parent = mnt->mnt_parent;
-		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
-			mp = parent->mnt_mp;
-			parent = parent->mnt_parent;
-		}
-		if (parent != mnt->mnt_parent) {
-			mnt_change_mountpoint(parent, mp, mnt);
-			mnt_notify_add(mnt);
+	bool remove_this = false, found = false, umount_this = false;
+	struct mount *n;
+
+	if (!is_candidate(m)) { // trim_ancestors() left it on list
+		remove_from_candidate_list(m);
+		return;
+	}
+
+	list_for_each_entry(n, &m->mnt_mounts, mnt_child) {
+		if (!is_candidate(n)) {
+			found = true;
+			if (n != m->overmount) {
+				remove_this = true;
+				break;
+			}
 		}
 	}
+	if (found) {
+		trim_ancestors(m);
+	} else if (!IS_MNT_LOCKED(m) && list_empty(&m->mnt_mounts)) {
+		remove_this = true;
+		umount_this = true;
+	}
+	if (remove_this) {
+		remove_from_candidate_list(m);
+		if (umount_this)
+			umount_one(m, to_umount);
+	}
 }
 
-static void cleanup_umount_visitations(struct list_head *visited)
+static void handle_locked(struct mount *m, struct list_head *to_umount)
 {
-	while (!list_empty(visited)) {
-		struct mount *mnt =
-			list_first_entry(visited, struct mount, mnt_umounting);
-		list_del_init(&mnt->mnt_umounting);
+	struct mount *cutoff = m, *p;
+
+	if (!is_candidate(m)) { // trim_ancestors() left it on list
+		remove_from_candidate_list(m);
+		return;
+	}
+	for (p = m; is_candidate(p); p = p->mnt_parent) {
+		remove_from_candidate_list(p);
+		if (!IS_MNT_LOCKED(p))
+			cutoff = p->mnt_parent;
+	}
+	if (will_be_unmounted(p))
+		cutoff = p;
+	while (m != cutoff) {
+		umount_one(m, to_umount);
+		m = m->mnt_parent;
 	}
 }
 
 /*
- * collect all mounts that receive propagation from the mount in @list,
- * and return these additional mounts in the same list.
- * @list: the list of mounts to be unmounted.
+ * @m is not to going away, and it overmounts the top of a stack of mounts
+ * that are going away.  We know that all of those are fully overmounted
+ * by the one above (@m being the topmost of the chain), so @m can be slid
+ * in place where the bottom of the stack is attached.
  *
- * vfsmount lock must be held for write
+ * NOTE: here we temporarily violate a constraint - two mounts end up with
+ * the same parent and mountpoint; that will be remedied as soon as we
+ * return from propagate_umount() - its caller (umount_tree()) will detach
+ * the stack from the parent it (and now @m) is attached to.  umount_tree()
+ * might choose to keep unmounted pieces stuck to each other, but it always
+ * detaches them from the mounts that remain in the tree.
  */
-int propagate_umount(struct list_head *list)
+static void reparent(struct mount *m)
 {
-	struct mount *mnt;
-	LIST_HEAD(to_restore);
-	LIST_HEAD(to_umount);
-	LIST_HEAD(visited);
-
-	/* Find candidates for unmounting */
-	list_for_each_entry_reverse(mnt, list, mnt_list) {
-		struct mount *parent = mnt->mnt_parent;
-		struct mount *m;
+	struct mount *p = m;
+	struct mountpoint *mp;
 
-		/*
-		 * If this mount has already been visited it is known that it's
-		 * entire peer group and all of their slaves in the propagation
-		 * tree for the mountpoint has already been visited and there is
-		 * no need to visit them again.
-		 */
-		if (!list_empty(&mnt->mnt_umounting))
-			continue;
+	do {
+		mp = p->mnt_mp;
+		p = p->mnt_parent;
+	} while (will_be_unmounted(p));
 
-		list_add_tail(&mnt->mnt_umounting, &visited);
-		for (m = propagation_next(parent, parent); m;
-		     m = propagation_next(m, parent)) {
-			struct mount *child = __lookup_mnt(&m->mnt,
-							   mnt->mnt_mountpoint);
-			if (!child)
-				continue;
+	mnt_change_mountpoint(p, mp, m);
+	mnt_notify_add(m);
+}
 
-			if (!list_empty(&child->mnt_umounting)) {
-				/*
-				 * If the child has already been visited it is
-				 * know that it's entire peer group and all of
-				 * their slaves in the propgation tree for the
-				 * mountpoint has already been visited and there
-				 * is no need to visit this subtree again.
-				 */
-				m = skip_propagation_subtree(m, parent);
-				continue;
-			} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
-				/*
-				 * We have come across a partially unmounted
-				 * mount in a list that has not been visited
-				 * yet. Remember it has been visited and
-				 * continue about our merry way.
-				 */
-				list_add_tail(&child->mnt_umounting, &visited);
-				continue;
-			}
+/**
+ * propagate_umount - apply propagation rules to the set of mounts for umount()
+ * @set: the list of mounts to be unmounted.
+ *
+ * Collect all mounts that receive propagation from the mount in @set and have
+ * no obstacles to being unmounted.  Add these additional mounts to the set.
+ *
+ * See Documentation/filesystems/propagate_umount.txt if you do anything in
+ * this area.
+ *
+ * Locks held:
+ * mount_lock (write_seqlock), namespace_sem (exclusive).
+ */
+void propagate_umount(struct list_head *set)
+{
+	struct mount *m, *p;
+	LIST_HEAD(to_umount);	// committed to unmounting
+	LIST_HEAD(candidates);	// undecided umount candidates
 
-			/* Check the child and parents while progress is made */
-			while (__propagate_umount(child,
-						  &to_umount, &to_restore)) {
-				/* Is the parent a umount candidate? */
-				child = child->mnt_parent;
-				if (list_empty(&child->mnt_umounting))
-					break;
-			}
-		}
+	// collect all candidates
+	gather_candidates(set, &candidates);
+
+	// reduce the set until it's non-shifting
+	list_for_each_entry_safe(m, p, &candidates, mnt_list)
+		trim_one(m, &to_umount);
+
+	// ... and non-revealing
+	while (!list_empty(&candidates)) {
+		m = list_first_entry(&candidates,struct mount, mnt_list);
+		handle_locked(m, &to_umount);
 	}
 
-	umount_list(&to_umount, &to_restore);
-	restore_mounts(&to_restore);
-	cleanup_umount_visitations(&visited);
-	list_splice_tail(&to_umount, list);
+	// now to_umount consists of all acceptable candidates
+	// deal with reparenting of remaining overmounts on those
+	list_for_each_entry(m, &to_umount, mnt_list) {
+		if (m->overmount)
+			reparent(m->overmount);
+	}
 
-	return 0;
+	// and fold them into the set
+	list_splice_tail_init(&to_umount, set);
 }
diff --git a/fs/pnode.h b/fs/pnode.h
index 93fa9311bd07..04f1ac53aa49 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -42,7 +42,7 @@ static inline bool peers(const struct mount *m1, const struct mount *m2)
 void change_mnt_propagation(struct mount *, int);
 int propagate_mnt(struct mount *, struct mountpoint *, struct mount *,
 		struct hlist_head *);
-int propagate_umount(struct list_head *);
+void propagate_umount(struct list_head *);
 int propagate_mount_busy(struct mount *, int);
 void propagate_mount_unlock(struct mount *);
 void mnt_release_group_id(struct mount *);
diff --git a/include/linux/mount.h b/include/linux/mount.h
index c145820fcbbf..65fa8442c00a 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -40,6 +40,7 @@ enum mount_flags {
 
 	MNT_INTERNAL	= 0x4000,
 
+	MNT_UMOUNT_CANDIDATE	= 0x020000,
 	MNT_LOCK_ATIME		= 0x040000,
 	MNT_LOCK_NOEXEC		= 0x080000,
 	MNT_LOCK_NOSUID		= 0x100000,
@@ -66,7 +67,7 @@ enum mount_flags {
 
 	MNT_INTERNAL_FLAGS = MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL |
 			     MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED |
-			     MNT_LOCKED,
+			     MNT_LOCKED | MNT_UMOUNT_CANDIDATE,
 };
 
 struct vfsmount {
-- 
cgit v1.2.3


From 406fea79992561f47fd3511dd8b7c8abeeff7045 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 21 Jun 2025 18:06:19 -0400
Subject: mount: separate the flags accessed only under namespace_sem

Several flags are updated and checked only under namespace_sem; we are
already making use of that when we are checking them without mount_lock,
but we have to hold mount_lock for all updates, which makes things
clumsier than they have to be.

Take MNT_SHARED, MNT_UNBINDABLE, MNT_MARKED and MNT_UMOUNT_CANDIDATE
into a separate field (->mnt_t_flags), renaming them to T_SHARED,
etc. to avoid confusion.  All accesses must be under namespace_sem.

That changes locking requirements for mnt_change_propagation() and
set_mnt_shared() - only namespace_sem is needed now.  The same goes
for SET_MNT_MARKED et.al.

There might be more flags moved from ->mnt_flags to that field;
this is just the initial set.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 Documentation/filesystems/propagate_umount.txt | 12 ++++++------
 fs/mount.h                                     | 17 +++++++++++++++++
 fs/namespace.c                                 |  4 ----
 fs/pnode.c                                     | 22 ++++++++++------------
 fs/pnode.h                                     | 19 +++++++++++--------
 include/linux/mount.h                          | 18 ++----------------
 6 files changed, 46 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/propagate_umount.txt b/Documentation/filesystems/propagate_umount.txt
index 6906903a8aa2..c90349e5b889 100644
--- a/Documentation/filesystems/propagate_umount.txt
+++ b/Documentation/filesystems/propagate_umount.txt
@@ -453,11 +453,11 @@ original set.
 So let's go for
 	* original set ("set").  Linkage via mnt_list
 	* undecided candidates ("candidates").  Subset of a list,
-consisting of all its elements marked with a new flag (MNT_UMOUNT_CANDIDATE).
+consisting of all its elements marked with a new flag (T_UMOUNT_CANDIDATE).
 Initially all elements of the list will be marked that way; in the
 end the list will become empty and no mounts will remain marked with
 that flag.
-	* Reuse MNT_MARKED for "has been already seen by trim_ancestors()".
+	* Reuse T_MARKED for "has been already seen by trim_ancestors()".
 	* anything in U that hadn't been in the original set - elements of
 candidates will gradually be either discarded or moved there.  In other
 words, it's the candidates we have already decided to unmount.	Its role
@@ -465,13 +465,13 @@ is reasonably close to the old "to_umount", so let's use that name.
 Linkage via mnt_list.
 
 For gather_candidates() we'll need to maintain both candidates (S -
-set) and intersection of S with set.  Use MNT_UMOUNT_CANDIDATE for
+set) and intersection of S with set.  Use T_UMOUNT_CANDIDATE for
 all elements we encounter, putting the ones not already in the original
 set into the list of candidates.  When we are done, strip that flag from
 all elements of the original set.  That gives a cheap way to check
 if element belongs to S (in gather_candidates) and to candidates
 itself (at later stages).  Call that predicate is_candidate(); it would
-be m->mnt_flags & MNT_UMOUNT_CANDIDATE.
+be m->mnt_t_flags & T_UMOUNT_CANDIDATE.
 
 All elements of the original set are marked with MNT_UMOUNT and we'll
 need the same for elements added when joining the contents of to_umount
@@ -480,5 +480,5 @@ to to_umount; that's close to what the old 'umount_one' is doing, so
 let's keep that name.  It also gives us another predicate we need -
 "belongs to union of set and to_umount"; will_be_unmounted() for now.
 
-Removals from the candidates list should strip both MNT_MARKED and
-MNT_UMOUNT_CANDIDATE; call it remove_from_candidates_list().
+Removals from the candidates list should strip both T_MARKED and
+T_UMOUNT_CANDIDATE; call it remove_from_candidates_list().
diff --git a/fs/mount.h b/fs/mount.h
index 4355c482a841..f299dc85446d 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -84,6 +84,7 @@ struct mount {
 	struct list_head to_notify;	/* need to queue notification */
 	struct mnt_namespace *prev_ns;	/* previous namespace (NULL if none) */
 #endif
+	int mnt_t_flags;		/* namespace_sem-protected flags */
 	int mnt_id;			/* mount identifier, reused */
 	u64 mnt_id_unique;		/* mount ID unique until reboot */
 	int mnt_group_id;		/* peer group identifier */
@@ -93,6 +94,22 @@ struct mount {
 	struct mount *overmount;	/* mounted on ->mnt_root */
 } __randomize_layout;
 
+enum {
+	T_SHARED		= 1, /* mount is shared */
+	T_UNBINDABLE		= 2, /* mount is unbindable */
+	T_MARKED		= 4, /* internal mark for propagate_... */
+	T_UMOUNT_CANDIDATE	= 8, /* for propagate_umount */
+
+	/*
+	 * T_SHARED_MASK is the set of flags that should be cleared when a
+	 * mount becomes shared.  Currently, this is only the flag that says a
+	 * mount cannot be bind mounted, since this is how we create a mount
+	 * that shares events with another mount.  If you add a new T_*
+	 * flag, consider how it interacts with shared mounts.
+	 */
+	T_SHARED_MASK	= T_UNBINDABLE,
+};
+
 #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
 
 static inline struct mount *real_mount(struct vfsmount *mnt)
diff --git a/fs/namespace.c b/fs/namespace.c
index 4bdf6a6e75ca..da27365418a5 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -2917,10 +2917,8 @@ static int do_change_type(struct path *path, int ms_flags)
 			goto out_unlock;
 	}
 
-	lock_mount_hash();
 	for (m = mnt; m; m = (recurse ? next_mnt(m, mnt) : NULL))
 		change_mnt_propagation(m, type);
-	unlock_mount_hash();
 
  out_unlock:
 	namespace_unlock();
@@ -3409,9 +3407,7 @@ static int do_set_group(struct path *from_path, struct path *to_path)
 	if (IS_MNT_SHARED(from)) {
 		to->mnt_group_id = from->mnt_group_id;
 		list_add(&to->mnt_share, &from->mnt_share);
-		lock_mount_hash();
 		set_mnt_shared(to);
-		unlock_mount_hash();
 	}
 
 	err = 0;
diff --git a/fs/pnode.c b/fs/pnode.c
index 827d71736ac5..b997663de6d0 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -112,7 +112,7 @@ static int do_make_slave(struct mount *mnt)
 }
 
 /*
- * vfsmount lock must be held for write
+ * EXCL[namespace_sem]
  */
 void change_mnt_propagation(struct mount *mnt, int type)
 {
@@ -125,9 +125,9 @@ void change_mnt_propagation(struct mount *mnt, int type)
 		list_del_init(&mnt->mnt_slave);
 		mnt->mnt_master = NULL;
 		if (type == MS_UNBINDABLE)
-			mnt->mnt.mnt_flags |= MNT_UNBINDABLE;
+			mnt->mnt_t_flags |= T_UNBINDABLE;
 		else
-			mnt->mnt.mnt_flags &= ~MNT_UNBINDABLE;
+			mnt->mnt_t_flags &= ~T_UNBINDABLE;
 	}
 }
 
@@ -263,9 +263,9 @@ static int propagate_one(struct mount *m, struct mountpoint *dest_mp)
 		return PTR_ERR(child);
 	read_seqlock_excl(&mount_lock);
 	mnt_set_mountpoint(m, dest_mp, child);
+	read_sequnlock_excl(&mount_lock);
 	if (m->mnt_master != dest_master)
 		SET_MNT_MARK(m->mnt_master);
-	read_sequnlock_excl(&mount_lock);
 	last_dest = m;
 	last_source = child;
 	hlist_add_head(&child->mnt_hash, list);
@@ -322,13 +322,11 @@ int propagate_mnt(struct mount *dest_mnt, struct mountpoint *dest_mp,
 		} while (n != m);
 	}
 out:
-	read_seqlock_excl(&mount_lock);
 	hlist_for_each_entry(n, tree_list, mnt_hash) {
 		m = n->mnt_parent;
 		if (m->mnt_master != dest_mnt->mnt_master)
 			CLEAR_MNT_MARK(m->mnt_master);
 	}
-	read_sequnlock_excl(&mount_lock);
 	return ret;
 }
 
@@ -447,7 +445,7 @@ void propagate_mount_unlock(struct mount *mnt)
 
 static inline bool is_candidate(struct mount *m)
 {
-	return m->mnt.mnt_flags & MNT_UMOUNT_CANDIDATE;
+	return m->mnt_t_flags & T_UMOUNT_CANDIDATE;
 }
 
 static inline bool will_be_unmounted(struct mount *m)
@@ -464,7 +462,7 @@ static void umount_one(struct mount *m, struct list_head *to_umount)
 
 static void remove_from_candidate_list(struct mount *m)
 {
-	m->mnt.mnt_flags &= ~(MNT_MARKED | MNT_UMOUNT_CANDIDATE);
+	m->mnt_t_flags &= ~(T_MARKED | T_UMOUNT_CANDIDATE);
 	list_del_init(&m->mnt_list);
 }
 
@@ -476,7 +474,7 @@ static void gather_candidates(struct list_head *set,
 	list_for_each_entry(m, set, mnt_list) {
 		if (is_candidate(m))
 			continue;
-		m->mnt.mnt_flags |= MNT_UMOUNT_CANDIDATE;
+		m->mnt_t_flags |= T_UMOUNT_CANDIDATE;
 		p = m->mnt_parent;
 		q = propagation_next(p, p);
 		while (q) {
@@ -494,7 +492,7 @@ static void gather_candidates(struct list_head *set,
 					q = skip_propagation_subtree(q, p);
 					continue;
 				}
-				child->mnt.mnt_flags |= MNT_UMOUNT_CANDIDATE;
+				child->mnt_t_flags |= T_UMOUNT_CANDIDATE;
 				if (!will_be_unmounted(child))
 					list_add(&child->mnt_list, candidates);
 			}
@@ -502,7 +500,7 @@ static void gather_candidates(struct list_head *set,
 		}
 	}
 	list_for_each_entry(m, set, mnt_list)
-		m->mnt.mnt_flags &= ~MNT_UMOUNT_CANDIDATE;
+		m->mnt_t_flags &= ~T_UMOUNT_CANDIDATE;
 }
 
 /*
@@ -519,7 +517,7 @@ static void trim_ancestors(struct mount *m)
 			return;
 		SET_MNT_MARK(m);
 		if (m != p->overmount)
-			p->mnt.mnt_flags &= ~MNT_UMOUNT_CANDIDATE;
+			p->mnt_t_flags &= ~T_UMOUNT_CANDIDATE;
 	}
 }
 
diff --git a/fs/pnode.h b/fs/pnode.h
index 04f1ac53aa49..507e30e7a420 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -10,14 +10,14 @@
 #include <linux/list.h>
 #include "mount.h"
 
-#define IS_MNT_SHARED(m) ((m)->mnt.mnt_flags & MNT_SHARED)
+#define IS_MNT_SHARED(m) ((m)->mnt_t_flags & T_SHARED)
 #define IS_MNT_SLAVE(m) ((m)->mnt_master)
 #define IS_MNT_NEW(m) (!(m)->mnt_ns)
-#define CLEAR_MNT_SHARED(m) ((m)->mnt.mnt_flags &= ~MNT_SHARED)
-#define IS_MNT_UNBINDABLE(m) ((m)->mnt.mnt_flags & MNT_UNBINDABLE)
-#define IS_MNT_MARKED(m) ((m)->mnt.mnt_flags & MNT_MARKED)
-#define SET_MNT_MARK(m) ((m)->mnt.mnt_flags |= MNT_MARKED)
-#define CLEAR_MNT_MARK(m) ((m)->mnt.mnt_flags &= ~MNT_MARKED)
+#define CLEAR_MNT_SHARED(m) ((m)->mnt_t_flags &= ~T_SHARED)
+#define IS_MNT_UNBINDABLE(m) ((m)->mnt_t_flags & T_UNBINDABLE)
+#define IS_MNT_MARKED(m) ((m)->mnt_t_flags & T_MARKED)
+#define SET_MNT_MARK(m) ((m)->mnt_t_flags |= T_MARKED)
+#define CLEAR_MNT_MARK(m) ((m)->mnt_t_flags &= ~T_MARKED)
 #define IS_MNT_LOCKED(m) ((m)->mnt.mnt_flags & MNT_LOCKED)
 
 #define CL_EXPIRE    		0x01
@@ -28,10 +28,13 @@
 #define CL_SHARED_TO_SLAVE	0x20
 #define CL_COPY_MNT_NS_FILE	0x40
 
+/*
+ * EXCL[namespace_sem]
+ */
 static inline void set_mnt_shared(struct mount *mnt)
 {
-	mnt->mnt.mnt_flags &= ~MNT_SHARED_MASK;
-	mnt->mnt.mnt_flags |= MNT_SHARED;
+	mnt->mnt_t_flags &= ~T_SHARED_MASK;
+	mnt->mnt_t_flags |= T_SHARED;
 }
 
 static inline bool peers(const struct mount *m1, const struct mount *m2)
diff --git a/include/linux/mount.h b/include/linux/mount.h
index 65fa8442c00a..5f9c053b0897 100644
--- a/include/linux/mount.h
+++ b/include/linux/mount.h
@@ -35,12 +35,8 @@ enum mount_flags {
 	MNT_SHRINKABLE	= 0x100,
 	MNT_WRITE_HOLD	= 0x200,
 
-	MNT_SHARED	= 0x1000, /* if the vfsmount is a shared mount */
-	MNT_UNBINDABLE	= 0x2000, /* if the vfsmount is a unbindable mount */
-
 	MNT_INTERNAL	= 0x4000,
 
-	MNT_UMOUNT_CANDIDATE	= 0x020000,
 	MNT_LOCK_ATIME		= 0x040000,
 	MNT_LOCK_NOEXEC		= 0x080000,
 	MNT_LOCK_NOSUID		= 0x100000,
@@ -49,25 +45,15 @@ enum mount_flags {
 	MNT_LOCKED		= 0x800000,
 	MNT_DOOMED		= 0x1000000,
 	MNT_SYNC_UMOUNT		= 0x2000000,
-	MNT_MARKED		= 0x4000000,
 	MNT_UMOUNT		= 0x8000000,
 
-	/*
-	 * MNT_SHARED_MASK is the set of flags that should be cleared when a
-	 * mount becomes shared.  Currently, this is only the flag that says a
-	 * mount cannot be bind mounted, since this is how we create a mount
-	 * that shares events with another mount.  If you add a new MNT_*
-	 * flag, consider how it interacts with shared mounts.
-	 */
-	MNT_SHARED_MASK	= MNT_UNBINDABLE,
 	MNT_USER_SETTABLE_MASK  = MNT_NOSUID | MNT_NODEV | MNT_NOEXEC
 				  | MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME
 				  | MNT_READONLY | MNT_NOSYMFOLLOW,
 	MNT_ATIME_MASK = MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME,
 
-	MNT_INTERNAL_FLAGS = MNT_SHARED | MNT_WRITE_HOLD | MNT_INTERNAL |
-			     MNT_DOOMED | MNT_SYNC_UMOUNT | MNT_MARKED |
-			     MNT_LOCKED | MNT_UMOUNT_CANDIDATE,
+	MNT_INTERNAL_FLAGS = MNT_WRITE_HOLD | MNT_INTERNAL | MNT_DOOMED |
+			     MNT_SYNC_UMOUNT | MNT_LOCKED
 };
 
 struct vfsmount {
-- 
cgit v1.2.3


From a0f26fcc383965e0522b81269062a9278bc802fe Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Fri, 27 Jun 2025 09:42:33 +0900
Subject: ata: libata: Remove ATA_DFLAG_ZAC device flag

The ATA device flag ATA_DFLAG_ZAC is used to indicate if a devie is a
host managed or host aware zoned device. However, this flag is not used
in the hot path and only used during device scanning/revalidation and
for inquiry and sense SCSI command translation.

Save one bit from struct ata_device flags field by replacing this flag
with the internal helper function ata_dev_is_zac(). This function
returns true if the device class is ATA_DEV_ZAC (host managed ZAC device
case) or if its identify data reports it supports the zoned command set
(host aware ZAC device case).

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 13 +------------
 drivers/ata/libata-scsi.c |  5 ++---
 drivers/ata/libata.h      |  7 +++++++
 include/linux/libata.h    |  1 -
 4 files changed, 10 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 79b20da0a256..3918ea624e0b 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2421,18 +2421,7 @@ static void ata_dev_config_zac(struct ata_device *dev)
 	dev->zac_zones_optimal_nonseq = U32_MAX;
 	dev->zac_zones_max_open = U32_MAX;
 
-	/*
-	 * Always set the 'ZAC' flag for Host-managed devices.
-	 */
-	if (dev->class == ATA_DEV_ZAC)
-		dev->flags |= ATA_DFLAG_ZAC;
-	else if (ata_id_zoned_cap(dev->id) == 0x01)
-		/*
-		 * Check for host-aware devices.
-		 */
-		dev->flags |= ATA_DFLAG_ZAC;
-
-	if (!(dev->flags & ATA_DFLAG_ZAC))
+	if (!ata_dev_is_zac(dev))
 		return;
 
 	if (!ata_identify_page_supported(dev, ATA_LOG_ZONED_INFORMATION)) {
diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
index a21c9895408d..ccd7651710be 100644
--- a/drivers/ata/libata-scsi.c
+++ b/drivers/ata/libata-scsi.c
@@ -1923,8 +1923,7 @@ static unsigned int ata_scsiop_inq_00(struct ata_device *dev,
 	};
 
 	for (i = 0; i < sizeof(pages); i++) {
-		if (pages[i] == 0xb6 &&
-		    !(dev->flags & ATA_DFLAG_ZAC))
+		if (pages[i] == 0xb6 && !ata_dev_is_zac(dev))
 			continue;
 		rbuf[num_pages + 4] = pages[i];
 		num_pages++;
@@ -2181,7 +2180,7 @@ static unsigned int ata_scsiop_inq_b2(struct ata_device *dev,
 static unsigned int ata_scsiop_inq_b6(struct ata_device *dev,
 				      struct scsi_cmnd *cmd, u8 *rbuf)
 {
-	if (!(dev->flags & ATA_DFLAG_ZAC)) {
+	if (!ata_dev_is_zac(dev)) {
 		ata_scsi_set_invalid_field(dev, cmd, 2, 0xff);
 		return 0;
 	}
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index ce5c628fa6fd..48ee7acb87af 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -44,6 +44,13 @@ static inline bool ata_sstatus_online(u32 sstatus)
 	return (sstatus & 0xf) == 0x3;
 }
 
+static inline bool ata_dev_is_zac(struct ata_device *dev)
+{
+	/* Host managed device or host aware device */
+	return dev->class == ATA_DEV_ZAC ||
+		ata_id_zoned_cap(dev->id) == 0x01;
+}
+
 #ifdef CONFIG_ATA_FORCE
 extern void ata_force_cbl(struct ata_port *ap);
 #else
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 1e5aec839041..721f0805b6c9 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -144,7 +144,6 @@ enum {
 	ATA_DFLAG_DEVSLP	= (1 << 27), /* device supports Device Sleep */
 	ATA_DFLAG_ACPI_DISABLED = (1 << 28), /* ACPI for the device is disabled */
 	ATA_DFLAG_D_SENSE	= (1 << 29), /* Descriptor sense requested */
-	ATA_DFLAG_ZAC		= (1 << 30), /* ZAC device */
 
 	ATA_DFLAG_FEATURES_MASK	= (ATA_DFLAG_TRUSTED | ATA_DFLAG_DA |	\
 				   ATA_DFLAG_DEVSLP | ATA_DFLAG_NCQ_SEND_RECV | \
-- 
cgit v1.2.3


From 2b89eb177c466bb1f84dff8db04d614b33a7ab95 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 19 Jun 2025 18:35:48 +0900
Subject: ata: libata: Improve LPM policies description

Improve the comment describing enum ata_lpm_policy and add comments
within that enum to describe each of the different possible values.
The enum values comments match the description given for the
CONFIG_SATA_MOBILE_LPM_POLICY config parameter.

No functional changes.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
---
 include/linux/libata.h | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/libata.h b/include/linux/libata.h
index 721f0805b6c9..7462218312ad 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -499,16 +499,28 @@ enum ata_completion_errors {
 };
 
 /*
- * Link power management policy: If you alter this, you also need to
- * alter libata-sata.c (for the ascii descriptions)
+ * Link Power Management (LPM) policies.
+ *
+ * The default LPM policy to use for a device link is defined using these values
+ * with the CONFIG_SATA_MOBILE_LPM_POLICY config option and applied through the
+ * target_lpm_policy field of struct ata_port.
+ *
+ * If you alter this, you also need to alter the policy names used with the
+ * sysfs attribute link_power_management_policy defined in libata-sata.c.
  */
 enum ata_lpm_policy {
+	/* Keep firmware settings */
 	ATA_LPM_UNKNOWN,
+	/* No power savings (maximum performance) */
 	ATA_LPM_MAX_POWER,
+	/* HIPM (Partial) */
 	ATA_LPM_MED_POWER,
-	ATA_LPM_MED_POWER_WITH_DIPM, /* Med power + DIPM as win IRST does */
-	ATA_LPM_MIN_POWER_WITH_PARTIAL, /* Min Power + partial and slumber */
-	ATA_LPM_MIN_POWER, /* Min power + no partial (slumber only) */
+	/* HIPM (Partial) and DIPM (Partial and Slumber) */
+	ATA_LPM_MED_POWER_WITH_DIPM,
+	/* HIPM (Partial and DevSleep) and DIPM (Partial and Slumber) */
+	ATA_LPM_MIN_POWER_WITH_PARTIAL,
+	/* HIPM (Slumber and DevSleep) and DIPM (Partial and Slumber) */
+	ATA_LPM_MIN_POWER,
 };
 
 enum ata_lpm_hints {
-- 
cgit v1.2.3


From 08ad63bbd681ae4eeb50644564435035c38e5795 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Fri, 20 Jun 2025 14:58:01 +0200
Subject: gpio: constify arguments of gpiod_is_equal()

This function is not meant to modify the GPIO descriptors in any way so
we can safely constify both arguments.

Link: https://lore.kernel.org/r/20250620-gpiod-is-equal-improv-v1-1-a75060505d2c@linaro.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c        | 2 +-
 include/linux/gpio/consumer.h | 5 +++--
 2 files changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 5b0b4fc97543..6b4f94c3887f 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -286,7 +286,7 @@ EXPORT_SYMBOL_GPL(gpiod_to_gpio_device);
  * Returns:
  * True if the descriptors refer to the same physical pin. False otherwise.
  */
-bool gpiod_is_equal(struct gpio_desc *desc, struct gpio_desc *other)
+bool gpiod_is_equal(const struct gpio_desc *desc, const struct gpio_desc *other)
 {
 	return desc == other;
 }
diff --git a/include/linux/gpio/consumer.h b/include/linux/gpio/consumer.h
index f0b1982da0cc..00df68c51405 100644
--- a/include/linux/gpio/consumer.h
+++ b/include/linux/gpio/consumer.h
@@ -181,7 +181,8 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev,
 					      enum gpiod_flags flags,
 					      const char *label);
 
-bool gpiod_is_equal(struct gpio_desc *desc, struct gpio_desc *other);
+bool gpiod_is_equal(const struct gpio_desc *desc,
+		    const struct gpio_desc *other);
 
 #else /* CONFIG_GPIOLIB */
 
@@ -551,7 +552,7 @@ struct gpio_desc *devm_fwnode_gpiod_get_index(struct device *dev,
 }
 
 static inline bool
-gpiod_is_equal(struct gpio_desc *desc, struct gpio_desc *other)
+gpiod_is_equal(const struct gpio_desc *desc, const struct gpio_desc *other)
 {
 	WARN_ON(desc || other);
 	return false;
-- 
cgit v1.2.3


From 62b5848f73dd4f8ae17304dae54562d0c9ecdd3d Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Tue, 24 Jun 2025 16:32:20 +0200
Subject: power: sequencing: add defines for return values of the match()
 callback

Instead of using 0 and 1 as magic numbers, let's add proper defines
whose names tell the reader what the meaning behind them is.

Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250624-pwrseq-match-defines-v1-3-a59d90a951f1@linaro.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/power/sequencing/core.c | 6 +++---
 include/linux/pwrseq/provider.h | 3 +++
 2 files changed, 6 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/power/sequencing/core.c b/drivers/power/sequencing/core.c
index 0ffc259c6bb6..190564e55988 100644
--- a/drivers/power/sequencing/core.c
+++ b/drivers/power/sequencing/core.c
@@ -628,7 +628,7 @@ static int pwrseq_match_device(struct device *pwrseq_dev, void *data)
 		return 0;
 
 	ret = pwrseq->match(pwrseq, match_data->dev);
-	if (ret <= 0)
+	if (ret == PWRSEQ_NO_MATCH || ret < 0)
 		return ret;
 
 	/* We got the matching device, let's find the right target. */
@@ -651,7 +651,7 @@ static int pwrseq_match_device(struct device *pwrseq_dev, void *data)
 
 	match_data->desc->pwrseq = pwrseq_device_get(pwrseq);
 
-	return 1;
+	return PWRSEQ_MATCH_OK;
 }
 
 /**
@@ -684,7 +684,7 @@ struct pwrseq_desc *pwrseq_get(struct device *dev, const char *target)
 			       pwrseq_match_device);
 	if (ret < 0)
 		return ERR_PTR(ret);
-	if (ret == 0)
+	if (ret == PWRSEQ_NO_MATCH)
 		/* No device matched. */
 		return ERR_PTR(-EPROBE_DEFER);
 
diff --git a/include/linux/pwrseq/provider.h b/include/linux/pwrseq/provider.h
index cbc3607cbfcf..33b3d2c2e39d 100644
--- a/include/linux/pwrseq/provider.h
+++ b/include/linux/pwrseq/provider.h
@@ -13,6 +13,9 @@ struct pwrseq_device;
 typedef int (*pwrseq_power_state_func)(struct pwrseq_device *);
 typedef int (*pwrseq_match_func)(struct pwrseq_device *, struct device *);
 
+#define PWRSEQ_NO_MATCH 0
+#define PWRSEQ_MATCH_OK 1
+
 /**
  * struct pwrseq_unit_data - Configuration of a single power sequencing
  *                           unit.
-- 
cgit v1.2.3


From b1c26e059536d8acbf9d508374f4b76537e20fb7 Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Tue, 10 Jun 2025 15:58:16 -0500
Subject: Move FCH header to a location accessible by all archs
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

A new header fch.h was created to store registers used by different AMD
drivers.  This header was included by i2c-piix4 in
commit 624b0d5696a8 ("i2c: piix4, x86/platform: Move the SB800 PIIX4 FCH
definitions to <asm/amd/fch.h>"). To prevent compile failures on non-x86
archs i2c-piix4 was set to only compile on x86 by commit 7e173eb82ae9717
("i2c: piix4: Make CONFIG_I2C_PIIX4 dependent on CONFIG_X86").
This was not a good decision because loongarch and mips both actually
support i2c-piix4 and set it enabled in the defconfig.

Move the header to a location accessible by all architectures.

Fixes: 624b0d5696a89 ("i2c: piix4, x86/platform: Move the SB800 PIIX4 FCH definitions to <asm/amd/fch.h>")
Suggested-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250610205817.3912944-1-superm1@kernel.org
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 arch/x86/include/asm/amd/fch.h            | 13 -------------
 arch/x86/kernel/cpu/amd.c                 |  2 +-
 drivers/i2c/busses/i2c-piix4.c            |  2 +-
 drivers/platform/x86/amd/pmc/pmc-quirks.c |  2 +-
 include/linux/platform_data/x86/amd-fch.h | 13 +++++++++++++
 5 files changed, 16 insertions(+), 16 deletions(-)
 delete mode 100644 arch/x86/include/asm/amd/fch.h
 create mode 100644 include/linux/platform_data/x86/amd-fch.h

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/amd/fch.h b/arch/x86/include/asm/amd/fch.h
deleted file mode 100644
index 2cf5153edbc2..000000000000
--- a/arch/x86/include/asm/amd/fch.h
+++ /dev/null
@@ -1,13 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _ASM_X86_AMD_FCH_H_
-#define _ASM_X86_AMD_FCH_H_
-
-#define FCH_PM_BASE			0xFED80300
-
-/* Register offsets from PM base: */
-#define FCH_PM_DECODEEN			0x00
-#define FCH_PM_DECODEEN_SMBUS0SEL	GENMASK(20, 19)
-#define FCH_PM_SCRATCH			0x80
-#define FCH_PM_S5_RESET_STATUS		0xC0
-
-#endif /* _ASM_X86_AMD_FCH_H_ */
diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
index 93da466dfe2c..9543d5de4e7d 100644
--- a/arch/x86/kernel/cpu/amd.c
+++ b/arch/x86/kernel/cpu/amd.c
@@ -9,7 +9,7 @@
 #include <linux/sched/clock.h>
 #include <linux/random.h>
 #include <linux/topology.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
 #include <asm/processor.h>
 #include <asm/apic.h>
 #include <asm/cacheinfo.h>
diff --git a/drivers/i2c/busses/i2c-piix4.c b/drivers/i2c/busses/i2c-piix4.c
index 9d3a4dc2bd60..ac3bb550303f 100644
--- a/drivers/i2c/busses/i2c-piix4.c
+++ b/drivers/i2c/busses/i2c-piix4.c
@@ -34,7 +34,7 @@
 #include <linux/dmi.h>
 #include <linux/acpi.h>
 #include <linux/io.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
 
 #include "i2c-piix4.h"
 
diff --git a/drivers/platform/x86/amd/pmc/pmc-quirks.c b/drivers/platform/x86/amd/pmc/pmc-quirks.c
index f292111bd065..131f10b68308 100644
--- a/drivers/platform/x86/amd/pmc/pmc-quirks.c
+++ b/drivers/platform/x86/amd/pmc/pmc-quirks.c
@@ -11,7 +11,7 @@
 #include <linux/dmi.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
-#include <asm/amd/fch.h>
+#include <linux/platform_data/x86/amd-fch.h>
 
 #include "pmc.h"
 
diff --git a/include/linux/platform_data/x86/amd-fch.h b/include/linux/platform_data/x86/amd-fch.h
new file mode 100644
index 000000000000..2cf5153edbc2
--- /dev/null
+++ b/include/linux/platform_data/x86/amd-fch.h
@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_AMD_FCH_H_
+#define _ASM_X86_AMD_FCH_H_
+
+#define FCH_PM_BASE			0xFED80300
+
+/* Register offsets from PM base: */
+#define FCH_PM_DECODEEN			0x00
+#define FCH_PM_DECODEEN_SMBUS0SEL	GENMASK(20, 19)
+#define FCH_PM_SCRATCH			0x80
+#define FCH_PM_S5_RESET_STATUS		0xC0
+
+#endif /* _ASM_X86_AMD_FCH_H_ */
-- 
cgit v1.2.3


From 7ff495e26a39f3e7a3d4058df59b5b6d6f943cab Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Mon, 30 Jun 2025 09:51:38 +0200
Subject: local_lock: Move this_cpu_ptr() notation from internal to main header

local_lock.h is the main header for the local_lock_t type and provides
wrappers around internal functions prefixed with __ in
local_lock_internal.h.

Move the this_cpu_ptr() dereference of the variable from the internal to
the main header. Since it is all macro implemented, this_cpu_ptr() will
still happen within the preempt/ IRQ disabled section.

This frees the internal implementation (__) to be used on local_lock_t
types which are local variables and must not be accessed via
this_cpu_ptr().

Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Waiman Long <longman@redhat.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/all/20250630075138.3448715-2-bigeasy@linutronix.de
---
 include/linux/local_lock.h          | 20 ++++++++++----------
 include/linux/local_lock_internal.h | 30 +++++++++++++++---------------
 2 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/local_lock.h b/include/linux/local_lock.h
index 16a2ee4f8310..2ba846419524 100644
--- a/include/linux/local_lock.h
+++ b/include/linux/local_lock.h
@@ -13,13 +13,13 @@
  * local_lock - Acquire a per CPU local lock
  * @lock:	The lock variable
  */
-#define local_lock(lock)		__local_lock(lock)
+#define local_lock(lock)		__local_lock(this_cpu_ptr(lock))
 
 /**
  * local_lock_irq - Acquire a per CPU local lock and disable interrupts
  * @lock:	The lock variable
  */
-#define local_lock_irq(lock)		__local_lock_irq(lock)
+#define local_lock_irq(lock)		__local_lock_irq(this_cpu_ptr(lock))
 
 /**
  * local_lock_irqsave - Acquire a per CPU local lock, save and disable
@@ -28,19 +28,19 @@
  * @flags:	Storage for interrupt flags
  */
 #define local_lock_irqsave(lock, flags)				\
-	__local_lock_irqsave(lock, flags)
+	__local_lock_irqsave(this_cpu_ptr(lock), flags)
 
 /**
  * local_unlock - Release a per CPU local lock
  * @lock:	The lock variable
  */
-#define local_unlock(lock)		__local_unlock(lock)
+#define local_unlock(lock)		__local_unlock(this_cpu_ptr(lock))
 
 /**
  * local_unlock_irq - Release a per CPU local lock and enable interrupts
  * @lock:	The lock variable
  */
-#define local_unlock_irq(lock)		__local_unlock_irq(lock)
+#define local_unlock_irq(lock)		__local_unlock_irq(this_cpu_ptr(lock))
 
 /**
  * local_unlock_irqrestore - Release a per CPU local lock and restore
@@ -49,7 +49,7 @@
  * @flags:      Interrupt flags to restore
  */
 #define local_unlock_irqrestore(lock, flags)			\
-	__local_unlock_irqrestore(lock, flags)
+	__local_unlock_irqrestore(this_cpu_ptr(lock), flags)
 
 /**
  * local_lock_init - Runtime initialize a lock instance
@@ -64,7 +64,7 @@
  * locking constrains it will _always_ fail to acquire the lock in NMI or
  * HARDIRQ context on PREEMPT_RT.
  */
-#define local_trylock(lock)		__local_trylock(lock)
+#define local_trylock(lock)		__local_trylock(this_cpu_ptr(lock))
 
 /**
  * local_trylock_irqsave - Try to acquire a per CPU local lock, save and disable
@@ -77,7 +77,7 @@
  * HARDIRQ context on PREEMPT_RT.
  */
 #define local_trylock_irqsave(lock, flags)			\
-	__local_trylock_irqsave(lock, flags)
+	__local_trylock_irqsave(this_cpu_ptr(lock), flags)
 
 DEFINE_GUARD(local_lock, local_lock_t __percpu*,
 	     local_lock(_T),
@@ -91,10 +91,10 @@ DEFINE_LOCK_GUARD_1(local_lock_irqsave, local_lock_t __percpu,
 		    unsigned long flags)
 
 #define local_lock_nested_bh(_lock)				\
-	__local_lock_nested_bh(_lock)
+	__local_lock_nested_bh(this_cpu_ptr(_lock))
 
 #define local_unlock_nested_bh(_lock)				\
-	__local_unlock_nested_bh(_lock)
+	__local_unlock_nested_bh(this_cpu_ptr(_lock))
 
 DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*,
 	     local_lock_nested_bh(_T),
diff --git a/include/linux/local_lock_internal.h b/include/linux/local_lock_internal.h
index 8d5ac16a9b17..d80b5306a2c0 100644
--- a/include/linux/local_lock_internal.h
+++ b/include/linux/local_lock_internal.h
@@ -99,14 +99,14 @@ do {								\
 		local_trylock_t *tl;					\
 		local_lock_t *l;					\
 									\
-		l = (local_lock_t *)this_cpu_ptr(lock);			\
+		l = (local_lock_t *)(lock);				\
 		tl = (local_trylock_t *)l;				\
 		_Generic((lock),					\
-			__percpu local_trylock_t *: ({			\
+			local_trylock_t *: ({				\
 				lockdep_assert(tl->acquired == 0);	\
 				WRITE_ONCE(tl->acquired, 1);		\
 			}),						\
-			__percpu local_lock_t *: (void)0);		\
+			local_lock_t *: (void)0);			\
 		local_lock_acquire(l);					\
 	} while (0)
 
@@ -133,7 +133,7 @@ do {								\
 		local_trylock_t *tl;				\
 								\
 		preempt_disable();				\
-		tl = this_cpu_ptr(lock);			\
+		tl = (lock);					\
 		if (READ_ONCE(tl->acquired)) {			\
 			preempt_enable();			\
 			tl = NULL;				\
@@ -150,7 +150,7 @@ do {								\
 		local_trylock_t *tl;				\
 								\
 		local_irq_save(flags);				\
-		tl = this_cpu_ptr(lock);			\
+		tl = (lock);					\
 		if (READ_ONCE(tl->acquired)) {			\
 			local_irq_restore(flags);		\
 			tl = NULL;				\
@@ -167,15 +167,15 @@ do {								\
 		local_trylock_t *tl;					\
 		local_lock_t *l;					\
 									\
-		l = (local_lock_t *)this_cpu_ptr(lock);			\
+		l = (local_lock_t *)(lock);				\
 		tl = (local_trylock_t *)l;				\
 		local_lock_release(l);					\
 		_Generic((lock),					\
-			__percpu local_trylock_t *: ({			\
+			local_trylock_t *: ({				\
 				lockdep_assert(tl->acquired == 1);	\
 				WRITE_ONCE(tl->acquired, 0);		\
 			}),						\
-			__percpu local_lock_t *: (void)0);		\
+			local_lock_t *: (void)0);			\
 	} while (0)
 
 #define __local_unlock(lock)					\
@@ -199,11 +199,11 @@ do {								\
 #define __local_lock_nested_bh(lock)				\
 	do {							\
 		lockdep_assert_in_softirq();			\
-		local_lock_acquire(this_cpu_ptr(lock));	\
+		local_lock_acquire((lock));			\
 	} while (0)
 
 #define __local_unlock_nested_bh(lock)				\
-	local_lock_release(this_cpu_ptr(lock))
+	local_lock_release((lock))
 
 #else /* !CONFIG_PREEMPT_RT */
 
@@ -227,7 +227,7 @@ typedef spinlock_t local_trylock_t;
 #define __local_lock(__lock)					\
 	do {							\
 		migrate_disable();				\
-		spin_lock(this_cpu_ptr((__lock)));		\
+		spin_lock((__lock));				\
 	} while (0)
 
 #define __local_lock_irq(lock)			__local_lock(lock)
@@ -241,7 +241,7 @@ typedef spinlock_t local_trylock_t;
 
 #define __local_unlock(__lock)					\
 	do {							\
-		spin_unlock(this_cpu_ptr((__lock)));		\
+		spin_unlock((__lock));				\
 		migrate_enable();				\
 	} while (0)
 
@@ -252,12 +252,12 @@ typedef spinlock_t local_trylock_t;
 #define __local_lock_nested_bh(lock)				\
 do {								\
 	lockdep_assert_in_softirq_func();			\
-	spin_lock(this_cpu_ptr(lock));				\
+	spin_lock((lock));					\
 } while (0)
 
 #define __local_unlock_nested_bh(lock)				\
 do {								\
-	spin_unlock(this_cpu_ptr((lock)));			\
+	spin_unlock((lock));					\
 } while (0)
 
 #define __local_trylock(lock)					\
@@ -268,7 +268,7 @@ do {								\
 			__locked = 0;				\
 		} else {					\
 			migrate_disable();			\
-			__locked = spin_trylock(this_cpu_ptr((lock)));	\
+			__locked = spin_trylock((lock));	\
 			if (!__locked)				\
 				migrate_enable();		\
 		}						\
-- 
cgit v1.2.3


From f2703a104e89077e622e2f34ac686262c5180d71 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Fri, 6 Jun 2025 20:22:28 -0700
Subject: lib/crc32: Remove unused combination support

Remove crc32_le_combine() and crc32_le_shift(), since they are no longer
used.

Although combination is an interesting thing that can be done with CRCs,
it turned out that none of the users of it in the kernel were even close
to being worthwhile.  All were much better off simply chaining the CRCs
or processing zeroes.

Let's remove the CRC32 combination code for now.  It can come back
(potentially optimized with carryless multiplication instructions) if
there is ever a case where it would actually be worthwhile.

Link: https://lore.kernel.org/r/20250607032228.27868-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 include/linux/crc32.h | 25 -------------------
 lib/crc32.c           | 67 ---------------------------------------------------
 lib/tests/crc_kunit.c | 39 +-----------------------------
 3 files changed, 1 insertion(+), 130 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/crc32.h b/include/linux/crc32.h
index 8c1883b81b42..36bbc0405aa0 100644
--- a/include/linux/crc32.h
+++ b/include/linux/crc32.h
@@ -48,31 +48,6 @@ u32 crc32_optimizations(void);
 static inline u32 crc32_optimizations(void) { return 0; }
 #endif
 
-/**
- * crc32_le_combine - Combine two crc32 check values into one. For two
- * 		      sequences of bytes, seq1 and seq2 with lengths len1
- * 		      and len2, crc32_le() check values were calculated
- * 		      for each, crc1 and crc2.
- *
- * @crc1: crc32 of the first block
- * @crc2: crc32 of the second block
- * @len2: length of the second block
- *
- * Return: The crc32_le() check value of seq1 and seq2 concatenated,
- * 	   requiring only crc1, crc2, and len2. Note: If seq_full denotes
- * 	   the concatenated memory area of seq1 with seq2, and crc_full
- * 	   the crc32_le() value of seq_full, then crc_full ==
- * 	   crc32_le_combine(crc1, crc2, len2) when crc_full was seeded
- * 	   with the same initializer as crc1, and crc2 seed was 0. See
- * 	   also crc32_combine_test().
- */
-u32 crc32_le_shift(u32 crc, size_t len);
-
-static inline u32 crc32_le_combine(u32 crc1, u32 crc2, size_t len2)
-{
-	return crc32_le_shift(crc1, len2) ^ crc2;
-}
-
 #define crc32(seed, data, length)  crc32_le(seed, (unsigned char const *)(data), length)
 
 /*
diff --git a/lib/crc32.c b/lib/crc32.c
index 95429861d3ac..6811b37df2aa 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -25,7 +25,6 @@
 /* see: Documentation/staging/crc32.rst for a description of algorithms */
 
 #include <linux/crc32.h>
-#include <linux/crc32poly.h>
 #include <linux/module.h>
 #include <linux/types.h>
 
@@ -51,72 +50,6 @@ u32 crc32c_base(u32 crc, const u8 *p, size_t len)
 }
 EXPORT_SYMBOL(crc32c_base);
 
-/*
- * This multiplies the polynomials x and y modulo the given modulus.
- * This follows the "little-endian" CRC convention that the lsbit
- * represents the highest power of x, and the msbit represents x^0.
- */
-static u32 gf2_multiply(u32 x, u32 y, u32 modulus)
-{
-	u32 product = x & 1 ? y : 0;
-	int i;
-
-	for (i = 0; i < 31; i++) {
-		product = (product >> 1) ^ (product & 1 ? modulus : 0);
-		x >>= 1;
-		product ^= x & 1 ? y : 0;
-	}
-
-	return product;
-}
-
-/**
- * crc32_generic_shift - Append @len 0 bytes to crc, in logarithmic time
- * @crc: The original little-endian CRC (i.e. lsbit is x^31 coefficient)
- * @len: The number of bytes. @crc is multiplied by x^(8*@len)
- * @polynomial: The modulus used to reduce the result to 32 bits.
- *
- * It's possible to parallelize CRC computations by computing a CRC
- * over separate ranges of a buffer, then summing them.
- * This shifts the given CRC by 8*len bits (i.e. produces the same effect
- * as appending len bytes of zero to the data), in time proportional
- * to log(len).
- */
-static u32 crc32_generic_shift(u32 crc, size_t len, u32 polynomial)
-{
-	u32 power = polynomial;	/* CRC of x^32 */
-	int i;
-
-	/* Shift up to 32 bits in the simple linear way */
-	for (i = 0; i < 8 * (int)(len & 3); i++)
-		crc = (crc >> 1) ^ (crc & 1 ? polynomial : 0);
-
-	len >>= 2;
-	if (!len)
-		return crc;
-
-	for (;;) {
-		/* "power" is x^(2^i), modulo the polynomial */
-		if (len & 1)
-			crc = gf2_multiply(crc, power, polynomial);
-
-		len >>= 1;
-		if (!len)
-			break;
-
-		/* Square power, advancing to x^(2^(i+1)) */
-		power = gf2_multiply(power, power, polynomial);
-	}
-
-	return crc;
-}
-
-u32 crc32_le_shift(u32 crc, size_t len)
-{
-	return crc32_generic_shift(crc, len, CRC32_POLY_LE);
-}
-EXPORT_SYMBOL(crc32_le_shift);
-
 u32 crc32_be_base(u32 crc, const u8 *p, size_t len)
 {
 	while (len--)
diff --git a/lib/tests/crc_kunit.c b/lib/tests/crc_kunit.c
index 064c2d581557..f08d985d8860 100644
--- a/lib/tests/crc_kunit.c
+++ b/lib/tests/crc_kunit.c
@@ -36,14 +36,12 @@ static size_t test_buflen;
  *	  can fit any CRC up to CRC-64.  The CRC is passed in, and is expected
  *	  to be returned in, the least significant bits of the u64.  The
  *	  function is expected to *not* invert the CRC at the beginning and end.
- * @combine_func: Optional function to combine two CRCs.
  */
 struct crc_variant {
 	int bits;
 	bool le;
 	u64 poly;
 	u64 (*func)(u64 crc, const u8 *p, size_t len);
-	u64 (*combine_func)(u64 crc1, u64 crc2, size_t len2);
 };
 
 static u32 rand32(void)
@@ -144,7 +142,7 @@ static size_t generate_random_length(size_t max_length)
 }
 
 /* Test that v->func gives the same CRCs as a reference implementation. */
-static void crc_main_test(struct kunit *test, const struct crc_variant *v)
+static void crc_test(struct kunit *test, const struct crc_variant *v)
 {
 	size_t i;
 
@@ -188,35 +186,6 @@ static void crc_main_test(struct kunit *test, const struct crc_variant *v)
 	}
 }
 
-/* Test that CRC(concat(A, B)) == combine_CRCs(CRC(A), CRC(B), len(B)). */
-static void crc_combine_test(struct kunit *test, const struct crc_variant *v)
-{
-	int i;
-
-	for (i = 0; i < 100; i++) {
-		u64 init_crc = generate_random_initial_crc(v);
-		size_t len1 = generate_random_length(CRC_KUNIT_MAX_LEN);
-		size_t len2 = generate_random_length(CRC_KUNIT_MAX_LEN - len1);
-		u64 crc1, crc2, expected_crc, actual_crc;
-
-		prandom_bytes_state(&rng, test_buffer, len1 + len2);
-		crc1 = v->func(init_crc, test_buffer, len1);
-		crc2 = v->func(0, &test_buffer[len1], len2);
-		expected_crc = v->func(init_crc, test_buffer, len1 + len2);
-		actual_crc = v->combine_func(crc1, crc2, len2);
-		KUNIT_EXPECT_EQ_MSG(test, expected_crc, actual_crc,
-				    "CRC combination gave wrong result with len1=%zu len2=%zu\n",
-				    len1, len2);
-	}
-}
-
-static void crc_test(struct kunit *test, const struct crc_variant *v)
-{
-	crc_main_test(test, v);
-	if (v->combine_func)
-		crc_combine_test(test, v);
-}
-
 static __always_inline void
 crc_benchmark(struct kunit *test,
 	      u64 (*crc_func)(u64 crc, const u8 *p, size_t len))
@@ -337,17 +306,11 @@ static u64 crc32_le_wrapper(u64 crc, const u8 *p, size_t len)
 	return crc32_le(crc, p, len);
 }
 
-static u64 crc32_le_combine_wrapper(u64 crc1, u64 crc2, size_t len2)
-{
-	return crc32_le_combine(crc1, crc2, len2);
-}
-
 static const struct crc_variant crc_variant_crc32_le = {
 	.bits = 32,
 	.le = true,
 	.poly = 0xedb88320,
 	.func = crc32_le_wrapper,
-	.combine_func = crc32_le_combine_wrapper,
 };
 
 static void crc32_le_test(struct kunit *test)
-- 
cgit v1.2.3


From 89a51591405e09a862b9ca1ccfa880986c495c3c Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Sat, 7 Jun 2025 13:04:43 -0700
Subject: lib/crc: Move files into lib/crc/

Move all CRC files in lib/ into a subdirectory lib/crc/ to keep them
from cluttering up the main lib/ directory.

Reviewed-by: "Martin K. Petersen" <martin.petersen@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: "Jason A. Donenfeld" <Jason@zx2c4.com>
Link: https://lore.kernel.org/r/20250607200454.73587-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 Documentation/core-api/kernel-api.rst |  14 +-
 MAINTAINERS                           |   3 +-
 include/linux/crc64.h                 |   3 -
 lib/Kconfig                           |  88 +------
 lib/Kconfig.debug                     |  21 --
 lib/Makefile                          |  32 +--
 lib/crc-ccitt.c                       |  68 -----
 lib/crc-itu-t.c                       |  67 -----
 lib/crc-t10dif.c                      |  65 -----
 lib/crc/.gitignore                    |   5 +
 lib/crc/Kconfig                       | 111 +++++++++
 lib/crc/Makefile                      |  32 +++
 lib/crc/crc-ccitt.c                   |  65 +++++
 lib/crc/crc-itu-t.c                   |  67 +++++
 lib/crc/crc-t10dif.c                  |  65 +++++
 lib/crc/crc16.c                       |  64 +++++
 lib/crc/crc32.c                       |  59 +++++
 lib/crc/crc4.c                        |  44 ++++
 lib/crc/crc64.c                       |  58 +++++
 lib/crc/crc7.c                        |  72 ++++++
 lib/crc/crc8.c                        |  86 +++++++
 lib/crc/gen_crc32table.c              |  89 +++++++
 lib/crc/gen_crc64table.c              |  88 +++++++
 lib/crc/tests/Makefile                |   2 +
 lib/crc/tests/crc_kunit.c             | 452 ++++++++++++++++++++++++++++++++++
 lib/crc16.c                           |  64 -----
 lib/crc32.c                           |  59 -----
 lib/crc4.c                            |  44 ----
 lib/crc64.c                           |  58 -----
 lib/crc7.c                            |  72 ------
 lib/crc8.c                            |  86 -------
 lib/gen_crc32table.c                  |  89 -------
 lib/gen_crc64table.c                  |  95 -------
 lib/tests/Makefile                    |   1 -
 lib/tests/crc_kunit.c                 | 452 ----------------------------------
 35 files changed, 1369 insertions(+), 1371 deletions(-)
 delete mode 100644 lib/crc-ccitt.c
 delete mode 100644 lib/crc-itu-t.c
 delete mode 100644 lib/crc-t10dif.c
 create mode 100644 lib/crc/.gitignore
 create mode 100644 lib/crc/Kconfig
 create mode 100644 lib/crc/Makefile
 create mode 100644 lib/crc/crc-ccitt.c
 create mode 100644 lib/crc/crc-itu-t.c
 create mode 100644 lib/crc/crc-t10dif.c
 create mode 100644 lib/crc/crc16.c
 create mode 100644 lib/crc/crc32.c
 create mode 100644 lib/crc/crc4.c
 create mode 100644 lib/crc/crc64.c
 create mode 100644 lib/crc/crc7.c
 create mode 100644 lib/crc/crc8.c
 create mode 100644 lib/crc/gen_crc32table.c
 create mode 100644 lib/crc/gen_crc64table.c
 create mode 100644 lib/crc/tests/Makefile
 create mode 100644 lib/crc/tests/crc_kunit.c
 delete mode 100644 lib/crc16.c
 delete mode 100644 lib/crc32.c
 delete mode 100644 lib/crc4.c
 delete mode 100644 lib/crc64.c
 delete mode 100644 lib/crc7.c
 delete mode 100644 lib/crc8.c
 delete mode 100644 lib/gen_crc32table.c
 delete mode 100644 lib/gen_crc64table.c
 delete mode 100644 lib/tests/crc_kunit.c

(limited to 'include/linux')

diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index ae92a2571388..c4642d9f13a9 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -136,24 +136,24 @@ Arithmetic Overflow Checking
 CRC Functions
 -------------
 
-.. kernel-doc:: lib/crc4.c
+.. kernel-doc:: lib/crc/crc4.c
    :export:
 
-.. kernel-doc:: lib/crc7.c
+.. kernel-doc:: lib/crc/crc7.c
    :export:
 
-.. kernel-doc:: lib/crc8.c
+.. kernel-doc:: lib/crc/crc8.c
    :export:
 
-.. kernel-doc:: lib/crc16.c
+.. kernel-doc:: lib/crc/crc16.c
    :export:
 
-.. kernel-doc:: lib/crc32.c
+.. kernel-doc:: lib/crc/crc32.c
 
-.. kernel-doc:: lib/crc-ccitt.c
+.. kernel-doc:: lib/crc/crc-ccitt.c
    :export:
 
-.. kernel-doc:: lib/crc-itu-t.c
+.. kernel-doc:: lib/crc/crc-itu-t.c
    :export:
 
 Base 2 log and power Functions
diff --git a/MAINTAINERS b/MAINTAINERS
index 4bac4ea21b64..b0ec17dfbe03 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6361,8 +6361,7 @@ T:	git https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git crc-ne
 F:	Documentation/staging/crc*
 F:	arch/*/lib/crc*
 F:	include/linux/crc*
-F:	lib/crc*
-F:	lib/tests/crc_kunit.c
+F:	lib/crc/
 F:	scripts/gen-crc-consts.py
 
 CREATIVE SB0540
diff --git a/include/linux/crc64.h b/include/linux/crc64.h
index 41de30b907df..b6aa290a7931 100644
--- a/include/linux/crc64.h
+++ b/include/linux/crc64.h
@@ -1,7 +1,4 @@
 /* SPDX-License-Identifier: GPL-2.0 */
-/*
- * See lib/crc64.c for the related specification and polynomial arithmetic.
- */
 #ifndef _LINUX_CRC64_H
 #define _LINUX_CRC64_H
 
diff --git a/lib/Kconfig b/lib/Kconfig
index 37db228f70a9..c483951b624f 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -136,95 +136,9 @@ config TRACE_MMIO_ACCESS
 	  Create tracepoints for MMIO read/write operations. These trace events
 	  can be used for logging all MMIO read/write operations.
 
+source "lib/crc/Kconfig"
 source "lib/crypto/Kconfig"
 
-config CRC_CCITT
-	tristate
-	help
-	  The CRC-CCITT library functions.  Select this if your module uses any
-	  of the functions from <linux/crc-ccitt.h>.
-
-config CRC16
-	tristate
-	help
-	  The CRC16 library functions.  Select this if your module uses any of
-	  the functions from <linux/crc16.h>.
-
-config CRC_T10DIF
-	tristate
-	help
-	  The CRC-T10DIF library functions.  Select this if your module uses
-	  any of the functions from <linux/crc-t10dif.h>.
-
-config ARCH_HAS_CRC_T10DIF
-	bool
-
-config CRC_T10DIF_ARCH
-	tristate
-	default CRC_T10DIF if ARCH_HAS_CRC_T10DIF && CRC_OPTIMIZATIONS
-
-config CRC_ITU_T
-	tristate
-	help
-	  The CRC-ITU-T library functions.  Select this if your module uses
-	  any of the functions from <linux/crc-itu-t.h>.
-
-config CRC32
-	tristate
-	select BITREVERSE
-	help
-	  The CRC32 library functions.  Select this if your module uses any of
-	  the functions from <linux/crc32.h> or <linux/crc32c.h>.
-
-config ARCH_HAS_CRC32
-	bool
-
-config CRC32_ARCH
-	tristate
-	default CRC32 if ARCH_HAS_CRC32 && CRC_OPTIMIZATIONS
-
-config CRC64
-	tristate
-	help
-	  The CRC64 library functions.  Select this if your module uses any of
-	  the functions from <linux/crc64.h>.
-
-config ARCH_HAS_CRC64
-	bool
-
-config CRC64_ARCH
-	tristate
-	default CRC64 if ARCH_HAS_CRC64 && CRC_OPTIMIZATIONS
-
-config CRC4
-	tristate
-	help
-	  The CRC4 library functions.  Select this if your module uses any of
-	  the functions from <linux/crc4.h>.
-
-config CRC7
-	tristate
-	help
-	  The CRC7 library functions.  Select this if your module uses any of
-	  the functions from <linux/crc7.h>.
-
-config CRC8
-	tristate
-	help
-	  The CRC8 library functions.  Select this if your module uses any of
-	  the functions from <linux/crc8.h>.
-
-config CRC_OPTIMIZATIONS
-	bool "Enable optimized CRC implementations" if EXPERT
-	default y
-	help
-	  Disabling this option reduces code size slightly by disabling the
-	  architecture-optimized implementations of any CRC variants that are
-	  enabled.  CRC checksumming performance may get much slower.
-
-	  Keep this enabled unless you're really trying to minimize the size of
-	  the kernel.
-
 config XXHASH
 	tristate
 
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index ebe33181b6e6..3fda96761adb 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -2901,27 +2901,6 @@ config HW_BREAKPOINT_KUNIT_TEST
 
 	  If unsure, say N.
 
-config CRC_KUNIT_TEST
-	tristate "KUnit tests for CRC functions" if !KUNIT_ALL_TESTS
-	depends on KUNIT
-	default KUNIT_ALL_TESTS
-	select CRC7
-	select CRC16
-	select CRC_T10DIF
-	select CRC32
-	select CRC64
-	help
-	  Unit tests for the CRC library functions.
-
-	  This is intended to help people writing architecture-specific
-	  optimized versions.  If unsure, say N.
-
-config CRC_BENCHMARK
-	bool "Benchmark for the CRC functions"
-	depends on CRC_KUNIT_TEST
-	help
-	  Include benchmarks in the KUnit test suite for the CRC functions.
-
 config SIPHASH_KUNIT_TEST
 	tristate "Perform selftest on siphash functions" if !KUNIT_ALL_TESTS
 	depends on KUNIT
diff --git a/lib/Makefile b/lib/Makefile
index c38582f187dd..14a5928bb57f 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -122,7 +122,7 @@ endif
 obj-$(CONFIG_DEBUG_INFO_REDUCED) += debug_info.o
 CFLAGS_debug_info.o += $(call cc-option, -femit-struct-debug-detailed=any)
 
-obj-y += math/ crypto/ tests/ vdso/
+obj-y += math/ crc/ crypto/ tests/ vdso/
 
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
 obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
@@ -148,15 +148,6 @@ obj-$(CONFIG_BITREVERSE) += bitrev.o
 obj-$(CONFIG_LINEAR_RANGES) += linear_ranges.o
 obj-$(CONFIG_PACKING)	+= packing.o
 obj-$(CONFIG_PACKING_KUNIT_TEST) += packing_test.o
-obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
-obj-$(CONFIG_CRC16)	+= crc16.o
-obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o
-obj-$(CONFIG_CRC_ITU_T)	+= crc-itu-t.o
-obj-$(CONFIG_CRC32)	+= crc32.o
-obj-$(CONFIG_CRC64)     += crc64.o
-obj-$(CONFIG_CRC4)	+= crc4.o
-obj-$(CONFIG_CRC7)	+= crc7.o
-obj-$(CONFIG_CRC8)	+= crc8.o
 obj-$(CONFIG_XXHASH)	+= xxhash.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
@@ -294,27 +285,6 @@ obj-$(CONFIG_ASN1_ENCODER) += asn1_encoder.o
 
 obj-$(CONFIG_FONT_SUPPORT) += fonts/
 
-hostprogs	:= gen_crc32table
-hostprogs	+= gen_crc64table
-clean-files	:= crc32table.h
-clean-files	+= crc64table.h
-
-$(obj)/crc32.o: $(obj)/crc32table.h
-
-quiet_cmd_crc32 = GEN     $@
-      cmd_crc32 = $< > $@
-
-$(obj)/crc32table.h: $(obj)/gen_crc32table
-	$(call cmd,crc32)
-
-$(obj)/crc64.o: $(obj)/crc64table.h
-
-quiet_cmd_crc64 = GEN     $@
-      cmd_crc64 = $< > $@
-
-$(obj)/crc64table.h: $(obj)/gen_crc64table
-	$(call cmd,crc64)
-
 #
 # Build a fast OID lookip registry from include/linux/oid_registry.h
 #
diff --git a/lib/crc-ccitt.c b/lib/crc-ccitt.c
deleted file mode 100644
index 9cddf35d3b66..000000000000
--- a/lib/crc-ccitt.c
+++ /dev/null
@@ -1,68 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *	linux/lib/crc-ccitt.c
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/crc-ccitt.h>
-
-/*
- * This mysterious table is just the CRC of each possible byte. It can be
- * computed using the standard bit-at-a-time methods. The polynomial can
- * be seen in entry 128, 0x8408. This corresponds to x^0 + x^5 + x^12.
- * Add the implicit x^16, and you have the standard CRC-CCITT.
- */
-u16 const crc_ccitt_table[256] = {
-	0x0000, 0x1189, 0x2312, 0x329b, 0x4624, 0x57ad, 0x6536, 0x74bf,
-	0x8c48, 0x9dc1, 0xaf5a, 0xbed3, 0xca6c, 0xdbe5, 0xe97e, 0xf8f7,
-	0x1081, 0x0108, 0x3393, 0x221a, 0x56a5, 0x472c, 0x75b7, 0x643e,
-	0x9cc9, 0x8d40, 0xbfdb, 0xae52, 0xdaed, 0xcb64, 0xf9ff, 0xe876,
-	0x2102, 0x308b, 0x0210, 0x1399, 0x6726, 0x76af, 0x4434, 0x55bd,
-	0xad4a, 0xbcc3, 0x8e58, 0x9fd1, 0xeb6e, 0xfae7, 0xc87c, 0xd9f5,
-	0x3183, 0x200a, 0x1291, 0x0318, 0x77a7, 0x662e, 0x54b5, 0x453c,
-	0xbdcb, 0xac42, 0x9ed9, 0x8f50, 0xfbef, 0xea66, 0xd8fd, 0xc974,
-	0x4204, 0x538d, 0x6116, 0x709f, 0x0420, 0x15a9, 0x2732, 0x36bb,
-	0xce4c, 0xdfc5, 0xed5e, 0xfcd7, 0x8868, 0x99e1, 0xab7a, 0xbaf3,
-	0x5285, 0x430c, 0x7197, 0x601e, 0x14a1, 0x0528, 0x37b3, 0x263a,
-	0xdecd, 0xcf44, 0xfddf, 0xec56, 0x98e9, 0x8960, 0xbbfb, 0xaa72,
-	0x6306, 0x728f, 0x4014, 0x519d, 0x2522, 0x34ab, 0x0630, 0x17b9,
-	0xef4e, 0xfec7, 0xcc5c, 0xddd5, 0xa96a, 0xb8e3, 0x8a78, 0x9bf1,
-	0x7387, 0x620e, 0x5095, 0x411c, 0x35a3, 0x242a, 0x16b1, 0x0738,
-	0xffcf, 0xee46, 0xdcdd, 0xcd54, 0xb9eb, 0xa862, 0x9af9, 0x8b70,
-	0x8408, 0x9581, 0xa71a, 0xb693, 0xc22c, 0xd3a5, 0xe13e, 0xf0b7,
-	0x0840, 0x19c9, 0x2b52, 0x3adb, 0x4e64, 0x5fed, 0x6d76, 0x7cff,
-	0x9489, 0x8500, 0xb79b, 0xa612, 0xd2ad, 0xc324, 0xf1bf, 0xe036,
-	0x18c1, 0x0948, 0x3bd3, 0x2a5a, 0x5ee5, 0x4f6c, 0x7df7, 0x6c7e,
-	0xa50a, 0xb483, 0x8618, 0x9791, 0xe32e, 0xf2a7, 0xc03c, 0xd1b5,
-	0x2942, 0x38cb, 0x0a50, 0x1bd9, 0x6f66, 0x7eef, 0x4c74, 0x5dfd,
-	0xb58b, 0xa402, 0x9699, 0x8710, 0xf3af, 0xe226, 0xd0bd, 0xc134,
-	0x39c3, 0x284a, 0x1ad1, 0x0b58, 0x7fe7, 0x6e6e, 0x5cf5, 0x4d7c,
-	0xc60c, 0xd785, 0xe51e, 0xf497, 0x8028, 0x91a1, 0xa33a, 0xb2b3,
-	0x4a44, 0x5bcd, 0x6956, 0x78df, 0x0c60, 0x1de9, 0x2f72, 0x3efb,
-	0xd68d, 0xc704, 0xf59f, 0xe416, 0x90a9, 0x8120, 0xb3bb, 0xa232,
-	0x5ac5, 0x4b4c, 0x79d7, 0x685e, 0x1ce1, 0x0d68, 0x3ff3, 0x2e7a,
-	0xe70e, 0xf687, 0xc41c, 0xd595, 0xa12a, 0xb0a3, 0x8238, 0x93b1,
-	0x6b46, 0x7acf, 0x4854, 0x59dd, 0x2d62, 0x3ceb, 0x0e70, 0x1ff9,
-	0xf78f, 0xe606, 0xd49d, 0xc514, 0xb1ab, 0xa022, 0x92b9, 0x8330,
-	0x7bc7, 0x6a4e, 0x58d5, 0x495c, 0x3de3, 0x2c6a, 0x1ef1, 0x0f78
-};
-EXPORT_SYMBOL(crc_ccitt_table);
-
-/**
- *	crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data
- *	buffer
- *	@crc: previous CRC value
- *	@buffer: data pointer
- *	@len: number of bytes in the buffer
- */
-u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len)
-{
-	while (len--)
-		crc = crc_ccitt_byte(crc, *buffer++);
-	return crc;
-}
-EXPORT_SYMBOL(crc_ccitt);
-
-MODULE_DESCRIPTION("CRC-CCITT calculations");
-MODULE_LICENSE("GPL");
diff --git a/lib/crc-itu-t.c b/lib/crc-itu-t.c
deleted file mode 100644
index 1d26a1647da5..000000000000
--- a/lib/crc-itu-t.c
+++ /dev/null
@@ -1,67 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *      crc-itu-t.c
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/crc-itu-t.h>
-
-/* CRC table for the CRC ITU-T V.41 0x1021 (x^16 + x^12 + x^5 + 1) */
-const u16 crc_itu_t_table[256] = {
-	0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50a5, 0x60c6, 0x70e7,
-	0x8108, 0x9129, 0xa14a, 0xb16b, 0xc18c, 0xd1ad, 0xe1ce, 0xf1ef,
-	0x1231, 0x0210, 0x3273, 0x2252, 0x52b5, 0x4294, 0x72f7, 0x62d6,
-	0x9339, 0x8318, 0xb37b, 0xa35a, 0xd3bd, 0xc39c, 0xf3ff, 0xe3de,
-	0x2462, 0x3443, 0x0420, 0x1401, 0x64e6, 0x74c7, 0x44a4, 0x5485,
-	0xa56a, 0xb54b, 0x8528, 0x9509, 0xe5ee, 0xf5cf, 0xc5ac, 0xd58d,
-	0x3653, 0x2672, 0x1611, 0x0630, 0x76d7, 0x66f6, 0x5695, 0x46b4,
-	0xb75b, 0xa77a, 0x9719, 0x8738, 0xf7df, 0xe7fe, 0xd79d, 0xc7bc,
-	0x48c4, 0x58e5, 0x6886, 0x78a7, 0x0840, 0x1861, 0x2802, 0x3823,
-	0xc9cc, 0xd9ed, 0xe98e, 0xf9af, 0x8948, 0x9969, 0xa90a, 0xb92b,
-	0x5af5, 0x4ad4, 0x7ab7, 0x6a96, 0x1a71, 0x0a50, 0x3a33, 0x2a12,
-	0xdbfd, 0xcbdc, 0xfbbf, 0xeb9e, 0x9b79, 0x8b58, 0xbb3b, 0xab1a,
-	0x6ca6, 0x7c87, 0x4ce4, 0x5cc5, 0x2c22, 0x3c03, 0x0c60, 0x1c41,
-	0xedae, 0xfd8f, 0xcdec, 0xddcd, 0xad2a, 0xbd0b, 0x8d68, 0x9d49,
-	0x7e97, 0x6eb6, 0x5ed5, 0x4ef4, 0x3e13, 0x2e32, 0x1e51, 0x0e70,
-	0xff9f, 0xefbe, 0xdfdd, 0xcffc, 0xbf1b, 0xaf3a, 0x9f59, 0x8f78,
-	0x9188, 0x81a9, 0xb1ca, 0xa1eb, 0xd10c, 0xc12d, 0xf14e, 0xe16f,
-	0x1080, 0x00a1, 0x30c2, 0x20e3, 0x5004, 0x4025, 0x7046, 0x6067,
-	0x83b9, 0x9398, 0xa3fb, 0xb3da, 0xc33d, 0xd31c, 0xe37f, 0xf35e,
-	0x02b1, 0x1290, 0x22f3, 0x32d2, 0x4235, 0x5214, 0x6277, 0x7256,
-	0xb5ea, 0xa5cb, 0x95a8, 0x8589, 0xf56e, 0xe54f, 0xd52c, 0xc50d,
-	0x34e2, 0x24c3, 0x14a0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
-	0xa7db, 0xb7fa, 0x8799, 0x97b8, 0xe75f, 0xf77e, 0xc71d, 0xd73c,
-	0x26d3, 0x36f2, 0x0691, 0x16b0, 0x6657, 0x7676, 0x4615, 0x5634,
-	0xd94c, 0xc96d, 0xf90e, 0xe92f, 0x99c8, 0x89e9, 0xb98a, 0xa9ab,
-	0x5844, 0x4865, 0x7806, 0x6827, 0x18c0, 0x08e1, 0x3882, 0x28a3,
-	0xcb7d, 0xdb5c, 0xeb3f, 0xfb1e, 0x8bf9, 0x9bd8, 0xabbb, 0xbb9a,
-	0x4a75, 0x5a54, 0x6a37, 0x7a16, 0x0af1, 0x1ad0, 0x2ab3, 0x3a92,
-	0xfd2e, 0xed0f, 0xdd6c, 0xcd4d, 0xbdaa, 0xad8b, 0x9de8, 0x8dc9,
-	0x7c26, 0x6c07, 0x5c64, 0x4c45, 0x3ca2, 0x2c83, 0x1ce0, 0x0cc1,
-	0xef1f, 0xff3e, 0xcf5d, 0xdf7c, 0xaf9b, 0xbfba, 0x8fd9, 0x9ff8,
-	0x6e17, 0x7e36, 0x4e55, 0x5e74, 0x2e93, 0x3eb2, 0x0ed1, 0x1ef0
-};
-
-EXPORT_SYMBOL(crc_itu_t_table);
-
-/**
- * crc_itu_t - Compute the CRC-ITU-T for the data buffer
- *
- * @crc:     previous CRC value
- * @buffer:  data pointer
- * @len:     number of bytes in the buffer
- *
- * Returns the updated CRC value
- */
-u16 crc_itu_t(u16 crc, const u8 *buffer, size_t len)
-{
-	while (len--)
-		crc = crc_itu_t_byte(crc, *buffer++);
-	return crc;
-}
-EXPORT_SYMBOL(crc_itu_t);
-
-MODULE_DESCRIPTION("CRC ITU-T V.41 calculations");
-MODULE_LICENSE("GPL");
-
diff --git a/lib/crc-t10dif.c b/lib/crc-t10dif.c
deleted file mode 100644
index 311c2ab829f1..000000000000
--- a/lib/crc-t10dif.c
+++ /dev/null
@@ -1,65 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * T10 Data Integrity Field CRC16 calculation
- *
- * Copyright (c) 2007 Oracle Corporation.  All rights reserved.
- * Written by Martin K. Petersen <martin.petersen@oracle.com>
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/crc-t10dif.h>
-
-/*
- * Table generated using the following polynomial:
- * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1
- * gt: 0x8bb7
- */
-static const u16 t10_dif_crc_table[256] = {
-	0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B,
-	0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6,
-	0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6,
-	0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B,
-	0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1,
-	0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C,
-	0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C,
-	0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781,
-	0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8,
-	0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255,
-	0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925,
-	0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698,
-	0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472,
-	0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF,
-	0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF,
-	0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02,
-	0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA,
-	0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067,
-	0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17,
-	0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA,
-	0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640,
-	0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD,
-	0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D,
-	0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30,
-	0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759,
-	0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4,
-	0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394,
-	0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29,
-	0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3,
-	0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E,
-	0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E,
-	0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3
-};
-
-u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len; i++)
-		crc = (crc << 8) ^ t10_dif_crc_table[(crc >> 8) ^ p[i]];
-
-	return crc;
-}
-EXPORT_SYMBOL(crc_t10dif_generic);
-
-MODULE_DESCRIPTION("T10 DIF CRC calculation");
-MODULE_LICENSE("GPL");
diff --git a/lib/crc/.gitignore b/lib/crc/.gitignore
new file mode 100644
index 000000000000..a9e48103c9fb
--- /dev/null
+++ b/lib/crc/.gitignore
@@ -0,0 +1,5 @@
+# SPDX-License-Identifier: GPL-2.0-only
+/crc32table.h
+/crc64table.h
+/gen_crc32table
+/gen_crc64table
diff --git a/lib/crc/Kconfig b/lib/crc/Kconfig
new file mode 100644
index 000000000000..e0e7168b74c7
--- /dev/null
+++ b/lib/crc/Kconfig
@@ -0,0 +1,111 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+# Kconfig for the kernel's cyclic redundancy check (CRC) library code
+
+config CRC4
+	tristate
+	help
+	  The CRC4 library functions.  Select this if your module uses any of
+	  the functions from <linux/crc4.h>.
+
+config CRC7
+	tristate
+	help
+	  The CRC7 library functions.  Select this if your module uses any of
+	  the functions from <linux/crc7.h>.
+
+config CRC8
+	tristate
+	help
+	  The CRC8 library functions.  Select this if your module uses any of
+	  the functions from <linux/crc8.h>.
+
+config CRC16
+	tristate
+	help
+	  The CRC16 library functions.  Select this if your module uses any of
+	  the functions from <linux/crc16.h>.
+
+config CRC_CCITT
+	tristate
+	help
+	  The CRC-CCITT library functions.  Select this if your module uses any
+	  of the functions from <linux/crc-ccitt.h>.
+
+config CRC_ITU_T
+	tristate
+	help
+	  The CRC-ITU-T library functions.  Select this if your module uses
+	  any of the functions from <linux/crc-itu-t.h>.
+
+config CRC_T10DIF
+	tristate
+	help
+	  The CRC-T10DIF library functions.  Select this if your module uses
+	  any of the functions from <linux/crc-t10dif.h>.
+
+config ARCH_HAS_CRC_T10DIF
+	bool
+
+config CRC_T10DIF_ARCH
+	tristate
+	default CRC_T10DIF if ARCH_HAS_CRC_T10DIF && CRC_OPTIMIZATIONS
+
+config CRC32
+	tristate
+	select BITREVERSE
+	help
+	  The CRC32 library functions.  Select this if your module uses any of
+	  the functions from <linux/crc32.h> or <linux/crc32c.h>.
+
+config ARCH_HAS_CRC32
+	bool
+
+config CRC32_ARCH
+	tristate
+	default CRC32 if ARCH_HAS_CRC32 && CRC_OPTIMIZATIONS
+
+config CRC64
+	tristate
+	help
+	  The CRC64 library functions.  Select this if your module uses any of
+	  the functions from <linux/crc64.h>.
+
+config ARCH_HAS_CRC64
+	bool
+
+config CRC64_ARCH
+	tristate
+	default CRC64 if ARCH_HAS_CRC64 && CRC_OPTIMIZATIONS
+
+config CRC_OPTIMIZATIONS
+	bool "Enable optimized CRC implementations" if EXPERT
+	default y
+	help
+	  Disabling this option reduces code size slightly by disabling the
+	  architecture-optimized implementations of any CRC variants that are
+	  enabled.  CRC checksumming performance may get much slower.
+
+	  Keep this enabled unless you're really trying to minimize the size of
+	  the kernel.
+
+config CRC_KUNIT_TEST
+	tristate "KUnit tests for CRC functions" if !KUNIT_ALL_TESTS
+	depends on KUNIT
+	default KUNIT_ALL_TESTS
+	select CRC7
+	select CRC16
+	select CRC_T10DIF
+	select CRC32
+	select CRC64
+	help
+	  Unit tests for the CRC library functions.
+
+	  This is intended to help people writing architecture-specific
+	  optimized versions.  If unsure, say N.
+
+config CRC_BENCHMARK
+	bool "Benchmark for the CRC functions"
+	depends on CRC_KUNIT_TEST
+	help
+	  Include benchmarks in the KUnit test suite for the CRC functions.
diff --git a/lib/crc/Makefile b/lib/crc/Makefile
new file mode 100644
index 000000000000..ff4c30dda452
--- /dev/null
+++ b/lib/crc/Makefile
@@ -0,0 +1,32 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+# Makefile for the kernel's cyclic redundancy check (CRC) library code
+
+obj-$(CONFIG_CRC4) += crc4.o
+obj-$(CONFIG_CRC7) += crc7.o
+obj-$(CONFIG_CRC8) += crc8.o
+obj-$(CONFIG_CRC16) += crc16.o
+obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
+obj-$(CONFIG_CRC_ITU_T) += crc-itu-t.o
+obj-$(CONFIG_CRC_T10DIF) += crc-t10dif.o
+obj-$(CONFIG_CRC32) += crc32.o
+obj-$(CONFIG_CRC64) += crc64.o
+obj-y += tests/
+
+hostprogs := gen_crc32table gen_crc64table
+clean-files := crc32table.h crc64table.h
+
+$(obj)/crc32.o: $(obj)/crc32table.h
+$(obj)/crc64.o: $(obj)/crc64table.h
+
+quiet_cmd_crc32 = GEN     $@
+      cmd_crc32 = $< > $@
+
+quiet_cmd_crc64 = GEN     $@
+      cmd_crc64 = $< > $@
+
+$(obj)/crc32table.h: $(obj)/gen_crc32table
+	$(call cmd,crc32)
+
+$(obj)/crc64table.h: $(obj)/gen_crc64table
+	$(call cmd,crc64)
diff --git a/lib/crc/crc-ccitt.c b/lib/crc/crc-ccitt.c
new file mode 100644
index 000000000000..8d2bc419230b
--- /dev/null
+++ b/lib/crc/crc-ccitt.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-ccitt.h>
+
+/*
+ * This mysterious table is just the CRC of each possible byte. It can be
+ * computed using the standard bit-at-a-time methods. The polynomial can
+ * be seen in entry 128, 0x8408. This corresponds to x^0 + x^5 + x^12.
+ * Add the implicit x^16, and you have the standard CRC-CCITT.
+ */
+u16 const crc_ccitt_table[256] = {
+	0x0000, 0x1189, 0x2312, 0x329b, 0x4624, 0x57ad, 0x6536, 0x74bf,
+	0x8c48, 0x9dc1, 0xaf5a, 0xbed3, 0xca6c, 0xdbe5, 0xe97e, 0xf8f7,
+	0x1081, 0x0108, 0x3393, 0x221a, 0x56a5, 0x472c, 0x75b7, 0x643e,
+	0x9cc9, 0x8d40, 0xbfdb, 0xae52, 0xdaed, 0xcb64, 0xf9ff, 0xe876,
+	0x2102, 0x308b, 0x0210, 0x1399, 0x6726, 0x76af, 0x4434, 0x55bd,
+	0xad4a, 0xbcc3, 0x8e58, 0x9fd1, 0xeb6e, 0xfae7, 0xc87c, 0xd9f5,
+	0x3183, 0x200a, 0x1291, 0x0318, 0x77a7, 0x662e, 0x54b5, 0x453c,
+	0xbdcb, 0xac42, 0x9ed9, 0x8f50, 0xfbef, 0xea66, 0xd8fd, 0xc974,
+	0x4204, 0x538d, 0x6116, 0x709f, 0x0420, 0x15a9, 0x2732, 0x36bb,
+	0xce4c, 0xdfc5, 0xed5e, 0xfcd7, 0x8868, 0x99e1, 0xab7a, 0xbaf3,
+	0x5285, 0x430c, 0x7197, 0x601e, 0x14a1, 0x0528, 0x37b3, 0x263a,
+	0xdecd, 0xcf44, 0xfddf, 0xec56, 0x98e9, 0x8960, 0xbbfb, 0xaa72,
+	0x6306, 0x728f, 0x4014, 0x519d, 0x2522, 0x34ab, 0x0630, 0x17b9,
+	0xef4e, 0xfec7, 0xcc5c, 0xddd5, 0xa96a, 0xb8e3, 0x8a78, 0x9bf1,
+	0x7387, 0x620e, 0x5095, 0x411c, 0x35a3, 0x242a, 0x16b1, 0x0738,
+	0xffcf, 0xee46, 0xdcdd, 0xcd54, 0xb9eb, 0xa862, 0x9af9, 0x8b70,
+	0x8408, 0x9581, 0xa71a, 0xb693, 0xc22c, 0xd3a5, 0xe13e, 0xf0b7,
+	0x0840, 0x19c9, 0x2b52, 0x3adb, 0x4e64, 0x5fed, 0x6d76, 0x7cff,
+	0x9489, 0x8500, 0xb79b, 0xa612, 0xd2ad, 0xc324, 0xf1bf, 0xe036,
+	0x18c1, 0x0948, 0x3bd3, 0x2a5a, 0x5ee5, 0x4f6c, 0x7df7, 0x6c7e,
+	0xa50a, 0xb483, 0x8618, 0x9791, 0xe32e, 0xf2a7, 0xc03c, 0xd1b5,
+	0x2942, 0x38cb, 0x0a50, 0x1bd9, 0x6f66, 0x7eef, 0x4c74, 0x5dfd,
+	0xb58b, 0xa402, 0x9699, 0x8710, 0xf3af, 0xe226, 0xd0bd, 0xc134,
+	0x39c3, 0x284a, 0x1ad1, 0x0b58, 0x7fe7, 0x6e6e, 0x5cf5, 0x4d7c,
+	0xc60c, 0xd785, 0xe51e, 0xf497, 0x8028, 0x91a1, 0xa33a, 0xb2b3,
+	0x4a44, 0x5bcd, 0x6956, 0x78df, 0x0c60, 0x1de9, 0x2f72, 0x3efb,
+	0xd68d, 0xc704, 0xf59f, 0xe416, 0x90a9, 0x8120, 0xb3bb, 0xa232,
+	0x5ac5, 0x4b4c, 0x79d7, 0x685e, 0x1ce1, 0x0d68, 0x3ff3, 0x2e7a,
+	0xe70e, 0xf687, 0xc41c, 0xd595, 0xa12a, 0xb0a3, 0x8238, 0x93b1,
+	0x6b46, 0x7acf, 0x4854, 0x59dd, 0x2d62, 0x3ceb, 0x0e70, 0x1ff9,
+	0xf78f, 0xe606, 0xd49d, 0xc514, 0xb1ab, 0xa022, 0x92b9, 0x8330,
+	0x7bc7, 0x6a4e, 0x58d5, 0x495c, 0x3de3, 0x2c6a, 0x1ef1, 0x0f78
+};
+EXPORT_SYMBOL(crc_ccitt_table);
+
+/**
+ *	crc_ccitt - recompute the CRC (CRC-CCITT variant) for the data
+ *	buffer
+ *	@crc: previous CRC value
+ *	@buffer: data pointer
+ *	@len: number of bytes in the buffer
+ */
+u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len)
+{
+	while (len--)
+		crc = crc_ccitt_byte(crc, *buffer++);
+	return crc;
+}
+EXPORT_SYMBOL(crc_ccitt);
+
+MODULE_DESCRIPTION("CRC-CCITT calculations");
+MODULE_LICENSE("GPL");
diff --git a/lib/crc/crc-itu-t.c b/lib/crc/crc-itu-t.c
new file mode 100644
index 000000000000..1d26a1647da5
--- /dev/null
+++ b/lib/crc/crc-itu-t.c
@@ -0,0 +1,67 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *      crc-itu-t.c
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-itu-t.h>
+
+/* CRC table for the CRC ITU-T V.41 0x1021 (x^16 + x^12 + x^5 + 1) */
+const u16 crc_itu_t_table[256] = {
+	0x0000, 0x1021, 0x2042, 0x3063, 0x4084, 0x50a5, 0x60c6, 0x70e7,
+	0x8108, 0x9129, 0xa14a, 0xb16b, 0xc18c, 0xd1ad, 0xe1ce, 0xf1ef,
+	0x1231, 0x0210, 0x3273, 0x2252, 0x52b5, 0x4294, 0x72f7, 0x62d6,
+	0x9339, 0x8318, 0xb37b, 0xa35a, 0xd3bd, 0xc39c, 0xf3ff, 0xe3de,
+	0x2462, 0x3443, 0x0420, 0x1401, 0x64e6, 0x74c7, 0x44a4, 0x5485,
+	0xa56a, 0xb54b, 0x8528, 0x9509, 0xe5ee, 0xf5cf, 0xc5ac, 0xd58d,
+	0x3653, 0x2672, 0x1611, 0x0630, 0x76d7, 0x66f6, 0x5695, 0x46b4,
+	0xb75b, 0xa77a, 0x9719, 0x8738, 0xf7df, 0xe7fe, 0xd79d, 0xc7bc,
+	0x48c4, 0x58e5, 0x6886, 0x78a7, 0x0840, 0x1861, 0x2802, 0x3823,
+	0xc9cc, 0xd9ed, 0xe98e, 0xf9af, 0x8948, 0x9969, 0xa90a, 0xb92b,
+	0x5af5, 0x4ad4, 0x7ab7, 0x6a96, 0x1a71, 0x0a50, 0x3a33, 0x2a12,
+	0xdbfd, 0xcbdc, 0xfbbf, 0xeb9e, 0x9b79, 0x8b58, 0xbb3b, 0xab1a,
+	0x6ca6, 0x7c87, 0x4ce4, 0x5cc5, 0x2c22, 0x3c03, 0x0c60, 0x1c41,
+	0xedae, 0xfd8f, 0xcdec, 0xddcd, 0xad2a, 0xbd0b, 0x8d68, 0x9d49,
+	0x7e97, 0x6eb6, 0x5ed5, 0x4ef4, 0x3e13, 0x2e32, 0x1e51, 0x0e70,
+	0xff9f, 0xefbe, 0xdfdd, 0xcffc, 0xbf1b, 0xaf3a, 0x9f59, 0x8f78,
+	0x9188, 0x81a9, 0xb1ca, 0xa1eb, 0xd10c, 0xc12d, 0xf14e, 0xe16f,
+	0x1080, 0x00a1, 0x30c2, 0x20e3, 0x5004, 0x4025, 0x7046, 0x6067,
+	0x83b9, 0x9398, 0xa3fb, 0xb3da, 0xc33d, 0xd31c, 0xe37f, 0xf35e,
+	0x02b1, 0x1290, 0x22f3, 0x32d2, 0x4235, 0x5214, 0x6277, 0x7256,
+	0xb5ea, 0xa5cb, 0x95a8, 0x8589, 0xf56e, 0xe54f, 0xd52c, 0xc50d,
+	0x34e2, 0x24c3, 0x14a0, 0x0481, 0x7466, 0x6447, 0x5424, 0x4405,
+	0xa7db, 0xb7fa, 0x8799, 0x97b8, 0xe75f, 0xf77e, 0xc71d, 0xd73c,
+	0x26d3, 0x36f2, 0x0691, 0x16b0, 0x6657, 0x7676, 0x4615, 0x5634,
+	0xd94c, 0xc96d, 0xf90e, 0xe92f, 0x99c8, 0x89e9, 0xb98a, 0xa9ab,
+	0x5844, 0x4865, 0x7806, 0x6827, 0x18c0, 0x08e1, 0x3882, 0x28a3,
+	0xcb7d, 0xdb5c, 0xeb3f, 0xfb1e, 0x8bf9, 0x9bd8, 0xabbb, 0xbb9a,
+	0x4a75, 0x5a54, 0x6a37, 0x7a16, 0x0af1, 0x1ad0, 0x2ab3, 0x3a92,
+	0xfd2e, 0xed0f, 0xdd6c, 0xcd4d, 0xbdaa, 0xad8b, 0x9de8, 0x8dc9,
+	0x7c26, 0x6c07, 0x5c64, 0x4c45, 0x3ca2, 0x2c83, 0x1ce0, 0x0cc1,
+	0xef1f, 0xff3e, 0xcf5d, 0xdf7c, 0xaf9b, 0xbfba, 0x8fd9, 0x9ff8,
+	0x6e17, 0x7e36, 0x4e55, 0x5e74, 0x2e93, 0x3eb2, 0x0ed1, 0x1ef0
+};
+
+EXPORT_SYMBOL(crc_itu_t_table);
+
+/**
+ * crc_itu_t - Compute the CRC-ITU-T for the data buffer
+ *
+ * @crc:     previous CRC value
+ * @buffer:  data pointer
+ * @len:     number of bytes in the buffer
+ *
+ * Returns the updated CRC value
+ */
+u16 crc_itu_t(u16 crc, const u8 *buffer, size_t len)
+{
+	while (len--)
+		crc = crc_itu_t_byte(crc, *buffer++);
+	return crc;
+}
+EXPORT_SYMBOL(crc_itu_t);
+
+MODULE_DESCRIPTION("CRC ITU-T V.41 calculations");
+MODULE_LICENSE("GPL");
+
diff --git a/lib/crc/crc-t10dif.c b/lib/crc/crc-t10dif.c
new file mode 100644
index 000000000000..311c2ab829f1
--- /dev/null
+++ b/lib/crc/crc-t10dif.c
@@ -0,0 +1,65 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * T10 Data Integrity Field CRC16 calculation
+ *
+ * Copyright (c) 2007 Oracle Corporation.  All rights reserved.
+ * Written by Martin K. Petersen <martin.petersen@oracle.com>
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-t10dif.h>
+
+/*
+ * Table generated using the following polynomial:
+ * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1
+ * gt: 0x8bb7
+ */
+static const u16 t10_dif_crc_table[256] = {
+	0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B,
+	0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6,
+	0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6,
+	0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B,
+	0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1,
+	0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C,
+	0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C,
+	0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781,
+	0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8,
+	0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255,
+	0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925,
+	0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698,
+	0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472,
+	0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF,
+	0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF,
+	0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02,
+	0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA,
+	0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067,
+	0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17,
+	0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA,
+	0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640,
+	0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD,
+	0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D,
+	0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30,
+	0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759,
+	0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4,
+	0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394,
+	0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29,
+	0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3,
+	0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E,
+	0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E,
+	0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3
+};
+
+u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len)
+{
+	size_t i;
+
+	for (i = 0; i < len; i++)
+		crc = (crc << 8) ^ t10_dif_crc_table[(crc >> 8) ^ p[i]];
+
+	return crc;
+}
+EXPORT_SYMBOL(crc_t10dif_generic);
+
+MODULE_DESCRIPTION("T10 DIF CRC calculation");
+MODULE_LICENSE("GPL");
diff --git a/lib/crc/crc16.c b/lib/crc/crc16.c
new file mode 100644
index 000000000000..9c71eda9bf4b
--- /dev/null
+++ b/lib/crc/crc16.c
@@ -0,0 +1,64 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *      crc16.c
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc16.h>
+
+/** CRC table for the CRC-16. The poly is 0x8005 (x^16 + x^15 + x^2 + 1) */
+static const u16 crc16_table[256] = {
+	0x0000, 0xC0C1, 0xC181, 0x0140, 0xC301, 0x03C0, 0x0280, 0xC241,
+	0xC601, 0x06C0, 0x0780, 0xC741, 0x0500, 0xC5C1, 0xC481, 0x0440,
+	0xCC01, 0x0CC0, 0x0D80, 0xCD41, 0x0F00, 0xCFC1, 0xCE81, 0x0E40,
+	0x0A00, 0xCAC1, 0xCB81, 0x0B40, 0xC901, 0x09C0, 0x0880, 0xC841,
+	0xD801, 0x18C0, 0x1980, 0xD941, 0x1B00, 0xDBC1, 0xDA81, 0x1A40,
+	0x1E00, 0xDEC1, 0xDF81, 0x1F40, 0xDD01, 0x1DC0, 0x1C80, 0xDC41,
+	0x1400, 0xD4C1, 0xD581, 0x1540, 0xD701, 0x17C0, 0x1680, 0xD641,
+	0xD201, 0x12C0, 0x1380, 0xD341, 0x1100, 0xD1C1, 0xD081, 0x1040,
+	0xF001, 0x30C0, 0x3180, 0xF141, 0x3300, 0xF3C1, 0xF281, 0x3240,
+	0x3600, 0xF6C1, 0xF781, 0x3740, 0xF501, 0x35C0, 0x3480, 0xF441,
+	0x3C00, 0xFCC1, 0xFD81, 0x3D40, 0xFF01, 0x3FC0, 0x3E80, 0xFE41,
+	0xFA01, 0x3AC0, 0x3B80, 0xFB41, 0x3900, 0xF9C1, 0xF881, 0x3840,
+	0x2800, 0xE8C1, 0xE981, 0x2940, 0xEB01, 0x2BC0, 0x2A80, 0xEA41,
+	0xEE01, 0x2EC0, 0x2F80, 0xEF41, 0x2D00, 0xEDC1, 0xEC81, 0x2C40,
+	0xE401, 0x24C0, 0x2580, 0xE541, 0x2700, 0xE7C1, 0xE681, 0x2640,
+	0x2200, 0xE2C1, 0xE381, 0x2340, 0xE101, 0x21C0, 0x2080, 0xE041,
+	0xA001, 0x60C0, 0x6180, 0xA141, 0x6300, 0xA3C1, 0xA281, 0x6240,
+	0x6600, 0xA6C1, 0xA781, 0x6740, 0xA501, 0x65C0, 0x6480, 0xA441,
+	0x6C00, 0xACC1, 0xAD81, 0x6D40, 0xAF01, 0x6FC0, 0x6E80, 0xAE41,
+	0xAA01, 0x6AC0, 0x6B80, 0xAB41, 0x6900, 0xA9C1, 0xA881, 0x6840,
+	0x7800, 0xB8C1, 0xB981, 0x7940, 0xBB01, 0x7BC0, 0x7A80, 0xBA41,
+	0xBE01, 0x7EC0, 0x7F80, 0xBF41, 0x7D00, 0xBDC1, 0xBC81, 0x7C40,
+	0xB401, 0x74C0, 0x7580, 0xB541, 0x7700, 0xB7C1, 0xB681, 0x7640,
+	0x7200, 0xB2C1, 0xB381, 0x7340, 0xB101, 0x71C0, 0x7080, 0xB041,
+	0x5000, 0x90C1, 0x9181, 0x5140, 0x9301, 0x53C0, 0x5280, 0x9241,
+	0x9601, 0x56C0, 0x5780, 0x9741, 0x5500, 0x95C1, 0x9481, 0x5440,
+	0x9C01, 0x5CC0, 0x5D80, 0x9D41, 0x5F00, 0x9FC1, 0x9E81, 0x5E40,
+	0x5A00, 0x9AC1, 0x9B81, 0x5B40, 0x9901, 0x59C0, 0x5880, 0x9841,
+	0x8801, 0x48C0, 0x4980, 0x8941, 0x4B00, 0x8BC1, 0x8A81, 0x4A40,
+	0x4E00, 0x8EC1, 0x8F81, 0x4F40, 0x8D01, 0x4DC0, 0x4C80, 0x8C41,
+	0x4400, 0x84C1, 0x8581, 0x4540, 0x8701, 0x47C0, 0x4680, 0x8641,
+	0x8201, 0x42C0, 0x4380, 0x8341, 0x4100, 0x81C1, 0x8081, 0x4040
+};
+
+/**
+ * crc16 - compute the CRC-16 for the data buffer
+ * @crc:	previous CRC value
+ * @p:		data pointer
+ * @len:	number of bytes in the buffer
+ *
+ * Returns the updated CRC value.
+ */
+u16 crc16(u16 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc >> 8) ^ crc16_table[(crc & 0xff) ^ *p++];
+	return crc;
+}
+EXPORT_SYMBOL(crc16);
+
+MODULE_DESCRIPTION("CRC16 calculations");
+MODULE_LICENSE("GPL");
+
diff --git a/lib/crc/crc32.c b/lib/crc/crc32.c
new file mode 100644
index 000000000000..6811b37df2aa
--- /dev/null
+++ b/lib/crc/crc32.c
@@ -0,0 +1,59 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin
+ * cleaned up code to current version of sparse and added the slicing-by-8
+ * algorithm to the closely similar existing slicing-by-4 algorithm.
+ *
+ * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com>
+ * Nicer crc32 functions/docs submitted by linux@horizon.com.  Thanks!
+ * Code was from the public domain, copyright abandoned.  Code was
+ * subsequently included in the kernel, thus was re-licensed under the
+ * GNU GPL v2.
+ *
+ * Oct 12, 2000 Matt Domsch <Matt_Domsch@dell.com>
+ * Same crc32 function was used in 5 other places in the kernel.
+ * I made one version, and deleted the others.
+ * There are various incantations of crc32().  Some use a seed of 0 or ~0.
+ * Some xor at the end with ~0.  The generic crc32() function takes
+ * seed as an argument, and doesn't xor at the end.  Then individual
+ * users can do whatever they need.
+ *   drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0.
+ *   fs/jffs2 uses seed 0, doesn't xor with ~0.
+ *   fs/partitions/efi.c uses seed ~0, xor's with ~0.
+ */
+
+/* see: Documentation/staging/crc32.rst for a description of algorithms */
+
+#include <linux/crc32.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+#include "crc32table.h"
+
+MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
+MODULE_DESCRIPTION("Various CRC32 calculations");
+MODULE_LICENSE("GPL");
+
+u32 crc32_le_base(u32 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++];
+	return crc;
+}
+EXPORT_SYMBOL(crc32_le_base);
+
+u32 crc32c_base(u32 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++];
+	return crc;
+}
+EXPORT_SYMBOL(crc32c_base);
+
+u32 crc32_be_base(u32 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++];
+	return crc;
+}
+EXPORT_SYMBOL(crc32_be_base);
diff --git a/lib/crc/crc4.c b/lib/crc/crc4.c
new file mode 100644
index 000000000000..e7e1779c67d9
--- /dev/null
+++ b/lib/crc/crc4.c
@@ -0,0 +1,44 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * crc4.c - simple crc-4 calculations.
+ */
+
+#include <linux/crc4.h>
+#include <linux/module.h>
+
+static const uint8_t crc4_tab[] = {
+	0x0, 0x7, 0xe, 0x9, 0xb, 0xc, 0x5, 0x2,
+	0x1, 0x6, 0xf, 0x8, 0xa, 0xd, 0x4, 0x3,
+};
+
+/**
+ * crc4 - calculate the 4-bit crc of a value.
+ * @c:    starting crc4
+ * @x:    value to checksum
+ * @bits: number of bits in @x to checksum
+ *
+ * Returns the crc4 value of @x, using polynomial 0b10111.
+ *
+ * The @x value is treated as left-aligned, and bits above @bits are ignored
+ * in the crc calculations.
+ */
+uint8_t crc4(uint8_t c, uint64_t x, int bits)
+{
+	int i;
+
+	/* mask off anything above the top bit */
+	x &= (1ull << bits) - 1;
+
+	/* Align to 4-bits */
+	bits = (bits + 3) & ~0x3;
+
+	/* Calculate crc4 over four-bit nibbles, starting at the MSbit */
+	for (i = bits - 4; i >= 0; i -= 4)
+		c = crc4_tab[c ^ ((x >> i) & 0xf)];
+
+	return c;
+}
+EXPORT_SYMBOL_GPL(crc4);
+
+MODULE_DESCRIPTION("CRC4 calculations");
+MODULE_LICENSE("GPL");
diff --git a/lib/crc/crc64.c b/lib/crc/crc64.c
new file mode 100644
index 000000000000..5b1b17057f0a
--- /dev/null
+++ b/lib/crc/crc64.c
@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Normal 64-bit CRC calculation.
+ *
+ * This is a basic crc64 implementation following ECMA-182 specification,
+ * which can be found from,
+ * https://www.ecma-international.org/publications/standards/Ecma-182.htm
+ *
+ * Dr. Ross N. Williams has a great document to introduce the idea of CRC
+ * algorithm, here the CRC64 code is also inspired by the table-driven
+ * algorithm and detail example from this paper. This paper can be found
+ * from,
+ * http://www.ross.net/crc/download/crc_v3.txt
+ *
+ * crc64table[256] is the lookup table of a table-driven 64-bit CRC
+ * calculation, which is generated by gen_crc64table.c in kernel build
+ * time. The polynomial of crc64 arithmetic is from ECMA-182 specification
+ * as well, which is defined as,
+ *
+ * x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
+ * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
+ * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
+ * x^7 + x^4 + x + 1
+ *
+ * crc64nvmetable[256] uses the CRC64 polynomial from the NVME NVM Command Set
+ * Specification and uses least-significant-bit first bit order:
+ *
+ * x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 + x^47 +
+ * x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 + x^26 + x^23 +
+ * x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 + x^4 + x^3 + 1
+ *
+ * Copyright 2018 SUSE Linux.
+ *   Author: Coly Li <colyli@suse.de>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/crc64.h>
+#include "crc64table.h"
+
+MODULE_DESCRIPTION("CRC64 calculations");
+MODULE_LICENSE("GPL v2");
+
+u64 crc64_be_generic(u64 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc << 8) ^ crc64table[(crc >> 56) ^ *p++];
+	return crc;
+}
+EXPORT_SYMBOL_GPL(crc64_be_generic);
+
+u64 crc64_nvme_generic(u64 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc >> 8) ^ crc64nvmetable[(crc & 0xff) ^ *p++];
+	return crc;
+}
+EXPORT_SYMBOL_GPL(crc64_nvme_generic);
diff --git a/lib/crc/crc7.c b/lib/crc/crc7.c
new file mode 100644
index 000000000000..8dd991cc6114
--- /dev/null
+++ b/lib/crc/crc7.c
@@ -0,0 +1,72 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *      crc7.c
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc7.h>
+
+/*
+ * Table for CRC-7 (polynomial x^7 + x^3 + 1).
+ * This is a big-endian CRC (msbit is highest power of x),
+ * aligned so the msbit of the byte is the x^6 coefficient
+ * and the lsbit is not used.
+ */
+static const u8 crc7_be_syndrome_table[256] = {
+	0x00, 0x12, 0x24, 0x36, 0x48, 0x5a, 0x6c, 0x7e,
+	0x90, 0x82, 0xb4, 0xa6, 0xd8, 0xca, 0xfc, 0xee,
+	0x32, 0x20, 0x16, 0x04, 0x7a, 0x68, 0x5e, 0x4c,
+	0xa2, 0xb0, 0x86, 0x94, 0xea, 0xf8, 0xce, 0xdc,
+	0x64, 0x76, 0x40, 0x52, 0x2c, 0x3e, 0x08, 0x1a,
+	0xf4, 0xe6, 0xd0, 0xc2, 0xbc, 0xae, 0x98, 0x8a,
+	0x56, 0x44, 0x72, 0x60, 0x1e, 0x0c, 0x3a, 0x28,
+	0xc6, 0xd4, 0xe2, 0xf0, 0x8e, 0x9c, 0xaa, 0xb8,
+	0xc8, 0xda, 0xec, 0xfe, 0x80, 0x92, 0xa4, 0xb6,
+	0x58, 0x4a, 0x7c, 0x6e, 0x10, 0x02, 0x34, 0x26,
+	0xfa, 0xe8, 0xde, 0xcc, 0xb2, 0xa0, 0x96, 0x84,
+	0x6a, 0x78, 0x4e, 0x5c, 0x22, 0x30, 0x06, 0x14,
+	0xac, 0xbe, 0x88, 0x9a, 0xe4, 0xf6, 0xc0, 0xd2,
+	0x3c, 0x2e, 0x18, 0x0a, 0x74, 0x66, 0x50, 0x42,
+	0x9e, 0x8c, 0xba, 0xa8, 0xd6, 0xc4, 0xf2, 0xe0,
+	0x0e, 0x1c, 0x2a, 0x38, 0x46, 0x54, 0x62, 0x70,
+	0x82, 0x90, 0xa6, 0xb4, 0xca, 0xd8, 0xee, 0xfc,
+	0x12, 0x00, 0x36, 0x24, 0x5a, 0x48, 0x7e, 0x6c,
+	0xb0, 0xa2, 0x94, 0x86, 0xf8, 0xea, 0xdc, 0xce,
+	0x20, 0x32, 0x04, 0x16, 0x68, 0x7a, 0x4c, 0x5e,
+	0xe6, 0xf4, 0xc2, 0xd0, 0xae, 0xbc, 0x8a, 0x98,
+	0x76, 0x64, 0x52, 0x40, 0x3e, 0x2c, 0x1a, 0x08,
+	0xd4, 0xc6, 0xf0, 0xe2, 0x9c, 0x8e, 0xb8, 0xaa,
+	0x44, 0x56, 0x60, 0x72, 0x0c, 0x1e, 0x28, 0x3a,
+	0x4a, 0x58, 0x6e, 0x7c, 0x02, 0x10, 0x26, 0x34,
+	0xda, 0xc8, 0xfe, 0xec, 0x92, 0x80, 0xb6, 0xa4,
+	0x78, 0x6a, 0x5c, 0x4e, 0x30, 0x22, 0x14, 0x06,
+	0xe8, 0xfa, 0xcc, 0xde, 0xa0, 0xb2, 0x84, 0x96,
+	0x2e, 0x3c, 0x0a, 0x18, 0x66, 0x74, 0x42, 0x50,
+	0xbe, 0xac, 0x9a, 0x88, 0xf6, 0xe4, 0xd2, 0xc0,
+	0x1c, 0x0e, 0x38, 0x2a, 0x54, 0x46, 0x70, 0x62,
+	0x8c, 0x9e, 0xa8, 0xba, 0xc4, 0xd6, 0xe0, 0xf2
+};
+
+/**
+ * crc7_be - update the CRC7 for the data buffer
+ * @crc:     previous CRC7 value
+ * @buffer:  data pointer
+ * @len:     number of bytes in the buffer
+ * Context: any
+ *
+ * Returns the updated CRC7 value.
+ * The CRC7 is left-aligned in the byte (the lsbit is always 0), as that
+ * makes the computation easier, and all callers want it in that form.
+ *
+ */
+u8 crc7_be(u8 crc, const u8 *buffer, size_t len)
+{
+	while (len--)
+		crc = crc7_be_syndrome_table[crc ^ *buffer++];
+	return crc;
+}
+EXPORT_SYMBOL(crc7_be);
+
+MODULE_DESCRIPTION("CRC7 calculations");
+MODULE_LICENSE("GPL");
diff --git a/lib/crc/crc8.c b/lib/crc/crc8.c
new file mode 100644
index 000000000000..1ad8e501d9b6
--- /dev/null
+++ b/lib/crc/crc8.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2011 Broadcom Corporation
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+ * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
+ * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+ * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#define pr_fmt(fmt)		KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/crc8.h>
+#include <linux/printk.h>
+
+/**
+ * crc8_populate_msb - fill crc table for given polynomial in reverse bit order.
+ *
+ * @table:	table to be filled.
+ * @polynomial:	polynomial for which table is to be filled.
+ */
+void crc8_populate_msb(u8 table[CRC8_TABLE_SIZE], u8 polynomial)
+{
+	int i, j;
+	const u8 msbit = 0x80;
+	u8 t = msbit;
+
+	table[0] = 0;
+
+	for (i = 1; i < CRC8_TABLE_SIZE; i *= 2) {
+		t = (t << 1) ^ (t & msbit ? polynomial : 0);
+		for (j = 0; j < i; j++)
+			table[i+j] = table[j] ^ t;
+	}
+}
+EXPORT_SYMBOL(crc8_populate_msb);
+
+/**
+ * crc8_populate_lsb - fill crc table for given polynomial in regular bit order.
+ *
+ * @table:	table to be filled.
+ * @polynomial:	polynomial for which table is to be filled.
+ */
+void crc8_populate_lsb(u8 table[CRC8_TABLE_SIZE], u8 polynomial)
+{
+	int i, j;
+	u8 t = 1;
+
+	table[0] = 0;
+
+	for (i = (CRC8_TABLE_SIZE >> 1); i; i >>= 1) {
+		t = (t >> 1) ^ (t & 1 ? polynomial : 0);
+		for (j = 0; j < CRC8_TABLE_SIZE; j += 2*i)
+			table[i+j] = table[j] ^ t;
+	}
+}
+EXPORT_SYMBOL(crc8_populate_lsb);
+
+/**
+ * crc8 - calculate a crc8 over the given input data.
+ *
+ * @table: crc table used for calculation.
+ * @pdata: pointer to data buffer.
+ * @nbytes: number of bytes in data buffer.
+ * @crc: previous returned crc8 value.
+ */
+u8 crc8(const u8 table[CRC8_TABLE_SIZE], const u8 *pdata, size_t nbytes, u8 crc)
+{
+	/* loop over the buffer data */
+	while (nbytes-- > 0)
+		crc = table[(crc ^ *pdata++) & 0xff];
+
+	return crc;
+}
+EXPORT_SYMBOL(crc8);
+
+MODULE_DESCRIPTION("CRC8 (by Williams, Ross N.) function");
+MODULE_AUTHOR("Broadcom Corporation");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/crc/gen_crc32table.c b/lib/crc/gen_crc32table.c
new file mode 100644
index 000000000000..9a7f31658e35
--- /dev/null
+++ b/lib/crc/gen_crc32table.c
@@ -0,0 +1,89 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <stdio.h>
+#include "../../include/linux/crc32poly.h"
+#include "../../include/generated/autoconf.h"
+#include <inttypes.h>
+
+static uint32_t crc32table_le[256];
+static uint32_t crc32table_be[256];
+static uint32_t crc32ctable_le[256];
+
+/**
+ * crc32init_le() - allocate and initialize LE table data
+ *
+ * crc is the crc of the byte i; other entries are filled in based on the
+ * fact that crctable[i^j] = crctable[i] ^ crctable[j].
+ *
+ */
+static void crc32init_le_generic(const uint32_t polynomial, uint32_t tab[256])
+{
+	unsigned i, j;
+	uint32_t crc = 1;
+
+	tab[0] = 0;
+
+	for (i = 128; i; i >>= 1) {
+		crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
+		for (j = 0; j < 256; j += 2 * i)
+			tab[i + j] = crc ^ tab[j];
+	}
+}
+
+static void crc32init_le(void)
+{
+	crc32init_le_generic(CRC32_POLY_LE, crc32table_le);
+}
+
+static void crc32cinit_le(void)
+{
+	crc32init_le_generic(CRC32C_POLY_LE, crc32ctable_le);
+}
+
+/**
+ * crc32init_be() - allocate and initialize BE table data
+ */
+static void crc32init_be(void)
+{
+	unsigned i, j;
+	uint32_t crc = 0x80000000;
+
+	crc32table_be[0] = 0;
+
+	for (i = 1; i < 256; i <<= 1) {
+		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRC32_POLY_BE : 0);
+		for (j = 0; j < i; j++)
+			crc32table_be[i + j] = crc ^ crc32table_be[j];
+	}
+}
+
+static void output_table(const uint32_t table[256])
+{
+	int i;
+
+	for (i = 0; i < 256; i += 4) {
+		printf("\t0x%08x, 0x%08x, 0x%08x, 0x%08x,\n",
+		       table[i], table[i + 1], table[i + 2], table[i + 3]);
+	}
+}
+
+int main(int argc, char** argv)
+{
+	printf("/* this file is generated - do not edit */\n\n");
+
+	crc32init_le();
+	printf("static const u32 ____cacheline_aligned crc32table_le[256] = {\n");
+	output_table(crc32table_le);
+	printf("};\n");
+
+	crc32init_be();
+	printf("static const u32 ____cacheline_aligned crc32table_be[256] = {\n");
+	output_table(crc32table_be);
+	printf("};\n");
+
+	crc32cinit_le();
+	printf("static const u32 ____cacheline_aligned crc32ctable_le[256] = {\n");
+	output_table(crc32ctable_le);
+	printf("};\n");
+
+	return 0;
+}
diff --git a/lib/crc/gen_crc64table.c b/lib/crc/gen_crc64table.c
new file mode 100644
index 000000000000..f2be9f62bab7
--- /dev/null
+++ b/lib/crc/gen_crc64table.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This host program runs at kernel build time and generates the lookup tables
+ * used by the generic CRC64 code.
+ *
+ * Copyright 2018 SUSE Linux.
+ *   Author: Coly Li <colyli@suse.de>
+ */
+#include <inttypes.h>
+#include <stdio.h>
+
+#define CRC64_ECMA182_POLY 0x42F0E1EBA9EA3693ULL
+#define CRC64_NVME_POLY 0x9A6C9329AC4BC9B5ULL
+
+static uint64_t crc64_table[256] = {0};
+static uint64_t crc64_nvme_table[256] = {0};
+
+static void generate_reflected_crc64_table(uint64_t table[256], uint64_t poly)
+{
+	uint64_t i, j, c, crc;
+
+	for (i = 0; i < 256; i++) {
+		crc = 0ULL;
+		c = i;
+
+		for (j = 0; j < 8; j++) {
+			if ((crc ^ (c >> j)) & 1)
+				crc = (crc >> 1) ^ poly;
+			else
+				crc >>= 1;
+		}
+		table[i] = crc;
+	}
+}
+
+static void generate_crc64_table(uint64_t table[256], uint64_t poly)
+{
+	uint64_t i, j, c, crc;
+
+	for (i = 0; i < 256; i++) {
+		crc = 0;
+		c = i << 56;
+
+		for (j = 0; j < 8; j++) {
+			if ((crc ^ c) & 0x8000000000000000ULL)
+				crc = (crc << 1) ^ poly;
+			else
+				crc <<= 1;
+			c <<= 1;
+		}
+
+		table[i] = crc;
+	}
+}
+
+static void output_table(uint64_t table[256])
+{
+	int i;
+
+	for (i = 0; i < 256; i++) {
+		printf("\t0x%016" PRIx64 "ULL", table[i]);
+		if (i & 0x1)
+			printf(",\n");
+		else
+			printf(", ");
+	}
+	printf("};\n");
+}
+
+static void print_crc64_tables(void)
+{
+	printf("/* this file is generated - do not edit */\n\n");
+	printf("#include <linux/types.h>\n");
+	printf("#include <linux/cache.h>\n\n");
+	printf("static const u64 ____cacheline_aligned crc64table[256] = {\n");
+	output_table(crc64_table);
+
+	printf("\nstatic const u64 ____cacheline_aligned crc64nvmetable[256] = {\n");
+	output_table(crc64_nvme_table);
+}
+
+int main(int argc, char *argv[])
+{
+	generate_crc64_table(crc64_table, CRC64_ECMA182_POLY);
+	generate_reflected_crc64_table(crc64_nvme_table, CRC64_NVME_POLY);
+	print_crc64_tables();
+	return 0;
+}
diff --git a/lib/crc/tests/Makefile b/lib/crc/tests/Makefile
new file mode 100644
index 000000000000..65f63c318ef5
--- /dev/null
+++ b/lib/crc/tests/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0-only
+obj-$(CONFIG_CRC_KUNIT_TEST) += crc_kunit.o
diff --git a/lib/crc/tests/crc_kunit.c b/lib/crc/tests/crc_kunit.c
new file mode 100644
index 000000000000..f08d985d8860
--- /dev/null
+++ b/lib/crc/tests/crc_kunit.c
@@ -0,0 +1,452 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Unit tests and benchmarks for the CRC library functions
+ *
+ * Copyright 2024 Google LLC
+ *
+ * Author: Eric Biggers <ebiggers@google.com>
+ */
+#include <kunit/test.h>
+#include <linux/crc7.h>
+#include <linux/crc16.h>
+#include <linux/crc-t10dif.h>
+#include <linux/crc32.h>
+#include <linux/crc32c.h>
+#include <linux/crc64.h>
+#include <linux/prandom.h>
+#include <linux/vmalloc.h>
+
+#define CRC_KUNIT_SEED			42
+#define CRC_KUNIT_MAX_LEN		16384
+#define CRC_KUNIT_NUM_TEST_ITERS	1000
+
+static struct rnd_state rng;
+static u8 *test_buffer;
+static size_t test_buflen;
+
+/**
+ * struct crc_variant - describes a CRC variant
+ * @bits: Number of bits in the CRC, 1 <= @bits <= 64.
+ * @le: true if it's a "little endian" CRC (reversed mapping between bits and
+ *	polynomial coefficients in each byte), false if it's a "big endian" CRC
+ *	(natural mapping between bits and polynomial coefficients in each byte)
+ * @poly: The generator polynomial with the highest-order term omitted.
+ *	  Bit-reversed if @le is true.
+ * @func: The function to compute a CRC.  The type signature uses u64 so that it
+ *	  can fit any CRC up to CRC-64.  The CRC is passed in, and is expected
+ *	  to be returned in, the least significant bits of the u64.  The
+ *	  function is expected to *not* invert the CRC at the beginning and end.
+ */
+struct crc_variant {
+	int bits;
+	bool le;
+	u64 poly;
+	u64 (*func)(u64 crc, const u8 *p, size_t len);
+};
+
+static u32 rand32(void)
+{
+	return prandom_u32_state(&rng);
+}
+
+static u64 rand64(void)
+{
+	u32 n = rand32();
+
+	return ((u64)n << 32) | rand32();
+}
+
+static u64 crc_mask(const struct crc_variant *v)
+{
+	return (u64)-1 >> (64 - v->bits);
+}
+
+/* Reference implementation of any CRC variant */
+static u64 crc_ref(const struct crc_variant *v,
+		   u64 crc, const u8 *p, size_t len)
+{
+	size_t i, j;
+
+	for (i = 0; i < len; i++) {
+		for (j = 0; j < 8; j++) {
+			if (v->le) {
+				crc ^= (p[i] >> j) & 1;
+				crc = (crc >> 1) ^ ((crc & 1) ? v->poly : 0);
+			} else {
+				crc ^= (u64)((p[i] >> (7 - j)) & 1) <<
+				       (v->bits - 1);
+				if (crc & (1ULL << (v->bits - 1)))
+					crc = ((crc << 1) ^ v->poly) &
+					      crc_mask(v);
+				else
+					crc <<= 1;
+			}
+		}
+	}
+	return crc;
+}
+
+static int crc_suite_init(struct kunit_suite *suite)
+{
+	/*
+	 * Allocate the test buffer using vmalloc() with a page-aligned length
+	 * so that it is immediately followed by a guard page.  This allows
+	 * buffer overreads to be detected, even in assembly code.
+	 */
+	test_buflen = round_up(CRC_KUNIT_MAX_LEN, PAGE_SIZE);
+	test_buffer = vmalloc(test_buflen);
+	if (!test_buffer)
+		return -ENOMEM;
+
+	prandom_seed_state(&rng, CRC_KUNIT_SEED);
+	prandom_bytes_state(&rng, test_buffer, test_buflen);
+	return 0;
+}
+
+static void crc_suite_exit(struct kunit_suite *suite)
+{
+	vfree(test_buffer);
+	test_buffer = NULL;
+}
+
+/* Generate a random initial CRC. */
+static u64 generate_random_initial_crc(const struct crc_variant *v)
+{
+	switch (rand32() % 4) {
+	case 0:
+		return 0;
+	case 1:
+		return crc_mask(v); /* All 1 bits */
+	default:
+		return rand64() & crc_mask(v);
+	}
+}
+
+/* Generate a random length, preferring small lengths. */
+static size_t generate_random_length(size_t max_length)
+{
+	size_t len;
+
+	switch (rand32() % 3) {
+	case 0:
+		len = rand32() % 128;
+		break;
+	case 1:
+		len = rand32() % 3072;
+		break;
+	default:
+		len = rand32();
+		break;
+	}
+	return len % (max_length + 1);
+}
+
+/* Test that v->func gives the same CRCs as a reference implementation. */
+static void crc_test(struct kunit *test, const struct crc_variant *v)
+{
+	size_t i;
+
+	for (i = 0; i < CRC_KUNIT_NUM_TEST_ITERS; i++) {
+		u64 init_crc, expected_crc, actual_crc;
+		size_t len, offset;
+		bool nosimd;
+
+		init_crc = generate_random_initial_crc(v);
+		len = generate_random_length(CRC_KUNIT_MAX_LEN);
+
+		/* Generate a random offset. */
+		if (rand32() % 2 == 0) {
+			/* Use a random alignment mod 64 */
+			offset = rand32() % 64;
+			offset = min(offset, CRC_KUNIT_MAX_LEN - len);
+		} else {
+			/* Go up to the guard page, to catch buffer overreads */
+			offset = test_buflen - len;
+		}
+
+		if (rand32() % 8 == 0)
+			/* Refresh the data occasionally. */
+			prandom_bytes_state(&rng, &test_buffer[offset], len);
+
+		nosimd = rand32() % 8 == 0;
+
+		/*
+		 * Compute the CRC, and verify that it equals the CRC computed
+		 * by a simple bit-at-a-time reference implementation.
+		 */
+		expected_crc = crc_ref(v, init_crc, &test_buffer[offset], len);
+		if (nosimd)
+			local_irq_disable();
+		actual_crc = v->func(init_crc, &test_buffer[offset], len);
+		if (nosimd)
+			local_irq_enable();
+		KUNIT_EXPECT_EQ_MSG(test, expected_crc, actual_crc,
+				    "Wrong result with len=%zu offset=%zu nosimd=%d",
+				    len, offset, nosimd);
+	}
+}
+
+static __always_inline void
+crc_benchmark(struct kunit *test,
+	      u64 (*crc_func)(u64 crc, const u8 *p, size_t len))
+{
+	static const size_t lens_to_test[] = {
+		1, 16, 64, 127, 128, 200, 256, 511, 512, 1024, 3173, 4096, 16384,
+	};
+	size_t len, i, j, num_iters;
+	/*
+	 * The CRC value that this function computes in a series of calls to
+	 * crc_func is never actually used, so use volatile to ensure that the
+	 * computations are done as intended and don't all get optimized out.
+	 */
+	volatile u64 crc = 0;
+	u64 t;
+
+	if (!IS_ENABLED(CONFIG_CRC_BENCHMARK))
+		kunit_skip(test, "not enabled");
+
+	/* warm-up */
+	for (i = 0; i < 10000000; i += CRC_KUNIT_MAX_LEN)
+		crc = crc_func(crc, test_buffer, CRC_KUNIT_MAX_LEN);
+
+	for (i = 0; i < ARRAY_SIZE(lens_to_test); i++) {
+		len = lens_to_test[i];
+		KUNIT_ASSERT_LE(test, len, CRC_KUNIT_MAX_LEN);
+		num_iters = 10000000 / (len + 128);
+		preempt_disable();
+		t = ktime_get_ns();
+		for (j = 0; j < num_iters; j++)
+			crc = crc_func(crc, test_buffer, len);
+		t = ktime_get_ns() - t;
+		preempt_enable();
+		kunit_info(test, "len=%zu: %llu MB/s\n",
+			   len, div64_u64((u64)len * num_iters * 1000, t));
+	}
+}
+
+/* crc7_be */
+
+static u64 crc7_be_wrapper(u64 crc, const u8 *p, size_t len)
+{
+	/*
+	 * crc7_be() left-aligns the 7-bit CRC in a u8, whereas the test wants a
+	 * right-aligned CRC (in a u64).  Convert between the conventions.
+	 */
+	return crc7_be(crc << 1, p, len) >> 1;
+}
+
+static const struct crc_variant crc_variant_crc7_be = {
+	.bits = 7,
+	.poly = 0x9,
+	.func = crc7_be_wrapper,
+};
+
+static void crc7_be_test(struct kunit *test)
+{
+	crc_test(test, &crc_variant_crc7_be);
+}
+
+static void crc7_be_benchmark(struct kunit *test)
+{
+	crc_benchmark(test, crc7_be_wrapper);
+}
+
+/* crc16 */
+
+static u64 crc16_wrapper(u64 crc, const u8 *p, size_t len)
+{
+	return crc16(crc, p, len);
+}
+
+static const struct crc_variant crc_variant_crc16 = {
+	.bits = 16,
+	.le = true,
+	.poly = 0xa001,
+	.func = crc16_wrapper,
+};
+
+static void crc16_test(struct kunit *test)
+{
+	crc_test(test, &crc_variant_crc16);
+}
+
+static void crc16_benchmark(struct kunit *test)
+{
+	crc_benchmark(test, crc16_wrapper);
+}
+
+/* crc_t10dif */
+
+static u64 crc_t10dif_wrapper(u64 crc, const u8 *p, size_t len)
+{
+	return crc_t10dif_update(crc, p, len);
+}
+
+static const struct crc_variant crc_variant_crc_t10dif = {
+	.bits = 16,
+	.le = false,
+	.poly = 0x8bb7,
+	.func = crc_t10dif_wrapper,
+};
+
+static void crc_t10dif_test(struct kunit *test)
+{
+	crc_test(test, &crc_variant_crc_t10dif);
+}
+
+static void crc_t10dif_benchmark(struct kunit *test)
+{
+	crc_benchmark(test, crc_t10dif_wrapper);
+}
+
+/* crc32_le */
+
+static u64 crc32_le_wrapper(u64 crc, const u8 *p, size_t len)
+{
+	return crc32_le(crc, p, len);
+}
+
+static const struct crc_variant crc_variant_crc32_le = {
+	.bits = 32,
+	.le = true,
+	.poly = 0xedb88320,
+	.func = crc32_le_wrapper,
+};
+
+static void crc32_le_test(struct kunit *test)
+{
+	crc_test(test, &crc_variant_crc32_le);
+}
+
+static void crc32_le_benchmark(struct kunit *test)
+{
+	crc_benchmark(test, crc32_le_wrapper);
+}
+
+/* crc32_be */
+
+static u64 crc32_be_wrapper(u64 crc, const u8 *p, size_t len)
+{
+	return crc32_be(crc, p, len);
+}
+
+static const struct crc_variant crc_variant_crc32_be = {
+	.bits = 32,
+	.le = false,
+	.poly = 0x04c11db7,
+	.func = crc32_be_wrapper,
+};
+
+static void crc32_be_test(struct kunit *test)
+{
+	crc_test(test, &crc_variant_crc32_be);
+}
+
+static void crc32_be_benchmark(struct kunit *test)
+{
+	crc_benchmark(test, crc32_be_wrapper);
+}
+
+/* crc32c */
+
+static u64 crc32c_wrapper(u64 crc, const u8 *p, size_t len)
+{
+	return crc32c(crc, p, len);
+}
+
+static const struct crc_variant crc_variant_crc32c = {
+	.bits = 32,
+	.le = true,
+	.poly = 0x82f63b78,
+	.func = crc32c_wrapper,
+};
+
+static void crc32c_test(struct kunit *test)
+{
+	crc_test(test, &crc_variant_crc32c);
+}
+
+static void crc32c_benchmark(struct kunit *test)
+{
+	crc_benchmark(test, crc32c_wrapper);
+}
+
+/* crc64_be */
+
+static u64 crc64_be_wrapper(u64 crc, const u8 *p, size_t len)
+{
+	return crc64_be(crc, p, len);
+}
+
+static const struct crc_variant crc_variant_crc64_be = {
+	.bits = 64,
+	.le = false,
+	.poly = 0x42f0e1eba9ea3693,
+	.func = crc64_be_wrapper,
+};
+
+static void crc64_be_test(struct kunit *test)
+{
+	crc_test(test, &crc_variant_crc64_be);
+}
+
+static void crc64_be_benchmark(struct kunit *test)
+{
+	crc_benchmark(test, crc64_be_wrapper);
+}
+
+/* crc64_nvme */
+
+static u64 crc64_nvme_wrapper(u64 crc, const u8 *p, size_t len)
+{
+	/* The inversions that crc64_nvme() does have to be undone here. */
+	return ~crc64_nvme(~crc, p, len);
+}
+
+static const struct crc_variant crc_variant_crc64_nvme = {
+	.bits = 64,
+	.le = true,
+	.poly = 0x9a6c9329ac4bc9b5,
+	.func = crc64_nvme_wrapper,
+};
+
+static void crc64_nvme_test(struct kunit *test)
+{
+	crc_test(test, &crc_variant_crc64_nvme);
+}
+
+static void crc64_nvme_benchmark(struct kunit *test)
+{
+	crc_benchmark(test, crc64_nvme_wrapper);
+}
+
+static struct kunit_case crc_test_cases[] = {
+	KUNIT_CASE(crc7_be_test),
+	KUNIT_CASE(crc7_be_benchmark),
+	KUNIT_CASE(crc16_test),
+	KUNIT_CASE(crc16_benchmark),
+	KUNIT_CASE(crc_t10dif_test),
+	KUNIT_CASE(crc_t10dif_benchmark),
+	KUNIT_CASE(crc32_le_test),
+	KUNIT_CASE(crc32_le_benchmark),
+	KUNIT_CASE(crc32_be_test),
+	KUNIT_CASE(crc32_be_benchmark),
+	KUNIT_CASE(crc32c_test),
+	KUNIT_CASE(crc32c_benchmark),
+	KUNIT_CASE(crc64_be_test),
+	KUNIT_CASE(crc64_be_benchmark),
+	KUNIT_CASE(crc64_nvme_test),
+	KUNIT_CASE(crc64_nvme_benchmark),
+	{},
+};
+
+static struct kunit_suite crc_test_suite = {
+	.name = "crc",
+	.test_cases = crc_test_cases,
+	.suite_init = crc_suite_init,
+	.suite_exit = crc_suite_exit,
+};
+kunit_test_suite(crc_test_suite);
+
+MODULE_DESCRIPTION("Unit tests and benchmarks for the CRC library functions");
+MODULE_LICENSE("GPL");
diff --git a/lib/crc16.c b/lib/crc16.c
deleted file mode 100644
index 9c71eda9bf4b..000000000000
--- a/lib/crc16.c
+++ /dev/null
@@ -1,64 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *      crc16.c
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/crc16.h>
-
-/** CRC table for the CRC-16. The poly is 0x8005 (x^16 + x^15 + x^2 + 1) */
-static const u16 crc16_table[256] = {
-	0x0000, 0xC0C1, 0xC181, 0x0140, 0xC301, 0x03C0, 0x0280, 0xC241,
-	0xC601, 0x06C0, 0x0780, 0xC741, 0x0500, 0xC5C1, 0xC481, 0x0440,
-	0xCC01, 0x0CC0, 0x0D80, 0xCD41, 0x0F00, 0xCFC1, 0xCE81, 0x0E40,
-	0x0A00, 0xCAC1, 0xCB81, 0x0B40, 0xC901, 0x09C0, 0x0880, 0xC841,
-	0xD801, 0x18C0, 0x1980, 0xD941, 0x1B00, 0xDBC1, 0xDA81, 0x1A40,
-	0x1E00, 0xDEC1, 0xDF81, 0x1F40, 0xDD01, 0x1DC0, 0x1C80, 0xDC41,
-	0x1400, 0xD4C1, 0xD581, 0x1540, 0xD701, 0x17C0, 0x1680, 0xD641,
-	0xD201, 0x12C0, 0x1380, 0xD341, 0x1100, 0xD1C1, 0xD081, 0x1040,
-	0xF001, 0x30C0, 0x3180, 0xF141, 0x3300, 0xF3C1, 0xF281, 0x3240,
-	0x3600, 0xF6C1, 0xF781, 0x3740, 0xF501, 0x35C0, 0x3480, 0xF441,
-	0x3C00, 0xFCC1, 0xFD81, 0x3D40, 0xFF01, 0x3FC0, 0x3E80, 0xFE41,
-	0xFA01, 0x3AC0, 0x3B80, 0xFB41, 0x3900, 0xF9C1, 0xF881, 0x3840,
-	0x2800, 0xE8C1, 0xE981, 0x2940, 0xEB01, 0x2BC0, 0x2A80, 0xEA41,
-	0xEE01, 0x2EC0, 0x2F80, 0xEF41, 0x2D00, 0xEDC1, 0xEC81, 0x2C40,
-	0xE401, 0x24C0, 0x2580, 0xE541, 0x2700, 0xE7C1, 0xE681, 0x2640,
-	0x2200, 0xE2C1, 0xE381, 0x2340, 0xE101, 0x21C0, 0x2080, 0xE041,
-	0xA001, 0x60C0, 0x6180, 0xA141, 0x6300, 0xA3C1, 0xA281, 0x6240,
-	0x6600, 0xA6C1, 0xA781, 0x6740, 0xA501, 0x65C0, 0x6480, 0xA441,
-	0x6C00, 0xACC1, 0xAD81, 0x6D40, 0xAF01, 0x6FC0, 0x6E80, 0xAE41,
-	0xAA01, 0x6AC0, 0x6B80, 0xAB41, 0x6900, 0xA9C1, 0xA881, 0x6840,
-	0x7800, 0xB8C1, 0xB981, 0x7940, 0xBB01, 0x7BC0, 0x7A80, 0xBA41,
-	0xBE01, 0x7EC0, 0x7F80, 0xBF41, 0x7D00, 0xBDC1, 0xBC81, 0x7C40,
-	0xB401, 0x74C0, 0x7580, 0xB541, 0x7700, 0xB7C1, 0xB681, 0x7640,
-	0x7200, 0xB2C1, 0xB381, 0x7340, 0xB101, 0x71C0, 0x7080, 0xB041,
-	0x5000, 0x90C1, 0x9181, 0x5140, 0x9301, 0x53C0, 0x5280, 0x9241,
-	0x9601, 0x56C0, 0x5780, 0x9741, 0x5500, 0x95C1, 0x9481, 0x5440,
-	0x9C01, 0x5CC0, 0x5D80, 0x9D41, 0x5F00, 0x9FC1, 0x9E81, 0x5E40,
-	0x5A00, 0x9AC1, 0x9B81, 0x5B40, 0x9901, 0x59C0, 0x5880, 0x9841,
-	0x8801, 0x48C0, 0x4980, 0x8941, 0x4B00, 0x8BC1, 0x8A81, 0x4A40,
-	0x4E00, 0x8EC1, 0x8F81, 0x4F40, 0x8D01, 0x4DC0, 0x4C80, 0x8C41,
-	0x4400, 0x84C1, 0x8581, 0x4540, 0x8701, 0x47C0, 0x4680, 0x8641,
-	0x8201, 0x42C0, 0x4380, 0x8341, 0x4100, 0x81C1, 0x8081, 0x4040
-};
-
-/**
- * crc16 - compute the CRC-16 for the data buffer
- * @crc:	previous CRC value
- * @p:		data pointer
- * @len:	number of bytes in the buffer
- *
- * Returns the updated CRC value.
- */
-u16 crc16(u16 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc >> 8) ^ crc16_table[(crc & 0xff) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL(crc16);
-
-MODULE_DESCRIPTION("CRC16 calculations");
-MODULE_LICENSE("GPL");
-
diff --git a/lib/crc32.c b/lib/crc32.c
deleted file mode 100644
index 6811b37df2aa..000000000000
--- a/lib/crc32.c
+++ /dev/null
@@ -1,59 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin
- * cleaned up code to current version of sparse and added the slicing-by-8
- * algorithm to the closely similar existing slicing-by-4 algorithm.
- *
- * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com>
- * Nicer crc32 functions/docs submitted by linux@horizon.com.  Thanks!
- * Code was from the public domain, copyright abandoned.  Code was
- * subsequently included in the kernel, thus was re-licensed under the
- * GNU GPL v2.
- *
- * Oct 12, 2000 Matt Domsch <Matt_Domsch@dell.com>
- * Same crc32 function was used in 5 other places in the kernel.
- * I made one version, and deleted the others.
- * There are various incantations of crc32().  Some use a seed of 0 or ~0.
- * Some xor at the end with ~0.  The generic crc32() function takes
- * seed as an argument, and doesn't xor at the end.  Then individual
- * users can do whatever they need.
- *   drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0.
- *   fs/jffs2 uses seed 0, doesn't xor with ~0.
- *   fs/partitions/efi.c uses seed ~0, xor's with ~0.
- */
-
-/* see: Documentation/staging/crc32.rst for a description of algorithms */
-
-#include <linux/crc32.h>
-#include <linux/module.h>
-#include <linux/types.h>
-
-#include "crc32table.h"
-
-MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
-MODULE_DESCRIPTION("Various CRC32 calculations");
-MODULE_LICENSE("GPL");
-
-u32 crc32_le_base(u32 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL(crc32_le_base);
-
-u32 crc32c_base(u32 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL(crc32c_base);
-
-u32 crc32_be_base(u32 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL(crc32_be_base);
diff --git a/lib/crc4.c b/lib/crc4.c
deleted file mode 100644
index e7e1779c67d9..000000000000
--- a/lib/crc4.c
+++ /dev/null
@@ -1,44 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * crc4.c - simple crc-4 calculations.
- */
-
-#include <linux/crc4.h>
-#include <linux/module.h>
-
-static const uint8_t crc4_tab[] = {
-	0x0, 0x7, 0xe, 0x9, 0xb, 0xc, 0x5, 0x2,
-	0x1, 0x6, 0xf, 0x8, 0xa, 0xd, 0x4, 0x3,
-};
-
-/**
- * crc4 - calculate the 4-bit crc of a value.
- * @c:    starting crc4
- * @x:    value to checksum
- * @bits: number of bits in @x to checksum
- *
- * Returns the crc4 value of @x, using polynomial 0b10111.
- *
- * The @x value is treated as left-aligned, and bits above @bits are ignored
- * in the crc calculations.
- */
-uint8_t crc4(uint8_t c, uint64_t x, int bits)
-{
-	int i;
-
-	/* mask off anything above the top bit */
-	x &= (1ull << bits) - 1;
-
-	/* Align to 4-bits */
-	bits = (bits + 3) & ~0x3;
-
-	/* Calculate crc4 over four-bit nibbles, starting at the MSbit */
-	for (i = bits - 4; i >= 0; i -= 4)
-		c = crc4_tab[c ^ ((x >> i) & 0xf)];
-
-	return c;
-}
-EXPORT_SYMBOL_GPL(crc4);
-
-MODULE_DESCRIPTION("CRC4 calculations");
-MODULE_LICENSE("GPL");
diff --git a/lib/crc64.c b/lib/crc64.c
deleted file mode 100644
index 5b1b17057f0a..000000000000
--- a/lib/crc64.c
+++ /dev/null
@@ -1,58 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Normal 64-bit CRC calculation.
- *
- * This is a basic crc64 implementation following ECMA-182 specification,
- * which can be found from,
- * https://www.ecma-international.org/publications/standards/Ecma-182.htm
- *
- * Dr. Ross N. Williams has a great document to introduce the idea of CRC
- * algorithm, here the CRC64 code is also inspired by the table-driven
- * algorithm and detail example from this paper. This paper can be found
- * from,
- * http://www.ross.net/crc/download/crc_v3.txt
- *
- * crc64table[256] is the lookup table of a table-driven 64-bit CRC
- * calculation, which is generated by gen_crc64table.c in kernel build
- * time. The polynomial of crc64 arithmetic is from ECMA-182 specification
- * as well, which is defined as,
- *
- * x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
- * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
- * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
- * x^7 + x^4 + x + 1
- *
- * crc64nvmetable[256] uses the CRC64 polynomial from the NVME NVM Command Set
- * Specification and uses least-significant-bit first bit order:
- *
- * x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 + x^47 +
- * x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 + x^26 + x^23 +
- * x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 + x^4 + x^3 + 1
- *
- * Copyright 2018 SUSE Linux.
- *   Author: Coly Li <colyli@suse.de>
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/crc64.h>
-#include "crc64table.h"
-
-MODULE_DESCRIPTION("CRC64 calculations");
-MODULE_LICENSE("GPL v2");
-
-u64 crc64_be_generic(u64 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc << 8) ^ crc64table[(crc >> 56) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL_GPL(crc64_be_generic);
-
-u64 crc64_nvme_generic(u64 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc >> 8) ^ crc64nvmetable[(crc & 0xff) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL_GPL(crc64_nvme_generic);
diff --git a/lib/crc7.c b/lib/crc7.c
deleted file mode 100644
index 8dd991cc6114..000000000000
--- a/lib/crc7.c
+++ /dev/null
@@ -1,72 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- *      crc7.c
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/crc7.h>
-
-/*
- * Table for CRC-7 (polynomial x^7 + x^3 + 1).
- * This is a big-endian CRC (msbit is highest power of x),
- * aligned so the msbit of the byte is the x^6 coefficient
- * and the lsbit is not used.
- */
-static const u8 crc7_be_syndrome_table[256] = {
-	0x00, 0x12, 0x24, 0x36, 0x48, 0x5a, 0x6c, 0x7e,
-	0x90, 0x82, 0xb4, 0xa6, 0xd8, 0xca, 0xfc, 0xee,
-	0x32, 0x20, 0x16, 0x04, 0x7a, 0x68, 0x5e, 0x4c,
-	0xa2, 0xb0, 0x86, 0x94, 0xea, 0xf8, 0xce, 0xdc,
-	0x64, 0x76, 0x40, 0x52, 0x2c, 0x3e, 0x08, 0x1a,
-	0xf4, 0xe6, 0xd0, 0xc2, 0xbc, 0xae, 0x98, 0x8a,
-	0x56, 0x44, 0x72, 0x60, 0x1e, 0x0c, 0x3a, 0x28,
-	0xc6, 0xd4, 0xe2, 0xf0, 0x8e, 0x9c, 0xaa, 0xb8,
-	0xc8, 0xda, 0xec, 0xfe, 0x80, 0x92, 0xa4, 0xb6,
-	0x58, 0x4a, 0x7c, 0x6e, 0x10, 0x02, 0x34, 0x26,
-	0xfa, 0xe8, 0xde, 0xcc, 0xb2, 0xa0, 0x96, 0x84,
-	0x6a, 0x78, 0x4e, 0x5c, 0x22, 0x30, 0x06, 0x14,
-	0xac, 0xbe, 0x88, 0x9a, 0xe4, 0xf6, 0xc0, 0xd2,
-	0x3c, 0x2e, 0x18, 0x0a, 0x74, 0x66, 0x50, 0x42,
-	0x9e, 0x8c, 0xba, 0xa8, 0xd6, 0xc4, 0xf2, 0xe0,
-	0x0e, 0x1c, 0x2a, 0x38, 0x46, 0x54, 0x62, 0x70,
-	0x82, 0x90, 0xa6, 0xb4, 0xca, 0xd8, 0xee, 0xfc,
-	0x12, 0x00, 0x36, 0x24, 0x5a, 0x48, 0x7e, 0x6c,
-	0xb0, 0xa2, 0x94, 0x86, 0xf8, 0xea, 0xdc, 0xce,
-	0x20, 0x32, 0x04, 0x16, 0x68, 0x7a, 0x4c, 0x5e,
-	0xe6, 0xf4, 0xc2, 0xd0, 0xae, 0xbc, 0x8a, 0x98,
-	0x76, 0x64, 0x52, 0x40, 0x3e, 0x2c, 0x1a, 0x08,
-	0xd4, 0xc6, 0xf0, 0xe2, 0x9c, 0x8e, 0xb8, 0xaa,
-	0x44, 0x56, 0x60, 0x72, 0x0c, 0x1e, 0x28, 0x3a,
-	0x4a, 0x58, 0x6e, 0x7c, 0x02, 0x10, 0x26, 0x34,
-	0xda, 0xc8, 0xfe, 0xec, 0x92, 0x80, 0xb6, 0xa4,
-	0x78, 0x6a, 0x5c, 0x4e, 0x30, 0x22, 0x14, 0x06,
-	0xe8, 0xfa, 0xcc, 0xde, 0xa0, 0xb2, 0x84, 0x96,
-	0x2e, 0x3c, 0x0a, 0x18, 0x66, 0x74, 0x42, 0x50,
-	0xbe, 0xac, 0x9a, 0x88, 0xf6, 0xe4, 0xd2, 0xc0,
-	0x1c, 0x0e, 0x38, 0x2a, 0x54, 0x46, 0x70, 0x62,
-	0x8c, 0x9e, 0xa8, 0xba, 0xc4, 0xd6, 0xe0, 0xf2
-};
-
-/**
- * crc7_be - update the CRC7 for the data buffer
- * @crc:     previous CRC7 value
- * @buffer:  data pointer
- * @len:     number of bytes in the buffer
- * Context: any
- *
- * Returns the updated CRC7 value.
- * The CRC7 is left-aligned in the byte (the lsbit is always 0), as that
- * makes the computation easier, and all callers want it in that form.
- *
- */
-u8 crc7_be(u8 crc, const u8 *buffer, size_t len)
-{
-	while (len--)
-		crc = crc7_be_syndrome_table[crc ^ *buffer++];
-	return crc;
-}
-EXPORT_SYMBOL(crc7_be);
-
-MODULE_DESCRIPTION("CRC7 calculations");
-MODULE_LICENSE("GPL");
diff --git a/lib/crc8.c b/lib/crc8.c
deleted file mode 100644
index 1ad8e501d9b6..000000000000
--- a/lib/crc8.c
+++ /dev/null
@@ -1,86 +0,0 @@
-/*
- * Copyright (c) 2011 Broadcom Corporation
- *
- * Permission to use, copy, modify, and/or distribute this software for any
- * purpose with or without fee is hereby granted, provided that the above
- * copyright notice and this permission notice appear in all copies.
- *
- * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
- * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
- * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
- * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
- * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
- * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
- * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
- */
-
-#define pr_fmt(fmt)		KBUILD_MODNAME ": " fmt
-
-#include <linux/module.h>
-#include <linux/crc8.h>
-#include <linux/printk.h>
-
-/**
- * crc8_populate_msb - fill crc table for given polynomial in reverse bit order.
- *
- * @table:	table to be filled.
- * @polynomial:	polynomial for which table is to be filled.
- */
-void crc8_populate_msb(u8 table[CRC8_TABLE_SIZE], u8 polynomial)
-{
-	int i, j;
-	const u8 msbit = 0x80;
-	u8 t = msbit;
-
-	table[0] = 0;
-
-	for (i = 1; i < CRC8_TABLE_SIZE; i *= 2) {
-		t = (t << 1) ^ (t & msbit ? polynomial : 0);
-		for (j = 0; j < i; j++)
-			table[i+j] = table[j] ^ t;
-	}
-}
-EXPORT_SYMBOL(crc8_populate_msb);
-
-/**
- * crc8_populate_lsb - fill crc table for given polynomial in regular bit order.
- *
- * @table:	table to be filled.
- * @polynomial:	polynomial for which table is to be filled.
- */
-void crc8_populate_lsb(u8 table[CRC8_TABLE_SIZE], u8 polynomial)
-{
-	int i, j;
-	u8 t = 1;
-
-	table[0] = 0;
-
-	for (i = (CRC8_TABLE_SIZE >> 1); i; i >>= 1) {
-		t = (t >> 1) ^ (t & 1 ? polynomial : 0);
-		for (j = 0; j < CRC8_TABLE_SIZE; j += 2*i)
-			table[i+j] = table[j] ^ t;
-	}
-}
-EXPORT_SYMBOL(crc8_populate_lsb);
-
-/**
- * crc8 - calculate a crc8 over the given input data.
- *
- * @table: crc table used for calculation.
- * @pdata: pointer to data buffer.
- * @nbytes: number of bytes in data buffer.
- * @crc: previous returned crc8 value.
- */
-u8 crc8(const u8 table[CRC8_TABLE_SIZE], const u8 *pdata, size_t nbytes, u8 crc)
-{
-	/* loop over the buffer data */
-	while (nbytes-- > 0)
-		crc = table[(crc ^ *pdata++) & 0xff];
-
-	return crc;
-}
-EXPORT_SYMBOL(crc8);
-
-MODULE_DESCRIPTION("CRC8 (by Williams, Ross N.) function");
-MODULE_AUTHOR("Broadcom Corporation");
-MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c
deleted file mode 100644
index 6d03425b849e..000000000000
--- a/lib/gen_crc32table.c
+++ /dev/null
@@ -1,89 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-#include <stdio.h>
-#include "../include/linux/crc32poly.h"
-#include "../include/generated/autoconf.h"
-#include <inttypes.h>
-
-static uint32_t crc32table_le[256];
-static uint32_t crc32table_be[256];
-static uint32_t crc32ctable_le[256];
-
-/**
- * crc32init_le() - allocate and initialize LE table data
- *
- * crc is the crc of the byte i; other entries are filled in based on the
- * fact that crctable[i^j] = crctable[i] ^ crctable[j].
- *
- */
-static void crc32init_le_generic(const uint32_t polynomial, uint32_t tab[256])
-{
-	unsigned i, j;
-	uint32_t crc = 1;
-
-	tab[0] = 0;
-
-	for (i = 128; i; i >>= 1) {
-		crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
-		for (j = 0; j < 256; j += 2 * i)
-			tab[i + j] = crc ^ tab[j];
-	}
-}
-
-static void crc32init_le(void)
-{
-	crc32init_le_generic(CRC32_POLY_LE, crc32table_le);
-}
-
-static void crc32cinit_le(void)
-{
-	crc32init_le_generic(CRC32C_POLY_LE, crc32ctable_le);
-}
-
-/**
- * crc32init_be() - allocate and initialize BE table data
- */
-static void crc32init_be(void)
-{
-	unsigned i, j;
-	uint32_t crc = 0x80000000;
-
-	crc32table_be[0] = 0;
-
-	for (i = 1; i < 256; i <<= 1) {
-		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRC32_POLY_BE : 0);
-		for (j = 0; j < i; j++)
-			crc32table_be[i + j] = crc ^ crc32table_be[j];
-	}
-}
-
-static void output_table(const uint32_t table[256])
-{
-	int i;
-
-	for (i = 0; i < 256; i += 4) {
-		printf("\t0x%08x, 0x%08x, 0x%08x, 0x%08x,\n",
-		       table[i], table[i + 1], table[i + 2], table[i + 3]);
-	}
-}
-
-int main(int argc, char** argv)
-{
-	printf("/* this file is generated - do not edit */\n\n");
-
-	crc32init_le();
-	printf("static const u32 ____cacheline_aligned crc32table_le[256] = {\n");
-	output_table(crc32table_le);
-	printf("};\n");
-
-	crc32init_be();
-	printf("static const u32 ____cacheline_aligned crc32table_be[256] = {\n");
-	output_table(crc32table_be);
-	printf("};\n");
-
-	crc32cinit_le();
-	printf("static const u32 ____cacheline_aligned crc32ctable_le[256] = {\n");
-	output_table(crc32ctable_le);
-	printf("};\n");
-
-	return 0;
-}
diff --git a/lib/gen_crc64table.c b/lib/gen_crc64table.c
deleted file mode 100644
index e05a4230a0a0..000000000000
--- a/lib/gen_crc64table.c
+++ /dev/null
@@ -1,95 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Generate lookup table for the table-driven CRC64 calculation.
- *
- * gen_crc64table is executed in kernel build time and generates
- * lib/crc64table.h. This header is included by lib/crc64.c for
- * the table-driven CRC64 calculation.
- *
- * See lib/crc64.c for more information about which specification
- * and polynomial arithmetic that gen_crc64table.c follows to
- * generate the lookup table.
- *
- * Copyright 2018 SUSE Linux.
- *   Author: Coly Li <colyli@suse.de>
- */
-#include <inttypes.h>
-#include <stdio.h>
-
-#define CRC64_ECMA182_POLY 0x42F0E1EBA9EA3693ULL
-#define CRC64_NVME_POLY 0x9A6C9329AC4BC9B5ULL
-
-static uint64_t crc64_table[256] = {0};
-static uint64_t crc64_nvme_table[256] = {0};
-
-static void generate_reflected_crc64_table(uint64_t table[256], uint64_t poly)
-{
-	uint64_t i, j, c, crc;
-
-	for (i = 0; i < 256; i++) {
-		crc = 0ULL;
-		c = i;
-
-		for (j = 0; j < 8; j++) {
-			if ((crc ^ (c >> j)) & 1)
-				crc = (crc >> 1) ^ poly;
-			else
-				crc >>= 1;
-		}
-		table[i] = crc;
-	}
-}
-
-static void generate_crc64_table(uint64_t table[256], uint64_t poly)
-{
-	uint64_t i, j, c, crc;
-
-	for (i = 0; i < 256; i++) {
-		crc = 0;
-		c = i << 56;
-
-		for (j = 0; j < 8; j++) {
-			if ((crc ^ c) & 0x8000000000000000ULL)
-				crc = (crc << 1) ^ poly;
-			else
-				crc <<= 1;
-			c <<= 1;
-		}
-
-		table[i] = crc;
-	}
-}
-
-static void output_table(uint64_t table[256])
-{
-	int i;
-
-	for (i = 0; i < 256; i++) {
-		printf("\t0x%016" PRIx64 "ULL", table[i]);
-		if (i & 0x1)
-			printf(",\n");
-		else
-			printf(", ");
-	}
-	printf("};\n");
-}
-
-static void print_crc64_tables(void)
-{
-	printf("/* this file is generated - do not edit */\n\n");
-	printf("#include <linux/types.h>\n");
-	printf("#include <linux/cache.h>\n\n");
-	printf("static const u64 ____cacheline_aligned crc64table[256] = {\n");
-	output_table(crc64_table);
-
-	printf("\nstatic const u64 ____cacheline_aligned crc64nvmetable[256] = {\n");
-	output_table(crc64_nvme_table);
-}
-
-int main(int argc, char *argv[])
-{
-	generate_crc64_table(crc64_table, CRC64_ECMA182_POLY);
-	generate_reflected_crc64_table(crc64_nvme_table, CRC64_NVME_POLY);
-	print_crc64_tables();
-	return 0;
-}
diff --git a/lib/tests/Makefile b/lib/tests/Makefile
index 56d645014482..741d3ac2cba2 100644
--- a/lib/tests/Makefile
+++ b/lib/tests/Makefile
@@ -10,7 +10,6 @@ obj-$(CONFIG_BLACKHOLE_DEV_KUNIT_TEST) += blackhole_dev_kunit.o
 obj-$(CONFIG_CHECKSUM_KUNIT) += checksum_kunit.o
 obj-$(CONFIG_CMDLINE_KUNIT_TEST) += cmdline_kunit.o
 obj-$(CONFIG_CPUMASK_KUNIT_TEST) += cpumask_kunit.o
-obj-$(CONFIG_CRC_KUNIT_TEST) += crc_kunit.o
 CFLAGS_fortify_kunit.o += $(call cc-disable-warning, unsequenced)
 CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-overread)
 CFLAGS_fortify_kunit.o += $(call cc-disable-warning, stringop-truncation)
diff --git a/lib/tests/crc_kunit.c b/lib/tests/crc_kunit.c
deleted file mode 100644
index f08d985d8860..000000000000
--- a/lib/tests/crc_kunit.c
+++ /dev/null
@@ -1,452 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-or-later
-/*
- * Unit tests and benchmarks for the CRC library functions
- *
- * Copyright 2024 Google LLC
- *
- * Author: Eric Biggers <ebiggers@google.com>
- */
-#include <kunit/test.h>
-#include <linux/crc7.h>
-#include <linux/crc16.h>
-#include <linux/crc-t10dif.h>
-#include <linux/crc32.h>
-#include <linux/crc32c.h>
-#include <linux/crc64.h>
-#include <linux/prandom.h>
-#include <linux/vmalloc.h>
-
-#define CRC_KUNIT_SEED			42
-#define CRC_KUNIT_MAX_LEN		16384
-#define CRC_KUNIT_NUM_TEST_ITERS	1000
-
-static struct rnd_state rng;
-static u8 *test_buffer;
-static size_t test_buflen;
-
-/**
- * struct crc_variant - describes a CRC variant
- * @bits: Number of bits in the CRC, 1 <= @bits <= 64.
- * @le: true if it's a "little endian" CRC (reversed mapping between bits and
- *	polynomial coefficients in each byte), false if it's a "big endian" CRC
- *	(natural mapping between bits and polynomial coefficients in each byte)
- * @poly: The generator polynomial with the highest-order term omitted.
- *	  Bit-reversed if @le is true.
- * @func: The function to compute a CRC.  The type signature uses u64 so that it
- *	  can fit any CRC up to CRC-64.  The CRC is passed in, and is expected
- *	  to be returned in, the least significant bits of the u64.  The
- *	  function is expected to *not* invert the CRC at the beginning and end.
- */
-struct crc_variant {
-	int bits;
-	bool le;
-	u64 poly;
-	u64 (*func)(u64 crc, const u8 *p, size_t len);
-};
-
-static u32 rand32(void)
-{
-	return prandom_u32_state(&rng);
-}
-
-static u64 rand64(void)
-{
-	u32 n = rand32();
-
-	return ((u64)n << 32) | rand32();
-}
-
-static u64 crc_mask(const struct crc_variant *v)
-{
-	return (u64)-1 >> (64 - v->bits);
-}
-
-/* Reference implementation of any CRC variant */
-static u64 crc_ref(const struct crc_variant *v,
-		   u64 crc, const u8 *p, size_t len)
-{
-	size_t i, j;
-
-	for (i = 0; i < len; i++) {
-		for (j = 0; j < 8; j++) {
-			if (v->le) {
-				crc ^= (p[i] >> j) & 1;
-				crc = (crc >> 1) ^ ((crc & 1) ? v->poly : 0);
-			} else {
-				crc ^= (u64)((p[i] >> (7 - j)) & 1) <<
-				       (v->bits - 1);
-				if (crc & (1ULL << (v->bits - 1)))
-					crc = ((crc << 1) ^ v->poly) &
-					      crc_mask(v);
-				else
-					crc <<= 1;
-			}
-		}
-	}
-	return crc;
-}
-
-static int crc_suite_init(struct kunit_suite *suite)
-{
-	/*
-	 * Allocate the test buffer using vmalloc() with a page-aligned length
-	 * so that it is immediately followed by a guard page.  This allows
-	 * buffer overreads to be detected, even in assembly code.
-	 */
-	test_buflen = round_up(CRC_KUNIT_MAX_LEN, PAGE_SIZE);
-	test_buffer = vmalloc(test_buflen);
-	if (!test_buffer)
-		return -ENOMEM;
-
-	prandom_seed_state(&rng, CRC_KUNIT_SEED);
-	prandom_bytes_state(&rng, test_buffer, test_buflen);
-	return 0;
-}
-
-static void crc_suite_exit(struct kunit_suite *suite)
-{
-	vfree(test_buffer);
-	test_buffer = NULL;
-}
-
-/* Generate a random initial CRC. */
-static u64 generate_random_initial_crc(const struct crc_variant *v)
-{
-	switch (rand32() % 4) {
-	case 0:
-		return 0;
-	case 1:
-		return crc_mask(v); /* All 1 bits */
-	default:
-		return rand64() & crc_mask(v);
-	}
-}
-
-/* Generate a random length, preferring small lengths. */
-static size_t generate_random_length(size_t max_length)
-{
-	size_t len;
-
-	switch (rand32() % 3) {
-	case 0:
-		len = rand32() % 128;
-		break;
-	case 1:
-		len = rand32() % 3072;
-		break;
-	default:
-		len = rand32();
-		break;
-	}
-	return len % (max_length + 1);
-}
-
-/* Test that v->func gives the same CRCs as a reference implementation. */
-static void crc_test(struct kunit *test, const struct crc_variant *v)
-{
-	size_t i;
-
-	for (i = 0; i < CRC_KUNIT_NUM_TEST_ITERS; i++) {
-		u64 init_crc, expected_crc, actual_crc;
-		size_t len, offset;
-		bool nosimd;
-
-		init_crc = generate_random_initial_crc(v);
-		len = generate_random_length(CRC_KUNIT_MAX_LEN);
-
-		/* Generate a random offset. */
-		if (rand32() % 2 == 0) {
-			/* Use a random alignment mod 64 */
-			offset = rand32() % 64;
-			offset = min(offset, CRC_KUNIT_MAX_LEN - len);
-		} else {
-			/* Go up to the guard page, to catch buffer overreads */
-			offset = test_buflen - len;
-		}
-
-		if (rand32() % 8 == 0)
-			/* Refresh the data occasionally. */
-			prandom_bytes_state(&rng, &test_buffer[offset], len);
-
-		nosimd = rand32() % 8 == 0;
-
-		/*
-		 * Compute the CRC, and verify that it equals the CRC computed
-		 * by a simple bit-at-a-time reference implementation.
-		 */
-		expected_crc = crc_ref(v, init_crc, &test_buffer[offset], len);
-		if (nosimd)
-			local_irq_disable();
-		actual_crc = v->func(init_crc, &test_buffer[offset], len);
-		if (nosimd)
-			local_irq_enable();
-		KUNIT_EXPECT_EQ_MSG(test, expected_crc, actual_crc,
-				    "Wrong result with len=%zu offset=%zu nosimd=%d",
-				    len, offset, nosimd);
-	}
-}
-
-static __always_inline void
-crc_benchmark(struct kunit *test,
-	      u64 (*crc_func)(u64 crc, const u8 *p, size_t len))
-{
-	static const size_t lens_to_test[] = {
-		1, 16, 64, 127, 128, 200, 256, 511, 512, 1024, 3173, 4096, 16384,
-	};
-	size_t len, i, j, num_iters;
-	/*
-	 * The CRC value that this function computes in a series of calls to
-	 * crc_func is never actually used, so use volatile to ensure that the
-	 * computations are done as intended and don't all get optimized out.
-	 */
-	volatile u64 crc = 0;
-	u64 t;
-
-	if (!IS_ENABLED(CONFIG_CRC_BENCHMARK))
-		kunit_skip(test, "not enabled");
-
-	/* warm-up */
-	for (i = 0; i < 10000000; i += CRC_KUNIT_MAX_LEN)
-		crc = crc_func(crc, test_buffer, CRC_KUNIT_MAX_LEN);
-
-	for (i = 0; i < ARRAY_SIZE(lens_to_test); i++) {
-		len = lens_to_test[i];
-		KUNIT_ASSERT_LE(test, len, CRC_KUNIT_MAX_LEN);
-		num_iters = 10000000 / (len + 128);
-		preempt_disable();
-		t = ktime_get_ns();
-		for (j = 0; j < num_iters; j++)
-			crc = crc_func(crc, test_buffer, len);
-		t = ktime_get_ns() - t;
-		preempt_enable();
-		kunit_info(test, "len=%zu: %llu MB/s\n",
-			   len, div64_u64((u64)len * num_iters * 1000, t));
-	}
-}
-
-/* crc7_be */
-
-static u64 crc7_be_wrapper(u64 crc, const u8 *p, size_t len)
-{
-	/*
-	 * crc7_be() left-aligns the 7-bit CRC in a u8, whereas the test wants a
-	 * right-aligned CRC (in a u64).  Convert between the conventions.
-	 */
-	return crc7_be(crc << 1, p, len) >> 1;
-}
-
-static const struct crc_variant crc_variant_crc7_be = {
-	.bits = 7,
-	.poly = 0x9,
-	.func = crc7_be_wrapper,
-};
-
-static void crc7_be_test(struct kunit *test)
-{
-	crc_test(test, &crc_variant_crc7_be);
-}
-
-static void crc7_be_benchmark(struct kunit *test)
-{
-	crc_benchmark(test, crc7_be_wrapper);
-}
-
-/* crc16 */
-
-static u64 crc16_wrapper(u64 crc, const u8 *p, size_t len)
-{
-	return crc16(crc, p, len);
-}
-
-static const struct crc_variant crc_variant_crc16 = {
-	.bits = 16,
-	.le = true,
-	.poly = 0xa001,
-	.func = crc16_wrapper,
-};
-
-static void crc16_test(struct kunit *test)
-{
-	crc_test(test, &crc_variant_crc16);
-}
-
-static void crc16_benchmark(struct kunit *test)
-{
-	crc_benchmark(test, crc16_wrapper);
-}
-
-/* crc_t10dif */
-
-static u64 crc_t10dif_wrapper(u64 crc, const u8 *p, size_t len)
-{
-	return crc_t10dif_update(crc, p, len);
-}
-
-static const struct crc_variant crc_variant_crc_t10dif = {
-	.bits = 16,
-	.le = false,
-	.poly = 0x8bb7,
-	.func = crc_t10dif_wrapper,
-};
-
-static void crc_t10dif_test(struct kunit *test)
-{
-	crc_test(test, &crc_variant_crc_t10dif);
-}
-
-static void crc_t10dif_benchmark(struct kunit *test)
-{
-	crc_benchmark(test, crc_t10dif_wrapper);
-}
-
-/* crc32_le */
-
-static u64 crc32_le_wrapper(u64 crc, const u8 *p, size_t len)
-{
-	return crc32_le(crc, p, len);
-}
-
-static const struct crc_variant crc_variant_crc32_le = {
-	.bits = 32,
-	.le = true,
-	.poly = 0xedb88320,
-	.func = crc32_le_wrapper,
-};
-
-static void crc32_le_test(struct kunit *test)
-{
-	crc_test(test, &crc_variant_crc32_le);
-}
-
-static void crc32_le_benchmark(struct kunit *test)
-{
-	crc_benchmark(test, crc32_le_wrapper);
-}
-
-/* crc32_be */
-
-static u64 crc32_be_wrapper(u64 crc, const u8 *p, size_t len)
-{
-	return crc32_be(crc, p, len);
-}
-
-static const struct crc_variant crc_variant_crc32_be = {
-	.bits = 32,
-	.le = false,
-	.poly = 0x04c11db7,
-	.func = crc32_be_wrapper,
-};
-
-static void crc32_be_test(struct kunit *test)
-{
-	crc_test(test, &crc_variant_crc32_be);
-}
-
-static void crc32_be_benchmark(struct kunit *test)
-{
-	crc_benchmark(test, crc32_be_wrapper);
-}
-
-/* crc32c */
-
-static u64 crc32c_wrapper(u64 crc, const u8 *p, size_t len)
-{
-	return crc32c(crc, p, len);
-}
-
-static const struct crc_variant crc_variant_crc32c = {
-	.bits = 32,
-	.le = true,
-	.poly = 0x82f63b78,
-	.func = crc32c_wrapper,
-};
-
-static void crc32c_test(struct kunit *test)
-{
-	crc_test(test, &crc_variant_crc32c);
-}
-
-static void crc32c_benchmark(struct kunit *test)
-{
-	crc_benchmark(test, crc32c_wrapper);
-}
-
-/* crc64_be */
-
-static u64 crc64_be_wrapper(u64 crc, const u8 *p, size_t len)
-{
-	return crc64_be(crc, p, len);
-}
-
-static const struct crc_variant crc_variant_crc64_be = {
-	.bits = 64,
-	.le = false,
-	.poly = 0x42f0e1eba9ea3693,
-	.func = crc64_be_wrapper,
-};
-
-static void crc64_be_test(struct kunit *test)
-{
-	crc_test(test, &crc_variant_crc64_be);
-}
-
-static void crc64_be_benchmark(struct kunit *test)
-{
-	crc_benchmark(test, crc64_be_wrapper);
-}
-
-/* crc64_nvme */
-
-static u64 crc64_nvme_wrapper(u64 crc, const u8 *p, size_t len)
-{
-	/* The inversions that crc64_nvme() does have to be undone here. */
-	return ~crc64_nvme(~crc, p, len);
-}
-
-static const struct crc_variant crc_variant_crc64_nvme = {
-	.bits = 64,
-	.le = true,
-	.poly = 0x9a6c9329ac4bc9b5,
-	.func = crc64_nvme_wrapper,
-};
-
-static void crc64_nvme_test(struct kunit *test)
-{
-	crc_test(test, &crc_variant_crc64_nvme);
-}
-
-static void crc64_nvme_benchmark(struct kunit *test)
-{
-	crc_benchmark(test, crc64_nvme_wrapper);
-}
-
-static struct kunit_case crc_test_cases[] = {
-	KUNIT_CASE(crc7_be_test),
-	KUNIT_CASE(crc7_be_benchmark),
-	KUNIT_CASE(crc16_test),
-	KUNIT_CASE(crc16_benchmark),
-	KUNIT_CASE(crc_t10dif_test),
-	KUNIT_CASE(crc_t10dif_benchmark),
-	KUNIT_CASE(crc32_le_test),
-	KUNIT_CASE(crc32_le_benchmark),
-	KUNIT_CASE(crc32_be_test),
-	KUNIT_CASE(crc32_be_benchmark),
-	KUNIT_CASE(crc32c_test),
-	KUNIT_CASE(crc32c_benchmark),
-	KUNIT_CASE(crc64_be_test),
-	KUNIT_CASE(crc64_be_benchmark),
-	KUNIT_CASE(crc64_nvme_test),
-	KUNIT_CASE(crc64_nvme_benchmark),
-	{},
-};
-
-static struct kunit_suite crc_test_suite = {
-	.name = "crc",
-	.test_cases = crc_test_cases,
-	.suite_init = crc_suite_init,
-	.suite_exit = crc_suite_exit,
-};
-kunit_test_suite(crc_test_suite);
-
-MODULE_DESCRIPTION("Unit tests and benchmarks for the CRC library functions");
-MODULE_LICENSE("GPL");
-- 
cgit v1.2.3


From 0bcfca56406dc6342e30fafe41a2f34cdde029b4 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Sat, 7 Jun 2025 13:04:44 -0700
Subject: lib/crc: Prepare for arch-optimized code in subdirs of lib/crc/

Rework how lib/crc/ supports arch-optimized code.  First, instead of the
arch-optimized CRC code being in arch/$(SRCARCH)/lib/, it will now be in
lib/crc/$(SRCARCH)/.  Second, the API functions (e.g. crc32c()),
arch-optimized functions (e.g. crc32c_arch()), and generic functions
(e.g. crc32c_base()) will now be part of a single module for each CRC
type, allowing better inlining and dead code elimination.  The second
change is made possible by the first.

As an example, consider CONFIG_CRC32=m on x86.  We'll now have just
crc32.ko instead of both crc32-x86.ko and crc32.ko.  The two modules
were already coupled together and always both got loaded together via
direct symbol dependency, so the separation provided no benefit.

Note: later I'd like to apply the same design to lib/crypto/ too, where
often the API functions are out-of-line so this will work even better.
In those cases, for each algorithm we currently have 3 modules all
coupled together, e.g. libsha256.ko, libsha256-generic.ko, and
sha256-x86.ko.  We should have just one, inline things properly, and
rely on the compiler's dead code elimination to decide the inclusion of
the generic code instead of manually setting it via kconfig.

Having arch-specific code outside arch/ was somewhat controversial when
Zinc proposed it back in 2018.  But I don't think the concerns are
warranted.  It's better from a technical perspective, as it enables the
improvements mentioned above.  This model is already successfully used
in other places in the kernel such as lib/raid6/.  The community of each
architecture still remains free to work on the code, even if it's not in
arch/.  At the time there was also a desire to put the library code in
the same files as the old-school crypto API, but that was a mistake; now
that the library is separate, that's no longer a constraint either.

Reviewed-by: "Martin K. Petersen" <martin.petersen@oracle.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Acked-by: "Jason A. Donenfeld" <Jason@zx2c4.com>
Link: https://lore.kernel.org/r/20250607200454.73587-3-ebiggers@kernel.org
Link: https://lore.kernel.org/r/20250612054514.142728-1-ebiggers@kernel.org
Link: https://lore.kernel.org/r/20250621012221.4351-1-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 Documentation/core-api/kernel-api.rst |   2 +-
 MAINTAINERS                           |   1 -
 include/linux/crc-t10dif.h            |  10 +---
 include/linux/crc32.h                 |  30 +---------
 include/linux/crc64.h                 |  19 +------
 lib/crc/Kconfig                       |  13 +++--
 lib/crc/Makefile                      |  20 ++++++-
 lib/crc/crc-t10dif-main.c             |  88 ++++++++++++++++++++++++++++
 lib/crc/crc-t10dif.c                  |  65 ---------------------
 lib/crc/crc32-main.c                  | 104 ++++++++++++++++++++++++++++++++++
 lib/crc/crc32.c                       |  59 -------------------
 lib/crc/crc64-main.c                  |  91 +++++++++++++++++++++++++++++
 lib/crc/crc64.c                       |  58 -------------------
 13 files changed, 315 insertions(+), 245 deletions(-)
 create mode 100644 lib/crc/crc-t10dif-main.c
 delete mode 100644 lib/crc/crc-t10dif.c
 create mode 100644 lib/crc/crc32-main.c
 delete mode 100644 lib/crc/crc32.c
 create mode 100644 lib/crc/crc64-main.c
 delete mode 100644 lib/crc/crc64.c

(limited to 'include/linux')

diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index c4642d9f13a9..9c8370891a39 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -148,7 +148,7 @@ CRC Functions
 .. kernel-doc:: lib/crc/crc16.c
    :export:
 
-.. kernel-doc:: lib/crc/crc32.c
+.. kernel-doc:: lib/crc/crc32-main.c
 
 .. kernel-doc:: lib/crc/crc-ccitt.c
    :export:
diff --git a/MAINTAINERS b/MAINTAINERS
index b0ec17dfbe03..d75676e17ac7 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6359,7 +6359,6 @@ L:	linux-crypto@vger.kernel.org
 S:	Maintained
 T:	git https://git.kernel.org/pub/scm/linux/kernel/git/ebiggers/linux.git crc-next
 F:	Documentation/staging/crc*
-F:	arch/*/lib/crc*
 F:	include/linux/crc*
 F:	lib/crc/
 F:	scripts/gen-crc-consts.py
diff --git a/include/linux/crc-t10dif.h b/include/linux/crc-t10dif.h
index a559fdff3f7e..ecc8bc2dd7f4 100644
--- a/include/linux/crc-t10dif.h
+++ b/include/linux/crc-t10dif.h
@@ -4,15 +4,7 @@
 
 #include <linux/types.h>
 
-u16 crc_t10dif_arch(u16 crc, const u8 *p, size_t len);
-u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len);
-
-static inline u16 crc_t10dif_update(u16 crc, const u8 *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC_T10DIF_ARCH))
-		return crc_t10dif_arch(crc, p, len);
-	return crc_t10dif_generic(crc, p, len);
-}
+u16 crc_t10dif_update(u16 crc, const u8 *p, size_t len);
 
 static inline u16 crc_t10dif(const u8 *p, size_t len)
 {
diff --git a/include/linux/crc32.h b/include/linux/crc32.h
index 36bbc0405aa0..22dbe7144eb4 100644
--- a/include/linux/crc32.h
+++ b/include/linux/crc32.h
@@ -5,33 +5,9 @@
 #include <linux/types.h>
 #include <linux/bitrev.h>
 
-u32 crc32_le_arch(u32 crc, const u8 *p, size_t len);
-u32 crc32_le_base(u32 crc, const u8 *p, size_t len);
-u32 crc32_be_arch(u32 crc, const u8 *p, size_t len);
-u32 crc32_be_base(u32 crc, const u8 *p, size_t len);
-u32 crc32c_arch(u32 crc, const u8 *p, size_t len);
-u32 crc32c_base(u32 crc, const u8 *p, size_t len);
-
-static inline u32 crc32_le(u32 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC32_ARCH))
-		return crc32_le_arch(crc, p, len);
-	return crc32_le_base(crc, p, len);
-}
-
-static inline u32 crc32_be(u32 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC32_ARCH))
-		return crc32_be_arch(crc, p, len);
-	return crc32_be_base(crc, p, len);
-}
-
-static inline u32 crc32c(u32 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC32_ARCH))
-		return crc32c_arch(crc, p, len);
-	return crc32c_base(crc, p, len);
-}
+u32 crc32_le(u32 crc, const void *p, size_t len);
+u32 crc32_be(u32 crc, const void *p, size_t len);
+u32 crc32c(u32 crc, const void *p, size_t len);
 
 /*
  * crc32_optimizations() returns flags that indicate which CRC32 library
diff --git a/include/linux/crc64.h b/include/linux/crc64.h
index b6aa290a7931..fc0c06ab1993 100644
--- a/include/linux/crc64.h
+++ b/include/linux/crc64.h
@@ -4,11 +4,6 @@
 
 #include <linux/types.h>
 
-u64 crc64_be_arch(u64 crc, const u8 *p, size_t len);
-u64 crc64_be_generic(u64 crc, const u8 *p, size_t len);
-u64 crc64_nvme_arch(u64 crc, const u8 *p, size_t len);
-u64 crc64_nvme_generic(u64 crc, const u8 *p, size_t len);
-
 /**
  * crc64_be - Calculate bitwise big-endian ECMA-182 CRC64
  * @crc: seed value for computation. 0 or (u64)~0 for a new CRC calculation,
@@ -16,12 +11,7 @@ u64 crc64_nvme_generic(u64 crc, const u8 *p, size_t len);
  * @p: pointer to buffer over which CRC64 is run
  * @len: length of buffer @p
  */
-static inline u64 crc64_be(u64 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC64_ARCH))
-		return crc64_be_arch(crc, p, len);
-	return crc64_be_generic(crc, p, len);
-}
+u64 crc64_be(u64 crc, const void *p, size_t len);
 
 /**
  * crc64_nvme - Calculate CRC64-NVME
@@ -33,11 +23,6 @@ static inline u64 crc64_be(u64 crc, const void *p, size_t len)
  * This computes the CRC64 defined in the NVME NVM Command Set Specification,
  * *including the bitwise inversion at the beginning and end*.
  */
-static inline u64 crc64_nvme(u64 crc, const void *p, size_t len)
-{
-	if (IS_ENABLED(CONFIG_CRC64_ARCH))
-		return ~crc64_nvme_arch(~crc, p, len);
-	return ~crc64_nvme_generic(~crc, p, len);
-}
+u64 crc64_nvme(u64 crc, const void *p, size_t len);
 
 #endif /* _LINUX_CRC64_H */
diff --git a/lib/crc/Kconfig b/lib/crc/Kconfig
index e0e7168b74c7..04c7aeb0fc8e 100644
--- a/lib/crc/Kconfig
+++ b/lib/crc/Kconfig
@@ -48,8 +48,8 @@ config ARCH_HAS_CRC_T10DIF
 	bool
 
 config CRC_T10DIF_ARCH
-	tristate
-	default CRC_T10DIF if ARCH_HAS_CRC_T10DIF && CRC_OPTIMIZATIONS
+	bool
+	depends on CRC_T10DIF && CRC_OPTIMIZATIONS
 
 config CRC32
 	tristate
@@ -62,8 +62,8 @@ config ARCH_HAS_CRC32
 	bool
 
 config CRC32_ARCH
-	tristate
-	default CRC32 if ARCH_HAS_CRC32 && CRC_OPTIMIZATIONS
+	bool
+	depends on CRC32 && CRC_OPTIMIZATIONS
 
 config CRC64
 	tristate
@@ -75,11 +75,12 @@ config ARCH_HAS_CRC64
 	bool
 
 config CRC64_ARCH
-	tristate
-	default CRC64 if ARCH_HAS_CRC64 && CRC_OPTIMIZATIONS
+	bool
+	depends on CRC64 && CRC_OPTIMIZATIONS
 
 config CRC_OPTIMIZATIONS
 	bool "Enable optimized CRC implementations" if EXPERT
+	depends on !UML
 	default y
 	help
 	  Disabling this option reduces code size slightly by disabling the
diff --git a/lib/crc/Makefile b/lib/crc/Makefile
index ff4c30dda452..926edc3b035f 100644
--- a/lib/crc/Makefile
+++ b/lib/crc/Makefile
@@ -8,16 +8,32 @@ obj-$(CONFIG_CRC8) += crc8.o
 obj-$(CONFIG_CRC16) += crc16.o
 obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
 obj-$(CONFIG_CRC_ITU_T) += crc-itu-t.o
+
 obj-$(CONFIG_CRC_T10DIF) += crc-t10dif.o
+crc-t10dif-y := crc-t10dif-main.o
+ifeq ($(CONFIG_CRC_T10DIF_ARCH),y)
+CFLAGS_crc-t10dif-main.o += -I$(src)/$(SRCARCH)
+endif
+
 obj-$(CONFIG_CRC32) += crc32.o
+crc32-y := crc32-main.o
+ifeq ($(CONFIG_CRC32_ARCH),y)
+CFLAGS_crc32-main.o += -I$(src)/$(SRCARCH)
+endif
+
 obj-$(CONFIG_CRC64) += crc64.o
+crc64-y := crc64-main.o
+ifeq ($(CONFIG_CRC64_ARCH),y)
+CFLAGS_crc64-main.o += -I$(src)/$(SRCARCH)
+endif
+
 obj-y += tests/
 
 hostprogs := gen_crc32table gen_crc64table
 clean-files := crc32table.h crc64table.h
 
-$(obj)/crc32.o: $(obj)/crc32table.h
-$(obj)/crc64.o: $(obj)/crc64table.h
+$(obj)/crc32-main.o: $(obj)/crc32table.h
+$(obj)/crc64-main.o: $(obj)/crc64table.h
 
 quiet_cmd_crc32 = GEN     $@
       cmd_crc32 = $< > $@
diff --git a/lib/crc/crc-t10dif-main.c b/lib/crc/crc-t10dif-main.c
new file mode 100644
index 000000000000..bc91f3888184
--- /dev/null
+++ b/lib/crc/crc-t10dif-main.c
@@ -0,0 +1,88 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * T10 Data Integrity Field CRC16 calculation
+ *
+ * Copyright (c) 2007 Oracle Corporation.  All rights reserved.
+ * Written by Martin K. Petersen <martin.petersen@oracle.com>
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-t10dif.h>
+
+/*
+ * Table generated using the following polynomial:
+ * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1
+ * gt: 0x8bb7
+ */
+static const u16 t10_dif_crc_table[256] = {
+	0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B,
+	0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6,
+	0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6,
+	0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B,
+	0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1,
+	0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C,
+	0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C,
+	0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781,
+	0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8,
+	0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255,
+	0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925,
+	0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698,
+	0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472,
+	0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF,
+	0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF,
+	0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02,
+	0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA,
+	0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067,
+	0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17,
+	0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA,
+	0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640,
+	0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD,
+	0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D,
+	0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30,
+	0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759,
+	0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4,
+	0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394,
+	0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29,
+	0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3,
+	0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E,
+	0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E,
+	0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3
+};
+
+static inline u16 __maybe_unused
+crc_t10dif_generic(u16 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc << 8) ^ t10_dif_crc_table[(crc >> 8) ^ *p++];
+	return crc;
+}
+
+#ifdef CONFIG_CRC_T10DIF_ARCH
+#include "crc-t10dif.h" /* $(SRCARCH)/crc-t10dif.h */
+#else
+#define crc_t10dif_arch crc_t10dif_generic
+#endif
+
+u16 crc_t10dif_update(u16 crc, const u8 *p, size_t len)
+{
+	return crc_t10dif_arch(crc, p, len);
+}
+EXPORT_SYMBOL(crc_t10dif_update);
+
+#ifdef crc_t10dif_mod_init_arch
+static int __init crc_t10dif_mod_init(void)
+{
+	crc_t10dif_mod_init_arch();
+	return 0;
+}
+subsys_initcall(crc_t10dif_mod_init);
+
+static void __exit crc_t10dif_mod_exit(void)
+{
+}
+module_exit(crc_t10dif_mod_exit);
+#endif
+
+MODULE_DESCRIPTION("CRC-T10DIF library functions");
+MODULE_LICENSE("GPL");
diff --git a/lib/crc/crc-t10dif.c b/lib/crc/crc-t10dif.c
deleted file mode 100644
index 311c2ab829f1..000000000000
--- a/lib/crc/crc-t10dif.c
+++ /dev/null
@@ -1,65 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * T10 Data Integrity Field CRC16 calculation
- *
- * Copyright (c) 2007 Oracle Corporation.  All rights reserved.
- * Written by Martin K. Petersen <martin.petersen@oracle.com>
- */
-
-#include <linux/types.h>
-#include <linux/module.h>
-#include <linux/crc-t10dif.h>
-
-/*
- * Table generated using the following polynomial:
- * x^16 + x^15 + x^11 + x^9 + x^8 + x^7 + x^5 + x^4 + x^2 + x + 1
- * gt: 0x8bb7
- */
-static const u16 t10_dif_crc_table[256] = {
-	0x0000, 0x8BB7, 0x9CD9, 0x176E, 0xB205, 0x39B2, 0x2EDC, 0xA56B,
-	0xEFBD, 0x640A, 0x7364, 0xF8D3, 0x5DB8, 0xD60F, 0xC161, 0x4AD6,
-	0x54CD, 0xDF7A, 0xC814, 0x43A3, 0xE6C8, 0x6D7F, 0x7A11, 0xF1A6,
-	0xBB70, 0x30C7, 0x27A9, 0xAC1E, 0x0975, 0x82C2, 0x95AC, 0x1E1B,
-	0xA99A, 0x222D, 0x3543, 0xBEF4, 0x1B9F, 0x9028, 0x8746, 0x0CF1,
-	0x4627, 0xCD90, 0xDAFE, 0x5149, 0xF422, 0x7F95, 0x68FB, 0xE34C,
-	0xFD57, 0x76E0, 0x618E, 0xEA39, 0x4F52, 0xC4E5, 0xD38B, 0x583C,
-	0x12EA, 0x995D, 0x8E33, 0x0584, 0xA0EF, 0x2B58, 0x3C36, 0xB781,
-	0xD883, 0x5334, 0x445A, 0xCFED, 0x6A86, 0xE131, 0xF65F, 0x7DE8,
-	0x373E, 0xBC89, 0xABE7, 0x2050, 0x853B, 0x0E8C, 0x19E2, 0x9255,
-	0x8C4E, 0x07F9, 0x1097, 0x9B20, 0x3E4B, 0xB5FC, 0xA292, 0x2925,
-	0x63F3, 0xE844, 0xFF2A, 0x749D, 0xD1F6, 0x5A41, 0x4D2F, 0xC698,
-	0x7119, 0xFAAE, 0xEDC0, 0x6677, 0xC31C, 0x48AB, 0x5FC5, 0xD472,
-	0x9EA4, 0x1513, 0x027D, 0x89CA, 0x2CA1, 0xA716, 0xB078, 0x3BCF,
-	0x25D4, 0xAE63, 0xB90D, 0x32BA, 0x97D1, 0x1C66, 0x0B08, 0x80BF,
-	0xCA69, 0x41DE, 0x56B0, 0xDD07, 0x786C, 0xF3DB, 0xE4B5, 0x6F02,
-	0x3AB1, 0xB106, 0xA668, 0x2DDF, 0x88B4, 0x0303, 0x146D, 0x9FDA,
-	0xD50C, 0x5EBB, 0x49D5, 0xC262, 0x6709, 0xECBE, 0xFBD0, 0x7067,
-	0x6E7C, 0xE5CB, 0xF2A5, 0x7912, 0xDC79, 0x57CE, 0x40A0, 0xCB17,
-	0x81C1, 0x0A76, 0x1D18, 0x96AF, 0x33C4, 0xB873, 0xAF1D, 0x24AA,
-	0x932B, 0x189C, 0x0FF2, 0x8445, 0x212E, 0xAA99, 0xBDF7, 0x3640,
-	0x7C96, 0xF721, 0xE04F, 0x6BF8, 0xCE93, 0x4524, 0x524A, 0xD9FD,
-	0xC7E6, 0x4C51, 0x5B3F, 0xD088, 0x75E3, 0xFE54, 0xE93A, 0x628D,
-	0x285B, 0xA3EC, 0xB482, 0x3F35, 0x9A5E, 0x11E9, 0x0687, 0x8D30,
-	0xE232, 0x6985, 0x7EEB, 0xF55C, 0x5037, 0xDB80, 0xCCEE, 0x4759,
-	0x0D8F, 0x8638, 0x9156, 0x1AE1, 0xBF8A, 0x343D, 0x2353, 0xA8E4,
-	0xB6FF, 0x3D48, 0x2A26, 0xA191, 0x04FA, 0x8F4D, 0x9823, 0x1394,
-	0x5942, 0xD2F5, 0xC59B, 0x4E2C, 0xEB47, 0x60F0, 0x779E, 0xFC29,
-	0x4BA8, 0xC01F, 0xD771, 0x5CC6, 0xF9AD, 0x721A, 0x6574, 0xEEC3,
-	0xA415, 0x2FA2, 0x38CC, 0xB37B, 0x1610, 0x9DA7, 0x8AC9, 0x017E,
-	0x1F65, 0x94D2, 0x83BC, 0x080B, 0xAD60, 0x26D7, 0x31B9, 0xBA0E,
-	0xF0D8, 0x7B6F, 0x6C01, 0xE7B6, 0x42DD, 0xC96A, 0xDE04, 0x55B3
-};
-
-u16 crc_t10dif_generic(u16 crc, const u8 *p, size_t len)
-{
-	size_t i;
-
-	for (i = 0; i < len; i++)
-		crc = (crc << 8) ^ t10_dif_crc_table[(crc >> 8) ^ p[i]];
-
-	return crc;
-}
-EXPORT_SYMBOL(crc_t10dif_generic);
-
-MODULE_DESCRIPTION("T10 DIF CRC calculation");
-MODULE_LICENSE("GPL");
diff --git a/lib/crc/crc32-main.c b/lib/crc/crc32-main.c
new file mode 100644
index 000000000000..7843512ffef4
--- /dev/null
+++ b/lib/crc/crc32-main.c
@@ -0,0 +1,104 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin
+ * cleaned up code to current version of sparse and added the slicing-by-8
+ * algorithm to the closely similar existing slicing-by-4 algorithm.
+ *
+ * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com>
+ * Nicer crc32 functions/docs submitted by linux@horizon.com.  Thanks!
+ * Code was from the public domain, copyright abandoned.  Code was
+ * subsequently included in the kernel, thus was re-licensed under the
+ * GNU GPL v2.
+ *
+ * Oct 12, 2000 Matt Domsch <Matt_Domsch@dell.com>
+ * Same crc32 function was used in 5 other places in the kernel.
+ * I made one version, and deleted the others.
+ * There are various incantations of crc32().  Some use a seed of 0 or ~0.
+ * Some xor at the end with ~0.  The generic crc32() function takes
+ * seed as an argument, and doesn't xor at the end.  Then individual
+ * users can do whatever they need.
+ *   drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0.
+ *   fs/jffs2 uses seed 0, doesn't xor with ~0.
+ *   fs/partitions/efi.c uses seed ~0, xor's with ~0.
+ */
+
+/* see: Documentation/staging/crc32.rst for a description of algorithms */
+
+#include <linux/crc32.h>
+#include <linux/module.h>
+#include <linux/types.h>
+
+#include "crc32table.h"
+
+static inline u32 __maybe_unused
+crc32_le_base(u32 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++];
+	return crc;
+}
+
+static inline u32 __maybe_unused
+crc32_be_base(u32 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++];
+	return crc;
+}
+
+static inline u32 __maybe_unused
+crc32c_base(u32 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++];
+	return crc;
+}
+
+#ifdef CONFIG_CRC32_ARCH
+#include "crc32.h" /* $(SRCARCH)/crc32.h */
+
+u32 crc32_optimizations(void)
+{
+	return crc32_optimizations_arch();
+}
+EXPORT_SYMBOL(crc32_optimizations);
+#else
+#define crc32_le_arch crc32_le_base
+#define crc32_be_arch crc32_be_base
+#define crc32c_arch crc32c_base
+#endif
+
+u32 crc32_le(u32 crc, const void *p, size_t len)
+{
+	return crc32_le_arch(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_le);
+
+u32 crc32_be(u32 crc, const void *p, size_t len)
+{
+	return crc32_be_arch(crc, p, len);
+}
+EXPORT_SYMBOL(crc32_be);
+
+u32 crc32c(u32 crc, const void *p, size_t len)
+{
+	return crc32c_arch(crc, p, len);
+}
+EXPORT_SYMBOL(crc32c);
+
+#ifdef crc32_mod_init_arch
+static int __init crc32_mod_init(void)
+{
+	crc32_mod_init_arch();
+	return 0;
+}
+subsys_initcall(crc32_mod_init);
+
+static void __exit crc32_mod_exit(void)
+{
+}
+module_exit(crc32_mod_exit);
+#endif
+
+MODULE_DESCRIPTION("CRC32 library functions");
+MODULE_LICENSE("GPL");
diff --git a/lib/crc/crc32.c b/lib/crc/crc32.c
deleted file mode 100644
index 6811b37df2aa..000000000000
--- a/lib/crc/crc32.c
+++ /dev/null
@@ -1,59 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin
- * cleaned up code to current version of sparse and added the slicing-by-8
- * algorithm to the closely similar existing slicing-by-4 algorithm.
- *
- * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com>
- * Nicer crc32 functions/docs submitted by linux@horizon.com.  Thanks!
- * Code was from the public domain, copyright abandoned.  Code was
- * subsequently included in the kernel, thus was re-licensed under the
- * GNU GPL v2.
- *
- * Oct 12, 2000 Matt Domsch <Matt_Domsch@dell.com>
- * Same crc32 function was used in 5 other places in the kernel.
- * I made one version, and deleted the others.
- * There are various incantations of crc32().  Some use a seed of 0 or ~0.
- * Some xor at the end with ~0.  The generic crc32() function takes
- * seed as an argument, and doesn't xor at the end.  Then individual
- * users can do whatever they need.
- *   drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0.
- *   fs/jffs2 uses seed 0, doesn't xor with ~0.
- *   fs/partitions/efi.c uses seed ~0, xor's with ~0.
- */
-
-/* see: Documentation/staging/crc32.rst for a description of algorithms */
-
-#include <linux/crc32.h>
-#include <linux/module.h>
-#include <linux/types.h>
-
-#include "crc32table.h"
-
-MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
-MODULE_DESCRIPTION("Various CRC32 calculations");
-MODULE_LICENSE("GPL");
-
-u32 crc32_le_base(u32 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc >> 8) ^ crc32table_le[(crc & 255) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL(crc32_le_base);
-
-u32 crc32c_base(u32 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc >> 8) ^ crc32ctable_le[(crc & 255) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL(crc32c_base);
-
-u32 crc32_be_base(u32 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc << 8) ^ crc32table_be[(crc >> 24) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL(crc32_be_base);
diff --git a/lib/crc/crc64-main.c b/lib/crc/crc64-main.c
new file mode 100644
index 000000000000..038afc7f4d44
--- /dev/null
+++ b/lib/crc/crc64-main.c
@@ -0,0 +1,91 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Normal 64-bit CRC calculation.
+ *
+ * This is a basic crc64 implementation following ECMA-182 specification,
+ * which can be found from,
+ * https://www.ecma-international.org/publications/standards/Ecma-182.htm
+ *
+ * Dr. Ross N. Williams has a great document to introduce the idea of CRC
+ * algorithm, here the CRC64 code is also inspired by the table-driven
+ * algorithm and detail example from this paper. This paper can be found
+ * from,
+ * http://www.ross.net/crc/download/crc_v3.txt
+ *
+ * crc64table[256] is the lookup table of a table-driven 64-bit CRC
+ * calculation, which is generated by gen_crc64table.c in kernel build
+ * time. The polynomial of crc64 arithmetic is from ECMA-182 specification
+ * as well, which is defined as,
+ *
+ * x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
+ * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
+ * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
+ * x^7 + x^4 + x + 1
+ *
+ * crc64nvmetable[256] uses the CRC64 polynomial from the NVME NVM Command Set
+ * Specification and uses least-significant-bit first bit order:
+ *
+ * x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 + x^47 +
+ * x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 + x^26 + x^23 +
+ * x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 + x^4 + x^3 + 1
+ *
+ * Copyright 2018 SUSE Linux.
+ *   Author: Coly Li <colyli@suse.de>
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/crc64.h>
+#include "crc64table.h"
+
+static inline u64 __maybe_unused
+crc64_be_generic(u64 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc << 8) ^ crc64table[(crc >> 56) ^ *p++];
+	return crc;
+}
+
+static inline u64 __maybe_unused
+crc64_nvme_generic(u64 crc, const u8 *p, size_t len)
+{
+	while (len--)
+		crc = (crc >> 8) ^ crc64nvmetable[(crc & 0xff) ^ *p++];
+	return crc;
+}
+
+#ifdef CONFIG_CRC64_ARCH
+#include "crc64.h" /* $(SRCARCH)/crc64.h */
+#else
+#define crc64_be_arch crc64_be_generic
+#define crc64_nvme_arch crc64_nvme_generic
+#endif
+
+u64 crc64_be(u64 crc, const void *p, size_t len)
+{
+	return crc64_be_arch(crc, p, len);
+}
+EXPORT_SYMBOL_GPL(crc64_be);
+
+u64 crc64_nvme(u64 crc, const void *p, size_t len)
+{
+	return ~crc64_nvme_arch(~crc, p, len);
+}
+EXPORT_SYMBOL_GPL(crc64_nvme);
+
+#ifdef crc64_mod_init_arch
+static int __init crc64_mod_init(void)
+{
+	crc64_mod_init_arch();
+	return 0;
+}
+subsys_initcall(crc64_mod_init);
+
+static void __exit crc64_mod_exit(void)
+{
+}
+module_exit(crc64_mod_exit);
+#endif
+
+MODULE_DESCRIPTION("CRC64 library functions");
+MODULE_LICENSE("GPL");
diff --git a/lib/crc/crc64.c b/lib/crc/crc64.c
deleted file mode 100644
index 5b1b17057f0a..000000000000
--- a/lib/crc/crc64.c
+++ /dev/null
@@ -1,58 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * Normal 64-bit CRC calculation.
- *
- * This is a basic crc64 implementation following ECMA-182 specification,
- * which can be found from,
- * https://www.ecma-international.org/publications/standards/Ecma-182.htm
- *
- * Dr. Ross N. Williams has a great document to introduce the idea of CRC
- * algorithm, here the CRC64 code is also inspired by the table-driven
- * algorithm and detail example from this paper. This paper can be found
- * from,
- * http://www.ross.net/crc/download/crc_v3.txt
- *
- * crc64table[256] is the lookup table of a table-driven 64-bit CRC
- * calculation, which is generated by gen_crc64table.c in kernel build
- * time. The polynomial of crc64 arithmetic is from ECMA-182 specification
- * as well, which is defined as,
- *
- * x^64 + x^62 + x^57 + x^55 + x^54 + x^53 + x^52 + x^47 + x^46 + x^45 +
- * x^40 + x^39 + x^38 + x^37 + x^35 + x^33 + x^32 + x^31 + x^29 + x^27 +
- * x^24 + x^23 + x^22 + x^21 + x^19 + x^17 + x^13 + x^12 + x^10 + x^9 +
- * x^7 + x^4 + x + 1
- *
- * crc64nvmetable[256] uses the CRC64 polynomial from the NVME NVM Command Set
- * Specification and uses least-significant-bit first bit order:
- *
- * x^64 + x^63 + x^61 + x^59 + x^58 + x^56 + x^55 + x^52 + x^49 + x^48 + x^47 +
- * x^46 + x^44 + x^41 + x^37 + x^36 + x^34 + x^32 + x^31 + x^28 + x^26 + x^23 +
- * x^22 + x^19 + x^16 + x^13 + x^12 + x^10 + x^9 + x^6 + x^4 + x^3 + 1
- *
- * Copyright 2018 SUSE Linux.
- *   Author: Coly Li <colyli@suse.de>
- */
-
-#include <linux/module.h>
-#include <linux/types.h>
-#include <linux/crc64.h>
-#include "crc64table.h"
-
-MODULE_DESCRIPTION("CRC64 calculations");
-MODULE_LICENSE("GPL v2");
-
-u64 crc64_be_generic(u64 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc << 8) ^ crc64table[(crc >> 56) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL_GPL(crc64_be_generic);
-
-u64 crc64_nvme_generic(u64 crc, const u8 *p, size_t len)
-{
-	while (len--)
-		crc = (crc >> 8) ^ crc64nvmetable[(crc & 0xff) ^ *p++];
-	return crc;
-}
-EXPORT_SYMBOL_GPL(crc64_nvme_generic);
-- 
cgit v1.2.3


From 8c7c675155ce3f0f6b12c57a47298a390661652d Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Thu, 19 Jun 2025 11:34:12 -0700
Subject: lib/crc: crc32: Document crc32_le(), crc32_be(), and crc32c()

Document these widely used functions.

Update kernel-api.rst to point to the correct place, instead of to
crc32-main.c which no longer contains kerneldoc comments.

Simplify the documentation in crc32poly.h to just point to the
corresponding functions, now that they are properly documented.  Change
the value of CRC32C_POLY_LE to lower case, for consistency.

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250619183414.100082-2-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 Documentation/core-api/kernel-api.rst |  4 +--
 include/linux/crc32.h                 | 66 +++++++++++++++++++++++++++++++++++
 include/linux/crc32poly.h             | 16 +++------
 3 files changed, 73 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/kernel-api.rst b/Documentation/core-api/kernel-api.rst
index 9c8370891a39..0096463c7d7f 100644
--- a/Documentation/core-api/kernel-api.rst
+++ b/Documentation/core-api/kernel-api.rst
@@ -148,14 +148,14 @@ CRC Functions
 .. kernel-doc:: lib/crc/crc16.c
    :export:
 
-.. kernel-doc:: lib/crc/crc32-main.c
-
 .. kernel-doc:: lib/crc/crc-ccitt.c
    :export:
 
 .. kernel-doc:: lib/crc/crc-itu-t.c
    :export:
 
+.. kernel-doc:: include/linux/crc32.h
+
 Base 2 log and power Functions
 ------------------------------
 
diff --git a/include/linux/crc32.h b/include/linux/crc32.h
index 22dbe7144eb4..f9c173206d4d 100644
--- a/include/linux/crc32.h
+++ b/include/linux/crc32.h
@@ -5,8 +5,74 @@
 #include <linux/types.h>
 #include <linux/bitrev.h>
 
+/**
+ * crc32_le() - Compute least-significant-bit-first IEEE CRC-32
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
+ *
+ * This implements the CRC variant that is often known as the IEEE CRC-32, or
+ * simply CRC-32, and is widely used in Ethernet and other applications:
+ *
+ * - Polynomial: x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 +
+ *		 x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+ * - Bit order: Least-significant-bit-first
+ * - Polynomial in integer form: 0xedb88320
+ *
+ * This does *not* invert the CRC at the beginning or end.  The caller is
+ * expected to do that if it needs to.  Inverting at both ends is recommended.
+ *
+ * For new applications, prefer to use CRC-32C instead.  See crc32c().
+ *
+ * Context: Any context
+ * Return: The new CRC value
+ */
 u32 crc32_le(u32 crc, const void *p, size_t len);
+
+/**
+ * crc32_be() - Compute most-significant-bit-first IEEE CRC-32
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
+ *
+ * crc32_be() is the same as crc32_le() except that crc32_be() computes the
+ * *most-significant-bit-first* variant of the CRC.  I.e., within each byte, the
+ * most significant bit is processed first (treated as highest order polynomial
+ * coefficient).  The same bit order is also used for the CRC value itself:
+ *
+ * - Polynomial: x^32 + x^26 + x^23 + x^22 + x^16 + x^12 + x^11 + x^10 + x^8 +
+ *		 x^7 + x^5 + x^4 + x^2 + x^1 + x^0
+ * - Bit order: Most-significant-bit-first
+ * - Polynomial in integer form: 0x04c11db7
+ *
+ * Context: Any context
+ * Return: The new CRC value
+ */
 u32 crc32_be(u32 crc, const void *p, size_t len);
+
+/**
+ * crc32c() - Compute CRC-32C
+ * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
+ *	 the previous CRC value if computing incrementally.
+ * @p: Pointer to the data buffer
+ * @len: Length of data in bytes
+ *
+ * This implements CRC-32C, i.e. the Castagnoli CRC.  This is the recommended
+ * CRC variant to use in new applications that want a 32-bit CRC.
+ *
+ * - Polynomial: x^32 + x^28 + x^27 + x^26 + x^25 + x^23 + x^22 + x^20 + x^19 +
+ *		 x^18 + x^14 + x^13 + x^11 + x^10 + x^9 + x^8 + x^6 + x^0
+ * - Bit order: Least-significant-bit-first
+ * - Polynomial in integer form: 0x82f63b78
+ *
+ * This does *not* invert the CRC at the beginning or end.  The caller is
+ * expected to do that if it needs to.  Inverting at both ends is recommended.
+ *
+ * Context: Any context
+ * Return: The new CRC value
+ */
 u32 crc32c(u32 crc, const void *p, size_t len);
 
 /*
diff --git a/include/linux/crc32poly.h b/include/linux/crc32poly.h
index 62c4b7790a28..ccab711295fa 100644
--- a/include/linux/crc32poly.h
+++ b/include/linux/crc32poly.h
@@ -2,19 +2,13 @@
 #ifndef _LINUX_CRC32_POLY_H
 #define _LINUX_CRC32_POLY_H
 
-/*
- * There are multiple 16-bit CRC polynomials in common use, but this is
- * *the* standard CRC-32 polynomial, first popularized by Ethernet.
- * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0
- */
+/* The polynomial used by crc32_le(), in integer form.  See crc32_le(). */
 #define CRC32_POLY_LE 0xedb88320
+
+/* The polynomial used by crc32_be(), in integer form.  See crc32_be(). */
 #define CRC32_POLY_BE 0x04c11db7
 
-/*
- * This is the CRC32c polynomial, as outlined by Castagnoli.
- * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+
- * x^8+x^6+x^0
- */
-#define CRC32C_POLY_LE 0x82F63B78
+/* The polynomial used by crc32c(), in integer form.  See crc32c(). */
+#define CRC32C_POLY_LE 0x82f63b78
 
 #endif /* _LINUX_CRC32_POLY_H */
-- 
cgit v1.2.3


From 0b5a58c078167f73d10711734cdc8ea592561ca9 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Thu, 19 Jun 2025 11:34:13 -0700
Subject: lib/crc: crc32: Change crc32() from macro to inline function and
 remove cast

There's no need for crc32() to be a macro.  Make it an inline function
instead.  Also, remove the cast of the data pointer to
'unsigned char const *', which is no longer necessary now that the type
used in the function prototype is 'const void *'.

Acked-by: Ard Biesheuvel <ardb@kernel.org>
Link: https://lore.kernel.org/r/20250619183414.100082-3-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 include/linux/crc32.h | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/crc32.h b/include/linux/crc32.h
index f9c173206d4d..da78b215ff2e 100644
--- a/include/linux/crc32.h
+++ b/include/linux/crc32.h
@@ -30,6 +30,12 @@
  */
 u32 crc32_le(u32 crc, const void *p, size_t len);
 
+/* This is just an alias for crc32_le(). */
+static inline u32 crc32(u32 crc, const void *p, size_t len)
+{
+	return crc32_le(crc, p, len);
+}
+
 /**
  * crc32_be() - Compute most-significant-bit-first IEEE CRC-32
  * @crc: Initial CRC value.  ~0 (recommended) or 0 for a new CRC computation, or
@@ -90,8 +96,6 @@ u32 crc32_optimizations(void);
 static inline u32 crc32_optimizations(void) { return 0; }
 #endif
 
-#define crc32(seed, data, length)  crc32_le(seed, (unsigned char const *)(data), length)
-
 /*
  * Helpers for hash table generation of ethernet nics:
  *
-- 
cgit v1.2.3


From a70e9f647f501e36a6a092888b1ea7386b7c5664 Mon Sep 17 00:00:00 2001
From: Jinjie Ruan <ruanjinjie@huawei.com>
Date: Tue, 24 Jun 2025 20:35:56 +0200
Subject: entry: Split generic entry into generic exception and syscall entry

Currently CONFIG_GENERIC_ENTRY enables both the generic exception
entry logic and the generic syscall entry logic, which are otherwise
loosely coupled.

Introduce separate config options for these so that architectures can
select the two independently. This will make it easier for
architectures to migrate to generic entry code.

Suggested-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Jinjie Ruan <ruanjinjie@huawei.com>
Signed-off-by: Linus Walleij <linus.walleij@linaro.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/20250213130007.1418890-2-ruanjinjie@huawei.com
Link: https://lore.kernel.org/all/20250624-generic-entry-split-v1-1-53d5ef4f94df@linaro.org

[Linus Walleij: rebase onto v6.16-rc1]
---
 MAINTAINERS                      |   1 +
 arch/Kconfig                     |   9 +
 include/linux/entry-common.h     | 382 +-------------------------------------
 include/linux/irq-entry-common.h | 389 +++++++++++++++++++++++++++++++++++++++
 kernel/entry/Makefile            |   3 +-
 kernel/entry/common.c            | 113 +-----------
 kernel/entry/syscall-common.c    | 112 +++++++++++
 kernel/sched/core.c              |   8 +-
 8 files changed, 519 insertions(+), 498 deletions(-)
 create mode 100644 include/linux/irq-entry-common.h
 create mode 100644 kernel/entry/syscall-common.c

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..e92292a0e480 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -10052,6 +10052,7 @@ S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git core/entry
 F:	include/linux/entry-common.h
 F:	include/linux/entry-kvm.h
+F:	include/linux/irq-entry-common.h
 F:	kernel/entry/
 
 GENERIC GPIO I2C DRIVER
diff --git a/arch/Kconfig b/arch/Kconfig
index a3308a220f86..9233fbfd8dd3 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -64,8 +64,17 @@ config HOTPLUG_PARALLEL
 	bool
 	select HOTPLUG_SPLIT_STARTUP
 
+config GENERIC_IRQ_ENTRY
+	bool
+
+config GENERIC_SYSCALL
+	bool
+	depends on GENERIC_IRQ_ENTRY
+
 config GENERIC_ENTRY
 	bool
+	select GENERIC_IRQ_ENTRY
+	select GENERIC_SYSCALL
 
 config KPROBES
 	bool "Kprobes"
diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index f94f3fdf15fc..7177436f0f9e 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -2,28 +2,16 @@
 #ifndef __LINUX_ENTRYCOMMON_H
 #define __LINUX_ENTRYCOMMON_H
 
-#include <linux/static_call_types.h>
+#include <linux/irq-entry-common.h>
 #include <linux/ptrace.h>
-#include <linux/syscalls.h>
 #include <linux/seccomp.h>
 #include <linux/sched.h>
-#include <linux/context_tracking.h>
 #include <linux/livepatch.h>
 #include <linux/resume_user_mode.h>
-#include <linux/tick.h>
-#include <linux/kmsan.h>
 
 #include <asm/entry-common.h>
 #include <asm/syscall.h>
 
-/*
- * Define dummy _TIF work flags if not defined by the architecture or for
- * disabled functionality.
- */
-#ifndef _TIF_PATCH_PENDING
-# define _TIF_PATCH_PENDING		(0)
-#endif
-
 #ifndef _TIF_UPROBE
 # define _TIF_UPROBE			(0)
 #endif
@@ -56,69 +44,6 @@
 				 SYSCALL_WORK_SYSCALL_EXIT_TRAP	|	\
 				 ARCH_SYSCALL_WORK_EXIT)
 
-/*
- * TIF flags handled in exit_to_user_mode_loop()
- */
-#ifndef ARCH_EXIT_TO_USER_MODE_WORK
-# define ARCH_EXIT_TO_USER_MODE_WORK		(0)
-#endif
-
-#define EXIT_TO_USER_MODE_WORK						\
-	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
-	 _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY |			\
-	 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |			\
-	 ARCH_EXIT_TO_USER_MODE_WORK)
-
-/**
- * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs
- * @regs:	Pointer to currents pt_regs
- *
- * Defaults to an empty implementation. Can be replaced by architecture
- * specific code.
- *
- * Invoked from syscall_enter_from_user_mode() in the non-instrumentable
- * section. Use __always_inline so the compiler cannot push it out of line
- * and make it instrumentable.
- */
-static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs);
-
-#ifndef arch_enter_from_user_mode
-static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
-#endif
-
-/**
- * enter_from_user_mode - Establish state when coming from user mode
- *
- * Syscall/interrupt entry disables interrupts, but user mode is traced as
- * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
- *
- * 1) Tell lockdep that interrupts are disabled
- * 2) Invoke context tracking if enabled to reactivate RCU
- * 3) Trace interrupts off state
- *
- * Invoked from architecture specific syscall entry code with interrupts
- * disabled. The calling code has to be non-instrumentable. When the
- * function returns all state is correct and interrupts are still
- * disabled. The subsequent functions can be instrumented.
- *
- * This is invoked when there is architecture specific functionality to be
- * done between establishing state and enabling interrupts. The caller must
- * enable interrupts before invoking syscall_enter_from_user_mode_work().
- */
-static __always_inline void enter_from_user_mode(struct pt_regs *regs)
-{
-	arch_enter_from_user_mode(regs);
-	lockdep_hardirqs_off(CALLER_ADDR0);
-
-	CT_WARN_ON(__ct_state() != CT_STATE_USER);
-	user_exit_irqoff();
-
-	instrumentation_begin();
-	kmsan_unpoison_entry_regs(regs);
-	trace_hardirqs_off_finish();
-	instrumentation_end();
-}
-
 /**
  * syscall_enter_from_user_mode_prepare - Establish state and enable interrupts
  * @regs:	Pointer to currents pt_regs
@@ -203,170 +128,6 @@ static __always_inline long syscall_enter_from_user_mode(struct pt_regs *regs, l
 	return ret;
 }
 
-/**
- * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
- * @ti_work:	Cached TIF flags gathered with interrupts disabled
- *
- * Defaults to local_irq_enable(). Can be supplied by architecture specific
- * code.
- */
-static inline void local_irq_enable_exit_to_user(unsigned long ti_work);
-
-#ifndef local_irq_enable_exit_to_user
-static inline void local_irq_enable_exit_to_user(unsigned long ti_work)
-{
-	local_irq_enable();
-}
-#endif
-
-/**
- * local_irq_disable_exit_to_user - Exit to user variant of local_irq_disable()
- *
- * Defaults to local_irq_disable(). Can be supplied by architecture specific
- * code.
- */
-static inline void local_irq_disable_exit_to_user(void);
-
-#ifndef local_irq_disable_exit_to_user
-static inline void local_irq_disable_exit_to_user(void)
-{
-	local_irq_disable();
-}
-#endif
-
-/**
- * arch_exit_to_user_mode_work - Architecture specific TIF work for exit
- *				 to user mode.
- * @regs:	Pointer to currents pt_regs
- * @ti_work:	Cached TIF flags gathered with interrupts disabled
- *
- * Invoked from exit_to_user_mode_loop() with interrupt enabled
- *
- * Defaults to NOOP. Can be supplied by architecture specific code.
- */
-static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
-					       unsigned long ti_work);
-
-#ifndef arch_exit_to_user_mode_work
-static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
-					       unsigned long ti_work)
-{
-}
-#endif
-
-/**
- * arch_exit_to_user_mode_prepare - Architecture specific preparation for
- *				    exit to user mode.
- * @regs:	Pointer to currents pt_regs
- * @ti_work:	Cached TIF flags gathered with interrupts disabled
- *
- * Invoked from exit_to_user_mode_prepare() with interrupt disabled as the last
- * function before return. Defaults to NOOP.
- */
-static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
-						  unsigned long ti_work);
-
-#ifndef arch_exit_to_user_mode_prepare
-static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
-						  unsigned long ti_work)
-{
-}
-#endif
-
-/**
- * arch_exit_to_user_mode - Architecture specific final work before
- *			    exit to user mode.
- *
- * Invoked from exit_to_user_mode() with interrupt disabled as the last
- * function before return. Defaults to NOOP.
- *
- * This needs to be __always_inline because it is non-instrumentable code
- * invoked after context tracking switched to user mode.
- *
- * An architecture implementation must not do anything complex, no locking
- * etc. The main purpose is for speculation mitigations.
- */
-static __always_inline void arch_exit_to_user_mode(void);
-
-#ifndef arch_exit_to_user_mode
-static __always_inline void arch_exit_to_user_mode(void) { }
-#endif
-
-/**
- * arch_do_signal_or_restart -  Architecture specific signal delivery function
- * @regs:	Pointer to currents pt_regs
- *
- * Invoked from exit_to_user_mode_loop().
- */
-void arch_do_signal_or_restart(struct pt_regs *regs);
-
-/**
- * exit_to_user_mode_loop - do any pending work before leaving to user space
- */
-unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
-				     unsigned long ti_work);
-
-/**
- * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
- * @regs:	Pointer to pt_regs on entry stack
- *
- * 1) check that interrupts are disabled
- * 2) call tick_nohz_user_enter_prepare()
- * 3) call exit_to_user_mode_loop() if any flags from
- *    EXIT_TO_USER_MODE_WORK are set
- * 4) check that interrupts are still disabled
- */
-static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
-{
-	unsigned long ti_work;
-
-	lockdep_assert_irqs_disabled();
-
-	/* Flush pending rcuog wakeup before the last need_resched() check */
-	tick_nohz_user_enter_prepare();
-
-	ti_work = read_thread_flags();
-	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
-		ti_work = exit_to_user_mode_loop(regs, ti_work);
-
-	arch_exit_to_user_mode_prepare(regs, ti_work);
-
-	/* Ensure that kernel state is sane for a return to userspace */
-	kmap_assert_nomap();
-	lockdep_assert_irqs_disabled();
-	lockdep_sys_exit();
-}
-
-/**
- * exit_to_user_mode - Fixup state when exiting to user mode
- *
- * Syscall/interrupt exit enables interrupts, but the kernel state is
- * interrupts disabled when this is invoked. Also tell RCU about it.
- *
- * 1) Trace interrupts on state
- * 2) Invoke context tracking if enabled to adjust RCU state
- * 3) Invoke architecture specific last minute exit code, e.g. speculation
- *    mitigations, etc.: arch_exit_to_user_mode()
- * 4) Tell lockdep that interrupts are enabled
- *
- * Invoked from architecture specific code when syscall_exit_to_user_mode()
- * is not suitable as the last step before returning to userspace. Must be
- * invoked with interrupts disabled and the caller must be
- * non-instrumentable.
- * The caller has to invoke syscall_exit_to_user_mode_work() before this.
- */
-static __always_inline void exit_to_user_mode(void)
-{
-	instrumentation_begin();
-	trace_hardirqs_on_prepare();
-	lockdep_hardirqs_on_prepare();
-	instrumentation_end();
-
-	user_enter_irqoff();
-	arch_exit_to_user_mode();
-	lockdep_hardirqs_on(CALLER_ADDR0);
-}
-
 /**
  * syscall_exit_work - Handle work before returning to user mode
  * @regs:	Pointer to current pt_regs
@@ -451,145 +212,4 @@ static __always_inline void syscall_exit_to_user_mode(struct pt_regs *regs)
 	exit_to_user_mode();
 }
 
-/**
- * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
- * @regs:	Pointer to currents pt_regs
- *
- * Invoked from architecture specific entry code with interrupts disabled.
- * Can only be called when the interrupt entry came from user mode. The
- * calling code must be non-instrumentable.  When the function returns all
- * state is correct and the subsequent functions can be instrumented.
- *
- * The function establishes state (lockdep, RCU (context tracking), tracing)
- */
-void irqentry_enter_from_user_mode(struct pt_regs *regs);
-
-/**
- * irqentry_exit_to_user_mode - Interrupt exit work
- * @regs:	Pointer to current's pt_regs
- *
- * Invoked with interrupts disabled and fully valid regs. Returns with all
- * work handled, interrupts disabled such that the caller can immediately
- * switch to user mode. Called from architecture specific interrupt
- * handling code.
- *
- * The call order is #2 and #3 as described in syscall_exit_to_user_mode().
- * Interrupt exit is not invoking #1 which is the syscall specific one time
- * work.
- */
-void irqentry_exit_to_user_mode(struct pt_regs *regs);
-
-#ifndef irqentry_state
-/**
- * struct irqentry_state - Opaque object for exception state storage
- * @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the
- *            exit path has to invoke ct_irq_exit().
- * @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that
- *           lockdep state is restored correctly on exit from nmi.
- *
- * This opaque object is filled in by the irqentry_*_enter() functions and
- * must be passed back into the corresponding irqentry_*_exit() functions
- * when the exception is complete.
- *
- * Callers of irqentry_*_[enter|exit]() must consider this structure opaque
- * and all members private.  Descriptions of the members are provided to aid in
- * the maintenance of the irqentry_*() functions.
- */
-typedef struct irqentry_state {
-	union {
-		bool	exit_rcu;
-		bool	lockdep;
-	};
-} irqentry_state_t;
-#endif
-
-/**
- * irqentry_enter - Handle state tracking on ordinary interrupt entries
- * @regs:	Pointer to pt_regs of interrupted context
- *
- * Invokes:
- *  - lockdep irqflag state tracking as low level ASM entry disabled
- *    interrupts.
- *
- *  - Context tracking if the exception hit user mode.
- *
- *  - The hardirq tracer to keep the state consistent as low level ASM
- *    entry disabled interrupts.
- *
- * As a precondition, this requires that the entry came from user mode,
- * idle, or a kernel context in which RCU is watching.
- *
- * For kernel mode entries RCU handling is done conditional. If RCU is
- * watching then the only RCU requirement is to check whether the tick has
- * to be restarted. If RCU is not watching then ct_irq_enter() has to be
- * invoked on entry and ct_irq_exit() on exit.
- *
- * Avoiding the ct_irq_enter/exit() calls is an optimization but also
- * solves the problem of kernel mode pagefaults which can schedule, which
- * is not possible after invoking ct_irq_enter() without undoing it.
- *
- * For user mode entries irqentry_enter_from_user_mode() is invoked to
- * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
- * would not be possible.
- *
- * Returns: An opaque object that must be passed to idtentry_exit()
- */
-irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
-
-/**
- * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt
- *
- * Conditional reschedule with additional sanity checks.
- */
-void raw_irqentry_exit_cond_resched(void);
-#ifdef CONFIG_PREEMPT_DYNAMIC
-#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-#define irqentry_exit_cond_resched_dynamic_enabled	raw_irqentry_exit_cond_resched
-#define irqentry_exit_cond_resched_dynamic_disabled	NULL
-DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
-#define irqentry_exit_cond_resched()	static_call(irqentry_exit_cond_resched)()
-#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
-void dynamic_irqentry_exit_cond_resched(void);
-#define irqentry_exit_cond_resched()	dynamic_irqentry_exit_cond_resched()
-#endif
-#else /* CONFIG_PREEMPT_DYNAMIC */
-#define irqentry_exit_cond_resched()	raw_irqentry_exit_cond_resched()
-#endif /* CONFIG_PREEMPT_DYNAMIC */
-
-/**
- * irqentry_exit - Handle return from exception that used irqentry_enter()
- * @regs:	Pointer to pt_regs (exception entry regs)
- * @state:	Return value from matching call to irqentry_enter()
- *
- * Depending on the return target (kernel/user) this runs the necessary
- * preemption and work checks if possible and required and returns to
- * the caller with interrupts disabled and no further work pending.
- *
- * This is the last action before returning to the low level ASM code which
- * just needs to return to the appropriate context.
- *
- * Counterpart to irqentry_enter().
- */
-void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state);
-
-/**
- * irqentry_nmi_enter - Handle NMI entry
- * @regs:	Pointer to currents pt_regs
- *
- * Similar to irqentry_enter() but taking care of the NMI constraints.
- */
-irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
-
-/**
- * irqentry_nmi_exit - Handle return from NMI handling
- * @regs:	Pointer to pt_regs (NMI entry regs)
- * @irq_state:	Return value from matching call to irqentry_nmi_enter()
- *
- * Last action before returning to the low level assembly code.
- *
- * Counterpart to irqentry_nmi_enter().
- */
-void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
-
 #endif
diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
new file mode 100644
index 000000000000..8af374331900
--- /dev/null
+++ b/include/linux/irq-entry-common.h
@@ -0,0 +1,389 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_IRQENTRYCOMMON_H
+#define __LINUX_IRQENTRYCOMMON_H
+
+#include <linux/static_call_types.h>
+#include <linux/syscalls.h>
+#include <linux/context_tracking.h>
+#include <linux/tick.h>
+#include <linux/kmsan.h>
+
+#include <asm/entry-common.h>
+
+/*
+ * Define dummy _TIF work flags if not defined by the architecture or for
+ * disabled functionality.
+ */
+#ifndef _TIF_PATCH_PENDING
+# define _TIF_PATCH_PENDING		(0)
+#endif
+
+/*
+ * TIF flags handled in exit_to_user_mode_loop()
+ */
+#ifndef ARCH_EXIT_TO_USER_MODE_WORK
+# define ARCH_EXIT_TO_USER_MODE_WORK		(0)
+#endif
+
+#define EXIT_TO_USER_MODE_WORK						\
+	(_TIF_SIGPENDING | _TIF_NOTIFY_RESUME | _TIF_UPROBE |		\
+	 _TIF_NEED_RESCHED | _TIF_NEED_RESCHED_LAZY |			\
+	 _TIF_PATCH_PENDING | _TIF_NOTIFY_SIGNAL |			\
+	 ARCH_EXIT_TO_USER_MODE_WORK)
+
+/**
+ * arch_enter_from_user_mode - Architecture specific sanity check for user mode regs
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Defaults to an empty implementation. Can be replaced by architecture
+ * specific code.
+ *
+ * Invoked from syscall_enter_from_user_mode() in the non-instrumentable
+ * section. Use __always_inline so the compiler cannot push it out of line
+ * and make it instrumentable.
+ */
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs);
+
+#ifndef arch_enter_from_user_mode
+static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
+#endif
+
+/**
+ * enter_from_user_mode - Establish state when coming from user mode
+ *
+ * Syscall/interrupt entry disables interrupts, but user mode is traced as
+ * interrupts enabled. Also with NO_HZ_FULL RCU might be idle.
+ *
+ * 1) Tell lockdep that interrupts are disabled
+ * 2) Invoke context tracking if enabled to reactivate RCU
+ * 3) Trace interrupts off state
+ *
+ * Invoked from architecture specific syscall entry code with interrupts
+ * disabled. The calling code has to be non-instrumentable. When the
+ * function returns all state is correct and interrupts are still
+ * disabled. The subsequent functions can be instrumented.
+ *
+ * This is invoked when there is architecture specific functionality to be
+ * done between establishing state and enabling interrupts. The caller must
+ * enable interrupts before invoking syscall_enter_from_user_mode_work().
+ */
+static __always_inline void enter_from_user_mode(struct pt_regs *regs)
+{
+	arch_enter_from_user_mode(regs);
+	lockdep_hardirqs_off(CALLER_ADDR0);
+
+	CT_WARN_ON(__ct_state() != CT_STATE_USER);
+	user_exit_irqoff();
+
+	instrumentation_begin();
+	kmsan_unpoison_entry_regs(regs);
+	trace_hardirqs_off_finish();
+	instrumentation_end();
+}
+
+/**
+ * local_irq_enable_exit_to_user - Exit to user variant of local_irq_enable()
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Defaults to local_irq_enable(). Can be supplied by architecture specific
+ * code.
+ */
+static inline void local_irq_enable_exit_to_user(unsigned long ti_work);
+
+#ifndef local_irq_enable_exit_to_user
+static inline void local_irq_enable_exit_to_user(unsigned long ti_work)
+{
+	local_irq_enable();
+}
+#endif
+
+/**
+ * local_irq_disable_exit_to_user - Exit to user variant of local_irq_disable()
+ *
+ * Defaults to local_irq_disable(). Can be supplied by architecture specific
+ * code.
+ */
+static inline void local_irq_disable_exit_to_user(void);
+
+#ifndef local_irq_disable_exit_to_user
+static inline void local_irq_disable_exit_to_user(void)
+{
+	local_irq_disable();
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode_work - Architecture specific TIF work for exit
+ *				 to user mode.
+ * @regs:	Pointer to currents pt_regs
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Invoked from exit_to_user_mode_loop() with interrupt enabled
+ *
+ * Defaults to NOOP. Can be supplied by architecture specific code.
+ */
+static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+					       unsigned long ti_work);
+
+#ifndef arch_exit_to_user_mode_work
+static inline void arch_exit_to_user_mode_work(struct pt_regs *regs,
+					       unsigned long ti_work)
+{
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode_prepare - Architecture specific preparation for
+ *				    exit to user mode.
+ * @regs:	Pointer to currents pt_regs
+ * @ti_work:	Cached TIF flags gathered with interrupts disabled
+ *
+ * Invoked from exit_to_user_mode_prepare() with interrupt disabled as the last
+ * function before return. Defaults to NOOP.
+ */
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work);
+
+#ifndef arch_exit_to_user_mode_prepare
+static inline void arch_exit_to_user_mode_prepare(struct pt_regs *regs,
+						  unsigned long ti_work)
+{
+}
+#endif
+
+/**
+ * arch_exit_to_user_mode - Architecture specific final work before
+ *			    exit to user mode.
+ *
+ * Invoked from exit_to_user_mode() with interrupt disabled as the last
+ * function before return. Defaults to NOOP.
+ *
+ * This needs to be __always_inline because it is non-instrumentable code
+ * invoked after context tracking switched to user mode.
+ *
+ * An architecture implementation must not do anything complex, no locking
+ * etc. The main purpose is for speculation mitigations.
+ */
+static __always_inline void arch_exit_to_user_mode(void);
+
+#ifndef arch_exit_to_user_mode
+static __always_inline void arch_exit_to_user_mode(void) { }
+#endif
+
+/**
+ * arch_do_signal_or_restart -  Architecture specific signal delivery function
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Invoked from exit_to_user_mode_loop().
+ */
+void arch_do_signal_or_restart(struct pt_regs *regs);
+
+/**
+ * exit_to_user_mode_loop - do any pending work before leaving to user space
+ */
+unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
+				     unsigned long ti_work);
+
+/**
+ * exit_to_user_mode_prepare - call exit_to_user_mode_loop() if required
+ * @regs:	Pointer to pt_regs on entry stack
+ *
+ * 1) check that interrupts are disabled
+ * 2) call tick_nohz_user_enter_prepare()
+ * 3) call exit_to_user_mode_loop() if any flags from
+ *    EXIT_TO_USER_MODE_WORK are set
+ * 4) check that interrupts are still disabled
+ */
+static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
+{
+	unsigned long ti_work;
+
+	lockdep_assert_irqs_disabled();
+
+	/* Flush pending rcuog wakeup before the last need_resched() check */
+	tick_nohz_user_enter_prepare();
+
+	ti_work = read_thread_flags();
+	if (unlikely(ti_work & EXIT_TO_USER_MODE_WORK))
+		ti_work = exit_to_user_mode_loop(regs, ti_work);
+
+	arch_exit_to_user_mode_prepare(regs, ti_work);
+
+	/* Ensure that kernel state is sane for a return to userspace */
+	kmap_assert_nomap();
+	lockdep_assert_irqs_disabled();
+	lockdep_sys_exit();
+}
+
+/**
+ * exit_to_user_mode - Fixup state when exiting to user mode
+ *
+ * Syscall/interrupt exit enables interrupts, but the kernel state is
+ * interrupts disabled when this is invoked. Also tell RCU about it.
+ *
+ * 1) Trace interrupts on state
+ * 2) Invoke context tracking if enabled to adjust RCU state
+ * 3) Invoke architecture specific last minute exit code, e.g. speculation
+ *    mitigations, etc.: arch_exit_to_user_mode()
+ * 4) Tell lockdep that interrupts are enabled
+ *
+ * Invoked from architecture specific code when syscall_exit_to_user_mode()
+ * is not suitable as the last step before returning to userspace. Must be
+ * invoked with interrupts disabled and the caller must be
+ * non-instrumentable.
+ * The caller has to invoke syscall_exit_to_user_mode_work() before this.
+ */
+static __always_inline void exit_to_user_mode(void)
+{
+	instrumentation_begin();
+	trace_hardirqs_on_prepare();
+	lockdep_hardirqs_on_prepare();
+	instrumentation_end();
+
+	user_enter_irqoff();
+	arch_exit_to_user_mode();
+	lockdep_hardirqs_on(CALLER_ADDR0);
+}
+
+/**
+ * irqentry_enter_from_user_mode - Establish state before invoking the irq handler
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Invoked from architecture specific entry code with interrupts disabled.
+ * Can only be called when the interrupt entry came from user mode. The
+ * calling code must be non-instrumentable.  When the function returns all
+ * state is correct and the subsequent functions can be instrumented.
+ *
+ * The function establishes state (lockdep, RCU (context tracking), tracing)
+ */
+void irqentry_enter_from_user_mode(struct pt_regs *regs);
+
+/**
+ * irqentry_exit_to_user_mode - Interrupt exit work
+ * @regs:	Pointer to current's pt_regs
+ *
+ * Invoked with interrupts disabled and fully valid regs. Returns with all
+ * work handled, interrupts disabled such that the caller can immediately
+ * switch to user mode. Called from architecture specific interrupt
+ * handling code.
+ *
+ * The call order is #2 and #3 as described in syscall_exit_to_user_mode().
+ * Interrupt exit is not invoking #1 which is the syscall specific one time
+ * work.
+ */
+void irqentry_exit_to_user_mode(struct pt_regs *regs);
+
+#ifndef irqentry_state
+/**
+ * struct irqentry_state - Opaque object for exception state storage
+ * @exit_rcu: Used exclusively in the irqentry_*() calls; signals whether the
+ *            exit path has to invoke ct_irq_exit().
+ * @lockdep: Used exclusively in the irqentry_nmi_*() calls; ensures that
+ *           lockdep state is restored correctly on exit from nmi.
+ *
+ * This opaque object is filled in by the irqentry_*_enter() functions and
+ * must be passed back into the corresponding irqentry_*_exit() functions
+ * when the exception is complete.
+ *
+ * Callers of irqentry_*_[enter|exit]() must consider this structure opaque
+ * and all members private.  Descriptions of the members are provided to aid in
+ * the maintenance of the irqentry_*() functions.
+ */
+typedef struct irqentry_state {
+	union {
+		bool	exit_rcu;
+		bool	lockdep;
+	};
+} irqentry_state_t;
+#endif
+
+/**
+ * irqentry_enter - Handle state tracking on ordinary interrupt entries
+ * @regs:	Pointer to pt_regs of interrupted context
+ *
+ * Invokes:
+ *  - lockdep irqflag state tracking as low level ASM entry disabled
+ *    interrupts.
+ *
+ *  - Context tracking if the exception hit user mode.
+ *
+ *  - The hardirq tracer to keep the state consistent as low level ASM
+ *    entry disabled interrupts.
+ *
+ * As a precondition, this requires that the entry came from user mode,
+ * idle, or a kernel context in which RCU is watching.
+ *
+ * For kernel mode entries RCU handling is done conditional. If RCU is
+ * watching then the only RCU requirement is to check whether the tick has
+ * to be restarted. If RCU is not watching then ct_irq_enter() has to be
+ * invoked on entry and ct_irq_exit() on exit.
+ *
+ * Avoiding the ct_irq_enter/exit() calls is an optimization but also
+ * solves the problem of kernel mode pagefaults which can schedule, which
+ * is not possible after invoking ct_irq_enter() without undoing it.
+ *
+ * For user mode entries irqentry_enter_from_user_mode() is invoked to
+ * establish the proper context for NOHZ_FULL. Otherwise scheduling on exit
+ * would not be possible.
+ *
+ * Returns: An opaque object that must be passed to idtentry_exit()
+ */
+irqentry_state_t noinstr irqentry_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_exit_cond_resched - Conditionally reschedule on return from interrupt
+ *
+ * Conditional reschedule with additional sanity checks.
+ */
+void raw_irqentry_exit_cond_resched(void);
+#ifdef CONFIG_PREEMPT_DYNAMIC
+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
+#define irqentry_exit_cond_resched_dynamic_enabled	raw_irqentry_exit_cond_resched
+#define irqentry_exit_cond_resched_dynamic_disabled	NULL
+DECLARE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
+#define irqentry_exit_cond_resched()	static_call(irqentry_exit_cond_resched)()
+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
+DECLARE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
+void dynamic_irqentry_exit_cond_resched(void);
+#define irqentry_exit_cond_resched()	dynamic_irqentry_exit_cond_resched()
+#endif
+#else /* CONFIG_PREEMPT_DYNAMIC */
+#define irqentry_exit_cond_resched()	raw_irqentry_exit_cond_resched()
+#endif /* CONFIG_PREEMPT_DYNAMIC */
+
+/**
+ * irqentry_exit - Handle return from exception that used irqentry_enter()
+ * @regs:	Pointer to pt_regs (exception entry regs)
+ * @state:	Return value from matching call to irqentry_enter()
+ *
+ * Depending on the return target (kernel/user) this runs the necessary
+ * preemption and work checks if possible and required and returns to
+ * the caller with interrupts disabled and no further work pending.
+ *
+ * This is the last action before returning to the low level ASM code which
+ * just needs to return to the appropriate context.
+ *
+ * Counterpart to irqentry_enter().
+ */
+void noinstr irqentry_exit(struct pt_regs *regs, irqentry_state_t state);
+
+/**
+ * irqentry_nmi_enter - Handle NMI entry
+ * @regs:	Pointer to currents pt_regs
+ *
+ * Similar to irqentry_enter() but taking care of the NMI constraints.
+ */
+irqentry_state_t noinstr irqentry_nmi_enter(struct pt_regs *regs);
+
+/**
+ * irqentry_nmi_exit - Handle return from NMI handling
+ * @regs:	Pointer to pt_regs (NMI entry regs)
+ * @irq_state:	Return value from matching call to irqentry_nmi_enter()
+ *
+ * Last action before returning to the low level assembly code.
+ *
+ * Counterpart to irqentry_nmi_enter().
+ */
+void noinstr irqentry_nmi_exit(struct pt_regs *regs, irqentry_state_t irq_state);
+
+#endif
diff --git a/kernel/entry/Makefile b/kernel/entry/Makefile
index d4b8bd0af79b..77fcd83dd663 100644
--- a/kernel/entry/Makefile
+++ b/kernel/entry/Makefile
@@ -12,5 +12,6 @@ ccflags-$(CONFIG_TRACE_BRANCH_PROFILING) += -DDISABLE_BRANCH_PROFILING
 CFLAGS_REMOVE_common.o	 = -fstack-protector -fstack-protector-strong
 CFLAGS_common.o		+= -fno-stack-protector
 
-obj-$(CONFIG_GENERIC_ENTRY) 		+= common.o syscall_user_dispatch.o
+obj-$(CONFIG_GENERIC_IRQ_ENTRY) 	+= common.o
+obj-$(CONFIG_GENERIC_SYSCALL) 		+= syscall-common.o syscall_user_dispatch.o
 obj-$(CONFIG_KVM_XFER_TO_GUEST_WORK)	+= kvm.o
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index a8dd1f27417c..b82032777310 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -1,84 +1,13 @@
 // SPDX-License-Identifier: GPL-2.0
 
-#include <linux/context_tracking.h>
-#include <linux/entry-common.h>
+#include <linux/irq-entry-common.h>
 #include <linux/resume_user_mode.h>
 #include <linux/highmem.h>
 #include <linux/jump_label.h>
 #include <linux/kmsan.h>
 #include <linux/livepatch.h>
-#include <linux/audit.h>
 #include <linux/tick.h>
 
-#include "common.h"
-
-#define CREATE_TRACE_POINTS
-#include <trace/events/syscalls.h>
-
-static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
-{
-	if (unlikely(audit_context())) {
-		unsigned long args[6];
-
-		syscall_get_arguments(current, regs, args);
-		audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
-	}
-}
-
-long syscall_trace_enter(struct pt_regs *regs, long syscall,
-				unsigned long work)
-{
-	long ret = 0;
-
-	/*
-	 * Handle Syscall User Dispatch.  This must comes first, since
-	 * the ABI here can be something that doesn't make sense for
-	 * other syscall_work features.
-	 */
-	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
-		if (syscall_user_dispatch(regs))
-			return -1L;
-	}
-
-	/* Handle ptrace */
-	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
-		ret = ptrace_report_syscall_entry(regs);
-		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
-			return -1L;
-	}
-
-	/* Do seccomp after ptrace, to catch any tracer changes. */
-	if (work & SYSCALL_WORK_SECCOMP) {
-		ret = __secure_computing();
-		if (ret == -1L)
-			return ret;
-	}
-
-	/* Either of the above might have changed the syscall number */
-	syscall = syscall_get_nr(current, regs);
-
-	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
-		trace_sys_enter(regs, syscall);
-		/*
-		 * Probes or BPF hooks in the tracepoint may have changed the
-		 * system call number as well.
-		 */
-		syscall = syscall_get_nr(current, regs);
-	}
-
-	syscall_enter_audit(regs, syscall);
-
-	return ret ? : syscall;
-}
-
-noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
-{
-	enter_from_user_mode(regs);
-	instrumentation_begin();
-	local_irq_enable();
-	instrumentation_end();
-}
-
 /* Workaround to allow gradual conversion of architecture code */
 void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
 
@@ -133,46 +62,6 @@ __always_inline unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
 	return ti_work;
 }
 
-/*
- * If SYSCALL_EMU is set, then the only reason to report is when
- * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
- * instruction has been already reported in syscall_enter_from_user_mode().
- */
-static inline bool report_single_step(unsigned long work)
-{
-	if (work & SYSCALL_WORK_SYSCALL_EMU)
-		return false;
-
-	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
-}
-
-void syscall_exit_work(struct pt_regs *regs, unsigned long work)
-{
-	bool step;
-
-	/*
-	 * If the syscall was rolled back due to syscall user dispatching,
-	 * then the tracers below are not invoked for the same reason as
-	 * the entry side was not invoked in syscall_trace_enter(): The ABI
-	 * of these syscalls is unknown.
-	 */
-	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
-		if (unlikely(current->syscall_dispatch.on_dispatch)) {
-			current->syscall_dispatch.on_dispatch = false;
-			return;
-		}
-	}
-
-	audit_syscall_exit(regs);
-
-	if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
-		trace_sys_exit(regs, syscall_get_return_value(current, regs));
-
-	step = report_single_step(work);
-	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
-		ptrace_report_syscall_exit(regs, step);
-}
-
 noinstr void irqentry_enter_from_user_mode(struct pt_regs *regs)
 {
 	enter_from_user_mode(regs);
diff --git a/kernel/entry/syscall-common.c b/kernel/entry/syscall-common.c
new file mode 100644
index 000000000000..66e6ba7fa80c
--- /dev/null
+++ b/kernel/entry/syscall-common.c
@@ -0,0 +1,112 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/audit.h>
+#include <linux/entry-common.h>
+#include "common.h"
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/syscalls.h>
+
+static inline void syscall_enter_audit(struct pt_regs *regs, long syscall)
+{
+	if (unlikely(audit_context())) {
+		unsigned long args[6];
+
+		syscall_get_arguments(current, regs, args);
+		audit_syscall_entry(syscall, args[0], args[1], args[2], args[3]);
+	}
+}
+
+long syscall_trace_enter(struct pt_regs *regs, long syscall,
+				unsigned long work)
+{
+	long ret = 0;
+
+	/*
+	 * Handle Syscall User Dispatch.  This must comes first, since
+	 * the ABI here can be something that doesn't make sense for
+	 * other syscall_work features.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (syscall_user_dispatch(regs))
+			return -1L;
+	}
+
+	/* Handle ptrace */
+	if (work & (SYSCALL_WORK_SYSCALL_TRACE | SYSCALL_WORK_SYSCALL_EMU)) {
+		ret = ptrace_report_syscall_entry(regs);
+		if (ret || (work & SYSCALL_WORK_SYSCALL_EMU))
+			return -1L;
+	}
+
+	/* Do seccomp after ptrace, to catch any tracer changes. */
+	if (work & SYSCALL_WORK_SECCOMP) {
+		ret = __secure_computing();
+		if (ret == -1L)
+			return ret;
+	}
+
+	/* Either of the above might have changed the syscall number */
+	syscall = syscall_get_nr(current, regs);
+
+	if (unlikely(work & SYSCALL_WORK_SYSCALL_TRACEPOINT)) {
+		trace_sys_enter(regs, syscall);
+		/*
+		 * Probes or BPF hooks in the tracepoint may have changed the
+		 * system call number as well.
+		 */
+		syscall = syscall_get_nr(current, regs);
+	}
+
+	syscall_enter_audit(regs, syscall);
+
+	return ret ? : syscall;
+}
+
+noinstr void syscall_enter_from_user_mode_prepare(struct pt_regs *regs)
+{
+	enter_from_user_mode(regs);
+	instrumentation_begin();
+	local_irq_enable();
+	instrumentation_end();
+}
+
+/*
+ * If SYSCALL_EMU is set, then the only reason to report is when
+ * SINGLESTEP is set (i.e. PTRACE_SYSEMU_SINGLESTEP).  This syscall
+ * instruction has been already reported in syscall_enter_from_user_mode().
+ */
+static inline bool report_single_step(unsigned long work)
+{
+	if (work & SYSCALL_WORK_SYSCALL_EMU)
+		return false;
+
+	return work & SYSCALL_WORK_SYSCALL_EXIT_TRAP;
+}
+
+void syscall_exit_work(struct pt_regs *regs, unsigned long work)
+{
+	bool step;
+
+	/*
+	 * If the syscall was rolled back due to syscall user dispatching,
+	 * then the tracers below are not invoked for the same reason as
+	 * the entry side was not invoked in syscall_trace_enter(): The ABI
+	 * of these syscalls is unknown.
+	 */
+	if (work & SYSCALL_WORK_SYSCALL_USER_DISPATCH) {
+		if (unlikely(current->syscall_dispatch.on_dispatch)) {
+			current->syscall_dispatch.on_dispatch = false;
+			return;
+		}
+	}
+
+	audit_syscall_exit(regs);
+
+	if (work & SYSCALL_WORK_SYSCALL_TRACEPOINT)
+		trace_sys_exit(regs, syscall_get_return_value(current, regs));
+
+	step = report_single_step(work);
+	if (step || work & SYSCALL_WORK_SYSCALL_TRACE)
+		ptrace_report_syscall_exit(regs, step);
+}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index dce50fa57471..e6269e7954f3 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -69,8 +69,8 @@
 #include <linux/livepatch_sched.h>
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
-# ifdef CONFIG_GENERIC_ENTRY
-#  include <linux/entry-common.h>
+# ifdef CONFIG_GENERIC_IRQ_ENTRY
+#  include <linux/irq-entry-common.h>
 # endif
 #endif
 
@@ -7427,8 +7427,8 @@ EXPORT_SYMBOL(__cond_resched_rwlock_write);
 
 #ifdef CONFIG_PREEMPT_DYNAMIC
 
-#ifdef CONFIG_GENERIC_ENTRY
-#include <linux/entry-common.h>
+#ifdef CONFIG_GENERIC_IRQ_ENTRY
+#include <linux/irq-entry-common.h>
 #endif
 
 /*
-- 
cgit v1.2.3


From 9b8b84879d4adc506b0d3944e20b28d9f3f6994b Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 18 Jun 2025 15:00:45 +0900
Subject: block: Increase BLK_DEF_MAX_SECTORS_CAP

Back in 2015, commit d2be537c3ba3 ("block: bump BLK_DEF_MAX_SECTORS to
2560") increased the default maximum size of a block device I/O to 2560
sectors (1280 KiB) to "accommodate a 10-data-disk stripe write with
chunk size 128k". This choice is rather arbitrary and since then,
improvements to the block layer have software RAID drivers correctly
advertize their stripe width through chunk_sectors and abuses of
BLK_DEF_MAX_SECTORS_CAP by drivers (to set the HW limit rather than the
default user controlled maximum I/O size) have been fixed.

Since many block devices can benefit from a larger value of
BLK_DEF_MAX_SECTORS_CAP, and in particular HDDs, increase this value to
be 4MiB, or 8192 sectors.

And given that BLK_DEF_MAX_SECTORS_CAP is only used in the block layer
and should not be used by drivers directly, move this macro definition
to the block layer internal header file block/blk.h.

Suggested-by: Martin K . Petersen <martin.petersen@oracle.com>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20250618060045.37593-1-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk.h            | 9 +++++++++
 include/linux/blkdev.h | 9 ---------
 2 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk.h b/block/blk.h
index 37ec459fe656..1141b343d0b5 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -13,6 +13,15 @@
 
 struct elevator_type;
 
+/*
+ * Default upper limit for the software max_sectors limit used for regular I/Os.
+ * This can be increased through sysfs.
+ *
+ * This should not be confused with the max_hw_sector limit that is entirely
+ * controlled by the block device driver, usually based on hardware limits.
+ */
+#define BLK_DEF_MAX_SECTORS_CAP	(SZ_4M >> SECTOR_SHIFT)
+
 #define	BLK_DEV_MAX_SECTORS	(LLONG_MAX >> 9)
 #define	BLK_MIN_SEGMENT_SIZE	4096
 
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a59880c809c7..5c626d23cbb2 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -1220,15 +1220,6 @@ enum blk_default_limits {
 	BLK_SEG_BOUNDARY_MASK	= 0xFFFFFFFFUL,
 };
 
-/*
- * Default upper limit for the software max_sectors limit used for
- * regular file system I/O.  This can be increased through sysfs.
- *
- * Not to be confused with the max_hw_sector limit that is entirely
- * controlled by the driver, usually based on hardware limits.
- */
-#define BLK_DEF_MAX_SECTORS_CAP	2560u
-
 static inline struct queue_limits *bdev_limits(struct block_device *bdev)
 {
 	return &bdev_get_queue(bdev)->limits;
-- 
cgit v1.2.3


From 3f66ccbaaef3a0c5bd844eab04e3207b4061c546 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 25 Jun 2025 18:33:23 +0900
Subject: block: Make REQ_OP_ZONE_FINISH a write operation

REQ_OP_ZONE_FINISH is defined as "12", which makes
op_is_write(REQ_OP_ZONE_FINISH) return false, despite the fact that a
zone finish operation is an operation that modifies a zone (transition
it to full) and so should be considered as a write operation (albeit
one that does not transfer any data to the device).

Fix this by redefining REQ_OP_ZONE_FINISH to be an odd number (13), and
redefine REQ_OP_ZONE_RESET and REQ_OP_ZONE_RESET_ALL using sequential
odd numbers from that new value.

Fixes: 6c1b1da58f8c ("block: add zone open, close and finish operations")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250625093327.548866-2-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blk_types.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 3d1577f07c1c..930daff207df 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -350,11 +350,11 @@ enum req_op {
 	/* Close a zone */
 	REQ_OP_ZONE_CLOSE	= (__force blk_opf_t)11,
 	/* Transition a zone to full */
-	REQ_OP_ZONE_FINISH	= (__force blk_opf_t)12,
+	REQ_OP_ZONE_FINISH	= (__force blk_opf_t)13,
 	/* reset a zone write pointer */
-	REQ_OP_ZONE_RESET	= (__force blk_opf_t)13,
+	REQ_OP_ZONE_RESET	= (__force blk_opf_t)15,
 	/* reset all the zone present on the device */
-	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)15,
+	REQ_OP_ZONE_RESET_ALL	= (__force blk_opf_t)17,
 
 	/* Driver private requests */
 	REQ_OP_DRV_IN		= (__force blk_opf_t)34,
-- 
cgit v1.2.3


From f70291411ba20d50008db90a6f0731efac27872c Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 25 Jun 2025 18:33:24 +0900
Subject: block: Introduce bio_needs_zone_write_plugging()

In preparation for fixing device mapper zone write handling, introduce
the inline helper function bio_needs_zone_write_plugging() to test if a
BIO requires handling through zone write plugging using the function
blk_zone_plug_bio(). This function returns true for any write
(op_is_write(bio) == true) operation directed at a zoned block device
using zone write plugging, that is, a block device with a disk that has
a zone write plug hash table.

This helper allows simplifying the check on entry to blk_zone_plug_bio()
and used in to protect calls to it for blk-mq devices and DM devices.

Fixes: f211268ed1f9 ("dm: Use the block layer zone append emulation")
Cc: stable@vger.kernel.org
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250625093327.548866-3-dlemoal@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq.c         |  6 ++++--
 block/blk-zoned.c      | 20 +-----------------
 drivers/md/dm.c        |  4 +++-
 include/linux/blkdev.h | 55 ++++++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 63 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq.c b/block/blk-mq.c
index 4806b867e37d..0c61492724d2 100644
--- a/block/blk-mq.c
+++ b/block/blk-mq.c
@@ -3169,8 +3169,10 @@ void blk_mq_submit_bio(struct bio *bio)
 	if (blk_mq_attempt_bio_merge(q, bio, nr_segs))
 		goto queue_exit;
 
-	if (blk_queue_is_zoned(q) && blk_zone_plug_bio(bio, nr_segs))
-		goto queue_exit;
+	if (bio_needs_zone_write_plugging(bio)) {
+		if (blk_zone_plug_bio(bio, nr_segs))
+			goto queue_exit;
+	}
 
 new_request:
 	if (rq) {
diff --git a/block/blk-zoned.c b/block/blk-zoned.c
index 351d659280e1..efe71b1a1da1 100644
--- a/block/blk-zoned.c
+++ b/block/blk-zoned.c
@@ -1116,25 +1116,7 @@ bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
 {
 	struct block_device *bdev = bio->bi_bdev;
 
-	if (!bdev->bd_disk->zone_wplugs_hash)
-		return false;
-
-	/*
-	 * If the BIO already has the plugging flag set, then it was already
-	 * handled through this path and this is a submission from the zone
-	 * plug bio submit work.
-	 */
-	if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING))
-		return false;
-
-	/*
-	 * We do not need to do anything special for empty flush BIOs, e.g
-	 * BIOs such as issued by blkdev_issue_flush(). The is because it is
-	 * the responsibility of the user to first wait for the completion of
-	 * write operations for flush to have any effect on the persistence of
-	 * the written data.
-	 */
-	if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
+	if (WARN_ON_ONCE(!bdev->bd_disk->zone_wplugs_hash))
 		return false;
 
 	/*
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1726f0f828cc..6e3de50eae47 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1788,7 +1788,9 @@ static inline bool dm_zone_bio_needs_split(struct mapped_device *md,
 }
 static inline bool dm_zone_plug_bio(struct mapped_device *md, struct bio *bio)
 {
-	return dm_emulate_zone_append(md) && blk_zone_plug_bio(bio, 0);
+	if (!bio_needs_zone_write_plugging(bio))
+		return false;
+	return blk_zone_plug_bio(bio, 0);
 }
 
 static blk_status_t __send_zone_reset_all_emulated(struct clone_info *ci,
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 5c626d23cbb2..a51f92b6c340 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -837,6 +837,55 @@ static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return disk->nr_zones;
 }
+
+/**
+ * bio_needs_zone_write_plugging - Check if a BIO needs to be handled with zone
+ *				   write plugging
+ * @bio: The BIO being submitted
+ *
+ * Return true whenever @bio execution needs to be handled through zone
+ * write plugging (using blk_zone_plug_bio()). Return false otherwise.
+ */
+static inline bool bio_needs_zone_write_plugging(struct bio *bio)
+{
+	enum req_op op = bio_op(bio);
+
+	/*
+	 * Only zoned block devices have a zone write plug hash table. But not
+	 * all of them have one (e.g. DM devices may not need one).
+	 */
+	if (!bio->bi_bdev->bd_disk->zone_wplugs_hash)
+		return false;
+
+	/* Only write operations need zone write plugging. */
+	if (!op_is_write(op))
+		return false;
+
+	/* Ignore empty flush */
+	if (op_is_flush(bio->bi_opf) && !bio_sectors(bio))
+		return false;
+
+	/* Ignore BIOs that already have been handled by zone write plugging. */
+	if (bio_flagged(bio, BIO_ZONE_WRITE_PLUGGING))
+		return false;
+
+	/*
+	 * All zone write operations must be handled through zone write plugging
+	 * using blk_zone_plug_bio().
+	 */
+	switch (op) {
+	case REQ_OP_ZONE_APPEND:
+	case REQ_OP_WRITE:
+	case REQ_OP_WRITE_ZEROES:
+	case REQ_OP_ZONE_FINISH:
+	case REQ_OP_ZONE_RESET:
+	case REQ_OP_ZONE_RESET_ALL:
+		return true;
+	default:
+		return false;
+	}
+}
+
 bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs);
 
 /**
@@ -866,6 +915,12 @@ static inline unsigned int disk_nr_zones(struct gendisk *disk)
 {
 	return 0;
 }
+
+static inline bool bio_needs_zone_write_plugging(struct bio *bio)
+{
+	return false;
+}
+
 static inline bool blk_zone_plug_bio(struct bio *bio, unsigned int nr_segs)
 {
 	return false;
-- 
cgit v1.2.3


From 38446014648c9f7b2843f87517c8f2b73906bb40 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 25 Jun 2025 13:34:58 +0200
Subject: block: don't merge different kinds of P2P transfers in a single bio

To get out of the DMA mapping helpers having to check every segment for
it's P2P status, ensure that bios either contain P2P transfers or non-P2P
transfers, and that a P2P bio only contains ranges from a single device.

This means we do the page zone access in the bio add path where it should
be still page hot, and will only have do the fairly expensive P2P topology
lookup once per bio down in the DMA mapping path, and only for already
marked bios.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Logan Gunthorpe <logang@deltatee.com>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20250625113531.522027-2-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bio-integrity.c     |  3 +++
 block/bio.c               | 20 +++++++++++++-------
 include/linux/blk_types.h |  2 ++
 3 files changed, 18 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio-integrity.c b/block/bio-integrity.c
index 10912988c8f5..6b077ca937f6 100644
--- a/block/bio-integrity.c
+++ b/block/bio-integrity.c
@@ -128,6 +128,9 @@ int bio_integrity_add_page(struct bio *bio, struct page *page,
 	if (bip->bip_vcnt > 0) {
 		struct bio_vec *bv = &bip->bip_vec[bip->bip_vcnt - 1];
 
+		if (!zone_device_pages_have_same_pgmap(bv->bv_page, page))
+			return 0;
+
 		if (bvec_try_merge_hw_page(q, bv, page, len, offset)) {
 			bip->bip_iter.bi_size += len;
 			return len;
diff --git a/block/bio.c b/block/bio.c
index 3c0a558c90f5..92c512e876c8 100644
--- a/block/bio.c
+++ b/block/bio.c
@@ -930,8 +930,6 @@ static bool bvec_try_merge_page(struct bio_vec *bv, struct page *page,
 		return false;
 	if (xen_domain() && !xen_biovec_phys_mergeable(bv, page))
 		return false;
-	if (!zone_device_pages_have_same_pgmap(bv->bv_page, page))
-		return false;
 
 	if ((vec_end_addr & PAGE_MASK) != ((page_addr + off) & PAGE_MASK)) {
 		if (IS_ENABLED(CONFIG_KMSAN))
@@ -982,6 +980,9 @@ void __bio_add_page(struct bio *bio, struct page *page,
 	WARN_ON_ONCE(bio_flagged(bio, BIO_CLONED));
 	WARN_ON_ONCE(bio_full(bio, len));
 
+	if (is_pci_p2pdma_page(page))
+		bio->bi_opf |= REQ_P2PDMA | REQ_NOMERGE;
+
 	bvec_set_page(&bio->bi_io_vec[bio->bi_vcnt], page, len, off);
 	bio->bi_iter.bi_size += len;
 	bio->bi_vcnt++;
@@ -1022,11 +1023,16 @@ int bio_add_page(struct bio *bio, struct page *page,
 	if (bio->bi_iter.bi_size > UINT_MAX - len)
 		return 0;
 
-	if (bio->bi_vcnt > 0 &&
-	    bvec_try_merge_page(&bio->bi_io_vec[bio->bi_vcnt - 1],
-				page, len, offset)) {
-		bio->bi_iter.bi_size += len;
-		return len;
+	if (bio->bi_vcnt > 0) {
+		struct bio_vec *bv = &bio->bi_io_vec[bio->bi_vcnt - 1];
+
+		if (!zone_device_pages_have_same_pgmap(bv->bv_page, page))
+			return 0;
+
+		if (bvec_try_merge_page(bv, page, len, offset)) {
+			bio->bi_iter.bi_size += len;
+			return len;
+		}
 	}
 
 	if (bio->bi_vcnt >= bio->bi_max_vecs)
diff --git a/include/linux/blk_types.h b/include/linux/blk_types.h
index 930daff207df..09b99d52fd36 100644
--- a/include/linux/blk_types.h
+++ b/include/linux/blk_types.h
@@ -386,6 +386,7 @@ enum req_flag_bits {
 	__REQ_DRV,		/* for driver use */
 	__REQ_FS_PRIVATE,	/* for file system (submitter) use */
 	__REQ_ATOMIC,		/* for atomic write operations */
+	__REQ_P2PDMA,		/* contains P2P DMA pages */
 	/*
 	 * Command specific flags, keep last:
 	 */
@@ -418,6 +419,7 @@ enum req_flag_bits {
 #define REQ_DRV		(__force blk_opf_t)(1ULL << __REQ_DRV)
 #define REQ_FS_PRIVATE	(__force blk_opf_t)(1ULL << __REQ_FS_PRIVATE)
 #define REQ_ATOMIC	(__force blk_opf_t)(1ULL << __REQ_ATOMIC)
+#define REQ_P2PDMA	(__force blk_opf_t)(1ULL << __REQ_P2PDMA)
 
 #define REQ_NOUNMAP	(__force blk_opf_t)(1ULL << __REQ_NOUNMAP)
 
-- 
cgit v1.2.3


From 858299dc61603670823f8c1d62bf3fc7af44b18b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Wed, 25 Jun 2025 13:34:59 +0200
Subject: block: add scatterlist-less DMA mapping helpers

Add a new blk_rq_dma_map / blk_rq_dma_unmap pair that does away with
the wasteful scatterlist structure.  Instead it uses the mapping iterator
to either add segments to the IOVA for IOMMU operations, or just maps
them one by one for the direct mapping.  For the IOMMU case instead of
a scatterlist with an entry for each segment, only a single [dma_addr,len]
pair needs to be stored for processing a request, and for the direct
mapping the per-segment allocation shrinks from
[page,offset,len,dma_addr,dma_len] to just [dma_addr,len].

One big difference to the scatterlist API, which could be considered
downside, is that the IOVA collapsing only works when the driver sets
a virt_boundary that matches the IOMMU granule.  For NVMe this is done
already so it works perfectly.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Keith Busch <kbusch@kernel.org>
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/20250625113531.522027-3-hch@lst.de
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-dma.c         | 161 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/blk-mq-dma.h |  63 ++++++++++++++++++
 2 files changed, 224 insertions(+)
 create mode 100644 include/linux/blk-mq-dma.h

(limited to 'include/linux')

diff --git a/block/blk-mq-dma.c b/block/blk-mq-dma.c
index 82bae475dfa4..ad283017caef 100644
--- a/block/blk-mq-dma.c
+++ b/block/blk-mq-dma.c
@@ -2,6 +2,7 @@
 /*
  * Copyright (C) 2025 Christoph Hellwig
  */
+#include <linux/blk-mq-dma.h>
 #include "blk.h"
 
 struct phys_vec {
@@ -61,6 +62,166 @@ static bool blk_map_iter_next(struct request *req, struct req_iterator *iter,
 	return true;
 }
 
+/*
+ * The IOVA-based DMA API wants to be able to coalesce at the minimal IOMMU page
+ * size granularity (which is guaranteed to be <= PAGE_SIZE and usually 4k), so
+ * we need to ensure our segments are aligned to this as well.
+ *
+ * Note that there is no point in using the slightly more complicated IOVA based
+ * path for single segment mappings.
+ */
+static inline bool blk_can_dma_map_iova(struct request *req,
+		struct device *dma_dev)
+{
+	return !((queue_virt_boundary(req->q) + 1) &
+		dma_get_merge_boundary(dma_dev));
+}
+
+static bool blk_dma_map_bus(struct blk_dma_iter *iter, struct phys_vec *vec)
+{
+	iter->addr = pci_p2pdma_bus_addr_map(&iter->p2pdma, vec->paddr);
+	iter->len = vec->len;
+	return true;
+}
+
+static bool blk_dma_map_direct(struct request *req, struct device *dma_dev,
+		struct blk_dma_iter *iter, struct phys_vec *vec)
+{
+	iter->addr = dma_map_page(dma_dev, phys_to_page(vec->paddr),
+			offset_in_page(vec->paddr), vec->len, rq_dma_dir(req));
+	if (dma_mapping_error(dma_dev, iter->addr)) {
+		iter->status = BLK_STS_RESOURCE;
+		return false;
+	}
+	iter->len = vec->len;
+	return true;
+}
+
+static bool blk_rq_dma_map_iova(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, struct blk_dma_iter *iter,
+		struct phys_vec *vec)
+{
+	enum dma_data_direction dir = rq_dma_dir(req);
+	unsigned int mapped = 0;
+	int error;
+
+	iter->addr = state->addr;
+	iter->len = dma_iova_size(state);
+
+	do {
+		error = dma_iova_link(dma_dev, state, vec->paddr, mapped,
+				vec->len, dir, 0);
+		if (error)
+			break;
+		mapped += vec->len;
+	} while (blk_map_iter_next(req, &iter->iter, vec));
+
+	error = dma_iova_sync(dma_dev, state, 0, mapped);
+	if (error) {
+		iter->status = errno_to_blk_status(error);
+		return false;
+	}
+
+	return true;
+}
+
+/**
+ * blk_rq_dma_map_iter_start - map the first DMA segment for a request
+ * @req:	request to map
+ * @dma_dev:	device to map to
+ * @state:	DMA IOVA state
+ * @iter:	block layer DMA iterator
+ *
+ * Start DMA mapping @req to @dma_dev.  @state and @iter are provided by the
+ * caller and don't need to be initialized.  @state needs to be stored for use
+ * at unmap time, @iter is only needed at map time.
+ *
+ * Returns %false if there is no segment to map, including due to an error, or
+ * %true ft it did map a segment.
+ *
+ * If a segment was mapped, the DMA address for it is returned in @iter.addr and
+ * the length in @iter.len.  If no segment was mapped the status code is
+ * returned in @iter.status.
+ *
+ * The caller can call blk_rq_dma_map_coalesce() to check if further segments
+ * need to be mapped after this, or go straight to blk_rq_dma_map_iter_next()
+ * to try to map the following segments.
+ */
+bool blk_rq_dma_map_iter_start(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, struct blk_dma_iter *iter)
+{
+	unsigned int total_len = blk_rq_payload_bytes(req);
+	struct phys_vec vec;
+
+	iter->iter.bio = req->bio;
+	iter->iter.iter = req->bio->bi_iter;
+	memset(&iter->p2pdma, 0, sizeof(iter->p2pdma));
+	iter->status = BLK_STS_OK;
+
+	/*
+	 * Grab the first segment ASAP because we'll need it to check for P2P
+	 * transfers.
+	 */
+	if (!blk_map_iter_next(req, &iter->iter, &vec))
+		return false;
+
+	if (IS_ENABLED(CONFIG_PCI_P2PDMA) && (req->cmd_flags & REQ_P2PDMA)) {
+		switch (pci_p2pdma_state(&iter->p2pdma, dma_dev,
+					 phys_to_page(vec.paddr))) {
+		case PCI_P2PDMA_MAP_BUS_ADDR:
+			return blk_dma_map_bus(iter, &vec);
+		case PCI_P2PDMA_MAP_THRU_HOST_BRIDGE:
+			/*
+			 * P2P transfers through the host bridge are treated the
+			 * same as non-P2P transfers below and during unmap.
+			 */
+			req->cmd_flags &= ~REQ_P2PDMA;
+			break;
+		default:
+			iter->status = BLK_STS_INVAL;
+			return false;
+		}
+	}
+
+	if (blk_can_dma_map_iova(req, dma_dev) &&
+	    dma_iova_try_alloc(dma_dev, state, vec.paddr, total_len))
+		return blk_rq_dma_map_iova(req, dma_dev, state, iter, &vec);
+	return blk_dma_map_direct(req, dma_dev, iter, &vec);
+}
+EXPORT_SYMBOL_GPL(blk_rq_dma_map_iter_start);
+
+/**
+ * blk_rq_dma_map_iter_next - map the next DMA segment for a request
+ * @req:	request to map
+ * @dma_dev:	device to map to
+ * @state:	DMA IOVA state
+ * @iter:	block layer DMA iterator
+ *
+ * Iterate to the next mapping after a previous call to
+ * blk_rq_dma_map_iter_start().  See there for a detailed description of the
+ * arguments.
+ *
+ * Returns %false if there is no segment to map, including due to an error, or
+ * %true ft it did map a segment.
+ *
+ * If a segment was mapped, the DMA address for it is returned in @iter.addr and
+ * the length in @iter.len.  If no segment was mapped the status code is
+ * returned in @iter.status.
+ */
+bool blk_rq_dma_map_iter_next(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, struct blk_dma_iter *iter)
+{
+	struct phys_vec vec;
+
+	if (!blk_map_iter_next(req, &iter->iter, &vec))
+		return false;
+
+	if (iter->p2pdma.map == PCI_P2PDMA_MAP_BUS_ADDR)
+		return blk_dma_map_bus(iter, &vec);
+	return blk_dma_map_direct(req, dma_dev, iter, &vec);
+}
+EXPORT_SYMBOL_GPL(blk_rq_dma_map_iter_next);
+
 static inline struct scatterlist *
 blk_next_sg(struct scatterlist **sg, struct scatterlist *sglist)
 {
diff --git a/include/linux/blk-mq-dma.h b/include/linux/blk-mq-dma.h
new file mode 100644
index 000000000000..c26a01aeae00
--- /dev/null
+++ b/include/linux/blk-mq-dma.h
@@ -0,0 +1,63 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+#ifndef BLK_MQ_DMA_H
+#define BLK_MQ_DMA_H
+
+#include <linux/blk-mq.h>
+#include <linux/pci-p2pdma.h>
+
+struct blk_dma_iter {
+	/* Output address range for this iteration */
+	dma_addr_t			addr;
+	u32				len;
+
+	/* Status code. Only valid when blk_rq_dma_map_iter_* returned false */
+	blk_status_t			status;
+
+	/* Internal to blk_rq_dma_map_iter_* */
+	struct req_iterator		iter;
+	struct pci_p2pdma_map_state	p2pdma;
+};
+
+bool blk_rq_dma_map_iter_start(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, struct blk_dma_iter *iter);
+bool blk_rq_dma_map_iter_next(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, struct blk_dma_iter *iter);
+
+/**
+ * blk_rq_dma_map_coalesce - were all segments coalesced?
+ * @state: DMA state to check
+ *
+ * Returns true if blk_rq_dma_map_iter_start coalesced all segments into a
+ * single DMA range.
+ */
+static inline bool blk_rq_dma_map_coalesce(struct dma_iova_state *state)
+{
+	return dma_use_iova(state);
+}
+
+/**
+ * blk_rq_dma_unmap - try to DMA unmap a request
+ * @req:	request to unmap
+ * @dma_dev:	device to unmap from
+ * @state:	DMA IOVA state
+ * @mapped_len: number of bytes to unmap
+ *
+ * Returns %false if the callers need to manually unmap every DMA segment
+ * mapped using @iter or %true if no work is left to be done.
+ */
+static inline bool blk_rq_dma_unmap(struct request *req, struct device *dma_dev,
+		struct dma_iova_state *state, size_t mapped_len)
+{
+	if (req->cmd_flags & REQ_P2PDMA)
+		return true;
+
+	if (dma_use_iova(state)) {
+		dma_iova_destroy(dma_dev, state, mapped_len, rq_dma_dir(req),
+				 0);
+		return true;
+	}
+
+	return !dma_need_unmap(dma_dev);
+}
+
+#endif /* BLK_MQ_DMA_H */
-- 
cgit v1.2.3


From 2ad26b7bedcd4941e6dafa1851e2054b369b9d25 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Mon, 19 May 2025 16:41:08 +0100
Subject: include: linux: move adi-axi-common.h out of fpga
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The adi-axi-common.h header has some common defines used in various ADI
IPs. However they are not specific for any fpga manager so it's
questionable for the header to live under include/linux/fpga. Hence
let's just move one directory up and update all users.

Suggested-by: Xu Yilun <yilun.xu@linux.intel.com>
Acked-by: Xu Yilun <yilun.xu@intel.com>
Acked-by: Jonathan Cameron <Jonathan.Cameron@huawei.com> # for IIO
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250519-dev-axi-clkgen-limits-v6-3-bc4b3b61d1d4@analog.com
Acked-by: Mark Brown <broonie@kernel.org>
Acked-by: Uwe Kleine-König <ukleinek@kernel.org>
Reviewed-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 drivers/dma/dma-axi-dmac.c          |  2 +-
 drivers/hwmon/axi-fan-control.c     |  2 +-
 drivers/iio/adc/adi-axi-adc.c       |  3 +--
 drivers/iio/dac/adi-axi-dac.c       |  2 +-
 drivers/pwm/pwm-axi-pwmgen.c        |  2 +-
 drivers/spi/spi-axi-spi-engine.c    |  2 +-
 include/linux/adi-axi-common.h      | 23 +++++++++++++++++++++++
 include/linux/fpga/adi-axi-common.h | 23 -----------------------
 8 files changed, 29 insertions(+), 30 deletions(-)
 create mode 100644 include/linux/adi-axi-common.h
 delete mode 100644 include/linux/fpga/adi-axi-common.h

(limited to 'include/linux')

diff --git a/drivers/dma/dma-axi-dmac.c b/drivers/dma/dma-axi-dmac.c
index 36943b0c6d60..5b06b0dc67ee 100644
--- a/drivers/dma/dma-axi-dmac.c
+++ b/drivers/dma/dma-axi-dmac.c
@@ -6,6 +6,7 @@
  *  Author: Lars-Peter Clausen <lars@metafoo.de>
  */
 
+#include <linux/adi-axi-common.h>
 #include <linux/bitfield.h>
 #include <linux/clk.h>
 #include <linux/device.h>
@@ -22,7 +23,6 @@
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/slab.h>
-#include <linux/fpga/adi-axi-common.h>
 
 #include <dt-bindings/dma/axi-dmac.h>
 
diff --git a/drivers/hwmon/axi-fan-control.c b/drivers/hwmon/axi-fan-control.c
index 35c862eb158b..b7bb325c3ad9 100644
--- a/drivers/hwmon/axi-fan-control.c
+++ b/drivers/hwmon/axi-fan-control.c
@@ -4,9 +4,9 @@
  *
  * Copyright 2019 Analog Devices Inc.
  */
+#include <linux/adi-axi-common.h>
 #include <linux/bits.h>
 #include <linux/clk.h>
-#include <linux/fpga/adi-axi-common.h>
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/interrupt.h>
diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c
index 4116c44197b8..b3cc78187c9d 100644
--- a/drivers/iio/adc/adi-axi-adc.c
+++ b/drivers/iio/adc/adi-axi-adc.c
@@ -6,6 +6,7 @@
  * Copyright 2012-2020 Analog Devices Inc.
  */
 
+#include <linux/adi-axi-common.h>
 #include <linux/bitfield.h>
 #include <linux/cleanup.h>
 #include <linux/clk.h>
@@ -20,8 +21,6 @@
 #include <linux/regmap.h>
 #include <linux/slab.h>
 
-#include <linux/fpga/adi-axi-common.h>
-
 #include <linux/iio/backend.h>
 #include <linux/iio/buffer-dmaengine.h>
 #include <linux/iio/buffer.h>
diff --git a/drivers/iio/dac/adi-axi-dac.c b/drivers/iio/dac/adi-axi-dac.c
index 33faba4b02c2..890a0ac0d85e 100644
--- a/drivers/iio/dac/adi-axi-dac.c
+++ b/drivers/iio/dac/adi-axi-dac.c
@@ -5,6 +5,7 @@
  *
  * Copyright 2016-2024 Analog Devices Inc.
  */
+#include <linux/adi-axi-common.h>
 #include <linux/bitfield.h>
 #include <linux/bits.h>
 #include <linux/cleanup.h>
@@ -23,7 +24,6 @@
 #include <linux/regmap.h>
 #include <linux/units.h>
 
-#include <linux/fpga/adi-axi-common.h>
 #include <linux/iio/backend.h>
 #include <linux/iio/buffer-dmaengine.h>
 #include <linux/iio/buffer.h>
diff --git a/drivers/pwm/pwm-axi-pwmgen.c b/drivers/pwm/pwm-axi-pwmgen.c
index 60dcd3542373..b40522f01002 100644
--- a/drivers/pwm/pwm-axi-pwmgen.c
+++ b/drivers/pwm/pwm-axi-pwmgen.c
@@ -18,10 +18,10 @@
  * - Supports normal polarity. Does not support changing polarity.
  * - On disable, the PWM output becomes low (inactive).
  */
+#include <linux/adi-axi-common.h>
 #include <linux/bits.h>
 #include <linux/clk.h>
 #include <linux/err.h>
-#include <linux/fpga/adi-axi-common.h>
 #include <linux/io.h>
 #include <linux/minmax.h>
 #include <linux/module.h>
diff --git a/drivers/spi/spi-axi-spi-engine.c b/drivers/spi/spi-axi-spi-engine.c
index 8cc19934b48b..512d53a8ef4d 100644
--- a/drivers/spi/spi-axi-spi-engine.c
+++ b/drivers/spi/spi-axi-spi-engine.c
@@ -6,12 +6,12 @@
  *  Author: Lars-Peter Clausen <lars@metafoo.de>
  */
 
+#include <linux/adi-axi-common.h>
 #include <linux/bitfield.h>
 #include <linux/bitops.h>
 #include <linux/clk.h>
 #include <linux/completion.h>
 #include <linux/dmaengine.h>
-#include <linux/fpga/adi-axi-common.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
diff --git a/include/linux/adi-axi-common.h b/include/linux/adi-axi-common.h
new file mode 100644
index 000000000000..141ac3f251e6
--- /dev/null
+++ b/include/linux/adi-axi-common.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Analog Devices AXI common registers & definitions
+ *
+ * Copyright 2019 Analog Devices Inc.
+ *
+ * https://wiki.analog.com/resources/fpga/docs/axi_ip
+ * https://wiki.analog.com/resources/fpga/docs/hdl/regmap
+ */
+
+#ifndef ADI_AXI_COMMON_H_
+#define ADI_AXI_COMMON_H_
+
+#define ADI_AXI_REG_VERSION			0x0000
+
+#define ADI_AXI_PCORE_VER(major, minor, patch)	\
+	(((major) << 16) | ((minor) << 8) | (patch))
+
+#define ADI_AXI_PCORE_VER_MAJOR(version)	(((version) >> 16) & 0xff)
+#define ADI_AXI_PCORE_VER_MINOR(version)	(((version) >> 8) & 0xff)
+#define ADI_AXI_PCORE_VER_PATCH(version)	((version) & 0xff)
+
+#endif /* ADI_AXI_COMMON_H_ */
diff --git a/include/linux/fpga/adi-axi-common.h b/include/linux/fpga/adi-axi-common.h
deleted file mode 100644
index 141ac3f251e6..000000000000
--- a/include/linux/fpga/adi-axi-common.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-/*
- * Analog Devices AXI common registers & definitions
- *
- * Copyright 2019 Analog Devices Inc.
- *
- * https://wiki.analog.com/resources/fpga/docs/axi_ip
- * https://wiki.analog.com/resources/fpga/docs/hdl/regmap
- */
-
-#ifndef ADI_AXI_COMMON_H_
-#define ADI_AXI_COMMON_H_
-
-#define ADI_AXI_REG_VERSION			0x0000
-
-#define ADI_AXI_PCORE_VER(major, minor, patch)	\
-	(((major) << 16) | ((minor) << 8) | (patch))
-
-#define ADI_AXI_PCORE_VER_MAJOR(version)	(((version) >> 16) & 0xff)
-#define ADI_AXI_PCORE_VER_MINOR(version)	(((version) >> 8) & 0xff)
-#define ADI_AXI_PCORE_VER_PATCH(version)	((version) & 0xff)
-
-#endif /* ADI_AXI_COMMON_H_ */
-- 
cgit v1.2.3


From 6fc942f777b1a94fd2dacd4836aaf7e3b440baf8 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Mon, 19 May 2025 16:41:09 +0100
Subject: include: adi-axi-common: add new helper macros
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add new helper macros and enums to help identifying the platform and some
characteristics of it at runtime.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250519-dev-axi-clkgen-limits-v6-4-bc4b3b61d1d4@analog.com
Reviewed-by: David Lechner <dlechner@baylibre.com>
Signed-off-by: Stephen Boyd <sboyd@kernel.org>
---
 include/linux/adi-axi-common.h | 33 +++++++++++++++++++++++++++++++++
 1 file changed, 33 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/adi-axi-common.h b/include/linux/adi-axi-common.h
index 141ac3f251e6..f64f4ad4beda 100644
--- a/include/linux/adi-axi-common.h
+++ b/include/linux/adi-axi-common.h
@@ -12,6 +12,7 @@
 #define ADI_AXI_COMMON_H_
 
 #define ADI_AXI_REG_VERSION			0x0000
+#define ADI_AXI_REG_FPGA_INFO			0x001C
 
 #define ADI_AXI_PCORE_VER(major, minor, patch)	\
 	(((major) << 16) | ((minor) << 8) | (patch))
@@ -20,4 +21,36 @@
 #define ADI_AXI_PCORE_VER_MINOR(version)	(((version) >> 8) & 0xff)
 #define ADI_AXI_PCORE_VER_PATCH(version)	((version) & 0xff)
 
+#define ADI_AXI_INFO_FPGA_TECH(info)            (((info) >> 24) & 0xff)
+#define ADI_AXI_INFO_FPGA_FAMILY(info)          (((info) >> 16) & 0xff)
+#define ADI_AXI_INFO_FPGA_SPEED_GRADE(info)     (((info) >> 8) & 0xff)
+
+enum adi_axi_fpga_technology {
+	ADI_AXI_FPGA_TECH_UNKNOWN = 0,
+	ADI_AXI_FPGA_TECH_SERIES7,
+	ADI_AXI_FPGA_TECH_ULTRASCALE,
+	ADI_AXI_FPGA_TECH_ULTRASCALE_PLUS,
+};
+
+enum adi_axi_fpga_family {
+	ADI_AXI_FPGA_FAMILY_UNKNOWN = 0,
+	ADI_AXI_FPGA_FAMILY_ARTIX,
+	ADI_AXI_FPGA_FAMILY_KINTEX,
+	ADI_AXI_FPGA_FAMILY_VIRTEX,
+	ADI_AXI_FPGA_FAMILY_ZYNQ,
+};
+
+enum adi_axi_fpga_speed_grade {
+	ADI_AXI_FPGA_SPEED_UNKNOWN      = 0,
+	ADI_AXI_FPGA_SPEED_1    = 10,
+	ADI_AXI_FPGA_SPEED_1L   = 11,
+	ADI_AXI_FPGA_SPEED_1H   = 12,
+	ADI_AXI_FPGA_SPEED_1HV  = 13,
+	ADI_AXI_FPGA_SPEED_1LV  = 14,
+	ADI_AXI_FPGA_SPEED_2    = 20,
+	ADI_AXI_FPGA_SPEED_2L   = 21,
+	ADI_AXI_FPGA_SPEED_2LV  = 22,
+	ADI_AXI_FPGA_SPEED_3    = 30,
+};
+
 #endif /* ADI_AXI_COMMON_H_ */
-- 
cgit v1.2.3


From 12c409aa1ec2592280a2ddcc66ff8f3c7f7bb171 Mon Sep 17 00:00:00 2001
From: Denis OSTERLAND-HEIM <denis.osterland@diehl.com>
Date: Wed, 28 May 2025 12:57:50 +0200
Subject: pps: fix poll support

Because pps_cdev_poll() returns unconditionally EPOLLIN,
a user space program that calls select/poll get always an immediate data
ready-to-read response. As a result the intended use to wait until next
data becomes ready does not work.

User space snippet:

    struct pollfd pollfd = {
      .fd = open("/dev/pps0", O_RDONLY),
      .events = POLLIN|POLLERR,
      .revents = 0 };
    while(1) {
      poll(&pollfd, 1, 2000/*ms*/); // returns immediate, but should wait
      if(revents & EPOLLIN) { // always true
        struct pps_fdata fdata;
        memset(&fdata, 0, sizeof(memdata));
        ioctl(PPS_FETCH, &fdata); // currently fetches data at max speed
      }
    }

Lets remember the last fetch event counter and compare this value
in pps_cdev_poll() with most recent event counter
and return 0 if they are equal.

Signed-off-by: Denis OSTERLAND-HEIM <denis.osterland@diehl.com>
Co-developed-by: Rodolfo Giometti <giometti@enneenne.com>
Signed-off-by: Rodolfo Giometti <giometti@enneenne.com>
Fixes: eae9d2ba0cfc ("LinuxPPS: core support")
Link: https://lore.kernel.org/all/f6bed779-6d59-4f0f-8a59-b6312bd83b4e@enneenne.com/
Acked-by: Rodolfo Giometti <giometti@enneenne.com>
Link: https://lore.kernel.org/r/c3c50ad1eb19ef553eca8a57c17f4c006413ab70.camel@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/pps/pps.c          | 11 +++++++++--
 include/linux/pps_kernel.h |  1 +
 2 files changed, 10 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pps/pps.c b/drivers/pps/pps.c
index 6a02245ea35f..9463232af8d2 100644
--- a/drivers/pps/pps.c
+++ b/drivers/pps/pps.c
@@ -41,6 +41,9 @@ static __poll_t pps_cdev_poll(struct file *file, poll_table *wait)
 
 	poll_wait(file, &pps->queue, wait);
 
+	if (pps->last_fetched_ev == pps->last_ev)
+		return 0;
+
 	return EPOLLIN | EPOLLRDNORM;
 }
 
@@ -186,9 +189,11 @@ static long pps_cdev_ioctl(struct file *file,
 		if (err)
 			return err;
 
-		/* Return the fetched timestamp */
+		/* Return the fetched timestamp and save last fetched event  */
 		spin_lock_irq(&pps->lock);
 
+		pps->last_fetched_ev = pps->last_ev;
+
 		fdata.info.assert_sequence = pps->assert_sequence;
 		fdata.info.clear_sequence = pps->clear_sequence;
 		fdata.info.assert_tu = pps->assert_tu;
@@ -272,9 +277,11 @@ static long pps_cdev_compat_ioctl(struct file *file,
 		if (err)
 			return err;
 
-		/* Return the fetched timestamp */
+		/* Return the fetched timestamp and save last fetched event  */
 		spin_lock_irq(&pps->lock);
 
+		pps->last_fetched_ev = pps->last_ev;
+
 		compat.info.assert_sequence = pps->assert_sequence;
 		compat.info.clear_sequence = pps->clear_sequence;
 		compat.info.current_mode = pps->current_mode;
diff --git a/include/linux/pps_kernel.h b/include/linux/pps_kernel.h
index c7abce28ed29..aab0aebb529e 100644
--- a/include/linux/pps_kernel.h
+++ b/include/linux/pps_kernel.h
@@ -52,6 +52,7 @@ struct pps_device {
 	int current_mode;			/* PPS mode at event time */
 
 	unsigned int last_ev;			/* last PPS event id */
+	unsigned int last_fetched_ev;		/* last fetched PPS event id */
 	wait_queue_head_t queue;		/* PPS event queue */
 
 	unsigned int id;			/* PPS source unique ID */
-- 
cgit v1.2.3


From b75e1f0619bd707e027812e262af3fbce445e71a Mon Sep 17 00:00:00 2001
From: Matti Vaittinen <mazziesaccount@gmail.com>
Date: Mon, 9 Jun 2025 10:26:47 +0300
Subject: device property: Use tidy for_each_named_* macros

Implementing if-conditions inside for_each_x() macros requires some
thinking to avoid side effects in the calling code. Resulting code
may look somewhat awkward, and there are couple of different ways it is
usually done.

Standardizing this to one way can help making it more obvious for a code
reader and writer. The newly added for_each_if() is a way to achieve this.

Use for_each_if() to make these macros look like many others which
should in the long run help reading the code.

Signed-off-by: Matti Vaittinen <mazziesaccount@gmail.com>
Acked-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/c98b39a7195006fdd24590b8d11bb271a72a0c8a.1749453752.git.mazziesaccount@gmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/property.h | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/property.h b/include/linux/property.h
index f718dd4789e5..82f0cb3abd1e 100644
--- a/include/linux/property.h
+++ b/include/linux/property.h
@@ -17,6 +17,7 @@
 #include <linux/fwnode.h>
 #include <linux/stddef.h>
 #include <linux/types.h>
+#include <linux/util_macros.h>
 
 struct device;
 
@@ -169,7 +170,7 @@ struct fwnode_handle *fwnode_get_next_available_child_node(
 
 #define fwnode_for_each_named_child_node(fwnode, child, name)		\
 	fwnode_for_each_child_node(fwnode, child)			\
-		if (!fwnode_name_eq(child, name)) { } else
+		for_each_if(fwnode_name_eq(child, name))
 
 #define fwnode_for_each_available_child_node(fwnode, child)		       \
 	for (child = fwnode_get_next_available_child_node(fwnode, NULL); child;\
@@ -184,7 +185,7 @@ struct fwnode_handle *device_get_next_child_node(const struct device *dev,
 
 #define device_for_each_named_child_node(dev, child, name)		\
 	device_for_each_child_node(dev, child)				\
-		if (!fwnode_name_eq(child, name)) { } else
+		for_each_if(fwnode_name_eq(child, name))
 
 #define device_for_each_child_node_scoped(dev, child)			\
 	for (struct fwnode_handle *child __free(fwnode_handle) =	\
@@ -193,7 +194,7 @@ struct fwnode_handle *device_get_next_child_node(const struct device *dev,
 
 #define device_for_each_named_child_node_scoped(dev, child, name)	\
 	device_for_each_child_node_scoped(dev, child)			\
-		if (!fwnode_name_eq(child, name)) { } else
+		for_each_if(fwnode_name_eq(child, name))
 
 struct fwnode_handle *fwnode_get_named_child_node(const struct fwnode_handle *fwnode,
 						  const char *childname);
-- 
cgit v1.2.3


From c6603b1d6556cc02d0169f74508ab0e3e3e4bd76 Mon Sep 17 00:00:00 2001
From: Anuj Gupta <anuj20.g@samsung.com>
Date: Mon, 30 Jun 2025 14:35:45 +0530
Subject: block: rename tuple_size field in blk_integrity to metadata_size

The tuple_size field in blk_integrity currently represents the total
size of metadata associated with each data interval. To make the meaning
more explicit, rename tuple_size to metadata_size. This is a purely
mechanical rename with no functional changes.

Suggested-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Link: https://lore.kernel.org/20250630090548.3317-2-anuj20.g@samsung.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/bio-integrity-auto.c        |  4 ++--
 block/blk-integrity.c             |  2 +-
 block/blk-settings.c              |  6 +++---
 block/t10-pi.c                    | 16 ++++++++--------
 drivers/md/dm-crypt.c             |  4 ++--
 drivers/md/dm-integrity.c         | 12 ++++++------
 drivers/nvdimm/btt.c              |  2 +-
 drivers/nvme/host/core.c          |  2 +-
 drivers/nvme/target/io-cmd-bdev.c |  2 +-
 drivers/scsi/sd_dif.c             |  2 +-
 include/linux/blk-integrity.h     |  4 ++--
 include/linux/blkdev.h            |  2 +-
 12 files changed, 29 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/block/bio-integrity-auto.c b/block/bio-integrity-auto.c
index 9c6657664792..687952f63bbb 100644
--- a/block/bio-integrity-auto.c
+++ b/block/bio-integrity-auto.c
@@ -54,10 +54,10 @@ static bool bi_offload_capable(struct blk_integrity *bi)
 {
 	switch (bi->csum_type) {
 	case BLK_INTEGRITY_CSUM_CRC64:
-		return bi->tuple_size == sizeof(struct crc64_pi_tuple);
+		return bi->metadata_size == sizeof(struct crc64_pi_tuple);
 	case BLK_INTEGRITY_CSUM_CRC:
 	case BLK_INTEGRITY_CSUM_IP:
-		return bi->tuple_size == sizeof(struct t10_pi_tuple);
+		return bi->metadata_size == sizeof(struct t10_pi_tuple);
 	default:
 		pr_warn_once("%s: unknown integrity checksum type:%d\n",
 			__func__, bi->csum_type);
diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index e4e2567061f9..c1102bf4cd8d 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -239,7 +239,7 @@ static ssize_t format_show(struct device *dev, struct device_attribute *attr,
 {
 	struct blk_integrity *bi = dev_to_bi(dev);
 
-	if (!bi->tuple_size)
+	if (!bi->metadata_size)
 		return sysfs_emit(page, "none\n");
 	return sysfs_emit(page, "%s\n", blk_integrity_profile_name(bi));
 }
diff --git a/block/blk-settings.c b/block/blk-settings.c
index a000daafbfb4..787500ff00c3 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -114,7 +114,7 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 {
 	struct blk_integrity *bi = &lim->integrity;
 
-	if (!bi->tuple_size) {
+	if (!bi->metadata_size) {
 		if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE ||
 		    bi->tag_size || ((bi->flags & BLK_INTEGRITY_REF_TAG))) {
 			pr_warn("invalid PI settings.\n");
@@ -875,7 +875,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		return true;
 
 	if (ti->flags & BLK_INTEGRITY_STACKED) {
-		if (ti->tuple_size != bi->tuple_size)
+		if (ti->metadata_size != bi->metadata_size)
 			goto incompatible;
 		if (ti->interval_exp != bi->interval_exp)
 			goto incompatible;
@@ -891,7 +891,7 @@ bool queue_limits_stack_integrity(struct queue_limits *t,
 		ti->flags |= (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE) |
 			     (bi->flags & BLK_INTEGRITY_REF_TAG);
 		ti->csum_type = bi->csum_type;
-		ti->tuple_size = bi->tuple_size;
+		ti->metadata_size = bi->metadata_size;
 		ti->pi_offset = bi->pi_offset;
 		ti->interval_exp = bi->interval_exp;
 		ti->tag_size = bi->tag_size;
diff --git a/block/t10-pi.c b/block/t10-pi.c
index 851db518ee5e..0c4ed9702146 100644
--- a/block/t10-pi.c
+++ b/block/t10-pi.c
@@ -56,7 +56,7 @@ static void t10_pi_generate(struct blk_integrity_iter *iter,
 			pi->ref_tag = 0;
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 }
@@ -105,7 +105,7 @@ static blk_status_t t10_pi_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 
@@ -125,7 +125,7 @@ next:
 static void t10_pi_type1_prepare(struct request *rq)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -177,7 +177,7 @@ static void t10_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u32 ref_tag = t10_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -234,7 +234,7 @@ static void ext_pi_crc64_generate(struct blk_integrity_iter *iter,
 			put_unaligned_be48(0ULL, pi->ref_tag);
 
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 }
@@ -289,7 +289,7 @@ static blk_status_t ext_pi_crc64_verify(struct blk_integrity_iter *iter,
 
 next:
 		iter->data_buf += iter->interval;
-		iter->prot_buf += bi->tuple_size;
+		iter->prot_buf += bi->metadata_size;
 		iter->seed++;
 	}
 
@@ -299,7 +299,7 @@ next:
 static void ext_pi_type1_prepare(struct request *rq)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
@@ -340,7 +340,7 @@ static void ext_pi_type1_complete(struct request *rq, unsigned int nr_bytes)
 {
 	struct blk_integrity *bi = &rq->q->limits.integrity;
 	unsigned intervals = nr_bytes >> bi->interval_exp;
-	const int tuple_sz = bi->tuple_size;
+	const int tuple_sz = bi->metadata_size;
 	u64 ref_tag = ext_pi_ref_tag(rq);
 	u8 offset = bi->pi_offset;
 	struct bio *bio;
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index 9dfdb63220d7..3d6d06b94c9f 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1189,11 +1189,11 @@ static int crypt_integrity_ctr(struct crypt_config *cc, struct dm_target *ti)
 		return -EINVAL;
 	}
 
-	if (bi->tuple_size < cc->used_tag_size) {
+	if (bi->metadata_size < cc->used_tag_size) {
 		ti->error = "Integrity profile tag size mismatch.";
 		return -EINVAL;
 	}
-	cc->tuple_size = bi->tuple_size;
+	cc->tuple_size = bi->metadata_size;
 	if (1 << bi->interval_exp != cc->sector_size) {
 		ti->error = "Integrity profile sector size mismatch.";
 		return -EINVAL;
diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
index 4395657fa583..efeee0a873c0 100644
--- a/drivers/md/dm-integrity.c
+++ b/drivers/md/dm-integrity.c
@@ -3906,8 +3906,8 @@ static void dm_integrity_io_hints(struct dm_target *ti, struct queue_limits *lim
 		struct blk_integrity *bi = &limits->integrity;
 
 		memset(bi, 0, sizeof(*bi));
-		bi->tuple_size = ic->tag_size;
-		bi->tag_size = bi->tuple_size;
+		bi->metadata_size = ic->tag_size;
+		bi->tag_size = bi->metadata_size;
 		bi->interval_exp =
 			ic->sb->log2_sectors_per_block + SECTOR_SHIFT;
 	}
@@ -4746,18 +4746,18 @@ static int dm_integrity_ctr(struct dm_target *ti, unsigned int argc, char **argv
 			ti->error = "Integrity profile not supported";
 			goto bad;
 		}
-		/*printk("tag_size: %u, tuple_size: %u\n", bi->tag_size, bi->tuple_size);*/
-		if (bi->tuple_size < ic->tag_size) {
+		/*printk("tag_size: %u, metadata_size: %u\n", bi->tag_size, bi->metadata_size);*/
+		if (bi->metadata_size < ic->tag_size) {
 			r = -EINVAL;
 			ti->error = "The integrity profile is smaller than tag size";
 			goto bad;
 		}
-		if ((unsigned long)bi->tuple_size > PAGE_SIZE / 2) {
+		if ((unsigned long)bi->metadata_size > PAGE_SIZE / 2) {
 			r = -EINVAL;
 			ti->error = "Too big tuple size";
 			goto bad;
 		}
-		ic->tuple_size = bi->tuple_size;
+		ic->tuple_size = bi->metadata_size;
 		if (1 << bi->interval_exp != ic->sectors_per_block << SECTOR_SHIFT) {
 			r = -EINVAL;
 			ti->error = "Integrity profile sector size mismatch";
diff --git a/drivers/nvdimm/btt.c b/drivers/nvdimm/btt.c
index 423dcd190906..2a1aa32e6693 100644
--- a/drivers/nvdimm/btt.c
+++ b/drivers/nvdimm/btt.c
@@ -1506,7 +1506,7 @@ static int btt_blk_init(struct btt *btt)
 	int rc;
 
 	if (btt_meta_size(btt) && IS_ENABLED(CONFIG_BLK_DEV_INTEGRITY)) {
-		lim.integrity.tuple_size = btt_meta_size(btt);
+		lim.integrity.metadata_size = btt_meta_size(btt);
 		lim.integrity.tag_size = btt_meta_size(btt);
 	}
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index 92697f98c601..b027dda38e69 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1866,7 +1866,7 @@ static bool nvme_init_integrity(struct nvme_ns_head *head,
 		break;
 	}
 
-	bi->tuple_size = head->ms;
+	bi->metadata_size = head->ms;
 	bi->pi_offset = info->pi_offset;
 	return true;
 }
diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
index eba42df2f821..42fb19f94ab8 100644
--- a/drivers/nvme/target/io-cmd-bdev.c
+++ b/drivers/nvme/target/io-cmd-bdev.c
@@ -65,7 +65,7 @@ static void nvmet_bdev_ns_enable_integrity(struct nvmet_ns *ns)
 		return;
 
 	if (bi->csum_type == BLK_INTEGRITY_CSUM_CRC) {
-		ns->metadata_size = bi->tuple_size;
+		ns->metadata_size = bi->metadata_size;
 		if (bi->flags & BLK_INTEGRITY_REF_TAG)
 			ns->pi_type = NVME_NS_DPS_PI_TYPE1;
 		else
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index ae6ce6f5d622..18bfca1f1c78 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -52,7 +52,7 @@ void sd_dif_config_host(struct scsi_disk *sdkp, struct queue_limits *lim)
 	if (type != T10_PI_TYPE3_PROTECTION)
 		bi->flags |= BLK_INTEGRITY_REF_TAG;
 
-	bi->tuple_size = sizeof(struct t10_pi_tuple);
+	bi->metadata_size = sizeof(struct t10_pi_tuple);
 
 	if (dif && type) {
 		bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index c7eae0bfb013..d27730da47f3 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -33,7 +33,7 @@ int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
 static inline bool
 blk_integrity_queue_supports_integrity(struct request_queue *q)
 {
-	return q->limits.integrity.tuple_size;
+	return q->limits.integrity.metadata_size;
 }
 
 static inline struct blk_integrity *blk_get_integrity(struct gendisk *disk)
@@ -74,7 +74,7 @@ static inline unsigned int bio_integrity_intervals(struct blk_integrity *bi,
 static inline unsigned int bio_integrity_bytes(struct blk_integrity *bi,
 					       unsigned int sectors)
 {
-	return bio_integrity_intervals(bi, sectors) * bi->tuple_size;
+	return bio_integrity_intervals(bi, sectors) * bi->metadata_size;
 }
 
 static inline bool blk_integrity_rq(struct request *rq)
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index a59880c809c7..ccda87d06a38 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -116,7 +116,7 @@ enum blk_integrity_checksum {
 struct blk_integrity {
 	unsigned char				flags;
 	enum blk_integrity_checksum		csum_type;
-	unsigned char				tuple_size;
+	unsigned char				metadata_size;
 	unsigned char				pi_offset;
 	unsigned char				interval_exp;
 	unsigned char				tag_size;
-- 
cgit v1.2.3


From 76e45252a4cefa205439eb6610a244771e7d88da Mon Sep 17 00:00:00 2001
From: Anuj Gupta <anuj20.g@samsung.com>
Date: Mon, 30 Jun 2025 14:35:46 +0530
Subject: block: introduce pi_tuple_size field in blk_integrity

Introduce a new pi_tuple_size field in struct blk_integrity to
explicitly represent the size (in bytes) of the protection information
(PI) tuple. This is a prep patch.
Add validation in blk_validate_integrity_limits() to ensure that
pi size matches the expected size for known checksum types and never
exceeds the pi_tuple_size.

Suggested-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Link: https://lore.kernel.org/20250630090548.3317-3-anuj20.g@samsung.com
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/blk-settings.c     | 38 ++++++++++++++++++++++++++++++++++++++
 drivers/nvme/host/core.c |  2 ++
 drivers/scsi/sd_dif.c    |  1 +
 include/linux/blkdev.h   |  1 +
 4 files changed, 42 insertions(+)

(limited to 'include/linux')

diff --git a/block/blk-settings.c b/block/blk-settings.c
index 787500ff00c3..32f3cdc9835a 100644
--- a/block/blk-settings.c
+++ b/block/blk-settings.c
@@ -14,6 +14,8 @@
 #include <linux/jiffies.h>
 #include <linux/gfp.h>
 #include <linux/dma-mapping.h>
+#include <linux/t10-pi.h>
+#include <linux/crc64.h>
 
 #include "blk.h"
 #include "blk-rq-qos.h"
@@ -135,6 +137,42 @@ static int blk_validate_integrity_limits(struct queue_limits *lim)
 		return -EINVAL;
 	}
 
+	if (bi->pi_tuple_size > bi->metadata_size) {
+		pr_warn("pi_tuple_size (%u) exceeds metadata_size (%u)\n",
+			 bi->pi_tuple_size,
+			 bi->metadata_size);
+		return -EINVAL;
+	}
+
+	switch (bi->csum_type) {
+	case BLK_INTEGRITY_CSUM_NONE:
+		if (bi->pi_tuple_size) {
+			pr_warn("pi_tuple_size must be 0 when checksum type \
+				 is none\n");
+			return -EINVAL;
+		}
+		break;
+	case BLK_INTEGRITY_CSUM_CRC:
+	case BLK_INTEGRITY_CSUM_IP:
+		if (bi->pi_tuple_size != sizeof(struct t10_pi_tuple)) {
+			pr_warn("pi_tuple_size mismatch for T10 PI: expected \
+				 %zu, got %u\n",
+				 sizeof(struct t10_pi_tuple),
+				 bi->pi_tuple_size);
+			return -EINVAL;
+		}
+		break;
+	case BLK_INTEGRITY_CSUM_CRC64:
+		if (bi->pi_tuple_size != sizeof(struct crc64_pi_tuple)) {
+			pr_warn("pi_tuple_size mismatch for CRC64 PI: \
+				 expected %zu, got %u\n",
+				 sizeof(struct crc64_pi_tuple),
+				 bi->pi_tuple_size);
+			return -EINVAL;
+		}
+		break;
+	}
+
 	if (!bi->interval_exp)
 		bi->interval_exp = ilog2(lim->logical_block_size);
 
diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
index b027dda38e69..fe72accab516 100644
--- a/drivers/nvme/host/core.c
+++ b/drivers/nvme/host/core.c
@@ -1867,6 +1867,8 @@ static bool nvme_init_integrity(struct nvme_ns_head *head,
 	}
 
 	bi->metadata_size = head->ms;
+	if (bi->csum_type)
+		bi->pi_tuple_size = head->pi_size;
 	bi->pi_offset = info->pi_offset;
 	return true;
 }
diff --git a/drivers/scsi/sd_dif.c b/drivers/scsi/sd_dif.c
index 18bfca1f1c78..ff4217fef93b 100644
--- a/drivers/scsi/sd_dif.c
+++ b/drivers/scsi/sd_dif.c
@@ -53,6 +53,7 @@ void sd_dif_config_host(struct scsi_disk *sdkp, struct queue_limits *lim)
 		bi->flags |= BLK_INTEGRITY_REF_TAG;
 
 	bi->metadata_size = sizeof(struct t10_pi_tuple);
+	bi->pi_tuple_size = bi->metadata_size;
 
 	if (dif && type) {
 		bi->flags |= BLK_INTEGRITY_DEVICE_CAPABLE;
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index ccda87d06a38..0d4011dcfed3 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -120,6 +120,7 @@ struct blk_integrity {
 	unsigned char				pi_offset;
 	unsigned char				interval_exp;
 	unsigned char				tag_size;
+	unsigned char				pi_tuple_size;
 };
 
 typedef unsigned int __bitwise blk_mode_t;
-- 
cgit v1.2.3


From 9eb22f7fedfc9eb1b7f431a5359abd4d15b0b0cd Mon Sep 17 00:00:00 2001
From: Anuj Gupta <anuj20.g@samsung.com>
Date: Mon, 30 Jun 2025 14:35:48 +0530
Subject: fs: add ioctl to query metadata and protection info capabilities

Add a new ioctl, FS_IOC_GETLBMD_CAP, to query metadata and protection
info (PI) capabilities. This ioctl returns information about the files
integrity profile. This is useful for userspace applications to
understand a files end-to-end data protection support and configure the
I/O accordingly.

For now this interface is only supported by block devices. However the
design and placement of this ioctl in generic FS ioctl space allows us
to extend it to work over files as well. This maybe useful when
filesystems start supporting  PI-aware layouts.

A new structure struct logical_block_metadata_cap is introduced, which
contains the following fields:

1. lbmd_flags: bitmask of logical block metadata capability flags
2. lbmd_interval: the amount of data described by each unit of logical
block metadata
3. lbmd_size: size in bytes of the logical block metadata associated
with each interval
4. lbmd_opaque_size: size in bytes of the opaque block tag associated
with each interval
5. lbmd_opaque_offset: offset in bytes of the opaque block tag within
the logical block metadata
6. lbmd_pi_size: size in bytes of the T10 PI tuple associated with each
interval
7. lbmd_pi_offset: offset in bytes of T10 PI tuple within the logical
block metadata
8. lbmd_pi_guard_tag_type: T10 PI guard tag type
9. lbmd_pi_app_tag_size: size in bytes of the T10 PI application tag
10. lbmd_pi_ref_tag_size: size in bytes of the T10 PI reference tag
11. lbmd_pi_storage_tag_size: size in bytes of the T10 PI storage tag

The internal logic to fetch the capability is encapsulated in a helper
function blk_get_meta_cap(), which uses the blk_integrity profile
associated with the device. The ioctl returns -EOPNOTSUPP, if
CONFIG_BLK_DEV_INTEGRITY is not enabled.

Suggested-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
Link: https://lore.kernel.org/20250630090548.3317-5-anuj20.g@samsung.com
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/blk-integrity.c         | 52 ++++++++++++++++++++++++++++++++++++++
 block/ioctl.c                 |  4 +++
 include/linux/blk-integrity.h |  7 +++++
 include/uapi/linux/fs.h       | 59 +++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 122 insertions(+)

(limited to 'include/linux')

diff --git a/block/blk-integrity.c b/block/blk-integrity.c
index c1102bf4cd8d..9d9dc9c32083 100644
--- a/block/blk-integrity.c
+++ b/block/blk-integrity.c
@@ -13,6 +13,7 @@
 #include <linux/scatterlist.h>
 #include <linux/export.h>
 #include <linux/slab.h>
+#include <linux/t10-pi.h>
 
 #include "blk.h"
 
@@ -54,6 +55,57 @@ new_segment:
 	return segments;
 }
 
+int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+		     struct logical_block_metadata_cap __user *argp)
+{
+	struct blk_integrity *bi = blk_get_integrity(bdev->bd_disk);
+	struct logical_block_metadata_cap meta_cap = {};
+	size_t usize = _IOC_SIZE(cmd);
+
+	if (!argp)
+		return -EINVAL;
+	if (usize < LBMD_SIZE_VER0)
+		return -EINVAL;
+	if (!bi)
+		goto out;
+
+	if (bi->flags & BLK_INTEGRITY_DEVICE_CAPABLE)
+		meta_cap.lbmd_flags |= LBMD_PI_CAP_INTEGRITY;
+	if (bi->flags & BLK_INTEGRITY_REF_TAG)
+		meta_cap.lbmd_flags |= LBMD_PI_CAP_REFTAG;
+	meta_cap.lbmd_interval = 1 << bi->interval_exp;
+	meta_cap.lbmd_size = bi->metadata_size;
+	meta_cap.lbmd_pi_size = bi->pi_tuple_size;
+	meta_cap.lbmd_pi_offset = bi->pi_offset;
+	meta_cap.lbmd_opaque_size = bi->metadata_size - bi->pi_tuple_size;
+	if (meta_cap.lbmd_opaque_size && !bi->pi_offset)
+		meta_cap.lbmd_opaque_offset = bi->pi_tuple_size;
+
+	meta_cap.lbmd_guard_tag_type = bi->csum_type;
+	if (bi->csum_type != BLK_INTEGRITY_CSUM_NONE)
+		meta_cap.lbmd_app_tag_size = 2;
+
+	if (bi->flags & BLK_INTEGRITY_REF_TAG) {
+		switch (bi->csum_type) {
+		case BLK_INTEGRITY_CSUM_CRC64:
+			meta_cap.lbmd_ref_tag_size =
+				sizeof_field(struct crc64_pi_tuple, ref_tag);
+			break;
+		case BLK_INTEGRITY_CSUM_CRC:
+		case BLK_INTEGRITY_CSUM_IP:
+			meta_cap.lbmd_ref_tag_size =
+				sizeof_field(struct t10_pi_tuple, ref_tag);
+			break;
+		default:
+			break;
+		}
+	}
+
+out:
+	return copy_struct_to_user(argp, usize, &meta_cap, sizeof(meta_cap),
+				   NULL);
+}
+
 /**
  * blk_rq_map_integrity_sg - Map integrity metadata into a scatterlist
  * @rq:		request to map
diff --git a/block/ioctl.c b/block/ioctl.c
index e472cc1030c6..9ad403733e19 100644
--- a/block/ioctl.c
+++ b/block/ioctl.c
@@ -13,6 +13,7 @@
 #include <linux/uaccess.h>
 #include <linux/pagemap.h>
 #include <linux/io_uring/cmd.h>
+#include <linux/blk-integrity.h>
 #include <uapi/linux/blkdev.h>
 #include "blk.h"
 #include "blk-crypto-internal.h"
@@ -566,6 +567,9 @@ static int blkdev_common_ioctl(struct block_device *bdev, blk_mode_t mode,
 {
 	unsigned int max_sectors;
 
+	if (_IOC_NR(cmd) == _IOC_NR(FS_IOC_GETLBMD_CAP))
+		return blk_get_meta_cap(bdev, cmd, argp);
+
 	switch (cmd) {
 	case BLKFLSBUF:
 		return blkdev_flushbuf(bdev, cmd, arg);
diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index d27730da47f3..e04c6e5bf1c6 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -29,6 +29,8 @@ int blk_rq_map_integrity_sg(struct request *, struct scatterlist *);
 int blk_rq_count_integrity_sg(struct request_queue *, struct bio *);
 int blk_rq_integrity_map_user(struct request *rq, void __user *ubuf,
 			      ssize_t bytes);
+int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+		     struct logical_block_metadata_cap __user *argp);
 
 static inline bool
 blk_integrity_queue_supports_integrity(struct request_queue *q)
@@ -92,6 +94,11 @@ static inline struct bio_vec rq_integrity_vec(struct request *rq)
 				 rq->bio->bi_integrity->bip_iter);
 }
 #else /* CONFIG_BLK_DEV_INTEGRITY */
+static inline int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
+				   struct logical_block_metadata_cap __user *argp)
+{
+	return -EOPNOTSUPP;
+}
 static inline int blk_rq_count_integrity_sg(struct request_queue *q,
 					    struct bio *b)
 {
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 0098b0ce8ccb..83720a2fd20d 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -91,6 +91,63 @@ struct fs_sysfs_path {
 	__u8			name[128];
 };
 
+/* Protection info capability flags */
+#define	LBMD_PI_CAP_INTEGRITY		(1 << 0)
+#define	LBMD_PI_CAP_REFTAG		(1 << 1)
+
+/* Checksum types for Protection Information */
+#define LBMD_PI_CSUM_NONE		0
+#define LBMD_PI_CSUM_IP			1
+#define LBMD_PI_CSUM_CRC16_T10DIF	2
+#define LBMD_PI_CSUM_CRC64_NVME		4
+
+/* sizeof first published struct */
+#define LBMD_SIZE_VER0			16
+
+/*
+ * Logical block metadata capability descriptor
+ * If the device does not support metadata, all the fields will be zero.
+ * Applications must check lbmd_flags to determine whether metadata is
+ * supported or not.
+ */
+struct logical_block_metadata_cap {
+	/* Bitmask of logical block metadata capability flags */
+	__u32	lbmd_flags;
+	/*
+	 * The amount of data described by each unit of logical block
+	 * metadata
+	 */
+	__u16	lbmd_interval;
+	/*
+	 * Size in bytes of the logical block metadata associated with each
+	 * interval
+	 */
+	__u8	lbmd_size;
+	/*
+	 * Size in bytes of the opaque block tag associated with each
+	 * interval
+	 */
+	__u8	lbmd_opaque_size;
+	/*
+	 * Offset in bytes of the opaque block tag within the logical block
+	 * metadata
+	 */
+	__u8	lbmd_opaque_offset;
+	/* Size in bytes of the T10 PI tuple associated with each interval */
+	__u8	lbmd_pi_size;
+	/* Offset in bytes of T10 PI tuple within the logical block metadata */
+	__u8	lbmd_pi_offset;
+	/* T10 PI guard tag type */
+	__u8	lbmd_guard_tag_type;
+	/* Size in bytes of the T10 PI application tag */
+	__u8	lbmd_app_tag_size;
+	/* Size in bytes of the T10 PI reference tag */
+	__u8	lbmd_ref_tag_size;
+	/* Size in bytes of the T10 PI storage tag */
+	__u8	lbmd_storage_tag_size;
+	__u8	pad;
+};
+
 /* extent-same (dedupe) ioctls; these MUST match the btrfs ioctl definitions */
 #define FILE_DEDUPE_RANGE_SAME		0
 #define FILE_DEDUPE_RANGE_DIFFERS	1
@@ -247,6 +304,8 @@ struct fsxattr {
  * also /sys/kernel/debug/ for filesystems with debugfs exports
  */
 #define FS_IOC_GETFSSYSFSPATH		_IOR(0x15, 1, struct fs_sysfs_path)
+/* Get logical block metadata capability details */
+#define FS_IOC_GETLBMD_CAP		_IOWR(0x15, 2, struct logical_block_metadata_cap)
 
 /*
  * Inode flags (FS_IOC_GETFLAGS / FS_IOC_SETFLAGS)
-- 
cgit v1.2.3


From e78f70bad29c5ae1e1076698b690b15794e9b81e Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 1 Jul 2025 14:32:25 +0200
Subject: time/timecounter: Fix the lie that struct cyclecounter is const

In both the read callback for struct cyclecounter, and in struct
timecounter, struct cyclecounter is declared as a const pointer.

Unfortunatly, a number of users of this pointer treat it as a non-const
pointer as it is burried in a larger structure that is heavily modified by
the callback function when accessed.  This lie had been hidden by the fact
that container_of() "casts away" a const attribute of a pointer without any
compiler warning happening at all.

Fix this all up by removing the const attribute in the needed places so
that everyone can see that the structure really isn't const, but can,
and is, modified by the users of it.

Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/2025070124-backyard-hurt-783a@gregkh
---
 arch/microblaze/kernel/timer.c                        | 2 +-
 drivers/clocksource/arm_arch_timer.c                  | 2 +-
 drivers/net/can/rockchip/rockchip_canfd-timestamp.c   | 2 +-
 drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c   | 2 +-
 drivers/net/can/usb/gs_usb.c                          | 2 +-
 drivers/net/dsa/mv88e6xxx/chip.h                      | 2 +-
 drivers/net/dsa/mv88e6xxx/ptp.c                       | 6 +++---
 drivers/net/ethernet/amd/xgbe/xgbe-ptp.c              | 2 +-
 drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c      | 2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c         | 2 +-
 drivers/net/ethernet/cavium/common/cavium_ptp.c       | 2 +-
 drivers/net/ethernet/freescale/fec_ptp.c              | 2 +-
 drivers/net/ethernet/intel/e1000e/netdev.c            | 2 +-
 drivers/net/ethernet/intel/igb/igb_ptp.c              | 4 ++--
 drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c          | 4 ++--
 drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c | 2 +-
 drivers/net/ethernet/mellanox/mlx4/en_clock.c         | 2 +-
 drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c   | 2 +-
 drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c    | 2 +-
 drivers/net/ethernet/pensando/ionic/ionic_phc.c       | 2 +-
 drivers/net/ethernet/qlogic/qede/qede_ptp.c           | 2 +-
 drivers/net/ethernet/ti/cpts.c                        | 2 +-
 drivers/net/ethernet/wangxun/libwx/wx_ptp.c           | 2 +-
 drivers/ptp/ptp_mock.c                                | 2 +-
 drivers/ptp/ptp_vclock.c                              | 2 +-
 include/linux/timecounter.h                           | 6 +++---
 kernel/time/timecounter.c                             | 2 +-
 sound/hda/hdac_stream.c                               | 2 +-
 28 files changed, 34 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/arch/microblaze/kernel/timer.c b/arch/microblaze/kernel/timer.c
index ccb4b4b59bca..a2ab67b747a1 100644
--- a/arch/microblaze/kernel/timer.c
+++ b/arch/microblaze/kernel/timer.c
@@ -193,7 +193,7 @@ static struct timecounter xilinx_tc = {
 	.cc = NULL,
 };
 
-static u64 xilinx_cc_read(const struct cyclecounter *cc)
+static u64 xilinx_cc_read(struct cyclecounter *cc)
 {
 	return xilinx_read(NULL);
 }
diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c
index 981a578043a5..80ba6a54248c 100644
--- a/drivers/clocksource/arm_arch_timer.c
+++ b/drivers/clocksource/arm_arch_timer.c
@@ -243,7 +243,7 @@ static u64 arch_counter_read(struct clocksource *cs)
 	return arch_timer_read_counter();
 }
 
-static u64 arch_counter_read_cc(const struct cyclecounter *cc)
+static u64 arch_counter_read_cc(struct cyclecounter *cc)
 {
 	return arch_timer_read_counter();
 }
diff --git a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
index fa85a75be65a..72774cd2f94b 100644
--- a/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
+++ b/drivers/net/can/rockchip/rockchip_canfd-timestamp.c
@@ -8,7 +8,7 @@
 
 #include "rockchip_canfd.h"
 
-static u64 rkcanfd_timestamp_read(const struct cyclecounter *cc)
+static u64 rkcanfd_timestamp_read(struct cyclecounter *cc)
 {
 	const struct rkcanfd_priv *priv = container_of(cc, struct rkcanfd_priv, cc);
 
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
index 202ca0d24d03..413a5cb75c13 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
@@ -11,7 +11,7 @@
 
 #include "mcp251xfd.h"
 
-static u64 mcp251xfd_timestamp_raw_read(const struct cyclecounter *cc)
+static u64 mcp251xfd_timestamp_raw_read(struct cyclecounter *cc)
 {
 	const struct mcp251xfd_priv *priv;
 	u32 ts_raw = 0;
diff --git a/drivers/net/can/usb/gs_usb.c b/drivers/net/can/usb/gs_usb.c
index bb6335278e46..c9482d6e947b 100644
--- a/drivers/net/can/usb/gs_usb.c
+++ b/drivers/net/can/usb/gs_usb.c
@@ -420,7 +420,7 @@ static inline int gs_usb_get_timestamp(const struct gs_usb *parent,
 	return 0;
 }
 
-static u64 gs_usb_timestamp_read(const struct cyclecounter *cc) __must_hold(&dev->tc_lock)
+static u64 gs_usb_timestamp_read(struct cyclecounter *cc) __must_hold(&dev->tc_lock)
 {
 	struct gs_usb *parent = container_of(cc, struct gs_usb, cc);
 	u32 timestamp = 0;
diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h
index 7d00482f53a3..feddf505c918 100644
--- a/drivers/net/dsa/mv88e6xxx/chip.h
+++ b/drivers/net/dsa/mv88e6xxx/chip.h
@@ -732,7 +732,7 @@ struct mv88e6xxx_avb_ops {
 };
 
 struct mv88e6xxx_ptp_ops {
-	u64 (*clock_read)(const struct cyclecounter *cc);
+	u64 (*clock_read)(struct cyclecounter *cc);
 	int (*ptp_enable)(struct ptp_clock_info *ptp,
 			  struct ptp_clock_request *rq, int on);
 	int (*ptp_verify)(struct ptp_clock_info *ptp, unsigned int pin,
diff --git a/drivers/net/dsa/mv88e6xxx/ptp.c b/drivers/net/dsa/mv88e6xxx/ptp.c
index 1d3b2c94c53e..e8c9207e932e 100644
--- a/drivers/net/dsa/mv88e6xxx/ptp.c
+++ b/drivers/net/dsa/mv88e6xxx/ptp.c
@@ -138,7 +138,7 @@ mv88e6xxx_cc_coeff_get(struct mv88e6xxx_chip *chip)
 	}
 }
 
-static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
+static u64 mv88e6352_ptp_clock_read(struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
 	u16 phc_time[2];
@@ -152,7 +152,7 @@ static u64 mv88e6352_ptp_clock_read(const struct cyclecounter *cc)
 		return ((u32)phc_time[1] << 16) | phc_time[0];
 }
 
-static u64 mv88e6165_ptp_clock_read(const struct cyclecounter *cc)
+static u64 mv88e6165_ptp_clock_read(struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
 	u16 phc_time[2];
@@ -483,7 +483,7 @@ const struct mv88e6xxx_ptp_ops mv88e6390_ptp_ops = {
 		(1 << HWTSTAMP_FILTER_PTP_V2_DELAY_REQ),
 };
 
-static u64 mv88e6xxx_ptp_clock_read(const struct cyclecounter *cc)
+static u64 mv88e6xxx_ptp_clock_read(struct cyclecounter *cc)
 {
 	struct mv88e6xxx_chip *chip = cc_to_chip(cc);
 
diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
index 978c4dd01fa0..e8d5c05de77a 100644
--- a/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
+++ b/drivers/net/ethernet/amd/xgbe/xgbe-ptp.c
@@ -13,7 +13,7 @@
 #include "xgbe.h"
 #include "xgbe-common.h"
 
-static u64 xgbe_cc_read(const struct cyclecounter *cc)
+static u64 xgbe_cc_read(struct cyclecounter *cc)
 {
 	struct xgbe_prv_data *pdata = container_of(cc,
 						   struct xgbe_prv_data,
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
index c9a1a1d504c0..48ad2d6e125b 100644
--- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
+++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c
@@ -15176,7 +15176,7 @@ void bnx2x_set_rx_ts(struct bnx2x *bp, struct sk_buff *skb)
 }
 
 /* Read the PHC */
-static u64 bnx2x_cyclecounter_read(const struct cyclecounter *cc)
+static u64 bnx2x_cyclecounter_read(struct cyclecounter *cc)
 {
 	struct bnx2x *bp = container_of(cc, struct bnx2x, cyclecounter);
 	int port = BP_PORT(bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 0669d43472f5..7542b6d2568b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -702,7 +702,7 @@ static void bnxt_unmap_ptp_regs(struct bnxt *bp)
 		  (BNXT_PTP_GRC_WIN - 1) * 4);
 }
 
-static u64 bnxt_cc_read(const struct cyclecounter *cc)
+static u64 bnxt_cc_read(struct cyclecounter *cc)
 {
 	struct bnxt_ptp_cfg *ptp = container_of(cc, struct bnxt_ptp_cfg, cc);
 	u64 ns = 0;
diff --git a/drivers/net/ethernet/cavium/common/cavium_ptp.c b/drivers/net/ethernet/cavium/common/cavium_ptp.c
index 984f0dd7b62e..61e261657073 100644
--- a/drivers/net/ethernet/cavium/common/cavium_ptp.c
+++ b/drivers/net/ethernet/cavium/common/cavium_ptp.c
@@ -209,7 +209,7 @@ static int cavium_ptp_enable(struct ptp_clock_info *ptp_info,
 	return -EOPNOTSUPP;
 }
 
-static u64 cavium_ptp_cc_read(const struct cyclecounter *cc)
+static u64 cavium_ptp_cc_read(struct cyclecounter *cc)
 {
 	struct cavium_ptp *clock =
 		container_of(cc, struct cavium_ptp, cycle_counter);
diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
index 876d90832596..c28ca17a81fd 100644
--- a/drivers/net/ethernet/freescale/fec_ptp.c
+++ b/drivers/net/ethernet/freescale/fec_ptp.c
@@ -96,7 +96,7 @@
  * cyclecounter structure used to construct a ns counter from the
  * arbitrary fixed point registers
  */
-static u64 fec_ptp_read(const struct cyclecounter *cc)
+static u64 fec_ptp_read(struct cyclecounter *cc)
 {
 	struct fec_enet_private *fep =
 		container_of(cc, struct fec_enet_private, cc);
diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c
index 7719e15813ee..b27a61fab371 100644
--- a/drivers/net/ethernet/intel/e1000e/netdev.c
+++ b/drivers/net/ethernet/intel/e1000e/netdev.c
@@ -4436,7 +4436,7 @@ u64 e1000e_read_systim(struct e1000_adapter *adapter,
  * e1000e_cyclecounter_read - read raw cycle counter (used by time counter)
  * @cc: cyclecounter structure
  **/
-static u64 e1000e_cyclecounter_read(const struct cyclecounter *cc)
+static u64 e1000e_cyclecounter_read(struct cyclecounter *cc)
 {
 	struct e1000_adapter *adapter = container_of(cc, struct e1000_adapter,
 						     cc);
diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c
index 793c96016288..2f1fae2bcdd2 100644
--- a/drivers/net/ethernet/intel/igb/igb_ptp.c
+++ b/drivers/net/ethernet/intel/igb/igb_ptp.c
@@ -73,7 +73,7 @@ static void igb_ptp_tx_hwtstamp(struct igb_adapter *adapter);
 static void igb_ptp_sdp_init(struct igb_adapter *adapter);
 
 /* SYSTIM read access for the 82576 */
-static u64 igb_ptp_read_82576(const struct cyclecounter *cc)
+static u64 igb_ptp_read_82576(struct cyclecounter *cc)
 {
 	struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc);
 	struct e1000_hw *hw = &igb->hw;
@@ -90,7 +90,7 @@ static u64 igb_ptp_read_82576(const struct cyclecounter *cc)
 }
 
 /* SYSTIM read access for the 82580 */
-static u64 igb_ptp_read_82580(const struct cyclecounter *cc)
+static u64 igb_ptp_read_82580(struct cyclecounter *cc)
 {
 	struct igb_adapter *igb = container_of(cc, struct igb_adapter, cc);
 	struct e1000_hw *hw = &igb->hw;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
index eef25e11d938..eafb61415bd1 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c
@@ -327,7 +327,7 @@ static void ixgbe_ptp_setup_sdp_X550(struct ixgbe_adapter *adapter)
  * result of SYSTIME is 32bits of "billions of cycles" and 32 bits of
  * "cycles", rather than seconds and nanoseconds.
  */
-static u64 ixgbe_ptp_read_X550(const struct cyclecounter *cc)
+static u64 ixgbe_ptp_read_X550(struct cyclecounter *cc)
 {
 	struct ixgbe_adapter *adapter =
 		container_of(cc, struct ixgbe_adapter, hw_cc);
@@ -364,7 +364,7 @@ static u64 ixgbe_ptp_read_X550(const struct cyclecounter *cc)
  * cyclecounter structure used to construct a ns counter from the
  * arbitrary fixed point registers
  */
-static u64 ixgbe_ptp_read_82599(const struct cyclecounter *cc)
+static u64 ixgbe_ptp_read_82599(struct cyclecounter *cc)
 {
 	struct ixgbe_adapter *adapter =
 		container_of(cc, struct ixgbe_adapter, hw_cc);
diff --git a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
index 63130ba37e9d..e52cc6b1a26c 100644
--- a/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
+++ b/drivers/net/ethernet/marvell/octeontx2/nic/otx2_ptp.c
@@ -193,7 +193,7 @@ static int ptp_pps_on(struct otx2_ptp *ptp, int on, u64 period)
 	return otx2_sync_mbox_msg(&ptp->nic->mbox);
 }
 
-static u64 ptp_cc_read(const struct cyclecounter *cc)
+static u64 ptp_cc_read(struct cyclecounter *cc)
 {
 	struct otx2_ptp *ptp = container_of(cc, struct otx2_ptp, cycle_counter);
 
diff --git a/drivers/net/ethernet/mellanox/mlx4/en_clock.c b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
index d73a2044dc26..2aeaafcfb993 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_clock.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_clock.c
@@ -38,7 +38,7 @@
 
 /* mlx4_en_read_clock - read raw cycle counter (to be used by time counter)
  */
-static u64 mlx4_en_read_clock(const struct cyclecounter *tc)
+static u64 mlx4_en_read_clock(struct cyclecounter *tc)
 {
 	struct mlx4_en_dev *mdev =
 		container_of(tc, struct mlx4_en_dev, cycles);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
index cec18efadc73..214d732d18e9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/clock.c
@@ -343,7 +343,7 @@ static u64 mlx5_read_time(struct mlx5_core_dev *dev,
 			   (u64)timer_l | (u64)timer_h1 << 32;
 }
 
-static u64 read_internal_timer(const struct cyclecounter *cc)
+static u64 read_internal_timer(struct cyclecounter *cc)
 {
 	struct mlx5_timer *timer = container_of(cc, struct mlx5_timer, cycles);
 	struct mlx5_clock *clock = container_of(timer, struct mlx5_clock, timer);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
index e8182dd76c7d..5b9f0844b8f6 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_ptp.c
@@ -131,7 +131,7 @@ static u64 __mlxsw_sp1_ptp_read_frc(struct mlxsw_sp1_ptp_clock *clock,
 	return (u64) frc_l | (u64) frc_h2 << 32;
 }
 
-static u64 mlxsw_sp1_ptp_read_frc(const struct cyclecounter *cc)
+static u64 mlxsw_sp1_ptp_read_frc(struct cyclecounter *cc)
 {
 	struct mlxsw_sp1_ptp_clock *clock =
 		container_of(cc, struct mlxsw_sp1_ptp_clock, cycles);
diff --git a/drivers/net/ethernet/pensando/ionic/ionic_phc.c b/drivers/net/ethernet/pensando/ionic/ionic_phc.c
index 7505efdff8e9..9f5c81d44f99 100644
--- a/drivers/net/ethernet/pensando/ionic/ionic_phc.c
+++ b/drivers/net/ethernet/pensando/ionic/ionic_phc.c
@@ -290,7 +290,7 @@ static u64 ionic_hwstamp_read(struct ionic *ionic,
 	return (u64)tick_low | ((u64)tick_high << 32);
 }
 
-static u64 ionic_cc_read(const struct cyclecounter *cc)
+static u64 ionic_cc_read(struct cyclecounter *cc)
 {
 	struct ionic_phc *phc = container_of(cc, struct ionic_phc, cc);
 	struct ionic *ionic = phc->lif->ionic;
diff --git a/drivers/net/ethernet/qlogic/qede/qede_ptp.c b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
index 9d6399a5c780..a38f1e72c62b 100644
--- a/drivers/net/ethernet/qlogic/qede/qede_ptp.c
+++ b/drivers/net/ethernet/qlogic/qede/qede_ptp.c
@@ -181,7 +181,7 @@ static void qede_ptp_task(struct work_struct *work)
 }
 
 /* Read the PHC. This API is invoked with ptp_lock held. */
-static u64 qede_ptp_read_cc(const struct cyclecounter *cc)
+static u64 qede_ptp_read_cc(struct cyclecounter *cc)
 {
 	struct qede_dev *edev;
 	struct qede_ptp *ptp;
diff --git a/drivers/net/ethernet/ti/cpts.c b/drivers/net/ethernet/ti/cpts.c
index dbbea9146040..2ba4c8795d60 100644
--- a/drivers/net/ethernet/ti/cpts.c
+++ b/drivers/net/ethernet/ti/cpts.c
@@ -181,7 +181,7 @@ void cpts_misc_interrupt(struct cpts *cpts)
 }
 EXPORT_SYMBOL_GPL(cpts_misc_interrupt);
 
-static u64 cpts_systim_read(const struct cyclecounter *cc)
+static u64 cpts_systim_read(struct cyclecounter *cc)
 {
 	struct cpts *cpts = container_of(cc, struct cpts, cc);
 
diff --git a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
index 2c39b879f977..44f3e6505246 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_ptp.c
@@ -652,7 +652,7 @@ static int wx_ptp_set_timestamp_mode(struct wx *wx,
 	return 0;
 }
 
-static u64 wx_ptp_read(const struct cyclecounter *hw_cc)
+static u64 wx_ptp_read(struct cyclecounter *hw_cc)
 {
 	struct wx *wx = container_of(hw_cc, struct wx, hw_cc);
 
diff --git a/drivers/ptp/ptp_mock.c b/drivers/ptp/ptp_mock.c
index e7b459c846a2..bbd14ce24b34 100644
--- a/drivers/ptp/ptp_mock.c
+++ b/drivers/ptp/ptp_mock.c
@@ -41,7 +41,7 @@ struct mock_phc {
 	spinlock_t lock;
 };
 
-static u64 mock_phc_cc_read(const struct cyclecounter *cc)
+static u64 mock_phc_cc_read(struct cyclecounter *cc)
 {
 	return ktime_get_raw_ns();
 }
diff --git a/drivers/ptp/ptp_vclock.c b/drivers/ptp/ptp_vclock.c
index 7febfdcbde8b..2fdeedd60e21 100644
--- a/drivers/ptp/ptp_vclock.c
+++ b/drivers/ptp/ptp_vclock.c
@@ -164,7 +164,7 @@ static const struct ptp_clock_info ptp_vclock_info = {
 	.do_aux_work	= ptp_vclock_refresh,
 };
 
-static u64 ptp_vclock_read(const struct cyclecounter *cc)
+static u64 ptp_vclock_read(struct cyclecounter *cc)
 {
 	struct ptp_vclock *vclock = cc_to_vclock(cc);
 	struct ptp_clock *ptp = vclock->pclock;
diff --git a/include/linux/timecounter.h b/include/linux/timecounter.h
index 0982d1d52b24..dce03a5cafb7 100644
--- a/include/linux/timecounter.h
+++ b/include/linux/timecounter.h
@@ -28,7 +28,7 @@
  * @shift:		cycle to nanosecond divisor (power of two)
  */
 struct cyclecounter {
-	u64 (*read)(const struct cyclecounter *cc);
+	u64 (*read)(struct cyclecounter *cc);
 	u64 mask;
 	u32 mult;
 	u32 shift;
@@ -53,7 +53,7 @@ struct cyclecounter {
  * @frac:		accumulated fractional nanoseconds
  */
 struct timecounter {
-	const struct cyclecounter *cc;
+	struct cyclecounter *cc;
 	u64 cycle_last;
 	u64 nsec;
 	u64 mask;
@@ -100,7 +100,7 @@ static inline void timecounter_adjtime(struct timecounter *tc, s64 delta)
  * the time stamp counter by the number of elapsed nanoseconds.
  */
 extern void timecounter_init(struct timecounter *tc,
-			     const struct cyclecounter *cc,
+			     struct cyclecounter *cc,
 			     u64 start_tstamp);
 
 /**
diff --git a/kernel/time/timecounter.c b/kernel/time/timecounter.c
index e6285288d765..3d2a354cfe1c 100644
--- a/kernel/time/timecounter.c
+++ b/kernel/time/timecounter.c
@@ -6,7 +6,7 @@
 #include <linux/timecounter.h>
 
 void timecounter_init(struct timecounter *tc,
-		      const struct cyclecounter *cc,
+		      struct cyclecounter *cc,
 		      u64 start_tstamp)
 {
 	tc->cc = cc;
diff --git a/sound/hda/hdac_stream.c b/sound/hda/hdac_stream.c
index e7f6208af5b0..4a87bef8834f 100644
--- a/sound/hda/hdac_stream.c
+++ b/sound/hda/hdac_stream.c
@@ -634,7 +634,7 @@ int snd_hdac_stream_set_params(struct hdac_stream *azx_dev,
 }
 EXPORT_SYMBOL_GPL(snd_hdac_stream_set_params);
 
-static u64 azx_cc_read(const struct cyclecounter *cc)
+static u64 azx_cc_read(struct cyclecounter *cc)
 {
 	struct hdac_stream *azx_dev = container_of(cc, struct hdac_stream, cc);
 
-- 
cgit v1.2.3


From b9f58d3572a8e1ef707b941eae58ec4014b9269d Mon Sep 17 00:00:00 2001
From: Li Chen <chenl311@chinatelecom.cn>
Date: Fri, 20 Jun 2025 21:13:07 +0800
Subject: ACPI: Return -ENODEV from acpi_parse_spcr() when SPCR support is
 disabled

If CONFIG_ACPI_SPCR_TABLE is disabled, acpi_parse_spcr()
currently returns 0, which may incorrectly suggest that
SPCR parsing was successful. This patch changes the behavior
to return -ENODEV to clearly indicate that SPCR support
is not available.

This prepares the codebase for future changes that depend
on acpi_parse_spcr() failure detection, such as suppressing
misleading console messages.

Signed-off-by: Li Chen <chenl311@chinatelecom.cn>
Acked-by: Hanjun Guo <guohanjun@huawei.com>
Link: https://lore.kernel.org/r/20250620131309.126555-2-me@linux.beauty
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
---
 include/linux/acpi.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index f102c0fe3431..71e692f95290 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -1503,7 +1503,7 @@ int acpi_parse_spcr(bool enable_earlycon, bool enable_console);
 #else
 static inline int acpi_parse_spcr(bool enable_earlycon, bool enable_console)
 {
-	return 0;
+	return -ENODEV;
 }
 #endif
 
-- 
cgit v1.2.3


From 536f5941adde41c99a18a0ba03b457adc9702ab8 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 27 Jun 2025 17:19:23 +0300
Subject: libnvdimm: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

While doing that, sort headers alphabetically.

Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20250627142001.994860-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Ira Weiny <ira.weiny@intel.com>
---
 include/linux/libnvdimm.h | 15 ++++++++++-----
 1 file changed, 10 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/libnvdimm.h b/include/linux/libnvdimm.h
index e772aae71843..28f086c4a187 100644
--- a/include/linux/libnvdimm.h
+++ b/include/linux/libnvdimm.h
@@ -6,12 +6,12 @@
  */
 #ifndef __LIBNVDIMM_H__
 #define __LIBNVDIMM_H__
-#include <linux/kernel.h>
+
+#include <linux/io.h>
 #include <linux/sizes.h>
+#include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/uuid.h>
-#include <linux/spinlock.h>
-#include <linux/bio.h>
 
 struct badrange_entry {
 	u64 start;
@@ -80,7 +80,9 @@ typedef int (*ndctl_fn)(struct nvdimm_bus_descriptor *nd_desc,
 		struct nvdimm *nvdimm, unsigned int cmd, void *buf,
 		unsigned int buf_len, int *cmd_rc);
 
+struct attribute_group;
 struct device_node;
+struct module;
 struct nvdimm_bus_descriptor {
 	const struct attribute_group **attr_groups;
 	unsigned long cmd_mask;
@@ -121,6 +123,8 @@ struct nd_mapping_desc {
 	int position;
 };
 
+struct bio;
+struct resource;
 struct nd_region;
 struct nd_region_desc {
 	struct resource *res;
@@ -147,8 +151,6 @@ static inline void __iomem *devm_nvdimm_ioremap(struct device *dev,
 	return (void __iomem *) devm_nvdimm_memremap(dev, offset, size, 0);
 }
 
-struct nvdimm_bus;
-
 /*
  * Note that separate bits for locked + unlocked are defined so that
  * 'flags == 0' corresponds to an error / not-supported state.
@@ -238,6 +240,9 @@ struct nvdimm_fw_ops {
 	int (*arm)(struct nvdimm *nvdimm, enum nvdimm_fwa_trigger arg);
 };
 
+struct kobject;
+struct nvdimm_bus;
+
 void badrange_init(struct badrange *badrange);
 int badrange_add(struct badrange *badrange, u64 addr, u64 length);
 void badrange_forget(struct badrange *badrange, phys_addr_t start,
-- 
cgit v1.2.3


From b6139a6abf673029008f80d42abd3848d80a9108 Mon Sep 17 00:00:00 2001
From: Daniel Wagner <wagi@kernel.org>
Date: Tue, 17 Jun 2025 15:43:23 +0200
Subject: lib/group_cpus: Let group_cpu_evenly() return the number of
 initialized masks

group_cpu_evenly() might have allocated less groups then requested:

group_cpu_evenly()
  __group_cpus_evenly()
    alloc_nodes_groups()
      # allocated total groups may be less than numgrps when
      # active total CPU number is less then numgrps

In this case, the caller will do an out of bound access because the
caller assumes the masks returned has numgrps.

Return the number of groups created so the caller can limit the access
range accordingly.

Acked-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250617-isolcpus-queue-counters-v1-1-13923686b54b@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-cpumap.c        |  6 +++---
 drivers/virtio/virtio_vdpa.c |  9 +++++----
 fs/fuse/virtio_fs.c          |  6 +++---
 include/linux/group_cpus.h   |  2 +-
 kernel/irq/affinity.c        | 11 +++++------
 lib/group_cpus.c             | 16 ++++++++--------
 6 files changed, 25 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 444798c5374f..269161252add 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -19,9 +19,9 @@
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 {
 	const struct cpumask *masks;
-	unsigned int queue, cpu;
+	unsigned int queue, cpu, nr_masks;
 
-	masks = group_cpus_evenly(qmap->nr_queues);
+	masks = group_cpus_evenly(qmap->nr_queues, &nr_masks);
 	if (!masks) {
 		for_each_possible_cpu(cpu)
 			qmap->mq_map[cpu] = qmap->queue_offset;
@@ -29,7 +29,7 @@ void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 	}
 
 	for (queue = 0; queue < qmap->nr_queues; queue++) {
-		for_each_cpu(cpu, &masks[queue])
+		for_each_cpu(cpu, &masks[queue % nr_masks])
 			qmap->mq_map[cpu] = qmap->queue_offset + queue;
 	}
 	kfree(masks);
diff --git a/drivers/virtio/virtio_vdpa.c b/drivers/virtio/virtio_vdpa.c
index 1f60c9d5cb18..a7b297dae489 100644
--- a/drivers/virtio/virtio_vdpa.c
+++ b/drivers/virtio/virtio_vdpa.c
@@ -329,20 +329,21 @@ create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
 
 	for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
 		unsigned int this_vecs = affd->set_size[i];
+		unsigned int nr_masks;
 		int j;
-		struct cpumask *result = group_cpus_evenly(this_vecs);
+		struct cpumask *result = group_cpus_evenly(this_vecs, &nr_masks);
 
 		if (!result) {
 			kfree(masks);
 			return NULL;
 		}
 
-		for (j = 0; j < this_vecs; j++)
+		for (j = 0; j < nr_masks; j++)
 			cpumask_copy(&masks[curvec + j], &result[j]);
 		kfree(result);
 
-		curvec += this_vecs;
-		usedvecs += this_vecs;
+		curvec += nr_masks;
+		usedvecs += nr_masks;
 	}
 
 	/* Fill out vectors at the end that don't need affinity */
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 53c2626e90e7..3fbfb1a2942b 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -862,7 +862,7 @@ static void virtio_fs_requests_done_work(struct work_struct *work)
 static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *fs)
 {
 	const struct cpumask *mask, *masks;
-	unsigned int q, cpu;
+	unsigned int q, cpu, nr_masks;
 
 	/* First attempt to map using existing transport layer affinities
 	 * e.g. PCIe MSI-X
@@ -882,7 +882,7 @@ static void virtio_fs_map_queues(struct virtio_device *vdev, struct virtio_fs *f
 	return;
 fallback:
 	/* Attempt to map evenly in groups over the CPUs */
-	masks = group_cpus_evenly(fs->num_request_queues);
+	masks = group_cpus_evenly(fs->num_request_queues, &nr_masks);
 	/* If even this fails we default to all CPUs use first request queue */
 	if (!masks) {
 		for_each_possible_cpu(cpu)
@@ -891,7 +891,7 @@ fallback:
 	}
 
 	for (q = 0; q < fs->num_request_queues; q++) {
-		for_each_cpu(cpu, &masks[q])
+		for_each_cpu(cpu, &masks[q % nr_masks])
 			fs->mq_map[cpu] = q + VQ_REQUEST;
 	}
 	kfree(masks);
diff --git a/include/linux/group_cpus.h b/include/linux/group_cpus.h
index e42807ec61f6..9d4e5ab6c314 100644
--- a/include/linux/group_cpus.h
+++ b/include/linux/group_cpus.h
@@ -9,6 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/cpu.h>
 
-struct cpumask *group_cpus_evenly(unsigned int numgrps);
+struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks);
 
 #endif
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 44a4eba80315..4013e6ad2b2f 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -69,21 +69,20 @@ irq_create_affinity_masks(unsigned int nvecs, struct irq_affinity *affd)
 	 * have multiple sets, build each sets affinity mask separately.
 	 */
 	for (i = 0, usedvecs = 0; i < affd->nr_sets; i++) {
-		unsigned int this_vecs = affd->set_size[i];
-		int j;
-		struct cpumask *result = group_cpus_evenly(this_vecs);
+		unsigned int nr_masks, this_vecs = affd->set_size[i];
+		struct cpumask *result = group_cpus_evenly(this_vecs, &nr_masks);
 
 		if (!result) {
 			kfree(masks);
 			return NULL;
 		}
 
-		for (j = 0; j < this_vecs; j++)
+		for (int j = 0; j < nr_masks; j++)
 			cpumask_copy(&masks[curvec + j].mask, &result[j]);
 		kfree(result);
 
-		curvec += this_vecs;
-		usedvecs += this_vecs;
+		curvec += nr_masks;
+		usedvecs += nr_masks;
 	}
 
 	/* Fill out vectors at the end that don't need affinity */
diff --git a/lib/group_cpus.c b/lib/group_cpus.c
index 18d43a406114..6d08ac05f371 100644
--- a/lib/group_cpus.c
+++ b/lib/group_cpus.c
@@ -332,9 +332,11 @@ static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps,
 /**
  * group_cpus_evenly - Group all CPUs evenly per NUMA/CPU locality
  * @numgrps: number of groups
+ * @nummasks: number of initialized cpumasks
  *
  * Return: cpumask array if successful, NULL otherwise. And each element
- * includes CPUs assigned to this group
+ * includes CPUs assigned to this group. nummasks contains the number
+ * of initialized masks which can be less than numgrps.
  *
  * Try to put close CPUs from viewpoint of CPU and NUMA locality into
  * same group, and run two-stage grouping:
@@ -344,7 +346,7 @@ static int __group_cpus_evenly(unsigned int startgrp, unsigned int numgrps,
  * We guarantee in the resulted grouping that all CPUs are covered, and
  * no same CPU is assigned to multiple groups
  */
-struct cpumask *group_cpus_evenly(unsigned int numgrps)
+struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks)
 {
 	unsigned int curgrp = 0, nr_present = 0, nr_others = 0;
 	cpumask_var_t *node_to_cpumask;
@@ -389,7 +391,7 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 	ret = __group_cpus_evenly(curgrp, numgrps, node_to_cpumask,
 				  npresmsk, nmsk, masks);
 	if (ret < 0)
-		goto fail_build_affinity;
+		goto fail_node_to_cpumask;
 	nr_present = ret;
 
 	/*
@@ -408,10 +410,6 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 	if (ret >= 0)
 		nr_others = ret;
 
- fail_build_affinity:
-	if (ret >= 0)
-		WARN_ON(nr_present + nr_others < numgrps);
-
  fail_node_to_cpumask:
 	free_node_to_cpumask(node_to_cpumask);
 
@@ -424,10 +422,11 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 		kfree(masks);
 		return NULL;
 	}
+	*nummasks = min(nr_present + nr_others, numgrps);
 	return masks;
 }
 #else /* CONFIG_SMP */
-struct cpumask *group_cpus_evenly(unsigned int numgrps)
+struct cpumask *group_cpus_evenly(unsigned int numgrps, unsigned int *nummasks)
 {
 	struct cpumask *masks;
 
@@ -440,6 +439,7 @@ struct cpumask *group_cpus_evenly(unsigned int numgrps)
 
 	/* assign all CPUs(cpu 0) to the 1st group only */
 	cpumask_copy(&masks[0], cpu_possible_mask);
+	*nummasks = 1;
 	return masks;
 }
 #endif /* CONFIG_SMP */
-- 
cgit v1.2.3


From 3f27c1de5df265f9d8edf0cc5d75dc92e328484a Mon Sep 17 00:00:00 2001
From: Daniel Wagner <wagi@kernel.org>
Date: Tue, 17 Jun 2025 15:43:24 +0200
Subject: blk-mq: add number of queue calc helper

Add two variants of helper functions that calculate the correct number
of queues to use. Two variants are needed because some drivers base
their maximum number of queues on the possible CPU mask, while others
use the online CPU mask.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Reviewed-by: Ming Lei <ming.lei@redhat.com>
Signed-off-by: Daniel Wagner <wagi@kernel.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Link: https://lore.kernel.org/r/20250617-isolcpus-queue-counters-v1-2-13923686b54b@kernel.org
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/blk-mq-cpumap.c  | 40 ++++++++++++++++++++++++++++++++++++++++
 include/linux/blk-mq.h |  2 ++
 2 files changed, 42 insertions(+)

(limited to 'include/linux')

diff --git a/block/blk-mq-cpumap.c b/block/blk-mq-cpumap.c
index 269161252add..705da074ad6c 100644
--- a/block/blk-mq-cpumap.c
+++ b/block/blk-mq-cpumap.c
@@ -12,10 +12,50 @@
 #include <linux/cpu.h>
 #include <linux/group_cpus.h>
 #include <linux/device/bus.h>
+#include <linux/sched/isolation.h>
 
 #include "blk.h"
 #include "blk-mq.h"
 
+static unsigned int blk_mq_num_queues(const struct cpumask *mask,
+				      unsigned int max_queues)
+{
+	unsigned int num;
+
+	num = cpumask_weight(mask);
+	return min_not_zero(num, max_queues);
+}
+
+/**
+ * blk_mq_num_possible_queues - Calc nr of queues for multiqueue devices
+ * @max_queues:	The maximum number of queues the hardware/driver
+ *		supports. If max_queues is 0, the argument is
+ *		ignored.
+ *
+ * Calculates the number of queues to be used for a multiqueue
+ * device based on the number of possible CPUs.
+ */
+unsigned int blk_mq_num_possible_queues(unsigned int max_queues)
+{
+	return blk_mq_num_queues(cpu_possible_mask, max_queues);
+}
+EXPORT_SYMBOL_GPL(blk_mq_num_possible_queues);
+
+/**
+ * blk_mq_num_online_queues - Calc nr of queues for multiqueue devices
+ * @max_queues:	The maximum number of queues the hardware/driver
+ *		supports. If max_queues is 0, the argument is
+ *		ignored.
+ *
+ * Calculates the number of queues to be used for a multiqueue
+ * device based on the number of online CPUs.
+ */
+unsigned int blk_mq_num_online_queues(unsigned int max_queues)
+{
+	return blk_mq_num_queues(cpu_online_mask, max_queues);
+}
+EXPORT_SYMBOL_GPL(blk_mq_num_online_queues);
+
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap)
 {
 	const struct cpumask *masks;
diff --git a/include/linux/blk-mq.h b/include/linux/blk-mq.h
index de8c85a03bb7..2a5a828f19a0 100644
--- a/include/linux/blk-mq.h
+++ b/include/linux/blk-mq.h
@@ -947,6 +947,8 @@ int blk_mq_freeze_queue_wait_timeout(struct request_queue *q,
 void blk_mq_unfreeze_queue_non_owner(struct request_queue *q);
 void blk_freeze_queue_start_non_owner(struct request_queue *q);
 
+unsigned int blk_mq_num_possible_queues(unsigned int max_queues);
+unsigned int blk_mq_num_online_queues(unsigned int max_queues);
 void blk_mq_map_queues(struct blk_mq_queue_map *qmap);
 void blk_mq_map_hw_queues(struct blk_mq_queue_map *qmap,
 			  struct device *dev, unsigned int offset);
-- 
cgit v1.2.3


From fc9a099567813a9fef0da07b94ecb8dee64703c4 Mon Sep 17 00:00:00 2001
From: Petr Tesarik <ptesarik@suse.com>
Date: Fri, 27 Jun 2025 12:10:11 +0200
Subject: docs: dma-api: add a kernel-doc comment for dma_pool_zalloc()

Document the dma_pool_zalloc() wrapper.

Signed-off-by: Petr Tesarik <ptesarik@suse.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Marek Szyprowski <m.szyprowski@samsung.com>
[jc: fixed up dma_pool_alloc() reference in dmapool.h]
Signed-off-by: Jonathan Corbet <corbet@lwn.net>
Link: https://lore.kernel.org/r/20250627101015.1600042-5-ptesarik@suse.com
---
 Documentation/core-api/mm-api.rst | 2 ++
 include/linux/dmapool.h           | 8 ++++++++
 2 files changed, 10 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index af8151db88b2..a61766328ac0 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -97,6 +97,8 @@ DMA pools
 .. kernel-doc:: mm/dmapool.c
    :export:
 
+.. kernel-doc:: include/linux/dmapool.h
+
 More Memory Management Functions
 ================================
 
diff --git a/include/linux/dmapool.h b/include/linux/dmapool.h
index 06c4de602b2f..7d40b51933d1 100644
--- a/include/linux/dmapool.h
+++ b/include/linux/dmapool.h
@@ -60,6 +60,14 @@ static inline struct dma_pool *dma_pool_create(const char *name,
 				    NUMA_NO_NODE);
 }
 
+/**
+ * dma_pool_zalloc - Get a zero-initialized block of DMA coherent memory.
+ * @pool: dma pool that will produce the block
+ * @mem_flags: GFP_* bitmask
+ * @handle: pointer to dma address of block
+ *
+ * Same as dma_pool_alloc(), but the returned memory is zeroed.
+ */
 static inline void *dma_pool_zalloc(struct dma_pool *pool, gfp_t mem_flags,
 				    dma_addr_t *handle)
 {
-- 
cgit v1.2.3


From 5e1e6ec2e346c0850f304c31abdef4158007474e Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:46 +0100
Subject: netfs: Merge i_size update functions

Netfslib has two functions for updating the i_size after a write: one for
buffered writes into the pagecache and one for direct/unbuffered writes.
However, what needs to be done is much the same in both cases, so merge
them together.

This does raise one question, though: should updating the i_size after a
direct write do the same estimated update of i_blocks as is done for
buffered writes.

Also get rid of the cleanup function pointer from netfs_io_request as it's
only used for direct write to update i_size; instead do the i_size setting
directly from write collection.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-12-dhowells@redhat.com
cc: Steve French <sfrench@samba.org>
cc: Paulo Alcantara <pc@manguebit.org>
cc: linux-cifs@vger.kernel.org
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/buffered_write.c | 36 +++++++++++++++++++++---------------
 fs/netfs/direct_write.c   | 19 -------------------
 fs/netfs/internal.h       |  6 ++++++
 fs/netfs/write_collect.c  |  6 ++++--
 include/linux/netfs.h     |  1 -
 5 files changed, 31 insertions(+), 37 deletions(-)

(limited to 'include/linux')

diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index b87ef3fe4ea4..f27ea5099a68 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -53,30 +53,38 @@ static struct folio *netfs_grab_folio_for_write(struct address_space *mapping,
  * data written into the pagecache until we can find out from the server what
  * the values actually are.
  */
-static void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
-				loff_t i_size, loff_t pos, size_t copied)
+void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
+			 loff_t pos, size_t copied)
 {
+	loff_t i_size, end = pos + copied;
 	blkcnt_t add;
 	size_t gap;
 
+	if (end <= i_size_read(inode))
+		return;
+
 	if (ctx->ops->update_i_size) {
-		ctx->ops->update_i_size(inode, pos);
+		ctx->ops->update_i_size(inode, end);
 		return;
 	}
 
 	spin_lock(&inode->i_lock);
-	i_size_write(inode, pos);
+
+	i_size = i_size_read(inode);
+	if (end > i_size) {
+		i_size_write(inode, end);
 #if IS_ENABLED(CONFIG_FSCACHE)
-	fscache_update_cookie(ctx->cache, NULL, &pos);
+		fscache_update_cookie(ctx->cache, NULL, &end);
 #endif
 
-	gap = SECTOR_SIZE - (i_size & (SECTOR_SIZE - 1));
-	if (copied > gap) {
-		add = DIV_ROUND_UP(copied - gap, SECTOR_SIZE);
+		gap = SECTOR_SIZE - (i_size & (SECTOR_SIZE - 1));
+		if (copied > gap) {
+			add = DIV_ROUND_UP(copied - gap, SECTOR_SIZE);
 
-		inode->i_blocks = min_t(blkcnt_t,
-					DIV_ROUND_UP(pos, SECTOR_SIZE),
-					inode->i_blocks + add);
+			inode->i_blocks = min_t(blkcnt_t,
+						DIV_ROUND_UP(end, SECTOR_SIZE),
+						inode->i_blocks + add);
+		}
 	}
 	spin_unlock(&inode->i_lock);
 }
@@ -113,7 +121,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 	struct folio *folio = NULL, *writethrough = NULL;
 	unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0;
 	ssize_t written = 0, ret, ret2;
-	loff_t i_size, pos = iocb->ki_pos;
+	loff_t pos = iocb->ki_pos;
 	size_t max_chunk = mapping_max_folio_size(mapping);
 	bool maybe_trouble = false;
 
@@ -346,10 +354,8 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
 		flush_dcache_folio(folio);
 
 		/* Update the inode size if we moved the EOF marker */
+		netfs_update_i_size(ctx, inode, pos, copied);
 		pos += copied;
-		i_size = i_size_read(inode);
-		if (pos > i_size)
-			netfs_update_i_size(ctx, inode, i_size, pos, copied);
 		written += copied;
 
 		if (likely(!wreq)) {
diff --git a/fs/netfs/direct_write.c b/fs/netfs/direct_write.c
index 3efa5894b2c0..dcf2b096cc4e 100644
--- a/fs/netfs/direct_write.c
+++ b/fs/netfs/direct_write.c
@@ -9,24 +9,6 @@
 #include <linux/uio.h>
 #include "internal.h"
 
-static void netfs_cleanup_dio_write(struct netfs_io_request *wreq)
-{
-	struct inode *inode = wreq->inode;
-	unsigned long long end = wreq->start + wreq->transferred;
-
-	if (wreq->error || end <= i_size_read(inode))
-		return;
-
-	spin_lock(&inode->i_lock);
-	if (end > i_size_read(inode)) {
-		if (wreq->netfs_ops->update_i_size)
-			wreq->netfs_ops->update_i_size(inode, end);
-		else
-			i_size_write(inode, end);
-	}
-	spin_unlock(&inode->i_lock);
-}
-
 /*
  * Perform an unbuffered write where we may have to do an RMW operation on an
  * encrypted file.  This can also be used for direct I/O writes.
@@ -102,7 +84,6 @@ ssize_t netfs_unbuffered_write_iter_locked(struct kiocb *iocb, struct iov_iter *
 	if (async)
 		wreq->iocb = iocb;
 	wreq->len = iov_iter_count(&wreq->buffer.iter);
-	wreq->cleanup = netfs_cleanup_dio_write;
 	ret = netfs_unbuffered_write(wreq, is_sync_kiocb(iocb), wreq->len);
 	if (ret < 0) {
 		_debug("begin = %zd", ret);
diff --git a/fs/netfs/internal.h b/fs/netfs/internal.h
index d6656d2b54ab..f9bb9464a147 100644
--- a/fs/netfs/internal.h
+++ b/fs/netfs/internal.h
@@ -27,6 +27,12 @@ void netfs_cache_read_terminated(void *priv, ssize_t transferred_or_error);
 int netfs_prefetch_for_write(struct file *file, struct folio *folio,
 			     size_t offset, size_t len);
 
+/*
+ * buffered_write.c
+ */
+void netfs_update_i_size(struct netfs_inode *ctx, struct inode *inode,
+			 loff_t pos, size_t copied);
+
 /*
  * main.c
  */
diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index 2ac85a819b71..33a93258f36e 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -393,8 +393,10 @@ bool netfs_write_collection(struct netfs_io_request *wreq)
 		ictx->ops->invalidate_cache(wreq);
 	}
 
-	if (wreq->cleanup)
-		wreq->cleanup(wreq);
+	if ((wreq->origin == NETFS_UNBUFFERED_WRITE ||
+	     wreq->origin == NETFS_DIO_WRITE) &&
+	    !wreq->error)
+		netfs_update_i_size(ictx, &ictx->inode, wreq->start, wreq->transferred);
 
 	if (wreq->origin == NETFS_DIO_WRITE &&
 	    wreq->mapping->nrpages) {
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 065c17385e53..d8186b90fb38 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -279,7 +279,6 @@ struct netfs_io_request {
 #define NETFS_RREQ_USE_PGPRIV2		31	/* [DEPRECATED] Use PG_private_2 to mark
 						 * write to cache on read */
 	const struct netfs_request_ops *netfs_ops;
-	void (*cleanup)(struct netfs_io_request *req);
 };
 
 /*
-- 
cgit v1.2.3


From 4e32541076833f5ce2e23523c9faa25f7b2cc96f Mon Sep 17 00:00:00 2001
From: David Howells <dhowells@redhat.com>
Date: Tue, 1 Jul 2025 17:38:47 +0100
Subject: netfs: Renumber the NETFS_RREQ_* flags to make traces easier to read

Renumber the NETFS_RREQ_* flags to put the most useful status bits in the
bottom nibble - and therefore the last hex digit in the trace output -
making it easier to grasp the state at a glance.

In particular, put the IN_PROGRESS flag in bit 0 and ALL_QUEUED at bit 1.

Also make the flags field in /proc/fs/netfs/requests larger to accommodate
all the flags.

Also make the flags field in the netfs_sreq tracepoint larger to
accommodate all the NETFS_SREQ_* flags.

Signed-off-by: David Howells <dhowells@redhat.com>
Link: https://lore.kernel.org/20250701163852.2171681-13-dhowells@redhat.com
Reviewed-by: Paulo Alcantara <pc@manguebit.org>
cc: netfs@lists.linux.dev
cc: linux-fsdevel@vger.kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/netfs/main.c              |  6 +++---
 include/linux/netfs.h        | 20 ++++++++++----------
 include/trace/events/netfs.h |  2 +-
 3 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/netfs/main.c b/fs/netfs/main.c
index 3db401d269e7..73da6c9f5777 100644
--- a/fs/netfs/main.c
+++ b/fs/netfs/main.c
@@ -58,15 +58,15 @@ static int netfs_requests_seq_show(struct seq_file *m, void *v)
 
 	if (v == &netfs_io_requests) {
 		seq_puts(m,
-			 "REQUEST  OR REF FL ERR  OPS COVERAGE\n"
-			 "======== == === == ==== === =========\n"
+			 "REQUEST  OR REF FLAG ERR  OPS COVERAGE\n"
+			 "======== == === ==== ==== === =========\n"
 			 );
 		return 0;
 	}
 
 	rreq = list_entry(v, struct netfs_io_request, proc_link);
 	seq_printf(m,
-		   "%08x %s %3d %2lx %4ld %3d @%04llx %llx/%llx",
+		   "%08x %s %3d %4lx %4ld %3d @%04llx %llx/%llx",
 		   rreq->debug_id,
 		   netfs_origins[rreq->origin],
 		   refcount_read(&rreq->ref),
diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index d8186b90fb38..f43f075852c0 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -265,17 +265,17 @@ struct netfs_io_request {
 	bool			direct_bv_unpin; /* T if direct_bv[] must be unpinned */
 	refcount_t		ref;
 	unsigned long		flags;
-#define NETFS_RREQ_OFFLOAD_COLLECTION	0	/* Offload collection to workqueue */
-#define NETFS_RREQ_NO_UNLOCK_FOLIO	2	/* Don't unlock no_unlock_folio on completion */
-#define NETFS_RREQ_FAILED		4	/* The request failed */
-#define NETFS_RREQ_IN_PROGRESS		5	/* Unlocked when the request completes (has ref) */
-#define NETFS_RREQ_FOLIO_COPY_TO_CACHE	6	/* Copy current folio to cache from read */
-#define NETFS_RREQ_UPLOAD_TO_SERVER	8	/* Need to write to the server */
-#define NETFS_RREQ_PAUSE		11	/* Pause subrequest generation */
+#define NETFS_RREQ_IN_PROGRESS		0	/* Unlocked when the request completes (has ref) */
+#define NETFS_RREQ_ALL_QUEUED		1	/* All subreqs are now queued */
+#define NETFS_RREQ_PAUSE		2	/* Pause subrequest generation */
+#define NETFS_RREQ_FAILED		3	/* The request failed */
+#define NETFS_RREQ_RETRYING		4	/* Set if we're in the retry path */
+#define NETFS_RREQ_SHORT_TRANSFER	5	/* Set if we have a short transfer */
+#define NETFS_RREQ_OFFLOAD_COLLECTION	8	/* Offload collection to workqueue */
+#define NETFS_RREQ_NO_UNLOCK_FOLIO	9	/* Don't unlock no_unlock_folio on completion */
+#define NETFS_RREQ_FOLIO_COPY_TO_CACHE	10	/* Copy current folio to cache from read */
+#define NETFS_RREQ_UPLOAD_TO_SERVER	11	/* Need to write to the server */
 #define NETFS_RREQ_USE_IO_ITER		12	/* Use ->io_iter rather than ->i_pages */
-#define NETFS_RREQ_ALL_QUEUED		13	/* All subreqs are now queued */
-#define NETFS_RREQ_RETRYING		14	/* Set if we're in the retry path */
-#define NETFS_RREQ_SHORT_TRANSFER	15	/* Set if we have a short transfer */
 #define NETFS_RREQ_USE_PGPRIV2		31	/* [DEPRECATED] Use PG_private_2 to mark
 						 * write to cache on read */
 	const struct netfs_request_ops *netfs_ops;
diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
index ba35dc66e986..c2d581429a7b 100644
--- a/include/trace/events/netfs.h
+++ b/include/trace/events/netfs.h
@@ -367,7 +367,7 @@ TRACE_EVENT(netfs_sreq,
 		    __entry->slot	= sreq->io_iter.folioq_slot;
 			   ),
 
-	    TP_printk("R=%08x[%x] %s %s f=%02x s=%llx %zx/%zx s=%u e=%d",
+	    TP_printk("R=%08x[%x] %s %s f=%03x s=%llx %zx/%zx s=%u e=%d",
 		      __entry->rreq, __entry->index,
 		      __print_symbolic(__entry->source, netfs_sreq_sources),
 		      __print_symbolic(__entry->what, netfs_sreq_traces),
-- 
cgit v1.2.3


From 2f952c9e8fe13c6ee15c05189f1f87c1a70b866c Mon Sep 17 00:00:00 2001
From: Andrey Albershteyn <aalbersh@kernel.org>
Date: Mon, 30 Jun 2025 18:20:11 +0200
Subject: fs: split fileattr related helpers into separate file

This patch moves function related to file extended attributes
manipulations to separate file. Refactoring only.

Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Link: https://lore.kernel.org/20250630-xattrat-syscall-v6-1-c4e3bc35227b@kernel.org
Reviewed-by: Amir Goldstein <amir73il@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/Makefile              |   3 +-
 fs/file_attr.c           | 319 +++++++++++++++++++++++++++++++++++++++++++++++
 fs/ioctl.c               | 309 ---------------------------------------------
 include/linux/fileattr.h |   4 +
 4 files changed, 325 insertions(+), 310 deletions(-)
 create mode 100644 fs/file_attr.c

(limited to 'include/linux')

diff --git a/fs/Makefile b/fs/Makefile
index 79c08b914c47..334654f9584b 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -15,7 +15,8 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		pnode.o splice.o sync.o utimes.o d_path.o \
 		stack.o fs_struct.o statfs.o fs_pin.o nsfs.o \
 		fs_types.o fs_context.o fs_parser.o fsopen.o init.o \
-		kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o
+		kernel_read_file.o mnt_idmapping.o remap_range.o pidfs.o \
+		file_attr.o
 
 obj-$(CONFIG_BUFFER_HEAD)	+= buffer.o mpage.o
 obj-$(CONFIG_PROC_FS)		+= proc_namespace.o
diff --git a/fs/file_attr.c b/fs/file_attr.c
new file mode 100644
index 000000000000..a4dd1d9646c8
--- /dev/null
+++ b/fs/file_attr.c
@@ -0,0 +1,319 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/fs.h>
+#include <linux/security.h>
+#include <linux/fscrypt.h>
+#include <linux/fileattr.h>
+#include <linux/export.h>
+
+/**
+ * fileattr_fill_xflags - initialize fileattr with xflags
+ * @fa:		fileattr pointer
+ * @xflags:	FS_XFLAG_* flags
+ *
+ * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags).  All
+ * other fields are zeroed.
+ */
+void fileattr_fill_xflags(struct fileattr *fa, u32 xflags)
+{
+	memset(fa, 0, sizeof(*fa));
+	fa->fsx_valid = true;
+	fa->fsx_xflags = xflags;
+	if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE)
+		fa->flags |= FS_IMMUTABLE_FL;
+	if (fa->fsx_xflags & FS_XFLAG_APPEND)
+		fa->flags |= FS_APPEND_FL;
+	if (fa->fsx_xflags & FS_XFLAG_SYNC)
+		fa->flags |= FS_SYNC_FL;
+	if (fa->fsx_xflags & FS_XFLAG_NOATIME)
+		fa->flags |= FS_NOATIME_FL;
+	if (fa->fsx_xflags & FS_XFLAG_NODUMP)
+		fa->flags |= FS_NODUMP_FL;
+	if (fa->fsx_xflags & FS_XFLAG_DAX)
+		fa->flags |= FS_DAX_FL;
+	if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT)
+		fa->flags |= FS_PROJINHERIT_FL;
+}
+EXPORT_SYMBOL(fileattr_fill_xflags);
+
+/**
+ * fileattr_fill_flags - initialize fileattr with flags
+ * @fa:		fileattr pointer
+ * @flags:	FS_*_FL flags
+ *
+ * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags).
+ * All other fields are zeroed.
+ */
+void fileattr_fill_flags(struct fileattr *fa, u32 flags)
+{
+	memset(fa, 0, sizeof(*fa));
+	fa->flags_valid = true;
+	fa->flags = flags;
+	if (fa->flags & FS_SYNC_FL)
+		fa->fsx_xflags |= FS_XFLAG_SYNC;
+	if (fa->flags & FS_IMMUTABLE_FL)
+		fa->fsx_xflags |= FS_XFLAG_IMMUTABLE;
+	if (fa->flags & FS_APPEND_FL)
+		fa->fsx_xflags |= FS_XFLAG_APPEND;
+	if (fa->flags & FS_NODUMP_FL)
+		fa->fsx_xflags |= FS_XFLAG_NODUMP;
+	if (fa->flags & FS_NOATIME_FL)
+		fa->fsx_xflags |= FS_XFLAG_NOATIME;
+	if (fa->flags & FS_DAX_FL)
+		fa->fsx_xflags |= FS_XFLAG_DAX;
+	if (fa->flags & FS_PROJINHERIT_FL)
+		fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
+}
+EXPORT_SYMBOL(fileattr_fill_flags);
+
+/**
+ * vfs_fileattr_get - retrieve miscellaneous file attributes
+ * @dentry:	the object to retrieve from
+ * @fa:		fileattr pointer
+ *
+ * Call i_op->fileattr_get() callback, if exists.
+ *
+ * Return: 0 on success, or a negative error on failure.
+ */
+int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+{
+	struct inode *inode = d_inode(dentry);
+
+	if (!inode->i_op->fileattr_get)
+		return -ENOIOCTLCMD;
+
+	return inode->i_op->fileattr_get(dentry, fa);
+}
+EXPORT_SYMBOL(vfs_fileattr_get);
+
+/**
+ * copy_fsxattr_to_user - copy fsxattr to userspace.
+ * @fa:		fileattr pointer
+ * @ufa:	fsxattr user pointer
+ *
+ * Return: 0 on success, or -EFAULT on failure.
+ */
+int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa)
+{
+	struct fsxattr xfa;
+
+	memset(&xfa, 0, sizeof(xfa));
+	xfa.fsx_xflags = fa->fsx_xflags;
+	xfa.fsx_extsize = fa->fsx_extsize;
+	xfa.fsx_nextents = fa->fsx_nextents;
+	xfa.fsx_projid = fa->fsx_projid;
+	xfa.fsx_cowextsize = fa->fsx_cowextsize;
+
+	if (copy_to_user(ufa, &xfa, sizeof(xfa)))
+		return -EFAULT;
+
+	return 0;
+}
+EXPORT_SYMBOL(copy_fsxattr_to_user);
+
+static int copy_fsxattr_from_user(struct fileattr *fa,
+				  struct fsxattr __user *ufa)
+{
+	struct fsxattr xfa;
+
+	if (copy_from_user(&xfa, ufa, sizeof(xfa)))
+		return -EFAULT;
+
+	fileattr_fill_xflags(fa, xfa.fsx_xflags);
+	fa->fsx_extsize = xfa.fsx_extsize;
+	fa->fsx_nextents = xfa.fsx_nextents;
+	fa->fsx_projid = xfa.fsx_projid;
+	fa->fsx_cowextsize = xfa.fsx_cowextsize;
+
+	return 0;
+}
+
+/*
+ * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject
+ * any invalid configurations.
+ *
+ * Note: must be called with inode lock held.
+ */
+static int fileattr_set_prepare(struct inode *inode,
+			      const struct fileattr *old_ma,
+			      struct fileattr *fa)
+{
+	int err;
+
+	/*
+	 * The IMMUTABLE and APPEND_ONLY flags can only be changed by
+	 * the relevant capability.
+	 */
+	if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) &&
+	    !capable(CAP_LINUX_IMMUTABLE))
+		return -EPERM;
+
+	err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags);
+	if (err)
+		return err;
+
+	/*
+	 * Project Quota ID state is only allowed to change from within the init
+	 * namespace. Enforce that restriction only if we are trying to change
+	 * the quota ID state. Everything else is allowed in user namespaces.
+	 */
+	if (current_user_ns() != &init_user_ns) {
+		if (old_ma->fsx_projid != fa->fsx_projid)
+			return -EINVAL;
+		if ((old_ma->fsx_xflags ^ fa->fsx_xflags) &
+				FS_XFLAG_PROJINHERIT)
+			return -EINVAL;
+	} else {
+		/*
+		 * Caller is allowed to change the project ID. If it is being
+		 * changed, make sure that the new value is valid.
+		 */
+		if (old_ma->fsx_projid != fa->fsx_projid &&
+		    !projid_valid(make_kprojid(&init_user_ns, fa->fsx_projid)))
+			return -EINVAL;
+	}
+
+	/* Check extent size hints. */
+	if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode))
+		return -EINVAL;
+
+	if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
+			!S_ISDIR(inode->i_mode))
+		return -EINVAL;
+
+	if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) &&
+	    !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
+		return -EINVAL;
+
+	/*
+	 * It is only valid to set the DAX flag on regular files and
+	 * directories on filesystems.
+	 */
+	if ((fa->fsx_xflags & FS_XFLAG_DAX) &&
+	    !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
+		return -EINVAL;
+
+	/* Extent size hints of zero turn off the flags. */
+	if (fa->fsx_extsize == 0)
+		fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT);
+	if (fa->fsx_cowextsize == 0)
+		fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE;
+
+	return 0;
+}
+
+/**
+ * vfs_fileattr_set - change miscellaneous file attributes
+ * @idmap:	idmap of the mount
+ * @dentry:	the object to change
+ * @fa:		fileattr pointer
+ *
+ * After verifying permissions, call i_op->fileattr_set() callback, if
+ * exists.
+ *
+ * Verifying attributes involves retrieving current attributes with
+ * i_op->fileattr_get(), this also allows initializing attributes that have
+ * not been set by the caller to current values.  Inode lock is held
+ * thoughout to prevent racing with another instance.
+ *
+ * Return: 0 on success, or a negative error on failure.
+ */
+int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry,
+		     struct fileattr *fa)
+{
+	struct inode *inode = d_inode(dentry);
+	struct fileattr old_ma = {};
+	int err;
+
+	if (!inode->i_op->fileattr_set)
+		return -ENOIOCTLCMD;
+
+	if (!inode_owner_or_capable(idmap, inode))
+		return -EPERM;
+
+	inode_lock(inode);
+	err = vfs_fileattr_get(dentry, &old_ma);
+	if (!err) {
+		/* initialize missing bits from old_ma */
+		if (fa->flags_valid) {
+			fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON;
+			fa->fsx_extsize = old_ma.fsx_extsize;
+			fa->fsx_nextents = old_ma.fsx_nextents;
+			fa->fsx_projid = old_ma.fsx_projid;
+			fa->fsx_cowextsize = old_ma.fsx_cowextsize;
+		} else {
+			fa->flags |= old_ma.flags & ~FS_COMMON_FL;
+		}
+		err = fileattr_set_prepare(inode, &old_ma, fa);
+		if (!err)
+			err = inode->i_op->fileattr_set(idmap, dentry, fa);
+	}
+	inode_unlock(inode);
+
+	return err;
+}
+EXPORT_SYMBOL(vfs_fileattr_set);
+
+int ioctl_getflags(struct file *file, unsigned int __user *argp)
+{
+	struct fileattr fa = { .flags_valid = true }; /* hint only */
+	int err;
+
+	err = vfs_fileattr_get(file->f_path.dentry, &fa);
+	if (!err)
+		err = put_user(fa.flags, argp);
+	return err;
+}
+EXPORT_SYMBOL(ioctl_getflags);
+
+int ioctl_setflags(struct file *file, unsigned int __user *argp)
+{
+	struct mnt_idmap *idmap = file_mnt_idmap(file);
+	struct dentry *dentry = file->f_path.dentry;
+	struct fileattr fa;
+	unsigned int flags;
+	int err;
+
+	err = get_user(flags, argp);
+	if (!err) {
+		err = mnt_want_write_file(file);
+		if (!err) {
+			fileattr_fill_flags(&fa, flags);
+			err = vfs_fileattr_set(idmap, dentry, &fa);
+			mnt_drop_write_file(file);
+		}
+	}
+	return err;
+}
+EXPORT_SYMBOL(ioctl_setflags);
+
+int ioctl_fsgetxattr(struct file *file, void __user *argp)
+{
+	struct fileattr fa = { .fsx_valid = true }; /* hint only */
+	int err;
+
+	err = vfs_fileattr_get(file->f_path.dentry, &fa);
+	if (!err)
+		err = copy_fsxattr_to_user(&fa, argp);
+
+	return err;
+}
+EXPORT_SYMBOL(ioctl_fsgetxattr);
+
+int ioctl_fssetxattr(struct file *file, void __user *argp)
+{
+	struct mnt_idmap *idmap = file_mnt_idmap(file);
+	struct dentry *dentry = file->f_path.dentry;
+	struct fileattr fa;
+	int err;
+
+	err = copy_fsxattr_from_user(&fa, argp);
+	if (!err) {
+		err = mnt_want_write_file(file);
+		if (!err) {
+			err = vfs_fileattr_set(idmap, dentry, &fa);
+			mnt_drop_write_file(file);
+		}
+	}
+	return err;
+}
+EXPORT_SYMBOL(ioctl_fssetxattr);
diff --git a/fs/ioctl.c b/fs/ioctl.c
index 69107a245b4c..0248cb8db2d3 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -453,315 +453,6 @@ out:
 	return ret;
 }
 
-/**
- * fileattr_fill_xflags - initialize fileattr with xflags
- * @fa:		fileattr pointer
- * @xflags:	FS_XFLAG_* flags
- *
- * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags).  All
- * other fields are zeroed.
- */
-void fileattr_fill_xflags(struct fileattr *fa, u32 xflags)
-{
-	memset(fa, 0, sizeof(*fa));
-	fa->fsx_valid = true;
-	fa->fsx_xflags = xflags;
-	if (fa->fsx_xflags & FS_XFLAG_IMMUTABLE)
-		fa->flags |= FS_IMMUTABLE_FL;
-	if (fa->fsx_xflags & FS_XFLAG_APPEND)
-		fa->flags |= FS_APPEND_FL;
-	if (fa->fsx_xflags & FS_XFLAG_SYNC)
-		fa->flags |= FS_SYNC_FL;
-	if (fa->fsx_xflags & FS_XFLAG_NOATIME)
-		fa->flags |= FS_NOATIME_FL;
-	if (fa->fsx_xflags & FS_XFLAG_NODUMP)
-		fa->flags |= FS_NODUMP_FL;
-	if (fa->fsx_xflags & FS_XFLAG_DAX)
-		fa->flags |= FS_DAX_FL;
-	if (fa->fsx_xflags & FS_XFLAG_PROJINHERIT)
-		fa->flags |= FS_PROJINHERIT_FL;
-}
-EXPORT_SYMBOL(fileattr_fill_xflags);
-
-/**
- * fileattr_fill_flags - initialize fileattr with flags
- * @fa:		fileattr pointer
- * @flags:	FS_*_FL flags
- *
- * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags).
- * All other fields are zeroed.
- */
-void fileattr_fill_flags(struct fileattr *fa, u32 flags)
-{
-	memset(fa, 0, sizeof(*fa));
-	fa->flags_valid = true;
-	fa->flags = flags;
-	if (fa->flags & FS_SYNC_FL)
-		fa->fsx_xflags |= FS_XFLAG_SYNC;
-	if (fa->flags & FS_IMMUTABLE_FL)
-		fa->fsx_xflags |= FS_XFLAG_IMMUTABLE;
-	if (fa->flags & FS_APPEND_FL)
-		fa->fsx_xflags |= FS_XFLAG_APPEND;
-	if (fa->flags & FS_NODUMP_FL)
-		fa->fsx_xflags |= FS_XFLAG_NODUMP;
-	if (fa->flags & FS_NOATIME_FL)
-		fa->fsx_xflags |= FS_XFLAG_NOATIME;
-	if (fa->flags & FS_DAX_FL)
-		fa->fsx_xflags |= FS_XFLAG_DAX;
-	if (fa->flags & FS_PROJINHERIT_FL)
-		fa->fsx_xflags |= FS_XFLAG_PROJINHERIT;
-}
-EXPORT_SYMBOL(fileattr_fill_flags);
-
-/**
- * vfs_fileattr_get - retrieve miscellaneous file attributes
- * @dentry:	the object to retrieve from
- * @fa:		fileattr pointer
- *
- * Call i_op->fileattr_get() callback, if exists.
- *
- * Return: 0 on success, or a negative error on failure.
- */
-int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
-{
-	struct inode *inode = d_inode(dentry);
-
-	if (!inode->i_op->fileattr_get)
-		return -ENOIOCTLCMD;
-
-	return inode->i_op->fileattr_get(dentry, fa);
-}
-EXPORT_SYMBOL(vfs_fileattr_get);
-
-/**
- * copy_fsxattr_to_user - copy fsxattr to userspace.
- * @fa:		fileattr pointer
- * @ufa:	fsxattr user pointer
- *
- * Return: 0 on success, or -EFAULT on failure.
- */
-int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa)
-{
-	struct fsxattr xfa;
-
-	memset(&xfa, 0, sizeof(xfa));
-	xfa.fsx_xflags = fa->fsx_xflags;
-	xfa.fsx_extsize = fa->fsx_extsize;
-	xfa.fsx_nextents = fa->fsx_nextents;
-	xfa.fsx_projid = fa->fsx_projid;
-	xfa.fsx_cowextsize = fa->fsx_cowextsize;
-
-	if (copy_to_user(ufa, &xfa, sizeof(xfa)))
-		return -EFAULT;
-
-	return 0;
-}
-EXPORT_SYMBOL(copy_fsxattr_to_user);
-
-static int copy_fsxattr_from_user(struct fileattr *fa,
-				  struct fsxattr __user *ufa)
-{
-	struct fsxattr xfa;
-
-	if (copy_from_user(&xfa, ufa, sizeof(xfa)))
-		return -EFAULT;
-
-	fileattr_fill_xflags(fa, xfa.fsx_xflags);
-	fa->fsx_extsize = xfa.fsx_extsize;
-	fa->fsx_nextents = xfa.fsx_nextents;
-	fa->fsx_projid = xfa.fsx_projid;
-	fa->fsx_cowextsize = xfa.fsx_cowextsize;
-
-	return 0;
-}
-
-/*
- * Generic function to check FS_IOC_FSSETXATTR/FS_IOC_SETFLAGS values and reject
- * any invalid configurations.
- *
- * Note: must be called with inode lock held.
- */
-static int fileattr_set_prepare(struct inode *inode,
-			      const struct fileattr *old_ma,
-			      struct fileattr *fa)
-{
-	int err;
-
-	/*
-	 * The IMMUTABLE and APPEND_ONLY flags can only be changed by
-	 * the relevant capability.
-	 */
-	if ((fa->flags ^ old_ma->flags) & (FS_APPEND_FL | FS_IMMUTABLE_FL) &&
-	    !capable(CAP_LINUX_IMMUTABLE))
-		return -EPERM;
-
-	err = fscrypt_prepare_setflags(inode, old_ma->flags, fa->flags);
-	if (err)
-		return err;
-
-	/*
-	 * Project Quota ID state is only allowed to change from within the init
-	 * namespace. Enforce that restriction only if we are trying to change
-	 * the quota ID state. Everything else is allowed in user namespaces.
-	 */
-	if (current_user_ns() != &init_user_ns) {
-		if (old_ma->fsx_projid != fa->fsx_projid)
-			return -EINVAL;
-		if ((old_ma->fsx_xflags ^ fa->fsx_xflags) &
-				FS_XFLAG_PROJINHERIT)
-			return -EINVAL;
-	} else {
-		/*
-		 * Caller is allowed to change the project ID. If it is being
-		 * changed, make sure that the new value is valid.
-		 */
-		if (old_ma->fsx_projid != fa->fsx_projid &&
-		    !projid_valid(make_kprojid(&init_user_ns, fa->fsx_projid)))
-			return -EINVAL;
-	}
-
-	/* Check extent size hints. */
-	if ((fa->fsx_xflags & FS_XFLAG_EXTSIZE) && !S_ISREG(inode->i_mode))
-		return -EINVAL;
-
-	if ((fa->fsx_xflags & FS_XFLAG_EXTSZINHERIT) &&
-			!S_ISDIR(inode->i_mode))
-		return -EINVAL;
-
-	if ((fa->fsx_xflags & FS_XFLAG_COWEXTSIZE) &&
-	    !S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode))
-		return -EINVAL;
-
-	/*
-	 * It is only valid to set the DAX flag on regular files and
-	 * directories on filesystems.
-	 */
-	if ((fa->fsx_xflags & FS_XFLAG_DAX) &&
-	    !(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)))
-		return -EINVAL;
-
-	/* Extent size hints of zero turn off the flags. */
-	if (fa->fsx_extsize == 0)
-		fa->fsx_xflags &= ~(FS_XFLAG_EXTSIZE | FS_XFLAG_EXTSZINHERIT);
-	if (fa->fsx_cowextsize == 0)
-		fa->fsx_xflags &= ~FS_XFLAG_COWEXTSIZE;
-
-	return 0;
-}
-
-/**
- * vfs_fileattr_set - change miscellaneous file attributes
- * @idmap:	idmap of the mount
- * @dentry:	the object to change
- * @fa:		fileattr pointer
- *
- * After verifying permissions, call i_op->fileattr_set() callback, if
- * exists.
- *
- * Verifying attributes involves retrieving current attributes with
- * i_op->fileattr_get(), this also allows initializing attributes that have
- * not been set by the caller to current values.  Inode lock is held
- * thoughout to prevent racing with another instance.
- *
- * Return: 0 on success, or a negative error on failure.
- */
-int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry,
-		     struct fileattr *fa)
-{
-	struct inode *inode = d_inode(dentry);
-	struct fileattr old_ma = {};
-	int err;
-
-	if (!inode->i_op->fileattr_set)
-		return -ENOIOCTLCMD;
-
-	if (!inode_owner_or_capable(idmap, inode))
-		return -EPERM;
-
-	inode_lock(inode);
-	err = vfs_fileattr_get(dentry, &old_ma);
-	if (!err) {
-		/* initialize missing bits from old_ma */
-		if (fa->flags_valid) {
-			fa->fsx_xflags |= old_ma.fsx_xflags & ~FS_XFLAG_COMMON;
-			fa->fsx_extsize = old_ma.fsx_extsize;
-			fa->fsx_nextents = old_ma.fsx_nextents;
-			fa->fsx_projid = old_ma.fsx_projid;
-			fa->fsx_cowextsize = old_ma.fsx_cowextsize;
-		} else {
-			fa->flags |= old_ma.flags & ~FS_COMMON_FL;
-		}
-		err = fileattr_set_prepare(inode, &old_ma, fa);
-		if (!err)
-			err = inode->i_op->fileattr_set(idmap, dentry, fa);
-	}
-	inode_unlock(inode);
-
-	return err;
-}
-EXPORT_SYMBOL(vfs_fileattr_set);
-
-static int ioctl_getflags(struct file *file, unsigned int __user *argp)
-{
-	struct fileattr fa = { .flags_valid = true }; /* hint only */
-	int err;
-
-	err = vfs_fileattr_get(file->f_path.dentry, &fa);
-	if (!err)
-		err = put_user(fa.flags, argp);
-	return err;
-}
-
-static int ioctl_setflags(struct file *file, unsigned int __user *argp)
-{
-	struct mnt_idmap *idmap = file_mnt_idmap(file);
-	struct dentry *dentry = file->f_path.dentry;
-	struct fileattr fa;
-	unsigned int flags;
-	int err;
-
-	err = get_user(flags, argp);
-	if (!err) {
-		err = mnt_want_write_file(file);
-		if (!err) {
-			fileattr_fill_flags(&fa, flags);
-			err = vfs_fileattr_set(idmap, dentry, &fa);
-			mnt_drop_write_file(file);
-		}
-	}
-	return err;
-}
-
-static int ioctl_fsgetxattr(struct file *file, void __user *argp)
-{
-	struct fileattr fa = { .fsx_valid = true }; /* hint only */
-	int err;
-
-	err = vfs_fileattr_get(file->f_path.dentry, &fa);
-	if (!err)
-		err = copy_fsxattr_to_user(&fa, argp);
-
-	return err;
-}
-
-static int ioctl_fssetxattr(struct file *file, void __user *argp)
-{
-	struct mnt_idmap *idmap = file_mnt_idmap(file);
-	struct dentry *dentry = file->f_path.dentry;
-	struct fileattr fa;
-	int err;
-
-	err = copy_fsxattr_from_user(&fa, argp);
-	if (!err) {
-		err = mnt_want_write_file(file);
-		if (!err) {
-			err = vfs_fileattr_set(idmap, dentry, &fa);
-			mnt_drop_write_file(file);
-		}
-	}
-	return err;
-}
-
 static int ioctl_getfsuuid(struct file *file, void __user *argp)
 {
 	struct super_block *sb = file_inode(file)->i_sb;
diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h
index 47c05a9851d0..6030d0bf7ad3 100644
--- a/include/linux/fileattr.h
+++ b/include/linux/fileattr.h
@@ -55,5 +55,9 @@ static inline bool fileattr_has_fsx(const struct fileattr *fa)
 int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
 int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry,
 		     struct fileattr *fa);
+int ioctl_getflags(struct file *file, unsigned int __user *argp);
+int ioctl_setflags(struct file *file, unsigned int __user *argp);
+int ioctl_fsgetxattr(struct file *file, void __user *argp);
+int ioctl_fssetxattr(struct file *file, void __user *argp);
 
 #endif /* _LINUX_FILEATTR_H */
-- 
cgit v1.2.3


From defdd02d783c6fa22d0005bdc238ccd9174faf20 Mon Sep 17 00:00:00 2001
From: Andrey Albershteyn <aalbersh@redhat.com>
Date: Mon, 30 Jun 2025 18:20:12 +0200
Subject: lsm: introduce new hooks for setting/getting inode fsxattr

Introduce new hooks for setting and getting filesystem extended
attributes on inode (FS_IOC_FSGETXATTR).

Cc: selinux@vger.kernel.org
Cc: Paul Moore <paul@paul-moore.com>

Acked-by: Paul Moore <paul@paul-moore.com>
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Link: https://lore.kernel.org/20250630-xattrat-syscall-v6-2-c4e3bc35227b@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file_attr.c                | 19 ++++++++++++++++---
 include/linux/lsm_hook_defs.h |  2 ++
 include/linux/security.h      | 16 ++++++++++++++++
 security/security.c           | 30 ++++++++++++++++++++++++++++++
 4 files changed, 64 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file_attr.c b/fs/file_attr.c
index a4dd1d9646c8..0aee402acde4 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -77,10 +77,15 @@ EXPORT_SYMBOL(fileattr_fill_flags);
 int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
+	int error;
 
 	if (!inode->i_op->fileattr_get)
 		return -ENOIOCTLCMD;
 
+	error = security_inode_file_getattr(dentry, fa);
+	if (error)
+		return error;
+
 	return inode->i_op->fileattr_get(dentry, fa);
 }
 EXPORT_SYMBOL(vfs_fileattr_get);
@@ -243,12 +248,20 @@ int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry,
 		} else {
 			fa->flags |= old_ma.flags & ~FS_COMMON_FL;
 		}
+
 		err = fileattr_set_prepare(inode, &old_ma, fa);
-		if (!err)
-			err = inode->i_op->fileattr_set(idmap, dentry, fa);
+		if (err)
+			goto out;
+		err = security_inode_file_setattr(dentry, fa);
+		if (err)
+			goto out;
+		err = inode->i_op->fileattr_set(idmap, dentry, fa);
+		if (err)
+			goto out;
 	}
-	inode_unlock(inode);
 
+out:
+	inode_unlock(inode);
 	return err;
 }
 EXPORT_SYMBOL(vfs_fileattr_set);
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index bf3bbac4e02a..9600a4350e79 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -157,6 +157,8 @@ LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *name)
 LSM_HOOK(void, LSM_RET_VOID, inode_post_removexattr, struct dentry *dentry,
 	 const char *name)
+LSM_HOOK(int, 0, inode_file_setattr, struct dentry *dentry, struct fileattr *fa)
+LSM_HOOK(int, 0, inode_file_getattr, struct dentry *dentry, struct fileattr *fa)
 LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *acl_name, struct posix_acl *kacl)
 LSM_HOOK(void, LSM_RET_VOID, inode_post_set_acl, struct dentry *dentry,
diff --git a/include/linux/security.h b/include/linux/security.h
index dba349629229..9ed0d0e0c81f 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -451,6 +451,10 @@ int security_inode_listxattr(struct dentry *dentry);
 int security_inode_removexattr(struct mnt_idmap *idmap,
 			       struct dentry *dentry, const char *name);
 void security_inode_post_removexattr(struct dentry *dentry, const char *name);
+int security_inode_file_setattr(struct dentry *dentry,
+			      struct fileattr *fa);
+int security_inode_file_getattr(struct dentry *dentry,
+			      struct fileattr *fa);
 int security_inode_need_killpriv(struct dentry *dentry);
 int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry);
 int security_inode_getsecurity(struct mnt_idmap *idmap,
@@ -1052,6 +1056,18 @@ static inline void security_inode_post_removexattr(struct dentry *dentry,
 						   const char *name)
 { }
 
+static inline int security_inode_file_setattr(struct dentry *dentry,
+					      struct fileattr *fa)
+{
+	return 0;
+}
+
+static inline int security_inode_file_getattr(struct dentry *dentry,
+					      struct fileattr *fa)
+{
+	return 0;
+}
+
 static inline int security_inode_need_killpriv(struct dentry *dentry)
 {
 	return cap_inode_need_killpriv(dentry);
diff --git a/security/security.c b/security/security.c
index 596d41818577..711b4de40b8d 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2622,6 +2622,36 @@ void security_inode_post_removexattr(struct dentry *dentry, const char *name)
 	call_void_hook(inode_post_removexattr, dentry, name);
 }
 
+/**
+ * security_inode_file_setattr() - check if setting fsxattr is allowed
+ * @dentry: file to set filesystem extended attributes on
+ * @fa: extended attributes to set on the inode
+ *
+ * Called when file_setattr() syscall or FS_IOC_FSSETXATTR ioctl() is called on
+ * inode
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_file_setattr(struct dentry *dentry, struct fileattr *fa)
+{
+	return call_int_hook(inode_file_setattr, dentry, fa);
+}
+
+/**
+ * security_inode_file_getattr() - check if retrieving fsxattr is allowed
+ * @dentry: file to retrieve filesystem extended attributes from
+ * @fa: extended attributes to get
+ *
+ * Called when file_getattr() syscall or FS_IOC_FSGETXATTR ioctl() is called on
+ * inode
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+int security_inode_file_getattr(struct dentry *dentry, struct fileattr *fa)
+{
+	return call_int_hook(inode_file_getattr, dentry, fa);
+}
+
 /**
  * security_inode_need_killpriv() - Check if security_inode_killpriv() required
  * @dentry: associated dentry
-- 
cgit v1.2.3


From 1a4eabf662543c62ae1e71a26d1c8e6643c66388 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:01 +0100
Subject: mfd: adp5585: Refactor how regmap defaults are handled
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The only thing changing between variants is the regmap default
registers. Hence, instead of having a regmap configuration for every
variant (duplicating lots of fields), add a chip info type of structure
with a regmap ID to identify which defaults to use and populate
regmap_config at runtime given a template plus the id. Also note that
between variants, the defaults can be the same which means the chip info
structure can be used in more than one compatible.

This will also make it simpler adding new chips with more variants.

Also note that the chip info structures are deliberately not const as
they will also contain lots of members that are the same between the
different devices variants and so we will fill those at runtime.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-6-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/adp5585.c       | 80 +++++++++++++++++++++++----------------------
 include/linux/mfd/adp5585.h | 11 +++++++
 2 files changed, 52 insertions(+), 39 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/adp5585.c b/drivers/mfd/adp5585.c
index c764f4818758..4d92b6362928 100644
--- a/drivers/mfd/adp5585.c
+++ b/drivers/mfd/adp5585.c
@@ -81,42 +81,36 @@ static const u8 adp5585_regmap_defaults_04[ADP5585_MAX_REG + 1] = {
 	/* 0x38 */ 0x00, 0x00, 0x00, 0x00, 0x00,
 };
 
-enum adp5585_regmap_type {
-	ADP5585_REGMAP_00,
-	ADP5585_REGMAP_02,
-	ADP5585_REGMAP_04,
+static const u8 *adp5585_regmap_defaults[ADP5585_MAX] = {
+	[ADP5585_00] = adp5585_regmap_defaults_00,
+	[ADP5585_01] = adp5585_regmap_defaults_00,
+	[ADP5585_02] = adp5585_regmap_defaults_02,
+	[ADP5585_03] = adp5585_regmap_defaults_00,
+	[ADP5585_04] = adp5585_regmap_defaults_04,
 };
 
-static const struct regmap_config adp5585_regmap_configs[] = {
-	[ADP5585_REGMAP_00] = {
-		.reg_bits = 8,
-		.val_bits = 8,
-		.max_register = ADP5585_MAX_REG,
-		.volatile_table = &adp5585_volatile_regs,
-		.cache_type = REGCACHE_MAPLE,
-		.reg_defaults_raw = adp5585_regmap_defaults_00,
-		.num_reg_defaults_raw = sizeof(adp5585_regmap_defaults_00),
-	},
-	[ADP5585_REGMAP_02] = {
-		.reg_bits = 8,
-		.val_bits = 8,
-		.max_register = ADP5585_MAX_REG,
-		.volatile_table = &adp5585_volatile_regs,
-		.cache_type = REGCACHE_MAPLE,
-		.reg_defaults_raw = adp5585_regmap_defaults_02,
-		.num_reg_defaults_raw = sizeof(adp5585_regmap_defaults_02),
-	},
-	[ADP5585_REGMAP_04] = {
-		.reg_bits = 8,
-		.val_bits = 8,
-		.max_register = ADP5585_MAX_REG,
-		.volatile_table = &adp5585_volatile_regs,
-		.cache_type = REGCACHE_MAPLE,
-		.reg_defaults_raw = adp5585_regmap_defaults_04,
-		.num_reg_defaults_raw = sizeof(adp5585_regmap_defaults_04),
-	},
+static const struct regmap_config adp5585_regmap_config_template = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = ADP5585_MAX_REG,
+	.volatile_table = &adp5585_volatile_regs,
+	.cache_type = REGCACHE_MAPLE,
+	.num_reg_defaults_raw = ADP5585_MAX_REG + 1,
 };
 
+static struct regmap_config *adp5585_fill_regmap_config(const struct adp5585_dev *adp5585)
+{
+	struct regmap_config *regmap_config;
+
+	regmap_config = devm_kmemdup(adp5585->dev, &adp5585_regmap_config_template,
+				     sizeof(*regmap_config), GFP_KERNEL);
+	if (!regmap_config)
+		return ERR_PTR(-ENOMEM);
+
+	regmap_config->reg_defaults_raw = adp5585_regmap_defaults[adp5585->variant];
+	return regmap_config;
+}
+
 static int adp5585_add_devices(struct device *dev)
 {
 	int ret;
@@ -147,7 +141,7 @@ static void adp5585_osc_disable(void *data)
 
 static int adp5585_i2c_probe(struct i2c_client *i2c)
 {
-	const struct regmap_config *regmap_config;
+	struct regmap_config *regmap_config;
 	struct adp5585_dev *adp5585;
 	unsigned int id;
 	int ret;
@@ -157,8 +151,16 @@ static int adp5585_i2c_probe(struct i2c_client *i2c)
 		return -ENOMEM;
 
 	i2c_set_clientdata(i2c, adp5585);
+	adp5585->dev = &i2c->dev;
+
+	adp5585->variant = (enum adp5585_variant)(uintptr_t)i2c_get_match_data(i2c);
+	if (!adp5585->variant)
+		return -ENODEV;
+
+	regmap_config = adp5585_fill_regmap_config(adp5585);
+	if (IS_ERR(regmap_config))
+		return PTR_ERR(regmap_config);
 
-	regmap_config = i2c_get_match_data(i2c);
 	adp5585->regmap = devm_regmap_init_i2c(i2c, regmap_config);
 	if (IS_ERR(adp5585->regmap))
 		return dev_err_probe(&i2c->dev, PTR_ERR(adp5585->regmap),
@@ -212,19 +214,19 @@ static DEFINE_SIMPLE_DEV_PM_OPS(adp5585_pm, adp5585_suspend, adp5585_resume);
 static const struct of_device_id adp5585_of_match[] = {
 	{
 		.compatible = "adi,adp5585-00",
-		.data = &adp5585_regmap_configs[ADP5585_REGMAP_00],
+		.data = (void *)ADP5585_00,
 	}, {
 		.compatible = "adi,adp5585-01",
-		.data = &adp5585_regmap_configs[ADP5585_REGMAP_00],
+		.data = (void *)ADP5585_01,
 	}, {
 		.compatible = "adi,adp5585-02",
-		.data = &adp5585_regmap_configs[ADP5585_REGMAP_02],
+		.data = (void *)ADP5585_02,
 	}, {
 		.compatible = "adi,adp5585-03",
-		.data = &adp5585_regmap_configs[ADP5585_REGMAP_00],
+		.data = (void *)ADP5585_03,
 	}, {
 		.compatible = "adi,adp5585-04",
-		.data = &adp5585_regmap_configs[ADP5585_REGMAP_04],
+		.data = (void *)ADP5585_04,
 	},
 	{ /* sentinel */ }
 };
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index 016033cd68e4..c56af8d8d76c 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -119,8 +119,19 @@
 
 struct regmap;
 
+enum adp5585_variant {
+	ADP5585_00 = 1,
+	ADP5585_01,
+	ADP5585_02,
+	ADP5585_03,
+	ADP5585_04,
+	ADP5585_MAX
+};
+
 struct adp5585_dev {
+	struct device *dev;
 	struct regmap *regmap;
+	enum adp5585_variant variant;
 };
 
 #endif
-- 
cgit v1.2.3


From 0190a72f28ee0995c546fd4fcf80ed25a0fc4b28 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:02 +0100
Subject: mfd: adp5585: Add support for adp5589
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ADP5589 is a 19 I/O port expander with built-in keypad matrix decoder,
programmable logic, reset generator, and PWM generator.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-7-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/adp5585.c       | 123 ++++++++++++++++++++++++++++++++++++++++----
 include/linux/mfd/adp5585.h |  10 ++++
 2 files changed, 124 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/adp5585.c b/drivers/mfd/adp5585.c
index 4d92b6362928..00996571ef90 100644
--- a/drivers/mfd/adp5585.c
+++ b/drivers/mfd/adp5585.c
@@ -29,6 +29,11 @@ static const struct mfd_cell adp5585_devs[ADP5585_DEV_MAX] = {
 	MFD_CELL_NAME("adp5585-pwm"),
 };
 
+static const struct mfd_cell adp5589_devs[] = {
+	MFD_CELL_NAME("adp5589-gpio"),
+	MFD_CELL_NAME("adp5589-pwm"),
+};
+
 static const struct regmap_range adp5585_volatile_ranges[] = {
 	regmap_reg_range(ADP5585_ID, ADP5585_GPI_STATUS_B),
 };
@@ -38,6 +43,15 @@ static const struct regmap_access_table adp5585_volatile_regs = {
 	.n_yes_ranges = ARRAY_SIZE(adp5585_volatile_ranges),
 };
 
+static const struct regmap_range adp5589_volatile_ranges[] = {
+	regmap_reg_range(ADP5585_ID, ADP5589_GPI_STATUS_C),
+};
+
+static const struct regmap_access_table adp5589_volatile_regs = {
+	.yes_ranges = adp5589_volatile_ranges,
+	.n_yes_ranges = ARRAY_SIZE(adp5589_volatile_ranges),
+};
+
 /*
  * Chip variants differ in the default configuration of pull-up and pull-down
  * resistors, and therefore have different default register values:
@@ -81,12 +95,54 @@ static const u8 adp5585_regmap_defaults_04[ADP5585_MAX_REG + 1] = {
 	/* 0x38 */ 0x00, 0x00, 0x00, 0x00, 0x00,
 };
 
+static const u8 adp5589_regmap_defaults_00[ADP5589_MAX_REG + 1] = {
+	/* 0x00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x08 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x10 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x18 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x20 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x28 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x30 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x38 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x40 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x48 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+
+static const u8 adp5589_regmap_defaults_01[ADP5589_MAX_REG + 1] = {
+	/* 0x00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x08 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x10 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x18 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x20 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x28 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x30 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x38 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x20, 0x00, 0x00,
+	/* 0x40 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x48 */ 0x00, 0x00, 0x00, 0x00, 0x20, 0x00, 0x00,
+};
+
+static const u8 adp5589_regmap_defaults_02[ADP5589_MAX_REG + 1] = {
+	/* 0x00 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x08 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x10 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x18 */ 0x00, 0x41, 0x01, 0x00, 0x11, 0x04, 0x00, 0x00,
+	/* 0x20 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x28 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x30 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x38 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x40 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+	/* 0x48 */ 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00,
+};
+
 static const u8 *adp5585_regmap_defaults[ADP5585_MAX] = {
 	[ADP5585_00] = adp5585_regmap_defaults_00,
 	[ADP5585_01] = adp5585_regmap_defaults_00,
 	[ADP5585_02] = adp5585_regmap_defaults_02,
 	[ADP5585_03] = adp5585_regmap_defaults_00,
 	[ADP5585_04] = adp5585_regmap_defaults_04,
+	[ADP5589_00] = adp5589_regmap_defaults_00,
+	[ADP5589_01] = adp5589_regmap_defaults_01,
+	[ADP5589_02] = adp5589_regmap_defaults_02,
 };
 
 static const struct regmap_config adp5585_regmap_config_template = {
@@ -98,33 +154,69 @@ static const struct regmap_config adp5585_regmap_config_template = {
 	.num_reg_defaults_raw = ADP5585_MAX_REG + 1,
 };
 
-static struct regmap_config *adp5585_fill_regmap_config(const struct adp5585_dev *adp5585)
+static const struct regmap_config adp5589_regmap_config_template = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = ADP5589_MAX_REG,
+	.volatile_table = &adp5589_volatile_regs,
+	.cache_type = REGCACHE_MAPLE,
+	.num_reg_defaults_raw = ADP5589_MAX_REG + 1,
+};
+
+static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp5585)
 {
 	struct regmap_config *regmap_config;
 
-	regmap_config = devm_kmemdup(adp5585->dev, &adp5585_regmap_config_template,
-				     sizeof(*regmap_config), GFP_KERNEL);
+	switch (adp5585->variant) {
+	case ADP5585_00:
+	case ADP5585_01:
+	case ADP5585_02:
+	case ADP5585_03:
+	case ADP5585_04:
+		adp5585->id = ADP5585_MAN_ID_VALUE;
+		regmap_config = devm_kmemdup(adp5585->dev, &adp5585_regmap_config_template,
+					     sizeof(*regmap_config), GFP_KERNEL);
+		break;
+	case ADP5589_00:
+	case ADP5589_01:
+	case ADP5589_02:
+		adp5585->id = ADP5589_MAN_ID_VALUE;
+		regmap_config = devm_kmemdup(adp5585->dev, &adp5589_regmap_config_template,
+					     sizeof(*regmap_config), GFP_KERNEL);
+		break;
+	default:
+		return ERR_PTR(-ENODEV);
+	}
+
 	if (!regmap_config)
 		return ERR_PTR(-ENOMEM);
 
 	regmap_config->reg_defaults_raw = adp5585_regmap_defaults[adp5585->variant];
+
 	return regmap_config;
 }
 
-static int adp5585_add_devices(struct device *dev)
+static int adp5585_add_devices(const struct adp5585_dev *adp5585)
 {
+	struct device *dev = adp5585->dev;
+	const struct mfd_cell *cells;
 	int ret;
 
+	if (adp5585->id == ADP5585_MAN_ID_VALUE)
+		cells = adp5585_devs;
+	else
+		cells = adp5589_devs;
+
 	if (device_property_present(dev, "#pwm-cells")) {
 		ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO,
-					   &adp5585_devs[ADP5585_DEV_PWM], 1, NULL, 0, NULL);
+					   &cells[ADP5585_DEV_PWM], 1, NULL, 0, NULL);
 		if (ret)
 			return dev_err_probe(dev, ret, "Failed to add PWM device\n");
 	}
 
 	if (device_property_present(dev, "#gpio-cells")) {
 		ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO,
-					   &adp5585_devs[ADP5585_DEV_GPIO], 1, NULL, 0, NULL);
+					   &cells[ADP5585_DEV_GPIO], 1, NULL, 0, NULL);
 		if (ret)
 			return dev_err_probe(dev, ret, "Failed to add GPIO device\n");
 	}
@@ -157,7 +249,7 @@ static int adp5585_i2c_probe(struct i2c_client *i2c)
 	if (!adp5585->variant)
 		return -ENODEV;
 
-	regmap_config = adp5585_fill_regmap_config(adp5585);
+	regmap_config = adp5585_fill_variant_config(adp5585);
 	if (IS_ERR(regmap_config))
 		return PTR_ERR(regmap_config);
 
@@ -171,7 +263,8 @@ static int adp5585_i2c_probe(struct i2c_client *i2c)
 		return dev_err_probe(&i2c->dev, ret,
 				     "Failed to read device ID\n");
 
-	if ((id & ADP5585_MAN_ID_MASK) != ADP5585_MAN_ID_VALUE)
+	id &= ADP5585_MAN_ID_MASK;
+	if (id != adp5585->id)
 		return dev_err_probe(&i2c->dev, -ENODEV,
 				     "Invalid device ID 0x%02x\n", id);
 
@@ -187,7 +280,7 @@ static int adp5585_i2c_probe(struct i2c_client *i2c)
 	if (ret)
 		return ret;
 
-	return adp5585_add_devices(&i2c->dev);
+	return adp5585_add_devices(adp5585);
 }
 
 static int adp5585_suspend(struct device *dev)
@@ -227,6 +320,18 @@ static const struct of_device_id adp5585_of_match[] = {
 	}, {
 		.compatible = "adi,adp5585-04",
 		.data = (void *)ADP5585_04,
+	}, {
+		.compatible = "adi,adp5589-00",
+		.data = (void *)ADP5589_00,
+	}, {
+		.compatible = "adi,adp5589-01",
+		.data = (void *)ADP5589_01,
+	}, {
+		.compatible = "adi,adp5589-02",
+		.data = (void *)ADP5589_02,
+	}, {
+		.compatible = "adi,adp5589",
+		.data = (void *)ADP5589_00,
 	},
 	{ /* sentinel */ }
 };
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index c56af8d8d76c..70e58122a36a 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -117,6 +117,12 @@
 #define ADP5585_BANK(n)			((n) >= 6 ? 1 : 0)
 #define ADP5585_BIT(n)			((n) >= 6 ? BIT((n) - 6) : BIT(n))
 
+/* ADP5589 */
+#define		ADP5589_MAN_ID_VALUE		0x10
+#define ADP5589_GPI_STATUS_C		0x18
+#define ADP5589_INT_EN			0x4e
+#define ADP5589_MAX_REG			ADP5589_INT_EN
+
 struct regmap;
 
 enum adp5585_variant {
@@ -125,6 +131,9 @@ enum adp5585_variant {
 	ADP5585_02,
 	ADP5585_03,
 	ADP5585_04,
+	ADP5589_00,
+	ADP5589_01,
+	ADP5589_02,
 	ADP5585_MAX
 };
 
@@ -132,6 +141,7 @@ struct adp5585_dev {
 	struct device *dev;
 	struct regmap *regmap;
 	enum adp5585_variant variant;
+	unsigned int id;
 };
 
 #endif
-- 
cgit v1.2.3


From 7077fb501b95360c7fe35553f2bdb1ccf34edd16 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:03 +0100
Subject: mfd: adp5585: Add a per chip reg struture
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

There are some differences in the register map between the devices.
Hence, add a register structure per device. This will be needed in
following patches.

On top of that adp5585_fill_regmap_config() is renamed and reworked so
that the current struct adp5585_info act as template (they indeed
contain all the different data between variants) which can then be
complemented depending on the device (as identified by the id register).
This is done like this since a lot of the data is pretty much the same
between variants of the same device.

Reviewed-by: Lee Jones <lee@kernel.org>
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-8-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/adp5585.c       | 10 ++++++++++
 include/linux/mfd/adp5585.h |  6 ++++++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/adp5585.c b/drivers/mfd/adp5585.c
index 00996571ef90..ae12372bdde9 100644
--- a/drivers/mfd/adp5585.c
+++ b/drivers/mfd/adp5585.c
@@ -163,6 +163,14 @@ static const struct regmap_config adp5589_regmap_config_template = {
 	.num_reg_defaults_raw = ADP5589_MAX_REG + 1,
 };
 
+static const struct adp5585_regs adp5585_regs = {
+	.ext_cfg = ADP5585_PIN_CONFIG_C,
+};
+
+static const struct adp5585_regs adp5589_regs = {
+	.ext_cfg = ADP5589_PIN_CONFIG_D,
+};
+
 static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp5585)
 {
 	struct regmap_config *regmap_config;
@@ -174,6 +182,7 @@ static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp
 	case ADP5585_03:
 	case ADP5585_04:
 		adp5585->id = ADP5585_MAN_ID_VALUE;
+		adp5585->regs = &adp5585_regs;
 		regmap_config = devm_kmemdup(adp5585->dev, &adp5585_regmap_config_template,
 					     sizeof(*regmap_config), GFP_KERNEL);
 		break;
@@ -181,6 +190,7 @@ static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp
 	case ADP5589_01:
 	case ADP5589_02:
 		adp5585->id = ADP5589_MAN_ID_VALUE;
+		adp5585->regs = &adp5589_regs;
 		regmap_config = devm_kmemdup(adp5585->dev, &adp5589_regmap_config_template,
 					     sizeof(*regmap_config), GFP_KERNEL);
 		break;
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index 70e58122a36a..6ecb90a6276c 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -120,6 +120,7 @@
 /* ADP5589 */
 #define		ADP5589_MAN_ID_VALUE		0x10
 #define ADP5589_GPI_STATUS_C		0x18
+#define ADP5589_PIN_CONFIG_D		0x4C
 #define ADP5589_INT_EN			0x4e
 #define ADP5589_MAX_REG			ADP5589_INT_EN
 
@@ -137,9 +138,14 @@ enum adp5585_variant {
 	ADP5585_MAX
 };
 
+struct adp5585_regs {
+	unsigned int ext_cfg;
+};
+
 struct adp5585_dev {
 	struct device *dev;
 	struct regmap *regmap;
+	const struct adp5585_regs *regs;
 	enum adp5585_variant variant;
 	unsigned int id;
 };
-- 
cgit v1.2.3


From 9f425bf713b511b1078e0fea5a88c497e13dbb64 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:04 +0100
Subject: gpio: adp5585: add support for the adp5589 expander
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Support the adp5589 I/O expander which supports up to 19 pins. We need
to add a chip_info based struct since accessing register "banks"
and "bits" differs between devices.

Also some register addresses are different.

While at it move ADP558X_GPIO_MAX defines to the main header file and
rename them. That information will be needed by the top level device in
a following change.

Acked-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-9-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/gpio/gpio-adp5585.c | 151 ++++++++++++++++++++++++++++++++++----------
 include/linux/mfd/adp5585.h |  18 +++---
 2 files changed, 126 insertions(+), 43 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpio-adp5585.c b/drivers/gpio/gpio-adp5585.c
index d5c0f1b267c8..cdf107742579 100644
--- a/drivers/gpio/gpio-adp5585.c
+++ b/drivers/gpio/gpio-adp5585.c
@@ -4,6 +4,7 @@
  *
  * Copyright 2022 NXP
  * Copyright 2024 Ideas on Board Oy
+ * Copyright 2025 Analog Devices, Inc.
  */
 
 #include <linux/device.h>
@@ -14,57 +15,106 @@
 #include <linux/regmap.h>
 #include <linux/types.h>
 
-#define ADP5585_GPIO_MAX	11
+/*
+ * Bank 0 covers pins "GPIO 1/R0" to "GPIO 6/R5", numbered 0 to 5 by the
+ * driver, and bank 1 covers pins "GPIO 7/C0" to "GPIO 11/C4", numbered 6 to
+ * 10. Some variants of the ADP5585 don't support "GPIO 6/R5". As the driver
+ * uses identical GPIO numbering for all variants to avoid confusion, GPIO 5 is
+ * marked as reserved in the device tree for variants that don't support it.
+ */
+#define ADP5585_BANK(n)			((n) >= 6 ? 1 : 0)
+#define ADP5585_BIT(n)			((n) >= 6 ? BIT((n) - 6) : BIT(n))
+
+/*
+ * Bank 0 covers pins "GPIO 1/R0" to "GPIO 8/R7", numbered 0 to 7 by the
+ * driver, bank 1 covers pins "GPIO 9/C0" to "GPIO 16/C7", numbered 8 to
+ * 15 and bank 3 covers pins "GPIO 17/C8" to "GPIO 19/C10", numbered 16 to 18.
+ */
+#define ADP5589_BANK(n)			((n) >> 3)
+#define ADP5589_BIT(n)			BIT((n) & 0x7)
+
+struct adp5585_gpio_chip {
+	int (*bank)(unsigned int off);
+	int (*bit)(unsigned int off);
+	unsigned int max_gpio;
+	unsigned int debounce_dis_a;
+	unsigned int rpull_cfg_a;
+	unsigned int gpo_data_a;
+	unsigned int gpo_out_a;
+	unsigned int gpio_dir_a;
+	unsigned int gpi_stat_a;
+	bool has_bias_hole;
+};
 
 struct adp5585_gpio_dev {
 	struct gpio_chip gpio_chip;
+	const struct adp5585_gpio_chip *info;
 	struct regmap *regmap;
 };
 
+static int adp5585_gpio_bank(unsigned int off)
+{
+	return ADP5585_BANK(off);
+}
+
+static int adp5585_gpio_bit(unsigned int off)
+{
+	return ADP5585_BIT(off);
+}
+
+static int adp5589_gpio_bank(unsigned int off)
+{
+	return ADP5589_BANK(off);
+}
+
+static int adp5589_gpio_bit(unsigned int off)
+{
+	return ADP5589_BIT(off);
+}
+
 static int adp5585_gpio_get_direction(struct gpio_chip *chip, unsigned int off)
 {
 	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(chip);
-	unsigned int bank = ADP5585_BANK(off);
-	unsigned int bit = ADP5585_BIT(off);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
 	unsigned int val;
 
-	regmap_read(adp5585_gpio->regmap, ADP5585_GPIO_DIRECTION_A + bank, &val);
+	regmap_read(adp5585_gpio->regmap, info->gpio_dir_a + info->bank(off), &val);
 
-	return val & bit ? GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN;
+	return val & info->bit(off) ? GPIO_LINE_DIRECTION_OUT : GPIO_LINE_DIRECTION_IN;
 }
 
 static int adp5585_gpio_direction_input(struct gpio_chip *chip, unsigned int off)
 {
 	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(chip);
-	unsigned int bank = ADP5585_BANK(off);
-	unsigned int bit = ADP5585_BIT(off);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
 
-	return regmap_clear_bits(adp5585_gpio->regmap,
-				 ADP5585_GPIO_DIRECTION_A + bank, bit);
+	return regmap_clear_bits(adp5585_gpio->regmap, info->gpio_dir_a + info->bank(off),
+				 info->bit(off));
 }
 
 static int adp5585_gpio_direction_output(struct gpio_chip *chip, unsigned int off, int val)
 {
 	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(chip);
-	unsigned int bank = ADP5585_BANK(off);
-	unsigned int bit = ADP5585_BIT(off);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
+	unsigned int bank = info->bank(off);
+	unsigned int bit = info->bit(off);
 	int ret;
 
-	ret = regmap_update_bits(adp5585_gpio->regmap,
-				 ADP5585_GPO_DATA_OUT_A + bank, bit,
-				 val ? bit : 0);
+	ret = regmap_update_bits(adp5585_gpio->regmap, info->gpo_data_a + bank,
+				 bit, val ? bit : 0);
 	if (ret)
 		return ret;
 
-	return regmap_set_bits(adp5585_gpio->regmap,
-			       ADP5585_GPIO_DIRECTION_A + bank, bit);
+	return regmap_set_bits(adp5585_gpio->regmap, info->gpio_dir_a + bank,
+			       bit);
 }
 
 static int adp5585_gpio_get_value(struct gpio_chip *chip, unsigned int off)
 {
 	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(chip);
-	unsigned int bank = ADP5585_BANK(off);
-	unsigned int bit = ADP5585_BIT(off);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
+	unsigned int bank = info->bank(off);
+	unsigned int bit = info->bit(off);
 	unsigned int reg;
 	unsigned int val;
 
@@ -79,8 +129,8 @@ static int adp5585_gpio_get_value(struct gpio_chip *chip, unsigned int off)
 	 * .direction_input(), .direction_output() or .set() operations racing
 	 * with this.
 	 */
-	regmap_read(adp5585_gpio->regmap, ADP5585_GPIO_DIRECTION_A + bank, &val);
-	reg = val & bit ? ADP5585_GPO_DATA_OUT_A : ADP5585_GPI_STATUS_A;
+	regmap_read(adp5585_gpio->regmap, info->gpio_dir_a + bank, &val);
+	reg = val & bit ? info->gpo_data_a : info->gpi_stat_a;
 	regmap_read(adp5585_gpio->regmap, reg + bank, &val);
 
 	return !!(val & bit);
@@ -90,17 +140,17 @@ static int adp5585_gpio_set_value(struct gpio_chip *chip, unsigned int off,
 				  int val)
 {
 	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(chip);
-	unsigned int bank = ADP5585_BANK(off);
-	unsigned int bit = ADP5585_BIT(off);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
+	unsigned int bit = adp5585_gpio->info->bit(off);
 
-	return regmap_update_bits(adp5585_gpio->regmap,
-				  ADP5585_GPO_DATA_OUT_A + bank,
+	return regmap_update_bits(adp5585_gpio->regmap, info->gpo_data_a + info->bank(off),
 				  bit, val ? bit : 0);
 }
 
 static int adp5585_gpio_set_bias(struct adp5585_gpio_dev *adp5585_gpio,
 				 unsigned int off, unsigned int bias)
 {
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
 	unsigned int bit, reg, mask, val;
 
 	/*
@@ -108,8 +158,10 @@ static int adp5585_gpio_set_bias(struct adp5585_gpio_dev *adp5585_gpio,
 	 * consecutive registers ADP5585_RPULL_CONFIG_*, with a hole of 4 bits
 	 * after R5.
 	 */
-	bit = off * 2 + (off > 5 ? 4 : 0);
-	reg = ADP5585_RPULL_CONFIG_A + bit / 8;
+	bit = off * 2;
+	if (info->has_bias_hole)
+		bit += (off > 5 ? 4 : 0);
+	reg = info->rpull_cfg_a + bit / 8;
 	mask = ADP5585_Rx_PULL_CFG_MASK << (bit % 8);
 	val = bias << (bit % 8);
 
@@ -119,22 +171,22 @@ static int adp5585_gpio_set_bias(struct adp5585_gpio_dev *adp5585_gpio,
 static int adp5585_gpio_set_drive(struct adp5585_gpio_dev *adp5585_gpio,
 				  unsigned int off, enum pin_config_param drive)
 {
-	unsigned int bank = ADP5585_BANK(off);
-	unsigned int bit = ADP5585_BIT(off);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
+	unsigned int bit = adp5585_gpio->info->bit(off);
 
 	return regmap_update_bits(adp5585_gpio->regmap,
-				  ADP5585_GPO_OUT_MODE_A + bank, bit,
+				  info->gpo_out_a + info->bank(off), bit,
 				  drive == PIN_CONFIG_DRIVE_OPEN_DRAIN ? bit : 0);
 }
 
 static int adp5585_gpio_set_debounce(struct adp5585_gpio_dev *adp5585_gpio,
 				     unsigned int off, unsigned int debounce)
 {
-	unsigned int bank = ADP5585_BANK(off);
-	unsigned int bit = ADP5585_BIT(off);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
+	unsigned int bit = adp5585_gpio->info->bit(off);
 
 	return regmap_update_bits(adp5585_gpio->regmap,
-				  ADP5585_DEBOUNCE_DIS_A + bank, bit,
+				  info->debounce_dis_a + info->bank(off), bit,
 				  debounce ? 0 : bit);
 }
 
@@ -175,6 +227,7 @@ static int adp5585_gpio_set_config(struct gpio_chip *chip, unsigned int off,
 static int adp5585_gpio_probe(struct platform_device *pdev)
 {
 	struct adp5585_dev *adp5585 = dev_get_drvdata(pdev->dev.parent);
+	const struct platform_device_id *id = platform_get_device_id(pdev);
 	struct adp5585_gpio_dev *adp5585_gpio;
 	struct device *dev = &pdev->dev;
 	struct gpio_chip *gc;
@@ -186,6 +239,10 @@ static int adp5585_gpio_probe(struct platform_device *pdev)
 
 	adp5585_gpio->regmap = adp5585->regmap;
 
+	adp5585_gpio->info = (const struct adp5585_gpio_chip *)id->driver_data;
+	if (!adp5585_gpio->info)
+		return -ENODEV;
+
 	device_set_of_node_from_dev(dev, dev->parent);
 
 	gc = &adp5585_gpio->gpio_chip;
@@ -199,7 +256,7 @@ static int adp5585_gpio_probe(struct platform_device *pdev)
 	gc->can_sleep = true;
 
 	gc->base = -1;
-	gc->ngpio = ADP5585_GPIO_MAX;
+	gc->ngpio = adp5585_gpio->info->max_gpio;
 	gc->label = pdev->name;
 	gc->owner = THIS_MODULE;
 
@@ -211,8 +268,34 @@ static int adp5585_gpio_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct adp5585_gpio_chip adp5585_gpio_chip_info = {
+	.bank = adp5585_gpio_bank,
+	.bit = adp5585_gpio_bit,
+	.debounce_dis_a = ADP5585_DEBOUNCE_DIS_A,
+	.rpull_cfg_a = ADP5585_RPULL_CONFIG_A,
+	.gpo_data_a = ADP5585_GPO_DATA_OUT_A,
+	.gpo_out_a = ADP5585_GPO_OUT_MODE_A,
+	.gpio_dir_a = ADP5585_GPIO_DIRECTION_A,
+	.gpi_stat_a = ADP5585_GPI_STATUS_A,
+	.max_gpio = ADP5585_PIN_MAX,
+	.has_bias_hole = true,
+};
+
+static const struct adp5585_gpio_chip adp5589_gpio_chip_info = {
+	.bank = adp5589_gpio_bank,
+	.bit = adp5589_gpio_bit,
+	.debounce_dis_a = ADP5589_DEBOUNCE_DIS_A,
+	.rpull_cfg_a = ADP5589_RPULL_CONFIG_A,
+	.gpo_data_a = ADP5589_GPO_DATA_OUT_A,
+	.gpo_out_a = ADP5589_GPO_OUT_MODE_A,
+	.gpio_dir_a = ADP5589_GPIO_DIRECTION_A,
+	.gpi_stat_a = ADP5589_GPI_STATUS_A,
+	.max_gpio = ADP5589_PIN_MAX,
+};
+
 static const struct platform_device_id adp5585_gpio_id_table[] = {
-	{ "adp5585-gpio" },
+	{ "adp5585-gpio", (kernel_ulong_t)&adp5585_gpio_chip_info },
+	{ "adp5589-gpio", (kernel_ulong_t)&adp5589_gpio_chip_info },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(platform, adp5585_gpio_id_table);
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index 6ecb90a6276c..d26f722cf31a 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -107,23 +107,23 @@
 
 #define ADP5585_MAX_REG			ADP5585_INT_EN
 
-/*
- * Bank 0 covers pins "GPIO 1/R0" to "GPIO 6/R5", numbered 0 to 5 by the
- * driver, and bank 1 covers pins "GPIO 7/C0" to "GPIO 11/C4", numbered 6 to
- * 10. Some variants of the ADP5585 don't support "GPIO 6/R5". As the driver
- * uses identical GPIO numbering for all variants to avoid confusion, GPIO 5 is
- * marked as reserved in the device tree for variants that don't support it.
- */
-#define ADP5585_BANK(n)			((n) >= 6 ? 1 : 0)
-#define ADP5585_BIT(n)			((n) >= 6 ? BIT((n) - 6) : BIT(n))
+#define ADP5585_PIN_MAX			11
 
 /* ADP5589 */
 #define		ADP5589_MAN_ID_VALUE		0x10
+#define ADP5589_GPI_STATUS_A		0x16
 #define ADP5589_GPI_STATUS_C		0x18
+#define ADP5589_RPULL_CONFIG_A		0x19
+#define ADP5589_DEBOUNCE_DIS_A		0x27
+#define ADP5589_GPO_DATA_OUT_A		0x2a
+#define ADP5589_GPO_OUT_MODE_A		0x2d
+#define		ADP5589_GPIO_DIRECTION_A	0x30
 #define ADP5589_PIN_CONFIG_D		0x4C
 #define ADP5589_INT_EN			0x4e
 #define ADP5589_MAX_REG			ADP5589_INT_EN
 
+#define ADP5589_PIN_MAX			19
+
 struct regmap;
 
 enum adp5585_variant {
-- 
cgit v1.2.3


From 75024f97e82e63d02b0743500efb1e264a1c2dd4 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:05 +0100
Subject: pwm: adp5585: add support for adp5589
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for the adp5589 I/O expander. From a PWM point of view it is
pretty similar to adp5585. Main difference is the address
of registers meaningful for configuring the PWM.

Acked-by: Uwe Kleine-König <ukleinek@kernel.org>
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-10-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/pwm/pwm-adp5585.c   | 73 ++++++++++++++++++++++++++++++++++-----------
 include/linux/mfd/adp5585.h |  3 ++
 2 files changed, 59 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pwm/pwm-adp5585.c b/drivers/pwm/pwm-adp5585.c
index add36bc7d221..dc2860979e24 100644
--- a/drivers/pwm/pwm-adp5585.c
+++ b/drivers/pwm/pwm-adp5585.c
@@ -33,21 +33,33 @@
 #define ADP5585_PWM_MIN_PERIOD_NS	(2ULL * NSEC_PER_SEC / ADP5585_PWM_OSC_FREQ_HZ)
 #define ADP5585_PWM_MAX_PERIOD_NS	(2ULL * 0xffff * NSEC_PER_SEC / ADP5585_PWM_OSC_FREQ_HZ)
 
+struct adp5585_pwm_chip {
+	unsigned int pwm_cfg;
+	unsigned int pwm_offt_low;
+	unsigned int pwm_ont_low;
+};
+
+struct adp5585_pwm {
+	const struct adp5585_pwm_chip *info;
+	struct regmap *regmap;
+	unsigned int ext_cfg;
+};
+
 static int pwm_adp5585_request(struct pwm_chip *chip, struct pwm_device *pwm)
 {
-	struct regmap *regmap = pwmchip_get_drvdata(chip);
+	struct adp5585_pwm *adp5585_pwm = pwmchip_get_drvdata(chip);
 
 	/* Configure the R3 pin as PWM output. */
-	return regmap_update_bits(regmap, ADP5585_PIN_CONFIG_C,
+	return regmap_update_bits(adp5585_pwm->regmap, adp5585_pwm->ext_cfg,
 				  ADP5585_R3_EXTEND_CFG_MASK,
 				  ADP5585_R3_EXTEND_CFG_PWM_OUT);
 }
 
 static void pwm_adp5585_free(struct pwm_chip *chip, struct pwm_device *pwm)
 {
-	struct regmap *regmap = pwmchip_get_drvdata(chip);
+	struct adp5585_pwm *adp5585_pwm = pwmchip_get_drvdata(chip);
 
-	regmap_update_bits(regmap, ADP5585_PIN_CONFIG_C,
+	regmap_update_bits(adp5585_pwm->regmap, adp5585_pwm->ext_cfg,
 			   ADP5585_R3_EXTEND_CFG_MASK,
 			   ADP5585_R3_EXTEND_CFG_GPIO4);
 }
@@ -56,14 +68,16 @@ static int pwm_adp5585_apply(struct pwm_chip *chip,
 			     struct pwm_device *pwm,
 			     const struct pwm_state *state)
 {
-	struct regmap *regmap = pwmchip_get_drvdata(chip);
+	struct adp5585_pwm *adp5585_pwm = pwmchip_get_drvdata(chip);
+	const struct adp5585_pwm_chip *info = adp5585_pwm->info;
+	struct regmap *regmap = adp5585_pwm->regmap;
 	u64 period, duty_cycle;
 	u32 on, off;
 	__le16 val;
 	int ret;
 
 	if (!state->enabled) {
-		regmap_clear_bits(regmap, ADP5585_PWM_CFG, ADP5585_PWM_EN);
+		regmap_clear_bits(regmap, info->pwm_cfg, ADP5585_PWM_EN);
 		return 0;
 	}
 
@@ -84,41 +98,43 @@ static int pwm_adp5585_apply(struct pwm_chip *chip,
 	off = div_u64(period, NSEC_PER_SEC / ADP5585_PWM_OSC_FREQ_HZ) - on;
 
 	val = cpu_to_le16(off);
-	ret = regmap_bulk_write(regmap, ADP5585_PWM_OFFT_LOW, &val, 2);
+	ret = regmap_bulk_write(regmap, info->pwm_offt_low, &val, 2);
 	if (ret)
 		return ret;
 
 	val = cpu_to_le16(on);
-	ret = regmap_bulk_write(regmap, ADP5585_PWM_ONT_LOW, &val, 2);
+	ret = regmap_bulk_write(regmap, info->pwm_ont_low, &val, 2);
 	if (ret)
 		return ret;
 
 	/* Enable PWM in continuous mode and no external AND'ing. */
-	ret = regmap_update_bits(regmap, ADP5585_PWM_CFG,
+	ret = regmap_update_bits(regmap, info->pwm_cfg,
 				 ADP5585_PWM_IN_AND | ADP5585_PWM_MODE |
 				 ADP5585_PWM_EN, ADP5585_PWM_EN);
 	if (ret)
 		return ret;
 
-	return regmap_set_bits(regmap, ADP5585_PWM_CFG, ADP5585_PWM_EN);
+	return regmap_set_bits(regmap, info->pwm_cfg, ADP5585_PWM_EN);
 }
 
 static int pwm_adp5585_get_state(struct pwm_chip *chip,
 				 struct pwm_device *pwm,
 				 struct pwm_state *state)
 {
-	struct regmap *regmap = pwmchip_get_drvdata(chip);
+	struct adp5585_pwm *adp5585_pwm = pwmchip_get_drvdata(chip);
+	const struct adp5585_pwm_chip *info = adp5585_pwm->info;
+	struct regmap *regmap = adp5585_pwm->regmap;
 	unsigned int on, off;
 	unsigned int val;
 	__le16 on_off;
 	int ret;
 
-	ret = regmap_bulk_read(regmap, ADP5585_PWM_OFFT_LOW, &on_off, 2);
+	ret = regmap_bulk_read(regmap, info->pwm_offt_low, &on_off, 2);
 	if (ret)
 		return ret;
 	off = le16_to_cpu(on_off);
 
-	ret = regmap_bulk_read(regmap, ADP5585_PWM_ONT_LOW, &on_off, 2);
+	ret = regmap_bulk_read(regmap, info->pwm_ont_low, &on_off, 2);
 	if (ret)
 		return ret;
 	on = le16_to_cpu(on_off);
@@ -128,7 +144,7 @@ static int pwm_adp5585_get_state(struct pwm_chip *chip,
 
 	state->polarity = PWM_POLARITY_NORMAL;
 
-	regmap_read(regmap, ADP5585_PWM_CFG, &val);
+	regmap_read(regmap, info->pwm_cfg, &val);
 	state->enabled = !!(val & ADP5585_PWM_EN);
 
 	return 0;
@@ -143,18 +159,28 @@ static const struct pwm_ops adp5585_pwm_ops = {
 
 static int adp5585_pwm_probe(struct platform_device *pdev)
 {
+	const struct platform_device_id *id = platform_get_device_id(pdev);
 	struct device *dev = &pdev->dev;
 	struct adp5585_dev *adp5585 = dev_get_drvdata(dev->parent);
+	struct adp5585_pwm *adp5585_pwm;
 	struct pwm_chip *chip;
 	int ret;
 
-	chip = devm_pwmchip_alloc(dev, ADP5585_PWM_CHAN_NUM, 0);
+	chip = devm_pwmchip_alloc(dev, ADP5585_PWM_CHAN_NUM,
+				  sizeof(*adp5585_pwm));
 	if (IS_ERR(chip))
 		return PTR_ERR(chip);
 
+	adp5585_pwm = pwmchip_get_drvdata(chip);
+	adp5585_pwm->regmap = adp5585->regmap;
+	adp5585_pwm->ext_cfg = adp5585->regs->ext_cfg;
+
+	adp5585_pwm->info = (const struct adp5585_pwm_chip *)id->driver_data;
+	if (!adp5585_pwm->info)
+		return -ENODEV;
+
 	device_set_of_node_from_dev(dev, dev->parent);
 
-	pwmchip_set_drvdata(chip, adp5585->regmap);
 	chip->ops = &adp5585_pwm_ops;
 
 	ret = devm_pwmchip_add(dev, chip);
@@ -164,8 +190,21 @@ static int adp5585_pwm_probe(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct adp5585_pwm_chip adp5589_pwm_chip_info = {
+	.pwm_cfg = ADP5585_PWM_CFG,
+	.pwm_offt_low = ADP5585_PWM_OFFT_LOW,
+	.pwm_ont_low = ADP5585_PWM_ONT_LOW,
+};
+
+static const struct adp5585_pwm_chip adp5585_pwm_chip_info = {
+	.pwm_cfg = ADP5589_PWM_CFG,
+	.pwm_offt_low = ADP5589_PWM_OFFT_LOW,
+	.pwm_ont_low = ADP5589_PWM_ONT_LOW,
+};
+
 static const struct platform_device_id adp5585_pwm_id_table[] = {
-	{ "adp5585-pwm" },
+	{ "adp5585-pwm", (kernel_ulong_t)&adp5585_pwm_chip_info },
+	{ "adp5589-pwm", (kernel_ulong_t)&adp5589_pwm_chip_info },
 	{ /* Sentinel */ }
 };
 MODULE_DEVICE_TABLE(platform, adp5585_pwm_id_table);
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index d26f722cf31a..77f7c74f084d 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -118,6 +118,9 @@
 #define ADP5589_GPO_DATA_OUT_A		0x2a
 #define ADP5589_GPO_OUT_MODE_A		0x2d
 #define		ADP5589_GPIO_DIRECTION_A	0x30
+#define ADP5589_PWM_OFFT_LOW		0x3e
+#define ADP5589_PWM_ONT_LOW		0x40
+#define ADP5589_PWM_CFG			0x42
 #define ADP5589_PIN_CONFIG_D		0x4C
 #define ADP5589_INT_EN			0x4e
 #define ADP5589_MAX_REG			ADP5589_INT_EN
-- 
cgit v1.2.3


From 47a1f759b776ec9287f675f5d4fbf60b94cc566d Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:07 +0100
Subject: mfd: adp5585: Add support for event handling
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

These devices are capable of generate FIFO based events based on KEY or
GPI presses. Add support for handling these events. This is in
preparation of adding full support for keymap and gpis based events.

Reviewed-by: Lee Jones <lee@kernel.org>
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-12-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/adp5585.c       | 176 ++++++++++++++++++++++++++++++++++++++++++--
 include/linux/mfd/adp5585.h |  18 +++++
 2 files changed, 186 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/adp5585.c b/drivers/mfd/adp5585.c
index ae12372bdde9..ae2448697ef4 100644
--- a/drivers/mfd/adp5585.c
+++ b/drivers/mfd/adp5585.c
@@ -8,6 +8,7 @@
  */
 
 #include <linux/array_size.h>
+#include <linux/bitfield.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/i2c.h>
@@ -165,10 +166,16 @@ static const struct regmap_config adp5589_regmap_config_template = {
 
 static const struct adp5585_regs adp5585_regs = {
 	.ext_cfg = ADP5585_PIN_CONFIG_C,
+	.int_en = ADP5585_INT_EN,
+	.gen_cfg = ADP5585_GENERAL_CFG,
+	.poll_ptime_cfg = ADP5585_POLL_PTIME_CFG,
 };
 
 static const struct adp5585_regs adp5589_regs = {
 	.ext_cfg = ADP5589_PIN_CONFIG_D,
+	.int_en = ADP5589_INT_EN,
+	.gen_cfg = ADP5589_GENERAL_CFG,
+	.poll_ptime_cfg = ADP5589_POLL_PTIME_CFG,
 };
 
 static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp5585)
@@ -241,6 +248,146 @@ static void adp5585_osc_disable(void *data)
 	regmap_write(adp5585->regmap, ADP5585_GENERAL_CFG, 0);
 }
 
+static void adp5585_report_events(struct adp5585_dev *adp5585, int ev_cnt)
+{
+	unsigned int i;
+
+	for (i = 0; i < ev_cnt; i++) {
+		unsigned long key_val, key_press;
+		unsigned int key;
+		int ret;
+
+		ret = regmap_read(adp5585->regmap, ADP5585_FIFO_1 + i, &key);
+		if (ret)
+			return;
+
+		key_val = FIELD_GET(ADP5585_KEY_EVENT_MASK, key);
+		key_press = FIELD_GET(ADP5585_KEV_EV_PRESS_MASK, key);
+
+		blocking_notifier_call_chain(&adp5585->event_notifier, key_val, (void *)key_press);
+	}
+}
+
+static irqreturn_t adp5585_irq(int irq, void *data)
+{
+	struct adp5585_dev *adp5585 = data;
+	unsigned int status, ev_cnt;
+	int ret;
+
+	ret = regmap_read(adp5585->regmap, ADP5585_INT_STATUS, &status);
+	if (ret)
+		return IRQ_HANDLED;
+
+	if (status & ADP5585_OVRFLOW_INT)
+		dev_err_ratelimited(adp5585->dev, "Event overflow error\n");
+
+	if (!(status & ADP5585_EVENT_INT))
+		goto out_irq;
+
+	ret = regmap_read(adp5585->regmap, ADP5585_STATUS, &ev_cnt);
+	if (ret)
+		goto out_irq;
+
+	ev_cnt = FIELD_GET(ADP5585_EC_MASK, ev_cnt);
+	if (!ev_cnt)
+		goto out_irq;
+
+	adp5585_report_events(adp5585, ev_cnt);
+out_irq:
+	regmap_write(adp5585->regmap, ADP5585_INT_STATUS, status);
+	return IRQ_HANDLED;
+}
+
+static int adp5585_setup(struct adp5585_dev *adp5585)
+{
+	const struct adp5585_regs *regs = adp5585->regs;
+	unsigned int reg_val, i;
+	int ret;
+
+	/* Clear any possible event by reading all the FIFO entries */
+	for (i = 0; i < ADP5585_EV_MAX; i++) {
+		ret = regmap_read(adp5585->regmap, ADP5585_FIFO_1 + i, &reg_val);
+		if (ret)
+			return ret;
+	}
+
+	ret = regmap_write(adp5585->regmap, regs->poll_ptime_cfg, adp5585->ev_poll_time);
+	if (ret)
+		return ret;
+
+	/*
+	 * Enable the internal oscillator, as it's shared between multiple
+	 * functions.
+	 */
+	ret = regmap_write(adp5585->regmap, regs->gen_cfg,
+			   ADP5585_OSC_FREQ_500KHZ | ADP5585_INT_CFG | ADP5585_OSC_EN);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(adp5585->dev, adp5585_osc_disable, adp5585);
+}
+
+static int adp5585_parse_fw(struct adp5585_dev *adp5585)
+{
+	unsigned int prop_val;
+	int ret;
+
+	ret = device_property_read_u32(adp5585->dev, "poll-interval", &prop_val);
+	if (!ret) {
+		adp5585->ev_poll_time = prop_val / 10 - 1;
+		/*
+		 * ev_poll_time is the raw value to be written on the register and 0 to 3 are the
+		 * valid values.
+		 */
+		if (adp5585->ev_poll_time > 3)
+			return dev_err_probe(adp5585->dev, -EINVAL,
+					     "Invalid value(%u) for poll-interval\n", prop_val);
+	}
+
+	return 0;
+}
+
+static void adp5585_irq_disable(void *data)
+{
+	struct adp5585_dev *adp5585 = data;
+
+	regmap_write(adp5585->regmap, adp5585->regs->int_en, 0);
+}
+
+static int adp5585_irq_enable(struct i2c_client *i2c,
+			      struct adp5585_dev *adp5585)
+{
+	const struct adp5585_regs *regs = adp5585->regs;
+	unsigned int stat;
+	int ret;
+
+	if (i2c->irq <= 0)
+		return 0;
+
+	ret = devm_request_threaded_irq(&i2c->dev, i2c->irq, NULL, adp5585_irq,
+					IRQF_ONESHOT, i2c->name, adp5585);
+	if (ret)
+		return ret;
+
+	/*
+	 * Clear any possible outstanding interrupt before enabling them. We do that by reading
+	 * the status register and writing back the same value.
+	 */
+	ret = regmap_read(adp5585->regmap, ADP5585_INT_STATUS, &stat);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(adp5585->regmap, ADP5585_INT_STATUS, stat);
+	if (ret)
+		return ret;
+
+	ret = regmap_write(adp5585->regmap, regs->int_en, ADP5585_OVRFLOW_IEN | ADP5585_EVENT_IEN);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(&i2c->dev, adp5585_irq_disable, adp5585);
+}
+
 static int adp5585_i2c_probe(struct i2c_client *i2c)
 {
 	struct regmap_config *regmap_config;
@@ -254,6 +401,8 @@ static int adp5585_i2c_probe(struct i2c_client *i2c)
 
 	i2c_set_clientdata(i2c, adp5585);
 	adp5585->dev = &i2c->dev;
+	adp5585->irq = i2c->irq;
+	BLOCKING_INIT_NOTIFIER_HEAD(&adp5585->event_notifier);
 
 	adp5585->variant = (enum adp5585_variant)(uintptr_t)i2c_get_match_data(i2c);
 	if (!adp5585->variant)
@@ -278,25 +427,28 @@ static int adp5585_i2c_probe(struct i2c_client *i2c)
 		return dev_err_probe(&i2c->dev, -ENODEV,
 				     "Invalid device ID 0x%02x\n", id);
 
-	/*
-	 * Enable the internal oscillator, as it's shared between multiple
-	 * functions.
-	 */
-	ret = regmap_set_bits(adp5585->regmap, ADP5585_GENERAL_CFG, ADP5585_OSC_EN);
+	ret = adp5585_parse_fw(adp5585);
 	if (ret)
 		return ret;
 
-	ret = devm_add_action_or_reset(&i2c->dev, adp5585_osc_disable, adp5585);
+	ret = adp5585_setup(adp5585);
 	if (ret)
 		return ret;
 
-	return adp5585_add_devices(adp5585);
+	ret = adp5585_add_devices(adp5585);
+	if (ret)
+		return ret;
+
+	return adp5585_irq_enable(i2c, adp5585);
 }
 
 static int adp5585_suspend(struct device *dev)
 {
 	struct adp5585_dev *adp5585 = dev_get_drvdata(dev);
 
+	if (adp5585->irq)
+		disable_irq(adp5585->irq);
+
 	regcache_cache_only(adp5585->regmap, true);
 
 	return 0;
@@ -305,11 +457,19 @@ static int adp5585_suspend(struct device *dev)
 static int adp5585_resume(struct device *dev)
 {
 	struct adp5585_dev *adp5585 = dev_get_drvdata(dev);
+	int ret;
 
 	regcache_cache_only(adp5585->regmap, false);
 	regcache_mark_dirty(adp5585->regmap);
 
-	return regcache_sync(adp5585->regmap);
+	ret = regcache_sync(adp5585->regmap);
+	if (ret)
+		return ret;
+
+	if (adp5585->irq)
+		enable_irq(adp5585->irq);
+
+	return 0;
 }
 
 static DEFINE_SIMPLE_DEV_PM_OPS(adp5585_pm, adp5585_suspend, adp5585_resume);
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index 77f7c74f084d..43a33a3d3f5a 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -10,13 +10,20 @@
 #define __MFD_ADP5585_H_
 
 #include <linux/bits.h>
+#include <linux/notifier.h>
 
 #define ADP5585_ID			0x00
 #define		ADP5585_MAN_ID_VALUE		0x20
 #define		ADP5585_MAN_ID_MASK		GENMASK(7, 4)
+#define		ADP5585_REV_ID_MASK		GENMASK(3, 0)
 #define ADP5585_INT_STATUS		0x01
+#define		ADP5585_OVRFLOW_INT		BIT(2)
+#define		ADP5585_EVENT_INT		BIT(0)
 #define ADP5585_STATUS			0x02
+#define		ADP5585_EC_MASK			GENMASK(4, 0)
 #define ADP5585_FIFO_1			0x03
+#define		ADP5585_KEV_EV_PRESS_MASK	BIT(7)
+#define		ADP5585_KEY_EVENT_MASK		GENMASK(6, 0)
 #define ADP5585_FIFO_2			0x04
 #define ADP5585_FIFO_3			0x05
 #define ADP5585_FIFO_4			0x06
@@ -32,6 +39,7 @@
 #define ADP5585_FIFO_14			0x10
 #define ADP5585_FIFO_15			0x11
 #define ADP5585_FIFO_16			0x12
+#define		ADP5585_EV_MAX			(ADP5585_FIFO_16 - ADP5585_FIFO_1 + 1)
 #define ADP5585_GPI_INT_STAT_A		0x13
 #define ADP5585_GPI_INT_STAT_B		0x14
 #define ADP5585_GPI_STATUS_A		0x15
@@ -104,6 +112,8 @@
 #define		ADP5585_INT_CFG			BIT(1)
 #define		ADP5585_RST_CFG			BIT(0)
 #define ADP5585_INT_EN			0x3c
+#define		ADP5585_OVRFLOW_IEN		BIT(2)
+#define		ADP5585_EVENT_IEN		BIT(0)
 
 #define ADP5585_MAX_REG			ADP5585_INT_EN
 
@@ -121,7 +131,9 @@
 #define ADP5589_PWM_OFFT_LOW		0x3e
 #define ADP5589_PWM_ONT_LOW		0x40
 #define ADP5589_PWM_CFG			0x42
+#define ADP5589_POLL_PTIME_CFG		0x48
 #define ADP5589_PIN_CONFIG_D		0x4C
+#define ADP5589_GENERAL_CFG		0x4d
 #define ADP5589_INT_EN			0x4e
 #define ADP5589_MAX_REG			ADP5589_INT_EN
 
@@ -142,15 +154,21 @@ enum adp5585_variant {
 };
 
 struct adp5585_regs {
+	unsigned int gen_cfg;
 	unsigned int ext_cfg;
+	unsigned int int_en;
+	unsigned int poll_ptime_cfg;
 };
 
 struct adp5585_dev {
 	struct device *dev;
 	struct regmap *regmap;
 	const struct adp5585_regs *regs;
+	struct blocking_notifier_head event_notifier;
 	enum adp5585_variant variant;
 	unsigned int id;
+	int irq;
+	unsigned int ev_poll_time;
 };
 
 #endif
-- 
cgit v1.2.3


From 333812da70d5f71bf5e176f6d55a5f716301b5fc Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:08 +0100
Subject: mfd: adp5585: Support reset and unlock events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ADP558x family of devices can be programmed to respond to some
especial events, In case of the unlock events, one can lock the keypad
and use KEYS or GPIs events to unlock it. For the reset events, one can
again use a combinations of GPIs/KEYs in order to generate an event that
will trigger the device to generate an output reset pulse.

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-13-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/adp5585.c       | 274 +++++++++++++++++++++++++++++++++++++++++++-
 include/linux/mfd/adp5585.h |  40 +++++++
 2 files changed, 312 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/adp5585.c b/drivers/mfd/adp5585.c
index ae2448697ef4..30014deee41f 100644
--- a/drivers/mfd/adp5585.c
+++ b/drivers/mfd/adp5585.c
@@ -169,6 +169,9 @@ static const struct adp5585_regs adp5585_regs = {
 	.int_en = ADP5585_INT_EN,
 	.gen_cfg = ADP5585_GENERAL_CFG,
 	.poll_ptime_cfg = ADP5585_POLL_PTIME_CFG,
+	.reset_cfg = ADP5585_RESET_CFG,
+	.reset1_event_a = ADP5585_RESET1_EVENT_A,
+	.reset2_event_a = ADP5585_RESET2_EVENT_A,
 };
 
 static const struct adp5585_regs adp5589_regs = {
@@ -176,8 +179,54 @@ static const struct adp5585_regs adp5589_regs = {
 	.int_en = ADP5589_INT_EN,
 	.gen_cfg = ADP5589_GENERAL_CFG,
 	.poll_ptime_cfg = ADP5589_POLL_PTIME_CFG,
+	.reset_cfg = ADP5589_RESET_CFG,
+	.reset1_event_a = ADP5589_RESET1_EVENT_A,
+	.reset2_event_a = ADP5589_RESET2_EVENT_A,
 };
 
+static int adp5585_validate_event(const struct adp5585_dev *adp5585, unsigned int ev)
+{
+	if (adp5585->has_pin6) {
+		if (ev >= ADP5585_ROW5_KEY_EVENT_START && ev <= ADP5585_ROW5_KEY_EVENT_END)
+			return 0;
+		if (ev >= ADP5585_GPI_EVENT_START && ev <= ADP5585_GPI_EVENT_END)
+			return 0;
+
+		return dev_err_probe(adp5585->dev, -EINVAL,
+				     "Invalid unlock/reset event(%u) for this device\n", ev);
+	}
+
+	if (ev >= ADP5585_KEY_EVENT_START && ev <= ADP5585_KEY_EVENT_END)
+		return 0;
+	if (ev >= ADP5585_GPI_EVENT_START && ev <= ADP5585_GPI_EVENT_END) {
+		/*
+		 * Some variants of the adp5585 do not have the Row 5
+		 * (meaning pin 6 or GPIO 6) available. Instead that pin serves
+		 * as a reset pin. So, we need to make sure no event is
+		 * configured for it.
+		 */
+		if (ev == (ADP5585_GPI_EVENT_START + 5))
+			return dev_err_probe(adp5585->dev, -EINVAL,
+					     "Invalid unlock/reset event(%u). R5 not available\n",
+					     ev);
+		return 0;
+	}
+
+	return dev_err_probe(adp5585->dev, -EINVAL,
+			     "Invalid unlock/reset event(%u) for this device\n", ev);
+}
+
+static int adp5589_validate_event(const struct adp5585_dev *adp5585, unsigned int ev)
+{
+	if (ev >= ADP5589_KEY_EVENT_START && ev <= ADP5589_KEY_EVENT_END)
+		return 0;
+	if (ev >= ADP5589_GPI_EVENT_START && ev <= ADP5589_GPI_EVENT_END)
+		return 0;
+
+	return dev_err_probe(adp5585->dev, -EINVAL,
+			     "Invalid unlock/reset event(%u) for this device\n", ev);
+}
+
 static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp5585)
 {
 	struct regmap_config *regmap_config;
@@ -190,6 +239,8 @@ static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp
 	case ADP5585_04:
 		adp5585->id = ADP5585_MAN_ID_VALUE;
 		adp5585->regs = &adp5585_regs;
+		if (adp5585->variant == ADP5585_01)
+			adp5585->has_pin6 = true;
 		regmap_config = devm_kmemdup(adp5585->dev, &adp5585_regmap_config_template,
 					     sizeof(*regmap_config), GFP_KERNEL);
 		break;
@@ -198,6 +249,8 @@ static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp
 	case ADP5589_02:
 		adp5585->id = ADP5589_MAN_ID_VALUE;
 		adp5585->regs = &adp5589_regs;
+		adp5585->has_unlock = true;
+		adp5585->has_pin6 = true;
 		regmap_config = devm_kmemdup(adp5585->dev, &adp5589_regmap_config_template,
 					     sizeof(*regmap_config), GFP_KERNEL);
 		break;
@@ -213,6 +266,167 @@ static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp
 	return regmap_config;
 }
 
+static int adp5585_parse_ev_array(const struct adp5585_dev *adp5585, const char *prop, u32 *events,
+				  u32 *n_events, u32 max_evs, bool reset_ev)
+{
+	struct device *dev = adp5585->dev;
+	unsigned int ev;
+	int ret;
+
+	/*
+	 * The device has the capability of handling special events through GPIs or a Keypad:
+	 *  unlock events: Unlock the keymap until one of the configured events is detected.
+	 *  reset events: Generate a reset pulse when one of the configured events is detected.
+	 */
+	ret = device_property_count_u32(dev, prop);
+	if (ret < 0)
+		return 0;
+
+	*n_events = ret;
+
+	if (!adp5585->has_unlock && !reset_ev)
+		return dev_err_probe(dev, -EOPNOTSUPP, "Unlock keys not supported\n");
+
+	if (*n_events > max_evs)
+		return dev_err_probe(dev, -EINVAL,
+				     "Invalid number of keys(%u > %u) for %s\n",
+				     *n_events, max_evs, prop);
+
+	ret = device_property_read_u32_array(dev, prop, events, *n_events);
+	if (ret)
+		return ret;
+
+	for (ev = 0; ev < *n_events; ev++) {
+		if (!reset_ev && events[ev] == ADP5589_UNLOCK_WILDCARD)
+			continue;
+
+		if (adp5585->id == ADP5585_MAN_ID_VALUE)
+			ret = adp5585_validate_event(adp5585, events[ev]);
+		else
+			ret = adp5589_validate_event(adp5585, events[ev]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static int adp5585_unlock_ev_parse(struct adp5585_dev *adp5585)
+{
+	struct device *dev = adp5585->dev;
+	int ret;
+
+	ret = adp5585_parse_ev_array(adp5585, "adi,unlock-events", adp5585->unlock_keys,
+				     &adp5585->nkeys_unlock, ARRAY_SIZE(adp5585->unlock_keys),
+				     false);
+	if (ret)
+		return ret;
+	if (!adp5585->nkeys_unlock)
+		return 0;
+
+	ret = device_property_read_u32(dev, "adi,unlock-trigger-sec", &adp5585->unlock_time);
+	if (!ret) {
+		if (adp5585->unlock_time > ADP5585_MAX_UNLOCK_TIME_SEC)
+			return dev_err_probe(dev, -EINVAL,
+					     "Invalid unlock time(%u > %d)\n",
+					     adp5585->unlock_time,
+					     ADP5585_MAX_UNLOCK_TIME_SEC);
+	}
+
+	return 0;
+}
+
+static int adp5585_reset_ev_parse(struct adp5585_dev *adp5585)
+{
+	struct device *dev = adp5585->dev;
+	u32 prop_val;
+	int ret;
+
+	ret = adp5585_parse_ev_array(adp5585, "adi,reset1-events", adp5585->reset1_keys,
+				     &adp5585->nkeys_reset1,
+				     ARRAY_SIZE(adp5585->reset1_keys), true);
+	if (ret)
+		return ret;
+
+	ret = adp5585_parse_ev_array(adp5585, "adi,reset2-events",
+				     adp5585->reset2_keys,
+				     &adp5585->nkeys_reset2,
+				     ARRAY_SIZE(adp5585->reset2_keys), true);
+	if (ret)
+		return ret;
+
+	if (!adp5585->nkeys_reset1 && !adp5585->nkeys_reset2)
+		return 0;
+
+	if (adp5585->nkeys_reset1 && device_property_read_bool(dev, "adi,reset1-active-high"))
+		adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET1_POL, 1);
+
+	if (adp5585->nkeys_reset2 && device_property_read_bool(dev, "adi,reset2-active-high"))
+		adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET2_POL, 1);
+
+	if (device_property_read_bool(dev, "adi,rst-passthrough-enable"))
+		adp5585->reset_cfg |= FIELD_PREP(ADP5585_RST_PASSTHRU_EN, 1);
+
+	ret = device_property_read_u32(dev, "adi,reset-trigger-ms", &prop_val);
+	if (!ret) {
+		switch (prop_val) {
+		case 0:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET_TRIG_TIME, 0);
+			break;
+		case 1000:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET_TRIG_TIME, 1);
+			break;
+		case 1500:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET_TRIG_TIME, 2);
+			break;
+		case 2000:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET_TRIG_TIME, 3);
+			break;
+		case 2500:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET_TRIG_TIME, 4);
+			break;
+		case 3000:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET_TRIG_TIME, 5);
+			break;
+		case 3500:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET_TRIG_TIME, 6);
+			break;
+		case 4000:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_RESET_TRIG_TIME, 7);
+			break;
+		default:
+			return dev_err_probe(dev, -EINVAL,
+					     "Invalid value(%u) for adi,reset-trigger-ms\n",
+					     prop_val);
+		}
+	}
+
+	ret = device_property_read_u32(dev, "adi,reset-pulse-width-us", &prop_val);
+	if (!ret) {
+		switch (prop_val) {
+		case 500:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_PULSE_WIDTH, 0);
+			break;
+		case 1000:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_PULSE_WIDTH, 1);
+			break;
+		case 2000:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_PULSE_WIDTH, 2);
+			break;
+		case 10000:
+			adp5585->reset_cfg |= FIELD_PREP(ADP5585_PULSE_WIDTH, 3);
+			break;
+		default:
+			return dev_err_probe(dev, -EINVAL,
+					     "Invalid value(%u) for adi,reset-pulse-width-us\n",
+					     prop_val);
+		}
+		return ret;
+	}
+
+	return 0;
+}
+
 static int adp5585_add_devices(const struct adp5585_dev *adp5585)
 {
 	struct device *dev = adp5585->dev;
@@ -301,9 +515,61 @@ out_irq:
 static int adp5585_setup(struct adp5585_dev *adp5585)
 {
 	const struct adp5585_regs *regs = adp5585->regs;
-	unsigned int reg_val, i;
+	unsigned int reg_val = 0, i;
 	int ret;
 
+	/* Configure the device with reset and unlock events */
+	for (i = 0; i < adp5585->nkeys_unlock; i++) {
+		ret = regmap_write(adp5585->regmap, ADP5589_UNLOCK1 + i,
+				   adp5585->unlock_keys[i] | ADP5589_UNLOCK_EV_PRESS);
+		if (ret)
+			return ret;
+	}
+
+	if (adp5585->nkeys_unlock) {
+		ret = regmap_update_bits(adp5585->regmap, ADP5589_UNLOCK_TIMERS,
+					 ADP5589_UNLOCK_TIMER, adp5585->unlock_time);
+		if (ret)
+			return ret;
+
+		ret = regmap_set_bits(adp5585->regmap, ADP5589_LOCK_CFG, ADP5589_LOCK_EN);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < adp5585->nkeys_reset1; i++) {
+		ret = regmap_write(adp5585->regmap, regs->reset1_event_a + i,
+				   adp5585->reset1_keys[i] | ADP5585_RESET_EV_PRESS);
+		if (ret)
+			return ret;
+	}
+
+	for (i = 0; i < adp5585->nkeys_reset2; i++) {
+		ret = regmap_write(adp5585->regmap, regs->reset2_event_a + i,
+				   adp5585->reset2_keys[i] | ADP5585_RESET_EV_PRESS);
+		if (ret)
+			return ret;
+	}
+
+	if (adp5585->nkeys_reset1 || adp5585->nkeys_reset2) {
+		ret = regmap_write(adp5585->regmap, regs->reset_cfg, adp5585->reset_cfg);
+		if (ret)
+			return ret;
+
+		/* If there's a reset1 event, then R4 is used as an output for the reset signal */
+		if (adp5585->nkeys_reset1)
+			reg_val = ADP5585_R4_EXTEND_CFG_RESET1;
+		/* If there's a reset2 event, then C4 is used as an output for the reset signal */
+		if (adp5585->nkeys_reset2)
+			reg_val |= ADP5585_C4_EXTEND_CFG_RESET2;
+
+		ret = regmap_update_bits(adp5585->regmap, regs->ext_cfg,
+					 ADP5585_C4_EXTEND_CFG_MASK | ADP5585_R4_EXTEND_CFG_MASK,
+					 reg_val);
+		if (ret)
+			return ret;
+	}
+
 	/* Clear any possible event by reading all the FIFO entries */
 	for (i = 0; i < ADP5585_EV_MAX; i++) {
 		ret = regmap_read(adp5585->regmap, ADP5585_FIFO_1 + i, &reg_val);
@@ -344,7 +610,11 @@ static int adp5585_parse_fw(struct adp5585_dev *adp5585)
 					     "Invalid value(%u) for poll-interval\n", prop_val);
 	}
 
-	return 0;
+	ret = adp5585_unlock_ev_parse(adp5585);
+	if (ret)
+		return ret;
+
+	return adp5585_reset_ev_parse(adp5585);
 }
 
 static void adp5585_irq_disable(void *data)
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index 43a33a3d3f5a..db483ef9693a 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -68,6 +68,7 @@
 #define ADP5585_GPIO_DIRECTION_A	0x27
 #define ADP5585_GPIO_DIRECTION_B	0x28
 #define ADP5585_RESET1_EVENT_A		0x29
+#define		ADP5585_RESET_EV_PRESS		BIT(7)
 #define ADP5585_RESET1_EVENT_B		0x2a
 #define ADP5585_RESET1_EVENT_C		0x2b
 #define ADP5585_RESET2_EVENT_A		0x2c
@@ -118,6 +119,13 @@
 #define ADP5585_MAX_REG			ADP5585_INT_EN
 
 #define ADP5585_PIN_MAX			11
+#define ADP5585_MAX_UNLOCK_TIME_SEC	7
+#define ADP5585_KEY_EVENT_START		1
+#define ADP5585_KEY_EVENT_END		25
+#define ADP5585_GPI_EVENT_START		37
+#define ADP5585_GPI_EVENT_END		47
+#define ADP5585_ROW5_KEY_EVENT_START	1
+#define ADP5585_ROW5_KEY_EVENT_END	30
 
 /* ADP5589 */
 #define		ADP5589_MAN_ID_VALUE		0x10
@@ -128,6 +136,20 @@
 #define ADP5589_GPO_DATA_OUT_A		0x2a
 #define ADP5589_GPO_OUT_MODE_A		0x2d
 #define		ADP5589_GPIO_DIRECTION_A	0x30
+#define ADP5589_UNLOCK1			0x33
+#define		ADP5589_UNLOCK_EV_PRESS		BIT(7)
+#define ADP5589_UNLOCK_TIMERS		0x36
+#define		ADP5589_UNLOCK_TIMER		GENMASK(2, 0)
+#define ADP5589_LOCK_CFG		0x37
+#define		ADP5589_LOCK_EN			BIT(0)
+#define ADP5589_RESET1_EVENT_A		0x38
+#define ADP5589_RESET2_EVENT_A		0x3B
+#define ADP5589_RESET_CFG		0x3D
+#define		ADP5585_RESET2_POL		BIT(7)
+#define		ADP5585_RESET1_POL		BIT(6)
+#define		ADP5585_RST_PASSTHRU_EN		BIT(5)
+#define		ADP5585_RESET_TRIG_TIME		GENMASK(4, 2)
+#define		ADP5585_PULSE_WIDTH		GENMASK(1, 0)
 #define ADP5589_PWM_OFFT_LOW		0x3e
 #define ADP5589_PWM_ONT_LOW		0x40
 #define ADP5589_PWM_CFG			0x42
@@ -138,6 +160,11 @@
 #define ADP5589_MAX_REG			ADP5589_INT_EN
 
 #define ADP5589_PIN_MAX			19
+#define ADP5589_KEY_EVENT_START		1
+#define ADP5589_KEY_EVENT_END		88
+#define ADP5589_GPI_EVENT_START		97
+#define ADP5589_GPI_EVENT_END		115
+#define ADP5589_UNLOCK_WILDCARD		127
 
 struct regmap;
 
@@ -158,6 +185,9 @@ struct adp5585_regs {
 	unsigned int ext_cfg;
 	unsigned int int_en;
 	unsigned int poll_ptime_cfg;
+	unsigned int reset_cfg;
+	unsigned int reset1_event_a;
+	unsigned int reset2_event_a;
 };
 
 struct adp5585_dev {
@@ -167,8 +197,18 @@ struct adp5585_dev {
 	struct blocking_notifier_head event_notifier;
 	enum adp5585_variant variant;
 	unsigned int id;
+	bool has_unlock;
+	bool has_pin6;
 	int irq;
 	unsigned int ev_poll_time;
+	unsigned int unlock_time;
+	unsigned int unlock_keys[2];
+	unsigned int nkeys_unlock;
+	unsigned int reset1_keys[3];
+	unsigned int nkeys_reset1;
+	unsigned int reset2_keys[2];
+	unsigned int nkeys_reset2;
+	u8 reset_cfg;
 };
 
 #endif
-- 
cgit v1.2.3


From bd113a13e1fa51789f55987369b80e1d8bc19389 Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:09 +0100
Subject: mfd: adp5585: Add support for input devices
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The ADP558x family supports a built in keypad matrix decoder which can
be added as an Input device. In order to both support the Input and the
GPIO device, we need to create a bitmap of the supported pins and track
their usage since they can either be used as GPIOs (GPIs) or as part of
the keymap.

We also need to mark special pins busy in case some features are being
used (ex: pwm or reset events).

Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-14-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/adp5585.c       | 31 +++++++++++++++++++++++++++++++
 include/linux/mfd/adp5585.h | 10 ++++++++++
 2 files changed, 41 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/adp5585.c b/drivers/mfd/adp5585.c
index 30014deee41f..8f0fd7374426 100644
--- a/drivers/mfd/adp5585.c
+++ b/drivers/mfd/adp5585.c
@@ -22,17 +22,20 @@
 enum {
 	ADP5585_DEV_GPIO,
 	ADP5585_DEV_PWM,
+	ADP5585_DEV_INPUT,
 	ADP5585_DEV_MAX
 };
 
 static const struct mfd_cell adp5585_devs[ADP5585_DEV_MAX] = {
 	MFD_CELL_NAME("adp5585-gpio"),
 	MFD_CELL_NAME("adp5585-pwm"),
+	MFD_CELL_NAME("adp5585-keys"),
 };
 
 static const struct mfd_cell adp5589_devs[] = {
 	MFD_CELL_NAME("adp5589-gpio"),
 	MFD_CELL_NAME("adp5589-pwm"),
+	MFD_CELL_NAME("adp5589-keys"),
 };
 
 static const struct regmap_range adp5585_volatile_ranges[] = {
@@ -172,6 +175,7 @@ static const struct adp5585_regs adp5585_regs = {
 	.reset_cfg = ADP5585_RESET_CFG,
 	.reset1_event_a = ADP5585_RESET1_EVENT_A,
 	.reset2_event_a = ADP5585_RESET2_EVENT_A,
+	.pin_cfg_a = ADP5585_PIN_CONFIG_A,
 };
 
 static const struct adp5585_regs adp5589_regs = {
@@ -182,6 +186,7 @@ static const struct adp5585_regs adp5589_regs = {
 	.reset_cfg = ADP5589_RESET_CFG,
 	.reset1_event_a = ADP5589_RESET1_EVENT_A,
 	.reset2_event_a = ADP5589_RESET2_EVENT_A,
+	.pin_cfg_a = ADP5589_PIN_CONFIG_A,
 };
 
 static int adp5585_validate_event(const struct adp5585_dev *adp5585, unsigned int ev)
@@ -239,6 +244,8 @@ static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp
 	case ADP5585_04:
 		adp5585->id = ADP5585_MAN_ID_VALUE;
 		adp5585->regs = &adp5585_regs;
+		adp5585->n_pins = ADP5585_PIN_MAX;
+		adp5585->reset2_out = ADP5585_RESET2_OUT;
 		if (adp5585->variant == ADP5585_01)
 			adp5585->has_pin6 = true;
 		regmap_config = devm_kmemdup(adp5585->dev, &adp5585_regmap_config_template,
@@ -251,6 +258,8 @@ static struct regmap_config *adp5585_fill_variant_config(struct adp5585_dev *adp
 		adp5585->regs = &adp5589_regs;
 		adp5585->has_unlock = true;
 		adp5585->has_pin6 = true;
+		adp5585->n_pins = ADP5589_PIN_MAX;
+		adp5585->reset2_out = ADP5589_RESET2_OUT;
 		regmap_config = devm_kmemdup(adp5585->dev, &adp5589_regmap_config_template,
 					     sizeof(*regmap_config), GFP_KERNEL);
 		break;
@@ -439,6 +448,8 @@ static int adp5585_add_devices(const struct adp5585_dev *adp5585)
 		cells = adp5589_devs;
 
 	if (device_property_present(dev, "#pwm-cells")) {
+		/* Make sure the PWM output pin is not used by the GPIO or INPUT devices */
+		__set_bit(ADP5585_PWM_OUT, adp5585->pin_usage);
 		ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO,
 					   &cells[ADP5585_DEV_PWM], 1, NULL, 0, NULL);
 		if (ret)
@@ -452,6 +463,13 @@ static int adp5585_add_devices(const struct adp5585_dev *adp5585)
 			return dev_err_probe(dev, ret, "Failed to add GPIO device\n");
 	}
 
+	if (device_property_present(adp5585->dev, "adi,keypad-pins")) {
+		ret = devm_mfd_add_devices(adp5585->dev, PLATFORM_DEVID_AUTO,
+					   &cells[ADP5585_DEV_INPUT], 1, NULL, 0, NULL);
+		if (ret)
+			return dev_err_probe(dev, ret, "Failed to add input device\n");
+	}
+
 	return 0;
 }
 
@@ -518,6 +536,10 @@ static int adp5585_setup(struct adp5585_dev *adp5585)
 	unsigned int reg_val = 0, i;
 	int ret;
 
+	/* If pin_6 (ROW5/GPI6) is not available, make sure to mark it as "busy" */
+	if (!adp5585->has_pin6)
+		__set_bit(ADP5585_ROW5, adp5585->pin_usage);
+
 	/* Configure the device with reset and unlock events */
 	for (i = 0; i < adp5585->nkeys_unlock; i++) {
 		ret = regmap_write(adp5585->regmap, ADP5589_UNLOCK1 + i,
@@ -542,6 +564,9 @@ static int adp5585_setup(struct adp5585_dev *adp5585)
 				   adp5585->reset1_keys[i] | ADP5585_RESET_EV_PRESS);
 		if (ret)
 			return ret;
+
+		/* Mark that pin as not usable for the INPUT and GPIO devices. */
+		__set_bit(ADP5585_RESET1_OUT, adp5585->pin_usage);
 	}
 
 	for (i = 0; i < adp5585->nkeys_reset2; i++) {
@@ -549,6 +574,8 @@ static int adp5585_setup(struct adp5585_dev *adp5585)
 				   adp5585->reset2_keys[i] | ADP5585_RESET_EV_PRESS);
 		if (ret)
 			return ret;
+
+		__set_bit(adp5585->reset2_out, adp5585->pin_usage);
 	}
 
 	if (adp5585->nkeys_reset1 || adp5585->nkeys_reset2) {
@@ -697,6 +724,10 @@ static int adp5585_i2c_probe(struct i2c_client *i2c)
 		return dev_err_probe(&i2c->dev, -ENODEV,
 				     "Invalid device ID 0x%02x\n", id);
 
+	adp5585->pin_usage = devm_bitmap_zalloc(&i2c->dev, adp5585->n_pins, GFP_KERNEL);
+	if (!adp5585->pin_usage)
+		return -ENOMEM;
+
 	ret = adp5585_parse_fw(adp5585);
 	if (ret)
 		return ret;
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index db483ef9693a..41c5d2e1cc7c 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -126,6 +126,10 @@
 #define ADP5585_GPI_EVENT_END		47
 #define ADP5585_ROW5_KEY_EVENT_START	1
 #define ADP5585_ROW5_KEY_EVENT_END	30
+#define ADP5585_PWM_OUT			3
+#define ADP5585_RESET1_OUT		4
+#define ADP5585_RESET2_OUT		9
+#define ADP5585_ROW5			5
 
 /* ADP5589 */
 #define		ADP5589_MAN_ID_VALUE		0x10
@@ -154,6 +158,7 @@
 #define ADP5589_PWM_ONT_LOW		0x40
 #define ADP5589_PWM_CFG			0x42
 #define ADP5589_POLL_PTIME_CFG		0x48
+#define ADP5589_PIN_CONFIG_A		0x49
 #define ADP5589_PIN_CONFIG_D		0x4C
 #define ADP5589_GENERAL_CFG		0x4d
 #define ADP5589_INT_EN			0x4e
@@ -165,6 +170,7 @@
 #define ADP5589_GPI_EVENT_START		97
 #define ADP5589_GPI_EVENT_END		115
 #define ADP5589_UNLOCK_WILDCARD		127
+#define ADP5589_RESET2_OUT		12
 
 struct regmap;
 
@@ -188,6 +194,7 @@ struct adp5585_regs {
 	unsigned int reset_cfg;
 	unsigned int reset1_event_a;
 	unsigned int reset2_event_a;
+	unsigned int pin_cfg_a;
 };
 
 struct adp5585_dev {
@@ -195,6 +202,9 @@ struct adp5585_dev {
 	struct regmap *regmap;
 	const struct adp5585_regs *regs;
 	struct blocking_notifier_head event_notifier;
+	unsigned long *pin_usage;
+	unsigned int n_pins;
+	unsigned int reset2_out;
 	enum adp5585_variant variant;
 	unsigned int id;
 	bool has_unlock;
-- 
cgit v1.2.3


From 988b28a83b658137e58123f4dafc3a1588e1cb2b Mon Sep 17 00:00:00 2001
From: Nuno Sá <nuno.sa@analog.com>
Date: Tue, 1 Jul 2025 15:32:10 +0100
Subject: gpio: adp5585: support gpi events
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add support for adding GPIs to the event FIFO. This is done by adding
irq_chip support. Like this, one can use the input gpio_keys driver as a
"frontend" device and input handler.

As part of this change, we now implement .request() and .free() as we can't
blindly consume all available pins as GPIOs (example: some pins can be
used for forming a keymap matrix).

Also note that the number of pins can now be obtained from the parent,
top level device. Hence the 'max_gpio' variable can be removed.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Acked-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Signed-off-by: Nuno Sá <nuno.sa@analog.com>
Link: https://lore.kernel.org/r/20250701-dev-adp5589-fw-v7-15-b1fcfe9e9826@analog.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/gpio/Kconfig        |   1 +
 drivers/gpio/gpio-adp5585.c | 221 +++++++++++++++++++++++++++++++++++++++++++-
 include/linux/mfd/adp5585.h |   2 +
 3 files changed, 220 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 44f922e10db2..b552401e3f73 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -1263,6 +1263,7 @@ config GPIO_ADP5520
 config GPIO_ADP5585
 	tristate "GPIO Support for ADP5585"
 	depends on MFD_ADP5585
+	select GPIOLIB_IRQCHIP
 	help
 	  This option enables support for the GPIO function found in the Analog
 	  Devices ADP5585.
diff --git a/drivers/gpio/gpio-adp5585.c b/drivers/gpio/gpio-adp5585.c
index cdf107742579..b2c8836c5f84 100644
--- a/drivers/gpio/gpio-adp5585.c
+++ b/drivers/gpio/gpio-adp5585.c
@@ -7,10 +7,15 @@
  * Copyright 2025 Analog Devices, Inc.
  */
 
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <linux/container_of.h>
 #include <linux/device.h>
 #include <linux/gpio/driver.h>
 #include <linux/mfd/adp5585.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
 #include <linux/platform_device.h>
 #include <linux/regmap.h>
 #include <linux/types.h>
@@ -36,20 +41,29 @@
 struct adp5585_gpio_chip {
 	int (*bank)(unsigned int off);
 	int (*bit)(unsigned int off);
-	unsigned int max_gpio;
 	unsigned int debounce_dis_a;
 	unsigned int rpull_cfg_a;
 	unsigned int gpo_data_a;
 	unsigned int gpo_out_a;
 	unsigned int gpio_dir_a;
 	unsigned int gpi_stat_a;
+	unsigned int gpi_int_lvl_a;
+	unsigned int gpi_ev_a;
+	unsigned int gpi_ev_min;
+	unsigned int gpi_ev_max;
 	bool has_bias_hole;
 };
 
 struct adp5585_gpio_dev {
 	struct gpio_chip gpio_chip;
+	struct notifier_block nb;
 	const struct adp5585_gpio_chip *info;
 	struct regmap *regmap;
+	unsigned long irq_mask;
+	unsigned long irq_en;
+	unsigned long irq_active_high;
+	/* used for irqchip bus locking */
+	struct mutex bus_lock;
 };
 
 static int adp5585_gpio_bank(unsigned int off)
@@ -224,12 +238,175 @@ static int adp5585_gpio_set_config(struct gpio_chip *chip, unsigned int off,
 	};
 }
 
+static int adp5585_gpio_request(struct gpio_chip *chip, unsigned int off)
+{
+	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(chip);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
+	struct device *dev = chip->parent;
+	struct adp5585_dev *adp5585 = dev_get_drvdata(dev->parent);
+	const struct adp5585_regs *regs = adp5585->regs;
+	int ret;
+
+	ret = test_and_set_bit(off, adp5585->pin_usage);
+	if (ret)
+		return -EBUSY;
+
+	/* make sure it's configured for GPIO */
+	return regmap_clear_bits(adp5585_gpio->regmap,
+				 regs->pin_cfg_a + info->bank(off),
+				 info->bit(off));
+}
+
+static void adp5585_gpio_free(struct gpio_chip *chip, unsigned int off)
+{
+	struct device *dev = chip->parent;
+	struct adp5585_dev *adp5585 = dev_get_drvdata(dev->parent);
+
+	clear_bit(off, adp5585->pin_usage);
+}
+
+static int adp5585_gpio_key_event(struct notifier_block *nb, unsigned long key,
+				  void *data)
+{
+	struct adp5585_gpio_dev *adp5585_gpio = container_of(nb, struct adp5585_gpio_dev, nb);
+	struct device *dev = adp5585_gpio->gpio_chip.parent;
+	unsigned long key_press = (unsigned long)data;
+	unsigned int irq, irq_type;
+	struct irq_data *irqd;
+	bool active_high;
+	unsigned int off;
+
+	/* make sure the event is for me */
+	if (key < adp5585_gpio->info->gpi_ev_min || key > adp5585_gpio->info->gpi_ev_max)
+		return NOTIFY_DONE;
+
+	off = key - adp5585_gpio->info->gpi_ev_min;
+	active_high = test_bit(off, &adp5585_gpio->irq_active_high);
+
+	irq = irq_find_mapping(adp5585_gpio->gpio_chip.irq.domain, off);
+	if (!irq)
+		return NOTIFY_BAD;
+
+	irqd = irq_get_irq_data(irq);
+	if (!irqd) {
+		dev_err(dev, "Could not get irq(%u) data\n", irq);
+		return NOTIFY_BAD;
+	}
+
+	dev_dbg_ratelimited(dev, "gpio-keys event(%u) press=%lu, a_high=%u\n",
+			    off, key_press, active_high);
+
+	if (!active_high)
+		key_press = !key_press;
+
+	irq_type = irqd_get_trigger_type(irqd);
+
+	if ((irq_type & IRQ_TYPE_EDGE_RISING && key_press) ||
+	    (irq_type & IRQ_TYPE_EDGE_FALLING && !key_press))
+		handle_nested_irq(irq);
+
+	return NOTIFY_STOP;
+}
+
+static void adp5585_irq_bus_lock(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(gc);
+
+	mutex_lock(&adp5585_gpio->bus_lock);
+}
+
+static void adp5585_irq_bus_sync_unlock(struct irq_data *d)
+{
+	struct gpio_chip *chip = irq_data_get_irq_chip_data(d);
+	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(chip);
+	const struct adp5585_gpio_chip *info = adp5585_gpio->info;
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+	bool active_high = test_bit(hwirq, &adp5585_gpio->irq_active_high);
+	bool enabled = test_bit(hwirq, &adp5585_gpio->irq_en);
+	bool masked = test_bit(hwirq, &adp5585_gpio->irq_mask);
+	unsigned int bank = adp5585_gpio->info->bank(hwirq);
+	unsigned int bit = adp5585_gpio->info->bit(hwirq);
+
+	if (masked && !enabled)
+		goto out_unlock;
+	if (!masked && enabled)
+		goto out_unlock;
+
+	regmap_update_bits(adp5585_gpio->regmap, info->gpi_int_lvl_a + bank, bit,
+			   active_high ? bit : 0);
+	regmap_update_bits(adp5585_gpio->regmap, info->gpi_ev_a + bank, bit,
+			   masked ? 0 : bit);
+	assign_bit(hwirq, &adp5585_gpio->irq_en, !masked);
+
+out_unlock:
+	mutex_unlock(&adp5585_gpio->bus_lock);
+}
+
+static void adp5585_irq_mask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+
+	__set_bit(hwirq, &adp5585_gpio->irq_mask);
+	gpiochip_disable_irq(gc, hwirq);
+}
+
+static void adp5585_irq_unmask(struct irq_data *d)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+
+	gpiochip_enable_irq(gc, hwirq);
+	__clear_bit(hwirq, &adp5585_gpio->irq_mask);
+}
+
+static int adp5585_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct gpio_chip *gc = irq_data_get_irq_chip_data(d);
+	struct adp5585_gpio_dev *adp5585_gpio = gpiochip_get_data(gc);
+	irq_hw_number_t hwirq = irqd_to_hwirq(d);
+
+	if (!(type & IRQ_TYPE_EDGE_BOTH))
+		return -EINVAL;
+
+	assign_bit(hwirq, &adp5585_gpio->irq_active_high,
+		   type == IRQ_TYPE_EDGE_RISING);
+
+	irq_set_handler_locked(d, handle_edge_irq);
+	return 0;
+}
+
+static const struct irq_chip adp5585_irq_chip = {
+	.name = "adp5585",
+	.irq_mask = adp5585_irq_mask,
+	.irq_unmask = adp5585_irq_unmask,
+	.irq_bus_lock = adp5585_irq_bus_lock,
+	.irq_bus_sync_unlock = adp5585_irq_bus_sync_unlock,
+	.irq_set_type = adp5585_irq_set_type,
+	.flags = IRQCHIP_SKIP_SET_WAKE | IRQCHIP_IMMUTABLE,
+	GPIOCHIP_IRQ_RESOURCE_HELPERS,
+};
+
+static void adp5585_gpio_unreg_notifier(void *data)
+{
+	struct adp5585_gpio_dev *adp5585_gpio = data;
+	struct device *dev = adp5585_gpio->gpio_chip.parent;
+	struct adp5585_dev *adp5585 = dev_get_drvdata(dev->parent);
+
+	blocking_notifier_chain_unregister(&adp5585->event_notifier,
+					   &adp5585_gpio->nb);
+}
+
 static int adp5585_gpio_probe(struct platform_device *pdev)
 {
 	struct adp5585_dev *adp5585 = dev_get_drvdata(pdev->dev.parent);
 	const struct platform_device_id *id = platform_get_device_id(pdev);
 	struct adp5585_gpio_dev *adp5585_gpio;
 	struct device *dev = &pdev->dev;
+	struct gpio_irq_chip *girq;
 	struct gpio_chip *gc;
 	int ret;
 
@@ -253,13 +430,43 @@ static int adp5585_gpio_probe(struct platform_device *pdev)
 	gc->get = adp5585_gpio_get_value;
 	gc->set_rv = adp5585_gpio_set_value;
 	gc->set_config = adp5585_gpio_set_config;
+	gc->request = adp5585_gpio_request;
+	gc->free = adp5585_gpio_free;
 	gc->can_sleep = true;
 
 	gc->base = -1;
-	gc->ngpio = adp5585_gpio->info->max_gpio;
+	gc->ngpio = adp5585->n_pins;
 	gc->label = pdev->name;
 	gc->owner = THIS_MODULE;
 
+	if (device_property_present(dev->parent, "interrupt-controller")) {
+		if (!adp5585->irq)
+			return dev_err_probe(dev, -EINVAL,
+					     "Unable to serve as interrupt controller without IRQ\n");
+
+		girq = &adp5585_gpio->gpio_chip.irq;
+		gpio_irq_chip_set_chip(girq, &adp5585_irq_chip);
+		girq->handler = handle_bad_irq;
+		girq->threaded = true;
+
+		adp5585_gpio->nb.notifier_call = adp5585_gpio_key_event;
+		ret = blocking_notifier_chain_register(&adp5585->event_notifier,
+						       &adp5585_gpio->nb);
+		if (ret)
+			return ret;
+
+		ret = devm_add_action_or_reset(dev, adp5585_gpio_unreg_notifier,
+					       adp5585_gpio);
+		if (ret)
+			return ret;
+	}
+
+	/* everything masked by default */
+	adp5585_gpio->irq_mask = ~0UL;
+
+	ret = devm_mutex_init(dev, &adp5585_gpio->bus_lock);
+	if (ret)
+		return ret;
 	ret = devm_gpiochip_add_data(dev, &adp5585_gpio->gpio_chip,
 				     adp5585_gpio);
 	if (ret)
@@ -277,8 +484,11 @@ static const struct adp5585_gpio_chip adp5585_gpio_chip_info = {
 	.gpo_out_a = ADP5585_GPO_OUT_MODE_A,
 	.gpio_dir_a = ADP5585_GPIO_DIRECTION_A,
 	.gpi_stat_a = ADP5585_GPI_STATUS_A,
-	.max_gpio = ADP5585_PIN_MAX,
 	.has_bias_hole = true,
+	.gpi_ev_min = ADP5585_GPI_EVENT_START,
+	.gpi_ev_max = ADP5585_GPI_EVENT_END,
+	.gpi_int_lvl_a = ADP5585_GPI_INT_LEVEL_A,
+	.gpi_ev_a = ADP5585_GPI_EVENT_EN_A,
 };
 
 static const struct adp5585_gpio_chip adp5589_gpio_chip_info = {
@@ -290,7 +500,10 @@ static const struct adp5585_gpio_chip adp5589_gpio_chip_info = {
 	.gpo_out_a = ADP5589_GPO_OUT_MODE_A,
 	.gpio_dir_a = ADP5589_GPIO_DIRECTION_A,
 	.gpi_stat_a = ADP5589_GPI_STATUS_A,
-	.max_gpio = ADP5589_PIN_MAX,
+	.gpi_ev_min = ADP5589_GPI_EVENT_START,
+	.gpi_ev_max = ADP5589_GPI_EVENT_END,
+	.gpi_int_lvl_a = ADP5589_GPI_INT_LEVEL_A,
+	.gpi_ev_a = ADP5589_GPI_EVENT_EN_A,
 };
 
 static const struct platform_device_id adp5585_gpio_id_table[] = {
diff --git a/include/linux/mfd/adp5585.h b/include/linux/mfd/adp5585.h
index 41c5d2e1cc7c..5237da6b4a9f 100644
--- a/include/linux/mfd/adp5585.h
+++ b/include/linux/mfd/adp5585.h
@@ -136,6 +136,8 @@
 #define ADP5589_GPI_STATUS_A		0x16
 #define ADP5589_GPI_STATUS_C		0x18
 #define ADP5589_RPULL_CONFIG_A		0x19
+#define ADP5589_GPI_INT_LEVEL_A		0x1e
+#define ADP5589_GPI_EVENT_EN_A		0x21
 #define ADP5589_DEBOUNCE_DIS_A		0x27
 #define ADP5589_GPO_DATA_OUT_A		0x2a
 #define ADP5589_GPO_OUT_MODE_A		0x2d
-- 
cgit v1.2.3


From e3d6e1b9a34c745b635f122ac471a198867cd0ec Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Tue, 1 Apr 2025 00:36:02 +0900
Subject: tracing: tprobe-events: Support multiple tprobes on the same
 tracepoint

Allow user to set multiple tracepoint-probe events on the same
tracepoint. After the last tprobe-event is removed, the tracepoint
callback is unregistered.

Link: https://lore.kernel.org/all/174343536245.843280.6548776576601537671.stgit@devnote2/

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 include/linux/module.h      |   4 +
 kernel/trace/trace_fprobe.c | 251 +++++++++++++++++++++++++++++++++++---------
 2 files changed, 205 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 5faa1fb1f4b4..2cb5be5cc7e6 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -14,6 +14,7 @@
 #include <linux/buildid.h>
 #include <linux/compiler.h>
 #include <linux/cache.h>
+#include <linux/cleanup.h>
 #include <linux/kmod.h>
 #include <linux/init.h>
 #include <linux/elf.h>
@@ -1019,4 +1020,7 @@ static inline unsigned long find_kallsyms_symbol_value(struct module *mod,
 
 #endif  /* CONFIG_MODULES && CONFIG_KALLSYMS */
 
+/* Define __free(module_put) macro for struct module *. */
+DEFINE_FREE(module_put, struct module *, if (_T) module_put(_T))
+
 #endif /* _LINUX_MODULE_H */
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 017d6ebfdf8b..4a9ce7b0e084 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -21,7 +21,6 @@
 #define FPROBE_EVENT_SYSTEM "fprobes"
 #define TRACEPOINT_EVENT_SYSTEM "tracepoints"
 #define RETHOOK_MAXACTIVE_MAX 4096
-#define TRACEPOINT_STUB ERR_PTR(-ENOENT)
 
 static int trace_fprobe_create(const char *raw_command);
 static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev);
@@ -38,6 +37,89 @@ static struct dyn_event_operations trace_fprobe_ops = {
 	.match = trace_fprobe_match,
 };
 
+struct tracepoint_user {
+	struct tracepoint	*tpoint;
+	unsigned int		refcount;
+};
+
+static bool tracepoint_user_is_registered(struct tracepoint_user *tuser)
+{
+	return tuser && tuser->tpoint;
+}
+
+static int tracepoint_user_register(struct tracepoint_user *tuser)
+{
+	struct tracepoint *tpoint = tuser->tpoint;
+
+	if (!tpoint)
+		return 0;
+
+	return tracepoint_probe_register_prio_may_exist(tpoint,
+					tpoint->probestub, NULL, 0);
+}
+
+static void tracepoint_user_unregister(struct tracepoint_user *tuser)
+{
+	if (!tuser->tpoint)
+		return;
+
+	WARN_ON_ONCE(tracepoint_probe_unregister(tuser->tpoint, tuser->tpoint->probestub, NULL));
+	tuser->tpoint = NULL;
+}
+
+static unsigned long tracepoint_user_ip(struct tracepoint_user *tuser)
+{
+	if (!tuser->tpoint)
+		return 0UL;
+
+	return (unsigned long)tuser->tpoint->probestub;
+}
+
+static bool tracepoint_user_within_module(struct tracepoint_user *tuser,
+					  struct module *mod)
+{
+	return within_module(tracepoint_user_ip(tuser), mod);
+}
+
+static struct tracepoint_user *tracepoint_user_allocate(struct tracepoint *tpoint)
+{
+	struct tracepoint_user *tuser;
+
+	tuser = kzalloc(sizeof(*tuser), GFP_KERNEL);
+	if (!tuser)
+		return NULL;
+	tuser->tpoint = tpoint;
+	tuser->refcount = 1;
+
+	return tuser;
+}
+
+/* These must be called with event_mutex */
+static void tracepoint_user_get(struct tracepoint_user *tuser)
+{
+	tuser->refcount++;
+}
+
+static void tracepoint_user_put(struct tracepoint_user *tuser)
+{
+	if (--tuser->refcount > 0)
+		return;
+
+	if (tracepoint_user_is_registered(tuser))
+		tracepoint_user_unregister(tuser);
+	kfree(tuser);
+}
+
+static const char *tracepoint_user_lookup(struct tracepoint_user *tuser, char *buf)
+{
+	struct tracepoint *tpoint = tuser->tpoint;
+
+	if (!tpoint)
+		return NULL;
+
+	return kallsyms_lookup((unsigned long)tpoint->probestub, NULL, NULL, NULL, buf);
+}
+
 /*
  * Fprobe event core functions
  */
@@ -45,7 +127,7 @@ struct trace_fprobe {
 	struct dyn_event	devent;
 	struct fprobe		fp;
 	const char		*symbol;
-	struct tracepoint	*tpoint;
+	struct tracepoint_user	*tuser;
 	struct trace_probe	tp;
 };
 
@@ -75,7 +157,7 @@ static bool trace_fprobe_is_return(struct trace_fprobe *tf)
 
 static bool trace_fprobe_is_tracepoint(struct trace_fprobe *tf)
 {
-	return tf->tpoint != NULL;
+	return tf->tuser != NULL;
 }
 
 static const char *trace_fprobe_symbol(struct trace_fprobe *tf)
@@ -125,6 +207,56 @@ static bool trace_fprobe_is_registered(struct trace_fprobe *tf)
 	return fprobe_is_registered(&tf->fp);
 }
 
+static struct tracepoint *find_tracepoint(const char *tp_name,
+	struct module **tp_mod);
+
+/*
+ * Get tracepoint_user if exist, or allocate new one. If tracepoint is on a
+ * module, get its refcounter.
+ */
+static struct tracepoint_user *
+trace_fprobe_get_tracepoint_user(const char *name, struct module **pmod)
+{
+	struct tracepoint_user *tuser __free(kfree) = NULL;
+	struct tracepoint *tpoint;
+	struct trace_fprobe *tf;
+	struct dyn_event *dpos;
+	struct module *mod __free(module_put) = NULL;
+	int ret;
+
+	/*
+	 * Find appropriate tracepoint and locking module.
+	 * Note: tpoint can be NULL if it is unloaded (or failed to get module.)
+	 */
+	tpoint = find_tracepoint(name, &mod);
+
+	/* Search existing tracepoint_user */
+	for_each_trace_fprobe(tf, dpos) {
+		if (!trace_fprobe_is_tracepoint(tf))
+			continue;
+		if (!strcmp(tf->symbol, name)) {
+			tracepoint_user_get(tf->tuser);
+			*pmod = no_free_ptr(mod);
+			return tf->tuser;
+		}
+	}
+
+	/* Not found, allocate and register new tracepoint_user. */
+	tuser = tracepoint_user_allocate(tpoint);
+	if (!tuser)
+		return NULL;
+
+	if (tpoint) {
+		/* If the tracepoint is not loaded, tpoint can be NULL. */
+		ret = tracepoint_user_register(tuser);
+		if (ret)
+			return ERR_PTR(ret);
+	}
+
+	*pmod = no_free_ptr(mod);
+	return_ptr(tuser);
+}
+
 /*
  * Note that we don't verify the fetch_insn code, since it does not come
  * from user space.
@@ -410,6 +542,8 @@ static void free_trace_fprobe(struct trace_fprobe *tf)
 {
 	if (tf) {
 		trace_probe_cleanup(&tf->tp);
+		if (tf->tuser)
+			tracepoint_user_put(tf->tuser);
 		kfree(tf->symbol);
 		kfree(tf);
 	}
@@ -424,7 +558,7 @@ DEFINE_FREE(free_trace_fprobe, struct trace_fprobe *, if (!IS_ERR_OR_NULL(_T)) f
 static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 					       const char *event,
 					       const char *symbol,
-					       struct tracepoint *tpoint,
+					       struct tracepoint_user *tuser,
 					       int nargs, bool is_return)
 {
 	struct trace_fprobe *tf __free(free_trace_fprobe) = NULL;
@@ -443,7 +577,7 @@ static struct trace_fprobe *alloc_trace_fprobe(const char *group,
 	else
 		tf->fp.entry_handler = fentry_dispatcher;
 
-	tf->tpoint = tpoint;
+	tf->tuser = tuser;
 
 	ret = trace_probe_init(&tf->tp, event, group, false, nargs);
 	if (ret < 0)
@@ -709,19 +843,11 @@ static int unregister_fprobe_event(struct trace_fprobe *tf)
 
 static int __regsiter_tracepoint_fprobe(struct trace_fprobe *tf)
 {
-	struct tracepoint *tpoint = tf->tpoint;
-	unsigned long ip = (unsigned long)tpoint->probestub;
-	int ret;
+	unsigned long ip = tracepoint_user_ip(tf->tuser);
+
+	if (!ip)
+		return -ENOENT;
 
-	/*
-	 * Here, we do 2 steps to enable fprobe on a tracepoint.
-	 * At first, put __probestub_##TP function on the tracepoint
-	 * and put a fprobe on the stub function.
-	 */
-	ret = tracepoint_probe_register_prio_may_exist(tpoint,
-				tpoint->probestub, NULL, 0);
-	if (ret < 0)
-		return ret;
 	return register_fprobe_ips(&tf->fp, &ip, 1);
 }
 
@@ -753,7 +879,7 @@ static int __register_trace_fprobe(struct trace_fprobe *tf)
 	if (trace_fprobe_is_tracepoint(tf)) {
 
 		/* This tracepoint is not loaded yet */
-		if (tf->tpoint == TRACEPOINT_STUB)
+		if (!tracepoint_user_is_registered(tf->tuser))
 			return 0;
 
 		return __regsiter_tracepoint_fprobe(tf);
@@ -770,9 +896,8 @@ static void __unregister_trace_fprobe(struct trace_fprobe *tf)
 		unregister_fprobe(&tf->fp);
 		memset(&tf->fp, 0, sizeof(tf->fp));
 		if (trace_fprobe_is_tracepoint(tf)) {
-			tracepoint_probe_unregister(tf->tpoint,
-					tf->tpoint->probestub, NULL);
-			tf->tpoint = NULL;
+			tracepoint_user_put(tf->tuser);
+			tf->tuser = NULL;
 		}
 	}
 }
@@ -988,7 +1113,7 @@ static int __tracepoint_probe_module_cb(struct notifier_block *self,
 					unsigned long val, void *data)
 {
 	struct tp_module *tp_mod = data;
-	struct tracepoint *tpoint;
+	struct tracepoint_user *tuser;
 	struct trace_fprobe *tf;
 	struct dyn_event *pos;
 
@@ -999,21 +1124,46 @@ static int __tracepoint_probe_module_cb(struct notifier_block *self,
 	for_each_trace_fprobe(tf, pos) {
 		if (!trace_fprobe_is_tracepoint(tf))
 			continue;
-		if (val == MODULE_STATE_COMING && tf->tpoint == TRACEPOINT_STUB) {
+
+		if (val == MODULE_STATE_COMING) {
+			/*
+			 * If any tracepoint used by tprobe is in the module,
+			 * register the stub.
+			 */
+			struct tracepoint *tpoint;
+
 			tpoint = find_tracepoint_in_module(tp_mod->mod, tf->symbol);
-			if (tpoint) {
-				tf->tpoint = tpoint;
-				if (!WARN_ON_ONCE(__regsiter_tracepoint_fprobe(tf)) &&
-				    trace_probe_is_enabled(&tf->tp))
-					reenable_trace_fprobe(tf);
+			/* This is not a tracepoint in this module. Skip it. */
+			if (!tpoint)
+				continue;
+
+			tuser = tf->tuser;
+			/* If the tracepoint is not registered yet, register it. */
+			if (!tracepoint_user_is_registered(tuser)) {
+				tuser->tpoint = tpoint;
+				if (WARN_ON_ONCE(tracepoint_user_register(tuser)))
+					continue;
 			}
-		} else if (val == MODULE_STATE_GOING &&
-			   tf->tpoint != TRACEPOINT_STUB &&
-			   within_module((unsigned long)tf->tpoint->probestub, tp_mod->mod)) {
-			unregister_fprobe(&tf->fp);
-			tracepoint_probe_unregister(tf->tpoint,
-				tf->tpoint->probestub, NULL);
-			tf->tpoint = TRACEPOINT_STUB;
+
+			/* Finally enable fprobe on this module. */
+			if (!WARN_ON_ONCE(__regsiter_tracepoint_fprobe(tf)) &&
+			    trace_probe_is_enabled(&tf->tp))
+				reenable_trace_fprobe(tf);
+		} else if (val == MODULE_STATE_GOING) {
+			tuser = tf->tuser;
+			/* Unregister all tracepoint_user in this module. */
+			if (tracepoint_user_is_registered(tuser) &&
+			    tracepoint_user_within_module(tuser, tp_mod->mod))
+				tracepoint_user_unregister(tuser);
+
+			/*
+			 * Here we need to handle shared tracepoint_user case.
+			 * Such tuser is unregistered, but trace_fprobe itself
+			 * is registered. (Note this only handles tprobes.)
+			 */
+			if (!tracepoint_user_is_registered(tuser) &&
+			    trace_fprobe_is_registered(tf))
+				unregister_fprobe(&tf->fp);
 		}
 	}
 	mutex_unlock(&event_mutex);
@@ -1082,7 +1232,9 @@ static int parse_symbol_and_return(int argc, const char *argv[],
 	return 0;
 }
 
-DEFINE_FREE(module_put, struct module *, if (_T) module_put(_T))
+DEFINE_FREE(tuser_put, struct tracepoint_user *,
+	if (!IS_ERR_OR_NULL(_T))
+		tracepoint_user_put(_T))
 
 static int trace_fprobe_create_internal(int argc, const char *argv[],
 					struct traceprobe_parse_context *ctx)
@@ -1112,6 +1264,8 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 	 *  FETCHARG:TYPE : use TYPE instead of unsigned long.
 	 */
 	struct trace_fprobe *tf __free(free_trace_fprobe) = NULL;
+	struct tracepoint_user *tuser __free(tuser_put) = NULL;
+	struct module *mod __free(module_put) = NULL;
 	int i, new_argc = 0, ret = 0;
 	bool is_return = false;
 	char *symbol __free(kfree) = NULL;
@@ -1123,8 +1277,6 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 	char abuf[MAX_BTF_ARGS_LEN];
 	char *dbuf __free(kfree) = NULL;
 	bool is_tracepoint = false;
-	struct module *tp_mod __free(module_put) = NULL;
-	struct tracepoint *tpoint = NULL;
 
 	if ((argv[0][0] != 'f' && argv[0][0] != 't') || argc < 2)
 		return -ECANCELED;
@@ -1177,20 +1329,18 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 
 	if (is_tracepoint) {
 		ctx->flags |= TPARG_FL_TPOINT;
-		tpoint = find_tracepoint(symbol, &tp_mod);
-		if (tpoint) {
-			ctx->funcname = kallsyms_lookup(
-				(unsigned long)tpoint->probestub,
-				NULL, NULL, NULL, sbuf);
-		} else if (IS_ENABLED(CONFIG_MODULES)) {
-				/* This *may* be loaded afterwards */
-				tpoint = TRACEPOINT_STUB;
-				ctx->funcname = symbol;
-		} else {
+		tuser = trace_fprobe_get_tracepoint_user(symbol, &mod);
+		if (!tuser)
+			return -ENOMEM;
+		if (IS_ERR(tuser)) {
 			trace_probe_log_set_index(1);
 			trace_probe_log_err(0, NO_TRACEPOINT);
-			return -EINVAL;
+			return PTR_ERR(tuser);
 		}
+		ctx->funcname = tracepoint_user_lookup(tuser, sbuf);
+		/* If tracepoint is not loaded yet, use symbol name as funcname. */
+		if (!ctx->funcname)
+			ctx->funcname = symbol;
 	} else
 		ctx->funcname = symbol;
 
@@ -1214,13 +1364,14 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 		return ret;
 
 	/* setup a probe */
-	tf = alloc_trace_fprobe(group, event, symbol, tpoint, argc, is_return);
+	tf = alloc_trace_fprobe(group, event, symbol, tuser, argc, is_return);
 	if (IS_ERR(tf)) {
 		ret = PTR_ERR(tf);
 		/* This must return -ENOMEM, else there is a bug */
 		WARN_ON_ONCE(ret != -ENOMEM);
 		return ret;
 	}
+	tuser = NULL; /* Move tuser to tf. */
 
 	/* parse arguments */
 	for (i = 0; i < argc; i++) {
-- 
cgit v1.2.3


From 2db832ec9090d3b5f726f49ad4d0322d6b68a490 Mon Sep 17 00:00:00 2001
From: "Masami Hiramatsu (Google)" <mhiramat@kernel.org>
Date: Tue, 1 Apr 2025 00:36:11 +0900
Subject: tracing: fprobe-events: Register fprobe-events only when it is
 enabled

Currently fprobe events are registered when it is defined. Thus it will
give some overhead even if it is disabled. This changes it to register the
fprobe only when it is enabled.

Link: https://lore.kernel.org/all/174343537128.843280.16131300052837035043.stgit@devnote2/

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
---
 include/linux/fprobe.h      |   5 +
 kernel/trace/fprobe.c       |   5 +
 kernel/trace/trace_fprobe.c | 237 ++++++++++++++++++++++----------------------
 3 files changed, 126 insertions(+), 121 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fprobe.h b/include/linux/fprobe.h
index 702099f08929..7964db96e41a 100644
--- a/include/linux/fprobe.h
+++ b/include/linux/fprobe.h
@@ -94,6 +94,7 @@ int register_fprobe_ips(struct fprobe *fp, unsigned long *addrs, int num);
 int register_fprobe_syms(struct fprobe *fp, const char **syms, int num);
 int unregister_fprobe(struct fprobe *fp);
 bool fprobe_is_registered(struct fprobe *fp);
+int fprobe_count_ips_from_filter(const char *filter, const char *notfilter);
 #else
 static inline int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter)
 {
@@ -115,6 +116,10 @@ static inline bool fprobe_is_registered(struct fprobe *fp)
 {
 	return false;
 }
+static inline int fprobe_count_ips_from_filter(const char *filter, const char *notfilter)
+{
+	return -EOPNOTSUPP;
+}
 #endif
 
 /**
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index ba7ff14f5339..b78fce0982c7 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -648,6 +648,11 @@ static int fprobe_init(struct fprobe *fp, unsigned long *addrs, int num)
 
 #define FPROBE_IPS_MAX	INT_MAX
 
+int fprobe_count_ips_from_filter(const char *filter, const char *notfilter)
+{
+	return get_ips_from_filter(filter, notfilter, NULL, NULL, FPROBE_IPS_MAX);
+}
+
 /**
  * register_fprobe() - Register fprobe to ftrace by pattern.
  * @fp: A fprobe data structure to be registered.
diff --git a/kernel/trace/trace_fprobe.c b/kernel/trace/trace_fprobe.c
index 4a9ce7b0e084..79ffc1b2d519 100644
--- a/kernel/trace/trace_fprobe.c
+++ b/kernel/trace/trace_fprobe.c
@@ -600,98 +600,6 @@ static struct trace_fprobe *find_trace_fprobe(const char *event,
 	return NULL;
 }
 
-static inline int __enable_trace_fprobe(struct trace_fprobe *tf)
-{
-	if (trace_fprobe_is_registered(tf))
-		enable_fprobe(&tf->fp);
-
-	return 0;
-}
-
-static void __disable_trace_fprobe(struct trace_probe *tp)
-{
-	struct trace_fprobe *tf;
-
-	list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
-		if (!trace_fprobe_is_registered(tf))
-			continue;
-		disable_fprobe(&tf->fp);
-	}
-}
-
-/*
- * Enable trace_probe
- * if the file is NULL, enable "perf" handler, or enable "trace" handler.
- */
-static int enable_trace_fprobe(struct trace_event_call *call,
-			       struct trace_event_file *file)
-{
-	struct trace_probe *tp;
-	struct trace_fprobe *tf;
-	bool enabled;
-	int ret = 0;
-
-	tp = trace_probe_primary_from_call(call);
-	if (WARN_ON_ONCE(!tp))
-		return -ENODEV;
-	enabled = trace_probe_is_enabled(tp);
-
-	/* This also changes "enabled" state */
-	if (file) {
-		ret = trace_probe_add_file(tp, file);
-		if (ret)
-			return ret;
-	} else
-		trace_probe_set_flag(tp, TP_FLAG_PROFILE);
-
-	if (!enabled) {
-		list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
-			/* TODO: check the fprobe is gone */
-			__enable_trace_fprobe(tf);
-		}
-	}
-
-	return 0;
-}
-
-/*
- * Disable trace_probe
- * if the file is NULL, disable "perf" handler, or disable "trace" handler.
- */
-static int disable_trace_fprobe(struct trace_event_call *call,
-				struct trace_event_file *file)
-{
-	struct trace_probe *tp;
-
-	tp = trace_probe_primary_from_call(call);
-	if (WARN_ON_ONCE(!tp))
-		return -ENODEV;
-
-	if (file) {
-		if (!trace_probe_get_file_link(tp, file))
-			return -ENOENT;
-		if (!trace_probe_has_single_file(tp))
-			goto out;
-		trace_probe_clear_flag(tp, TP_FLAG_TRACE);
-	} else
-		trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
-
-	if (!trace_probe_is_enabled(tp))
-		__disable_trace_fprobe(tp);
-
- out:
-	if (file)
-		/*
-		 * Synchronization is done in below function. For perf event,
-		 * file == NULL and perf_trace_event_unreg() calls
-		 * tracepoint_synchronize_unregister() to ensure synchronize
-		 * event. We don't need to care about it.
-		 */
-		trace_probe_remove_file(tp, file);
-
-	return 0;
-}
-
 /* Event entry printers */
 static enum print_line_t
 print_fentry_event(struct trace_iterator *iter, int flags,
@@ -851,6 +759,29 @@ static int __regsiter_tracepoint_fprobe(struct trace_fprobe *tf)
 	return register_fprobe_ips(&tf->fp, &ip, 1);
 }
 
+/* Returns an error if the target function is not available, or 0 */
+static int trace_fprobe_verify_target(struct trace_fprobe *tf)
+{
+	int ret;
+
+	if (trace_fprobe_is_tracepoint(tf)) {
+
+		/* This tracepoint is not loaded yet */
+		if (!tracepoint_user_is_registered(tf->tuser))
+			return 0;
+
+		/* We assume all stab function is tracable. */
+		return tracepoint_user_ip(tf->tuser) ? 0 : -ENOENT;
+	}
+
+	/*
+	 * Note: since we don't lock the module, even if this succeeded,
+	 * register_fprobe() later can fail.
+	 */
+	ret = fprobe_count_ips_from_filter(tf->symbol, NULL);
+	return (ret < 0) ? ret : 0;
+}
+
 /* Internal register function - just handle fprobe and flags */
 static int __register_trace_fprobe(struct trace_fprobe *tf)
 {
@@ -870,11 +801,7 @@ static int __register_trace_fprobe(struct trace_fprobe *tf)
 			return ret;
 	}
 
-	/* Set/clear disabled flag according to tp->flag */
-	if (trace_probe_is_enabled(&tf->tp))
-		tf->fp.flags &= ~FPROBE_FL_DISABLED;
-	else
-		tf->fp.flags |= FPROBE_FL_DISABLED;
+	tf->fp.flags &= ~FPROBE_FL_DISABLED;
 
 	if (trace_fprobe_is_tracepoint(tf)) {
 
@@ -895,10 +822,10 @@ static void __unregister_trace_fprobe(struct trace_fprobe *tf)
 	if (trace_fprobe_is_registered(tf)) {
 		unregister_fprobe(&tf->fp);
 		memset(&tf->fp, 0, sizeof(tf->fp));
-		if (trace_fprobe_is_tracepoint(tf)) {
-			tracepoint_user_put(tf->tuser);
-			tf->tuser = NULL;
-		}
+	}
+	if (trace_fprobe_is_tracepoint(tf)) {
+		tracepoint_user_put(tf->tuser);
+		tf->tuser = NULL;
 	}
 }
 
@@ -958,7 +885,7 @@ static bool trace_fprobe_has_same_fprobe(struct trace_fprobe *orig,
 	return false;
 }
 
-static int append_trace_fprobe(struct trace_fprobe *tf, struct trace_fprobe *to)
+static int append_trace_fprobe_event(struct trace_fprobe *tf, struct trace_fprobe *to)
 {
 	int ret;
 
@@ -986,7 +913,7 @@ static int append_trace_fprobe(struct trace_fprobe *tf, struct trace_fprobe *to)
 	if (ret)
 		return ret;
 
-	ret = __register_trace_fprobe(tf);
+	ret = trace_fprobe_verify_target(tf);
 	if (ret)
 		trace_probe_unlink(&tf->tp);
 	else
@@ -995,8 +922,8 @@ static int append_trace_fprobe(struct trace_fprobe *tf, struct trace_fprobe *to)
 	return ret;
 }
 
-/* Register a trace_probe and probe_event */
-static int register_trace_fprobe(struct trace_fprobe *tf)
+/* Register a trace_probe and probe_event, and check the fprobe is available. */
+static int register_trace_fprobe_event(struct trace_fprobe *tf)
 {
 	struct trace_fprobe *old_tf;
 	int ret;
@@ -1006,7 +933,7 @@ static int register_trace_fprobe(struct trace_fprobe *tf)
 	old_tf = find_trace_fprobe(trace_probe_name(&tf->tp),
 				   trace_probe_group_name(&tf->tp));
 	if (old_tf)
-		return append_trace_fprobe(tf, old_tf);
+		return append_trace_fprobe_event(tf, old_tf);
 
 	/* Register new event */
 	ret = register_fprobe_event(tf);
@@ -1019,8 +946,8 @@ static int register_trace_fprobe(struct trace_fprobe *tf)
 		return ret;
 	}
 
-	/* Register fprobe */
-	ret = __register_trace_fprobe(tf);
+	/* Verify fprobe is sane. */
+	ret = trace_fprobe_verify_target(tf);
 	if (ret < 0)
 		unregister_fprobe_event(tf);
 	else
@@ -1084,15 +1011,6 @@ static struct tracepoint *find_tracepoint(const char *tp_name,
 }
 
 #ifdef CONFIG_MODULES
-static void reenable_trace_fprobe(struct trace_fprobe *tf)
-{
-	struct trace_probe *tp = &tf->tp;
-
-	list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
-		__enable_trace_fprobe(tf);
-	}
-}
-
 /*
  * Find a tracepoint from specified module. In this case, this does not get the
  * module's refcount. The caller must ensure the module is not freed.
@@ -1146,9 +1064,8 @@ static int __tracepoint_probe_module_cb(struct notifier_block *self,
 			}
 
 			/* Finally enable fprobe on this module. */
-			if (!WARN_ON_ONCE(__regsiter_tracepoint_fprobe(tf)) &&
-			    trace_probe_is_enabled(&tf->tp))
-				reenable_trace_fprobe(tf);
+			if (trace_probe_is_enabled(&tf->tp) && !trace_fprobe_is_registered(tf))
+				WARN_ON_ONCE(__regsiter_tracepoint_fprobe(tf));
 		} else if (val == MODULE_STATE_GOING) {
 			tuser = tf->tuser;
 			/* Unregister all tracepoint_user in this module. */
@@ -1397,7 +1314,7 @@ static int trace_fprobe_create_internal(int argc, const char *argv[],
 	if (ret < 0)
 		return ret;
 
-	ret = register_trace_fprobe(tf);
+	ret = register_trace_fprobe_event(tf);
 	if (ret) {
 		trace_probe_log_set_index(1);
 		if (ret == -EILSEQ)
@@ -1466,6 +1383,84 @@ static int trace_fprobe_show(struct seq_file *m, struct dyn_event *ev)
 	return 0;
 }
 
+/*
+ * Enable trace_probe
+ * if the file is NULL, enable "perf" handler, or enable "trace" handler.
+ */
+static int enable_trace_fprobe(struct trace_event_call *call,
+			       struct trace_event_file *file)
+{
+	struct trace_probe *tp;
+	struct trace_fprobe *tf;
+	bool enabled;
+	int ret = 0;
+
+	tp = trace_probe_primary_from_call(call);
+	if (WARN_ON_ONCE(!tp))
+		return -ENODEV;
+	enabled = trace_probe_is_enabled(tp);
+
+	/* This also changes "enabled" state */
+	if (file) {
+		ret = trace_probe_add_file(tp, file);
+		if (ret)
+			return ret;
+	} else
+		trace_probe_set_flag(tp, TP_FLAG_PROFILE);
+
+	if (!enabled) {
+		list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
+			ret = __register_trace_fprobe(tf);
+			if (ret < 0)
+				return ret;
+		}
+	}
+
+	return 0;
+}
+
+/*
+ * Disable trace_probe
+ * if the file is NULL, disable "perf" handler, or disable "trace" handler.
+ */
+static int disable_trace_fprobe(struct trace_event_call *call,
+				struct trace_event_file *file)
+{
+	struct trace_fprobe *tf;
+	struct trace_probe *tp;
+
+	tp = trace_probe_primary_from_call(call);
+	if (WARN_ON_ONCE(!tp))
+		return -ENODEV;
+
+	if (file) {
+		if (!trace_probe_get_file_link(tp, file))
+			return -ENOENT;
+		if (!trace_probe_has_single_file(tp))
+			goto out;
+		trace_probe_clear_flag(tp, TP_FLAG_TRACE);
+	} else
+		trace_probe_clear_flag(tp, TP_FLAG_PROFILE);
+
+	if (!trace_probe_is_enabled(tp)) {
+		list_for_each_entry(tf, trace_probe_probe_list(tp), tp.list) {
+			unregister_fprobe(&tf->fp);
+		}
+	}
+
+ out:
+	if (file)
+		/*
+		 * Synchronization is done in below function. For perf event,
+		 * file == NULL and perf_trace_event_unreg() calls
+		 * tracepoint_synchronize_unregister() to ensure synchronize
+		 * event. We don't need to care about it.
+		 */
+		trace_probe_remove_file(tp, file);
+
+	return 0;
+}
+
 /*
  * called by perf_trace_init() or __ftrace_set_clr_event() under event_mutex.
  */
-- 
cgit v1.2.3


From 002d90627cdbf7efd16f0846a814889409e42f07 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 26 Jun 2025 20:59:26 +0300
Subject: firmware/nvram: bcm47xx: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Signed-off-by: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
---
 include/linux/bcm47xx_nvram.h | 1 -
 include/linux/bcm47xx_sprom.h | 2 +-
 2 files changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bcm47xx_nvram.h b/include/linux/bcm47xx_nvram.h
index 7615f8d7b1ed..e4b6ce953ddb 100644
--- a/include/linux/bcm47xx_nvram.h
+++ b/include/linux/bcm47xx_nvram.h
@@ -7,7 +7,6 @@
 
 #include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/kernel.h>
 #include <linux/vmalloc.h>
 
 #ifdef CONFIG_BCM47XX_NVRAM
diff --git a/include/linux/bcm47xx_sprom.h b/include/linux/bcm47xx_sprom.h
index f8254fd53e15..40a7da3ef50e 100644
--- a/include/linux/bcm47xx_sprom.h
+++ b/include/linux/bcm47xx_sprom.h
@@ -5,8 +5,8 @@
 #ifndef __BCM47XX_SPROM_H
 #define __BCM47XX_SPROM_H
 
+#include <linux/errno.h>
 #include <linux/types.h>
-#include <linux/kernel.h>
 #include <linux/vmalloc.h>
 
 struct ssb_sprom;
-- 
cgit v1.2.3


From 276e136bff7edcdecc6e206c81594ef06aa40743 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Mon, 30 Jun 2025 18:20:15 +0200
Subject: fs: prepare for extending file_get/setattr()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We intend to add support for more xflags to selective filesystems and
We cannot rely on copy_struct_from_user() to detect this extension.

In preparation of extending the API, do not allow setting xflags unknown
by this kernel version.

Also do not pass the read-only flags and read-only field fsx_nextents to
filesystem.

These changes should not affect existing chattr programs that use the
ioctl to get fsxattr before setting the new values.

Link: https://lore.kernel.org/linux-fsdevel/20250216164029.20673-4-pali@kernel.org/
Cc: Pali Rohár <pali@kernel.org>
Cc: Andrey Albershteyn <aalbersh@redhat.com>
Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Link: https://lore.kernel.org/20250630-xattrat-syscall-v6-5-c4e3bc35227b@kernel.org
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/file_attr.c           |  8 +++++++-
 include/linux/fileattr.h | 20 ++++++++++++++++++++
 2 files changed, 27 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/file_attr.c b/fs/file_attr.c
index 5c98cf8d5519..775f43fc9687 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -100,9 +100,10 @@ EXPORT_SYMBOL(vfs_fileattr_get);
 int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa)
 {
 	struct fsxattr xfa;
+	__u32 mask = FS_XFLAGS_MASK;
 
 	memset(&xfa, 0, sizeof(xfa));
-	xfa.fsx_xflags = fa->fsx_xflags;
+	xfa.fsx_xflags = fa->fsx_xflags & mask;
 	xfa.fsx_extsize = fa->fsx_extsize;
 	xfa.fsx_nextents = fa->fsx_nextents;
 	xfa.fsx_projid = fa->fsx_projid;
@@ -119,11 +120,16 @@ static int copy_fsxattr_from_user(struct fileattr *fa,
 				  struct fsxattr __user *ufa)
 {
 	struct fsxattr xfa;
+	__u32 mask = FS_XFLAGS_MASK;
 
 	if (copy_from_user(&xfa, ufa, sizeof(xfa)))
 		return -EFAULT;
 
+	if (xfa.fsx_xflags & ~mask)
+		return -EOPNOTSUPP;
+
 	fileattr_fill_xflags(fa, xfa.fsx_xflags);
+	fa->fsx_xflags &= ~FS_XFLAG_RDONLY_MASK;
 	fa->fsx_extsize = xfa.fsx_extsize;
 	fa->fsx_nextents = xfa.fsx_nextents;
 	fa->fsx_projid = xfa.fsx_projid;
diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h
index 6030d0bf7ad3..e2a2f4ae242d 100644
--- a/include/linux/fileattr.h
+++ b/include/linux/fileattr.h
@@ -14,6 +14,26 @@
 	 FS_XFLAG_NODUMP | FS_XFLAG_NOATIME | FS_XFLAG_DAX | \
 	 FS_XFLAG_PROJINHERIT)
 
+/* Read-only inode flags */
+#define FS_XFLAG_RDONLY_MASK \
+	(FS_XFLAG_PREALLOC | FS_XFLAG_HASATTR)
+
+/* Flags to indicate valid value of fsx_ fields */
+#define FS_XFLAG_VALUES_MASK \
+	(FS_XFLAG_EXTSIZE | FS_XFLAG_COWEXTSIZE)
+
+/* Flags for directories */
+#define FS_XFLAG_DIRONLY_MASK \
+	(FS_XFLAG_RTINHERIT | FS_XFLAG_NOSYMLINKS | FS_XFLAG_EXTSZINHERIT)
+
+/* Misc settable flags */
+#define FS_XFLAG_MISC_MASK \
+	(FS_XFLAG_REALTIME | FS_XFLAG_NODEFRAG | FS_XFLAG_FILESTREAM)
+
+#define FS_XFLAGS_MASK \
+	(FS_XFLAG_COMMON | FS_XFLAG_RDONLY_MASK | FS_XFLAG_VALUES_MASK | \
+	 FS_XFLAG_DIRONLY_MASK | FS_XFLAG_MISC_MASK)
+
 /*
  * Merged interface for miscellaneous file attributes.  'flags' originates from
  * ext* and 'fsx_flags' from xfs.  There's some overlap between the two, which
-- 
cgit v1.2.3


From be7efb2d20d67f334a7de2aef77ae6c69367e646 Mon Sep 17 00:00:00 2001
From: Andrey Albershteyn <aalbersh@redhat.com>
Date: Mon, 30 Jun 2025 18:20:16 +0200
Subject: fs: introduce file_getattr and file_setattr syscalls

Introduce file_getattr() and file_setattr() syscalls to manipulate inode
extended attributes. The syscalls takes pair of file descriptor and
pathname. Then it operates on inode opened accroding to openat()
semantics. The struct file_attr is passed to obtain/change extended
attributes.

This is an alternative to FS_IOC_FSSETXATTR ioctl with a difference
that file don't need to be open as we can reference it with a path
instead of fd. By having this we can manipulated inode extended
attributes not only on regular files but also on special ones. This
is not possible with FS_IOC_FSSETXATTR ioctl as with special files
we can not call ioctl() directly on the filesystem inode using fd.

This patch adds two new syscalls which allows userspace to get/set
extended inode attributes on special files by using parent directory
and a path - *at() like syscall.

CC: linux-api@vger.kernel.org
CC: linux-fsdevel@vger.kernel.org
CC: linux-xfs@vger.kernel.org
Signed-off-by: Andrey Albershteyn <aalbersh@kernel.org>
Link: https://lore.kernel.org/20250630-xattrat-syscall-v6-6-c4e3bc35227b@kernel.org
Acked-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 arch/alpha/kernel/syscalls/syscall.tbl      |   2 +
 arch/arm/tools/syscall.tbl                  |   2 +
 arch/arm64/tools/syscall_32.tbl             |   2 +
 arch/m68k/kernel/syscalls/syscall.tbl       |   2 +
 arch/microblaze/kernel/syscalls/syscall.tbl |   2 +
 arch/mips/kernel/syscalls/syscall_n32.tbl   |   2 +
 arch/mips/kernel/syscalls/syscall_n64.tbl   |   2 +
 arch/mips/kernel/syscalls/syscall_o32.tbl   |   2 +
 arch/parisc/kernel/syscalls/syscall.tbl     |   2 +
 arch/powerpc/kernel/syscalls/syscall.tbl    |   2 +
 arch/s390/kernel/syscalls/syscall.tbl       |   2 +
 arch/sh/kernel/syscalls/syscall.tbl         |   2 +
 arch/sparc/kernel/syscalls/syscall.tbl      |   2 +
 arch/x86/entry/syscalls/syscall_32.tbl      |   2 +
 arch/x86/entry/syscalls/syscall_64.tbl      |   2 +
 arch/xtensa/kernel/syscalls/syscall.tbl     |   2 +
 fs/file_attr.c                              | 152 ++++++++++++++++++++++++++++
 include/linux/syscalls.h                    |   7 ++
 include/uapi/asm-generic/unistd.h           |   8 +-
 include/uapi/linux/fs.h                     |  18 ++++
 scripts/syscall.tbl                         |   2 +
 21 files changed, 218 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/alpha/kernel/syscalls/syscall.tbl b/arch/alpha/kernel/syscalls/syscall.tbl
index 2dd6340de6b4..16dca28ebf17 100644
--- a/arch/alpha/kernel/syscalls/syscall.tbl
+++ b/arch/alpha/kernel/syscalls/syscall.tbl
@@ -507,3 +507,5 @@
 575	common	listxattrat			sys_listxattrat
 576	common	removexattrat			sys_removexattrat
 577	common	open_tree_attr			sys_open_tree_attr
+578	common	file_getattr			sys_file_getattr
+579	common	file_setattr			sys_file_setattr
diff --git a/arch/arm/tools/syscall.tbl b/arch/arm/tools/syscall.tbl
index 27c1d5ebcd91..b07e699aaa3c 100644
--- a/arch/arm/tools/syscall.tbl
+++ b/arch/arm/tools/syscall.tbl
@@ -482,3 +482,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/arch/arm64/tools/syscall_32.tbl b/arch/arm64/tools/syscall_32.tbl
index 0765b3a8d6d6..8d9088bc577d 100644
--- a/arch/arm64/tools/syscall_32.tbl
+++ b/arch/arm64/tools/syscall_32.tbl
@@ -479,3 +479,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/arch/m68k/kernel/syscalls/syscall.tbl b/arch/m68k/kernel/syscalls/syscall.tbl
index 9fe47112c586..f41d38dfbf13 100644
--- a/arch/m68k/kernel/syscalls/syscall.tbl
+++ b/arch/m68k/kernel/syscalls/syscall.tbl
@@ -467,3 +467,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/arch/microblaze/kernel/syscalls/syscall.tbl b/arch/microblaze/kernel/syscalls/syscall.tbl
index 7b6e97828e55..580af574fe73 100644
--- a/arch/microblaze/kernel/syscalls/syscall.tbl
+++ b/arch/microblaze/kernel/syscalls/syscall.tbl
@@ -473,3 +473,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/arch/mips/kernel/syscalls/syscall_n32.tbl b/arch/mips/kernel/syscalls/syscall_n32.tbl
index aa70e371bb54..d824ffe9a014 100644
--- a/arch/mips/kernel/syscalls/syscall_n32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n32.tbl
@@ -406,3 +406,5 @@
 465	n32	listxattrat			sys_listxattrat
 466	n32	removexattrat			sys_removexattrat
 467	n32	open_tree_attr			sys_open_tree_attr
+468	n32	file_getattr			sys_file_getattr
+469	n32	file_setattr			sys_file_setattr
diff --git a/arch/mips/kernel/syscalls/syscall_n64.tbl b/arch/mips/kernel/syscalls/syscall_n64.tbl
index 1e8c44c7b614..7a7049c2c307 100644
--- a/arch/mips/kernel/syscalls/syscall_n64.tbl
+++ b/arch/mips/kernel/syscalls/syscall_n64.tbl
@@ -382,3 +382,5 @@
 465	n64	listxattrat			sys_listxattrat
 466	n64	removexattrat			sys_removexattrat
 467	n64	open_tree_attr			sys_open_tree_attr
+468	n64	file_getattr			sys_file_getattr
+469	n64	file_setattr			sys_file_setattr
diff --git a/arch/mips/kernel/syscalls/syscall_o32.tbl b/arch/mips/kernel/syscalls/syscall_o32.tbl
index 114a5a1a6230..d330274f0601 100644
--- a/arch/mips/kernel/syscalls/syscall_o32.tbl
+++ b/arch/mips/kernel/syscalls/syscall_o32.tbl
@@ -455,3 +455,5 @@
 465	o32	listxattrat			sys_listxattrat
 466	o32	removexattrat			sys_removexattrat
 467	o32	open_tree_attr			sys_open_tree_attr
+468	o32	file_getattr			sys_file_getattr
+469	o32	file_setattr			sys_file_setattr
diff --git a/arch/parisc/kernel/syscalls/syscall.tbl b/arch/parisc/kernel/syscalls/syscall.tbl
index 94df3cb957e9..88a788a7b18d 100644
--- a/arch/parisc/kernel/syscalls/syscall.tbl
+++ b/arch/parisc/kernel/syscalls/syscall.tbl
@@ -466,3 +466,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/arch/powerpc/kernel/syscalls/syscall.tbl b/arch/powerpc/kernel/syscalls/syscall.tbl
index 9a084bdb8926..b453e80dfc00 100644
--- a/arch/powerpc/kernel/syscalls/syscall.tbl
+++ b/arch/powerpc/kernel/syscalls/syscall.tbl
@@ -558,3 +558,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/arch/s390/kernel/syscalls/syscall.tbl b/arch/s390/kernel/syscalls/syscall.tbl
index a4569b96ef06..8a6744d658db 100644
--- a/arch/s390/kernel/syscalls/syscall.tbl
+++ b/arch/s390/kernel/syscalls/syscall.tbl
@@ -470,3 +470,5 @@
 465  common	listxattrat		sys_listxattrat			sys_listxattrat
 466  common	removexattrat		sys_removexattrat		sys_removexattrat
 467  common	open_tree_attr		sys_open_tree_attr		sys_open_tree_attr
+468  common	file_getattr		sys_file_getattr		sys_file_getattr
+469  common	file_setattr		sys_file_setattr		sys_file_setattr
diff --git a/arch/sh/kernel/syscalls/syscall.tbl b/arch/sh/kernel/syscalls/syscall.tbl
index 52a7652fcff6..5e9c9eff5539 100644
--- a/arch/sh/kernel/syscalls/syscall.tbl
+++ b/arch/sh/kernel/syscalls/syscall.tbl
@@ -471,3 +471,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/arch/sparc/kernel/syscalls/syscall.tbl b/arch/sparc/kernel/syscalls/syscall.tbl
index 83e45eb6c095..ebb7d06d1044 100644
--- a/arch/sparc/kernel/syscalls/syscall.tbl
+++ b/arch/sparc/kernel/syscalls/syscall.tbl
@@ -513,3 +513,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index ac007ea00979..4877e16da69a 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -473,3 +473,5 @@
 465	i386	listxattrat		sys_listxattrat
 466	i386	removexattrat		sys_removexattrat
 467	i386	open_tree_attr		sys_open_tree_attr
+468	i386	file_getattr		sys_file_getattr
+469	i386	file_setattr		sys_file_setattr
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index cfb5ca41e30d..92cf0fe2291e 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -391,6 +391,8 @@
 465	common	listxattrat		sys_listxattrat
 466	common	removexattrat		sys_removexattrat
 467	common	open_tree_attr		sys_open_tree_attr
+468	common	file_getattr		sys_file_getattr
+469	common	file_setattr		sys_file_setattr
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/xtensa/kernel/syscalls/syscall.tbl b/arch/xtensa/kernel/syscalls/syscall.tbl
index f657a77314f8..374e4cb788d8 100644
--- a/arch/xtensa/kernel/syscalls/syscall.tbl
+++ b/arch/xtensa/kernel/syscalls/syscall.tbl
@@ -438,3 +438,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
diff --git a/fs/file_attr.c b/fs/file_attr.c
index 775f43fc9687..21d6a0607345 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -4,6 +4,10 @@
 #include <linux/fscrypt.h>
 #include <linux/fileattr.h>
 #include <linux/export.h>
+#include <linux/syscalls.h>
+#include <linux/namei.h>
+
+#include "internal.h"
 
 /**
  * fileattr_fill_xflags - initialize fileattr with xflags
@@ -90,6 +94,19 @@ int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 EXPORT_SYMBOL(vfs_fileattr_get);
 
+static void fileattr_to_file_attr(const struct fileattr *fa,
+				  struct file_attr *fattr)
+{
+	__u32 mask = FS_XFLAGS_MASK;
+
+	memset(fattr, 0, sizeof(struct file_attr));
+	fattr->fa_xflags = fa->fsx_xflags & mask;
+	fattr->fa_extsize = fa->fsx_extsize;
+	fattr->fa_nextents = fa->fsx_nextents;
+	fattr->fa_projid = fa->fsx_projid;
+	fattr->fa_cowextsize = fa->fsx_cowextsize;
+}
+
 /**
  * copy_fsxattr_to_user - copy fsxattr to userspace.
  * @fa:		fileattr pointer
@@ -116,6 +133,23 @@ int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa)
 }
 EXPORT_SYMBOL(copy_fsxattr_to_user);
 
+static int file_attr_to_fileattr(const struct file_attr *fattr,
+				 struct fileattr *fa)
+{
+	__u32 mask = FS_XFLAGS_MASK;
+
+	if (fattr->fa_xflags & ~mask)
+		return -EINVAL;
+
+	fileattr_fill_xflags(fa, fattr->fa_xflags);
+	fa->fsx_xflags &= ~FS_XFLAG_RDONLY_MASK;
+	fa->fsx_extsize = fattr->fa_extsize;
+	fa->fsx_projid = fattr->fa_projid;
+	fa->fsx_cowextsize = fattr->fa_cowextsize;
+
+	return 0;
+}
+
 static int copy_fsxattr_from_user(struct fileattr *fa,
 				  struct fsxattr __user *ufa)
 {
@@ -344,3 +378,121 @@ int ioctl_fssetxattr(struct file *file, void __user *argp)
 	return err;
 }
 EXPORT_SYMBOL(ioctl_fssetxattr);
+
+SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename,
+		struct file_attr __user *, ufattr, size_t, usize,
+		unsigned int, at_flags)
+{
+	struct path filepath __free(path_put) = {};
+	struct filename *name __free(putname) = NULL;
+	unsigned int lookup_flags = 0;
+	struct file_attr fattr;
+	struct fileattr fa;
+	int error;
+
+	BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0);
+	BUILD_BUG_ON(sizeof(struct file_attr) != FILE_ATTR_SIZE_LATEST);
+
+	if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	if (!(at_flags & AT_SYMLINK_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+
+	if (usize > PAGE_SIZE)
+		return -E2BIG;
+
+	if (usize < FILE_ATTR_SIZE_VER0)
+		return -EINVAL;
+
+	name = getname_maybe_null(filename, at_flags);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	if (!name && dfd >= 0) {
+		CLASS(fd, f)(dfd);
+		if (fd_empty(f))
+			return -EBADF;
+
+		filepath = fd_file(f)->f_path;
+		path_get(&filepath);
+	} else {
+		error = filename_lookup(dfd, name, lookup_flags, &filepath,
+					NULL);
+		if (error)
+			return error;
+	}
+
+	error = vfs_fileattr_get(filepath.dentry, &fa);
+	if (error)
+		return error;
+
+	fileattr_to_file_attr(&fa, &fattr);
+	error = copy_struct_to_user(ufattr, usize, &fattr,
+				    sizeof(struct file_attr), NULL);
+
+	return error;
+}
+
+SYSCALL_DEFINE5(file_setattr, int, dfd, const char __user *, filename,
+		struct file_attr __user *, ufattr, size_t, usize,
+		unsigned int, at_flags)
+{
+	struct path filepath __free(path_put) = {};
+	struct filename *name __free(putname) = NULL;
+	unsigned int lookup_flags = 0;
+	struct file_attr fattr;
+	struct fileattr fa;
+	int error;
+
+	BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0);
+	BUILD_BUG_ON(sizeof(struct file_attr) != FILE_ATTR_SIZE_LATEST);
+
+	if ((at_flags & ~(AT_SYMLINK_NOFOLLOW | AT_EMPTY_PATH)) != 0)
+		return -EINVAL;
+
+	if (!(at_flags & AT_SYMLINK_NOFOLLOW))
+		lookup_flags |= LOOKUP_FOLLOW;
+
+	if (usize > PAGE_SIZE)
+		return -E2BIG;
+
+	if (usize < FILE_ATTR_SIZE_VER0)
+		return -EINVAL;
+
+	error = copy_struct_from_user(&fattr, sizeof(struct file_attr), ufattr,
+				      usize);
+	if (error)
+		return error;
+
+	error = file_attr_to_fileattr(&fattr, &fa);
+	if (error)
+		return error;
+
+	name = getname_maybe_null(filename, at_flags);
+	if (IS_ERR(name))
+		return PTR_ERR(name);
+
+	if (!name && dfd >= 0) {
+		CLASS(fd, f)(dfd);
+		if (fd_empty(f))
+			return -EBADF;
+
+		filepath = fd_file(f)->f_path;
+		path_get(&filepath);
+	} else {
+		error = filename_lookup(dfd, name, lookup_flags, &filepath,
+					NULL);
+		if (error)
+			return error;
+	}
+
+	error = mnt_want_write(filepath.mnt);
+	if (!error) {
+		error = vfs_fileattr_set(mnt_idmap(filepath.mnt),
+					 filepath.dentry, &fa);
+		mnt_drop_write(filepath.mnt);
+	}
+
+	return error;
+}
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index e5603cc91963..77f45e5d4413 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -78,6 +78,7 @@ struct cachestat;
 struct statmount;
 struct mnt_id_req;
 struct xattr_args;
+struct file_attr;
 
 #include <linux/types.h>
 #include <linux/aio_abi.h>
@@ -371,6 +372,12 @@ asmlinkage long sys_removexattrat(int dfd, const char __user *path,
 asmlinkage long sys_lremovexattr(const char __user *path,
 				 const char __user *name);
 asmlinkage long sys_fremovexattr(int fd, const char __user *name);
+asmlinkage long sys_file_getattr(int dfd, const char __user *filename,
+				 struct file_attr __user *attr, size_t usize,
+				 unsigned int at_flags);
+asmlinkage long sys_file_setattr(int dfd, const char __user *filename,
+				 struct file_attr __user *attr, size_t usize,
+				 unsigned int at_flags);
 asmlinkage long sys_getcwd(char __user *buf, unsigned long size);
 asmlinkage long sys_eventfd2(unsigned int count, int flags);
 asmlinkage long sys_epoll_create1(int flags);
diff --git a/include/uapi/asm-generic/unistd.h b/include/uapi/asm-generic/unistd.h
index 2892a45023af..04e0077fb4c9 100644
--- a/include/uapi/asm-generic/unistd.h
+++ b/include/uapi/asm-generic/unistd.h
@@ -852,8 +852,14 @@ __SYSCALL(__NR_removexattrat, sys_removexattrat)
 #define __NR_open_tree_attr 467
 __SYSCALL(__NR_open_tree_attr, sys_open_tree_attr)
 
+/* fs/inode.c */
+#define __NR_file_getattr 468
+__SYSCALL(__NR_file_getattr, sys_file_getattr)
+#define __NR_file_setattr 469
+__SYSCALL(__NR_file_setattr, sys_file_setattr)
+
 #undef __NR_syscalls
-#define __NR_syscalls 468
+#define __NR_syscalls 470
 
 /*
  * 32 bit systems traditionally used different
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 0098b0ce8ccb..9663dbdda181 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -148,6 +148,24 @@ struct fsxattr {
 	unsigned char	fsx_pad[8];
 };
 
+/*
+ * Variable size structure for file_[sg]et_attr().
+ *
+ * Note. This is alternative to the structure 'struct fileattr'/'struct fsxattr'.
+ * As this structure is passed to/from userspace with its size, this can
+ * be versioned based on the size.
+ */
+struct file_attr {
+	__u64 fa_xflags;	/* xflags field value (get/set) */
+	__u32 fa_extsize;	/* extsize field value (get/set)*/
+	__u32 fa_nextents;	/* nextents field value (get)   */
+	__u32 fa_projid;	/* project identifier (get/set) */
+	__u32 fa_cowextsize;	/* CoW extsize field value (get/set) */
+};
+
+#define FILE_ATTR_SIZE_VER0 24
+#define FILE_ATTR_SIZE_LATEST FILE_ATTR_SIZE_VER0
+
 /*
  * Flags for the fsx_xflags field
  */
diff --git a/scripts/syscall.tbl b/scripts/syscall.tbl
index 580b4e246aec..d1ae5e92c615 100644
--- a/scripts/syscall.tbl
+++ b/scripts/syscall.tbl
@@ -408,3 +408,5 @@
 465	common	listxattrat			sys_listxattrat
 466	common	removexattrat			sys_removexattrat
 467	common	open_tree_attr			sys_open_tree_attr
+468	common	file_getattr			sys_file_getattr
+469	common	file_setattr			sys_file_setattr
-- 
cgit v1.2.3


From 0dc7e656ddd54c3267b7cc18c1ac8ec1297ed02f Mon Sep 17 00:00:00 2001
From: Gabor Juhos <j4g8y7@gmail.com>
Date: Wed, 2 Jul 2025 14:35:23 +0200
Subject: mtd: nand: qpic-common: add defines for ECC_MODE values

Add defines for the values of the ECC_MODE field of the NAND_DEV0_ECC_CFG
register and change both the 'qcom-nandc' and 'spi-qpic-snand' drivers to
use those instead of magic numbers.

No functional changes. This is in preparation for adding 8 bit ECC strength
support for the 'spi-qpic-snand' driver.

Reviewed-by: Md Sadre Alam <quic_mdalam@quicinc.com>
Signed-off-by: Gabor Juhos <j4g8y7@gmail.com>
Acked-by: Miquel Raynal <miquel.raynal@bootlin.com>
Link: https://patch.msgid.link/20250702-qpic-snand-8bit-ecc-v2-1-ae2c17a30bb7@gmail.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 drivers/mtd/nand/raw/qcom_nandc.c    | 6 +++---
 drivers/spi/spi-qpic-snand.c         | 2 +-
 include/linux/mtd/nand-qpic-common.h | 2 ++
 3 files changed, 6 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/raw/qcom_nandc.c b/drivers/mtd/nand/raw/qcom_nandc.c
index 1003cf118c01..4dd6f1a4e797 100644
--- a/drivers/mtd/nand/raw/qcom_nandc.c
+++ b/drivers/mtd/nand/raw/qcom_nandc.c
@@ -1379,7 +1379,7 @@ static int qcom_nand_attach_chip(struct nand_chip *chip)
 	struct qcom_nand_controller *nandc = get_qcom_nand_controller(chip);
 	int cwperpage, bad_block_byte, ret;
 	bool wide_bus;
-	int ecc_mode = 1;
+	int ecc_mode = ECC_MODE_8BIT;
 
 	/* controller only supports 512 bytes data steps */
 	ecc->size = NANDC_STEP_SIZE;
@@ -1400,7 +1400,7 @@ static int qcom_nand_attach_chip(struct nand_chip *chip)
 	if (ecc->strength >= 8) {
 		/* 8 bit ECC defaults to BCH ECC on all platforms */
 		host->bch_enabled = true;
-		ecc_mode = 1;
+		ecc_mode = ECC_MODE_8BIT;
 
 		if (wide_bus) {
 			host->ecc_bytes_hw = 14;
@@ -1420,7 +1420,7 @@ static int qcom_nand_attach_chip(struct nand_chip *chip)
 		if (nandc->props->ecc_modes & ECC_BCH_4BIT) {
 			/* BCH */
 			host->bch_enabled = true;
-			ecc_mode = 0;
+			ecc_mode = ECC_MODE_4BIT;
 
 			if (wide_bus) {
 				host->ecc_bytes_hw = 8;
diff --git a/drivers/spi/spi-qpic-snand.c b/drivers/spi/spi-qpic-snand.c
index ca55f9bcd17b..7219bcaf4055 100644
--- a/drivers/spi/spi-qpic-snand.c
+++ b/drivers/spi/spi-qpic-snand.c
@@ -343,7 +343,7 @@ static int qcom_spi_ecc_init_ctx_pipelined(struct nand_device *nand)
 			       FIELD_PREP(ECC_SW_RESET, 0) |
 			       FIELD_PREP(ECC_NUM_DATA_BYTES_MASK, ecc_cfg->cw_data) |
 			       FIELD_PREP(ECC_FORCE_CLK_OPEN, 1) |
-			       FIELD_PREP(ECC_MODE_MASK, 0) |
+			       FIELD_PREP(ECC_MODE_MASK, ECC_MODE_4BIT) |
 			       FIELD_PREP(ECC_PARITY_SIZE_BYTES_BCH_MASK, ecc_cfg->ecc_bytes_hw);
 
 	ecc_cfg->ecc_buf_cfg = FIELD_PREP(NUM_STEPS_MASK, 0x203);
diff --git a/include/linux/mtd/nand-qpic-common.h b/include/linux/mtd/nand-qpic-common.h
index e8462deda6db..0d944db363cd 100644
--- a/include/linux/mtd/nand-qpic-common.h
+++ b/include/linux/mtd/nand-qpic-common.h
@@ -101,6 +101,8 @@
 #define	ECC_SW_RESET			BIT(1)
 #define	ECC_MODE			4
 #define	ECC_MODE_MASK			GENMASK(5, 4)
+#define	ECC_MODE_4BIT			0
+#define	ECC_MODE_8BIT			1
 #define	ECC_PARITY_SIZE_BYTES_BCH	8
 #define	ECC_PARITY_SIZE_BYTES_BCH_MASK	GENMASK(12, 8)
 #define	ECC_NUM_DATA_BYTES		16
-- 
cgit v1.2.3


From cb335325b1431152f696c53e32465ba192cd119a Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Mon, 30 Jun 2025 12:26:39 +0300
Subject: leds: Unexport of_led_get()

There are no users outside the module.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250630092639.1574860-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/leds/led-class.c | 3 +--
 include/linux/leds.h     | 1 -
 2 files changed, 1 insertion(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
index c20ac8ccf52b..669c21ef8611 100644
--- a/drivers/leds/led-class.c
+++ b/drivers/leds/led-class.c
@@ -256,7 +256,7 @@ static const struct class leds_class = {
  * Returns the LED device parsed from the phandle specified in the "leds"
  * property of a device tree node or a negative error-code on failure.
  */
-struct led_classdev *of_led_get(struct device_node *np, int index)
+static struct led_classdev *of_led_get(struct device_node *np, int index)
 {
 	struct device *led_dev;
 	struct device_node *led_node;
@@ -270,7 +270,6 @@ struct led_classdev *of_led_get(struct device_node *np, int index)
 
 	return led_module_get(led_dev);
 }
-EXPORT_SYMBOL_GPL(of_led_get);
 
 /**
  * led_put() - release a LED device
diff --git a/include/linux/leds.h b/include/linux/leds.h
index b3f0aa081064..b16b803cc1ac 100644
--- a/include/linux/leds.h
+++ b/include/linux/leds.h
@@ -294,7 +294,6 @@ void led_remove_lookup(struct led_lookup_data *led_lookup);
 struct led_classdev *__must_check led_get(struct device *dev, char *con_id);
 struct led_classdev *__must_check devm_led_get(struct device *dev, char *con_id);
 
-extern struct led_classdev *of_led_get(struct device_node *np, int index);
 extern void led_put(struct led_classdev *led_cdev);
 struct led_classdev *__must_check devm_of_led_get(struct device *dev,
 						  int index);
-- 
cgit v1.2.3


From 4d313f2bd22213caace3fe4fb02977b527f9c6c3 Mon Sep 17 00:00:00 2001
From: Jason Wang <jasowang@redhat.com>
Date: Tue, 1 Jul 2025 09:03:51 +0800
Subject: tun: remove unnecessary tun_xdp_hdr structure

With f95f0f95cfb7("net, xdp: Introduce xdp_init_buff utility routine"),
buffer length could be stored as frame size so there's no need to have
a dedicated tun_xdp_hdr structure. We can simply store virtio net
header instead.

Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20250701010352.74515-1-jasowang@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tap.c      | 5 ++---
 drivers/net/tun.c      | 5 ++---
 drivers/vhost/net.c    | 8 ++------
 include/linux/if_tun.h | 5 -----
 4 files changed, 6 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index bdf0788d8e66..d82eb7276a8b 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1044,9 +1044,8 @@ static const struct file_operations tap_fops = {
 
 static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
 {
-	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
-	struct virtio_net_hdr *gso = &hdr->gso;
-	int buflen = hdr->buflen;
+	struct virtio_net_hdr *gso = xdp->data_hard_start;
+	int buflen = xdp->frame_sz;
 	int vnet_hdr_len = 0;
 	struct tap_dev *tap;
 	struct sk_buff *skb;
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index f8c5e2fd04df..447c37959504 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -2356,13 +2356,12 @@ static int tun_xdp_one(struct tun_struct *tun,
 		       struct tun_page *tpage)
 {
 	unsigned int datasize = xdp->data_end - xdp->data;
-	struct tun_xdp_hdr *hdr = xdp->data_hard_start;
-	struct virtio_net_hdr *gso = &hdr->gso;
+	struct virtio_net_hdr *gso = xdp->data_hard_start;
 	struct bpf_prog *xdp_prog;
 	struct sk_buff *skb = NULL;
 	struct sk_buff_head *queue;
 	u32 rxhash = 0, act;
-	int buflen = hdr->buflen;
+	int buflen = xdp->frame_sz;
 	int metasize = 0;
 	int ret = 0;
 	bool skb_xdp = false;
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
index 7cbfc7d718b3..777eb6193985 100644
--- a/drivers/vhost/net.c
+++ b/drivers/vhost/net.c
@@ -668,7 +668,6 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 	struct socket *sock = vhost_vq_get_backend(vq);
 	struct virtio_net_hdr *gso;
 	struct xdp_buff *xdp = &nvq->xdp[nvq->batched_xdp];
-	struct tun_xdp_hdr *hdr;
 	size_t len = iov_iter_count(from);
 	int headroom = vhost_sock_xdp(sock) ? XDP_PACKET_HEADROOM : 0;
 	int buflen = SKB_DATA_ALIGN(sizeof(struct skb_shared_info));
@@ -691,15 +690,13 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 	if (unlikely(!buf))
 		return -ENOMEM;
 
-	copied = copy_from_iter(buf + offsetof(struct tun_xdp_hdr, gso),
-				sock_hlen, from);
+	copied = copy_from_iter(buf, sock_hlen, from);
 	if (copied != sock_hlen) {
 		ret = -EFAULT;
 		goto err;
 	}
 
-	hdr = buf;
-	gso = &hdr->gso;
+	gso = buf;
 
 	if (!sock_hlen)
 		memset(buf, 0, pad);
@@ -727,7 +724,6 @@ static int vhost_net_build_xdp(struct vhost_net_virtqueue *nvq,
 
 	xdp_init_buff(xdp, buflen, NULL);
 	xdp_prepare_buff(xdp, buf, pad, len, true);
-	hdr->buflen = buflen;
 
 	++nvq->batched_xdp;
 
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 043d442994b0..80166eb62f41 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -19,11 +19,6 @@ struct tun_msg_ctl {
 	void *ptr;
 };
 
-struct tun_xdp_hdr {
-	int buflen;
-	struct virtio_net_hdr gso;
-};
-
 #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
 struct socket *tun_get_socket(struct file *);
 struct ptr_ring *tun_get_tx_ring(struct file *file);
-- 
cgit v1.2.3


From 9fd45235fdd2c2615a03c86ebe5a88b050dc5680 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Thu, 9 May 2024 16:32:51 -0400
Subject: add locked_recursive_removal()

simple_recursive_removal() assumes that parent is not locked and
locks it when it finally gets to removing the victim itself.
Usually that's what we want, but there are places where the
parent is *already* locked and we need it to stay that way.
In those cases simple_recursive_removal() would, of course,
deadlock, so we have to play racy games with unlocking/relocking
the parent around the call or open-code the entire thing.

A better solution is to provide a variant that expects to
be called with the parent already locked by the caller.
Parent should be locked with I_MUTEX_PARENT, to avoid false
positives from lockdep.

Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/libfs.c         | 25 +++++++++++++++++++++----
 include/linux/fs.h |  2 ++
 2 files changed, 23 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/libfs.c b/fs/libfs.c
index 20b05a6db770..429caacc5229 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -605,8 +605,9 @@ struct dentry *find_next_child(struct dentry *parent, struct dentry *prev)
 }
 EXPORT_SYMBOL(find_next_child);
 
-void simple_recursive_removal(struct dentry *dentry,
-                              void (*callback)(struct dentry *))
+static void __simple_recursive_removal(struct dentry *dentry,
+                              void (*callback)(struct dentry *),
+			      bool locked)
 {
 	struct dentry *this = dget(dentry);
 	while (true) {
@@ -625,7 +626,8 @@ void simple_recursive_removal(struct dentry *dentry,
 			victim = this;
 			this = this->d_parent;
 			inode = this->d_inode;
-			inode_lock_nested(inode, I_MUTEX_CHILD);
+			if (!locked || victim != dentry)
+				inode_lock_nested(inode, I_MUTEX_CHILD);
 			if (simple_positive(victim)) {
 				d_invalidate(victim);	// avoid lost mounts
 				if (callback)
@@ -638,7 +640,8 @@ void simple_recursive_removal(struct dentry *dentry,
 						      inode_set_ctime_current(inode));
 				if (d_is_dir(dentry))
 					drop_nlink(inode);
-				inode_unlock(inode);
+				if (!locked)
+					inode_unlock(inode);
 				dput(dentry);
 				return;
 			}
@@ -647,8 +650,22 @@ void simple_recursive_removal(struct dentry *dentry,
 		this = child;
 	}
 }
+
+void simple_recursive_removal(struct dentry *dentry,
+                              void (*callback)(struct dentry *))
+{
+	return __simple_recursive_removal(dentry, callback, false);
+}
 EXPORT_SYMBOL(simple_recursive_removal);
 
+/* caller holds parent directory with I_MUTEX_PARENT */
+void locked_recursive_removal(struct dentry *dentry,
+                              void (*callback)(struct dentry *))
+{
+	return __simple_recursive_removal(dentry, callback, true);
+}
+EXPORT_SYMBOL(locked_recursive_removal);
+
 static const struct super_operations simple_super_operations = {
 	.statfs		= simple_statfs,
 };
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..4f0c6bf8d652 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3595,6 +3595,8 @@ extern int simple_rename(struct mnt_idmap *, struct inode *,
 			 unsigned int);
 extern void simple_recursive_removal(struct dentry *,
                               void (*callback)(struct dentry *));
+extern void locked_recursive_removal(struct dentry *,
+                              void (*callback)(struct dentry *));
 extern int noop_fsync(struct file *, loff_t, loff_t, int);
 extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 extern int simple_empty(struct dentry *);
-- 
cgit v1.2.3


From 59200f45267481582f4e42334a510f01d0b89449 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sat, 22 Mar 2025 21:06:11 -0400
Subject: new helper: simple_start_creating()

Set the things up for kernel-initiated creation of object in
a tree-in-dcache filesystem.  With respect to locking it's
an equivalent of filename_create() - we either get a negative
dentry with locked parent, or ERR_PTR() and no locks taken.

tracefs and debugfs had that open-coded as part of their
object creation machinery; switched to calling new helper.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/debugfs/inode.c | 21 +++------------------
 fs/libfs.c         | 25 +++++++++++++++++++++++++
 fs/tracefs/inode.c | 15 ++-------------
 include/linux/fs.h |  1 +
 4 files changed, 31 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 30c4944e1862..52befd94acee 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -384,27 +384,12 @@ static struct dentry *start_creating(const char *name, struct dentry *parent)
 	if (!parent)
 		parent = debugfs_mount->mnt_root;
 
-	inode_lock(d_inode(parent));
-	if (unlikely(IS_DEADDIR(d_inode(parent))))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_noperm(&QSTR(name), parent);
-	if (!IS_ERR(dentry) && d_really_is_positive(dentry)) {
-		if (d_is_dir(dentry))
-			pr_err("Directory '%s' with parent '%s' already present!\n",
-			       name, parent->d_name.name);
-		else
-			pr_err("File '%s' in directory '%s' already present!\n",
-			       name, parent->d_name.name);
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-	}
-
+	dentry = simple_start_creating(parent, name);
 	if (IS_ERR(dentry)) {
-		inode_unlock(d_inode(parent));
+		if (dentry == ERR_PTR(-EEXIST))
+			pr_err("'%s' already exists in '%pd'\n", name, parent);
 		simple_release_fs(&debugfs_mount, &debugfs_mount_count);
 	}
-
 	return dentry;
 }
 
diff --git a/fs/libfs.c b/fs/libfs.c
index 20b05a6db770..dbbfa3703937 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -2260,3 +2260,28 @@ void stashed_dentry_prune(struct dentry *dentry)
 	 */
 	cmpxchg(stashed, dentry, NULL);
 }
+
+/* parent must be held exclusive */
+struct dentry *simple_start_creating(struct dentry *parent, const char *name)
+{
+	struct dentry *dentry;
+	struct inode *dir = d_inode(parent);
+
+	inode_lock(dir);
+	if (unlikely(IS_DEADDIR(dir))) {
+		inode_unlock(dir);
+		return ERR_PTR(-ENOENT);
+	}
+	dentry = lookup_noperm(&QSTR(name), parent);
+	if (IS_ERR(dentry)) {
+		inode_unlock(dir);
+		return dentry;
+	}
+	if (dentry->d_inode) {
+		dput(dentry);
+		inode_unlock(dir);
+		return ERR_PTR(-EEXIST);
+	}
+	return dentry;
+}
+EXPORT_SYMBOL(simple_start_creating);
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index a3fd3cc591bd..4e5d091e9263 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -551,20 +551,9 @@ struct dentry *tracefs_start_creating(const char *name, struct dentry *parent)
 	if (!parent)
 		parent = tracefs_mount->mnt_root;
 
-	inode_lock(d_inode(parent));
-	if (unlikely(IS_DEADDIR(d_inode(parent))))
-		dentry = ERR_PTR(-ENOENT);
-	else
-		dentry = lookup_noperm(&QSTR(name), parent);
-	if (!IS_ERR(dentry) && d_inode(dentry)) {
-		dput(dentry);
-		dentry = ERR_PTR(-EEXIST);
-	}
-
-	if (IS_ERR(dentry)) {
-		inode_unlock(d_inode(parent));
+	dentry = simple_start_creating(parent, name);
+	if (IS_ERR(dentry))
 		simple_release_fs(&tracefs_mount, &tracefs_mount_count);
-	}
 
 	return dentry;
 }
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..9f75f8836bbd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3619,6 +3619,7 @@ extern int simple_fill_super(struct super_block *, unsigned long,
 			     const struct tree_descr *);
 extern int simple_pin_fs(struct file_system_type *, struct vfsmount **mount, int *count);
 extern void simple_release_fs(struct vfsmount **mount, int *count);
+struct dentry *simple_start_creating(struct dentry *, const char *);
 
 extern ssize_t simple_read_from_buffer(void __user *to, size_t count,
 			loff_t *ppos, const void *from, size_t available);
-- 
cgit v1.2.3


From bccea4ed060f1f6476ac7a0649ffa73f77d6e94c Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 20 Feb 2024 00:24:19 -0500
Subject: rpc_unlink(): saner calling conventions

1) pass it pipe instead of pipe->dentry
2) zero pipe->dentry afterwards
3) it always returns 0; why bother?

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/nfs/blocklayout/rpc_pipefs.c    | 12 ++----------
 fs/nfs/nfs4idmap.c                 |  6 +-----
 fs/nfsd/nfs4recover.c              | 12 ++----------
 include/linux/sunrpc/rpc_pipe_fs.h |  2 +-
 net/sunrpc/auth_gss/auth_gss.c     |  6 +-----
 net/sunrpc/rpc_pipe.c              | 12 +++++++-----
 6 files changed, 14 insertions(+), 36 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index d8d50a88de04..25d429e44eb4 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -154,13 +154,6 @@ static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
 	return dentry;
 }
 
-static void nfs4blocklayout_unregister_sb(struct super_block *sb,
-					  struct rpc_pipe *pipe)
-{
-	if (pipe->dentry)
-		rpc_unlink(pipe->dentry);
-}
-
 static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
 			   void *ptr)
 {
@@ -188,8 +181,7 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
 		nn->bl_device_pipe->dentry = dentry;
 		break;
 	case RPC_PIPEFS_UMOUNT:
-		if (nn->bl_device_pipe->dentry)
-			nfs4blocklayout_unregister_sb(sb, nn->bl_device_pipe);
+		rpc_unlink(nn->bl_device_pipe);
 		break;
 	default:
 		ret = -ENOTSUPP;
@@ -224,7 +216,7 @@ static void nfs4blocklayout_unregister_net(struct net *net,
 
 	pipefs_sb = rpc_get_sb_net(net);
 	if (pipefs_sb) {
-		nfs4blocklayout_unregister_sb(pipefs_sb, pipe);
+		rpc_unlink(pipe);
 		rpc_put_sb_net(net);
 	}
 }
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index 25a7c771cfd8..adc03232b851 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -424,12 +424,8 @@ static void nfs_idmap_pipe_destroy(struct dentry *dir,
 		struct rpc_pipe_dir_object *pdo)
 {
 	struct idmap *idmap = pdo->pdo_data;
-	struct rpc_pipe *pipe = idmap->idmap_pipe;
 
-	if (pipe->dentry) {
-		rpc_unlink(pipe->dentry);
-		pipe->dentry = NULL;
-	}
+	rpc_unlink(idmap->idmap_pipe);
 }
 
 static int nfs_idmap_pipe_create(struct dentry *dir,
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index 82785db730d9..bbd29b3b573f 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -963,13 +963,6 @@ nfsd4_cld_register_sb(struct super_block *sb, struct rpc_pipe *pipe)
 	return dentry;
 }
 
-static void
-nfsd4_cld_unregister_sb(struct rpc_pipe *pipe)
-{
-	if (pipe->dentry)
-		rpc_unlink(pipe->dentry);
-}
-
 static struct dentry *
 nfsd4_cld_register_net(struct net *net, struct rpc_pipe *pipe)
 {
@@ -991,7 +984,7 @@ nfsd4_cld_unregister_net(struct net *net, struct rpc_pipe *pipe)
 
 	sb = rpc_get_sb_net(net);
 	if (sb) {
-		nfsd4_cld_unregister_sb(pipe);
+		rpc_unlink(pipe);
 		rpc_put_sb_net(net);
 	}
 }
@@ -2142,8 +2135,7 @@ rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr)
 		cn->cn_pipe->dentry = dentry;
 		break;
 	case RPC_PIPEFS_UMOUNT:
-		if (cn->cn_pipe->dentry)
-			nfsd4_cld_unregister_sb(cn->cn_pipe);
+		rpc_unlink(cn->cn_pipe);
 		break;
 	default:
 		ret = -ENOTSUPP;
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index 3b35b6f6533a..a8c0a500d55c 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -129,7 +129,7 @@ struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags);
 void rpc_destroy_pipe_data(struct rpc_pipe *pipe);
 extern struct dentry *rpc_mkpipe_dentry(struct dentry *, const char *, void *,
 					struct rpc_pipe *);
-extern int rpc_unlink(struct dentry *);
+extern void rpc_unlink(struct rpc_pipe *);
 extern int register_rpc_pipefs(void);
 extern void unregister_rpc_pipefs(void);
 
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index 0fa244f16876..f2a44d589cfb 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -887,12 +887,8 @@ static void gss_pipe_dentry_destroy(struct dentry *dir,
 		struct rpc_pipe_dir_object *pdo)
 {
 	struct gss_pipe *gss_pipe = pdo->pdo_data;
-	struct rpc_pipe *pipe = gss_pipe->pipe;
 
-	if (pipe->dentry != NULL) {
-		rpc_unlink(pipe->dentry);
-		pipe->dentry = NULL;
-	}
+	rpc_unlink(gss_pipe->pipe);
 }
 
 static int gss_pipe_dentry_create(struct dentry *dir,
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 46fa00ac5e0e..2046582c4f35 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -737,17 +737,19 @@ EXPORT_SYMBOL_GPL(rpc_mkpipe_dentry);
 
 /**
  * rpc_unlink - remove a pipe
- * @dentry: dentry for the pipe, as returned from rpc_mkpipe
+ * @pipe: the pipe to be removed
  *
  * After this call, lookups will no longer find the pipe, and any
  * attempts to read or write using preexisting opens of the pipe will
  * return -EPIPE.
  */
-int
-rpc_unlink(struct dentry *dentry)
+void
+rpc_unlink(struct rpc_pipe *pipe)
 {
-	simple_recursive_removal(dentry, rpc_close_pipes);
-	return 0;
+	if (pipe->dentry) {
+		simple_recursive_removal(pipe->dentry, rpc_close_pipes);
+		pipe->dentry = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(rpc_unlink);
 
-- 
cgit v1.2.3


From 19a6314a997f6adde0c100ecf9224d1ab43c9603 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Tue, 20 Feb 2024 02:41:59 -0500
Subject: rpc_mkpipe_dentry(): saner calling conventions

Instead of returning a dentry or ERR_PTR(-E...), return 0 and store
dentry into pipe->dentry on success and return -E... on failure.

Callers are happier that way...

NOTE: dummy rpc_pipe is getting ->dentry set; we never access that,
since we
	1) never call rpc_unlink() for it (dentry is taken out by
->kill_sb())
	2) never call rpc_queue_upcall() for it (writing to that
sucker fails; no downcalls are ever submitted, so no replies are
going to arrive)
IOW, having that ->dentry set (and left dangling) is harmless,
if ugly; cleaner solution will take more massage.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 fs/nfs/blocklayout/rpc_pipefs.c    | 41 +++++++++++++++-----------------------
 fs/nfs/nfs4idmap.c                 |  8 +-------
 fs/nfsd/nfs4recover.c              | 37 +++++++++++++---------------------
 include/linux/sunrpc/rpc_pipe_fs.h |  2 +-
 net/sunrpc/auth_gss/auth_gss.c     |  7 +------
 net/sunrpc/rpc_pipe.c              | 29 +++++++++++----------------
 6 files changed, 45 insertions(+), 79 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/blocklayout/rpc_pipefs.c b/fs/nfs/blocklayout/rpc_pipefs.c
index 25d429e44eb4..d526f5ba7887 100644
--- a/fs/nfs/blocklayout/rpc_pipefs.c
+++ b/fs/nfs/blocklayout/rpc_pipefs.c
@@ -141,17 +141,18 @@ static const struct rpc_pipe_ops bl_upcall_ops = {
 	.destroy_msg	= bl_pipe_destroy_msg,
 };
 
-static struct dentry *nfs4blocklayout_register_sb(struct super_block *sb,
+static int nfs4blocklayout_register_sb(struct super_block *sb,
 					    struct rpc_pipe *pipe)
 {
-	struct dentry *dir, *dentry;
+	struct dentry *dir;
+	int err;
 
 	dir = rpc_d_lookup_sb(sb, NFS_PIPE_DIRNAME);
 	if (dir == NULL)
-		return ERR_PTR(-ENOENT);
-	dentry = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
+		return -ENOENT;
+	err = rpc_mkpipe_dentry(dir, "blocklayout", NULL, pipe);
 	dput(dir);
-	return dentry;
+	return err;
 }
 
 static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
@@ -160,7 +161,6 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
 	struct super_block *sb = ptr;
 	struct net *net = sb->s_fs_info;
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
-	struct dentry *dentry;
 	int ret = 0;
 
 	if (!try_module_get(THIS_MODULE))
@@ -173,12 +173,7 @@ static int rpc_pipefs_event(struct notifier_block *nb, unsigned long event,
 
 	switch (event) {
 	case RPC_PIPEFS_MOUNT:
-		dentry = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
-		if (IS_ERR(dentry)) {
-			ret = PTR_ERR(dentry);
-			break;
-		}
-		nn->bl_device_pipe->dentry = dentry;
+		ret = nfs4blocklayout_register_sb(sb, nn->bl_device_pipe);
 		break;
 	case RPC_PIPEFS_UMOUNT:
 		rpc_unlink(nn->bl_device_pipe);
@@ -195,18 +190,17 @@ static struct notifier_block nfs4blocklayout_block = {
 	.notifier_call = rpc_pipefs_event,
 };
 
-static struct dentry *nfs4blocklayout_register_net(struct net *net,
-						   struct rpc_pipe *pipe)
+static int nfs4blocklayout_register_net(struct net *net, struct rpc_pipe *pipe)
 {
 	struct super_block *pipefs_sb;
-	struct dentry *dentry;
+	int ret;
 
 	pipefs_sb = rpc_get_sb_net(net);
 	if (!pipefs_sb)
-		return NULL;
-	dentry = nfs4blocklayout_register_sb(pipefs_sb, pipe);
+		return 0;
+	ret = nfs4blocklayout_register_sb(pipefs_sb, pipe);
 	rpc_put_sb_net(net);
-	return dentry;
+	return ret;
 }
 
 static void nfs4blocklayout_unregister_net(struct net *net,
@@ -224,20 +218,17 @@ static void nfs4blocklayout_unregister_net(struct net *net,
 static int nfs4blocklayout_net_init(struct net *net)
 {
 	struct nfs_net *nn = net_generic(net, nfs_net_id);
-	struct dentry *dentry;
+	int err;
 
 	mutex_init(&nn->bl_mutex);
 	init_waitqueue_head(&nn->bl_wq);
 	nn->bl_device_pipe = rpc_mkpipe_data(&bl_upcall_ops, 0);
 	if (IS_ERR(nn->bl_device_pipe))
 		return PTR_ERR(nn->bl_device_pipe);
-	dentry = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
-	if (IS_ERR(dentry)) {
+	err = nfs4blocklayout_register_net(net, nn->bl_device_pipe);
+	if (unlikely(err))
 		rpc_destroy_pipe_data(nn->bl_device_pipe);
-		return PTR_ERR(dentry);
-	}
-	nn->bl_device_pipe->dentry = dentry;
-	return 0;
+	return err;
 }
 
 static void nfs4blocklayout_net_exit(struct net *net)
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index adc03232b851..00932500fce4 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -432,14 +432,8 @@ static int nfs_idmap_pipe_create(struct dentry *dir,
 		struct rpc_pipe_dir_object *pdo)
 {
 	struct idmap *idmap = pdo->pdo_data;
-	struct rpc_pipe *pipe = idmap->idmap_pipe;
-	struct dentry *dentry;
 
-	dentry = rpc_mkpipe_dentry(dir, "idmap", idmap, pipe);
-	if (IS_ERR(dentry))
-		return PTR_ERR(dentry);
-	pipe->dentry = dentry;
-	return 0;
+	return rpc_mkpipe_dentry(dir, "idmap", idmap, idmap->idmap_pipe);
 }
 
 static const struct rpc_pipe_dir_object_ops nfs_idmap_pipe_dir_object_ops = {
diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
index bbd29b3b573f..2231192ec33f 100644
--- a/fs/nfsd/nfs4recover.c
+++ b/fs/nfsd/nfs4recover.c
@@ -950,31 +950,32 @@ static const struct rpc_pipe_ops cld_upcall_ops = {
 	.destroy_msg	= cld_pipe_destroy_msg,
 };
 
-static struct dentry *
+static int
 nfsd4_cld_register_sb(struct super_block *sb, struct rpc_pipe *pipe)
 {
-	struct dentry *dir, *dentry;
+	struct dentry *dir;
+	int err;
 
 	dir = rpc_d_lookup_sb(sb, NFSD_PIPE_DIR);
 	if (dir == NULL)
-		return ERR_PTR(-ENOENT);
-	dentry = rpc_mkpipe_dentry(dir, NFSD_CLD_PIPE, NULL, pipe);
+		return -ENOENT;
+	err = rpc_mkpipe_dentry(dir, NFSD_CLD_PIPE, NULL, pipe);
 	dput(dir);
-	return dentry;
+	return err;
 }
 
-static struct dentry *
+static int
 nfsd4_cld_register_net(struct net *net, struct rpc_pipe *pipe)
 {
 	struct super_block *sb;
-	struct dentry *dentry;
+	int err;
 
 	sb = rpc_get_sb_net(net);
 	if (!sb)
-		return NULL;
-	dentry = nfsd4_cld_register_sb(sb, pipe);
+		return 0;
+	err = nfsd4_cld_register_sb(sb, pipe);
 	rpc_put_sb_net(net);
-	return dentry;
+	return err;
 }
 
 static void
@@ -994,7 +995,6 @@ static int
 __nfsd4_init_cld_pipe(struct net *net)
 {
 	int ret;
-	struct dentry *dentry;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct cld_net *cn;
 
@@ -1015,13 +1015,10 @@ __nfsd4_init_cld_pipe(struct net *net)
 	spin_lock_init(&cn->cn_lock);
 	INIT_LIST_HEAD(&cn->cn_list);
 
-	dentry = nfsd4_cld_register_net(net, cn->cn_pipe);
-	if (IS_ERR(dentry)) {
-		ret = PTR_ERR(dentry);
+	ret = nfsd4_cld_register_net(net, cn->cn_pipe);
+	if (unlikely(ret))
 		goto err_destroy_data;
-	}
 
-	cn->cn_pipe->dentry = dentry;
 #ifdef CONFIG_NFSD_LEGACY_CLIENT_TRACKING
 	cn->cn_has_legacy = false;
 #endif
@@ -2114,7 +2111,6 @@ rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr)
 	struct net *net = sb->s_fs_info;
 	struct nfsd_net *nn = net_generic(net, nfsd_net_id);
 	struct cld_net *cn = nn->cld_net;
-	struct dentry *dentry;
 	int ret = 0;
 
 	if (!try_module_get(THIS_MODULE))
@@ -2127,12 +2123,7 @@ rpc_pipefs_event(struct notifier_block *nb, unsigned long event, void *ptr)
 
 	switch (event) {
 	case RPC_PIPEFS_MOUNT:
-		dentry = nfsd4_cld_register_sb(sb, cn->cn_pipe);
-		if (IS_ERR(dentry)) {
-			ret = PTR_ERR(dentry);
-			break;
-		}
-		cn->cn_pipe->dentry = dentry;
+		ret = nfsd4_cld_register_sb(sb, cn->cn_pipe);
 		break;
 	case RPC_PIPEFS_UMOUNT:
 		rpc_unlink(cn->cn_pipe);
diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index a8c0a500d55c..8cc3a5df9801 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -127,7 +127,7 @@ extern void rpc_remove_cache_dir(struct dentry *);
 
 struct rpc_pipe *rpc_mkpipe_data(const struct rpc_pipe_ops *ops, int flags);
 void rpc_destroy_pipe_data(struct rpc_pipe *pipe);
-extern struct dentry *rpc_mkpipe_dentry(struct dentry *, const char *, void *,
+extern int rpc_mkpipe_dentry(struct dentry *, const char *, void *,
 					struct rpc_pipe *);
 extern void rpc_unlink(struct rpc_pipe *);
 extern int register_rpc_pipefs(void);
diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c
index f2a44d589cfb..6c23d46a1dcc 100644
--- a/net/sunrpc/auth_gss/auth_gss.c
+++ b/net/sunrpc/auth_gss/auth_gss.c
@@ -895,13 +895,8 @@ static int gss_pipe_dentry_create(struct dentry *dir,
 		struct rpc_pipe_dir_object *pdo)
 {
 	struct gss_pipe *p = pdo->pdo_data;
-	struct dentry *dentry;
 
-	dentry = rpc_mkpipe_dentry(dir, p->name, p->clnt, p->pipe);
-	if (IS_ERR(dentry))
-		return PTR_ERR(dentry);
-	p->pipe->dentry = dentry;
-	return 0;
+	return rpc_mkpipe_dentry(dir, p->name, p->clnt, p->pipe);
 }
 
 static const struct rpc_pipe_dir_object_ops gss_pipe_dir_object_ops = {
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index 2046582c4f35..dac1c35a642f 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -702,7 +702,7 @@ out_err:
  * The @private argument passed here will be available to all these methods
  * from the file pointer, via RPC_I(file_inode(file))->private.
  */
-struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name,
+int rpc_mkpipe_dentry(struct dentry *parent, const char *name,
 				 void *private, struct rpc_pipe *pipe)
 {
 	struct dentry *dentry;
@@ -717,21 +717,19 @@ struct dentry *rpc_mkpipe_dentry(struct dentry *parent, const char *name,
 
 	inode_lock_nested(dir, I_MUTEX_PARENT);
 	dentry = __rpc_lookup_create_exclusive(parent, name);
-	if (IS_ERR(dentry))
-		goto out;
+	if (IS_ERR(dentry)) {
+		inode_unlock(dir);
+		return PTR_ERR(dentry);
+	}
 	err = __rpc_mkpipe_dentry(dir, dentry, umode, &rpc_pipe_fops,
 				  private, pipe);
-	if (err)
-		goto out_err;
-out:
+	if (unlikely(err))
+		pr_warn("%s() failed to create pipe %pd/%s (errno = %d)\n",
+			__func__, parent, name, err);
+	else
+		pipe->dentry = dentry;
 	inode_unlock(dir);
-	return dentry;
-out_err:
-	dentry = ERR_PTR(err);
-	printk(KERN_WARNING "%s: %s() failed to create pipe %pd/%s (errno = %d)\n",
-			__FILE__, __func__, parent, name,
-			err);
-	goto out;
+	return err;
 }
 EXPORT_SYMBOL_GPL(rpc_mkpipe_dentry);
 
@@ -1185,7 +1183,6 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
 	int ret = 0;
 	struct dentry *gssd_dentry;
 	struct dentry *clnt_dentry = NULL;
-	struct dentry *pipe_dentry = NULL;
 
 	/* We should never get this far if "gssd" doesn't exist */
 	gssd_dentry = try_lookup_noperm(&QSTR(files[RPCAUTH_gssd].name), root);
@@ -1209,10 +1206,8 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data)
 		dput(clnt_dentry);
 		return ret;
 	}
-	pipe_dentry = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data);
+	ret = rpc_mkpipe_dentry(clnt_dentry, "gssd", NULL, pipe_data);
 	dput(clnt_dentry);
-	if (IS_ERR(pipe_dentry))
-		ret = PTR_ERR(pipe_dentry);
 	return ret;
 }
 
-- 
cgit v1.2.3


From 350db61fbeb940502a16e74153ee5954d03622e9 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Sun, 23 Mar 2025 00:51:10 -0400
Subject: rpc_create_client_dir(): return 0 or -E...

Callers couldn't care less which dentry did we get - anything
valid is treated as success.

Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
---
 include/linux/sunrpc/rpc_pipe_fs.h |  2 +-
 net/sunrpc/clnt.c                  | 36 ++++++++++++++----------------------
 net/sunrpc/rpc_pipe.c              | 12 ++++++------
 3 files changed, 21 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/rpc_pipe_fs.h b/include/linux/sunrpc/rpc_pipe_fs.h
index 8cc3a5df9801..2cb406f8ff4e 100644
--- a/include/linux/sunrpc/rpc_pipe_fs.h
+++ b/include/linux/sunrpc/rpc_pipe_fs.h
@@ -98,7 +98,7 @@ static inline bool rpc_msg_is_inflight(const struct rpc_pipe_msg *msg) {
 }
 
 struct rpc_clnt;
-extern struct dentry *rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
+extern int rpc_create_client_dir(struct dentry *, const char *, struct rpc_clnt *);
 extern int rpc_remove_client_dir(struct rpc_clnt *);
 
 extern void rpc_init_pipe_dir_head(struct rpc_pipe_dir_head *pdh);
diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
index 21426c3049d3..8ca354ecfd02 100644
--- a/net/sunrpc/clnt.c
+++ b/net/sunrpc/clnt.c
@@ -112,47 +112,46 @@ static void rpc_clnt_remove_pipedir(struct rpc_clnt *clnt)
 	}
 }
 
-static struct dentry *rpc_setup_pipedir_sb(struct super_block *sb,
+static int rpc_setup_pipedir_sb(struct super_block *sb,
 				    struct rpc_clnt *clnt)
 {
 	static uint32_t clntid;
 	const char *dir_name = clnt->cl_program->pipe_dir_name;
 	char name[15];
-	struct dentry *dir, *dentry;
+	struct dentry *dir;
+	int err;
 
 	dir = rpc_d_lookup_sb(sb, dir_name);
 	if (dir == NULL) {
 		pr_info("RPC: pipefs directory doesn't exist: %s\n", dir_name);
-		return dir;
+		return -ENOENT;
 	}
 	for (;;) {
 		snprintf(name, sizeof(name), "clnt%x", (unsigned int)clntid++);
 		name[sizeof(name) - 1] = '\0';
-		dentry = rpc_create_client_dir(dir, name, clnt);
-		if (!IS_ERR(dentry))
+		err = rpc_create_client_dir(dir, name, clnt);
+		if (!err)
 			break;
-		if (dentry == ERR_PTR(-EEXIST))
+		if (err == -EEXIST)
 			continue;
 		printk(KERN_INFO "RPC: Couldn't create pipefs entry"
-				" %s/%s, error %ld\n",
-				dir_name, name, PTR_ERR(dentry));
+				" %s/%s, error %d\n",
+				dir_name, name, err);
 		break;
 	}
 	dput(dir);
-	return dentry;
+	return err;
 }
 
 static int
 rpc_setup_pipedir(struct super_block *pipefs_sb, struct rpc_clnt *clnt)
 {
-	struct dentry *dentry;
-
 	clnt->pipefs_sb = pipefs_sb;
 
 	if (clnt->cl_program->pipe_dir_name != NULL) {
-		dentry = rpc_setup_pipedir_sb(pipefs_sb, clnt);
-		if (IS_ERR(dentry))
-			return PTR_ERR(dentry);
+		int err = rpc_setup_pipedir_sb(pipefs_sb, clnt);
+		if (err && err != -ENOENT)
+			return err;
 	}
 	return 0;
 }
@@ -180,16 +179,9 @@ static int rpc_clnt_skip_event(struct rpc_clnt *clnt, unsigned long event)
 static int __rpc_clnt_handle_event(struct rpc_clnt *clnt, unsigned long event,
 				   struct super_block *sb)
 {
-	struct dentry *dentry;
-
 	switch (event) {
 	case RPC_PIPEFS_MOUNT:
-		dentry = rpc_setup_pipedir_sb(sb, clnt);
-		if (!dentry)
-			return -ENOENT;
-		if (IS_ERR(dentry))
-			return PTR_ERR(dentry);
-		break;
+		return rpc_setup_pipedir_sb(sb, clnt);
 	case RPC_PIPEFS_UMOUNT:
 		__rpc_clnt_remove_pipedir(clnt);
 		break;
diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c
index e4b53530eb1b..a12ec709c445 100644
--- a/net/sunrpc/rpc_pipe.c
+++ b/net/sunrpc/rpc_pipe.c
@@ -863,27 +863,27 @@ rpc_destroy_pipe_dir_objects(struct rpc_pipe_dir_head *pdh)
  * information about the client, together with any "pipes" that may
  * later be created using rpc_mkpipe().
  */
-struct dentry *rpc_create_client_dir(struct dentry *dentry,
-				   const char *name,
-				   struct rpc_clnt *rpc_client)
+int rpc_create_client_dir(struct dentry *dentry,
+			   const char *name,
+			   struct rpc_clnt *rpc_client)
 {
 	struct dentry *ret;
 	int err;
 
 	ret = rpc_new_dir(dentry, name, 0555);
 	if (IS_ERR(ret))
-		return ret;
+		return PTR_ERR(ret);
 	err = rpc_new_file(ret, "info", S_IFREG | 0400,
 			      &rpc_info_operations, rpc_client);
 	if (err) {
 		pr_warn("%s failed to populate directory %pd\n",
 				__func__, ret);
 		simple_recursive_removal(ret, NULL);
-		return ERR_PTR(err);
+		return err;
 	}
 	rpc_client->cl_pipedir_objects.pdh_dentry = ret;
 	rpc_create_pipe_dir_objects(&rpc_client->cl_pipedir_objects);
-	return ret;
+	return 0;
 }
 
 /**
-- 
cgit v1.2.3


From 8a67d4b49bbdebcd255abde9e652092c3de3b657 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 2 Jul 2025 19:28:19 -0700
Subject: platform/x86/intel/vsec: Add device links to enforce dependencies
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

New Intel VSEC features will have dependencies on other features, requiring
certain supplier drivers to be probed before their consumers. To enforce
this dependency ordering, introduce device links using device_link_add(),
ensuring that suppliers are fully registered before consumers are probed.

- Add device link tracking by storing supplier devices and tracking their
  state.
- Implement intel_vsec_link_devices() to establish links between suppliers
  and consumers based on feature dependencies.
- Add get_consumer_dependencies() to retrieve supplier-consumer
  relationships.
- Modify feature registration logic:
  * Consumers now check that all required suppliers are registered before
    being initialized.
  * suppliers_ready() verifies that all required supplier devices are
    available.
- Prevent potential null consumer name issue in sysfs:
  - Use dev_set_name() when creating auxiliary devices to ensure a
    unique, non-null consumer name.
- Update intel_vsec_pci_probe() to loop up to the number of possible
  features or when all devices are registered, whichever comes first.
- Introduce VSEC_CAP_UNUSED to prevent sub-features (registered via
  exported APIs) from being mistakenly linked.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20250703022832.1302928-5-david.e.box@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/vsec.c | 223 ++++++++++++++++++++++++++++++++++++--
 include/linux/intel_vsec.h        |  28 ++++-
 2 files changed, 236 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 8bdb74d86f24..aa1f7e63039d 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -15,9 +15,12 @@
 
 #include <linux/auxiliary_bus.h>
 #include <linux/bits.h>
+#include <linux/bitops.h>
+#include <linux/bug.h>
 #include <linux/cleanup.h>
 #include <linux/delay.h>
 #include <linux/idr.h>
+#include <linux/log2.h>
 #include <linux/intel_vsec.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
@@ -32,8 +35,17 @@ static DEFINE_IDA(intel_vsec_ida);
 static DEFINE_IDA(intel_vsec_sdsi_ida);
 static DEFINE_XARRAY_ALLOC(auxdev_array);
 
+enum vsec_device_state {
+	STATE_NOT_FOUND,
+	STATE_REGISTERED,
+	STATE_SKIP,
+};
+
 struct vsec_priv {
 	struct intel_vsec_platform_info *info;
+	struct device *suppliers[VSEC_FEATURE_COUNT];
+	enum vsec_device_state state[VSEC_FEATURE_COUNT];
+	unsigned long found_caps;
 };
 
 static const char *intel_vsec_name(enum intel_vsec_id id)
@@ -95,6 +107,74 @@ static void intel_vsec_dev_release(struct device *dev)
 	kfree(intel_vsec_dev);
 }
 
+static const struct vsec_feature_dependency *
+get_consumer_dependencies(struct vsec_priv *priv, int cap_id)
+{
+	const struct vsec_feature_dependency *deps = priv->info->deps;
+	int consumer_id = priv->info->num_deps;
+
+	if (!deps)
+		return NULL;
+
+	while (consumer_id--)
+		if (deps[consumer_id].feature == BIT(cap_id))
+			return &deps[consumer_id];
+
+	return NULL;
+}
+
+/*
+ * Although pci_device_id table is available in the pdev, this prototype is
+ * necessary because the code using it can be called by an exported API that
+ * might pass a different pdev.
+ */
+static const struct pci_device_id intel_vsec_pci_ids[];
+
+static int intel_vsec_link_devices(struct pci_dev *pdev, struct device *dev,
+				   int consumer_id)
+{
+	const struct vsec_feature_dependency *deps;
+	enum vsec_device_state *state;
+	struct device **suppliers;
+	struct vsec_priv *priv;
+	int supplier_id;
+
+	if (!consumer_id)
+		return 0;
+
+	if (!pci_match_id(intel_vsec_pci_ids, pdev))
+		return 0;
+
+	priv = pci_get_drvdata(pdev);
+	state = priv->state;
+	suppliers = priv->suppliers;
+
+	priv->suppliers[consumer_id] = dev;
+
+	deps = get_consumer_dependencies(priv, consumer_id);
+	if (!deps)
+		return 0;
+
+	for_each_set_bit(supplier_id, &deps->supplier_bitmap, VSEC_FEATURE_COUNT) {
+		struct device_link *link;
+
+		if (state[supplier_id] != STATE_REGISTERED)
+			continue;
+
+		if (!suppliers[supplier_id]) {
+			dev_err(dev, "Bad supplier list\n");
+			return -EINVAL;
+		}
+
+		link = device_link_add(dev, suppliers[supplier_id],
+				       DL_FLAG_AUTOPROBE_CONSUMER);
+		if (!link)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
 int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
 		       struct intel_vsec_device *intel_vsec_dev,
 		       const char *name)
@@ -132,19 +212,37 @@ int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
 		return ret;
 	}
 
+	/*
+	 * Assign a name now to ensure that the device link doesn't contain
+	 * a null string for the consumer name. This is a problem when a supplier
+	 * supplies more than one consumer and can lead to a duplicate name error
+	 * when the link is created in sysfs.
+	 */
+	ret = dev_set_name(&auxdev->dev, "%s.%s.%d", KBUILD_MODNAME, auxdev->name,
+			   auxdev->id);
+	if (ret)
+		goto cleanup_aux;
+
+	ret = intel_vsec_link_devices(pdev, &auxdev->dev, intel_vsec_dev->cap_id);
+	if (ret)
+		goto cleanup_aux;
+
 	ret = auxiliary_device_add(auxdev);
-	if (ret < 0) {
-		auxiliary_device_uninit(auxdev);
-		return ret;
-	}
+	if (ret)
+		goto cleanup_aux;
 
 	return devm_add_action_or_reset(parent, intel_vsec_remove_aux,
 				       auxdev);
+
+cleanup_aux:
+	auxiliary_device_uninit(auxdev);
+	return ret;
 }
 EXPORT_SYMBOL_NS_GPL(intel_vsec_add_aux, "INTEL_VSEC");
 
 static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *header,
-			      struct intel_vsec_platform_info *info)
+			      struct intel_vsec_platform_info *info,
+			      unsigned long cap_id)
 {
 	struct intel_vsec_device __free(kfree) *intel_vsec_dev = NULL;
 	struct resource __free(kfree) *res = NULL;
@@ -211,6 +309,7 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 	intel_vsec_dev->quirks = info->quirks;
 	intel_vsec_dev->base_addr = info->base_addr;
 	intel_vsec_dev->priv_data = info->priv_data;
+	intel_vsec_dev->cap_id = cap_id;
 
 	if (header->id == VSEC_ID_SDSI)
 		intel_vsec_dev->ida = &intel_vsec_sdsi_ida;
@@ -225,6 +324,101 @@ static int intel_vsec_add_dev(struct pci_dev *pdev, struct intel_vsec_header *he
 				  intel_vsec_name(header->id));
 }
 
+static bool suppliers_ready(struct vsec_priv *priv,
+			    const struct vsec_feature_dependency *consumer_deps,
+			    int cap_id)
+{
+	enum vsec_device_state *state = priv->state;
+	int supplier_id;
+
+	if (WARN_ON_ONCE(consumer_deps->feature != BIT(cap_id)))
+		return false;
+
+	/*
+	 * Verify that all required suppliers have been found. Return false
+	 * immediately if any are still missing.
+	 */
+	for_each_set_bit(supplier_id, &consumer_deps->supplier_bitmap, VSEC_FEATURE_COUNT) {
+		if (state[supplier_id] == STATE_SKIP)
+			continue;
+
+		if (state[supplier_id] == STATE_NOT_FOUND)
+			return false;
+	}
+
+	/*
+	 * All suppliers have been found and the consumer is ready to be
+	 * registered.
+	 */
+	return true;
+}
+
+static int get_cap_id(u32 header_id, unsigned long *cap_id)
+{
+	switch (header_id) {
+	case VSEC_ID_TELEMETRY:
+		*cap_id = ilog2(VSEC_CAP_TELEMETRY);
+		break;
+	case VSEC_ID_WATCHER:
+		*cap_id = ilog2(VSEC_CAP_WATCHER);
+		break;
+	case VSEC_ID_CRASHLOG:
+		*cap_id = ilog2(VSEC_CAP_CRASHLOG);
+		break;
+	case VSEC_ID_SDSI:
+		*cap_id = ilog2(VSEC_CAP_SDSI);
+		break;
+	case VSEC_ID_TPMI:
+		*cap_id = ilog2(VSEC_CAP_TPMI);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int intel_vsec_register_device(struct pci_dev *pdev,
+				      struct intel_vsec_header *header,
+				      struct intel_vsec_platform_info *info)
+{
+	const struct vsec_feature_dependency *consumer_deps;
+	struct vsec_priv *priv;
+	unsigned long cap_id;
+	int ret;
+
+	ret = get_cap_id(header->id, &cap_id);
+	if (ret)
+		return ret;
+
+	/*
+	 * Only track dependencies for devices probed by the VSEC driver.
+	 * For others using the exported APIs, add the device directly.
+	 */
+	if (!pci_match_id(intel_vsec_pci_ids, pdev))
+		return intel_vsec_add_dev(pdev, header, info, cap_id);
+
+	priv = pci_get_drvdata(pdev);
+	if (priv->state[cap_id] == STATE_REGISTERED ||
+	    priv->state[cap_id] == STATE_SKIP)
+		return -EEXIST;
+
+	priv->found_caps |= BIT(cap_id);
+
+	consumer_deps = get_consumer_dependencies(priv, cap_id);
+	if (!consumer_deps || suppliers_ready(priv, consumer_deps, cap_id)) {
+		ret = intel_vsec_add_dev(pdev, header, info, cap_id);
+		if (ret)
+			priv->state[cap_id] = STATE_SKIP;
+		else
+			priv->state[cap_id] = STATE_REGISTERED;
+
+		return ret;
+	}
+
+	return -EAGAIN;
+}
+
 static bool intel_vsec_walk_header(struct pci_dev *pdev,
 				   struct intel_vsec_platform_info *info)
 {
@@ -233,7 +427,7 @@ static bool intel_vsec_walk_header(struct pci_dev *pdev,
 	int ret;
 
 	for ( ; *header; header++) {
-		ret = intel_vsec_add_dev(pdev, *header, info);
+		ret = intel_vsec_register_device(pdev, *header, info);
 		if (!ret)
 			have_devices = true;
 	}
@@ -281,7 +475,7 @@ static bool intel_vsec_walk_dvsec(struct pci_dev *pdev,
 		pci_read_config_dword(pdev, pos + PCI_DVSEC_HEADER2, &hdr);
 		header.id = PCI_DVSEC_HEADER2_ID(hdr);
 
-		ret = intel_vsec_add_dev(pdev, &header, info);
+		ret = intel_vsec_register_device(pdev, &header, info);
 		if (ret)
 			continue;
 
@@ -326,7 +520,7 @@ static bool intel_vsec_walk_vsec(struct pci_dev *pdev,
 		header.tbir = INTEL_DVSEC_TABLE_BAR(table);
 		header.offset = INTEL_DVSEC_TABLE_OFFSET(table);
 
-		ret = intel_vsec_add_dev(pdev, &header, info);
+		ret = intel_vsec_register_device(pdev, &header, info);
 		if (ret)
 			continue;
 
@@ -378,7 +572,8 @@ static int intel_vsec_pci_probe(struct pci_dev *pdev, const struct pci_device_id
 {
 	struct intel_vsec_platform_info *info;
 	struct vsec_priv *priv;
-	int ret;
+	int num_caps, ret;
+	bool found_any = false;
 
 	ret = pcim_enable_device(pdev);
 	if (ret)
@@ -396,7 +591,15 @@ static int intel_vsec_pci_probe(struct pci_dev *pdev, const struct pci_device_id
 	priv->info = info;
 	pci_set_drvdata(pdev, priv);
 
-	if (!intel_vsec_get_features(pdev, info))
+	num_caps = hweight_long(info->caps);
+	while (num_caps--) {
+		found_any |= intel_vsec_get_features(pdev, info);
+
+		if (priv->found_caps == info->caps)
+			break;
+	}
+
+	if (!found_any)
 		return -ENODEV;
 
 	return 0;
diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h
index bc95821f1bfb..71067afaca99 100644
--- a/include/linux/intel_vsec.h
+++ b/include/linux/intel_vsec.h
@@ -5,11 +5,18 @@
 #include <linux/auxiliary_bus.h>
 #include <linux/bits.h>
 
-#define VSEC_CAP_TELEMETRY	BIT(0)
-#define VSEC_CAP_WATCHER	BIT(1)
-#define VSEC_CAP_CRASHLOG	BIT(2)
-#define VSEC_CAP_SDSI		BIT(3)
-#define VSEC_CAP_TPMI		BIT(4)
+/*
+ * VSEC_CAP_UNUSED is reserved. It exists to prevent zero initialized
+ * intel_vsec devices from being automatically set to a known
+ * capability with ID 0
+ */
+#define VSEC_CAP_UNUSED		BIT(0)
+#define VSEC_CAP_TELEMETRY	BIT(1)
+#define VSEC_CAP_WATCHER	BIT(2)
+#define VSEC_CAP_CRASHLOG	BIT(3)
+#define VSEC_CAP_SDSI		BIT(4)
+#define VSEC_CAP_TPMI		BIT(5)
+#define VSEC_FEATURE_COUNT	6
 
 /* Intel DVSEC offsets */
 #define INTEL_DVSEC_ENTRIES		0xA
@@ -81,22 +88,31 @@ struct pmt_callbacks {
 	int (*read_telem)(struct pci_dev *pdev, u32 guid, u64 *data, loff_t off, u32 count);
 };
 
+struct vsec_feature_dependency {
+	unsigned long feature;
+	unsigned long supplier_bitmap;
+};
+
 /**
  * struct intel_vsec_platform_info - Platform specific data
  * @parent:    parent device in the auxbus chain
  * @headers:   list of headers to define the PMT client devices to create
+ * @deps:      array of feature dependencies
  * @priv_data: private data, usable by parent devices, currently a callback
  * @caps:      bitmask of PMT capabilities for the given headers
  * @quirks:    bitmask of VSEC device quirks
  * @base_addr: allow a base address to be specified (rather than derived)
+ * @num_deps:  Count feature dependencies
  */
 struct intel_vsec_platform_info {
 	struct device *parent;
 	struct intel_vsec_header **headers;
+	const struct vsec_feature_dependency *deps;
 	void *priv_data;
 	unsigned long caps;
 	unsigned long quirks;
 	u64 base_addr;
+	int num_deps;
 };
 
 /**
@@ -110,6 +126,7 @@ struct intel_vsec_platform_info {
  * @priv_data:     any private data needed
  * @quirks:        specified quirks
  * @base_addr:     base address of entries (if specified)
+ * @cap_id:        the enumerated id of the vsec feature
  */
 struct intel_vsec_device {
 	struct auxiliary_device auxdev;
@@ -122,6 +139,7 @@ struct intel_vsec_device {
 	size_t priv_data_size;
 	unsigned long quirks;
 	u64 base_addr;
+	unsigned long cap_id;
 };
 
 int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
-- 
cgit v1.2.3


From 10f32796e86c04f73b7f8580cc9483765ed19f49 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 2 Jul 2025 19:28:22 -0700
Subject: platform/x86/intel/vsec: Add new Discovery feature
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add the PCIe VSEC ID for new Intel Platform Monitoring Technology
Capability Discovery feature. Discovery provides detailed information for
the various Intel VSEC features. Also make the driver a supplier for
TPMI and Telemetry drivers which will use the information.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20250703022832.1302928-8-david.e.box@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/vsec.c | 26 ++++++++++++++++++++++++--
 include/linux/intel_vsec.h        |  4 +++-
 2 files changed, 27 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 30e558af6888..4d76f1ac3c8c 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -66,6 +66,9 @@ static const char *intel_vsec_name(enum intel_vsec_id id)
 	case VSEC_ID_TPMI:
 		return "tpmi";
 
+	case VSEC_ID_DISCOVERY:
+		return "discovery";
+
 	default:
 		return NULL;
 	}
@@ -84,6 +87,8 @@ static bool intel_vsec_supported(u16 id, unsigned long caps)
 		return !!(caps & VSEC_CAP_SDSI);
 	case VSEC_ID_TPMI:
 		return !!(caps & VSEC_CAP_TPMI);
+	case VSEC_ID_DISCOVERY:
+		return !!(caps & VSEC_CAP_DISCOVERY);
 	default:
 		return false;
 	}
@@ -138,6 +143,8 @@ static bool vsec_driver_present(int cap_id)
 		return IS_ENABLED(CONFIG_INTEL_SDSI);
 	case VSEC_CAP_TPMI:
 		return IS_ENABLED(CONFIG_INTEL_TPMI);
+	case VSEC_CAP_DISCOVERY:
+		return IS_ENABLED(CONFIG_INTEL_PMT_DISCOVERY);
 	default:
 		return false;
 	}
@@ -392,6 +399,9 @@ static int get_cap_id(u32 header_id, unsigned long *cap_id)
 	case VSEC_ID_TPMI:
 		*cap_id = ilog2(VSEC_CAP_TPMI);
 		break;
+	case VSEC_ID_DISCOVERY:
+		*cap_id = ilog2(VSEC_CAP_DISCOVERY);
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -681,14 +691,26 @@ static const struct intel_vsec_platform_info mtl_info = {
 	.caps = VSEC_CAP_TELEMETRY,
 };
 
+static const struct vsec_feature_dependency oobmsm_deps[] = {
+	{
+		.feature = VSEC_CAP_TELEMETRY,
+		.supplier_bitmap = VSEC_CAP_DISCOVERY,
+	},
+};
+
 /* OOBMSM info */
 static const struct intel_vsec_platform_info oobmsm_info = {
-	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_SDSI | VSEC_CAP_TPMI,
+	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_SDSI | VSEC_CAP_TPMI |
+		VSEC_CAP_DISCOVERY,
+	.deps = oobmsm_deps,
+	.num_deps = ARRAY_SIZE(oobmsm_deps),
 };
 
 /* DMR OOBMSM info */
 static const struct intel_vsec_platform_info dmr_oobmsm_info = {
-	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_TPMI,
+	.caps = VSEC_CAP_TELEMETRY | VSEC_CAP_TPMI | VSEC_CAP_DISCOVERY,
+	.deps = oobmsm_deps,
+	.num_deps = ARRAY_SIZE(oobmsm_deps),
 };
 
 /* TGL info */
diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h
index 71067afaca99..a07796d7d43b 100644
--- a/include/linux/intel_vsec.h
+++ b/include/linux/intel_vsec.h
@@ -16,7 +16,8 @@
 #define VSEC_CAP_CRASHLOG	BIT(3)
 #define VSEC_CAP_SDSI		BIT(4)
 #define VSEC_CAP_TPMI		BIT(5)
-#define VSEC_FEATURE_COUNT	6
+#define VSEC_CAP_DISCOVERY	BIT(6)
+#define VSEC_FEATURE_COUNT	7
 
 /* Intel DVSEC offsets */
 #define INTEL_DVSEC_ENTRIES		0xA
@@ -33,6 +34,7 @@ enum intel_vsec_id {
 	VSEC_ID_TELEMETRY	= 2,
 	VSEC_ID_WATCHER		= 3,
 	VSEC_ID_CRASHLOG	= 4,
+	VSEC_ID_DISCOVERY	= 12,
 	VSEC_ID_SDSI		= 65,
 	VSEC_ID_TPMI		= 66,
 };
-- 
cgit v1.2.3


From d9a0788093565c300f7c8dd034dbfa6ac4da9aa6 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 2 Jul 2025 19:28:23 -0700
Subject: platform/x86/intel/pmt: Add PMT Discovery driver
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

This patch introduces a new driver to enumerate and expose Intel Platform
Monitoring Technology (PMT) capabilities via a simple discovery mechanism.
The PMT Discovery driver parses hardware-provided discovery tables from
Intel Out of Band Management Services Modules (OOBMSM) and extracts feature
information for various providers (such as TPMI, Telemetry, Crash Log,
etc). This unified interface simplifies the process of determining which
manageability and telemetry features are supported by a given platform.

This new feature is described in the Intel Platform Monitoring Technology
3.0 specification, section 6.6 Capability.

Key changes and additions:

New file drivers/platform/x86/intel/pmt/discovery.c:
  – Implements the discovery logic to map the discovery resource, read
    the feature discovery table, and validate feature parameters.
New file drivers/platform/x86/intel/pmt/features.c:
  – Defines feature names, layouts, and associated capability masks.
  – Provides a mapping between raw hardware attributes and sysfs
    representations for easier integration with user-space tools.
New header include/linux/intel_pmt_features.h:
  – Declares constants, masks, and feature identifiers used across the
    PMT framework.
Sysfs integration:
  – Feature attributes are exposed under /sys/class/intel_pmt.
  – Each device is represented by a subfolder within the intel_pmt class,
    named using its DBDF (Domain:Bus:Device.Function), e.g.:
        features-0000:00:03.1
  – Example directory layout for a device:

    /sys/class/intel_pmt/features-0000:00:03.1/
    ├── accelerator_telemetry
    ├── crash_log
    ├── per_core_environment_telemetry
    ├── per_core_performance_telemetry
    ├── per_rmid_energy_telemetry
    ├── per_rmid_perf_telemetry
    ├── tpmi_control
    ├── tracing
    └── uncore_telemetry

By exposing PMT feature details through sysfs and integrating with the
existing PMT class, this driver paves the way for more streamlined
integration of PMT-based manageability and telemetry tools.

Link: https://www.intel.com/content/www/us/en/content-details/710389/intel-platform-monitoring-technology-intel-pmt-external-specification.html
Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20250703022832.1302928-9-david.e.box@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/pmt/Kconfig     |  12 +
 drivers/platform/x86/intel/pmt/Makefile    |   2 +
 drivers/platform/x86/intel/pmt/class.c     |  35 +-
 drivers/platform/x86/intel/pmt/class.h     |   2 +
 drivers/platform/x86/intel/pmt/discovery.c | 602 +++++++++++++++++++++++++++++
 drivers/platform/x86/intel/pmt/features.c  | 205 ++++++++++
 include/linux/intel_pmt_features.h         | 157 ++++++++
 7 files changed, 1013 insertions(+), 2 deletions(-)
 create mode 100644 drivers/platform/x86/intel/pmt/discovery.c
 create mode 100644 drivers/platform/x86/intel/pmt/features.c
 create mode 100644 include/linux/intel_pmt_features.h

(limited to 'include/linux')

diff --git a/drivers/platform/x86/intel/pmt/Kconfig b/drivers/platform/x86/intel/pmt/Kconfig
index e916fc966221..0ad91b5112e9 100644
--- a/drivers/platform/x86/intel/pmt/Kconfig
+++ b/drivers/platform/x86/intel/pmt/Kconfig
@@ -38,3 +38,15 @@ config INTEL_PMT_CRASHLOG
 
 	  To compile this driver as a module, choose M here: the module
 	  will be called intel_pmt_crashlog.
+
+config INTEL_PMT_DISCOVERY
+	tristate "Intel Platform Monitoring Technology (PMT) Discovery driver"
+	depends on INTEL_VSEC
+	select INTEL_PMT_CLASS
+	help
+	  The Intel Platform Monitoring Technology (PMT) discovery driver provides
+	  access to details about the various PMT features and feature specific
+	  attributes.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called pmt_discovery.
diff --git a/drivers/platform/x86/intel/pmt/Makefile b/drivers/platform/x86/intel/pmt/Makefile
index 279e158c7c23..8aed7e1592e4 100644
--- a/drivers/platform/x86/intel/pmt/Makefile
+++ b/drivers/platform/x86/intel/pmt/Makefile
@@ -10,3 +10,5 @@ obj-$(CONFIG_INTEL_PMT_TELEMETRY)	+= pmt_telemetry.o
 pmt_telemetry-y				:= telemetry.o
 obj-$(CONFIG_INTEL_PMT_CRASHLOG)	+= pmt_crashlog.o
 pmt_crashlog-y				:= crashlog.o
+obj-$(CONFIG_INTEL_PMT_DISCOVERY)	+= pmt_discovery.o
+pmt_discovery-y				:= discovery.o features.o
diff --git a/drivers/platform/x86/intel/pmt/class.c b/drivers/platform/x86/intel/pmt/class.c
index 7233b654bbad..a806a81ece52 100644
--- a/drivers/platform/x86/intel/pmt/class.c
+++ b/drivers/platform/x86/intel/pmt/class.c
@@ -9,11 +9,13 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/log2.h>
 #include <linux/intel_vsec.h>
 #include <linux/io-64-nonatomic-lo-hi.h>
 #include <linux/module.h>
 #include <linux/mm.h>
 #include <linux/pci.h>
+#include <linux/sysfs.h>
 
 #include "class.h"
 
@@ -166,12 +168,41 @@ static struct attribute *intel_pmt_attrs[] = {
 	&dev_attr_offset.attr,
 	NULL
 };
-ATTRIBUTE_GROUPS(intel_pmt);
 
-static struct class intel_pmt_class = {
+static umode_t intel_pmt_attr_visible(struct kobject *kobj,
+				      struct attribute *attr, int n)
+{
+	struct device *dev = container_of(kobj, struct device, kobj);
+	struct auxiliary_device *auxdev = to_auxiliary_dev(dev->parent);
+	struct intel_vsec_device *ivdev = auxdev_to_ivdev(auxdev);
+
+	/*
+	 * Place the discovery features folder in /sys/class/intel_pmt, but
+	 * exclude the common attributes as they are not applicable.
+	 */
+	if (ivdev->cap_id == ilog2(VSEC_CAP_DISCOVERY))
+		return 0;
+
+	return attr->mode;
+}
+
+static bool intel_pmt_group_visible(struct kobject *kobj)
+{
+	return true;
+}
+DEFINE_SYSFS_GROUP_VISIBLE(intel_pmt);
+
+static const struct attribute_group intel_pmt_group = {
+	.attrs = intel_pmt_attrs,
+	.is_visible = SYSFS_GROUP_VISIBLE(intel_pmt),
+};
+__ATTRIBUTE_GROUPS(intel_pmt);
+
+struct class intel_pmt_class = {
 	.name = "intel_pmt",
 	.dev_groups = intel_pmt_groups,
 };
+EXPORT_SYMBOL_GPL(intel_pmt_class);
 
 static int intel_pmt_populate_entry(struct intel_pmt_entry *entry,
 				    struct intel_vsec_device *ivdev,
diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h
index b2006d57779d..39c32357ee2c 100644
--- a/drivers/platform/x86/intel/pmt/class.h
+++ b/drivers/platform/x86/intel/pmt/class.h
@@ -20,6 +20,7 @@
 #define GET_ADDRESS(v)		((v) & GENMASK(31, 3))
 
 struct pci_dev;
+extern struct class intel_pmt_class;
 
 struct telem_endpoint {
 	struct pci_dev		*pcidev;
@@ -48,6 +49,7 @@ struct intel_pmt_entry {
 	unsigned long		base_addr;
 	size_t			size;
 	u32			guid;
+	u32			num_rmids; /* Number of Resource Monitoring IDs */
 	int			devid;
 };
 
diff --git a/drivers/platform/x86/intel/pmt/discovery.c b/drivers/platform/x86/intel/pmt/discovery.c
new file mode 100644
index 000000000000..4b4fa3137ad2
--- /dev/null
+++ b/drivers/platform/x86/intel/pmt/discovery.c
@@ -0,0 +1,602 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Intel Platform Monitory Technology Discovery driver
+ *
+ * Copyright (c) 2025, Intel Corporation.
+ * All Rights Reserved.
+ */
+
+#include <linux/auxiliary_bus.h>
+#include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/bug.h>
+#include <linux/cleanup.h>
+#include <linux/container_of.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/kdev_t.h>
+#include <linux/kobject.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/overflow.h>
+#include <linux/pci.h>
+#include <linux/slab.h>
+#include <linux/string_choices.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
+#include <linux/uaccess.h>
+
+#include <linux/intel_pmt_features.h>
+#include <linux/intel_vsec.h>
+
+#include "class.h"
+
+#define MAX_FEATURE_VERSION	0
+#define DT_TBIR			GENMASK(2, 0)
+#define FEAT_ATTR_SIZE(x)	((x) * sizeof(u32))
+#define PMT_GUID_SIZE(x)	((x) * sizeof(u32))
+#define PMT_ACCESS_TYPE_RSVD	0xF
+#define SKIP_FEATURE		1
+
+struct feature_discovery_table {
+	u32	access_type:4;
+	u32	version:8;
+	u32	size:16;
+	u32	reserved:4;
+	u32	id;
+	u32	offset;
+	u32	reserved2;
+};
+
+/* Common feature table header */
+struct feature_header {
+	u32	attr_size:8;
+	u32	num_guids:8;
+	u32	reserved:16;
+};
+
+/* Feature attribute fields */
+struct caps {
+	u32		caps;
+};
+
+struct command {
+	u32		max_stream_size:16;
+	u32		max_command_size:16;
+};
+
+struct watcher {
+	u32		reserved:21;
+	u32		period:11;
+	struct command	command;
+};
+
+struct rmid {
+	u32		num_rmids:16;	/* Number of Resource Monitoring IDs */
+	u32		reserved:16;
+	struct watcher	watcher;
+};
+
+struct feature_table {
+	struct feature_header	header;
+	struct caps		caps;
+	union {
+		struct command command;
+		struct watcher watcher;
+		struct rmid rmid;
+	};
+	u32			*guids;
+};
+
+/* For backreference in struct feature */
+struct pmt_features_priv;
+
+struct feature {
+	struct feature_table		table;
+	struct kobject			kobj;
+	struct pmt_features_priv	*priv;
+	struct list_head		list;
+	const struct attribute_group	*attr_group;
+	enum pmt_feature_id		id;
+};
+
+struct pmt_features_priv {
+	struct device		*parent;
+	struct device		*dev;
+	int			count;
+	u32			mask;
+	struct feature		feature[];
+};
+
+static LIST_HEAD(pmt_feature_list);
+static DEFINE_MUTEX(feature_list_lock);
+
+#define to_pmt_feature(x) container_of(x, struct feature, kobj)
+static void pmt_feature_release(struct kobject *kobj)
+{
+}
+
+static ssize_t caps_show(struct kobject *kobj, struct kobj_attribute *attr,
+			 char *buf)
+{
+	struct feature *feature = to_pmt_feature(kobj);
+	struct pmt_cap **pmt_caps;
+	u32 caps = feature->table.caps.caps;
+	ssize_t ret = 0;
+
+	switch (feature->id) {
+	case FEATURE_PER_CORE_PERF_TELEM:
+		pmt_caps = pmt_caps_pcpt;
+		break;
+	case FEATURE_PER_CORE_ENV_TELEM:
+		pmt_caps = pmt_caps_pcet;
+		break;
+	case FEATURE_PER_RMID_PERF_TELEM:
+		pmt_caps = pmt_caps_rmid_perf;
+		break;
+	case FEATURE_ACCEL_TELEM:
+		pmt_caps = pmt_caps_accel;
+		break;
+	case FEATURE_UNCORE_TELEM:
+		pmt_caps = pmt_caps_uncore;
+		break;
+	case FEATURE_CRASH_LOG:
+		pmt_caps = pmt_caps_crashlog;
+		break;
+	case FEATURE_PETE_LOG:
+		pmt_caps = pmt_caps_pete;
+		break;
+	case FEATURE_TPMI_CTRL:
+		pmt_caps = pmt_caps_tpmi;
+		break;
+	case FEATURE_TRACING:
+		pmt_caps = pmt_caps_tracing;
+		break;
+	case FEATURE_PER_RMID_ENERGY_TELEM:
+		pmt_caps = pmt_caps_rmid_energy;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	while (*pmt_caps) {
+		struct pmt_cap *pmt_cap = *pmt_caps;
+
+		while (pmt_cap->name) {
+			ret += sysfs_emit_at(buf, ret, "%-40s Available: %s\n", pmt_cap->name,
+					     str_yes_no(pmt_cap->mask & caps));
+			pmt_cap++;
+		}
+		pmt_caps++;
+	}
+
+	return ret;
+}
+static struct kobj_attribute caps_attribute = __ATTR_RO(caps);
+
+static struct watcher *get_watcher(struct feature *feature)
+{
+	switch (feature_layout[feature->id]) {
+	case LAYOUT_RMID:
+		return &feature->table.rmid.watcher;
+	case LAYOUT_WATCHER:
+		return &feature->table.watcher;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+}
+
+static struct command *get_command(struct feature *feature)
+{
+	switch (feature_layout[feature->id]) {
+	case LAYOUT_RMID:
+		return &feature->table.rmid.watcher.command;
+	case LAYOUT_WATCHER:
+		return &feature->table.watcher.command;
+	case LAYOUT_COMMAND:
+		return &feature->table.command;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+}
+
+static ssize_t num_rmids_show(struct kobject *kobj,
+			      struct kobj_attribute *attr, char *buf)
+{
+	struct feature *feature = to_pmt_feature(kobj);
+
+	return sysfs_emit(buf, "%u\n", feature->table.rmid.num_rmids);
+}
+static struct kobj_attribute num_rmids_attribute = __ATTR_RO(num_rmids);
+
+static ssize_t min_watcher_period_ms_show(struct kobject *kobj,
+					  struct kobj_attribute *attr, char *buf)
+{
+	struct feature *feature = to_pmt_feature(kobj);
+	struct watcher *watcher = get_watcher(feature);
+
+	if (IS_ERR(watcher))
+		return PTR_ERR(watcher);
+
+	return sysfs_emit(buf, "%u\n", watcher->period);
+}
+static struct kobj_attribute min_watcher_period_ms_attribute =
+	__ATTR_RO(min_watcher_period_ms);
+
+static ssize_t max_stream_size_show(struct kobject *kobj,
+				    struct kobj_attribute *attr, char *buf)
+{
+	struct feature *feature = to_pmt_feature(kobj);
+	struct command *command = get_command(feature);
+
+	if (IS_ERR(command))
+		return PTR_ERR(command);
+
+	return sysfs_emit(buf, "%u\n", command->max_stream_size);
+}
+static struct kobj_attribute max_stream_size_attribute =
+	__ATTR_RO(max_stream_size);
+
+static ssize_t max_command_size_show(struct kobject *kobj,
+				     struct kobj_attribute *attr, char *buf)
+{
+	struct feature *feature = to_pmt_feature(kobj);
+	struct command *command = get_command(feature);
+
+	if (IS_ERR(command))
+		return PTR_ERR(command);
+
+	return sysfs_emit(buf, "%u\n", command->max_command_size);
+}
+static struct kobj_attribute max_command_size_attribute =
+	__ATTR_RO(max_command_size);
+
+static ssize_t guids_show(struct kobject *kobj, struct kobj_attribute *attr,
+			  char *buf)
+{
+	struct feature *feature = to_pmt_feature(kobj);
+	int i, count = 0;
+
+	for (i = 0; i < feature->table.header.num_guids; i++)
+		count += sysfs_emit_at(buf, count, "0x%x\n",
+				       feature->table.guids[i]);
+
+	return count;
+}
+static struct kobj_attribute guids_attribute = __ATTR_RO(guids);
+
+static struct attribute *pmt_feature_rmid_attrs[] = {
+	&caps_attribute.attr,
+	&num_rmids_attribute.attr,
+	&min_watcher_period_ms_attribute.attr,
+	&max_stream_size_attribute.attr,
+	&max_command_size_attribute.attr,
+	&guids_attribute.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(pmt_feature_rmid);
+
+static const struct kobj_type pmt_feature_rmid_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = pmt_feature_release,
+	.default_groups = pmt_feature_rmid_groups,
+};
+
+static struct attribute *pmt_feature_watcher_attrs[] = {
+	&caps_attribute.attr,
+	&min_watcher_period_ms_attribute.attr,
+	&max_stream_size_attribute.attr,
+	&max_command_size_attribute.attr,
+	&guids_attribute.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(pmt_feature_watcher);
+
+static const struct kobj_type pmt_feature_watcher_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = pmt_feature_release,
+	.default_groups = pmt_feature_watcher_groups,
+};
+
+static struct attribute *pmt_feature_command_attrs[] = {
+	&caps_attribute.attr,
+	&max_stream_size_attribute.attr,
+	&max_command_size_attribute.attr,
+	&guids_attribute.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(pmt_feature_command);
+
+static const struct kobj_type pmt_feature_command_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = pmt_feature_release,
+	.default_groups = pmt_feature_command_groups,
+};
+
+static struct attribute *pmt_feature_guids_attrs[] = {
+	&caps_attribute.attr,
+	&guids_attribute.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(pmt_feature_guids);
+
+static const struct kobj_type pmt_feature_guids_ktype = {
+	.sysfs_ops = &kobj_sysfs_ops,
+	.release = pmt_feature_release,
+	.default_groups = pmt_feature_guids_groups,
+};
+
+static int
+pmt_feature_get_disc_table(struct pmt_features_priv *priv,
+			   struct resource *disc_res,
+			   struct feature_discovery_table *disc_tbl)
+{
+	void __iomem *disc_base;
+
+	disc_base = devm_ioremap_resource(priv->dev, disc_res);
+	if (IS_ERR(disc_base))
+		return PTR_ERR(disc_base);
+
+	memcpy_fromio(disc_tbl, disc_base, sizeof(*disc_tbl));
+
+	devm_iounmap(priv->dev, disc_base);
+
+	if (priv->mask & BIT(disc_tbl->id))
+		return dev_err_probe(priv->dev, -EINVAL, "Duplicate feature: %s\n",
+				     pmt_feature_names[disc_tbl->id]);
+
+	/*
+	 * Some devices may expose non-functioning entries that are
+	 * reserved for future use. They have zero size. Do not fail
+	 * probe for these. Just ignore them.
+	 */
+	if (disc_tbl->size == 0 || disc_tbl->access_type == PMT_ACCESS_TYPE_RSVD)
+		return SKIP_FEATURE;
+
+	if (disc_tbl->version > MAX_FEATURE_VERSION)
+		return SKIP_FEATURE;
+
+	if (!pmt_feature_id_is_valid(disc_tbl->id))
+		return SKIP_FEATURE;
+
+	priv->mask |= BIT(disc_tbl->id);
+
+	return 0;
+}
+
+static int
+pmt_feature_get_feature_table(struct pmt_features_priv *priv,
+			      struct feature *feature,
+			      struct feature_discovery_table *disc_tbl,
+			      struct resource *disc_res)
+{
+	struct feature_table *feat_tbl = &feature->table;
+	struct feature_header *header;
+	struct resource res = {};
+	resource_size_t res_size;
+	void __iomem *feat_base, *feat_offset;
+	void *tbl_offset;
+	size_t size;
+	u32 *guids;
+	u8 tbir;
+
+	tbir = FIELD_GET(DT_TBIR, disc_tbl->offset);
+
+	switch (disc_tbl->access_type) {
+	case ACCESS_LOCAL:
+		if (tbir)
+			return dev_err_probe(priv->dev, -EINVAL,
+				"Unsupported BAR index %u for access type %u\n",
+				tbir, disc_tbl->access_type);
+
+
+		/*
+		 * For access_type LOCAL, the base address is as follows:
+		 * base address = end of discovery region + base offset + 1
+		 */
+		res = DEFINE_RES_MEM(disc_res->end + disc_tbl->offset + 1,
+				     disc_tbl->size * sizeof(u32));
+		break;
+
+	default:
+		return dev_err_probe(priv->dev, -EINVAL, "Unrecognized access_type %u\n",
+				     disc_tbl->access_type);
+	}
+
+	feature->id = disc_tbl->id;
+
+	/* Get the feature table */
+	feat_base = devm_ioremap_resource(priv->dev, &res);
+	if (IS_ERR(feat_base))
+		return PTR_ERR(feat_base);
+
+	feat_offset = feat_base;
+	tbl_offset = feat_tbl;
+
+	/* Get the header */
+	header = &feat_tbl->header;
+	memcpy_fromio(header, feat_offset, sizeof(*header));
+
+	/* Validate fields fit within mapped resource */
+	size = sizeof(*header) + FEAT_ATTR_SIZE(header->attr_size) +
+	       PMT_GUID_SIZE(header->num_guids);
+	res_size = resource_size(&res);
+	if (WARN(size > res_size, "Bad table size %ld > %pa", size, &res_size))
+		return -EINVAL;
+
+	/* Get the feature attributes, including capability fields */
+	tbl_offset += sizeof(*header);
+	feat_offset += sizeof(*header);
+
+	memcpy_fromio(tbl_offset, feat_offset, FEAT_ATTR_SIZE(header->attr_size));
+
+	/* Finally, get the guids */
+	guids = devm_kmalloc(priv->dev, PMT_GUID_SIZE(header->num_guids), GFP_KERNEL);
+	if (!guids)
+		return -ENOMEM;
+
+	feat_offset += FEAT_ATTR_SIZE(header->attr_size);
+
+	memcpy_fromio(guids, feat_offset, PMT_GUID_SIZE(header->num_guids));
+
+	feat_tbl->guids = guids;
+
+	devm_iounmap(priv->dev, feat_base);
+
+	return 0;
+}
+
+static void pmt_features_add_feat(struct feature *feature)
+{
+	guard(mutex)(&feature_list_lock);
+	list_add(&feature->list, &pmt_feature_list);
+}
+
+static void pmt_features_remove_feat(struct feature *feature)
+{
+	guard(mutex)(&feature_list_lock);
+	list_del(&feature->list);
+}
+
+/* Get the discovery table and use it to get the feature table */
+static int pmt_features_discovery(struct pmt_features_priv *priv,
+				  struct feature *feature,
+				  struct intel_vsec_device *ivdev,
+				  int idx)
+{
+	struct feature_discovery_table disc_tbl = {}; /* Avoid false warning */
+	struct resource *disc_res = &ivdev->resource[idx];
+	const struct kobj_type *ktype;
+	int ret;
+
+	ret = pmt_feature_get_disc_table(priv, disc_res, &disc_tbl);
+	if (ret)
+		return ret;
+
+	ret = pmt_feature_get_feature_table(priv, feature, &disc_tbl, disc_res);
+	if (ret)
+		return ret;
+
+	switch (feature_layout[feature->id]) {
+	case LAYOUT_RMID:
+		ktype = &pmt_feature_rmid_ktype;
+		feature->attr_group = &pmt_feature_rmid_group;
+		break;
+	case LAYOUT_WATCHER:
+		ktype = &pmt_feature_watcher_ktype;
+		feature->attr_group = &pmt_feature_watcher_group;
+		break;
+	case LAYOUT_COMMAND:
+		ktype = &pmt_feature_command_ktype;
+		feature->attr_group = &pmt_feature_command_group;
+		break;
+	case LAYOUT_CAPS_ONLY:
+		ktype = &pmt_feature_guids_ktype;
+		feature->attr_group = &pmt_feature_guids_group;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	ret = kobject_init_and_add(&feature->kobj, ktype, &priv->dev->kobj,
+				   pmt_feature_names[feature->id]);
+	if (ret)
+		return ret;
+
+	kobject_uevent(&feature->kobj, KOBJ_ADD);
+	pmt_features_add_feat(feature);
+
+	return 0;
+}
+
+static void pmt_features_remove(struct auxiliary_device *auxdev)
+{
+	struct pmt_features_priv *priv = auxiliary_get_drvdata(auxdev);
+	int i;
+
+	for (i = 0; i < priv->count; i++) {
+		struct feature *feature = &priv->feature[i];
+
+		pmt_features_remove_feat(feature);
+		sysfs_remove_group(&feature->kobj, feature->attr_group);
+		kobject_put(&feature->kobj);
+	}
+
+	device_unregister(priv->dev);
+}
+
+static int pmt_features_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id)
+{
+	struct intel_vsec_device *ivdev = auxdev_to_ivdev(auxdev);
+	struct pmt_features_priv *priv;
+	size_t size;
+	int ret, i;
+
+	size = struct_size(priv, feature, ivdev->num_resources);
+	priv = devm_kzalloc(&auxdev->dev, size, GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->parent = &ivdev->pcidev->dev;
+	auxiliary_set_drvdata(auxdev, priv);
+
+	priv->dev = device_create(&intel_pmt_class, &auxdev->dev, MKDEV(0, 0), priv,
+				  "%s-%s", "features", dev_name(priv->parent));
+	if (IS_ERR(priv->dev))
+		return dev_err_probe(priv->dev, PTR_ERR(priv->dev),
+				     "Could not create %s-%s device node\n",
+				     "features", dev_name(priv->dev));
+
+	/* Initialize each feature */
+	for (i = 0; i < ivdev->num_resources; i++) {
+		struct feature *feature = &priv->feature[priv->count];
+
+		ret = pmt_features_discovery(priv, feature, ivdev, i);
+		if (ret == SKIP_FEATURE)
+			continue;
+		if (ret != 0)
+			goto abort_probe;
+
+		feature->priv = priv;
+		priv->count++;
+	}
+
+	return 0;
+
+abort_probe:
+	/*
+	 * Only fully initialized features are tracked in priv->count, which is
+	 * incremented only after a feature is completely set up (i.e., after
+	 * discovery and sysfs registration). If feature initialization fails,
+	 * the failing feature's state is local and does not require rollback.
+	 *
+	 * Therefore, on error, we can safely call the driver's remove() routine
+	 * pmt_features_remove() to clean up only those features that were
+	 * fully initialized and counted. All other resources are device-managed
+	 * and will be cleaned up automatically during device_unregister().
+	 */
+	pmt_features_remove(auxdev);
+
+	return ret;
+}
+
+static const struct auxiliary_device_id pmt_features_id_table[] = {
+	{ .name = "intel_vsec.discovery" },
+	{}
+};
+MODULE_DEVICE_TABLE(auxiliary, pmt_features_id_table);
+
+static struct auxiliary_driver pmt_features_aux_driver = {
+	.id_table	= pmt_features_id_table,
+	.remove		= pmt_features_remove,
+	.probe		= pmt_features_probe,
+};
+module_auxiliary_driver(pmt_features_aux_driver);
+
+MODULE_AUTHOR("David E. Box <david.e.box@linux.intel.com>");
+MODULE_DESCRIPTION("Intel PMT Discovery driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("INTEL_PMT");
diff --git a/drivers/platform/x86/intel/pmt/features.c b/drivers/platform/x86/intel/pmt/features.c
new file mode 100644
index 000000000000..8a39cddc75c8
--- /dev/null
+++ b/drivers/platform/x86/intel/pmt/features.c
@@ -0,0 +1,205 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2025, Intel Corporation.
+ * All Rights Reserved.
+ *
+ * Author: "David E. Box" <david.e.box@linux.intel.com>
+ */
+
+#include <linux/export.h>
+#include <linux/types.h>
+
+#include <linux/intel_pmt_features.h>
+
+const char * const pmt_feature_names[] = {
+	[FEATURE_PER_CORE_PERF_TELEM]	= "per_core_performance_telemetry",
+	[FEATURE_PER_CORE_ENV_TELEM]	= "per_core_environment_telemetry",
+	[FEATURE_PER_RMID_PERF_TELEM]	= "per_rmid_perf_telemetry",
+	[FEATURE_ACCEL_TELEM]		= "accelerator_telemetry",
+	[FEATURE_UNCORE_TELEM]		= "uncore_telemetry",
+	[FEATURE_CRASH_LOG]		= "crash_log",
+	[FEATURE_PETE_LOG]		= "pete_log",
+	[FEATURE_TPMI_CTRL]		= "tpmi_control",
+	[FEATURE_TRACING]		= "tracing",
+	[FEATURE_PER_RMID_ENERGY_TELEM]	= "per_rmid_energy_telemetry",
+};
+EXPORT_SYMBOL_NS_GPL(pmt_feature_names, "INTEL_PMT_DISCOVERY");
+
+enum feature_layout feature_layout[] = {
+	[FEATURE_PER_CORE_PERF_TELEM]	= LAYOUT_WATCHER,
+	[FEATURE_PER_CORE_ENV_TELEM]	= LAYOUT_WATCHER,
+	[FEATURE_PER_RMID_PERF_TELEM]	= LAYOUT_RMID,
+	[FEATURE_ACCEL_TELEM]		= LAYOUT_WATCHER,
+	[FEATURE_UNCORE_TELEM]		= LAYOUT_WATCHER,
+	[FEATURE_CRASH_LOG]		= LAYOUT_COMMAND,
+	[FEATURE_PETE_LOG]		= LAYOUT_COMMAND,
+	[FEATURE_TPMI_CTRL]		= LAYOUT_CAPS_ONLY,
+	[FEATURE_TRACING]		= LAYOUT_CAPS_ONLY,
+	[FEATURE_PER_RMID_ENERGY_TELEM]	= LAYOUT_RMID,
+};
+
+struct pmt_cap pmt_cap_common[] = {
+	{PMT_CAP_TELEM,		"telemetry"},
+	{PMT_CAP_WATCHER,	"watcher"},
+	{PMT_CAP_CRASHLOG,	"crashlog"},
+	{PMT_CAP_STREAMING,	"streaming"},
+	{PMT_CAP_THRESHOLD,	"threshold"},
+	{PMT_CAP_WINDOW,	"window"},
+	{PMT_CAP_CONFIG,	"config"},
+	{PMT_CAP_TRACING,	"tracing"},
+	{PMT_CAP_INBAND,	"inband"},
+	{PMT_CAP_OOB,		"oob"},
+	{PMT_CAP_SECURED_CHAN,	"secure_chan"},
+	{PMT_CAP_PMT_SP,	"pmt_sp"},
+	{PMT_CAP_PMT_SP_POLICY,	"pmt_sp_policy"},
+	{}
+};
+
+struct pmt_cap pmt_cap_pcpt[] = {
+	{PMT_CAP_PCPT_CORE_PERF,	"core_performance"},
+	{PMT_CAP_PCPT_CORE_C0_RES,	"core_c0_residency"},
+	{PMT_CAP_PCPT_CORE_ACTIVITY,	"core_activity"},
+	{PMT_CAP_PCPT_CACHE_PERF,	"cache_performance"},
+	{PMT_CAP_PCPT_QUALITY_TELEM,	"quality_telemetry"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_pcpt[] = {
+	pmt_cap_common,
+	pmt_cap_pcpt,
+	NULL
+};
+
+struct pmt_cap pmt_cap_pcet[] = {
+	{PMT_CAP_PCET_WORKPOINT_HIST,	"workpoint_histogram"},
+	{PMT_CAP_PCET_CORE_CURR_TEMP,	"core_current_temp"},
+	{PMT_CAP_PCET_CORE_INST_RES,	"core_inst_residency"},
+	{PMT_CAP_PCET_QUALITY_TELEM,	"quality_telemetry"},
+	{PMT_CAP_PCET_CORE_CDYN_LVL,	"core_cdyn_level"},
+	{PMT_CAP_PCET_CORE_STRESS_LVL,	"core_stress_level"},
+	{PMT_CAP_PCET_CORE_DAS,		"core_digital_aging_sensor"},
+	{PMT_CAP_PCET_FIVR_HEALTH,	"fivr_health"},
+	{PMT_CAP_PCET_ENERGY,		"energy"},
+	{PMT_CAP_PCET_PEM_STATUS,	"pem_status"},
+	{PMT_CAP_PCET_CORE_C_STATE,	"core_c_state"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_pcet[] = {
+	pmt_cap_common,
+	pmt_cap_pcet,
+	NULL
+};
+
+struct pmt_cap pmt_cap_rmid_perf[] = {
+	{PMT_CAP_RMID_CORES_PERF,	"core_performance"},
+	{PMT_CAP_RMID_CACHE_PERF,	"cache_performance"},
+	{PMT_CAP_RMID_PERF_QUAL,	"performance_quality"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_rmid_perf[] = {
+	pmt_cap_common,
+	pmt_cap_rmid_perf,
+	NULL
+};
+
+struct pmt_cap pmt_cap_accel[] = {
+	{PMT_CAP_ACCEL_CPM_TELEM,	"content_processing_module"},
+	{PMT_CAP_ACCEL_TIP_TELEM,	"content_turbo_ip"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_accel[] = {
+	pmt_cap_common,
+	pmt_cap_accel,
+	NULL
+};
+
+struct pmt_cap pmt_cap_uncore[] = {
+	{PMT_CAP_UNCORE_IO_CA_TELEM,	"io_ca"},
+	{PMT_CAP_UNCORE_RMID_TELEM,	"rmid"},
+	{PMT_CAP_UNCORE_D2D_ULA_TELEM,	"d2d_ula"},
+	{PMT_CAP_UNCORE_PKGC_TELEM,	"package_c"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_uncore[] = {
+	pmt_cap_common,
+	pmt_cap_uncore,
+	NULL
+};
+
+struct pmt_cap pmt_cap_crashlog[] = {
+	{PMT_CAP_CRASHLOG_MAN_TRIG,	"manual_trigger"},
+	{PMT_CAP_CRASHLOG_CORE,		"core"},
+	{PMT_CAP_CRASHLOG_UNCORE,	"uncore"},
+	{PMT_CAP_CRASHLOG_TOR,		"tor"},
+	{PMT_CAP_CRASHLOG_S3M,		"s3m"},
+	{PMT_CAP_CRASHLOG_PERSISTENCY,	"persistency"},
+	{PMT_CAP_CRASHLOG_CLIP_GPIO,	"crashlog_in_progress"},
+	{PMT_CAP_CRASHLOG_PRE_RESET,	"pre_reset_extraction"},
+	{PMT_CAP_CRASHLOG_POST_RESET,	"post_reset_extraction"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_crashlog[] = {
+	pmt_cap_common,
+	pmt_cap_crashlog,
+	NULL
+};
+
+struct pmt_cap pmt_cap_pete[] = {
+	{PMT_CAP_PETE_MAN_TRIG,		"manual_trigger"},
+	{PMT_CAP_PETE_ENCRYPTION,	"encryption"},
+	{PMT_CAP_PETE_PERSISTENCY,	"persistency"},
+	{PMT_CAP_PETE_REQ_TOKENS,	"required_tokens"},
+	{PMT_CAP_PETE_PROD_ENABLED,	"production_enabled"},
+	{PMT_CAP_PETE_DEBUG_ENABLED,	"debug_enabled"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_pete[] = {
+	pmt_cap_common,
+	pmt_cap_pete,
+	NULL
+};
+
+struct pmt_cap pmt_cap_tpmi[] = {
+	{PMT_CAP_TPMI_MAILBOX,		"mailbox"},
+	{PMT_CAP_TPMI_LOCK,		"bios_lock"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_tpmi[] = {
+	pmt_cap_common,
+	pmt_cap_tpmi,
+	NULL
+};
+
+struct pmt_cap pmt_cap_tracing[] = {
+	{PMT_CAP_TRACE_SRAR,		"srar_errors"},
+	{PMT_CAP_TRACE_CORRECTABLE,	"correctable_errors"},
+	{PMT_CAP_TRACE_MCTP,		"mctp"},
+	{PMT_CAP_TRACE_MRT,		"memory_resiliency"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_tracing[] = {
+	pmt_cap_common,
+	pmt_cap_tracing,
+	NULL
+};
+
+struct pmt_cap pmt_cap_rmid_energy[] = {
+	{PMT_CAP_RMID_ENERGY,		"energy"},
+	{PMT_CAP_RMID_ACTIVITY,		"activity"},
+	{PMT_CAP_RMID_ENERGY_QUAL,	"energy_quality"},
+	{}
+};
+
+struct pmt_cap *pmt_caps_rmid_energy[] = {
+	pmt_cap_common,
+	pmt_cap_rmid_energy,
+	NULL
+};
diff --git a/include/linux/intel_pmt_features.h b/include/linux/intel_pmt_features.h
new file mode 100644
index 000000000000..53573a4a49b7
--- /dev/null
+++ b/include/linux/intel_pmt_features.h
@@ -0,0 +1,157 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FEATURES_H
+#define _FEATURES_H
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+/* Common masks */
+#define PMT_CAP_TELEM			BIT(0)
+#define PMT_CAP_WATCHER			BIT(1)
+#define PMT_CAP_CRASHLOG		BIT(2)
+#define PMT_CAP_STREAMING		BIT(3)
+#define PMT_CAP_THRESHOLD		BIT(4)
+#define PMT_CAP_WINDOW			BIT(5)
+#define PMT_CAP_CONFIG			BIT(6)
+#define PMT_CAP_TRACING			BIT(7)
+#define PMT_CAP_INBAND			BIT(8)
+#define PMT_CAP_OOB			BIT(9)
+#define PMT_CAP_SECURED_CHAN		BIT(10)
+
+#define PMT_CAP_PMT_SP			BIT(11)
+#define PMT_CAP_PMT_SP_POLICY		GENMASK(17, 12)
+
+/* Per Core Performance Telemetry (PCPT) specific masks */
+#define PMT_CAP_PCPT_CORE_PERF		BIT(18)
+#define PMT_CAP_PCPT_CORE_C0_RES	BIT(19)
+#define PMT_CAP_PCPT_CORE_ACTIVITY	BIT(20)
+#define PMT_CAP_PCPT_CACHE_PERF		BIT(21)
+#define PMT_CAP_PCPT_QUALITY_TELEM	BIT(22)
+
+/* Per Core Environmental Telemetry (PCET) specific masks */
+#define PMT_CAP_PCET_WORKPOINT_HIST	BIT(18)
+#define PMT_CAP_PCET_CORE_CURR_TEMP	BIT(19)
+#define PMT_CAP_PCET_CORE_INST_RES	BIT(20)
+#define PMT_CAP_PCET_QUALITY_TELEM	BIT(21)	/* Same as PMT_CAP_PCPT */
+#define PMT_CAP_PCET_CORE_CDYN_LVL	BIT(22)
+#define PMT_CAP_PCET_CORE_STRESS_LVL	BIT(23)
+#define PMT_CAP_PCET_CORE_DAS		BIT(24)
+#define PMT_CAP_PCET_FIVR_HEALTH	BIT(25)
+#define PMT_CAP_PCET_ENERGY		BIT(26)
+#define PMT_CAP_PCET_PEM_STATUS		BIT(27)
+#define PMT_CAP_PCET_CORE_C_STATE	BIT(28)
+
+/* Per RMID Performance Telemetry specific masks */
+#define PMT_CAP_RMID_CORES_PERF		BIT(18)
+#define PMT_CAP_RMID_CACHE_PERF		BIT(19)
+#define PMT_CAP_RMID_PERF_QUAL		BIT(20)
+
+/* Accelerator Telemetry specific masks */
+#define PMT_CAP_ACCEL_CPM_TELEM		BIT(18)
+#define PMT_CAP_ACCEL_TIP_TELEM		BIT(19)
+
+/* Uncore Telemetry specific masks */
+#define PMT_CAP_UNCORE_IO_CA_TELEM	BIT(18)
+#define PMT_CAP_UNCORE_RMID_TELEM	BIT(19)
+#define PMT_CAP_UNCORE_D2D_ULA_TELEM	BIT(20)
+#define PMT_CAP_UNCORE_PKGC_TELEM	BIT(21)
+
+/* Crash Log specific masks */
+#define PMT_CAP_CRASHLOG_MAN_TRIG	BIT(11)
+#define PMT_CAP_CRASHLOG_CORE		BIT(12)
+#define PMT_CAP_CRASHLOG_UNCORE		BIT(13)
+#define PMT_CAP_CRASHLOG_TOR		BIT(14)
+#define PMT_CAP_CRASHLOG_S3M		BIT(15)
+#define PMT_CAP_CRASHLOG_PERSISTENCY	BIT(16)
+#define PMT_CAP_CRASHLOG_CLIP_GPIO	BIT(17)
+#define PMT_CAP_CRASHLOG_PRE_RESET	BIT(18)
+#define PMT_CAP_CRASHLOG_POST_RESET	BIT(19)
+
+/* PeTe Log specific masks */
+#define PMT_CAP_PETE_MAN_TRIG		BIT(11)
+#define PMT_CAP_PETE_ENCRYPTION		BIT(12)
+#define PMT_CAP_PETE_PERSISTENCY	BIT(13)
+#define PMT_CAP_PETE_REQ_TOKENS		BIT(14)
+#define PMT_CAP_PETE_PROD_ENABLED	BIT(15)
+#define PMT_CAP_PETE_DEBUG_ENABLED	BIT(16)
+
+/* TPMI control specific masks */
+#define PMT_CAP_TPMI_MAILBOX		BIT(11)
+#define PMT_CAP_TPMI_LOCK		BIT(12)
+
+/* Tracing specific masks */
+#define PMT_CAP_TRACE_SRAR		BIT(11)
+#define PMT_CAP_TRACE_CORRECTABLE	BIT(12)
+#define PMT_CAP_TRACE_MCTP		BIT(13)
+#define PMT_CAP_TRACE_MRT		BIT(14)
+
+/* Per RMID Energy Telemetry specific masks */
+#define PMT_CAP_RMID_ENERGY		BIT(18)
+#define PMT_CAP_RMID_ACTIVITY		BIT(19)
+#define PMT_CAP_RMID_ENERGY_QUAL	BIT(20)
+
+enum pmt_feature_id {
+	FEATURE_INVALID			= 0x0,
+	FEATURE_PER_CORE_PERF_TELEM	= 0x1,
+	FEATURE_PER_CORE_ENV_TELEM	= 0x2,
+	FEATURE_PER_RMID_PERF_TELEM	= 0x3,
+	FEATURE_ACCEL_TELEM		= 0x4,
+	FEATURE_UNCORE_TELEM		= 0x5,
+	FEATURE_CRASH_LOG		= 0x6,
+	FEATURE_PETE_LOG		= 0x7,
+	FEATURE_TPMI_CTRL		= 0x8,
+	FEATURE_RESERVED		= 0x9,
+	FEATURE_TRACING			= 0xA,
+	FEATURE_PER_RMID_ENERGY_TELEM	= 0xB,
+	FEATURE_MAX			= 0xB,
+};
+
+enum feature_layout {
+	LAYOUT_RMID,
+	LAYOUT_WATCHER,
+	LAYOUT_COMMAND,
+	LAYOUT_CAPS_ONLY,
+};
+
+struct pmt_cap {
+	u32		mask;
+	const char	*name;
+};
+
+extern const char * const pmt_feature_names[];
+extern enum feature_layout feature_layout[];
+extern struct pmt_cap pmt_cap_common[];
+extern struct pmt_cap pmt_cap_pcpt[];
+extern struct pmt_cap *pmt_caps_pcpt[];
+extern struct pmt_cap pmt_cap_pcet[];
+extern struct pmt_cap *pmt_caps_pcet[];
+extern struct pmt_cap pmt_cap_rmid_perf[];
+extern struct pmt_cap *pmt_caps_rmid_perf[];
+extern struct pmt_cap pmt_cap_accel[];
+extern struct pmt_cap *pmt_caps_accel[];
+extern struct pmt_cap pmt_cap_uncore[];
+extern struct pmt_cap *pmt_caps_uncore[];
+extern struct pmt_cap pmt_cap_crashlog[];
+extern struct pmt_cap *pmt_caps_crashlog[];
+extern struct pmt_cap pmt_cap_pete[];
+extern struct pmt_cap *pmt_caps_pete[];
+extern struct pmt_cap pmt_cap_tpmi[];
+extern struct pmt_cap *pmt_caps_tpmi[];
+extern struct pmt_cap pmt_cap_s3m[];
+extern struct pmt_cap *pmt_caps_s3m[];
+extern struct pmt_cap pmt_cap_tracing[];
+extern struct pmt_cap *pmt_caps_tracing[];
+extern struct pmt_cap pmt_cap_rmid_energy[];
+extern struct pmt_cap *pmt_caps_rmid_energy[];
+
+static inline bool pmt_feature_id_is_valid(enum pmt_feature_id id)
+{
+	if (id > FEATURE_MAX)
+		return false;
+
+	if (id == FEATURE_INVALID || id == FEATURE_RESERVED)
+		return false;
+
+	return true;
+}
+#endif
-- 
cgit v1.2.3


From 934954df0f44de5e10afc1af84c06f78149f15fe Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 2 Jul 2025 19:28:25 -0700
Subject: platform/x86/intel/tpmi: Relocate platform info to intel_vsec.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The TPMI platform information provides a mapping of OOBMSM PCI devices to
logical CPUs. Since this mapping is consistent across all OOBMSM features
(e.g., TPMI, PMT, SDSi), it can be leveraged by multiple drivers. To
facilitate reuse, relocate the struct intel_tpmi_plat_info to intel_vsec.h,
renaming it to struct oobmsm_plat_info, making it accessible to other
features. While modifying headers, place them in alphabetical order.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://lore.kernel.org/r/20250703022832.1302928-11-david.e.box@linux.intel.com
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/plr_tpmi.c              |  3 ++-
 .../x86/intel/speed_select_if/isst_tpmi_core.c     |  9 ++++----
 .../intel/uncore-frequency/uncore-frequency-tpmi.c |  7 +++---
 drivers/platform/x86/intel/vsec_tpmi.c             |  4 ++--
 drivers/powercap/intel_rapl_tpmi.c                 |  9 ++++----
 include/linux/intel_tpmi.h                         | 27 +++-------------------
 include/linux/intel_vsec.h                         | 22 ++++++++++++++++++
 7 files changed, 43 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/intel/plr_tpmi.c b/drivers/platform/x86/intel/plr_tpmi.c
index 2b55347a5a93..58132da47745 100644
--- a/drivers/platform/x86/intel/plr_tpmi.c
+++ b/drivers/platform/x86/intel/plr_tpmi.c
@@ -14,6 +14,7 @@
 #include <linux/err.h>
 #include <linux/gfp_types.h>
 #include <linux/intel_tpmi.h>
+#include <linux/intel_vsec.h>
 #include <linux/io.h>
 #include <linux/iopoll.h>
 #include <linux/kstrtox.h>
@@ -256,7 +257,7 @@ DEFINE_SHOW_STORE_ATTRIBUTE(plr_status);
 
 static int intel_plr_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id)
 {
-	struct intel_tpmi_plat_info *plat_info;
+	struct oobmsm_plat_info *plat_info;
 	struct dentry *dentry;
 	int i, num_resources;
 	struct resource *res;
diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
index 18c035710eb9..34bff2f65a83 100644
--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
@@ -22,6 +22,7 @@
 #include <linux/auxiliary_bus.h>
 #include <linux/delay.h>
 #include <linux/intel_tpmi.h>
+#include <linux/intel_vsec.h>
 #include <linux/fs.h>
 #include <linux/io.h>
 #include <linux/kernel.h>
@@ -1546,7 +1547,7 @@ int tpmi_sst_dev_add(struct auxiliary_device *auxdev)
 {
 	struct tpmi_per_power_domain_info *pd_info;
 	bool read_blocked = 0, write_blocked = 0;
-	struct intel_tpmi_plat_info *plat_info;
+	struct oobmsm_plat_info *plat_info;
 	struct device *dev = &auxdev->dev;
 	struct tpmi_sst_struct *tpmi_sst;
 	u8 i, num_resources, io_die_cnt;
@@ -1698,7 +1699,7 @@ EXPORT_SYMBOL_NS_GPL(tpmi_sst_dev_add, "INTEL_TPMI_SST");
 void tpmi_sst_dev_remove(struct auxiliary_device *auxdev)
 {
 	struct tpmi_sst_struct *tpmi_sst = auxiliary_get_drvdata(auxdev);
-	struct intel_tpmi_plat_info *plat_info;
+	struct oobmsm_plat_info *plat_info;
 
 	plat_info = tpmi_get_platform_data(auxdev);
 	if (!plat_info)
@@ -1720,7 +1721,7 @@ void tpmi_sst_dev_suspend(struct auxiliary_device *auxdev)
 {
 	struct tpmi_sst_struct *tpmi_sst = auxiliary_get_drvdata(auxdev);
 	struct tpmi_per_power_domain_info *power_domain_info;
-	struct intel_tpmi_plat_info *plat_info;
+	struct oobmsm_plat_info *plat_info;
 	void __iomem *cp_base;
 
 	plat_info = tpmi_get_platform_data(auxdev);
@@ -1748,7 +1749,7 @@ void tpmi_sst_dev_resume(struct auxiliary_device *auxdev)
 {
 	struct tpmi_sst_struct *tpmi_sst = auxiliary_get_drvdata(auxdev);
 	struct tpmi_per_power_domain_info *power_domain_info;
-	struct intel_tpmi_plat_info *plat_info;
+	struct oobmsm_plat_info *plat_info;
 	void __iomem *cp_base;
 
 	plat_info = tpmi_get_platform_data(auxdev);
diff --git a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
index 44d9948ed224..6df55c8e16b7 100644
--- a/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
+++ b/drivers/platform/x86/intel/uncore-frequency/uncore-frequency-tpmi.c
@@ -22,9 +22,10 @@
 #include <linux/auxiliary_bus.h>
 #include <linux/bitfield.h>
 #include <linux/bits.h>
+#include <linux/intel_tpmi.h>
+#include <linux/intel_vsec.h>
 #include <linux/io.h>
 #include <linux/module.h>
-#include <linux/intel_tpmi.h>
 
 #include "../tpmi_power_domains.h"
 #include "uncore-frequency-common.h"
@@ -448,7 +449,7 @@ static void remove_cluster_entries(struct tpmi_uncore_struct *tpmi_uncore)
 }
 
 static void set_cdie_id(int domain_id, struct tpmi_uncore_cluster_info *cluster_info,
-		       struct intel_tpmi_plat_info *plat_info)
+			struct oobmsm_plat_info *plat_info)
 {
 
 	cluster_info->cdie_id = domain_id;
@@ -465,7 +466,7 @@ static void set_cdie_id(int domain_id, struct tpmi_uncore_cluster_info *cluster_
 static int uncore_probe(struct auxiliary_device *auxdev, const struct auxiliary_device_id *id)
 {
 	bool read_blocked = 0, write_blocked = 0;
-	struct intel_tpmi_plat_info *plat_info;
+	struct oobmsm_plat_info *plat_info;
 	struct tpmi_uncore_struct *tpmi_uncore;
 	bool uncore_sysfs_added = false;
 	int ret, i, pkg = 0;
diff --git a/drivers/platform/x86/intel/vsec_tpmi.c b/drivers/platform/x86/intel/vsec_tpmi.c
index 5c383a27bbe8..d95a0d994546 100644
--- a/drivers/platform/x86/intel/vsec_tpmi.c
+++ b/drivers/platform/x86/intel/vsec_tpmi.c
@@ -116,7 +116,7 @@ struct intel_tpmi_info {
 	struct intel_vsec_device *vsec_dev;
 	int feature_count;
 	u64 pfs_start;
-	struct intel_tpmi_plat_info plat_info;
+	struct oobmsm_plat_info plat_info;
 	void __iomem *tpmi_control_mem;
 	struct dentry *dbgfs_dir;
 };
@@ -187,7 +187,7 @@ struct tpmi_feature_state {
 /* Used during auxbus device creation */
 static DEFINE_IDA(intel_vsec_tpmi_ida);
 
-struct intel_tpmi_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev)
+struct oobmsm_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev)
 {
 	struct intel_vsec_device *vsec_dev = auxdev_to_ivdev(auxdev);
 
diff --git a/drivers/powercap/intel_rapl_tpmi.c b/drivers/powercap/intel_rapl_tpmi.c
index af2368f4db10..82201bf4685d 100644
--- a/drivers/powercap/intel_rapl_tpmi.c
+++ b/drivers/powercap/intel_rapl_tpmi.c
@@ -9,9 +9,10 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/auxiliary_bus.h>
-#include <linux/io.h>
-#include <linux/intel_tpmi.h>
 #include <linux/intel_rapl.h>
+#include <linux/intel_tpmi.h>
+#include <linux/intel_vsec.h>
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/slab.h>
 
@@ -48,7 +49,7 @@ enum tpmi_rapl_register {
 
 struct tpmi_rapl_package {
 	struct rapl_if_priv priv;
-	struct intel_tpmi_plat_info *tpmi_info;
+	struct oobmsm_plat_info *tpmi_info;
 	struct rapl_package *rp;
 	void __iomem *base;
 	struct list_head node;
@@ -253,7 +254,7 @@ static int intel_rapl_tpmi_probe(struct auxiliary_device *auxdev,
 				 const struct auxiliary_device_id *id)
 {
 	struct tpmi_rapl_package *trp;
-	struct intel_tpmi_plat_info *info;
+	struct oobmsm_plat_info *info;
 	struct resource *res;
 	u32 offset;
 	int ret;
diff --git a/include/linux/intel_tpmi.h b/include/linux/intel_tpmi.h
index ff480b47ae64..94c06bf214fb 100644
--- a/include/linux/intel_tpmi.h
+++ b/include/linux/intel_tpmi.h
@@ -8,6 +8,8 @@
 
 #include <linux/bitfield.h>
 
+struct oobmsm_plat_info;
+
 #define TPMI_VERSION_INVALID	0xff
 #define TPMI_MINOR_VERSION(val)	FIELD_GET(GENMASK(4, 0), val)
 #define TPMI_MAJOR_VERSION(val)	FIELD_GET(GENMASK(7, 5), val)
@@ -26,30 +28,7 @@ enum intel_tpmi_id {
 	TPMI_INFO_ID = 0x81,	/* Special ID for PCI BDF and Package ID information */
 };
 
-/**
- * struct intel_tpmi_plat_info - Platform information for a TPMI device instance
- * @cdie_mask:       Mask of all compute dies in the partition
- * @package_id:      CPU Package id
- * @partition:       Package partition id when multiple VSEC PCI devices per package
- * @segment:         PCI segment ID
- * @bus_number:      PCI bus number
- * @device_number:   PCI device number
- * @function_number: PCI function number
- *
- * Structure to store platform data for a TPMI device instance. This
- * struct is used to return data via tpmi_get_platform_data().
- */
-struct intel_tpmi_plat_info {
-	u16 cdie_mask;
-	u8 package_id;
-	u8 partition;
-	u8 segment;
-	u8 bus_number;
-	u8 device_number;
-	u8 function_number;
-};
-
-struct intel_tpmi_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev);
+struct oobmsm_plat_info *tpmi_get_platform_data(struct auxiliary_device *auxdev);
 struct resource *tpmi_get_resource_at_index(struct auxiliary_device *auxdev, int index);
 int tpmi_get_resource_count(struct auxiliary_device *auxdev);
 int tpmi_get_feature_status(struct auxiliary_device *auxdev, int feature_id, bool *read_blocked,
diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h
index a07796d7d43b..cd78d0b2e623 100644
--- a/include/linux/intel_vsec.h
+++ b/include/linux/intel_vsec.h
@@ -144,6 +144,28 @@ struct intel_vsec_device {
 	unsigned long cap_id;
 };
 
+/**
+ * struct oobmsm_plat_info - Platform information for a device instance
+ * @cdie_mask:       Mask of all compute dies in the partition
+ * @package_id:      CPU Package id
+ * @partition:       Package partition id when multiple VSEC PCI devices per package
+ * @segment:         PCI segment ID
+ * @bus_number:      PCI bus number
+ * @device_number:   PCI device number
+ * @function_number: PCI function number
+ *
+ * Structure to store platform data for a OOBMSM device instance.
+ */
+struct oobmsm_plat_info {
+	u16 cdie_mask;
+	u8 package_id;
+	u8 partition;
+	u8 segment;
+	u8 bus_number;
+	u8 device_number;
+	u8 function_number;
+};
+
 int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
 		       struct intel_vsec_device *intel_vsec_dev,
 		       const char *name);
-- 
cgit v1.2.3


From a885a2780937afac4f31f00d11663f50d05dfb35 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 2 Jul 2025 19:28:26 -0700
Subject: platform/x86/intel/vsec: Set OOBMSM to CPU mapping
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add functions, intel_vsec_set/get_mapping(), to set and retrieve the
OOBMSM-to-CPU mapping data in the private data of the parent Intel VSEC
driver. With this mapping information available, other Intel VSEC features
on the same OOBMSM device can easily access and use the mapping data,
allowing each of the OOBMSM features to map to the CPUs they provides data
for.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20250703022832.1302928-12-david.e.box@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/vsec.c | 31 +++++++++++++++++++++++++++++++
 include/linux/intel_vsec.h        | 12 ++++++++++++
 2 files changed, 43 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/intel/vsec.c b/drivers/platform/x86/intel/vsec.c
index 4d76f1ac3c8c..711ff4edfe21 100644
--- a/drivers/platform/x86/intel/vsec.c
+++ b/drivers/platform/x86/intel/vsec.c
@@ -44,6 +44,7 @@ enum vsec_device_state {
 struct vsec_priv {
 	struct intel_vsec_platform_info *info;
 	struct device *suppliers[VSEC_FEATURE_COUNT];
+	struct oobmsm_plat_info plat_info;
 	enum vsec_device_state state[VSEC_FEATURE_COUNT];
 	unsigned long found_caps;
 };
@@ -665,6 +666,36 @@ static int intel_vsec_pci_probe(struct pci_dev *pdev, const struct pci_device_id
 	return 0;
 }
 
+int intel_vsec_set_mapping(struct oobmsm_plat_info *plat_info,
+			   struct intel_vsec_device *vsec_dev)
+{
+	struct vsec_priv *priv;
+
+	priv = pci_get_drvdata(vsec_dev->pcidev);
+	if (!priv)
+		return -EINVAL;
+
+	priv->plat_info = *plat_info;
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(intel_vsec_set_mapping, "INTEL_VSEC");
+
+struct oobmsm_plat_info *intel_vsec_get_mapping(struct pci_dev *pdev)
+{
+	struct vsec_priv *priv;
+
+	if (!pci_match_id(intel_vsec_pci_ids, pdev))
+		return ERR_PTR(-EINVAL);
+
+	priv = pci_get_drvdata(pdev);
+	if (!priv)
+		return ERR_PTR(-EINVAL);
+
+	return &priv->plat_info;
+}
+EXPORT_SYMBOL_NS_GPL(intel_vsec_get_mapping, "INTEL_VSEC");
+
 /* DG1 info */
 static struct intel_vsec_header dg1_header = {
 	.length = 0x10,
diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h
index cd78d0b2e623..4bd0c6e7857c 100644
--- a/include/linux/intel_vsec.h
+++ b/include/linux/intel_vsec.h
@@ -183,11 +183,23 @@ static inline struct intel_vsec_device *auxdev_to_ivdev(struct auxiliary_device
 #if IS_ENABLED(CONFIG_INTEL_VSEC)
 int intel_vsec_register(struct pci_dev *pdev,
 			 struct intel_vsec_platform_info *info);
+int intel_vsec_set_mapping(struct oobmsm_plat_info *plat_info,
+			   struct intel_vsec_device *vsec_dev);
+struct oobmsm_plat_info *intel_vsec_get_mapping(struct pci_dev *pdev);
 #else
 static inline int intel_vsec_register(struct pci_dev *pdev,
 				       struct intel_vsec_platform_info *info)
 {
 	return -ENODEV;
 }
+static inline int intel_vsec_set_mapping(struct oobmsm_plat_info *plat_info,
+					 struct intel_vsec_device *vsec_dev)
+{
+	return -ENODEV;
+}
+static inline struct oobmsm_plat_info *intel_vsec_get_mapping(struct pci_dev *pdev)
+{
+	return ERR_PTR(-ENODEV);
+}
 #endif
 #endif
-- 
cgit v1.2.3


From 86fc85c75bcd9b0f28afadd60c9f890669b42ba4 Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 2 Jul 2025 19:28:28 -0700
Subject: platform/x86/intel/pmt/discovery: Get telemetry attributes
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add intel_pmt_get_features() in PMT Discovery to enable the PMT Telemetry
driver to obtain attributes of the aggregated telemetry spaces it
enumerates. The function gathers feature flags and associated data (like
the number of RMIDs) from each PMT entry, laying the groundwork for a
future kernel interface that will allow direct access to telemetry regions
based on their capabilities.

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20250703022832.1302928-14-david.e.box@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/pmt/Kconfig     |  1 +
 drivers/platform/x86/intel/pmt/class.h     |  7 +++++++
 drivers/platform/x86/intel/pmt/discovery.c | 33 ++++++++++++++++++++++++++++++
 drivers/platform/x86/intel/pmt/telemetry.c |  5 +++++
 include/linux/intel_vsec.h                 | 16 +++++++++++++++
 5 files changed, 62 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/intel/pmt/Kconfig b/drivers/platform/x86/intel/pmt/Kconfig
index 0ad91b5112e9..83ae17eab462 100644
--- a/drivers/platform/x86/intel/pmt/Kconfig
+++ b/drivers/platform/x86/intel/pmt/Kconfig
@@ -18,6 +18,7 @@ config INTEL_PMT_CLASS
 config INTEL_PMT_TELEMETRY
 	tristate "Intel Platform Monitoring Technology (PMT) Telemetry driver"
 	depends on INTEL_VSEC
+	select INTEL_PMT_DISCOVERY
 	select INTEL_PMT_CLASS
 	help
 	  The Intel Platform Monitory Technology (PMT) Telemetry driver provides
diff --git a/drivers/platform/x86/intel/pmt/class.h b/drivers/platform/x86/intel/pmt/class.h
index 39c32357ee2c..fdf7e79d8c0d 100644
--- a/drivers/platform/x86/intel/pmt/class.h
+++ b/drivers/platform/x86/intel/pmt/class.h
@@ -48,6 +48,7 @@ struct intel_pmt_entry {
 	struct pmt_callbacks	*cb;
 	unsigned long		base_addr;
 	size_t			size;
+	u64			feature_flags;
 	u32			guid;
 	u32			num_rmids; /* Number of Resource Monitoring IDs */
 	int			devid;
@@ -71,4 +72,10 @@ int intel_pmt_dev_create(struct intel_pmt_entry *entry,
 			 struct intel_vsec_device *dev, int idx);
 void intel_pmt_dev_destroy(struct intel_pmt_entry *entry,
 			   struct intel_pmt_namespace *ns);
+#if IS_ENABLED(CONFIG_INTEL_PMT_DISCOVERY)
+void intel_pmt_get_features(struct intel_pmt_entry *entry);
+#else
+static inline void intel_pmt_get_features(struct intel_pmt_entry *entry) {}
+#endif
+
 #endif
diff --git a/drivers/platform/x86/intel/pmt/discovery.c b/drivers/platform/x86/intel/pmt/discovery.c
index 4b4fa3137ad2..e72d43b675b4 100644
--- a/drivers/platform/x86/intel/pmt/discovery.c
+++ b/drivers/platform/x86/intel/pmt/discovery.c
@@ -583,6 +583,39 @@ abort_probe:
 	return ret;
 }
 
+static void pmt_get_features(struct intel_pmt_entry *entry, struct feature *f)
+{
+	int num_guids = f->table.header.num_guids;
+	int i;
+
+	for (i = 0; i < num_guids; i++) {
+		if (f->table.guids[i] != entry->guid)
+			continue;
+
+		entry->feature_flags |= BIT(f->id);
+
+		if (feature_layout[f->id] == LAYOUT_RMID)
+			entry->num_rmids = f->table.rmid.num_rmids;
+		else
+			entry->num_rmids = 0; /* entry is kzalloc but set anyway */
+	}
+}
+
+void intel_pmt_get_features(struct intel_pmt_entry *entry)
+{
+	struct feature *feature;
+
+	mutex_lock(&feature_list_lock);
+	list_for_each_entry(feature, &pmt_feature_list, list) {
+		if (feature->priv->parent != &entry->ep->pcidev->dev)
+			continue;
+
+		pmt_get_features(entry, feature);
+	}
+	mutex_unlock(&feature_list_lock);
+}
+EXPORT_SYMBOL_NS_GPL(intel_pmt_get_features, "INTEL_PMT");
+
 static const struct auxiliary_device_id pmt_features_id_table[] = {
 	{ .name = "intel_vsec.discovery" },
 	{}
diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c
index ac3a9bdf5601..58d06749e417 100644
--- a/drivers/platform/x86/intel/pmt/telemetry.c
+++ b/drivers/platform/x86/intel/pmt/telemetry.c
@@ -9,11 +9,14 @@
  */
 
 #include <linux/auxiliary_bus.h>
+#include <linux/intel_pmt_features.h>
 #include <linux/intel_vsec.h>
 #include <linux/kernel.h>
+#include <linux/kref.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
+#include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/overflow.h>
 
@@ -311,6 +314,8 @@ static int pmt_telem_probe(struct auxiliary_device *auxdev, const struct auxilia
 			continue;
 
 		priv->num_entries++;
+
+		intel_pmt_get_features(entry);
 	}
 
 	return 0;
diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h
index 4bd0c6e7857c..f185e9c01c90 100644
--- a/include/linux/intel_vsec.h
+++ b/include/linux/intel_vsec.h
@@ -4,6 +4,7 @@
 
 #include <linux/auxiliary_bus.h>
 #include <linux/bits.h>
+#include <linux/intel_pmt_features.h>
 
 /*
  * VSEC_CAP_UNUSED is reserved. It exists to prevent zero initialized
@@ -166,6 +167,21 @@ struct oobmsm_plat_info {
 	u8 function_number;
 };
 
+struct telemetry_region {
+	struct oobmsm_plat_info	plat_info;
+	void __iomem		*addr;
+	size_t			size;
+	u32			guid;
+	u32			num_rmids;
+};
+
+struct pmt_feature_group {
+	enum pmt_feature_id	id;
+	int			count;
+	struct kref		kref;
+	struct telemetry_region	regions[];
+};
+
 int intel_vsec_add_aux(struct pci_dev *pdev, struct device *parent,
 		       struct intel_vsec_device *intel_vsec_dev,
 		       const char *name);
-- 
cgit v1.2.3


From 42dabe5442887946b16e64c6ebe91d2671a96fbb Mon Sep 17 00:00:00 2001
From: "David E. Box" <david.e.box@linux.intel.com>
Date: Wed, 2 Jul 2025 19:28:29 -0700
Subject: platform/x86/intel/pmt/telemetry: Add API to retrieve telemetry
 regions by feature
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce a new API, intel_pmt_get_regions_by_feature(), that gathers
telemetry regions based on a provided capability flag. This API enables
retrieval of regions with various capabilities (for example, RMID-based
telemetry) and provides a unified interface for accessing them. Resource
management is handled via reference counting using
intel_pmt_put_feature_group().

Signed-off-by: David E. Box <david.e.box@linux.intel.com>
Link: https://lore.kernel.org/r/20250703022832.1302928-15-david.e.box@linux.intel.com
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/platform/x86/intel/pmt/telemetry.c | 89 +++++++++++++++++++++++++++++-
 include/linux/intel_vsec.h                 | 18 ++++++
 2 files changed, 106 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/platform/x86/intel/pmt/telemetry.c b/drivers/platform/x86/intel/pmt/telemetry.c
index 58d06749e417..a4dfca6cac19 100644
--- a/drivers/platform/x86/intel/pmt/telemetry.c
+++ b/drivers/platform/x86/intel/pmt/telemetry.c
@@ -9,16 +9,21 @@
  */
 
 #include <linux/auxiliary_bus.h>
+#include <linux/bitops.h>
+#include <linux/cleanup.h>
+#include <linux/err.h>
 #include <linux/intel_pmt_features.h>
 #include <linux/intel_vsec.h>
 #include <linux/kernel.h>
 #include <linux/kref.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/overflow.h>
 #include <linux/pci.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/uaccess.h>
-#include <linux/overflow.h>
+#include <linux/xarray.h>
 
 #include "class.h"
 
@@ -209,6 +214,87 @@ unlock:
 }
 EXPORT_SYMBOL_NS_GPL(pmt_telem_get_endpoint_info, "INTEL_PMT_TELEMETRY");
 
+static int pmt_copy_region(struct telemetry_region *region,
+			   struct intel_pmt_entry *entry)
+{
+
+	struct oobmsm_plat_info *plat_info;
+
+	plat_info = intel_vsec_get_mapping(entry->ep->pcidev);
+	if (IS_ERR(plat_info))
+		return PTR_ERR(plat_info);
+
+	region->plat_info = *plat_info;
+	region->guid = entry->guid;
+	region->addr = entry->ep->base;
+	region->size = entry->size;
+	region->num_rmids = entry->num_rmids;
+
+	return 0;
+}
+
+static void pmt_feature_group_release(struct kref *kref)
+{
+	struct pmt_feature_group *feature_group;
+
+	feature_group = container_of(kref, struct pmt_feature_group, kref);
+	kfree(feature_group);
+}
+
+struct pmt_feature_group *intel_pmt_get_regions_by_feature(enum pmt_feature_id id)
+{
+	struct pmt_feature_group *feature_group __free(kfree) = NULL;
+	struct telemetry_region *region;
+	struct intel_pmt_entry *entry;
+	unsigned long idx;
+	int count = 0;
+	size_t size;
+
+	if (!pmt_feature_id_is_valid(id))
+		return ERR_PTR(-EINVAL);
+
+	guard(mutex)(&ep_lock);
+	xa_for_each(&telem_array, idx, entry) {
+		if (entry->feature_flags & BIT(id))
+			count++;
+	}
+
+	if (!count)
+		return ERR_PTR(-ENOENT);
+
+	size = struct_size(feature_group, regions, count);
+	feature_group = kzalloc(size, GFP_KERNEL);
+	if (!feature_group)
+		return ERR_PTR(-ENOMEM);
+
+	feature_group->count = count;
+
+	region = feature_group->regions;
+	xa_for_each(&telem_array, idx, entry) {
+		int ret;
+
+		if (!(entry->feature_flags & BIT(id)))
+			continue;
+
+		ret = pmt_copy_region(region, entry);
+		if (ret)
+			return ERR_PTR(ret);
+
+		region++;
+	}
+
+	kref_init(&feature_group->kref);
+
+	return no_free_ptr(feature_group);
+}
+EXPORT_SYMBOL(intel_pmt_get_regions_by_feature);
+
+void intel_pmt_put_feature_group(struct pmt_feature_group *feature_group)
+{
+	kref_put(&feature_group->kref, pmt_feature_group_release);
+}
+EXPORT_SYMBOL(intel_pmt_put_feature_group);
+
 int pmt_telem_read(struct telem_endpoint *ep, u32 id, u64 *data, u32 count)
 {
 	u32 offset, size;
@@ -353,3 +439,4 @@ MODULE_AUTHOR("David E. Box <david.e.box@linux.intel.com>");
 MODULE_DESCRIPTION("Intel PMT Telemetry driver");
 MODULE_LICENSE("GPL v2");
 MODULE_IMPORT_NS("INTEL_PMT");
+MODULE_IMPORT_NS("INTEL_VSEC");
diff --git a/include/linux/intel_vsec.h b/include/linux/intel_vsec.h
index f185e9c01c90..53f6fe88e369 100644
--- a/include/linux/intel_vsec.h
+++ b/include/linux/intel_vsec.h
@@ -4,6 +4,7 @@
 
 #include <linux/auxiliary_bus.h>
 #include <linux/bits.h>
+#include <linux/err.h>
 #include <linux/intel_pmt_features.h>
 
 /*
@@ -218,4 +219,21 @@ static inline struct oobmsm_plat_info *intel_vsec_get_mapping(struct pci_dev *pd
 	return ERR_PTR(-ENODEV);
 }
 #endif
+
+#if IS_ENABLED(CONFIG_INTEL_PMT_TELEMETRY)
+struct pmt_feature_group *
+intel_pmt_get_regions_by_feature(enum pmt_feature_id id);
+
+void intel_pmt_put_feature_group(struct pmt_feature_group *feature_group);
+#else
+static inline struct pmt_feature_group *
+intel_pmt_get_regions_by_feature(enum pmt_feature_id id)
+{
+	return ERR_PTR(-ENODEV);
+}
+
+static inline void
+intel_pmt_put_feature_group(struct pmt_feature_group *feature_group) {}
+#endif
+
 #endif
-- 
cgit v1.2.3


From fd72f265bb00d2dd2a3bbad7ec45520025e3a926 Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Thu, 22 May 2025 16:52:23 +0200
Subject: netfilter: conntrack: remove DCCP protocol support

The DCCP socket family has now been removed from this tree, see:

  8bb3212be4b4 ("Merge branch 'net-retire-dccp-socket'")

Remove connection tracking and NAT support for this protocol, this
should not pose a problem because no DCCP traffic is expected to be seen
on the wire.

As for the code for matching on dccp header for iptables and nftables,
mark it as deprecated and keep it in place. Ruleset restoration is an
atomic operation. Without dccp matching support, an astray match on dccp
could break this operation leaving your computer with no policy in
place, so let's follow a more conservative approach for matches.

Add CONFIG_NFT_EXTHDR_DCCP which is set to 'n' by default to deprecate
dccp extension support. Similarly, label CONFIG_NETFILTER_XT_MATCH_DCCP
as deprecated too and also set it to 'n' by default.

Code to match on DCCP protocol from ebtables also remains in place, this
is just a few checks on IPPROTO_DCCP from _check() path which is
exercised when ruleset is loaded. There is another use of IPPROTO_DCCP
from the _check() path in the iptables multiport match. Another check
for IPPROTO_DCCP from the packet in the reject target is also removed.

So let's schedule removal of the dccp matching for a second stage, this
should not interfer with the dccp retirement since this is only matching
on the dccp header.

Cc: "David S. Miller" <davem@davemloft.net>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Paolo Abeni <pabeni@redhat.com>
Cc: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 Documentation/networking/nf_conntrack-sysctl.rst |   1 -
 arch/arm/configs/omap2plus_defconfig             |   1 -
 arch/loongarch/configs/loongson3_defconfig       |   1 -
 arch/m68k/configs/amiga_defconfig                |   1 -
 arch/m68k/configs/apollo_defconfig               |   1 -
 arch/m68k/configs/atari_defconfig                |   1 -
 arch/m68k/configs/bvme6000_defconfig             |   1 -
 arch/m68k/configs/hp300_defconfig                |   1 -
 arch/m68k/configs/mac_defconfig                  |   1 -
 arch/m68k/configs/multi_defconfig                |   1 -
 arch/m68k/configs/mvme147_defconfig              |   1 -
 arch/m68k/configs/mvme16x_defconfig              |   1 -
 arch/m68k/configs/q40_defconfig                  |   1 -
 arch/m68k/configs/sun3_defconfig                 |   1 -
 arch/m68k/configs/sun3x_defconfig                |   1 -
 arch/mips/configs/fuloong2e_defconfig            |   1 -
 arch/mips/configs/ip22_defconfig                 |   1 -
 arch/mips/configs/loongson2k_defconfig           |   1 -
 arch/mips/configs/loongson3_defconfig            |   1 -
 arch/mips/configs/malta_defconfig                |   1 -
 arch/mips/configs/malta_kvm_defconfig            |   1 -
 arch/mips/configs/maltaup_xpa_defconfig          |   1 -
 arch/mips/configs/rb532_defconfig                |   1 -
 arch/mips/configs/rm200_defconfig                |   1 -
 arch/powerpc/configs/cell_defconfig              |   1 -
 arch/s390/configs/debug_defconfig                |   1 -
 arch/s390/configs/defconfig                      |   1 -
 arch/sh/configs/titan_defconfig                  |   1 -
 include/linux/netfilter/nf_conntrack_dccp.h      |  38 --
 include/net/netfilter/ipv4/nf_conntrack_ipv4.h   |   3 -
 include/net/netfilter/nf_conntrack.h             |   2 -
 include/net/netfilter/nf_conntrack_l4proto.h     |  13 -
 include/net/netfilter/nf_reject.h                |   1 -
 include/net/netns/conntrack.h                    |  13 -
 net/netfilter/Kconfig                            |  20 +-
 net/netfilter/Makefile                           |   1 -
 net/netfilter/nf_conntrack_core.c                |   8 -
 net/netfilter/nf_conntrack_netlink.c             |   1 -
 net/netfilter/nf_conntrack_proto.c               |   6 -
 net/netfilter/nf_conntrack_proto_dccp.c          | 826 -----------------------
 net/netfilter/nf_conntrack_standalone.c          |  92 ---
 net/netfilter/nf_nat_core.c                      |   6 -
 net/netfilter/nf_nat_proto.c                     |  43 --
 net/netfilter/nfnetlink_cttimeout.c              |   5 -
 net/netfilter/nft_exthdr.c                       |   8 +
 45 files changed, 16 insertions(+), 1098 deletions(-)
 delete mode 100644 include/linux/netfilter/nf_conntrack_dccp.h
 delete mode 100644 net/netfilter/nf_conntrack_proto_dccp.c

(limited to 'include/linux')

diff --git a/Documentation/networking/nf_conntrack-sysctl.rst b/Documentation/networking/nf_conntrack-sysctl.rst
index 238b66d0e059..35f889259fcd 100644
--- a/Documentation/networking/nf_conntrack-sysctl.rst
+++ b/Documentation/networking/nf_conntrack-sysctl.rst
@@ -85,7 +85,6 @@ nf_conntrack_log_invalid - INTEGER
 	- 1   - log ICMP packets
 	- 6   - log TCP packets
 	- 17  - log UDP packets
-	- 33  - log DCCP packets
 	- 41  - log ICMPv6 packets
 	- 136 - log UDPLITE packets
 	- 255 - log packets of any protocol
diff --git a/arch/arm/configs/omap2plus_defconfig b/arch/arm/configs/omap2plus_defconfig
index 9f9780c8e62a..fee43d156622 100644
--- a/arch/arm/configs/omap2plus_defconfig
+++ b/arch/arm/configs/omap2plus_defconfig
@@ -142,7 +142,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
 CONFIG_NETFILTER_XT_MATCH_CPU=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
diff --git a/arch/loongarch/configs/loongson3_defconfig b/arch/loongarch/configs/loongson3_defconfig
index 0d59af6007b7..68e337aed2bb 100644
--- a/arch/loongarch/configs/loongson3_defconfig
+++ b/arch/loongarch/configs/loongson3_defconfig
@@ -225,7 +225,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
 CONFIG_NETFILTER_XT_MATCH_CPU=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
diff --git a/arch/m68k/configs/amiga_defconfig b/arch/m68k/configs/amiga_defconfig
index d05690289e33..83eab331872f 100644
--- a/arch/m68k/configs/amiga_defconfig
+++ b/arch/m68k/configs/amiga_defconfig
@@ -85,7 +85,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/apollo_defconfig b/arch/m68k/configs/apollo_defconfig
index a1747fbe23fb..0e5de7edd544 100644
--- a/arch/m68k/configs/apollo_defconfig
+++ b/arch/m68k/configs/apollo_defconfig
@@ -81,7 +81,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/atari_defconfig b/arch/m68k/configs/atari_defconfig
index 74293551f66b..35fc466095f4 100644
--- a/arch/m68k/configs/atari_defconfig
+++ b/arch/m68k/configs/atari_defconfig
@@ -88,7 +88,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/bvme6000_defconfig b/arch/m68k/configs/bvme6000_defconfig
index 419b13ae950a..53b7844cf301 100644
--- a/arch/m68k/configs/bvme6000_defconfig
+++ b/arch/m68k/configs/bvme6000_defconfig
@@ -78,7 +78,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/hp300_defconfig b/arch/m68k/configs/hp300_defconfig
index 4c81d756587c..560fdf3ed106 100644
--- a/arch/m68k/configs/hp300_defconfig
+++ b/arch/m68k/configs/hp300_defconfig
@@ -80,7 +80,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/mac_defconfig b/arch/m68k/configs/mac_defconfig
index daa01d7fb462..2e28e54b52f8 100644
--- a/arch/m68k/configs/mac_defconfig
+++ b/arch/m68k/configs/mac_defconfig
@@ -79,7 +79,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/multi_defconfig b/arch/m68k/configs/multi_defconfig
index 641ca22eb3b2..f5f6b8e65c26 100644
--- a/arch/m68k/configs/multi_defconfig
+++ b/arch/m68k/configs/multi_defconfig
@@ -99,7 +99,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/mvme147_defconfig b/arch/m68k/configs/mvme147_defconfig
index f98ffa7a1640..36bbf98d6aa4 100644
--- a/arch/m68k/configs/mvme147_defconfig
+++ b/arch/m68k/configs/mvme147_defconfig
@@ -77,7 +77,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/mvme16x_defconfig b/arch/m68k/configs/mvme16x_defconfig
index 2bfc3f4b48f9..e247bff8f1a4 100644
--- a/arch/m68k/configs/mvme16x_defconfig
+++ b/arch/m68k/configs/mvme16x_defconfig
@@ -78,7 +78,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/q40_defconfig b/arch/m68k/configs/q40_defconfig
index 2bd46cbcca2a..27aa4eb5d3f4 100644
--- a/arch/m68k/configs/q40_defconfig
+++ b/arch/m68k/configs/q40_defconfig
@@ -79,7 +79,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/sun3_defconfig b/arch/m68k/configs/sun3_defconfig
index dc7fc94fc669..b338f2043d97 100644
--- a/arch/m68k/configs/sun3_defconfig
+++ b/arch/m68k/configs/sun3_defconfig
@@ -74,7 +74,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/m68k/configs/sun3x_defconfig b/arch/m68k/configs/sun3x_defconfig
index b026a54867f5..87ee47da4e31 100644
--- a/arch/m68k/configs/sun3x_defconfig
+++ b/arch/m68k/configs/sun3x_defconfig
@@ -75,7 +75,6 @@ CONFIG_NETFILTER=y
 CONFIG_NETFILTER_NETLINK_HOOK=m
 CONFIG_NF_CONNTRACK=m
 CONFIG_NF_CONNTRACK_ZONES=y
-# CONFIG_NF_CT_PROTO_DCCP is not set
 CONFIG_NF_CONNTRACK_AMANDA=m
 CONFIG_NF_CONNTRACK_FTP=m
 CONFIG_NF_CONNTRACK_H323=m
diff --git a/arch/mips/configs/fuloong2e_defconfig b/arch/mips/configs/fuloong2e_defconfig
index 114fcd67898d..cdedbb8a8f53 100644
--- a/arch/mips/configs/fuloong2e_defconfig
+++ b/arch/mips/configs/fuloong2e_defconfig
@@ -44,7 +44,6 @@ CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_IPRANGE=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
diff --git a/arch/mips/configs/ip22_defconfig b/arch/mips/configs/ip22_defconfig
index f1a8ccf2c459..2decf8b98d31 100644
--- a/arch/mips/configs/ip22_defconfig
+++ b/arch/mips/configs/ip22_defconfig
@@ -79,7 +79,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
 CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
diff --git a/arch/mips/configs/loongson2k_defconfig b/arch/mips/configs/loongson2k_defconfig
index 4b7f914d01d0..6aea6a5b1b66 100644
--- a/arch/mips/configs/loongson2k_defconfig
+++ b/arch/mips/configs/loongson2k_defconfig
@@ -52,7 +52,6 @@ CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
diff --git a/arch/mips/configs/loongson3_defconfig b/arch/mips/configs/loongson3_defconfig
index 98844b457b7f..43a72c410538 100644
--- a/arch/mips/configs/loongson3_defconfig
+++ b/arch/mips/configs/loongson3_defconfig
@@ -72,7 +72,6 @@ CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
diff --git a/arch/mips/configs/malta_defconfig b/arch/mips/configs/malta_defconfig
index 869a14b3184f..9fcbac829920 100644
--- a/arch/mips/configs/malta_defconfig
+++ b/arch/mips/configs/malta_defconfig
@@ -80,7 +80,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
 CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
diff --git a/arch/mips/configs/malta_kvm_defconfig b/arch/mips/configs/malta_kvm_defconfig
index 41e1fea303ea..19102386a81c 100644
--- a/arch/mips/configs/malta_kvm_defconfig
+++ b/arch/mips/configs/malta_kvm_defconfig
@@ -84,7 +84,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
 CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
diff --git a/arch/mips/configs/maltaup_xpa_defconfig b/arch/mips/configs/maltaup_xpa_defconfig
index 13ff1877e26e..1dd07c9d1812 100644
--- a/arch/mips/configs/maltaup_xpa_defconfig
+++ b/arch/mips/configs/maltaup_xpa_defconfig
@@ -82,7 +82,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
 CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_HELPER=m
diff --git a/arch/mips/configs/rb532_defconfig b/arch/mips/configs/rb532_defconfig
index 9fb114ef5e2d..30d18b084cda 100644
--- a/arch/mips/configs/rb532_defconfig
+++ b/arch/mips/configs/rb532_defconfig
@@ -56,7 +56,6 @@ CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_TRACE=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=y
 CONFIG_NETFILTER_XT_MATCH_MULTIPORT=y
diff --git a/arch/mips/configs/rm200_defconfig b/arch/mips/configs/rm200_defconfig
index 7b5a5591ccc9..39a2419e1f3e 100644
--- a/arch/mips/configs/rm200_defconfig
+++ b/arch/mips/configs/rm200_defconfig
@@ -64,7 +64,6 @@ CONFIG_NETFILTER_XT_MATCH_COMMENT=m
 CONFIG_NETFILTER_XT_MATCH_CONNBYTES=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
diff --git a/arch/powerpc/configs/cell_defconfig b/arch/powerpc/configs/cell_defconfig
index 3347192b77b8..7a31b52e92e1 100644
--- a/arch/powerpc/configs/cell_defconfig
+++ b/arch/powerpc/configs/cell_defconfig
@@ -62,7 +62,6 @@ CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_TARGET_TCPMSS=m
 CONFIG_NETFILTER_XT_TARGET_TCPOPTSTRIP=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_HASHLIMIT=m
diff --git a/arch/s390/configs/debug_defconfig b/arch/s390/configs/debug_defconfig
index 8ecad727497e..0808a3718298 100644
--- a/arch/s390/configs/debug_defconfig
+++ b/arch/s390/configs/debug_defconfig
@@ -248,7 +248,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
 CONFIG_NETFILTER_XT_MATCH_CPU=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
diff --git a/arch/s390/configs/defconfig b/arch/s390/configs/defconfig
index c13a77765162..6118e3105adb 100644
--- a/arch/s390/configs/defconfig
+++ b/arch/s390/configs/defconfig
@@ -239,7 +239,6 @@ CONFIG_NETFILTER_XT_MATCH_CONNLIMIT=m
 CONFIG_NETFILTER_XT_MATCH_CONNMARK=m
 CONFIG_NETFILTER_XT_MATCH_CONNTRACK=m
 CONFIG_NETFILTER_XT_MATCH_CPU=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_DEVGROUP=m
 CONFIG_NETFILTER_XT_MATCH_DSCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
diff --git a/arch/sh/configs/titan_defconfig b/arch/sh/configs/titan_defconfig
index f022ada363b5..8ef72b8dbcd3 100644
--- a/arch/sh/configs/titan_defconfig
+++ b/arch/sh/configs/titan_defconfig
@@ -61,7 +61,6 @@ CONFIG_NETFILTER_XT_TARGET_CLASSIFY=m
 CONFIG_NETFILTER_XT_TARGET_MARK=m
 CONFIG_NETFILTER_XT_TARGET_NFQUEUE=m
 CONFIG_NETFILTER_XT_MATCH_COMMENT=m
-CONFIG_NETFILTER_XT_MATCH_DCCP=m
 CONFIG_NETFILTER_XT_MATCH_ESP=m
 CONFIG_NETFILTER_XT_MATCH_LENGTH=m
 CONFIG_NETFILTER_XT_MATCH_LIMIT=m
diff --git a/include/linux/netfilter/nf_conntrack_dccp.h b/include/linux/netfilter/nf_conntrack_dccp.h
deleted file mode 100644
index c509ed76e714..000000000000
--- a/include/linux/netfilter/nf_conntrack_dccp.h
+++ /dev/null
@@ -1,38 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _NF_CONNTRACK_DCCP_H
-#define _NF_CONNTRACK_DCCP_H
-
-/* Exposed to userspace over nfnetlink */
-enum ct_dccp_states {
-	CT_DCCP_NONE,
-	CT_DCCP_REQUEST,
-	CT_DCCP_RESPOND,
-	CT_DCCP_PARTOPEN,
-	CT_DCCP_OPEN,
-	CT_DCCP_CLOSEREQ,
-	CT_DCCP_CLOSING,
-	CT_DCCP_TIMEWAIT,
-	CT_DCCP_IGNORE,
-	CT_DCCP_INVALID,
-	__CT_DCCP_MAX
-};
-#define CT_DCCP_MAX		(__CT_DCCP_MAX - 1)
-
-enum ct_dccp_roles {
-	CT_DCCP_ROLE_CLIENT,
-	CT_DCCP_ROLE_SERVER,
-	__CT_DCCP_ROLE_MAX
-};
-#define CT_DCCP_ROLE_MAX	(__CT_DCCP_ROLE_MAX - 1)
-
-#include <linux/netfilter/nf_conntrack_tuple_common.h>
-
-struct nf_ct_dccp {
-	u_int8_t	role[IP_CT_DIR_MAX];
-	u_int8_t	state;
-	u_int8_t	last_pkt;
-	u_int8_t	last_dir;
-	u_int64_t	handshake_seq;
-};
-
-#endif /* _NF_CONNTRACK_DCCP_H */
diff --git a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
index 2c8c2b023848..8d65ffbf57de 100644
--- a/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
+++ b/include/net/netfilter/ipv4/nf_conntrack_ipv4.h
@@ -13,9 +13,6 @@
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp;
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp;
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp;
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp;
-#endif
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 extern const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp;
 #endif
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index 3f02a45773e8..a844aa46d076 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -18,7 +18,6 @@
 
 #include <linux/netfilter/nf_conntrack_common.h>
 #include <linux/netfilter/nf_conntrack_tcp.h>
-#include <linux/netfilter/nf_conntrack_dccp.h>
 #include <linux/netfilter/nf_conntrack_sctp.h>
 #include <linux/netfilter/nf_conntrack_proto_gre.h>
 
@@ -31,7 +30,6 @@ struct nf_ct_udp {
 /* per conntrack: protocol private data */
 union nf_conntrack_proto {
 	/* insert conntrack proto private data here */
-	struct nf_ct_dccp dccp;
 	struct ip_ct_sctp sctp;
 	struct ip_ct_tcp tcp;
 	struct nf_ct_udp udp;
diff --git a/include/net/netfilter/nf_conntrack_l4proto.h b/include/net/netfilter/nf_conntrack_l4proto.h
index 1f47bef51722..6929f8daf1ed 100644
--- a/include/net/netfilter/nf_conntrack_l4proto.h
+++ b/include/net/netfilter/nf_conntrack_l4proto.h
@@ -117,11 +117,6 @@ int nf_conntrack_tcp_packet(struct nf_conn *ct,
 			    unsigned int dataoff,
 			    enum ip_conntrack_info ctinfo,
 			    const struct nf_hook_state *state);
-int nf_conntrack_dccp_packet(struct nf_conn *ct,
-			     struct sk_buff *skb,
-			     unsigned int dataoff,
-			     enum ip_conntrack_info ctinfo,
-			     const struct nf_hook_state *state);
 int nf_conntrack_sctp_packet(struct nf_conn *ct,
 			     struct sk_buff *skb,
 			     unsigned int dataoff,
@@ -137,7 +132,6 @@ void nf_conntrack_generic_init_net(struct net *net);
 void nf_conntrack_tcp_init_net(struct net *net);
 void nf_conntrack_udp_init_net(struct net *net);
 void nf_conntrack_gre_init_net(struct net *net);
-void nf_conntrack_dccp_init_net(struct net *net);
 void nf_conntrack_sctp_init_net(struct net *net);
 void nf_conntrack_icmp_init_net(struct net *net);
 void nf_conntrack_icmpv6_init_net(struct net *net);
@@ -223,13 +217,6 @@ static inline bool nf_conntrack_tcp_established(const struct nf_conn *ct)
 }
 #endif
 
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-static inline struct nf_dccp_net *nf_dccp_pernet(struct net *net)
-{
-	return &net->ct.nf_ct_proto.dccp;
-}
-#endif
-
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 static inline struct nf_sctp_net *nf_sctp_pernet(struct net *net)
 {
diff --git a/include/net/netfilter/nf_reject.h b/include/net/netfilter/nf_reject.h
index 7c669792fb9c..f1db33bc6bf8 100644
--- a/include/net/netfilter/nf_reject.h
+++ b/include/net/netfilter/nf_reject.h
@@ -34,7 +34,6 @@ static inline bool nf_reject_verify_csum(struct sk_buff *skb, int dataoff,
 
 		/* Protocols with partial checksums. */
 		case IPPROTO_UDPLITE:
-		case IPPROTO_DCCP:
 			return false;
 	}
 	return true;
diff --git a/include/net/netns/conntrack.h b/include/net/netns/conntrack.h
index bae914815aa3..ab74b5ed0b01 100644
--- a/include/net/netns/conntrack.h
+++ b/include/net/netns/conntrack.h
@@ -7,9 +7,6 @@
 #include <linux/atomic.h>
 #include <linux/workqueue.h>
 #include <linux/netfilter/nf_conntrack_tcp.h>
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-#include <linux/netfilter/nf_conntrack_dccp.h>
-#endif
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 #include <linux/netfilter/nf_conntrack_sctp.h>
 #endif
@@ -50,13 +47,6 @@ struct nf_icmp_net {
 	unsigned int timeout;
 };
 
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-struct nf_dccp_net {
-	u8 dccp_loose;
-	unsigned int dccp_timeout[CT_DCCP_MAX + 1];
-};
-#endif
-
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 struct nf_sctp_net {
 	unsigned int timeouts[SCTP_CONNTRACK_MAX];
@@ -82,9 +72,6 @@ struct nf_ip_net {
 	struct nf_udp_net	udp;
 	struct nf_icmp_net	icmp;
 	struct nf_icmp_net	icmpv6;
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	struct nf_dccp_net	dccp;
-#endif
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 	struct nf_sctp_net	sctp;
 #endif
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 2560416218d0..ba60b48d7567 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -195,16 +195,6 @@ config NF_CONNTRACK_LABELS
 config NF_CONNTRACK_OVS
 	bool
 
-config NF_CT_PROTO_DCCP
-	bool 'DCCP protocol connection tracking support'
-	depends on NETFILTER_ADVANCED
-	default y
-	help
-	  With this option enabled, the layer 3 independent connection
-	  tracking code will be able to do state tracking on DCCP connections.
-
-	  If unsure, say Y.
-
 config NF_CT_PROTO_GRE
 	bool
 
@@ -516,6 +506,12 @@ config NFT_CT
 	  This option adds the "ct" expression that you can use to match
 	  connection tracking information such as the flow state.
 
+config NFT_EXTHDR_DCCP
+	bool "Netfilter nf_tables exthdr DCCP support (DEPRECATED)"
+	default n
+	help
+	  This option adds support for matching on DCCP extension headers.
+
 config NFT_FLOW_OFFLOAD
 	depends on NF_CONNTRACK && NF_FLOW_TABLE
 	tristate "Netfilter nf_tables hardware flow offload module"
@@ -1278,9 +1274,9 @@ config NETFILTER_XT_MATCH_CPU
 	  To compile it as a module, choose M here.  If unsure, say N.
 
 config NETFILTER_XT_MATCH_DCCP
-	tristate '"dccp" protocol match support'
+	tristate '"dccp" protocol match support (DEPRECATED)'
 	depends on NETFILTER_ADVANCED
-	default IP_DCCP
+	default n
 	help
 	  With this option enabled, you will be able to use the iptables
 	  `dccp' match in order to match on DCCP source/destination ports
diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile
index f0aa4d7ef499..e43e20f529f8 100644
--- a/net/netfilter/Makefile
+++ b/net/netfilter/Makefile
@@ -12,7 +12,6 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_TIMESTAMP) += nf_conntrack_timestamp.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o
 nf_conntrack-$(CONFIG_NF_CONNTRACK_OVS) += nf_conntrack_ovs.o
-nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o
 nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o
 nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o
 ifeq ($(CONFIG_NF_CONNTRACK),m)
diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c
index 201d3c4ec623..1097f26a6788 100644
--- a/net/netfilter/nf_conntrack_core.c
+++ b/net/netfilter/nf_conntrack_core.c
@@ -328,9 +328,6 @@ nf_ct_get_tuple(const struct sk_buff *skb,
 #endif
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 	case IPPROTO_SCTP:
-#endif
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	case IPPROTO_DCCP:
 #endif
 		/* fallthrough */
 		return nf_ct_get_tuple_ports(skb, dataoff, tuple);
@@ -1982,11 +1979,6 @@ static int nf_conntrack_handle_packet(struct nf_conn *ct,
 		return nf_conntrack_sctp_packet(ct, skb, dataoff,
 						ctinfo, state);
 #endif
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	case IPPROTO_DCCP:
-		return nf_conntrack_dccp_packet(ct, skb, dataoff,
-						ctinfo, state);
-#endif
 #ifdef CONFIG_NF_CT_PROTO_GRE
 	case IPPROTO_GRE:
 		return nf_conntrack_gre_packet(ct, skb, dataoff,
diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
index 2cc0fde23344..486d52b45fe5 100644
--- a/net/netfilter/nf_conntrack_netlink.c
+++ b/net/netfilter/nf_conntrack_netlink.c
@@ -2036,7 +2036,6 @@ static void ctnetlink_change_mark(struct nf_conn *ct,
 
 static const struct nla_policy protoinfo_policy[CTA_PROTOINFO_MAX+1] = {
 	[CTA_PROTOINFO_TCP]	= { .type = NLA_NESTED },
-	[CTA_PROTOINFO_DCCP]	= { .type = NLA_NESTED },
 	[CTA_PROTOINFO_SCTP]	= { .type = NLA_NESTED },
 };
 
diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c
index f36727ed91e1..bc1d96686b9c 100644
--- a/net/netfilter/nf_conntrack_proto.c
+++ b/net/netfilter/nf_conntrack_proto.c
@@ -100,9 +100,6 @@ const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto)
 	case IPPROTO_UDP: return &nf_conntrack_l4proto_udp;
 	case IPPROTO_TCP: return &nf_conntrack_l4proto_tcp;
 	case IPPROTO_ICMP: return &nf_conntrack_l4proto_icmp;
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	case IPPROTO_DCCP: return &nf_conntrack_l4proto_dccp;
-#endif
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 	case IPPROTO_SCTP: return &nf_conntrack_l4proto_sctp;
 #endif
@@ -681,9 +678,6 @@ void nf_conntrack_proto_pernet_init(struct net *net)
 #if IS_ENABLED(CONFIG_IPV6)
 	nf_conntrack_icmpv6_init_net(net);
 #endif
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	nf_conntrack_dccp_init_net(net);
-#endif
 #ifdef CONFIG_NF_CT_PROTO_SCTP
 	nf_conntrack_sctp_init_net(net);
 #endif
diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c
deleted file mode 100644
index ebc4f733bb2e..000000000000
--- a/net/netfilter/nf_conntrack_proto_dccp.c
+++ /dev/null
@@ -1,826 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * DCCP connection tracking protocol helper
- *
- * Copyright (c) 2005, 2006, 2008 Patrick McHardy <kaber@trash.net>
- */
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sysctl.h>
-#include <linux/spinlock.h>
-#include <linux/skbuff.h>
-#include <linux/dccp.h>
-#include <linux/slab.h>
-
-#include <net/net_namespace.h>
-#include <net/netns/generic.h>
-
-#include <linux/netfilter/nfnetlink_conntrack.h>
-#include <net/netfilter/nf_conntrack.h>
-#include <net/netfilter/nf_conntrack_l4proto.h>
-#include <net/netfilter/nf_conntrack_ecache.h>
-#include <net/netfilter/nf_conntrack_timeout.h>
-#include <net/netfilter/nf_log.h>
-
-/* Timeouts are based on values from RFC4340:
- *
- * - REQUEST:
- *
- *   8.1.2. Client Request
- *
- *   A client MAY give up on its DCCP-Requests after some time
- *   (3 minutes, for example).
- *
- * - RESPOND:
- *
- *   8.1.3. Server Response
- *
- *   It MAY also leave the RESPOND state for CLOSED after a timeout of
- *   not less than 4MSL (8 minutes);
- *
- * - PARTOPEN:
- *
- *   8.1.5. Handshake Completion
- *
- *   If the client remains in PARTOPEN for more than 4MSL (8 minutes),
- *   it SHOULD reset the connection with Reset Code 2, "Aborted".
- *
- * - OPEN:
- *
- *   The DCCP timestamp overflows after 11.9 hours. If the connection
- *   stays idle this long the sequence number won't be recognized
- *   as valid anymore.
- *
- * - CLOSEREQ/CLOSING:
- *
- *   8.3. Termination
- *
- *   The retransmission timer should initially be set to go off in two
- *   round-trip times and should back off to not less than once every
- *   64 seconds ...
- *
- * - TIMEWAIT:
- *
- *   4.3. States
- *
- *   A server or client socket remains in this state for 2MSL (4 minutes)
- *   after the connection has been town down, ...
- */
-
-#define DCCP_MSL (2 * 60 * HZ)
-
-#ifdef CONFIG_NF_CONNTRACK_PROCFS
-static const char * const dccp_state_names[] = {
-	[CT_DCCP_NONE]		= "NONE",
-	[CT_DCCP_REQUEST]	= "REQUEST",
-	[CT_DCCP_RESPOND]	= "RESPOND",
-	[CT_DCCP_PARTOPEN]	= "PARTOPEN",
-	[CT_DCCP_OPEN]		= "OPEN",
-	[CT_DCCP_CLOSEREQ]	= "CLOSEREQ",
-	[CT_DCCP_CLOSING]	= "CLOSING",
-	[CT_DCCP_TIMEWAIT]	= "TIMEWAIT",
-	[CT_DCCP_IGNORE]	= "IGNORE",
-	[CT_DCCP_INVALID]	= "INVALID",
-};
-#endif
-
-#define sNO	CT_DCCP_NONE
-#define sRQ	CT_DCCP_REQUEST
-#define sRS	CT_DCCP_RESPOND
-#define sPO	CT_DCCP_PARTOPEN
-#define sOP	CT_DCCP_OPEN
-#define sCR	CT_DCCP_CLOSEREQ
-#define sCG	CT_DCCP_CLOSING
-#define sTW	CT_DCCP_TIMEWAIT
-#define sIG	CT_DCCP_IGNORE
-#define sIV	CT_DCCP_INVALID
-
-/*
- * DCCP state transition table
- *
- * The assumption is the same as for TCP tracking:
- *
- * We are the man in the middle. All the packets go through us but might
- * get lost in transit to the destination. It is assumed that the destination
- * can't receive segments we haven't seen.
- *
- * The following states exist:
- *
- * NONE:	Initial state, expecting Request
- * REQUEST:	Request seen, waiting for Response from server
- * RESPOND:	Response from server seen, waiting for Ack from client
- * PARTOPEN:	Ack after Response seen, waiting for packet other than Response,
- * 		Reset or Sync from server
- * OPEN:	Packet other than Response, Reset or Sync seen
- * CLOSEREQ:	CloseReq from server seen, expecting Close from client
- * CLOSING:	Close seen, expecting Reset
- * TIMEWAIT:	Reset seen
- * IGNORE:	Not determinable whether packet is valid
- *
- * Some states exist only on one side of the connection: REQUEST, RESPOND,
- * PARTOPEN, CLOSEREQ. For the other side these states are equivalent to
- * the one it was in before.
- *
- * Packets are marked as ignored (sIG) if we don't know if they're valid
- * (for example a reincarnation of a connection we didn't notice is dead
- * already) and the server may send back a connection closing Reset or a
- * Response. They're also used for Sync/SyncAck packets, which we don't
- * care about.
- */
-static const u_int8_t
-dccp_state_table[CT_DCCP_ROLE_MAX + 1][DCCP_PKT_SYNCACK + 1][CT_DCCP_MAX + 1] = {
-	[CT_DCCP_ROLE_CLIENT] = {
-		[DCCP_PKT_REQUEST] = {
-		/*
-		 * sNO -> sRQ		Regular Request
-		 * sRQ -> sRQ		Retransmitted Request or reincarnation
-		 * sRS -> sRS		Retransmitted Request (apparently Response
-		 * 			got lost after we saw it) or reincarnation
-		 * sPO -> sIG		Ignore, conntrack might be out of sync
-		 * sOP -> sIG		Ignore, conntrack might be out of sync
-		 * sCR -> sIG		Ignore, conntrack might be out of sync
-		 * sCG -> sIG		Ignore, conntrack might be out of sync
-		 * sTW -> sRQ		Reincarnation
-		 *
-		 *	sNO, sRQ, sRS, sPO. sOP, sCR, sCG, sTW, */
-			sRQ, sRQ, sRS, sIG, sIG, sIG, sIG, sRQ,
-		},
-		[DCCP_PKT_RESPONSE] = {
-		/*
-		 * sNO -> sIV		Invalid
-		 * sRQ -> sIG		Ignore, might be response to ignored Request
-		 * sRS -> sIG		Ignore, might be response to ignored Request
-		 * sPO -> sIG		Ignore, might be response to ignored Request
-		 * sOP -> sIG		Ignore, might be response to ignored Request
-		 * sCR -> sIG		Ignore, might be response to ignored Request
-		 * sCG -> sIG		Ignore, might be response to ignored Request
-		 * sTW -> sIV		Invalid, reincarnation in reverse direction
-		 *			goes through sRQ
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIV,
-		},
-		[DCCP_PKT_ACK] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sPO		Ack for Response, move to PARTOPEN (8.1.5.)
-		 * sPO -> sPO		Retransmitted Ack for Response, remain in PARTOPEN
-		 * sOP -> sOP		Regular ACK, remain in OPEN
-		 * sCR -> sCR		Ack in CLOSEREQ MAY be processed (8.3.)
-		 * sCG -> sCG		Ack in CLOSING MAY be processed (8.3.)
-		 * sTW -> sIV
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sPO, sPO, sOP, sCR, sCG, sIV
-		},
-		[DCCP_PKT_DATA] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sIV		No connection
-		 * sPO -> sIV		MUST use DataAck in PARTOPEN state (8.1.5.)
-		 * sOP -> sOP		Regular Data packet
-		 * sCR -> sCR		Data in CLOSEREQ MAY be processed (8.3.)
-		 * sCG -> sCG		Data in CLOSING MAY be processed (8.3.)
-		 * sTW -> sIV
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sIV, sIV, sOP, sCR, sCG, sIV,
-		},
-		[DCCP_PKT_DATAACK] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sPO		Ack for Response, move to PARTOPEN (8.1.5.)
-		 * sPO -> sPO		Remain in PARTOPEN state
-		 * sOP -> sOP		Regular DataAck packet in OPEN state
-		 * sCR -> sCR		DataAck in CLOSEREQ MAY be processed (8.3.)
-		 * sCG -> sCG		DataAck in CLOSING MAY be processed (8.3.)
-		 * sTW -> sIV
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sPO, sPO, sOP, sCR, sCG, sIV
-		},
-		[DCCP_PKT_CLOSEREQ] = {
-		/*
-		 * CLOSEREQ may only be sent by the server.
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sIV, sIV, sIV, sIV, sIV, sIV
-		},
-		[DCCP_PKT_CLOSE] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sIV		No connection
-		 * sPO -> sCG		Client-initiated close
-		 * sOP -> sCG		Client-initiated close
-		 * sCR -> sCG		Close in response to CloseReq (8.3.)
-		 * sCG -> sCG		Retransmit
-		 * sTW -> sIV		Late retransmit, already in TIME_WAIT
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sIV, sCG, sCG, sCG, sIV, sIV
-		},
-		[DCCP_PKT_RESET] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sTW		Sync received or timeout, SHOULD send Reset (8.1.1.)
-		 * sRS -> sTW		Response received without Request
-		 * sPO -> sTW		Timeout, SHOULD send Reset (8.1.5.)
-		 * sOP -> sTW		Connection reset
-		 * sCR -> sTW		Connection reset
-		 * sCG -> sTW		Connection reset
-		 * sTW -> sIG		Ignore (don't refresh timer)
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sTW, sTW, sTW, sTW, sTW, sTW, sIG
-		},
-		[DCCP_PKT_SYNC] = {
-		/*
-		 * We currently ignore Sync packets
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
-		},
-		[DCCP_PKT_SYNCACK] = {
-		/*
-		 * We currently ignore SyncAck packets
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
-		},
-	},
-	[CT_DCCP_ROLE_SERVER] = {
-		[DCCP_PKT_REQUEST] = {
-		/*
-		 * sNO -> sIV		Invalid
-		 * sRQ -> sIG		Ignore, conntrack might be out of sync
-		 * sRS -> sIG		Ignore, conntrack might be out of sync
-		 * sPO -> sIG		Ignore, conntrack might be out of sync
-		 * sOP -> sIG		Ignore, conntrack might be out of sync
-		 * sCR -> sIG		Ignore, conntrack might be out of sync
-		 * sCG -> sIG		Ignore, conntrack might be out of sync
-		 * sTW -> sRQ		Reincarnation, must reverse roles
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sRQ
-		},
-		[DCCP_PKT_RESPONSE] = {
-		/*
-		 * sNO -> sIV		Response without Request
-		 * sRQ -> sRS		Response to clients Request
-		 * sRS -> sRS		Retransmitted Response (8.1.3. SHOULD NOT)
-		 * sPO -> sIG		Response to an ignored Request or late retransmit
-		 * sOP -> sIG		Ignore, might be response to ignored Request
-		 * sCR -> sIG		Ignore, might be response to ignored Request
-		 * sCG -> sIG		Ignore, might be response to ignored Request
-		 * sTW -> sIV		Invalid, Request from client in sTW moves to sRQ
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sRS, sRS, sIG, sIG, sIG, sIG, sIV
-		},
-		[DCCP_PKT_ACK] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sIV		No connection
-		 * sPO -> sOP		Enter OPEN state (8.1.5.)
-		 * sOP -> sOP		Regular Ack in OPEN state
-		 * sCR -> sIV		Waiting for Close from client
-		 * sCG -> sCG		Ack in CLOSING MAY be processed (8.3.)
-		 * sTW -> sIV
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV
-		},
-		[DCCP_PKT_DATA] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sIV		No connection
-		 * sPO -> sOP		Enter OPEN state (8.1.5.)
-		 * sOP -> sOP		Regular Data packet in OPEN state
-		 * sCR -> sIV		Waiting for Close from client
-		 * sCG -> sCG		Data in CLOSING MAY be processed (8.3.)
-		 * sTW -> sIV
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV
-		},
-		[DCCP_PKT_DATAACK] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sIV		No connection
-		 * sPO -> sOP		Enter OPEN state (8.1.5.)
-		 * sOP -> sOP		Regular DataAck in OPEN state
-		 * sCR -> sIV		Waiting for Close from client
-		 * sCG -> sCG		Data in CLOSING MAY be processed (8.3.)
-		 * sTW -> sIV
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sIV, sOP, sOP, sIV, sCG, sIV
-		},
-		[DCCP_PKT_CLOSEREQ] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sIV		No connection
-		 * sPO -> sOP -> sCR	Move directly to CLOSEREQ (8.1.5.)
-		 * sOP -> sCR		CloseReq in OPEN state
-		 * sCR -> sCR		Retransmit
-		 * sCG -> sCR		Simultaneous close, client sends another Close
-		 * sTW -> sIV		Already closed
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sIV, sCR, sCR, sCR, sCR, sIV
-		},
-		[DCCP_PKT_CLOSE] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sIV		No connection
-		 * sRS -> sIV		No connection
-		 * sPO -> sOP -> sCG	Move direcly to CLOSING
-		 * sOP -> sCG		Move to CLOSING
-		 * sCR -> sIV		Close after CloseReq is invalid
-		 * sCG -> sCG		Retransmit
-		 * sTW -> sIV		Already closed
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIV, sIV, sCG, sCG, sIV, sCG, sIV
-		},
-		[DCCP_PKT_RESET] = {
-		/*
-		 * sNO -> sIV		No connection
-		 * sRQ -> sTW		Reset in response to Request
-		 * sRS -> sTW		Timeout, SHOULD send Reset (8.1.3.)
-		 * sPO -> sTW		Timeout, SHOULD send Reset (8.1.3.)
-		 * sOP -> sTW
-		 * sCR -> sTW
-		 * sCG -> sTW
-		 * sTW -> sIG		Ignore (don't refresh timer)
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW, sTW */
-			sIV, sTW, sTW, sTW, sTW, sTW, sTW, sTW, sIG
-		},
-		[DCCP_PKT_SYNC] = {
-		/*
-		 * We currently ignore Sync packets
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
-		},
-		[DCCP_PKT_SYNCACK] = {
-		/*
-		 * We currently ignore SyncAck packets
-		 *
-		 *	sNO, sRQ, sRS, sPO, sOP, sCR, sCG, sTW */
-			sIV, sIG, sIG, sIG, sIG, sIG, sIG, sIG,
-		},
-	},
-};
-
-static noinline bool
-dccp_new(struct nf_conn *ct, const struct sk_buff *skb,
-	 const struct dccp_hdr *dh,
-	 const struct nf_hook_state *hook_state)
-{
-	struct net *net = nf_ct_net(ct);
-	struct nf_dccp_net *dn;
-	const char *msg;
-	u_int8_t state;
-
-	state = dccp_state_table[CT_DCCP_ROLE_CLIENT][dh->dccph_type][CT_DCCP_NONE];
-	switch (state) {
-	default:
-		dn = nf_dccp_pernet(net);
-		if (dn->dccp_loose == 0) {
-			msg = "not picking up existing connection ";
-			goto out_invalid;
-		}
-		break;
-	case CT_DCCP_REQUEST:
-		break;
-	case CT_DCCP_INVALID:
-		msg = "invalid state transition ";
-		goto out_invalid;
-	}
-
-	ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT;
-	ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER;
-	ct->proto.dccp.state = CT_DCCP_NONE;
-	ct->proto.dccp.last_pkt = DCCP_PKT_REQUEST;
-	ct->proto.dccp.last_dir = IP_CT_DIR_ORIGINAL;
-	ct->proto.dccp.handshake_seq = 0;
-	return true;
-
-out_invalid:
-	nf_ct_l4proto_log_invalid(skb, ct, hook_state, "%s", msg);
-	return false;
-}
-
-static u64 dccp_ack_seq(const struct dccp_hdr *dh)
-{
-	const struct dccp_hdr_ack_bits *dhack;
-
-	dhack = (void *)dh + __dccp_basic_hdr_len(dh);
-	return ((u64)ntohs(dhack->dccph_ack_nr_high) << 32) +
-		     ntohl(dhack->dccph_ack_nr_low);
-}
-
-static bool dccp_error(const struct dccp_hdr *dh,
-		       struct sk_buff *skb, unsigned int dataoff,
-		       const struct nf_hook_state *state)
-{
-	static const unsigned long require_seq48 = 1 << DCCP_PKT_REQUEST |
-						   1 << DCCP_PKT_RESPONSE |
-						   1 << DCCP_PKT_CLOSEREQ |
-						   1 << DCCP_PKT_CLOSE |
-						   1 << DCCP_PKT_RESET |
-						   1 << DCCP_PKT_SYNC |
-						   1 << DCCP_PKT_SYNCACK;
-	unsigned int dccp_len = skb->len - dataoff;
-	unsigned int cscov;
-	const char *msg;
-	u8 type;
-
-	BUILD_BUG_ON(DCCP_PKT_INVALID >= BITS_PER_LONG);
-
-	if (dh->dccph_doff * 4 < sizeof(struct dccp_hdr) ||
-	    dh->dccph_doff * 4 > dccp_len) {
-		msg = "nf_ct_dccp: truncated/malformed packet ";
-		goto out_invalid;
-	}
-
-	cscov = dccp_len;
-	if (dh->dccph_cscov) {
-		cscov = (dh->dccph_cscov - 1) * 4;
-		if (cscov > dccp_len) {
-			msg = "nf_ct_dccp: bad checksum coverage ";
-			goto out_invalid;
-		}
-	}
-
-	if (state->hook == NF_INET_PRE_ROUTING &&
-	    state->net->ct.sysctl_checksum &&
-	    nf_checksum_partial(skb, state->hook, dataoff, cscov,
-				IPPROTO_DCCP, state->pf)) {
-		msg = "nf_ct_dccp: bad checksum ";
-		goto out_invalid;
-	}
-
-	type = dh->dccph_type;
-	if (type >= DCCP_PKT_INVALID) {
-		msg = "nf_ct_dccp: reserved packet type ";
-		goto out_invalid;
-	}
-
-	if (test_bit(type, &require_seq48) && !dh->dccph_x) {
-		msg = "nf_ct_dccp: type lacks 48bit sequence numbers";
-		goto out_invalid;
-	}
-
-	return false;
-out_invalid:
-	nf_l4proto_log_invalid(skb, state, IPPROTO_DCCP, "%s", msg);
-	return true;
-}
-
-struct nf_conntrack_dccp_buf {
-	struct dccp_hdr dh;	 /* generic header part */
-	struct dccp_hdr_ext ext; /* optional depending dh->dccph_x */
-	union {			 /* depends on header type */
-		struct dccp_hdr_ack_bits ack;
-		struct dccp_hdr_request req;
-		struct dccp_hdr_response response;
-		struct dccp_hdr_reset rst;
-	} u;
-};
-
-static struct dccp_hdr *
-dccp_header_pointer(const struct sk_buff *skb, int offset, const struct dccp_hdr *dh,
-		    struct nf_conntrack_dccp_buf *buf)
-{
-	unsigned int hdrlen = __dccp_hdr_len(dh);
-
-	if (hdrlen > sizeof(*buf))
-		return NULL;
-
-	return skb_header_pointer(skb, offset, hdrlen, buf);
-}
-
-int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb,
-			     unsigned int dataoff,
-			     enum ip_conntrack_info ctinfo,
-			     const struct nf_hook_state *state)
-{
-	enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo);
-	struct nf_conntrack_dccp_buf _dh;
-	u_int8_t type, old_state, new_state;
-	enum ct_dccp_roles role;
-	unsigned int *timeouts;
-	struct dccp_hdr *dh;
-
-	dh = skb_header_pointer(skb, dataoff, sizeof(*dh), &_dh.dh);
-	if (!dh)
-		return -NF_ACCEPT;
-
-	if (dccp_error(dh, skb, dataoff, state))
-		return -NF_ACCEPT;
-
-	/* pull again, including possible 48 bit sequences and subtype header */
-	dh = dccp_header_pointer(skb, dataoff, dh, &_dh);
-	if (!dh)
-		return -NF_ACCEPT;
-
-	type = dh->dccph_type;
-	if (!nf_ct_is_confirmed(ct) && !dccp_new(ct, skb, dh, state))
-		return -NF_ACCEPT;
-
-	if (type == DCCP_PKT_RESET &&
-	    !test_bit(IPS_SEEN_REPLY_BIT, &ct->status)) {
-		/* Tear down connection immediately if only reply is a RESET */
-		nf_ct_kill_acct(ct, ctinfo, skb);
-		return NF_ACCEPT;
-	}
-
-	spin_lock_bh(&ct->lock);
-
-	role = ct->proto.dccp.role[dir];
-	old_state = ct->proto.dccp.state;
-	new_state = dccp_state_table[role][type][old_state];
-
-	switch (new_state) {
-	case CT_DCCP_REQUEST:
-		if (old_state == CT_DCCP_TIMEWAIT &&
-		    role == CT_DCCP_ROLE_SERVER) {
-			/* Reincarnation in the reverse direction: reopen and
-			 * reverse client/server roles. */
-			ct->proto.dccp.role[dir] = CT_DCCP_ROLE_CLIENT;
-			ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_SERVER;
-		}
-		break;
-	case CT_DCCP_RESPOND:
-		if (old_state == CT_DCCP_REQUEST)
-			ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
-		break;
-	case CT_DCCP_PARTOPEN:
-		if (old_state == CT_DCCP_RESPOND &&
-		    type == DCCP_PKT_ACK &&
-		    dccp_ack_seq(dh) == ct->proto.dccp.handshake_seq)
-			set_bit(IPS_ASSURED_BIT, &ct->status);
-		break;
-	case CT_DCCP_IGNORE:
-		/*
-		 * Connection tracking might be out of sync, so we ignore
-		 * packets that might establish a new connection and resync
-		 * if the server responds with a valid Response.
-		 */
-		if (ct->proto.dccp.last_dir == !dir &&
-		    ct->proto.dccp.last_pkt == DCCP_PKT_REQUEST &&
-		    type == DCCP_PKT_RESPONSE) {
-			ct->proto.dccp.role[!dir] = CT_DCCP_ROLE_CLIENT;
-			ct->proto.dccp.role[dir] = CT_DCCP_ROLE_SERVER;
-			ct->proto.dccp.handshake_seq = dccp_hdr_seq(dh);
-			new_state = CT_DCCP_RESPOND;
-			break;
-		}
-		ct->proto.dccp.last_dir = dir;
-		ct->proto.dccp.last_pkt = type;
-
-		spin_unlock_bh(&ct->lock);
-		nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid packet");
-		return NF_ACCEPT;
-	case CT_DCCP_INVALID:
-		spin_unlock_bh(&ct->lock);
-		nf_ct_l4proto_log_invalid(skb, ct, state, "%s", "invalid state transition");
-		return -NF_ACCEPT;
-	}
-
-	ct->proto.dccp.last_dir = dir;
-	ct->proto.dccp.last_pkt = type;
-	ct->proto.dccp.state = new_state;
-	spin_unlock_bh(&ct->lock);
-
-	if (new_state != old_state)
-		nf_conntrack_event_cache(IPCT_PROTOINFO, ct);
-
-	timeouts = nf_ct_timeout_lookup(ct);
-	if (!timeouts)
-		timeouts = nf_dccp_pernet(nf_ct_net(ct))->dccp_timeout;
-	nf_ct_refresh_acct(ct, ctinfo, skb, timeouts[new_state]);
-
-	return NF_ACCEPT;
-}
-
-static bool dccp_can_early_drop(const struct nf_conn *ct)
-{
-	switch (ct->proto.dccp.state) {
-	case CT_DCCP_CLOSEREQ:
-	case CT_DCCP_CLOSING:
-	case CT_DCCP_TIMEWAIT:
-		return true;
-	default:
-		break;
-	}
-
-	return false;
-}
-
-#ifdef CONFIG_NF_CONNTRACK_PROCFS
-static void dccp_print_conntrack(struct seq_file *s, struct nf_conn *ct)
-{
-	seq_printf(s, "%s ", dccp_state_names[ct->proto.dccp.state]);
-}
-#endif
-
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-static int dccp_to_nlattr(struct sk_buff *skb, struct nlattr *nla,
-			  struct nf_conn *ct, bool destroy)
-{
-	struct nlattr *nest_parms;
-
-	spin_lock_bh(&ct->lock);
-	nest_parms = nla_nest_start(skb, CTA_PROTOINFO_DCCP);
-	if (!nest_parms)
-		goto nla_put_failure;
-	if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_STATE, ct->proto.dccp.state))
-		goto nla_put_failure;
-
-	if (destroy)
-		goto skip_state;
-
-	if (nla_put_u8(skb, CTA_PROTOINFO_DCCP_ROLE,
-		       ct->proto.dccp.role[IP_CT_DIR_ORIGINAL]) ||
-	    nla_put_be64(skb, CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ,
-			 cpu_to_be64(ct->proto.dccp.handshake_seq),
-			 CTA_PROTOINFO_DCCP_PAD))
-		goto nla_put_failure;
-skip_state:
-	nla_nest_end(skb, nest_parms);
-	spin_unlock_bh(&ct->lock);
-
-	return 0;
-
-nla_put_failure:
-	spin_unlock_bh(&ct->lock);
-	return -1;
-}
-
-static const struct nla_policy dccp_nla_policy[CTA_PROTOINFO_DCCP_MAX + 1] = {
-	[CTA_PROTOINFO_DCCP_STATE]	= { .type = NLA_U8 },
-	[CTA_PROTOINFO_DCCP_ROLE]	= { .type = NLA_U8 },
-	[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ] = { .type = NLA_U64 },
-	[CTA_PROTOINFO_DCCP_PAD]	= { .type = NLA_UNSPEC },
-};
-
-#define DCCP_NLATTR_SIZE ( \
-	NLA_ALIGN(NLA_HDRLEN + 1) + \
-	NLA_ALIGN(NLA_HDRLEN + 1) + \
-	NLA_ALIGN(NLA_HDRLEN + sizeof(u64)) + \
-	NLA_ALIGN(NLA_HDRLEN + 0))
-
-static int nlattr_to_dccp(struct nlattr *cda[], struct nf_conn *ct)
-{
-	struct nlattr *attr = cda[CTA_PROTOINFO_DCCP];
-	struct nlattr *tb[CTA_PROTOINFO_DCCP_MAX + 1];
-	int err;
-
-	if (!attr)
-		return 0;
-
-	err = nla_parse_nested_deprecated(tb, CTA_PROTOINFO_DCCP_MAX, attr,
-					  dccp_nla_policy, NULL);
-	if (err < 0)
-		return err;
-
-	if (!tb[CTA_PROTOINFO_DCCP_STATE] ||
-	    !tb[CTA_PROTOINFO_DCCP_ROLE] ||
-	    nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) > CT_DCCP_ROLE_MAX ||
-	    nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]) >= CT_DCCP_IGNORE) {
-		return -EINVAL;
-	}
-
-	spin_lock_bh(&ct->lock);
-	ct->proto.dccp.state = nla_get_u8(tb[CTA_PROTOINFO_DCCP_STATE]);
-	if (nla_get_u8(tb[CTA_PROTOINFO_DCCP_ROLE]) == CT_DCCP_ROLE_CLIENT) {
-		ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_CLIENT;
-		ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_SERVER;
-	} else {
-		ct->proto.dccp.role[IP_CT_DIR_ORIGINAL] = CT_DCCP_ROLE_SERVER;
-		ct->proto.dccp.role[IP_CT_DIR_REPLY] = CT_DCCP_ROLE_CLIENT;
-	}
-	if (tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]) {
-		ct->proto.dccp.handshake_seq =
-		be64_to_cpu(nla_get_be64(tb[CTA_PROTOINFO_DCCP_HANDSHAKE_SEQ]));
-	}
-	spin_unlock_bh(&ct->lock);
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-
-#include <linux/netfilter/nfnetlink.h>
-#include <linux/netfilter/nfnetlink_cttimeout.h>
-
-static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[],
-				      struct net *net, void *data)
-{
-	struct nf_dccp_net *dn = nf_dccp_pernet(net);
-	unsigned int *timeouts = data;
-	int i;
-
-	if (!timeouts)
-		 timeouts = dn->dccp_timeout;
-
-	/* set default DCCP timeouts. */
-	for (i=0; i<CT_DCCP_MAX; i++)
-		timeouts[i] = dn->dccp_timeout[i];
-
-	/* there's a 1:1 mapping between attributes and protocol states. */
-	for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) {
-		if (tb[i]) {
-			timeouts[i] = ntohl(nla_get_be32(tb[i])) * HZ;
-		}
-	}
-
-	timeouts[CTA_TIMEOUT_DCCP_UNSPEC] = timeouts[CTA_TIMEOUT_DCCP_REQUEST];
-	return 0;
-}
-
-static int
-dccp_timeout_obj_to_nlattr(struct sk_buff *skb, const void *data)
-{
-        const unsigned int *timeouts = data;
-	int i;
-
-	for (i=CTA_TIMEOUT_DCCP_UNSPEC+1; i<CTA_TIMEOUT_DCCP_MAX+1; i++) {
-		if (nla_put_be32(skb, i, htonl(timeouts[i] / HZ)))
-			goto nla_put_failure;
-	}
-	return 0;
-
-nla_put_failure:
-	return -ENOSPC;
-}
-
-static const struct nla_policy
-dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = {
-	[CTA_TIMEOUT_DCCP_REQUEST]	= { .type = NLA_U32 },
-	[CTA_TIMEOUT_DCCP_RESPOND]	= { .type = NLA_U32 },
-	[CTA_TIMEOUT_DCCP_PARTOPEN]	= { .type = NLA_U32 },
-	[CTA_TIMEOUT_DCCP_OPEN]		= { .type = NLA_U32 },
-	[CTA_TIMEOUT_DCCP_CLOSEREQ]	= { .type = NLA_U32 },
-	[CTA_TIMEOUT_DCCP_CLOSING]	= { .type = NLA_U32 },
-	[CTA_TIMEOUT_DCCP_TIMEWAIT]	= { .type = NLA_U32 },
-};
-#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
-
-void nf_conntrack_dccp_init_net(struct net *net)
-{
-	struct nf_dccp_net *dn = nf_dccp_pernet(net);
-
-	/* default values */
-	dn->dccp_loose = 1;
-	dn->dccp_timeout[CT_DCCP_REQUEST]	= 2 * DCCP_MSL;
-	dn->dccp_timeout[CT_DCCP_RESPOND]	= 4 * DCCP_MSL;
-	dn->dccp_timeout[CT_DCCP_PARTOPEN]	= 4 * DCCP_MSL;
-	dn->dccp_timeout[CT_DCCP_OPEN]		= 12 * 3600 * HZ;
-	dn->dccp_timeout[CT_DCCP_CLOSEREQ]	= 64 * HZ;
-	dn->dccp_timeout[CT_DCCP_CLOSING]	= 64 * HZ;
-	dn->dccp_timeout[CT_DCCP_TIMEWAIT]	= 2 * DCCP_MSL;
-
-	/* timeouts[0] is unused, make it same as SYN_SENT so
-	 * ->timeouts[0] contains 'new' timeout, like udp or icmp.
-	 */
-	dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST];
-}
-
-const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp = {
-	.l4proto		= IPPROTO_DCCP,
-	.can_early_drop		= dccp_can_early_drop,
-#ifdef CONFIG_NF_CONNTRACK_PROCFS
-	.print_conntrack	= dccp_print_conntrack,
-#endif
-#if IS_ENABLED(CONFIG_NF_CT_NETLINK)
-	.nlattr_size		= DCCP_NLATTR_SIZE,
-	.to_nlattr		= dccp_to_nlattr,
-	.from_nlattr		= nlattr_to_dccp,
-	.tuple_to_nlattr	= nf_ct_port_tuple_to_nlattr,
-	.nlattr_tuple_size	= nf_ct_port_nlattr_tuple_size,
-	.nlattr_to_tuple	= nf_ct_port_nlattr_to_tuple,
-	.nla_policy		= nf_ct_port_nla_policy,
-#endif
-#ifdef CONFIG_NF_CONNTRACK_TIMEOUT
-	.ctnl_timeout		= {
-		.nlattr_to_obj	= dccp_timeout_nlattr_to_obj,
-		.obj_to_nlattr	= dccp_timeout_obj_to_nlattr,
-		.nlattr_max	= CTA_TIMEOUT_DCCP_MAX,
-		.obj_size	= sizeof(unsigned int) * CT_DCCP_MAX,
-		.nla_policy	= dccp_timeout_nla_policy,
-	},
-#endif /* CONFIG_NF_CONNTRACK_TIMEOUT */
-};
diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c
index 6c4cff10357d..829f60496008 100644
--- a/net/netfilter/nf_conntrack_standalone.c
+++ b/net/netfilter/nf_conntrack_standalone.c
@@ -67,11 +67,6 @@ print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple,
 			   ntohs(tuple->dst.u.udp.port));
 
 		break;
-	case IPPROTO_DCCP:
-		seq_printf(s, "sport=%hu dport=%hu ",
-			   ntohs(tuple->src.u.dccp.port),
-			   ntohs(tuple->dst.u.dccp.port));
-		break;
 	case IPPROTO_SCTP:
 		seq_printf(s, "sport=%hu dport=%hu ",
 			   ntohs(tuple->src.u.sctp.port),
@@ -279,7 +274,6 @@ static const char* l4proto_name(u16 proto)
 	case IPPROTO_ICMP: return "icmp";
 	case IPPROTO_TCP: return "tcp";
 	case IPPROTO_UDP: return "udp";
-	case IPPROTO_DCCP: return "dccp";
 	case IPPROTO_GRE: return "gre";
 	case IPPROTO_SCTP: return "sctp";
 	case IPPROTO_UDPLITE: return "udplite";
@@ -612,16 +606,6 @@ enum nf_ct_sysctl_index {
 	NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT,
 #endif
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST,
-	NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_RESPOND,
-	NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_PARTOPEN,
-	NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_OPEN,
-	NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSEREQ,
-	NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSING,
-	NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_TIMEWAIT,
-	NF_SYSCTL_CT_PROTO_DCCP_LOOSE,
-#endif
 #ifdef CONFIG_NF_CT_PROTO_GRE
 	NF_SYSCTL_CT_PROTO_TIMEOUT_GRE,
 	NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM,
@@ -895,58 +879,6 @@ static struct ctl_table nf_ct_sysctl_table[] = {
 		.proc_handler	= proc_dointvec_jiffies,
 	},
 #endif
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = {
-		.procname	= "nf_conntrack_dccp_timeout_request",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_RESPOND] = {
-		.procname	= "nf_conntrack_dccp_timeout_respond",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_PARTOPEN] = {
-		.procname	= "nf_conntrack_dccp_timeout_partopen",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_OPEN] = {
-		.procname	= "nf_conntrack_dccp_timeout_open",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSEREQ] = {
-		.procname	= "nf_conntrack_dccp_timeout_closereq",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSING] = {
-		.procname	= "nf_conntrack_dccp_timeout_closing",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_TIMEWAIT] = {
-		.procname	= "nf_conntrack_dccp_timeout_timewait",
-		.maxlen		= sizeof(unsigned int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_jiffies,
-	},
-	[NF_SYSCTL_CT_PROTO_DCCP_LOOSE] = {
-		.procname	= "nf_conntrack_dccp_loose",
-		.maxlen		= sizeof(u8),
-		.mode		= 0644,
-		.proc_handler	= proc_dou8vec_minmax,
-		.extra1 	= SYSCTL_ZERO,
-		.extra2 	= SYSCTL_ONE,
-	},
-#endif
 #ifdef CONFIG_NF_CT_PROTO_GRE
 	[NF_SYSCTL_CT_PROTO_TIMEOUT_GRE] = {
 		.procname       = "nf_conntrack_gre_timeout",
@@ -1032,29 +964,6 @@ static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net,
 #endif
 }
 
-static void nf_conntrack_standalone_init_dccp_sysctl(struct net *net,
-						     struct ctl_table *table)
-{
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	struct nf_dccp_net *dn = nf_dccp_pernet(net);
-
-#define XASSIGN(XNAME, dn) \
-	table[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_ ## XNAME].data = \
-			&(dn)->dccp_timeout[CT_DCCP_ ## XNAME]
-
-	XASSIGN(REQUEST, dn);
-	XASSIGN(RESPOND, dn);
-	XASSIGN(PARTOPEN, dn);
-	XASSIGN(OPEN, dn);
-	XASSIGN(CLOSEREQ, dn);
-	XASSIGN(CLOSING, dn);
-	XASSIGN(TIMEWAIT, dn);
-#undef XASSIGN
-
-	table[NF_SYSCTL_CT_PROTO_DCCP_LOOSE].data = &dn->dccp_loose;
-#endif
-}
-
 static void nf_conntrack_standalone_init_gre_sysctl(struct net *net,
 						    struct ctl_table *table)
 {
@@ -1100,7 +1009,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net)
 
 	nf_conntrack_standalone_init_tcp_sysctl(net, table);
 	nf_conntrack_standalone_init_sctp_sysctl(net, table);
-	nf_conntrack_standalone_init_dccp_sysctl(net, table);
 	nf_conntrack_standalone_init_gre_sysctl(net, table);
 
 	/* Don't allow non-init_net ns to alter global sysctls */
diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c
index f391cd267922..78a61dac4ade 100644
--- a/net/netfilter/nf_nat_core.c
+++ b/net/netfilter/nf_nat_core.c
@@ -69,7 +69,6 @@ static void nf_nat_ipv4_decode_session(struct sk_buff *skb,
 		if (t->dst.protonum == IPPROTO_TCP ||
 		    t->dst.protonum == IPPROTO_UDP ||
 		    t->dst.protonum == IPPROTO_UDPLITE ||
-		    t->dst.protonum == IPPROTO_DCCP ||
 		    t->dst.protonum == IPPROTO_SCTP)
 			fl4->fl4_dport = t->dst.u.all;
 	}
@@ -81,7 +80,6 @@ static void nf_nat_ipv4_decode_session(struct sk_buff *skb,
 		if (t->dst.protonum == IPPROTO_TCP ||
 		    t->dst.protonum == IPPROTO_UDP ||
 		    t->dst.protonum == IPPROTO_UDPLITE ||
-		    t->dst.protonum == IPPROTO_DCCP ||
 		    t->dst.protonum == IPPROTO_SCTP)
 			fl4->fl4_sport = t->src.u.all;
 	}
@@ -102,7 +100,6 @@ static void nf_nat_ipv6_decode_session(struct sk_buff *skb,
 		if (t->dst.protonum == IPPROTO_TCP ||
 		    t->dst.protonum == IPPROTO_UDP ||
 		    t->dst.protonum == IPPROTO_UDPLITE ||
-		    t->dst.protonum == IPPROTO_DCCP ||
 		    t->dst.protonum == IPPROTO_SCTP)
 			fl6->fl6_dport = t->dst.u.all;
 	}
@@ -114,7 +111,6 @@ static void nf_nat_ipv6_decode_session(struct sk_buff *skb,
 		if (t->dst.protonum == IPPROTO_TCP ||
 		    t->dst.protonum == IPPROTO_UDP ||
 		    t->dst.protonum == IPPROTO_UDPLITE ||
-		    t->dst.protonum == IPPROTO_DCCP ||
 		    t->dst.protonum == IPPROTO_SCTP)
 			fl6->fl6_sport = t->src.u.all;
 	}
@@ -432,7 +428,6 @@ static bool l4proto_in_range(const struct nf_conntrack_tuple *tuple,
 	case IPPROTO_TCP:
 	case IPPROTO_UDP:
 	case IPPROTO_UDPLITE:
-	case IPPROTO_DCCP:
 	case IPPROTO_SCTP:
 		if (maniptype == NF_NAT_MANIP_SRC)
 			port = tuple->src.u.all;
@@ -632,7 +627,6 @@ static void nf_nat_l4proto_unique_tuple(struct nf_conntrack_tuple *tuple,
 	case IPPROTO_UDPLITE:
 	case IPPROTO_TCP:
 	case IPPROTO_SCTP:
-	case IPPROTO_DCCP:
 		if (maniptype == NF_NAT_MANIP_SRC)
 			keyptr = &tuple->src.u.all;
 		else
diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c
index dc450cc81222..b14a434b9561 100644
--- a/net/netfilter/nf_nat_proto.c
+++ b/net/netfilter/nf_nat_proto.c
@@ -179,46 +179,6 @@ tcp_manip_pkt(struct sk_buff *skb,
 	return true;
 }
 
-static bool
-dccp_manip_pkt(struct sk_buff *skb,
-	       unsigned int iphdroff, unsigned int hdroff,
-	       const struct nf_conntrack_tuple *tuple,
-	       enum nf_nat_manip_type maniptype)
-{
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-	struct dccp_hdr *hdr;
-	__be16 *portptr, oldport, newport;
-	int hdrsize = 8; /* DCCP connection tracking guarantees this much */
-
-	if (skb->len >= hdroff + sizeof(struct dccp_hdr))
-		hdrsize = sizeof(struct dccp_hdr);
-
-	if (skb_ensure_writable(skb, hdroff + hdrsize))
-		return false;
-
-	hdr = (struct dccp_hdr *)(skb->data + hdroff);
-
-	if (maniptype == NF_NAT_MANIP_SRC) {
-		newport = tuple->src.u.dccp.port;
-		portptr = &hdr->dccph_sport;
-	} else {
-		newport = tuple->dst.u.dccp.port;
-		portptr = &hdr->dccph_dport;
-	}
-
-	oldport = *portptr;
-	*portptr = newport;
-
-	if (hdrsize < sizeof(*hdr))
-		return true;
-
-	nf_csum_update(skb, iphdroff, &hdr->dccph_checksum, tuple, maniptype);
-	inet_proto_csum_replace2(&hdr->dccph_checksum, skb, oldport, newport,
-				 false);
-#endif
-	return true;
-}
-
 static bool
 icmp_manip_pkt(struct sk_buff *skb,
 	       unsigned int iphdroff, unsigned int hdroff,
@@ -338,9 +298,6 @@ static bool l4proto_manip_pkt(struct sk_buff *skb,
 	case IPPROTO_ICMPV6:
 		return icmpv6_manip_pkt(skb, iphdroff, hdroff,
 					tuple, maniptype);
-	case IPPROTO_DCCP:
-		return dccp_manip_pkt(skb, iphdroff, hdroff,
-				      tuple, maniptype);
 	case IPPROTO_GRE:
 		return gre_manip_pkt(skb, iphdroff, hdroff,
 				     tuple, maniptype);
diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c
index eab4f476b47f..38d75484e531 100644
--- a/net/netfilter/nfnetlink_cttimeout.c
+++ b/net/netfilter/nfnetlink_cttimeout.c
@@ -461,11 +461,6 @@ static int cttimeout_default_get(struct sk_buff *skb,
 	case IPPROTO_UDPLITE:
 		timeouts = nf_udp_pernet(info->net)->timeouts;
 		break;
-	case IPPROTO_DCCP:
-#ifdef CONFIG_NF_CT_PROTO_DCCP
-		timeouts = nf_dccp_pernet(info->net)->dccp_timeout;
-#endif
-		break;
 	case IPPROTO_ICMPV6:
 		timeouts = &nf_icmpv6_pernet(info->net)->timeout;
 		break;
diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c
index c74012c99125..7eedf4e3ae9c 100644
--- a/net/netfilter/nft_exthdr.c
+++ b/net/netfilter/nft_exthdr.c
@@ -407,6 +407,7 @@ err:
 		regs->verdict.code = NFT_BREAK;
 }
 
+#ifdef CONFIG_NFT_EXTHDR_DCCP
 static void nft_exthdr_dccp_eval(const struct nft_expr *expr,
 				 struct nft_regs *regs,
 				 const struct nft_pktinfo *pkt)
@@ -482,6 +483,7 @@ static void nft_exthdr_dccp_eval(const struct nft_expr *expr,
 err:
 	*dest = 0;
 }
+#endif
 
 static const struct nla_policy nft_exthdr_policy[NFTA_EXTHDR_MAX + 1] = {
 	[NFTA_EXTHDR_DREG]		= { .type = NLA_U32 },
@@ -634,6 +636,7 @@ static int nft_exthdr_ipv4_init(const struct nft_ctx *ctx,
 	return 0;
 }
 
+#ifdef CONFIG_NFT_EXTHDR_DCCP
 static int nft_exthdr_dccp_init(const struct nft_ctx *ctx,
 				const struct nft_expr *expr,
 				const struct nlattr * const tb[])
@@ -649,6 +652,7 @@ static int nft_exthdr_dccp_init(const struct nft_ctx *ctx,
 
 	return 0;
 }
+#endif
 
 static int nft_exthdr_dump_common(struct sk_buff *skb, const struct nft_exthdr *priv)
 {
@@ -779,6 +783,7 @@ static const struct nft_expr_ops nft_exthdr_sctp_ops = {
 	.reduce		= nft_exthdr_reduce,
 };
 
+#ifdef CONFIG_NFT_EXTHDR_DCCP
 static const struct nft_expr_ops nft_exthdr_dccp_ops = {
 	.type		= &nft_exthdr_type,
 	.size		= NFT_EXPR_SIZE(sizeof(struct nft_exthdr)),
@@ -787,6 +792,7 @@ static const struct nft_expr_ops nft_exthdr_dccp_ops = {
 	.dump		= nft_exthdr_dump,
 	.reduce		= nft_exthdr_reduce,
 };
+#endif
 
 static const struct nft_expr_ops *
 nft_exthdr_select_ops(const struct nft_ctx *ctx,
@@ -822,10 +828,12 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx,
 		if (tb[NFTA_EXTHDR_DREG])
 			return &nft_exthdr_sctp_ops;
 		break;
+#ifdef CONFIG_NFT_EXTHDR_DCCP
 	case NFT_EXTHDR_OP_DCCP:
 		if (tb[NFTA_EXTHDR_DREG])
 			return &nft_exthdr_dccp_ops;
 		break;
+#endif
 	}
 
 	return ERR_PTR(-EOPNOTSUPP);
-- 
cgit v1.2.3


From 9931d2899eec3737f4e4fa9fc900be7329816e94 Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Fri, 20 Jun 2025 13:52:28 +0800
Subject: ASoC: fsl_mqs: Distinguish different modules by system manager
 indices

On i.MX94, the MQS2 also needs to be configured by SCMI interface, add
sm_index variable in struct fsl_mqs_soc_data to distinguish the MQS1 and
MQS2 on this platform.

Add the system manager indices for i.MX94 in the header file.

Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Link: https://patch.msgid.link/20250620055229.965942-2-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/firmware/imx/sm.h |  8 ++++++++
 sound/soc/fsl/fsl_mqs.c         | 11 ++++++++---
 2 files changed, 16 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/firmware/imx/sm.h b/include/linux/firmware/imx/sm.h
index a8a17eeb7d90..a6220c500f7c 100644
--- a/include/linux/firmware/imx/sm.h
+++ b/include/linux/firmware/imx/sm.h
@@ -18,6 +18,14 @@
 #define SCMI_IMX_CTRL_SAI4_MCLK		4	/* WAKE SAI4 MCLK */
 #define SCMI_IMX_CTRL_SAI5_MCLK		5	/* WAKE SAI5 MCLK */
 
+#define SCMI_IMX94_CTRL_PDM_CLK_SEL	0U	/*!< AON PDM clock sel */
+#define SCMI_IMX94_CTRL_MQS1_SETTINGS	1U	/*!< AON MQS settings */
+#define SCMI_IMX94_CTRL_MQS2_SETTINGS	2U	/*!< WAKE MQS settings */
+#define SCMI_IMX94_CTRL_SAI1_MCLK	3U	/*!< AON SAI1 MCLK */
+#define SCMI_IMX94_CTRL_SAI2_MCLK	4U	/*!< WAKE SAI2 MCLK */
+#define SCMI_IMX94_CTRL_SAI3_MCLK	5U	/*!< WAKE SAI3 MCLK */
+#define SCMI_IMX94_CTRL_SAI4_MCLK	6U	/*!< WAKE SAI4 MCLK */
+
 int scmi_imx_misc_ctrl_get(u32 id, u32 *num, u32 *val);
 int scmi_imx_misc_ctrl_set(u32 id, u32 val);
 
diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c
index e34e5ea98de5..11f2f3792dce 100644
--- a/sound/soc/fsl/fsl_mqs.c
+++ b/sound/soc/fsl/fsl_mqs.c
@@ -39,6 +39,7 @@ enum reg_type {
  * struct fsl_mqs_soc_data - soc specific data
  *
  * @type: control register space type
+ * @sm_index: index from definition in system manager
  * @ctrl_off: control register offset
  * @en_mask: enable bit mask
  * @en_shift: enable bit shift
@@ -51,6 +52,7 @@ enum reg_type {
  */
 struct fsl_mqs_soc_data {
 	enum reg_type type;
+	int  sm_index;
 	int  ctrl_off;
 	int  en_mask;
 	int  en_shift;
@@ -82,7 +84,7 @@ static int fsl_mqs_sm_read(void *context, unsigned int reg, unsigned int *val)
 
 	if (IS_ENABLED(CONFIG_IMX_SCMI_MISC_DRV) &&
 	    mqs_priv->soc->ctrl_off == reg)
-		return scmi_imx_misc_ctrl_get(SCMI_IMX_CTRL_MQS1_SETTINGS, &num, val);
+		return scmi_imx_misc_ctrl_get(mqs_priv->soc->sm_index, &num, val);
 
 	return -EINVAL;
 };
@@ -93,7 +95,7 @@ static int fsl_mqs_sm_write(void *context, unsigned int reg, unsigned int val)
 
 	if (IS_ENABLED(CONFIG_IMX_SCMI_MISC_DRV) &&
 	    mqs_priv->soc->ctrl_off == reg)
-		return scmi_imx_misc_ctrl_set(SCMI_IMX_CTRL_MQS1_SETTINGS, val);
+		return scmi_imx_misc_ctrl_set(mqs_priv->soc->sm_index, val);
 
 	return -EINVAL;
 };
@@ -386,6 +388,7 @@ static const struct fsl_mqs_soc_data fsl_mqs_imx93_data = {
 
 static const struct fsl_mqs_soc_data fsl_mqs_imx95_aon_data = {
 	.type = TYPE_REG_SM,
+	.sm_index = SCMI_IMX_CTRL_MQS1_SETTINGS,
 	.ctrl_off = 0x88,
 	.en_mask  = BIT(1),
 	.en_shift = 1,
@@ -412,6 +415,7 @@ static const struct fsl_mqs_soc_data fsl_mqs_imx95_netc_data = {
 
 static const struct fsl_mqs_soc_data fsl_mqs_imx943_aon_data = {
 	.type = TYPE_REG_SM,
+	.sm_index = SCMI_IMX94_CTRL_MQS1_SETTINGS,
 	.ctrl_off = 0x88,
 	.en_mask  = BIT(1),
 	.en_shift = 1,
@@ -424,7 +428,8 @@ static const struct fsl_mqs_soc_data fsl_mqs_imx943_aon_data = {
 };
 
 static const struct fsl_mqs_soc_data fsl_mqs_imx943_wakeup_data = {
-	.type = TYPE_REG_GPR,
+	.type = TYPE_REG_SM,
+	.sm_index = SCMI_IMX94_CTRL_MQS2_SETTINGS,
 	.ctrl_off = 0x10,
 	.en_mask  = BIT(1),
 	.en_shift = 1,
-- 
cgit v1.2.3


From baee26a9d6cd3d3c6c3c03c56270aa647a67e4bd Mon Sep 17 00:00:00 2001
From: Shengjiu Wang <shengjiu.wang@nxp.com>
Date: Fri, 20 Jun 2025 13:52:29 +0800
Subject: ASoC: fsl_mqs: rename system manager indices for i.MX95

The system manager indices names are different for each platform, rename
the indices for i.MX95 to differentiate with other platform.

Signed-off-by: Shengjiu Wang <shengjiu.wang@nxp.com>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Link: https://patch.msgid.link/20250620055229.965942-3-shengjiu.wang@nxp.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/firmware/imx/sm.h | 12 ++++++------
 sound/soc/fsl/fsl_mqs.c         |  2 +-
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/firmware/imx/sm.h b/include/linux/firmware/imx/sm.h
index a6220c500f7c..d4212bc42b2c 100644
--- a/include/linux/firmware/imx/sm.h
+++ b/include/linux/firmware/imx/sm.h
@@ -11,12 +11,12 @@
 #include <linux/scmi_imx_protocol.h>
 #include <linux/types.h>
 
-#define SCMI_IMX_CTRL_PDM_CLK_SEL	0	/* AON PDM clock sel */
-#define SCMI_IMX_CTRL_MQS1_SETTINGS	1	/* AON MQS settings */
-#define SCMI_IMX_CTRL_SAI1_MCLK		2	/* AON SAI1 MCLK */
-#define SCMI_IMX_CTRL_SAI3_MCLK		3	/* WAKE SAI3 MCLK */
-#define SCMI_IMX_CTRL_SAI4_MCLK		4	/* WAKE SAI4 MCLK */
-#define SCMI_IMX_CTRL_SAI5_MCLK		5	/* WAKE SAI5 MCLK */
+#define SCMI_IMX95_CTRL_PDM_CLK_SEL	0	/* AON PDM clock sel */
+#define SCMI_IMX95_CTRL_MQS1_SETTINGS	1	/* AON MQS settings */
+#define SCMI_IMX95_CTRL_SAI1_MCLK	2	/* AON SAI1 MCLK */
+#define SCMI_IMX95_CTRL_SAI3_MCLK	3	/* WAKE SAI3 MCLK */
+#define SCMI_IMX95_CTRL_SAI4_MCLK	4	/* WAKE SAI4 MCLK */
+#define SCMI_IMX95_CTRL_SAI5_MCLK	5	/* WAKE SAI5 MCLK */
 
 #define SCMI_IMX94_CTRL_PDM_CLK_SEL	0U	/*!< AON PDM clock sel */
 #define SCMI_IMX94_CTRL_MQS1_SETTINGS	1U	/*!< AON MQS settings */
diff --git a/sound/soc/fsl/fsl_mqs.c b/sound/soc/fsl/fsl_mqs.c
index 11f2f3792dce..901f840df904 100644
--- a/sound/soc/fsl/fsl_mqs.c
+++ b/sound/soc/fsl/fsl_mqs.c
@@ -388,7 +388,7 @@ static const struct fsl_mqs_soc_data fsl_mqs_imx93_data = {
 
 static const struct fsl_mqs_soc_data fsl_mqs_imx95_aon_data = {
 	.type = TYPE_REG_SM,
-	.sm_index = SCMI_IMX_CTRL_MQS1_SETTINGS,
+	.sm_index = SCMI_IMX95_CTRL_MQS1_SETTINGS,
 	.ctrl_off = 0x88,
 	.en_mask  = BIT(1),
 	.en_shift = 1,
-- 
cgit v1.2.3


From 5b605dbee07dda8fd538af1f07cbf1baf0a49cbc Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Jul 2025 15:26:58 +0200
Subject: timekeeping: Provide ktime_get_clock_ts64()

PTP implements an inline switch case for taking timestamps from various
POSIX clock IDs, which already consumes quite some text space. Expanding it
for auxiliary clocks really becomes too big for inlining.

Provide a out of line version.

The function invalidates the timestamp in case the clock is invalid. The
invalidation allows to implement a validation check without the need to
propagate a return value through deep existing call chains.

Due to merge logistics this temporarily defines CLOCK_AUX[_LAST] if
undefined, so that the plain branch, which does not contain any of the core
timekeeper changes, can be pulled into the networking tree as prerequisite
for the PTP side changes. These temporary defines are removed after that
branch is merged into the tip::timers/ptp branch. That way the result in
-next or upstream in the next merge window has zero dependencies.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Acked-by: John Stultz <jstultz@google.com>
Link: https://lore.kernel.org/all/20250701132628.357686408@linutronix.de
---
 include/linux/timekeeping.h | 10 ++++++++++
 kernel/time/timekeeping.c   | 33 +++++++++++++++++++++++++++++++++
 2 files changed, 43 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 542773650200..4a4c2778abae 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -44,6 +44,7 @@ extern void ktime_get_ts64(struct timespec64 *ts);
 extern void ktime_get_real_ts64(struct timespec64 *tv);
 extern void ktime_get_coarse_ts64(struct timespec64 *ts);
 extern void ktime_get_coarse_real_ts64(struct timespec64 *ts);
+extern void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts);
 
 /* Multigrain timestamp interfaces */
 extern void ktime_get_coarse_real_ts64_mg(struct timespec64 *ts);
@@ -345,4 +346,13 @@ void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock,
 extern int update_persistent_clock64(struct timespec64 now);
 #endif
 
+/* Temporary workaround to avoid merge dependencies and cross tree messes */
+#ifndef CLOCK_AUX
+#define CLOCK_AUX			MAX_CLOCKS
+#define MAX_AUX_CLOCKS			8
+#define CLOCK_AUX_LAST			(CLOCK_AUX + MAX_AUX_CLOCKS - 1)
+
+static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { return false; }
+#endif
+
 #endif
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index a009c91f7b05..572e3bd0cc94 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -1573,6 +1573,39 @@ void ktime_get_raw_ts64(struct timespec64 *ts)
 }
 EXPORT_SYMBOL(ktime_get_raw_ts64);
 
+/**
+ * ktime_get_clock_ts64 - Returns time of a clock in a timespec
+ * @id:		POSIX clock ID of the clock to read
+ * @ts:		Pointer to the timespec64 to be set
+ *
+ * The timestamp is invalidated (@ts->sec is set to -1) if the
+ * clock @id is not available.
+ */
+void ktime_get_clock_ts64(clockid_t id, struct timespec64 *ts)
+{
+	/* Invalidate time stamp */
+	ts->tv_sec = -1;
+	ts->tv_nsec = 0;
+
+	switch (id) {
+	case CLOCK_REALTIME:
+		ktime_get_real_ts64(ts);
+		return;
+	case CLOCK_MONOTONIC:
+		ktime_get_ts64(ts);
+		return;
+	case CLOCK_MONOTONIC_RAW:
+		ktime_get_raw_ts64(ts);
+		return;
+	case CLOCK_AUX ... CLOCK_AUX_LAST:
+		if (IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS))
+			ktime_get_aux_ts64(id, ts);
+		return;
+	default:
+		WARN_ON_ONCE(1);
+	}
+}
+EXPORT_SYMBOL_GPL(ktime_get_clock_ts64);
 
 /**
  * timekeeping_valid_for_hres - Check if timekeeping is suitable for hres
-- 
cgit v1.2.3


From 8959338617a85e35820e3a7fa21801cf55b068bf Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 3 Jul 2025 14:39:28 +0200
Subject: timekeeping: Remove the temporary CLOCK_AUX workaround

ktime_get_clock_ts64() was provided for the networking tree as a stand
alone commit based on v6.16-rc1. It contains a temporary workaround for the
CLOCK_AUX* defines, which are only available in the timekeeping tree.

As this commit is now merged into the timers/ptp branch, which contains the
real CLOCK_AUX* defines, the workaround is obsolete.

Remove it.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250701130923.579834908@linutronix.de
---
 include/linux/timekeeping.h | 9 ---------
 1 file changed, 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/timekeeping.h b/include/linux/timekeeping.h
index 6121924d93c4..aee2c1a46e47 100644
--- a/include/linux/timekeeping.h
+++ b/include/linux/timekeeping.h
@@ -357,13 +357,4 @@ void read_persistent_wall_and_boot_offset(struct timespec64 *wall_clock,
 extern int update_persistent_clock64(struct timespec64 now);
 #endif
 
-/* Temporary workaround to avoid merge dependencies and cross tree messes */
-#ifndef CLOCK_AUX
-#define CLOCK_AUX			MAX_CLOCKS
-#define MAX_AUX_CLOCKS			8
-#define CLOCK_AUX_LAST			(CLOCK_AUX + MAX_AUX_CLOCKS - 1)
-
-static inline bool ktime_get_aux_ts64(clockid_t id, struct timespec64 *kt) { return false; }
-#endif
-
 #endif
-- 
cgit v1.2.3


From 4c09a4cebd0320c5381afad3fb6f997f20082a3b Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Tue, 1 Jul 2025 15:27:00 +0200
Subject: ptp: Use ktime_get_clock_ts64() for timestamping

The inlined ptp_read_system_[pre|post]ts() switch cases expand to a copious
amount of text in drivers, e.g. ~500 bytes in e1000e. Adding auxiliary
clock support to the inlines would increase it further.

Replace the inline switch case with a call to ktime_get_clock_ts64(), which
reduces the code size in drivers and allows to access auxiliary clocks once
they are enabled in the IOCTL parameter filter.

No functional change.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Acked-by: John Stultz <jstultz@google.com>
Link: https://patch.msgid.link/20250701132628.426168092@linutronix.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 include/linux/ptp_clock_kernel.h | 34 ++++------------------------------
 1 file changed, 4 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ptp_clock_kernel.h b/include/linux/ptp_clock_kernel.h
index eced7e9bf69a..3d089bd4d5e9 100644
--- a/include/linux/ptp_clock_kernel.h
+++ b/include/linux/ptp_clock_kernel.h
@@ -477,40 +477,14 @@ static inline ktime_t ptp_convert_timestamp(const ktime_t *hwtstamp,
 
 static inline void ptp_read_system_prets(struct ptp_system_timestamp *sts)
 {
-	if (sts) {
-		switch (sts->clockid) {
-		case CLOCK_REALTIME:
-			ktime_get_real_ts64(&sts->pre_ts);
-			break;
-		case CLOCK_MONOTONIC:
-			ktime_get_ts64(&sts->pre_ts);
-			break;
-		case CLOCK_MONOTONIC_RAW:
-			ktime_get_raw_ts64(&sts->pre_ts);
-			break;
-		default:
-			break;
-		}
-	}
+	if (sts)
+		ktime_get_clock_ts64(sts->clockid, &sts->pre_ts);
 }
 
 static inline void ptp_read_system_postts(struct ptp_system_timestamp *sts)
 {
-	if (sts) {
-		switch (sts->clockid) {
-		case CLOCK_REALTIME:
-			ktime_get_real_ts64(&sts->post_ts);
-			break;
-		case CLOCK_MONOTONIC:
-			ktime_get_ts64(&sts->post_ts);
-			break;
-		case CLOCK_MONOTONIC_RAW:
-			ktime_get_raw_ts64(&sts->post_ts);
-			break;
-		default:
-			break;
-		}
-	}
+	if (sts)
+		ktime_get_clock_ts64(sts->clockid, &sts->post_ts);
 }
 
 #endif
-- 
cgit v1.2.3


From 858e65af91351f8842bbe2c5ae6f100778783f42 Mon Sep 17 00:00:00 2001
From: Thomas Gleixner <tglx@linutronix.de>
Date: Thu, 26 Jun 2025 16:48:58 +0200
Subject: irqdomain: Add device pointer to irq_domain_info and msi_domain_info

Add device pointer to irq_domain_info and msi_domain_info, so that the device
can be specified at domain creation time.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/943e52403b20cf13c320d55bd4446b4562466aab.1750860131.git.namcao@linutronix.de
---
 include/linux/irqdomain.h | 2 ++
 include/linux/msi.h       | 2 ++
 kernel/irq/irqdomain.c    | 1 +
 kernel/irq/msi.c          | 3 ++-
 4 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 7387d183029b..266b5e5bb8ce 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -279,6 +279,7 @@ struct irq_domain_chip_generic_info;
  *			domains are added using same fwnode
  * @ops:		Domain operation callbacks
  * @host_data:		Controller private data pointer
+ * @dev:		Device which creates the domain
  * @dgc_info:		Geneneric chip information structure pointer used to
  *			create generic chips for the domain if not NULL.
  * @init:		Function called when the domain is created.
@@ -298,6 +299,7 @@ struct irq_domain_info {
 	const char				*name_suffix;
 	const struct irq_domain_ops		*ops;
 	void					*host_data;
+	struct device				*dev;
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
 	/**
 	 * @parent: Pointer to the parent irq domain used in a hierarchy domain
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 6863540f4b71..77227d23ea84 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -488,6 +488,7 @@ struct msi_domain_ops {
  *			gets initialized to the maximum software index limit
  *			by the domain creation code.
  * @ops:		The callback data structure
+ * @dev:		Device which creates the domain
  * @chip:		Optional: associated interrupt chip
  * @chip_data:		Optional: associated interrupt chip data
  * @handler:		Optional: associated interrupt flow handler
@@ -501,6 +502,7 @@ struct msi_domain_info {
 	enum irq_domain_bus_token	bus_token;
 	unsigned int			hwsize;
 	struct msi_domain_ops		*ops;
+	struct device			*dev;
 	struct irq_chip			*chip;
 	void				*chip_data;
 	irq_flow_handler_t		handler;
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index c8b6de09047b..4afbd3ac532f 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -317,6 +317,7 @@ static struct irq_domain *__irq_domain_instantiate(const struct irq_domain_info
 
 	domain->flags |= info->domain_flags;
 	domain->exit = info->exit;
+	domain->dev = info->dev;
 
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
 	if (info->parent) {
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index 9febe797a5f6..9b09ad3f9914 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -889,6 +889,7 @@ static struct irq_domain *__msi_create_irq_domain(struct fwnode_handle *fwnode,
 
 	if (domain) {
 		irq_domain_update_bus_token(domain, info->bus_token);
+		domain->dev = info->dev;
 		if (info->flags & MSI_FLAG_PARENT_PM_DEV)
 			domain->pm_dev = parent->pm_dev;
 	}
@@ -1051,6 +1052,7 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 	bundle->info.data = domain_data;
 	bundle->info.chip_data = chip_data;
 	bundle->info.alloc_data = &bundle->alloc_info;
+	bundle->info.dev = dev;
 
 	pops = parent->msi_parent_ops;
 	snprintf(bundle->name, sizeof(bundle->name), "%s%s-%s",
@@ -1089,7 +1091,6 @@ bool msi_create_device_irq_domain(struct device *dev, unsigned int domid,
 	if (!domain)
 		return false;
 
-	domain->dev = dev;
 	dev->msi.data->__domains[domid].domain = domain;
 
 	if (msi_domain_prepare_irqs(domain, dev, hwsize, &bundle->alloc_info)) {
-- 
cgit v1.2.3


From 9047685cfd2911c36ce89a16270aafa71057c507 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 26 Jun 2025 18:42:44 +0300
Subject: PM: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://patch.msgid.link/20250626154244.324265-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 include/linux/pm.h | 11 ++++++-----
 1 file changed, 6 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pm.h b/include/linux/pm.h
index f0bd8fbae4f2..938b1b446a5d 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -8,14 +8,15 @@
 #ifndef _LINUX_PM_H
 #define _LINUX_PM_H
 
+#include <linux/completion.h>
 #include <linux/export.h>
-#include <linux/list.h>
-#include <linux/workqueue.h>
+#include <linux/hrtimer_types.h>
+#include <linux/mutex.h>
 #include <linux/spinlock.h>
+#include <linux/types.h>
+#include <linux/util_macros.h>
 #include <linux/wait.h>
-#include <linux/timer.h>
-#include <linux/hrtimer.h>
-#include <linux/completion.h>
+#include <linux/workqueue_types.h>
 
 /*
  * Callbacks for platform drivers to implement.
-- 
cgit v1.2.3


From c021c1b38f90d639423c1369625daa703a8472ea Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 27 Jun 2025 21:08:48 +0200
Subject: PM: Move two sleep-related functions under CONFIG_PM_SLEEP

Since pm_runtime_force_resume() and pm_runtime_need_not_resume() are only
needed for handling system-wide PM transitions, there is no reason to
compile them in if CONFIG_PM_SLEEP is unset.

Accordingly, move them under CONFIG_PM_SLEEP and make the static
inline stub for pm_runtime_force_resume() return an error to indicate
that it should not be used outside CONFIG_PM_SLEEP.

Putting pm_runtime_force_resume() also allows subsequent changes to
be more straightforward because this function is going to access a
device PM flag that is only defined when CONFIG_PM_SLEEP is set.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://patch.msgid.link/3384523.aeNJFYEL58@rjwysocki.net
---
 drivers/base/power/runtime.c | 18 +++++++++++-------
 include/linux/pm_runtime.h   | 16 ++++++++++++----
 2 files changed, 23 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 7dd815ab83a0..fe1f7cc663ac 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1941,13 +1941,6 @@ void pm_runtime_drop_link(struct device_link *link)
 	pm_request_idle(link->supplier);
 }
 
-bool pm_runtime_need_not_resume(struct device *dev)
-{
-	return atomic_read(&dev->power.usage_count) <= 1 &&
-		(atomic_read(&dev->power.child_count) == 0 ||
-		 dev->power.ignore_children);
-}
-
 /**
  * pm_runtime_force_suspend - Force a device into suspend state if needed.
  * @dev: Device to suspend.
@@ -2009,6 +2002,8 @@ err:
 }
 EXPORT_SYMBOL_GPL(pm_runtime_force_suspend);
 
+#ifdef CONFIG_PM_SLEEP
+
 /**
  * pm_runtime_force_resume - Force a device into resume state if needed.
  * @dev: Device to resume.
@@ -2052,3 +2047,12 @@ out:
 	return ret;
 }
 EXPORT_SYMBOL_GPL(pm_runtime_force_resume);
+
+bool pm_runtime_need_not_resume(struct device *dev)
+{
+	return atomic_read(&dev->power.usage_count) <= 1 &&
+		(atomic_read(&dev->power.child_count) == 0 ||
+		 dev->power.ignore_children);
+}
+
+#endif /* CONFIG_PM_SLEEP */
diff --git a/include/linux/pm_runtime.h b/include/linux/pm_runtime.h
index e7cb70fcc0af..9bea07f22041 100644
--- a/include/linux/pm_runtime.h
+++ b/include/linux/pm_runtime.h
@@ -66,9 +66,7 @@ static inline bool queue_pm_work(struct work_struct *work)
 
 extern int pm_generic_runtime_suspend(struct device *dev);
 extern int pm_generic_runtime_resume(struct device *dev);
-extern bool pm_runtime_need_not_resume(struct device *dev);
 extern int pm_runtime_force_suspend(struct device *dev);
-extern int pm_runtime_force_resume(struct device *dev);
 
 extern int __pm_runtime_idle(struct device *dev, int rpmflags);
 extern int __pm_runtime_suspend(struct device *dev, int rpmflags);
@@ -257,9 +255,7 @@ static inline bool queue_pm_work(struct work_struct *work) { return false; }
 
 static inline int pm_generic_runtime_suspend(struct device *dev) { return 0; }
 static inline int pm_generic_runtime_resume(struct device *dev) { return 0; }
-static inline bool pm_runtime_need_not_resume(struct device *dev) {return true; }
 static inline int pm_runtime_force_suspend(struct device *dev) { return 0; }
-static inline int pm_runtime_force_resume(struct device *dev) { return 0; }
 
 static inline int __pm_runtime_idle(struct device *dev, int rpmflags)
 {
@@ -330,6 +326,18 @@ static inline void pm_runtime_release_supplier(struct device_link *link) {}
 
 #endif /* !CONFIG_PM */
 
+#ifdef CONFIG_PM_SLEEP
+
+bool pm_runtime_need_not_resume(struct device *dev);
+int pm_runtime_force_resume(struct device *dev);
+
+#else /* !CONFIG_PM_SLEEP */
+
+static inline bool pm_runtime_need_not_resume(struct device *dev) {return true; }
+static inline int pm_runtime_force_resume(struct device *dev) { return -ENXIO; }
+
+#endif /* CONFIG_PM_SLEEP */
+
 /**
  * pm_runtime_idle - Conditionally set up autosuspend of a device or suspend it.
  * @dev: Target device.
-- 
cgit v1.2.3


From ffda4ca4608ea811aee2aace211bbf27c68a8853 Mon Sep 17 00:00:00 2001
From: "Rafael J. Wysocki" <rafael.j.wysocki@intel.com>
Date: Fri, 27 Jun 2025 21:23:42 +0200
Subject: PM: sleep: Add strict_midlayer flag to struct dev_pm_info

Add a new flag, called strict_midlayer, to struct dev_pm_info, along
with helper functions for updating and reading its value, to allow
middle layer code that provides proper callbacks for device suspend-
resume during system-wide PM transitions to let pm_runtime_force_suspend()
and and pm_runtime_force_resume() know that they should only invoke
runtime PM callbacks coming from the device's driver.

Namely, if this flag is set, pm_runtime_force_suspend() and
and pm_runtime_force_resume() will invoke runtime PM callbacks
provided by the device's driver directly with the assumption that
they have been called via a middle layer callback for device suspend
or resume, respectively.

For instance, acpi_general_pm_domain provides specific
callback functions for system suspend, acpi_subsys_suspend(),
acpi_subsys_suspend_late() and acpi_subsys_suspend_noirq(), and
it does not expect its runtime suspend callback function,
acpi_subsys_runtime_suspend(), to be invoked at any point during
system suspend. In particular, it does not expect that function
to be called from within any of the system suspend callback functions
mentioned above which would happen if a device driver collaborating
with acpi_general_pm_domain used pm_runtime_force_suspend() as its
callback function for any system suspend phase later than "prepare".

The new flag allows this expectation of acpi_general_pm_domain to
be formally expressed, which is going to be done subsequently.

Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://patch.msgid.link/24017035.6Emhk5qWAg@rjwysocki.net
---
 drivers/base/power/runtime.c | 21 +++++++++++++++++++--
 include/linux/device.h       | 27 +++++++++++++++++++++++++++
 include/linux/pm.h           |  1 +
 3 files changed, 47 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/power/runtime.c b/drivers/base/power/runtime.c
index 8cd1a4db5e84..05ff3d2209e6 100644
--- a/drivers/base/power/runtime.c
+++ b/drivers/base/power/runtime.c
@@ -1958,6 +1958,23 @@ void pm_runtime_drop_link(struct device_link *link)
 	pm_request_idle(link->supplier);
 }
 
+static pm_callback_t get_callback(struct device *dev, size_t cb_offset)
+{
+	/*
+	 * Setting power.strict_midlayer means that the middle layer
+	 * code does not want its runtime PM callbacks to be invoked via
+	 * pm_runtime_force_suspend() and pm_runtime_force_resume(), so
+	 * return a direct pointer to the driver callback in that case.
+	 */
+	if (dev_pm_strict_midlayer_is_set(dev))
+		return __rpm_get_driver_callback(dev, cb_offset);
+
+	return __rpm_get_callback(dev, cb_offset);
+}
+
+#define GET_CALLBACK(dev, callback) \
+		get_callback(dev, offsetof(struct dev_pm_ops, callback))
+
 /**
  * pm_runtime_force_suspend - Force a device into suspend state if needed.
  * @dev: Device to suspend.
@@ -1984,7 +2001,7 @@ int pm_runtime_force_suspend(struct device *dev)
 	if (pm_runtime_status_suspended(dev) || dev->power.needs_force_resume)
 		return 0;
 
-	callback = RPM_GET_CALLBACK(dev, runtime_suspend);
+	callback = GET_CALLBACK(dev, runtime_suspend);
 
 	dev_pm_enable_wake_irq_check(dev, true);
 	ret = callback ? callback(dev) : 0;
@@ -2046,7 +2063,7 @@ int pm_runtime_force_resume(struct device *dev)
 	    pm_runtime_status_suspended(dev)))
 		goto out;
 
-	callback = RPM_GET_CALLBACK(dev, runtime_resume);
+	callback = GET_CALLBACK(dev, runtime_resume);
 
 	dev_pm_disable_wake_irq_check(dev, false);
 	ret = callback ? callback(dev) : 0;
diff --git a/include/linux/device.h b/include/linux/device.h
index 4940db137fff..5137f9d213ec 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -879,6 +879,33 @@ static inline bool dev_pm_smart_suspend(struct device *dev)
 #endif
 }
 
+/*
+ * dev_pm_set_strict_midlayer - Update the device's power.strict_midlayer flag
+ * @dev: Target device.
+ * @val: New flag value.
+ *
+ * When set, power.strict_midlayer means that the middle layer power management
+ * code (typically, a bus type or a PM domain) does not expect its runtime PM
+ * suspend callback to be invoked at all during system-wide PM transitions and
+ * it does not expect its runtime PM resume callback to be invoked at any point
+ * when runtime PM is disabled for the device during system-wide PM transitions.
+ */
+static inline void dev_pm_set_strict_midlayer(struct device *dev, bool val)
+{
+#ifdef CONFIG_PM_SLEEP
+	dev->power.strict_midlayer = val;
+#endif
+}
+
+static inline bool dev_pm_strict_midlayer_is_set(struct device *dev)
+{
+#ifdef CONFIG_PM_SLEEP
+	return dev->power.strict_midlayer;
+#else
+	return false;
+#endif
+}
+
 static inline void device_lock(struct device *dev)
 {
 	mutex_lock(&dev->mutex);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index f0bd8fbae4f2..4149d45f6f76 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -683,6 +683,7 @@ struct dev_pm_info {
 	bool			smart_suspend:1;	/* Owned by the PM core */
 	bool			must_resume:1;		/* Owned by the PM core */
 	bool			may_skip_resume:1;	/* Set by subsystems */
+	bool			strict_midlayer:1;
 #else
 	bool			should_wakeup:1;
 #endif
-- 
cgit v1.2.3


From 803f0700a3bbf528c4c624a22f87d08178ca0fbe Mon Sep 17 00:00:00 2001
From: Tao Chen <chen.dylane@linux.dev>
Date: Wed, 2 Jul 2025 23:39:56 +0800
Subject: bpf: Show precise link_type for {uprobe,kprobe}_multi fdinfo

Alexei suggested, 'link_type' can be more precise and differentiate
for human in fdinfo. In fact BPF_LINK_TYPE_KPROBE_MULTI includes
kretprobe_multi type, the same as BPF_LINK_TYPE_UPROBE_MULTI, so we
can show it more concretely.

link_type:	kprobe_multi
link_id:	1
prog_tag:	d2b307e915f0dd37
...
link_type:	kretprobe_multi
link_id:	2
prog_tag:	ab9ea0545870781d
...
link_type:	uprobe_multi
link_id:	9
prog_tag:	e729f789e34a8eca
...
link_type:	uretprobe_multi
link_id:	10
prog_tag:	7db356c03e61a4d4

Co-developed-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Tao Chen <chen.dylane@linux.dev>
Link: https://lore.kernel.org/r/20250702153958.639852-1-chen.dylane@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h      |  1 +
 kernel/bpf/syscall.c     |  9 ++++++++-
 kernel/trace/bpf_trace.c | 10 ++++------
 3 files changed, 13 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 5dd556e89cce..287c956cdbd2 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1702,6 +1702,7 @@ struct bpf_link {
 	 * link's semantics is determined by target attach hook
 	 */
 	bool sleepable;
+	u32 flags;
 	/* rcu is used before freeing, work can be used to schedule that
 	 * RCU-based freeing before that, so they never overlap
 	 */
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 56500381c28a..f1d9ee9717a1 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3228,7 +3228,14 @@ static void bpf_link_show_fdinfo(struct seq_file *m, struct file *filp)
 	char prog_tag[sizeof(prog->tag) * 2 + 1] = { };
 
 	if (type < ARRAY_SIZE(bpf_link_type_strs) && bpf_link_type_strs[type]) {
-		seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]);
+		if (link->type == BPF_LINK_TYPE_KPROBE_MULTI)
+			seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_KPROBE_MULTI_RETURN ?
+				   "kretprobe_multi" : "kprobe_multi");
+		else if (link->type == BPF_LINK_TYPE_UPROBE_MULTI)
+			seq_printf(m, "link_type:\t%s\n", link->flags == BPF_F_UPROBE_MULTI_RETURN ?
+				   "uretprobe_multi" : "uprobe_multi");
+		else
+			seq_printf(m, "link_type:\t%s\n", bpf_link_type_strs[type]);
 	} else {
 		WARN_ONCE(1, "missing BPF_LINK_TYPE(...) for link type %u\n", type);
 		seq_printf(m, "link_type:\t<%u>\n", type);
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 0a06ea6638fe..81d7a4e5ae15 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2466,7 +2466,6 @@ struct bpf_kprobe_multi_link {
 	u32 cnt;
 	u32 mods_cnt;
 	struct module **mods;
-	u32 flags;
 };
 
 struct bpf_kprobe_multi_run_ctx {
@@ -2586,7 +2585,7 @@ static int bpf_kprobe_multi_link_fill_link_info(const struct bpf_link *link,
 
 	kmulti_link = container_of(link, struct bpf_kprobe_multi_link, link);
 	info->kprobe_multi.count = kmulti_link->cnt;
-	info->kprobe_multi.flags = kmulti_link->flags;
+	info->kprobe_multi.flags = kmulti_link->link.flags;
 	info->kprobe_multi.missed = kmulti_link->fp.nmissed;
 
 	if (!uaddrs)
@@ -2976,7 +2975,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	link->addrs = addrs;
 	link->cookies = cookies;
 	link->cnt = cnt;
-	link->flags = flags;
+	link->link.flags = flags;
 
 	if (cookies) {
 		/*
@@ -3045,7 +3044,6 @@ struct bpf_uprobe_multi_link {
 	struct path path;
 	struct bpf_link link;
 	u32 cnt;
-	u32 flags;
 	struct bpf_uprobe *uprobes;
 	struct task_struct *task;
 };
@@ -3109,7 +3107,7 @@ static int bpf_uprobe_multi_link_fill_link_info(const struct bpf_link *link,
 
 	umulti_link = container_of(link, struct bpf_uprobe_multi_link, link);
 	info->uprobe_multi.count = umulti_link->cnt;
-	info->uprobe_multi.flags = umulti_link->flags;
+	info->uprobe_multi.flags = umulti_link->link.flags;
 	info->uprobe_multi.pid = umulti_link->task ?
 				 task_pid_nr_ns(umulti_link->task, task_active_pid_ns(current)) : 0;
 
@@ -3369,7 +3367,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	link->uprobes = uprobes;
 	link->path = path;
 	link->task = task;
-	link->flags = flags;
+	link->link.flags = flags;
 
 	bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
 		      &bpf_uprobe_multi_link_lops, prog);
-- 
cgit v1.2.3


From 0426729f46cd1f6354fad07267a21579186a5757 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 3 Jul 2025 13:48:07 -0700
Subject: bpf: Refactor bprintf buffer support

Refactor code to be able to get and put bprintf buffers and use
bpf_printf_prepare independently. This will be used in the next patch to
implement BPF streams support, particularly as a staging buffer for
strings that need to be formatted and then allocated and pushed into a
stream.

Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250703204818.925464-2-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h  | 15 ++++++++++++++-
 kernel/bpf/helpers.c | 26 +++++++++++---------------
 2 files changed, 25 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 287c956cdbd2..a07451457d9e 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3551,6 +3551,16 @@ bool btf_id_set_contains(const struct btf_id_set *set, u32 id);
 #define MAX_BPRINTF_VARARGS		12
 #define MAX_BPRINTF_BUF			1024
 
+/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary
+ * arguments representation.
+ */
+#define MAX_BPRINTF_BIN_ARGS	512
+
+struct bpf_bprintf_buffers {
+	char bin_args[MAX_BPRINTF_BIN_ARGS];
+	char buf[MAX_BPRINTF_BUF];
+};
+
 struct bpf_bprintf_data {
 	u32 *bin_args;
 	char *buf;
@@ -3558,9 +3568,12 @@ struct bpf_bprintf_data {
 	bool get_buf;
 };
 
-int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
+int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 num_args, struct bpf_bprintf_data *data);
 void bpf_bprintf_cleanup(struct bpf_bprintf_data *data);
+int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs);
+void bpf_put_buffers(void);
+
 
 #ifdef CONFIG_BPF_LSM
 void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype);
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index 5269381d6d3d..da66ce307e75 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -764,22 +764,13 @@ static int bpf_trace_copy_string(char *buf, void *unsafe_ptr, char fmt_ptype,
 	return -EINVAL;
 }
 
-/* Per-cpu temp buffers used by printf-like helpers to store the bprintf binary
- * arguments representation.
- */
-#define MAX_BPRINTF_BIN_ARGS	512
-
 /* Support executing three nested bprintf helper calls on a given CPU */
 #define MAX_BPRINTF_NEST_LEVEL	3
-struct bpf_bprintf_buffers {
-	char bin_args[MAX_BPRINTF_BIN_ARGS];
-	char buf[MAX_BPRINTF_BUF];
-};
 
 static DEFINE_PER_CPU(struct bpf_bprintf_buffers[MAX_BPRINTF_NEST_LEVEL], bpf_bprintf_bufs);
 static DEFINE_PER_CPU(int, bpf_bprintf_nest_level);
 
-static int try_get_buffers(struct bpf_bprintf_buffers **bufs)
+int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs)
 {
 	int nest_level;
 
@@ -795,16 +786,21 @@ static int try_get_buffers(struct bpf_bprintf_buffers **bufs)
 	return 0;
 }
 
-void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
+void bpf_put_buffers(void)
 {
-	if (!data->bin_args && !data->buf)
-		return;
 	if (WARN_ON_ONCE(this_cpu_read(bpf_bprintf_nest_level) == 0))
 		return;
 	this_cpu_dec(bpf_bprintf_nest_level);
 	preempt_enable();
 }
 
+void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
+{
+	if (!data->bin_args && !data->buf)
+		return;
+	bpf_put_buffers();
+}
+
 /*
  * bpf_bprintf_prepare - Generic pass on format strings for bprintf-like helpers
  *
@@ -819,7 +815,7 @@ void bpf_bprintf_cleanup(struct bpf_bprintf_data *data)
  * In argument preparation mode, if 0 is returned, safe temporary buffers are
  * allocated and bpf_bprintf_cleanup should be called to free them after use.
  */
-int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
+int bpf_bprintf_prepare(const char *fmt, u32 fmt_size, const u64 *raw_args,
 			u32 num_args, struct bpf_bprintf_data *data)
 {
 	bool get_buffers = (data->get_bin_args && num_args) || data->get_buf;
@@ -835,7 +831,7 @@ int bpf_bprintf_prepare(char *fmt, u32 fmt_size, const u64 *raw_args,
 		return -EINVAL;
 	fmt_size = fmt_end - fmt;
 
-	if (get_buffers && try_get_buffers(&buffers))
+	if (get_buffers && bpf_try_get_buffers(&buffers))
 		return -EBUSY;
 
 	if (data->get_bin_args) {
-- 
cgit v1.2.3


From 5ab154f1463a111e1dc8fd5d31eaa7a2a71fe2e6 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 3 Jul 2025 13:48:08 -0700
Subject: bpf: Introduce BPF standard streams

Add support for a stream API to the kernel and expose related kfuncs to
BPF programs. Two streams are exposed, BPF_STDOUT and BPF_STDERR. These
can be used for printing messages that can be consumed from user space,
thus it's similar in spirit to existing trace_pipe interface.

The kernel will use the BPF_STDERR stream to notify the program of any
errors encountered at runtime. BPF programs themselves may use both
streams for writing debug messages. BPF library-like code may use
BPF_STDERR to print warnings or errors on misuse at runtime.

The implementation of a stream is as follows. Everytime a message is
emitted from the kernel (directly, or through a BPF program), a record
is allocated by bump allocating from per-cpu region backed by a page
obtained using alloc_pages_nolock(). This ensures that we can allocate
memory from any context. The eventual plan is to discard this scheme in
favor of Alexei's kmalloc_nolock() [0].

This record is then locklessly inserted into a list (llist_add()) so
that the printing side doesn't require holding any locks, and works in
any context. Each stream has a maximum capacity of 4MB of text, and each
printed message is accounted against this limit.

Messages from a program are emitted using the bpf_stream_vprintk kfunc,
which takes a stream_id argument in addition to working otherwise
similar to bpf_trace_vprintk.

The bprintf buffer helpers are extracted out to be reused for printing
the string into them before copying it into the stream, so that we can
(with the defined max limit) format a string and know its true length
before performing allocations of the stream element.

For consuming elements from a stream, we expose a bpf(2) syscall command
named BPF_PROG_STREAM_READ_BY_FD, which allows reading data from the
stream of a given prog_fd into a user space buffer. The main logic is
implemented in bpf_stream_read(). The log messages are queued in
bpf_stream::log by the bpf_stream_vprintk kfunc, and then pulled and
ordered correctly in the stream backlog.

For this purpose, we hold a lock around bpf_stream_backlog_peek(), as
llist_del_first() (if we maintained a second lockless list for the
backlog) wouldn't be safe from multiple threads anyway. Then, if we
fail to find something in the backlog log, we splice out everything from
the lockless log, and place it in the backlog log, and then return the
head of the backlog. Once the full length of the element is consumed, we
will pop it and free it.

The lockless list bpf_stream::log is a LIFO stack. Elements obtained
using a llist_del_all() operation are in LIFO order, thus would break
the chronological ordering if printed directly. Hence, this batch of
messages is first reversed. Then, it is stashed into a separate list in
the stream, i.e. the backlog_log. The head of this list is the actual
message that should always be returned to the caller. All of this is
done in bpf_stream_backlog_fill().

From the kernel side, the writing into the stream will be a bit more
involved than the typical printk. First, the kernel typically may print
a collection of messages into the stream, and parallel writers into the
stream may suffer from interleaving of messages. To ensure each group of
messages is visible atomically, we can lift the advantage of using a
lockless list for pushing in messages.

To enable this, we add a bpf_stream_stage() macro, and require kernel
users to use bpf_stream_printk statements for the passed expression to
write into the stream. Underneath the macro, we have a message staging
API, where a bpf_stream_stage object on the stack accumulates the
messages being printed into a local llist_head, and then a commit
operation splices the whole batch into the stream's lockless log list.

This is especially pertinent for rqspinlock deadlock messages printed to
program streams. After this change, we see each deadlock invocation as a
non-interleaving contiguous message without any confusion on the
reader's part, improving their user experience in debugging the fault.

While programs cannot benefit from this staged stream writing API, they
could just as well hold an rqspinlock around their print statements to
serialize messages, hence this is kept kernel-internal for now.

Overall, this infrastructure provides NMI-safe any context printing of
messages to two dedicated streams.

Later patches will add support for printing splats in case of BPF arena
page faults, rqspinlock deadlocks, and cond_break timeouts, and
integration of this facility into bpftool for dumping messages to user
space.

  [0]: https://lore.kernel.org/bpf/20250501032718.65476-1-alexei.starovoitov@gmail.com

Reviewed-by: Eduard Zingerman <eddyz87@gmail.com>
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250703204818.925464-3-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            |  52 +++++
 include/uapi/linux/bpf.h       |  24 +++
 kernel/bpf/Makefile            |   2 +-
 kernel/bpf/core.c              |   5 +
 kernel/bpf/helpers.c           |   1 +
 kernel/bpf/stream.c            | 478 +++++++++++++++++++++++++++++++++++++++++
 kernel/bpf/syscall.c           |  25 +++
 kernel/bpf/verifier.c          |   1 +
 tools/include/uapi/linux/bpf.h |  24 +++
 9 files changed, 611 insertions(+), 1 deletion(-)
 create mode 100644 kernel/bpf/stream.c

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a07451457d9e..f61aeccb23c3 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1538,6 +1538,37 @@ struct btf_mod_pair {
 
 struct bpf_kfunc_desc_tab;
 
+enum bpf_stream_id {
+	BPF_STDOUT = 1,
+	BPF_STDERR = 2,
+};
+
+struct bpf_stream_elem {
+	struct llist_node node;
+	int total_len;
+	int consumed_len;
+	char str[];
+};
+
+enum {
+	/* 100k bytes */
+	BPF_STREAM_MAX_CAPACITY = 100000ULL,
+};
+
+struct bpf_stream {
+	atomic_t capacity;
+	struct llist_head log;	/* list of in-flight stream elements in LIFO order */
+
+	struct mutex lock;  /* lock protecting backlog_{head,tail} */
+	struct llist_node *backlog_head; /* list of in-flight stream elements in FIFO order */
+	struct llist_node *backlog_tail; /* tail of the list above */
+};
+
+struct bpf_stream_stage {
+	struct llist_head log;
+	int len;
+};
+
 struct bpf_prog_aux {
 	atomic64_t refcnt;
 	u32 used_map_cnt;
@@ -1646,6 +1677,7 @@ struct bpf_prog_aux {
 		struct work_struct work;
 		struct rcu_head	rcu;
 	};
+	struct bpf_stream stream[2];
 };
 
 struct bpf_prog {
@@ -2409,6 +2441,7 @@ int  generic_map_delete_batch(struct bpf_map *map,
 struct bpf_map *bpf_map_get_curr_or_next(u32 *id);
 struct bpf_prog *bpf_prog_get_curr_or_next(u32 *id);
 
+
 int bpf_map_alloc_pages(const struct bpf_map *map, int nid,
 			unsigned long nr_pages, struct page **page_array);
 #ifdef CONFIG_MEMCG
@@ -3574,6 +3607,25 @@ void bpf_bprintf_cleanup(struct bpf_bprintf_data *data);
 int bpf_try_get_buffers(struct bpf_bprintf_buffers **bufs);
 void bpf_put_buffers(void);
 
+void bpf_prog_stream_init(struct bpf_prog *prog);
+void bpf_prog_stream_free(struct bpf_prog *prog);
+int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, int len);
+void bpf_stream_stage_init(struct bpf_stream_stage *ss);
+void bpf_stream_stage_free(struct bpf_stream_stage *ss);
+__printf(2, 3)
+int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...);
+int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog,
+			    enum bpf_stream_id stream_id);
+
+#define bpf_stream_printk(ss, ...) bpf_stream_stage_printk(&ss, __VA_ARGS__)
+
+#define bpf_stream_stage(ss, prog, stream_id, expr)            \
+	({                                                     \
+		bpf_stream_stage_init(&ss);                    \
+		(expr);                                        \
+		bpf_stream_stage_commit(&ss, prog, stream_id); \
+		bpf_stream_stage_free(&ss);                    \
+	})
 
 #ifdef CONFIG_BPF_LSM
 void bpf_cgroup_atype_get(u32 attach_btf_id, int cgroup_atype);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 719ba230032f..0670e15a6100 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -906,6 +906,17 @@ union bpf_iter_link_info {
  *		A new file descriptor (a nonnegative integer), or -1 if an
  *		error occurred (in which case, *errno* is set appropriately).
  *
+ * BPF_PROG_STREAM_READ_BY_FD
+ *	Description
+ *		Read data of a program's BPF stream. The program is identified
+ *		by *prog_fd*, and the stream is identified by the *stream_id*.
+ *		The data is copied to a buffer pointed to by *stream_buf*, and
+ *		filled less than or equal to *stream_buf_len* bytes.
+ *
+ *	Return
+ *		Number of bytes read from the stream on success, or -1 if an
+ *		error occurred (in which case, *errno* is set appropriately).
+ *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -961,6 +972,7 @@ enum bpf_cmd {
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
 	BPF_TOKEN_CREATE,
+	BPF_PROG_STREAM_READ_BY_FD,
 	__MAX_BPF_CMD,
 };
 
@@ -1463,6 +1475,11 @@ struct bpf_stack_build_id {
 
 #define BPF_OBJ_NAME_LEN 16U
 
+enum {
+	BPF_STREAM_STDOUT = 1,
+	BPF_STREAM_STDERR = 2,
+};
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -1849,6 +1866,13 @@ union bpf_attr {
 		__u32		bpffs_fd;
 	} token_create;
 
+	struct {
+		__aligned_u64	stream_buf;
+		__u32		stream_buf_len;
+		__u32		stream_id;
+		__u32		prog_fd;
+	} prog_stream_read;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 3a335c50e6e3..269c04a24664 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_BPF_SYSCALL) += bpf_local_storage.o bpf_task_storage.o
 obj-${CONFIG_BPF_LSM}	  += bpf_inode_storage.o
 obj-$(CONFIG_BPF_SYSCALL) += disasm.o mprog.o
 obj-$(CONFIG_BPF_JIT) += trampoline.o
-obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o rqspinlock.o
+obj-$(CONFIG_BPF_SYSCALL) += btf.o memalloc.o rqspinlock.o stream.o
 ifeq ($(CONFIG_MMU)$(CONFIG_64BIT),yy)
 obj-$(CONFIG_BPF_SYSCALL) += arena.o range_tree.o
 endif
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index e536a34a32c8..f0def24573ae 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -134,6 +134,10 @@ struct bpf_prog *bpf_prog_alloc_no_stats(unsigned int size, gfp_t gfp_extra_flag
 	mutex_init(&fp->aux->ext_mutex);
 	mutex_init(&fp->aux->dst_mutex);
 
+#ifdef CONFIG_BPF_SYSCALL
+	bpf_prog_stream_init(fp);
+#endif
+
 	return fp;
 }
 
@@ -2862,6 +2866,7 @@ static void bpf_prog_free_deferred(struct work_struct *work)
 	aux = container_of(work, struct bpf_prog_aux, work);
 #ifdef CONFIG_BPF_SYSCALL
 	bpf_free_kfunc_btf_tab(aux->kfunc_btf_tab);
+	bpf_prog_stream_free(aux->prog);
 #endif
 #ifdef CONFIG_CGROUP_BPF
 	if (aux->cgroup_atype != CGROUP_BPF_ATTACH_TYPE_INVALID)
diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
index da66ce307e75..6bfcbcdf6588 100644
--- a/kernel/bpf/helpers.c
+++ b/kernel/bpf/helpers.c
@@ -3825,6 +3825,7 @@ BTF_ID_FLAGS(func, bpf_strnstr);
 #if defined(CONFIG_BPF_LSM) && defined(CONFIG_CGROUPS)
 BTF_ID_FLAGS(func, bpf_cgroup_read_xattr, KF_RCU)
 #endif
+BTF_ID_FLAGS(func, bpf_stream_vprintk, KF_TRUSTED_ARGS)
 BTF_KFUNCS_END(common_btf_ids)
 
 static const struct btf_kfunc_id_set common_kfunc_set = {
diff --git a/kernel/bpf/stream.c b/kernel/bpf/stream.c
new file mode 100644
index 000000000000..e434541358db
--- /dev/null
+++ b/kernel/bpf/stream.c
@@ -0,0 +1,478 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
+
+#include <linux/bpf.h>
+#include <linux/bpf_mem_alloc.h>
+#include <linux/percpu.h>
+#include <linux/refcount.h>
+#include <linux/gfp.h>
+#include <linux/memory.h>
+#include <linux/local_lock.h>
+#include <linux/mutex.h>
+
+/*
+ * Simple per-CPU NMI-safe bump allocation mechanism, backed by the NMI-safe
+ * try_alloc_pages()/free_pages_nolock() primitives. We allocate a page and
+ * stash it in a local per-CPU variable, and bump allocate from the page
+ * whenever items need to be printed to a stream. Each page holds a global
+ * atomic refcount in its first 4 bytes, and then records of variable length
+ * that describe the printed messages. Once the global refcount has dropped to
+ * zero, it is a signal to free the page back to the kernel's page allocator,
+ * given all the individual records in it have been consumed.
+ *
+ * It is possible the same page is used to serve allocations across different
+ * programs, which may be consumed at different times individually, hence
+ * maintaining a reference count per-page is critical for correct lifetime
+ * tracking.
+ *
+ * The bpf_stream_page code will be replaced to use kmalloc_nolock() once it
+ * lands.
+ */
+struct bpf_stream_page {
+	refcount_t ref;
+	u32 consumed;
+	char buf[];
+};
+
+/* Available room to add data to a refcounted page. */
+#define BPF_STREAM_PAGE_SZ (PAGE_SIZE - offsetofend(struct bpf_stream_page, consumed))
+
+static DEFINE_PER_CPU(local_trylock_t, stream_local_lock) = INIT_LOCAL_TRYLOCK(stream_local_lock);
+static DEFINE_PER_CPU(struct bpf_stream_page *, stream_pcpu_page);
+
+static bool bpf_stream_page_local_lock(unsigned long *flags)
+{
+	return local_trylock_irqsave(&stream_local_lock, *flags);
+}
+
+static void bpf_stream_page_local_unlock(unsigned long *flags)
+{
+	local_unlock_irqrestore(&stream_local_lock, *flags);
+}
+
+static void bpf_stream_page_free(struct bpf_stream_page *stream_page)
+{
+	struct page *p;
+
+	if (!stream_page)
+		return;
+	p = virt_to_page(stream_page);
+	free_pages_nolock(p, 0);
+}
+
+static void bpf_stream_page_get(struct bpf_stream_page *stream_page)
+{
+	refcount_inc(&stream_page->ref);
+}
+
+static void bpf_stream_page_put(struct bpf_stream_page *stream_page)
+{
+	if (refcount_dec_and_test(&stream_page->ref))
+		bpf_stream_page_free(stream_page);
+}
+
+static void bpf_stream_page_init(struct bpf_stream_page *stream_page)
+{
+	refcount_set(&stream_page->ref, 1);
+	stream_page->consumed = 0;
+}
+
+static struct bpf_stream_page *bpf_stream_page_replace(void)
+{
+	struct bpf_stream_page *stream_page, *old_stream_page;
+	struct page *page;
+
+	page = alloc_pages_nolock(NUMA_NO_NODE, 0);
+	if (!page)
+		return NULL;
+	stream_page = page_address(page);
+	bpf_stream_page_init(stream_page);
+
+	old_stream_page = this_cpu_read(stream_pcpu_page);
+	if (old_stream_page)
+		bpf_stream_page_put(old_stream_page);
+	this_cpu_write(stream_pcpu_page, stream_page);
+	return stream_page;
+}
+
+static int bpf_stream_page_check_room(struct bpf_stream_page *stream_page, int len)
+{
+	int min = offsetof(struct bpf_stream_elem, str[0]);
+	int consumed = stream_page->consumed;
+	int total = BPF_STREAM_PAGE_SZ;
+	int rem = max(0, total - consumed - min);
+
+	/* Let's give room of at least 8 bytes. */
+	WARN_ON_ONCE(rem % 8 != 0);
+	rem = rem < 8 ? 0 : rem;
+	return min(len, rem);
+}
+
+static void bpf_stream_elem_init(struct bpf_stream_elem *elem, int len)
+{
+	init_llist_node(&elem->node);
+	elem->total_len = len;
+	elem->consumed_len = 0;
+}
+
+static struct bpf_stream_page *bpf_stream_page_from_elem(struct bpf_stream_elem *elem)
+{
+	unsigned long addr = (unsigned long)elem;
+
+	return (struct bpf_stream_page *)PAGE_ALIGN_DOWN(addr);
+}
+
+static struct bpf_stream_elem *bpf_stream_page_push_elem(struct bpf_stream_page *stream_page, int len)
+{
+	u32 consumed = stream_page->consumed;
+
+	stream_page->consumed += round_up(offsetof(struct bpf_stream_elem, str[len]), 8);
+	return (struct bpf_stream_elem *)&stream_page->buf[consumed];
+}
+
+static struct bpf_stream_elem *bpf_stream_page_reserve_elem(int len)
+{
+	struct bpf_stream_elem *elem = NULL;
+	struct bpf_stream_page *page;
+	int room = 0;
+
+	page = this_cpu_read(stream_pcpu_page);
+	if (!page)
+		page = bpf_stream_page_replace();
+	if (!page)
+		return NULL;
+
+	room = bpf_stream_page_check_room(page, len);
+	if (room != len)
+		page = bpf_stream_page_replace();
+	if (!page)
+		return NULL;
+	bpf_stream_page_get(page);
+	room = bpf_stream_page_check_room(page, len);
+	WARN_ON_ONCE(room != len);
+
+	elem = bpf_stream_page_push_elem(page, room);
+	bpf_stream_elem_init(elem, room);
+	return elem;
+}
+
+static struct bpf_stream_elem *bpf_stream_elem_alloc(int len)
+{
+	const int max_len = ARRAY_SIZE((struct bpf_bprintf_buffers){}.buf);
+	struct bpf_stream_elem *elem;
+	unsigned long flags;
+
+	BUILD_BUG_ON(max_len > BPF_STREAM_PAGE_SZ);
+	/*
+	 * Length denotes the amount of data to be written as part of stream element,
+	 * thus includes '\0' byte. We're capped by how much bpf_bprintf_buffers can
+	 * accomodate, therefore deny allocations that won't fit into them.
+	 */
+	if (len < 0 || len > max_len)
+		return NULL;
+
+	if (!bpf_stream_page_local_lock(&flags))
+		return NULL;
+	elem = bpf_stream_page_reserve_elem(len);
+	bpf_stream_page_local_unlock(&flags);
+	return elem;
+}
+
+static int __bpf_stream_push_str(struct llist_head *log, const char *str, int len)
+{
+	struct bpf_stream_elem *elem = NULL;
+
+	/*
+	 * Allocate a bpf_prog_stream_elem and push it to the bpf_prog_stream
+	 * log, elements will be popped at once and reversed to print the log.
+	 */
+	elem = bpf_stream_elem_alloc(len);
+	if (!elem)
+		return -ENOMEM;
+
+	memcpy(elem->str, str, len);
+	llist_add(&elem->node, log);
+
+	return 0;
+}
+
+static int bpf_stream_consume_capacity(struct bpf_stream *stream, int len)
+{
+	if (atomic_read(&stream->capacity) >= BPF_STREAM_MAX_CAPACITY)
+		return -ENOSPC;
+	if (atomic_add_return(len, &stream->capacity) >= BPF_STREAM_MAX_CAPACITY) {
+		atomic_sub(len, &stream->capacity);
+		return -ENOSPC;
+	}
+	return 0;
+}
+
+static void bpf_stream_release_capacity(struct bpf_stream *stream, struct bpf_stream_elem *elem)
+{
+	int len = elem->total_len;
+
+	atomic_sub(len, &stream->capacity);
+}
+
+static int bpf_stream_push_str(struct bpf_stream *stream, const char *str, int len)
+{
+	int ret = bpf_stream_consume_capacity(stream, len);
+
+	return ret ?: __bpf_stream_push_str(&stream->log, str, len);
+}
+
+static struct bpf_stream *bpf_stream_get(enum bpf_stream_id stream_id, struct bpf_prog_aux *aux)
+{
+	if (stream_id != BPF_STDOUT && stream_id != BPF_STDERR)
+		return NULL;
+	return &aux->stream[stream_id - 1];
+}
+
+static void bpf_stream_free_elem(struct bpf_stream_elem *elem)
+{
+	struct bpf_stream_page *p;
+
+	p = bpf_stream_page_from_elem(elem);
+	bpf_stream_page_put(p);
+}
+
+static void bpf_stream_free_list(struct llist_node *list)
+{
+	struct bpf_stream_elem *elem, *tmp;
+
+	llist_for_each_entry_safe(elem, tmp, list, node)
+		bpf_stream_free_elem(elem);
+}
+
+static struct llist_node *bpf_stream_backlog_peek(struct bpf_stream *stream)
+{
+	return stream->backlog_head;
+}
+
+static struct llist_node *bpf_stream_backlog_pop(struct bpf_stream *stream)
+{
+	struct llist_node *node;
+
+	node = stream->backlog_head;
+	if (stream->backlog_head == stream->backlog_tail)
+		stream->backlog_head = stream->backlog_tail = NULL;
+	else
+		stream->backlog_head = node->next;
+	return node;
+}
+
+static void bpf_stream_backlog_fill(struct bpf_stream *stream)
+{
+	struct llist_node *head, *tail;
+
+	if (llist_empty(&stream->log))
+		return;
+	tail = llist_del_all(&stream->log);
+	if (!tail)
+		return;
+	head = llist_reverse_order(tail);
+
+	if (!stream->backlog_head) {
+		stream->backlog_head = head;
+		stream->backlog_tail = tail;
+	} else {
+		stream->backlog_tail->next = head;
+		stream->backlog_tail = tail;
+	}
+
+	return;
+}
+
+static bool bpf_stream_consume_elem(struct bpf_stream_elem *elem, int *len)
+{
+	int rem = elem->total_len - elem->consumed_len;
+	int used = min(rem, *len);
+
+	elem->consumed_len += used;
+	*len -= used;
+
+	return elem->consumed_len == elem->total_len;
+}
+
+static int bpf_stream_read(struct bpf_stream *stream, void __user *buf, int len)
+{
+	int rem_len = len, cons_len, ret = 0;
+	struct bpf_stream_elem *elem = NULL;
+	struct llist_node *node;
+
+	mutex_lock(&stream->lock);
+
+	while (rem_len) {
+		int pos = len - rem_len;
+		bool cont;
+
+		node = bpf_stream_backlog_peek(stream);
+		if (!node) {
+			bpf_stream_backlog_fill(stream);
+			node = bpf_stream_backlog_peek(stream);
+		}
+		if (!node)
+			break;
+		elem = container_of(node, typeof(*elem), node);
+
+		cons_len = elem->consumed_len;
+		cont = bpf_stream_consume_elem(elem, &rem_len) == false;
+
+		ret = copy_to_user(buf + pos, elem->str + cons_len,
+				   elem->consumed_len - cons_len);
+		/* Restore in case of error. */
+		if (ret) {
+			ret = -EFAULT;
+			elem->consumed_len = cons_len;
+			break;
+		}
+
+		if (cont)
+			continue;
+		bpf_stream_backlog_pop(stream);
+		bpf_stream_release_capacity(stream, elem);
+		bpf_stream_free_elem(elem);
+	}
+
+	mutex_unlock(&stream->lock);
+	return ret ? ret : len - rem_len;
+}
+
+int bpf_prog_stream_read(struct bpf_prog *prog, enum bpf_stream_id stream_id, void __user *buf, int len)
+{
+	struct bpf_stream *stream;
+
+	stream = bpf_stream_get(stream_id, prog->aux);
+	if (!stream)
+		return -ENOENT;
+	return bpf_stream_read(stream, buf, len);
+}
+
+__bpf_kfunc_start_defs();
+
+/*
+ * Avoid using enum bpf_stream_id so that kfunc users don't have to pull in the
+ * enum in headers.
+ */
+__bpf_kfunc int bpf_stream_vprintk(int stream_id, const char *fmt__str, const void *args, u32 len__sz, void *aux__prog)
+{
+	struct bpf_bprintf_data data = {
+		.get_bin_args	= true,
+		.get_buf	= true,
+	};
+	struct bpf_prog_aux *aux = aux__prog;
+	u32 fmt_size = strlen(fmt__str) + 1;
+	struct bpf_stream *stream;
+	u32 data_len = len__sz;
+	int ret, num_args;
+
+	stream = bpf_stream_get(stream_id, aux);
+	if (!stream)
+		return -ENOENT;
+
+	if (data_len & 7 || data_len > MAX_BPRINTF_VARARGS * 8 ||
+	    (data_len && !args))
+		return -EINVAL;
+	num_args = data_len / 8;
+
+	ret = bpf_bprintf_prepare(fmt__str, fmt_size, args, num_args, &data);
+	if (ret < 0)
+		return ret;
+
+	ret = bstr_printf(data.buf, MAX_BPRINTF_BUF, fmt__str, data.bin_args);
+	/* Exclude NULL byte during push. */
+	ret = bpf_stream_push_str(stream, data.buf, ret);
+	bpf_bprintf_cleanup(&data);
+
+	return ret;
+}
+
+__bpf_kfunc_end_defs();
+
+/* Added kfunc to common_btf_ids */
+
+void bpf_prog_stream_init(struct bpf_prog *prog)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) {
+		atomic_set(&prog->aux->stream[i].capacity, 0);
+		init_llist_head(&prog->aux->stream[i].log);
+		mutex_init(&prog->aux->stream[i].lock);
+		prog->aux->stream[i].backlog_head = NULL;
+		prog->aux->stream[i].backlog_tail = NULL;
+	}
+}
+
+void bpf_prog_stream_free(struct bpf_prog *prog)
+{
+	struct llist_node *list;
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(prog->aux->stream); i++) {
+		list = llist_del_all(&prog->aux->stream[i].log);
+		bpf_stream_free_list(list);
+		bpf_stream_free_list(prog->aux->stream[i].backlog_head);
+	}
+}
+
+void bpf_stream_stage_init(struct bpf_stream_stage *ss)
+{
+	init_llist_head(&ss->log);
+	ss->len = 0;
+}
+
+void bpf_stream_stage_free(struct bpf_stream_stage *ss)
+{
+	struct llist_node *node;
+
+	node = llist_del_all(&ss->log);
+	bpf_stream_free_list(node);
+}
+
+int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...)
+{
+	struct bpf_bprintf_buffers *buf;
+	va_list args;
+	int ret;
+
+	if (bpf_try_get_buffers(&buf))
+		return -EBUSY;
+
+	va_start(args, fmt);
+	ret = vsnprintf(buf->buf, ARRAY_SIZE(buf->buf), fmt, args);
+	va_end(args);
+	ss->len += ret;
+	/* Exclude NULL byte during push. */
+	ret = __bpf_stream_push_str(&ss->log, buf->buf, ret);
+	bpf_put_buffers();
+	return ret;
+}
+
+int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog,
+			    enum bpf_stream_id stream_id)
+{
+	struct llist_node *list, *head, *tail;
+	struct bpf_stream *stream;
+	int ret;
+
+	stream = bpf_stream_get(stream_id, prog->aux);
+	if (!stream)
+		return -EINVAL;
+
+	ret = bpf_stream_consume_capacity(stream, ss->len);
+	if (ret)
+		return ret;
+
+	list = llist_del_all(&ss->log);
+	head = tail = list;
+
+	if (!list)
+		return 0;
+	while (llist_next(list)) {
+		tail = llist_next(list);
+		list = tail;
+	}
+	llist_add_batch(head, tail, &stream->log);
+	return 0;
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index f1d9ee9717a1..7db7182a3057 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5943,6 +5943,28 @@ static int token_create(union bpf_attr *attr)
 	return bpf_token_create(attr);
 }
 
+#define BPF_PROG_STREAM_READ_BY_FD_LAST_FIELD prog_stream_read.prog_fd
+
+static int prog_stream_read(union bpf_attr *attr)
+{
+	char __user *buf = u64_to_user_ptr(attr->prog_stream_read.stream_buf);
+	u32 len = attr->prog_stream_read.stream_buf_len;
+	struct bpf_prog *prog;
+	int ret;
+
+	if (CHECK_ATTR(BPF_PROG_STREAM_READ_BY_FD))
+		return -EINVAL;
+
+	prog = bpf_prog_get(attr->prog_stream_read.prog_fd);
+	if (IS_ERR(prog))
+		return PTR_ERR(prog);
+
+	ret = bpf_prog_stream_read(prog, attr->prog_stream_read.stream_id, buf, len);
+	bpf_prog_put(prog);
+
+	return ret;
+}
+
 static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size)
 {
 	union bpf_attr attr;
@@ -6079,6 +6101,9 @@ static int __sys_bpf(enum bpf_cmd cmd, bpfptr_t uattr, unsigned int size)
 	case BPF_TOKEN_CREATE:
 		err = token_create(&attr);
 		break;
+	case BPF_PROG_STREAM_READ_BY_FD:
+		err = prog_stream_read(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 52e36fd23f40..9f09dcd2eabb 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -46,6 +46,7 @@ static const struct bpf_verifier_ops * const bpf_verifier_ops[] = {
 
 enum bpf_features {
 	BPF_FEAT_RDONLY_CAST_TO_VOID = 0,
+	BPF_FEAT_STREAMS	     = 1,
 	__MAX_BPF_FEAT,
 };
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 719ba230032f..0670e15a6100 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -906,6 +906,17 @@ union bpf_iter_link_info {
  *		A new file descriptor (a nonnegative integer), or -1 if an
  *		error occurred (in which case, *errno* is set appropriately).
  *
+ * BPF_PROG_STREAM_READ_BY_FD
+ *	Description
+ *		Read data of a program's BPF stream. The program is identified
+ *		by *prog_fd*, and the stream is identified by the *stream_id*.
+ *		The data is copied to a buffer pointed to by *stream_buf*, and
+ *		filled less than or equal to *stream_buf_len* bytes.
+ *
+ *	Return
+ *		Number of bytes read from the stream on success, or -1 if an
+ *		error occurred (in which case, *errno* is set appropriately).
+ *
  * NOTES
  *	eBPF objects (maps and programs) can be shared between processes.
  *
@@ -961,6 +972,7 @@ enum bpf_cmd {
 	BPF_LINK_DETACH,
 	BPF_PROG_BIND_MAP,
 	BPF_TOKEN_CREATE,
+	BPF_PROG_STREAM_READ_BY_FD,
 	__MAX_BPF_CMD,
 };
 
@@ -1463,6 +1475,11 @@ struct bpf_stack_build_id {
 
 #define BPF_OBJ_NAME_LEN 16U
 
+enum {
+	BPF_STREAM_STDOUT = 1,
+	BPF_STREAM_STDERR = 2,
+};
+
 union bpf_attr {
 	struct { /* anonymous struct used by BPF_MAP_CREATE command */
 		__u32	map_type;	/* one of enum bpf_map_type */
@@ -1849,6 +1866,13 @@ union bpf_attr {
 		__u32		bpffs_fd;
 	} token_create;
 
+	struct {
+		__aligned_u64	stream_buf;
+		__u32		stream_buf_len;
+		__u32		stream_id;
+		__u32		prog_fd;
+	} prog_stream_read;
+
 } __attribute__((aligned(8)));
 
 /* The description below is an attempt at providing documentation to eBPF
-- 
cgit v1.2.3


From 0e521efaf36350b8f783984541efa56f560c90b0 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 3 Jul 2025 13:48:09 -0700
Subject: bpf: Add function to extract program source info

Prepare a function for use in future patches that can extract the file
info, line info, and the source line number for a given BPF program
provided it's program counter.

Only the basename of the file path is provided, given it can be
excessively long in some cases.

This will be used in later patches to print source info to the BPF
stream.

Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250703204818.925464-4-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h |  3 +++
 kernel/bpf/core.c   | 47 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f61aeccb23c3..c3802af11bac 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3661,4 +3661,7 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog)
 	return prog->aux->func_idx != 0;
 }
 
+int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep,
+			   const char **linep, int *nump);
+
 #endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index f0def24573ae..2dc5b846ae50 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -3213,3 +3213,50 @@ EXPORT_SYMBOL(bpf_stats_enabled_key);
 
 EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception);
 EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_bulk_tx);
+
+#ifdef CONFIG_BPF_SYSCALL
+
+int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep,
+			   const char **linep, int *nump)
+{
+	int idx = -1, insn_start, insn_end, len;
+	struct bpf_line_info *linfo;
+	void **jited_linfo;
+	struct btf *btf;
+
+	btf = prog->aux->btf;
+	linfo = prog->aux->linfo;
+	jited_linfo = prog->aux->jited_linfo;
+
+	if (!btf || !linfo || !jited_linfo)
+		return -EINVAL;
+	len = prog->aux->func ? prog->aux->func[prog->aux->func_idx]->len : prog->len;
+
+	linfo = &prog->aux->linfo[prog->aux->linfo_idx];
+	jited_linfo = &prog->aux->jited_linfo[prog->aux->linfo_idx];
+
+	insn_start = linfo[0].insn_off;
+	insn_end = insn_start + len;
+
+	for (int i = 0; i < prog->aux->nr_linfo &&
+	     linfo[i].insn_off >= insn_start && linfo[i].insn_off < insn_end; i++) {
+		if (jited_linfo[i] >= (void *)ip)
+			break;
+		idx = i;
+	}
+
+	if (idx == -1)
+		return -ENOENT;
+
+	/* Get base component of the file path. */
+	*filep = btf_name_by_offset(btf, linfo[idx].file_name_off);
+	*filep = kbasename(*filep);
+	/* Obtain the source line, and strip whitespace in prefix. */
+	*linep = btf_name_by_offset(btf, linfo[idx].line_off);
+	while (isspace(**linep))
+		*linep += 1;
+	*nump = BPF_LINE_INFO_LINE_NUM(linfo[idx].line_col);
+	return 0;
+}
+
+#endif
-- 
cgit v1.2.3


From f0c53fd4a742f957da7077a691a85ef9775907dc Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 3 Jul 2025 13:48:11 -0700
Subject: bpf: Add function to find program from stack trace

In preparation of figuring out the closest program that led to the
current point in the kernel, implement a function that scans through the
stack trace and finds out the closest BPF program when walking down the
stack trace.

Special care needs to be taken to skip over kernel and BPF subprog
frames. We basically scan until we find a BPF main prog frame. The
assumption is that if a program calls into us transitively, we'll
hit it along the way. If not, we end up returning NULL.

Contextually the function will be used in places where we know the
program may have called into us.

Due to reliance on arch_bpf_stack_walk(), this function only works on
x86 with CONFIG_UNWINDER_ORC, arm64, and s390. Remove the warning from
arch_bpf_stack_walk as well since we call it outside bpf_throw()
context.

Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250703204818.925464-6-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/x86/net/bpf_jit_comp.c |  1 -
 include/linux/bpf.h         |  1 +
 kernel/bpf/core.c           | 33 +++++++++++++++++++++++++++++++++
 3 files changed, 34 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 15672cb926fc..40e1b3b9634f 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -3845,7 +3845,6 @@ void arch_bpf_stack_walk(bool (*consume_fn)(void *cookie, u64 ip, u64 sp, u64 bp
 	}
 	return;
 #endif
-	WARN(1, "verification of programs using bpf_throw should have failed\n");
 }
 
 void bpf_arch_poke_desc_update(struct bpf_jit_poke_descriptor *poke,
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index c3802af11bac..b267c378d884 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3663,5 +3663,6 @@ static inline bool bpf_is_subprog(const struct bpf_prog *prog)
 
 int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char **filep,
 			   const char **linep, int *nump);
+struct bpf_prog *bpf_prog_find_from_stack(void);
 
 #endif /* _LINUX_BPF_H */
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 833442661742..037d67cf5fb1 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -3262,4 +3262,37 @@ int bpf_prog_get_file_line(struct bpf_prog *prog, unsigned long ip, const char *
 	return 0;
 }
 
+struct walk_stack_ctx {
+	struct bpf_prog *prog;
+};
+
+static bool find_from_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp)
+{
+	struct walk_stack_ctx *ctxp = cookie;
+	struct bpf_prog *prog;
+
+	/*
+	 * The RCU read lock is held to safely traverse the latch tree, but we
+	 * don't need its protection when accessing the prog, since it has an
+	 * active stack frame on the current stack trace, and won't disappear.
+	 */
+	rcu_read_lock();
+	prog = bpf_prog_ksym_find(ip);
+	rcu_read_unlock();
+	if (!prog)
+		return true;
+	if (bpf_is_subprog(prog))
+		return true;
+	ctxp->prog = prog;
+	return false;
+}
+
+struct bpf_prog *bpf_prog_find_from_stack(void)
+{
+	struct walk_stack_ctx ctx = {};
+
+	arch_bpf_stack_walk(find_from_stack_cb, &ctx);
+	return ctx.prog;
+}
+
 #endif
-- 
cgit v1.2.3


From d7c431cafcb4917b0d87b5cd10637cd47b6c8d79 Mon Sep 17 00:00:00 2001
From: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Date: Thu, 3 Jul 2025 13:48:12 -0700
Subject: bpf: Add dump_stack() analogue to print to BPF stderr

Introduce a kernel function which is the analogue of dump_stack()
printing some useful information and the stack trace. This is not
exposed to BPF programs yet, but can be made available in the future.

When we have a program counter for a BPF program in the stack trace,
also additionally output the filename and line number to make the trace
helpful. The rest of the trace can be passed into ./decode_stacktrace.sh
to obtain the line numbers for kernel symbols.

Reviewed-by: Emil Tsalapatis <emil@etsalapatis.com>
Signed-off-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Link: https://lore.kernel.org/r/20250703204818.925464-7-memxor@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h |  2 ++
 kernel/bpf/stream.c | 48 ++++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 50 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index b267c378d884..34dd90ec7fad 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -3616,8 +3616,10 @@ __printf(2, 3)
 int bpf_stream_stage_printk(struct bpf_stream_stage *ss, const char *fmt, ...);
 int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog,
 			    enum bpf_stream_id stream_id);
+int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss);
 
 #define bpf_stream_printk(ss, ...) bpf_stream_stage_printk(&ss, __VA_ARGS__)
+#define bpf_stream_dump_stack(ss) bpf_stream_stage_dump_stack(&ss)
 
 #define bpf_stream_stage(ss, prog, stream_id, expr)            \
 	({                                                     \
diff --git a/kernel/bpf/stream.c b/kernel/bpf/stream.c
index e434541358db..8c842f845245 100644
--- a/kernel/bpf/stream.c
+++ b/kernel/bpf/stream.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2025 Meta Platforms, Inc. and affiliates. */
 
 #include <linux/bpf.h>
+#include <linux/filter.h>
 #include <linux/bpf_mem_alloc.h>
 #include <linux/percpu.h>
 #include <linux/refcount.h>
@@ -476,3 +477,50 @@ int bpf_stream_stage_commit(struct bpf_stream_stage *ss, struct bpf_prog *prog,
 	llist_add_batch(head, tail, &stream->log);
 	return 0;
 }
+
+struct dump_stack_ctx {
+	struct bpf_stream_stage *ss;
+	int err;
+};
+
+static bool dump_stack_cb(void *cookie, u64 ip, u64 sp, u64 bp)
+{
+	struct dump_stack_ctx *ctxp = cookie;
+	const char *file = "", *line = "";
+	struct bpf_prog *prog;
+	int num, ret;
+
+	rcu_read_lock();
+	prog = bpf_prog_ksym_find(ip);
+	rcu_read_unlock();
+	if (prog) {
+		ret = bpf_prog_get_file_line(prog, ip, &file, &line, &num);
+		if (ret < 0)
+			goto end;
+		ctxp->err = bpf_stream_stage_printk(ctxp->ss, "%pS\n  %s @ %s:%d\n",
+						    (void *)ip, line, file, num);
+		return !ctxp->err;
+	}
+end:
+	ctxp->err = bpf_stream_stage_printk(ctxp->ss, "%pS\n", (void *)ip);
+	return !ctxp->err;
+}
+
+int bpf_stream_stage_dump_stack(struct bpf_stream_stage *ss)
+{
+	struct dump_stack_ctx ctx = { .ss = ss };
+	int ret;
+
+	ret = bpf_stream_stage_printk(ss, "CPU: %d UID: %d PID: %d Comm: %s\n",
+				      raw_smp_processor_id(), __kuid_val(current_real_cred()->euid),
+				      current->pid, current->comm);
+	if (ret)
+		return ret;
+	ret = bpf_stream_stage_printk(ss, "Call trace:\n");
+	if (ret)
+		return ret;
+	arch_bpf_stack_walk(dump_stack_cb, &ctx);
+	if (ctx.err)
+		return ctx.err;
+	return bpf_stream_stage_printk(ss, "\n");
+}
-- 
cgit v1.2.3


From 82bc4abf28d8147dd5da9ba52f0aa1bac23c125e Mon Sep 17 00:00:00 2001
From: Yonghong Song <yonghong.song@linux.dev>
Date: Thu, 3 Jul 2025 07:11:17 -0700
Subject: bpf: Avoid putting struct bpf_scc_callchain variables on the stack

Add a 'struct bpf_scc_callchain callchain_buf' field in bpf_verifier_env.
This way, the previous bpf_scc_callchain local variables can be
replaced by taking address of env->callchain_buf. This can reduce stack
usage and fix the following error:
    kernel/bpf/verifier.c:19921:12: error: stack frame size (1368) exceeds limit (1280) in 'do_check'
        [-Werror,-Wframe-larger-than]

Reported-by: Arnd Bergmann <arnd@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Acked-by: Eduard Zingerman <eddyz87@gmail.com>
Signed-off-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/r/20250703141117.1485108-1-yonghong.song@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf_verifier.h |  1 +
 kernel/bpf/verifier.c        | 36 ++++++++++++++++++------------------
 2 files changed, 19 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 7e459e839f8b..94defa405c85 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -841,6 +841,7 @@ struct bpf_verifier_env {
 	char tmp_str_buf[TMP_STR_BUF_LEN];
 	struct bpf_insn insn_buf[INSN_BUF_SIZE];
 	struct bpf_insn epilogue_buf[INSN_BUF_SIZE];
+	struct bpf_scc_callchain callchain_buf;
 	/* array of pointers to bpf_scc_info indexed by SCC id */
 	struct bpf_scc_info **scc_info;
 	u32 scc_cnt;
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 92dba3c9664f..0f6cc2275695 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -1914,19 +1914,19 @@ static char *format_callchain(struct bpf_verifier_env *env, struct bpf_scc_callc
  */
 static int maybe_enter_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
 {
-	struct bpf_scc_callchain callchain;
+	struct bpf_scc_callchain *callchain = &env->callchain_buf;
 	struct bpf_scc_visit *visit;
 
-	if (!compute_scc_callchain(env, st, &callchain))
+	if (!compute_scc_callchain(env, st, callchain))
 		return 0;
-	visit = scc_visit_lookup(env, &callchain);
-	visit = visit ?: scc_visit_alloc(env, &callchain);
+	visit = scc_visit_lookup(env, callchain);
+	visit = visit ?: scc_visit_alloc(env, callchain);
 	if (!visit)
 		return -ENOMEM;
 	if (!visit->entry_state) {
 		visit->entry_state = st;
 		if (env->log.level & BPF_LOG_LEVEL2)
-			verbose(env, "SCC enter %s\n", format_callchain(env, &callchain));
+			verbose(env, "SCC enter %s\n", format_callchain(env, callchain));
 	}
 	return 0;
 }
@@ -1939,21 +1939,21 @@ static int propagate_backedges(struct bpf_verifier_env *env, struct bpf_scc_visi
  */
 static int maybe_exit_scc(struct bpf_verifier_env *env, struct bpf_verifier_state *st)
 {
-	struct bpf_scc_callchain callchain;
+	struct bpf_scc_callchain *callchain = &env->callchain_buf;
 	struct bpf_scc_visit *visit;
 
-	if (!compute_scc_callchain(env, st, &callchain))
+	if (!compute_scc_callchain(env, st, callchain))
 		return 0;
-	visit = scc_visit_lookup(env, &callchain);
+	visit = scc_visit_lookup(env, callchain);
 	if (!visit) {
 		verifier_bug(env, "scc exit: no visit info for call chain %s",
-			     format_callchain(env, &callchain));
+			     format_callchain(env, callchain));
 		return -EFAULT;
 	}
 	if (visit->entry_state != st)
 		return 0;
 	if (env->log.level & BPF_LOG_LEVEL2)
-		verbose(env, "SCC exit %s\n", format_callchain(env, &callchain));
+		verbose(env, "SCC exit %s\n", format_callchain(env, callchain));
 	visit->entry_state = NULL;
 	env->num_backedges -= visit->num_backedges;
 	visit->num_backedges = 0;
@@ -1968,22 +1968,22 @@ static int add_scc_backedge(struct bpf_verifier_env *env,
 			    struct bpf_verifier_state *st,
 			    struct bpf_scc_backedge *backedge)
 {
-	struct bpf_scc_callchain callchain;
+	struct bpf_scc_callchain *callchain = &env->callchain_buf;
 	struct bpf_scc_visit *visit;
 
-	if (!compute_scc_callchain(env, st, &callchain)) {
+	if (!compute_scc_callchain(env, st, callchain)) {
 		verifier_bug(env, "add backedge: no SCC in verification path, insn_idx %d",
 			     st->insn_idx);
 		return -EFAULT;
 	}
-	visit = scc_visit_lookup(env, &callchain);
+	visit = scc_visit_lookup(env, callchain);
 	if (!visit) {
 		verifier_bug(env, "add backedge: no visit info for call chain %s",
-			     format_callchain(env, &callchain));
+			     format_callchain(env, callchain));
 		return -EFAULT;
 	}
 	if (env->log.level & BPF_LOG_LEVEL2)
-		verbose(env, "SCC backedge %s\n", format_callchain(env, &callchain));
+		verbose(env, "SCC backedge %s\n", format_callchain(env, callchain));
 	backedge->next = visit->backedges;
 	visit->backedges = backedge;
 	visit->num_backedges++;
@@ -1999,12 +1999,12 @@ static int add_scc_backedge(struct bpf_verifier_env *env,
 static bool incomplete_read_marks(struct bpf_verifier_env *env,
 				  struct bpf_verifier_state *st)
 {
-	struct bpf_scc_callchain callchain;
+	struct bpf_scc_callchain *callchain = &env->callchain_buf;
 	struct bpf_scc_visit *visit;
 
-	if (!compute_scc_callchain(env, st, &callchain))
+	if (!compute_scc_callchain(env, st, callchain))
 		return false;
-	visit = scc_visit_lookup(env, &callchain);
+	visit = scc_visit_lookup(env, callchain);
 	if (!visit)
 		return false;
 	return !!visit->backedges;
-- 
cgit v1.2.3


From 6d4405b16d37090a0c905079eab951cfb5044a65 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 3 Jul 2025 19:36:19 +0900
Subject: ata: libata-core: Cache the general purpose log directory

The function ata_log_supported() tests if a log page is supported by a
device using the General Purpose Log Directory log page, which lists the
size of all surported log pages. However, this log page is read from the
device using ata_read_log_page() every time ata_log_supported() is
called. That is not necessary.

Avoid reading the General Purpose Log Directory log page by caching its
content in the gp_log_dir buffer defined as part of struct ata_device.
The functions ata_read_log_directory() and ata_clear_log_directory() are
introduced to manage this buffer. ata_clear_log_directory() zero-fill
the gp_log_dir buffer every time ata_dev_configure() is called, that is,
when the device is first scanned and when it is being revalidated.
The function ata_log_supported() is modified to call
ata_read_log_directory() instead of ata_read_log_page().

The function ata_read_log_directory() calls ata_read_log_page() to read
the General Purpose Log Directory log page from the device only if the
first 16-bits word of the log is not equal to 0x0001, that is, it is not
equal to the ACS mandated value for the log version.

With this, the log page is read from the device only once for every
ata_dev_configure() call. For instance, with pr_debug enabled, a call
to ata_dev_configure() before this patch generates the following log
page accesses:

ata3.00: read log page - log 0x0, page 0x0
ata3.00: read log page - log 0x13, page 0x0
ata3.00: read log page - log 0x0, page 0x0
ata3.00: read log page - log 0x12, page 0x0
ata3.00: read log page - log 0x0, page 0x0
ata3.00: read log page - log 0x30, page 0x0
ata3.00: read log page - log 0x30, page 0x8
ata3.00: read log page - log 0x0, page 0x0
ata3.00: read log page - log 0x0, page 0x0
ata3.00: read log page - log 0x0, page 0x0
ata3.00: read log page - log 0x30, page 0x0
ata3.00: read log page - log 0x0, page 0x0
ata3.00: read log page - log 0x30, page 0x0
ata3.00: read log page - log 0x30, page 0x3
ata3.00: read log page - log 0x30, page 0x4
ata3.00: read log page - log 0x18, page 0x0

That is, the general purpose log directory page is read 7 times.
With this patch applied, the number of accesses to this log page is
reduced to one:

ata3.00: read log page - log 0x0, page 0x0
ata3.00: read log page - log 0x13, page 0x0
ata3.00: read log page - log 0x12, page 0x0
ata3.00: read log page - log 0x30, page 0x0
ata3.00: read log page - log 0x30, page 0x8
ata3.00: read log page - log 0x30, page 0x0
ata3.00: read log page - log 0x30, page 0x0
ata3.00: read log page - log 0x30, page 0x3
ata3.00: read log page - log 0x30, page 0x4
ata3.00: read log page - log 0x18, page 0x0

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/20250703103622.291272-2-dlemoal@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c | 39 +++++++++++++++++++++++++++++++++++++--
 include/linux/libata.h    |  3 +++
 2 files changed, 40 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 7f6cebe61b33..30913bc6fe21 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -2154,14 +2154,46 @@ retry:
 	return err_mask;
 }
 
+static inline void ata_clear_log_directory(struct ata_device *dev)
+{
+	memset(dev->gp_log_dir, 0, ATA_SECT_SIZE);
+}
+
+static int ata_read_log_directory(struct ata_device *dev)
+{
+	u16 version;
+
+	/* If the log page is already cached, do nothing. */
+	version = get_unaligned_le16(&dev->gp_log_dir[0]);
+	if (version == 0x0001)
+		return 0;
+
+	if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, dev->gp_log_dir, 1)) {
+		ata_clear_log_directory(dev);
+		return -EIO;
+	}
+
+	version = get_unaligned_le16(&dev->gp_log_dir[0]);
+	if (version != 0x0001) {
+		ata_dev_err(dev, "Invalid log directory version 0x%04x\n",
+			    version);
+		ata_clear_log_directory(dev);
+		dev->quirks |= ATA_QUIRK_NO_LOG_DIR;
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int ata_log_supported(struct ata_device *dev, u8 log)
 {
 	if (dev->quirks & ATA_QUIRK_NO_LOG_DIR)
 		return 0;
 
-	if (ata_read_log_page(dev, ATA_LOG_DIRECTORY, 0, dev->sector_buf, 1))
+	if (ata_read_log_directory(dev))
 		return 0;
-	return get_unaligned_le16(&dev->sector_buf[log * 2]);
+
+	return get_unaligned_le16(&dev->gp_log_dir[log * 2]);
 }
 
 static bool ata_identify_page_supported(struct ata_device *dev, u8 page)
@@ -2890,6 +2922,9 @@ int ata_dev_configure(struct ata_device *dev)
 		return 0;
 	}
 
+	/* Clear the general purpose log directory cache. */
+	ata_clear_log_directory(dev);
+
 	/* Set quirks */
 	dev->quirks |= ata_dev_quirks(dev);
 	ata_force_quirks(dev);
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 7462218312ad..78a4addc6659 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -761,6 +761,9 @@ struct ata_device {
 		u32		gscr[SATA_PMP_GSCR_DWORDS]; /* PMP GSCR block */
 	} ____cacheline_aligned;
 
+	/* General Purpose Log Directory log page */
+	u8			gp_log_dir[ATA_SECT_SIZE] ____cacheline_aligned;
+
 	/* DEVSLP Timing Variables from Identify Device Data Log */
 	u8			devslp_timing[ATA_LOG_DEVSLP_SIZE];
 
-- 
cgit v1.2.3


From 31921e87b2d2614e261096fdabedef1db7679611 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Thu, 3 Jul 2025 19:36:22 +0900
Subject: ata: libata-core: Rename ata_do_set_mode()

With the renaming of libata-eh ata_set_mode() function to
ata_eh_set_mode(), libata-core function ata_do_set_mode() can now be
renamed to the simpler ata_set_mode().

All the call sites of the former ata_do_set_mode() are updated to use
the new function name.

No functional changes.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Link: https://lore.kernel.org/r/20250703103622.291272-5-dlemoal@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-core.c   | 6 +++---
 drivers/ata/libata-eh.c     | 2 +-
 drivers/ata/pata_optidma.c  | 4 +++-
 drivers/ata/pata_pcmcia.c   | 4 ++--
 drivers/ata/pata_pdc2027x.c | 2 +-
 drivers/ata/sata_sil.c      | 2 +-
 include/linux/libata.h      | 2 +-
 7 files changed, 12 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index 72abd2996e9c..bbf1318a2b9a 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -3510,7 +3510,7 @@ static int ata_dev_set_mode(struct ata_device *dev)
 }
 
 /**
- *	ata_do_set_mode - Program timings and issue SET FEATURES - XFER
+ *	ata_set_mode - Program timings and issue SET FEATURES - XFER
  *	@link: link on which timings will be programmed
  *	@r_failed_dev: out parameter for failed device
  *
@@ -3526,7 +3526,7 @@ static int ata_dev_set_mode(struct ata_device *dev)
  *	0 on success, negative errno otherwise
  */
 
-int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
+int ata_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
 {
 	struct ata_port *ap = link->ap;
 	struct ata_device *dev;
@@ -3607,7 +3607,7 @@ int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev)
 		*r_failed_dev = dev;
 	return rc;
 }
-EXPORT_SYMBOL_GPL(ata_do_set_mode);
+EXPORT_SYMBOL_GPL(ata_set_mode);
 
 /**
  *	ata_wait_ready - wait for link to become ready
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 8b2a0a56ffe1..e5fa61fb8a59 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -3444,7 +3444,7 @@ static int ata_eh_set_mode(struct ata_link *link,
 	if (ap->ops->set_mode)
 		rc = ap->ops->set_mode(link, r_failed_dev);
 	else
-		rc = ata_do_set_mode(link, r_failed_dev);
+		rc = ata_set_mode(link, r_failed_dev);
 
 	/* if transfer mode has changed, set DUBIOUS_XFER on device */
 	ata_for_each_dev(dev, link, ENABLED) {
diff --git a/drivers/ata/pata_optidma.c b/drivers/ata/pata_optidma.c
index dfc36b4ec9c6..cc876dc7a9d8 100644
--- a/drivers/ata/pata_optidma.c
+++ b/drivers/ata/pata_optidma.c
@@ -322,7 +322,9 @@ static int optidma_set_mode(struct ata_link *link, struct ata_device **r_failed)
 	u8 r;
 	int nybble = 4 * ap->port_no;
 	struct pci_dev *pdev = to_pci_dev(ap->host->dev);
-	int rc  = ata_do_set_mode(link, r_failed);
+	int rc;
+
+	rc = ata_set_mode(link, r_failed);
 	if (rc == 0) {
 		pci_read_config_byte(pdev, 0x43, &r);
 
diff --git a/drivers/ata/pata_pcmcia.c b/drivers/ata/pata_pcmcia.c
index 5b602206c522..cf3810933a27 100644
--- a/drivers/ata/pata_pcmcia.c
+++ b/drivers/ata/pata_pcmcia.c
@@ -46,7 +46,7 @@ static int pcmcia_set_mode(struct ata_link *link, struct ata_device **r_failed_d
 	struct ata_device *slave = &link->device[1];
 
 	if (!ata_dev_enabled(master) || !ata_dev_enabled(slave))
-		return ata_do_set_mode(link, r_failed_dev);
+		return ata_set_mode(link, r_failed_dev);
 
 	if (memcmp(master->id + ATA_ID_FW_REV,  slave->id + ATA_ID_FW_REV,
 			   ATA_ID_FW_REV_LEN + ATA_ID_PROD_LEN) == 0) {
@@ -58,7 +58,7 @@ static int pcmcia_set_mode(struct ata_link *link, struct ata_device **r_failed_d
 			ata_dev_disable(slave);
 		}
 	}
-	return ata_do_set_mode(link, r_failed_dev);
+	return ata_set_mode(link, r_failed_dev);
 }
 
 /**
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index 6820c5597b14..a4ee3b92c9aa 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -387,7 +387,7 @@ static int pdc2027x_set_mode(struct ata_link *link, struct ata_device **r_failed
 	struct ata_device *dev;
 	int rc;
 
-	rc = ata_do_set_mode(link, r_failed);
+	rc = ata_set_mode(link, r_failed);
 	if (rc < 0)
 		return rc;
 
diff --git a/drivers/ata/sata_sil.c b/drivers/ata/sata_sil.c
index 3a99f66198a9..1b6dc950a42a 100644
--- a/drivers/ata/sata_sil.c
+++ b/drivers/ata/sata_sil.c
@@ -351,7 +351,7 @@ static int sil_set_mode(struct ata_link *link, struct ata_device **r_failed)
 	u32 tmp, dev_mode[2] = { };
 	int rc;
 
-	rc = ata_do_set_mode(link, r_failed);
+	rc = ata_set_mode(link, r_failed);
 	if (rc)
 		return rc;
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 78a4addc6659..d092747be588 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1218,7 +1218,7 @@ extern int ata_ncq_prio_enabled(struct ata_port *ap, struct scsi_device *sdev,
 extern int ata_ncq_prio_enable(struct ata_port *ap, struct scsi_device *sdev,
 			       bool enable);
 extern struct ata_device *ata_dev_pair(struct ata_device *adev);
-extern int ata_do_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
+int ata_set_mode(struct ata_link *link, struct ata_device **r_failed_dev);
 extern void ata_scsi_port_error_handler(struct Scsi_Host *host, struct ata_port *ap);
 extern void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap, struct list_head *eh_q);
 
-- 
cgit v1.2.3


From 60bc47b5a0b164082d448815d7db3066266aa3ed Mon Sep 17 00:00:00 2001
From: Yicong Yang <yangyicong@hisilicon.com>
Date: Tue, 1 Jul 2025 19:02:13 +0800
Subject: watchdog/perf: Provide function for adjusting the event period

Architecture's using perf events for hard lockup detection needs to
convert the watchdog_thresh to the event's period, some architecture
for example arm64 perform this conversion using the CPU's maximum
frequency which will be acquired by cpufreq. However by the time
the lockup detector's initialized the cpufreq driver may not be
initialized, thus launch a watchdog with inaccurate period. Provide
a function hardlockup_detector_perf_adjust_period() to allowing
adjust the event period. Then architecture can update with more
accurate period if cpufreq is initialized.

Reviewed-by: Douglas Anderson <dianders@chromium.org>
Signed-off-by: Yicong Yang <yangyicong@hisilicon.com>
Link: https://lore.kernel.org/r/20250701110214.27242-2-yangyicong@huawei.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/nmi.h    |  2 ++
 kernel/watchdog_perf.c | 22 ++++++++++++++++++++++
 2 files changed, 24 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index e78fa535f61d..cf3c6ab408aa 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -103,10 +103,12 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs);
 extern void hardlockup_detector_perf_stop(void);
 extern void hardlockup_detector_perf_restart(void);
 extern void hardlockup_config_perf_event(const char *str);
+extern void hardlockup_detector_perf_adjust_period(u64 period);
 #else
 static inline void hardlockup_detector_perf_stop(void) { }
 static inline void hardlockup_detector_perf_restart(void) { }
 static inline void hardlockup_config_perf_event(const char *str) { }
+static inline void hardlockup_detector_perf_adjust_period(u64 period) { }
 #endif
 
 void watchdog_hardlockup_stop(void);
diff --git a/kernel/watchdog_perf.c b/kernel/watchdog_perf.c
index 75af12ff774e..9c58f5b4381d 100644
--- a/kernel/watchdog_perf.c
+++ b/kernel/watchdog_perf.c
@@ -186,6 +186,28 @@ void watchdog_hardlockup_disable(unsigned int cpu)
 	}
 }
 
+/**
+ * hardlockup_detector_perf_adjust_period - Adjust the event period due
+ *                                          to current cpu frequency change
+ * @period: The target period to be set
+ */
+void hardlockup_detector_perf_adjust_period(u64 period)
+{
+	struct perf_event *event = this_cpu_read(watchdog_ev);
+
+	if (!(watchdog_enabled & WATCHDOG_HARDLOCKUP_ENABLED))
+		return;
+
+	if (!event)
+		return;
+
+	if (event->attr.sample_period == period)
+		return;
+
+	if (perf_event_period(event, period))
+		pr_err("failed to change period to %llu\n", period);
+}
+
 /**
  * hardlockup_detector_perf_stop - Globally stop watchdog events
  *
-- 
cgit v1.2.3


From ca115d7e754691c0219eec95ec94dbac7f87daef Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 3 Jul 2025 09:36:41 +0200
Subject: tree-wide: s/struct fileattr/struct file_kattr/g

Now that we expose struct file_attr as our uapi struct rename all the
internal struct to struct file_kattr to clearly communicate that it is a
kernel internal struct. This is similar to struct mount_{k}attr and
others.

Link: https://lore.kernel.org/20250703-restlaufzeit-baurecht-9ed44552b481@brauner
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/locking.rst |  4 ++--
 Documentation/filesystems/vfs.rst     |  4 ++--
 fs/bcachefs/fs.c                      |  4 ++--
 fs/btrfs/ioctl.c                      |  4 ++--
 fs/btrfs/ioctl.h                      |  6 +++---
 fs/ecryptfs/inode.c                   |  4 ++--
 fs/efivarfs/inode.c                   |  4 ++--
 fs/ext2/ext2.h                        |  4 ++--
 fs/ext2/ioctl.c                       |  4 ++--
 fs/ext4/ext4.h                        |  4 ++--
 fs/ext4/ioctl.c                       |  4 ++--
 fs/f2fs/f2fs.h                        |  4 ++--
 fs/f2fs/file.c                        |  4 ++--
 fs/file_attr.c                        | 34 +++++++++++++++++-----------------
 fs/fuse/fuse_i.h                      |  4 ++--
 fs/fuse/ioctl.c                       |  4 ++--
 fs/gfs2/file.c                        |  4 ++--
 fs/gfs2/inode.h                       |  4 ++--
 fs/hfsplus/hfsplus_fs.h               |  4 ++--
 fs/hfsplus/inode.c                    |  4 ++--
 fs/jfs/ioctl.c                        |  4 ++--
 fs/jfs/jfs_inode.h                    |  4 ++--
 fs/nilfs2/ioctl.c                     |  4 ++--
 fs/nilfs2/nilfs.h                     |  4 ++--
 fs/ocfs2/ioctl.c                      |  4 ++--
 fs/ocfs2/ioctl.h                      |  4 ++--
 fs/orangefs/inode.c                   |  4 ++--
 fs/overlayfs/copy_up.c                |  4 ++--
 fs/overlayfs/inode.c                  | 12 ++++++------
 fs/overlayfs/overlayfs.h              | 10 +++++-----
 fs/overlayfs/util.c                   |  2 +-
 fs/ubifs/ioctl.c                      |  4 ++--
 fs/ubifs/ubifs.h                      |  4 ++--
 fs/xfs/xfs_ioctl.c                    | 18 +++++++++---------
 fs/xfs/xfs_ioctl.h                    |  4 ++--
 include/linux/fileattr.h              | 14 +++++++-------
 include/linux/fs.h                    |  6 +++---
 include/linux/lsm_hook_defs.h         |  4 ++--
 include/linux/security.h              |  8 ++++----
 include/uapi/linux/fs.h               |  2 +-
 mm/shmem.c                            |  4 ++--
 security/security.c                   |  4 ++--
 security/selinux/hooks.c              |  4 ++--
 43 files changed, 122 insertions(+), 122 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 2e567e341c3b..2ff02653d7cc 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -87,8 +87,8 @@ prototypes::
 	int (*tmpfile) (struct mnt_idmap *, struct inode *,
 			struct file *, umode_t);
 	int (*fileattr_set)(struct mnt_idmap *idmap,
-			    struct dentry *dentry, struct fileattr *fa);
-	int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
+			    struct dentry *dentry, struct file_kattr *fa);
+	int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa);
 	struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int);
 	struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
 
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index fd32a9a17bfb..f2bbf4def123 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -515,8 +515,8 @@ As of kernel 2.6.22, the following members are defined:
 		struct posix_acl * (*get_acl)(struct mnt_idmap *, struct dentry *, int);
 	        int (*set_acl)(struct mnt_idmap *, struct dentry *, struct posix_acl *, int);
 		int (*fileattr_set)(struct mnt_idmap *idmap,
-				    struct dentry *dentry, struct fileattr *fa);
-		int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
+				    struct dentry *dentry, struct file_kattr *fa);
+		int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa);
 	        struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
 	};
 
diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
index 85d13f800165..7c4de887629c 100644
--- a/fs/bcachefs/fs.c
+++ b/fs/bcachefs/fs.c
@@ -1619,7 +1619,7 @@ static const __maybe_unused unsigned bch_flags_to_xflags[] = {
 };
 
 static int bch2_fileattr_get(struct dentry *dentry,
-			     struct fileattr *fa)
+			     struct file_kattr *fa)
 {
 	struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
@@ -1682,7 +1682,7 @@ static int fssetxattr_inode_update_fn(struct btree_trans *trans,
 
 static int bch2_fileattr_set(struct mnt_idmap *idmap,
 			     struct dentry *dentry,
-			     struct fileattr *fa)
+			     struct file_kattr *fa)
 {
 	struct bch_inode_info *inode = to_bch_ei(d_inode(dentry));
 	struct bch_fs *c = inode->v.i_sb->s_fs_info;
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 913acef3f0a9..ffb28bfba4fa 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -245,7 +245,7 @@ static int btrfs_check_ioctl_vol_args2_subvol_name(const struct btrfs_ioctl_vol_
  * Set flags/xflags from the internal inode flags. The remaining items of
  * fsxattr are zeroed.
  */
-int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int btrfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	const struct btrfs_inode *inode = BTRFS_I(d_inode(dentry));
 
@@ -254,7 +254,7 @@ int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int btrfs_fileattr_set(struct mnt_idmap *idmap,
-		       struct dentry *dentry, struct fileattr *fa)
+		       struct dentry *dentry, struct file_kattr *fa)
 {
 	struct btrfs_inode *inode = BTRFS_I(d_inode(dentry));
 	struct btrfs_root *root = inode->root;
diff --git a/fs/btrfs/ioctl.h b/fs/btrfs/ioctl.h
index e08ea446cf48..ccf6bed9cc24 100644
--- a/fs/btrfs/ioctl.h
+++ b/fs/btrfs/ioctl.h
@@ -8,7 +8,7 @@
 struct file;
 struct dentry;
 struct mnt_idmap;
-struct fileattr;
+struct file_kattr;
 struct io_uring_cmd;
 struct btrfs_inode;
 struct btrfs_fs_info;
@@ -16,9 +16,9 @@ struct btrfs_ioctl_balance_args;
 
 long btrfs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
-int btrfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int btrfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int btrfs_fileattr_set(struct mnt_idmap *idmap,
-		       struct dentry *dentry, struct fileattr *fa);
+		       struct dentry *dentry, struct file_kattr *fa);
 int btrfs_ioctl_get_supported_features(void __user *arg);
 void btrfs_sync_inode_flags_to_i_flags(struct btrfs_inode *inode);
 void btrfs_update_ioctl_balance_args(struct btrfs_fs_info *fs_info,
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index 493d7f194956..d83416af17b4 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -1124,13 +1124,13 @@ out:
 	return rc;
 }
 
-static int ecryptfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+static int ecryptfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	return vfs_fileattr_get(ecryptfs_dentry_to_lower(dentry), fa);
 }
 
 static int ecryptfs_fileattr_set(struct mnt_idmap *idmap,
-				 struct dentry *dentry, struct fileattr *fa)
+				 struct dentry *dentry, struct file_kattr *fa)
 {
 	struct dentry *lower_dentry = ecryptfs_dentry_to_lower(dentry);
 	int rc;
diff --git a/fs/efivarfs/inode.c b/fs/efivarfs/inode.c
index 98a7299a9ee9..2891614abf8d 100644
--- a/fs/efivarfs/inode.c
+++ b/fs/efivarfs/inode.c
@@ -138,7 +138,7 @@ const struct inode_operations efivarfs_dir_inode_operations = {
 };
 
 static int
-efivarfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+efivarfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	unsigned int i_flags;
 	unsigned int flags = 0;
@@ -154,7 +154,7 @@ efivarfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 
 static int
 efivarfs_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa)
+		      struct dentry *dentry, struct file_kattr *fa)
 {
 	unsigned int i_flags = 0;
 
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 4025f875252a..cf97b76e9fd3 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -750,9 +750,9 @@ extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		       u64 start, u64 len);
 
 /* ioctl.c */
-extern int ext2_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+extern int ext2_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 extern int ext2_fileattr_set(struct mnt_idmap *idmap,
-			     struct dentry *dentry, struct fileattr *fa);
+			     struct dentry *dentry, struct file_kattr *fa);
 extern long ext2_ioctl(struct file *, unsigned int, unsigned long);
 extern long ext2_compat_ioctl(struct file *, unsigned int, unsigned long);
 
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 44e04484e570..c3fea55b8efa 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -18,7 +18,7 @@
 #include <linux/uaccess.h>
 #include <linux/fileattr.h>
 
-int ext2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int ext2_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct ext2_inode_info *ei = EXT2_I(d_inode(dentry));
 
@@ -28,7 +28,7 @@ int ext2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int ext2_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa)
+		      struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct ext2_inode_info *ei = EXT2_I(inode);
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 18373de980f2..7d962e7f388a 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -3103,8 +3103,8 @@ extern int ext4_ind_remove_space(handle_t *handle, struct inode *inode,
 extern long ext4_ioctl(struct file *, unsigned int, unsigned long);
 extern long ext4_compat_ioctl(struct file *, unsigned int, unsigned long);
 int ext4_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa);
-int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+		      struct dentry *dentry, struct file_kattr *fa);
+int ext4_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 extern void ext4_reset_inode_seed(struct inode *inode);
 int ext4_update_overhead(struct super_block *sb, bool force);
 int ext4_force_shutdown(struct super_block *sb, u32 flags);
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index 5668a17458ae..84e3c73952d7 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -980,7 +980,7 @@ group_add_out:
 	return err;
 }
 
-int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int ext4_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct ext4_inode_info *ei = EXT4_I(inode);
@@ -997,7 +997,7 @@ int ext4_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int ext4_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa)
+		      struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	u32 flags = fa->flags;
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 9333a22b9a01..c78464792ceb 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3615,9 +3615,9 @@ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
 int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
 						bool readonly, bool need_lock);
 int f2fs_precache_extents(struct inode *inode);
-int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int f2fs_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int f2fs_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa);
+		      struct dentry *dentry, struct file_kattr *fa);
 long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
 long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int f2fs_transfer_project_quota(struct inode *inode, kprojid_t kprojid);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 6bd3de64f2a8..90180ca22abd 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -3356,7 +3356,7 @@ static int f2fs_ioc_setproject(struct inode *inode, __u32 projid)
 }
 #endif
 
-int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int f2fs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct f2fs_inode_info *fi = F2FS_I(inode);
@@ -3380,7 +3380,7 @@ int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int f2fs_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa)
+		      struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	u32 fsflags = fa->flags, mask = F2FS_SETTABLE_FS_FL;
diff --git a/fs/file_attr.c b/fs/file_attr.c
index 21d6a0607345..17745c89e2be 100644
--- a/fs/file_attr.c
+++ b/fs/file_attr.c
@@ -17,7 +17,7 @@
  * Set ->fsx_xflags, ->fsx_valid and ->flags (translated xflags).  All
  * other fields are zeroed.
  */
-void fileattr_fill_xflags(struct fileattr *fa, u32 xflags)
+void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags)
 {
 	memset(fa, 0, sizeof(*fa));
 	fa->fsx_valid = true;
@@ -47,7 +47,7 @@ EXPORT_SYMBOL(fileattr_fill_xflags);
  * Set ->flags, ->flags_valid and ->fsx_xflags (translated flags).
  * All other fields are zeroed.
  */
-void fileattr_fill_flags(struct fileattr *fa, u32 flags)
+void fileattr_fill_flags(struct file_kattr *fa, u32 flags)
 {
 	memset(fa, 0, sizeof(*fa));
 	fa->flags_valid = true;
@@ -78,7 +78,7 @@ EXPORT_SYMBOL(fileattr_fill_flags);
  *
  * Return: 0 on success, or a negative error on failure.
  */
-int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	int error;
@@ -94,7 +94,7 @@ int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 EXPORT_SYMBOL(vfs_fileattr_get);
 
-static void fileattr_to_file_attr(const struct fileattr *fa,
+static void fileattr_to_file_attr(const struct file_kattr *fa,
 				  struct file_attr *fattr)
 {
 	__u32 mask = FS_XFLAGS_MASK;
@@ -114,7 +114,7 @@ static void fileattr_to_file_attr(const struct fileattr *fa,
  *
  * Return: 0 on success, or -EFAULT on failure.
  */
-int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa)
+int copy_fsxattr_to_user(const struct file_kattr *fa, struct fsxattr __user *ufa)
 {
 	struct fsxattr xfa;
 	__u32 mask = FS_XFLAGS_MASK;
@@ -134,7 +134,7 @@ int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa)
 EXPORT_SYMBOL(copy_fsxattr_to_user);
 
 static int file_attr_to_fileattr(const struct file_attr *fattr,
-				 struct fileattr *fa)
+				 struct file_kattr *fa)
 {
 	__u32 mask = FS_XFLAGS_MASK;
 
@@ -150,7 +150,7 @@ static int file_attr_to_fileattr(const struct file_attr *fattr,
 	return 0;
 }
 
-static int copy_fsxattr_from_user(struct fileattr *fa,
+static int copy_fsxattr_from_user(struct file_kattr *fa,
 				  struct fsxattr __user *ufa)
 {
 	struct fsxattr xfa;
@@ -179,8 +179,8 @@ static int copy_fsxattr_from_user(struct fileattr *fa,
  * Note: must be called with inode lock held.
  */
 static int fileattr_set_prepare(struct inode *inode,
-			      const struct fileattr *old_ma,
-			      struct fileattr *fa)
+			      const struct file_kattr *old_ma,
+			      struct file_kattr *fa)
 {
 	int err;
 
@@ -263,10 +263,10 @@ static int fileattr_set_prepare(struct inode *inode,
  * Return: 0 on success, or a negative error on failure.
  */
 int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry,
-		     struct fileattr *fa)
+		     struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
-	struct fileattr old_ma = {};
+	struct file_kattr old_ma = {};
 	int err;
 
 	if (!inode->i_op->fileattr_set)
@@ -308,7 +308,7 @@ EXPORT_SYMBOL(vfs_fileattr_set);
 
 int ioctl_getflags(struct file *file, unsigned int __user *argp)
 {
-	struct fileattr fa = { .flags_valid = true }; /* hint only */
+	struct file_kattr fa = { .flags_valid = true }; /* hint only */
 	int err;
 
 	err = vfs_fileattr_get(file->f_path.dentry, &fa);
@@ -324,7 +324,7 @@ int ioctl_setflags(struct file *file, unsigned int __user *argp)
 {
 	struct mnt_idmap *idmap = file_mnt_idmap(file);
 	struct dentry *dentry = file->f_path.dentry;
-	struct fileattr fa;
+	struct file_kattr fa;
 	unsigned int flags;
 	int err;
 
@@ -345,7 +345,7 @@ EXPORT_SYMBOL(ioctl_setflags);
 
 int ioctl_fsgetxattr(struct file *file, void __user *argp)
 {
-	struct fileattr fa = { .fsx_valid = true }; /* hint only */
+	struct file_kattr fa = { .fsx_valid = true }; /* hint only */
 	int err;
 
 	err = vfs_fileattr_get(file->f_path.dentry, &fa);
@@ -362,7 +362,7 @@ int ioctl_fssetxattr(struct file *file, void __user *argp)
 {
 	struct mnt_idmap *idmap = file_mnt_idmap(file);
 	struct dentry *dentry = file->f_path.dentry;
-	struct fileattr fa;
+	struct file_kattr fa;
 	int err;
 
 	err = copy_fsxattr_from_user(&fa, argp);
@@ -387,7 +387,7 @@ SYSCALL_DEFINE5(file_getattr, int, dfd, const char __user *, filename,
 	struct filename *name __free(putname) = NULL;
 	unsigned int lookup_flags = 0;
 	struct file_attr fattr;
-	struct fileattr fa;
+	struct file_kattr fa;
 	int error;
 
 	BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0);
@@ -442,7 +442,7 @@ SYSCALL_DEFINE5(file_setattr, int, dfd, const char __user *, filename,
 	struct filename *name __free(putname) = NULL;
 	unsigned int lookup_flags = 0;
 	struct file_attr fattr;
-	struct fileattr fa;
+	struct file_kattr fa;
 	int error;
 
 	BUILD_BUG_ON(sizeof(struct file_attr) < FILE_ATTR_SIZE_VER0);
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index b54f4f57789f..501f64ceeab3 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -1486,9 +1486,9 @@ void fuse_dax_cancel_work(struct fuse_conn *fc);
 long fuse_file_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 long fuse_file_compat_ioctl(struct file *file, unsigned int cmd,
 			    unsigned long arg);
-int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int fuse_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int fuse_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa);
+		      struct dentry *dentry, struct file_kattr *fa);
 
 /* iomode.c */
 int fuse_file_cached_io_open(struct inode *inode, struct fuse_file *ff);
diff --git a/fs/fuse/ioctl.c b/fs/fuse/ioctl.c
index f2692f7d5932..57032eadca6c 100644
--- a/fs/fuse/ioctl.c
+++ b/fs/fuse/ioctl.c
@@ -502,7 +502,7 @@ static void fuse_priv_ioctl_cleanup(struct inode *inode, struct fuse_file *ff)
 	fuse_file_release(inode, ff, O_RDONLY, NULL, S_ISDIR(inode->i_mode));
 }
 
-int fuse_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int fuse_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct fuse_file *ff;
@@ -542,7 +542,7 @@ cleanup:
 }
 
 int fuse_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa)
+		      struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct fuse_file *ff;
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index fd1147aa3891..65f4371f428c 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -155,7 +155,7 @@ static inline u32 gfs2_gfsflags_to_fsflags(struct inode *inode, u32 gfsflags)
 	return fsflags;
 }
 
-int gfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int gfs2_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct gfs2_inode *ip = GFS2_I(inode);
@@ -276,7 +276,7 @@ out:
 }
 
 int gfs2_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa)
+		      struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	u32 fsflags = fa->flags, gfsflags = 0;
diff --git a/fs/gfs2/inode.h b/fs/gfs2/inode.h
index eafe123617e6..dd970e644fe0 100644
--- a/fs/gfs2/inode.h
+++ b/fs/gfs2/inode.h
@@ -107,9 +107,9 @@ loff_t gfs2_seek_hole(struct file *file, loff_t offset);
 extern const struct file_operations gfs2_file_fops_nolock;
 extern const struct file_operations gfs2_dir_fops_nolock;
 
-int gfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int gfs2_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int gfs2_fileattr_set(struct mnt_idmap *idmap,
-		      struct dentry *dentry, struct fileattr *fa);
+		      struct dentry *dentry, struct file_kattr *fa);
 void gfs2_set_inode_flags(struct inode *inode);
 
 #ifdef CONFIG_GFS2_FS_LOCKING_DLM
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 2f089bff0095..927db2b8b17c 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -489,9 +489,9 @@ int hfsplus_getattr(struct mnt_idmap *idmap, const struct path *path,
 		    unsigned int query_flags);
 int hfsplus_file_fsync(struct file *file, loff_t start, loff_t end,
 		       int datasync);
-int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int hfsplus_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int hfsplus_fileattr_set(struct mnt_idmap *idmap,
-			 struct dentry *dentry, struct fileattr *fa);
+			 struct dentry *dentry, struct file_kattr *fa);
 
 /* ioctl.c */
 long hfsplus_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index f331e9574217..3ec0b33808c0 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -654,7 +654,7 @@ out:
 	return res;
 }
 
-int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int hfsplus_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
@@ -673,7 +673,7 @@ int hfsplus_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int hfsplus_fileattr_set(struct mnt_idmap *idmap,
-			 struct dentry *dentry, struct fileattr *fa)
+			 struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct hfsplus_inode_info *hip = HFSPLUS_I(inode);
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index f7bd7e8f5be4..563f148be8af 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -57,7 +57,7 @@ static long jfs_map_ext2(unsigned long flags, int from)
 	return mapped;
 }
 
-int jfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int jfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct jfs_inode_info *jfs_inode = JFS_IP(d_inode(dentry));
 	unsigned int flags = jfs_inode->mode2 & JFS_FL_USER_VISIBLE;
@@ -71,7 +71,7 @@ int jfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int jfs_fileattr_set(struct mnt_idmap *idmap,
-		     struct dentry *dentry, struct fileattr *fa)
+		     struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct jfs_inode_info *jfs_inode = JFS_IP(inode);
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index ea80661597ac..2c6c81c8cb9f 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -9,9 +9,9 @@ struct fid;
 
 extern struct inode *ialloc(struct inode *, umode_t);
 extern int jfs_fsync(struct file *, loff_t, loff_t, int);
-extern int jfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+extern int jfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 extern int jfs_fileattr_set(struct mnt_idmap *idmap,
-			    struct dentry *dentry, struct fileattr *fa);
+			    struct dentry *dentry, struct file_kattr *fa);
 extern long jfs_ioctl(struct file *, unsigned int, unsigned long);
 extern struct inode *jfs_iget(struct super_block *, unsigned long);
 extern int jfs_commit_inode(struct inode *, int);
diff --git a/fs/nilfs2/ioctl.c b/fs/nilfs2/ioctl.c
index a66d62a51f77..3288c3b4be9e 100644
--- a/fs/nilfs2/ioctl.c
+++ b/fs/nilfs2/ioctl.c
@@ -118,7 +118,7 @@ static int nilfs_ioctl_wrap_copy(struct the_nilfs *nilfs,
  *
  * Return: always 0 as success.
  */
-int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int nilfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 
@@ -136,7 +136,7 @@ int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
  * Return: 0 on success, or a negative error code on failure.
  */
 int nilfs_fileattr_set(struct mnt_idmap *idmap,
-		       struct dentry *dentry, struct fileattr *fa)
+		       struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct nilfs_transaction_info ti;
diff --git a/fs/nilfs2/nilfs.h b/fs/nilfs2/nilfs.h
index cb6ed54accd7..f466daa39440 100644
--- a/fs/nilfs2/nilfs.h
+++ b/fs/nilfs2/nilfs.h
@@ -268,9 +268,9 @@ int nilfs_set_link(struct inode *dir, struct nilfs_dir_entry *de,
 extern int nilfs_sync_file(struct file *, loff_t, loff_t, int);
 
 /* ioctl.c */
-int nilfs_fileattr_get(struct dentry *dentry, struct fileattr *m);
+int nilfs_fileattr_get(struct dentry *dentry, struct file_kattr *m);
 int nilfs_fileattr_set(struct mnt_idmap *idmap,
-		       struct dentry *dentry, struct fileattr *fa);
+		       struct dentry *dentry, struct file_kattr *fa);
 long nilfs_ioctl(struct file *, unsigned int, unsigned long);
 long nilfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 int nilfs_ioctl_prepare_clean_segments(struct the_nilfs *, struct nilfs_argv *,
diff --git a/fs/ocfs2/ioctl.c b/fs/ocfs2/ioctl.c
index 7ae96fb8807a..db14c92302a1 100644
--- a/fs/ocfs2/ioctl.c
+++ b/fs/ocfs2/ioctl.c
@@ -62,7 +62,7 @@ static inline int o2info_coherent(struct ocfs2_info_request *req)
 	return (!(req->ir_flags & OCFS2_INFO_FL_NON_COHERENT));
 }
 
-int ocfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int ocfs2_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	unsigned int flags;
@@ -83,7 +83,7 @@ int ocfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int ocfs2_fileattr_set(struct mnt_idmap *idmap,
-		       struct dentry *dentry, struct fileattr *fa)
+		       struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	unsigned int flags = fa->flags;
diff --git a/fs/ocfs2/ioctl.h b/fs/ocfs2/ioctl.h
index 48a5fdfe87a1..4a1c2313b429 100644
--- a/fs/ocfs2/ioctl.h
+++ b/fs/ocfs2/ioctl.h
@@ -11,9 +11,9 @@
 #ifndef OCFS2_IOCTL_PROTO_H
 #define OCFS2_IOCTL_PROTO_H
 
-int ocfs2_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int ocfs2_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int ocfs2_fileattr_set(struct mnt_idmap *idmap,
-		       struct dentry *dentry, struct fileattr *fa);
+		       struct dentry *dentry, struct file_kattr *fa);
 long ocfs2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
 long ocfs2_compat_ioctl(struct file *file, unsigned cmd, unsigned long arg);
 
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 08a6f372a352..926d1659902d 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -887,7 +887,7 @@ int orangefs_update_time(struct inode *inode, int flags)
 	return __orangefs_setattr(inode, &iattr);
 }
 
-static int orangefs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+static int orangefs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	u64 val = 0;
 	int ret;
@@ -908,7 +908,7 @@ static int orangefs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 static int orangefs_fileattr_set(struct mnt_idmap *idmap,
-				 struct dentry *dentry, struct fileattr *fa)
+				 struct dentry *dentry, struct file_kattr *fa)
 {
 	u64 val = 0;
 
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index 2c646b7076d0..74817e1ece19 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -171,8 +171,8 @@ out:
 static int ovl_copy_fileattr(struct inode *inode, const struct path *old,
 			     const struct path *new)
 {
-	struct fileattr oldfa = { .flags_valid = true };
-	struct fileattr newfa = { .flags_valid = true };
+	struct file_kattr oldfa = { .flags_valid = true };
+	struct file_kattr newfa = { .flags_valid = true };
 	int err;
 
 	err = ovl_real_fileattr_get(old, &oldfa);
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index cf3581dc1034..ecb9f2019395 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -610,7 +610,7 @@ static int ovl_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
  * Introducing security_inode_fileattr_get/set() hooks would solve this issue
  * properly.
  */
-static int ovl_security_fileattr(const struct path *realpath, struct fileattr *fa,
+static int ovl_security_fileattr(const struct path *realpath, struct file_kattr *fa,
 				 bool set)
 {
 	struct file *file;
@@ -637,7 +637,7 @@ static int ovl_security_fileattr(const struct path *realpath, struct fileattr *f
 	return err;
 }
 
-int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa)
+int ovl_real_fileattr_set(const struct path *realpath, struct file_kattr *fa)
 {
 	int err;
 
@@ -649,7 +649,7 @@ int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa)
 }
 
 int ovl_fileattr_set(struct mnt_idmap *idmap,
-		     struct dentry *dentry, struct fileattr *fa)
+		     struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct path upperpath;
@@ -697,7 +697,7 @@ out:
 }
 
 /* Convert inode protection flags to fileattr flags */
-static void ovl_fileattr_prot_flags(struct inode *inode, struct fileattr *fa)
+static void ovl_fileattr_prot_flags(struct inode *inode, struct file_kattr *fa)
 {
 	BUILD_BUG_ON(OVL_PROT_FS_FLAGS_MASK & ~FS_COMMON_FL);
 	BUILD_BUG_ON(OVL_PROT_FSX_FLAGS_MASK & ~FS_XFLAG_COMMON);
@@ -712,7 +712,7 @@ static void ovl_fileattr_prot_flags(struct inode *inode, struct fileattr *fa)
 	}
 }
 
-int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa)
+int ovl_real_fileattr_get(const struct path *realpath, struct file_kattr *fa)
 {
 	int err;
 
@@ -723,7 +723,7 @@ int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa)
 	return vfs_fileattr_get(realpath->dentry, fa);
 }
 
-int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int ovl_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct path realpath;
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 8baaba0a3fe5..e19d91f22186 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -815,7 +815,7 @@ void ovl_copyattr(struct inode *to);
 
 void ovl_check_protattr(struct inode *inode, struct dentry *upper);
 int ovl_set_protattr(struct inode *inode, struct dentry *upper,
-		      struct fileattr *fa);
+		      struct file_kattr *fa);
 
 static inline void ovl_copyflags(struct inode *from, struct inode *to)
 {
@@ -847,11 +847,11 @@ struct dentry *ovl_create_temp(struct ovl_fs *ofs, struct dentry *workdir,
 
 /* file.c */
 extern const struct file_operations ovl_file_operations;
-int ovl_real_fileattr_get(const struct path *realpath, struct fileattr *fa);
-int ovl_real_fileattr_set(const struct path *realpath, struct fileattr *fa);
-int ovl_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int ovl_real_fileattr_get(const struct path *realpath, struct file_kattr *fa);
+int ovl_real_fileattr_set(const struct path *realpath, struct file_kattr *fa);
+int ovl_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int ovl_fileattr_set(struct mnt_idmap *idmap,
-		     struct dentry *dentry, struct fileattr *fa);
+		     struct dentry *dentry, struct file_kattr *fa);
 struct ovl_file;
 struct ovl_file *ovl_file_alloc(struct file *realfile);
 void ovl_file_free(struct ovl_file *of);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index dcccb4b4a66c..607860f199a8 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -959,7 +959,7 @@ void ovl_check_protattr(struct inode *inode, struct dentry *upper)
 }
 
 int ovl_set_protattr(struct inode *inode, struct dentry *upper,
-		      struct fileattr *fa)
+		      struct file_kattr *fa)
 {
 	struct ovl_fs *ofs = OVL_FS(inode->i_sb);
 	char buf[OVL_PROTATTR_MAX];
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index 2c99349cf537..79536b2e3d7a 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -130,7 +130,7 @@ static int setflags(struct inode *inode, int flags)
 	return err;
 }
 
-int ubifs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+int ubifs_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	int flags = ubifs2ioctl(ubifs_inode(inode)->flags);
@@ -145,7 +145,7 @@ int ubifs_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 int ubifs_fileattr_set(struct mnt_idmap *idmap,
-		       struct dentry *dentry, struct fileattr *fa)
+		       struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	int flags = fa->flags;
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index 256dbaeeb0de..5db45c9e26ee 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -2073,9 +2073,9 @@ int ubifs_recover_size(struct ubifs_info *c, bool in_place);
 void ubifs_destroy_size_tree(struct ubifs_info *c);
 
 /* ioctl.c */
-int ubifs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int ubifs_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int ubifs_fileattr_set(struct mnt_idmap *idmap,
-		       struct dentry *dentry, struct fileattr *fa);
+		       struct dentry *dentry, struct file_kattr *fa);
 long ubifs_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 void ubifs_set_inode_flags(struct inode *inode);
 #ifdef CONFIG_COMPAT
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index d250f7f74e3b..911b68175ad8 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -444,7 +444,7 @@ static void
 xfs_fill_fsxattr(
 	struct xfs_inode	*ip,
 	int			whichfork,
-	struct fileattr		*fa)
+	struct file_kattr	*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct xfs_ifork	*ifp = xfs_ifork_ptr(ip, whichfork);
@@ -496,7 +496,7 @@ xfs_ioc_fsgetxattra(
 	xfs_inode_t		*ip,
 	void			__user *arg)
 {
-	struct fileattr		fa;
+	struct file_kattr	fa;
 
 	xfs_ilock(ip, XFS_ILOCK_SHARED);
 	xfs_fill_fsxattr(ip, XFS_ATTR_FORK, &fa);
@@ -508,7 +508,7 @@ xfs_ioc_fsgetxattra(
 int
 xfs_fileattr_get(
 	struct dentry		*dentry,
-	struct fileattr		*fa)
+	struct file_kattr	*fa)
 {
 	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
 
@@ -526,7 +526,7 @@ static int
 xfs_ioctl_setattr_xflags(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*ip,
-	struct fileattr		*fa)
+	struct file_kattr	*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	bool			rtflag = (fa->fsx_xflags & FS_XFLAG_REALTIME);
@@ -582,7 +582,7 @@ xfs_ioctl_setattr_xflags(
 static void
 xfs_ioctl_setattr_prepare_dax(
 	struct xfs_inode	*ip,
-	struct fileattr		*fa)
+	struct file_kattr	*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	struct inode            *inode = VFS_I(ip);
@@ -642,7 +642,7 @@ out_error:
 static int
 xfs_ioctl_setattr_check_extsize(
 	struct xfs_inode	*ip,
-	struct fileattr		*fa)
+	struct file_kattr	*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_failaddr_t		failaddr;
@@ -684,7 +684,7 @@ xfs_ioctl_setattr_check_extsize(
 static int
 xfs_ioctl_setattr_check_cowextsize(
 	struct xfs_inode	*ip,
-	struct fileattr		*fa)
+	struct file_kattr	*fa)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_failaddr_t		failaddr;
@@ -709,7 +709,7 @@ xfs_ioctl_setattr_check_cowextsize(
 static int
 xfs_ioctl_setattr_check_projid(
 	struct xfs_inode	*ip,
-	struct fileattr		*fa)
+	struct file_kattr	*fa)
 {
 	if (!fa->fsx_valid)
 		return 0;
@@ -725,7 +725,7 @@ int
 xfs_fileattr_set(
 	struct mnt_idmap	*idmap,
 	struct dentry		*dentry,
-	struct fileattr		*fa)
+	struct file_kattr	*fa)
 {
 	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
 	struct xfs_mount	*mp = ip->i_mount;
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index 12124946f347..f5ed5cf9d3df 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -17,13 +17,13 @@ xfs_ioc_swapext(
 extern int
 xfs_fileattr_get(
 	struct dentry		*dentry,
-	struct fileattr		*fa);
+	struct file_kattr	*fa);
 
 extern int
 xfs_fileattr_set(
 	struct mnt_idmap	*idmap,
 	struct dentry		*dentry,
-	struct fileattr		*fa);
+	struct file_kattr	*fa);
 
 extern long
 xfs_file_ioctl(
diff --git a/include/linux/fileattr.h b/include/linux/fileattr.h
index e2a2f4ae242d..f89dcfad3f8f 100644
--- a/include/linux/fileattr.h
+++ b/include/linux/fileattr.h
@@ -40,7 +40,7 @@
  * is handled by the VFS helpers, so filesystems are free to implement just one
  * or both of these sub-interfaces.
  */
-struct fileattr {
+struct file_kattr {
 	u32	flags;		/* flags (FS_IOC_GETFLAGS/FS_IOC_SETFLAGS) */
 	/* struct fsxattr: */
 	u32	fsx_xflags;	/* xflags field value (get/set) */
@@ -53,10 +53,10 @@ struct fileattr {
 	bool	fsx_valid:1;
 };
 
-int copy_fsxattr_to_user(const struct fileattr *fa, struct fsxattr __user *ufa);
+int copy_fsxattr_to_user(const struct file_kattr *fa, struct fsxattr __user *ufa);
 
-void fileattr_fill_xflags(struct fileattr *fa, u32 xflags);
-void fileattr_fill_flags(struct fileattr *fa, u32 flags);
+void fileattr_fill_xflags(struct file_kattr *fa, u32 xflags);
+void fileattr_fill_flags(struct file_kattr *fa, u32 flags);
 
 /**
  * fileattr_has_fsx - check for extended flags/attributes
@@ -65,16 +65,16 @@ void fileattr_fill_flags(struct fileattr *fa, u32 flags);
  * Return: true if any attributes are present that are not represented in
  * ->flags.
  */
-static inline bool fileattr_has_fsx(const struct fileattr *fa)
+static inline bool fileattr_has_fsx(const struct file_kattr *fa)
 {
 	return fa->fsx_valid &&
 		((fa->fsx_xflags & ~FS_XFLAG_COMMON) || fa->fsx_extsize != 0 ||
 		 fa->fsx_projid != 0 ||	fa->fsx_cowextsize != 0);
 }
 
-int vfs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+int vfs_fileattr_get(struct dentry *dentry, struct file_kattr *fa);
 int vfs_fileattr_set(struct mnt_idmap *idmap, struct dentry *dentry,
-		     struct fileattr *fa);
+		     struct file_kattr *fa);
 int ioctl_getflags(struct file *file, unsigned int __user *argp);
 int ioctl_setflags(struct file *file, unsigned int __user *argp);
 int ioctl_fsgetxattr(struct file *file, void __user *argp);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..0c58617645ea 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -80,7 +80,7 @@ struct fsnotify_mark_connector;
 struct fsnotify_sb_info;
 struct fs_context;
 struct fs_parameter_spec;
-struct fileattr;
+struct file_kattr;
 struct iomap_ops;
 
 extern void __init inode_init(void);
@@ -2254,8 +2254,8 @@ struct inode_operations {
 	int (*set_acl)(struct mnt_idmap *, struct dentry *,
 		       struct posix_acl *, int);
 	int (*fileattr_set)(struct mnt_idmap *idmap,
-			    struct dentry *dentry, struct fileattr *fa);
-	int (*fileattr_get)(struct dentry *dentry, struct fileattr *fa);
+			    struct dentry *dentry, struct file_kattr *fa);
+	int (*fileattr_get)(struct dentry *dentry, struct file_kattr *fa);
 	struct offset_ctx *(*get_offset_ctx)(struct inode *inode);
 } ____cacheline_aligned;
 
diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
index 9600a4350e79..fd11fffdd3c3 100644
--- a/include/linux/lsm_hook_defs.h
+++ b/include/linux/lsm_hook_defs.h
@@ -157,8 +157,8 @@ LSM_HOOK(int, 0, inode_removexattr, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *name)
 LSM_HOOK(void, LSM_RET_VOID, inode_post_removexattr, struct dentry *dentry,
 	 const char *name)
-LSM_HOOK(int, 0, inode_file_setattr, struct dentry *dentry, struct fileattr *fa)
-LSM_HOOK(int, 0, inode_file_getattr, struct dentry *dentry, struct fileattr *fa)
+LSM_HOOK(int, 0, inode_file_setattr, struct dentry *dentry, struct file_kattr *fa)
+LSM_HOOK(int, 0, inode_file_getattr, struct dentry *dentry, struct file_kattr *fa)
 LSM_HOOK(int, 0, inode_set_acl, struct mnt_idmap *idmap,
 	 struct dentry *dentry, const char *acl_name, struct posix_acl *kacl)
 LSM_HOOK(void, LSM_RET_VOID, inode_post_set_acl, struct dentry *dentry,
diff --git a/include/linux/security.h b/include/linux/security.h
index 9ed0d0e0c81f..b95b5540c429 100644
--- a/include/linux/security.h
+++ b/include/linux/security.h
@@ -452,9 +452,9 @@ int security_inode_removexattr(struct mnt_idmap *idmap,
 			       struct dentry *dentry, const char *name);
 void security_inode_post_removexattr(struct dentry *dentry, const char *name);
 int security_inode_file_setattr(struct dentry *dentry,
-			      struct fileattr *fa);
+			      struct file_kattr *fa);
 int security_inode_file_getattr(struct dentry *dentry,
-			      struct fileattr *fa);
+			      struct file_kattr *fa);
 int security_inode_need_killpriv(struct dentry *dentry);
 int security_inode_killpriv(struct mnt_idmap *idmap, struct dentry *dentry);
 int security_inode_getsecurity(struct mnt_idmap *idmap,
@@ -1057,13 +1057,13 @@ static inline void security_inode_post_removexattr(struct dentry *dentry,
 { }
 
 static inline int security_inode_file_setattr(struct dentry *dentry,
-					      struct fileattr *fa)
+					      struct file_kattr *fa)
 {
 	return 0;
 }
 
 static inline int security_inode_file_getattr(struct dentry *dentry,
-					      struct fileattr *fa)
+					      struct file_kattr *fa)
 {
 	return 0;
 }
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 9663dbdda181..6e136c9c6a22 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -151,7 +151,7 @@ struct fsxattr {
 /*
  * Variable size structure for file_[sg]et_attr().
  *
- * Note. This is alternative to the structure 'struct fileattr'/'struct fsxattr'.
+ * Note. This is alternative to the structure 'struct file_kattr'/'struct fsxattr'.
  * As this structure is passed to/from userspace with its size, this can
  * be versioned based on the size.
  */
diff --git a/mm/shmem.c b/mm/shmem.c
index 0c5fb4ffa03a..6311fe35c577 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -4183,7 +4183,7 @@ static const char *shmem_get_link(struct dentry *dentry, struct inode *inode,
 
 #ifdef CONFIG_TMPFS_XATTR
 
-static int shmem_fileattr_get(struct dentry *dentry, struct fileattr *fa)
+static int shmem_fileattr_get(struct dentry *dentry, struct file_kattr *fa)
 {
 	struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
 
@@ -4193,7 +4193,7 @@ static int shmem_fileattr_get(struct dentry *dentry, struct fileattr *fa)
 }
 
 static int shmem_fileattr_set(struct mnt_idmap *idmap,
-			      struct dentry *dentry, struct fileattr *fa)
+			      struct dentry *dentry, struct file_kattr *fa)
 {
 	struct inode *inode = d_inode(dentry);
 	struct shmem_inode_info *info = SHMEM_I(inode);
diff --git a/security/security.c b/security/security.c
index 711b4de40b8d..a5766cbf6f7c 100644
--- a/security/security.c
+++ b/security/security.c
@@ -2632,7 +2632,7 @@ void security_inode_post_removexattr(struct dentry *dentry, const char *name)
  *
  * Return: Returns 0 if permission is granted.
  */
-int security_inode_file_setattr(struct dentry *dentry, struct fileattr *fa)
+int security_inode_file_setattr(struct dentry *dentry, struct file_kattr *fa)
 {
 	return call_int_hook(inode_file_setattr, dentry, fa);
 }
@@ -2647,7 +2647,7 @@ int security_inode_file_setattr(struct dentry *dentry, struct fileattr *fa)
  *
  * Return: Returns 0 if permission is granted.
  */
-int security_inode_file_getattr(struct dentry *dentry, struct fileattr *fa)
+int security_inode_file_getattr(struct dentry *dentry, struct file_kattr *fa)
 {
 	return call_int_hook(inode_file_getattr, dentry, fa);
 }
diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
index be7aca2269fa..0dadce2267c1 100644
--- a/security/selinux/hooks.c
+++ b/security/selinux/hooks.c
@@ -3481,13 +3481,13 @@ static int selinux_inode_removexattr(struct mnt_idmap *idmap,
 }
 
 static int selinux_inode_file_setattr(struct dentry *dentry,
-				      struct fileattr *fa)
+				      struct file_kattr *fa)
 {
 	return dentry_has_perm(current_cred(), dentry, FILE__SETATTR);
 }
 
 static int selinux_inode_file_getattr(struct dentry *dentry,
-				      struct fileattr *fa)
+				      struct file_kattr *fa)
 {
 	return dentry_has_perm(current_cred(), dentry, FILE__GETATTR);
 }
-- 
cgit v1.2.3


From 1924272b9ce1edc5694e6d112097fd51e821980e Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Thu, 26 Jun 2025 11:02:28 +0200
Subject: soc: qcom: Add UBWC config provider

Add a file that will serve as a single source of truth for UBWC
configuration data for various multimedia blocks.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/660959/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/soc/qcom/Kconfig       |   8 ++
 drivers/soc/qcom/Makefile      |   1 +
 drivers/soc/qcom/ubwc_config.c | 251 +++++++++++++++++++++++++++++++++++++++++
 include/linux/soc/qcom/ubwc.h  |  65 +++++++++++
 4 files changed, 325 insertions(+)
 create mode 100644 drivers/soc/qcom/ubwc_config.c
 create mode 100644 include/linux/soc/qcom/ubwc.h

(limited to 'include/linux')

diff --git a/drivers/soc/qcom/Kconfig b/drivers/soc/qcom/Kconfig
index 58e63cf0036b..2caadbbcf830 100644
--- a/drivers/soc/qcom/Kconfig
+++ b/drivers/soc/qcom/Kconfig
@@ -296,3 +296,11 @@ config QCOM_PBS
 	  PBS trigger event to the PBS RAM.
 
 endmenu
+
+config QCOM_UBWC_CONFIG
+	tristate
+	help
+	  Most Qualcomm SoCs feature a number of Universal Bandwidth Compression
+	  (UBWC) engines across various IP blocks, which need to be initialized
+	  with coherent configuration data. This module functions as a single
+	  source of truth for that information.
diff --git a/drivers/soc/qcom/Makefile b/drivers/soc/qcom/Makefile
index acbca2ab5cc2..b7f1d2a57367 100644
--- a/drivers/soc/qcom/Makefile
+++ b/drivers/soc/qcom/Makefile
@@ -39,3 +39,4 @@ obj-$(CONFIG_QCOM_ICC_BWMON)	+= icc-bwmon.o
 qcom_ice-objs			+= ice.o
 obj-$(CONFIG_QCOM_INLINE_CRYPTO_ENGINE)	+= qcom_ice.o
 obj-$(CONFIG_QCOM_PBS) +=	qcom-pbs.o
+obj-$(CONFIG_QCOM_UBWC_CONFIG) += ubwc_config.o
diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
new file mode 100644
index 000000000000..18a853a3f76c
--- /dev/null
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
+ */
+
+#include <linux/debugfs.h>
+#include <linux/io.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/platform_device.h>
+
+#include <linux/soc/qcom/ubwc.h>
+
+static const struct qcom_ubwc_cfg_data msm8937_data = {
+	.ubwc_enc_version = UBWC_1_0,
+	.ubwc_dec_version = UBWC_1_0,
+	.highest_bank_bit = 14,
+};
+
+static const struct qcom_ubwc_cfg_data msm8998_data = {
+	.ubwc_enc_version = UBWC_1_0,
+	.ubwc_dec_version = UBWC_1_0,
+	.highest_bank_bit = 15,
+};
+
+static const struct qcom_ubwc_cfg_data qcm2290_data = {
+	/* no UBWC */
+	.highest_bank_bit = 15,
+};
+
+static const struct qcom_ubwc_cfg_data sa8775p_data = {
+	.ubwc_enc_version = UBWC_4_0,
+	.ubwc_dec_version = UBWC_4_0,
+	.ubwc_swizzle = 4,
+	.ubwc_bank_spread = true,
+	.highest_bank_bit = 13,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data sar2130p_data = {
+	.ubwc_enc_version = UBWC_3_0, /* 4.0.2 in hw */
+	.ubwc_dec_version = UBWC_4_3,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	.highest_bank_bit = 13,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data sc7180_data = {
+	.ubwc_enc_version = UBWC_2_0,
+	.ubwc_dec_version = UBWC_2_0,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	.highest_bank_bit = 14,
+};
+
+static const struct qcom_ubwc_cfg_data sc7280_data = {
+	.ubwc_enc_version = UBWC_3_0,
+	.ubwc_dec_version = UBWC_4_0,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	.highest_bank_bit = 14,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data sc8180x_data = {
+	.ubwc_enc_version = UBWC_3_0,
+	.ubwc_dec_version = UBWC_3_0,
+	.highest_bank_bit = 16,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data sc8280xp_data = {
+	.ubwc_enc_version = UBWC_4_0,
+	.ubwc_dec_version = UBWC_4_0,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	.highest_bank_bit = 16,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data sdm670_data = {
+	.ubwc_enc_version = UBWC_2_0,
+	.ubwc_dec_version = UBWC_2_0,
+	.highest_bank_bit = 14,
+};
+
+static const struct qcom_ubwc_cfg_data sdm845_data = {
+	.ubwc_enc_version = UBWC_2_0,
+	.ubwc_dec_version = UBWC_2_0,
+	.highest_bank_bit = 15,
+};
+
+static const struct qcom_ubwc_cfg_data sm6115_data = {
+	.ubwc_enc_version = UBWC_1_0,
+	.ubwc_dec_version = UBWC_2_0,
+	.ubwc_swizzle = 7,
+	.ubwc_bank_spread = true,
+	.highest_bank_bit = 14,
+};
+
+static const struct qcom_ubwc_cfg_data sm6125_data = {
+	.ubwc_enc_version = UBWC_1_0,
+	.ubwc_dec_version = UBWC_3_0,
+	.ubwc_swizzle = 1,
+	.highest_bank_bit = 14,
+};
+
+static const struct qcom_ubwc_cfg_data sm6150_data = {
+	.ubwc_enc_version = UBWC_2_0,
+	.ubwc_dec_version = UBWC_2_0,
+	.highest_bank_bit = 14,
+};
+
+static const struct qcom_ubwc_cfg_data sm6350_data = {
+	.ubwc_enc_version = UBWC_2_0,
+	.ubwc_dec_version = UBWC_2_0,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	.highest_bank_bit = 14,
+};
+
+static const struct qcom_ubwc_cfg_data sm7150_data = {
+	.ubwc_enc_version = UBWC_2_0,
+	.ubwc_dec_version = UBWC_2_0,
+	.highest_bank_bit = 14,
+};
+
+static const struct qcom_ubwc_cfg_data sm8150_data = {
+	.ubwc_enc_version = UBWC_3_0,
+	.ubwc_dec_version = UBWC_3_0,
+	.highest_bank_bit = 15,
+};
+
+static const struct qcom_ubwc_cfg_data sm8250_data = {
+	.ubwc_enc_version = UBWC_4_0,
+	.ubwc_dec_version = UBWC_4_0,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
+	.highest_bank_bit = 16,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data sm8350_data = {
+	.ubwc_enc_version = UBWC_4_0,
+	.ubwc_dec_version = UBWC_4_0,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
+	.highest_bank_bit = 16,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data sm8550_data = {
+	.ubwc_enc_version = UBWC_4_0,
+	.ubwc_dec_version = UBWC_4_3,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
+	.highest_bank_bit = 16,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data sm8750_data = {
+	.ubwc_enc_version = UBWC_5_0,
+	.ubwc_dec_version = UBWC_5_0,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
+	.highest_bank_bit = 16,
+	.macrotile_mode = true,
+};
+
+static const struct qcom_ubwc_cfg_data x1e80100_data = {
+	.ubwc_enc_version = UBWC_4_0,
+	.ubwc_dec_version = UBWC_4_3,
+	.ubwc_swizzle = 6,
+	.ubwc_bank_spread = true,
+	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
+	.highest_bank_bit = 16,
+	.macrotile_mode = true,
+};
+
+static const struct of_device_id qcom_ubwc_configs[] __maybe_unused = {
+	{ .compatible = "qcom,apq8096", .data = &msm8998_data },
+	{ .compatible = "qcom,msm8917", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8937", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8953", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8956", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8976", .data = &msm8937_data },
+	{ .compatible = "qcom,msm8996", .data = &msm8998_data },
+	{ .compatible = "qcom,msm8998", .data = &msm8998_data },
+	{ .compatible = "qcom,qcm2290", .data = &qcm2290_data, },
+	{ .compatible = "qcom,qcm6490", .data = &sc7280_data, },
+	{ .compatible = "qcom,sa8155p", .data = &sm8150_data, },
+	{ .compatible = "qcom,sa8540p", .data = &sc8280xp_data, },
+	{ .compatible = "qcom,sa8775p", .data = &sa8775p_data, },
+	{ .compatible = "qcom,sar2130p", .data = &sar2130p_data },
+	{ .compatible = "qcom,sc7180", .data = &sc7180_data },
+	{ .compatible = "qcom,sc7280", .data = &sc7280_data, },
+	{ .compatible = "qcom,sc8180x", .data = &sc8180x_data, },
+	{ .compatible = "qcom,sc8280xp", .data = &sc8280xp_data, },
+	{ .compatible = "qcom,sdm630", .data = &msm8937_data },
+	{ .compatible = "qcom,sdm636", .data = &msm8937_data },
+	{ .compatible = "qcom,sdm660", .data = &msm8937_data },
+	{ .compatible = "qcom,sdm670", .data = &sdm670_data, },
+	{ .compatible = "qcom,sdm845", .data = &sdm845_data, },
+	{ .compatible = "qcom,sm4250", .data = &sm6115_data, },
+	{ .compatible = "qcom,sm6115", .data = &sm6115_data, },
+	{ .compatible = "qcom,sm6125", .data = &sm6125_data, },
+	{ .compatible = "qcom,sm6150", .data = &sm6150_data, },
+	{ .compatible = "qcom,sm6350", .data = &sm6350_data, },
+	{ .compatible = "qcom,sm6375", .data = &sm6350_data, },
+	{ .compatible = "qcom,sm7125", .data = &sc7180_data },
+	{ .compatible = "qcom,sm7150", .data = &sm7150_data, },
+	{ .compatible = "qcom,sm8150", .data = &sm8150_data, },
+	{ .compatible = "qcom,sm8250", .data = &sm8250_data, },
+	{ .compatible = "qcom,sm8350", .data = &sm8350_data, },
+	{ .compatible = "qcom,sm8450", .data = &sm8350_data, },
+	{ .compatible = "qcom,sm8550", .data = &sm8550_data, },
+	{ .compatible = "qcom,sm8650", .data = &sm8550_data, },
+	{ .compatible = "qcom,sm8750", .data = &sm8750_data, },
+	{ .compatible = "qcom,x1e80100", .data = &x1e80100_data, },
+	{ .compatible = "qcom,x1p42100", .data = &x1e80100_data, },
+	{ }
+};
+
+const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void)
+{
+	const struct of_device_id *match;
+	struct device_node *root;
+
+	root = of_find_node_by_path("/");
+	if (!root)
+		return ERR_PTR(-ENODEV);
+
+	match = of_match_node(qcom_ubwc_configs, root);
+	of_node_put(root);
+	if (!match) {
+		pr_err("Couldn't find UBWC config data for this platform!\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	return match->data;
+}
+EXPORT_SYMBOL_GPL(qcom_ubwc_config_get_data);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("UBWC config database for QTI SoCs");
diff --git a/include/linux/soc/qcom/ubwc.h b/include/linux/soc/qcom/ubwc.h
new file mode 100644
index 000000000000..b92fc402638b
--- /dev/null
+++ b/include/linux/soc/qcom/ubwc.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2018, The Linux Foundation
+ * Copyright (c) Qualcomm Technologies, Inc. and/or its subsidiaries.
+ */
+
+#ifndef __QCOM_UBWC_H__
+#define __QCOM_UBWC_H__
+
+#include <linux/bits.h>
+#include <linux/types.h>
+
+struct qcom_ubwc_cfg_data {
+	u32 ubwc_enc_version;
+	/* Can be read from MDSS_BASE + 0x58 */
+	u32 ubwc_dec_version;
+
+	/**
+	 * @ubwc_swizzle: Whether to enable level 1, 2 & 3 bank swizzling.
+	 *
+	 * UBWC 1.0 always enables all three levels.
+	 * UBWC 2.0 removes level 1 bank swizzling, leaving levels 2 & 3.
+	 * UBWC 4.0 adds the optional ability to disable levels 2 & 3.
+	 *
+	 * This is a bitmask where BIT(0) enables level 1, BIT(1)
+	 * controls level 2, and BIT(2) enables level 3.
+	 */
+	u32 ubwc_swizzle;
+
+	/**
+	 * @highest_bank_bit: Highest Bank Bit
+	 *
+	 * The Highest Bank Bit value represents the bit of the highest
+	 * DDR bank.  This should ideally use DRAM type detection.
+	 */
+	int highest_bank_bit;
+	bool ubwc_bank_spread;
+
+	/**
+	 * @macrotile_mode: Macrotile Mode
+	 *
+	 * Whether to use 4-channel macrotiling mode or the newer
+	 * 8-channel macrotiling mode introduced in UBWC 3.1. 0 is
+	 * 4-channel and 1 is 8-channel.
+	 */
+	bool macrotile_mode;
+};
+
+#define UBWC_1_0 0x10000000
+#define UBWC_2_0 0x20000000
+#define UBWC_3_0 0x30000000
+#define UBWC_4_0 0x40000000
+#define UBWC_4_3 0x40030000
+#define UBWC_5_0 0x50000000
+
+#ifdef CONFIG_QCOM_UBWC_CONFIG
+const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void);
+#else
+static inline const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void)
+{
+	return ERR_PTR(-EOPNOTSUPP);
+}
+#endif
+
+#endif /* __QCOM_UBWC_H__ */
-- 
cgit v1.2.3


From 45a2974157d2d8b6f26911582d64089cab992d8b Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Thu, 26 Jun 2025 11:02:30 +0200
Subject: drm/msm: Use the central UBWC config database

As discussed a lot in the past, the UBWC config must be coherent across
a number of IP blocks (currently display and GPU, but it also may/will
concern camera/video as the drivers evolve).

So far, we've been trying to keep the values reasonable in each of the
two drivers separately, but it really make sense to do so centrally,
especially given certain fields (e.g. HBB) may need to be gathered
dynamically.

To reduce room for error, move to fetching the config from a central
source, so that the data programmed into the hardware is consistent
across all multimedia blocks that request it.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/660963/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/Kconfig                 |   1 +
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c |   6 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h |   4 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c     |   7 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h     |   2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c   |   3 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c      |   2 +-
 drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h      |   2 +-
 drivers/gpu/drm/msm/msm_mdss.c              | 332 +++++-----------------------
 drivers/gpu/drm/msm/msm_mdss.h              |  29 ---
 include/linux/soc/qcom/ubwc.h               |   2 +-
 11 files changed, 71 insertions(+), 319 deletions(-)
 delete mode 100644 drivers/gpu/drm/msm/msm_mdss.h

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/msm/Kconfig b/drivers/gpu/drm/msm/Kconfig
index 1523bc3e9540..8fb99f64a615 100644
--- a/drivers/gpu/drm/msm/Kconfig
+++ b/drivers/gpu/drm/msm/Kconfig
@@ -31,6 +31,7 @@ config DRM_MSM
 	select SHMEM
 	select TMPFS
 	select QCOM_SCM
+	select QCOM_UBWC_CONFIG
 	select WANT_DEV_COREDUMP
 	select SND_SOC_HDMI_CODEC if SND_SOC
 	select SYNC_FILE
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
index 7dfd0e0a7795..6f1fc790ad6d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.c
@@ -10,11 +10,11 @@
 #include "dpu_hw_sspp.h"
 #include "dpu_kms.h"
 
-#include "msm_mdss.h"
-
 #include <drm/drm_file.h>
 #include <drm/drm_managed.h>
 
+#include <linux/soc/qcom/ubwc.h>
+
 #define DPU_FETCH_CONFIG_RESET_VALUE   0x00000087
 
 /* SSPP registers */
@@ -684,7 +684,7 @@ int _dpu_hw_sspp_init_debugfs(struct dpu_hw_sspp *hw_pipe, struct dpu_kms *kms,
 struct dpu_hw_sspp *dpu_hw_sspp_init(struct drm_device *dev,
 				     const struct dpu_sspp_cfg *cfg,
 				     void __iomem *addr,
-				     const struct msm_mdss_data *mdss_data,
+				     const struct qcom_ubwc_cfg_data *mdss_data,
 				     const struct dpu_mdss_version *mdss_rev)
 {
 	struct dpu_hw_sspp *hw_pipe;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
index ed90e78d178a..bdac5c04bf79 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_sspp.h
@@ -308,7 +308,7 @@ struct dpu_hw_sspp_ops {
 struct dpu_hw_sspp {
 	struct dpu_hw_blk base;
 	struct dpu_hw_blk_reg_map hw;
-	const struct msm_mdss_data *ubwc;
+	const struct qcom_ubwc_cfg_data *ubwc;
 
 	/* Pipe */
 	enum dpu_sspp idx;
@@ -325,7 +325,7 @@ struct dpu_kms;
 struct dpu_hw_sspp *dpu_hw_sspp_init(struct drm_device *dev,
 				     const struct dpu_sspp_cfg *cfg,
 				     void __iomem *addr,
-				     const struct msm_mdss_data *mdss_data,
+				     const struct qcom_ubwc_cfg_data *mdss_data,
 				     const struct dpu_mdss_version *mdss_rev);
 
 int _dpu_hw_sspp_init_debugfs(struct dpu_hw_sspp *hw_pipe, struct dpu_kms *kms,
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
index fa463ccc135d..e63a62664f39 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c
@@ -20,9 +20,10 @@
 #include <drm/drm_vblank.h>
 #include <drm/drm_writeback.h>
 
+#include <linux/soc/qcom/ubwc.h>
+
 #include "msm_drv.h"
 #include "msm_mmu.h"
-#include "msm_mdss.h"
 #include "msm_gem.h"
 #include "disp/msm_disp_snapshot.h"
 
@@ -1189,10 +1190,10 @@ static int dpu_kms_hw_init(struct msm_kms *kms)
 		goto err_pm_put;
 	}
 
-	dpu_kms->mdss = msm_mdss_get_mdss_data(dpu_kms->pdev->dev.parent);
+	dpu_kms->mdss = qcom_ubwc_config_get_data();
 	if (IS_ERR(dpu_kms->mdss)) {
 		rc = PTR_ERR(dpu_kms->mdss);
-		DPU_ERROR("failed to get MDSS data: %d\n", rc);
+		DPU_ERROR("failed to get UBWC config data: %d\n", rc);
 		goto err_pm_put;
 	}
 
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
index a57ec2ec1060..993cf512f8c5 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
@@ -60,7 +60,7 @@ struct dpu_kms {
 	struct msm_kms base;
 	struct drm_device *dev;
 	const struct dpu_mdss_cfg *catalog;
-	const struct msm_mdss_data *mdss;
+	const struct qcom_ubwc_cfg_data *mdss;
 
 	/* io/register spaces: */
 	void __iomem *mmio, *vbif[VBIF_MAX];
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
index 07f0461223c3..01171c535a27 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
@@ -17,8 +17,9 @@
 #include <drm/drm_framebuffer.h>
 #include <drm/drm_gem_atomic_helper.h>
 
+#include <linux/soc/qcom/ubwc.h>
+
 #include "msm_drv.h"
-#include "msm_mdss.h"
 #include "dpu_kms.h"
 #include "dpu_hw_sspp.h"
 #include "dpu_hw_util.h"
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
index a2219c4f55a4..25382120cb1a 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.c
@@ -40,7 +40,7 @@ static inline bool reserved_by_other(uint32_t *res_map, int idx,
 int dpu_rm_init(struct drm_device *dev,
 		struct dpu_rm *rm,
 		const struct dpu_mdss_cfg *cat,
-		const struct msm_mdss_data *mdss_data,
+		const struct qcom_ubwc_cfg_data *mdss_data,
 		void __iomem *mmio)
 {
 	int rc, i;
diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
index aa62966056d4..ccd64404f12d 100644
--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
+++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_rm.h
@@ -69,7 +69,7 @@ struct msm_display_topology {
 int dpu_rm_init(struct drm_device *dev,
 		struct dpu_rm *rm,
 		const struct dpu_mdss_cfg *cat,
-		const struct msm_mdss_data *mdss_data,
+		const struct qcom_ubwc_cfg_data *mdss_data,
 		void __iomem *mmio);
 
 int dpu_rm_reserve(struct dpu_rm *rm,
diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
index 597c8e649853..1f5fe7811e01 100644
--- a/drivers/gpu/drm/msm/msm_mdss.c
+++ b/drivers/gpu/drm/msm/msm_mdss.c
@@ -16,14 +16,17 @@
 #include <linux/pm_runtime.h>
 #include <linux/reset.h>
 
-#include "msm_mdss.h"
+#include <linux/soc/qcom/ubwc.h>
+
 #include "msm_kms.h"
 
 #include <generated/mdss.xml.h>
 
 #define MIN_IB_BW	400000000UL /* Min ib vote 400MB */
 
-#define DEFAULT_REG_BW	153600 /* Used in mdss fbdev driver */
+struct msm_mdss_data {
+	u32 reg_bus_bw;
+};
 
 struct msm_mdss {
 	struct device *dev;
@@ -36,7 +39,8 @@ struct msm_mdss {
 		unsigned long enabled_mask;
 		struct irq_domain *domain;
 	} irq_controller;
-	const struct msm_mdss_data *mdss_data;
+	const struct qcom_ubwc_cfg_data *mdss_data;
+	u32 reg_bus_bw;
 	struct icc_path *mdp_path[2];
 	u32 num_mdp_paths;
 	struct icc_path *reg_bus_path;
@@ -165,7 +169,7 @@ static int _msm_mdss_irq_domain_add(struct msm_mdss *msm_mdss)
 
 static void msm_mdss_setup_ubwc_dec_20(struct msm_mdss *msm_mdss)
 {
-	const struct msm_mdss_data *data = msm_mdss->mdss_data;
+	const struct qcom_ubwc_cfg_data *data = msm_mdss->mdss_data;
 	u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle) |
 		    MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit - 13);
 
@@ -180,7 +184,7 @@ static void msm_mdss_setup_ubwc_dec_20(struct msm_mdss *msm_mdss)
 
 static void msm_mdss_setup_ubwc_dec_30(struct msm_mdss *msm_mdss)
 {
-	const struct msm_mdss_data *data = msm_mdss->mdss_data;
+	const struct qcom_ubwc_cfg_data *data = msm_mdss->mdss_data;
 	u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle & 0x1) |
 		    MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit - 13);
 
@@ -198,7 +202,7 @@ static void msm_mdss_setup_ubwc_dec_30(struct msm_mdss *msm_mdss)
 
 static void msm_mdss_setup_ubwc_dec_40(struct msm_mdss *msm_mdss)
 {
-	const struct msm_mdss_data *data = msm_mdss->mdss_data;
+	const struct qcom_ubwc_cfg_data *data = msm_mdss->mdss_data;
 	u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle) |
 		    MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit - 13);
 
@@ -224,7 +228,7 @@ static void msm_mdss_setup_ubwc_dec_40(struct msm_mdss *msm_mdss)
 
 static void msm_mdss_setup_ubwc_dec_50(struct msm_mdss *msm_mdss)
 {
-	const struct msm_mdss_data *data = msm_mdss->mdss_data;
+	const struct qcom_ubwc_cfg_data *data = msm_mdss->mdss_data;
 	u32 value = MDSS_UBWC_STATIC_UBWC_SWIZZLE(data->ubwc_swizzle) |
 		    MDSS_UBWC_STATIC_HIGHEST_BANK_BIT(data->highest_bank_bit);
 
@@ -240,69 +244,6 @@ static void msm_mdss_setup_ubwc_dec_50(struct msm_mdss *msm_mdss)
 	writel_relaxed(1, msm_mdss->mmio + REG_MDSS_UBWC_PREDICTION_MODE);
 }
 
-#define MDSS_HW_MAJ_MIN		\
-	(MDSS_HW_VERSION_MAJOR__MASK | MDSS_HW_VERSION_MINOR__MASK)
-
-#define MDSS_HW_MSM8996		0x1007
-#define MDSS_HW_MSM8937		0x100e
-#define MDSS_HW_MSM8953		0x1010
-#define MDSS_HW_MSM8998		0x3000
-#define MDSS_HW_SDM660		0x3002
-#define MDSS_HW_SDM630		0x3003
-
-/*
- * MDP5 platforms use generic qcom,mdp5 compat string, so we have to generate this data
- */
-static const struct msm_mdss_data *msm_mdss_generate_mdp5_mdss_data(struct msm_mdss *mdss)
-{
-	struct msm_mdss_data *data;
-	u32 hw_rev;
-
-	data = devm_kzalloc(mdss->dev, sizeof(*data), GFP_KERNEL);
-	if (!data)
-		return NULL;
-
-	hw_rev = readl_relaxed(mdss->mmio + REG_MDSS_HW_VERSION);
-	hw_rev = FIELD_GET(MDSS_HW_MAJ_MIN, hw_rev);
-
-	if (hw_rev == MDSS_HW_MSM8996 ||
-	    hw_rev == MDSS_HW_MSM8937 ||
-	    hw_rev == MDSS_HW_MSM8953 ||
-	    hw_rev == MDSS_HW_MSM8998 ||
-	    hw_rev == MDSS_HW_SDM660 ||
-	    hw_rev == MDSS_HW_SDM630) {
-		data->ubwc_dec_version = UBWC_1_0;
-		data->ubwc_enc_version = UBWC_1_0;
-	}
-
-	if (hw_rev == MDSS_HW_MSM8996 ||
-	    hw_rev == MDSS_HW_MSM8998)
-		data->highest_bank_bit = 15;
-	else
-		data->highest_bank_bit = 14;
-
-	return data;
-}
-
-const struct msm_mdss_data *msm_mdss_get_mdss_data(struct device *dev)
-{
-	struct msm_mdss *mdss;
-
-	if (!dev)
-		return ERR_PTR(-EINVAL);
-
-	mdss = dev_get_drvdata(dev);
-
-	/*
-	 * We could not do it at the probe time, since hw revision register was
-	 * not readable. Fill data structure now for the MDP5 platforms.
-	 */
-	if (!mdss->mdss_data && mdss->is_mdp5)
-		mdss->mdss_data = msm_mdss_generate_mdp5_mdss_data(mdss);
-
-	return mdss->mdss_data;
-}
-
 static int msm_mdss_enable(struct msm_mdss *msm_mdss)
 {
 	int ret, i;
@@ -315,12 +256,8 @@ static int msm_mdss_enable(struct msm_mdss *msm_mdss)
 	for (i = 0; i < msm_mdss->num_mdp_paths; i++)
 		icc_set_bw(msm_mdss->mdp_path[i], 0, Bps_to_icc(MIN_IB_BW));
 
-	if (msm_mdss->mdss_data && msm_mdss->mdss_data->reg_bus_bw)
-		icc_set_bw(msm_mdss->reg_bus_path, 0,
-			   msm_mdss->mdss_data->reg_bus_bw);
-	else
-		icc_set_bw(msm_mdss->reg_bus_path, 0,
-			   DEFAULT_REG_BW);
+	icc_set_bw(msm_mdss->reg_bus_path, 0,
+		   msm_mdss->reg_bus_bw);
 
 	ret = clk_bulk_prepare_enable(msm_mdss->num_clocks, msm_mdss->clocks);
 	if (ret) {
@@ -459,6 +396,7 @@ static int mdp5_mdss_parse_clock(struct platform_device *pdev, struct clk_bulk_d
 
 static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5)
 {
+	const struct msm_mdss_data *mdss_data;
 	struct msm_mdss *msm_mdss;
 	int ret;
 	int irq;
@@ -471,7 +409,15 @@ static struct msm_mdss *msm_mdss_init(struct platform_device *pdev, bool is_mdp5
 	if (!msm_mdss)
 		return ERR_PTR(-ENOMEM);
 
-	msm_mdss->mdss_data = of_device_get_match_data(&pdev->dev);
+	msm_mdss->mdss_data = qcom_ubwc_config_get_data();
+	if (IS_ERR(msm_mdss->mdss_data))
+		return ERR_CAST(msm_mdss->mdss_data);
+
+	mdss_data = of_device_get_match_data(&pdev->dev);
+	if (!mdss_data)
+		return ERR_PTR(-EINVAL);
+
+	msm_mdss->reg_bus_bw = mdss_data->reg_bus_bw;
 
 	msm_mdss->mmio = devm_platform_ioremap_resource_byname(pdev, is_mdp5 ? "mdss_phys" : "mdss");
 	if (IS_ERR(msm_mdss->mmio))
@@ -590,217 +536,49 @@ static void mdss_remove(struct platform_device *pdev)
 	msm_mdss_destroy(mdss);
 }
 
-static const struct msm_mdss_data msm8998_data = {
-	.ubwc_enc_version = UBWC_1_0,
-	.ubwc_dec_version = UBWC_1_0,
-	.highest_bank_bit = 15,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data qcm2290_data = {
-	/* no UBWC */
-	.highest_bank_bit = 15,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sa8775p_data = {
-	.ubwc_enc_version = UBWC_4_0,
-	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 4,
-	.ubwc_bank_spread = true,
-	.highest_bank_bit = 13,
-	.macrotile_mode = true,
-	.reg_bus_bw = 74000,
-};
-
-static const struct msm_mdss_data sar2130p_data = {
-	.ubwc_enc_version = UBWC_3_0, /* 4.0.2 in hw */
-	.ubwc_dec_version = UBWC_4_3,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	.highest_bank_bit = 13,
-	.macrotile_mode = 1,
-	.reg_bus_bw = 74000,
-};
-
-static const struct msm_mdss_data sc7180_data = {
-	.ubwc_enc_version = UBWC_2_0,
-	.ubwc_dec_version = UBWC_2_0,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	.highest_bank_bit = 14,
-	.reg_bus_bw = 76800,
+static const struct msm_mdss_data data_57k = {
+	.reg_bus_bw = 57000,
 };
 
-static const struct msm_mdss_data sc7280_data = {
-	.ubwc_enc_version = UBWC_3_0,
-	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	.highest_bank_bit = 14,
-	.macrotile_mode = true,
+static const struct msm_mdss_data data_74k = {
 	.reg_bus_bw = 74000,
 };
 
-static const struct msm_mdss_data sc8180x_data = {
-	.ubwc_enc_version = UBWC_3_0,
-	.ubwc_dec_version = UBWC_3_0,
-	.highest_bank_bit = 16,
-	.macrotile_mode = true,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sc8280xp_data = {
-	.ubwc_enc_version = UBWC_4_0,
-	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	.highest_bank_bit = 16,
-	.macrotile_mode = true,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sdm670_data = {
-	.ubwc_enc_version = UBWC_2_0,
-	.ubwc_dec_version = UBWC_2_0,
-	.highest_bank_bit = 14,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sdm845_data = {
-	.ubwc_enc_version = UBWC_2_0,
-	.ubwc_dec_version = UBWC_2_0,
-	.highest_bank_bit = 15,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sm6350_data = {
-	.ubwc_enc_version = UBWC_2_0,
-	.ubwc_dec_version = UBWC_2_0,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	.highest_bank_bit = 14,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sm7150_data = {
-	.ubwc_enc_version = UBWC_2_0,
-	.ubwc_dec_version = UBWC_2_0,
-	.highest_bank_bit = 14,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sm8150_data = {
-	.ubwc_enc_version = UBWC_3_0,
-	.ubwc_dec_version = UBWC_3_0,
-	.highest_bank_bit = 15,
+static const struct msm_mdss_data data_76k8 = {
 	.reg_bus_bw = 76800,
 };
 
-static const struct msm_mdss_data sm6115_data = {
-	.ubwc_enc_version = UBWC_1_0,
-	.ubwc_dec_version = UBWC_2_0,
-	.ubwc_swizzle = 7,
-	.ubwc_bank_spread = true,
-	.highest_bank_bit = 14,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sm6125_data = {
-	.ubwc_enc_version = UBWC_1_0,
-	.ubwc_dec_version = UBWC_3_0,
-	.ubwc_swizzle = 1,
-	.highest_bank_bit = 14,
-};
-
-static const struct msm_mdss_data sm6150_data = {
-	.ubwc_enc_version = UBWC_2_0,
-	.ubwc_dec_version = UBWC_2_0,
-	.highest_bank_bit = 14,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sm8250_data = {
-	.ubwc_enc_version = UBWC_4_0,
-	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	/* TODO: highest_bank_bit = 2 for LP_DDR4 */
-	.highest_bank_bit = 16,
-	.macrotile_mode = true,
-	.reg_bus_bw = 76800,
-};
-
-static const struct msm_mdss_data sm8350_data = {
-	.ubwc_enc_version = UBWC_4_0,
-	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	/* TODO: highest_bank_bit = 2 for LP_DDR4 */
-	.highest_bank_bit = 16,
-	.macrotile_mode = true,
-	.reg_bus_bw = 74000,
-};
-
-static const struct msm_mdss_data sm8550_data = {
-	.ubwc_enc_version = UBWC_4_0,
-	.ubwc_dec_version = UBWC_4_3,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	/* TODO: highest_bank_bit = 2 for LP_DDR4 */
-	.highest_bank_bit = 16,
-	.macrotile_mode = true,
-	.reg_bus_bw = 57000,
-};
-
-static const struct msm_mdss_data sm8750_data = {
-	.ubwc_enc_version = UBWC_5_0,
-	.ubwc_dec_version = UBWC_5_0,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	/* TODO: highest_bank_bit = 2 for LP_DDR4 */
-	.highest_bank_bit = 16,
-	.macrotile_mode = true,
-	.reg_bus_bw = 57000,
-};
-
-static const struct msm_mdss_data x1e80100_data = {
-	.ubwc_enc_version = UBWC_4_0,
-	.ubwc_dec_version = UBWC_4_3,
-	.ubwc_swizzle = 6,
-	.ubwc_bank_spread = true,
-	/* TODO: highest_bank_bit = 2 for LP_DDR4 */
-	.highest_bank_bit = 16,
-	.macrotile_mode = true,
-	/* TODO: Add reg_bus_bw with real value */
+static const struct msm_mdss_data data_153k6 = {
+	.reg_bus_bw = 153600,
 };
 
 static const struct of_device_id mdss_dt_match[] = {
-	{ .compatible = "qcom,mdss" },
-	{ .compatible = "qcom,msm8998-mdss", .data = &msm8998_data },
-	{ .compatible = "qcom,qcm2290-mdss", .data = &qcm2290_data },
-	{ .compatible = "qcom,sa8775p-mdss", .data = &sa8775p_data },
-	{ .compatible = "qcom,sar2130p-mdss", .data = &sar2130p_data },
-	{ .compatible = "qcom,sdm670-mdss", .data = &sdm670_data },
-	{ .compatible = "qcom,sdm845-mdss", .data = &sdm845_data },
-	{ .compatible = "qcom,sc7180-mdss", .data = &sc7180_data },
-	{ .compatible = "qcom,sc7280-mdss", .data = &sc7280_data },
-	{ .compatible = "qcom,sc8180x-mdss", .data = &sc8180x_data },
-	{ .compatible = "qcom,sc8280xp-mdss", .data = &sc8280xp_data },
-	{ .compatible = "qcom,sm6115-mdss", .data = &sm6115_data },
-	{ .compatible = "qcom,sm6125-mdss", .data = &sm6125_data },
-	{ .compatible = "qcom,sm6150-mdss", .data = &sm6150_data },
-	{ .compatible = "qcom,sm6350-mdss", .data = &sm6350_data },
-	{ .compatible = "qcom,sm6375-mdss", .data = &sm6350_data },
-	{ .compatible = "qcom,sm7150-mdss", .data = &sm7150_data },
-	{ .compatible = "qcom,sm8150-mdss", .data = &sm8150_data },
-	{ .compatible = "qcom,sm8250-mdss", .data = &sm8250_data },
-	{ .compatible = "qcom,sm8350-mdss", .data = &sm8350_data },
-	{ .compatible = "qcom,sm8450-mdss", .data = &sm8350_data },
-	{ .compatible = "qcom,sm8550-mdss", .data = &sm8550_data },
-	{ .compatible = "qcom,sm8650-mdss", .data = &sm8550_data},
-	{ .compatible = "qcom,sm8750-mdss", .data = &sm8750_data},
-	{ .compatible = "qcom,x1e80100-mdss", .data = &x1e80100_data},
+	{ .compatible = "qcom,mdss", .data = &data_153k6 },
+	{ .compatible = "qcom,msm8998-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,qcm2290-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sa8775p-mdss", .data = &data_74k },
+	{ .compatible = "qcom,sar2130p-mdss", .data = &data_74k },
+	{ .compatible = "qcom,sdm670-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sdm845-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sc7180-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sc7280-mdss", .data = &data_74k },
+	{ .compatible = "qcom,sc8180x-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sc8280xp-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm6115-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm6125-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm6150-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm6350-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm6375-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm7150-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm8150-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm8250-mdss", .data = &data_76k8 },
+	{ .compatible = "qcom,sm8350-mdss", .data = &data_74k },
+	{ .compatible = "qcom,sm8450-mdss", .data = &data_74k },
+	{ .compatible = "qcom,sm8550-mdss", .data = &data_57k },
+	{ .compatible = "qcom,sm8650-mdss", .data = &data_57k },
+	{ .compatible = "qcom,sm8750-mdss", .data = &data_57k },
+	/* TODO: x1e8: Add reg_bus_bw with real value */
+	{ .compatible = "qcom,x1e80100-mdss", .data = &data_153k6 },
 	{}
 };
 MODULE_DEVICE_TABLE(of, mdss_dt_match);
diff --git a/drivers/gpu/drm/msm/msm_mdss.h b/drivers/gpu/drm/msm/msm_mdss.h
deleted file mode 100644
index dd0160c6ba1a..000000000000
--- a/drivers/gpu/drm/msm/msm_mdss.h
+++ /dev/null
@@ -1,29 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-only */
-/*
- * Copyright (c) 2018, The Linux Foundation
- */
-
-#ifndef __MSM_MDSS_H__
-#define __MSM_MDSS_H__
-
-struct msm_mdss_data {
-	u32 ubwc_enc_version;
-	/* can be read from register 0x58 */
-	u32 ubwc_dec_version;
-	u32 ubwc_swizzle;
-	u32 highest_bank_bit;
-	bool ubwc_bank_spread;
-	bool macrotile_mode;
-	u32 reg_bus_bw;
-};
-
-#define UBWC_1_0 0x10000000
-#define UBWC_2_0 0x20000000
-#define UBWC_3_0 0x30000000
-#define UBWC_4_0 0x40000000
-#define UBWC_4_3 0x40030000
-#define UBWC_5_0 0x50000000
-
-const struct msm_mdss_data *msm_mdss_get_mdss_data(struct device *dev);
-
-#endif /* __MSM_MDSS_H__ */
diff --git a/include/linux/soc/qcom/ubwc.h b/include/linux/soc/qcom/ubwc.h
index b92fc402638b..d65df559603d 100644
--- a/include/linux/soc/qcom/ubwc.h
+++ b/include/linux/soc/qcom/ubwc.h
@@ -53,7 +53,7 @@ struct qcom_ubwc_cfg_data {
 #define UBWC_4_3 0x40030000
 #define UBWC_5_0 0x50000000
 
-#ifdef CONFIG_QCOM_UBWC_CONFIG
+#if IS_ENABLED(CONFIG_QCOM_UBWC_CONFIG)
 const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void);
 #else
 static inline const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void)
-- 
cgit v1.2.3


From 87cfc79dcd605056247c62d65ea41ce6c65cdbe3 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Thu, 26 Jun 2025 11:02:34 +0200
Subject: drm/msm/a6xx: Resolve the meaning of UBWC_MODE

This bit is set iff the UBWC version is 1.0. That notably does not
include QCM2290's "no UBWC".

This commit is intentionally cross-subsystem to ease review, as the
patchset is intended to be merged together, with a maintainer
consensus.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/660971/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c |  2 +-
 include/linux/soc/qcom/ubwc.h         | 10 ++++++++++
 2 files changed, 11 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index 1d541416a4cb..f998dc240d49 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -687,11 +687,11 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 	 */
 	BUG_ON(adreno_gpu->ubwc_config.highest_bank_bit < 13);
 	u32 hbb = adreno_gpu->ubwc_config.highest_bank_bit - 13;
+	bool ubwc_mode = qcom_ubwc_get_ubwc_mode(cfg);
 	bool amsbc = cfg->ubwc_enc_version >= UBWC_3_0;
 	u8 uavflagprd_inv = 0;
 	u32 hbb_hi = hbb >> 2;
 	u32 hbb_lo = hbb & 3;
-	u32 ubwc_mode = adreno_gpu->ubwc_config.ubwc_swizzle & 1;
 	u32 level2_swizzling_dis = !(adreno_gpu->ubwc_config.ubwc_swizzle & 2);
 
 	if (adreno_is_a650_family(adreno_gpu) || adreno_is_a7xx(adreno_gpu))
diff --git a/include/linux/soc/qcom/ubwc.h b/include/linux/soc/qcom/ubwc.h
index d65df559603d..f0334f4ece20 100644
--- a/include/linux/soc/qcom/ubwc.h
+++ b/include/linux/soc/qcom/ubwc.h
@@ -62,4 +62,14 @@ static inline const struct qcom_ubwc_cfg_data *qcom_ubwc_config_get_data(void)
 }
 #endif
 
+static inline bool qcom_ubwc_get_ubwc_mode(const struct qcom_ubwc_cfg_data *cfg)
+{
+	bool ret = cfg->ubwc_enc_version == UBWC_1_0;
+
+	if (ret && !(cfg->ubwc_swizzle & BIT(0)))
+		pr_err("UBWC config discrepancy - level 1 swizzling disabled on UBWC 1.0\n");
+
+	return ret;
+}
+
 #endif /* __QCOM_UBWC_H__ */
-- 
cgit v1.2.3


From 709dd2ff2357734f5a0b2ef68e1f7c4256543a70 Mon Sep 17 00:00:00 2001
From: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Date: Thu, 26 Jun 2025 11:02:39 +0200
Subject: soc: qcom: ubwc: Add #defines for UBWC swizzle bits

Make the values a bit more meaningful.

This commit is intentionally cross-subsystem to ease review, as the
patchset is intended to be merged together, with a maintainer
consensus.

Reviewed-by: Dmitry Baryshkov <dmitry.baryshkov@oss.qualcomm.com>
Signed-off-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Patchwork: https://patchwork.freedesktop.org/patch/660981/
Signed-off-by: Rob Clark <robin.clark@oss.qualcomm.com>
---
 drivers/gpu/drm/msm/adreno/a6xx_gpu.c |  2 +-
 drivers/soc/qcom/ubwc_config.c        | 37 +++++++++++++++++++++++------------
 include/linux/soc/qcom/ubwc.h         |  8 ++++----
 3 files changed, 30 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
index b34b1cbed350..d83133f39522 100644
--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
@@ -680,7 +680,7 @@ static void a6xx_set_ubwc_config(struct msm_gpu *gpu)
 	BUG_ON(adreno_gpu->ubwc_config.highest_bank_bit < 13);
 	u32 hbb = adreno_gpu->ubwc_config.highest_bank_bit - 13;
 	bool rgb565_predicator = cfg->ubwc_enc_version >= UBWC_4_0;
-	u32 level2_swizzling_dis = !(cfg->ubwc_swizzle & BIT(1));
+	u32 level2_swizzling_dis = !(cfg->ubwc_swizzle & UBWC_SWIZZLE_ENABLE_LVL2);
 	bool ubwc_mode = qcom_ubwc_get_ubwc_mode(cfg);
 	bool amsbc = cfg->ubwc_enc_version >= UBWC_3_0;
 	bool min_acc_len_64b = false;
diff --git a/drivers/soc/qcom/ubwc_config.c b/drivers/soc/qcom/ubwc_config.c
index 3eb2f2118e5d..816bad6674ab 100644
--- a/drivers/soc/qcom/ubwc_config.c
+++ b/drivers/soc/qcom/ubwc_config.c
@@ -32,7 +32,7 @@ static const struct qcom_ubwc_cfg_data qcm2290_data = {
 static const struct qcom_ubwc_cfg_data sa8775p_data = {
 	.ubwc_enc_version = UBWC_4_0,
 	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 4,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	.highest_bank_bit = 13,
 	.macrotile_mode = true,
@@ -41,7 +41,8 @@ static const struct qcom_ubwc_cfg_data sa8775p_data = {
 static const struct qcom_ubwc_cfg_data sar2130p_data = {
 	.ubwc_enc_version = UBWC_3_0, /* 4.0.2 in hw */
 	.ubwc_dec_version = UBWC_4_3,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	.highest_bank_bit = 13,
 	.macrotile_mode = true,
@@ -50,7 +51,8 @@ static const struct qcom_ubwc_cfg_data sar2130p_data = {
 static const struct qcom_ubwc_cfg_data sc7180_data = {
 	.ubwc_enc_version = UBWC_2_0,
 	.ubwc_dec_version = UBWC_2_0,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	.highest_bank_bit = 14,
 };
@@ -58,7 +60,8 @@ static const struct qcom_ubwc_cfg_data sc7180_data = {
 static const struct qcom_ubwc_cfg_data sc7280_data = {
 	.ubwc_enc_version = UBWC_3_0,
 	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	.highest_bank_bit = 14,
 	.macrotile_mode = true,
@@ -74,7 +77,8 @@ static const struct qcom_ubwc_cfg_data sc8180x_data = {
 static const struct qcom_ubwc_cfg_data sc8280xp_data = {
 	.ubwc_enc_version = UBWC_4_0,
 	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	.highest_bank_bit = 16,
 	.macrotile_mode = true,
@@ -95,7 +99,9 @@ static const struct qcom_ubwc_cfg_data sdm845_data = {
 static const struct qcom_ubwc_cfg_data sm6115_data = {
 	.ubwc_enc_version = UBWC_1_0,
 	.ubwc_dec_version = UBWC_2_0,
-	.ubwc_swizzle = 7,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL1 |
+			UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	.highest_bank_bit = 14,
 };
@@ -103,7 +109,9 @@ static const struct qcom_ubwc_cfg_data sm6115_data = {
 static const struct qcom_ubwc_cfg_data sm6125_data = {
 	.ubwc_enc_version = UBWC_1_0,
 	.ubwc_dec_version = UBWC_3_0,
-	.ubwc_swizzle = 7,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL1 |
+			UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.highest_bank_bit = 14,
 };
 
@@ -116,7 +124,8 @@ static const struct qcom_ubwc_cfg_data sm6150_data = {
 static const struct qcom_ubwc_cfg_data sm6350_data = {
 	.ubwc_enc_version = UBWC_2_0,
 	.ubwc_dec_version = UBWC_2_0,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	.highest_bank_bit = 14,
 };
@@ -136,7 +145,8 @@ static const struct qcom_ubwc_cfg_data sm8150_data = {
 static const struct qcom_ubwc_cfg_data sm8250_data = {
 	.ubwc_enc_version = UBWC_4_0,
 	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
 	.highest_bank_bit = 16,
@@ -146,7 +156,8 @@ static const struct qcom_ubwc_cfg_data sm8250_data = {
 static const struct qcom_ubwc_cfg_data sm8350_data = {
 	.ubwc_enc_version = UBWC_4_0,
 	.ubwc_dec_version = UBWC_4_0,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
 	.highest_bank_bit = 16,
@@ -156,7 +167,8 @@ static const struct qcom_ubwc_cfg_data sm8350_data = {
 static const struct qcom_ubwc_cfg_data sm8550_data = {
 	.ubwc_enc_version = UBWC_4_0,
 	.ubwc_dec_version = UBWC_4_3,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
 	.highest_bank_bit = 16,
@@ -176,7 +188,8 @@ static const struct qcom_ubwc_cfg_data sm8750_data = {
 static const struct qcom_ubwc_cfg_data x1e80100_data = {
 	.ubwc_enc_version = UBWC_4_0,
 	.ubwc_dec_version = UBWC_4_3,
-	.ubwc_swizzle = 6,
+	.ubwc_swizzle = UBWC_SWIZZLE_ENABLE_LVL2 |
+			UBWC_SWIZZLE_ENABLE_LVL3,
 	.ubwc_bank_spread = true,
 	/* TODO: highest_bank_bit = 15 for LP_DDR4 */
 	.highest_bank_bit = 16,
diff --git a/include/linux/soc/qcom/ubwc.h b/include/linux/soc/qcom/ubwc.h
index f0334f4ece20..1ed8b1b16bc9 100644
--- a/include/linux/soc/qcom/ubwc.h
+++ b/include/linux/soc/qcom/ubwc.h
@@ -21,11 +21,11 @@ struct qcom_ubwc_cfg_data {
 	 * UBWC 1.0 always enables all three levels.
 	 * UBWC 2.0 removes level 1 bank swizzling, leaving levels 2 & 3.
 	 * UBWC 4.0 adds the optional ability to disable levels 2 & 3.
-	 *
-	 * This is a bitmask where BIT(0) enables level 1, BIT(1)
-	 * controls level 2, and BIT(2) enables level 3.
 	 */
 	u32 ubwc_swizzle;
+#define UBWC_SWIZZLE_ENABLE_LVL1	BIT(0)
+#define UBWC_SWIZZLE_ENABLE_LVL2	BIT(1)
+#define UBWC_SWIZZLE_ENABLE_LVL3	BIT(2)
 
 	/**
 	 * @highest_bank_bit: Highest Bank Bit
@@ -66,7 +66,7 @@ static inline bool qcom_ubwc_get_ubwc_mode(const struct qcom_ubwc_cfg_data *cfg)
 {
 	bool ret = cfg->ubwc_enc_version == UBWC_1_0;
 
-	if (ret && !(cfg->ubwc_swizzle & BIT(0)))
+	if (ret && !(cfg->ubwc_swizzle & UBWC_SWIZZLE_ENABLE_LVL1))
 		pr_err("UBWC config discrepancy - level 1 swizzling disabled on UBWC 1.0\n");
 
 	return ret;
-- 
cgit v1.2.3


From 9c06f26ba5f5da14bcac405c7a652dcf578a785d Mon Sep 17 00:00:00 2001
From: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Date: Wed, 30 Apr 2025 13:56:01 +0200
Subject: pwm: Add support for pwmchip devices for faster and easier userspace
 access
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With this change each pwmchip defining the new-style waveform callbacks
can be accessed from userspace via a character device. Compared to the
sysfs-API this is faster and allows to pass the whole configuration in a
single ioctl allowing atomic application and thus reducing glitches.

On an STM32MP13 I see:

	root@DistroKit:~ time pwmtestperf
	real	0m 1.27s
	user	0m 0.02s
	sys	0m 1.21s
	root@DistroKit:~ rm /dev/pwmchip0
	root@DistroKit:~ time pwmtestperf
	real	0m 3.61s
	user	0m 0.27s
	sys	0m 3.26s

pwmtestperf does essentially:

	for i in 0 .. 50000:
		pwm_set_waveform(duty_length_ns=i, period_length_ns=50000, duty_offset_ns=0)

and in the presence of /dev/pwmchip0 is uses the ioctls introduced here,
without that device it uses /sys/class/pwm/pwmchip0.

Signed-off-by: Uwe Kleine-König <u.kleine-koenig@baylibre.com>
Link: https://lore.kernel.org/r/ad4a4e49ae3f8ea81e23cac1ac12b338c3bf5c5b.1746010245.git.u.kleine-koenig@baylibre.com
Signed-off-by: Uwe Kleine-König <ukleinek@kernel.org>
---
 drivers/pwm/core.c       | 322 ++++++++++++++++++++++++++++++++++++++++++++---
 include/linux/pwm.h      |   3 +
 include/uapi/linux/pwm.h |  53 ++++++++
 3 files changed, 363 insertions(+), 15 deletions(-)
 create mode 100644 include/uapi/linux/pwm.h

(limited to 'include/linux')

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index edf776b8ad53..50aa0528a265 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -23,9 +23,13 @@
 
 #include <dt-bindings/pwm/pwm.h>
 
+#include <uapi/linux/pwm.h>
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/pwm.h>
 
+#define PWM_MINOR_COUNT 256
+
 /* protects access to pwm_chips */
 static DEFINE_MUTEX(pwm_lock);
 
@@ -2007,20 +2011,9 @@ struct pwm_device *pwm_get(struct device *dev, const char *con_id)
 }
 EXPORT_SYMBOL_GPL(pwm_get);
 
-/**
- * pwm_put() - release a PWM device
- * @pwm: PWM device
- */
-void pwm_put(struct pwm_device *pwm)
+static void __pwm_put(struct pwm_device *pwm)
 {
-	struct pwm_chip *chip;
-
-	if (!pwm)
-		return;
-
-	chip = pwm->chip;
-
-	guard(mutex)(&pwm_lock);
+	struct pwm_chip *chip = pwm->chip;
 
 	/*
 	 * Trigger a warning if a consumer called pwm_put() twice.
@@ -2041,6 +2034,20 @@ void pwm_put(struct pwm_device *pwm)
 
 	module_put(chip->owner);
 }
+
+/**
+ * pwm_put() - release a PWM device
+ * @pwm: PWM device
+ */
+void pwm_put(struct pwm_device *pwm)
+{
+	if (!pwm)
+		return;
+
+	guard(mutex)(&pwm_lock);
+
+	__pwm_put(pwm);
+}
 EXPORT_SYMBOL_GPL(pwm_put);
 
 static void devm_pwm_release(void *pwm)
@@ -2110,6 +2117,274 @@ struct pwm_device *devm_fwnode_pwm_get(struct device *dev,
 }
 EXPORT_SYMBOL_GPL(devm_fwnode_pwm_get);
 
+struct pwm_cdev_data {
+	struct pwm_chip *chip;
+	struct pwm_device *pwm[];
+};
+
+static int pwm_cdev_open(struct inode *inode, struct file *file)
+{
+	struct pwm_chip *chip = container_of(inode->i_cdev, struct pwm_chip, cdev);
+	struct pwm_cdev_data *cdata;
+
+	guard(mutex)(&pwm_lock);
+
+	if (!chip->operational)
+		return -ENXIO;
+
+	cdata = kzalloc(struct_size(cdata, pwm, chip->npwm), GFP_KERNEL);
+	if (!cdata)
+		return -ENOMEM;
+
+	cdata->chip = chip;
+
+	file->private_data = cdata;
+
+	return nonseekable_open(inode, file);
+}
+
+static int pwm_cdev_release(struct inode *inode, struct file *file)
+{
+	struct pwm_cdev_data *cdata = file->private_data;
+	unsigned int i;
+
+	for (i = 0; i < cdata->chip->npwm; ++i) {
+		struct pwm_device *pwm = cdata->pwm[i];
+
+		if (pwm) {
+			const char *label = pwm->label;
+
+			pwm_put(cdata->pwm[i]);
+			kfree(label);
+		}
+	}
+	kfree(cdata);
+
+	return 0;
+}
+
+static int pwm_cdev_request(struct pwm_cdev_data *cdata, unsigned int hwpwm)
+{
+	struct pwm_chip *chip = cdata->chip;
+
+	if (hwpwm >= chip->npwm)
+		return -EINVAL;
+
+	if (!cdata->pwm[hwpwm]) {
+		struct pwm_device *pwm = &chip->pwms[hwpwm];
+		const char *label;
+		int ret;
+
+		label = kasprintf(GFP_KERNEL, "pwm-cdev (pid=%d)", current->pid);
+		if (!label)
+			return -ENOMEM;
+
+		ret = pwm_device_request(pwm, label);
+		if (ret < 0) {
+			kfree(label);
+			return ret;
+		}
+
+		cdata->pwm[hwpwm] = pwm;
+	}
+
+	return 0;
+}
+
+static int pwm_cdev_free(struct pwm_cdev_data *cdata, unsigned int hwpwm)
+{
+	struct pwm_chip *chip = cdata->chip;
+
+	if (hwpwm >= chip->npwm)
+		return -EINVAL;
+
+	if (cdata->pwm[hwpwm]) {
+		struct pwm_device *pwm = cdata->pwm[hwpwm];
+		const char *label = pwm->label;
+
+		__pwm_put(pwm);
+
+		kfree(label);
+
+		cdata->pwm[hwpwm] = NULL;
+	}
+
+	return 0;
+}
+
+static struct pwm_device *pwm_cdev_get_requested_pwm(struct pwm_cdev_data *cdata,
+						     u32 hwpwm)
+{
+	struct pwm_chip *chip = cdata->chip;
+
+	if (hwpwm >= chip->npwm)
+		return ERR_PTR(-EINVAL);
+
+	if (cdata->pwm[hwpwm])
+		return cdata->pwm[hwpwm];
+
+	return ERR_PTR(-EINVAL);
+}
+
+static long pwm_cdev_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
+{
+	int ret = 0;
+	struct pwm_cdev_data *cdata = file->private_data;
+	struct pwm_chip *chip = cdata->chip;
+
+	guard(mutex)(&pwm_lock);
+
+	if (!chip->operational)
+		return -ENODEV;
+
+	switch (cmd) {
+	case PWM_IOCTL_REQUEST:
+		{
+			unsigned int hwpwm = arg;
+
+			return pwm_cdev_request(cdata, hwpwm);
+		}
+
+	case PWM_IOCTL_FREE:
+		{
+			unsigned int hwpwm = arg;
+
+			return pwm_cdev_free(cdata, hwpwm);
+		}
+
+	case PWM_IOCTL_ROUNDWF:
+		{
+			struct pwmchip_waveform cwf;
+			struct pwm_waveform wf;
+			struct pwm_device *pwm;
+
+			ret = copy_from_user(&cwf,
+					     (struct pwmchip_waveform __user *)arg,
+					     sizeof(cwf));
+			if (ret)
+				return -EFAULT;
+
+			if (cwf.__pad != 0)
+				return -EINVAL;
+
+			pwm = pwm_cdev_get_requested_pwm(cdata, cwf.hwpwm);
+			if (IS_ERR(pwm))
+				return PTR_ERR(pwm);
+
+			wf = (struct pwm_waveform) {
+				.period_length_ns = cwf.period_length_ns,
+				.duty_length_ns = cwf.duty_length_ns,
+				.duty_offset_ns = cwf.duty_offset_ns,
+			};
+
+			ret = pwm_round_waveform_might_sleep(pwm, &wf);
+			if (ret < 0)
+				return ret;
+
+			cwf = (struct pwmchip_waveform) {
+				.hwpwm = cwf.hwpwm,
+				.period_length_ns = wf.period_length_ns,
+				.duty_length_ns = wf.duty_length_ns,
+				.duty_offset_ns = wf.duty_offset_ns,
+			};
+
+			return copy_to_user((struct pwmchip_waveform __user *)arg,
+					    &cwf, sizeof(cwf));
+		}
+
+	case PWM_IOCTL_GETWF:
+		{
+			struct pwmchip_waveform cwf;
+			struct pwm_waveform wf;
+			struct pwm_device *pwm;
+
+			ret = copy_from_user(&cwf,
+					     (struct pwmchip_waveform __user *)arg,
+					     sizeof(cwf));
+			if (ret)
+				return -EFAULT;
+
+			if (cwf.__pad != 0)
+				return -EINVAL;
+
+			pwm = pwm_cdev_get_requested_pwm(cdata, cwf.hwpwm);
+			if (IS_ERR(pwm))
+				return PTR_ERR(pwm);
+
+			ret = pwm_get_waveform_might_sleep(pwm, &wf);
+			if (ret)
+				return ret;
+
+			cwf = (struct pwmchip_waveform) {
+				.hwpwm = cwf.hwpwm,
+				.period_length_ns = wf.period_length_ns,
+				.duty_length_ns = wf.duty_length_ns,
+				.duty_offset_ns = wf.duty_offset_ns,
+			};
+
+			return copy_to_user((struct pwmchip_waveform __user *)arg,
+					    &cwf, sizeof(cwf));
+		}
+
+	case PWM_IOCTL_SETROUNDEDWF:
+	case PWM_IOCTL_SETEXACTWF:
+		{
+			struct pwmchip_waveform cwf;
+			struct pwm_waveform wf;
+			struct pwm_device *pwm;
+
+			ret = copy_from_user(&cwf,
+					     (struct pwmchip_waveform __user *)arg,
+					     sizeof(cwf));
+			if (ret)
+				return -EFAULT;
+
+			if (cwf.__pad != 0)
+				return -EINVAL;
+
+			wf = (struct pwm_waveform){
+				.period_length_ns = cwf.period_length_ns,
+				.duty_length_ns = cwf.duty_length_ns,
+				.duty_offset_ns = cwf.duty_offset_ns,
+			};
+
+			if (!pwm_wf_valid(&wf))
+				return -EINVAL;
+
+			pwm = pwm_cdev_get_requested_pwm(cdata, cwf.hwpwm);
+			if (IS_ERR(pwm))
+				return PTR_ERR(pwm);
+
+			ret = pwm_set_waveform_might_sleep(pwm, &wf,
+							   cmd == PWM_IOCTL_SETEXACTWF);
+
+			/*
+			 * If userspace cares about rounding deviations it has
+			 * to check the values anyhow, so simplify handling for
+			 * them and don't signal uprounding. This matches the
+			 * behaviour of PWM_IOCTL_ROUNDWF which also returns 0
+			 * in that case.
+			 */
+			if (ret == 1)
+				ret = 0;
+
+			return ret;
+		}
+
+	default:
+		return -ENOTTY;
+	}
+}
+
+static const struct file_operations pwm_cdev_fileops = {
+	.open = pwm_cdev_open,
+	.release = pwm_cdev_release,
+	.owner = THIS_MODULE,
+	.unlocked_ioctl = pwm_cdev_ioctl,
+};
+
+static dev_t pwm_devt;
+
 /**
  * __pwmchip_add() - register a new PWM chip
  * @chip: the PWM chip to add
@@ -2162,7 +2437,17 @@ int __pwmchip_add(struct pwm_chip *chip, struct module *owner)
 	scoped_guard(pwmchip, chip)
 		chip->operational = true;
 
-	ret = device_add(&chip->dev);
+	if (chip->ops->write_waveform) {
+		if (chip->id < PWM_MINOR_COUNT)
+			chip->dev.devt = MKDEV(MAJOR(pwm_devt), chip->id);
+		else
+			dev_warn(&chip->dev, "chip id too high to create a chardev\n");
+	}
+
+	cdev_init(&chip->cdev, &pwm_cdev_fileops);
+	chip->cdev.owner = owner;
+
+	ret = cdev_device_add(&chip->cdev, &chip->dev);
 	if (ret)
 		goto err_device_add;
 
@@ -2213,7 +2498,7 @@ void pwmchip_remove(struct pwm_chip *chip)
 		idr_remove(&pwm_chips, chip->id);
 	}
 
-	device_del(&chip->dev);
+	cdev_device_del(&chip->cdev, &chip->dev);
 }
 EXPORT_SYMBOL_GPL(pwmchip_remove);
 
@@ -2357,9 +2642,16 @@ static int __init pwm_init(void)
 {
 	int ret;
 
+	ret = alloc_chrdev_region(&pwm_devt, 0, PWM_MINOR_COUNT, "pwm");
+	if (ret) {
+		pr_err("Failed to initialize chrdev region for PWM usage\n");
+		return ret;
+	}
+
 	ret = class_register(&pwm_class);
 	if (ret) {
 		pr_err("Failed to initialize PWM class (%pe)\n", ERR_PTR(ret));
+		unregister_chrdev_region(pwm_devt, 256);
 		return ret;
 	}
 
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 63a17d2b4ec8..2492c91452f9 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -2,6 +2,7 @@
 #ifndef __LINUX_PWM_H
 #define __LINUX_PWM_H
 
+#include <linux/cdev.h>
 #include <linux/device.h>
 #include <linux/err.h>
 #include <linux/module.h>
@@ -311,6 +312,7 @@ struct pwm_ops {
 /**
  * struct pwm_chip - abstract a PWM controller
  * @dev: device providing the PWMs
+ * @cdev: &struct cdev for this device
  * @ops: callbacks for this PWM controller
  * @owner: module providing this chip
  * @id: unique number of this PWM chip
@@ -325,6 +327,7 @@ struct pwm_ops {
  */
 struct pwm_chip {
 	struct device dev;
+	struct cdev cdev;
 	const struct pwm_ops *ops;
 	struct module *owner;
 	unsigned int id;
diff --git a/include/uapi/linux/pwm.h b/include/uapi/linux/pwm.h
new file mode 100644
index 000000000000..182d59cc07ee
--- /dev/null
+++ b/include/uapi/linux/pwm.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0-only WITH Linux-syscall-note */
+
+#ifndef _UAPI_PWM_H_
+#define _UAPI_PWM_H_
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/**
+ * struct pwmchip_waveform - Describe a PWM waveform for a pwm_chip's PWM channel
+ * @hwpwm: per-chip relative index of the PWM device
+ * @__pad: padding, must be zero
+ * @period_length_ns: duration of the repeating period.
+ *    A value of 0 represents a disabled PWM.
+ * @duty_length_ns: duration of the active part in each period
+ * @duty_offset_ns: offset of the rising edge from a period's start
+ */
+struct pwmchip_waveform {
+	__u32 hwpwm;
+	__u32 __pad;
+	__u64 period_length_ns;
+	__u64 duty_length_ns;
+	__u64 duty_offset_ns;
+};
+
+/* Reserves the passed hwpwm for exclusive control. */
+#define PWM_IOCTL_REQUEST	_IO(0x75, 1)
+
+/* counter part to PWM_IOCTL_REQUEST */
+#define PWM_IOCTL_FREE		_IO(0x75, 2)
+
+/*
+ * Modifies the passed wf according to hardware constraints. All parameters are
+ * rounded down to the next possible value, unless there is no such value, then
+ * values are rounded up. Note that zero isn't considered for rounding down
+ * period_length_ns.
+ */
+#define PWM_IOCTL_ROUNDWF	_IOWR(0x75, 3, struct pwmchip_waveform)
+
+/* Get the currently implemented waveform */
+#define PWM_IOCTL_GETWF		_IOWR(0x75, 4, struct pwmchip_waveform)
+
+/* Like PWM_IOCTL_ROUNDWF + PWM_IOCTL_SETEXACTWF in one go. */
+#define PWM_IOCTL_SETROUNDEDWF	_IOW(0x75, 5, struct pwmchip_waveform)
+
+/*
+ * Program the PWM to emit exactly the passed waveform, subject only to rounding
+ * down each value less than 1 ns. Returns 0 on success, -EDOM if the waveform
+ * cannot be implemented exactly, or other negative error codes.
+ */
+#define PWM_IOCTL_SETEXACTWF	_IOW(0x75, 6, struct pwmchip_waveform)
+
+#endif /* _UAPI_PWM_H_ */
-- 
cgit v1.2.3


From edd3bcb1801e1bb98f4f81485140e18c86406ced Mon Sep 17 00:00:00 2001
From: Michal Wilczynski <m.wilczynski@samsung.com>
Date: Wed, 2 Jul 2025 15:45:29 +0200
Subject: pwm: Expose PWM_WFHWSIZE in public header
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The WFHWSIZE constant defines the maximum size for the hardware-specific
waveform representation buffer. It is currently local to
drivers/pwm/core.c, which makes it inaccessible to external tools like
bindgen.

Move the constant to include/linux/pwm.h to make it part of the public
API. As part of this change, rename it to PWM_WFHWSIZE to follow
standard kernel conventions for namespacing macros in public headers.

This allows bindgen to automatically generate a corresponding constant
for the Rust PWM abstractions, ensuring the value remains synchronized
between the C core and Rust code and preventing future maintenance
issues.

Signed-off-by: Michal Wilczynski <m.wilczynski@samsung.com>
Link: https://lore.kernel.org/r/20250702-rust-next-pwm-working-fan-for-sending-v7-1-67ef39ff1d29@samsung.com
Signed-off-by: Uwe Kleine-König <ukleinek@kernel.org>
---
 drivers/pwm/core.c  | 26 ++++++++++++--------------
 include/linux/pwm.h |  2 ++
 2 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pwm/core.c b/drivers/pwm/core.c
index 50aa0528a265..0d66376a83ec 100644
--- a/drivers/pwm/core.c
+++ b/drivers/pwm/core.c
@@ -210,8 +210,6 @@ static int __pwm_write_waveform(struct pwm_chip *chip, struct pwm_device *pwm, c
 	return ret;
 }
 
-#define WFHWSIZE 20
-
 /**
  * pwm_round_waveform_might_sleep - Query hardware capabilities
  * Cannot be used in atomic context.
@@ -248,10 +246,10 @@ int pwm_round_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform *
 	struct pwm_chip *chip = pwm->chip;
 	const struct pwm_ops *ops = chip->ops;
 	struct pwm_waveform wf_req = *wf;
-	char wfhw[WFHWSIZE];
+	char wfhw[PWM_WFHWSIZE];
 	int ret_tohw, ret_fromhw;
 
-	BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
+	BUG_ON(PWM_WFHWSIZE < ops->sizeof_wfhw);
 
 	if (!pwmchip_supports_waveform(chip))
 		return -EOPNOTSUPP;
@@ -306,10 +304,10 @@ int pwm_get_waveform_might_sleep(struct pwm_device *pwm, struct pwm_waveform *wf
 {
 	struct pwm_chip *chip = pwm->chip;
 	const struct pwm_ops *ops = chip->ops;
-	char wfhw[WFHWSIZE];
+	char wfhw[PWM_WFHWSIZE];
 	int err;
 
-	BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
+	BUG_ON(PWM_WFHWSIZE < ops->sizeof_wfhw);
 
 	if (!pwmchip_supports_waveform(chip) || !ops->read_waveform)
 		return -EOPNOTSUPP;
@@ -334,11 +332,11 @@ static int __pwm_set_waveform(struct pwm_device *pwm,
 {
 	struct pwm_chip *chip = pwm->chip;
 	const struct pwm_ops *ops = chip->ops;
-	char wfhw[WFHWSIZE];
+	char wfhw[PWM_WFHWSIZE];
 	struct pwm_waveform wf_rounded;
 	int err, ret_tohw;
 
-	BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
+	BUG_ON(PWM_WFHWSIZE < ops->sizeof_wfhw);
 
 	if (!pwmchip_supports_waveform(chip))
 		return -EOPNOTSUPP;
@@ -650,9 +648,9 @@ static int __pwm_apply(struct pwm_device *pwm, const struct pwm_state *state)
 
 	if (pwmchip_supports_waveform(chip)) {
 		struct pwm_waveform wf;
-		char wfhw[WFHWSIZE];
+		char wfhw[PWM_WFHWSIZE];
 
-		BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
+		BUG_ON(PWM_WFHWSIZE < ops->sizeof_wfhw);
 
 		pwm_state2wf(state, &wf);
 
@@ -809,10 +807,10 @@ int pwm_get_state_hw(struct pwm_device *pwm, struct pwm_state *state)
 		return -ENODEV;
 
 	if (pwmchip_supports_waveform(chip) && ops->read_waveform) {
-		char wfhw[WFHWSIZE];
+		char wfhw[PWM_WFHWSIZE];
 		struct pwm_waveform wf;
 
-		BUG_ON(WFHWSIZE < ops->sizeof_wfhw);
+		BUG_ON(PWM_WFHWSIZE < ops->sizeof_wfhw);
 
 		ret = __pwm_read_waveform(chip, pwm, &wfhw);
 		if (ret)
@@ -1696,8 +1694,8 @@ static bool pwm_ops_check(const struct pwm_chip *chip)
 		    !ops->write_waveform)
 			return false;
 
-		if (WFHWSIZE < ops->sizeof_wfhw) {
-			dev_warn(pwmchip_parent(chip), "WFHWSIZE < %zu\n", ops->sizeof_wfhw);
+		if (PWM_WFHWSIZE < ops->sizeof_wfhw) {
+			dev_warn(pwmchip_parent(chip), "PWM_WFHWSIZE < %zu\n", ops->sizeof_wfhw);
 			return false;
 		}
 	} else {
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 2492c91452f9..8cafc483db53 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -274,6 +274,8 @@ struct pwm_capture {
 	unsigned int duty_cycle;
 };
 
+#define PWM_WFHWSIZE 20
+
 /**
  * struct pwm_ops - PWM controller operations
  * @request: optional hook for requesting a PWM
-- 
cgit v1.2.3


From 9bad4bec5daddbb296481af759f9d56c849ba96f Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Tue, 1 Jul 2025 13:49:40 +0200
Subject: gpio: mmio: remove struct bgpio_pdata

With no more users, we can now remove struct bgpio_pdata. Move the
relevant bits from bgpio_parse_fw() into bgpio_pdev_probe() while
maintaining the logical ordering (get flags before calling
bgpio_init()).

Link: https://lore.kernel.org/r/20250701-gpio-mmio-pdata-v2-6-ebf34d273497@linaro.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpio-mmio.c    | 73 ++++++++++++---------------------------------
 include/linux/gpio/driver.h |  6 ----
 2 files changed, 19 insertions(+), 60 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c
index 7d062f9a2c6a..a8103e26298c 100644
--- a/drivers/gpio/gpio-mmio.c
+++ b/drivers/gpio/gpio-mmio.c
@@ -712,43 +712,6 @@ static const struct of_device_id bgpio_of_match[] = {
 };
 MODULE_DEVICE_TABLE(of, bgpio_of_match);
 
-static struct bgpio_pdata *bgpio_parse_fw(struct device *dev, unsigned long *flags)
-{
-	struct bgpio_pdata *pdata;
-	const char *label;
-	unsigned int base;
-	int ret;
-
-	if (!dev_fwnode(dev))
-		return NULL;
-
-	pdata = devm_kzalloc(dev, sizeof(*pdata), GFP_KERNEL);
-	if (!pdata)
-		return ERR_PTR(-ENOMEM);
-
-	pdata->base = -1;
-
-	if (device_is_big_endian(dev))
-		*flags |= BGPIOF_BIG_ENDIAN_BYTE_ORDER;
-
-	if (device_property_read_bool(dev, "no-output"))
-		*flags |= BGPIOF_NO_OUTPUT;
-
-	ret = device_property_read_string(dev, "label", &label);
-	if (!ret)
-		pdata->label = label;
-
-	/*
-	 * This property *must not* be used in device-tree sources, it's only
-	 * meant to be passed to the driver from board files and MFD core.
-	 */
-	ret = device_property_read_u32(dev, "gpio-mmio,base", &base);
-	if (!ret && base <= INT_MAX)
-		pdata->base = base;
-
-	return pdata;
-}
-
 static int bgpio_pdev_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
@@ -760,18 +723,10 @@ static int bgpio_pdev_probe(struct platform_device *pdev)
 	void __iomem *dirin;
 	unsigned long sz;
 	unsigned long flags = 0;
+	unsigned int base;
 	int err;
 	struct gpio_chip *gc;
-	struct bgpio_pdata *pdata;
-
-	pdata = bgpio_parse_fw(dev, &flags);
-	if (IS_ERR(pdata))
-		return PTR_ERR(pdata);
-
-	if (!pdata) {
-		pdata = dev_get_platdata(dev);
-		flags = pdev->id_entry->driver_data;
-	}
+	const char *label;
 
 	r = platform_get_resource_byname(pdev, IORESOURCE_MEM, "dat");
 	if (!r)
@@ -803,17 +758,27 @@ static int bgpio_pdev_probe(struct platform_device *pdev)
 	if (!gc)
 		return -ENOMEM;
 
+	if (device_is_big_endian(dev))
+		flags |= BGPIOF_BIG_ENDIAN_BYTE_ORDER;
+
+	if (device_property_read_bool(dev, "no-output"))
+		flags |= BGPIOF_NO_OUTPUT;
+
 	err = bgpio_init(gc, dev, sz, dat, set, clr, dirout, dirin, flags);
 	if (err)
 		return err;
 
-	if (pdata) {
-		if (pdata->label)
-			gc->label = pdata->label;
-		gc->base = pdata->base;
-		if (pdata->ngpio > 0)
-			gc->ngpio = pdata->ngpio;
-	}
+	err = device_property_read_string(dev, "label", &label);
+	if (!err)
+		gc->label = label;
+
+	/*
+	 * This property *must not* be used in device-tree sources, it's only
+	 * meant to be passed to the driver from board files and MFD core.
+	 */
+	err = device_property_read_u32(dev, "gpio-mmio,base", &base);
+	if (!err && base <= INT_MAX)
+		gc->base = base;
 
 	platform_set_drvdata(pdev, gc);
 
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index b53233051bee..602d4acd36b2 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -718,12 +718,6 @@ const unsigned long *gpiochip_query_valid_mask(const struct gpio_chip *gc);
 /* get driver data */
 void *gpiochip_get_data(struct gpio_chip *gc);
 
-struct bgpio_pdata {
-	const char *label;
-	int base;
-	int ngpio;
-};
-
 #ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
 
 int gpiochip_populate_parent_fwspec_twocell(struct gpio_chip *gc,
-- 
cgit v1.2.3


From 8595375e4fded27de24b189c692c2c50051a7b3b Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Wed, 2 Jul 2025 11:22:08 +0200
Subject: gpio: generic: add new generic GPIO chip API

As the first step in removing the fields specific to the gpio-mmio
module from struct gpio_chip, we introduce a new set of generic GPIO
chip interfaces that are meant to replace the existing bgpio_ ones.

The new initialization function - gpio_generic_chip_init() - takes a
configuration structure as argument instead of 9 separate parameters.
This will allow easy extension if needed in the future. We hide the
locking details behind a set of helpers in order to be able to move the
raw spinlock out of struct gpio_chip without the users noticing.

For now, the new APIs just wrap the existing ones. Once all users have
been converted to the new interfaces, we'll pull them into gpio-mmio and
implement them in a backward-compatible way while also moving all fields
specific to the generic GPIO chip into struct gpio_generic_chip.

Reviewed-by: Linus Walleij <linus.walleij@linaro.org>
Link: https://lore.kernel.org/r/20250702-gpio-mmio-rework-v2-1-6b77aab684d8@linaro.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 include/linux/gpio/generic.h | 120 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 120 insertions(+)
 create mode 100644 include/linux/gpio/generic.h

(limited to 'include/linux')

diff --git a/include/linux/gpio/generic.h b/include/linux/gpio/generic.h
new file mode 100644
index 000000000000..b511acd58ab0
--- /dev/null
+++ b/include/linux/gpio/generic.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+
+#ifndef __LINUX_GPIO_GENERIC_H
+#define __LINUX_GPIO_GENERIC_H
+
+#include <linux/cleanup.h>
+#include <linux/gpio/driver.h>
+#include <linux/spinlock.h>
+
+struct device;
+
+/**
+ * struct gpio_generic_chip_config - Generic GPIO chip configuration data
+ * @dev: Parent device of the new GPIO chip (compulsory).
+ * @sz: Size (width) of the MMIO registers in bytes, typically 1, 2 or 4.
+ * @dat: MMIO address for the register to READ the value of the GPIO lines, it
+ *       is expected that a 1 in the corresponding bit in this register means
+ *       the line is asserted.
+ * @set: MMIO address for the register to SET the value of the GPIO lines, it
+ *       is expected that we write the line with 1 in this register to drive
+ *       the GPIO line high.
+ * @clr: MMIO address for the register to CLEAR the value of the GPIO lines,
+ *       it is expected that we write the line with 1 in this register to
+ *       drive the GPIO line low. It is allowed to leave this address as NULL,
+ *       in that case the SET register will be assumed to also clear the GPIO
+ *       lines, by actively writing the line with 0.
+ * @dirout: MMIO address for the register to set the line as OUTPUT. It is
+ *          assumed that setting a line to 1 in this register will turn that
+ *          line into an output line. Conversely, setting the line to 0 will
+ *          turn that line into an input.
+ * @dirin: MMIO address for the register to set this line as INPUT. It is
+ *         assumed that setting a line to 1 in this register will turn that
+ *         line into an input line. Conversely, setting the line to 0 will
+ *         turn that line into an output.
+ * @flags: Different flags that will affect the behaviour of the device, such
+ *         as endianness etc.
+ */
+struct gpio_generic_chip_config {
+	struct device *dev;
+	unsigned long sz;
+	void __iomem *dat;
+	void __iomem *set;
+	void __iomem *clr;
+	void __iomem *dirout;
+	void __iomem *dirin;
+	unsigned long flags;
+};
+
+/**
+ * struct gpio_generic_chip - Generic GPIO chip implementation.
+ * @gc: The underlying struct gpio_chip object, implementing low-level GPIO
+ *      chip routines.
+ */
+struct gpio_generic_chip {
+	struct gpio_chip gc;
+};
+
+/**
+ * gpio_generic_chip_init() - Initialize a generic GPIO chip.
+ * @chip: Generic GPIO chip to set up.
+ * @cfg: Generic GPIO chip configuration.
+ *
+ * Returns 0 on success, negative error number on failure.
+ */
+static inline int
+gpio_generic_chip_init(struct gpio_generic_chip *chip,
+		       const struct gpio_generic_chip_config *cfg)
+{
+	return bgpio_init(&chip->gc, cfg->dev, cfg->sz, cfg->dat, cfg->set,
+			  cfg->clr, cfg->dirout, cfg->dirin, cfg->flags);
+}
+
+/**
+ * gpio_generic_chip_set() - Set the GPIO line value of the generic GPIO chip.
+ * @chip: Generic GPIO chip to use.
+ * @offset: Hardware offset of the line to set.
+ * @value: New GPIO line value.
+ *
+ * Some modules using the generic GPIO chip, need to set line values in their
+ * direction setters but they don't have access to the gpio-mmio symbols so
+ * they use the function pointer in struct gpio_chip directly. This is not
+ * optimal and can lead to crashes at run-time in some instances. This wrapper
+ * provides a safe interface for users.
+ *
+ * Returns: 0 on success, negative error number of failure.
+ */
+static inline int
+gpio_generic_chip_set(struct gpio_generic_chip *chip, unsigned int offset,
+		      int value)
+{
+	if (WARN_ON(!chip->gc.set_rv))
+		return -EOPNOTSUPP;
+
+	return chip->gc.set_rv(&chip->gc, offset, value);
+}
+
+#define gpio_generic_chip_lock(gen_gc) \
+	raw_spin_lock(&(gen_gc)->gc.bgpio_lock)
+
+#define gpio_generic_chip_unlock(gen_gc) \
+	raw_spin_unlock(&(gen_gc)->gc.bgpio_lock)
+
+#define gpio_generic_chip_lock_irqsave(gen_gc, flags) \
+	raw_spin_lock_irqsave(&(gen_gc)->gc.bgpio_lock, flags)
+
+#define gpio_generic_chip_unlock_irqrestore(gen_gc, flags) \
+	raw_spin_unlock_irqrestore(&(gen_gc)->gc.bgpio_lock, flags)
+
+DEFINE_LOCK_GUARD_1(gpio_generic_lock,
+		    struct gpio_generic_chip,
+		    gpio_generic_chip_lock(_T->lock),
+		    gpio_generic_chip_unlock(_T->lock))
+
+DEFINE_LOCK_GUARD_1(gpio_generic_lock_irqsave,
+		    struct gpio_generic_chip,
+		    gpio_generic_chip_lock_irqsave(_T->lock, _T->flags),
+		    gpio_generic_chip_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+#endif /* __LINUX_GPIO_GENERIC_H */
-- 
cgit v1.2.3


From c5fd399a24c8e2865524361f7dc4d4a6899be4f4 Mon Sep 17 00:00:00 2001
From: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Date: Tue, 1 Jul 2025 17:55:41 +1000
Subject: wifi: mac80211: correctly identify S1G short beacon

mac80211 identifies a short beacon by the presence of the next
TBTT field, however the standard actually doesn't explicitly state that
the next TBTT can't be in a long beacon or even that it is required in
a short beacon - and as a result this validation does not work for all
vendor implementations.

The standard explicitly states that an S1G long beacon shall contain
the S1G beacon compatibility element as the first element in a beacon
transmitted at a TBTT that is not a TSBTT (Target Short Beacon
Transmission Time) as per IEEE80211-2024 11.1.3.10.1. This is validated
by 9.3.4.3 Table 9-76 which states that the S1G beacon compatibility
element is only allowed in the full set and is not allowed in the
minimum set of elements permitted for use within short beacons.

Correctly identify short beacons by the lack of an S1G beacon
compatibility element as the first element in an S1G beacon frame.

Fixes: 9eaffe5078ca ("cfg80211: convert S1G beacon to scan results")
Signed-off-by: Simon Wadsworth <simon@morsemicro.com>
Signed-off-by: Lachlan Hodges <lachlan.hodges@morsemicro.com>
Link: https://patch.msgid.link/20250701075541.162619-1-lachlan.hodges@morsemicro.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h | 45 +++++++++++++++++++++++++++++++++------------
 net/mac80211/mlme.c       |  7 +++++--
 2 files changed, 38 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 22f39e5e2ff1..996be3c2cff0 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -662,18 +662,6 @@ static inline bool ieee80211_s1g_has_cssid(__le16 fc)
 		(fc & cpu_to_le16(IEEE80211_S1G_BCN_CSSID));
 }
 
-/**
- * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon
- * @fc: frame control bytes in little-endian byteorder
- * Return: whether or not the frame is an S1G short beacon,
- *	i.e. it is an S1G beacon with 'next TBTT' flag set
- */
-static inline bool ieee80211_is_s1g_short_beacon(__le16 fc)
-{
-	return ieee80211_is_s1g_beacon(fc) &&
-		(fc & cpu_to_le16(IEEE80211_S1G_BCN_NEXT_TBTT));
-}
-
 /**
  * ieee80211_is_atim - check if IEEE80211_FTYPE_MGMT && IEEE80211_STYPE_ATIM
  * @fc: frame control bytes in little-endian byteorder
@@ -4901,6 +4889,39 @@ static inline bool ieee80211_is_ftm(struct sk_buff *skb)
 	return false;
 }
 
+/**
+ * ieee80211_is_s1g_short_beacon - check if frame is an S1G short beacon
+ * @fc: frame control bytes in little-endian byteorder
+ * @variable: pointer to the beacon frame elements
+ * @variable_len: length of the frame elements
+ * Return: whether or not the frame is an S1G short beacon. As per
+ *	IEEE80211-2024 11.1.3.10.1, The S1G beacon compatibility element shall
+ *	always be present as the first element in beacon frames generated at a
+ *	TBTT (Target Beacon Transmission Time), so any frame not containing
+ *	this element must have been generated at a TSBTT (Target Short Beacon
+ *	Transmission Time) that is not a TBTT. Additionally, short beacons are
+ *	prohibited from containing the S1G beacon compatibility element as per
+ *	IEEE80211-2024 9.3.4.3 Table 9-76, so if we have an S1G beacon with
+ *	either no elements or the first element is not the beacon compatibility
+ *	element, we have a short beacon.
+ */
+static inline bool ieee80211_is_s1g_short_beacon(__le16 fc, const u8 *variable,
+						 size_t variable_len)
+{
+	if (!ieee80211_is_s1g_beacon(fc))
+		return false;
+
+	/*
+	 * If the frame does not contain at least 1 element (this is perfectly
+	 * valid in a short beacon) and is an S1G beacon, we have a short
+	 * beacon.
+	 */
+	if (variable_len < 2)
+		return true;
+
+	return variable[0] != WLAN_EID_S1G_BCN_COMPAT;
+}
+
 struct element {
 	u8 id;
 	u8 datalen;
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 2d46d4af60d7..7ddb8e77b4c7 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -7195,6 +7195,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 	struct ieee80211_bss_conf *bss_conf = link->conf;
 	struct ieee80211_vif_cfg *vif_cfg = &sdata->vif.cfg;
 	struct ieee80211_mgmt *mgmt = (void *) hdr;
+	struct ieee80211_ext *ext = NULL;
 	size_t baselen;
 	struct ieee802_11_elems *elems;
 	struct ieee80211_local *local = sdata->local;
@@ -7220,7 +7221,7 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 	/* Process beacon from the current BSS */
 	bssid = ieee80211_get_bssid(hdr, len, sdata->vif.type);
 	if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
-		struct ieee80211_ext *ext = (void *) mgmt;
+		ext = (void *)mgmt;
 		variable = ext->u.s1g_beacon.variable +
 			   ieee80211_s1g_optional_len(ext->frame_control);
 	}
@@ -7407,7 +7408,9 @@ static void ieee80211_rx_mgmt_beacon(struct ieee80211_link_data *link,
 	}
 
 	if ((ncrc == link->u.mgd.beacon_crc && link->u.mgd.beacon_crc_valid) ||
-	    ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+	    (ext && ieee80211_is_s1g_short_beacon(ext->frame_control,
+						  parse_params.start,
+						  parse_params.len)))
 		goto free;
 	link->u.mgd.beacon_crc = ncrc;
 	link->u.mgd.beacon_crc_valid = true;
-- 
cgit v1.2.3


From 377d7860c960ac8e672881bc50353d867e2f94a4 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Thu, 12 Jun 2025 15:25:33 +0200
Subject: cred: add auto cleanup method

Add a simple auto cleanup method for struct cred.

Link: https://lore.kernel.org/20250612-work-coredump-massage-v1-19-315c0c34ba94@kernel.org
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/cred.h | 2 ++
 1 file changed, 2 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cred.h b/include/linux/cred.h
index 5658a3bfe803..a102a10f833f 100644
--- a/include/linux/cred.h
+++ b/include/linux/cred.h
@@ -263,6 +263,8 @@ static inline void put_cred(const struct cred *cred)
 	put_cred_many(cred, 1);
 }
 
+DEFINE_FREE(put_cred, struct cred *, if (!IS_ERR_OR_NULL(_T)) put_cred(_T))
+
 /**
  * current_cred - Access the current task's subjective credentials
  *
-- 
cgit v1.2.3


From 3ebed2fddf6fac5729ffc8c471c87d111b641678 Mon Sep 17 00:00:00 2001
From: Armin Wolf <W_Armin@gmx.de>
Date: Fri, 27 Jun 2025 22:51:22 +0200
Subject: power: supply: core: Add power_supply_get/set_property_direct()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Power supply extensions might want to interact with the underlying
power supply to retrieve data like serial numbers, charging status
and more. However doing so causes psy->extensions_sem to be locked
twice, possibly causing a deadlock.

Provide special variants of power_supply_get/set_property() that
ignore any power supply extensions and thus do not touch the
associated psy->extensions_sem lock.

Suggested-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Armin Wolf <W_Armin@gmx.de>
Acked-by: Sebastian Reichel <sebastian.reichel@collabora.com>
Reviewed-by: Hans de Goede <hansg@kernel.org>
Link: https://lore.kernel.org/r/20250627205124.250433-1-W_Armin@gmx.de
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
---
 drivers/power/supply/power_supply_core.c | 82 +++++++++++++++++++++++++++-----
 include/linux/power_supply.h             |  8 ++++
 2 files changed, 78 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/power/supply/power_supply_core.c b/drivers/power/supply/power_supply_core.c
index 33a5bfce4604..cfb0e3e0d4aa 100644
--- a/drivers/power/supply/power_supply_core.c
+++ b/drivers/power/supply/power_supply_core.c
@@ -1235,9 +1235,8 @@ bool power_supply_has_property(struct power_supply *psy,
 	return false;
 }
 
-int power_supply_get_property(struct power_supply *psy,
-			    enum power_supply_property psp,
-			    union power_supply_propval *val)
+static int __power_supply_get_property(struct power_supply *psy, enum power_supply_property psp,
+				       union power_supply_propval *val, bool use_extensions)
 {
 	struct power_supply_ext_registration *reg;
 
@@ -1247,10 +1246,14 @@ int power_supply_get_property(struct power_supply *psy,
 		return -ENODEV;
 	}
 
-	scoped_guard(rwsem_read, &psy->extensions_sem) {
-		power_supply_for_each_extension(reg, psy) {
-			if (power_supply_ext_has_property(reg->ext, psp))
+	if (use_extensions) {
+		scoped_guard(rwsem_read, &psy->extensions_sem) {
+			power_supply_for_each_extension(reg, psy) {
+				if (!power_supply_ext_has_property(reg->ext, psp))
+					continue;
+
 				return reg->ext->get_property(psy, reg->ext, reg->data, psp, val);
+			}
 		}
 	}
 
@@ -1261,20 +1264,49 @@ int power_supply_get_property(struct power_supply *psy,
 	else
 		return -EINVAL;
 }
+
+int power_supply_get_property(struct power_supply *psy, enum power_supply_property psp,
+			      union power_supply_propval *val)
+{
+	return __power_supply_get_property(psy, psp, val, true);
+}
 EXPORT_SYMBOL_GPL(power_supply_get_property);
 
-int power_supply_set_property(struct power_supply *psy,
-			    enum power_supply_property psp,
-			    const union power_supply_propval *val)
+/**
+ * power_supply_get_property_direct - Read a power supply property without checking for extensions
+ * @psy: The power supply
+ * @psp: The power supply property to read
+ * @val: The resulting value of the power supply property
+ *
+ * Read a power supply property without taking into account any power supply extensions registered
+ * on the given power supply. This is mostly useful for power supply extensions that want to access
+ * their own power supply as using power_supply_get_property() directly will result in a potential
+ * deadlock.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int power_supply_get_property_direct(struct power_supply *psy, enum power_supply_property psp,
+				     union power_supply_propval *val)
+{
+        return __power_supply_get_property(psy, psp, val, false);
+}
+EXPORT_SYMBOL_GPL(power_supply_get_property_direct);
+
+
+static int __power_supply_set_property(struct power_supply *psy, enum power_supply_property psp,
+				       const union power_supply_propval *val, bool use_extensions)
 {
 	struct power_supply_ext_registration *reg;
 
 	if (atomic_read(&psy->use_cnt) <= 0)
 		return -ENODEV;
 
-	scoped_guard(rwsem_read, &psy->extensions_sem) {
-		power_supply_for_each_extension(reg, psy) {
-			if (power_supply_ext_has_property(reg->ext, psp)) {
+	if (use_extensions) {
+		scoped_guard(rwsem_read, &psy->extensions_sem) {
+			power_supply_for_each_extension(reg, psy) {
+				if (!power_supply_ext_has_property(reg->ext, psp))
+					continue;
+
 				if (reg->ext->set_property)
 					return reg->ext->set_property(psy, reg->ext, reg->data,
 								      psp, val);
@@ -1289,8 +1321,34 @@ int power_supply_set_property(struct power_supply *psy,
 
 	return psy->desc->set_property(psy, psp, val);
 }
+
+int power_supply_set_property(struct power_supply *psy, enum power_supply_property psp,
+			      const union power_supply_propval *val)
+{
+	return __power_supply_set_property(psy, psp, val, true);
+}
 EXPORT_SYMBOL_GPL(power_supply_set_property);
 
+/**
+ * power_supply_set_property_direct - Write a power supply property without checking for extensions
+ * @psy: The power supply
+ * @psp: The power supply property to write
+ * @val: The value to write to the power supply property
+ *
+ * Write a power supply property without taking into account any power supply extensions registered
+ * on the given power supply. This is mostly useful for power supply extensions that want to access
+ * their own power supply as using power_supply_set_property() directly will result in a potential
+ * deadlock.
+ *
+ * Return: 0 on success or negative error code on failure.
+ */
+int power_supply_set_property_direct(struct power_supply *psy, enum power_supply_property psp,
+				     const union power_supply_propval *val)
+{
+	return __power_supply_set_property(psy, psp, val, false);
+}
+EXPORT_SYMBOL_GPL(power_supply_set_property_direct);
+
 int power_supply_property_is_writeable(struct power_supply *psy,
 					enum power_supply_property psp)
 {
diff --git a/include/linux/power_supply.h b/include/linux/power_supply.h
index 7803edaa8ff8..0cca01b5607b 100644
--- a/include/linux/power_supply.h
+++ b/include/linux/power_supply.h
@@ -888,15 +888,23 @@ static inline int power_supply_is_system_supplied(void) { return -ENOSYS; }
 extern int power_supply_get_property(struct power_supply *psy,
 			    enum power_supply_property psp,
 			    union power_supply_propval *val);
+int power_supply_get_property_direct(struct power_supply *psy, enum power_supply_property psp,
+				     union power_supply_propval *val);
 #if IS_ENABLED(CONFIG_POWER_SUPPLY)
 extern int power_supply_set_property(struct power_supply *psy,
 			    enum power_supply_property psp,
 			    const union power_supply_propval *val);
+int power_supply_set_property_direct(struct power_supply *psy, enum power_supply_property psp,
+				     const union power_supply_propval *val);
 #else
 static inline int power_supply_set_property(struct power_supply *psy,
 			    enum power_supply_property psp,
 			    const union power_supply_propval *val)
 { return 0; }
+static inline int power_supply_set_property_direct(struct power_supply *psy,
+						   enum power_supply_property psp,
+						   const union power_supply_propval *val)
+{ return 0; }
 #endif
 extern void power_supply_external_power_changed(struct power_supply *psy);
 
-- 
cgit v1.2.3


From 1cea5180f2f812c444ceebdc40f5d001bedd030d Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Sat, 5 Jul 2025 14:19:50 -0600
Subject: block: remove pktcdvd driver

This driver has long outlived it's utility, and it's broken and unloved.
The main use case for this was direct mount with UDF of cd-rw drives
that required 32kb packets. It would collect writes into that size and
write them out in multiples of that. That's not a common use case
anymore, the world has moved on from those kinds of media. To make
matters worse, it's actively breaking setups where it's not even
required or useful.

Link: https://lore.kernel.org/linux-block/fxg6dksau4jsk3u5xldlyo2m7qgiux6vtdrz5rywseotsouqdv@urcrwz6qtd3r/
Link: https://lore.kernel.org/linux-block/dcc4836e-6da9-4208-ad27-bbd44b3a2063@kernel.dk/
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Hannes Reinecke <hare@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/ABI/testing/debugfs-pktcdvd          |   18 -
 Documentation/ABI/testing/sysfs-class-pktcdvd      |   97 -
 Documentation/cdrom/packet-writing.rst             |  139 -
 Documentation/userspace-api/ioctl/ioctl-number.rst |    1 -
 MAINTAINERS                                        |    7 -
 drivers/block/Kconfig                              |   43 -
 drivers/block/Makefile                             |    1 -
 drivers/block/pktcdvd.c                            | 2916 --------------------
 include/linux/pktcdvd.h                            |  198 --
 9 files changed, 3420 deletions(-)
 delete mode 100644 Documentation/ABI/testing/debugfs-pktcdvd
 delete mode 100644 Documentation/ABI/testing/sysfs-class-pktcdvd
 delete mode 100644 Documentation/cdrom/packet-writing.rst
 delete mode 100644 drivers/block/pktcdvd.c
 delete mode 100644 include/linux/pktcdvd.h

(limited to 'include/linux')

diff --git a/Documentation/ABI/testing/debugfs-pktcdvd b/Documentation/ABI/testing/debugfs-pktcdvd
deleted file mode 100644
index f6f65a4faea0..000000000000
--- a/Documentation/ABI/testing/debugfs-pktcdvd
+++ /dev/null
@@ -1,18 +0,0 @@
-What:           /sys/kernel/debug/pktcdvd/pktcdvd[0-7]
-Date:           Oct. 2006
-KernelVersion:  2.6.20
-Contact:        Thomas Maier <balagi@justmail.de>
-Description:
-
-The pktcdvd module (packet writing driver) creates
-these files in debugfs:
-
-/sys/kernel/debug/pktcdvd/pktcdvd[0-7]/
-
-    ====            ====== ====================================
-    info            0444   Lots of driver statistics and infos.
-    ====            ====== ====================================
-
-Example::
-
-    cat /sys/kernel/debug/pktcdvd/pktcdvd0/info
diff --git a/Documentation/ABI/testing/sysfs-class-pktcdvd b/Documentation/ABI/testing/sysfs-class-pktcdvd
deleted file mode 100644
index ba1ce626591d..000000000000
--- a/Documentation/ABI/testing/sysfs-class-pktcdvd
+++ /dev/null
@@ -1,97 +0,0 @@
-sysfs interface
----------------
-The pktcdvd module (packet writing driver) creates the following files in the
-sysfs: (<devid> is in the format major:minor)
-
-What:		/sys/class/pktcdvd/add
-What:		/sys/class/pktcdvd/remove
-What:		/sys/class/pktcdvd/device_map
-Date:		Oct. 2006
-KernelVersion:	2.6.20
-Contact:	Thomas Maier <balagi@justmail.de>
-Description:
-
-		==========	==============================================
-		add		(WO) Write a block device id (major:minor) to
-				create a new pktcdvd device and map it to the
-				block device.
-
-		remove		(WO) Write the pktcdvd device id (major:minor)
-				to remove the pktcdvd device.
-
-		device_map	(RO) Shows the device mapping in format:
-				pktcdvd[0-7] <pktdevid> <blkdevid>
-		==========	==============================================
-
-
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/dev
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/uevent
-Date:		Oct. 2006
-KernelVersion:	2.6.20
-Contact:	Thomas Maier <balagi@justmail.de>
-Description:
-		dev:	(RO) Device id
-
-		uevent:	(WO) To send a uevent
-
-
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_started
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/packets_finished
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_written
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/kb_read_gather
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/stat/reset
-Date:		Oct. 2006
-KernelVersion:	2.6.20
-Contact:	Thomas Maier <balagi@justmail.de>
-Description:
-		packets_started:	(RO) Number of started packets.
-
-		packets_finished:	(RO) Number of finished packets.
-
-		kb_written:		(RO) kBytes written.
-
-		kb_read:		(RO) kBytes read.
-
-		kb_read_gather:		(RO) kBytes read to fill write packets.
-
-		reset:			(WO) Write any value to it to reset
-					pktcdvd device statistic values, like
-					bytes read/written.
-
-
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/write_queue/size
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_off
-What:		/sys/class/pktcdvd/pktcdvd[0-7]/write_queue/congestion_on
-Date:		Oct. 2006
-KernelVersion:	2.6.20
-Contact:	Thomas Maier <balagi@justmail.de>
-Description:
-		==============	================================================
-		size		(RO) Contains the size of the bio write queue.
-
-		congestion_off	(RW) If bio write queue size is below this mark,
-				accept new bio requests from the block layer.
-
-		congestion_on	(RW) If bio write queue size is higher as this
-				mark, do no longer accept bio write requests
-				from the block layer and wait till the pktcdvd
-				device has processed enough bio's so that bio
-				write queue size is below congestion off mark.
-				A value of <= 0 disables congestion control.
-		==============	================================================
-
-
-Example:
---------
-To use the pktcdvd sysfs interface directly, you can do::
-
-    # create a new pktcdvd device mapped to /dev/hdc
-    echo "22:0" >/sys/class/pktcdvd/add
-    cat /sys/class/pktcdvd/device_map
-    # assuming device pktcdvd0 was created, look at stat's
-    cat /sys/class/pktcdvd/pktcdvd0/stat/kb_written
-    # print the device id of the mapped block device
-    fgrep pktcdvd0 /sys/class/pktcdvd/device_map
-    # remove device, using pktcdvd0 device id   253:0
-    echo "253:0" >/sys/class/pktcdvd/remove
diff --git a/Documentation/cdrom/packet-writing.rst b/Documentation/cdrom/packet-writing.rst
deleted file mode 100644
index 43db58c50d29..000000000000
--- a/Documentation/cdrom/packet-writing.rst
+++ /dev/null
@@ -1,139 +0,0 @@
-==============
-Packet writing
-==============
-
-Getting started quick
----------------------
-
-- Select packet support in the block device section and UDF support in
-  the file system section.
-
-- Compile and install kernel and modules, reboot.
-
-- You need the udftools package (pktsetup, mkudffs, cdrwtool).
-  Download from https://github.com/pali/udftools
-
-- Grab a new CD-RW disc and format it (assuming CD-RW is hdc, substitute
-  as appropriate)::
-
-	# cdrwtool -d /dev/hdc -q
-
-- Setup your writer::
-
-	# pktsetup dev_name /dev/hdc
-
-- Now you can mount /dev/pktcdvd/dev_name and copy files to it. Enjoy::
-
-	# mount /dev/pktcdvd/dev_name /cdrom -t udf -o rw,noatime
-
-
-Packet writing for DVD-RW media
--------------------------------
-
-DVD-RW discs can be written to much like CD-RW discs if they are in
-the so called "restricted overwrite" mode. To put a disc in restricted
-overwrite mode, run::
-
-	# dvd+rw-format /dev/hdc
-
-You can then use the disc the same way you would use a CD-RW disc::
-
-	# pktsetup dev_name /dev/hdc
-	# mount /dev/pktcdvd/dev_name /cdrom -t udf -o rw,noatime
-
-
-Packet writing for DVD+RW media
--------------------------------
-
-According to the DVD+RW specification, a drive supporting DVD+RW discs
-shall implement "true random writes with 2KB granularity", which means
-that it should be possible to put any filesystem with a block size >=
-2KB on such a disc. For example, it should be possible to do::
-
-	# dvd+rw-format /dev/hdc   (only needed if the disc has never
-	                            been formatted)
-	# mkudffs /dev/hdc
-	# mount /dev/hdc /cdrom -t udf -o rw,noatime
-
-However, some drives don't follow the specification and expect the
-host to perform aligned writes at 32KB boundaries. Other drives do
-follow the specification, but suffer bad performance problems if the
-writes are not 32KB aligned.
-
-Both problems can be solved by using the pktcdvd driver, which always
-generates aligned writes::
-
-	# dvd+rw-format /dev/hdc
-	# pktsetup dev_name /dev/hdc
-	# mkudffs /dev/pktcdvd/dev_name
-	# mount /dev/pktcdvd/dev_name /cdrom -t udf -o rw,noatime
-
-
-Packet writing for DVD-RAM media
---------------------------------
-
-DVD-RAM discs are random writable, so using the pktcdvd driver is not
-necessary. However, using the pktcdvd driver can improve performance
-in the same way it does for DVD+RW media.
-
-
-Notes
------
-
-- CD-RW media can usually not be overwritten more than about 1000
-  times, so to avoid unnecessary wear on the media, you should always
-  use the noatime mount option.
-
-- Defect management (ie automatic remapping of bad sectors) has not
-  been implemented yet, so you are likely to get at least some
-  filesystem corruption if the disc wears out.
-
-- Since the pktcdvd driver makes the disc appear as a regular block
-  device with a 2KB block size, you can put any filesystem you like on
-  the disc. For example, run::
-
-	# /sbin/mke2fs /dev/pktcdvd/dev_name
-
-  to create an ext2 filesystem on the disc.
-
-
-Using the pktcdvd sysfs interface
----------------------------------
-
-Since Linux 2.6.20, the pktcdvd module has a sysfs interface
-and can be controlled by it. For example the "pktcdvd" tool uses
-this interface. (see http://tom.ist-im-web.de/linux/software/pktcdvd )
-
-"pktcdvd" works similar to "pktsetup", e.g.::
-
-	# pktcdvd -a dev_name /dev/hdc
-	# mkudffs /dev/pktcdvd/dev_name
-	# mount -t udf -o rw,noatime /dev/pktcdvd/dev_name /dvdram
-	# cp files /dvdram
-	# umount /dvdram
-	# pktcdvd -r dev_name
-
-
-For a description of the sysfs interface look into the file:
-
-  Documentation/ABI/testing/sysfs-class-pktcdvd
-
-
-Using the pktcdvd debugfs interface
------------------------------------
-
-To read pktcdvd device infos in human readable form, do::
-
-	# cat /sys/kernel/debug/pktcdvd/pktcdvd[0-7]/info
-
-For a description of the debugfs interface look into the file:
-
-  Documentation/ABI/testing/debugfs-pktcdvd
-
-
-
-Links
------
-
-See http://fy.chalmers.se/~appro/linux/DVD+RW/ for more information
-about DVD writing.
diff --git a/Documentation/userspace-api/ioctl/ioctl-number.rst b/Documentation/userspace-api/ioctl/ioctl-number.rst
index bc91756bde73..4f1532a251d2 100644
--- a/Documentation/userspace-api/ioctl/ioctl-number.rst
+++ b/Documentation/userspace-api/ioctl/ioctl-number.rst
@@ -220,7 +220,6 @@ Code  Seq#    Include File                                           Comments
              include/linux/falloc.h,
              linux/fs.h,
 'X'   all    fs/ocfs2/ocfs_fs.h                                      conflict!
-'X'   01     linux/pktcdvd.h                                         conflict!
 'Z'   14-15  drivers/message/fusion/mptctl.h
 '['   00-3F  linux/usb/tmc.h                                         USB Test and Measurement Devices
                                                                      <mailto:gregkh@linuxfoundation.org>
diff --git a/MAINTAINERS b/MAINTAINERS
index 4bac4ea21b64..560339f8acd3 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -19697,13 +19697,6 @@ S:	Supported
 F:	Documentation/devicetree/bindings/input/pine64,pinephone-keyboard.yaml
 F:	drivers/input/keyboard/pinephone-keyboard.c
 
-PKTCDVD DRIVER
-M:	linux-block@vger.kernel.org
-S:	Orphan
-F:	drivers/block/pktcdvd.c
-F:	include/linux/pktcdvd.h
-F:	include/uapi/linux/pktcdvd.h
-
 PLANTOWER PMS7003 AIR POLLUTION SENSOR DRIVER
 M:	Tomasz Duszynski <tduszyns@gmail.com>
 S:	Maintained
diff --git a/drivers/block/Kconfig b/drivers/block/Kconfig
index 0f70e2374e7f..df38fb364904 100644
--- a/drivers/block/Kconfig
+++ b/drivers/block/Kconfig
@@ -256,49 +256,6 @@ config BLK_DEV_RAM_SIZE
 	  The default value is 4096 kilobytes. Only change this if you know
 	  what you are doing.
 
-config CDROM_PKTCDVD
-	tristate "Packet writing on CD/DVD media (DEPRECATED)"
-	depends on !UML
-	depends on SCSI
-	select CDROM
-	help
-	  Note: This driver is deprecated and will be removed from the
-	  kernel in the near future!
-
-	  If you have a CDROM/DVD drive that supports packet writing, say
-	  Y to include support. It should work with any MMC/Mt Fuji
-	  compliant ATAPI or SCSI drive, which is just about any newer
-	  DVD/CD writer.
-
-	  Currently only writing to CD-RW, DVD-RW, DVD+RW and DVDRAM discs
-	  is possible.
-	  DVD-RW disks must be in restricted overwrite mode.
-
-	  See the file <file:Documentation/cdrom/packet-writing.rst>
-	  for further information on the use of this driver.
-
-	  To compile this driver as a module, choose M here: the
-	  module will be called pktcdvd.
-
-config CDROM_PKTCDVD_BUFFERS
-	int "Free buffers for data gathering"
-	depends on CDROM_PKTCDVD
-	default "8"
-	help
-	  This controls the maximum number of active concurrent packets. More
-	  concurrent packets can increase write performance, but also require
-	  more memory. Each concurrent packet will require approximately 64Kb
-	  of non-swappable kernel memory, memory which will be allocated when
-	  a disc is opened for writing.
-
-config CDROM_PKTCDVD_WCACHE
-	bool "Enable write caching"
-	depends on CDROM_PKTCDVD
-	help
-	  If enabled, write caching will be set for the CD-R/W device. For now
-	  this option is dangerous unless the CD-RW media is known good, as we
-	  don't do deferred write error handling yet.
-
 config ATA_OVER_ETH
 	tristate "ATA over Ethernet support"
 	depends on NET
diff --git a/drivers/block/Makefile b/drivers/block/Makefile
index 097707aca725..a695ce74ef22 100644
--- a/drivers/block/Makefile
+++ b/drivers/block/Makefile
@@ -23,7 +23,6 @@ obj-$(CONFIG_AMIGA_Z2RAM)	+= z2ram.o
 obj-$(CONFIG_N64CART)		+= n64cart.o
 obj-$(CONFIG_BLK_DEV_RAM)	+= brd.o
 obj-$(CONFIG_BLK_DEV_LOOP)	+= loop.o
-obj-$(CONFIG_CDROM_PKTCDVD)	+= pktcdvd.o
 obj-$(CONFIG_SUNVDC)		+= sunvdc.o
 
 obj-$(CONFIG_BLK_DEV_NBD)	+= nbd.o
diff --git a/drivers/block/pktcdvd.c b/drivers/block/pktcdvd.c
deleted file mode 100644
index d5cc7bd2875c..000000000000
--- a/drivers/block/pktcdvd.c
+++ /dev/null
@@ -1,2916 +0,0 @@
-/*
- * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
- * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
- * Copyright (C) 2006 Thomas Maier <balagi@justmail.de>
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * Packet writing layer for ATAPI and SCSI CD-RW, DVD+RW, DVD-RW and
- * DVD-RAM devices.
- *
- * Theory of operation:
- *
- * At the lowest level, there is the standard driver for the CD/DVD device,
- * such as drivers/scsi/sr.c. This driver can handle read and write requests,
- * but it doesn't know anything about the special restrictions that apply to
- * packet writing. One restriction is that write requests must be aligned to
- * packet boundaries on the physical media, and the size of a write request
- * must be equal to the packet size. Another restriction is that a
- * GPCMD_FLUSH_CACHE command has to be issued to the drive before a read
- * command, if the previous command was a write.
- *
- * The purpose of the packet writing driver is to hide these restrictions from
- * higher layers, such as file systems, and present a block device that can be
- * randomly read and written using 2kB-sized blocks.
- *
- * The lowest layer in the packet writing driver is the packet I/O scheduler.
- * Its data is defined by the struct packet_iosched and includes two bio
- * queues with pending read and write requests. These queues are processed
- * by the pkt_iosched_process_queue() function. The write requests in this
- * queue are already properly aligned and sized. This layer is responsible for
- * issuing the flush cache commands and scheduling the I/O in a good order.
- *
- * The next layer transforms unaligned write requests to aligned writes. This
- * transformation requires reading missing pieces of data from the underlying
- * block device, assembling the pieces to full packets and queuing them to the
- * packet I/O scheduler.
- *
- * At the top layer there is a custom ->submit_bio function that forwards
- * read requests directly to the iosched queue and puts write requests in the
- * unaligned write queue. A kernel thread performs the necessary read
- * gathering to convert the unaligned writes to aligned writes and then feeds
- * them to the packet I/O scheduler.
- *
- *************************************************************************/
-
-#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
-
-#include <linux/backing-dev.h>
-#include <linux/compat.h>
-#include <linux/debugfs.h>
-#include <linux/device.h>
-#include <linux/errno.h>
-#include <linux/file.h>
-#include <linux/freezer.h>
-#include <linux/kernel.h>
-#include <linux/kthread.h>
-#include <linux/miscdevice.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/nospec.h>
-#include <linux/pktcdvd.h>
-#include <linux/proc_fs.h>
-#include <linux/seq_file.h>
-#include <linux/slab.h>
-#include <linux/spinlock.h>
-#include <linux/types.h>
-#include <linux/uaccess.h>
-
-#include <scsi/scsi.h>
-#include <scsi/scsi_cmnd.h>
-#include <scsi/scsi_ioctl.h>
-
-#include <linux/unaligned.h>
-
-#define DRIVER_NAME	"pktcdvd"
-
-#define MAX_SPEED 0xffff
-
-static DEFINE_MUTEX(pktcdvd_mutex);
-static struct pktcdvd_device *pkt_devs[MAX_WRITERS];
-static struct proc_dir_entry *pkt_proc;
-static int pktdev_major;
-static int write_congestion_on  = PKT_WRITE_CONGESTION_ON;
-static int write_congestion_off = PKT_WRITE_CONGESTION_OFF;
-static struct mutex ctl_mutex;	/* Serialize open/close/setup/teardown */
-static mempool_t psd_pool;
-static struct bio_set pkt_bio_set;
-
-/* /sys/class/pktcdvd */
-static struct class	class_pktcdvd;
-static struct dentry	*pkt_debugfs_root = NULL; /* /sys/kernel/debug/pktcdvd */
-
-/* forward declaration */
-static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev);
-static int pkt_remove_dev(dev_t pkt_dev);
-
-static sector_t get_zone(sector_t sector, struct pktcdvd_device *pd)
-{
-	return (sector + pd->offset) & ~(sector_t)(pd->settings.size - 1);
-}
-
-/**********************************************************
- * sysfs interface for pktcdvd
- * by (C) 2006  Thomas Maier <balagi@justmail.de>
- 
-  /sys/class/pktcdvd/pktcdvd[0-7]/
-                     stat/reset
-                     stat/packets_started
-                     stat/packets_finished
-                     stat/kb_written
-                     stat/kb_read
-                     stat/kb_read_gather
-                     write_queue/size
-                     write_queue/congestion_off
-                     write_queue/congestion_on
- **********************************************************/
-
-static ssize_t packets_started_show(struct device *dev,
-				    struct device_attribute *attr, char *buf)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-
-	return sysfs_emit(buf, "%lu\n", pd->stats.pkt_started);
-}
-static DEVICE_ATTR_RO(packets_started);
-
-static ssize_t packets_finished_show(struct device *dev,
-				     struct device_attribute *attr, char *buf)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-
-	return sysfs_emit(buf, "%lu\n", pd->stats.pkt_ended);
-}
-static DEVICE_ATTR_RO(packets_finished);
-
-static ssize_t kb_written_show(struct device *dev,
-			       struct device_attribute *attr, char *buf)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-
-	return sysfs_emit(buf, "%lu\n", pd->stats.secs_w >> 1);
-}
-static DEVICE_ATTR_RO(kb_written);
-
-static ssize_t kb_read_show(struct device *dev,
-			    struct device_attribute *attr, char *buf)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-
-	return sysfs_emit(buf, "%lu\n", pd->stats.secs_r >> 1);
-}
-static DEVICE_ATTR_RO(kb_read);
-
-static ssize_t kb_read_gather_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-
-	return sysfs_emit(buf, "%lu\n", pd->stats.secs_rg >> 1);
-}
-static DEVICE_ATTR_RO(kb_read_gather);
-
-static ssize_t reset_store(struct device *dev, struct device_attribute *attr,
-			   const char *buf, size_t len)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-
-	if (len > 0) {
-		pd->stats.pkt_started = 0;
-		pd->stats.pkt_ended = 0;
-		pd->stats.secs_w = 0;
-		pd->stats.secs_rg = 0;
-		pd->stats.secs_r = 0;
-	}
-	return len;
-}
-static DEVICE_ATTR_WO(reset);
-
-static struct attribute *pkt_stat_attrs[] = {
-	&dev_attr_packets_finished.attr,
-	&dev_attr_packets_started.attr,
-	&dev_attr_kb_read.attr,
-	&dev_attr_kb_written.attr,
-	&dev_attr_kb_read_gather.attr,
-	&dev_attr_reset.attr,
-	NULL,
-};
-
-static const struct attribute_group pkt_stat_group = {
-	.name = "stat",
-	.attrs = pkt_stat_attrs,
-};
-
-static ssize_t size_show(struct device *dev,
-			 struct device_attribute *attr, char *buf)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-	int n;
-
-	spin_lock(&pd->lock);
-	n = sysfs_emit(buf, "%d\n", pd->bio_queue_size);
-	spin_unlock(&pd->lock);
-	return n;
-}
-static DEVICE_ATTR_RO(size);
-
-static void init_write_congestion_marks(int* lo, int* hi)
-{
-	if (*hi > 0) {
-		*hi = max(*hi, 500);
-		*hi = min(*hi, 1000000);
-		if (*lo <= 0)
-			*lo = *hi - 100;
-		else {
-			*lo = min(*lo, *hi - 100);
-			*lo = max(*lo, 100);
-		}
-	} else {
-		*hi = -1;
-		*lo = -1;
-	}
-}
-
-static ssize_t congestion_off_show(struct device *dev,
-				   struct device_attribute *attr, char *buf)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-	int n;
-
-	spin_lock(&pd->lock);
-	n = sysfs_emit(buf, "%d\n", pd->write_congestion_off);
-	spin_unlock(&pd->lock);
-	return n;
-}
-
-static ssize_t congestion_off_store(struct device *dev,
-				    struct device_attribute *attr,
-				    const char *buf, size_t len)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-	int val, ret;
-
-	ret = kstrtoint(buf, 10, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&pd->lock);
-	pd->write_congestion_off = val;
-	init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on);
-	spin_unlock(&pd->lock);
-	return len;
-}
-static DEVICE_ATTR_RW(congestion_off);
-
-static ssize_t congestion_on_show(struct device *dev,
-				  struct device_attribute *attr, char *buf)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-	int n;
-
-	spin_lock(&pd->lock);
-	n = sysfs_emit(buf, "%d\n", pd->write_congestion_on);
-	spin_unlock(&pd->lock);
-	return n;
-}
-
-static ssize_t congestion_on_store(struct device *dev,
-				   struct device_attribute *attr,
-				   const char *buf, size_t len)
-{
-	struct pktcdvd_device *pd = dev_get_drvdata(dev);
-	int val, ret;
-
-	ret = kstrtoint(buf, 10, &val);
-	if (ret)
-		return ret;
-
-	spin_lock(&pd->lock);
-	pd->write_congestion_on = val;
-	init_write_congestion_marks(&pd->write_congestion_off, &pd->write_congestion_on);
-	spin_unlock(&pd->lock);
-	return len;
-}
-static DEVICE_ATTR_RW(congestion_on);
-
-static struct attribute *pkt_wq_attrs[] = {
-	&dev_attr_congestion_on.attr,
-	&dev_attr_congestion_off.attr,
-	&dev_attr_size.attr,
-	NULL,
-};
-
-static const struct attribute_group pkt_wq_group = {
-	.name = "write_queue",
-	.attrs = pkt_wq_attrs,
-};
-
-static const struct attribute_group *pkt_groups[] = {
-	&pkt_stat_group,
-	&pkt_wq_group,
-	NULL,
-};
-
-static void pkt_sysfs_dev_new(struct pktcdvd_device *pd)
-{
-	if (class_is_registered(&class_pktcdvd)) {
-		pd->dev = device_create_with_groups(&class_pktcdvd, NULL,
-						    MKDEV(0, 0), pd, pkt_groups,
-						    "%s", pd->disk->disk_name);
-		if (IS_ERR(pd->dev))
-			pd->dev = NULL;
-	}
-}
-
-static void pkt_sysfs_dev_remove(struct pktcdvd_device *pd)
-{
-	if (class_is_registered(&class_pktcdvd))
-		device_unregister(pd->dev);
-}
-
-
-/********************************************************************
-  /sys/class/pktcdvd/
-                     add            map block device
-                     remove         unmap packet dev
-                     device_map     show mappings
- *******************************************************************/
-
-static ssize_t device_map_show(const struct class *c, const struct class_attribute *attr,
-			       char *data)
-{
-	int n = 0;
-	int idx;
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-	for (idx = 0; idx < MAX_WRITERS; idx++) {
-		struct pktcdvd_device *pd = pkt_devs[idx];
-		if (!pd)
-			continue;
-		n += sysfs_emit_at(data, n, "%s %u:%u %u:%u\n",
-			pd->disk->disk_name,
-			MAJOR(pd->pkt_dev), MINOR(pd->pkt_dev),
-			MAJOR(file_bdev(pd->bdev_file)->bd_dev),
-			MINOR(file_bdev(pd->bdev_file)->bd_dev));
-	}
-	mutex_unlock(&ctl_mutex);
-	return n;
-}
-static CLASS_ATTR_RO(device_map);
-
-static ssize_t add_store(const struct class *c, const struct class_attribute *attr,
-			 const char *buf, size_t count)
-{
-	unsigned int major, minor;
-
-	if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
-		/* pkt_setup_dev() expects caller to hold reference to self */
-		if (!try_module_get(THIS_MODULE))
-			return -ENODEV;
-
-		pkt_setup_dev(MKDEV(major, minor), NULL);
-
-		module_put(THIS_MODULE);
-
-		return count;
-	}
-
-	return -EINVAL;
-}
-static CLASS_ATTR_WO(add);
-
-static ssize_t remove_store(const struct class *c, const struct class_attribute *attr,
-			    const char *buf, size_t count)
-{
-	unsigned int major, minor;
-	if (sscanf(buf, "%u:%u", &major, &minor) == 2) {
-		pkt_remove_dev(MKDEV(major, minor));
-		return count;
-	}
-	return -EINVAL;
-}
-static CLASS_ATTR_WO(remove);
-
-static struct attribute *class_pktcdvd_attrs[] = {
-	&class_attr_add.attr,
-	&class_attr_remove.attr,
-	&class_attr_device_map.attr,
-	NULL,
-};
-ATTRIBUTE_GROUPS(class_pktcdvd);
-
-static struct class class_pktcdvd = {
-	.name		= DRIVER_NAME,
-	.class_groups	= class_pktcdvd_groups,
-};
-
-static int pkt_sysfs_init(void)
-{
-	/*
-	 * create control files in sysfs
-	 * /sys/class/pktcdvd/...
-	 */
-	return class_register(&class_pktcdvd);
-}
-
-static void pkt_sysfs_cleanup(void)
-{
-	class_unregister(&class_pktcdvd);
-}
-
-/********************************************************************
-  entries in debugfs
-
-  /sys/kernel/debug/pktcdvd[0-7]/
-			info
-
- *******************************************************************/
-
-static void pkt_count_states(struct pktcdvd_device *pd, int *states)
-{
-	struct packet_data *pkt;
-	int i;
-
-	for (i = 0; i < PACKET_NUM_STATES; i++)
-		states[i] = 0;
-
-	spin_lock(&pd->cdrw.active_list_lock);
-	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
-		states[pkt->state]++;
-	}
-	spin_unlock(&pd->cdrw.active_list_lock);
-}
-
-static int pkt_seq_show(struct seq_file *m, void *p)
-{
-	struct pktcdvd_device *pd = m->private;
-	char *msg;
-	int states[PACKET_NUM_STATES];
-
-	seq_printf(m, "Writer %s mapped to %pg:\n", pd->disk->disk_name,
-		   file_bdev(pd->bdev_file));
-
-	seq_printf(m, "\nSettings:\n");
-	seq_printf(m, "\tpacket size:\t\t%dkB\n", pd->settings.size / 2);
-
-	if (pd->settings.write_type == 0)
-		msg = "Packet";
-	else
-		msg = "Unknown";
-	seq_printf(m, "\twrite type:\t\t%s\n", msg);
-
-	seq_printf(m, "\tpacket type:\t\t%s\n", pd->settings.fp ? "Fixed" : "Variable");
-	seq_printf(m, "\tlink loss:\t\t%d\n", pd->settings.link_loss);
-
-	seq_printf(m, "\ttrack mode:\t\t%d\n", pd->settings.track_mode);
-
-	if (pd->settings.block_mode == PACKET_BLOCK_MODE1)
-		msg = "Mode 1";
-	else if (pd->settings.block_mode == PACKET_BLOCK_MODE2)
-		msg = "Mode 2";
-	else
-		msg = "Unknown";
-	seq_printf(m, "\tblock mode:\t\t%s\n", msg);
-
-	seq_printf(m, "\nStatistics:\n");
-	seq_printf(m, "\tpackets started:\t%lu\n", pd->stats.pkt_started);
-	seq_printf(m, "\tpackets ended:\t\t%lu\n", pd->stats.pkt_ended);
-	seq_printf(m, "\twritten:\t\t%lukB\n", pd->stats.secs_w >> 1);
-	seq_printf(m, "\tread gather:\t\t%lukB\n", pd->stats.secs_rg >> 1);
-	seq_printf(m, "\tread:\t\t\t%lukB\n", pd->stats.secs_r >> 1);
-
-	seq_printf(m, "\nMisc:\n");
-	seq_printf(m, "\treference count:\t%d\n", pd->refcnt);
-	seq_printf(m, "\tflags:\t\t\t0x%lx\n", pd->flags);
-	seq_printf(m, "\tread speed:\t\t%ukB/s\n", pd->read_speed);
-	seq_printf(m, "\twrite speed:\t\t%ukB/s\n", pd->write_speed);
-	seq_printf(m, "\tstart offset:\t\t%lu\n", pd->offset);
-	seq_printf(m, "\tmode page offset:\t%u\n", pd->mode_offset);
-
-	seq_printf(m, "\nQueue state:\n");
-	seq_printf(m, "\tbios queued:\t\t%d\n", pd->bio_queue_size);
-	seq_printf(m, "\tbios pending:\t\t%d\n", atomic_read(&pd->cdrw.pending_bios));
-	seq_printf(m, "\tcurrent sector:\t\t0x%llx\n", pd->current_sector);
-
-	pkt_count_states(pd, states);
-	seq_printf(m, "\tstate:\t\t\ti:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
-		   states[0], states[1], states[2], states[3], states[4], states[5]);
-
-	seq_printf(m, "\twrite congestion marks:\toff=%d on=%d\n",
-			pd->write_congestion_off,
-			pd->write_congestion_on);
-	return 0;
-}
-DEFINE_SHOW_ATTRIBUTE(pkt_seq);
-
-static void pkt_debugfs_dev_new(struct pktcdvd_device *pd)
-{
-	if (!pkt_debugfs_root)
-		return;
-	pd->dfs_d_root = debugfs_create_dir(pd->disk->disk_name, pkt_debugfs_root);
-
-	pd->dfs_f_info = debugfs_create_file("info", 0444, pd->dfs_d_root,
-					     pd, &pkt_seq_fops);
-}
-
-static void pkt_debugfs_dev_remove(struct pktcdvd_device *pd)
-{
-	if (!pkt_debugfs_root)
-		return;
-	debugfs_remove(pd->dfs_f_info);
-	debugfs_remove(pd->dfs_d_root);
-	pd->dfs_f_info = NULL;
-	pd->dfs_d_root = NULL;
-}
-
-static void pkt_debugfs_init(void)
-{
-	pkt_debugfs_root = debugfs_create_dir(DRIVER_NAME, NULL);
-}
-
-static void pkt_debugfs_cleanup(void)
-{
-	debugfs_remove(pkt_debugfs_root);
-	pkt_debugfs_root = NULL;
-}
-
-/* ----------------------------------------------------------*/
-
-
-static void pkt_bio_finished(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-
-	BUG_ON(atomic_read(&pd->cdrw.pending_bios) <= 0);
-	if (atomic_dec_and_test(&pd->cdrw.pending_bios)) {
-		dev_dbg(ddev, "queue empty\n");
-		atomic_set(&pd->iosched.attention, 1);
-		wake_up(&pd->wqueue);
-	}
-}
-
-/*
- * Allocate a packet_data struct
- */
-static struct packet_data *pkt_alloc_packet_data(int frames)
-{
-	int i;
-	struct packet_data *pkt;
-
-	pkt = kzalloc(sizeof(struct packet_data), GFP_KERNEL);
-	if (!pkt)
-		goto no_pkt;
-
-	pkt->frames = frames;
-	pkt->w_bio = bio_kmalloc(frames, GFP_KERNEL);
-	if (!pkt->w_bio)
-		goto no_bio;
-
-	for (i = 0; i < frames / FRAMES_PER_PAGE; i++) {
-		pkt->pages[i] = alloc_page(GFP_KERNEL|__GFP_ZERO);
-		if (!pkt->pages[i])
-			goto no_page;
-	}
-
-	spin_lock_init(&pkt->lock);
-	bio_list_init(&pkt->orig_bios);
-
-	for (i = 0; i < frames; i++) {
-		pkt->r_bios[i] = bio_kmalloc(1, GFP_KERNEL);
-		if (!pkt->r_bios[i])
-			goto no_rd_bio;
-	}
-
-	return pkt;
-
-no_rd_bio:
-	for (i = 0; i < frames; i++)
-		kfree(pkt->r_bios[i]);
-no_page:
-	for (i = 0; i < frames / FRAMES_PER_PAGE; i++)
-		if (pkt->pages[i])
-			__free_page(pkt->pages[i]);
-	kfree(pkt->w_bio);
-no_bio:
-	kfree(pkt);
-no_pkt:
-	return NULL;
-}
-
-/*
- * Free a packet_data struct
- */
-static void pkt_free_packet_data(struct packet_data *pkt)
-{
-	int i;
-
-	for (i = 0; i < pkt->frames; i++)
-		kfree(pkt->r_bios[i]);
-	for (i = 0; i < pkt->frames / FRAMES_PER_PAGE; i++)
-		__free_page(pkt->pages[i]);
-	kfree(pkt->w_bio);
-	kfree(pkt);
-}
-
-static void pkt_shrink_pktlist(struct pktcdvd_device *pd)
-{
-	struct packet_data *pkt, *next;
-
-	BUG_ON(!list_empty(&pd->cdrw.pkt_active_list));
-
-	list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_free_list, list) {
-		pkt_free_packet_data(pkt);
-	}
-	INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
-}
-
-static int pkt_grow_pktlist(struct pktcdvd_device *pd, int nr_packets)
-{
-	struct packet_data *pkt;
-
-	BUG_ON(!list_empty(&pd->cdrw.pkt_free_list));
-
-	while (nr_packets > 0) {
-		pkt = pkt_alloc_packet_data(pd->settings.size >> 2);
-		if (!pkt) {
-			pkt_shrink_pktlist(pd);
-			return 0;
-		}
-		pkt->id = nr_packets;
-		pkt->pd = pd;
-		list_add(&pkt->list, &pd->cdrw.pkt_free_list);
-		nr_packets--;
-	}
-	return 1;
-}
-
-static inline struct pkt_rb_node *pkt_rbtree_next(struct pkt_rb_node *node)
-{
-	struct rb_node *n = rb_next(&node->rb_node);
-	if (!n)
-		return NULL;
-	return rb_entry(n, struct pkt_rb_node, rb_node);
-}
-
-static void pkt_rbtree_erase(struct pktcdvd_device *pd, struct pkt_rb_node *node)
-{
-	rb_erase(&node->rb_node, &pd->bio_queue);
-	mempool_free(node, &pd->rb_pool);
-	pd->bio_queue_size--;
-	BUG_ON(pd->bio_queue_size < 0);
-}
-
-/*
- * Find the first node in the pd->bio_queue rb tree with a starting sector >= s.
- */
-static struct pkt_rb_node *pkt_rbtree_find(struct pktcdvd_device *pd, sector_t s)
-{
-	struct rb_node *n = pd->bio_queue.rb_node;
-	struct rb_node *next;
-	struct pkt_rb_node *tmp;
-
-	if (!n) {
-		BUG_ON(pd->bio_queue_size > 0);
-		return NULL;
-	}
-
-	for (;;) {
-		tmp = rb_entry(n, struct pkt_rb_node, rb_node);
-		if (s <= tmp->bio->bi_iter.bi_sector)
-			next = n->rb_left;
-		else
-			next = n->rb_right;
-		if (!next)
-			break;
-		n = next;
-	}
-
-	if (s > tmp->bio->bi_iter.bi_sector) {
-		tmp = pkt_rbtree_next(tmp);
-		if (!tmp)
-			return NULL;
-	}
-	BUG_ON(s > tmp->bio->bi_iter.bi_sector);
-	return tmp;
-}
-
-/*
- * Insert a node into the pd->bio_queue rb tree.
- */
-static void pkt_rbtree_insert(struct pktcdvd_device *pd, struct pkt_rb_node *node)
-{
-	struct rb_node **p = &pd->bio_queue.rb_node;
-	struct rb_node *parent = NULL;
-	sector_t s = node->bio->bi_iter.bi_sector;
-	struct pkt_rb_node *tmp;
-
-	while (*p) {
-		parent = *p;
-		tmp = rb_entry(parent, struct pkt_rb_node, rb_node);
-		if (s < tmp->bio->bi_iter.bi_sector)
-			p = &(*p)->rb_left;
-		else
-			p = &(*p)->rb_right;
-	}
-	rb_link_node(&node->rb_node, parent, p);
-	rb_insert_color(&node->rb_node, &pd->bio_queue);
-	pd->bio_queue_size++;
-}
-
-/*
- * Send a packet_command to the underlying block device and
- * wait for completion.
- */
-static int pkt_generic_packet(struct pktcdvd_device *pd, struct packet_command *cgc)
-{
-	struct request_queue *q = bdev_get_queue(file_bdev(pd->bdev_file));
-	struct scsi_cmnd *scmd;
-	struct request *rq;
-	int ret = 0;
-
-	rq = scsi_alloc_request(q, (cgc->data_direction == CGC_DATA_WRITE) ?
-			     REQ_OP_DRV_OUT : REQ_OP_DRV_IN, 0);
-	if (IS_ERR(rq))
-		return PTR_ERR(rq);
-	scmd = blk_mq_rq_to_pdu(rq);
-
-	if (cgc->buflen) {
-		ret = blk_rq_map_kern(rq, cgc->buffer, cgc->buflen,
-				      GFP_NOIO);
-		if (ret)
-			goto out;
-	}
-
-	scmd->cmd_len = COMMAND_SIZE(cgc->cmd[0]);
-	memcpy(scmd->cmnd, cgc->cmd, CDROM_PACKET_SIZE);
-
-	rq->timeout = 60*HZ;
-	if (cgc->quiet)
-		rq->rq_flags |= RQF_QUIET;
-
-	blk_execute_rq(rq, false);
-	if (scmd->result)
-		ret = -EIO;
-out:
-	blk_mq_free_request(rq);
-	return ret;
-}
-
-static const char *sense_key_string(__u8 index)
-{
-	static const char * const info[] = {
-		"No sense", "Recovered error", "Not ready",
-		"Medium error", "Hardware error", "Illegal request",
-		"Unit attention", "Data protect", "Blank check",
-	};
-
-	return index < ARRAY_SIZE(info) ? info[index] : "INVALID";
-}
-
-/*
- * A generic sense dump / resolve mechanism should be implemented across
- * all ATAPI + SCSI devices.
- */
-static void pkt_dump_sense(struct pktcdvd_device *pd,
-			   struct packet_command *cgc)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct scsi_sense_hdr *sshdr = cgc->sshdr;
-
-	if (sshdr)
-		dev_err(ddev, "%*ph - sense %02x.%02x.%02x (%s)\n",
-			CDROM_PACKET_SIZE, cgc->cmd,
-			sshdr->sense_key, sshdr->asc, sshdr->ascq,
-			sense_key_string(sshdr->sense_key));
-	else
-		dev_err(ddev, "%*ph - no sense\n", CDROM_PACKET_SIZE, cgc->cmd);
-}
-
-/*
- * flush the drive cache to media
- */
-static int pkt_flush_cache(struct pktcdvd_device *pd)
-{
-	struct packet_command cgc;
-
-	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.cmd[0] = GPCMD_FLUSH_CACHE;
-	cgc.quiet = 1;
-
-	/*
-	 * the IMMED bit -- we default to not setting it, although that
-	 * would allow a much faster close, this is safer
-	 */
-#if 0
-	cgc.cmd[1] = 1 << 1;
-#endif
-	return pkt_generic_packet(pd, &cgc);
-}
-
-/*
- * speed is given as the normal factor, e.g. 4 for 4x
- */
-static noinline_for_stack int pkt_set_speed(struct pktcdvd_device *pd,
-				unsigned write_speed, unsigned read_speed)
-{
-	struct packet_command cgc;
-	struct scsi_sense_hdr sshdr;
-	int ret;
-
-	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sshdr = &sshdr;
-	cgc.cmd[0] = GPCMD_SET_SPEED;
-	put_unaligned_be16(read_speed, &cgc.cmd[2]);
-	put_unaligned_be16(write_speed, &cgc.cmd[4]);
-
-	ret = pkt_generic_packet(pd, &cgc);
-	if (ret)
-		pkt_dump_sense(pd, &cgc);
-
-	return ret;
-}
-
-/*
- * Queue a bio for processing by the low-level CD device. Must be called
- * from process context.
- */
-static void pkt_queue_bio(struct pktcdvd_device *pd, struct bio *bio)
-{
-	/*
-	 * Some CDRW drives can not handle writes larger than one packet,
-	 * even if the size is a multiple of the packet size.
-	 */
-	bio->bi_opf |= REQ_NOMERGE;
-
-	spin_lock(&pd->iosched.lock);
-	if (bio_data_dir(bio) == READ)
-		bio_list_add(&pd->iosched.read_queue, bio);
-	else
-		bio_list_add(&pd->iosched.write_queue, bio);
-	spin_unlock(&pd->iosched.lock);
-
-	atomic_set(&pd->iosched.attention, 1);
-	wake_up(&pd->wqueue);
-}
-
-/*
- * Process the queued read/write requests. This function handles special
- * requirements for CDRW drives:
- * - A cache flush command must be inserted before a read request if the
- *   previous request was a write.
- * - Switching between reading and writing is slow, so don't do it more often
- *   than necessary.
- * - Optimize for throughput at the expense of latency. This means that streaming
- *   writes will never be interrupted by a read, but if the drive has to seek
- *   before the next write, switch to reading instead if there are any pending
- *   read requests.
- * - Set the read speed according to current usage pattern. When only reading
- *   from the device, it's best to use the highest possible read speed, but
- *   when switching often between reading and writing, it's better to have the
- *   same read and write speeds.
- */
-static void pkt_iosched_process_queue(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-
-	if (atomic_read(&pd->iosched.attention) == 0)
-		return;
-	atomic_set(&pd->iosched.attention, 0);
-
-	for (;;) {
-		struct bio *bio;
-		int reads_queued, writes_queued;
-
-		spin_lock(&pd->iosched.lock);
-		reads_queued = !bio_list_empty(&pd->iosched.read_queue);
-		writes_queued = !bio_list_empty(&pd->iosched.write_queue);
-		spin_unlock(&pd->iosched.lock);
-
-		if (!reads_queued && !writes_queued)
-			break;
-
-		if (pd->iosched.writing) {
-			int need_write_seek = 1;
-			spin_lock(&pd->iosched.lock);
-			bio = bio_list_peek(&pd->iosched.write_queue);
-			spin_unlock(&pd->iosched.lock);
-			if (bio && (bio->bi_iter.bi_sector ==
-				    pd->iosched.last_write))
-				need_write_seek = 0;
-			if (need_write_seek && reads_queued) {
-				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
-					dev_dbg(ddev, "write, waiting\n");
-					break;
-				}
-				pkt_flush_cache(pd);
-				pd->iosched.writing = 0;
-			}
-		} else {
-			if (!reads_queued && writes_queued) {
-				if (atomic_read(&pd->cdrw.pending_bios) > 0) {
-					dev_dbg(ddev, "read, waiting\n");
-					break;
-				}
-				pd->iosched.writing = 1;
-			}
-		}
-
-		spin_lock(&pd->iosched.lock);
-		if (pd->iosched.writing)
-			bio = bio_list_pop(&pd->iosched.write_queue);
-		else
-			bio = bio_list_pop(&pd->iosched.read_queue);
-		spin_unlock(&pd->iosched.lock);
-
-		if (!bio)
-			continue;
-
-		if (bio_data_dir(bio) == READ)
-			pd->iosched.successive_reads +=
-				bio->bi_iter.bi_size >> 10;
-		else {
-			pd->iosched.successive_reads = 0;
-			pd->iosched.last_write = bio_end_sector(bio);
-		}
-		if (pd->iosched.successive_reads >= HI_SPEED_SWITCH) {
-			if (pd->read_speed == pd->write_speed) {
-				pd->read_speed = MAX_SPEED;
-				pkt_set_speed(pd, pd->write_speed, pd->read_speed);
-			}
-		} else {
-			if (pd->read_speed != pd->write_speed) {
-				pd->read_speed = pd->write_speed;
-				pkt_set_speed(pd, pd->write_speed, pd->read_speed);
-			}
-		}
-
-		atomic_inc(&pd->cdrw.pending_bios);
-		submit_bio_noacct(bio);
-	}
-}
-
-/*
- * Special care is needed if the underlying block device has a small
- * max_phys_segments value.
- */
-static int pkt_set_segment_merging(struct pktcdvd_device *pd, struct request_queue *q)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-
-	if ((pd->settings.size << 9) / CD_FRAMESIZE <= queue_max_segments(q)) {
-		/*
-		 * The cdrom device can handle one segment/frame
-		 */
-		clear_bit(PACKET_MERGE_SEGS, &pd->flags);
-		return 0;
-	}
-
-	if ((pd->settings.size << 9) / PAGE_SIZE <= queue_max_segments(q)) {
-		/*
-		 * We can handle this case at the expense of some extra memory
-		 * copies during write operations
-		 */
-		set_bit(PACKET_MERGE_SEGS, &pd->flags);
-		return 0;
-	}
-
-	dev_err(ddev, "cdrom max_phys_segments too small\n");
-	return -EIO;
-}
-
-static void pkt_end_io_read(struct bio *bio)
-{
-	struct packet_data *pkt = bio->bi_private;
-	struct pktcdvd_device *pd = pkt->pd;
-	BUG_ON(!pd);
-
-	dev_dbg(disk_to_dev(pd->disk), "bio=%p sec0=%llx sec=%llx err=%d\n",
-		bio, pkt->sector, bio->bi_iter.bi_sector, bio->bi_status);
-
-	if (bio->bi_status)
-		atomic_inc(&pkt->io_errors);
-	bio_uninit(bio);
-	if (atomic_dec_and_test(&pkt->io_wait)) {
-		atomic_inc(&pkt->run_sm);
-		wake_up(&pd->wqueue);
-	}
-	pkt_bio_finished(pd);
-}
-
-static void pkt_end_io_packet_write(struct bio *bio)
-{
-	struct packet_data *pkt = bio->bi_private;
-	struct pktcdvd_device *pd = pkt->pd;
-	BUG_ON(!pd);
-
-	dev_dbg(disk_to_dev(pd->disk), "id=%d, err=%d\n", pkt->id, bio->bi_status);
-
-	pd->stats.pkt_ended++;
-
-	bio_uninit(bio);
-	pkt_bio_finished(pd);
-	atomic_dec(&pkt->io_wait);
-	atomic_inc(&pkt->run_sm);
-	wake_up(&pd->wqueue);
-}
-
-/*
- * Schedule reads for the holes in a packet
- */
-static void pkt_gather_data(struct pktcdvd_device *pd, struct packet_data *pkt)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	int frames_read = 0;
-	struct bio *bio;
-	int f;
-	char written[PACKET_MAX_SIZE];
-
-	BUG_ON(bio_list_empty(&pkt->orig_bios));
-
-	atomic_set(&pkt->io_wait, 0);
-	atomic_set(&pkt->io_errors, 0);
-
-	/*
-	 * Figure out which frames we need to read before we can write.
-	 */
-	memset(written, 0, sizeof(written));
-	spin_lock(&pkt->lock);
-	bio_list_for_each(bio, &pkt->orig_bios) {
-		int first_frame = (bio->bi_iter.bi_sector - pkt->sector) /
-			(CD_FRAMESIZE >> 9);
-		int num_frames = bio->bi_iter.bi_size / CD_FRAMESIZE;
-		pd->stats.secs_w += num_frames * (CD_FRAMESIZE >> 9);
-		BUG_ON(first_frame < 0);
-		BUG_ON(first_frame + num_frames > pkt->frames);
-		for (f = first_frame; f < first_frame + num_frames; f++)
-			written[f] = 1;
-	}
-	spin_unlock(&pkt->lock);
-
-	if (pkt->cache_valid) {
-		dev_dbg(ddev, "zone %llx cached\n", pkt->sector);
-		goto out_account;
-	}
-
-	/*
-	 * Schedule reads for missing parts of the packet.
-	 */
-	for (f = 0; f < pkt->frames; f++) {
-		int p, offset;
-
-		if (written[f])
-			continue;
-
-		bio = pkt->r_bios[f];
-		bio_init(bio, file_bdev(pd->bdev_file), bio->bi_inline_vecs, 1,
-			 REQ_OP_READ);
-		bio->bi_iter.bi_sector = pkt->sector + f * (CD_FRAMESIZE >> 9);
-		bio->bi_end_io = pkt_end_io_read;
-		bio->bi_private = pkt;
-
-		p = (f * CD_FRAMESIZE) / PAGE_SIZE;
-		offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
-		dev_dbg(ddev, "Adding frame %d, page:%p offs:%d\n", f,
-			pkt->pages[p], offset);
-		if (!bio_add_page(bio, pkt->pages[p], CD_FRAMESIZE, offset))
-			BUG();
-
-		atomic_inc(&pkt->io_wait);
-		pkt_queue_bio(pd, bio);
-		frames_read++;
-	}
-
-out_account:
-	dev_dbg(ddev, "need %d frames for zone %llx\n", frames_read, pkt->sector);
-	pd->stats.pkt_started++;
-	pd->stats.secs_rg += frames_read * (CD_FRAMESIZE >> 9);
-}
-
-/*
- * Find a packet matching zone, or the least recently used packet if
- * there is no match.
- */
-static struct packet_data *pkt_get_packet_data(struct pktcdvd_device *pd, int zone)
-{
-	struct packet_data *pkt;
-
-	list_for_each_entry(pkt, &pd->cdrw.pkt_free_list, list) {
-		if (pkt->sector == zone || pkt->list.next == &pd->cdrw.pkt_free_list) {
-			list_del_init(&pkt->list);
-			if (pkt->sector != zone)
-				pkt->cache_valid = 0;
-			return pkt;
-		}
-	}
-	BUG();
-	return NULL;
-}
-
-static void pkt_put_packet_data(struct pktcdvd_device *pd, struct packet_data *pkt)
-{
-	if (pkt->cache_valid) {
-		list_add(&pkt->list, &pd->cdrw.pkt_free_list);
-	} else {
-		list_add_tail(&pkt->list, &pd->cdrw.pkt_free_list);
-	}
-}
-
-static inline void pkt_set_state(struct device *ddev, struct packet_data *pkt,
-				 enum packet_data_state state)
-{
-	static const char *state_name[] = {
-		"IDLE", "WAITING", "READ_WAIT", "WRITE_WAIT", "RECOVERY", "FINISHED"
-	};
-	enum packet_data_state old_state = pkt->state;
-
-	dev_dbg(ddev, "pkt %2d : s=%6llx %s -> %s\n",
-		pkt->id, pkt->sector, state_name[old_state], state_name[state]);
-
-	pkt->state = state;
-}
-
-/*
- * Scan the work queue to see if we can start a new packet.
- * returns non-zero if any work was done.
- */
-static int pkt_handle_queue(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct packet_data *pkt, *p;
-	struct bio *bio = NULL;
-	sector_t zone = 0; /* Suppress gcc warning */
-	struct pkt_rb_node *node, *first_node;
-	struct rb_node *n;
-
-	atomic_set(&pd->scan_queue, 0);
-
-	if (list_empty(&pd->cdrw.pkt_free_list)) {
-		dev_dbg(ddev, "no pkt\n");
-		return 0;
-	}
-
-	/*
-	 * Try to find a zone we are not already working on.
-	 */
-	spin_lock(&pd->lock);
-	first_node = pkt_rbtree_find(pd, pd->current_sector);
-	if (!first_node) {
-		n = rb_first(&pd->bio_queue);
-		if (n)
-			first_node = rb_entry(n, struct pkt_rb_node, rb_node);
-	}
-	node = first_node;
-	while (node) {
-		bio = node->bio;
-		zone = get_zone(bio->bi_iter.bi_sector, pd);
-		list_for_each_entry(p, &pd->cdrw.pkt_active_list, list) {
-			if (p->sector == zone) {
-				bio = NULL;
-				goto try_next_bio;
-			}
-		}
-		break;
-try_next_bio:
-		node = pkt_rbtree_next(node);
-		if (!node) {
-			n = rb_first(&pd->bio_queue);
-			if (n)
-				node = rb_entry(n, struct pkt_rb_node, rb_node);
-		}
-		if (node == first_node)
-			node = NULL;
-	}
-	spin_unlock(&pd->lock);
-	if (!bio) {
-		dev_dbg(ddev, "no bio\n");
-		return 0;
-	}
-
-	pkt = pkt_get_packet_data(pd, zone);
-
-	pd->current_sector = zone + pd->settings.size;
-	pkt->sector = zone;
-	BUG_ON(pkt->frames != pd->settings.size >> 2);
-	pkt->write_size = 0;
-
-	/*
-	 * Scan work queue for bios in the same zone and link them
-	 * to this packet.
-	 */
-	spin_lock(&pd->lock);
-	dev_dbg(ddev, "looking for zone %llx\n", zone);
-	while ((node = pkt_rbtree_find(pd, zone)) != NULL) {
-		sector_t tmp = get_zone(node->bio->bi_iter.bi_sector, pd);
-
-		bio = node->bio;
-		dev_dbg(ddev, "found zone=%llx\n", tmp);
-		if (tmp != zone)
-			break;
-		pkt_rbtree_erase(pd, node);
-		spin_lock(&pkt->lock);
-		bio_list_add(&pkt->orig_bios, bio);
-		pkt->write_size += bio->bi_iter.bi_size / CD_FRAMESIZE;
-		spin_unlock(&pkt->lock);
-	}
-	/* check write congestion marks, and if bio_queue_size is
-	 * below, wake up any waiters
-	 */
-	if (pd->congested &&
-	    pd->bio_queue_size <= pd->write_congestion_off) {
-		pd->congested = false;
-		wake_up_var(&pd->congested);
-	}
-	spin_unlock(&pd->lock);
-
-	pkt->sleep_time = max(PACKET_WAIT_TIME, 1);
-	pkt_set_state(ddev, pkt, PACKET_WAITING_STATE);
-	atomic_set(&pkt->run_sm, 1);
-
-	spin_lock(&pd->cdrw.active_list_lock);
-	list_add(&pkt->list, &pd->cdrw.pkt_active_list);
-	spin_unlock(&pd->cdrw.active_list_lock);
-
-	return 1;
-}
-
-/**
- * bio_list_copy_data - copy contents of data buffers from one chain of bios to
- * another
- * @src: source bio list
- * @dst: destination bio list
- *
- * Stops when it reaches the end of either the @src list or @dst list - that is,
- * copies min(src->bi_size, dst->bi_size) bytes (or the equivalent for lists of
- * bios).
- */
-static void bio_list_copy_data(struct bio *dst, struct bio *src)
-{
-	struct bvec_iter src_iter = src->bi_iter;
-	struct bvec_iter dst_iter = dst->bi_iter;
-
-	while (1) {
-		if (!src_iter.bi_size) {
-			src = src->bi_next;
-			if (!src)
-				break;
-
-			src_iter = src->bi_iter;
-		}
-
-		if (!dst_iter.bi_size) {
-			dst = dst->bi_next;
-			if (!dst)
-				break;
-
-			dst_iter = dst->bi_iter;
-		}
-
-		bio_copy_data_iter(dst, &dst_iter, src, &src_iter);
-	}
-}
-
-/*
- * Assemble a bio to write one packet and queue the bio for processing
- * by the underlying block device.
- */
-static void pkt_start_write(struct pktcdvd_device *pd, struct packet_data *pkt)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	int f;
-
-	bio_init(pkt->w_bio, file_bdev(pd->bdev_file), pkt->w_bio->bi_inline_vecs,
-		 pkt->frames, REQ_OP_WRITE);
-	pkt->w_bio->bi_iter.bi_sector = pkt->sector;
-	pkt->w_bio->bi_end_io = pkt_end_io_packet_write;
-	pkt->w_bio->bi_private = pkt;
-
-	/* XXX: locking? */
-	for (f = 0; f < pkt->frames; f++) {
-		struct page *page = pkt->pages[(f * CD_FRAMESIZE) / PAGE_SIZE];
-		unsigned offset = (f * CD_FRAMESIZE) % PAGE_SIZE;
-
-		if (!bio_add_page(pkt->w_bio, page, CD_FRAMESIZE, offset))
-			BUG();
-	}
-	dev_dbg(ddev, "vcnt=%d\n", pkt->w_bio->bi_vcnt);
-
-	/*
-	 * Fill-in bvec with data from orig_bios.
-	 */
-	spin_lock(&pkt->lock);
-	bio_list_copy_data(pkt->w_bio, pkt->orig_bios.head);
-
-	pkt_set_state(ddev, pkt, PACKET_WRITE_WAIT_STATE);
-	spin_unlock(&pkt->lock);
-
-	dev_dbg(ddev, "Writing %d frames for zone %llx\n", pkt->write_size, pkt->sector);
-
-	if (test_bit(PACKET_MERGE_SEGS, &pd->flags) || (pkt->write_size < pkt->frames))
-		pkt->cache_valid = 1;
-	else
-		pkt->cache_valid = 0;
-
-	/* Start the write request */
-	atomic_set(&pkt->io_wait, 1);
-	pkt_queue_bio(pd, pkt->w_bio);
-}
-
-static void pkt_finish_packet(struct packet_data *pkt, blk_status_t status)
-{
-	struct bio *bio;
-
-	if (status)
-		pkt->cache_valid = 0;
-
-	/* Finish all bios corresponding to this packet */
-	while ((bio = bio_list_pop(&pkt->orig_bios))) {
-		bio->bi_status = status;
-		bio_endio(bio);
-	}
-}
-
-static void pkt_run_state_machine(struct pktcdvd_device *pd, struct packet_data *pkt)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-
-	dev_dbg(ddev, "pkt %d\n", pkt->id);
-
-	for (;;) {
-		switch (pkt->state) {
-		case PACKET_WAITING_STATE:
-			if ((pkt->write_size < pkt->frames) && (pkt->sleep_time > 0))
-				return;
-
-			pkt->sleep_time = 0;
-			pkt_gather_data(pd, pkt);
-			pkt_set_state(ddev, pkt, PACKET_READ_WAIT_STATE);
-			break;
-
-		case PACKET_READ_WAIT_STATE:
-			if (atomic_read(&pkt->io_wait) > 0)
-				return;
-
-			if (atomic_read(&pkt->io_errors) > 0) {
-				pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE);
-			} else {
-				pkt_start_write(pd, pkt);
-			}
-			break;
-
-		case PACKET_WRITE_WAIT_STATE:
-			if (atomic_read(&pkt->io_wait) > 0)
-				return;
-
-			if (!pkt->w_bio->bi_status) {
-				pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE);
-			} else {
-				pkt_set_state(ddev, pkt, PACKET_RECOVERY_STATE);
-			}
-			break;
-
-		case PACKET_RECOVERY_STATE:
-			dev_dbg(ddev, "No recovery possible\n");
-			pkt_set_state(ddev, pkt, PACKET_FINISHED_STATE);
-			break;
-
-		case PACKET_FINISHED_STATE:
-			pkt_finish_packet(pkt, pkt->w_bio->bi_status);
-			return;
-
-		default:
-			BUG();
-			break;
-		}
-	}
-}
-
-static void pkt_handle_packets(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct packet_data *pkt, *next;
-
-	/*
-	 * Run state machine for active packets
-	 */
-	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
-		if (atomic_read(&pkt->run_sm) > 0) {
-			atomic_set(&pkt->run_sm, 0);
-			pkt_run_state_machine(pd, pkt);
-		}
-	}
-
-	/*
-	 * Move no longer active packets to the free list
-	 */
-	spin_lock(&pd->cdrw.active_list_lock);
-	list_for_each_entry_safe(pkt, next, &pd->cdrw.pkt_active_list, list) {
-		if (pkt->state == PACKET_FINISHED_STATE) {
-			list_del(&pkt->list);
-			pkt_put_packet_data(pd, pkt);
-			pkt_set_state(ddev, pkt, PACKET_IDLE_STATE);
-			atomic_set(&pd->scan_queue, 1);
-		}
-	}
-	spin_unlock(&pd->cdrw.active_list_lock);
-}
-
-/*
- * kcdrwd is woken up when writes have been queued for one of our
- * registered devices
- */
-static int kcdrwd(void *foobar)
-{
-	struct pktcdvd_device *pd = foobar;
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct packet_data *pkt;
-	int states[PACKET_NUM_STATES];
-	long min_sleep_time, residue;
-
-	set_user_nice(current, MIN_NICE);
-	set_freezable();
-
-	for (;;) {
-		DECLARE_WAITQUEUE(wait, current);
-
-		/*
-		 * Wait until there is something to do
-		 */
-		add_wait_queue(&pd->wqueue, &wait);
-		for (;;) {
-			set_current_state(TASK_INTERRUPTIBLE);
-
-			/* Check if we need to run pkt_handle_queue */
-			if (atomic_read(&pd->scan_queue) > 0)
-				goto work_to_do;
-
-			/* Check if we need to run the state machine for some packet */
-			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
-				if (atomic_read(&pkt->run_sm) > 0)
-					goto work_to_do;
-			}
-
-			/* Check if we need to process the iosched queues */
-			if (atomic_read(&pd->iosched.attention) != 0)
-				goto work_to_do;
-
-			/* Otherwise, go to sleep */
-			pkt_count_states(pd, states);
-			dev_dbg(ddev, "i:%d ow:%d rw:%d ww:%d rec:%d fin:%d\n",
-				states[0], states[1], states[2], states[3], states[4], states[5]);
-
-			min_sleep_time = MAX_SCHEDULE_TIMEOUT;
-			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
-				if (pkt->sleep_time && pkt->sleep_time < min_sleep_time)
-					min_sleep_time = pkt->sleep_time;
-			}
-
-			dev_dbg(ddev, "sleeping\n");
-			residue = schedule_timeout(min_sleep_time);
-			dev_dbg(ddev, "wake up\n");
-
-			/* make swsusp happy with our thread */
-			try_to_freeze();
-
-			list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
-				if (!pkt->sleep_time)
-					continue;
-				pkt->sleep_time -= min_sleep_time - residue;
-				if (pkt->sleep_time <= 0) {
-					pkt->sleep_time = 0;
-					atomic_inc(&pkt->run_sm);
-				}
-			}
-
-			if (kthread_should_stop())
-				break;
-		}
-work_to_do:
-		set_current_state(TASK_RUNNING);
-		remove_wait_queue(&pd->wqueue, &wait);
-
-		if (kthread_should_stop())
-			break;
-
-		/*
-		 * if pkt_handle_queue returns true, we can queue
-		 * another request.
-		 */
-		while (pkt_handle_queue(pd))
-			;
-
-		/*
-		 * Handle packet state machine
-		 */
-		pkt_handle_packets(pd);
-
-		/*
-		 * Handle iosched queues
-		 */
-		pkt_iosched_process_queue(pd);
-	}
-
-	return 0;
-}
-
-static void pkt_print_settings(struct pktcdvd_device *pd)
-{
-	dev_info(disk_to_dev(pd->disk), "%s packets, %u blocks, Mode-%c disc\n",
-		 pd->settings.fp ? "Fixed" : "Variable",
-		 pd->settings.size >> 2,
-		 pd->settings.block_mode == 8 ? '1' : '2');
-}
-
-static int pkt_mode_sense(struct pktcdvd_device *pd, struct packet_command *cgc, int page_code, int page_control)
-{
-	memset(cgc->cmd, 0, sizeof(cgc->cmd));
-
-	cgc->cmd[0] = GPCMD_MODE_SENSE_10;
-	cgc->cmd[2] = page_code | (page_control << 6);
-	put_unaligned_be16(cgc->buflen, &cgc->cmd[7]);
-	cgc->data_direction = CGC_DATA_READ;
-	return pkt_generic_packet(pd, cgc);
-}
-
-static int pkt_mode_select(struct pktcdvd_device *pd, struct packet_command *cgc)
-{
-	memset(cgc->cmd, 0, sizeof(cgc->cmd));
-	memset(cgc->buffer, 0, 2);
-	cgc->cmd[0] = GPCMD_MODE_SELECT_10;
-	cgc->cmd[1] = 0x10;		/* PF */
-	put_unaligned_be16(cgc->buflen, &cgc->cmd[7]);
-	cgc->data_direction = CGC_DATA_WRITE;
-	return pkt_generic_packet(pd, cgc);
-}
-
-static int pkt_get_disc_info(struct pktcdvd_device *pd, disc_information *di)
-{
-	struct packet_command cgc;
-	int ret;
-
-	/* set up command and get the disc info */
-	init_cdrom_command(&cgc, di, sizeof(*di), CGC_DATA_READ);
-	cgc.cmd[0] = GPCMD_READ_DISC_INFO;
-	cgc.cmd[8] = cgc.buflen = 2;
-	cgc.quiet = 1;
-
-	ret = pkt_generic_packet(pd, &cgc);
-	if (ret)
-		return ret;
-
-	/* not all drives have the same disc_info length, so requeue
-	 * packet with the length the drive tells us it can supply
-	 */
-	cgc.buflen = be16_to_cpu(di->disc_information_length) +
-		     sizeof(di->disc_information_length);
-
-	if (cgc.buflen > sizeof(disc_information))
-		cgc.buflen = sizeof(disc_information);
-
-	cgc.cmd[8] = cgc.buflen;
-	return pkt_generic_packet(pd, &cgc);
-}
-
-static int pkt_get_track_info(struct pktcdvd_device *pd, __u16 track, __u8 type, track_information *ti)
-{
-	struct packet_command cgc;
-	int ret;
-
-	init_cdrom_command(&cgc, ti, 8, CGC_DATA_READ);
-	cgc.cmd[0] = GPCMD_READ_TRACK_RZONE_INFO;
-	cgc.cmd[1] = type & 3;
-	put_unaligned_be16(track, &cgc.cmd[4]);
-	cgc.cmd[8] = 8;
-	cgc.quiet = 1;
-
-	ret = pkt_generic_packet(pd, &cgc);
-	if (ret)
-		return ret;
-
-	cgc.buflen = be16_to_cpu(ti->track_information_length) +
-		     sizeof(ti->track_information_length);
-
-	if (cgc.buflen > sizeof(track_information))
-		cgc.buflen = sizeof(track_information);
-
-	cgc.cmd[8] = cgc.buflen;
-	return pkt_generic_packet(pd, &cgc);
-}
-
-static noinline_for_stack int pkt_get_last_written(struct pktcdvd_device *pd,
-						long *last_written)
-{
-	disc_information di;
-	track_information ti;
-	__u32 last_track;
-	int ret;
-
-	ret = pkt_get_disc_info(pd, &di);
-	if (ret)
-		return ret;
-
-	last_track = (di.last_track_msb << 8) | di.last_track_lsb;
-	ret = pkt_get_track_info(pd, last_track, 1, &ti);
-	if (ret)
-		return ret;
-
-	/* if this track is blank, try the previous. */
-	if (ti.blank) {
-		last_track--;
-		ret = pkt_get_track_info(pd, last_track, 1, &ti);
-		if (ret)
-			return ret;
-	}
-
-	/* if last recorded field is valid, return it. */
-	if (ti.lra_v) {
-		*last_written = be32_to_cpu(ti.last_rec_address);
-	} else {
-		/* make it up instead */
-		*last_written = be32_to_cpu(ti.track_start) +
-				be32_to_cpu(ti.track_size);
-		if (ti.free_blocks)
-			*last_written -= (be32_to_cpu(ti.free_blocks) + 7);
-	}
-	return 0;
-}
-
-/*
- * write mode select package based on pd->settings
- */
-static noinline_for_stack int pkt_set_write_settings(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct packet_command cgc;
-	struct scsi_sense_hdr sshdr;
-	write_param_page *wp;
-	char buffer[128];
-	int ret, size;
-
-	/* doesn't apply to DVD+RW or DVD-RAM */
-	if ((pd->mmc3_profile == 0x1a) || (pd->mmc3_profile == 0x12))
-		return 0;
-
-	memset(buffer, 0, sizeof(buffer));
-	init_cdrom_command(&cgc, buffer, sizeof(*wp), CGC_DATA_READ);
-	cgc.sshdr = &sshdr;
-	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
-	if (ret) {
-		pkt_dump_sense(pd, &cgc);
-		return ret;
-	}
-
-	size = 2 + get_unaligned_be16(&buffer[0]);
-	pd->mode_offset = get_unaligned_be16(&buffer[6]);
-	if (size > sizeof(buffer))
-		size = sizeof(buffer);
-
-	/*
-	 * now get it all
-	 */
-	init_cdrom_command(&cgc, buffer, size, CGC_DATA_READ);
-	cgc.sshdr = &sshdr;
-	ret = pkt_mode_sense(pd, &cgc, GPMODE_WRITE_PARMS_PAGE, 0);
-	if (ret) {
-		pkt_dump_sense(pd, &cgc);
-		return ret;
-	}
-
-	/*
-	 * write page is offset header + block descriptor length
-	 */
-	wp = (write_param_page *) &buffer[sizeof(struct mode_page_header) + pd->mode_offset];
-
-	wp->fp = pd->settings.fp;
-	wp->track_mode = pd->settings.track_mode;
-	wp->write_type = pd->settings.write_type;
-	wp->data_block_type = pd->settings.block_mode;
-
-	wp->multi_session = 0;
-
-#ifdef PACKET_USE_LS
-	wp->link_size = 7;
-	wp->ls_v = 1;
-#endif
-
-	if (wp->data_block_type == PACKET_BLOCK_MODE1) {
-		wp->session_format = 0;
-		wp->subhdr2 = 0x20;
-	} else if (wp->data_block_type == PACKET_BLOCK_MODE2) {
-		wp->session_format = 0x20;
-		wp->subhdr2 = 8;
-#if 0
-		wp->mcn[0] = 0x80;
-		memcpy(&wp->mcn[1], PACKET_MCN, sizeof(wp->mcn) - 1);
-#endif
-	} else {
-		/*
-		 * paranoia
-		 */
-		dev_err(ddev, "write mode wrong %d\n", wp->data_block_type);
-		return 1;
-	}
-	wp->packet_size = cpu_to_be32(pd->settings.size >> 2);
-
-	cgc.buflen = cgc.cmd[8] = size;
-	ret = pkt_mode_select(pd, &cgc);
-	if (ret) {
-		pkt_dump_sense(pd, &cgc);
-		return ret;
-	}
-
-	pkt_print_settings(pd);
-	return 0;
-}
-
-/*
- * 1 -- we can write to this track, 0 -- we can't
- */
-static int pkt_writable_track(struct pktcdvd_device *pd, track_information *ti)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-
-	switch (pd->mmc3_profile) {
-		case 0x1a: /* DVD+RW */
-		case 0x12: /* DVD-RAM */
-			/* The track is always writable on DVD+RW/DVD-RAM */
-			return 1;
-		default:
-			break;
-	}
-
-	if (!ti->packet || !ti->fp)
-		return 0;
-
-	/*
-	 * "good" settings as per Mt Fuji.
-	 */
-	if (ti->rt == 0 && ti->blank == 0)
-		return 1;
-
-	if (ti->rt == 0 && ti->blank == 1)
-		return 1;
-
-	if (ti->rt == 1 && ti->blank == 0)
-		return 1;
-
-	dev_err(ddev, "bad state %d-%d-%d\n", ti->rt, ti->blank, ti->packet);
-	return 0;
-}
-
-/*
- * 1 -- we can write to this disc, 0 -- we can't
- */
-static int pkt_writable_disc(struct pktcdvd_device *pd, disc_information *di)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-
-	switch (pd->mmc3_profile) {
-		case 0x0a: /* CD-RW */
-		case 0xffff: /* MMC3 not supported */
-			break;
-		case 0x1a: /* DVD+RW */
-		case 0x13: /* DVD-RW */
-		case 0x12: /* DVD-RAM */
-			return 1;
-		default:
-			dev_dbg(ddev, "Wrong disc profile (%x)\n", pd->mmc3_profile);
-			return 0;
-	}
-
-	/*
-	 * for disc type 0xff we should probably reserve a new track.
-	 * but i'm not sure, should we leave this to user apps? probably.
-	 */
-	if (di->disc_type == 0xff) {
-		dev_notice(ddev, "unknown disc - no track?\n");
-		return 0;
-	}
-
-	if (di->disc_type != 0x20 && di->disc_type != 0) {
-		dev_err(ddev, "wrong disc type (%x)\n", di->disc_type);
-		return 0;
-	}
-
-	if (di->erasable == 0) {
-		dev_err(ddev, "disc not erasable\n");
-		return 0;
-	}
-
-	if (di->border_status == PACKET_SESSION_RESERVED) {
-		dev_err(ddev, "can't write to last track (reserved)\n");
-		return 0;
-	}
-
-	return 1;
-}
-
-static noinline_for_stack int pkt_probe_settings(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct packet_command cgc;
-	unsigned char buf[12];
-	disc_information di;
-	track_information ti;
-	int ret, track;
-
-	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
-	cgc.cmd[0] = GPCMD_GET_CONFIGURATION;
-	cgc.cmd[8] = 8;
-	ret = pkt_generic_packet(pd, &cgc);
-	pd->mmc3_profile = ret ? 0xffff : get_unaligned_be16(&buf[6]);
-
-	memset(&di, 0, sizeof(disc_information));
-	memset(&ti, 0, sizeof(track_information));
-
-	ret = pkt_get_disc_info(pd, &di);
-	if (ret) {
-		dev_err(ddev, "failed get_disc\n");
-		return ret;
-	}
-
-	if (!pkt_writable_disc(pd, &di))
-		return -EROFS;
-
-	pd->type = di.erasable ? PACKET_CDRW : PACKET_CDR;
-
-	track = 1; /* (di.last_track_msb << 8) | di.last_track_lsb; */
-	ret = pkt_get_track_info(pd, track, 1, &ti);
-	if (ret) {
-		dev_err(ddev, "failed get_track\n");
-		return ret;
-	}
-
-	if (!pkt_writable_track(pd, &ti)) {
-		dev_err(ddev, "can't write to this track\n");
-		return -EROFS;
-	}
-
-	/*
-	 * we keep packet size in 512 byte units, makes it easier to
-	 * deal with request calculations.
-	 */
-	pd->settings.size = be32_to_cpu(ti.fixed_packet_size) << 2;
-	if (pd->settings.size == 0) {
-		dev_notice(ddev, "detected zero packet size!\n");
-		return -ENXIO;
-	}
-	if (pd->settings.size > PACKET_MAX_SECTORS) {
-		dev_err(ddev, "packet size is too big\n");
-		return -EROFS;
-	}
-	pd->settings.fp = ti.fp;
-	pd->offset = (be32_to_cpu(ti.track_start) << 2) & (pd->settings.size - 1);
-
-	if (ti.nwa_v) {
-		pd->nwa = be32_to_cpu(ti.next_writable);
-		set_bit(PACKET_NWA_VALID, &pd->flags);
-	}
-
-	/*
-	 * in theory we could use lra on -RW media as well and just zero
-	 * blocks that haven't been written yet, but in practice that
-	 * is just a no-go. we'll use that for -R, naturally.
-	 */
-	if (ti.lra_v) {
-		pd->lra = be32_to_cpu(ti.last_rec_address);
-		set_bit(PACKET_LRA_VALID, &pd->flags);
-	} else {
-		pd->lra = 0xffffffff;
-		set_bit(PACKET_LRA_VALID, &pd->flags);
-	}
-
-	/*
-	 * fine for now
-	 */
-	pd->settings.link_loss = 7;
-	pd->settings.write_type = 0;	/* packet */
-	pd->settings.track_mode = ti.track_mode;
-
-	/*
-	 * mode1 or mode2 disc
-	 */
-	switch (ti.data_mode) {
-		case PACKET_MODE1:
-			pd->settings.block_mode = PACKET_BLOCK_MODE1;
-			break;
-		case PACKET_MODE2:
-			pd->settings.block_mode = PACKET_BLOCK_MODE2;
-			break;
-		default:
-			dev_err(ddev, "unknown data mode\n");
-			return -EROFS;
-	}
-	return 0;
-}
-
-/*
- * enable/disable write caching on drive
- */
-static noinline_for_stack int pkt_write_caching(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct packet_command cgc;
-	struct scsi_sense_hdr sshdr;
-	unsigned char buf[64];
-	bool set = IS_ENABLED(CONFIG_CDROM_PKTCDVD_WCACHE);
-	int ret;
-
-	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_READ);
-	cgc.sshdr = &sshdr;
-	cgc.buflen = pd->mode_offset + 12;
-
-	/*
-	 * caching mode page might not be there, so quiet this command
-	 */
-	cgc.quiet = 1;
-
-	ret = pkt_mode_sense(pd, &cgc, GPMODE_WCACHING_PAGE, 0);
-	if (ret)
-		return ret;
-
-	/*
-	 * use drive write caching -- we need deferred error handling to be
-	 * able to successfully recover with this option (drive will return good
-	 * status as soon as the cdb is validated).
-	 */
-	buf[pd->mode_offset + 10] |= (set << 2);
-
-	cgc.buflen = cgc.cmd[8] = 2 + get_unaligned_be16(&buf[0]);
-	ret = pkt_mode_select(pd, &cgc);
-	if (ret) {
-		dev_err(ddev, "write caching control failed\n");
-		pkt_dump_sense(pd, &cgc);
-	} else if (!ret && set)
-		dev_notice(ddev, "enabled write caching\n");
-	return ret;
-}
-
-static int pkt_lock_door(struct pktcdvd_device *pd, int lockflag)
-{
-	struct packet_command cgc;
-
-	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.cmd[0] = GPCMD_PREVENT_ALLOW_MEDIUM_REMOVAL;
-	cgc.cmd[4] = lockflag ? 1 : 0;
-	return pkt_generic_packet(pd, &cgc);
-}
-
-/*
- * Returns drive maximum write speed
- */
-static noinline_for_stack int pkt_get_max_speed(struct pktcdvd_device *pd,
-						unsigned *write_speed)
-{
-	struct packet_command cgc;
-	struct scsi_sense_hdr sshdr;
-	unsigned char buf[256+18];
-	unsigned char *cap_buf;
-	int ret, offset;
-
-	cap_buf = &buf[sizeof(struct mode_page_header) + pd->mode_offset];
-	init_cdrom_command(&cgc, buf, sizeof(buf), CGC_DATA_UNKNOWN);
-	cgc.sshdr = &sshdr;
-
-	ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
-	if (ret) {
-		cgc.buflen = pd->mode_offset + cap_buf[1] + 2 +
-			     sizeof(struct mode_page_header);
-		ret = pkt_mode_sense(pd, &cgc, GPMODE_CAPABILITIES_PAGE, 0);
-		if (ret) {
-			pkt_dump_sense(pd, &cgc);
-			return ret;
-		}
-	}
-
-	offset = 20;			    /* Obsoleted field, used by older drives */
-	if (cap_buf[1] >= 28)
-		offset = 28;		    /* Current write speed selected */
-	if (cap_buf[1] >= 30) {
-		/* If the drive reports at least one "Logical Unit Write
-		 * Speed Performance Descriptor Block", use the information
-		 * in the first block. (contains the highest speed)
-		 */
-		int num_spdb = get_unaligned_be16(&cap_buf[30]);
-		if (num_spdb > 0)
-			offset = 34;
-	}
-
-	*write_speed = get_unaligned_be16(&cap_buf[offset]);
-	return 0;
-}
-
-/* These tables from cdrecord - I don't have orange book */
-/* standard speed CD-RW (1-4x) */
-static char clv_to_speed[16] = {
-	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
-	   0, 2, 4, 6, 8, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
-};
-/* high speed CD-RW (-10x) */
-static char hs_clv_to_speed[16] = {
-	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
-	   0, 2, 4, 6, 10, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0
-};
-/* ultra high speed CD-RW */
-static char us_clv_to_speed[16] = {
-	/* 0  1  2  3  4  5  6  7  8  9 10 11 12 13 14 15 */
-	   0, 2, 4, 8, 0, 0,16, 0,24,32,40,48, 0, 0, 0, 0
-};
-
-/*
- * reads the maximum media speed from ATIP
- */
-static noinline_for_stack int pkt_media_speed(struct pktcdvd_device *pd,
-						unsigned *speed)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct packet_command cgc;
-	struct scsi_sense_hdr sshdr;
-	unsigned char buf[64];
-	unsigned int size, st, sp;
-	int ret;
-
-	init_cdrom_command(&cgc, buf, 2, CGC_DATA_READ);
-	cgc.sshdr = &sshdr;
-	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
-	cgc.cmd[1] = 2;
-	cgc.cmd[2] = 4; /* READ ATIP */
-	cgc.cmd[8] = 2;
-	ret = pkt_generic_packet(pd, &cgc);
-	if (ret) {
-		pkt_dump_sense(pd, &cgc);
-		return ret;
-	}
-	size = 2 + get_unaligned_be16(&buf[0]);
-	if (size > sizeof(buf))
-		size = sizeof(buf);
-
-	init_cdrom_command(&cgc, buf, size, CGC_DATA_READ);
-	cgc.sshdr = &sshdr;
-	cgc.cmd[0] = GPCMD_READ_TOC_PMA_ATIP;
-	cgc.cmd[1] = 2;
-	cgc.cmd[2] = 4;
-	cgc.cmd[8] = size;
-	ret = pkt_generic_packet(pd, &cgc);
-	if (ret) {
-		pkt_dump_sense(pd, &cgc);
-		return ret;
-	}
-
-	if (!(buf[6] & 0x40)) {
-		dev_notice(ddev, "disc type is not CD-RW\n");
-		return 1;
-	}
-	if (!(buf[6] & 0x4)) {
-		dev_notice(ddev, "A1 values on media are not valid, maybe not CDRW?\n");
-		return 1;
-	}
-
-	st = (buf[6] >> 3) & 0x7; /* disc sub-type */
-
-	sp = buf[16] & 0xf; /* max speed from ATIP A1 field */
-
-	/* Info from cdrecord */
-	switch (st) {
-		case 0: /* standard speed */
-			*speed = clv_to_speed[sp];
-			break;
-		case 1: /* high speed */
-			*speed = hs_clv_to_speed[sp];
-			break;
-		case 2: /* ultra high speed */
-			*speed = us_clv_to_speed[sp];
-			break;
-		default:
-			dev_notice(ddev, "unknown disc sub-type %d\n", st);
-			return 1;
-	}
-	if (*speed) {
-		dev_info(ddev, "maximum media speed: %d\n", *speed);
-		return 0;
-	} else {
-		dev_notice(ddev, "unknown speed %d for sub-type %d\n", sp, st);
-		return 1;
-	}
-}
-
-static noinline_for_stack int pkt_perform_opc(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct packet_command cgc;
-	struct scsi_sense_hdr sshdr;
-	int ret;
-
-	dev_dbg(ddev, "Performing OPC\n");
-
-	init_cdrom_command(&cgc, NULL, 0, CGC_DATA_NONE);
-	cgc.sshdr = &sshdr;
-	cgc.timeout = 60*HZ;
-	cgc.cmd[0] = GPCMD_SEND_OPC;
-	cgc.cmd[1] = 1;
-	ret = pkt_generic_packet(pd, &cgc);
-	if (ret)
-		pkt_dump_sense(pd, &cgc);
-	return ret;
-}
-
-static int pkt_open_write(struct pktcdvd_device *pd)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	int ret;
-	unsigned int write_speed, media_write_speed, read_speed;
-
-	ret = pkt_probe_settings(pd);
-	if (ret) {
-		dev_dbg(ddev, "failed probe\n");
-		return ret;
-	}
-
-	ret = pkt_set_write_settings(pd);
-	if (ret) {
-		dev_notice(ddev, "failed saving write settings\n");
-		return -EIO;
-	}
-
-	pkt_write_caching(pd);
-
-	ret = pkt_get_max_speed(pd, &write_speed);
-	if (ret)
-		write_speed = 16 * 177;
-	switch (pd->mmc3_profile) {
-		case 0x13: /* DVD-RW */
-		case 0x1a: /* DVD+RW */
-		case 0x12: /* DVD-RAM */
-			dev_notice(ddev, "write speed %ukB/s\n", write_speed);
-			break;
-		default:
-			ret = pkt_media_speed(pd, &media_write_speed);
-			if (ret)
-				media_write_speed = 16;
-			write_speed = min(write_speed, media_write_speed * 177);
-			dev_notice(ddev, "write speed %ux\n", write_speed / 176);
-			break;
-	}
-	read_speed = write_speed;
-
-	ret = pkt_set_speed(pd, write_speed, read_speed);
-	if (ret) {
-		dev_notice(ddev, "couldn't set write speed\n");
-		return -EIO;
-	}
-	pd->write_speed = write_speed;
-	pd->read_speed = read_speed;
-
-	ret = pkt_perform_opc(pd);
-	if (ret)
-		dev_notice(ddev, "Optimum Power Calibration failed\n");
-
-	return 0;
-}
-
-/*
- * called at open time.
- */
-static int pkt_open_dev(struct pktcdvd_device *pd, bool write)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	int ret;
-	long lba;
-	struct request_queue *q;
-	struct file *bdev_file;
-
-	/*
-	 * We need to re-open the cdrom device without O_NONBLOCK to be able
-	 * to read/write from/to it. It is already opened in O_NONBLOCK mode
-	 * so open should not fail.
-	 */
-	bdev_file = bdev_file_open_by_dev(file_bdev(pd->bdev_file)->bd_dev,
-				       BLK_OPEN_READ, pd, NULL);
-	if (IS_ERR(bdev_file)) {
-		ret = PTR_ERR(bdev_file);
-		goto out;
-	}
-	pd->f_open_bdev = bdev_file;
-
-	ret = pkt_get_last_written(pd, &lba);
-	if (ret) {
-		dev_err(ddev, "pkt_get_last_written failed\n");
-		goto out_putdev;
-	}
-
-	set_capacity(pd->disk, lba << 2);
-	set_capacity_and_notify(file_bdev(pd->bdev_file)->bd_disk, lba << 2);
-
-	q = bdev_get_queue(file_bdev(pd->bdev_file));
-	if (write) {
-		ret = pkt_open_write(pd);
-		if (ret)
-			goto out_putdev;
-		set_bit(PACKET_WRITABLE, &pd->flags);
-	} else {
-		pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
-		clear_bit(PACKET_WRITABLE, &pd->flags);
-	}
-
-	ret = pkt_set_segment_merging(pd, q);
-	if (ret)
-		goto out_putdev;
-
-	if (write) {
-		if (!pkt_grow_pktlist(pd, CONFIG_CDROM_PKTCDVD_BUFFERS)) {
-			dev_err(ddev, "not enough memory for buffers\n");
-			ret = -ENOMEM;
-			goto out_putdev;
-		}
-		dev_info(ddev, "%lukB available on disc\n", lba << 1);
-	}
-	set_blocksize(bdev_file, CD_FRAMESIZE);
-
-	return 0;
-
-out_putdev:
-	fput(bdev_file);
-out:
-	return ret;
-}
-
-/*
- * called when the device is closed. makes sure that the device flushes
- * the internal cache before we close.
- */
-static void pkt_release_dev(struct pktcdvd_device *pd, int flush)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-
-	if (flush && pkt_flush_cache(pd))
-		dev_notice(ddev, "not flushing cache\n");
-
-	pkt_lock_door(pd, 0);
-
-	pkt_set_speed(pd, MAX_SPEED, MAX_SPEED);
-	fput(pd->f_open_bdev);
-	pd->f_open_bdev = NULL;
-
-	pkt_shrink_pktlist(pd);
-}
-
-static struct pktcdvd_device *pkt_find_dev_from_minor(unsigned int dev_minor)
-{
-	if (dev_minor >= MAX_WRITERS)
-		return NULL;
-
-	dev_minor = array_index_nospec(dev_minor, MAX_WRITERS);
-	return pkt_devs[dev_minor];
-}
-
-static int pkt_open(struct gendisk *disk, blk_mode_t mode)
-{
-	struct pktcdvd_device *pd = NULL;
-	int ret;
-
-	mutex_lock(&pktcdvd_mutex);
-	mutex_lock(&ctl_mutex);
-	pd = pkt_find_dev_from_minor(disk->first_minor);
-	if (!pd) {
-		ret = -ENODEV;
-		goto out;
-	}
-	BUG_ON(pd->refcnt < 0);
-
-	pd->refcnt++;
-	if (pd->refcnt > 1) {
-		if ((mode & BLK_OPEN_WRITE) &&
-		    !test_bit(PACKET_WRITABLE, &pd->flags)) {
-			ret = -EBUSY;
-			goto out_dec;
-		}
-	} else {
-		ret = pkt_open_dev(pd, mode & BLK_OPEN_WRITE);
-		if (ret)
-			goto out_dec;
-	}
-	mutex_unlock(&ctl_mutex);
-	mutex_unlock(&pktcdvd_mutex);
-	return 0;
-
-out_dec:
-	pd->refcnt--;
-out:
-	mutex_unlock(&ctl_mutex);
-	mutex_unlock(&pktcdvd_mutex);
-	return ret;
-}
-
-static void pkt_release(struct gendisk *disk)
-{
-	struct pktcdvd_device *pd = disk->private_data;
-
-	mutex_lock(&pktcdvd_mutex);
-	mutex_lock(&ctl_mutex);
-	pd->refcnt--;
-	BUG_ON(pd->refcnt < 0);
-	if (pd->refcnt == 0) {
-		int flush = test_bit(PACKET_WRITABLE, &pd->flags);
-		pkt_release_dev(pd, flush);
-	}
-	mutex_unlock(&ctl_mutex);
-	mutex_unlock(&pktcdvd_mutex);
-}
-
-
-static void pkt_end_io_read_cloned(struct bio *bio)
-{
-	struct packet_stacked_data *psd = bio->bi_private;
-	struct pktcdvd_device *pd = psd->pd;
-
-	psd->bio->bi_status = bio->bi_status;
-	bio_put(bio);
-	bio_endio(psd->bio);
-	mempool_free(psd, &psd_pool);
-	pkt_bio_finished(pd);
-}
-
-static void pkt_make_request_read(struct pktcdvd_device *pd, struct bio *bio)
-{
-	struct bio *cloned_bio = bio_alloc_clone(file_bdev(pd->bdev_file), bio,
-		GFP_NOIO, &pkt_bio_set);
-	struct packet_stacked_data *psd = mempool_alloc(&psd_pool, GFP_NOIO);
-
-	psd->pd = pd;
-	psd->bio = bio;
-	cloned_bio->bi_private = psd;
-	cloned_bio->bi_end_io = pkt_end_io_read_cloned;
-	pd->stats.secs_r += bio_sectors(bio);
-	pkt_queue_bio(pd, cloned_bio);
-}
-
-static void pkt_make_request_write(struct bio *bio)
-{
-	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data;
-	sector_t zone;
-	struct packet_data *pkt;
-	int was_empty, blocked_bio;
-	struct pkt_rb_node *node;
-
-	zone = get_zone(bio->bi_iter.bi_sector, pd);
-
-	/*
-	 * If we find a matching packet in state WAITING or READ_WAIT, we can
-	 * just append this bio to that packet.
-	 */
-	spin_lock(&pd->cdrw.active_list_lock);
-	blocked_bio = 0;
-	list_for_each_entry(pkt, &pd->cdrw.pkt_active_list, list) {
-		if (pkt->sector == zone) {
-			spin_lock(&pkt->lock);
-			if ((pkt->state == PACKET_WAITING_STATE) ||
-			    (pkt->state == PACKET_READ_WAIT_STATE)) {
-				bio_list_add(&pkt->orig_bios, bio);
-				pkt->write_size +=
-					bio->bi_iter.bi_size / CD_FRAMESIZE;
-				if ((pkt->write_size >= pkt->frames) &&
-				    (pkt->state == PACKET_WAITING_STATE)) {
-					atomic_inc(&pkt->run_sm);
-					wake_up(&pd->wqueue);
-				}
-				spin_unlock(&pkt->lock);
-				spin_unlock(&pd->cdrw.active_list_lock);
-				return;
-			} else {
-				blocked_bio = 1;
-			}
-			spin_unlock(&pkt->lock);
-		}
-	}
-	spin_unlock(&pd->cdrw.active_list_lock);
-
-	/*
-	 * Test if there is enough room left in the bio work queue
-	 * (queue size >= congestion on mark).
-	 * If not, wait till the work queue size is below the congestion off mark.
-	 */
-	spin_lock(&pd->lock);
-	if (pd->write_congestion_on > 0
-	    && pd->bio_queue_size >= pd->write_congestion_on) {
-		struct wait_bit_queue_entry wqe;
-
-		init_wait_var_entry(&wqe, &pd->congested, 0);
-		for (;;) {
-			prepare_to_wait_event(__var_waitqueue(&pd->congested),
-					      &wqe.wq_entry,
-					      TASK_UNINTERRUPTIBLE);
-			if (pd->bio_queue_size <= pd->write_congestion_off)
-				break;
-			pd->congested = true;
-			spin_unlock(&pd->lock);
-			schedule();
-			spin_lock(&pd->lock);
-		}
-	}
-	spin_unlock(&pd->lock);
-
-	/*
-	 * No matching packet found. Store the bio in the work queue.
-	 */
-	node = mempool_alloc(&pd->rb_pool, GFP_NOIO);
-	node->bio = bio;
-	spin_lock(&pd->lock);
-	BUG_ON(pd->bio_queue_size < 0);
-	was_empty = (pd->bio_queue_size == 0);
-	pkt_rbtree_insert(pd, node);
-	spin_unlock(&pd->lock);
-
-	/*
-	 * Wake up the worker thread.
-	 */
-	atomic_set(&pd->scan_queue, 1);
-	if (was_empty) {
-		/* This wake_up is required for correct operation */
-		wake_up(&pd->wqueue);
-	} else if (!list_empty(&pd->cdrw.pkt_free_list) && !blocked_bio) {
-		/*
-		 * This wake up is not required for correct operation,
-		 * but improves performance in some cases.
-		 */
-		wake_up(&pd->wqueue);
-	}
-}
-
-static void pkt_submit_bio(struct bio *bio)
-{
-	struct pktcdvd_device *pd = bio->bi_bdev->bd_disk->private_data;
-	struct device *ddev = disk_to_dev(pd->disk);
-	struct bio *split;
-
-	bio = bio_split_to_limits(bio);
-	if (!bio)
-		return;
-
-	dev_dbg(ddev, "start = %6llx stop = %6llx\n",
-		bio->bi_iter.bi_sector, bio_end_sector(bio));
-
-	/*
-	 * Clone READ bios so we can have our own bi_end_io callback.
-	 */
-	if (bio_data_dir(bio) == READ) {
-		pkt_make_request_read(pd, bio);
-		return;
-	}
-
-	if (!test_bit(PACKET_WRITABLE, &pd->flags)) {
-		dev_notice(ddev, "WRITE for ro device (%llu)\n", bio->bi_iter.bi_sector);
-		goto end_io;
-	}
-
-	if (!bio->bi_iter.bi_size || (bio->bi_iter.bi_size % CD_FRAMESIZE)) {
-		dev_err(ddev, "wrong bio size\n");
-		goto end_io;
-	}
-
-	do {
-		sector_t zone = get_zone(bio->bi_iter.bi_sector, pd);
-		sector_t last_zone = get_zone(bio_end_sector(bio) - 1, pd);
-
-		if (last_zone != zone) {
-			BUG_ON(last_zone != zone + pd->settings.size);
-
-			split = bio_split(bio, last_zone -
-					  bio->bi_iter.bi_sector,
-					  GFP_NOIO, &pkt_bio_set);
-			bio_chain(split, bio);
-		} else {
-			split = bio;
-		}
-
-		pkt_make_request_write(split);
-	} while (split != bio);
-
-	return;
-end_io:
-	bio_io_error(bio);
-}
-
-static int pkt_new_dev(struct pktcdvd_device *pd, dev_t dev)
-{
-	struct device *ddev = disk_to_dev(pd->disk);
-	int i;
-	struct file *bdev_file;
-	struct scsi_device *sdev;
-
-	if (pd->pkt_dev == dev) {
-		dev_err(ddev, "recursive setup not allowed\n");
-		return -EBUSY;
-	}
-	for (i = 0; i < MAX_WRITERS; i++) {
-		struct pktcdvd_device *pd2 = pkt_devs[i];
-		if (!pd2)
-			continue;
-		if (file_bdev(pd2->bdev_file)->bd_dev == dev) {
-			dev_err(ddev, "%pg already setup\n",
-				file_bdev(pd2->bdev_file));
-			return -EBUSY;
-		}
-		if (pd2->pkt_dev == dev) {
-			dev_err(ddev, "can't chain pktcdvd devices\n");
-			return -EBUSY;
-		}
-	}
-
-	bdev_file = bdev_file_open_by_dev(dev, BLK_OPEN_READ | BLK_OPEN_NDELAY,
-				       NULL, NULL);
-	if (IS_ERR(bdev_file))
-		return PTR_ERR(bdev_file);
-	sdev = scsi_device_from_queue(file_bdev(bdev_file)->bd_disk->queue);
-	if (!sdev) {
-		fput(bdev_file);
-		return -EINVAL;
-	}
-	put_device(&sdev->sdev_gendev);
-
-	/* This is safe, since we have a reference from open(). */
-	__module_get(THIS_MODULE);
-
-	pd->bdev_file = bdev_file;
-
-	atomic_set(&pd->cdrw.pending_bios, 0);
-	pd->cdrw.thread = kthread_run(kcdrwd, pd, "%s", pd->disk->disk_name);
-	if (IS_ERR(pd->cdrw.thread)) {
-		dev_err(ddev, "can't start kernel thread\n");
-		goto out_mem;
-	}
-
-	proc_create_single_data(pd->disk->disk_name, 0, pkt_proc, pkt_seq_show, pd);
-	dev_notice(ddev, "writer mapped to %pg\n", file_bdev(bdev_file));
-	return 0;
-
-out_mem:
-	fput(bdev_file);
-	/* This is safe: open() is still holding a reference. */
-	module_put(THIS_MODULE);
-	return -ENOMEM;
-}
-
-static int pkt_ioctl(struct block_device *bdev, blk_mode_t mode,
-		unsigned int cmd, unsigned long arg)
-{
-	struct pktcdvd_device *pd = bdev->bd_disk->private_data;
-	struct device *ddev = disk_to_dev(pd->disk);
-	int ret;
-
-	dev_dbg(ddev, "cmd %x, dev %d:%d\n", cmd, MAJOR(bdev->bd_dev), MINOR(bdev->bd_dev));
-
-	mutex_lock(&pktcdvd_mutex);
-	switch (cmd) {
-	case CDROMEJECT:
-		/*
-		 * The door gets locked when the device is opened, so we
-		 * have to unlock it or else the eject command fails.
-		 */
-		if (pd->refcnt == 1)
-			pkt_lock_door(pd, 0);
-		fallthrough;
-	/*
-	 * forward selected CDROM ioctls to CD-ROM, for UDF
-	 */
-	case CDROMMULTISESSION:
-	case CDROMREADTOCENTRY:
-	case CDROM_LAST_WRITTEN:
-	case CDROM_SEND_PACKET:
-	case SCSI_IOCTL_SEND_COMMAND:
-		if (!bdev->bd_disk->fops->ioctl)
-			ret = -ENOTTY;
-		else
-			ret = bdev->bd_disk->fops->ioctl(bdev, mode, cmd, arg);
-		break;
-	default:
-		dev_dbg(ddev, "Unknown ioctl (%x)\n", cmd);
-		ret = -ENOTTY;
-	}
-	mutex_unlock(&pktcdvd_mutex);
-
-	return ret;
-}
-
-static unsigned int pkt_check_events(struct gendisk *disk,
-				     unsigned int clearing)
-{
-	struct pktcdvd_device *pd = disk->private_data;
-	struct gendisk *attached_disk;
-
-	if (!pd)
-		return 0;
-	if (!pd->bdev_file)
-		return 0;
-	attached_disk = file_bdev(pd->bdev_file)->bd_disk;
-	if (!attached_disk || !attached_disk->fops->check_events)
-		return 0;
-	return attached_disk->fops->check_events(attached_disk, clearing);
-}
-
-static char *pkt_devnode(struct gendisk *disk, umode_t *mode)
-{
-	return kasprintf(GFP_KERNEL, "pktcdvd/%s", disk->disk_name);
-}
-
-static const struct block_device_operations pktcdvd_ops = {
-	.owner =		THIS_MODULE,
-	.submit_bio =		pkt_submit_bio,
-	.open =			pkt_open,
-	.release =		pkt_release,
-	.ioctl =		pkt_ioctl,
-	.compat_ioctl =		blkdev_compat_ptr_ioctl,
-	.check_events =		pkt_check_events,
-	.devnode =		pkt_devnode,
-};
-
-/*
- * Set up mapping from pktcdvd device to CD-ROM device.
- */
-static int pkt_setup_dev(dev_t dev, dev_t* pkt_dev)
-{
-	struct queue_limits lim = {
-		.max_hw_sectors		= PACKET_MAX_SECTORS,
-		.logical_block_size	= CD_FRAMESIZE,
-		.features		= BLK_FEAT_ROTATIONAL,
-	};
-	int idx;
-	int ret = -ENOMEM;
-	struct pktcdvd_device *pd;
-	struct gendisk *disk;
-
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	for (idx = 0; idx < MAX_WRITERS; idx++)
-		if (!pkt_devs[idx])
-			break;
-	if (idx == MAX_WRITERS) {
-		pr_err("max %d writers supported\n", MAX_WRITERS);
-		ret = -EBUSY;
-		goto out_mutex;
-	}
-
-	pd = kzalloc(sizeof(struct pktcdvd_device), GFP_KERNEL);
-	if (!pd)
-		goto out_mutex;
-
-	ret = mempool_init_kmalloc_pool(&pd->rb_pool, PKT_RB_POOL_SIZE,
-					sizeof(struct pkt_rb_node));
-	if (ret)
-		goto out_mem;
-
-	INIT_LIST_HEAD(&pd->cdrw.pkt_free_list);
-	INIT_LIST_HEAD(&pd->cdrw.pkt_active_list);
-	spin_lock_init(&pd->cdrw.active_list_lock);
-
-	spin_lock_init(&pd->lock);
-	spin_lock_init(&pd->iosched.lock);
-	bio_list_init(&pd->iosched.read_queue);
-	bio_list_init(&pd->iosched.write_queue);
-	init_waitqueue_head(&pd->wqueue);
-	pd->bio_queue = RB_ROOT;
-
-	pd->write_congestion_on  = write_congestion_on;
-	pd->write_congestion_off = write_congestion_off;
-
-	disk = blk_alloc_disk(&lim, NUMA_NO_NODE);
-	if (IS_ERR(disk)) {
-		ret = PTR_ERR(disk);
-		goto out_mem;
-	}
-	pd->disk = disk;
-	disk->major = pktdev_major;
-	disk->first_minor = idx;
-	disk->minors = 1;
-	disk->fops = &pktcdvd_ops;
-	disk->flags = GENHD_FL_REMOVABLE | GENHD_FL_NO_PART;
-	snprintf(disk->disk_name, sizeof(disk->disk_name), DRIVER_NAME"%d", idx);
-	disk->private_data = pd;
-
-	pd->pkt_dev = MKDEV(pktdev_major, idx);
-	ret = pkt_new_dev(pd, dev);
-	if (ret)
-		goto out_mem2;
-
-	/* inherit events of the host device */
-	disk->events = file_bdev(pd->bdev_file)->bd_disk->events;
-
-	ret = add_disk(disk);
-	if (ret)
-		goto out_mem2;
-
-	pkt_sysfs_dev_new(pd);
-	pkt_debugfs_dev_new(pd);
-
-	pkt_devs[idx] = pd;
-	if (pkt_dev)
-		*pkt_dev = pd->pkt_dev;
-
-	mutex_unlock(&ctl_mutex);
-	return 0;
-
-out_mem2:
-	put_disk(disk);
-out_mem:
-	mempool_exit(&pd->rb_pool);
-	kfree(pd);
-out_mutex:
-	mutex_unlock(&ctl_mutex);
-	pr_err("setup of pktcdvd device failed\n");
-	return ret;
-}
-
-/*
- * Tear down mapping from pktcdvd device to CD-ROM device.
- */
-static int pkt_remove_dev(dev_t pkt_dev)
-{
-	struct pktcdvd_device *pd;
-	struct device *ddev;
-	int idx;
-	int ret = 0;
-
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	for (idx = 0; idx < MAX_WRITERS; idx++) {
-		pd = pkt_devs[idx];
-		if (pd && (pd->pkt_dev == pkt_dev))
-			break;
-	}
-	if (idx == MAX_WRITERS) {
-		pr_debug("dev not setup\n");
-		ret = -ENXIO;
-		goto out;
-	}
-
-	if (pd->refcnt > 0) {
-		ret = -EBUSY;
-		goto out;
-	}
-
-	ddev = disk_to_dev(pd->disk);
-
-	if (!IS_ERR(pd->cdrw.thread))
-		kthread_stop(pd->cdrw.thread);
-
-	pkt_devs[idx] = NULL;
-
-	pkt_debugfs_dev_remove(pd);
-	pkt_sysfs_dev_remove(pd);
-
-	fput(pd->bdev_file);
-
-	remove_proc_entry(pd->disk->disk_name, pkt_proc);
-	dev_notice(ddev, "writer unmapped\n");
-
-	del_gendisk(pd->disk);
-	put_disk(pd->disk);
-
-	mempool_exit(&pd->rb_pool);
-	kfree(pd);
-
-	/* This is safe: open() is still holding a reference. */
-	module_put(THIS_MODULE);
-
-out:
-	mutex_unlock(&ctl_mutex);
-	return ret;
-}
-
-static void pkt_get_status(struct pkt_ctrl_command *ctrl_cmd)
-{
-	struct pktcdvd_device *pd;
-
-	mutex_lock_nested(&ctl_mutex, SINGLE_DEPTH_NESTING);
-
-	pd = pkt_find_dev_from_minor(ctrl_cmd->dev_index);
-	if (pd) {
-		ctrl_cmd->dev = new_encode_dev(file_bdev(pd->bdev_file)->bd_dev);
-		ctrl_cmd->pkt_dev = new_encode_dev(pd->pkt_dev);
-	} else {
-		ctrl_cmd->dev = 0;
-		ctrl_cmd->pkt_dev = 0;
-	}
-	ctrl_cmd->num_devices = MAX_WRITERS;
-
-	mutex_unlock(&ctl_mutex);
-}
-
-static long pkt_ctl_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	void __user *argp = (void __user *)arg;
-	struct pkt_ctrl_command ctrl_cmd;
-	int ret = 0;
-	dev_t pkt_dev = 0;
-
-	if (cmd != PACKET_CTRL_CMD)
-		return -ENOTTY;
-
-	if (copy_from_user(&ctrl_cmd, argp, sizeof(struct pkt_ctrl_command)))
-		return -EFAULT;
-
-	switch (ctrl_cmd.command) {
-	case PKT_CTRL_CMD_SETUP:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-		ret = pkt_setup_dev(new_decode_dev(ctrl_cmd.dev), &pkt_dev);
-		ctrl_cmd.pkt_dev = new_encode_dev(pkt_dev);
-		break;
-	case PKT_CTRL_CMD_TEARDOWN:
-		if (!capable(CAP_SYS_ADMIN))
-			return -EPERM;
-		ret = pkt_remove_dev(new_decode_dev(ctrl_cmd.pkt_dev));
-		break;
-	case PKT_CTRL_CMD_STATUS:
-		pkt_get_status(&ctrl_cmd);
-		break;
-	default:
-		return -ENOTTY;
-	}
-
-	if (copy_to_user(argp, &ctrl_cmd, sizeof(struct pkt_ctrl_command)))
-		return -EFAULT;
-	return ret;
-}
-
-#ifdef CONFIG_COMPAT
-static long pkt_ctl_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
-{
-	return pkt_ctl_ioctl(file, cmd, (unsigned long)compat_ptr(arg));
-}
-#endif
-
-static const struct file_operations pkt_ctl_fops = {
-	.open		= nonseekable_open,
-	.unlocked_ioctl	= pkt_ctl_ioctl,
-#ifdef CONFIG_COMPAT
-	.compat_ioctl	= pkt_ctl_compat_ioctl,
-#endif
-	.owner		= THIS_MODULE,
-};
-
-static struct miscdevice pkt_misc = {
-	.minor 		= MISC_DYNAMIC_MINOR,
-	.name  		= DRIVER_NAME,
-	.nodename	= "pktcdvd/control",
-	.fops  		= &pkt_ctl_fops
-};
-
-static int __init pkt_init(void)
-{
-	int ret;
-
-	mutex_init(&ctl_mutex);
-
-	ret = mempool_init_kmalloc_pool(&psd_pool, PSD_POOL_SIZE,
-				    sizeof(struct packet_stacked_data));
-	if (ret)
-		return ret;
-	ret = bioset_init(&pkt_bio_set, BIO_POOL_SIZE, 0, 0);
-	if (ret) {
-		mempool_exit(&psd_pool);
-		return ret;
-	}
-
-	ret = register_blkdev(pktdev_major, DRIVER_NAME);
-	if (ret < 0) {
-		pr_err("unable to register block device\n");
-		goto out2;
-	}
-	if (!pktdev_major)
-		pktdev_major = ret;
-
-	ret = pkt_sysfs_init();
-	if (ret)
-		goto out;
-
-	pkt_debugfs_init();
-
-	ret = misc_register(&pkt_misc);
-	if (ret) {
-		pr_err("unable to register misc device\n");
-		goto out_misc;
-	}
-
-	pkt_proc = proc_mkdir("driver/"DRIVER_NAME, NULL);
-
-	return 0;
-
-out_misc:
-	pkt_debugfs_cleanup();
-	pkt_sysfs_cleanup();
-out:
-	unregister_blkdev(pktdev_major, DRIVER_NAME);
-out2:
-	mempool_exit(&psd_pool);
-	bioset_exit(&pkt_bio_set);
-	return ret;
-}
-
-static void __exit pkt_exit(void)
-{
-	remove_proc_entry("driver/"DRIVER_NAME, NULL);
-	misc_deregister(&pkt_misc);
-
-	pkt_debugfs_cleanup();
-	pkt_sysfs_cleanup();
-
-	unregister_blkdev(pktdev_major, DRIVER_NAME);
-	mempool_exit(&psd_pool);
-	bioset_exit(&pkt_bio_set);
-}
-
-MODULE_DESCRIPTION("Packet writing layer for CD/DVD drives");
-MODULE_AUTHOR("Jens Axboe <axboe@suse.de>");
-MODULE_LICENSE("GPL");
-
-module_init(pkt_init);
-module_exit(pkt_exit);
diff --git a/include/linux/pktcdvd.h b/include/linux/pktcdvd.h
deleted file mode 100644
index 2f1b952d596a..000000000000
--- a/include/linux/pktcdvd.h
+++ /dev/null
@@ -1,198 +0,0 @@
-/*
- * Copyright (C) 2000 Jens Axboe <axboe@suse.de>
- * Copyright (C) 2001-2004 Peter Osterlund <petero2@telia.com>
- *
- * May be copied or modified under the terms of the GNU General Public
- * License.  See linux/COPYING for more information.
- *
- * Packet writing layer for ATAPI and SCSI CD-R, CD-RW, DVD-R, and
- * DVD-RW devices.
- *
- */
-#ifndef __PKTCDVD_H
-#define __PKTCDVD_H
-
-#include <linux/blkdev.h>
-#include <linux/completion.h>
-#include <linux/cdrom.h>
-#include <linux/kobject.h>
-#include <linux/sysfs.h>
-#include <linux/mempool.h>
-#include <uapi/linux/pktcdvd.h>
-
-/* default bio write queue congestion marks */
-#define PKT_WRITE_CONGESTION_ON    10000
-#define PKT_WRITE_CONGESTION_OFF   9000
-
-
-struct packet_settings
-{
-	__u32			size;		/* packet size in (512 byte) sectors */
-	__u8			fp;		/* fixed packets */
-	__u8			link_loss;	/* the rest is specified
-						 * as per Mt Fuji */
-	__u8			write_type;
-	__u8			track_mode;
-	__u8			block_mode;
-};
-
-/*
- * Very crude stats for now
- */
-struct packet_stats
-{
-	unsigned long		pkt_started;
-	unsigned long		pkt_ended;
-	unsigned long		secs_w;
-	unsigned long		secs_rg;
-	unsigned long		secs_r;
-};
-
-struct packet_cdrw
-{
-	struct list_head	pkt_free_list;
-	struct list_head	pkt_active_list;
-	spinlock_t		active_list_lock; /* Serialize access to pkt_active_list */
-	struct task_struct	*thread;
-	atomic_t		pending_bios;
-};
-
-/*
- * Switch to high speed reading after reading this many kilobytes
- * with no interspersed writes.
- */
-#define HI_SPEED_SWITCH 512
-
-struct packet_iosched
-{
-	atomic_t		attention;	/* Set to non-zero when queue processing is needed */
-	int			writing;	/* Non-zero when writing, zero when reading */
-	spinlock_t		lock;		/* Protecting read/write queue manipulations */
-	struct bio_list		read_queue;
-	struct bio_list		write_queue;
-	sector_t		last_write;	/* The sector where the last write ended */
-	int			successive_reads;
-};
-
-/*
- * 32 buffers of 2048 bytes
- */
-#if (PAGE_SIZE % CD_FRAMESIZE) != 0
-#error "PAGE_SIZE must be a multiple of CD_FRAMESIZE"
-#endif
-#define PACKET_MAX_SIZE		128
-#define FRAMES_PER_PAGE		(PAGE_SIZE / CD_FRAMESIZE)
-#define PACKET_MAX_SECTORS	(PACKET_MAX_SIZE * CD_FRAMESIZE >> 9)
-
-enum packet_data_state {
-	PACKET_IDLE_STATE,			/* Not used at the moment */
-	PACKET_WAITING_STATE,			/* Waiting for more bios to arrive, so */
-						/* we don't have to do as much */
-						/* data gathering */
-	PACKET_READ_WAIT_STATE,			/* Waiting for reads to fill in holes */
-	PACKET_WRITE_WAIT_STATE,		/* Waiting for the write to complete */
-	PACKET_RECOVERY_STATE,			/* Recover after read/write errors */
-	PACKET_FINISHED_STATE,			/* After write has finished */
-
-	PACKET_NUM_STATES			/* Number of possible states */
-};
-
-/*
- * Information needed for writing a single packet
- */
-struct pktcdvd_device;
-
-struct packet_data
-{
-	struct list_head	list;
-
-	spinlock_t		lock;		/* Lock protecting state transitions and */
-						/* orig_bios list */
-
-	struct bio_list		orig_bios;	/* Original bios passed to pkt_make_request */
-						/* that will be handled by this packet */
-	int			write_size;	/* Total size of all bios in the orig_bios */
-						/* list, measured in number of frames */
-
-	struct bio		*w_bio;		/* The bio we will send to the real CD */
-						/* device once we have all data for the */
-						/* packet we are going to write */
-	sector_t		sector;		/* First sector in this packet */
-	int			frames;		/* Number of frames in this packet */
-
-	enum packet_data_state	state;		/* Current state */
-	atomic_t		run_sm;		/* Incremented whenever the state */
-						/* machine needs to be run */
-	long			sleep_time;	/* Set this to non-zero to make the state */
-						/* machine run after this many jiffies. */
-
-	atomic_t		io_wait;	/* Number of pending IO operations */
-	atomic_t		io_errors;	/* Number of read/write errors during IO */
-
-	struct bio		*r_bios[PACKET_MAX_SIZE]; /* bios to use during data gathering */
-	struct page		*pages[PACKET_MAX_SIZE / FRAMES_PER_PAGE];
-
-	int			cache_valid;	/* If non-zero, the data for the zone defined */
-						/* by the sector variable is completely cached */
-						/* in the pages[] vector. */
-
-	int			id;		/* ID number for debugging */
-	struct pktcdvd_device	*pd;
-};
-
-struct pkt_rb_node {
-	struct rb_node		rb_node;
-	struct bio		*bio;
-};
-
-struct packet_stacked_data
-{
-	struct bio		*bio;		/* Original read request bio */
-	struct pktcdvd_device	*pd;
-};
-#define PSD_POOL_SIZE		64
-
-struct pktcdvd_device
-{
-	struct file		*bdev_file;	/* dev attached */
-	/* handle acquired for bdev during pkt_open_dev() */
-	struct file		*f_open_bdev;
-	dev_t			pkt_dev;	/* our dev */
-	struct packet_settings	settings;
-	struct packet_stats	stats;
-	int			refcnt;		/* Open count */
-	int			write_speed;	/* current write speed, kB/s */
-	int			read_speed;	/* current read speed, kB/s */
-	unsigned long		offset;		/* start offset */
-	__u8			mode_offset;	/* 0 / 8 */
-	__u8			type;
-	unsigned long		flags;
-	__u16			mmc3_profile;
-	__u32			nwa;		/* next writable address */
-	__u32			lra;		/* last recorded address */
-	struct packet_cdrw	cdrw;
-	wait_queue_head_t	wqueue;
-
-	spinlock_t		lock;		/* Serialize access to bio_queue */
-	struct rb_root		bio_queue;	/* Work queue of bios we need to handle */
-	int			bio_queue_size;	/* Number of nodes in bio_queue */
-	bool			congested;	/* Someone is waiting for bio_queue_size
-						 * to drop. */
-	sector_t		current_sector;	/* Keep track of where the elevator is */
-	atomic_t		scan_queue;	/* Set to non-zero when pkt_handle_queue */
-						/* needs to be run. */
-	mempool_t		rb_pool;	/* mempool for pkt_rb_node allocations */
-
-	struct packet_iosched   iosched;
-	struct gendisk		*disk;
-
-	int			write_congestion_off;
-	int			write_congestion_on;
-
-	struct device		*dev;		/* sysfs pktcdvd[0-7] dev */
-
-	struct dentry		*dfs_d_root;	/* debugfs: devname directory */
-	struct dentry		*dfs_f_info;	/* debugfs: info file */
-};
-
-#endif /* __PKTCDVD_H */
-- 
cgit v1.2.3


From c4aa454c64ae022e5a9d55b3c31e9b8dd8a1544f Mon Sep 17 00:00:00 2001
From: Eduard Zingerman <eddyz87@gmail.com>
Date: Fri, 4 Jul 2025 16:03:53 -0700
Subject: bpf: support for void/primitive __arg_untrusted global func params

Allow specifying __arg_untrusted for void */char */int */long *
parameters. Treat such parameters as
PTR_TO_MEM|MEM_RDONLY|PTR_UNTRUSTED of size zero.
Intended usage is as follows:

  int memcmp(char *a __arg_untrusted, char *b __arg_untrusted, size_t n) {
    bpf_for(i, 0, n) {
      if (a[i] - b[i])      // load at any offset is allowed
        return a[i] - b[i];
    }
    return 0;
  }

Allocate register id for ARG_PTR_TO_MEM parameters only when
PTR_MAYBE_NULL is set. Register id for PTR_TO_MEM is used only to
propagate non-null status after conditionals.

Suggested-by: Alexei Starovoitov <alexei.starovoitov@gmail.com>
Acked-by: Kumar Kartikeya Dwivedi <memxor@gmail.com>
Signed-off-by: Eduard Zingerman <eddyz87@gmail.com>
Link: https://lore.kernel.org/r/20250704230354.1323244-8-eddyz87@gmail.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/btf.h   |  1 +
 kernel/bpf/btf.c      | 15 ++++++++++++++-
 kernel/bpf/verifier.c |  7 ++++---
 3 files changed, 19 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/btf.h b/include/linux/btf.h
index a40beb9cf160..9eda6b113f9b 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -223,6 +223,7 @@ u32 btf_nr_types(const struct btf *btf);
 struct btf *btf_base_btf(const struct btf *btf);
 bool btf_type_is_i32(const struct btf_type *t);
 bool btf_type_is_i64(const struct btf_type *t);
+bool btf_type_is_primitive(const struct btf_type *t);
 bool btf_member_is_reg_int(const struct btf *btf, const struct btf_type *s,
 			   const struct btf_member *m,
 			   u32 expected_offset, u32 expected_size);
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index e0414d9f5e29..2dd13eea7b0e 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -891,6 +891,12 @@ bool btf_type_is_i64(const struct btf_type *t)
 	return btf_type_is_int(t) && __btf_type_int_is_regular(t, 8);
 }
 
+bool btf_type_is_primitive(const struct btf_type *t)
+{
+	return (btf_type_is_int(t) && btf_type_int_is_regular(t)) ||
+	       btf_is_any_enum(t);
+}
+
 /*
  * Check that given struct member is a regular int with expected
  * offset and size.
@@ -7830,6 +7836,13 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 				return -EINVAL;
 			}
 
+			ref_t = btf_type_skip_modifiers(btf, t->type, NULL);
+			if (btf_type_is_void(ref_t) || btf_type_is_primitive(ref_t)) {
+				sub->args[i].arg_type = ARG_PTR_TO_MEM | MEM_RDONLY | PTR_UNTRUSTED;
+				sub->args[i].mem_size = 0;
+				continue;
+			}
+
 			kern_type_id = btf_get_ptr_to_btf_id(log, i, btf, t);
 			if (kern_type_id < 0)
 				return kern_type_id;
@@ -7838,7 +7851,7 @@ int btf_prepare_func_args(struct bpf_verifier_env *env, int subprog)
 			ref_t = btf_type_by_id(vmlinux_btf, kern_type_id);
 			if (!btf_type_is_struct(ref_t)) {
 				tname = __btf_name_by_offset(vmlinux_btf, t->name_off);
-				bpf_log(log, "arg#%d has type %s '%s', but only struct types are allowed\n",
+				bpf_log(log, "arg#%d has type %s '%s', but only struct or primitive types are allowed\n",
 					i, btf_type_str(ref_t), tname);
 				return -EINVAL;
 			}
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 7af902c3ecc3..1e567fff6f23 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -23152,11 +23152,12 @@ static int do_check_common(struct bpf_verifier_env *env, int subprog)
 				__mark_dynptr_reg(reg, BPF_DYNPTR_TYPE_LOCAL, true, ++env->id_gen);
 			} else if (base_type(arg->arg_type) == ARG_PTR_TO_MEM) {
 				reg->type = PTR_TO_MEM;
-				if (arg->arg_type & PTR_MAYBE_NULL)
-					reg->type |= PTR_MAYBE_NULL;
+				reg->type |= arg->arg_type &
+					     (PTR_MAYBE_NULL | PTR_UNTRUSTED | MEM_RDONLY);
 				mark_reg_known_zero(env, regs, i);
 				reg->mem_size = arg->mem_size;
-				reg->id = ++env->id_gen;
+				if (arg->arg_type & PTR_MAYBE_NULL)
+					reg->id = ++env->id_gen;
 			} else if (base_type(arg->arg_type) == ARG_PTR_TO_BTF_ID) {
 				reg->type = PTR_TO_BTF_ID;
 				if (arg->arg_type & PTR_MAYBE_NULL)
-- 
cgit v1.2.3


From 4cdf1bdd45ac78a088773722f009883af30ad318 Mon Sep 17 00:00:00 2001
From: Pankaj Raghav <p.raghav@samsung.com>
Date: Fri, 4 Jul 2025 11:21:34 +0200
Subject: block: reject bs > ps block devices when THP is disabled

If THP is disabled and when a block device with logical block size >
page size is present, the following null ptr deref panic happens during
boot:

[   [13.2 mK  AOSAN: null-ptr-deref in range [0x0000000000000000-0x0000000000K0 0 0[07]
[   13.017749] RIP: 0010:create_empty_buffers+0x3b/0x380
<snip>
[   13.025448] Call Trace:
[   13.025692]  <TASK>
[   13.025895]  block_read_full_folio+0x610/0x780
[   13.026379]  ? __pfx_blkdev_get_block+0x10/0x10
[   13.027008]  ? __folio_batch_add_and_move+0x1fa/0x2b0
[   13.027548]  ? __pfx_blkdev_read_folio+0x10/0x10
[   13.028080]  filemap_read_folio+0x9b/0x200
[   13.028526]  ? __pfx_filemap_read_folio+0x10/0x10
[   13.029030]  ? __filemap_get_folio+0x43/0x620
[   13.029497]  do_read_cache_folio+0x155/0x3b0
[   13.029962]  ? __pfx_blkdev_read_folio+0x10/0x10
[   13.030381]  read_part_sector+0xb7/0x2a0
[   13.030805]  read_lba+0x174/0x2c0
<snip>
[   13.045348]  nvme_scan_ns+0x684/0x850 [nvme_core]
[   13.045858]  ? __pfx_nvme_scan_ns+0x10/0x10 [nvme_core]
[   13.046414]  ? _raw_spin_unlock+0x15/0x40
[   13.046843]  ? __switch_to+0x523/0x10a0
[   13.047253]  ? kvm_clock_get_cycles+0x14/0x30
[   13.047742]  ? __pfx_nvme_scan_ns_async+0x10/0x10 [nvme_core]
[   13.048353]  async_run_entry_fn+0x96/0x4f0
[   13.048787]  process_one_work+0x667/0x10a0
[   13.049219]  worker_thread+0x63c/0xf60

As large folio support depends on THP, only allow bs > ps block devices
if THP is enabled.

Fixes: 47dd67532303 ("block/bdev: lift block size restrictions to 64k")
Signed-off-by: Pankaj Raghav <p.raghav@samsung.com>
Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Link: https://lore.kernel.org/r/20250704092134.289491-1-p.raghav@samsung.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/blkdev.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 332b56f323d9..369a8e63c865 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -269,11 +269,16 @@ static inline dev_t disk_devt(struct gendisk *disk)
 	return MKDEV(disk->major, disk->first_minor);
 }
 
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
 /*
  * We should strive for 1 << (PAGE_SHIFT + MAX_PAGECACHE_ORDER)
  * however we constrain this to what we can validate and test.
  */
 #define BLK_MAX_BLOCK_SIZE      SZ_64K
+#else
+#define BLK_MAX_BLOCK_SIZE      PAGE_SIZE
+#endif
+
 
 /* blk_validate_limits() validates bsize, so drivers don't usually need to */
 static inline int blk_validate_block_size(unsigned long bsize)
-- 
cgit v1.2.3


From d42c7c6fd66a6e2a78ae1da666c5df6c2fde8389 Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Thu, 3 Jul 2025 14:27:06 +0300
Subject: PM: domains: Add flags to specify power on attach/detach

Calling dev_pm_domain_attach()/dev_pm_domain_detach() in bus driver
probe/remove functions can affect system behavior when the drivers
attached to the bus use devres-managed resources. Since devres actions
may need to access device registers, calling dev_pm_domain_detach() too
early, i.e., before these actions complete, can cause failures on some
systems. One such example is Renesas RZ/G3S SoC-based platforms.

If the device clocks are managed via PM domains, invoking
dev_pm_domain_detach() in the bus driver's remove function removes the
device's clocks from the PM domain, preventing any subsequent
pm_runtime_resume*() calls from enabling those clocks.

The second argument of dev_pm_domain_attach() specifies whether the PM
domain should be powered on during attachment. Likewise, the second
argument of dev_pm_domain_detach() indicates whether the domain should be
powered off during detachment.

Upcoming changes address the issue described above (initially for the
platform bus only) by deferring the call to dev_pm_domain_detach() until
after devres_release_all() in device_unbind_cleanup(). The detach_power_off
field in struct dev_pm_info stores the detach power off info from the
second argument of dev_pm_domain_attach().

Because there are cases where the device's PM domain power-on/off behavior
must be conditional (e.g., in i2c_device_probe()), the patch introduces
PD_FLAG_ATTACH_POWER_ON and PD_FLAG_DETACH_POWER_OFF flags to be passed
to dev_pm_domain_attach().

Finally, dev_pm_domain_attach() and its users are updated to use the newly
introduced PD_FLAG_ATTACH_POWER_ON and PD_FLAG_DETACH_POWER_OFF macros.

This change is preparatory.

Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Mathieu Poirier <mathieu.poirier@linaro.org>
Acked-by: Wolfram Sang <wsa+renesas@sang-engineering.com> # I2C
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://patch.msgid.link/20250703112708.1621607-2-claudiu.beznea.uj@bp.renesas.com
[ rjw: Changelog adjustments ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/amba/bus.c                       |  4 ++--
 drivers/base/auxiliary.c                 |  2 +-
 drivers/base/platform.c                  |  2 +-
 drivers/base/power/common.c              |  6 +++---
 drivers/clk/qcom/apcs-sdx55.c            |  2 +-
 drivers/gpu/drm/display/drm_dp_aux_bus.c |  2 +-
 drivers/i2c/i2c-core-base.c              |  2 +-
 drivers/mmc/core/sdio_bus.c              |  2 +-
 drivers/rpmsg/rpmsg_core.c               |  2 +-
 drivers/soundwire/bus_type.c             |  2 +-
 drivers/spi/spi.c                        |  2 +-
 drivers/tty/serdev/core.c                |  2 +-
 include/linux/pm_domain.h                | 10 ++++++++--
 13 files changed, 23 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/amba/bus.c b/drivers/amba/bus.c
index 71482d639a6d..74e34a07ef72 100644
--- a/drivers/amba/bus.c
+++ b/drivers/amba/bus.c
@@ -138,7 +138,7 @@ static int amba_read_periphid(struct amba_device *dev)
 	void __iomem *tmp;
 	int i, ret;
 
-	ret = dev_pm_domain_attach(&dev->dev, true);
+	ret = dev_pm_domain_attach(&dev->dev, PD_FLAG_ATTACH_POWER_ON);
 	if (ret) {
 		dev_dbg(&dev->dev, "can't get PM domain: %d\n", ret);
 		goto err_out;
@@ -291,7 +291,7 @@ static int amba_probe(struct device *dev)
 		if (ret < 0)
 			break;
 
-		ret = dev_pm_domain_attach(dev, true);
+		ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON);
 		if (ret)
 			break;
 
diff --git a/drivers/base/auxiliary.c b/drivers/base/auxiliary.c
index dba7c8e13a53..44cd3f85b659 100644
--- a/drivers/base/auxiliary.c
+++ b/drivers/base/auxiliary.c
@@ -217,7 +217,7 @@ static int auxiliary_bus_probe(struct device *dev)
 	struct auxiliary_device *auxdev = to_auxiliary_dev(dev);
 	int ret;
 
-	ret = dev_pm_domain_attach(dev, true);
+	ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON);
 	if (ret) {
 		dev_warn(dev, "Failed to attach to PM Domain : %d\n", ret);
 		return ret;
diff --git a/drivers/base/platform.c b/drivers/base/platform.c
index 075ec1d1b73a..df1ec34fdf56 100644
--- a/drivers/base/platform.c
+++ b/drivers/base/platform.c
@@ -1396,7 +1396,7 @@ static int platform_probe(struct device *_dev)
 	if (ret < 0)
 		return ret;
 
-	ret = dev_pm_domain_attach(_dev, true);
+	ret = dev_pm_domain_attach(_dev, PD_FLAG_ATTACH_POWER_ON);
 	if (ret)
 		goto out;
 
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index 781968a128ff..fecb85fa85ac 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -83,7 +83,7 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
 /**
  * dev_pm_domain_attach - Attach a device to its PM domain.
  * @dev: Device to attach.
- * @power_on: Used to indicate whether we should power on the device.
+ * @flags: indicate whether we should power on/off the device on attach/detach
  *
  * The @dev may only be attached to a single PM domain. By iterating through
  * the available alternatives we try to find a valid PM domain for the device.
@@ -100,14 +100,14 @@ EXPORT_SYMBOL_GPL(dev_pm_put_subsys_data);
  * Returns 0 on successfully attached PM domain, or when it is found that the
  * device doesn't need a PM domain, else a negative error code.
  */
-int dev_pm_domain_attach(struct device *dev, bool power_on)
+int dev_pm_domain_attach(struct device *dev, u32 flags)
 {
 	int ret;
 
 	if (dev->pm_domain)
 		return 0;
 
-	ret = acpi_dev_pm_attach(dev, power_on);
+	ret = acpi_dev_pm_attach(dev, !!(flags & PD_FLAG_ATTACH_POWER_ON));
 	if (!ret)
 		ret = genpd_dev_pm_attach(dev);
 
diff --git a/drivers/clk/qcom/apcs-sdx55.c b/drivers/clk/qcom/apcs-sdx55.c
index 3ba01622d8f0..90dd1f1855c2 100644
--- a/drivers/clk/qcom/apcs-sdx55.c
+++ b/drivers/clk/qcom/apcs-sdx55.c
@@ -111,7 +111,7 @@ static int qcom_apcs_sdx55_clk_probe(struct platform_device *pdev)
 	 * driver, there seems to be no better place to do this. So do it here!
 	 */
 	cpu_dev = get_cpu_device(0);
-	ret = dev_pm_domain_attach(cpu_dev, true);
+	ret = dev_pm_domain_attach(cpu_dev, PD_FLAG_ATTACH_POWER_ON);
 	if (ret) {
 		dev_err_probe(dev, ret, "can't get PM domain: %d\n", ret);
 		goto err;
diff --git a/drivers/gpu/drm/display/drm_dp_aux_bus.c b/drivers/gpu/drm/display/drm_dp_aux_bus.c
index ec7eac6b595f..718c9122bc3a 100644
--- a/drivers/gpu/drm/display/drm_dp_aux_bus.c
+++ b/drivers/gpu/drm/display/drm_dp_aux_bus.c
@@ -57,7 +57,7 @@ static int dp_aux_ep_probe(struct device *dev)
 		container_of(aux_ep, struct dp_aux_ep_device_with_data, aux_ep);
 	int ret;
 
-	ret = dev_pm_domain_attach(dev, true);
+	ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON);
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to attach to PM Domain\n");
 
diff --git a/drivers/i2c/i2c-core-base.c b/drivers/i2c/i2c-core-base.c
index 2ad2b1838f0f..38eabf1173da 100644
--- a/drivers/i2c/i2c-core-base.c
+++ b/drivers/i2c/i2c-core-base.c
@@ -573,7 +573,7 @@ static int i2c_device_probe(struct device *dev)
 		goto err_clear_wakeup_irq;
 
 	do_power_on = !i2c_acpi_waive_d0_probe(dev);
-	status = dev_pm_domain_attach(&client->dev, do_power_on);
+	status = dev_pm_domain_attach(&client->dev, do_power_on ? PD_FLAG_ATTACH_POWER_ON : 0);
 	if (status)
 		goto err_clear_wakeup_irq;
 
diff --git a/drivers/mmc/core/sdio_bus.c b/drivers/mmc/core/sdio_bus.c
index b66b637e2d57..656601754966 100644
--- a/drivers/mmc/core/sdio_bus.c
+++ b/drivers/mmc/core/sdio_bus.c
@@ -161,7 +161,7 @@ static int sdio_bus_probe(struct device *dev)
 	if (!id)
 		return -ENODEV;
 
-	ret = dev_pm_domain_attach(dev, false);
+	ret = dev_pm_domain_attach(dev, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/rpmsg/rpmsg_core.c b/drivers/rpmsg/rpmsg_core.c
index 6ee36adcbdba..bece5e635ee9 100644
--- a/drivers/rpmsg/rpmsg_core.c
+++ b/drivers/rpmsg/rpmsg_core.c
@@ -479,7 +479,7 @@ static int rpmsg_dev_probe(struct device *dev)
 	struct rpmsg_endpoint *ept = NULL;
 	int err;
 
-	err = dev_pm_domain_attach(dev, true);
+	err = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON);
 	if (err)
 		goto out;
 
diff --git a/drivers/soundwire/bus_type.c b/drivers/soundwire/bus_type.c
index 75d6f16efced..bc1e653080d9 100644
--- a/drivers/soundwire/bus_type.c
+++ b/drivers/soundwire/bus_type.c
@@ -101,7 +101,7 @@ static int sdw_drv_probe(struct device *dev)
 	/*
 	 * attach to power domain but don't turn on (last arg)
 	 */
-	ret = dev_pm_domain_attach(dev, false);
+	ret = dev_pm_domain_attach(dev, 0);
 	if (ret)
 		return ret;
 
diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c
index 1bc0fdbb1bd7..8200b47b2295 100644
--- a/drivers/spi/spi.c
+++ b/drivers/spi/spi.c
@@ -427,7 +427,7 @@ static int spi_probe(struct device *dev)
 	if (spi->irq < 0)
 		spi->irq = 0;
 
-	ret = dev_pm_domain_attach(dev, true);
+	ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON);
 	if (ret)
 		return ret;
 
diff --git a/drivers/tty/serdev/core.c b/drivers/tty/serdev/core.c
index 0213381fa358..d16c207a1a9b 100644
--- a/drivers/tty/serdev/core.c
+++ b/drivers/tty/serdev/core.c
@@ -399,7 +399,7 @@ static int serdev_drv_probe(struct device *dev)
 	const struct serdev_device_driver *sdrv = to_serdev_device_driver(dev->driver);
 	int ret;
 
-	ret = dev_pm_domain_attach(dev, true);
+	ret = dev_pm_domain_attach(dev, PD_FLAG_ATTACH_POWER_ON);
 	if (ret)
 		return ret;
 
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 0b18160901a2..62a35a78ce9b 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -36,10 +36,16 @@
  *				isn't specified, the index just follows the
  *				index for the attached PM domain.
  *
+ * PD_FLAG_ATTACH_POWER_ON:	Power on the domain during attach.
+ *
+ * PD_FLAG_DETACH_POWER_OFF:	Power off the domain during detach.
+ *
  */
 #define PD_FLAG_NO_DEV_LINK		BIT(0)
 #define PD_FLAG_DEV_LINK_ON		BIT(1)
 #define PD_FLAG_REQUIRED_OPP		BIT(2)
+#define PD_FLAG_ATTACH_POWER_ON		BIT(3)
+#define PD_FLAG_DETACH_POWER_OFF	BIT(4)
 
 struct dev_pm_domain_attach_data {
 	const char * const *pd_names;
@@ -501,7 +507,7 @@ struct generic_pm_domain *of_genpd_remove_last(struct device_node *np)
 #endif /* CONFIG_PM_GENERIC_DOMAINS_OF */
 
 #ifdef CONFIG_PM
-int dev_pm_domain_attach(struct device *dev, bool power_on);
+int dev_pm_domain_attach(struct device *dev, u32 flags);
 struct device *dev_pm_domain_attach_by_id(struct device *dev,
 					  unsigned int index);
 struct device *dev_pm_domain_attach_by_name(struct device *dev,
@@ -518,7 +524,7 @@ int dev_pm_domain_start(struct device *dev);
 void dev_pm_domain_set(struct device *dev, struct dev_pm_domain *pd);
 int dev_pm_domain_set_performance_state(struct device *dev, unsigned int state);
 #else
-static inline int dev_pm_domain_attach(struct device *dev, bool power_on)
+static inline int dev_pm_domain_attach(struct device *dev, u32 flags)
 {
 	return 0;
 }
-- 
cgit v1.2.3


From f99508074e78fea17f06d753d9ef453b174ec98e Mon Sep 17 00:00:00 2001
From: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Date: Thu, 3 Jul 2025 14:27:07 +0300
Subject: PM: domains: Detach on device_unbind_cleanup()

The dev_pm_domain_attach() function is typically used in bus code
alongside dev_pm_domain_detach(), often following patterns like:

static int bus_probe(struct device *_dev)
{
    struct bus_driver *drv = to_bus_driver(dev->driver);
    struct bus_device *dev = to_bus_device(_dev);
    int ret;

    // ...

    ret = dev_pm_domain_attach(_dev, true);
    if (ret)
        return ret;

    if (drv->probe)
        ret = drv->probe(dev);

    // ...
}

static void bus_remove(struct device *_dev)
{
    struct bus_driver *drv = to_bus_driver(dev->driver);
    struct bus_device *dev = to_bus_device(_dev);

    if (drv->remove)
        drv->remove(dev);
    dev_pm_domain_detach(_dev);
}

When the driver's probe function uses devres-managed resources that
depend on the power domain state, those resources are released later
during device_unbind_cleanup().

Releasing devres-managed resources that depend on the power domain state
after detaching the device from its PM domain can cause failures.

For example, if the driver uses devm_pm_runtime_enable() in its probe
function, and the device's clocks are managed by the PM domain, then
during removal the runtime PM is disabled in device_unbind_cleanup()
after the clocks have been removed from the PM domain. It may happen
that the devm_pm_runtime_enable() action causes the device to be runtime-
resumed. If the driver specific runtime PM APIs access registers directly,
this will lead to accessing device registers without clocks being enabled.
Similar issues may occur with other devres actions that access device
registers.

Add detach_power_off member to struct dev_pm_info, to be used
later in device_unbind_cleanup() as the power_off argument for
dev_pm_domain_detach(). This is a preparatory step toward removing
dev_pm_domain_detach() calls from bus remove functions. Since the current
PM domain detach functions (genpd_dev_pm_detach() and acpi_dev_pm_detach())
already set dev->pm_domain = NULL, there should be no issues with bus
drivers that still call dev_pm_domain_detach() in their remove functions.

Signed-off-by: Claudiu Beznea <claudiu.beznea.uj@bp.renesas.com>
Reviewed-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://patch.msgid.link/20250703112708.1621607-3-claudiu.beznea.uj@bp.renesas.com
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/base/dd.c           | 2 ++
 drivers/base/power/common.c | 3 +++
 include/linux/pm.h          | 1 +
 3 files changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/dd.c b/drivers/base/dd.c
index b526e0e0f52d..13ab98e033ea 100644
--- a/drivers/base/dd.c
+++ b/drivers/base/dd.c
@@ -25,6 +25,7 @@
 #include <linux/kthread.h>
 #include <linux/wait.h>
 #include <linux/async.h>
+#include <linux/pm_domain.h>
 #include <linux/pm_runtime.h>
 #include <linux/pinctrl/devinfo.h>
 #include <linux/slab.h>
@@ -552,6 +553,7 @@ static void device_unbind_cleanup(struct device *dev)
 	dev->dma_range_map = NULL;
 	device_set_driver(dev, NULL);
 	dev_set_drvdata(dev, NULL);
+	dev_pm_domain_detach(dev, dev->power.detach_power_off);
 	if (dev->pm_domain && dev->pm_domain->dismiss)
 		dev->pm_domain->dismiss(dev);
 	pm_runtime_reinit(dev);
diff --git a/drivers/base/power/common.c b/drivers/base/power/common.c
index fecb85fa85ac..6ecf9ce4a4e6 100644
--- a/drivers/base/power/common.c
+++ b/drivers/base/power/common.c
@@ -111,6 +111,9 @@ int dev_pm_domain_attach(struct device *dev, u32 flags)
 	if (!ret)
 		ret = genpd_dev_pm_attach(dev);
 
+	if (dev->pm_domain)
+		dev->power.detach_power_off = !!(flags & PD_FLAG_DETACH_POWER_OFF);
+
 	return ret < 0 ? ret : 0;
 }
 EXPORT_SYMBOL_GPL(dev_pm_domain_attach);
diff --git a/include/linux/pm.h b/include/linux/pm.h
index 938b1b446a5d..14e8370887e3 100644
--- a/include/linux/pm.h
+++ b/include/linux/pm.h
@@ -721,6 +721,7 @@ struct dev_pm_info {
 	struct pm_subsys_data	*subsys_data;  /* Owned by the subsystem. */
 	void (*set_latency_tolerance)(struct device *, s32);
 	struct dev_pm_qos	*qos;
+	bool			detach_power_off:1;	/* Owned by the driver core */
 };
 
 extern int dev_pm_get_subsys_data(struct device *dev);
-- 
cgit v1.2.3


From a683a5b2ba23598ad343e5ec10a4ef4077497fc9 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 2 Jul 2025 06:34:37 +0100
Subject: fold fs_struct->{lock,seq} into a seqlock

	The combination of spinlock_t lock and seqcount_spinlock_t seq
in struct fs_struct is an open-coded seqlock_t (see linux/seqlock_types.h).
	Combine and switch to equivalent seqlock_t primitives.  AFAICS,
that does end up with the same sequence of underlying operations in all
cases.
	While we are at it, get_fs_pwd() is open-coded verbatim in
get_path_from_fd(); rather than applying conversion to it, replace with
the call of get_fs_pwd() there.  Not worth splitting the commit for that,
IMO...

	A bit of historical background - conversion of seqlock_t to
use of seqcount_spinlock_t happened several months after the same
had been done to struct fs_struct; switching fs_struct to seqlock_t
could've been done immediately after that, but it looks like nobody
had gotten around to that until now.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/20250702053437.GC1880847@ZenIV
Acked-by: Ahmed S. Darwish <darwi@linutronix.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/d_path.c               |  8 ++++----
 fs/exec.c                 |  4 ++--
 fs/fhandle.c              |  6 +-----
 fs/fs_struct.c            | 36 ++++++++++++++----------------------
 fs/namei.c                |  8 ++++----
 include/linux/fs_struct.h | 11 +++++------
 kernel/fork.c             | 10 +++++-----
 7 files changed, 35 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/fs/d_path.c b/fs/d_path.c
index 5f4da5c8d5db..bb365511066b 100644
--- a/fs/d_path.c
+++ b/fs/d_path.c
@@ -241,9 +241,9 @@ static void get_fs_root_rcu(struct fs_struct *fs, struct path *root)
 	unsigned seq;
 
 	do {
-		seq = read_seqcount_begin(&fs->seq);
+		seq = read_seqbegin(&fs->seq);
 		*root = fs->root;
-	} while (read_seqcount_retry(&fs->seq, seq));
+	} while (read_seqretry(&fs->seq, seq));
 }
 
 /**
@@ -385,10 +385,10 @@ static void get_fs_root_and_pwd_rcu(struct fs_struct *fs, struct path *root,
 	unsigned seq;
 
 	do {
-		seq = read_seqcount_begin(&fs->seq);
+		seq = read_seqbegin(&fs->seq);
 		*root = fs->root;
 		*pwd = fs->pwd;
-	} while (read_seqcount_retry(&fs->seq, seq));
+	} while (read_seqretry(&fs->seq, seq));
 }
 
 /*
diff --git a/fs/exec.c b/fs/exec.c
index 1f5fdd2e096e..871078ddb220 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1510,7 +1510,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	 * state is protected by cred_guard_mutex we hold.
 	 */
 	n_fs = 1;
-	spin_lock(&p->fs->lock);
+	read_seqlock_excl(&p->fs->seq);
 	rcu_read_lock();
 	for_other_threads(p, t) {
 		if (t->fs == p->fs)
@@ -1523,7 +1523,7 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 		bprm->unsafe |= LSM_UNSAFE_SHARE;
 	else
 		p->fs->in_exec = 1;
-	spin_unlock(&p->fs->lock);
+	read_sequnlock_excl(&p->fs->seq);
 }
 
 static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
diff --git a/fs/fhandle.c b/fs/fhandle.c
index b1363ead6c5e..7c236f64cdea 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -180,11 +180,7 @@ static int get_path_anchor(int fd, struct path *root)
 	}
 
 	if (fd == AT_FDCWD) {
-		struct fs_struct *fs = current->fs;
-		spin_lock(&fs->lock);
-		*root = fs->pwd;
-		path_get(root);
-		spin_unlock(&fs->lock);
+		get_fs_pwd(current->fs, root);
 		return 0;
 	}
 
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 64c2d0814ed6..28be762ac1c6 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -17,12 +17,10 @@ void set_fs_root(struct fs_struct *fs, const struct path *path)
 	struct path old_root;
 
 	path_get(path);
-	spin_lock(&fs->lock);
-	write_seqcount_begin(&fs->seq);
+	write_seqlock(&fs->seq);
 	old_root = fs->root;
 	fs->root = *path;
-	write_seqcount_end(&fs->seq);
-	spin_unlock(&fs->lock);
+	write_sequnlock(&fs->seq);
 	if (old_root.dentry)
 		path_put(&old_root);
 }
@@ -36,12 +34,10 @@ void set_fs_pwd(struct fs_struct *fs, const struct path *path)
 	struct path old_pwd;
 
 	path_get(path);
-	spin_lock(&fs->lock);
-	write_seqcount_begin(&fs->seq);
+	write_seqlock(&fs->seq);
 	old_pwd = fs->pwd;
 	fs->pwd = *path;
-	write_seqcount_end(&fs->seq);
-	spin_unlock(&fs->lock);
+	write_sequnlock(&fs->seq);
 
 	if (old_pwd.dentry)
 		path_put(&old_pwd);
@@ -67,16 +63,14 @@ void chroot_fs_refs(const struct path *old_root, const struct path *new_root)
 		fs = p->fs;
 		if (fs) {
 			int hits = 0;
-			spin_lock(&fs->lock);
-			write_seqcount_begin(&fs->seq);
+			write_seqlock(&fs->seq);
 			hits += replace_path(&fs->root, old_root, new_root);
 			hits += replace_path(&fs->pwd, old_root, new_root);
-			write_seqcount_end(&fs->seq);
 			while (hits--) {
 				count++;
 				path_get(new_root);
 			}
-			spin_unlock(&fs->lock);
+			write_sequnlock(&fs->seq);
 		}
 		task_unlock(p);
 	}
@@ -99,10 +93,10 @@ void exit_fs(struct task_struct *tsk)
 	if (fs) {
 		int kill;
 		task_lock(tsk);
-		spin_lock(&fs->lock);
+		read_seqlock_excl(&fs->seq);
 		tsk->fs = NULL;
 		kill = !--fs->users;
-		spin_unlock(&fs->lock);
+		read_sequnlock_excl(&fs->seq);
 		task_unlock(tsk);
 		if (kill)
 			free_fs_struct(fs);
@@ -116,16 +110,15 @@ struct fs_struct *copy_fs_struct(struct fs_struct *old)
 	if (fs) {
 		fs->users = 1;
 		fs->in_exec = 0;
-		spin_lock_init(&fs->lock);
-		seqcount_spinlock_init(&fs->seq, &fs->lock);
+		seqlock_init(&fs->seq);
 		fs->umask = old->umask;
 
-		spin_lock(&old->lock);
+		read_seqlock_excl(&old->seq);
 		fs->root = old->root;
 		path_get(&fs->root);
 		fs->pwd = old->pwd;
 		path_get(&fs->pwd);
-		spin_unlock(&old->lock);
+		read_sequnlock_excl(&old->seq);
 	}
 	return fs;
 }
@@ -140,10 +133,10 @@ int unshare_fs_struct(void)
 		return -ENOMEM;
 
 	task_lock(current);
-	spin_lock(&fs->lock);
+	read_seqlock_excl(&fs->seq);
 	kill = !--fs->users;
 	current->fs = new_fs;
-	spin_unlock(&fs->lock);
+	read_sequnlock_excl(&fs->seq);
 	task_unlock(current);
 
 	if (kill)
@@ -162,7 +155,6 @@ EXPORT_SYMBOL(current_umask);
 /* to be mentioned only in INIT_TASK */
 struct fs_struct init_fs = {
 	.users		= 1,
-	.lock		= __SPIN_LOCK_UNLOCKED(init_fs.lock),
-	.seq		= SEQCNT_SPINLOCK_ZERO(init_fs.seq, &init_fs.lock),
+	.seq		= __SEQLOCK_UNLOCKED(init_fs.seq),
 	.umask		= 0022,
 };
diff --git a/fs/namei.c b/fs/namei.c
index 4bb889fc980b..f2fcaf84e111 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -1012,10 +1012,10 @@ static int set_root(struct nameidata *nd)
 		unsigned seq;
 
 		do {
-			seq = read_seqcount_begin(&fs->seq);
+			seq = read_seqbegin(&fs->seq);
 			nd->root = fs->root;
 			nd->root_seq = __read_seqcount_begin(&nd->root.dentry->d_seq);
-		} while (read_seqcount_retry(&fs->seq, seq));
+		} while (read_seqretry(&fs->seq, seq));
 	} else {
 		get_fs_root(fs, &nd->root);
 		nd->state |= ND_ROOT_GRABBED;
@@ -2580,11 +2580,11 @@ static const char *path_init(struct nameidata *nd, unsigned flags)
 			unsigned seq;
 
 			do {
-				seq = read_seqcount_begin(&fs->seq);
+				seq = read_seqbegin(&fs->seq);
 				nd->path = fs->pwd;
 				nd->inode = nd->path.dentry->d_inode;
 				nd->seq = __read_seqcount_begin(&nd->path.dentry->d_seq);
-			} while (read_seqcount_retry(&fs->seq, seq));
+			} while (read_seqretry(&fs->seq, seq));
 		} else {
 			get_fs_pwd(current->fs, &nd->path);
 			nd->inode = nd->path.dentry->d_inode;
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 783b48dedb72..baf200ab5c77 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -8,8 +8,7 @@
 
 struct fs_struct {
 	int users;
-	spinlock_t lock;
-	seqcount_spinlock_t seq;
+	seqlock_t seq;
 	int umask;
 	int in_exec;
 	struct path root, pwd;
@@ -26,18 +25,18 @@ extern int unshare_fs_struct(void);
 
 static inline void get_fs_root(struct fs_struct *fs, struct path *root)
 {
-	spin_lock(&fs->lock);
+	read_seqlock_excl(&fs->seq);
 	*root = fs->root;
 	path_get(root);
-	spin_unlock(&fs->lock);
+	read_sequnlock_excl(&fs->seq);
 }
 
 static inline void get_fs_pwd(struct fs_struct *fs, struct path *pwd)
 {
-	spin_lock(&fs->lock);
+	read_seqlock_excl(&fs->seq);
 	*pwd = fs->pwd;
 	path_get(pwd);
-	spin_unlock(&fs->lock);
+	read_sequnlock_excl(&fs->seq);
 }
 
 extern bool current_chrooted(void);
diff --git a/kernel/fork.c b/kernel/fork.c
index 1ee8eb11f38b..6318a25a16ba 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1542,14 +1542,14 @@ static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 	struct fs_struct *fs = current->fs;
 	if (clone_flags & CLONE_FS) {
 		/* tsk->fs is already what we want */
-		spin_lock(&fs->lock);
+		read_seqlock_excl(&fs->seq);
 		/* "users" and "in_exec" locked for check_unsafe_exec() */
 		if (fs->in_exec) {
-			spin_unlock(&fs->lock);
+			read_sequnlock_excl(&fs->seq);
 			return -EAGAIN;
 		}
 		fs->users++;
-		spin_unlock(&fs->lock);
+		read_sequnlock_excl(&fs->seq);
 		return 0;
 	}
 	tsk->fs = copy_fs_struct(fs);
@@ -3149,13 +3149,13 @@ int ksys_unshare(unsigned long unshare_flags)
 
 		if (new_fs) {
 			fs = current->fs;
-			spin_lock(&fs->lock);
+			read_seqlock_excl(&fs->seq);
 			current->fs = new_fs;
 			if (--fs->users)
 				new_fs = NULL;
 			else
 				new_fs = fs;
-			spin_unlock(&fs->lock);
+			read_sequnlock_excl(&fs->seq);
 		}
 
 		if (new_fd)
-- 
cgit v1.2.3


From 25489a4f556414445d342951615178368ee45cde Mon Sep 17 00:00:00 2001
From: Michal Luczaj <mhal@rbox.co>
Date: Wed, 2 Jul 2025 15:38:08 +0200
Subject: net: splice: Drop unused @gfp

Since its introduction in commit 2e910b95329c ("net: Add a function to
splice pages into an skbuff for MSG_SPLICE_PAGES"), skb_splice_from_iter()
never used the @gfp argument. Remove it and adapt callers.

No functional change intended.

Reviewed-by: Simon Horman <horms@kernel.org>
Signed-off-by: Michal Luczaj <mhal@rbox.co>
Link: https://patch.msgid.link/20250702-splice-drop-unused-v3-2-55f68b60d2b7@rbox.co
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c | 3 +--
 include/linux/skbuff.h                                      | 2 +-
 net/core/skbuff.c                                           | 3 +--
 net/ipv4/ip_output.c                                        | 3 +--
 net/ipv4/tcp.c                                              | 3 +--
 net/ipv6/ip6_output.c                                       | 3 +--
 net/kcm/kcmsock.c                                           | 3 +--
 net/unix/af_unix.c                                          | 3 +--
 8 files changed, 8 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
index d567e42e1760..465fa8077964 100644
--- a/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
+++ b/drivers/net/ethernet/chelsio/inline_crypto/chtls/chtls_io.c
@@ -1096,8 +1096,7 @@ new_buf:
 			copy = size;
 
 		if (msg->msg_flags & MSG_SPLICE_PAGES) {
-			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
-						   sk->sk_allocation);
+			err = skb_splice_from_iter(skb, &msg->msg_iter, copy);
 			if (err < 0) {
 				if (err == -EMSGSIZE)
 					goto new_buf;
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index 4f6dcb37bae8..b8b06e71b73e 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -5265,7 +5265,7 @@ static inline void skb_mark_for_recycle(struct sk_buff *skb)
 }
 
 ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
-			     ssize_t maxsize, gfp_t gfp);
+			     ssize_t maxsize);
 
 #endif	/* __KERNEL__ */
 #endif	/* _LINUX_SKBUFF_H */
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index ae0f1aae3c91..a34fe37cf7a5 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -7230,7 +7230,6 @@ static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
  * @skb: The buffer to add pages to
  * @iter: Iterator representing the pages to be added
  * @maxsize: Maximum amount of pages to be added
- * @gfp: Allocation flags
  *
  * This is a common helper function for supporting MSG_SPLICE_PAGES.  It
  * extracts pages from an iterator and adds them to the socket buffer if
@@ -7241,7 +7240,7 @@ static void skb_splice_csum_page(struct sk_buff *skb, struct page *page,
  * insufficient space in the buffer to transfer anything.
  */
 ssize_t skb_splice_from_iter(struct sk_buff *skb, struct iov_iter *iter,
-			     ssize_t maxsize, gfp_t gfp)
+			     ssize_t maxsize)
 {
 	size_t frag_limit = READ_ONCE(net_hotdata.sysctl_max_skb_frags);
 	struct page *pages[8], **ppages = pages;
diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c
index 414b47a0d513..10a1d182fd84 100644
--- a/net/ipv4/ip_output.c
+++ b/net/ipv4/ip_output.c
@@ -1222,8 +1222,7 @@ alloc_new_skb:
 			if (WARN_ON_ONCE(copy > msg->msg_iter.count))
 				goto error;
 
-			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
-						   sk->sk_allocation);
+			err = skb_splice_from_iter(skb, &msg->msg_iter, copy);
 			if (err < 0)
 				goto error;
 			copy = err;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 925b2c572ca2..860223c6f124 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1295,8 +1295,7 @@ new_segment:
 			if (!copy)
 				goto wait_for_space;
 
-			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
-						   sk->sk_allocation);
+			err = skb_splice_from_iter(skb, &msg->msg_iter, copy);
 			if (err < 0) {
 				if (err == -EMSGSIZE) {
 					tcp_mark_push(tp, skb);
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 877bee7ffee9..fcc20c7250eb 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1762,8 +1762,7 @@ alloc_new_skb:
 			if (WARN_ON_ONCE(copy > msg->msg_iter.count))
 				goto error;
 
-			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
-						   sk->sk_allocation);
+			err = skb_splice_from_iter(skb, &msg->msg_iter, copy);
 			if (err < 0)
 				goto error;
 			copy = err;
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 24aec295a51c..a0be3896a934 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -835,8 +835,7 @@ start:
 			if (!sk_wmem_schedule(sk, copy))
 				goto wait_for_memory;
 
-			err = skb_splice_from_iter(skb, &msg->msg_iter, copy,
-						   sk->sk_allocation);
+			err = skb_splice_from_iter(skb, &msg->msg_iter, copy);
 			if (err < 0) {
 				if (err == -EMSGSIZE)
 					goto wait_for_memory;
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 564c970d97ff..cd0d582bc7d4 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -2388,8 +2388,7 @@ static int unix_stream_sendmsg(struct socket *sock, struct msghdr *msg,
 
 		if (unlikely(msg->msg_flags & MSG_SPLICE_PAGES)) {
 			skb->ip_summed = CHECKSUM_UNNECESSARY;
-			err = skb_splice_from_iter(skb, &msg->msg_iter, size,
-						   sk->sk_allocation);
+			err = skb_splice_from_iter(skb, &msg->msg_iter, size);
 			if (err < 0)
 				goto out_free;
 
-- 
cgit v1.2.3


From c523058713abac66b0d83ae12a0574d76cd7df2b Mon Sep 17 00:00:00 2001
From: Heiner Kallweit <hkallweit1@gmail.com>
Date: Thu, 3 Jul 2025 07:55:52 +0200
Subject: net: phy: declare package-related struct members only if
 CONFIG_PHY_PACKAGE is enabled

Now that we have an own config symbol for the PHY package module,
we can use it to reduce size of these structs if it isn't enabled.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://patch.msgid.link/f0daefa4-406a-4a06-a4f0-7e31309f82bc@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/phy.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/phy.h b/include/linux/phy.h
index 74c1bcf64b3c..543a94751a6b 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -409,8 +409,10 @@ struct mii_bus {
 	/** @shared_lock: protect access to the shared element */
 	struct mutex shared_lock;
 
+#if IS_ENABLED(CONFIG_PHY_PACKAGE)
 	/** @shared: shared state across different PHYs */
 	struct phy_package_shared *shared[PHY_MAX_ADDR];
+#endif
 };
 #define to_mii_bus(d) container_of(d, struct mii_bus, dev)
 
@@ -718,9 +720,11 @@ struct phy_device {
 	/* For use by PHYs to maintain extra state */
 	void *priv;
 
+#if IS_ENABLED(CONFIG_PHY_PACKAGE)
 	/* shared data pointer */
 	/* For use by PHYs inside the same package that need a shared state. */
 	struct phy_package_shared *shared;
+#endif
 
 	/* Reporting cable test results */
 	struct sk_buff *skb;
-- 
cgit v1.2.3


From e7d4c1c5a54648fd5b787a4a0f81521ec7260bcd Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 8 Jul 2025 17:54:49 +0200
Subject: virtio: introduce extended features

The virtio specifications allows for up to 128 bits for the
device features. Soon we are going to use some of the 'extended'
bits features (above 64) for the virtio_net driver.

Introduce extended features as a fixed size array of u64. To minimize
the diffstat allows legacy driver to access the low 64 bits via a
transparent union.

Introduce an extended get_extended_features configuration callback
that devices supporting the extended features range must implement in
place of the traditional one.

Note that legacy and transport features don't need any change, as
they are always in the low 64 bit range.

Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/virtio/virtio.c         | 43 ++++++++++++--------
 drivers/virtio/virtio_debug.c   | 27 +++++++------
 include/linux/virtio.h          |  9 +++--
 include/linux/virtio_config.h   | 43 ++++++++++----------
 include/linux/virtio_features.h | 88 +++++++++++++++++++++++++++++++++++++++++
 5 files changed, 156 insertions(+), 54 deletions(-)
 create mode 100644 include/linux/virtio_features.h

(limited to 'include/linux')

diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c
index 95d5d7993e5b..5c48788cdbec 100644
--- a/drivers/virtio/virtio.c
+++ b/drivers/virtio/virtio.c
@@ -53,7 +53,7 @@ static ssize_t features_show(struct device *_d,
 
 	/* We actually represent this as a bitstring, as it could be
 	 * arbitrary length in future. */
-	for (i = 0; i < sizeof(dev->features)*8; i++)
+	for (i = 0; i < VIRTIO_FEATURES_MAX; i++)
 		len += sysfs_emit_at(buf, len, "%c",
 			       __virtio_test_bit(dev, i) ? '1' : '0');
 	len += sysfs_emit_at(buf, len, "\n");
@@ -272,22 +272,22 @@ static int virtio_dev_probe(struct device *_d)
 	int err, i;
 	struct virtio_device *dev = dev_to_virtio(_d);
 	struct virtio_driver *drv = drv_to_virtio(dev->dev.driver);
-	u64 device_features;
-	u64 driver_features;
+	u64 device_features[VIRTIO_FEATURES_DWORDS];
+	u64 driver_features[VIRTIO_FEATURES_DWORDS];
 	u64 driver_features_legacy;
 
 	/* We have a driver! */
 	virtio_add_status(dev, VIRTIO_CONFIG_S_DRIVER);
 
 	/* Figure out what features the device supports. */
-	device_features = dev->config->get_features(dev);
+	virtio_get_features(dev, device_features);
 
 	/* Figure out what features the driver supports. */
-	driver_features = 0;
+	virtio_features_zero(driver_features);
 	for (i = 0; i < drv->feature_table_size; i++) {
 		unsigned int f = drv->feature_table[i];
-		BUG_ON(f >= 64);
-		driver_features |= (1ULL << f);
+		if (!WARN_ON_ONCE(f >= VIRTIO_FEATURES_MAX))
+			virtio_features_set_bit(driver_features, f);
 	}
 
 	/* Some drivers have a separate feature table for virtio v1.0 */
@@ -295,24 +295,29 @@ static int virtio_dev_probe(struct device *_d)
 		driver_features_legacy = 0;
 		for (i = 0; i < drv->feature_table_size_legacy; i++) {
 			unsigned int f = drv->feature_table_legacy[i];
-			BUG_ON(f >= 64);
-			driver_features_legacy |= (1ULL << f);
+			if (!WARN_ON_ONCE(f >= 64))
+				driver_features_legacy |= (1ULL << f);
 		}
 	} else {
-		driver_features_legacy = driver_features;
+		driver_features_legacy = driver_features[0];
 	}
 
-	if (device_features & (1ULL << VIRTIO_F_VERSION_1))
-		dev->features = driver_features & device_features;
-	else
-		dev->features = driver_features_legacy & device_features;
+	if (virtio_features_test_bit(device_features, VIRTIO_F_VERSION_1)) {
+		for (i = 0; i < VIRTIO_FEATURES_DWORDS; ++i)
+			dev->features_array[i] = driver_features[i] &
+						 device_features[i];
+	} else {
+		virtio_features_from_u64(dev->features_array,
+					 driver_features_legacy &
+					 device_features[0]);
+	}
 
 	/* When debugging, user may filter some features by hand. */
 	virtio_debug_device_filter_features(dev);
 
 	/* Transport features always preserved to pass to finalize_features. */
 	for (i = VIRTIO_TRANSPORT_F_START; i < VIRTIO_TRANSPORT_F_END; i++)
-		if (device_features & (1ULL << i))
+		if (virtio_features_test_bit(device_features, i))
 			__virtio_set_bit(dev, i);
 
 	err = dev->config->finalize_features(dev);
@@ -320,14 +325,15 @@ static int virtio_dev_probe(struct device *_d)
 		goto err;
 
 	if (drv->validate) {
-		u64 features = dev->features;
+		u64 features[VIRTIO_FEATURES_DWORDS];
 
+		virtio_features_copy(features, dev->features_array);
 		err = drv->validate(dev);
 		if (err)
 			goto err;
 
 		/* Did validation change any features? Then write them again. */
-		if (features != dev->features) {
+		if (!virtio_features_equal(features, dev->features_array)) {
 			err = dev->config->finalize_features(dev);
 			if (err)
 				goto err;
@@ -701,6 +707,9 @@ EXPORT_SYMBOL_GPL(virtio_device_reset_done);
 
 static int virtio_init(void)
 {
+	BUILD_BUG_ON(offsetof(struct virtio_device, features) !=
+		     offsetof(struct virtio_device, features_array[0]));
+
 	if (bus_register(&virtio_bus) != 0)
 		panic("virtio bus registration failed");
 	virtio_debug_init();
diff --git a/drivers/virtio/virtio_debug.c b/drivers/virtio/virtio_debug.c
index 95c8fc7705bb..d58713ddf2e5 100644
--- a/drivers/virtio/virtio_debug.c
+++ b/drivers/virtio/virtio_debug.c
@@ -8,13 +8,13 @@ static struct dentry *virtio_debugfs_dir;
 
 static int virtio_debug_device_features_show(struct seq_file *s, void *data)
 {
+	u64 device_features[VIRTIO_FEATURES_DWORDS];
 	struct virtio_device *dev = s->private;
-	u64 device_features;
 	unsigned int i;
 
-	device_features = dev->config->get_features(dev);
-	for (i = 0; i < BITS_PER_LONG_LONG; i++) {
-		if (device_features & (1ULL << i))
+	virtio_get_features(dev, device_features);
+	for (i = 0; i < VIRTIO_FEATURES_MAX; i++) {
+		if (virtio_features_test_bit(device_features, i))
 			seq_printf(s, "%u\n", i);
 	}
 	return 0;
@@ -26,8 +26,8 @@ static int virtio_debug_filter_features_show(struct seq_file *s, void *data)
 	struct virtio_device *dev = s->private;
 	unsigned int i;
 
-	for (i = 0; i < BITS_PER_LONG_LONG; i++) {
-		if (dev->debugfs_filter_features & (1ULL << i))
+	for (i = 0; i < VIRTIO_FEATURES_MAX; i++) {
+		if (virtio_features_test_bit(dev->debugfs_filter_features, i))
 			seq_printf(s, "%u\n", i);
 	}
 	return 0;
@@ -39,7 +39,7 @@ static int virtio_debug_filter_features_clear(void *data, u64 val)
 	struct virtio_device *dev = data;
 
 	if (val == 1)
-		dev->debugfs_filter_features = 0;
+		virtio_features_zero(dev->debugfs_filter_features);
 	return 0;
 }
 
@@ -50,9 +50,10 @@ static int virtio_debug_filter_feature_add(void *data, u64 val)
 {
 	struct virtio_device *dev = data;
 
-	if (val >= BITS_PER_LONG_LONG)
+	if (val >= VIRTIO_FEATURES_MAX)
 		return -EINVAL;
-	dev->debugfs_filter_features |= BIT_ULL_MASK(val);
+
+	virtio_features_set_bit(dev->debugfs_filter_features, val);
 	return 0;
 }
 
@@ -63,9 +64,10 @@ static int virtio_debug_filter_feature_del(void *data, u64 val)
 {
 	struct virtio_device *dev = data;
 
-	if (val >= BITS_PER_LONG_LONG)
+	if (val >= VIRTIO_FEATURES_MAX)
 		return -EINVAL;
-	dev->debugfs_filter_features &= ~BIT_ULL_MASK(val);
+
+	virtio_features_clear_bit(dev->debugfs_filter_features, val);
 	return 0;
 }
 
@@ -91,7 +93,8 @@ EXPORT_SYMBOL_GPL(virtio_debug_device_init);
 
 void virtio_debug_device_filter_features(struct virtio_device *dev)
 {
-	dev->features &= ~dev->debugfs_filter_features;
+	virtio_features_andnot(dev->features_array, dev->features_array,
+			       dev->debugfs_filter_features);
 }
 EXPORT_SYMBOL_GPL(virtio_debug_device_filter_features);
 
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 64cb4b04be7a..04b90c88d164 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -11,6 +11,7 @@
 #include <linux/gfp.h>
 #include <linux/dma-mapping.h>
 #include <linux/completion.h>
+#include <linux/virtio_features.h>
 
 /**
  * struct virtqueue - a queue to register buffers for sending or receiving.
@@ -141,7 +142,9 @@ struct virtio_admin_cmd {
  * @config: the configuration ops for this device.
  * @vringh_config: configuration ops for host vrings.
  * @vqs: the list of virtqueues for this device.
- * @features: the features supported by both driver and device.
+ * @features: the 64 lower features supported by both driver and device.
+ * @features_array: the full features space supported by both driver and
+ *		    device.
  * @priv: private pointer for the driver's use.
  * @debugfs_dir: debugfs directory entry.
  * @debugfs_filter_features: features to be filtered set by debugfs.
@@ -159,11 +162,11 @@ struct virtio_device {
 	const struct virtio_config_ops *config;
 	const struct vringh_config_ops *vringh_config;
 	struct list_head vqs;
-	u64 features;
+	VIRTIO_DECLARE_FEATURES(features);
 	void *priv;
 #ifdef CONFIG_VIRTIO_DEBUG
 	struct dentry *debugfs_dir;
-	u64 debugfs_filter_features;
+	u64 debugfs_filter_features[VIRTIO_FEATURES_DWORDS];
 #endif
 };
 
diff --git a/include/linux/virtio_config.h b/include/linux/virtio_config.h
index b3e1d30c765b..918cf25cd3c6 100644
--- a/include/linux/virtio_config.h
+++ b/include/linux/virtio_config.h
@@ -77,7 +77,11 @@ struct virtqueue_info {
  *      vdev: the virtio_device
  * @get_features: get the array of feature bits for this device.
  *	vdev: the virtio_device
- *	Returns the first 64 feature bits (all we currently need).
+ *	Returns the first 64 feature bits.
+ * @get_extended_features:
+ *      vdev: the virtio_device
+ *      Returns the first VIRTIO_FEATURES_MAX feature bits (all we currently
+ *      need).
  * @finalize_features: confirm what device features we'll be using.
  *	vdev: the virtio_device
  *	This sends the driver feature bits to the device: it can change
@@ -121,6 +125,8 @@ struct virtio_config_ops {
 	void (*del_vqs)(struct virtio_device *);
 	void (*synchronize_cbs)(struct virtio_device *);
 	u64 (*get_features)(struct virtio_device *vdev);
+	void (*get_extended_features)(struct virtio_device *vdev,
+				      u64 *features);
 	int (*finalize_features)(struct virtio_device *vdev);
 	const char *(*bus_name)(struct virtio_device *vdev);
 	int (*set_vq_affinity)(struct virtqueue *vq,
@@ -147,13 +153,7 @@ void virtio_check_driver_offered_feature(const struct virtio_device *vdev,
 static inline bool __virtio_test_bit(const struct virtio_device *vdev,
 				     unsigned int fbit)
 {
-	/* Did you forget to fix assumptions on max features? */
-	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 64);
-	else
-		BUG_ON(fbit >= 64);
-
-	return vdev->features & BIT_ULL(fbit);
+	return virtio_features_test_bit(vdev->features_array, fbit);
 }
 
 /**
@@ -164,13 +164,7 @@ static inline bool __virtio_test_bit(const struct virtio_device *vdev,
 static inline void __virtio_set_bit(struct virtio_device *vdev,
 				    unsigned int fbit)
 {
-	/* Did you forget to fix assumptions on max features? */
-	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 64);
-	else
-		BUG_ON(fbit >= 64);
-
-	vdev->features |= BIT_ULL(fbit);
+	virtio_features_set_bit(vdev->features_array, fbit);
 }
 
 /**
@@ -181,13 +175,7 @@ static inline void __virtio_set_bit(struct virtio_device *vdev,
 static inline void __virtio_clear_bit(struct virtio_device *vdev,
 				      unsigned int fbit)
 {
-	/* Did you forget to fix assumptions on max features? */
-	if (__builtin_constant_p(fbit))
-		BUILD_BUG_ON(fbit >= 64);
-	else
-		BUG_ON(fbit >= 64);
-
-	vdev->features &= ~BIT_ULL(fbit);
+	virtio_features_clear_bit(vdev->features_array, fbit);
 }
 
 /**
@@ -204,6 +192,17 @@ static inline bool virtio_has_feature(const struct virtio_device *vdev,
 	return __virtio_test_bit(vdev, fbit);
 }
 
+static inline void virtio_get_features(struct virtio_device *vdev,
+				       u64 *features)
+{
+	if (vdev->config->get_extended_features) {
+		vdev->config->get_extended_features(vdev, features);
+		return;
+	}
+
+	virtio_features_from_u64(features, vdev->config->get_features(vdev));
+}
+
 /**
  * virtio_has_dma_quirk - determine whether this device has the DMA quirk
  * @vdev: the device
diff --git a/include/linux/virtio_features.h b/include/linux/virtio_features.h
new file mode 100644
index 000000000000..f748f2f87de8
--- /dev/null
+++ b/include/linux/virtio_features.h
@@ -0,0 +1,88 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VIRTIO_FEATURES_H
+#define _LINUX_VIRTIO_FEATURES_H
+
+#include <linux/bits.h>
+
+#define VIRTIO_FEATURES_DWORDS	2
+#define VIRTIO_FEATURES_MAX	(VIRTIO_FEATURES_DWORDS * 64)
+#define VIRTIO_FEATURES_WORDS	(VIRTIO_FEATURES_DWORDS * 2)
+#define VIRTIO_BIT(b)		BIT_ULL((b) & 0x3f)
+#define VIRTIO_DWORD(b)		((b) >> 6)
+#define VIRTIO_DECLARE_FEATURES(name)			\
+	union {						\
+		u64 name;				\
+		u64 name##_array[VIRTIO_FEATURES_DWORDS];\
+	}
+
+static inline bool virtio_features_chk_bit(unsigned int bit)
+{
+	if (__builtin_constant_p(bit)) {
+		/*
+		 * Don't care returning the correct value: the build
+		 * will fail before any bad features access
+		 */
+		BUILD_BUG_ON(bit >= VIRTIO_FEATURES_MAX);
+	} else {
+		if (WARN_ON_ONCE(bit >= VIRTIO_FEATURES_MAX))
+			return false;
+	}
+	return true;
+}
+
+static inline bool virtio_features_test_bit(const u64 *features,
+					    unsigned int bit)
+{
+	return virtio_features_chk_bit(bit) &&
+	       !!(features[VIRTIO_DWORD(bit)] & VIRTIO_BIT(bit));
+}
+
+static inline void virtio_features_set_bit(u64 *features,
+					   unsigned int bit)
+{
+	if (virtio_features_chk_bit(bit))
+		features[VIRTIO_DWORD(bit)] |= VIRTIO_BIT(bit);
+}
+
+static inline void virtio_features_clear_bit(u64 *features,
+					     unsigned int bit)
+{
+	if (virtio_features_chk_bit(bit))
+		features[VIRTIO_DWORD(bit)] &= ~VIRTIO_BIT(bit);
+}
+
+static inline void virtio_features_zero(u64 *features)
+{
+	memset(features, 0, sizeof(features[0]) * VIRTIO_FEATURES_DWORDS);
+}
+
+static inline void virtio_features_from_u64(u64 *features, u64 from)
+{
+	virtio_features_zero(features);
+	features[0] = from;
+}
+
+static inline bool virtio_features_equal(const u64 *f1, const u64 *f2)
+{
+	int i;
+
+	for (i = 0; i < VIRTIO_FEATURES_DWORDS; ++i)
+		if (f1[i] != f2[i])
+			return false;
+	return true;
+}
+
+static inline void virtio_features_copy(u64 *to, const u64 *from)
+{
+	memcpy(to, from, sizeof(to[0]) * VIRTIO_FEATURES_DWORDS);
+}
+
+static inline void virtio_features_andnot(u64 *to, const u64 *f1, const u64 *f2)
+{
+	int i;
+
+	for (i = 0; i < VIRTIO_FEATURES_DWORDS; i++)
+		to[i] = f1[i] & ~f2[i];
+}
+
+#endif
-- 
cgit v1.2.3


From 69b9461512246599ed80cf13358e7e6aff7285f9 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 8 Jul 2025 17:54:52 +0200
Subject: virtio_pci_modern: allow configuring extended features

The virtio specifications allows for up to 128 bits for the
device features. Soon we are going to use some of the 'extended'
bits features (above 64) for the virtio_net driver.

Extend the virtio pci modern driver to support configuring the full
virtio features range, replacing the unrolled loops reading and
writing the features space with explicit one bounded to the actual
features space size in word and implementing the get_extended_features
callback.

Note that in vp_finalize_features() we only need to cache the lower
64 features bits, to process the transport features.

Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/virtio/virtio_pci_modern.c     | 10 ++---
 drivers/virtio/virtio_pci_modern_dev.c | 69 ++++++++++++++++++++--------------
 include/linux/virtio_pci_modern.h      | 43 +++++++++++++++++++--
 3 files changed, 84 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c
index 7182f43ed055..dd0e65f71d41 100644
--- a/drivers/virtio/virtio_pci_modern.c
+++ b/drivers/virtio/virtio_pci_modern.c
@@ -22,11 +22,11 @@
 
 #define VIRTIO_AVQ_SGS_MAX	4
 
-static u64 vp_get_features(struct virtio_device *vdev)
+static void vp_get_features(struct virtio_device *vdev, u64 *features)
 {
 	struct virtio_pci_device *vp_dev = to_vp_device(vdev);
 
-	return vp_modern_get_features(&vp_dev->mdev);
+	vp_modern_get_extended_features(&vp_dev->mdev, features);
 }
 
 static int vp_avq_index(struct virtio_device *vdev, u16 *index, u16 *num)
@@ -437,7 +437,7 @@ static int vp_finalize_features(struct virtio_device *vdev)
 	if (vp_check_common_size(vdev))
 		return -EINVAL;
 
-	vp_modern_set_features(&vp_dev->mdev, vdev->features);
+	vp_modern_set_extended_features(&vp_dev->mdev, vdev->features_array);
 
 	return 0;
 }
@@ -1234,7 +1234,7 @@ static const struct virtio_config_ops virtio_pci_config_nodev_ops = {
 	.find_vqs	= vp_modern_find_vqs,
 	.del_vqs	= vp_del_vqs,
 	.synchronize_cbs = vp_synchronize_vectors,
-	.get_features	= vp_get_features,
+	.get_extended_features = vp_get_features,
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
@@ -1254,7 +1254,7 @@ static const struct virtio_config_ops virtio_pci_config_ops = {
 	.find_vqs	= vp_modern_find_vqs,
 	.del_vqs	= vp_del_vqs,
 	.synchronize_cbs = vp_synchronize_vectors,
-	.get_features	= vp_get_features,
+	.get_extended_features = vp_get_features,
 	.finalize_features = vp_finalize_features,
 	.bus_name	= vp_bus_name,
 	.set_vq_affinity = vp_set_vq_affinity,
diff --git a/drivers/virtio/virtio_pci_modern_dev.c b/drivers/virtio/virtio_pci_modern_dev.c
index 0d3dbfaf4b23..d665f8f73ea8 100644
--- a/drivers/virtio/virtio_pci_modern_dev.c
+++ b/drivers/virtio/virtio_pci_modern_dev.c
@@ -388,63 +388,74 @@ void vp_modern_remove(struct virtio_pci_modern_device *mdev)
 EXPORT_SYMBOL_GPL(vp_modern_remove);
 
 /*
- * vp_modern_get_features - get features from device
+ * vp_modern_get_extended_features - get features from device
  * @mdev: the modern virtio-pci device
+ * @features: the features array to be filled
  *
- * Returns the features read from the device
+ * Fill the specified features array with the features read from the device
  */
-u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev)
+void vp_modern_get_extended_features(struct virtio_pci_modern_device *mdev,
+				     u64 *features)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
 
-	u64 features;
+	virtio_features_zero(features);
+	for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) {
+		u64 cur;
 
-	vp_iowrite32(0, &cfg->device_feature_select);
-	features = vp_ioread32(&cfg->device_feature);
-	vp_iowrite32(1, &cfg->device_feature_select);
-	features |= ((u64)vp_ioread32(&cfg->device_feature) << 32);
-
-	return features;
+		vp_iowrite32(i, &cfg->device_feature_select);
+		cur = vp_ioread32(&cfg->device_feature);
+		features[i >> 1] |= cur << (32 * (i & 1));
+	}
 }
-EXPORT_SYMBOL_GPL(vp_modern_get_features);
+EXPORT_SYMBOL_GPL(vp_modern_get_extended_features);
 
 /*
  * vp_modern_get_driver_features - get driver features from device
  * @mdev: the modern virtio-pci device
+ * @features: the features array to be filled
  *
- * Returns the driver features read from the device
+ * Fill the specified features array with the driver features read from the
+ * device
  */
-u64 vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev)
+void
+vp_modern_get_driver_extended_features(struct virtio_pci_modern_device *mdev,
+				       u64 *features)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
 
-	u64 features;
-
-	vp_iowrite32(0, &cfg->guest_feature_select);
-	features = vp_ioread32(&cfg->guest_feature);
-	vp_iowrite32(1, &cfg->guest_feature_select);
-	features |= ((u64)vp_ioread32(&cfg->guest_feature) << 32);
+	virtio_features_zero(features);
+	for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) {
+		u64 cur;
 
-	return features;
+		vp_iowrite32(i, &cfg->guest_feature_select);
+		cur = vp_ioread32(&cfg->guest_feature);
+		features[i >> 1] |= cur << (32 * (i & 1));
+	}
 }
-EXPORT_SYMBOL_GPL(vp_modern_get_driver_features);
+EXPORT_SYMBOL_GPL(vp_modern_get_driver_extended_features);
 
 /*
- * vp_modern_set_features - set features to device
+ * vp_modern_set_extended_features - set features to device
  * @mdev: the modern virtio-pci device
  * @features: the features set to device
  */
-void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
-			    u64 features)
+void vp_modern_set_extended_features(struct virtio_pci_modern_device *mdev,
+				     const u64 *features)
 {
 	struct virtio_pci_common_cfg __iomem *cfg = mdev->common;
+	int i;
+
+	for (i = 0; i < VIRTIO_FEATURES_WORDS; i++) {
+		u32 cur = features[i >> 1] >> (32 * (i & 1));
 
-	vp_iowrite32(0, &cfg->guest_feature_select);
-	vp_iowrite32((u32)features, &cfg->guest_feature);
-	vp_iowrite32(1, &cfg->guest_feature_select);
-	vp_iowrite32(features >> 32, &cfg->guest_feature);
+		vp_iowrite32(i, &cfg->guest_feature_select);
+		vp_iowrite32(cur, &cfg->guest_feature);
+	}
 }
-EXPORT_SYMBOL_GPL(vp_modern_set_features);
+EXPORT_SYMBOL_GPL(vp_modern_set_extended_features);
 
 /*
  * vp_modern_generation - get the device genreation
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index c0b1b1ca1163..48bc12d1045b 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -3,6 +3,7 @@
 #define _LINUX_VIRTIO_PCI_MODERN_H
 
 #include <linux/pci.h>
+#include <linux/virtio_config.h>
 #include <linux/virtio_pci.h>
 
 /**
@@ -95,10 +96,44 @@ static inline void vp_iowrite64_twopart(u64 val,
 	vp_iowrite32(val >> 32, hi);
 }
 
-u64 vp_modern_get_features(struct virtio_pci_modern_device *mdev);
-u64 vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev);
-void vp_modern_set_features(struct virtio_pci_modern_device *mdev,
-		     u64 features);
+void
+vp_modern_get_driver_extended_features(struct virtio_pci_modern_device *mdev,
+				       u64 *features);
+void vp_modern_get_extended_features(struct virtio_pci_modern_device *mdev,
+				     u64 *features);
+void vp_modern_set_extended_features(struct virtio_pci_modern_device *mdev,
+				     const u64 *features);
+
+static inline u64
+vp_modern_get_features(struct virtio_pci_modern_device *mdev)
+{
+	u64 features_array[VIRTIO_FEATURES_DWORDS];
+
+	vp_modern_get_extended_features(mdev, features_array);
+	return features_array[0];
+}
+
+static inline u64
+vp_modern_get_driver_features(struct virtio_pci_modern_device *mdev)
+{
+	u64 features_array[VIRTIO_FEATURES_DWORDS];
+	int i;
+
+	vp_modern_get_driver_extended_features(mdev, features_array);
+	for (i = 1; i < VIRTIO_FEATURES_DWORDS; ++i)
+		WARN_ON_ONCE(features_array[i]);
+	return features_array[0];
+}
+
+static inline void
+vp_modern_set_features(struct virtio_pci_modern_device *mdev, u64 features)
+{
+	u64 features_array[VIRTIO_FEATURES_DWORDS];
+
+	virtio_features_from_u64(features_array, features);
+	vp_modern_set_extended_features(mdev, features_array);
+}
+
 u32 vp_modern_generation(struct virtio_pci_modern_device *mdev);
 u8 vp_modern_get_status(struct virtio_pci_modern_device *mdev);
 void vp_modern_set_status(struct virtio_pci_modern_device *mdev,
-- 
cgit v1.2.3


From a2fb4bc4e2a6a031683910d85b278c1d25ae5420 Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Tue, 8 Jul 2025 17:54:59 +0200
Subject: net: implement virtio helpers to handle UDP GSO tunneling.

The virtio specification are introducing support for GSO over UDP
tunnel.

This patch brings in the needed defines and the additional virtio hdr
parsing/building helpers.

The UDP tunnel support uses additional fields in the virtio hdr, and such
fields location can change depending on other negotiated features -
specifically VIRTIO_NET_F_HASH_REPORT.

Try to be as conservative as possible with the new field validation.

Existing implementation for plain GSO offloads allow for invalid/
self-contradictory values of such fields. With GSO over UDP tunnel we can
be more strict, with no need to deal with legacy implementation.

Since the checksum-related field validation is asymmetric in the driver
and in the device, introduce a separate helper to implement the new checks
(to be used only on the driver side).

Note that while the feature space exceeds the 64-bit boundaries, the
guest offload space is fixed by the specification of the
VIRTIO_NET_CTRL_GUEST_OFFLOADS_SET command to a 64-bit size.

Prior to the UDP tunnel GSO support, each guest offload bit corresponded
to the feature bit with the same value and vice versa.

Due to the limited 'guest offload' space, relevant features in the high
64 bits are 'mapped' to free bits in the lower range. That is simpler
than defining a new command (and associated features) to exchange an
extended guest offloads set.

As a consequence, the uAPIs also specify the mapped guest offload value
corresponding to the UDP tunnel GSO features.

Acked-by: Jason Wang <jasowang@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
--
v4 -> v5:
  - avoid lines above 80 chars

v3 -> v4:
  - fixed offset for UDP GSO tunnel, update accordingly the helpers
  - tried to clarified vlan_hlen semantic
  - virtio_net_chk_data_valid() -> virtio_net_handle_csum_offload()

v2 -> v3:
  - add definitions for possible vnet hdr layouts with tunnel support

v1 -> v2:
  - 'relay' -> 'rely' typo
  - less unclear comment WRT enforced inner GSO checks
  - inner header fields are allowed only with 'modern' virtio,
    thus are always le
  - clarified in the commit message the need for 'mapped features'
    defines
  - assume little_endian is true when UDP GSO is enabled.
  - fix inner proto type value
---
 include/linux/virtio_net.h      | 197 ++++++++++++++++++++++++++++++++++++++--
 include/uapi/linux/virtio_net.h |  33 +++++++
 2 files changed, 222 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
index 02a9f4dc594d..20e0584db1dd 100644
--- a/include/linux/virtio_net.h
+++ b/include/linux/virtio_net.h
@@ -47,9 +47,9 @@ static inline int virtio_net_hdr_set_proto(struct sk_buff *skb,
 	return 0;
 }
 
-static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
-					const struct virtio_net_hdr *hdr,
-					bool little_endian)
+static inline int __virtio_net_hdr_to_skb(struct sk_buff *skb,
+					  const struct virtio_net_hdr *hdr,
+					  bool little_endian, u8 hdr_gso_type)
 {
 	unsigned int nh_min_len = sizeof(struct iphdr);
 	unsigned int gso_type = 0;
@@ -57,8 +57,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 	unsigned int p_off = 0;
 	unsigned int ip_proto;
 
-	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
-		switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+	if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+		switch (hdr_gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
 		case VIRTIO_NET_HDR_GSO_TCPV4:
 			gso_type = SKB_GSO_TCPV4;
 			ip_proto = IPPROTO_TCP;
@@ -84,7 +84,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 			return -EINVAL;
 		}
 
-		if (hdr->gso_type & VIRTIO_NET_HDR_GSO_ECN)
+		if (hdr_gso_type & VIRTIO_NET_HDR_GSO_ECN)
 			gso_type |= SKB_GSO_TCP_ECN;
 
 		if (hdr->gso_size == 0)
@@ -122,7 +122,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
 
 				if (!protocol)
 					virtio_net_hdr_set_proto(skb, hdr);
-				else if (!virtio_net_hdr_match_proto(protocol, hdr->gso_type))
+				else if (!virtio_net_hdr_match_proto(protocol,
+								 hdr_gso_type))
 					return -EINVAL;
 				else
 					skb->protocol = protocol;
@@ -153,7 +154,7 @@ retry:
 		}
 	}
 
-	if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+	if (hdr_gso_type != VIRTIO_NET_HDR_GSO_NONE) {
 		u16 gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
 		unsigned int nh_off = p_off;
 		struct skb_shared_info *shinfo = skb_shinfo(skb);
@@ -199,6 +200,13 @@ retry:
 	return 0;
 }
 
+static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+					const struct virtio_net_hdr *hdr,
+					bool little_endian)
+{
+	return __virtio_net_hdr_to_skb(skb, hdr, little_endian, hdr->gso_type);
+}
+
 static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 					  struct virtio_net_hdr *hdr,
 					  bool little_endian,
@@ -242,4 +250,177 @@ static inline int virtio_net_hdr_from_skb(const struct sk_buff *skb,
 	return 0;
 }
 
+static inline unsigned int virtio_l3min(bool is_ipv6)
+{
+	return is_ipv6 ? sizeof(struct ipv6hdr) : sizeof(struct iphdr);
+}
+
+static inline int
+virtio_net_hdr_tnl_to_skb(struct sk_buff *skb,
+			  const struct virtio_net_hdr_v1_hash_tunnel *vhdr,
+			  bool tnl_hdr_negotiated,
+			  bool tnl_csum_negotiated,
+			  bool little_endian)
+{
+	const struct virtio_net_hdr *hdr = (const struct virtio_net_hdr *)vhdr;
+	unsigned int inner_nh, outer_th, inner_th;
+	unsigned int inner_l3min, outer_l3min;
+	u8 gso_inner_type, gso_tunnel_type;
+	bool outer_isv6, inner_isv6;
+	int ret;
+
+	gso_tunnel_type = hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL;
+	if (!gso_tunnel_type)
+		return virtio_net_hdr_to_skb(skb, hdr, little_endian);
+
+	/* Tunnel not supported/negotiated, but the hdr asks for it. */
+	if (!tnl_hdr_negotiated)
+		return -EINVAL;
+
+	/* Either ipv4 or ipv6. */
+	if (gso_tunnel_type == VIRTIO_NET_HDR_GSO_UDP_TUNNEL)
+		return -EINVAL;
+
+	/* The UDP tunnel must carry a GSO packet, but no UFO. */
+	gso_inner_type = hdr->gso_type & ~(VIRTIO_NET_HDR_GSO_ECN |
+					   VIRTIO_NET_HDR_GSO_UDP_TUNNEL);
+	if (!gso_inner_type || gso_inner_type == VIRTIO_NET_HDR_GSO_UDP)
+		return -EINVAL;
+
+	/* Rely on csum being present. */
+	if (!(hdr->flags & VIRTIO_NET_HDR_F_NEEDS_CSUM))
+		return -EINVAL;
+
+	/* Validate offsets. */
+	outer_isv6 = gso_tunnel_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6;
+	inner_isv6 = gso_inner_type == VIRTIO_NET_HDR_GSO_TCPV6;
+	inner_l3min = virtio_l3min(inner_isv6);
+	outer_l3min = ETH_HLEN + virtio_l3min(outer_isv6);
+
+	inner_th = __virtio16_to_cpu(little_endian, hdr->csum_start);
+	inner_nh = le16_to_cpu(vhdr->inner_nh_offset);
+	outer_th = le16_to_cpu(vhdr->outer_th_offset);
+	if (outer_th < outer_l3min ||
+	    inner_nh < outer_th + sizeof(struct udphdr) ||
+	    inner_th < inner_nh + inner_l3min)
+		return -EINVAL;
+
+	/* Let the basic parsing deal with plain GSO features. */
+	ret = __virtio_net_hdr_to_skb(skb, hdr, true,
+				      hdr->gso_type & ~gso_tunnel_type);
+	if (ret)
+		return ret;
+
+	/* In case of USO, the inner protocol is still unknown and
+	 * `inner_isv6` is just a guess, additional parsing is needed.
+	 * The previous validation ensures that accessing an ipv4 inner
+	 * network header is safe.
+	 */
+	if (gso_inner_type == VIRTIO_NET_HDR_GSO_UDP_L4) {
+		struct iphdr *iphdr = (struct iphdr *)(skb->data + inner_nh);
+
+		inner_isv6 = iphdr->version == 6;
+		inner_l3min = virtio_l3min(inner_isv6);
+		if (inner_th < inner_nh + inner_l3min)
+			return -EINVAL;
+	}
+
+	skb_set_inner_protocol(skb, inner_isv6 ? htons(ETH_P_IPV6) :
+						 htons(ETH_P_IP));
+	if (hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM) {
+		if (!tnl_csum_negotiated)
+			return -EINVAL;
+
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL_CSUM;
+	} else {
+		skb_shinfo(skb)->gso_type |= SKB_GSO_UDP_TUNNEL;
+	}
+
+	skb->inner_transport_header = inner_th + skb_headroom(skb);
+	skb->inner_network_header = inner_nh + skb_headroom(skb);
+	skb->inner_mac_header = inner_nh + skb_headroom(skb);
+	skb->transport_header = outer_th + skb_headroom(skb);
+	skb->encapsulation = 1;
+	return 0;
+}
+
+/* Checksum-related fields validation for the driver */
+static inline int virtio_net_handle_csum_offload(struct sk_buff *skb,
+						 struct virtio_net_hdr *hdr,
+						 bool tnl_csum_negotiated)
+{
+	if (!(hdr->gso_type & VIRTIO_NET_HDR_GSO_UDP_TUNNEL)) {
+		if (!(hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID))
+			return 0;
+
+		skb->ip_summed = CHECKSUM_UNNECESSARY;
+		if (!(hdr->flags & VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM))
+			return 0;
+
+		/* tunnel csum packets are invalid when the related
+		 * feature has not been negotiated
+		 */
+		if (!tnl_csum_negotiated)
+			return -EINVAL;
+		skb->csum_level = 1;
+		return 0;
+	}
+
+	/* DATA_VALID is mutually exclusive with NEEDS_CSUM, and GSO
+	 * over UDP tunnel requires the latter
+	 */
+	if (hdr->flags & VIRTIO_NET_HDR_F_DATA_VALID)
+		return -EINVAL;
+	return 0;
+}
+
+/*
+ * vlan_hlen always refers to the outermost MAC header. That also
+ * means it refers to the only MAC header, if the packet does not carry
+ * any encapsulation.
+ */
+static inline int
+virtio_net_hdr_tnl_from_skb(const struct sk_buff *skb,
+			    struct virtio_net_hdr_v1_hash_tunnel *vhdr,
+			    bool tnl_hdr_negotiated,
+			    bool little_endian,
+			    int vlan_hlen)
+{
+	struct virtio_net_hdr *hdr = (struct virtio_net_hdr *)vhdr;
+	unsigned int inner_nh, outer_th;
+	int tnl_gso_type;
+	int ret;
+
+	tnl_gso_type = skb_shinfo(skb)->gso_type & (SKB_GSO_UDP_TUNNEL |
+						    SKB_GSO_UDP_TUNNEL_CSUM);
+	if (!tnl_gso_type)
+		return virtio_net_hdr_from_skb(skb, hdr, little_endian, false,
+					       vlan_hlen);
+
+	/* Tunnel support not negotiated but skb ask for it. */
+	if (!tnl_hdr_negotiated)
+		return -EINVAL;
+
+	/* Let the basic parsing deal with plain GSO features. */
+	skb_shinfo(skb)->gso_type &= ~tnl_gso_type;
+	ret = virtio_net_hdr_from_skb(skb, hdr, true, false, vlan_hlen);
+	skb_shinfo(skb)->gso_type |= tnl_gso_type;
+	if (ret)
+		return ret;
+
+	if (skb->protocol == htons(ETH_P_IPV6))
+		hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6;
+	else
+		hdr->gso_type |= VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4;
+
+	if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM)
+		hdr->flags |= VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM;
+
+	inner_nh = skb->inner_network_header - skb_headroom(skb);
+	outer_th = skb->transport_header - skb_headroom(skb);
+	vhdr->inner_nh_offset = cpu_to_le16(inner_nh);
+	vhdr->outer_th_offset = cpu_to_le16(outer_th);
+	return 0;
+}
+
 #endif /* _LINUX_VIRTIO_NET_H */
diff --git a/include/uapi/linux/virtio_net.h b/include/uapi/linux/virtio_net.h
index 963540deae66..8bf27ab8bcb4 100644
--- a/include/uapi/linux/virtio_net.h
+++ b/include/uapi/linux/virtio_net.h
@@ -70,6 +70,28 @@
 					 * with the same MAC.
 					 */
 #define VIRTIO_NET_F_SPEED_DUPLEX 63	/* Device set linkspeed and duplex */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO 65 /* Driver can receive
+					      * GSO-over-UDP-tunnel packets
+					      */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM 66 /* Driver handles
+						   * GSO-over-UDP-tunnel
+						   * packets with partial csum
+						   * for the outer header
+						   */
+#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO 67 /* Device can receive
+					     * GSO-over-UDP-tunnel packets
+					     */
+#define VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO_CSUM 68 /* Device handles
+						  * GSO-over-UDP-tunnel
+						  * packets with partial csum
+						  * for the outer header
+						  */
+
+/* Offloads bits corresponding to VIRTIO_NET_F_HOST_UDP_TUNNEL_GSO{,_CSUM}
+ * features
+ */
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_MAPPED	46
+#define VIRTIO_NET_F_GUEST_UDP_TUNNEL_GSO_CSUM_MAPPED	47
 
 #ifndef VIRTIO_NET_NO_LEGACY
 #define VIRTIO_NET_F_GSO	6	/* Host handles pkts w/ any GSO type */
@@ -131,12 +153,17 @@ struct virtio_net_hdr_v1 {
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM	1	/* Use csum_start, csum_offset */
 #define VIRTIO_NET_HDR_F_DATA_VALID	2	/* Csum is valid */
 #define VIRTIO_NET_HDR_F_RSC_INFO	4	/* rsc info in csum_ fields */
+#define VIRTIO_NET_HDR_F_UDP_TUNNEL_CSUM 8	/* UDP tunnel csum offload */
 	__u8 flags;
 #define VIRTIO_NET_HDR_GSO_NONE		0	/* Not a GSO frame */
 #define VIRTIO_NET_HDR_GSO_TCPV4	1	/* GSO frame, IPv4 TCP (TSO) */
 #define VIRTIO_NET_HDR_GSO_UDP		3	/* GSO frame, IPv4 UDP (UFO) */
 #define VIRTIO_NET_HDR_GSO_TCPV6	4	/* GSO frame, IPv6 TCP */
 #define VIRTIO_NET_HDR_GSO_UDP_L4	5	/* GSO frame, IPv4& IPv6 UDP (USO) */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 0x20 /* UDPv4 tunnel present */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6 0x40 /* UDPv6 tunnel present */
+#define VIRTIO_NET_HDR_GSO_UDP_TUNNEL (VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV4 | \
+				       VIRTIO_NET_HDR_GSO_UDP_TUNNEL_IPV6)
 #define VIRTIO_NET_HDR_GSO_ECN		0x80	/* TCP has ECN set */
 	__u8 gso_type;
 	__virtio16 hdr_len;	/* Ethernet + IP + tcp/udp hdrs */
@@ -181,6 +208,12 @@ struct virtio_net_hdr_v1_hash {
 	__le16 padding;
 };
 
+struct virtio_net_hdr_v1_hash_tunnel {
+	struct virtio_net_hdr_v1_hash hash_hdr;
+	__le16 outer_th_offset;
+	__le16 inner_nh_offset;
+};
+
 #ifndef VIRTIO_NET_NO_LEGACY
 /* This header comes first in the scatter-gather list.
  * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, it must
-- 
cgit v1.2.3


From 58074a0fce66c6c97b35ce8a28ed4e7b780f9a8f Mon Sep 17 00:00:00 2001
From: "Rob Herring (Arm)" <robh@kernel.org>
Date: Wed, 11 Jun 2025 13:01:14 -0500
Subject: perf: arm_pmuv3: Add support for the Branch Record Buffer Extension
 (BRBE)

The ARMv9.2 architecture introduces the optional Branch Record Buffer
Extension (BRBE), which records information about branches as they are
executed into set of branch record registers. BRBE is similar to x86's
Last Branch Record (LBR) and PowerPC's Branch History Rolling Buffer
(BHRB).

BRBE supports filtering by exception level and can filter just the
source or target address if excluded to avoid leaking privileged
addresses. The h/w filter would be sufficient except when there are
multiple events with disjoint filtering requirements. In this case, BRBE
is configured with a union of all the events' desired branches, and then
the recorded branches are filtered based on each event's filter. For
example, with one event capturing kernel events and another event
capturing user events, BRBE will be configured to capture both kernel
and user branches. When handling event overflow, the branch records have
to be filtered by software to only include kernel or user branch
addresses for that event. In contrast, x86 simply configures LBR using
the last installed event which seems broken.

It is possible on x86 to configure branch filter such that no branches
are ever recorded (e.g. -j save_type). For BRBE, events with a
configuration that will result in no samples are rejected.

Recording branches in KVM guests is not supported like x86. However,
perf on x86 allows requesting branch recording in guests. The guest
events are recorded, but the resulting branches are all from the host.
For BRBE, events with branch recording and "exclude_host" set are
rejected. Requiring "exclude_guest" to be set did not work. The default
for the perf tool does set "exclude_guest" if no exception level
options are specified. However, specifying kernel or user events
defaults to including both host and guest. In this case, only host
branches are recorded.

BRBE can support some additional exception branch types compared to
x86. On x86, all exceptions other than syscalls are recorded as IRQ.
With BRBE, it is possible to better categorize these exceptions. One
limitation relative to x86 is we cannot distinguish a syscall return
from other exception returns. So all exception returns are recorded as
ERET type. The FIQ branch type is omitted as the only FIQ user is Apple
platforms which don't support BRBE. The debug branch types are omitted
as there is no clear need for them.

BRBE records are invalidated whenever events are reconfigured, a new
task is scheduled in, or after recording is paused (and the records
have been recorded for the event). The architecture allows branch
records to be invalidated by the PE under implementation defined
conditions. It is expected that these conditions are rare.

Cc: Catalin Marinas <catalin.marinas@arm.com>
Co-developed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Signed-off-by: Anshuman Khandual <anshuman.khandual@arm.com>
Co-developed-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: James Clark <james.clark@linaro.org>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
tested-by: Adam Young <admiyo@os.amperecomputing.com>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/20250611-arm-brbe-v19-v23-4-e7775563036e@kernel.org
[will: Fix sparse warnings about mixed declarations and code.
       Fix C99 comment syntax.]
Signed-off-by: Will Deacon <will@kernel.org>
---
 drivers/perf/Kconfig         |  11 +
 drivers/perf/Makefile        |   1 +
 drivers/perf/arm_brbe.c      | 805 +++++++++++++++++++++++++++++++++++++++++++
 drivers/perf/arm_brbe.h      |  47 +++
 drivers/perf/arm_pmu.c       |  16 +-
 drivers/perf/arm_pmuv3.c     | 107 +++++-
 include/linux/perf/arm_pmu.h |   8 +
 7 files changed, 990 insertions(+), 5 deletions(-)
 create mode 100644 drivers/perf/arm_brbe.c
 create mode 100644 drivers/perf/arm_brbe.h

(limited to 'include/linux')

diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index 278c929dc87a..a9188dec36fe 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -223,6 +223,17 @@ config ARM_SPE_PMU
 	  Extension, which provides periodic sampling of operations in
 	  the CPU pipeline and reports this via the perf AUX interface.
 
+config ARM64_BRBE
+	bool "Enable support for branch stack sampling using FEAT_BRBE"
+	depends on ARM_PMUV3 && ARM64
+	default y
+	help
+	  Enable perf support for Branch Record Buffer Extension (BRBE) which
+	  records all branches taken in an execution path. This supports some
+	  branch types and privilege based filtering. It captures additional
+	  relevant information such as cycle count, misprediction and branch
+	  type, branch privilege level etc.
+
 config ARM_DMC620_PMU
 	tristate "Enable PMU support for the ARM DMC-620 memory controller"
 	depends on (ARM64 && ACPI) || COMPILE_TEST
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index de71d2574857..192fc8b16204 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -23,6 +23,7 @@ obj-$(CONFIG_STARFIVE_STARLINK_PMU) += starfive_starlink_pmu.o
 obj-$(CONFIG_THUNDERX2_PMU) += thunderx2_pmu.o
 obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o
 obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o
+obj-$(CONFIG_ARM64_BRBE) += arm_brbe.o
 obj-$(CONFIG_ARM_DMC620_PMU) += arm_dmc620_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_TAD_PMU) += marvell_cn10k_tad_pmu.o
 obj-$(CONFIG_MARVELL_CN10K_DDR_PMU) += marvell_cn10k_ddr_pmu.o
diff --git a/drivers/perf/arm_brbe.c b/drivers/perf/arm_brbe.c
new file mode 100644
index 000000000000..ba554e0c846c
--- /dev/null
+++ b/drivers/perf/arm_brbe.c
@@ -0,0 +1,805 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Branch Record Buffer Extension Driver.
+ *
+ * Copyright (C) 2022-2025 ARM Limited
+ *
+ * Author: Anshuman Khandual <anshuman.khandual@arm.com>
+ */
+#include <linux/types.h>
+#include <linux/bitmap.h>
+#include <linux/perf/arm_pmu.h>
+#include "arm_brbe.h"
+
+#define BRBFCR_EL1_BRANCH_FILTERS (BRBFCR_EL1_DIRECT   | \
+				   BRBFCR_EL1_INDIRECT | \
+				   BRBFCR_EL1_RTN      | \
+				   BRBFCR_EL1_INDCALL  | \
+				   BRBFCR_EL1_DIRCALL  | \
+				   BRBFCR_EL1_CONDDIR)
+
+/*
+ * BRBTS_EL1 is currently not used for branch stack implementation
+ * purpose but BRBCR_ELx.TS needs to have a valid value from all
+ * available options. BRBCR_ELx_TS_VIRTUAL is selected for this.
+ */
+#define BRBCR_ELx_DEFAULT_TS      FIELD_PREP(BRBCR_ELx_TS_MASK, BRBCR_ELx_TS_VIRTUAL)
+
+/*
+ * BRBE Buffer Organization
+ *
+ * BRBE buffer is arranged as multiple banks of 32 branch record
+ * entries each. An individual branch record in a given bank could
+ * be accessed, after selecting the bank in BRBFCR_EL1.BANK and
+ * accessing the registers i.e [BRBSRC, BRBTGT, BRBINF] set with
+ * indices [0..31].
+ *
+ * Bank 0
+ *
+ *	---------------------------------	------
+ *	| 00 | BRBSRC | BRBTGT | BRBINF |	| 00 |
+ *	---------------------------------	------
+ *	| 01 | BRBSRC | BRBTGT | BRBINF |	| 01 |
+ *	---------------------------------	------
+ *	| .. | BRBSRC | BRBTGT | BRBINF |	| .. |
+ *	---------------------------------	------
+ *	| 31 | BRBSRC | BRBTGT | BRBINF |	| 31 |
+ *	---------------------------------	------
+ *
+ * Bank 1
+ *
+ *	---------------------------------	------
+ *	| 32 | BRBSRC | BRBTGT | BRBINF |	| 00 |
+ *	---------------------------------	------
+ *	| 33 | BRBSRC | BRBTGT | BRBINF |	| 01 |
+ *	---------------------------------	------
+ *	| .. | BRBSRC | BRBTGT | BRBINF |	| .. |
+ *	---------------------------------	------
+ *	| 63 | BRBSRC | BRBTGT | BRBINF |	| 31 |
+ *	---------------------------------	------
+ */
+#define BRBE_BANK_MAX_ENTRIES	32
+
+struct brbe_regset {
+	u64 brbsrc;
+	u64 brbtgt;
+	u64 brbinf;
+};
+
+#define PERF_BR_ARM64_MAX (PERF_BR_MAX + PERF_BR_NEW_MAX)
+
+struct brbe_hw_attr {
+	int	brbe_version;
+	int	brbe_cc;
+	int	brbe_nr;
+	int	brbe_format;
+};
+
+#define BRBE_REGN_CASE(n, case_macro) \
+	case n: case_macro(n); break
+
+#define BRBE_REGN_SWITCH(x, case_macro)				\
+	do {							\
+		switch (x) {					\
+		BRBE_REGN_CASE(0, case_macro);			\
+		BRBE_REGN_CASE(1, case_macro);			\
+		BRBE_REGN_CASE(2, case_macro);			\
+		BRBE_REGN_CASE(3, case_macro);			\
+		BRBE_REGN_CASE(4, case_macro);			\
+		BRBE_REGN_CASE(5, case_macro);			\
+		BRBE_REGN_CASE(6, case_macro);			\
+		BRBE_REGN_CASE(7, case_macro);			\
+		BRBE_REGN_CASE(8, case_macro);			\
+		BRBE_REGN_CASE(9, case_macro);			\
+		BRBE_REGN_CASE(10, case_macro);			\
+		BRBE_REGN_CASE(11, case_macro);			\
+		BRBE_REGN_CASE(12, case_macro);			\
+		BRBE_REGN_CASE(13, case_macro);			\
+		BRBE_REGN_CASE(14, case_macro);			\
+		BRBE_REGN_CASE(15, case_macro);			\
+		BRBE_REGN_CASE(16, case_macro);			\
+		BRBE_REGN_CASE(17, case_macro);			\
+		BRBE_REGN_CASE(18, case_macro);			\
+		BRBE_REGN_CASE(19, case_macro);			\
+		BRBE_REGN_CASE(20, case_macro);			\
+		BRBE_REGN_CASE(21, case_macro);			\
+		BRBE_REGN_CASE(22, case_macro);			\
+		BRBE_REGN_CASE(23, case_macro);			\
+		BRBE_REGN_CASE(24, case_macro);			\
+		BRBE_REGN_CASE(25, case_macro);			\
+		BRBE_REGN_CASE(26, case_macro);			\
+		BRBE_REGN_CASE(27, case_macro);			\
+		BRBE_REGN_CASE(28, case_macro);			\
+		BRBE_REGN_CASE(29, case_macro);			\
+		BRBE_REGN_CASE(30, case_macro);			\
+		BRBE_REGN_CASE(31, case_macro);			\
+		default: WARN(1, "Invalid BRB* index %d\n", x);	\
+		}						\
+	} while (0)
+
+#define RETURN_READ_BRBSRCN(n) \
+	return read_sysreg_s(SYS_BRBSRC_EL1(n))
+static inline u64 get_brbsrc_reg(int idx)
+{
+	BRBE_REGN_SWITCH(idx, RETURN_READ_BRBSRCN);
+	return 0;
+}
+
+#define RETURN_READ_BRBTGTN(n) \
+	return read_sysreg_s(SYS_BRBTGT_EL1(n))
+static u64 get_brbtgt_reg(int idx)
+{
+	BRBE_REGN_SWITCH(idx, RETURN_READ_BRBTGTN);
+	return 0;
+}
+
+#define RETURN_READ_BRBINFN(n) \
+	return read_sysreg_s(SYS_BRBINF_EL1(n))
+static u64 get_brbinf_reg(int idx)
+{
+	BRBE_REGN_SWITCH(idx, RETURN_READ_BRBINFN);
+	return 0;
+}
+
+static u64 brbe_record_valid(u64 brbinf)
+{
+	return FIELD_GET(BRBINFx_EL1_VALID_MASK, brbinf);
+}
+
+static bool brbe_invalid(u64 brbinf)
+{
+	return brbe_record_valid(brbinf) == BRBINFx_EL1_VALID_NONE;
+}
+
+static bool brbe_record_is_complete(u64 brbinf)
+{
+	return brbe_record_valid(brbinf) == BRBINFx_EL1_VALID_FULL;
+}
+
+static bool brbe_record_is_source_only(u64 brbinf)
+{
+	return brbe_record_valid(brbinf) == BRBINFx_EL1_VALID_SOURCE;
+}
+
+static bool brbe_record_is_target_only(u64 brbinf)
+{
+	return brbe_record_valid(brbinf) == BRBINFx_EL1_VALID_TARGET;
+}
+
+static int brbinf_get_in_tx(u64 brbinf)
+{
+	return FIELD_GET(BRBINFx_EL1_T_MASK, brbinf);
+}
+
+static int brbinf_get_mispredict(u64 brbinf)
+{
+	return FIELD_GET(BRBINFx_EL1_MPRED_MASK, brbinf);
+}
+
+static int brbinf_get_lastfailed(u64 brbinf)
+{
+	return FIELD_GET(BRBINFx_EL1_LASTFAILED_MASK, brbinf);
+}
+
+static u16 brbinf_get_cycles(u64 brbinf)
+{
+	u32 exp, mant, cycles;
+	/*
+	 * Captured cycle count is unknown and hence
+	 * should not be passed on to userspace.
+	 */
+	if (brbinf & BRBINFx_EL1_CCU)
+		return 0;
+
+	exp = FIELD_GET(BRBINFx_EL1_CC_EXP_MASK, brbinf);
+	mant = FIELD_GET(BRBINFx_EL1_CC_MANT_MASK, brbinf);
+
+	if (!exp)
+		return mant;
+
+	cycles = (mant | 0x100) << (exp - 1);
+
+	return min(cycles, U16_MAX);
+}
+
+static int brbinf_get_type(u64 brbinf)
+{
+	return FIELD_GET(BRBINFx_EL1_TYPE_MASK, brbinf);
+}
+
+static int brbinf_get_el(u64 brbinf)
+{
+	return FIELD_GET(BRBINFx_EL1_EL_MASK, brbinf);
+}
+
+void brbe_invalidate(void)
+{
+	/* Ensure all branches before this point are recorded */
+	isb();
+	asm volatile(BRB_IALL_INSN);
+	/* Ensure all branch records are invalidated after this point */
+	isb();
+}
+
+static bool valid_brbe_nr(int brbe_nr)
+{
+	return brbe_nr == BRBIDR0_EL1_NUMREC_8 ||
+	       brbe_nr == BRBIDR0_EL1_NUMREC_16 ||
+	       brbe_nr == BRBIDR0_EL1_NUMREC_32 ||
+	       brbe_nr == BRBIDR0_EL1_NUMREC_64;
+}
+
+static bool valid_brbe_cc(int brbe_cc)
+{
+	return brbe_cc == BRBIDR0_EL1_CC_20_BIT;
+}
+
+static bool valid_brbe_format(int brbe_format)
+{
+	return brbe_format == BRBIDR0_EL1_FORMAT_FORMAT_0;
+}
+
+static bool valid_brbidr(u64 brbidr)
+{
+	int brbe_format, brbe_cc, brbe_nr;
+
+	brbe_format = FIELD_GET(BRBIDR0_EL1_FORMAT_MASK, brbidr);
+	brbe_cc = FIELD_GET(BRBIDR0_EL1_CC_MASK, brbidr);
+	brbe_nr = FIELD_GET(BRBIDR0_EL1_NUMREC_MASK, brbidr);
+
+	return valid_brbe_format(brbe_format) && valid_brbe_cc(brbe_cc) && valid_brbe_nr(brbe_nr);
+}
+
+static bool valid_brbe_version(int brbe_version)
+{
+	return brbe_version == ID_AA64DFR0_EL1_BRBE_IMP ||
+	       brbe_version == ID_AA64DFR0_EL1_BRBE_BRBE_V1P1;
+}
+
+static void select_brbe_bank(int bank)
+{
+	u64 brbfcr;
+
+	brbfcr = read_sysreg_s(SYS_BRBFCR_EL1);
+	brbfcr &= ~BRBFCR_EL1_BANK_MASK;
+	brbfcr |= SYS_FIELD_PREP(BRBFCR_EL1, BANK, bank);
+	write_sysreg_s(brbfcr, SYS_BRBFCR_EL1);
+	/*
+	 * Arm ARM (DDI 0487K.a) D.18.4 rule PPBZP requires explicit sync
+	 * between setting BANK and accessing branch records.
+	 */
+	isb();
+}
+
+static bool __read_brbe_regset(struct brbe_regset *entry, int idx)
+{
+	entry->brbinf = get_brbinf_reg(idx);
+
+	if (brbe_invalid(entry->brbinf))
+		return false;
+
+	entry->brbsrc = get_brbsrc_reg(idx);
+	entry->brbtgt = get_brbtgt_reg(idx);
+	return true;
+}
+
+/*
+ * Generic perf branch filters supported on BRBE
+ *
+ * New branch filters need to be evaluated whether they could be supported on
+ * BRBE. This ensures that such branch filters would not just be accepted, to
+ * fail silently. PERF_SAMPLE_BRANCH_HV is a special case that is selectively
+ * supported only on platforms where kernel is in hyp mode.
+ */
+#define BRBE_EXCLUDE_BRANCH_FILTERS (PERF_SAMPLE_BRANCH_ABORT_TX	| \
+				     PERF_SAMPLE_BRANCH_IN_TX		| \
+				     PERF_SAMPLE_BRANCH_NO_TX		| \
+				     PERF_SAMPLE_BRANCH_CALL_STACK	| \
+				     PERF_SAMPLE_BRANCH_COUNTERS)
+
+#define BRBE_ALLOWED_BRANCH_TYPES   (PERF_SAMPLE_BRANCH_ANY		| \
+				     PERF_SAMPLE_BRANCH_ANY_CALL	| \
+				     PERF_SAMPLE_BRANCH_ANY_RETURN	| \
+				     PERF_SAMPLE_BRANCH_IND_CALL	| \
+				     PERF_SAMPLE_BRANCH_COND		| \
+				     PERF_SAMPLE_BRANCH_IND_JUMP	| \
+				     PERF_SAMPLE_BRANCH_CALL)
+
+
+#define BRBE_ALLOWED_BRANCH_FILTERS (PERF_SAMPLE_BRANCH_USER		| \
+				     PERF_SAMPLE_BRANCH_KERNEL		| \
+				     PERF_SAMPLE_BRANCH_HV		| \
+				     BRBE_ALLOWED_BRANCH_TYPES		| \
+				     PERF_SAMPLE_BRANCH_NO_FLAGS	| \
+				     PERF_SAMPLE_BRANCH_NO_CYCLES	| \
+				     PERF_SAMPLE_BRANCH_TYPE_SAVE	| \
+				     PERF_SAMPLE_BRANCH_HW_INDEX	| \
+				     PERF_SAMPLE_BRANCH_PRIV_SAVE)
+
+#define BRBE_PERF_BRANCH_FILTERS    (BRBE_ALLOWED_BRANCH_FILTERS	| \
+				     BRBE_EXCLUDE_BRANCH_FILTERS)
+
+/*
+ * BRBE supports the following functional branch type filters while
+ * generating branch records. These branch filters can be enabled,
+ * either individually or as a group i.e ORing multiple filters
+ * with each other.
+ *
+ * BRBFCR_EL1_CONDDIR  - Conditional direct branch
+ * BRBFCR_EL1_DIRCALL  - Direct call
+ * BRBFCR_EL1_INDCALL  - Indirect call
+ * BRBFCR_EL1_INDIRECT - Indirect branch
+ * BRBFCR_EL1_DIRECT   - Direct branch
+ * BRBFCR_EL1_RTN      - Subroutine return
+ */
+static u64 branch_type_to_brbfcr(int branch_type)
+{
+	u64 brbfcr = 0;
+
+	if (branch_type & PERF_SAMPLE_BRANCH_ANY) {
+		brbfcr |= BRBFCR_EL1_BRANCH_FILTERS;
+		return brbfcr;
+	}
+
+	if (branch_type & PERF_SAMPLE_BRANCH_ANY_CALL) {
+		brbfcr |= BRBFCR_EL1_INDCALL;
+		brbfcr |= BRBFCR_EL1_DIRCALL;
+	}
+
+	if (branch_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+		brbfcr |= BRBFCR_EL1_RTN;
+
+	if (branch_type & PERF_SAMPLE_BRANCH_IND_CALL)
+		brbfcr |= BRBFCR_EL1_INDCALL;
+
+	if (branch_type & PERF_SAMPLE_BRANCH_COND)
+		brbfcr |= BRBFCR_EL1_CONDDIR;
+
+	if (branch_type & PERF_SAMPLE_BRANCH_IND_JUMP)
+		brbfcr |= BRBFCR_EL1_INDIRECT;
+
+	if (branch_type & PERF_SAMPLE_BRANCH_CALL)
+		brbfcr |= BRBFCR_EL1_DIRCALL;
+
+	return brbfcr;
+}
+
+/*
+ * BRBE supports the following privilege mode filters while generating
+ * branch records.
+ *
+ * BRBCR_ELx_E0BRE - EL0 branch records
+ * BRBCR_ELx_ExBRE - EL1/EL2 branch records
+ *
+ * BRBE also supports the following additional functional branch type
+ * filters while generating branch records.
+ *
+ * BRBCR_ELx_EXCEPTION - Exception
+ * BRBCR_ELx_ERTN     -  Exception return
+ */
+static u64 branch_type_to_brbcr(int branch_type)
+{
+	u64 brbcr = BRBCR_ELx_FZP | BRBCR_ELx_DEFAULT_TS;
+
+	if (branch_type & PERF_SAMPLE_BRANCH_USER)
+		brbcr |= BRBCR_ELx_E0BRE;
+
+	/*
+	 * When running in the hyp mode, writing into BRBCR_EL1
+	 * actually writes into BRBCR_EL2 instead. Field E2BRE
+	 * is also at the same position as E1BRE.
+	 */
+	if (branch_type & PERF_SAMPLE_BRANCH_KERNEL)
+		brbcr |= BRBCR_ELx_ExBRE;
+
+	if (branch_type & PERF_SAMPLE_BRANCH_HV) {
+		if (is_kernel_in_hyp_mode())
+			brbcr |= BRBCR_ELx_ExBRE;
+	}
+
+	if (!(branch_type & PERF_SAMPLE_BRANCH_NO_CYCLES))
+		brbcr |= BRBCR_ELx_CC;
+
+	if (!(branch_type & PERF_SAMPLE_BRANCH_NO_FLAGS))
+		brbcr |= BRBCR_ELx_MPRED;
+
+	/*
+	 * The exception and exception return branches could be
+	 * captured, irrespective of the perf event's privilege.
+	 * If the perf event does not have enough privilege for
+	 * a given exception level, then addresses which falls
+	 * under that exception level will be reported as zero
+	 * for the captured branch record, creating source only
+	 * or target only records.
+	 */
+	if (branch_type & PERF_SAMPLE_BRANCH_KERNEL) {
+		if (branch_type & PERF_SAMPLE_BRANCH_ANY) {
+			brbcr |= BRBCR_ELx_EXCEPTION;
+			brbcr |= BRBCR_ELx_ERTN;
+		}
+
+		if (branch_type & PERF_SAMPLE_BRANCH_ANY_CALL)
+			brbcr |= BRBCR_ELx_EXCEPTION;
+
+		if (branch_type & PERF_SAMPLE_BRANCH_ANY_RETURN)
+			brbcr |= BRBCR_ELx_ERTN;
+	}
+	return brbcr;
+}
+
+bool brbe_branch_attr_valid(struct perf_event *event)
+{
+	u64 branch_type = event->attr.branch_sample_type;
+
+	/*
+	 * Ensure both perf branch filter allowed and exclude
+	 * masks are always in sync with the generic perf ABI.
+	 */
+	BUILD_BUG_ON(BRBE_PERF_BRANCH_FILTERS != (PERF_SAMPLE_BRANCH_MAX - 1));
+
+	if (branch_type & BRBE_EXCLUDE_BRANCH_FILTERS) {
+		pr_debug("requested branch filter not supported 0x%llx\n", branch_type);
+		return false;
+	}
+
+	/* Ensure at least 1 branch type is enabled */
+	if (!(branch_type & BRBE_ALLOWED_BRANCH_TYPES)) {
+		pr_debug("no branch type enabled 0x%llx\n", branch_type);
+		return false;
+	}
+
+	/*
+	 * No branches are recorded in guests nor nVHE hypervisors, so
+	 * excluding the host or both kernel and user is invalid.
+	 *
+	 * Ideally we'd just require exclude_guest and exclude_hv, but setting
+	 * event filters with perf for kernel or user don't set exclude_guest.
+	 * So effectively, exclude_guest and exclude_hv are ignored.
+	 */
+	if (event->attr.exclude_host || (event->attr.exclude_user && event->attr.exclude_kernel)) {
+		pr_debug("branch filter in hypervisor or guest only not supported 0x%llx\n", branch_type);
+		return false;
+	}
+
+	event->hw.branch_reg.config = branch_type_to_brbfcr(event->attr.branch_sample_type);
+	event->hw.extra_reg.config = branch_type_to_brbcr(event->attr.branch_sample_type);
+
+	return true;
+}
+
+unsigned int brbe_num_branch_records(const struct arm_pmu *armpmu)
+{
+	return FIELD_GET(BRBIDR0_EL1_NUMREC_MASK, armpmu->reg_brbidr);
+}
+
+void brbe_probe(struct arm_pmu *armpmu)
+{
+	u64 brbidr, aa64dfr0 = read_sysreg_s(SYS_ID_AA64DFR0_EL1);
+	u32 brbe;
+
+	brbe = cpuid_feature_extract_unsigned_field(aa64dfr0, ID_AA64DFR0_EL1_BRBE_SHIFT);
+	if (!valid_brbe_version(brbe))
+		return;
+
+	brbidr = read_sysreg_s(SYS_BRBIDR0_EL1);
+	if (!valid_brbidr(brbidr))
+		return;
+
+	armpmu->reg_brbidr = brbidr;
+}
+
+/*
+ * BRBE is assumed to be disabled/paused on entry
+ */
+void brbe_enable(const struct arm_pmu *arm_pmu)
+{
+	struct pmu_hw_events *cpuc = this_cpu_ptr(arm_pmu->hw_events);
+	u64 brbfcr = 0, brbcr = 0;
+
+	/*
+	 * Discard existing records to avoid a discontinuity, e.g. records
+	 * missed during handling an overflow.
+	 */
+	brbe_invalidate();
+
+	/*
+	 * Merge the permitted branch filters of all events.
+	 */
+	for (int i = 0; i < ARMPMU_MAX_HWEVENTS; i++) {
+		struct perf_event *event = cpuc->events[i];
+
+		if (event && has_branch_stack(event)) {
+			brbfcr |= event->hw.branch_reg.config;
+			brbcr |= event->hw.extra_reg.config;
+		}
+	}
+
+	/*
+	 * In VHE mode with MDCR_EL2.HPMN equal to PMCR_EL0.N, BRBCR_EL1.FZP
+	 * controls freezing the branch records on counter overflow rather than
+	 * BRBCR_EL2.FZP (which writes to BRBCR_EL1 are redirected to).
+	 * The exception levels are enabled/disabled in BRBCR_EL2, so keep EL1
+	 * and EL0 recording disabled for guests.
+	 *
+	 * As BRBCR_EL1 CC and MPRED bits also need to match, use the same
+	 * value for both registers just masking the exception levels.
+	 */
+	if (is_kernel_in_hyp_mode())
+		write_sysreg_s(brbcr & ~(BRBCR_ELx_ExBRE | BRBCR_ELx_E0BRE), SYS_BRBCR_EL12);
+	write_sysreg_s(brbcr, SYS_BRBCR_EL1);
+	/* Ensure BRBCR_ELx settings take effect before unpausing */
+	isb();
+
+	/* Finally write SYS_BRBFCR_EL to unpause BRBE */
+	write_sysreg_s(brbfcr, SYS_BRBFCR_EL1);
+	/* Synchronization in PMCR write ensures ordering WRT PMU enabling */
+}
+
+void brbe_disable(void)
+{
+	/*
+	 * No need for synchronization here as synchronization in PMCR write
+	 * ensures ordering and in the interrupt handler this is a NOP as
+	 * we're already paused.
+	 */
+	write_sysreg_s(BRBFCR_EL1_PAUSED, SYS_BRBFCR_EL1);
+	write_sysreg_s(0, SYS_BRBCR_EL1);
+}
+
+static const int brbe_type_to_perf_type_map[BRBINFx_EL1_TYPE_DEBUG_EXIT + 1][2] = {
+	[BRBINFx_EL1_TYPE_DIRECT_UNCOND] = { PERF_BR_UNCOND, 0 },
+	[BRBINFx_EL1_TYPE_INDIRECT] = { PERF_BR_IND, 0 },
+	[BRBINFx_EL1_TYPE_DIRECT_LINK] = { PERF_BR_CALL, 0 },
+	[BRBINFx_EL1_TYPE_INDIRECT_LINK] = { PERF_BR_IND_CALL, 0 },
+	[BRBINFx_EL1_TYPE_RET] = { PERF_BR_RET, 0 },
+	[BRBINFx_EL1_TYPE_DIRECT_COND] = { PERF_BR_COND, 0 },
+	[BRBINFx_EL1_TYPE_CALL] = { PERF_BR_SYSCALL, 0 },
+	[BRBINFx_EL1_TYPE_ERET] = { PERF_BR_ERET, 0 },
+	[BRBINFx_EL1_TYPE_IRQ] = { PERF_BR_IRQ, 0 },
+	[BRBINFx_EL1_TYPE_TRAP] = { PERF_BR_IRQ, 0 },
+	[BRBINFx_EL1_TYPE_SERROR] = { PERF_BR_SERROR, 0 },
+	[BRBINFx_EL1_TYPE_ALIGN_FAULT] = { PERF_BR_EXTEND_ABI, PERF_BR_NEW_FAULT_ALGN },
+	[BRBINFx_EL1_TYPE_INSN_FAULT] = { PERF_BR_EXTEND_ABI, PERF_BR_NEW_FAULT_INST },
+	[BRBINFx_EL1_TYPE_DATA_FAULT] = { PERF_BR_EXTEND_ABI, PERF_BR_NEW_FAULT_DATA },
+};
+
+static void brbe_set_perf_entry_type(struct perf_branch_entry *entry, u64 brbinf)
+{
+	int brbe_type = brbinf_get_type(brbinf);
+
+	if (brbe_type <= BRBINFx_EL1_TYPE_DEBUG_EXIT) {
+		const int *br_type = brbe_type_to_perf_type_map[brbe_type];
+
+		entry->type = br_type[0];
+		entry->new_type = br_type[1];
+	}
+}
+
+static int brbinf_get_perf_priv(u64 brbinf)
+{
+	int brbe_el = brbinf_get_el(brbinf);
+
+	switch (brbe_el) {
+	case BRBINFx_EL1_EL_EL0:
+		return PERF_BR_PRIV_USER;
+	case BRBINFx_EL1_EL_EL1:
+		return PERF_BR_PRIV_KERNEL;
+	case BRBINFx_EL1_EL_EL2:
+		if (is_kernel_in_hyp_mode())
+			return PERF_BR_PRIV_KERNEL;
+		return PERF_BR_PRIV_HV;
+	default:
+		pr_warn_once("%d - unknown branch privilege captured\n", brbe_el);
+		return PERF_BR_PRIV_UNKNOWN;
+	}
+}
+
+static bool perf_entry_from_brbe_regset(int index, struct perf_branch_entry *entry,
+					const struct perf_event *event)
+{
+	struct brbe_regset bregs;
+	u64 brbinf;
+
+	if (!__read_brbe_regset(&bregs, index))
+		return false;
+
+	brbinf = bregs.brbinf;
+	perf_clear_branch_entry_bitfields(entry);
+	if (brbe_record_is_complete(brbinf)) {
+		entry->from = bregs.brbsrc;
+		entry->to = bregs.brbtgt;
+	} else if (brbe_record_is_source_only(brbinf)) {
+		entry->from = bregs.brbsrc;
+		entry->to = 0;
+	} else if (brbe_record_is_target_only(brbinf)) {
+		entry->from = 0;
+		entry->to = bregs.brbtgt;
+	}
+
+	brbe_set_perf_entry_type(entry, brbinf);
+
+	if (!branch_sample_no_cycles(event))
+		entry->cycles = brbinf_get_cycles(brbinf);
+
+	if (!branch_sample_no_flags(event)) {
+		/* Mispredict info is available for source only and complete branch records. */
+		if (!brbe_record_is_target_only(brbinf)) {
+			entry->mispred = brbinf_get_mispredict(brbinf);
+			entry->predicted = !entry->mispred;
+		}
+
+		/*
+		 * Currently TME feature is neither implemented in any hardware
+		 * nor it is being supported in the kernel. Just warn here once
+		 * if TME related information shows up rather unexpectedly.
+		 */
+		if (brbinf_get_lastfailed(brbinf) || brbinf_get_in_tx(brbinf))
+			pr_warn_once("Unknown transaction states\n");
+	}
+
+	/*
+	 * Branch privilege level is available for target only and complete
+	 * branch records.
+	 */
+	if (!brbe_record_is_source_only(brbinf))
+		entry->priv = brbinf_get_perf_priv(brbinf);
+
+	return true;
+}
+
+#define PERF_BR_ARM64_ALL (				\
+	BIT(PERF_BR_COND) |				\
+	BIT(PERF_BR_UNCOND) |				\
+	BIT(PERF_BR_IND) |				\
+	BIT(PERF_BR_CALL) |				\
+	BIT(PERF_BR_IND_CALL) |				\
+	BIT(PERF_BR_RET))
+
+#define PERF_BR_ARM64_ALL_KERNEL (			\
+	BIT(PERF_BR_SYSCALL) |				\
+	BIT(PERF_BR_IRQ) |				\
+	BIT(PERF_BR_SERROR) |				\
+	BIT(PERF_BR_MAX + PERF_BR_NEW_FAULT_ALGN) |	\
+	BIT(PERF_BR_MAX + PERF_BR_NEW_FAULT_DATA) |	\
+	BIT(PERF_BR_MAX + PERF_BR_NEW_FAULT_INST))
+
+static void prepare_event_branch_type_mask(u64 branch_sample,
+					   unsigned long *event_type_mask)
+{
+	if (branch_sample & PERF_SAMPLE_BRANCH_ANY) {
+		if (branch_sample & PERF_SAMPLE_BRANCH_KERNEL)
+			bitmap_from_u64(event_type_mask,
+				BIT(PERF_BR_ERET) | PERF_BR_ARM64_ALL |
+				PERF_BR_ARM64_ALL_KERNEL);
+		else
+			bitmap_from_u64(event_type_mask, PERF_BR_ARM64_ALL);
+		return;
+	}
+
+	bitmap_zero(event_type_mask, PERF_BR_ARM64_MAX);
+
+	if (branch_sample & PERF_SAMPLE_BRANCH_ANY_CALL) {
+		if (branch_sample & PERF_SAMPLE_BRANCH_KERNEL)
+			bitmap_from_u64(event_type_mask, PERF_BR_ARM64_ALL_KERNEL);
+
+		set_bit(PERF_BR_CALL, event_type_mask);
+		set_bit(PERF_BR_IND_CALL, event_type_mask);
+	}
+
+	if (branch_sample & PERF_SAMPLE_BRANCH_IND_JUMP)
+		set_bit(PERF_BR_IND, event_type_mask);
+
+	if (branch_sample & PERF_SAMPLE_BRANCH_COND)
+		set_bit(PERF_BR_COND, event_type_mask);
+
+	if (branch_sample & PERF_SAMPLE_BRANCH_CALL)
+		set_bit(PERF_BR_CALL, event_type_mask);
+
+	if (branch_sample & PERF_SAMPLE_BRANCH_IND_CALL)
+		set_bit(PERF_BR_IND_CALL, event_type_mask);
+
+	if (branch_sample & PERF_SAMPLE_BRANCH_ANY_RETURN) {
+		set_bit(PERF_BR_RET, event_type_mask);
+
+		if (branch_sample & PERF_SAMPLE_BRANCH_KERNEL)
+			set_bit(PERF_BR_ERET, event_type_mask);
+	}
+}
+
+/*
+ * BRBE is configured with an OR of permissions from all events, so there may
+ * be events which have to be dropped or events where just the source or target
+ * address has to be zeroed.
+ */
+static bool filter_branch_privilege(struct perf_branch_entry *entry, u64 branch_sample_type)
+{
+	bool from_user = access_ok((void __user *)(unsigned long)entry->from, 4);
+	bool to_user = access_ok((void __user *)(unsigned long)entry->to, 4);
+	bool exclude_kernel = !((branch_sample_type & PERF_SAMPLE_BRANCH_KERNEL) ||
+		(is_kernel_in_hyp_mode() && (branch_sample_type & PERF_SAMPLE_BRANCH_HV)));
+
+	/* We can only have a half record if permissions have not been expanded */
+	if (!entry->from || !entry->to)
+		return true;
+
+	/*
+	 * If record is within a single exception level, just need to either
+	 * drop or keep the entire record.
+	 */
+	if (from_user == to_user)
+		return ((entry->priv == PERF_BR_PRIV_KERNEL) && !exclude_kernel) ||
+			((entry->priv == PERF_BR_PRIV_USER) &&
+			 (branch_sample_type & PERF_SAMPLE_BRANCH_USER));
+
+	/*
+	 * Record is across exception levels, mask addresses for the exception
+	 * level we're not capturing.
+	 */
+	if (!(branch_sample_type & PERF_SAMPLE_BRANCH_USER)) {
+		if (from_user)
+			entry->from = 0;
+		if (to_user)
+			entry->to = 0;
+	}
+
+	if (exclude_kernel) {
+		if (!from_user)
+			entry->from = 0;
+		if (!to_user)
+			entry->to = 0;
+	}
+
+	return true;
+}
+
+static bool filter_branch_type(struct perf_branch_entry *entry,
+			       const unsigned long *event_type_mask)
+{
+	if (entry->type == PERF_BR_EXTEND_ABI)
+		return test_bit(PERF_BR_MAX + entry->new_type, event_type_mask);
+	else
+		return test_bit(entry->type, event_type_mask);
+}
+
+static bool filter_branch_record(struct perf_branch_entry *entry,
+				 u64 branch_sample,
+				 const unsigned long *event_type_mask)
+{
+	return filter_branch_type(entry, event_type_mask) &&
+		filter_branch_privilege(entry, branch_sample);
+}
+
+void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,
+				const struct perf_event *event)
+{
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+	int nr_hw = brbe_num_branch_records(cpu_pmu);
+	int nr_banks = DIV_ROUND_UP(nr_hw, BRBE_BANK_MAX_ENTRIES);
+	int nr_filtered = 0;
+	u64 branch_sample_type = event->attr.branch_sample_type;
+	DECLARE_BITMAP(event_type_mask, PERF_BR_ARM64_MAX);
+
+	prepare_event_branch_type_mask(branch_sample_type, event_type_mask);
+
+	for (int bank = 0; bank < nr_banks; bank++) {
+		int nr_remaining = nr_hw - (bank * BRBE_BANK_MAX_ENTRIES);
+		int nr_this_bank = min(nr_remaining, BRBE_BANK_MAX_ENTRIES);
+
+		select_brbe_bank(bank);
+
+		for (int i = 0; i < nr_this_bank; i++) {
+			struct perf_branch_entry *pbe = &branch_stack->entries[nr_filtered];
+
+			if (!perf_entry_from_brbe_regset(i, pbe, event))
+				goto done;
+
+			if (!filter_branch_record(pbe, branch_sample_type, event_type_mask))
+				continue;
+
+			nr_filtered++;
+		}
+	}
+
+done:
+	branch_stack->nr = nr_filtered;
+}
diff --git a/drivers/perf/arm_brbe.h b/drivers/perf/arm_brbe.h
new file mode 100644
index 000000000000..b7c7d8796c86
--- /dev/null
+++ b/drivers/perf/arm_brbe.h
@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Branch Record Buffer Extension Helpers.
+ *
+ * Copyright (C) 2022-2025 ARM Limited
+ *
+ * Author: Anshuman Khandual <anshuman.khandual@arm.com>
+ */
+
+struct arm_pmu;
+struct perf_branch_stack;
+struct perf_event;
+
+#ifdef CONFIG_ARM64_BRBE
+void brbe_probe(struct arm_pmu *arm_pmu);
+unsigned int brbe_num_branch_records(const struct arm_pmu *armpmu);
+void brbe_invalidate(void);
+
+void brbe_enable(const struct arm_pmu *arm_pmu);
+void brbe_disable(void);
+
+bool brbe_branch_attr_valid(struct perf_event *event);
+void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,
+				const struct perf_event *event);
+#else
+static inline void brbe_probe(struct arm_pmu *arm_pmu) { }
+static inline unsigned int brbe_num_branch_records(const struct arm_pmu *armpmu)
+{
+	return 0;
+}
+
+static inline void brbe_invalidate(void) { }
+
+static inline void brbe_enable(const struct arm_pmu *arm_pmu) { };
+static inline void brbe_disable(void) { };
+
+static inline bool brbe_branch_attr_valid(struct perf_event *event)
+{
+	WARN_ON_ONCE(!has_branch_stack(event));
+	return false;
+}
+
+static void brbe_read_filtered_entries(struct perf_branch_stack *branch_stack,
+				       const struct perf_event *event)
+{
+}
+#endif
diff --git a/drivers/perf/arm_pmu.c b/drivers/perf/arm_pmu.c
index 2f33e69a8caf..5c310e803dd7 100644
--- a/drivers/perf/arm_pmu.c
+++ b/drivers/perf/arm_pmu.c
@@ -99,7 +99,7 @@ static const struct pmu_irq_ops percpu_pmunmi_ops = {
 	.free_pmuirq = armpmu_free_percpu_pmunmi
 };
 
-static DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
+DEFINE_PER_CPU(struct arm_pmu *, cpu_armpmu);
 static DEFINE_PER_CPU(int, cpu_irq);
 static DEFINE_PER_CPU(const struct pmu_irq_ops *, cpu_irq_ops);
 
@@ -318,6 +318,12 @@ armpmu_del(struct perf_event *event, int flags)
 	int idx = hwc->idx;
 
 	armpmu_stop(event, PERF_EF_UPDATE);
+
+	if (has_branch_stack(event)) {
+		hw_events->branch_users--;
+		perf_sched_cb_dec(event->pmu);
+	}
+
 	hw_events->events[idx] = NULL;
 	armpmu->clear_event_idx(hw_events, event);
 	perf_event_update_userpage(event);
@@ -345,6 +351,11 @@ armpmu_add(struct perf_event *event, int flags)
 	/* The newly-allocated counter should be empty */
 	WARN_ON_ONCE(hw_events->events[idx]);
 
+	if (has_branch_stack(event)) {
+		hw_events->branch_users++;
+		perf_sched_cb_inc(event->pmu);
+	}
+
 	event->hw.idx = idx;
 	hw_events->events[idx] = event;
 
@@ -509,8 +520,7 @@ static int armpmu_event_init(struct perf_event *event)
 		!cpumask_test_cpu(event->cpu, &armpmu->supported_cpus))
 		return -ENOENT;
 
-	/* does not support taken branch sampling */
-	if (has_branch_stack(event))
+	if (has_branch_stack(event) && !armpmu->reg_brbidr)
 		return -EOPNOTSUPP;
 
 	return __hw_perf_event_init(event);
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 3db9f4ed17e8..f6d7bab5d555 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -25,6 +25,8 @@
 #include <linux/smp.h>
 #include <linux/nmi.h>
 
+#include "arm_brbe.h"
+
 /* ARMv8 Cortex-A53 specific event types. */
 #define ARMV8_A53_PERFCTR_PREF_LINEFILL				0xC2
 
@@ -438,7 +440,19 @@ static ssize_t threshold_max_show(struct device *dev,
 
 static DEVICE_ATTR_RO(threshold_max);
 
+static ssize_t branches_show(struct device *dev,
+			     struct device_attribute *attr, char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+
+	return sysfs_emit(page, "%d\n", brbe_num_branch_records(cpu_pmu));
+}
+
+static DEVICE_ATTR_RO(branches);
+
 static struct attribute *armv8_pmuv3_caps_attrs[] = {
+	&dev_attr_branches.attr,
 	&dev_attr_slots.attr,
 	&dev_attr_bus_slots.attr,
 	&dev_attr_bus_width.attr,
@@ -446,9 +460,22 @@ static struct attribute *armv8_pmuv3_caps_attrs[] = {
 	NULL,
 };
 
+static umode_t caps_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	struct device *dev = kobj_to_dev(kobj);
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+
+	if (i == 0)
+		return brbe_num_branch_records(cpu_pmu) ? attr->mode : 0;
+
+	return attr->mode;
+}
+
 static const struct attribute_group armv8_pmuv3_caps_attr_group = {
 	.name = "caps",
 	.attrs = armv8_pmuv3_caps_attrs,
+	.is_visible = caps_is_visible,
 };
 
 /*
@@ -809,6 +836,7 @@ static void armv8pmu_disable_event(struct perf_event *event)
 static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 {
 	struct perf_event_context *ctx;
+	struct pmu_hw_events *hw_events = this_cpu_ptr(cpu_pmu->hw_events);
 	int nr_user = 0;
 
 	ctx = perf_cpu_task_ctx();
@@ -822,16 +850,34 @@ static void armv8pmu_start(struct arm_pmu *cpu_pmu)
 
 	kvm_vcpu_pmu_resync_el0();
 
+	if (hw_events->branch_users)
+		brbe_enable(cpu_pmu);
+
 	/* Enable all counters */
 	armv8pmu_pmcr_write(armv8pmu_pmcr_read() | ARMV8_PMU_PMCR_E);
 }
 
 static void armv8pmu_stop(struct arm_pmu *cpu_pmu)
 {
+	struct pmu_hw_events *hw_events = this_cpu_ptr(cpu_pmu->hw_events);
+
+	if (hw_events->branch_users)
+		brbe_disable();
+
 	/* Disable all counters */
 	armv8pmu_pmcr_write(armv8pmu_pmcr_read() & ~ARMV8_PMU_PMCR_E);
 }
 
+static void read_branch_records(struct pmu_hw_events *cpuc,
+				struct perf_event *event,
+				struct perf_sample_data *data)
+{
+	struct perf_branch_stack *branch_stack = cpuc->branch_stack;
+
+	brbe_read_filtered_entries(branch_stack, event);
+	perf_sample_save_brstack(data, event, branch_stack, NULL);
+}
+
 static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 {
 	u64 pmovsr;
@@ -882,6 +928,9 @@ static irqreturn_t armv8pmu_handle_irq(struct arm_pmu *cpu_pmu)
 		if (!armpmu_event_set_period(event))
 			continue;
 
+		if (has_branch_stack(event))
+			read_branch_records(cpuc, event, &data);
+
 		/*
 		 * Perf event overflow will queue the processing of the event as
 		 * an irq_work which will be taken care of in the handling of
@@ -938,7 +987,7 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
 
 	/* Always prefer to place a cycle counter into the cycle counter. */
 	if ((evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) &&
-	    !armv8pmu_event_get_threshold(&event->attr)) {
+	    !armv8pmu_event_get_threshold(&event->attr) && !has_branch_stack(event)) {
 		if (!test_and_set_bit(ARMV8_PMU_CYCLE_IDX, cpuc->used_mask))
 			return ARMV8_PMU_CYCLE_IDX;
 		else if (armv8pmu_event_is_64bit(event) &&
@@ -987,6 +1036,19 @@ static int armv8pmu_user_event_idx(struct perf_event *event)
 	return event->hw.idx + 1;
 }
 
+static void armv8pmu_sched_task(struct perf_event_pmu_context *pmu_ctx,
+				struct task_struct *task, bool sched_in)
+{
+	struct arm_pmu *armpmu = *this_cpu_ptr(&cpu_armpmu);
+	struct pmu_hw_events *hw_events = this_cpu_ptr(armpmu->hw_events);
+
+	if (!hw_events->branch_users)
+		return;
+
+	if (sched_in)
+		brbe_invalidate();
+}
+
 /*
  * Add an event filter to a given event.
  */
@@ -1004,6 +1066,13 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
 		return -EOPNOTSUPP;
 	}
 
+	if (has_branch_stack(perf_event)) {
+		if (!brbe_num_branch_records(cpu_pmu) || !brbe_branch_attr_valid(perf_event))
+			return -EOPNOTSUPP;
+
+		perf_event->attach_state |= PERF_ATTACH_SCHED_CB;
+	}
+
 	/*
 	 * If we're running in hyp mode, then we *are* the hypervisor.
 	 * Therefore we ignore exclude_hv in this configuration, since
@@ -1070,6 +1139,11 @@ static void armv8pmu_reset(void *info)
 	/* Clear the counters we flip at guest entry/exit */
 	kvm_clr_pmu_events(mask);
 
+	if (brbe_num_branch_records(cpu_pmu)) {
+		brbe_disable();
+		brbe_invalidate();
+	}
+
 	/*
 	 * Initialize & Reset PMNC. Request overflow interrupt for
 	 * 64 bit cycle counter but cheat in armv8pmu_write_counter().
@@ -1238,6 +1312,25 @@ static void __armv8pmu_probe_pmu(void *info)
 		cpu_pmu->reg_pmmir = read_pmmir();
 	else
 		cpu_pmu->reg_pmmir = 0;
+
+	brbe_probe(cpu_pmu);
+}
+
+static int branch_records_alloc(struct arm_pmu *armpmu)
+{
+	size_t size = struct_size_t(struct perf_branch_stack, entries,
+				    brbe_num_branch_records(armpmu));
+	int cpu;
+
+	for_each_cpu(cpu, &armpmu->supported_cpus) {
+		struct pmu_hw_events *events_cpu;
+
+		events_cpu = per_cpu_ptr(armpmu->hw_events, cpu);
+		events_cpu->branch_stack = kmalloc(size, GFP_KERNEL);
+		if (!events_cpu->branch_stack)
+			return -ENOMEM;
+	}
+	return 0;
 }
 
 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
@@ -1254,7 +1347,15 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
 	if (ret)
 		return ret;
 
-	return probe.present ? 0 : -ENODEV;
+	if (!probe.present)
+		return -ENODEV;
+
+	if (brbe_num_branch_records(cpu_pmu)) {
+		ret = branch_records_alloc(cpu_pmu);
+		if (ret)
+			return ret;
+	}
+	return 0;
 }
 
 static void armv8pmu_disable_user_access_ipi(void *unused)
@@ -1313,6 +1414,8 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 	cpu_pmu->set_event_filter	= armv8pmu_set_event_filter;
 
 	cpu_pmu->pmu.event_idx		= armv8pmu_user_event_idx;
+	if (brbe_num_branch_records(cpu_pmu))
+		cpu_pmu->pmu.sched_task		= armv8pmu_sched_task;
 
 	cpu_pmu->name			= name;
 	cpu_pmu->map_event		= map_event;
diff --git a/include/linux/perf/arm_pmu.h b/include/linux/perf/arm_pmu.h
index 6dc5e0cd76ca..93c9a26492fc 100644
--- a/include/linux/perf/arm_pmu.h
+++ b/include/linux/perf/arm_pmu.h
@@ -70,6 +70,11 @@ struct pmu_hw_events {
 	struct arm_pmu		*percpu_pmu;
 
 	int irq;
+
+	struct perf_branch_stack	*branch_stack;
+
+	/* Active events requesting branch records */
+	unsigned int		branch_users;
 };
 
 enum armpmu_attr_groups {
@@ -115,6 +120,7 @@ struct arm_pmu {
 	/* PMUv3 only */
 	int		pmuver;
 	u64		reg_pmmir;
+	u64		reg_brbidr;
 #define ARMV8_PMUV3_MAX_COMMON_EVENTS		0x40
 	DECLARE_BITMAP(pmceid_bitmap, ARMV8_PMUV3_MAX_COMMON_EVENTS);
 #define ARMV8_PMUV3_EXT_COMMON_EVENT_BASE	0x4000
@@ -126,6 +132,8 @@ struct arm_pmu {
 
 #define to_arm_pmu(p) (container_of(p, struct arm_pmu, pmu))
 
+DECLARE_PER_CPU(struct arm_pmu *, cpu_armpmu);
+
 u64 armpmu_event_update(struct perf_event *event);
 
 int armpmu_event_set_period(struct perf_event *event);
-- 
cgit v1.2.3


From fc582cd26e888b0652bc1494f252329453fd3b23 Mon Sep 17 00:00:00 2001
From: Jens Axboe <axboe@kernel.dk>
Date: Tue, 8 Jul 2025 11:00:32 -0600
Subject: io_uring/msg_ring: ensure io_kiocb freeing is deferred for RCU

syzbot reports that defer/local task_work adding via msg_ring can hit
a request that has been freed:

CPU: 1 UID: 0 PID: 19356 Comm: iou-wrk-19354 Not tainted 6.16.0-rc4-syzkaller-00108-g17bbde2e1716 #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 05/07/2025
Call Trace:
 <TASK>
 dump_stack_lvl+0x189/0x250 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:408 [inline]
 print_report+0xd2/0x2b0 mm/kasan/report.c:521
 kasan_report+0x118/0x150 mm/kasan/report.c:634
 io_req_local_work_add io_uring/io_uring.c:1184 [inline]
 __io_req_task_work_add+0x589/0x950 io_uring/io_uring.c:1252
 io_msg_remote_post io_uring/msg_ring.c:103 [inline]
 io_msg_data_remote io_uring/msg_ring.c:133 [inline]
 __io_msg_ring_data+0x820/0xaa0 io_uring/msg_ring.c:151
 io_msg_ring_data io_uring/msg_ring.c:173 [inline]
 io_msg_ring+0x134/0xa00 io_uring/msg_ring.c:314
 __io_issue_sqe+0x17e/0x4b0 io_uring/io_uring.c:1739
 io_issue_sqe+0x165/0xfd0 io_uring/io_uring.c:1762
 io_wq_submit_work+0x6e9/0xb90 io_uring/io_uring.c:1874
 io_worker_handle_work+0x7cd/0x1180 io_uring/io-wq.c:642
 io_wq_worker+0x42f/0xeb0 io_uring/io-wq.c:696
 ret_from_fork+0x3fc/0x770 arch/x86/kernel/process.c:148
 ret_from_fork_asm+0x1a/0x30 arch/x86/entry/entry_64.S:245
 </TASK>

which is supposed to be safe with how requests are allocated. But msg
ring requests alloc and free on their own, and hence must defer freeing
to a sane time.

Add an rcu_head and use kfree_rcu() in both spots where requests are
freed. Only the one in io_msg_tw_complete() is strictly required as it
has been visible on the other ring, but use it consistently in the other
spot as well.

This should not cause any other issues outside of KASAN rightfully
complaining about it.

Link: https://lore.kernel.org/io-uring/686cd2ea.a00a0220.338033.0007.GAE@google.com/
Reported-by: syzbot+54cbbfb4db9145d26fc2@syzkaller.appspotmail.com
Cc: stable@vger.kernel.org
Fixes: 0617bb500bfa ("io_uring/msg_ring: improve handling of target CQE posting")
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring_types.h | 2 ++
 io_uring/msg_ring.c            | 4 ++--
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
index 2922635986f5..a7efcec2e3d0 100644
--- a/include/linux/io_uring_types.h
+++ b/include/linux/io_uring_types.h
@@ -698,6 +698,8 @@ struct io_kiocb {
 		struct hlist_node	hash_node;
 		/* For IOPOLL setup queues, with hybrid polling */
 		u64                     iopoll_start;
+		/* for private io_kiocb freeing */
+		struct rcu_head		rcu_head;
 	};
 	/* internal polling, see IORING_FEAT_FAST_POLL */
 	struct async_poll		*apoll;
diff --git a/io_uring/msg_ring.c b/io_uring/msg_ring.c
index 71400d6cefc8..4c2578f2efcb 100644
--- a/io_uring/msg_ring.c
+++ b/io_uring/msg_ring.c
@@ -82,7 +82,7 @@ static void io_msg_tw_complete(struct io_kiocb *req, io_tw_token_t tw)
 		spin_unlock(&ctx->msg_lock);
 	}
 	if (req)
-		kmem_cache_free(req_cachep, req);
+		kfree_rcu(req, rcu_head);
 	percpu_ref_put(&ctx->refs);
 }
 
@@ -90,7 +90,7 @@ static int io_msg_remote_post(struct io_ring_ctx *ctx, struct io_kiocb *req,
 			      int res, u32 cflags, u64 user_data)
 {
 	if (!READ_ONCE(ctx->submitter_task)) {
-		kmem_cache_free(req_cachep, req);
+		kfree_rcu(req, rcu_head);
 		return -EOWNERDEAD;
 	}
 	req->opcode = IORING_OP_NOP;
-- 
cgit v1.2.3


From 7ec80fb3f025825e860b433685fb801d6de34bf3 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 3 Jul 2025 12:25:10 +0200
Subject: irqchip/gic-v5: Add GICv5 PPI support

The GICv5 CPU interface implements support for PE-Private Peripheral
Interrupts (PPI), that are handled (enabled/prioritized/delivered)
entirely within the CPU interface hardware.

To enable PPI interrupts, implement the baseline GICv5 host kernel
driver infrastructure required to handle interrupts on a GICv5 system.

Add the exception handling code path and definitions for GICv5
instructions.

Add GICv5 PPI handling code as a specific IRQ domain to:

- Set-up PPI priority
- Manage PPI configuration and state
- Manage IRQ flow handler
- IRQs allocation/free
- Hook-up a PPI specific IRQchip to provide the relevant methods

PPI IRQ priority is chosen as the minimum allowed priority by the
system design (after probing the number of priority bits implemented
by the CPU interface).

Co-developed-by: Sascha Bischoff <sascha.bischoff@arm.com>
Signed-off-by: Sascha Bischoff <sascha.bischoff@arm.com>
Co-developed-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250703-gicv5-host-v7-20-12e71f1b3528@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 MAINTAINERS                        |   2 +
 arch/arm64/include/asm/sysreg.h    |  19 ++
 drivers/irqchip/Kconfig            |   5 +
 drivers/irqchip/Makefile           |   1 +
 drivers/irqchip/irq-gic-v5.c       | 464 +++++++++++++++++++++++++++++++++++++
 include/linux/irqchip/arm-gic-v5.h |  19 ++
 6 files changed, 510 insertions(+)
 create mode 100644 drivers/irqchip/irq-gic-v5.c
 create mode 100644 include/linux/irqchip/arm-gic-v5.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index c5452096c593..b1202987eef5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1970,6 +1970,8 @@ M:	Marc Zyngier <maz@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/interrupt-controller/arm,gic-v5*.yaml
+F:	drivers/irqchip/irq-gic-v5*.[ch]
+F:	include/linux/irqchip/arm-gic-v5.h
 
 ARM HDLCD DRM DRIVER
 M:	Liviu Dudau <liviu.dudau@arm.com>
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 9b5fc6389715..36b82d74db37 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1082,6 +1082,25 @@
 
 #define GCS_CAP(x)	((((unsigned long)x) & GCS_CAP_ADDR_MASK) | \
 					       GCS_CAP_VALID_TOKEN)
+/*
+ * Definitions for GICv5 instructions
+ */
+#define GICV5_OP_GIC_CDDI		sys_insn(1, 0, 12, 2, 0)
+#define GICV5_OP_GIC_CDEOI		sys_insn(1, 0, 12, 1, 7)
+#define GICV5_OP_GICR_CDIA		sys_insn(1, 0, 12, 3, 0)
+
+/* Definitions for GIC CDDI */
+#define GICV5_GIC_CDDI_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDDI_ID_MASK		GENMASK_ULL(23, 0)
+
+/* Definitions for GICR CDIA */
+#define GICV5_GIC_CDIA_VALID_MASK	BIT_ULL(32)
+#define GICV5_GICR_CDIA_VALID(r)	FIELD_GET(GICV5_GIC_CDIA_VALID_MASK, r)
+#define GICV5_GIC_CDIA_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDIA_ID_MASK		GENMASK_ULL(23, 0)
+
+#define gicr_insn(insn)			read_sysreg_s(GICV5_OP_GICR_##insn)
+#define gic_insn(v, insn)		write_sysreg_s(v, GICV5_OP_GIC_##insn)
 
 #define ARM64_FEATURE_FIELD_BITS	4
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index 0d196e447142..3e4fb08b7a4d 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -54,6 +54,11 @@ config ARM_GIC_V3_ITS_FSL_MC
 	depends on FSL_MC_BUS
 	default ARM_GIC_V3_ITS
 
+config ARM_GIC_V5
+	bool
+	select IRQ_DOMAIN_HIERARCHY
+	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
+
 config ARM_NVIC
 	bool
 	select IRQ_DOMAIN_HIERARCHY
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 23ca4959e6ce..3d75659d99eb 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -36,6 +36,7 @@ obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-v3-mbi.o irq-gic-common.o
 obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o irq-gic-v4.o irq-gic-v3-its-msi-parent.o
 obj-$(CONFIG_ARM_GIC_V3_ITS_FSL_MC)	+= irq-gic-v3-its-fsl-mc-msi.o
 obj-$(CONFIG_PARTITION_PERCPU)		+= irq-partition-percpu.o
+obj-$(CONFIG_ARM_GIC_V5)		+= irq-gic-v5.o
 obj-$(CONFIG_HISILICON_IRQ_MBIGEN)	+= irq-mbigen.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c
new file mode 100644
index 000000000000..0bb940212e20
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v5.c
@@ -0,0 +1,464 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024-2025 ARM Limited, All Rights Reserved.
+ */
+
+#define pr_fmt(fmt)	"GICv5: " fmt
+
+#include <linux/irqdomain.h>
+#include <linux/wordpart.h>
+
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic-v5.h>
+
+#include <asm/cpufeature.h>
+#include <asm/exception.h>
+
+static u8 pri_bits __ro_after_init = 5;
+
+#define GICV5_IRQ_PRI_MASK	0x1f
+#define GICV5_IRQ_PRI_MI	(GICV5_IRQ_PRI_MASK & GENMASK(4, 5 - pri_bits))
+
+#define PPI_NR	128
+
+static bool gicv5_cpuif_has_gcie(void)
+{
+	return this_cpu_has_cap(ARM64_HAS_GICV5_CPUIF);
+}
+
+struct gicv5_chip_data {
+	struct fwnode_handle	*fwnode;
+	struct irq_domain	*ppi_domain;
+};
+
+static struct gicv5_chip_data gicv5_global_data __read_mostly;
+
+static void gicv5_ppi_priority_init(void)
+{
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR0_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR1_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR2_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR3_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR4_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR5_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR6_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR7_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR8_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR9_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR10_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR11_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR12_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR13_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR14_EL1);
+	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR15_EL1);
+
+	/*
+	 * Context syncronization required to make sure system register writes
+	 * effects are synchronised.
+	 */
+	isb();
+}
+
+static void gicv5_ppi_irq_mask(struct irq_data *d)
+{
+	u64 hwirq_id_bit = BIT_ULL(d->hwirq % 64);
+
+	if (d->hwirq < 64)
+		sysreg_clear_set_s(SYS_ICC_PPI_ENABLER0_EL1, hwirq_id_bit, 0);
+	else
+		sysreg_clear_set_s(SYS_ICC_PPI_ENABLER1_EL1, hwirq_id_bit, 0);
+
+	/*
+	 * We must ensure that the disable takes effect immediately to
+	 * guarantee that the lazy-disabled IRQ mechanism works.
+	 * A context synchronization event is required to guarantee it.
+	 * Reference: I_ZLTKB/R_YRGMH GICv5 specification - section 2.9.1.
+	 */
+	isb();
+}
+
+static void gicv5_ppi_irq_unmask(struct irq_data *d)
+{
+	u64 hwirq_id_bit = BIT_ULL(d->hwirq % 64);
+
+	if (d->hwirq < 64)
+		sysreg_clear_set_s(SYS_ICC_PPI_ENABLER0_EL1, 0, hwirq_id_bit);
+	else
+		sysreg_clear_set_s(SYS_ICC_PPI_ENABLER1_EL1, 0, hwirq_id_bit);
+	/*
+	 * We must ensure that the enable takes effect in finite time - a
+	 * context synchronization event is required to guarantee it, we
+	 * can not take for granted that would happen (eg a core going straight
+	 * into idle after enabling a PPI).
+	 * Reference: I_ZLTKB/R_YRGMH GICv5 specification - section 2.9.1.
+	 */
+	isb();
+}
+
+static void gicv5_hwirq_eoi(u32 hwirq_id, u8 hwirq_type)
+{
+	u64 cddi;
+
+	cddi = FIELD_PREP(GICV5_GIC_CDDI_ID_MASK, hwirq_id)	|
+	       FIELD_PREP(GICV5_GIC_CDDI_TYPE_MASK, hwirq_type);
+
+	gic_insn(cddi, CDDI);
+
+	gic_insn(0, CDEOI);
+}
+
+static void gicv5_ppi_irq_eoi(struct irq_data *d)
+{
+	gicv5_hwirq_eoi(d->hwirq, GICV5_HWIRQ_TYPE_PPI);
+}
+
+enum ppi_reg {
+	PPI_PENDING,
+	PPI_ACTIVE,
+	PPI_HM
+};
+
+static __always_inline u64 read_ppi_sysreg_s(unsigned int irq,
+					     const enum ppi_reg which)
+{
+	switch (which) {
+	case PPI_PENDING:
+		return irq < 64	? read_sysreg_s(SYS_ICC_PPI_SPENDR0_EL1) :
+				  read_sysreg_s(SYS_ICC_PPI_SPENDR1_EL1);
+	case PPI_ACTIVE:
+		return irq < 64	? read_sysreg_s(SYS_ICC_PPI_SACTIVER0_EL1) :
+				  read_sysreg_s(SYS_ICC_PPI_SACTIVER1_EL1);
+	case PPI_HM:
+		return irq < 64	? read_sysreg_s(SYS_ICC_PPI_HMR0_EL1) :
+				  read_sysreg_s(SYS_ICC_PPI_HMR1_EL1);
+	default:
+		BUILD_BUG_ON(1);
+	}
+}
+
+static __always_inline void write_ppi_sysreg_s(unsigned int irq, bool set,
+					       const enum ppi_reg which)
+{
+	u64 bit = BIT_ULL(irq % 64);
+
+	switch (which) {
+	case PPI_PENDING:
+		if (set) {
+			if (irq < 64)
+				write_sysreg_s(bit, SYS_ICC_PPI_SPENDR0_EL1);
+			else
+				write_sysreg_s(bit, SYS_ICC_PPI_SPENDR1_EL1);
+		} else {
+			if (irq < 64)
+				write_sysreg_s(bit, SYS_ICC_PPI_CPENDR0_EL1);
+			else
+				write_sysreg_s(bit, SYS_ICC_PPI_CPENDR1_EL1);
+		}
+		return;
+	case PPI_ACTIVE:
+		if (set) {
+			if (irq < 64)
+				write_sysreg_s(bit, SYS_ICC_PPI_SACTIVER0_EL1);
+			else
+				write_sysreg_s(bit, SYS_ICC_PPI_SACTIVER1_EL1);
+		} else {
+			if (irq < 64)
+				write_sysreg_s(bit, SYS_ICC_PPI_CACTIVER0_EL1);
+			else
+				write_sysreg_s(bit, SYS_ICC_PPI_CACTIVER1_EL1);
+		}
+		return;
+	default:
+		BUILD_BUG_ON(1);
+	}
+}
+
+static int gicv5_ppi_irq_get_irqchip_state(struct irq_data *d,
+					   enum irqchip_irq_state which,
+					   bool *state)
+{
+	u64 hwirq_id_bit = BIT_ULL(d->hwirq % 64);
+
+	switch (which) {
+	case IRQCHIP_STATE_PENDING:
+		*state = !!(read_ppi_sysreg_s(d->hwirq, PPI_PENDING) & hwirq_id_bit);
+		return 0;
+	case IRQCHIP_STATE_ACTIVE:
+		*state = !!(read_ppi_sysreg_s(d->hwirq, PPI_ACTIVE) & hwirq_id_bit);
+		return 0;
+	default:
+		pr_debug("Unexpected PPI irqchip state\n");
+		return -EINVAL;
+	}
+}
+
+static int gicv5_ppi_irq_set_irqchip_state(struct irq_data *d,
+					   enum irqchip_irq_state which,
+					   bool state)
+{
+	switch (which) {
+	case IRQCHIP_STATE_PENDING:
+		write_ppi_sysreg_s(d->hwirq, state, PPI_PENDING);
+		return 0;
+	case IRQCHIP_STATE_ACTIVE:
+		write_ppi_sysreg_s(d->hwirq, state, PPI_ACTIVE);
+		return 0;
+	default:
+		pr_debug("Unexpected PPI irqchip state\n");
+		return -EINVAL;
+	}
+}
+
+static bool gicv5_ppi_irq_is_level(irq_hw_number_t hwirq)
+{
+	u64 bit = BIT_ULL(hwirq % 64);
+
+	return !!(read_ppi_sysreg_s(hwirq, PPI_HM) & bit);
+}
+
+static const struct irq_chip gicv5_ppi_irq_chip = {
+	.name			= "GICv5-PPI",
+	.irq_mask		= gicv5_ppi_irq_mask,
+	.irq_unmask		= gicv5_ppi_irq_unmask,
+	.irq_eoi		= gicv5_ppi_irq_eoi,
+	.irq_get_irqchip_state	= gicv5_ppi_irq_get_irqchip_state,
+	.irq_set_irqchip_state	= gicv5_ppi_irq_set_irqchip_state,
+	.flags			= IRQCHIP_SKIP_SET_WAKE	  |
+				  IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static int gicv5_irq_ppi_domain_translate(struct irq_domain *d,
+					  struct irq_fwspec *fwspec,
+					  irq_hw_number_t *hwirq,
+					  unsigned int *type)
+{
+	if (!is_of_node(fwspec->fwnode))
+		return -EINVAL;
+
+	if (fwspec->param_count < 3)
+		return -EINVAL;
+
+	if (fwspec->param[0] != GICV5_HWIRQ_TYPE_PPI)
+		return -EINVAL;
+
+	*hwirq = fwspec->param[1];
+
+	/*
+	 * Handling mode is hardcoded for PPIs, set the type using
+	 * HW reported value.
+	 */
+	*type = gicv5_ppi_irq_is_level(*hwirq) ? IRQ_TYPE_LEVEL_LOW : IRQ_TYPE_EDGE_RISING;
+
+	return 0;
+}
+
+static int gicv5_irq_ppi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				      unsigned int nr_irqs, void *arg)
+{
+	unsigned int type = IRQ_TYPE_NONE;
+	struct irq_fwspec *fwspec = arg;
+	irq_hw_number_t hwirq;
+	int ret;
+
+	if (WARN_ON_ONCE(nr_irqs != 1))
+		return -EINVAL;
+
+	ret = gicv5_irq_ppi_domain_translate(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	if (type & IRQ_TYPE_LEVEL_MASK)
+		irq_set_status_flags(virq, IRQ_LEVEL);
+
+	irq_set_percpu_devid(virq);
+	irq_domain_set_info(domain, virq, hwirq, &gicv5_ppi_irq_chip, NULL,
+			    handle_percpu_devid_irq, NULL, NULL);
+
+	return 0;
+}
+
+static void gicv5_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				  unsigned int nr_irqs)
+{
+	struct irq_data *d;
+
+	if (WARN_ON_ONCE(nr_irqs != 1))
+		return;
+
+	d = irq_domain_get_irq_data(domain, virq);
+
+	irq_set_handler(virq, NULL);
+	irq_domain_reset_irq_data(d);
+}
+
+static int gicv5_irq_ppi_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec,
+				       enum irq_domain_bus_token bus_token)
+{
+	if (fwspec->fwnode != d->fwnode)
+		return 0;
+
+	if (fwspec->param[0] != GICV5_HWIRQ_TYPE_PPI)
+		return 0;
+
+	return (d == gicv5_global_data.ppi_domain);
+}
+
+static const struct irq_domain_ops gicv5_irq_ppi_domain_ops = {
+	.translate	= gicv5_irq_ppi_domain_translate,
+	.alloc		= gicv5_irq_ppi_domain_alloc,
+	.free		= gicv5_irq_domain_free,
+	.select		= gicv5_irq_ppi_domain_select
+};
+
+static void handle_irq_per_domain(u32 hwirq)
+{
+	u8 hwirq_type = FIELD_GET(GICV5_HWIRQ_TYPE, hwirq);
+	u32 hwirq_id = FIELD_GET(GICV5_HWIRQ_ID, hwirq);
+	struct irq_domain *domain;
+
+	switch (hwirq_type) {
+	case GICV5_HWIRQ_TYPE_PPI:
+		domain = gicv5_global_data.ppi_domain;
+		break;
+	default:
+		pr_err_once("Unknown IRQ type, bail out\n");
+		return;
+	}
+
+	if (generic_handle_domain_irq(domain, hwirq_id)) {
+		pr_err_once("Could not handle, hwirq = 0x%x", hwirq_id);
+		gicv5_hwirq_eoi(hwirq_id, hwirq_type);
+	}
+}
+
+static void __exception_irq_entry gicv5_handle_irq(struct pt_regs *regs)
+{
+	bool valid;
+	u32 hwirq;
+	u64 ia;
+
+	ia = gicr_insn(CDIA);
+	valid = GICV5_GICR_CDIA_VALID(ia);
+
+	if (!valid)
+		return;
+
+	/*
+	 * Ensure that the CDIA instruction effects (ie IRQ activation) are
+	 * completed before handling the interrupt.
+	 */
+	gsb_ack();
+
+	/*
+	 * Ensure instruction ordering between an acknowledgment and subsequent
+	 * instructions in the IRQ handler using an ISB.
+	 */
+	isb();
+
+	hwirq = FIELD_GET(GICV5_HWIRQ_INTID, ia);
+
+	handle_irq_per_domain(hwirq);
+}
+
+static void gicv5_cpu_disable_interrupts(void)
+{
+	u64 cr0;
+
+	cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 0);
+	write_sysreg_s(cr0, SYS_ICC_CR0_EL1);
+}
+
+static void gicv5_cpu_enable_interrupts(void)
+{
+	u64 cr0, pcr;
+
+	write_sysreg_s(0, SYS_ICC_PPI_ENABLER0_EL1);
+	write_sysreg_s(0, SYS_ICC_PPI_ENABLER1_EL1);
+
+	gicv5_ppi_priority_init();
+
+	pcr = FIELD_PREP(ICC_PCR_EL1_PRIORITY, GICV5_IRQ_PRI_MI);
+	write_sysreg_s(pcr, SYS_ICC_PCR_EL1);
+
+	cr0 = FIELD_PREP(ICC_CR0_EL1_EN, 1);
+	write_sysreg_s(cr0, SYS_ICC_CR0_EL1);
+}
+
+static int gicv5_starting_cpu(unsigned int cpu)
+{
+	if (WARN(!gicv5_cpuif_has_gcie(),
+		 "GICv5 system components present but CPU does not have FEAT_GCIE"))
+		return -ENODEV;
+
+	gicv5_cpu_enable_interrupts();
+
+	return 0;
+}
+
+static void __init gicv5_free_domains(void)
+{
+	if (gicv5_global_data.ppi_domain)
+		irq_domain_remove(gicv5_global_data.ppi_domain);
+
+	gicv5_global_data.ppi_domain = NULL;
+}
+
+static int __init gicv5_init_domains(struct fwnode_handle *handle)
+{
+	struct irq_domain *d;
+
+	d = irq_domain_create_linear(handle, PPI_NR, &gicv5_irq_ppi_domain_ops, NULL);
+	if (!d)
+		return -ENOMEM;
+
+	irq_domain_update_bus_token(d, DOMAIN_BUS_WIRED);
+	gicv5_global_data.ppi_domain = d;
+	gicv5_global_data.fwnode = handle;
+
+	return 0;
+}
+
+static void gicv5_set_cpuif_pribits(void)
+{
+	u64 icc_idr0 = read_sysreg_s(SYS_ICC_IDR0_EL1);
+
+	switch (FIELD_GET(ICC_IDR0_EL1_PRI_BITS, icc_idr0)) {
+	case ICC_IDR0_EL1_PRI_BITS_4BITS:
+		pri_bits = 4;
+		break;
+	case ICC_IDR0_EL1_PRI_BITS_5BITS:
+		pri_bits = 5;
+		break;
+	default:
+		pr_err("Unexpected ICC_IDR0_EL1_PRI_BITS value, default to 4");
+		pri_bits = 4;
+		break;
+	}
+}
+
+static int __init gicv5_of_init(struct device_node *node, struct device_node *parent)
+{
+	int ret = gicv5_init_domains(of_fwnode_handle(node));
+	if (ret)
+		return ret;
+
+	gicv5_set_cpuif_pribits();
+
+	ret = gicv5_starting_cpu(smp_processor_id());
+	if (ret)
+		goto out_dom;
+
+	ret = set_handle_irq(gicv5_handle_irq);
+	if (ret)
+		goto out_int;
+
+	return 0;
+
+out_int:
+	gicv5_cpu_disable_interrupts();
+out_dom:
+	gicv5_free_domains();
+
+	return ret;
+}
+IRQCHIP_DECLARE(gic_v5, "arm,gic-v5", gicv5_of_init);
diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h
new file mode 100644
index 000000000000..b08ec0308a9b
--- /dev/null
+++ b/include/linux/irqchip/arm-gic-v5.h
@@ -0,0 +1,19 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (C) 2025 ARM Limited, All Rights Reserved.
+ */
+#ifndef __LINUX_IRQCHIP_ARM_GIC_V5_H
+#define __LINUX_IRQCHIP_ARM_GIC_V5_H
+
+#include <asm/sysreg.h>
+
+/*
+ * INTID handling
+ */
+#define GICV5_HWIRQ_ID			GENMASK(23, 0)
+#define GICV5_HWIRQ_TYPE		GENMASK(31, 29)
+#define GICV5_HWIRQ_INTID		GENMASK_ULL(31, 0)
+
+#define GICV5_HWIRQ_TYPE_PPI		UL(0x1)
+
+#endif
-- 
cgit v1.2.3


From 5cb1b6dab2def316671ea2565291a86ad58b884c Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 3 Jul 2025 12:25:11 +0200
Subject: irqchip/gic-v5: Add GICv5 IRS/SPI support

The GICv5 Interrupt Routing Service (IRS) component implements
interrupt management and routing in the GICv5 architecture.

A GICv5 system comprises one or more IRSes, that together
handle the interrupt routing and state for the system.

An IRS supports Shared Peripheral Interrupts (SPIs), that are
interrupt sources directly connected to the IRS; they do not
rely on memory for storage. The number of supported SPIs is
fixed for a given implementation and can be probed through IRS
IDR registers.

SPI interrupt state and routing are managed through GICv5
instructions.

Each core (PE in GICv5 terms) in a GICv5 system is identified with
an Interrupt AFFinity ID (IAFFID).

An IRS manages a set of cores that are connected to it.

Firmware provides a topology description that the driver uses
to detect to which IRS a CPU (ie an IAFFID) is associated with.

Use probeable information and firmware description to initialize
the IRSes and implement GICv5 IRS SPIs support through an
SPI-specific IRQ domain.

The GICv5 IRS driver:

- Probes IRSes in the system to detect SPI ranges
- Associates an IRS with a set of cores connected to it
- Adds an IRQchip structure for SPI handling

SPIs priority is set to a value corresponding to the lowest
permissible priority in the system (taking into account the
implemented priority bits of the IRS and CPU interface).

Since all IRQs are set to the same priority value, the value
itself does not matter as long as it is a valid one.

Co-developed-by: Sascha Bischoff <sascha.bischoff@arm.com>
Signed-off-by: Sascha Bischoff <sascha.bischoff@arm.com>
Co-developed-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250703-gicv5-host-v7-21-12e71f1b3528@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/sysreg.h    |  36 +++
 drivers/irqchip/Makefile           |   2 +-
 drivers/irqchip/irq-gic-v5-irs.c   | 434 +++++++++++++++++++++++++++++++++++++
 drivers/irqchip/irq-gic-v5.c       | 347 +++++++++++++++++++++++++++--
 include/linux/irqchip/arm-gic-v5.h | 140 ++++++++++++
 5 files changed, 937 insertions(+), 22 deletions(-)
 create mode 100644 drivers/irqchip/irq-gic-v5-irs.c

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index 36b82d74db37..efd2e7a1fbe2 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1085,14 +1085,50 @@
 /*
  * Definitions for GICv5 instructions
  */
+#define GICV5_OP_GIC_CDAFF		sys_insn(1, 0, 12, 1, 3)
 #define GICV5_OP_GIC_CDDI		sys_insn(1, 0, 12, 2, 0)
+#define GICV5_OP_GIC_CDDIS		sys_insn(1, 0, 12, 1, 0)
+#define GICV5_OP_GIC_CDEN		sys_insn(1, 0, 12, 1, 1)
 #define GICV5_OP_GIC_CDEOI		sys_insn(1, 0, 12, 1, 7)
+#define GICV5_OP_GIC_CDPEND		sys_insn(1, 0, 12, 1, 4)
+#define GICV5_OP_GIC_CDPRI		sys_insn(1, 0, 12, 1, 2)
+#define GICV5_OP_GIC_CDRCFG		sys_insn(1, 0, 12, 1, 5)
 #define GICV5_OP_GICR_CDIA		sys_insn(1, 0, 12, 3, 0)
 
+/* Definitions for GIC CDAFF */
+#define GICV5_GIC_CDAFF_IAFFID_MASK	GENMASK_ULL(47, 32)
+#define GICV5_GIC_CDAFF_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDAFF_IRM_MASK	BIT_ULL(28)
+#define GICV5_GIC_CDAFF_ID_MASK		GENMASK_ULL(23, 0)
+
 /* Definitions for GIC CDDI */
 #define GICV5_GIC_CDDI_TYPE_MASK	GENMASK_ULL(31, 29)
 #define GICV5_GIC_CDDI_ID_MASK		GENMASK_ULL(23, 0)
 
+/* Definitions for GIC CDDIS */
+#define GICV5_GIC_CDDIS_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDDIS_TYPE(r)		FIELD_GET(GICV5_GIC_CDDIS_TYPE_MASK, r)
+#define GICV5_GIC_CDDIS_ID_MASK		GENMASK_ULL(23, 0)
+#define GICV5_GIC_CDDIS_ID(r)		FIELD_GET(GICV5_GIC_CDDIS_ID_MASK, r)
+
+/* Definitions for GIC CDEN */
+#define GICV5_GIC_CDEN_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDEN_ID_MASK		GENMASK_ULL(23, 0)
+
+/* Definitions for GIC CDPEND */
+#define GICV5_GIC_CDPEND_PENDING_MASK	BIT_ULL(32)
+#define GICV5_GIC_CDPEND_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDPEND_ID_MASK	GENMASK_ULL(23, 0)
+
+/* Definitions for GIC CDPRI */
+#define GICV5_GIC_CDPRI_PRIORITY_MASK	GENMASK_ULL(39, 35)
+#define GICV5_GIC_CDPRI_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDPRI_ID_MASK		GENMASK_ULL(23, 0)
+
+/* Definitions for GIC CDRCFG */
+#define GICV5_GIC_CDRCFG_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDRCFG_ID_MASK	GENMASK_ULL(23, 0)
+
 /* Definitions for GICR CDIA */
 #define GICV5_GIC_CDIA_VALID_MASK	BIT_ULL(32)
 #define GICV5_GICR_CDIA_VALID(r)	FIELD_GET(GICV5_GIC_CDIA_VALID_MASK, r)
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 3d75659d99eb..7a0e6cee09e1 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -36,7 +36,7 @@ obj-$(CONFIG_ARM_GIC_V3)		+= irq-gic-v3.o irq-gic-v3-mbi.o irq-gic-common.o
 obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o irq-gic-v4.o irq-gic-v3-its-msi-parent.o
 obj-$(CONFIG_ARM_GIC_V3_ITS_FSL_MC)	+= irq-gic-v3-its-fsl-mc-msi.o
 obj-$(CONFIG_PARTITION_PERCPU)		+= irq-partition-percpu.o
-obj-$(CONFIG_ARM_GIC_V5)		+= irq-gic-v5.o
+obj-$(CONFIG_ARM_GIC_V5)		+= irq-gic-v5.o irq-gic-v5-irs.o
 obj-$(CONFIG_HISILICON_IRQ_MBIGEN)	+= irq-mbigen.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c
new file mode 100644
index 000000000000..fba8efceb26e
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v5-irs.c
@@ -0,0 +1,434 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024-2025 ARM Limited, All Rights Reserved.
+ */
+
+#define pr_fmt(fmt)	"GICv5 IRS: " fmt
+
+#include <linux/of.h>
+#include <linux/of_address.h>
+
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic-v5.h>
+
+#define IRS_FLAGS_NON_COHERENT		BIT(0)
+
+static DEFINE_PER_CPU_READ_MOSTLY(struct gicv5_irs_chip_data *, per_cpu_irs_data);
+static LIST_HEAD(irs_nodes);
+
+static u32 irs_readl_relaxed(struct gicv5_irs_chip_data *irs_data,
+			     const u32 reg_offset)
+{
+	return readl_relaxed(irs_data->irs_base + reg_offset);
+}
+
+static void irs_writel_relaxed(struct gicv5_irs_chip_data *irs_data,
+			       const u32 val, const u32 reg_offset)
+{
+	writel_relaxed(val, irs_data->irs_base + reg_offset);
+}
+
+struct iaffid_entry {
+	u16	iaffid;
+	bool	valid;
+};
+
+static DEFINE_PER_CPU(struct iaffid_entry, cpu_iaffid);
+
+int gicv5_irs_cpu_to_iaffid(int cpuid, u16 *iaffid)
+{
+	if (!per_cpu(cpu_iaffid, cpuid).valid) {
+		pr_err("IAFFID for CPU %d has not been initialised\n", cpuid);
+		return -ENODEV;
+	}
+
+	*iaffid = per_cpu(cpu_iaffid, cpuid).iaffid;
+
+	return 0;
+}
+
+struct gicv5_irs_chip_data *gicv5_irs_lookup_by_spi_id(u32 spi_id)
+{
+	struct gicv5_irs_chip_data *irs_data;
+	u32 min, max;
+
+	list_for_each_entry(irs_data, &irs_nodes, entry) {
+		if (!irs_data->spi_range)
+			continue;
+
+		min = irs_data->spi_min;
+		max = irs_data->spi_min + irs_data->spi_range - 1;
+		if (spi_id >= min && spi_id <= max)
+			return irs_data;
+	}
+
+	return NULL;
+}
+
+static int gicv5_irs_wait_for_spi_op(struct gicv5_irs_chip_data *irs_data)
+{
+	u32 statusr;
+	int ret;
+
+	ret = gicv5_wait_for_op_atomic(irs_data->irs_base, GICV5_IRS_SPI_STATUSR,
+				       GICV5_IRS_SPI_STATUSR_IDLE, &statusr);
+	if (ret)
+		return ret;
+
+	return !!FIELD_GET(GICV5_IRS_SPI_STATUSR_V, statusr) ? 0 : -EIO;
+}
+
+static int gicv5_irs_wait_for_irs_pe(struct gicv5_irs_chip_data *irs_data,
+				     bool selr)
+{
+	bool valid = true;
+	u32 statusr;
+	int ret;
+
+	ret = gicv5_wait_for_op_atomic(irs_data->irs_base, GICV5_IRS_PE_STATUSR,
+				       GICV5_IRS_PE_STATUSR_IDLE, &statusr);
+	if (ret)
+		return ret;
+
+	if (selr)
+		valid = !!FIELD_GET(GICV5_IRS_PE_STATUSR_V, statusr);
+
+	return valid ? 0 : -EIO;
+}
+
+static int gicv5_irs_wait_for_pe_selr(struct gicv5_irs_chip_data *irs_data)
+{
+	return gicv5_irs_wait_for_irs_pe(irs_data, true);
+}
+
+static int gicv5_irs_wait_for_pe_cr0(struct gicv5_irs_chip_data *irs_data)
+{
+	return gicv5_irs_wait_for_irs_pe(irs_data, false);
+}
+
+int gicv5_spi_irq_set_type(struct irq_data *d, unsigned int type)
+{
+	struct gicv5_irs_chip_data *irs_data = d->chip_data;
+	u32 selr, cfgr;
+	bool level;
+	int ret;
+
+	/*
+	 * There is no distinction between HIGH/LOW for level IRQs
+	 * and RISING/FALLING for edge IRQs in the architecture,
+	 * hence consider them equivalent.
+	 */
+	switch (type) {
+	case IRQ_TYPE_EDGE_RISING:
+	case IRQ_TYPE_EDGE_FALLING:
+		level = false;
+		break;
+	case IRQ_TYPE_LEVEL_HIGH:
+	case IRQ_TYPE_LEVEL_LOW:
+		level = true;
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	guard(raw_spinlock)(&irs_data->spi_config_lock);
+
+	selr = FIELD_PREP(GICV5_IRS_SPI_SELR_ID, d->hwirq);
+	irs_writel_relaxed(irs_data, selr, GICV5_IRS_SPI_SELR);
+	ret = gicv5_irs_wait_for_spi_op(irs_data);
+	if (ret)
+		return ret;
+
+	cfgr = FIELD_PREP(GICV5_IRS_SPI_CFGR_TM, level);
+	irs_writel_relaxed(irs_data, cfgr, GICV5_IRS_SPI_CFGR);
+
+	return gicv5_irs_wait_for_spi_op(irs_data);
+}
+
+static int gicv5_irs_wait_for_idle(struct gicv5_irs_chip_data *irs_data)
+{
+	return gicv5_wait_for_op_atomic(irs_data->irs_base, GICV5_IRS_CR0,
+					GICV5_IRS_CR0_IDLE, NULL);
+}
+
+int gicv5_irs_register_cpu(int cpuid)
+{
+	struct gicv5_irs_chip_data *irs_data;
+	u32 selr, cr0;
+	u16 iaffid;
+	int ret;
+
+	ret = gicv5_irs_cpu_to_iaffid(cpuid, &iaffid);
+	if (ret) {
+		pr_err("IAFFID for CPU %d has not been initialised\n", cpuid);
+		return ret;
+	}
+
+	irs_data = per_cpu(per_cpu_irs_data, cpuid);
+	if (!irs_data) {
+		pr_err("No IRS associated with CPU %u\n", cpuid);
+		return -ENXIO;
+	}
+
+	selr = FIELD_PREP(GICV5_IRS_PE_SELR_IAFFID, iaffid);
+	irs_writel_relaxed(irs_data, selr, GICV5_IRS_PE_SELR);
+
+	ret = gicv5_irs_wait_for_pe_selr(irs_data);
+	if (ret) {
+		pr_err("IAFFID 0x%x used in IRS_PE_SELR is invalid\n", iaffid);
+		return -ENXIO;
+	}
+
+	cr0 = FIELD_PREP(GICV5_IRS_PE_CR0_DPS, 0x1);
+	irs_writel_relaxed(irs_data, cr0, GICV5_IRS_PE_CR0);
+
+	ret = gicv5_irs_wait_for_pe_cr0(irs_data);
+	if (ret)
+		return ret;
+
+	pr_debug("CPU %d enabled PE IAFFID 0x%x\n", cpuid, iaffid);
+
+	return 0;
+}
+
+static void __init gicv5_irs_init_bases(struct gicv5_irs_chip_data *irs_data,
+					void __iomem *irs_base,
+					struct fwnode_handle *handle)
+{
+	struct device_node *np = to_of_node(handle);
+	u32 cr0, cr1;
+
+	irs_data->fwnode = handle;
+	irs_data->irs_base = irs_base;
+
+	if (of_property_read_bool(np, "dma-noncoherent")) {
+		/*
+		 * A non-coherent IRS implies that some cache levels cannot be
+		 * used coherently by the cores and GIC. Our only option is to mark
+		 * memory attributes for the GIC as non-cacheable; by default,
+		 * non-cacheable memory attributes imply outer-shareable
+		 * shareability, the value written into IRS_CR1_SH is ignored.
+		 */
+		cr1 = FIELD_PREP(GICV5_IRS_CR1_VPED_WA, GICV5_NO_WRITE_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VPED_RA, GICV5_NO_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VMD_WA, GICV5_NO_WRITE_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VMD_RA, GICV5_NO_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VPET_RA, GICV5_NO_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VMT_RA, GICV5_NO_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_IST_WA, GICV5_NO_WRITE_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_IST_RA, GICV5_NO_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_IC, GICV5_NON_CACHE)		|
+			FIELD_PREP(GICV5_IRS_CR1_OC, GICV5_NON_CACHE);
+			irs_data->flags |= IRS_FLAGS_NON_COHERENT;
+	} else {
+		cr1 = FIELD_PREP(GICV5_IRS_CR1_VPED_WA, GICV5_WRITE_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VPED_RA, GICV5_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VMD_WA, GICV5_WRITE_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VMD_RA, GICV5_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VPET_RA, GICV5_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_VMT_RA, GICV5_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_IST_WA, GICV5_WRITE_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_IST_RA, GICV5_READ_ALLOC)	|
+			FIELD_PREP(GICV5_IRS_CR1_IC, GICV5_WB_CACHE)		|
+			FIELD_PREP(GICV5_IRS_CR1_OC, GICV5_WB_CACHE)		|
+			FIELD_PREP(GICV5_IRS_CR1_SH, GICV5_INNER_SHARE);
+	}
+
+	irs_writel_relaxed(irs_data, cr1, GICV5_IRS_CR1);
+
+	cr0 = FIELD_PREP(GICV5_IRS_CR0_IRSEN, 0x1);
+	irs_writel_relaxed(irs_data, cr0, GICV5_IRS_CR0);
+	gicv5_irs_wait_for_idle(irs_data);
+}
+
+static int __init gicv5_irs_of_init_affinity(struct device_node *node,
+					     struct gicv5_irs_chip_data *irs_data,
+					     u8 iaffid_bits)
+{
+	/*
+	 * Detect IAFFID<->CPU mappings from the device tree and
+	 * record IRS<->CPU topology information.
+	 */
+	u16 iaffid_mask = GENMASK(iaffid_bits - 1, 0);
+	int ret, i, ncpus, niaffids;
+
+	ncpus = of_count_phandle_with_args(node, "cpus", NULL);
+	if (ncpus < 0)
+		return -EINVAL;
+
+	niaffids = of_property_count_elems_of_size(node, "arm,iaffids",
+						   sizeof(u16));
+	if (niaffids != ncpus)
+		return -EINVAL;
+
+	u16 *iaffids __free(kfree) = kcalloc(niaffids, sizeof(*iaffids), GFP_KERNEL);
+	if (!iaffids)
+		return -ENOMEM;
+
+	ret = of_property_read_u16_array(node, "arm,iaffids", iaffids, niaffids);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < ncpus; i++) {
+		struct device_node *cpu_node;
+		int cpu;
+
+		cpu_node = of_parse_phandle(node, "cpus", i);
+		if (WARN_ON(!cpu_node))
+			continue;
+
+		cpu = of_cpu_node_to_id(cpu_node);
+		of_node_put(cpu_node);
+		if (WARN_ON(cpu < 0))
+			continue;
+
+		if (iaffids[i] & ~iaffid_mask) {
+			pr_warn("CPU %d iaffid 0x%x exceeds IRS iaffid bits\n",
+				cpu, iaffids[i]);
+			continue;
+		}
+
+		per_cpu(cpu_iaffid, cpu).iaffid = iaffids[i];
+		per_cpu(cpu_iaffid, cpu).valid = true;
+
+		/* We also know that the CPU is connected to this IRS */
+		per_cpu(per_cpu_irs_data, cpu) = irs_data;
+	}
+
+	return ret;
+}
+
+static void irs_setup_pri_bits(u32 idr1)
+{
+	switch (FIELD_GET(GICV5_IRS_IDR1_PRIORITY_BITS, idr1)) {
+	case GICV5_IRS_IDR1_PRIORITY_BITS_1BITS:
+		gicv5_global_data.irs_pri_bits = 1;
+		break;
+	case GICV5_IRS_IDR1_PRIORITY_BITS_2BITS:
+		gicv5_global_data.irs_pri_bits = 2;
+		break;
+	case GICV5_IRS_IDR1_PRIORITY_BITS_3BITS:
+		gicv5_global_data.irs_pri_bits = 3;
+		break;
+	case GICV5_IRS_IDR1_PRIORITY_BITS_4BITS:
+		gicv5_global_data.irs_pri_bits = 4;
+		break;
+	case GICV5_IRS_IDR1_PRIORITY_BITS_5BITS:
+		gicv5_global_data.irs_pri_bits = 5;
+		break;
+	default:
+		pr_warn("Detected wrong IDR priority bits value 0x%lx\n",
+			FIELD_GET(GICV5_IRS_IDR1_PRIORITY_BITS, idr1));
+		gicv5_global_data.irs_pri_bits = 1;
+		break;
+	}
+}
+
+static int __init gicv5_irs_init(struct device_node *node)
+{
+	struct gicv5_irs_chip_data *irs_data;
+	void __iomem *irs_base;
+	u32 idr, spi_count;
+	u8 iaffid_bits;
+	int ret;
+
+	irs_data = kzalloc(sizeof(*irs_data), GFP_KERNEL);
+	if (!irs_data)
+		return -ENOMEM;
+
+	raw_spin_lock_init(&irs_data->spi_config_lock);
+
+	ret = of_property_match_string(node, "reg-names", "ns-config");
+	if (ret < 0) {
+		pr_err("%pOF: ns-config reg-name not present\n", node);
+		goto out_err;
+	}
+
+	irs_base = of_io_request_and_map(node, ret, of_node_full_name(node));
+	if (IS_ERR(irs_base)) {
+		pr_err("%pOF: unable to map GICv5 IRS registers\n", node);
+		ret = PTR_ERR(irs_base);
+		goto out_err;
+	}
+
+	gicv5_irs_init_bases(irs_data, irs_base, &node->fwnode);
+
+	idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR1);
+	iaffid_bits = FIELD_GET(GICV5_IRS_IDR1_IAFFID_BITS, idr) + 1;
+
+	ret = gicv5_irs_of_init_affinity(node, irs_data, iaffid_bits);
+	if (ret) {
+		pr_err("Failed to parse CPU IAFFIDs from the device tree!\n");
+		goto out_iomem;
+	}
+
+	idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR7);
+	irs_data->spi_min = FIELD_GET(GICV5_IRS_IDR7_SPI_BASE, idr);
+
+	idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR6);
+	irs_data->spi_range = FIELD_GET(GICV5_IRS_IDR6_SPI_IRS_RANGE, idr);
+
+	if (irs_data->spi_range) {
+		pr_info("%s detected SPI range [%u-%u]\n",
+						of_node_full_name(node),
+						irs_data->spi_min,
+						irs_data->spi_min +
+						irs_data->spi_range - 1);
+	}
+
+	/*
+	 * Do the global setting only on the first IRS.
+	 * Global properties (iaffid_bits, global spi count) are guaranteed to
+	 * be consistent across IRSes by the architecture.
+	 */
+	if (list_empty(&irs_nodes)) {
+
+		idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR1);
+		irs_setup_pri_bits(idr);
+
+		idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR5);
+
+		spi_count = FIELD_GET(GICV5_IRS_IDR5_SPI_RANGE, idr);
+		gicv5_global_data.global_spi_count = spi_count;
+
+		pr_debug("Detected %u SPIs globally\n", spi_count);
+	}
+
+	list_add_tail(&irs_data->entry, &irs_nodes);
+
+	return 0;
+
+out_iomem:
+	iounmap(irs_base);
+out_err:
+	kfree(irs_data);
+	return ret;
+}
+
+void __init gicv5_irs_remove(void)
+{
+	struct gicv5_irs_chip_data *irs_data, *tmp_data;
+
+	list_for_each_entry_safe(irs_data, tmp_data, &irs_nodes, entry) {
+		iounmap(irs_data->irs_base);
+		list_del(&irs_data->entry);
+		kfree(irs_data);
+	}
+}
+
+int __init gicv5_irs_of_probe(struct device_node *parent)
+{
+	struct device_node *np;
+	int ret;
+
+	for_each_available_child_of_node(parent, np) {
+		if (!of_device_is_compatible(np, "arm,gic-v5-irs"))
+			continue;
+
+		ret = gicv5_irs_init(np);
+		if (ret)
+			pr_err("Failed to init IRS %s\n", np->full_name);
+	}
+
+	return list_empty(&irs_nodes) ? -ENODEV : 0;
+}
diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c
index 0bb940212e20..9c55ddcfa0df 100644
--- a/drivers/irqchip/irq-gic-v5.c
+++ b/drivers/irqchip/irq-gic-v5.c
@@ -26,12 +26,7 @@ static bool gicv5_cpuif_has_gcie(void)
 	return this_cpu_has_cap(ARM64_HAS_GICV5_CPUIF);
 }
 
-struct gicv5_chip_data {
-	struct fwnode_handle	*fwnode;
-	struct irq_domain	*ppi_domain;
-};
-
-static struct gicv5_chip_data gicv5_global_data __read_mostly;
+struct gicv5_chip_data gicv5_global_data __read_mostly;
 
 static void gicv5_ppi_priority_init(void)
 {
@@ -59,6 +54,30 @@ static void gicv5_ppi_priority_init(void)
 	isb();
 }
 
+static void gicv5_hwirq_init(irq_hw_number_t hwirq, u8 priority, u8 hwirq_type)
+{
+	u64 cdpri, cdaff;
+	u16 iaffid;
+	int ret;
+
+	if (hwirq_type == GICV5_HWIRQ_TYPE_SPI) {
+		cdpri = FIELD_PREP(GICV5_GIC_CDPRI_PRIORITY_MASK, priority)	|
+			FIELD_PREP(GICV5_GIC_CDPRI_TYPE_MASK, hwirq_type)	|
+			FIELD_PREP(GICV5_GIC_CDPRI_ID_MASK, hwirq);
+		gic_insn(cdpri, CDPRI);
+
+		ret = gicv5_irs_cpu_to_iaffid(smp_processor_id(), &iaffid);
+
+		if (WARN_ON_ONCE(ret))
+			return;
+
+		cdaff = FIELD_PREP(GICV5_GIC_CDAFF_IAFFID_MASK, iaffid)		|
+			FIELD_PREP(GICV5_GIC_CDAFF_TYPE_MASK, hwirq_type)	|
+			FIELD_PREP(GICV5_GIC_CDAFF_ID_MASK, hwirq);
+		gic_insn(cdaff, CDAFF);
+	}
+}
+
 static void gicv5_ppi_irq_mask(struct irq_data *d)
 {
 	u64 hwirq_id_bit = BIT_ULL(d->hwirq % 64);
@@ -77,6 +96,32 @@ static void gicv5_ppi_irq_mask(struct irq_data *d)
 	isb();
 }
 
+static void gicv5_iri_irq_mask(struct irq_data *d, u8 hwirq_type)
+{
+	u64 cddis;
+
+	cddis = FIELD_PREP(GICV5_GIC_CDDIS_ID_MASK, d->hwirq)	|
+		FIELD_PREP(GICV5_GIC_CDDIS_TYPE_MASK, hwirq_type);
+
+	gic_insn(cddis, CDDIS);
+	/*
+	 * We must make sure that GIC CDDIS write effects are propagated
+	 * immediately to make sure the disable takes effect to guarantee
+	 * that the lazy-disabled IRQ mechanism works.
+	 * Rule R_XCLJC states that the effects of a GIC system instruction
+	 * complete in finite time.
+	 * The GSB ensures completion of the GIC instruction and prevents
+	 * loads, stores and GIC instructions from executing part of their
+	 * functionality before the GSB SYS.
+	 */
+	gsb_sys();
+}
+
+static void gicv5_spi_irq_mask(struct irq_data *d)
+{
+	gicv5_iri_irq_mask(d, GICV5_HWIRQ_TYPE_SPI);
+}
+
 static void gicv5_ppi_irq_unmask(struct irq_data *d)
 {
 	u64 hwirq_id_bit = BIT_ULL(d->hwirq % 64);
@@ -95,6 +140,25 @@ static void gicv5_ppi_irq_unmask(struct irq_data *d)
 	isb();
 }
 
+static void gicv5_iri_irq_unmask(struct irq_data *d, u8 hwirq_type)
+{
+	u64 cden;
+
+	cden = FIELD_PREP(GICV5_GIC_CDEN_ID_MASK, d->hwirq)	|
+	       FIELD_PREP(GICV5_GIC_CDEN_TYPE_MASK, hwirq_type);
+	/*
+	 * Rule R_XCLJC states that the effects of a GIC system instruction
+	 * complete in finite time and that's the only requirement when
+	 * unmasking an SPI IRQ.
+	 */
+	gic_insn(cden, CDEN);
+}
+
+static void gicv5_spi_irq_unmask(struct irq_data *d)
+{
+	gicv5_iri_irq_unmask(d, GICV5_HWIRQ_TYPE_SPI);
+}
+
 static void gicv5_hwirq_eoi(u32 hwirq_id, u8 hwirq_type)
 {
 	u64 cddi;
@@ -112,6 +176,46 @@ static void gicv5_ppi_irq_eoi(struct irq_data *d)
 	gicv5_hwirq_eoi(d->hwirq, GICV5_HWIRQ_TYPE_PPI);
 }
 
+static void gicv5_spi_irq_eoi(struct irq_data *d)
+{
+	gicv5_hwirq_eoi(d->hwirq, GICV5_HWIRQ_TYPE_SPI);
+}
+
+static int gicv5_iri_irq_set_affinity(struct irq_data *d,
+				      const struct cpumask *mask_val,
+				      bool force, u8 hwirq_type)
+{
+	int ret, cpuid;
+	u16 iaffid;
+	u64 cdaff;
+
+	if (force)
+		cpuid = cpumask_first(mask_val);
+	else
+		cpuid = cpumask_any_and(mask_val, cpu_online_mask);
+
+	ret = gicv5_irs_cpu_to_iaffid(cpuid, &iaffid);
+	if (ret)
+		return ret;
+
+	cdaff = FIELD_PREP(GICV5_GIC_CDAFF_IAFFID_MASK, iaffid)		|
+		FIELD_PREP(GICV5_GIC_CDAFF_TYPE_MASK, hwirq_type)	|
+		FIELD_PREP(GICV5_GIC_CDAFF_ID_MASK, d->hwirq);
+	gic_insn(cdaff, CDAFF);
+
+	irq_data_update_effective_affinity(d, cpumask_of(cpuid));
+
+	return IRQ_SET_MASK_OK_DONE;
+}
+
+static int gicv5_spi_irq_set_affinity(struct irq_data *d,
+				      const struct cpumask *mask_val,
+				      bool force)
+{
+	return gicv5_iri_irq_set_affinity(d, mask_val, force,
+					  GICV5_HWIRQ_TYPE_SPI);
+}
+
 enum ppi_reg {
 	PPI_PENDING,
 	PPI_ACTIVE,
@@ -192,6 +296,46 @@ static int gicv5_ppi_irq_get_irqchip_state(struct irq_data *d,
 	}
 }
 
+static int gicv5_iri_irq_get_irqchip_state(struct irq_data *d,
+					   enum irqchip_irq_state which,
+					   bool *state, u8 hwirq_type)
+{
+	u64 icsr, cdrcfg;
+
+	cdrcfg = d->hwirq | FIELD_PREP(GICV5_GIC_CDRCFG_TYPE_MASK, hwirq_type);
+
+	gic_insn(cdrcfg, CDRCFG);
+	isb();
+	icsr = read_sysreg_s(SYS_ICC_ICSR_EL1);
+
+	if (FIELD_GET(ICC_ICSR_EL1_F, icsr)) {
+		pr_err("ICSR_EL1 is invalid\n");
+		return -EINVAL;
+	}
+
+	switch (which) {
+	case IRQCHIP_STATE_PENDING:
+		*state = !!(FIELD_GET(ICC_ICSR_EL1_Pending, icsr));
+		return 0;
+
+	case IRQCHIP_STATE_ACTIVE:
+		*state = !!(FIELD_GET(ICC_ICSR_EL1_Active, icsr));
+		return 0;
+
+	default:
+		pr_debug("Unexpected irqchip_irq_state\n");
+		return -EINVAL;
+	}
+}
+
+static int gicv5_spi_irq_get_irqchip_state(struct irq_data *d,
+					   enum irqchip_irq_state which,
+					   bool *state)
+{
+	return gicv5_iri_irq_get_irqchip_state(d, which, state,
+					       GICV5_HWIRQ_TYPE_SPI);
+}
+
 static int gicv5_ppi_irq_set_irqchip_state(struct irq_data *d,
 					   enum irqchip_irq_state which,
 					   bool state)
@@ -209,6 +353,45 @@ static int gicv5_ppi_irq_set_irqchip_state(struct irq_data *d,
 	}
 }
 
+static void gicv5_iri_irq_write_pending_state(struct irq_data *d, bool state,
+					      u8 hwirq_type)
+{
+	u64 cdpend;
+
+	cdpend = FIELD_PREP(GICV5_GIC_CDPEND_TYPE_MASK, hwirq_type)	|
+		 FIELD_PREP(GICV5_GIC_CDPEND_ID_MASK, d->hwirq)		|
+		 FIELD_PREP(GICV5_GIC_CDPEND_PENDING_MASK, state);
+
+	gic_insn(cdpend, CDPEND);
+}
+
+static void gicv5_spi_irq_write_pending_state(struct irq_data *d, bool state)
+{
+	gicv5_iri_irq_write_pending_state(d, state, GICV5_HWIRQ_TYPE_SPI);
+}
+
+static int gicv5_spi_irq_set_irqchip_state(struct irq_data *d,
+					   enum irqchip_irq_state which,
+					   bool state)
+{
+	switch (which) {
+	case IRQCHIP_STATE_PENDING:
+		gicv5_spi_irq_write_pending_state(d, state);
+		break;
+	default:
+		pr_debug("Unexpected irqchip_irq_state\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int gicv5_spi_irq_retrigger(struct irq_data *data)
+{
+	return !gicv5_spi_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING,
+						true);
+}
+
 static bool gicv5_ppi_irq_is_level(irq_hw_number_t hwirq)
 {
 	u64 bit = BIT_ULL(hwirq % 64);
@@ -227,10 +410,26 @@ static const struct irq_chip gicv5_ppi_irq_chip = {
 				  IRQCHIP_MASK_ON_SUSPEND,
 };
 
-static int gicv5_irq_ppi_domain_translate(struct irq_domain *d,
-					  struct irq_fwspec *fwspec,
-					  irq_hw_number_t *hwirq,
-					  unsigned int *type)
+static const struct irq_chip gicv5_spi_irq_chip = {
+	.name			= "GICv5-SPI",
+	.irq_mask		= gicv5_spi_irq_mask,
+	.irq_unmask		= gicv5_spi_irq_unmask,
+	.irq_eoi		= gicv5_spi_irq_eoi,
+	.irq_set_type		= gicv5_spi_irq_set_type,
+	.irq_set_affinity	= gicv5_spi_irq_set_affinity,
+	.irq_retrigger		= gicv5_spi_irq_retrigger,
+	.irq_get_irqchip_state	= gicv5_spi_irq_get_irqchip_state,
+	.irq_set_irqchip_state	= gicv5_spi_irq_set_irqchip_state,
+	.flags			= IRQCHIP_SET_TYPE_MASKED |
+				  IRQCHIP_SKIP_SET_WAKE	  |
+				  IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static __always_inline int gicv5_irq_domain_translate(struct irq_domain *d,
+						      struct irq_fwspec *fwspec,
+						      irq_hw_number_t *hwirq,
+						      unsigned int *type,
+						      const u8 hwirq_type)
 {
 	if (!is_of_node(fwspec->fwnode))
 		return -EINVAL;
@@ -238,20 +437,39 @@ static int gicv5_irq_ppi_domain_translate(struct irq_domain *d,
 	if (fwspec->param_count < 3)
 		return -EINVAL;
 
-	if (fwspec->param[0] != GICV5_HWIRQ_TYPE_PPI)
+	if (fwspec->param[0] != hwirq_type)
 		return -EINVAL;
 
 	*hwirq = fwspec->param[1];
 
-	/*
-	 * Handling mode is hardcoded for PPIs, set the type using
-	 * HW reported value.
-	 */
-	*type = gicv5_ppi_irq_is_level(*hwirq) ? IRQ_TYPE_LEVEL_LOW : IRQ_TYPE_EDGE_RISING;
+	switch (hwirq_type) {
+	case GICV5_HWIRQ_TYPE_PPI:
+		/*
+		 * Handling mode is hardcoded for PPIs, set the type using
+		 * HW reported value.
+		 */
+		*type = gicv5_ppi_irq_is_level(*hwirq) ? IRQ_TYPE_LEVEL_LOW :
+							 IRQ_TYPE_EDGE_RISING;
+		break;
+	case GICV5_HWIRQ_TYPE_SPI:
+		*type = fwspec->param[2] & IRQ_TYPE_SENSE_MASK;
+		break;
+	default:
+		BUILD_BUG_ON(1);
+	}
 
 	return 0;
 }
 
+static int gicv5_irq_ppi_domain_translate(struct irq_domain *d,
+					  struct irq_fwspec *fwspec,
+					  irq_hw_number_t *hwirq,
+					  unsigned int *type)
+{
+	return gicv5_irq_domain_translate(d, fwspec, hwirq, type,
+					  GICV5_HWIRQ_TYPE_PPI);
+}
+
 static int gicv5_irq_ppi_domain_alloc(struct irq_domain *domain, unsigned int virq,
 				      unsigned int nr_irqs, void *arg)
 {
@@ -310,6 +528,63 @@ static const struct irq_domain_ops gicv5_irq_ppi_domain_ops = {
 	.select		= gicv5_irq_ppi_domain_select
 };
 
+static int gicv5_irq_spi_domain_translate(struct irq_domain *d,
+					  struct irq_fwspec *fwspec,
+					  irq_hw_number_t *hwirq,
+					  unsigned int *type)
+{
+	return gicv5_irq_domain_translate(d, fwspec, hwirq, type,
+					  GICV5_HWIRQ_TYPE_SPI);
+}
+
+static int gicv5_irq_spi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				      unsigned int nr_irqs, void *arg)
+{
+	struct gicv5_irs_chip_data *chip_data;
+	unsigned int type = IRQ_TYPE_NONE;
+	struct irq_fwspec *fwspec = arg;
+	struct irq_data *irqd;
+	irq_hw_number_t hwirq;
+	int ret;
+
+	if (WARN_ON_ONCE(nr_irqs != 1))
+		return -EINVAL;
+
+	ret = gicv5_irq_spi_domain_translate(domain, fwspec, &hwirq, &type);
+	if (ret)
+		return ret;
+
+	irqd = irq_desc_get_irq_data(irq_to_desc(virq));
+	chip_data = gicv5_irs_lookup_by_spi_id(hwirq);
+
+	irq_domain_set_info(domain, virq, hwirq, &gicv5_spi_irq_chip, chip_data,
+			    handle_fasteoi_irq, NULL, NULL);
+	irq_set_probe(virq);
+	irqd_set_single_target(irqd);
+
+	gicv5_hwirq_init(hwirq, GICV5_IRQ_PRI_MI, GICV5_HWIRQ_TYPE_SPI);
+
+	return 0;
+}
+
+static int gicv5_irq_spi_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec,
+				       enum irq_domain_bus_token bus_token)
+{
+	if (fwspec->fwnode != d->fwnode)
+		return 0;
+
+	if (fwspec->param[0] != GICV5_HWIRQ_TYPE_SPI)
+		return 0;
+
+	return (d == gicv5_global_data.spi_domain);
+}
+
+static const struct irq_domain_ops gicv5_irq_spi_domain_ops = {
+	.translate	= gicv5_irq_spi_domain_translate,
+	.alloc		= gicv5_irq_spi_domain_alloc,
+	.free		= gicv5_irq_domain_free,
+	.select		= gicv5_irq_spi_domain_select
+};
 static void handle_irq_per_domain(u32 hwirq)
 {
 	u8 hwirq_type = FIELD_GET(GICV5_HWIRQ_TYPE, hwirq);
@@ -320,6 +595,9 @@ static void handle_irq_per_domain(u32 hwirq)
 	case GICV5_HWIRQ_TYPE_PPI:
 		domain = gicv5_global_data.ppi_domain;
 		break;
+	case GICV5_HWIRQ_TYPE_SPI:
+		domain = gicv5_global_data.spi_domain;
+		break;
 	default:
 		pr_err_once("Unknown IRQ type, bail out\n");
 		return;
@@ -392,19 +670,23 @@ static int gicv5_starting_cpu(unsigned int cpu)
 
 	gicv5_cpu_enable_interrupts();
 
-	return 0;
+	return gicv5_irs_register_cpu(cpu);
 }
 
 static void __init gicv5_free_domains(void)
 {
 	if (gicv5_global_data.ppi_domain)
 		irq_domain_remove(gicv5_global_data.ppi_domain);
+	if (gicv5_global_data.spi_domain)
+		irq_domain_remove(gicv5_global_data.spi_domain);
 
 	gicv5_global_data.ppi_domain = NULL;
+	gicv5_global_data.spi_domain = NULL;
 }
 
 static int __init gicv5_init_domains(struct fwnode_handle *handle)
 {
+	u32 spi_count = gicv5_global_data.global_spi_count;
 	struct irq_domain *d;
 
 	d = irq_domain_create_linear(handle, PPI_NR, &gicv5_irq_ppi_domain_ops, NULL);
@@ -413,6 +695,20 @@ static int __init gicv5_init_domains(struct fwnode_handle *handle)
 
 	irq_domain_update_bus_token(d, DOMAIN_BUS_WIRED);
 	gicv5_global_data.ppi_domain = d;
+
+	if (spi_count) {
+		d = irq_domain_create_linear(handle, spi_count,
+					     &gicv5_irq_spi_domain_ops, NULL);
+
+		if (!d) {
+			gicv5_free_domains();
+			return -ENOMEM;
+		}
+
+		gicv5_global_data.spi_domain = d;
+		irq_domain_update_bus_token(d, DOMAIN_BUS_WIRED);
+	}
+
 	gicv5_global_data.fwnode = handle;
 
 	return 0;
@@ -424,26 +720,33 @@ static void gicv5_set_cpuif_pribits(void)
 
 	switch (FIELD_GET(ICC_IDR0_EL1_PRI_BITS, icc_idr0)) {
 	case ICC_IDR0_EL1_PRI_BITS_4BITS:
-		pri_bits = 4;
+		gicv5_global_data.cpuif_pri_bits = 4;
 		break;
 	case ICC_IDR0_EL1_PRI_BITS_5BITS:
-		pri_bits = 5;
+		gicv5_global_data.cpuif_pri_bits = 5;
 		break;
 	default:
 		pr_err("Unexpected ICC_IDR0_EL1_PRI_BITS value, default to 4");
-		pri_bits = 4;
+		gicv5_global_data.cpuif_pri_bits = 4;
 		break;
 	}
 }
 
 static int __init gicv5_of_init(struct device_node *node, struct device_node *parent)
 {
-	int ret = gicv5_init_domains(of_fwnode_handle(node));
+	int ret = gicv5_irs_of_probe(node);
 	if (ret)
 		return ret;
 
+	ret = gicv5_init_domains(of_fwnode_handle(node));
+	if (ret)
+		goto out_irs;
+
 	gicv5_set_cpuif_pribits();
 
+	pri_bits = min_not_zero(gicv5_global_data.cpuif_pri_bits,
+				gicv5_global_data.irs_pri_bits);
+
 	ret = gicv5_starting_cpu(smp_processor_id());
 	if (ret)
 		goto out_dom;
@@ -458,6 +761,8 @@ out_int:
 	gicv5_cpu_disable_interrupts();
 out_dom:
 	gicv5_free_domains();
+out_irs:
+	gicv5_irs_remove();
 
 	return ret;
 }
diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h
index b08ec0308a9b..1064a69ab33f 100644
--- a/include/linux/irqchip/arm-gic-v5.h
+++ b/include/linux/irqchip/arm-gic-v5.h
@@ -5,6 +5,8 @@
 #ifndef __LINUX_IRQCHIP_ARM_GIC_V5_H
 #define __LINUX_IRQCHIP_ARM_GIC_V5_H
 
+#include <linux/iopoll.h>
+
 #include <asm/sysreg.h>
 
 /*
@@ -15,5 +17,143 @@
 #define GICV5_HWIRQ_INTID		GENMASK_ULL(31, 0)
 
 #define GICV5_HWIRQ_TYPE_PPI		UL(0x1)
+#define GICV5_HWIRQ_TYPE_SPI		UL(0x3)
+
+/*
+ * Tables attributes
+ */
+#define GICV5_NO_READ_ALLOC		0b0
+#define GICV5_READ_ALLOC		0b1
+#define GICV5_NO_WRITE_ALLOC		0b0
+#define GICV5_WRITE_ALLOC		0b1
+
+#define GICV5_NON_CACHE			0b00
+#define GICV5_WB_CACHE			0b01
+#define GICV5_WT_CACHE			0b10
+
+#define GICV5_NON_SHARE			0b00
+#define GICV5_OUTER_SHARE		0b10
+#define GICV5_INNER_SHARE		0b11
+
+/*
+ * IRS registers
+ */
+#define GICV5_IRS_IDR1			0x0004
+#define GICV5_IRS_IDR2			0x0008
+#define GICV5_IRS_IDR5			0x0014
+#define GICV5_IRS_IDR6			0x0018
+#define GICV5_IRS_IDR7			0x001c
+#define GICV5_IRS_CR0			0x0080
+#define GICV5_IRS_CR1			0x0084
+#define GICV5_IRS_SPI_SELR		0x0108
+#define GICV5_IRS_SPI_CFGR		0x0114
+#define GICV5_IRS_SPI_STATUSR		0x0118
+#define GICV5_IRS_PE_SELR		0x0140
+#define GICV5_IRS_PE_STATUSR		0x0144
+#define GICV5_IRS_PE_CR0		0x0148
+
+#define GICV5_IRS_IDR1_PRIORITY_BITS	GENMASK(22, 20)
+#define GICV5_IRS_IDR1_IAFFID_BITS	GENMASK(19, 16)
+
+#define GICV5_IRS_IDR1_PRIORITY_BITS_1BITS	0b000
+#define GICV5_IRS_IDR1_PRIORITY_BITS_2BITS	0b001
+#define GICV5_IRS_IDR1_PRIORITY_BITS_3BITS	0b010
+#define GICV5_IRS_IDR1_PRIORITY_BITS_4BITS	0b011
+#define GICV5_IRS_IDR1_PRIORITY_BITS_5BITS	0b100
+
+#define GICV5_IRS_IDR2_ISTMD_SZ		GENMASK(19, 15)
+#define GICV5_IRS_IDR2_ISTMD		BIT(14)
+#define GICV5_IRS_IDR2_IST_L2SZ		GENMASK(13, 11)
+#define GICV5_IRS_IDR2_IST_LEVELS	BIT(10)
+#define GICV5_IRS_IDR2_MIN_LPI_ID_BITS	GENMASK(9, 6)
+#define GICV5_IRS_IDR2_LPI		BIT(5)
+#define GICV5_IRS_IDR2_ID_BITS		GENMASK(4, 0)
+
+#define GICV5_IRS_IDR5_SPI_RANGE	GENMASK(24, 0)
+#define GICV5_IRS_IDR6_SPI_IRS_RANGE	GENMASK(24, 0)
+#define GICV5_IRS_IDR7_SPI_BASE		GENMASK(23, 0)
+#define GICV5_IRS_CR0_IDLE		BIT(1)
+#define GICV5_IRS_CR0_IRSEN		BIT(0)
+
+#define GICV5_IRS_CR1_VPED_WA		BIT(15)
+#define GICV5_IRS_CR1_VPED_RA		BIT(14)
+#define GICV5_IRS_CR1_VMD_WA		BIT(13)
+#define GICV5_IRS_CR1_VMD_RA		BIT(12)
+#define GICV5_IRS_CR1_VPET_WA		BIT(11)
+#define GICV5_IRS_CR1_VPET_RA		BIT(10)
+#define GICV5_IRS_CR1_VMT_WA		BIT(9)
+#define GICV5_IRS_CR1_VMT_RA		BIT(8)
+#define GICV5_IRS_CR1_IST_WA		BIT(7)
+#define GICV5_IRS_CR1_IST_RA		BIT(6)
+#define GICV5_IRS_CR1_IC		GENMASK(5, 4)
+#define GICV5_IRS_CR1_OC		GENMASK(3, 2)
+#define GICV5_IRS_CR1_SH		GENMASK(1, 0)
+
+#define GICV5_IRS_SPI_STATUSR_V		BIT(1)
+#define GICV5_IRS_SPI_STATUSR_IDLE	BIT(0)
+
+#define GICV5_IRS_SPI_SELR_ID		GENMASK(23, 0)
+
+#define GICV5_IRS_SPI_CFGR_TM		BIT(0)
+
+#define GICV5_IRS_PE_SELR_IAFFID	GENMASK(15, 0)
+
+#define GICV5_IRS_PE_STATUSR_V		BIT(1)
+#define GICV5_IRS_PE_STATUSR_IDLE	BIT(0)
+
+#define GICV5_IRS_PE_CR0_DPS		BIT(0)
+
+/*
+ * Global Data structures and functions
+ */
+struct gicv5_chip_data {
+	struct fwnode_handle	*fwnode;
+	struct irq_domain	*ppi_domain;
+	struct irq_domain	*spi_domain;
+	u32			global_spi_count;
+	u8			cpuif_pri_bits;
+	u8			irs_pri_bits;
+};
+
+extern struct gicv5_chip_data gicv5_global_data __read_mostly;
+
+struct gicv5_irs_chip_data {
+	struct list_head	entry;
+	struct fwnode_handle	*fwnode;
+	void __iomem		*irs_base;
+	u32			flags;
+	u32			spi_min;
+	u32			spi_range;
+	raw_spinlock_t		spi_config_lock;
+};
+
+static inline int gicv5_wait_for_op_s_atomic(void __iomem *addr, u32 offset,
+					     const char *reg_s, u32 mask,
+					     u32 *val)
+{
+	void __iomem *reg = addr + offset;
+	u32 tmp;
+	int ret;
+
+	ret = readl_poll_timeout_atomic(reg, tmp, tmp & mask, 1, 10 * USEC_PER_MSEC);
+	if (unlikely(ret == -ETIMEDOUT)) {
+		pr_err_ratelimited("%s timeout...\n", reg_s);
+		return ret;
+	}
+
+	if (val)
+		*val = tmp;
+
+	return 0;
+}
+
+#define gicv5_wait_for_op_atomic(base, reg, mask, val) \
+	gicv5_wait_for_op_s_atomic(base, reg, #reg, mask, val)
 
+int gicv5_irs_of_probe(struct device_node *parent);
+void gicv5_irs_remove(void);
+int gicv5_irs_register_cpu(int cpuid);
+int gicv5_irs_cpu_to_iaffid(int cpu_id, u16 *iaffid);
+struct gicv5_irs_chip_data *gicv5_irs_lookup_by_spi_id(u32 spi_id);
+int gicv5_spi_irq_set_type(struct irq_data *d, unsigned int type);
 #endif
-- 
cgit v1.2.3


From 0f0101325876859eb463792d4df3fd22b6539d29 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 3 Jul 2025 12:25:12 +0200
Subject: irqchip/gic-v5: Add GICv5 LPI/IPI support

An IRS supports Logical Peripheral Interrupts (LPIs) and implement
Linux IPIs on top of it.

LPIs are used for interrupt signals that are translated by a
GICv5 ITS (Interrupt Translation Service) but also for software
generated IRQs - namely interrupts that are not driven by a HW
signal, ie IPIs.

LPIs rely on memory storage for interrupt routing and state.

LPIs state and routing information is kept in the Interrupt
State Table (IST).

IRSes provide support for 1- or 2-level IST tables configured
to support a maximum number of interrupts that depend on the
OS configuration and the HW capabilities.

On systems that provide 2-level IST support, always allow
the maximum number of LPIs; On systems with only 1-level
support, limit the number of LPIs to 2^12 to prevent
wasting memory (presumably a system that supports a 1-level
only IST is not expecting a large number of interrupts).

On a 2-level IST system, L2 entries are allocated on
demand.

The IST table memory is allocated using the kmalloc() interface;
the allocation required may be smaller than a page and must be
made up of contiguous physical pages if larger than a page.

On systems where the IRS is not cache-coherent with the CPUs,
cache mainteinance operations are executed to clean and
invalidate the allocated memory to the point of coherency
making it visible to the IRS components.

On GICv5 systems, IPIs are implemented using LPIs.

Add an LPI IRQ domain and implement an IPI-specific IRQ domain created
as a child/subdomain of the LPI domain to allocate the required number
of LPIs needed to implement the IPIs.

IPIs are backed by LPIs, add LPIs allocation/de-allocation
functions.

The LPI INTID namespace is managed using an IDA to alloc/free LPI INTIDs.

Associate an IPI irqchip with IPI IRQ descriptors to provide
core code with the irqchip.ipi_send_single() method required
to raise an IPI.

Co-developed-by: Sascha Bischoff <sascha.bischoff@arm.com>
Signed-off-by: Sascha Bischoff <sascha.bischoff@arm.com>
Co-developed-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Will Deacon <will@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Marc Zyngier <maz@kernel.org>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>
Link: https://lore.kernel.org/r/20250703-gicv5-host-v7-22-12e71f1b3528@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 arch/arm64/include/asm/smp.h       |  17 ++
 arch/arm64/include/asm/sysreg.h    |   6 +
 arch/arm64/kernel/smp.c            |  17 --
 drivers/irqchip/irq-gic-v5-irs.c   | 364 +++++++++++++++++++++++++++++++++++++
 drivers/irqchip/irq-gic-v5.c       | 299 +++++++++++++++++++++++++++++-
 include/linux/irqchip/arm-gic-v5.h |  63 ++++++-
 6 files changed, 746 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/smp.h b/arch/arm64/include/asm/smp.h
index d6fd6efb66a6..d48ef6d5abcc 100644
--- a/arch/arm64/include/asm/smp.h
+++ b/arch/arm64/include/asm/smp.h
@@ -50,6 +50,23 @@ struct seq_file;
  */
 extern void smp_init_cpus(void);
 
+enum ipi_msg_type {
+	IPI_RESCHEDULE,
+	IPI_CALL_FUNC,
+	IPI_CPU_STOP,
+	IPI_CPU_STOP_NMI,
+	IPI_TIMER,
+	IPI_IRQ_WORK,
+	NR_IPI,
+	/*
+	 * Any enum >= NR_IPI and < MAX_IPI is special and not tracable
+	 * with trace_ipi_*
+	 */
+	IPI_CPU_BACKTRACE = NR_IPI,
+	IPI_KGDB_ROUNDUP,
+	MAX_IPI
+};
+
 /*
  * Register IPI interrupts with the arch SMP code
  */
diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
index efd2e7a1fbe2..948007cd3684 100644
--- a/arch/arm64/include/asm/sysreg.h
+++ b/arch/arm64/include/asm/sysreg.h
@@ -1088,6 +1088,7 @@
 #define GICV5_OP_GIC_CDAFF		sys_insn(1, 0, 12, 1, 3)
 #define GICV5_OP_GIC_CDDI		sys_insn(1, 0, 12, 2, 0)
 #define GICV5_OP_GIC_CDDIS		sys_insn(1, 0, 12, 1, 0)
+#define GICV5_OP_GIC_CDHM		sys_insn(1, 0, 12, 2, 1)
 #define GICV5_OP_GIC_CDEN		sys_insn(1, 0, 12, 1, 1)
 #define GICV5_OP_GIC_CDEOI		sys_insn(1, 0, 12, 1, 7)
 #define GICV5_OP_GIC_CDPEND		sys_insn(1, 0, 12, 1, 4)
@@ -1115,6 +1116,11 @@
 #define GICV5_GIC_CDEN_TYPE_MASK	GENMASK_ULL(31, 29)
 #define GICV5_GIC_CDEN_ID_MASK		GENMASK_ULL(23, 0)
 
+/* Definitions for GIC CDHM */
+#define GICV5_GIC_CDHM_HM_MASK		BIT_ULL(32)
+#define GICV5_GIC_CDHM_TYPE_MASK	GENMASK_ULL(31, 29)
+#define GICV5_GIC_CDHM_ID_MASK		GENMASK_ULL(23, 0)
+
 /* Definitions for GIC CDPEND */
 #define GICV5_GIC_CDPEND_PENDING_MASK	BIT_ULL(32)
 #define GICV5_GIC_CDPEND_TYPE_MASK	GENMASK_ULL(31, 29)
diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
index 2c501e917d38..4797e2c70014 100644
--- a/arch/arm64/kernel/smp.c
+++ b/arch/arm64/kernel/smp.c
@@ -64,23 +64,6 @@ struct secondary_data secondary_data;
 /* Number of CPUs which aren't online, but looping in kernel text. */
 static int cpus_stuck_in_kernel;
 
-enum ipi_msg_type {
-	IPI_RESCHEDULE,
-	IPI_CALL_FUNC,
-	IPI_CPU_STOP,
-	IPI_CPU_STOP_NMI,
-	IPI_TIMER,
-	IPI_IRQ_WORK,
-	NR_IPI,
-	/*
-	 * Any enum >= NR_IPI and < MAX_IPI is special and not tracable
-	 * with trace_ipi_*
-	 */
-	IPI_CPU_BACKTRACE = NR_IPI,
-	IPI_KGDB_ROUNDUP,
-	MAX_IPI
-};
-
 static int ipi_irq_base __ro_after_init;
 static int nr_ipi __ro_after_init = NR_IPI;
 
diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c
index fba8efceb26e..f00a4a6fece7 100644
--- a/drivers/irqchip/irq-gic-v5-irs.c
+++ b/drivers/irqchip/irq-gic-v5-irs.c
@@ -5,12 +5,20 @@
 
 #define pr_fmt(fmt)	"GICv5 IRS: " fmt
 
+#include <linux/log2.h>
 #include <linux/of.h>
 #include <linux/of_address.h>
 
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic-v5.h>
 
+/*
+ * Hardcoded ID_BITS limit for systems supporting only a 1-level IST
+ * table. Systems supporting only a 1-level IST table aren't expected
+ * to require more than 2^12 LPIs. Tweak as required.
+ */
+#define LPI_ID_BITS_LINEAR		12
+
 #define IRS_FLAGS_NON_COHERENT		BIT(0)
 
 static DEFINE_PER_CPU_READ_MOSTLY(struct gicv5_irs_chip_data *, per_cpu_irs_data);
@@ -28,6 +36,331 @@ static void irs_writel_relaxed(struct gicv5_irs_chip_data *irs_data,
 	writel_relaxed(val, irs_data->irs_base + reg_offset);
 }
 
+static u64 irs_readq_relaxed(struct gicv5_irs_chip_data *irs_data,
+			     const u32 reg_offset)
+{
+	return readq_relaxed(irs_data->irs_base + reg_offset);
+}
+
+static void irs_writeq_relaxed(struct gicv5_irs_chip_data *irs_data,
+			       const u64 val, const u32 reg_offset)
+{
+	writeq_relaxed(val, irs_data->irs_base + reg_offset);
+}
+
+/*
+ * The polling wait (in gicv5_wait_for_op_s_atomic()) on a GIC register
+ * provides the memory barriers (through MMIO accessors)
+ * required to synchronize CPU and GIC access to IST memory.
+ */
+static int gicv5_irs_ist_synchronise(struct gicv5_irs_chip_data *irs_data)
+{
+	return gicv5_wait_for_op_atomic(irs_data->irs_base, GICV5_IRS_IST_STATUSR,
+					GICV5_IRS_IST_STATUSR_IDLE, NULL);
+}
+
+static int __init gicv5_irs_init_ist_linear(struct gicv5_irs_chip_data *irs_data,
+					    unsigned int lpi_id_bits,
+					    unsigned int istsz)
+{
+	size_t l2istsz;
+	u32 n, cfgr;
+	void *ist;
+	u64 baser;
+	int ret;
+
+	/* Taken from GICv5 specifications 10.2.1.13 IRS_IST_BASER */
+	n = max(5, lpi_id_bits + 1 + istsz);
+
+	l2istsz = BIT(n + 1);
+	/*
+	 * Check memory requirements. For a linear IST we cap the
+	 * number of ID bits to a value that should never exceed
+	 * kmalloc interface memory allocation limits, so this
+	 * check is really belt and braces.
+	 */
+	if (l2istsz > KMALLOC_MAX_SIZE) {
+		u8 lpi_id_cap = ilog2(KMALLOC_MAX_SIZE) - 2 + istsz;
+
+		pr_warn("Limiting LPI ID bits from %u to %u\n",
+			lpi_id_bits, lpi_id_cap);
+		lpi_id_bits = lpi_id_cap;
+		l2istsz = KMALLOC_MAX_SIZE;
+	}
+
+	ist = kzalloc(l2istsz, GFP_KERNEL);
+	if (!ist)
+		return -ENOMEM;
+
+	if (irs_data->flags & IRS_FLAGS_NON_COHERENT)
+		dcache_clean_inval_poc((unsigned long)ist,
+				       (unsigned long)ist + l2istsz);
+	else
+		dsb(ishst);
+
+	cfgr = FIELD_PREP(GICV5_IRS_IST_CFGR_STRUCTURE,
+			  GICV5_IRS_IST_CFGR_STRUCTURE_LINEAR)	|
+	       FIELD_PREP(GICV5_IRS_IST_CFGR_ISTSZ, istsz)	|
+	       FIELD_PREP(GICV5_IRS_IST_CFGR_L2SZ,
+			  GICV5_IRS_IST_CFGR_L2SZ_4K)		|
+	       FIELD_PREP(GICV5_IRS_IST_CFGR_LPI_ID_BITS, lpi_id_bits);
+	irs_writel_relaxed(irs_data, cfgr, GICV5_IRS_IST_CFGR);
+
+	gicv5_global_data.ist.l2 = false;
+
+	baser = (virt_to_phys(ist) & GICV5_IRS_IST_BASER_ADDR_MASK) |
+		FIELD_PREP(GICV5_IRS_IST_BASER_VALID, 0x1);
+	irs_writeq_relaxed(irs_data, baser, GICV5_IRS_IST_BASER);
+
+	ret = gicv5_irs_ist_synchronise(irs_data);
+	if (ret) {
+		kfree(ist);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int __init gicv5_irs_init_ist_two_level(struct gicv5_irs_chip_data *irs_data,
+					       unsigned int lpi_id_bits,
+					       unsigned int istsz,
+					       unsigned int l2sz)
+{
+	__le64 *l1ist;
+	u32 cfgr, n;
+	size_t l1sz;
+	u64 baser;
+	int ret;
+
+	/* Taken from GICv5 specifications 10.2.1.13 IRS_IST_BASER */
+	n = max(5, lpi_id_bits - ((10 - istsz) + (2 * l2sz)) + 2);
+
+	l1sz = BIT(n + 1);
+
+	l1ist = kzalloc(l1sz, GFP_KERNEL);
+	if (!l1ist)
+		return -ENOMEM;
+
+	if (irs_data->flags & IRS_FLAGS_NON_COHERENT)
+		dcache_clean_inval_poc((unsigned long)l1ist,
+				       (unsigned long)l1ist + l1sz);
+	else
+		dsb(ishst);
+
+	cfgr = FIELD_PREP(GICV5_IRS_IST_CFGR_STRUCTURE,
+			  GICV5_IRS_IST_CFGR_STRUCTURE_TWO_LEVEL)	|
+	       FIELD_PREP(GICV5_IRS_IST_CFGR_ISTSZ, istsz)		|
+	       FIELD_PREP(GICV5_IRS_IST_CFGR_L2SZ, l2sz)		|
+	       FIELD_PREP(GICV5_IRS_IST_CFGR_LPI_ID_BITS, lpi_id_bits);
+	irs_writel_relaxed(irs_data, cfgr, GICV5_IRS_IST_CFGR);
+
+	/*
+	 * The L2SZ determine bits required at L2 level. Number of bytes
+	 * required by metadata is reported through istsz - the number of bits
+	 * covered by L2 entries scales accordingly.
+	 */
+	gicv5_global_data.ist.l2_size = BIT(11 + (2 * l2sz) + 1);
+	gicv5_global_data.ist.l2_bits = (10 - istsz) + (2 * l2sz);
+	gicv5_global_data.ist.l1ist_addr = l1ist;
+	gicv5_global_data.ist.l2 = true;
+
+	baser = (virt_to_phys(l1ist) & GICV5_IRS_IST_BASER_ADDR_MASK) |
+		FIELD_PREP(GICV5_IRS_IST_BASER_VALID, 0x1);
+	irs_writeq_relaxed(irs_data, baser, GICV5_IRS_IST_BASER);
+
+	ret = gicv5_irs_ist_synchronise(irs_data);
+	if (ret) {
+		kfree(l1ist);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Alloc L2 IST entries on demand.
+ *
+ * Locking/serialization is guaranteed by irqdomain core code by
+ * taking the hierarchical domain struct irq_domain.root->mutex.
+ */
+int gicv5_irs_iste_alloc(const u32 lpi)
+{
+	struct gicv5_irs_chip_data *irs_data;
+	unsigned int index;
+	u32 l2istr, l2bits;
+	__le64 *l1ist;
+	size_t l2size;
+	void *l2ist;
+	int ret;
+
+	if (!gicv5_global_data.ist.l2)
+		return 0;
+
+	irs_data = per_cpu(per_cpu_irs_data, smp_processor_id());
+	if (!irs_data)
+		return -ENOENT;
+
+	l2size = gicv5_global_data.ist.l2_size;
+	l2bits = gicv5_global_data.ist.l2_bits;
+	l1ist = gicv5_global_data.ist.l1ist_addr;
+	index = lpi >> l2bits;
+
+	if (FIELD_GET(GICV5_ISTL1E_VALID, le64_to_cpu(l1ist[index])))
+		return 0;
+
+	l2ist = kzalloc(l2size, GFP_KERNEL);
+	if (!l2ist)
+		return -ENOMEM;
+
+	l1ist[index] = cpu_to_le64(virt_to_phys(l2ist) & GICV5_ISTL1E_L2_ADDR_MASK);
+
+	if (irs_data->flags & IRS_FLAGS_NON_COHERENT) {
+		dcache_clean_inval_poc((unsigned long)l2ist,
+				       (unsigned long)l2ist + l2size);
+		dcache_clean_poc((unsigned long)(l1ist + index),
+				 (unsigned long)(l1ist + index) + sizeof(*l1ist));
+	} else {
+		dsb(ishst);
+	}
+
+	l2istr = FIELD_PREP(GICV5_IRS_MAP_L2_ISTR_ID, lpi);
+	irs_writel_relaxed(irs_data, l2istr, GICV5_IRS_MAP_L2_ISTR);
+
+	ret = gicv5_irs_ist_synchronise(irs_data);
+	if (ret) {
+		l1ist[index] = 0;
+		kfree(l2ist);
+		return ret;
+	}
+
+	/*
+	 * Make sure we invalidate the cache line pulled before the IRS
+	 * had a chance to update the L1 entry and mark it valid.
+	 */
+	if (irs_data->flags & IRS_FLAGS_NON_COHERENT) {
+		/*
+		 * gicv5_irs_ist_synchronise() includes memory
+		 * barriers (MMIO accessors) required to guarantee that the
+		 * following dcache invalidation is not executed before the
+		 * IST mapping operation has completed.
+		 */
+		dcache_inval_poc((unsigned long)(l1ist + index),
+				 (unsigned long)(l1ist + index) + sizeof(*l1ist));
+	}
+
+	return 0;
+}
+
+/*
+ * Try to match the L2 IST size to the pagesize, and if this is not possible
+ * pick the smallest supported L2 size in order to minimise the requirement for
+ * physically contiguous blocks of memory as page-sized allocations are
+ * guaranteed to be physically contiguous, and are by definition the easiest to
+ * find.
+ *
+ * Fall back to the smallest supported size (in the event that the pagesize
+ * itself is not supported) again serves to make it easier to find physically
+ * contiguous blocks of memory.
+ */
+static unsigned int gicv5_irs_l2_sz(u32 idr2)
+{
+	switch (PAGE_SIZE) {
+	case SZ_64K:
+		if (GICV5_IRS_IST_L2SZ_SUPPORT_64KB(idr2))
+			return GICV5_IRS_IST_CFGR_L2SZ_64K;
+		fallthrough;
+	case SZ_4K:
+		if (GICV5_IRS_IST_L2SZ_SUPPORT_4KB(idr2))
+			return GICV5_IRS_IST_CFGR_L2SZ_4K;
+		fallthrough;
+	case SZ_16K:
+		if (GICV5_IRS_IST_L2SZ_SUPPORT_16KB(idr2))
+			return GICV5_IRS_IST_CFGR_L2SZ_16K;
+		break;
+	}
+
+	if (GICV5_IRS_IST_L2SZ_SUPPORT_4KB(idr2))
+		return GICV5_IRS_IST_CFGR_L2SZ_4K;
+
+	return GICV5_IRS_IST_CFGR_L2SZ_64K;
+}
+
+static int __init gicv5_irs_init_ist(struct gicv5_irs_chip_data *irs_data)
+{
+	u32 lpi_id_bits, idr2_id_bits, idr2_min_lpi_id_bits, l2_iste_sz, l2sz;
+	u32 l2_iste_sz_split, idr2;
+	bool two_levels, istmd;
+	u64 baser;
+	int ret;
+
+	baser = irs_readq_relaxed(irs_data, GICV5_IRS_IST_BASER);
+	if (FIELD_GET(GICV5_IRS_IST_BASER_VALID, baser)) {
+		pr_err("IST is marked as valid already; cannot allocate\n");
+		return -EPERM;
+	}
+
+	idr2 = irs_readl_relaxed(irs_data, GICV5_IRS_IDR2);
+	two_levels = !!FIELD_GET(GICV5_IRS_IDR2_IST_LEVELS, idr2);
+
+	idr2_id_bits = FIELD_GET(GICV5_IRS_IDR2_ID_BITS, idr2);
+	idr2_min_lpi_id_bits = FIELD_GET(GICV5_IRS_IDR2_MIN_LPI_ID_BITS, idr2);
+
+	/*
+	 * For two level tables we are always supporting the maximum allowed
+	 * number of IDs.
+	 *
+	 * For 1-level tables, we should support a number of bits that
+	 * is >= min_lpi_id_bits but cap it to LPI_ID_BITS_LINEAR lest
+	 * the level 1-table gets too large and its memory allocation
+	 * may fail.
+	 */
+	if (two_levels) {
+		lpi_id_bits = idr2_id_bits;
+	} else {
+		lpi_id_bits = max(LPI_ID_BITS_LINEAR, idr2_min_lpi_id_bits);
+		lpi_id_bits = min(lpi_id_bits, idr2_id_bits);
+	}
+
+	/*
+	 * Cap the ID bits according to the CPUIF supported ID bits
+	 */
+	lpi_id_bits = min(lpi_id_bits, gicv5_global_data.cpuif_id_bits);
+
+	if (two_levels)
+		l2sz = gicv5_irs_l2_sz(idr2);
+
+	istmd = !!FIELD_GET(GICV5_IRS_IDR2_ISTMD, idr2);
+
+	l2_iste_sz = GICV5_IRS_IST_CFGR_ISTSZ_4;
+
+	if (istmd) {
+		l2_iste_sz_split = FIELD_GET(GICV5_IRS_IDR2_ISTMD_SZ, idr2);
+
+		if (lpi_id_bits < l2_iste_sz_split)
+			l2_iste_sz = GICV5_IRS_IST_CFGR_ISTSZ_8;
+		else
+			l2_iste_sz = GICV5_IRS_IST_CFGR_ISTSZ_16;
+	}
+
+	/*
+	 * Follow GICv5 specification recommendation to opt in for two
+	 * level tables (ref: 10.2.1.14 IRS_IST_CFGR).
+	 */
+	if (two_levels && (lpi_id_bits > ((10 - l2_iste_sz) + (2 * l2sz)))) {
+		ret = gicv5_irs_init_ist_two_level(irs_data, lpi_id_bits,
+						   l2_iste_sz, l2sz);
+	} else {
+		ret = gicv5_irs_init_ist_linear(irs_data, lpi_id_bits,
+						l2_iste_sz);
+	}
+	if (ret)
+		return ret;
+
+	gicv5_init_lpis(BIT(lpi_id_bits));
+
+	return 0;
+}
+
 struct iaffid_entry {
 	u16	iaffid;
 	bool	valid;
@@ -362,6 +695,13 @@ static int __init gicv5_irs_init(struct device_node *node)
 		goto out_iomem;
 	}
 
+	idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR2);
+	if (WARN(!FIELD_GET(GICV5_IRS_IDR2_LPI, idr),
+		 "LPI support not available - no IPIs, can't proceed\n")) {
+		ret = -ENODEV;
+		goto out_iomem;
+	}
+
 	idr = irs_readl_relaxed(irs_data, GICV5_IRS_IDR7);
 	irs_data->spi_min = FIELD_GET(GICV5_IRS_IDR7_SPI_BASE, idr);
 
@@ -391,6 +731,8 @@ static int __init gicv5_irs_init(struct device_node *node)
 		spi_count = FIELD_GET(GICV5_IRS_IDR5_SPI_RANGE, idr);
 		gicv5_global_data.global_spi_count = spi_count;
 
+		gicv5_init_lpi_domain();
+
 		pr_debug("Detected %u SPIs globally\n", spi_count);
 	}
 
@@ -409,6 +751,9 @@ void __init gicv5_irs_remove(void)
 {
 	struct gicv5_irs_chip_data *irs_data, *tmp_data;
 
+	gicv5_free_lpi_domain();
+	gicv5_deinit_lpis();
+
 	list_for_each_entry_safe(irs_data, tmp_data, &irs_nodes, entry) {
 		iounmap(irs_data->irs_base);
 		list_del(&irs_data->entry);
@@ -416,6 +761,25 @@ void __init gicv5_irs_remove(void)
 	}
 }
 
+int __init gicv5_irs_enable(void)
+{
+	struct gicv5_irs_chip_data *irs_data;
+	int ret;
+
+	irs_data = list_first_entry_or_null(&irs_nodes,
+					    struct gicv5_irs_chip_data, entry);
+	if (!irs_data)
+		return -ENODEV;
+
+	ret = gicv5_irs_init_ist(irs_data);
+	if (ret) {
+		pr_err("Failed to init IST\n");
+		return ret;
+	}
+
+	return 0;
+}
+
 int __init gicv5_irs_of_probe(struct device_node *parent)
 {
 	struct device_node *np;
diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c
index 9c55ddcfa0df..84ed13c4f2b1 100644
--- a/drivers/irqchip/irq-gic-v5.c
+++ b/drivers/irqchip/irq-gic-v5.c
@@ -5,7 +5,9 @@
 
 #define pr_fmt(fmt)	"GICv5: " fmt
 
+#include <linux/idr.h>
 #include <linux/irqdomain.h>
+#include <linux/slab.h>
 #include <linux/wordpart.h>
 
 #include <linux/irqchip.h>
@@ -28,6 +30,42 @@ static bool gicv5_cpuif_has_gcie(void)
 
 struct gicv5_chip_data gicv5_global_data __read_mostly;
 
+static DEFINE_IDA(lpi_ida);
+static u32 num_lpis __ro_after_init;
+
+void __init gicv5_init_lpis(u32 lpis)
+{
+	num_lpis = lpis;
+}
+
+void __init gicv5_deinit_lpis(void)
+{
+	num_lpis = 0;
+}
+
+static int alloc_lpi(void)
+{
+	if (!num_lpis)
+		return -ENOSPC;
+
+	return ida_alloc_max(&lpi_ida, num_lpis - 1, GFP_KERNEL);
+}
+
+static void release_lpi(u32 lpi)
+{
+	ida_free(&lpi_ida, lpi);
+}
+
+int gicv5_alloc_lpi(void)
+{
+	return alloc_lpi();
+}
+
+void gicv5_free_lpi(u32 lpi)
+{
+	release_lpi(lpi);
+}
+
 static void gicv5_ppi_priority_init(void)
 {
 	write_sysreg_s(REPEAT_BYTE(GICV5_IRQ_PRI_MI), SYS_ICC_PPI_PRIORITYR0_EL1);
@@ -60,7 +98,7 @@ static void gicv5_hwirq_init(irq_hw_number_t hwirq, u8 priority, u8 hwirq_type)
 	u16 iaffid;
 	int ret;
 
-	if (hwirq_type == GICV5_HWIRQ_TYPE_SPI) {
+	if (hwirq_type == GICV5_HWIRQ_TYPE_LPI || hwirq_type == GICV5_HWIRQ_TYPE_SPI) {
 		cdpri = FIELD_PREP(GICV5_GIC_CDPRI_PRIORITY_MASK, priority)	|
 			FIELD_PREP(GICV5_GIC_CDPRI_TYPE_MASK, hwirq_type)	|
 			FIELD_PREP(GICV5_GIC_CDPRI_ID_MASK, hwirq);
@@ -122,6 +160,11 @@ static void gicv5_spi_irq_mask(struct irq_data *d)
 	gicv5_iri_irq_mask(d, GICV5_HWIRQ_TYPE_SPI);
 }
 
+static void gicv5_lpi_irq_mask(struct irq_data *d)
+{
+	gicv5_iri_irq_mask(d, GICV5_HWIRQ_TYPE_LPI);
+}
+
 static void gicv5_ppi_irq_unmask(struct irq_data *d)
 {
 	u64 hwirq_id_bit = BIT_ULL(d->hwirq % 64);
@@ -149,7 +192,7 @@ static void gicv5_iri_irq_unmask(struct irq_data *d, u8 hwirq_type)
 	/*
 	 * Rule R_XCLJC states that the effects of a GIC system instruction
 	 * complete in finite time and that's the only requirement when
-	 * unmasking an SPI IRQ.
+	 * unmasking an SPI/LPI IRQ.
 	 */
 	gic_insn(cden, CDEN);
 }
@@ -159,6 +202,11 @@ static void gicv5_spi_irq_unmask(struct irq_data *d)
 	gicv5_iri_irq_unmask(d, GICV5_HWIRQ_TYPE_SPI);
 }
 
+static void gicv5_lpi_irq_unmask(struct irq_data *d)
+{
+	gicv5_iri_irq_unmask(d, GICV5_HWIRQ_TYPE_LPI);
+}
+
 static void gicv5_hwirq_eoi(u32 hwirq_id, u8 hwirq_type)
 {
 	u64 cddi;
@@ -181,6 +229,11 @@ static void gicv5_spi_irq_eoi(struct irq_data *d)
 	gicv5_hwirq_eoi(d->hwirq, GICV5_HWIRQ_TYPE_SPI);
 }
 
+static void gicv5_lpi_irq_eoi(struct irq_data *d)
+{
+	gicv5_hwirq_eoi(d->hwirq, GICV5_HWIRQ_TYPE_LPI);
+}
+
 static int gicv5_iri_irq_set_affinity(struct irq_data *d,
 				      const struct cpumask *mask_val,
 				      bool force, u8 hwirq_type)
@@ -216,6 +269,14 @@ static int gicv5_spi_irq_set_affinity(struct irq_data *d,
 					  GICV5_HWIRQ_TYPE_SPI);
 }
 
+static int gicv5_lpi_irq_set_affinity(struct irq_data *d,
+				      const struct cpumask *mask_val,
+				      bool force)
+{
+	return gicv5_iri_irq_set_affinity(d, mask_val, force,
+					  GICV5_HWIRQ_TYPE_LPI);
+}
+
 enum ppi_reg {
 	PPI_PENDING,
 	PPI_ACTIVE,
@@ -336,6 +397,14 @@ static int gicv5_spi_irq_get_irqchip_state(struct irq_data *d,
 					       GICV5_HWIRQ_TYPE_SPI);
 }
 
+static int gicv5_lpi_irq_get_irqchip_state(struct irq_data *d,
+					   enum irqchip_irq_state which,
+					   bool *state)
+{
+	return gicv5_iri_irq_get_irqchip_state(d, which, state,
+					       GICV5_HWIRQ_TYPE_LPI);
+}
+
 static int gicv5_ppi_irq_set_irqchip_state(struct irq_data *d,
 					   enum irqchip_irq_state which,
 					   bool state)
@@ -370,6 +439,11 @@ static void gicv5_spi_irq_write_pending_state(struct irq_data *d, bool state)
 	gicv5_iri_irq_write_pending_state(d, state, GICV5_HWIRQ_TYPE_SPI);
 }
 
+static void gicv5_lpi_irq_write_pending_state(struct irq_data *d, bool state)
+{
+	gicv5_iri_irq_write_pending_state(d, state, GICV5_HWIRQ_TYPE_LPI);
+}
+
 static int gicv5_spi_irq_set_irqchip_state(struct irq_data *d,
 					   enum irqchip_irq_state which,
 					   bool state)
@@ -386,12 +460,41 @@ static int gicv5_spi_irq_set_irqchip_state(struct irq_data *d,
 	return 0;
 }
 
+static int gicv5_lpi_irq_set_irqchip_state(struct irq_data *d,
+					   enum irqchip_irq_state which,
+					   bool state)
+{
+	switch (which) {
+	case IRQCHIP_STATE_PENDING:
+		gicv5_lpi_irq_write_pending_state(d, state);
+		break;
+
+	default:
+		pr_debug("Unexpected irqchip_irq_state\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
 static int gicv5_spi_irq_retrigger(struct irq_data *data)
 {
 	return !gicv5_spi_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING,
 						true);
 }
 
+static int gicv5_lpi_irq_retrigger(struct irq_data *data)
+{
+	return !gicv5_lpi_irq_set_irqchip_state(data, IRQCHIP_STATE_PENDING,
+						true);
+}
+
+static void gicv5_ipi_send_single(struct irq_data *d, unsigned int cpu)
+{
+	/* Mark the LPI pending */
+	irq_chip_retrigger_hierarchy(d);
+}
+
 static bool gicv5_ppi_irq_is_level(irq_hw_number_t hwirq)
 {
 	u64 bit = BIT_ULL(hwirq % 64);
@@ -425,6 +528,32 @@ static const struct irq_chip gicv5_spi_irq_chip = {
 				  IRQCHIP_MASK_ON_SUSPEND,
 };
 
+static const struct irq_chip gicv5_lpi_irq_chip = {
+	.name			= "GICv5-LPI",
+	.irq_mask		= gicv5_lpi_irq_mask,
+	.irq_unmask		= gicv5_lpi_irq_unmask,
+	.irq_eoi		= gicv5_lpi_irq_eoi,
+	.irq_set_affinity	= gicv5_lpi_irq_set_affinity,
+	.irq_retrigger		= gicv5_lpi_irq_retrigger,
+	.irq_get_irqchip_state	= gicv5_lpi_irq_get_irqchip_state,
+	.irq_set_irqchip_state	= gicv5_lpi_irq_set_irqchip_state,
+	.flags			= IRQCHIP_SKIP_SET_WAKE	  |
+				  IRQCHIP_MASK_ON_SUSPEND,
+};
+
+static const struct irq_chip gicv5_ipi_irq_chip = {
+	.name			= "GICv5-IPI",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_get_irqchip_state	= irq_chip_get_parent_state,
+	.irq_set_irqchip_state	= irq_chip_set_parent_state,
+	.ipi_send_single	= gicv5_ipi_send_single,
+	.flags			= IRQCHIP_SKIP_SET_WAKE	  |
+				  IRQCHIP_MASK_ON_SUSPEND,
+};
+
 static __always_inline int gicv5_irq_domain_translate(struct irq_domain *d,
 						      struct irq_fwspec *fwspec,
 						      irq_hw_number_t *hwirq,
@@ -585,6 +714,130 @@ static const struct irq_domain_ops gicv5_irq_spi_domain_ops = {
 	.free		= gicv5_irq_domain_free,
 	.select		= gicv5_irq_spi_domain_select
 };
+
+static void gicv5_lpi_config_reset(struct irq_data *d)
+{
+	u64 cdhm;
+
+	/*
+	 * Reset LPIs handling mode to edge by default and clear pending
+	 * state to make sure we start the LPI with a clean state from
+	 * previous incarnations.
+	 */
+	cdhm = FIELD_PREP(GICV5_GIC_CDHM_HM_MASK, 0)				|
+	       FIELD_PREP(GICV5_GIC_CDHM_TYPE_MASK, GICV5_HWIRQ_TYPE_LPI)	|
+	       FIELD_PREP(GICV5_GIC_CDHM_ID_MASK, d->hwirq);
+	gic_insn(cdhm, CDHM);
+
+	gicv5_lpi_irq_write_pending_state(d, false);
+}
+
+static int gicv5_irq_lpi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				      unsigned int nr_irqs, void *arg)
+{
+	irq_hw_number_t hwirq;
+	struct irq_data *irqd;
+	u32 *lpi = arg;
+	int ret;
+
+	if (WARN_ON_ONCE(nr_irqs != 1))
+		return -EINVAL;
+
+	hwirq = *lpi;
+
+	irqd = irq_domain_get_irq_data(domain, virq);
+
+	irq_domain_set_info(domain, virq, hwirq, &gicv5_lpi_irq_chip, NULL,
+			    handle_fasteoi_irq, NULL, NULL);
+	irqd_set_single_target(irqd);
+
+	ret = gicv5_irs_iste_alloc(hwirq);
+	if (ret < 0)
+		return ret;
+
+	gicv5_hwirq_init(hwirq, GICV5_IRQ_PRI_MI, GICV5_HWIRQ_TYPE_LPI);
+	gicv5_lpi_config_reset(irqd);
+
+	return 0;
+}
+
+static const struct irq_domain_ops gicv5_irq_lpi_domain_ops = {
+	.alloc	= gicv5_irq_lpi_domain_alloc,
+	.free	= gicv5_irq_domain_free,
+};
+
+void __init gicv5_init_lpi_domain(void)
+{
+	struct irq_domain *d;
+
+	d = irq_domain_create_tree(NULL, &gicv5_irq_lpi_domain_ops, NULL);
+	gicv5_global_data.lpi_domain = d;
+}
+
+void __init gicv5_free_lpi_domain(void)
+{
+	irq_domain_remove(gicv5_global_data.lpi_domain);
+	gicv5_global_data.lpi_domain = NULL;
+}
+
+static int gicv5_irq_ipi_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				      unsigned int nr_irqs, void *arg)
+{
+	struct irq_data *irqd;
+	int ret, i;
+	u32 lpi;
+
+	for (i = 0; i < nr_irqs; i++) {
+		ret = gicv5_alloc_lpi();
+		if (ret < 0)
+			return ret;
+
+		lpi = ret;
+
+		ret = irq_domain_alloc_irqs_parent(domain, virq + i, 1, &lpi);
+		if (ret) {
+			gicv5_free_lpi(lpi);
+			return ret;
+		}
+
+		irqd = irq_domain_get_irq_data(domain, virq + i);
+
+		irq_domain_set_hwirq_and_chip(domain, virq + i, i,
+				&gicv5_ipi_irq_chip, NULL);
+
+		irqd_set_single_target(irqd);
+
+		irq_set_handler(virq + i, handle_percpu_irq);
+	}
+
+	return 0;
+}
+
+static void gicv5_irq_ipi_domain_free(struct irq_domain *domain, unsigned int virq,
+				      unsigned int nr_irqs)
+{
+	struct irq_data *d;
+	unsigned int i;
+
+	for (i = 0; i < nr_irqs; i++) {
+		d = irq_domain_get_irq_data(domain, virq + i);
+
+		if (!d)
+			return;
+
+		gicv5_free_lpi(d->parent_data->hwirq);
+
+		irq_set_handler(virq + i, NULL);
+		irq_domain_reset_irq_data(d);
+		irq_domain_free_irqs_parent(domain, virq + i, 1);
+	}
+}
+
+static const struct irq_domain_ops gicv5_irq_ipi_domain_ops = {
+	.alloc	= gicv5_irq_ipi_domain_alloc,
+	.free	= gicv5_irq_ipi_domain_free,
+};
+
 static void handle_irq_per_domain(u32 hwirq)
 {
 	u8 hwirq_type = FIELD_GET(GICV5_HWIRQ_TYPE, hwirq);
@@ -598,6 +851,9 @@ static void handle_irq_per_domain(u32 hwirq)
 	case GICV5_HWIRQ_TYPE_SPI:
 		domain = gicv5_global_data.spi_domain;
 		break;
+	case GICV5_HWIRQ_TYPE_LPI:
+		domain = gicv5_global_data.lpi_domain;
+		break;
 	default:
 		pr_err_once("Unknown IRQ type, bail out\n");
 		return;
@@ -679,9 +935,12 @@ static void __init gicv5_free_domains(void)
 		irq_domain_remove(gicv5_global_data.ppi_domain);
 	if (gicv5_global_data.spi_domain)
 		irq_domain_remove(gicv5_global_data.spi_domain);
+	if (gicv5_global_data.ipi_domain)
+		irq_domain_remove(gicv5_global_data.ipi_domain);
 
 	gicv5_global_data.ppi_domain = NULL;
 	gicv5_global_data.spi_domain = NULL;
+	gicv5_global_data.ipi_domain = NULL;
 }
 
 static int __init gicv5_init_domains(struct fwnode_handle *handle)
@@ -709,6 +968,19 @@ static int __init gicv5_init_domains(struct fwnode_handle *handle)
 		irq_domain_update_bus_token(d, DOMAIN_BUS_WIRED);
 	}
 
+	if (!WARN(!gicv5_global_data.lpi_domain,
+		  "LPI domain uninitialized, can't set up IPIs")) {
+		d = irq_domain_create_hierarchy(gicv5_global_data.lpi_domain,
+						0, GICV5_IPIS_PER_CPU * nr_cpu_ids,
+						NULL, &gicv5_irq_ipi_domain_ops,
+						NULL);
+
+		if (!d) {
+			gicv5_free_domains();
+			return -ENOMEM;
+		}
+		gicv5_global_data.ipi_domain = d;
+	}
 	gicv5_global_data.fwnode = handle;
 
 	return 0;
@@ -732,6 +1004,24 @@ static void gicv5_set_cpuif_pribits(void)
 	}
 }
 
+static void gicv5_set_cpuif_idbits(void)
+{
+	u32 icc_idr0 = read_sysreg_s(SYS_ICC_IDR0_EL1);
+
+	switch (FIELD_GET(ICC_IDR0_EL1_ID_BITS, icc_idr0)) {
+	case ICC_IDR0_EL1_ID_BITS_16BITS:
+		gicv5_global_data.cpuif_id_bits = 16;
+		break;
+	case ICC_IDR0_EL1_ID_BITS_24BITS:
+		gicv5_global_data.cpuif_id_bits = 24;
+		break;
+	default:
+		pr_err("Unexpected ICC_IDR0_EL1_ID_BITS value, default to 16");
+		gicv5_global_data.cpuif_id_bits = 16;
+		break;
+	}
+}
+
 static int __init gicv5_of_init(struct device_node *node, struct device_node *parent)
 {
 	int ret = gicv5_irs_of_probe(node);
@@ -743,6 +1033,7 @@ static int __init gicv5_of_init(struct device_node *node, struct device_node *pa
 		goto out_irs;
 
 	gicv5_set_cpuif_pribits();
+	gicv5_set_cpuif_idbits();
 
 	pri_bits = min_not_zero(gicv5_global_data.cpuif_pri_bits,
 				gicv5_global_data.irs_pri_bits);
@@ -755,6 +1046,10 @@ static int __init gicv5_of_init(struct device_node *node, struct device_node *pa
 	if (ret)
 		goto out_int;
 
+	ret = gicv5_irs_enable();
+	if (ret)
+		goto out_int;
+
 	return 0;
 
 out_int:
diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h
index 1064a69ab33f..680eed794a35 100644
--- a/include/linux/irqchip/arm-gic-v5.h
+++ b/include/linux/irqchip/arm-gic-v5.h
@@ -7,8 +7,12 @@
 
 #include <linux/iopoll.h>
 
+#include <asm/cacheflush.h>
+#include <asm/smp.h>
 #include <asm/sysreg.h>
 
+#define GICV5_IPIS_PER_CPU		MAX_IPI
+
 /*
  * INTID handling
  */
@@ -17,6 +21,7 @@
 #define GICV5_HWIRQ_INTID		GENMASK_ULL(31, 0)
 
 #define GICV5_HWIRQ_TYPE_PPI		UL(0x1)
+#define GICV5_HWIRQ_TYPE_LPI		UL(0x2)
 #define GICV5_HWIRQ_TYPE_SPI		UL(0x3)
 
 /*
@@ -36,7 +41,7 @@
 #define GICV5_INNER_SHARE		0b11
 
 /*
- * IRS registers
+ * IRS registers and tables structures
  */
 #define GICV5_IRS_IDR1			0x0004
 #define GICV5_IRS_IDR2			0x0008
@@ -51,6 +56,10 @@
 #define GICV5_IRS_PE_SELR		0x0140
 #define GICV5_IRS_PE_STATUSR		0x0144
 #define GICV5_IRS_PE_CR0		0x0148
+#define GICV5_IRS_IST_BASER		0x0180
+#define GICV5_IRS_IST_CFGR		0x0190
+#define GICV5_IRS_IST_STATUSR		0x0194
+#define GICV5_IRS_MAP_L2_ISTR		0x01c0
 
 #define GICV5_IRS_IDR1_PRIORITY_BITS	GENMASK(22, 20)
 #define GICV5_IRS_IDR1_IAFFID_BITS	GENMASK(19, 16)
@@ -72,6 +81,11 @@
 #define GICV5_IRS_IDR5_SPI_RANGE	GENMASK(24, 0)
 #define GICV5_IRS_IDR6_SPI_IRS_RANGE	GENMASK(24, 0)
 #define GICV5_IRS_IDR7_SPI_BASE		GENMASK(23, 0)
+
+#define GICV5_IRS_IST_L2SZ_SUPPORT_4KB(r)	FIELD_GET(BIT(11), (r))
+#define GICV5_IRS_IST_L2SZ_SUPPORT_16KB(r)	FIELD_GET(BIT(12), (r))
+#define GICV5_IRS_IST_L2SZ_SUPPORT_64KB(r)	FIELD_GET(BIT(13), (r))
+
 #define GICV5_IRS_CR0_IDLE		BIT(1)
 #define GICV5_IRS_CR0_IRSEN		BIT(0)
 
@@ -103,6 +117,33 @@
 
 #define GICV5_IRS_PE_CR0_DPS		BIT(0)
 
+#define GICV5_IRS_IST_STATUSR_IDLE	BIT(0)
+
+#define GICV5_IRS_IST_CFGR_STRUCTURE	BIT(16)
+#define GICV5_IRS_IST_CFGR_ISTSZ	GENMASK(8, 7)
+#define GICV5_IRS_IST_CFGR_L2SZ		GENMASK(6, 5)
+#define GICV5_IRS_IST_CFGR_LPI_ID_BITS	GENMASK(4, 0)
+
+#define GICV5_IRS_IST_CFGR_STRUCTURE_LINEAR	0b0
+#define GICV5_IRS_IST_CFGR_STRUCTURE_TWO_LEVEL	0b1
+
+#define GICV5_IRS_IST_CFGR_ISTSZ_4	0b00
+#define GICV5_IRS_IST_CFGR_ISTSZ_8	0b01
+#define GICV5_IRS_IST_CFGR_ISTSZ_16	0b10
+
+#define GICV5_IRS_IST_CFGR_L2SZ_4K	0b00
+#define GICV5_IRS_IST_CFGR_L2SZ_16K	0b01
+#define GICV5_IRS_IST_CFGR_L2SZ_64K	0b10
+
+#define GICV5_IRS_IST_BASER_ADDR_MASK	GENMASK_ULL(55, 6)
+#define GICV5_IRS_IST_BASER_VALID	BIT_ULL(0)
+
+#define GICV5_IRS_MAP_L2_ISTR_ID	GENMASK(23, 0)
+
+#define GICV5_ISTL1E_VALID		BIT_ULL(0)
+
+#define GICV5_ISTL1E_L2_ADDR_MASK	GENMASK_ULL(55, 12)
+
 /*
  * Global Data structures and functions
  */
@@ -110,9 +151,18 @@ struct gicv5_chip_data {
 	struct fwnode_handle	*fwnode;
 	struct irq_domain	*ppi_domain;
 	struct irq_domain	*spi_domain;
+	struct irq_domain	*lpi_domain;
+	struct irq_domain	*ipi_domain;
 	u32			global_spi_count;
 	u8			cpuif_pri_bits;
+	u8			cpuif_id_bits;
 	u8			irs_pri_bits;
+	struct {
+		__le64 *l1ist_addr;
+		u32 l2_size;
+		u8 l2_bits;
+		bool l2;
+	} ist;
 };
 
 extern struct gicv5_chip_data gicv5_global_data __read_mostly;
@@ -150,10 +200,21 @@ static inline int gicv5_wait_for_op_s_atomic(void __iomem *addr, u32 offset,
 #define gicv5_wait_for_op_atomic(base, reg, mask, val) \
 	gicv5_wait_for_op_s_atomic(base, reg, #reg, mask, val)
 
+void __init gicv5_init_lpi_domain(void);
+void __init gicv5_free_lpi_domain(void);
+
 int gicv5_irs_of_probe(struct device_node *parent);
 void gicv5_irs_remove(void);
+int gicv5_irs_enable(void);
 int gicv5_irs_register_cpu(int cpuid);
 int gicv5_irs_cpu_to_iaffid(int cpu_id, u16 *iaffid);
 struct gicv5_irs_chip_data *gicv5_irs_lookup_by_spi_id(u32 spi_id);
 int gicv5_spi_irq_set_type(struct irq_data *d, unsigned int type);
+int gicv5_irs_iste_alloc(u32 lpi);
+
+void gicv5_init_lpis(u32 max);
+void gicv5_deinit_lpis(void);
+
+int gicv5_alloc_lpi(void);
+void gicv5_free_lpi(u32 lpi);
 #endif
-- 
cgit v1.2.3


From 31fd3becb920e0b31b99cf202ace637f75dd7e78 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 3 Jul 2025 12:25:14 +0200
Subject: of/irq: Add of_msi_xlate() helper function

Add an of_msi_xlate() helper that maps a device ID and returns
the device node of the MSI controller the device ID is mapped to.

Required by core functions that need an MSI controller device node
pointer at the same time as a mapped device ID, of_msi_map_id() is not
sufficient for that purpose.

Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Rob Herring <robh@kernel.org>
Cc: Marc Zyngier <maz@kernel.org>
Reviewed-by: Rob Herring (Arm) <robh@kernel.org>
Link: https://lore.kernel.org/r/20250703-gicv5-host-v7-24-12e71f1b3528@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 drivers/of/irq.c       | 22 +++++++++++++++++-----
 include/linux/of_irq.h |  5 +++++
 2 files changed, 22 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/of/irq.c b/drivers/of/irq.c
index f8ad79b9b1c9..74aaea61de13 100644
--- a/drivers/of/irq.c
+++ b/drivers/of/irq.c
@@ -670,8 +670,20 @@ err:
 	}
 }
 
-static u32 __of_msi_map_id(struct device *dev, struct device_node **np,
-			    u32 id_in)
+/**
+ * of_msi_xlate - map a MSI ID and find relevant MSI controller node
+ * @dev: device for which the mapping is to be done.
+ * @msi_np: Pointer to store the MSI controller node
+ * @id_in: Device ID.
+ *
+ * Walk up the device hierarchy looking for devices with a "msi-map"
+ * property. If found, apply the mapping to @id_in. @msi_np pointed
+ * value must be NULL on entry, if an MSI controller is found @msi_np is
+ * initialized to the MSI controller node with a reference held.
+ *
+ * Returns: The mapped MSI id.
+ */
+u32 of_msi_xlate(struct device *dev, struct device_node **msi_np, u32 id_in)
 {
 	struct device *parent_dev;
 	u32 id_out = id_in;
@@ -682,7 +694,7 @@ static u32 __of_msi_map_id(struct device *dev, struct device_node **np,
 	 */
 	for (parent_dev = dev; parent_dev; parent_dev = parent_dev->parent)
 		if (!of_map_id(parent_dev->of_node, id_in, "msi-map",
-				"msi-map-mask", np, &id_out))
+				"msi-map-mask", msi_np, &id_out))
 			break;
 	return id_out;
 }
@@ -700,7 +712,7 @@ static u32 __of_msi_map_id(struct device *dev, struct device_node **np,
  */
 u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in)
 {
-	return __of_msi_map_id(dev, &msi_np, id_in);
+	return of_msi_xlate(dev, &msi_np, id_in);
 }
 
 /**
@@ -719,7 +731,7 @@ struct irq_domain *of_msi_map_get_device_domain(struct device *dev, u32 id,
 {
 	struct device_node *np = NULL;
 
-	__of_msi_map_id(dev, &np, id);
+	of_msi_xlate(dev, &np, id);
 	return irq_find_matching_host(np, bus_token);
 }
 
diff --git a/include/linux/of_irq.h b/include/linux/of_irq.h
index 6337ad4e5fe8..a480063c9cb1 100644
--- a/include/linux/of_irq.h
+++ b/include/linux/of_irq.h
@@ -54,6 +54,7 @@ extern struct irq_domain *of_msi_map_get_device_domain(struct device *dev,
 							u32 id,
 							u32 bus_token);
 extern void of_msi_configure(struct device *dev, const struct device_node *np);
+extern u32 of_msi_xlate(struct device *dev, struct device_node **msi_np, u32 id_in);
 u32 of_msi_map_id(struct device *dev, struct device_node *msi_np, u32 id_in);
 #else
 static inline void of_irq_init(const struct of_device_id *matches)
@@ -100,6 +101,10 @@ static inline struct irq_domain *of_msi_map_get_device_domain(struct device *dev
 static inline void of_msi_configure(struct device *dev, struct device_node *np)
 {
 }
+static inline u32 of_msi_xlate(struct device *dev, struct device_node **msi_np, u32 id_in)
+{
+	return id_in;
+}
 static inline u32 of_msi_map_id(struct device *dev,
 				 struct device_node *msi_np, u32 id_in)
 {
-- 
cgit v1.2.3


From cd0ec59affb1f31347170bbafadb9c5cc716bca9 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 3 Jul 2025 12:25:15 +0200
Subject: PCI/MSI: Add pci_msi_map_rid_ctlr_node() helper function

IRQchip drivers need a PCI/MSI function to map a RID to a MSI
controller deviceID namespace and at the same time retrieve the
struct device_node pointer of the MSI controller the RID is mapped
to.

Add pci_msi_map_rid_ctlr_node() to achieve this purpose.

Cc  Bjorn Helgaas <bhelgaas@google.com>

Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250703-gicv5-host-v7-25-12e71f1b3528@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 drivers/pci/msi/irqdomain.c | 20 ++++++++++++++++++++
 include/linux/msi.h         |  1 +
 2 files changed, 21 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/pci/msi/irqdomain.c b/drivers/pci/msi/irqdomain.c
index c05152733993..8a6e80d3963a 100644
--- a/drivers/pci/msi/irqdomain.c
+++ b/drivers/pci/msi/irqdomain.c
@@ -427,6 +427,26 @@ u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev)
 	return rid;
 }
 
+/**
+ * pci_msi_map_rid_ctlr_node - Get the MSI controller node and MSI requester id (RID)
+ * @pdev:	The PCI device
+ * @node:	Pointer to store the MSI controller device node
+ *
+ * Use the firmware data to find the MSI controller node for @pdev.
+ * If found map the RID and initialize @node with it. @node value must
+ * be set to NULL on entry.
+ *
+ * Returns: The RID.
+ */
+u32 pci_msi_map_rid_ctlr_node(struct pci_dev *pdev, struct device_node **node)
+{
+	u32 rid = pci_dev_id(pdev);
+
+	pci_for_each_dma_alias(pdev, get_msi_id_cb, &rid);
+
+	return of_msi_xlate(&pdev->dev, node, rid);
+}
+
 /**
  * pci_msi_get_device_domain - Get the MSI domain for a given PCI device
  * @pdev:	The PCI device
diff --git a/include/linux/msi.h b/include/linux/msi.h
index 6863540f4b71..a418e2695b05 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -705,6 +705,7 @@ struct irq_domain *pci_msi_create_irq_domain(struct fwnode_handle *fwnode,
 					     struct msi_domain_info *info,
 					     struct irq_domain *parent);
 u32 pci_msi_domain_get_msi_rid(struct irq_domain *domain, struct pci_dev *pdev);
+u32 pci_msi_map_rid_ctlr_node(struct pci_dev *pdev, struct device_node **node);
 struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev);
 #else /* CONFIG_PCI_MSI */
 static inline struct irq_domain *pci_msi_get_device_domain(struct pci_dev *pdev)
-- 
cgit v1.2.3


From 8b65db1e93a227ad9cc1b67cb221b06869f0b35f Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 3 Jul 2025 12:25:17 +0200
Subject: irqchip/msi-lib: Add IRQ_DOMAIN_FLAG_FWNODE_PARENT handling

In some irqchip implementations the fwnode representing the IRQdomain
and the MSI controller fwnode do not match; in particular the IRQdomain
fwnode is the MSI controller fwnode parent.

To support selecting such IRQ domains, add a flag in core IRQ domain
code that explicitly tells the MSI lib to use the parent fwnode while
carrying out IRQ domain selection.

Update the msi-lib select callback with the resulting logic.

Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250703-gicv5-host-v7-27-12e71f1b3528@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 drivers/irqchip/irq-msi-lib.c | 5 ++++-
 include/linux/irqdomain.h     | 3 +++
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/irqchip/irq-msi-lib.c b/drivers/irqchip/irq-msi-lib.c
index 246c30205af4..454c7f16dd4d 100644
--- a/drivers/irqchip/irq-msi-lib.c
+++ b/drivers/irqchip/irq-msi-lib.c
@@ -133,11 +133,14 @@ int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec,
 {
 	const struct msi_parent_ops *ops = d->msi_parent_ops;
 	u32 busmask = BIT(bus_token);
+	struct fwnode_handle *fwh;
 
 	if (!ops)
 		return 0;
 
-	if (fwspec->fwnode != d->fwnode || fwspec->param_count != 0)
+	fwh = d->flags & IRQ_DOMAIN_FLAG_FWNODE_PARENT ? fwnode_get_parent(fwspec->fwnode)
+						       : fwspec->fwnode;
+	if (fwh != d->fwnode || fwspec->param_count != 0)
 		return 0;
 
 	/* Handle pure domain searches */
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 7387d183029b..25c7cbeed393 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -212,6 +212,9 @@ enum {
 	/* Address and data pair is mutable when irq_set_affinity() */
 	IRQ_DOMAIN_FLAG_MSI_IMMUTABLE	= (1 << 11),
 
+	/* IRQ domain requires parent fwnode matching */
+	IRQ_DOMAIN_FLAG_FWNODE_PARENT	= (1 << 12),
+
 	/*
 	 * Flags starting from IRQ_DOMAIN_FLAG_NONCORE are reserved
 	 * for implementation specific purposes and ignored by the
-- 
cgit v1.2.3


From 57d72196dfc8502b7e376ecdffb11c4f8766f26d Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 3 Jul 2025 12:25:18 +0200
Subject: irqchip/gic-v5: Add GICv5 ITS support

The GICv5 architecture implements Interrupt Translation Service
(ITS) components in order to translate events coming from peripherals
into interrupt events delivered to the connected IRSes.

Events (ie MSI memory writes to ITS translate frame), are translated
by the ITS using tables kept in memory.

ITS translation tables for peripherals is kept in memory storage
(device table [DT] and Interrupt Translation Table [ITT]) that
is allocated by the driver on boot.

Both tables can be 1- or 2-level; the structure is chosen by the
driver after probing the ITS HW parameters and checking the
allowed table splits and supported {device/event}_IDbits.

DT table entries are allocated on demand (ie when a device is
probed); the DT table is sized using the number of supported
deviceID bits in that that's a system design decision (ie the
number of deviceID bits implemented should reflect the number
of devices expected in a system) therefore it makes sense to
allocate a DT table that can cater for the maximum number of
devices.

DT and ITT tables are allocated using the kmalloc interface;
the allocation size may be smaller than a page or larger,
and must provide contiguous memory pages.

LPIs INTIDs backing the device events are allocated one-by-one
and only upon Linux IRQ allocation; this to avoid preallocating
a large number of LPIs to cover the HW device MSI vector
size whereas few MSI entries are actually enabled by a device.

ITS cacheability/shareability attributes are programmed
according to the provided firmware ITS description.

The GICv5 partially reuses the GICv3 ITS MSI parent infrastructure
and adds functions required to retrieve the ITS translate frame
addresses out of msi-map and msi-parent properties to implement
the GICv5 ITS MSI parent callbacks.

Co-developed-by: Sascha Bischoff <sascha.bischoff@arm.com>
Signed-off-by: Sascha Bischoff <sascha.bischoff@arm.com>
Co-developed-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250703-gicv5-host-v7-28-12e71f1b3528@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 MAINTAINERS                              |    1 +
 drivers/irqchip/Kconfig                  |    3 +
 drivers/irqchip/Makefile                 |    2 +-
 drivers/irqchip/irq-gic-its-msi-parent.c |  166 ++++
 drivers/irqchip/irq-gic-its-msi-parent.h |    1 +
 drivers/irqchip/irq-gic-v5-irs.c         |   24 +
 drivers/irqchip/irq-gic-v5-its.c         | 1206 ++++++++++++++++++++++++++++++
 drivers/irqchip/irq-gic-v5.c             |    2 +
 include/linux/irqchip/arm-gic-v5.h       |  157 ++++
 9 files changed, 1561 insertions(+), 1 deletion(-)
 create mode 100644 drivers/irqchip/irq-gic-v5-its.c

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index b1202987eef5..b035802ea41d 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1970,6 +1970,7 @@ M:	Marc Zyngier <maz@kernel.org>
 L:	linux-arm-kernel@lists.infradead.org (moderated for non-subscribers)
 S:	Maintained
 F:	Documentation/devicetree/bindings/interrupt-controller/arm,gic-v5*.yaml
+F:	drivers/irqchip/irq-gic-its-msi-parent.[ch]
 F:	drivers/irqchip/irq-gic-v5*.[ch]
 F:	include/linux/irqchip/arm-gic-v5.h
 
diff --git a/drivers/irqchip/Kconfig b/drivers/irqchip/Kconfig
index f9eae1a645c9..67d79d33407a 100644
--- a/drivers/irqchip/Kconfig
+++ b/drivers/irqchip/Kconfig
@@ -62,6 +62,9 @@ config ARM_GIC_V5
 	bool
 	select IRQ_DOMAIN_HIERARCHY
 	select GENERIC_IRQ_EFFECTIVE_AFF_MASK
+	select GENERIC_MSI_IRQ
+	select IRQ_MSI_LIB
+	select ARM_GIC_ITS_PARENT
 
 config ARM_NVIC
 	bool
diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 3ce6ea9a371b..5459f66e597f 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -37,7 +37,7 @@ obj-$(CONFIG_ARM_GIC_ITS_PARENT)	+= irq-gic-its-msi-parent.o
 obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o irq-gic-v4.o
 obj-$(CONFIG_ARM_GIC_V3_ITS_FSL_MC)	+= irq-gic-v3-its-fsl-mc-msi.o
 obj-$(CONFIG_PARTITION_PERCPU)		+= irq-partition-percpu.o
-obj-$(CONFIG_ARM_GIC_V5)		+= irq-gic-v5.o irq-gic-v5-irs.o
+obj-$(CONFIG_ARM_GIC_V5)		+= irq-gic-v5.o irq-gic-v5-irs.o irq-gic-v5-its.o
 obj-$(CONFIG_HISILICON_IRQ_MBIGEN)	+= irq-mbigen.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
diff --git a/drivers/irqchip/irq-gic-its-msi-parent.c b/drivers/irqchip/irq-gic-its-msi-parent.c
index 8beecfed2b84..eb1473f1448a 100644
--- a/drivers/irqchip/irq-gic-its-msi-parent.c
+++ b/drivers/irqchip/irq-gic-its-msi-parent.c
@@ -5,6 +5,7 @@
 // Copyright (C) 2022 Intel
 
 #include <linux/acpi_iort.h>
+#include <linux/of_address.h>
 #include <linux/pci.h>
 
 #include "irq-gic-its-msi-parent.h"
@@ -18,6 +19,23 @@
 				 MSI_FLAG_PCI_MSIX      |	\
 				 MSI_FLAG_MULTI_PCI_MSI)
 
+static int its_translate_frame_address(struct device_node *msi_node, phys_addr_t *pa)
+{
+	struct resource res;
+	int ret;
+
+	ret = of_property_match_string(msi_node, "reg-names", "ns-translate");
+	if (ret < 0)
+		return ret;
+
+	ret = of_address_to_resource(msi_node, ret, &res);
+	if (ret)
+		return ret;
+
+	*pa = res.start;
+	return 0;
+}
+
 #ifdef CONFIG_PCI_MSI
 static int its_pci_msi_vec_count(struct pci_dev *pdev, void *data)
 {
@@ -82,8 +100,46 @@ static int its_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
 	msi_info = msi_get_domain_info(domain->parent);
 	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
 }
+
+static int its_v5_pci_msi_prepare(struct irq_domain *domain, struct device *dev,
+				  int nvec, msi_alloc_info_t *info)
+{
+	struct device_node *msi_node = NULL;
+	struct msi_domain_info *msi_info;
+	struct pci_dev *pdev;
+	phys_addr_t pa;
+	u32 rid;
+	int ret;
+
+	if (!dev_is_pci(dev))
+		return -EINVAL;
+
+	pdev = to_pci_dev(dev);
+
+	rid = pci_msi_map_rid_ctlr_node(pdev, &msi_node);
+	if (!msi_node)
+		return -ENODEV;
+
+	ret = its_translate_frame_address(msi_node, &pa);
+	if (ret)
+		return -ENODEV;
+
+	of_node_put(msi_node);
+
+	/* ITS specific DeviceID */
+	info->scratchpad[0].ul = rid;
+	/* ITS translate frame physical address */
+	info->scratchpad[1].ul = pa;
+
+	/* Always allocate power of two vectors */
+	nvec = roundup_pow_of_two(nvec);
+
+	msi_info = msi_get_domain_info(domain->parent);
+	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
+}
 #else /* CONFIG_PCI_MSI */
 #define its_pci_msi_prepare	NULL
+#define its_v5_pci_msi_prepare	NULL
 #endif /* !CONFIG_PCI_MSI */
 
 static int of_pmsi_get_dev_id(struct irq_domain *domain, struct device *dev,
@@ -118,6 +174,53 @@ static int of_pmsi_get_dev_id(struct irq_domain *domain, struct device *dev,
 	return ret;
 }
 
+static int of_v5_pmsi_get_msi_info(struct irq_domain *domain, struct device *dev,
+				   u32 *dev_id, phys_addr_t *pa)
+{
+	int ret, index = 0;
+	/*
+	 * Retrieve the DeviceID and the ITS translate frame node pointer
+	 * out of the msi-parent property.
+	 */
+	do {
+		struct of_phandle_args args;
+
+		ret = of_parse_phandle_with_args(dev->of_node,
+						 "msi-parent", "#msi-cells",
+						 index, &args);
+		if (ret)
+			break;
+		/*
+		 * The IRQ domain fwnode is the msi controller parent
+		 * in GICv5 (where the msi controller nodes are the
+		 * ITS translate frames).
+		 */
+		if (args.np->parent == irq_domain_get_of_node(domain)) {
+			if (WARN_ON(args.args_count != 1))
+				return -EINVAL;
+			*dev_id = args.args[0];
+
+			ret = its_translate_frame_address(args.np, pa);
+			if (ret)
+				return -ENODEV;
+			break;
+		}
+		index++;
+	} while (!ret);
+
+	if (ret) {
+		struct device_node *np = NULL;
+
+		ret = of_map_id(dev->of_node, dev->id, "msi-map", "msi-map-mask", &np, dev_id);
+		if (np) {
+			ret = its_translate_frame_address(np, pa);
+			of_node_put(np);
+		}
+	}
+
+	return ret;
+}
+
 int __weak iort_pmsi_get_dev_id(struct device *dev, u32 *dev_id)
 {
 	return -1;
@@ -148,6 +251,33 @@ static int its_pmsi_prepare(struct irq_domain *domain, struct device *dev,
 					  dev, nvec, info);
 }
 
+static int its_v5_pmsi_prepare(struct irq_domain *domain, struct device *dev,
+			       int nvec, msi_alloc_info_t *info)
+{
+	struct msi_domain_info *msi_info;
+	phys_addr_t pa;
+	u32 dev_id;
+	int ret;
+
+	if (!dev->of_node)
+		return -ENODEV;
+
+	ret = of_v5_pmsi_get_msi_info(domain->parent, dev, &dev_id, &pa);
+	if (ret)
+		return ret;
+
+	/* ITS specific DeviceID */
+	info->scratchpad[0].ul = dev_id;
+	/* ITS translate frame physical address */
+	info->scratchpad[1].ul = pa;
+
+	/* Allocate always as a power of 2 */
+	nvec = roundup_pow_of_two(nvec);
+
+	msi_info = msi_get_domain_info(domain->parent);
+	return msi_info->ops->msi_prepare(domain->parent, dev, nvec, info);
+}
+
 static void its_msi_teardown(struct irq_domain *domain, msi_alloc_info_t *info)
 {
 	struct msi_domain_info *msi_info;
@@ -199,6 +329,32 @@ static bool its_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
 	return true;
 }
 
+static bool its_v5_init_dev_msi_info(struct device *dev, struct irq_domain *domain,
+				     struct irq_domain *real_parent, struct msi_domain_info *info)
+{
+	if (!msi_lib_init_dev_msi_info(dev, domain, real_parent, info))
+		return false;
+
+	switch (info->bus_token) {
+	case DOMAIN_BUS_PCI_DEVICE_MSI:
+	case DOMAIN_BUS_PCI_DEVICE_MSIX:
+		info->ops->msi_prepare = its_v5_pci_msi_prepare;
+		info->ops->msi_teardown = its_msi_teardown;
+		break;
+	case DOMAIN_BUS_DEVICE_MSI:
+	case DOMAIN_BUS_WIRED_TO_MSI:
+		info->ops->msi_prepare = its_v5_pmsi_prepare;
+		info->ops->msi_teardown = its_msi_teardown;
+		break;
+	default:
+		/* Confused. How did the lib return true? */
+		WARN_ON_ONCE(1);
+		return false;
+	}
+
+	return true;
+}
+
 const struct msi_parent_ops gic_v3_its_msi_parent_ops = {
 	.supported_flags	= ITS_MSI_FLAGS_SUPPORTED,
 	.required_flags		= ITS_MSI_FLAGS_REQUIRED,
@@ -208,3 +364,13 @@ const struct msi_parent_ops gic_v3_its_msi_parent_ops = {
 	.prefix			= "ITS-",
 	.init_dev_msi_info	= its_init_dev_msi_info,
 };
+
+const struct msi_parent_ops gic_v5_its_msi_parent_ops = {
+	.supported_flags	= ITS_MSI_FLAGS_SUPPORTED,
+	.required_flags		= ITS_MSI_FLAGS_REQUIRED,
+	.chip_flags		= MSI_CHIP_FLAG_SET_EOI,
+	.bus_select_token	= DOMAIN_BUS_NEXUS,
+	.bus_select_mask	= MATCH_PCI_MSI | MATCH_PLATFORM_MSI,
+	.prefix			= "ITS-v5-",
+	.init_dev_msi_info	= its_v5_init_dev_msi_info,
+};
diff --git a/drivers/irqchip/irq-gic-its-msi-parent.h b/drivers/irqchip/irq-gic-its-msi-parent.h
index 75e223e673ce..df016f347337 100644
--- a/drivers/irqchip/irq-gic-its-msi-parent.h
+++ b/drivers/irqchip/irq-gic-its-msi-parent.h
@@ -7,5 +7,6 @@
 #define _IRQ_GIC_ITS_MSI_PARENT_H
 
 extern const struct msi_parent_ops gic_v3_its_msi_parent_ops;
+extern const struct msi_parent_ops gic_v5_its_msi_parent_ops;
 
 #endif /* _IRQ_GIC_ITS_MSI_PARENT_H */
diff --git a/drivers/irqchip/irq-gic-v5-irs.c b/drivers/irqchip/irq-gic-v5-irs.c
index f00a4a6fece7..f845415f9143 100644
--- a/drivers/irqchip/irq-gic-v5-irs.c
+++ b/drivers/irqchip/irq-gic-v5-irs.c
@@ -484,6 +484,22 @@ static int gicv5_irs_wait_for_idle(struct gicv5_irs_chip_data *irs_data)
 					GICV5_IRS_CR0_IDLE, NULL);
 }
 
+void gicv5_irs_syncr(void)
+{
+	struct gicv5_irs_chip_data *irs_data;
+	u32 syncr;
+
+	irs_data = list_first_entry_or_null(&irs_nodes, struct gicv5_irs_chip_data, entry);
+	if (WARN_ON_ONCE(!irs_data))
+		return;
+
+	syncr = FIELD_PREP(GICV5_IRS_SYNCR_SYNC, 1);
+	irs_writel_relaxed(irs_data, syncr, GICV5_IRS_SYNCR);
+
+	gicv5_wait_for_op(irs_data->irs_base, GICV5_IRS_SYNC_STATUSR,
+			  GICV5_IRS_SYNC_STATUSR_IDLE);
+}
+
 int gicv5_irs_register_cpu(int cpuid)
 {
 	struct gicv5_irs_chip_data *irs_data;
@@ -780,6 +796,14 @@ int __init gicv5_irs_enable(void)
 	return 0;
 }
 
+void __init gicv5_irs_its_probe(void)
+{
+	struct gicv5_irs_chip_data *irs_data;
+
+	list_for_each_entry(irs_data, &irs_nodes, entry)
+		gicv5_its_of_probe(to_of_node(irs_data->fwnode));
+}
+
 int __init gicv5_irs_of_probe(struct device_node *parent)
 {
 	struct device_node *np;
diff --git a/drivers/irqchip/irq-gic-v5-its.c b/drivers/irqchip/irq-gic-v5-its.c
new file mode 100644
index 000000000000..700df6d0687e
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v5-its.c
@@ -0,0 +1,1206 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024-2025 ARM Limited, All Rights Reserved.
+ */
+
+#define pr_fmt(fmt)	"GICv5 ITS: " fmt
+
+#include <linux/bitmap.h>
+#include <linux/iommu.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_irq.h>
+#include <linux/slab.h>
+
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic-v5.h>
+#include <linux/irqchip/irq-msi-lib.h>
+
+#include "irq-gic-its-msi-parent.h"
+
+#define ITS_FLAGS_NON_COHERENT		BIT(0)
+
+struct gicv5_its_chip_data {
+	struct	xarray			its_devices;
+	struct	mutex			dev_alloc_lock;
+	struct	fwnode_handle		*fwnode;
+	struct gicv5_its_devtab_cfg	devtab_cfgr;
+	void	__iomem			*its_base;
+	u32				flags;
+	unsigned int			msi_domain_flags;
+};
+
+struct gicv5_its_dev {
+	struct gicv5_its_chip_data	*its_node;
+	struct gicv5_its_itt_cfg	itt_cfg;
+	unsigned long			*event_map;
+	u32				device_id;
+	u32				num_events;
+	phys_addr_t			its_trans_phys_base;
+};
+
+static u32 its_readl_relaxed(struct gicv5_its_chip_data *its_node, const u32 reg_offset)
+{
+	return readl_relaxed(its_node->its_base + reg_offset);
+}
+
+static void its_writel_relaxed(struct gicv5_its_chip_data *its_node, const u32 val,
+			       const u32 reg_offset)
+{
+	writel_relaxed(val, its_node->its_base + reg_offset);
+}
+
+static void its_writeq_relaxed(struct gicv5_its_chip_data *its_node, const u64 val,
+			       const u32 reg_offset)
+{
+	writeq_relaxed(val, its_node->its_base + reg_offset);
+}
+
+static void gicv5_its_dcache_clean(struct gicv5_its_chip_data *its, void *start,
+				   size_t sz)
+{
+	void *end = start + sz;
+
+	if (its->flags & ITS_FLAGS_NON_COHERENT)
+		dcache_clean_inval_poc((unsigned long)start, (unsigned long)end);
+	else
+		dsb(ishst);
+}
+
+static void its_write_table_entry(struct gicv5_its_chip_data *its, __le64 *entry,
+				  u64 val)
+{
+	WRITE_ONCE(*entry, cpu_to_le64(val));
+	gicv5_its_dcache_clean(its, entry, sizeof(*entry));
+}
+
+#define devtab_cfgr_field(its, f)	\
+	FIELD_GET(GICV5_ITS_DT_CFGR_##f, (its)->devtab_cfgr.cfgr)
+
+static int gicv5_its_cache_sync(struct gicv5_its_chip_data *its)
+{
+	return gicv5_wait_for_op_atomic(its->its_base, GICV5_ITS_STATUSR,
+					GICV5_ITS_STATUSR_IDLE, NULL);
+}
+
+static void gicv5_its_syncr(struct gicv5_its_chip_data *its,
+			    struct gicv5_its_dev *its_dev)
+{
+	u64 syncr;
+
+	syncr = FIELD_PREP(GICV5_ITS_SYNCR_SYNC, 1) |
+		FIELD_PREP(GICV5_ITS_SYNCR_DEVICEID, its_dev->device_id);
+
+	its_writeq_relaxed(its, syncr, GICV5_ITS_SYNCR);
+
+	gicv5_wait_for_op(its->its_base, GICV5_ITS_SYNC_STATUSR, GICV5_ITS_SYNC_STATUSR_IDLE);
+}
+
+/* Number of bits required for each L2 {device/interrupt translation} table size */
+#define ITS_L2SZ_64K_L2_BITS	13
+#define ITS_L2SZ_16K_L2_BITS	11
+#define ITS_L2SZ_4K_L2_BITS	9
+
+static unsigned int gicv5_its_l2sz_to_l2_bits(unsigned int sz)
+{
+	switch (sz) {
+	case GICV5_ITS_DT_ITT_CFGR_L2SZ_64k:
+		return ITS_L2SZ_64K_L2_BITS;
+	case GICV5_ITS_DT_ITT_CFGR_L2SZ_16k:
+		return ITS_L2SZ_16K_L2_BITS;
+	case GICV5_ITS_DT_ITT_CFGR_L2SZ_4k:
+	default:
+		return ITS_L2SZ_4K_L2_BITS;
+	}
+}
+
+static int gicv5_its_itt_cache_inv(struct gicv5_its_chip_data *its, u32 device_id,
+				   u16 event_id)
+{
+	u32 eventr, eidr;
+	u64 didr;
+
+	didr = FIELD_PREP(GICV5_ITS_DIDR_DEVICEID, device_id);
+	eidr = FIELD_PREP(GICV5_ITS_EIDR_EVENTID, event_id);
+	eventr = FIELD_PREP(GICV5_ITS_INV_EVENTR_I, 0x1);
+
+	its_writeq_relaxed(its, didr, GICV5_ITS_DIDR);
+	its_writel_relaxed(its, eidr, GICV5_ITS_EIDR);
+	its_writel_relaxed(its, eventr, GICV5_ITS_INV_EVENTR);
+
+	return gicv5_its_cache_sync(its);
+}
+
+static void gicv5_its_free_itt_linear(struct gicv5_its_dev *its_dev)
+{
+	kfree(its_dev->itt_cfg.linear.itt);
+}
+
+static void gicv5_its_free_itt_two_level(struct gicv5_its_dev *its_dev)
+{
+	unsigned int i, num_ents = its_dev->itt_cfg.l2.num_l1_ents;
+
+	for (i = 0; i < num_ents; i++)
+		kfree(its_dev->itt_cfg.l2.l2ptrs[i]);
+
+	kfree(its_dev->itt_cfg.l2.l2ptrs);
+	kfree(its_dev->itt_cfg.l2.l1itt);
+}
+
+static void gicv5_its_free_itt(struct gicv5_its_dev *its_dev)
+{
+	if (!its_dev->itt_cfg.l2itt)
+		gicv5_its_free_itt_linear(its_dev);
+	else
+		gicv5_its_free_itt_two_level(its_dev);
+}
+
+static int gicv5_its_create_itt_linear(struct gicv5_its_chip_data *its,
+				       struct gicv5_its_dev *its_dev,
+				       unsigned int event_id_bits)
+{
+	unsigned int num_ents = BIT(event_id_bits);
+	__le64 *itt;
+
+	itt = kcalloc(num_ents, sizeof(*itt), GFP_KERNEL);
+	if (!itt)
+		return -ENOMEM;
+
+	its_dev->itt_cfg.linear.itt = itt;
+	its_dev->itt_cfg.linear.num_ents = num_ents;
+	its_dev->itt_cfg.l2itt = false;
+	its_dev->itt_cfg.event_id_bits = event_id_bits;
+
+	gicv5_its_dcache_clean(its, itt, num_ents * sizeof(*itt));
+
+	return 0;
+}
+
+/*
+ * Allocate a two-level ITT. All ITT entries are allocated in one go, unlike
+ * with the device table. Span may be used to limit the second level table
+ * size, where possible.
+ */
+static int gicv5_its_create_itt_two_level(struct gicv5_its_chip_data *its,
+					  struct gicv5_its_dev *its_dev,
+					  unsigned int event_id_bits,
+					  unsigned int itt_l2sz,
+					  unsigned int num_events)
+{
+	unsigned int l1_bits, l2_bits, span, events_per_l2_table;
+	unsigned int i, complete_tables, final_span, num_ents;
+	__le64 *itt_l1, *itt_l2, **l2ptrs;
+	int ret;
+	u64 val;
+
+	ret = gicv5_its_l2sz_to_l2_bits(itt_l2sz);
+	if (ret >= event_id_bits) {
+		pr_debug("Incorrect l2sz (0x%x) for %u EventID bits. Cannot allocate ITT\n",
+			 itt_l2sz, event_id_bits);
+		return -EINVAL;
+	}
+
+	l2_bits = ret;
+
+	l1_bits = event_id_bits - l2_bits;
+
+	num_ents = BIT(l1_bits);
+
+	itt_l1 = kcalloc(num_ents, sizeof(*itt_l1), GFP_KERNEL);
+	if (!itt_l1)
+		return -ENOMEM;
+
+	l2ptrs = kcalloc(num_ents, sizeof(*l2ptrs), GFP_KERNEL);
+	if (!l2ptrs) {
+		kfree(itt_l1);
+		return -ENOMEM;
+	}
+
+	its_dev->itt_cfg.l2.l2ptrs = l2ptrs;
+
+	its_dev->itt_cfg.l2.l2sz = itt_l2sz;
+	its_dev->itt_cfg.l2.l1itt = itt_l1;
+	its_dev->itt_cfg.l2.num_l1_ents = num_ents;
+	its_dev->itt_cfg.l2itt = true;
+	its_dev->itt_cfg.event_id_bits = event_id_bits;
+
+	/*
+	 * Need to determine how many entries there are per L2 - this is based
+	 * on the number of bits in the table.
+	 */
+	events_per_l2_table = BIT(l2_bits);
+	complete_tables = num_events / events_per_l2_table;
+	final_span = order_base_2(num_events % events_per_l2_table);
+
+	for (i = 0; i < num_ents; i++) {
+		size_t l2sz;
+
+		span = i == complete_tables ? final_span : l2_bits;
+
+		itt_l2 = kcalloc(BIT(span), sizeof(*itt_l2), GFP_KERNEL);
+		if (!itt_l2) {
+			ret = -ENOMEM;
+			goto out_free;
+		}
+
+		its_dev->itt_cfg.l2.l2ptrs[i] = itt_l2;
+
+		l2sz = BIT(span) * sizeof(*itt_l2);
+
+		gicv5_its_dcache_clean(its, itt_l2, l2sz);
+
+		val = (virt_to_phys(itt_l2) & GICV5_ITTL1E_L2_ADDR_MASK) |
+		       FIELD_PREP(GICV5_ITTL1E_SPAN, span)		 |
+		       FIELD_PREP(GICV5_ITTL1E_VALID, 0x1);
+
+		WRITE_ONCE(itt_l1[i], cpu_to_le64(val));
+	}
+
+	gicv5_its_dcache_clean(its, itt_l1, num_ents * sizeof(*itt_l1));
+
+	return 0;
+
+out_free:
+	for (i = i - 1; i >= 0; i--)
+		kfree(its_dev->itt_cfg.l2.l2ptrs[i]);
+
+	kfree(its_dev->itt_cfg.l2.l2ptrs);
+	kfree(itt_l1);
+	return ret;
+}
+
+/*
+ * Function to check whether the device table or ITT table support
+ * a two-level table and if so depending on the number of id_bits
+ * requested, determine whether a two-level table is required.
+ *
+ * Return the 2-level size value if a two level table is deemed
+ * necessary.
+ */
+static bool gicv5_its_l2sz_two_level(bool devtab, u32 its_idr1, u8 id_bits, u8 *sz)
+{
+	unsigned int l2_bits, l2_sz;
+
+	if (devtab && !FIELD_GET(GICV5_ITS_IDR1_DT_LEVELS, its_idr1))
+		return false;
+
+	if (!devtab && !FIELD_GET(GICV5_ITS_IDR1_ITT_LEVELS, its_idr1))
+		return false;
+
+	/*
+	 * Pick an L2 size that matches the pagesize; if a match
+	 * is not found, go for the smallest supported l2 size granule.
+	 *
+	 * This ensures that we will always be able to allocate
+	 * contiguous memory at L2.
+	 */
+	switch (PAGE_SIZE) {
+	case SZ_64K:
+		if (GICV5_ITS_IDR1_L2SZ_SUPPORT_64KB(its_idr1)) {
+			l2_sz = GICV5_ITS_DT_ITT_CFGR_L2SZ_64k;
+			break;
+		}
+		fallthrough;
+	case SZ_4K:
+		if (GICV5_ITS_IDR1_L2SZ_SUPPORT_4KB(its_idr1)) {
+			l2_sz = GICV5_ITS_DT_ITT_CFGR_L2SZ_4k;
+			break;
+		}
+		fallthrough;
+	case SZ_16K:
+		if (GICV5_ITS_IDR1_L2SZ_SUPPORT_16KB(its_idr1)) {
+			l2_sz = GICV5_ITS_DT_ITT_CFGR_L2SZ_16k;
+			break;
+		}
+		if (GICV5_ITS_IDR1_L2SZ_SUPPORT_4KB(its_idr1)) {
+			l2_sz = GICV5_ITS_DT_ITT_CFGR_L2SZ_4k;
+			break;
+		}
+		if (GICV5_ITS_IDR1_L2SZ_SUPPORT_64KB(its_idr1)) {
+			l2_sz = GICV5_ITS_DT_ITT_CFGR_L2SZ_64k;
+			break;
+		}
+
+		l2_sz = GICV5_ITS_DT_ITT_CFGR_L2SZ_4k;
+		break;
+	}
+
+	l2_bits = gicv5_its_l2sz_to_l2_bits(l2_sz);
+
+	if (l2_bits > id_bits)
+		return false;
+
+	*sz = l2_sz;
+
+	return true;
+}
+
+static __le64 *gicv5_its_device_get_itte_ref(struct gicv5_its_dev *its_dev,
+					     u16 event_id)
+{
+	unsigned int l1_idx, l2_idx, l2_bits;
+	__le64 *l2_itt;
+
+	if (!its_dev->itt_cfg.l2itt) {
+		__le64 *itt = its_dev->itt_cfg.linear.itt;
+
+		return &itt[event_id];
+	}
+
+	l2_bits = gicv5_its_l2sz_to_l2_bits(its_dev->itt_cfg.l2.l2sz);
+	l1_idx = event_id >> l2_bits;
+	l2_idx = event_id & GENMASK(l2_bits - 1, 0);
+	l2_itt = its_dev->itt_cfg.l2.l2ptrs[l1_idx];
+
+	return &l2_itt[l2_idx];
+}
+
+static int gicv5_its_device_cache_inv(struct gicv5_its_chip_data *its,
+				      struct gicv5_its_dev *its_dev)
+{
+	u32 devicer;
+	u64 didr;
+
+	didr = FIELD_PREP(GICV5_ITS_DIDR_DEVICEID, its_dev->device_id);
+	devicer = FIELD_PREP(GICV5_ITS_INV_DEVICER_I, 0x1)	|
+		  FIELD_PREP(GICV5_ITS_INV_DEVICER_EVENTID_BITS,
+			     its_dev->itt_cfg.event_id_bits)	|
+		  FIELD_PREP(GICV5_ITS_INV_DEVICER_L1, 0x0);
+	its_writeq_relaxed(its, didr, GICV5_ITS_DIDR);
+	its_writel_relaxed(its, devicer, GICV5_ITS_INV_DEVICER);
+
+	return gicv5_its_cache_sync(its);
+}
+
+/*
+ * Allocate a level 2 device table entry, update L1 parent to reference it.
+ * Only used for 2-level device tables, and it is called on demand.
+ */
+static int gicv5_its_alloc_l2_devtab(struct gicv5_its_chip_data *its,
+				     unsigned int l1_index)
+{
+	__le64 *l2devtab, *l1devtab = its->devtab_cfgr.l2.l1devtab;
+	u8 span, l2sz, l2_bits;
+	u64 l1dte;
+
+	if (FIELD_GET(GICV5_DTL1E_VALID, le64_to_cpu(l1devtab[l1_index])))
+		return 0;
+
+	span = FIELD_GET(GICV5_DTL1E_SPAN, le64_to_cpu(l1devtab[l1_index]));
+	l2sz = devtab_cfgr_field(its, L2SZ);
+
+	l2_bits = gicv5_its_l2sz_to_l2_bits(l2sz);
+
+	/*
+	 * Span allows us to create a smaller L2 device table.
+	 * If it is too large, use the number of allowed L2 bits.
+	 */
+	if (span > l2_bits)
+		span = l2_bits;
+
+	l2devtab = kcalloc(BIT(span), sizeof(*l2devtab), GFP_KERNEL);
+	if (!l2devtab)
+		return -ENOMEM;
+
+	its->devtab_cfgr.l2.l2ptrs[l1_index] = l2devtab;
+
+	l1dte = FIELD_PREP(GICV5_DTL1E_SPAN, span)			|
+		(virt_to_phys(l2devtab) & GICV5_DTL1E_L2_ADDR_MASK)	|
+		FIELD_PREP(GICV5_DTL1E_VALID, 0x1);
+	its_write_table_entry(its, &l1devtab[l1_index], l1dte);
+
+	return 0;
+}
+
+static __le64 *gicv5_its_devtab_get_dte_ref(struct gicv5_its_chip_data *its,
+					    u32 device_id, bool alloc)
+{
+	u8 str = devtab_cfgr_field(its, STRUCTURE);
+	unsigned int l2sz, l2_bits, l1_idx, l2_idx;
+	__le64 *l2devtab;
+	int ret;
+
+	if (str == GICV5_ITS_DT_ITT_CFGR_STRUCTURE_LINEAR) {
+		l2devtab = its->devtab_cfgr.linear.devtab;
+		return &l2devtab[device_id];
+	}
+
+	l2sz = devtab_cfgr_field(its, L2SZ);
+	l2_bits = gicv5_its_l2sz_to_l2_bits(l2sz);
+	l1_idx = device_id >> l2_bits;
+	l2_idx = device_id & GENMASK(l2_bits - 1, 0);
+
+	if (alloc) {
+		/*
+		 * Allocate a new L2 device table here before
+		 * continuing. We make the assumption that the span in
+		 * the L1 table has been set correctly, and blindly use
+		 * that value.
+		 */
+		ret = gicv5_its_alloc_l2_devtab(its, l1_idx);
+		if (ret)
+			return NULL;
+	}
+
+	l2devtab = its->devtab_cfgr.l2.l2ptrs[l1_idx];
+	return &l2devtab[l2_idx];
+}
+
+/*
+ * Register a new device in the device table. Allocate an ITT and
+ * program the L2DTE entry according to the ITT structure that
+ * was chosen.
+ */
+static int gicv5_its_device_register(struct gicv5_its_chip_data *its,
+				     struct gicv5_its_dev *its_dev)
+{
+	u8 event_id_bits, device_id_bits, itt_struct, itt_l2sz;
+	phys_addr_t itt_phys_base;
+	bool two_level_itt;
+	u32 idr1, idr2;
+	__le64 *dte;
+	u64 val;
+	int ret;
+
+	device_id_bits = devtab_cfgr_field(its, DEVICEID_BITS);
+
+	if (its_dev->device_id >= BIT(device_id_bits)) {
+		pr_err("Supplied DeviceID (%u) outside of Device Table range (%u)!",
+		       its_dev->device_id, (u32)GENMASK(device_id_bits - 1, 0));
+		return -EINVAL;
+	}
+
+	dte = gicv5_its_devtab_get_dte_ref(its, its_dev->device_id, true);
+	if (!dte)
+		return -ENOMEM;
+
+	if (FIELD_GET(GICV5_DTL2E_VALID, le64_to_cpu(*dte)))
+		return -EBUSY;
+
+	/*
+	 * Determine how many bits we need, validate those against the max.
+	 * Based on these, determine if we should go for a 1- or 2-level ITT.
+	 */
+	event_id_bits = order_base_2(its_dev->num_events);
+
+	idr2 = its_readl_relaxed(its, GICV5_ITS_IDR2);
+
+	if (event_id_bits > FIELD_GET(GICV5_ITS_IDR2_EVENTID_BITS, idr2)) {
+		pr_err("Required EventID bits (%u) larger than supported bits (%u)!",
+		       event_id_bits,
+		       (u8)FIELD_GET(GICV5_ITS_IDR2_EVENTID_BITS, idr2));
+		return -EINVAL;
+	}
+
+	idr1 = its_readl_relaxed(its, GICV5_ITS_IDR1);
+
+	/*
+	 * L2 ITT size is programmed into the L2DTE regardless of
+	 * whether a two-level or linear ITT is built, init it.
+	 */
+	itt_l2sz = 0;
+
+	two_level_itt = gicv5_its_l2sz_two_level(false, idr1, event_id_bits,
+						  &itt_l2sz);
+	if (two_level_itt)
+		ret = gicv5_its_create_itt_two_level(its, its_dev, event_id_bits,
+						     itt_l2sz,
+						     its_dev->num_events);
+	else
+		ret = gicv5_its_create_itt_linear(its, its_dev, event_id_bits);
+	if (ret)
+		return ret;
+
+	itt_phys_base = two_level_itt ? virt_to_phys(its_dev->itt_cfg.l2.l1itt) :
+					virt_to_phys(its_dev->itt_cfg.linear.itt);
+
+	itt_struct = two_level_itt ? GICV5_ITS_DT_ITT_CFGR_STRUCTURE_TWO_LEVEL :
+				     GICV5_ITS_DT_ITT_CFGR_STRUCTURE_LINEAR;
+
+	val = FIELD_PREP(GICV5_DTL2E_EVENT_ID_BITS, event_id_bits)	|
+	      FIELD_PREP(GICV5_DTL2E_ITT_STRUCTURE, itt_struct)		|
+	      (itt_phys_base & GICV5_DTL2E_ITT_ADDR_MASK)		|
+	      FIELD_PREP(GICV5_DTL2E_ITT_L2SZ, itt_l2sz)		|
+	      FIELD_PREP(GICV5_DTL2E_VALID, 0x1);
+
+	its_write_table_entry(its, dte, val);
+
+	ret = gicv5_its_device_cache_inv(its, its_dev);
+	if (ret) {
+		its_write_table_entry(its, dte, 0);
+		gicv5_its_free_itt(its_dev);
+		return ret;
+	}
+
+	return 0;
+}
+
+/*
+ * Unregister a device in the device table. Lookup the device by ID, free the
+ * corresponding ITT, mark the device as invalid in the device table.
+ */
+static int gicv5_its_device_unregister(struct gicv5_its_chip_data *its,
+				       struct gicv5_its_dev *its_dev)
+{
+	__le64 *dte;
+
+	dte = gicv5_its_devtab_get_dte_ref(its, its_dev->device_id, false);
+
+	if (!FIELD_GET(GICV5_DTL2E_VALID, le64_to_cpu(*dte))) {
+		pr_debug("Device table entry for DeviceID 0x%x is not valid. Nothing to clean up!",
+			 its_dev->device_id);
+		return -EINVAL;
+	}
+
+	/* Zero everything - make it clear that this is an invalid entry */
+	its_write_table_entry(its, dte, 0);
+
+	gicv5_its_free_itt(its_dev);
+
+	return gicv5_its_device_cache_inv(its, its_dev);
+}
+
+/*
+ * Allocate a 1-level device table. All entries are allocated, but marked
+ * invalid.
+ */
+static int gicv5_its_alloc_devtab_linear(struct gicv5_its_chip_data *its,
+					u8 device_id_bits)
+{
+	__le64 *devtab;
+	size_t sz;
+	u64 baser;
+	u32 cfgr;
+
+	/*
+	 * We expect a GICv5 implementation requiring a large number of
+	 * deviceID bits to support a 2-level device table. If that's not
+	 * the case, cap the number of deviceIDs supported according to the
+	 * kmalloc limits so that the system can chug along with a linear
+	 * device table.
+	 */
+	sz = BIT_ULL(device_id_bits) * sizeof(*devtab);
+	if (sz > KMALLOC_MAX_SIZE) {
+		u8 device_id_cap = ilog2(KMALLOC_MAX_SIZE/sizeof(*devtab));
+
+		pr_warn("Limiting device ID bits from %u to %u\n",
+			device_id_bits, device_id_cap);
+		device_id_bits = device_id_cap;
+	}
+
+	devtab = kcalloc(BIT(device_id_bits), sizeof(*devtab), GFP_KERNEL);
+	if (!devtab)
+		return -ENOMEM;
+
+	gicv5_its_dcache_clean(its, devtab, sz);
+
+	cfgr = FIELD_PREP(GICV5_ITS_DT_CFGR_STRUCTURE,
+			  GICV5_ITS_DT_ITT_CFGR_STRUCTURE_LINEAR)	|
+	       FIELD_PREP(GICV5_ITS_DT_CFGR_L2SZ, 0)			|
+	       FIELD_PREP(GICV5_ITS_DT_CFGR_DEVICEID_BITS, device_id_bits);
+	its_writel_relaxed(its, cfgr, GICV5_ITS_DT_CFGR);
+
+	baser = virt_to_phys(devtab) & GICV5_ITS_DT_BASER_ADDR_MASK;
+	its_writeq_relaxed(its, baser, GICV5_ITS_DT_BASER);
+
+	its->devtab_cfgr.cfgr = cfgr;
+	its->devtab_cfgr.linear.devtab = devtab;
+
+	return 0;
+}
+
+/*
+ * Allocate a 2-level device table. L2 entries are not allocated,
+ * they are allocated on-demand.
+ */
+static int gicv5_its_alloc_devtab_two_level(struct gicv5_its_chip_data *its,
+					    u8 device_id_bits,
+					    u8 devtab_l2sz)
+{
+	unsigned int l1_bits, l2_bits, i;
+	__le64 *l1devtab, **l2ptrs;
+	size_t l1_sz;
+	u64 baser;
+	u32 cfgr;
+
+	l2_bits = gicv5_its_l2sz_to_l2_bits(devtab_l2sz);
+
+	l1_bits = device_id_bits - l2_bits;
+	l1_sz = BIT(l1_bits) * sizeof(*l1devtab);
+	/*
+	 * With 2-level device table support it is highly unlikely
+	 * that we are not able to allocate the required amount of
+	 * device table memory to cover deviceID space; cap the
+	 * deviceID space if we encounter such set-up.
+	 * If this ever becomes a problem we could revisit the policy
+	 * behind level 2 size selection to reduce level-1 deviceID bits.
+	 */
+	if (l1_sz > KMALLOC_MAX_SIZE) {
+		l1_bits = ilog2(KMALLOC_MAX_SIZE/sizeof(*l1devtab));
+
+		pr_warn("Limiting device ID bits from %u to %u\n",
+			device_id_bits, l1_bits + l2_bits);
+		device_id_bits = l1_bits + l2_bits;
+		l1_sz = KMALLOC_MAX_SIZE;
+	}
+
+	l1devtab = kcalloc(BIT(l1_bits), sizeof(*l1devtab), GFP_KERNEL);
+	if (!l1devtab)
+		return -ENOMEM;
+
+	l2ptrs = kcalloc(BIT(l1_bits), sizeof(*l2ptrs), GFP_KERNEL);
+	if (!l2ptrs) {
+		kfree(l1devtab);
+		return -ENOMEM;
+	}
+
+	for (i = 0; i < BIT(l1_bits); i++)
+		l1devtab[i] = cpu_to_le64(FIELD_PREP(GICV5_DTL1E_SPAN, l2_bits));
+
+	gicv5_its_dcache_clean(its, l1devtab, l1_sz);
+
+	cfgr = FIELD_PREP(GICV5_ITS_DT_CFGR_STRUCTURE,
+			  GICV5_ITS_DT_ITT_CFGR_STRUCTURE_TWO_LEVEL)	|
+	       FIELD_PREP(GICV5_ITS_DT_CFGR_L2SZ, devtab_l2sz)		|
+	       FIELD_PREP(GICV5_ITS_DT_CFGR_DEVICEID_BITS, device_id_bits);
+	its_writel_relaxed(its, cfgr, GICV5_ITS_DT_CFGR);
+
+	baser = virt_to_phys(l1devtab) & GICV5_ITS_DT_BASER_ADDR_MASK;
+	its_writeq_relaxed(its, baser, GICV5_ITS_DT_BASER);
+
+	its->devtab_cfgr.cfgr = cfgr;
+	its->devtab_cfgr.l2.l1devtab = l1devtab;
+	its->devtab_cfgr.l2.l2ptrs = l2ptrs;
+
+	return 0;
+}
+
+/*
+ * Initialise the device table as either 1- or 2-level depending on what is
+ * supported by the hardware.
+ */
+static int gicv5_its_init_devtab(struct gicv5_its_chip_data *its)
+{
+	u8 device_id_bits, devtab_l2sz;
+	bool two_level_devtab;
+	u32 idr1;
+
+	idr1 = its_readl_relaxed(its, GICV5_ITS_IDR1);
+
+	device_id_bits = FIELD_GET(GICV5_ITS_IDR1_DEVICEID_BITS, idr1);
+	two_level_devtab = gicv5_its_l2sz_two_level(true, idr1, device_id_bits,
+						    &devtab_l2sz);
+	if (two_level_devtab)
+		return gicv5_its_alloc_devtab_two_level(its, device_id_bits,
+						       devtab_l2sz);
+	else
+		return gicv5_its_alloc_devtab_linear(its, device_id_bits);
+}
+
+static void gicv5_its_deinit_devtab(struct gicv5_its_chip_data *its)
+{
+	u8 str = devtab_cfgr_field(its, STRUCTURE);
+
+	if (str == GICV5_ITS_DT_ITT_CFGR_STRUCTURE_LINEAR) {
+		kfree(its->devtab_cfgr.linear.devtab);
+	} else {
+		kfree(its->devtab_cfgr.l2.l1devtab);
+		kfree(its->devtab_cfgr.l2.l2ptrs);
+	}
+}
+
+static void gicv5_its_compose_msi_msg(struct irq_data *d, struct msi_msg *msg)
+{
+	struct gicv5_its_dev *its_dev = irq_data_get_irq_chip_data(d);
+	u64 addr = its_dev->its_trans_phys_base;
+
+	msg->data = FIELD_GET(GICV5_ITS_HWIRQ_EVENT_ID, d->hwirq);
+	msi_msg_set_addr(irq_data_get_msi_desc(d), msg, addr);
+}
+
+static const struct irq_chip gicv5_its_irq_chip = {
+	.name			= "GICv5-ITS-MSI",
+	.irq_mask		= irq_chip_mask_parent,
+	.irq_unmask		= irq_chip_unmask_parent,
+	.irq_eoi		= irq_chip_eoi_parent,
+	.irq_set_affinity	= irq_chip_set_affinity_parent,
+	.irq_get_irqchip_state	= irq_chip_get_parent_state,
+	.irq_set_irqchip_state	= irq_chip_set_parent_state,
+	.irq_compose_msi_msg	= gicv5_its_compose_msi_msg,
+};
+
+static struct gicv5_its_dev *gicv5_its_find_device(struct gicv5_its_chip_data *its,
+						   u32 device_id)
+{
+	struct gicv5_its_dev *dev = xa_load(&its->its_devices, device_id);
+
+	return dev ? dev : ERR_PTR(-ENODEV);
+}
+
+static struct gicv5_its_dev *gicv5_its_alloc_device(struct gicv5_its_chip_data *its, int nvec,
+						    u32 dev_id)
+{
+	struct gicv5_its_dev *its_dev;
+	void *entry;
+	int ret;
+
+	its_dev = gicv5_its_find_device(its, dev_id);
+	if (!IS_ERR(its_dev)) {
+		pr_err("A device with this DeviceID (0x%x) has already been registered.\n",
+		       dev_id);
+
+		return ERR_PTR(-EBUSY);
+	}
+
+	its_dev = kzalloc(sizeof(*its_dev), GFP_KERNEL);
+	if (!its_dev)
+		return ERR_PTR(-ENOMEM);
+
+	its_dev->device_id = dev_id;
+	its_dev->num_events = nvec;
+
+	ret = gicv5_its_device_register(its, its_dev);
+	if (ret) {
+		pr_err("Failed to register the device\n");
+		goto out_dev_free;
+	}
+
+	gicv5_its_device_cache_inv(its, its_dev);
+
+	its_dev->its_node = its;
+
+	its_dev->event_map = (unsigned long *)bitmap_zalloc(its_dev->num_events, GFP_KERNEL);
+	if (!its_dev->event_map) {
+		ret = -ENOMEM;
+		goto out_unregister;
+	}
+
+	entry = xa_store(&its->its_devices, dev_id, its_dev, GFP_KERNEL);
+	if (xa_is_err(entry)) {
+		ret = xa_err(entry);
+		goto out_bitmap_free;
+	}
+
+	return its_dev;
+
+out_bitmap_free:
+	bitmap_free(its_dev->event_map);
+out_unregister:
+	gicv5_its_device_unregister(its, its_dev);
+out_dev_free:
+	kfree(its_dev);
+	return ERR_PTR(ret);
+}
+
+static int gicv5_its_msi_prepare(struct irq_domain *domain, struct device *dev,
+				 int nvec, msi_alloc_info_t *info)
+{
+	u32 dev_id = info->scratchpad[0].ul;
+	struct msi_domain_info *msi_info;
+	struct gicv5_its_chip_data *its;
+	struct gicv5_its_dev *its_dev;
+
+	msi_info = msi_get_domain_info(domain);
+	its = msi_info->data;
+
+	guard(mutex)(&its->dev_alloc_lock);
+
+	its_dev = gicv5_its_alloc_device(its, nvec, dev_id);
+	if (IS_ERR(its_dev))
+		return PTR_ERR(its_dev);
+
+	its_dev->its_trans_phys_base = info->scratchpad[1].ul;
+	info->scratchpad[0].ptr = its_dev;
+
+	return 0;
+}
+
+static void gicv5_its_msi_teardown(struct irq_domain *domain, msi_alloc_info_t *info)
+{
+	struct gicv5_its_dev *its_dev = info->scratchpad[0].ptr;
+	struct msi_domain_info *msi_info;
+	struct gicv5_its_chip_data *its;
+
+	msi_info = msi_get_domain_info(domain);
+	its = msi_info->data;
+
+	guard(mutex)(&its->dev_alloc_lock);
+
+	if (WARN_ON_ONCE(!bitmap_empty(its_dev->event_map, its_dev->num_events)))
+		return;
+
+	xa_erase(&its->its_devices, its_dev->device_id);
+	bitmap_free(its_dev->event_map);
+	gicv5_its_device_unregister(its, its_dev);
+	kfree(its_dev);
+}
+
+static struct msi_domain_ops gicv5_its_msi_domain_ops = {
+	.msi_prepare	= gicv5_its_msi_prepare,
+	.msi_teardown	= gicv5_its_msi_teardown,
+};
+
+static int gicv5_its_map_event(struct gicv5_its_dev *its_dev, u16 event_id, u32 lpi)
+{
+	struct gicv5_its_chip_data *its = its_dev->its_node;
+	u64 itt_entry;
+	__le64 *itte;
+
+	itte = gicv5_its_device_get_itte_ref(its_dev, event_id);
+
+	if (FIELD_GET(GICV5_ITTL2E_VALID, *itte))
+		return -EEXIST;
+
+	itt_entry = FIELD_PREP(GICV5_ITTL2E_LPI_ID, lpi) |
+		    FIELD_PREP(GICV5_ITTL2E_VALID, 0x1);
+
+	its_write_table_entry(its, itte, itt_entry);
+
+	gicv5_its_itt_cache_inv(its, its_dev->device_id, event_id);
+
+	return 0;
+}
+
+static void gicv5_its_unmap_event(struct gicv5_its_dev *its_dev, u16 event_id)
+{
+	struct gicv5_its_chip_data *its = its_dev->its_node;
+	u64 itte_val;
+	__le64 *itte;
+
+	itte = gicv5_its_device_get_itte_ref(its_dev, event_id);
+
+	itte_val = le64_to_cpu(*itte);
+	itte_val &= ~GICV5_ITTL2E_VALID;
+
+	its_write_table_entry(its, itte, itte_val);
+
+	gicv5_its_itt_cache_inv(its, its_dev->device_id, event_id);
+}
+
+static int gicv5_its_alloc_eventid(struct gicv5_its_dev *its_dev,
+				   unsigned int nr_irqs, u32 *eventid)
+{
+	int ret;
+
+	ret = bitmap_find_free_region(its_dev->event_map,
+				      its_dev->num_events,
+				      get_count_order(nr_irqs));
+
+	if (ret < 0)
+		return ret;
+
+	*eventid = ret;
+
+	return 0;
+}
+
+static void gicv5_its_free_eventid(struct gicv5_its_dev *its_dev, u32 event_id_base,
+				   unsigned int nr_irqs)
+{
+	bitmap_release_region(its_dev->event_map, event_id_base,
+			      get_count_order(nr_irqs));
+}
+
+static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int virq,
+				      unsigned int nr_irqs, void *arg)
+{
+	u32 device_id, event_id_base, lpi;
+	struct gicv5_its_dev *its_dev;
+	msi_alloc_info_t *info = arg;
+	irq_hw_number_t hwirq;
+	struct irq_data *irqd;
+	int ret, i;
+
+	its_dev = info->scratchpad[0].ptr;
+
+	ret = gicv5_its_alloc_eventid(its_dev, nr_irqs, &event_id_base);
+	if (ret)
+		return ret;
+
+	ret = iommu_dma_prepare_msi(info->desc, its_dev->its_trans_phys_base);
+	if (ret)
+		goto out_eventid;
+
+	device_id = its_dev->device_id;
+
+	for (i = 0; i < nr_irqs; i++) {
+		lpi = gicv5_alloc_lpi();
+		if (ret < 0) {
+			pr_debug("Failed to find free LPI!\n");
+			goto out_eventid;
+		}
+
+		ret = irq_domain_alloc_irqs_parent(domain, virq + i, 1, &lpi);
+		if (ret)
+			goto out_free_lpi;
+
+		/*
+		 * Store eventid and deviceid into the hwirq for later use.
+		 *
+		 *	hwirq  = event_id << 32 | device_id
+		 */
+		hwirq = FIELD_PREP(GICV5_ITS_HWIRQ_DEVICE_ID, device_id) |
+			FIELD_PREP(GICV5_ITS_HWIRQ_EVENT_ID, (u64)event_id_base + i);
+		irq_domain_set_info(domain, virq + i, hwirq,
+				    &gicv5_its_irq_chip, its_dev,
+				    handle_fasteoi_irq, NULL, NULL);
+
+		irqd = irq_get_irq_data(virq + i);
+		irqd_set_single_target(irqd);
+		irqd_set_affinity_on_activate(irqd);
+		irqd_set_resend_when_in_progress(irqd);
+	}
+
+	return 0;
+
+out_free_lpi:
+	gicv5_free_lpi(lpi);
+out_eventid:
+	gicv5_its_free_eventid(its_dev, event_id_base, nr_irqs);
+	return ret;
+}
+
+static void gicv5_its_irq_domain_free(struct irq_domain *domain, unsigned int virq,
+				      unsigned int nr_irqs)
+{
+	struct irq_data *d = irq_domain_get_irq_data(domain, virq);
+	struct gicv5_its_chip_data *its;
+	struct gicv5_its_dev *its_dev;
+	u16 event_id_base;
+	unsigned int i;
+
+	its_dev = irq_data_get_irq_chip_data(d);
+	its = its_dev->its_node;
+
+	event_id_base = FIELD_GET(GICV5_ITS_HWIRQ_EVENT_ID, d->hwirq);
+
+	bitmap_release_region(its_dev->event_map, event_id_base,
+			      get_count_order(nr_irqs));
+
+	/*  Hierarchically free irq data */
+	for (i = 0; i < nr_irqs; i++) {
+		d = irq_domain_get_irq_data(domain, virq + i);
+
+		gicv5_free_lpi(d->parent_data->hwirq);
+		irq_domain_reset_irq_data(d);
+		irq_domain_free_irqs_parent(domain, virq + i, 1);
+	}
+
+	gicv5_its_syncr(its, its_dev);
+	gicv5_irs_syncr();
+}
+
+static int gicv5_its_irq_domain_activate(struct irq_domain *domain, struct irq_data *d,
+					 bool reserve)
+{
+	struct gicv5_its_dev *its_dev = irq_data_get_irq_chip_data(d);
+	u16 event_id;
+	u32 lpi;
+
+	event_id = FIELD_GET(GICV5_ITS_HWIRQ_EVENT_ID, d->hwirq);
+	lpi = d->parent_data->hwirq;
+
+	return gicv5_its_map_event(its_dev, event_id, lpi);
+}
+
+static void gicv5_its_irq_domain_deactivate(struct irq_domain *domain,
+					    struct irq_data *d)
+{
+	struct gicv5_its_dev *its_dev = irq_data_get_irq_chip_data(d);
+	u16 event_id;
+
+	event_id = FIELD_GET(GICV5_ITS_HWIRQ_EVENT_ID, d->hwirq);
+
+	gicv5_its_unmap_event(its_dev, event_id);
+}
+
+static const struct irq_domain_ops gicv5_its_irq_domain_ops = {
+	.alloc		= gicv5_its_irq_domain_alloc,
+	.free		= gicv5_its_irq_domain_free,
+	.activate	= gicv5_its_irq_domain_activate,
+	.deactivate	= gicv5_its_irq_domain_deactivate,
+	.select		= msi_lib_irq_domain_select,
+};
+
+static int gicv5_its_write_cr0(struct gicv5_its_chip_data *its, bool enable)
+{
+	u32 cr0 = FIELD_PREP(GICV5_ITS_CR0_ITSEN, enable);
+
+	its_writel_relaxed(its, cr0, GICV5_ITS_CR0);
+	return gicv5_wait_for_op_atomic(its->its_base, GICV5_ITS_CR0,
+					GICV5_ITS_CR0_IDLE, NULL);
+}
+
+static int gicv5_its_enable(struct gicv5_its_chip_data *its)
+{
+	return gicv5_its_write_cr0(its, true);
+}
+
+static int gicv5_its_disable(struct gicv5_its_chip_data *its)
+{
+	return gicv5_its_write_cr0(its, false);
+}
+
+static void gicv5_its_print_info(struct gicv5_its_chip_data *its_node)
+{
+	bool devtab_linear;
+	u8 device_id_bits;
+	u8 str;
+
+	device_id_bits = devtab_cfgr_field(its_node, DEVICEID_BITS);
+
+	str = devtab_cfgr_field(its_node, STRUCTURE);
+	devtab_linear = (str == GICV5_ITS_DT_ITT_CFGR_STRUCTURE_LINEAR);
+
+	pr_info("ITS %s enabled using %s device table device_id_bits %u\n",
+		fwnode_get_name(its_node->fwnode),
+		devtab_linear ? "linear" : "2-level",
+		device_id_bits);
+}
+
+static int gicv5_its_init_domain(struct gicv5_its_chip_data *its, struct irq_domain *parent)
+{
+	struct irq_domain_info dom_info = {
+		.fwnode		= its->fwnode,
+		.ops		= &gicv5_its_irq_domain_ops,
+		.domain_flags	= its->msi_domain_flags,
+		.parent		= parent,
+	};
+	struct msi_domain_info *info;
+
+	info = kzalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return -ENOMEM;
+
+	info->ops = &gicv5_its_msi_domain_ops;
+	info->data = its;
+	dom_info.host_data = info;
+
+	if (!msi_create_parent_irq_domain(&dom_info, &gic_v5_its_msi_parent_ops)) {
+		kfree(info);
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int __init gicv5_its_init_bases(void __iomem *its_base, struct fwnode_handle *handle,
+				       struct irq_domain *parent_domain)
+{
+	struct device_node *np = to_of_node(handle);
+	struct gicv5_its_chip_data *its_node;
+	u32 cr0, cr1;
+	bool enabled;
+	int ret;
+
+	its_node = kzalloc(sizeof(*its_node), GFP_KERNEL);
+	if (!its_node)
+		return -ENOMEM;
+
+	mutex_init(&its_node->dev_alloc_lock);
+	xa_init(&its_node->its_devices);
+	its_node->fwnode = handle;
+	its_node->its_base = its_base;
+	its_node->msi_domain_flags = IRQ_DOMAIN_FLAG_ISOLATED_MSI |
+				     IRQ_DOMAIN_FLAG_FWNODE_PARENT;
+
+	cr0 = its_readl_relaxed(its_node, GICV5_ITS_CR0);
+	enabled = FIELD_GET(GICV5_ITS_CR0_ITSEN, cr0);
+	if (WARN(enabled, "ITS %s enabled, disabling it before proceeding\n", np->full_name)) {
+		ret = gicv5_its_disable(its_node);
+		if (ret)
+			goto out_free_node;
+	}
+
+	if (of_property_read_bool(np, "dma-noncoherent")) {
+		/*
+		 * A non-coherent ITS implies that some cache levels cannot be
+		 * used coherently by the cores and GIC. Our only option is to mark
+		 * memory attributes for the GIC as non-cacheable; by default,
+		 * non-cacheable memory attributes imply outer-shareable
+		 * shareability, the value written into ITS_CR1_SH is ignored.
+		 */
+		cr1 = FIELD_PREP(GICV5_ITS_CR1_ITT_RA, GICV5_NO_READ_ALLOC)	|
+		      FIELD_PREP(GICV5_ITS_CR1_DT_RA, GICV5_NO_READ_ALLOC)	|
+		      FIELD_PREP(GICV5_ITS_CR1_IC, GICV5_NON_CACHE)		|
+		      FIELD_PREP(GICV5_ITS_CR1_OC, GICV5_NON_CACHE);
+		its_node->flags |= ITS_FLAGS_NON_COHERENT;
+	} else {
+		cr1 = FIELD_PREP(GICV5_ITS_CR1_ITT_RA, GICV5_READ_ALLOC)	|
+		      FIELD_PREP(GICV5_ITS_CR1_DT_RA, GICV5_READ_ALLOC)		|
+		      FIELD_PREP(GICV5_ITS_CR1_IC, GICV5_WB_CACHE)		|
+		      FIELD_PREP(GICV5_ITS_CR1_OC, GICV5_WB_CACHE)		|
+		      FIELD_PREP(GICV5_ITS_CR1_SH, GICV5_INNER_SHARE);
+	}
+
+	its_writel_relaxed(its_node, cr1, GICV5_ITS_CR1);
+
+	ret = gicv5_its_init_devtab(its_node);
+	if (ret)
+		goto out_free_node;
+
+	ret = gicv5_its_enable(its_node);
+	if (ret)
+		goto out_free_devtab;
+
+	ret = gicv5_its_init_domain(its_node, parent_domain);
+	if (ret)
+		goto out_disable_its;
+
+	gicv5_its_print_info(its_node);
+
+	return 0;
+
+out_disable_its:
+	gicv5_its_disable(its_node);
+out_free_devtab:
+	gicv5_its_deinit_devtab(its_node);
+out_free_node:
+	kfree(its_node);
+	return ret;
+}
+
+static int __init gicv5_its_init(struct device_node *node)
+{
+	void __iomem *its_base;
+	int ret, idx;
+
+	idx = of_property_match_string(node, "reg-names", "ns-config");
+	if (idx < 0) {
+		pr_err("%pOF: ns-config reg-name not present\n", node);
+		return -ENODEV;
+	}
+
+	its_base = of_io_request_and_map(node, idx, of_node_full_name(node));
+	if (IS_ERR(its_base)) {
+		pr_err("%pOF: unable to map GICv5 ITS_CONFIG_FRAME\n", node);
+		return PTR_ERR(its_base);
+	}
+
+	ret = gicv5_its_init_bases(its_base, of_fwnode_handle(node),
+				   gicv5_global_data.lpi_domain);
+	if (ret)
+		goto out_unmap;
+
+	return 0;
+
+out_unmap:
+	iounmap(its_base);
+	return ret;
+}
+
+void __init gicv5_its_of_probe(struct device_node *parent)
+{
+	struct device_node *np;
+
+	for_each_available_child_of_node(parent, np) {
+		if (!of_device_is_compatible(np, "arm,gic-v5-its"))
+			continue;
+
+		if (gicv5_its_init(np))
+			pr_err("Failed to init ITS %s\n", np->full_name);
+	}
+}
diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c
index 97ff935d79bd..a9e3e75adb96 100644
--- a/drivers/irqchip/irq-gic-v5.c
+++ b/drivers/irqchip/irq-gic-v5.c
@@ -1071,6 +1071,8 @@ static int __init gicv5_of_init(struct device_node *node, struct device_node *pa
 
 	gicv5_smp_init();
 
+	gicv5_irs_its_probe();
+
 	return 0;
 
 out_int:
diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h
index 680eed794a35..07b952549bfa 100644
--- a/include/linux/irqchip/arm-gic-v5.h
+++ b/include/linux/irqchip/arm-gic-v5.h
@@ -50,6 +50,8 @@
 #define GICV5_IRS_IDR7			0x001c
 #define GICV5_IRS_CR0			0x0080
 #define GICV5_IRS_CR1			0x0084
+#define GICV5_IRS_SYNCR			0x00c0
+#define GICV5_IRS_SYNC_STATUSR		0x00c4
 #define GICV5_IRS_SPI_SELR		0x0108
 #define GICV5_IRS_SPI_CFGR		0x0114
 #define GICV5_IRS_SPI_STATUSR		0x0118
@@ -103,6 +105,10 @@
 #define GICV5_IRS_CR1_OC		GENMASK(3, 2)
 #define GICV5_IRS_CR1_SH		GENMASK(1, 0)
 
+#define GICV5_IRS_SYNCR_SYNC		BIT(31)
+
+#define GICV5_IRS_SYNC_STATUSR_IDLE	BIT(0)
+
 #define GICV5_IRS_SPI_STATUSR_V		BIT(1)
 #define GICV5_IRS_SPI_STATUSR_IDLE	BIT(0)
 
@@ -144,6 +150,104 @@
 
 #define GICV5_ISTL1E_L2_ADDR_MASK	GENMASK_ULL(55, 12)
 
+/*
+ * ITS registers and tables structures
+ */
+#define GICV5_ITS_IDR1		0x0004
+#define GICV5_ITS_IDR2		0x0008
+#define GICV5_ITS_CR0		0x0080
+#define GICV5_ITS_CR1		0x0084
+#define GICV5_ITS_DT_BASER	0x00c0
+#define GICV5_ITS_DT_CFGR	0x00d0
+#define GICV5_ITS_DIDR		0x0100
+#define GICV5_ITS_EIDR		0x0108
+#define GICV5_ITS_INV_EVENTR	0x010c
+#define GICV5_ITS_INV_DEVICER	0x0110
+#define GICV5_ITS_STATUSR	0x0120
+#define GICV5_ITS_SYNCR		0x0140
+#define GICV5_ITS_SYNC_STATUSR	0x0148
+
+#define GICV5_ITS_IDR1_L2SZ			GENMASK(10, 8)
+#define GICV5_ITS_IDR1_ITT_LEVELS		BIT(7)
+#define GICV5_ITS_IDR1_DT_LEVELS		BIT(6)
+#define GICV5_ITS_IDR1_DEVICEID_BITS		GENMASK(5, 0)
+
+#define GICV5_ITS_IDR1_L2SZ_SUPPORT_4KB(r)	FIELD_GET(BIT(8), (r))
+#define GICV5_ITS_IDR1_L2SZ_SUPPORT_16KB(r)	FIELD_GET(BIT(9), (r))
+#define GICV5_ITS_IDR1_L2SZ_SUPPORT_64KB(r)	FIELD_GET(BIT(10), (r))
+
+#define GICV5_ITS_IDR2_XDMN_EVENTs		GENMASK(6, 5)
+#define GICV5_ITS_IDR2_EVENTID_BITS		GENMASK(4, 0)
+
+#define GICV5_ITS_CR0_IDLE			BIT(1)
+#define GICV5_ITS_CR0_ITSEN			BIT(0)
+
+#define GICV5_ITS_CR1_ITT_RA			BIT(7)
+#define GICV5_ITS_CR1_DT_RA			BIT(6)
+#define GICV5_ITS_CR1_IC			GENMASK(5, 4)
+#define GICV5_ITS_CR1_OC			GENMASK(3, 2)
+#define GICV5_ITS_CR1_SH			GENMASK(1, 0)
+
+#define GICV5_ITS_DT_CFGR_STRUCTURE		BIT(16)
+#define GICV5_ITS_DT_CFGR_L2SZ			GENMASK(7, 6)
+#define GICV5_ITS_DT_CFGR_DEVICEID_BITS		GENMASK(5, 0)
+
+#define GICV5_ITS_DT_BASER_ADDR_MASK		GENMASK_ULL(55, 3)
+
+#define GICV5_ITS_INV_DEVICER_I			BIT(31)
+#define GICV5_ITS_INV_DEVICER_EVENTID_BITS	GENMASK(5, 1)
+#define GICV5_ITS_INV_DEVICER_L1		BIT(0)
+
+#define GICV5_ITS_DIDR_DEVICEID			GENMASK_ULL(31, 0)
+
+#define GICV5_ITS_EIDR_EVENTID			GENMASK(15, 0)
+
+#define GICV5_ITS_INV_EVENTR_I			BIT(31)
+#define GICV5_ITS_INV_EVENTR_ITT_L2SZ		GENMASK(2, 1)
+#define GICV5_ITS_INV_EVENTR_L1			BIT(0)
+
+#define GICV5_ITS_STATUSR_IDLE			BIT(0)
+
+#define GICV5_ITS_SYNCR_SYNC			BIT_ULL(63)
+#define GICV5_ITS_SYNCR_SYNCALL			BIT_ULL(32)
+#define GICV5_ITS_SYNCR_DEVICEID		GENMASK_ULL(31, 0)
+
+#define GICV5_ITS_SYNC_STATUSR_IDLE		BIT(0)
+
+#define GICV5_DTL1E_VALID			BIT_ULL(0)
+/* Note that there is no shift for the address by design */
+#define GICV5_DTL1E_L2_ADDR_MASK		GENMASK_ULL(55, 3)
+#define GICV5_DTL1E_SPAN			GENMASK_ULL(63, 60)
+
+#define GICV5_DTL2E_VALID			BIT_ULL(0)
+#define GICV5_DTL2E_ITT_L2SZ			GENMASK_ULL(2, 1)
+/* Note that there is no shift for the address by design */
+#define GICV5_DTL2E_ITT_ADDR_MASK		GENMASK_ULL(55, 3)
+#define GICV5_DTL2E_ITT_DSWE			BIT_ULL(57)
+#define GICV5_DTL2E_ITT_STRUCTURE		BIT_ULL(58)
+#define GICV5_DTL2E_EVENT_ID_BITS		GENMASK_ULL(63, 59)
+
+#define GICV5_ITTL1E_VALID			BIT_ULL(0)
+/* Note that there is no shift for the address by design */
+#define GICV5_ITTL1E_L2_ADDR_MASK		GENMASK_ULL(55, 3)
+#define GICV5_ITTL1E_SPAN			GENMASK_ULL(63, 60)
+
+#define GICV5_ITTL2E_LPI_ID			GENMASK_ULL(23, 0)
+#define GICV5_ITTL2E_DAC			GENMASK_ULL(29, 28)
+#define GICV5_ITTL2E_VIRTUAL			BIT_ULL(30)
+#define GICV5_ITTL2E_VALID			BIT_ULL(31)
+#define GICV5_ITTL2E_VM_ID			GENMASK_ULL(47, 32)
+
+#define GICV5_ITS_DT_ITT_CFGR_L2SZ_4k		0b00
+#define GICV5_ITS_DT_ITT_CFGR_L2SZ_16k		0b01
+#define GICV5_ITS_DT_ITT_CFGR_L2SZ_64k		0b10
+
+#define GICV5_ITS_DT_ITT_CFGR_STRUCTURE_LINEAR		0
+#define GICV5_ITS_DT_ITT_CFGR_STRUCTURE_TWO_LEVEL	1
+
+#define GICV5_ITS_HWIRQ_DEVICE_ID		GENMASK_ULL(31, 0)
+#define GICV5_ITS_HWIRQ_EVENT_ID		GENMASK_ULL(63, 32)
+
 /*
  * Global Data structures and functions
  */
@@ -197,24 +301,77 @@ static inline int gicv5_wait_for_op_s_atomic(void __iomem *addr, u32 offset,
 	return 0;
 }
 
+static inline int gicv5_wait_for_op_s(void __iomem *addr, u32 offset,
+				      const char *reg_s, u32 mask)
+{
+	void __iomem *reg = addr + offset;
+	u32 val;
+	int ret;
+
+	ret = readl_poll_timeout(reg, val, val & mask, 1, 10 * USEC_PER_MSEC);
+	if (unlikely(ret == -ETIMEDOUT)) {
+		pr_err_ratelimited("%s timeout...\n", reg_s);
+		return ret;
+	}
+
+	return 0;
+}
+
 #define gicv5_wait_for_op_atomic(base, reg, mask, val) \
 	gicv5_wait_for_op_s_atomic(base, reg, #reg, mask, val)
 
+#define gicv5_wait_for_op(base, reg, mask) \
+	gicv5_wait_for_op_s(base, reg, #reg, mask)
+
 void __init gicv5_init_lpi_domain(void);
 void __init gicv5_free_lpi_domain(void);
 
 int gicv5_irs_of_probe(struct device_node *parent);
 void gicv5_irs_remove(void);
 int gicv5_irs_enable(void);
+void gicv5_irs_its_probe(void);
 int gicv5_irs_register_cpu(int cpuid);
 int gicv5_irs_cpu_to_iaffid(int cpu_id, u16 *iaffid);
 struct gicv5_irs_chip_data *gicv5_irs_lookup_by_spi_id(u32 spi_id);
 int gicv5_spi_irq_set_type(struct irq_data *d, unsigned int type);
 int gicv5_irs_iste_alloc(u32 lpi);
+void gicv5_irs_syncr(void);
+
+struct gicv5_its_devtab_cfg {
+	union {
+		struct {
+			__le64	*devtab;
+		} linear;
+		struct {
+			__le64	*l1devtab;
+			__le64	**l2ptrs;
+		} l2;
+	};
+	u32	cfgr;
+};
+
+struct gicv5_its_itt_cfg {
+	union {
+		struct {
+			__le64		*itt;
+			unsigned int	num_ents;
+		} linear;
+		struct {
+			__le64		*l1itt;
+			__le64		**l2ptrs;
+			unsigned int	num_l1_ents;
+			u8		l2sz;
+		} l2;
+	};
+	u8	event_id_bits;
+	bool	l2itt;
+};
 
 void gicv5_init_lpis(u32 max);
 void gicv5_deinit_lpis(void);
 
 int gicv5_alloc_lpi(void);
 void gicv5_free_lpi(u32 lpi);
+
+void __init gicv5_its_of_probe(struct device_node *parent);
 #endif
-- 
cgit v1.2.3


From 695949d8b16f11f2f172d8d0c7ccc1ae09ed6cb7 Mon Sep 17 00:00:00 2001
From: Lorenzo Pieralisi <lpieralisi@kernel.org>
Date: Thu, 3 Jul 2025 12:25:19 +0200
Subject: irqchip/gic-v5: Add GICv5 IWB support

The GICv5 architecture implements the Interrupt Wire Bridge (IWB) in
order to support wired interrupts that cannot be connected directly
to an IRS and instead uses the ITS to translate a wire event into
an IRQ signal.

Add the wired-to-MSI IWB driver to manage IWB wired interrupts.

An IWB is connected to an ITS and it has its own deviceID for all
interrupt wires that it manages; the IWB input wire number must be
exposed to the ITS as an eventID with a 1:1 mapping.

This eventID is not programmable and therefore requires a new
msi_alloc_info_t flag to make sure the ITS driver does not allocate
an eventid for the wire but rather it uses the msi_alloc_info_t.hwirq
number to gather the ITS eventID.

Co-developed-by: Sascha Bischoff <sascha.bischoff@arm.com>
Signed-off-by: Sascha Bischoff <sascha.bischoff@arm.com>
Co-developed-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/r/20250703-gicv5-host-v7-29-12e71f1b3528@kernel.org
Signed-off-by: Marc Zyngier <maz@kernel.org>
---
 drivers/irqchip/Makefile           |   3 +-
 drivers/irqchip/irq-gic-v5-its.c   |  40 ++++--
 drivers/irqchip/irq-gic-v5-iwb.c   | 284 +++++++++++++++++++++++++++++++++++++
 include/asm-generic/msi.h          |   1 +
 include/linux/irqchip/arm-gic-v5.h |  17 +++
 5 files changed, 335 insertions(+), 10 deletions(-)
 create mode 100644 drivers/irqchip/irq-gic-v5-iwb.c

(limited to 'include/linux')

diff --git a/drivers/irqchip/Makefile b/drivers/irqchip/Makefile
index 5459f66e597f..e83dad932ac0 100644
--- a/drivers/irqchip/Makefile
+++ b/drivers/irqchip/Makefile
@@ -37,7 +37,8 @@ obj-$(CONFIG_ARM_GIC_ITS_PARENT)	+= irq-gic-its-msi-parent.o
 obj-$(CONFIG_ARM_GIC_V3_ITS)		+= irq-gic-v3-its.o irq-gic-v4.o
 obj-$(CONFIG_ARM_GIC_V3_ITS_FSL_MC)	+= irq-gic-v3-its-fsl-mc-msi.o
 obj-$(CONFIG_PARTITION_PERCPU)		+= irq-partition-percpu.o
-obj-$(CONFIG_ARM_GIC_V5)		+= irq-gic-v5.o irq-gic-v5-irs.o irq-gic-v5-its.o
+obj-$(CONFIG_ARM_GIC_V5)		+= irq-gic-v5.o irq-gic-v5-irs.o irq-gic-v5-its.o \
+					   irq-gic-v5-iwb.o
 obj-$(CONFIG_HISILICON_IRQ_MBIGEN)	+= irq-mbigen.o
 obj-$(CONFIG_ARM_NVIC)			+= irq-nvic.o
 obj-$(CONFIG_ARM_VIC)			+= irq-vic.o
diff --git a/drivers/irqchip/irq-gic-v5-its.c b/drivers/irqchip/irq-gic-v5-its.c
index 700df6d0687e..340640fdbdf6 100644
--- a/drivers/irqchip/irq-gic-v5-its.c
+++ b/drivers/irqchip/irq-gic-v5-its.c
@@ -880,19 +880,41 @@ static void gicv5_its_unmap_event(struct gicv5_its_dev *its_dev, u16 event_id)
 	gicv5_its_itt_cache_inv(its, its_dev->device_id, event_id);
 }
 
-static int gicv5_its_alloc_eventid(struct gicv5_its_dev *its_dev,
+static int gicv5_its_alloc_eventid(struct gicv5_its_dev *its_dev, msi_alloc_info_t *info,
 				   unsigned int nr_irqs, u32 *eventid)
 {
-	int ret;
+	int event_id_base;
+
+	if (!(info->flags & MSI_ALLOC_FLAGS_FIXED_MSG_DATA)) {
+		event_id_base = bitmap_find_free_region(its_dev->event_map,
+							its_dev->num_events,
+							get_count_order(nr_irqs));
+		if (event_id_base < 0)
+			return event_id_base;
+	} else {
+		/*
+		 * We want to have a fixed EventID mapped for hardcoded
+		 * message data allocations.
+		 */
+		if (WARN_ON_ONCE(nr_irqs != 1))
+			return -EINVAL;
 
-	ret = bitmap_find_free_region(its_dev->event_map,
-				      its_dev->num_events,
-				      get_count_order(nr_irqs));
+		event_id_base = info->hwirq;
 
-	if (ret < 0)
-		return ret;
+		if (event_id_base >= its_dev->num_events) {
+			pr_err("EventID ouside of ITT range; cannot allocate an ITT entry!\n");
+
+			return -EINVAL;
+		}
+
+		if (test_and_set_bit(event_id_base, its_dev->event_map)) {
+			pr_warn("Can't reserve event_id bitmap\n");
+			return -EINVAL;
+
+		}
+	}
 
-	*eventid = ret;
+	*eventid = event_id_base;
 
 	return 0;
 }
@@ -916,7 +938,7 @@ static int gicv5_its_irq_domain_alloc(struct irq_domain *domain, unsigned int vi
 
 	its_dev = info->scratchpad[0].ptr;
 
-	ret = gicv5_its_alloc_eventid(its_dev, nr_irqs, &event_id_base);
+	ret = gicv5_its_alloc_eventid(its_dev, info, nr_irqs, &event_id_base);
 	if (ret)
 		return ret;
 
diff --git a/drivers/irqchip/irq-gic-v5-iwb.c b/drivers/irqchip/irq-gic-v5-iwb.c
new file mode 100644
index 000000000000..ed72fbdd4900
--- /dev/null
+++ b/drivers/irqchip/irq-gic-v5-iwb.c
@@ -0,0 +1,284 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2024-2025 ARM Limited, All Rights Reserved.
+ */
+#define pr_fmt(fmt)	"GICv5 IWB: " fmt
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/msi.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_platform.h>
+
+#include <linux/irqchip.h>
+#include <linux/irqchip/arm-gic-v5.h>
+
+struct gicv5_iwb_chip_data {
+	void __iomem	*iwb_base;
+	u16		nr_regs;
+};
+
+static u32 iwb_readl_relaxed(struct gicv5_iwb_chip_data *iwb_node, const u32 reg_offset)
+{
+	return readl_relaxed(iwb_node->iwb_base + reg_offset);
+}
+
+static void iwb_writel_relaxed(struct gicv5_iwb_chip_data *iwb_node, const u32 val,
+			       const u32 reg_offset)
+{
+	writel_relaxed(val, iwb_node->iwb_base + reg_offset);
+}
+
+static int gicv5_iwb_wait_for_wenabler(struct gicv5_iwb_chip_data *iwb_node)
+{
+	return gicv5_wait_for_op_atomic(iwb_node->iwb_base, GICV5_IWB_WENABLE_STATUSR,
+					GICV5_IWB_WENABLE_STATUSR_IDLE, NULL);
+}
+
+static int __gicv5_iwb_set_wire_enable(struct gicv5_iwb_chip_data *iwb_node,
+				       u32 iwb_wire, bool enable)
+{
+	u32 n = iwb_wire / 32;
+	u8 i = iwb_wire % 32;
+	u32 val;
+
+	if (n >= iwb_node->nr_regs) {
+		pr_err("IWB_WENABLER<n> is invalid for n=%u\n", n);
+		return -EINVAL;
+	}
+
+	/*
+	 * Enable IWB wire/pin at this point
+	 * Note: This is not the same as enabling the interrupt
+	 */
+	val = iwb_readl_relaxed(iwb_node, GICV5_IWB_WENABLER + (4 * n));
+	if (enable)
+		val |= BIT(i);
+	else
+		val &= ~BIT(i);
+	iwb_writel_relaxed(iwb_node, val, GICV5_IWB_WENABLER + (4 * n));
+
+	return gicv5_iwb_wait_for_wenabler(iwb_node);
+}
+
+static int gicv5_iwb_enable_wire(struct gicv5_iwb_chip_data *iwb_node,
+				 u32 iwb_wire)
+{
+	return __gicv5_iwb_set_wire_enable(iwb_node, iwb_wire, true);
+}
+
+static int gicv5_iwb_disable_wire(struct gicv5_iwb_chip_data *iwb_node,
+				  u32 iwb_wire)
+{
+	return __gicv5_iwb_set_wire_enable(iwb_node, iwb_wire, false);
+}
+
+static void gicv5_iwb_irq_disable(struct irq_data *d)
+{
+	struct gicv5_iwb_chip_data *iwb_node = irq_data_get_irq_chip_data(d);
+
+	gicv5_iwb_disable_wire(iwb_node, d->hwirq);
+	irq_chip_disable_parent(d);
+}
+
+static void gicv5_iwb_irq_enable(struct irq_data *d)
+{
+	struct gicv5_iwb_chip_data *iwb_node = irq_data_get_irq_chip_data(d);
+
+	gicv5_iwb_enable_wire(iwb_node, d->hwirq);
+	irq_chip_enable_parent(d);
+}
+
+static int gicv5_iwb_set_type(struct irq_data *d, unsigned int type)
+{
+	struct gicv5_iwb_chip_data *iwb_node = irq_data_get_irq_chip_data(d);
+	u32 iwb_wire, n, wtmr;
+	u8 i;
+
+	iwb_wire = d->hwirq;
+	i = iwb_wire % 32;
+	n = iwb_wire / 32;
+
+	if (n >= iwb_node->nr_regs) {
+		pr_err_once("reg %u out of range\n", n);
+		return -EINVAL;
+	}
+
+	wtmr = iwb_readl_relaxed(iwb_node, GICV5_IWB_WTMR + (4 * n));
+
+	switch (type) {
+	case IRQ_TYPE_LEVEL_HIGH:
+	case IRQ_TYPE_LEVEL_LOW:
+		wtmr |= BIT(i);
+		break;
+	case IRQ_TYPE_EDGE_RISING:
+	case IRQ_TYPE_EDGE_FALLING:
+		wtmr &= ~BIT(i);
+		break;
+	default:
+		pr_debug("unexpected wire trigger mode");
+		return -EINVAL;
+	}
+
+	iwb_writel_relaxed(iwb_node, wtmr, GICV5_IWB_WTMR + (4 * n));
+
+	return 0;
+}
+
+static void gicv5_iwb_domain_set_desc(msi_alloc_info_t *alloc_info, struct msi_desc *desc)
+{
+	alloc_info->desc = desc;
+	alloc_info->hwirq = (u32)desc->data.icookie.value;
+}
+
+static int gicv5_iwb_irq_domain_translate(struct irq_domain *d, struct irq_fwspec *fwspec,
+					  irq_hw_number_t *hwirq,
+					  unsigned int *type)
+{
+	if (!is_of_node(fwspec->fwnode))
+		return -EINVAL;
+
+	if (fwspec->param_count < 2)
+		return -EINVAL;
+
+	/*
+	 * param[0] is be the wire
+	 * param[1] is the interrupt type
+	 */
+	*hwirq = fwspec->param[0];
+	*type = fwspec->param[1] & IRQ_TYPE_SENSE_MASK;
+
+	return 0;
+}
+
+static void gicv5_iwb_write_msi_msg(struct irq_data *d, struct msi_msg *msg) {}
+
+static const struct msi_domain_template iwb_msi_template = {
+	.chip = {
+		.name			= "GICv5-IWB",
+		.irq_mask		= irq_chip_mask_parent,
+		.irq_unmask		= irq_chip_unmask_parent,
+		.irq_enable		= gicv5_iwb_irq_enable,
+		.irq_disable		= gicv5_iwb_irq_disable,
+		.irq_eoi		= irq_chip_eoi_parent,
+		.irq_set_type		= gicv5_iwb_set_type,
+		.irq_write_msi_msg	= gicv5_iwb_write_msi_msg,
+		.irq_set_affinity	= irq_chip_set_affinity_parent,
+		.irq_get_irqchip_state	= irq_chip_get_parent_state,
+		.irq_set_irqchip_state	= irq_chip_set_parent_state,
+		.flags			= IRQCHIP_SET_TYPE_MASKED |
+					  IRQCHIP_SKIP_SET_WAKE |
+					  IRQCHIP_MASK_ON_SUSPEND,
+	},
+
+	.ops = {
+		.set_desc		= gicv5_iwb_domain_set_desc,
+		.msi_translate		= gicv5_iwb_irq_domain_translate,
+	},
+
+	.info = {
+		.bus_token		= DOMAIN_BUS_WIRED_TO_MSI,
+		.flags			= MSI_FLAG_USE_DEV_FWNODE,
+	},
+
+	.alloc_info = {
+		.flags			= MSI_ALLOC_FLAGS_FIXED_MSG_DATA,
+	},
+};
+
+static bool gicv5_iwb_create_device_domain(struct device *dev, unsigned int size,
+				     struct gicv5_iwb_chip_data *iwb_node)
+{
+	if (WARN_ON_ONCE(!dev->msi.domain))
+		return false;
+
+	return msi_create_device_irq_domain(dev, MSI_DEFAULT_DOMAIN,
+					    &iwb_msi_template, size,
+					    NULL, iwb_node);
+}
+
+static struct gicv5_iwb_chip_data *
+gicv5_iwb_init_bases(void __iomem *iwb_base, struct platform_device *pdev)
+{
+	u32 nr_wires, idr0, cr0;
+	unsigned int n;
+	int ret;
+
+	struct gicv5_iwb_chip_data *iwb_node __free(kfree) = kzalloc(sizeof(*iwb_node),
+								     GFP_KERNEL);
+	if (!iwb_node)
+		return ERR_PTR(-ENOMEM);
+
+	iwb_node->iwb_base = iwb_base;
+
+	idr0 = iwb_readl_relaxed(iwb_node, GICV5_IWB_IDR0);
+	nr_wires = (FIELD_GET(GICV5_IWB_IDR0_IW_RANGE, idr0) + 1) * 32;
+
+	cr0 = iwb_readl_relaxed(iwb_node, GICV5_IWB_CR0);
+	if (!FIELD_GET(GICV5_IWB_CR0_IWBEN, cr0)) {
+		dev_err(&pdev->dev, "IWB must be enabled in firmware\n");
+		return ERR_PTR(-EINVAL);
+	}
+
+	iwb_node->nr_regs = FIELD_GET(GICV5_IWB_IDR0_IW_RANGE, idr0) + 1;
+
+	for (n = 0; n < iwb_node->nr_regs; n++)
+		iwb_writel_relaxed(iwb_node, 0, GICV5_IWB_WENABLER + (sizeof(u32) * n));
+
+	ret = gicv5_iwb_wait_for_wenabler(iwb_node);
+	if (ret)
+		return ERR_PTR(ret);
+
+	if (!gicv5_iwb_create_device_domain(&pdev->dev, nr_wires, iwb_node))
+		return ERR_PTR(-ENOMEM);
+
+	return_ptr(iwb_node);
+}
+
+static int gicv5_iwb_device_probe(struct platform_device *pdev)
+{
+	struct gicv5_iwb_chip_data *iwb_node;
+	void __iomem *iwb_base;
+	struct resource *res;
+	int ret;
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res)
+		return -EINVAL;
+
+	iwb_base = devm_ioremap(&pdev->dev, res->start, resource_size(res));
+	if (!iwb_base) {
+		dev_err(&pdev->dev, "failed to ioremap %pR\n", res);
+		return -ENOMEM;
+	}
+
+	iwb_node = gicv5_iwb_init_bases(iwb_base, pdev);
+	if (IS_ERR(iwb_node)) {
+		ret = PTR_ERR(iwb_node);
+		goto out_unmap;
+	}
+
+	return 0;
+
+out_unmap:
+	iounmap(iwb_base);
+	return ret;
+}
+
+static const struct of_device_id gicv5_iwb_of_match[] = {
+	{ .compatible = "arm,gic-v5-iwb" },
+	{ /* END */ }
+};
+MODULE_DEVICE_TABLE(of, gicv5_iwb_of_match);
+
+static struct platform_driver gicv5_iwb_platform_driver = {
+	.driver = {
+		.name			= "GICv5 IWB",
+		.of_match_table		= gicv5_iwb_of_match,
+		.suppress_bind_attrs	= true,
+	},
+	.probe				= gicv5_iwb_device_probe,
+};
+
+module_platform_driver(gicv5_iwb_platform_driver);
diff --git a/include/asm-generic/msi.h b/include/asm-generic/msi.h
index 124c734ca5d9..92cca4b23f13 100644
--- a/include/asm-generic/msi.h
+++ b/include/asm-generic/msi.h
@@ -33,6 +33,7 @@ typedef struct msi_alloc_info {
 
 /* Device generating MSIs is proxying for another device */
 #define MSI_ALLOC_FLAGS_PROXY_DEVICE	(1UL << 0)
+#define MSI_ALLOC_FLAGS_FIXED_MSG_DATA	(1UL << 1)
 
 #define GENERIC_MSI_DOMAIN_OPS		1
 
diff --git a/include/linux/irqchip/arm-gic-v5.h b/include/linux/irqchip/arm-gic-v5.h
index 07b952549bfa..68ddcdb1cec5 100644
--- a/include/linux/irqchip/arm-gic-v5.h
+++ b/include/linux/irqchip/arm-gic-v5.h
@@ -248,6 +248,23 @@
 #define GICV5_ITS_HWIRQ_DEVICE_ID		GENMASK_ULL(31, 0)
 #define GICV5_ITS_HWIRQ_EVENT_ID		GENMASK_ULL(63, 32)
 
+/*
+ * IWB registers
+ */
+#define GICV5_IWB_IDR0				0x0000
+#define GICV5_IWB_CR0				0x0080
+#define GICV5_IWB_WENABLE_STATUSR		0x00c0
+#define GICV5_IWB_WENABLER			0x2000
+#define GICV5_IWB_WTMR				0x4000
+
+#define GICV5_IWB_IDR0_INT_DOMS			GENMASK(14, 11)
+#define GICV5_IWB_IDR0_IW_RANGE			GENMASK(10, 0)
+
+#define GICV5_IWB_CR0_IDLE			BIT(1)
+#define GICV5_IWB_CR0_IWBEN			BIT(0)
+
+#define GICV5_IWB_WENABLE_STATUSR_IDLE		BIT(0)
+
 /*
  * Global Data structures and functions
  */
-- 
cgit v1.2.3


From 4e655028c29fbc455fdbbd3ca074443361adfa44 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Mon, 7 Jul 2025 11:41:14 -0700
Subject: net: ethtool: remove the compat code for _rxfh_context ops

All drivers are now converted to dedicated _rxfh_context ops.
Remove the use of >set_rxfh() to manage additional contexts.

Reviewed-by: Gal Pressman <gal@nvidia.com>
Reviewed-by: Edward Cree <ecree.xilinx@gmail.com>
Link: https://patch.msgid.link/20250707184115.2285277-5-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/ethtool.h |  4 ---
 net/core/dev.c          | 15 +-----------
 net/ethtool/ioctl.c     | 65 +++++++++++--------------------------------------
 net/ethtool/rss.c       |  3 +--
 4 files changed, 16 insertions(+), 71 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 59877fd2a1d3..de5bd76a400c 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -865,9 +865,6 @@ struct kernel_ethtool_ts_info {
  * @supported_input_xfrm: supported types of input xfrm from %RXH_XFRM_*.
  * @cap_link_lanes_supported: indicates if the driver supports lanes
  *	parameter.
- * @cap_rss_ctx_supported: indicates if the driver supports RSS
- *	contexts via legacy API, drivers implementing @create_rxfh_context
- *	do not have to set this bit.
  * @rxfh_per_ctx_fields: device supports selecting different header fields
  *	for Rx hash calculation and RSS for each additional context.
  * @rxfh_per_ctx_key: device supports setting different RSS key for each
@@ -1100,7 +1097,6 @@ struct kernel_ethtool_ts_info {
 struct ethtool_ops {
 	u32     supported_input_xfrm:8;
 	u32     cap_link_lanes_supported:1;
-	u32     cap_rss_ctx_supported:1;
 	u32	rxfh_per_ctx_fields:1;
 	u32	rxfh_per_ctx_key:1;
 	u32	cap_rss_rxnfc_adds:1;
diff --git a/net/core/dev.c b/net/core/dev.c
index ea129aa08317..fe677ccec5b0 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -11979,21 +11979,8 @@ static void netdev_rss_contexts_free(struct net_device *dev)
 
 	mutex_lock(&dev->ethtool->rss_lock);
 	xa_for_each(&dev->ethtool->rss_ctx, context, ctx) {
-		struct ethtool_rxfh_param rxfh;
-
-		rxfh.indir = ethtool_rxfh_context_indir(ctx);
-		rxfh.key = ethtool_rxfh_context_key(ctx);
-		rxfh.hfunc = ctx->hfunc;
-		rxfh.input_xfrm = ctx->input_xfrm;
-		rxfh.rss_context = context;
-		rxfh.rss_delete = true;
-
 		xa_erase(&dev->ethtool->rss_ctx, context);
-		if (dev->ethtool_ops->create_rxfh_context)
-			dev->ethtool_ops->remove_rxfh_context(dev, ctx,
-							      context, NULL);
-		else
-			dev->ethtool_ops->set_rxfh(dev, &rxfh, NULL);
+		dev->ethtool_ops->remove_rxfh_context(dev, ctx, context, NULL);
 		kfree(ctx);
 	}
 	xa_destroy(&dev->ethtool->rss_ctx);
diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
index b6d96e562c9a..d8a17350d3e8 100644
--- a/net/ethtool/ioctl.c
+++ b/net/ethtool/ioctl.c
@@ -1391,8 +1391,7 @@ static noinline_for_stack int ethtool_get_rxfh(struct net_device *dev,
 	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
-	if (rxfh.rss_context && !(ops->cap_rss_ctx_supported ||
-				  ops->create_rxfh_context))
+	if (rxfh.rss_context && !ops->create_rxfh_context)
 		return -EOPNOTSUPP;
 
 	rxfh.indir_size = rxfh_dev.indir_size;
@@ -1534,8 +1533,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	if (rxfh.rsvd8[0] || rxfh.rsvd8[1] || rxfh.rsvd32)
 		return -EINVAL;
 	/* Most drivers don't handle rss_context, check it's 0 as well */
-	if (rxfh.rss_context && !(ops->cap_rss_ctx_supported ||
-				  ops->create_rxfh_context))
+	if (rxfh.rss_context && !ops->create_rxfh_context)
 		return -EOPNOTSUPP;
 	/* Check input data transformation capabilities */
 	if (rxfh.input_xfrm && rxfh.input_xfrm != RXH_XFRM_SYM_XOR &&
@@ -1634,6 +1632,8 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	}
 
 	if (create) {
+		u32 limit, ctx_id;
+
 		if (rxfh_dev.rss_delete) {
 			ret = -EINVAL;
 			goto out_unlock;
@@ -1644,21 +1644,15 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 			goto out_unlock;
 		}
 
-		if (ops->create_rxfh_context) {
-			u32 limit = ops->rxfh_max_num_contexts ?: U32_MAX;
-			u32 ctx_id;
-
-			/* driver uses new API, core allocates ID */
-			ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx,
-				       XA_LIMIT(1, limit - 1),
-				       GFP_KERNEL_ACCOUNT);
-			if (ret < 0) {
-				kfree(ctx);
-				goto out_unlock;
-			}
-			WARN_ON(!ctx_id); /* can't happen */
-			rxfh.rss_context = ctx_id;
+		limit = ops->rxfh_max_num_contexts ?: U32_MAX;
+		ret = xa_alloc(&dev->ethtool->rss_ctx, &ctx_id, ctx,
+			       XA_LIMIT(1, limit - 1), GFP_KERNEL_ACCOUNT);
+		if (ret < 0) {
+			kfree(ctx);
+			goto out_unlock;
 		}
+		WARN_ON(!ctx_id); /* can't happen */
+		rxfh.rss_context = ctx_id;
 	} else if (rxfh.rss_context) {
 		ctx = xa_load(&dev->ethtool->rss_ctx, rxfh.rss_context);
 		if (!ctx) {
@@ -1670,7 +1664,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	rxfh_dev.rss_context = rxfh.rss_context;
 	rxfh_dev.input_xfrm = rxfh.input_xfrm;
 
-	if (rxfh.rss_context && ops->create_rxfh_context) {
+	if (rxfh.rss_context) {
 		if (create) {
 			ret = ops->create_rxfh_context(dev, ctx, &rxfh_dev,
 						       extack);
@@ -1693,8 +1687,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 	if (ret) {
 		if (create) {
 			/* failed to create, free our new tracking entry */
-			if (ops->create_rxfh_context)
-				xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context);
+			xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context);
 			kfree(ctx);
 		}
 		goto out_unlock;
@@ -1713,36 +1706,6 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
 			dev->priv_flags |= IFF_RXFH_CONFIGURED;
 	}
 	/* Update rss_ctx tracking */
-	if (create && !ops->create_rxfh_context) {
-		/* driver uses old API, it chose context ID */
-		if (WARN_ON(xa_load(&dev->ethtool->rss_ctx, rxfh_dev.rss_context))) {
-			/* context ID reused, our tracking is screwed */
-			kfree(ctx);
-			goto out_unlock;
-		}
-		/* Allocate the exact ID the driver gave us */
-		if (xa_is_err(xa_store(&dev->ethtool->rss_ctx, rxfh_dev.rss_context,
-				       ctx, GFP_KERNEL))) {
-			kfree(ctx);
-			goto out_unlock;
-		}
-
-		/* Fetch the defaults for the old API, in the new API drivers
-		 * should write defaults into ctx themselves.
-		 */
-		rxfh_dev.indir = (u32 *)rss_config;
-		rxfh_dev.indir_size = dev_indir_size;
-
-		rxfh_dev.key = rss_config + indir_bytes;
-		rxfh_dev.key_size = dev_key_size;
-
-		ret = ops->get_rxfh(dev, &rxfh_dev);
-		if (WARN_ON(ret)) {
-			xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context);
-			kfree(ctx);
-			goto out_unlock;
-		}
-	}
 	if (rxfh_dev.rss_delete) {
 		WARN_ON(xa_erase(&dev->ethtool->rss_ctx, rxfh.rss_context) != ctx);
 		kfree(ctx);
diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
index e717f23cbc10..4e8ca2c38175 100644
--- a/net/ethtool/rss.c
+++ b/net/ethtool/rss.c
@@ -163,8 +163,7 @@ rss_prepare_data(const struct ethnl_req_info *req_base,
 		return -EOPNOTSUPP;
 
 	/* Some drivers don't handle rss_context */
-	if (request->rss_context &&
-	    !ops->cap_rss_ctx_supported && !ops->create_rxfh_context)
+	if (request->rss_context && !ops->create_rxfh_context)
 		return -EOPNOTSUPP;
 
 	mutex_lock(&dev->ethtool->rss_lock);
-- 
cgit v1.2.3


From 1ec38ce3d024bebdff2a9ffb526e4d198605204d Mon Sep 17 00:00:00 2001
From: Sascha Bischoff <Sascha.Bischoff@arm.com>
Date: Fri, 27 Jun 2025 10:09:01 +0000
Subject: irqchip/gic-v5: Populate struct gic_kvm_info

Populate the gic_kvm_info struct based on support for
FEAT_GCIE_LEGACY.  The struct is used by KVM to probe for a compatible
GIC.

Co-authored-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Timothy Hayes <timothy.hayes@arm.com>
Signed-off-by: Sascha Bischoff <sascha.bischoff@arm.com>
Reviewed-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Link: https://lore.kernel.org/r/20250627100847.1022515-3-sascha.bischoff@arm.com
Signed-off-by: Oliver Upton <oliver.upton@linux.dev>
---
 drivers/irqchip/irq-gic-v5.c          | 33 +++++++++++++++++++++++++++++++++
 include/linux/irqchip/arm-vgic-info.h |  4 ++++
 2 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/irqchip/irq-gic-v5.c b/drivers/irqchip/irq-gic-v5.c
index 0e4789818131..4bd224f359a7 100644
--- a/drivers/irqchip/irq-gic-v5.c
+++ b/drivers/irqchip/irq-gic-v5.c
@@ -13,6 +13,7 @@
 
 #include <linux/irqchip.h>
 #include <linux/irqchip/arm-gic-v5.h>
+#include <linux/irqchip/arm-vgic-info.h>
 
 #include <asm/cpufeature.h>
 #include <asm/exception.h>
@@ -1058,6 +1059,36 @@ static void gicv5_set_cpuif_idbits(void)
 	}
 }
 
+#ifdef CONFIG_KVM
+static struct gic_kvm_info gic_v5_kvm_info __initdata;
+
+static bool __init gicv5_cpuif_has_gcie_legacy(void)
+{
+	u64 idr0 = read_sysreg_s(SYS_ICC_IDR0_EL1);
+	return !!FIELD_GET(ICC_IDR0_EL1_GCIE_LEGACY, idr0);
+}
+
+static void __init gic_of_setup_kvm_info(struct device_node *node)
+{
+	gic_v5_kvm_info.type = GIC_V5;
+	gic_v5_kvm_info.has_gcie_v3_compat = gicv5_cpuif_has_gcie_legacy();
+
+	/* GIC Virtual CPU interface maintenance interrupt */
+	gic_v5_kvm_info.no_maint_irq_mask = false;
+	gic_v5_kvm_info.maint_irq = irq_of_parse_and_map(node, 0);
+	if (!gic_v5_kvm_info.maint_irq) {
+		pr_warn("cannot find GICv5 virtual CPU interface maintenance interrupt\n");
+		return;
+	}
+
+	vgic_set_kvm_info(&gic_v5_kvm_info);
+}
+#else
+static inline void __init gic_of_setup_kvm_info(struct device_node *node)
+{
+}
+#endif // CONFIG_KVM
+
 static int __init gicv5_of_init(struct device_node *node, struct device_node *parent)
 {
 	int ret = gicv5_irs_of_probe(node);
@@ -1090,6 +1121,8 @@ static int __init gicv5_of_init(struct device_node *node, struct device_node *pa
 
 	gicv5_irs_its_probe();
 
+	gic_of_setup_kvm_info(node);
+
 	return 0;
 
 out_int:
diff --git a/include/linux/irqchip/arm-vgic-info.h b/include/linux/irqchip/arm-vgic-info.h
index a75b2c7de69d..ca1713fac6e3 100644
--- a/include/linux/irqchip/arm-vgic-info.h
+++ b/include/linux/irqchip/arm-vgic-info.h
@@ -15,6 +15,8 @@ enum gic_type {
 	GIC_V2,
 	/* Full GICv3, optionally with v2 compat */
 	GIC_V3,
+	/* Full GICv5, optionally with v3 compat */
+	GIC_V5,
 };
 
 struct gic_kvm_info {
@@ -34,6 +36,8 @@ struct gic_kvm_info {
 	bool		has_v4_1;
 	/* Deactivation impared, subpar stuff */
 	bool		no_hw_deactivation;
+	/* v3 compat support (GICv5 hosts, only) */
+	bool		has_gcie_v3_compat;
 };
 
 #ifdef CONFIG_KVM
-- 
cgit v1.2.3


From c56f97c5c71f17d781461d44acb777cd21521b81 Mon Sep 17 00:00:00 2001
From: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
Date: Thu, 19 Jun 2025 14:26:23 -0400
Subject: bitmap: generalize node_random()

Generalize node_random() and make it available to general bitmaps and
cpumasks users.

Notice, find_first_bit() is generally faster than find_nth_bit(), and we
employ it when there's a single set bit in the bitmap.

See commit 3e061d924fe9c7b4 ("lib/nodemask: optimize node_random for
nodemask with single NUMA node").

CC: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
---
 include/linux/find.h     |  2 ++
 include/linux/nodemask.h | 18 +++---------------
 lib/find_bit.c           | 24 ++++++++++++++++++++++++
 3 files changed, 29 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/find.h b/include/linux/find.h
index 5a2c267ea7f9..98c61838002c 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -44,6 +44,8 @@ unsigned long _find_next_bit_le(const unsigned long *addr, unsigned
 				long size, unsigned long offset);
 #endif
 
+unsigned long find_random_bit(const unsigned long *addr, unsigned long size);
+
 #ifndef find_next_bit
 /**
  * find_next_bit - find the next set bit in a memory region
diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h
index f08ae71585fa..7ad1f5c7407e 100644
--- a/include/linux/nodemask.h
+++ b/include/linux/nodemask.h
@@ -492,21 +492,9 @@ static __always_inline int num_node_state(enum node_states state)
 static __always_inline int node_random(const nodemask_t *maskp)
 {
 #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1)
-	int w, bit;
-
-	w = nodes_weight(*maskp);
-	switch (w) {
-	case 0:
-		bit = NUMA_NO_NODE;
-		break;
-	case 1:
-		bit = first_node(*maskp);
-		break;
-	default:
-		bit = find_nth_bit(maskp->bits, MAX_NUMNODES, get_random_u32_below(w));
-		break;
-	}
-	return bit;
+	int node = find_random_bit(maskp->bits, MAX_NUMNODES);
+
+	return node < MAX_NUMNODES ? node : NUMA_NO_NODE;
 #else
 	return 0;
 #endif
diff --git a/lib/find_bit.c b/lib/find_bit.c
index 06b6342aa3ae..d4b5a29e3e72 100644
--- a/lib/find_bit.c
+++ b/lib/find_bit.c
@@ -18,6 +18,7 @@
 #include <linux/math.h>
 #include <linux/minmax.h>
 #include <linux/swab.h>
+#include <linux/random.h>
 
 /*
  * Common helper for find_bit() function family
@@ -291,3 +292,26 @@ EXPORT_SYMBOL(_find_next_bit_le);
 #endif
 
 #endif /* __BIG_ENDIAN */
+
+/**
+ * find_random_bit - find a set bit at random position
+ * @addr: The address to base the search on
+ * @size: The bitmap size in bits
+ *
+ * Returns: a position of a random set bit; >= @size otherwise
+ */
+unsigned long find_random_bit(const unsigned long *addr, unsigned long size)
+{
+	int w = bitmap_weight(addr, size);
+
+	switch (w) {
+	case 0:
+		return size;
+	case 1:
+		/* Performance trick for single-bit bitmaps */
+		return find_first_bit(addr, size);
+	default:
+		return find_nth_bit(addr, size, get_random_u32_below(w));
+	}
+}
+EXPORT_SYMBOL(find_random_bit);
-- 
cgit v1.2.3


From 012b1043420c0bc62e52902499de40b66f37fd6a Mon Sep 17 00:00:00 2001
From: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
Date: Thu, 19 Jun 2025 14:26:24 -0400
Subject: cpumask: introduce cpumask_random()

Propagate find_random_bit() to cpumask API.

CC: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: "Yury Norov [NVIDIA]" <yury.norov@gmail.com>
---
 include/linux/cpumask.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 7ae80a7ca81e..39b71b662da3 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -354,6 +354,18 @@ unsigned int cpumask_next_wrap(int n, const struct cpumask *src)
 	return find_next_bit_wrap(cpumask_bits(src), small_cpumask_bits, n + 1);
 }
 
+/**
+ * cpumask_random - get random cpu in *src.
+ * @src: cpumask pointer
+ *
+ * Return: random set bit, or >= nr_cpu_ids if @src is empty.
+ */
+static __always_inline
+unsigned int cpumask_random(const struct cpumask *src)
+{
+	return find_random_bit(cpumask_bits(src), nr_cpu_ids);
+}
+
 /**
  * for_each_cpu - iterate over every cpu in a mask
  * @cpu: the (optionally unsigned) integer iterator
-- 
cgit v1.2.3


From eb1ac9ff6c4a5720b1a1476233be374c5dc44bff Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Wed, 2 Jul 2025 16:01:31 -0700
Subject: ipv6: anycast: Don't hold RTNL for IPV6_JOIN_ANYCAST.

inet6_sk(sk)->ipv6_ac_list is protected by lock_sock().

In ipv6_sock_ac_join(), only __dev_get_by_index(), __dev_get_by_flags(),
and __in6_dev_get() require RTNL.

__dev_get_by_flags() is only used by ipv6_sock_ac_join() and can be
converted to RCU version.

Let's replace RCU version helper and drop RTNL from IPV6_JOIN_ANYCAST.

setsockopt_needs_rtnl() will be removed in the next patch.

Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250702230210.3115355-15-kuni1840@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  4 ++--
 net/core/dev.c            | 38 ++++++++++++++++++--------------------
 net/ipv6/anycast.c        | 22 ++++++++++++++--------
 net/ipv6/ipv6_sockglue.c  |  4 ----
 4 files changed, 34 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5847c20994d3..a80d21a14612 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3332,8 +3332,8 @@ int dev_get_iflink(const struct net_device *dev);
 int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
 int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
 			  struct net_device_path_stack *stack);
-struct net_device *__dev_get_by_flags(struct net *net, unsigned short flags,
-				      unsigned short mask);
+struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,
+					unsigned short mask);
 struct net_device *dev_get_by_name(struct net *net, const char *name);
 struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
 struct net_device *__dev_get_by_name(struct net *net, const char *name);
diff --git a/net/core/dev.c b/net/core/dev.c
index fe677ccec5b0..e365b099484e 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1267,33 +1267,31 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 EXPORT_SYMBOL(dev_getfirstbyhwtype);
 
 /**
- *	__dev_get_by_flags - find any device with given flags
- *	@net: the applicable net namespace
- *	@if_flags: IFF_* values
- *	@mask: bitmask of bits in if_flags to check
+ * dev_get_by_flags_rcu - find any device with given flags
+ * @net: the applicable net namespace
+ * @if_flags: IFF_* values
+ * @mask: bitmask of bits in if_flags to check
  *
- *	Search for any interface with the given flags. Returns NULL if a device
- *	is not found or a pointer to the device. Must be called inside
- *	rtnl_lock(), and result refcount is unchanged.
+ * Search for any interface with the given flags.
+ *
+ * Context: rcu_read_lock() must be held.
+ * Returns: NULL if a device is not found or a pointer to the device.
  */
-
-struct net_device *__dev_get_by_flags(struct net *net, unsigned short if_flags,
-				      unsigned short mask)
+struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
+					unsigned short mask)
 {
-	struct net_device *dev, *ret;
-
-	ASSERT_RTNL();
+	struct net_device *dev;
 
-	ret = NULL;
-	for_each_netdev(net, dev) {
-		if (((dev->flags ^ if_flags) & mask) == 0) {
-			ret = dev;
-			break;
+	for_each_netdev_rcu(net, dev) {
+		if (((READ_ONCE(dev->flags) ^ if_flags) & mask) == 0) {
+			dev_hold(dev);
+			return dev;
 		}
 	}
-	return ret;
+
+	return NULL;
 }
-EXPORT_SYMBOL(__dev_get_by_flags);
+EXPORT_IPV6_MOD(dev_get_by_flags_rcu);
 
 /**
  *	dev_valid_name - check if name is okay for network device
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index fd3d104c6c05..53cf68e0242b 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -73,15 +73,13 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	struct inet6_dev *idev;
 	int err = 0, ishost;
 
-	ASSERT_RTNL();
-
 	if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
 		return -EPERM;
 	if (ipv6_addr_is_multicast(addr))
 		return -EINVAL;
 
 	if (ifindex)
-		dev = __dev_get_by_index(net, ifindex);
+		dev = dev_get_by_index(net, ifindex);
 
 	if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE)) {
 		err = -EINVAL;
@@ -102,18 +100,22 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	if (ifindex == 0) {
 		struct rt6_info *rt;
 
+		rcu_read_lock();
 		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
 		if (rt) {
-			dev = rt->dst.dev;
+			dev = dst_dev(&rt->dst);
+			dev_hold(dev);
 			ip6_rt_put(rt);
 		} else if (ishost) {
+			rcu_read_unlock();
 			err = -EADDRNOTAVAIL;
 			goto error;
 		} else {
 			/* router, no matching interface: just pick one */
-			dev = __dev_get_by_flags(net, IFF_UP,
-						 IFF_UP | IFF_LOOPBACK);
+			dev = dev_get_by_flags_rcu(net, IFF_UP,
+						   IFF_UP | IFF_LOOPBACK);
 		}
+		rcu_read_unlock();
 	}
 
 	if (!dev) {
@@ -121,7 +123,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		goto error;
 	}
 
-	idev = __in6_dev_get(dev);
+	idev = in6_dev_get(dev);
 	if (!idev) {
 		if (ifindex)
 			err = -ENODEV;
@@ -144,7 +146,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		if (ishost)
 			err = -EADDRNOTAVAIL;
 		if (err)
-			goto error;
+			goto error_idev;
 	}
 
 	err = __ipv6_dev_ac_inc(idev, addr);
@@ -154,7 +156,11 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		pac = NULL;
 	}
 
+error_idev:
+	in6_dev_put(idev);
 error:
+	dev_put(dev);
+
 	if (pac)
 		sock_kfree_s(sk, pac, sizeof(*pac));
 	return err;
diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c
index 3d891aa6e7f5..702dc33e50ad 100644
--- a/net/ipv6/ipv6_sockglue.c
+++ b/net/ipv6/ipv6_sockglue.c
@@ -119,10 +119,6 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk,
 
 static bool setsockopt_needs_rtnl(int optname)
 {
-	switch (optname) {
-	case IPV6_JOIN_ANYCAST:
-		return true;
-	}
 	return false;
 }
 
-- 
cgit v1.2.3


From afebe192ebfef7f6e0be0a070325995771bcd7e8 Mon Sep 17 00:00:00 2001
From: Benjamin Berg <benjamin.berg@intel.com>
Date: Mon, 9 Jun 2025 21:35:21 +0300
Subject: wifi: cfg80211: only verify part of Extended MLD Capabilities

We verify that the Extended MLD Capabilities are matching between links.
However, some bits are reserved and in particular the Recommended Max
Links subfield may not necessarily match. So only verify the known
subfields that can reliably be expected to be the same. More information
can be found in Table 9-417o, in IEEE P802.11be/D7.0.

Signed-off-by: Benjamin Berg <benjamin.berg@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250609213231.a2fad48dd3e6.Iae1740cd2ac833bc4a64fd2af718e1485158fd42@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h |  9 ++++++++-
 net/wireless/mlme.c       | 21 +++++++++++++++++++--
 2 files changed, 27 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index 120de474a8bf..e05219a912f9 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -9,7 +9,7 @@
  * Copyright (c) 2006, Michael Wu <flamingice@sourmilk.net>
  * Copyright (c) 2013 - 2014 Intel Mobile Communications GmbH
  * Copyright (c) 2016 - 2017 Intel Deutschland GmbH
- * Copyright (c) 2018 - 2024 Intel Corporation
+ * Copyright (c) 2018 - 2025 Intel Corporation
  */
 
 #ifndef LINUX_IEEE80211_H
@@ -5333,6 +5333,13 @@ static inline u16 ieee80211_mle_get_mld_capa_op(const u8 *data)
 	return get_unaligned_le16(common);
 }
 
+/* Defined in Figure 9-1074t in P802.11be_D7.0 */
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_PARAM_UPDATE           0x0001
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_RECO_MAX_LINKS_MASK    0x001e
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_NSTR_UPDATE               0x0020
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_EMLSR_ENA_ON_ONE_LINK     0x0040
+#define IEEE80211_EHT_ML_EXT_MLD_CAPA_BTM_MLD_RECO_MULTI_AP     0x0080
+
 /**
  * ieee80211_mle_get_ext_mld_capa_op - returns the extended MLD capabilities
  *	and operations.
diff --git a/net/wireless/mlme.c b/net/wireless/mlme.c
index 29e1ce8aff42..bb5bc6ff09d4 100644
--- a/net/wireless/mlme.c
+++ b/net/wireless/mlme.c
@@ -352,8 +352,25 @@ cfg80211_mlme_check_mlo_compat(const struct ieee80211_multi_link_elem *mle_a,
 		return -EINVAL;
 	}
 
-	if (ieee80211_mle_get_ext_mld_capa_op((const u8 *)mle_a) !=
-	    ieee80211_mle_get_ext_mld_capa_op((const u8 *)mle_b)) {
+	/*
+	 * Only verify the values in Extended MLD Capabilities that are
+	 * not reserved when transmitted by an AP (and expected to remain the
+	 * same over time).
+	 * The Recommended Max Simultaneous Links subfield in particular is
+	 * reserved when included in a unicast Probe Response frame and may
+	 * also change when the AP adds/removes links. The BTM MLD
+	 * Recommendation For Multiple APs Support subfield is reserved when
+	 * transmitted by an AP. All other bits are currently reserved.
+	 * See IEEE P802.11be/D7.0, Table 9-417o.
+	 */
+	if ((ieee80211_mle_get_ext_mld_capa_op((const u8 *)mle_a) &
+	     (IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_PARAM_UPDATE |
+	      IEEE80211_EHT_ML_EXT_MLD_CAPA_NSTR_UPDATE |
+	      IEEE80211_EHT_ML_EXT_MLD_CAPA_EMLSR_ENA_ON_ONE_LINK)) !=
+	    (ieee80211_mle_get_ext_mld_capa_op((const u8 *)mle_b) &
+	     (IEEE80211_EHT_ML_EXT_MLD_CAPA_OP_PARAM_UPDATE |
+	      IEEE80211_EHT_ML_EXT_MLD_CAPA_NSTR_UPDATE |
+	      IEEE80211_EHT_ML_EXT_MLD_CAPA_EMLSR_ENA_ON_ONE_LINK))) {
 		NL_SET_ERR_MSG(extack,
 			       "extended link MLD capabilities/ops mismatch");
 		return -EINVAL;
-- 
cgit v1.2.3


From a11ec0dc920b2a23da9d88063b5f15d7eada6128 Mon Sep 17 00:00:00 2001
From: Somashekhar Puttagangaiah <somashekhar.puttagangaiah@intel.com>
Date: Mon, 9 Jun 2025 21:35:26 +0300
Subject: wifi: cfg80211/mac80211: implement dot11ExtendedRegInfoSupport

Implement dot11ExtendedRegInfoSupport to advertise non-AP station
regulatory power capability as part of regulatory connectivity
element in (Re)Association request frames so that AP can achieve
maximum client connectivity. Control field which was interpreted
using value of 3-bits B5 to B3, now uses value of 4-bits B6 to B3 to
interpret the type of AP. Hence update IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO
to parse 4-bits control field. If older AP still updates only 3-bits
value of control field, station can still interpret the value as per
section E.2.7 of IEEE 802.11 REVme D7.0 and support the appropriate
AP type.

Also update IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP as the value of
standard power AP is changed to 8 instead of 4 so that AP can support both
LPI AP and SP AP to maximize the connectivity with stations. For backward
compatibility, keeping value 4 as old AP by limiting it to SP AP only.

Signed-off-by: Somashekhar Puttagangaiah <somashekhar.puttagangaiah@intel.com>
Reviewed-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Miri Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20250609213232.90cdef116aad.I85da390fbee59355e3855691933e6a5e55c47ac4@changeid
[fix kernel-doc]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 include/linux/ieee80211.h  | 34 ++++++++++++++++++++++++++++------
 net/mac80211/ieee80211_i.h |  2 ++
 net/mac80211/mlme.c        | 41 +++++++++++++++++++++++++++++++++++++++++
 net/mac80211/util.c        | 17 +++++++++++++++++
 net/wireless/scan.c        |  1 +
 5 files changed, 89 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ieee80211.h b/include/linux/ieee80211.h
index e05219a912f9..ea95c4a60fa6 100644
--- a/include/linux/ieee80211.h
+++ b/include/linux/ieee80211.h
@@ -2837,11 +2837,12 @@ static inline bool ieee80211_he_capa_size_ok(const u8 *data, u8 len)
 #define IEEE80211_HE_OPERATION_PARTIAL_BSS_COLOR		0x40000000
 #define IEEE80211_HE_OPERATION_BSS_COLOR_DISABLED		0x80000000
 
-#define IEEE80211_6GHZ_CTRL_REG_LPI_AP		0
-#define IEEE80211_6GHZ_CTRL_REG_SP_AP		1
-#define IEEE80211_6GHZ_CTRL_REG_VLP_AP		2
-#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP	3
-#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP	4
+#define IEEE80211_6GHZ_CTRL_REG_LPI_AP			0
+#define IEEE80211_6GHZ_CTRL_REG_SP_AP			1
+#define IEEE80211_6GHZ_CTRL_REG_VLP_AP			2
+#define IEEE80211_6GHZ_CTRL_REG_INDOOR_LPI_AP		3
+#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD	4
+#define IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP		8
 
 /**
  * struct ieee80211_he_6ghz_oper - HE 6 GHz operation Information field
@@ -2859,13 +2860,31 @@ struct ieee80211_he_6ghz_oper {
 #define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_80MHZ	2
 #define		IEEE80211_HE_6GHZ_OPER_CTRL_CHANWIDTH_160MHZ	3
 #define IEEE80211_HE_6GHZ_OPER_CTRL_DUP_BEACON	0x4
-#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO	0x38
+#define IEEE80211_HE_6GHZ_OPER_CTRL_REG_INFO	0x78
 	u8 control;
 	u8 ccfs0;
 	u8 ccfs1;
 	u8 minrate;
 } __packed;
 
+/**
+ * enum ieee80211_reg_conn_bits - represents Regulatory connectivity field bits.
+ *
+ * This enumeration defines bit flags used to represent regulatory connectivity
+ * field bits.
+ *
+ * @IEEE80211_REG_CONN_LPI_VALID: Indicates whether the LPI bit is valid.
+ * @IEEE80211_REG_CONN_LPI_VALUE: Represents the value of the LPI bit.
+ * @IEEE80211_REG_CONN_SP_VALID: Indicates whether the SP bit is valid.
+ * @IEEE80211_REG_CONN_SP_VALUE: Represents the value of the SP bit.
+ */
+enum ieee80211_reg_conn_bits {
+	IEEE80211_REG_CONN_LPI_VALID = BIT(0),
+	IEEE80211_REG_CONN_LPI_VALUE = BIT(1),
+	IEEE80211_REG_CONN_SP_VALID = BIT(2),
+	IEEE80211_REG_CONN_SP_VALUE = BIT(3),
+};
+
 /* transmit power interpretation type of transmit power envelope element */
 enum ieee80211_tx_power_intrpt_type {
 	IEEE80211_TPE_LOCAL_EIRP,
@@ -3847,6 +3866,7 @@ enum ieee80211_eid_ext {
 	WLAN_EID_EXT_FILS_PUBLIC_KEY = 12,
 	WLAN_EID_EXT_FILS_NONCE = 13,
 	WLAN_EID_EXT_FUTURE_CHAN_GUIDANCE = 14,
+	WLAN_EID_EXT_DH_PARAMETER = 32,
 	WLAN_EID_EXT_HE_CAPABILITY = 35,
 	WLAN_EID_EXT_HE_OPERATION = 36,
 	WLAN_EID_EXT_UORA = 37,
@@ -3870,6 +3890,8 @@ enum ieee80211_eid_ext {
 	WLAN_EID_EXT_EHT_CAPABILITY = 108,
 	WLAN_EID_EXT_TID_TO_LINK_MAPPING = 109,
 	WLAN_EID_EXT_BANDWIDTH_INDICATION = 135,
+	WLAN_EID_EXT_KNOWN_STA_IDENTIFCATION = 136,
+	WLAN_EID_EXT_NON_AP_STA_REG_CON = 137,
 };
 
 /* Action category code */
diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h
index 4ef7b3656aca..ec68204fddc9 100644
--- a/net/mac80211/ieee80211_i.h
+++ b/net/mac80211/ieee80211_i.h
@@ -2642,6 +2642,8 @@ int ieee80211_put_eht_cap(struct sk_buff *skb,
 			  struct ieee80211_sub_if_data *sdata,
 			  const struct ieee80211_supported_band *sband,
 			  const struct ieee80211_conn_settings *conn);
+int ieee80211_put_reg_conn(struct sk_buff *skb,
+			   enum ieee80211_channel_flags flags);
 
 /* channel management */
 bool ieee80211_chandef_ht_oper(const struct ieee80211_ht_operation *ht_oper,
diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
index 1bedd8d6e891..aaff7e9c3eb7 100644
--- a/net/mac80211/mlme.c
+++ b/net/mac80211/mlme.c
@@ -1641,6 +1641,30 @@ static size_t ieee80211_add_before_he_elems(struct sk_buff *skb,
 	return noffset;
 }
 
+static size_t ieee80211_add_before_reg_conn(struct sk_buff *skb,
+					    const u8 *elems, size_t elems_len,
+					    size_t offset)
+{
+	static const u8 before_reg_conn[] = {
+		/*
+		 * no need to list the ones split off before HE
+		 * or generated here
+		 */
+		WLAN_EID_EXTENSION, WLAN_EID_EXT_DH_PARAMETER,
+		WLAN_EID_EXTENSION, WLAN_EID_EXT_KNOWN_STA_IDENTIFCATION,
+	};
+	size_t noffset;
+
+	if (!elems_len)
+		return offset;
+
+	noffset = ieee80211_ie_split(elems, elems_len, before_reg_conn,
+				     ARRAY_SIZE(before_reg_conn), offset);
+	skb_put_data(skb, elems + offset, noffset - offset);
+
+	return noffset;
+}
+
 #define PRESENT_ELEMS_MAX	8
 #define PRESENT_ELEM_EXT_OFFS	0x100
 
@@ -1801,6 +1825,22 @@ ieee80211_add_link_elems(struct ieee80211_sub_if_data *sdata,
 		ieee80211_put_he_6ghz_cap(skb, sdata, smps_mode);
 	}
 
+	/*
+	 * if present, add any custom IEs that go before regulatory
+	 * connectivity element
+	 */
+	offset = ieee80211_add_before_reg_conn(skb, extra_elems,
+					       extra_elems_len, offset);
+
+	if (sband->band == NL80211_BAND_6GHZ) {
+		/*
+		 * as per Section E.2.7 of IEEE 802.11 REVme D7.0, non-AP STA
+		 * capable of operating on the 6 GHz band shall transmit
+		 * regulatory connectivity element.
+		 */
+		ieee80211_put_reg_conn(skb, chan->flags);
+	}
+
 	/*
 	 * careful - need to know about all the present elems before
 	 * calling ieee80211_assoc_add_ml_elem(), so add this one if
@@ -5931,6 +5971,7 @@ ieee80211_ap_power_type(u8 control)
 		return IEEE80211_REG_LPI_AP;
 	case IEEE80211_6GHZ_CTRL_REG_SP_AP:
 	case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP:
+	case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD:
 		return IEEE80211_REG_SP_AP;
 	case IEEE80211_6GHZ_CTRL_REG_VLP_AP:
 		return IEEE80211_REG_VLP_AP;
diff --git a/net/mac80211/util.c b/net/mac80211/util.c
index ff6c5d5e631d..a1cb63222b6d 100644
--- a/net/mac80211/util.c
+++ b/net/mac80211/util.c
@@ -2556,6 +2556,23 @@ end:
 	return 0;
 }
 
+int ieee80211_put_reg_conn(struct sk_buff *skb,
+			   enum ieee80211_channel_flags flags)
+{
+	u8 reg_conn = IEEE80211_REG_CONN_LPI_VALID |
+		      IEEE80211_REG_CONN_LPI_VALUE |
+		      IEEE80211_REG_CONN_SP_VALID;
+
+	if (!(flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT))
+		reg_conn |= IEEE80211_REG_CONN_SP_VALUE;
+
+	skb_put_u8(skb, WLAN_EID_EXTENSION);
+	skb_put_u8(skb, 1 + sizeof(reg_conn));
+	skb_put_u8(skb, WLAN_EID_EXT_NON_AP_STA_REG_CON);
+	skb_put_u8(skb, reg_conn);
+	return 0;
+}
+
 int ieee80211_put_he_6ghz_cap(struct sk_buff *skb,
 			      struct ieee80211_sub_if_data *sdata,
 			      enum ieee80211_smps_mode smps_mode)
diff --git a/net/wireless/scan.c b/net/wireless/scan.c
index b963ca5c606e..a8339ed52404 100644
--- a/net/wireless/scan.c
+++ b/net/wireless/scan.c
@@ -2231,6 +2231,7 @@ cfg80211_get_6ghz_power_type(const u8 *elems, size_t elems_len)
 		return IEEE80211_REG_LPI_AP;
 	case IEEE80211_6GHZ_CTRL_REG_SP_AP:
 	case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP:
+	case IEEE80211_6GHZ_CTRL_REG_INDOOR_SP_AP_OLD:
 		return IEEE80211_REG_SP_AP;
 	case IEEE80211_6GHZ_CTRL_REG_VLP_AP:
 		return IEEE80211_REG_VLP_AP;
-- 
cgit v1.2.3


From 488e6eaab88cfa4b6fd2e2bb72fac9cfdc8c403b Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Fri, 4 Jul 2025 17:57:49 +0800
Subject: usb: core: add dma-noncoherent buffer alloc and free API

This will add usb_alloc_noncoherent() and usb_free_noncoherent()
functions to support alloc and free buffer in a dma-noncoherent way.

To explicit manage the memory ownership for the kernel and device,
this will also add usb_dma_noncoherent_sync_for_cpu/device() functions
and call it at proper time.  The management requires the user save
sg_table returned by usb_alloc_noncoherent() to urb->sgt.

Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Reviewed-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://lore.kernel.org/r/20250704095751.73765-2-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/usb/core/hcd.c | 29 +++++++++++++-----
 drivers/usb/core/usb.c | 80 ++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/usb.h    | 11 +++++++
 3 files changed, 112 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/usb/core/hcd.c b/drivers/usb/core/hcd.c
index c22de97432a0..03771bbc6c01 100644
--- a/drivers/usb/core/hcd.c
+++ b/drivers/usb/core/hcd.c
@@ -1342,29 +1342,35 @@ void usb_hcd_unmap_urb_for_dma(struct usb_hcd *hcd, struct urb *urb)
 
 	dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 	if (IS_ENABLED(CONFIG_HAS_DMA) &&
-	    (urb->transfer_flags & URB_DMA_MAP_SG))
+	    (urb->transfer_flags & URB_DMA_MAP_SG)) {
 		dma_unmap_sg(hcd->self.sysdev,
 				urb->sg,
 				urb->num_sgs,
 				dir);
-	else if (IS_ENABLED(CONFIG_HAS_DMA) &&
-		 (urb->transfer_flags & URB_DMA_MAP_PAGE))
+	} else if (IS_ENABLED(CONFIG_HAS_DMA) &&
+		 (urb->transfer_flags & URB_DMA_MAP_PAGE)) {
 		dma_unmap_page(hcd->self.sysdev,
 				urb->transfer_dma,
 				urb->transfer_buffer_length,
 				dir);
-	else if (IS_ENABLED(CONFIG_HAS_DMA) &&
-		 (urb->transfer_flags & URB_DMA_MAP_SINGLE))
+	} else if (IS_ENABLED(CONFIG_HAS_DMA) &&
+		 (urb->transfer_flags & URB_DMA_MAP_SINGLE)) {
 		dma_unmap_single(hcd->self.sysdev,
 				urb->transfer_dma,
 				urb->transfer_buffer_length,
 				dir);
-	else if (urb->transfer_flags & URB_MAP_LOCAL)
+	} else if (urb->transfer_flags & URB_MAP_LOCAL) {
 		hcd_free_coherent(urb->dev->bus,
 				&urb->transfer_dma,
 				&urb->transfer_buffer,
 				urb->transfer_buffer_length,
 				dir);
+	} else if ((urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP) && urb->sgt) {
+		dma_sync_sgtable_for_cpu(hcd->self.sysdev, urb->sgt, dir);
+		if (dir == DMA_FROM_DEVICE)
+			invalidate_kernel_vmap_range(urb->transfer_buffer,
+						     urb->transfer_buffer_length);
+	}
 
 	/* Make it safe to call this routine more than once */
 	urb->transfer_flags &= ~(URB_DMA_MAP_SG | URB_DMA_MAP_PAGE |
@@ -1425,8 +1431,15 @@ int usb_hcd_map_urb_for_dma(struct usb_hcd *hcd, struct urb *urb,
 	}
 
 	dir = usb_urb_dir_in(urb) ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
-	if (urb->transfer_buffer_length != 0
-	    && !(urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP)) {
+	if (urb->transfer_flags & URB_NO_TRANSFER_DMA_MAP) {
+		if (!urb->sgt)
+			return 0;
+
+		if (dir == DMA_TO_DEVICE)
+			flush_kernel_vmap_range(urb->transfer_buffer,
+						urb->transfer_buffer_length);
+		dma_sync_sgtable_for_device(hcd->self.sysdev, urb->sgt, dir);
+	} else if (urb->transfer_buffer_length != 0) {
 		if (hcd->localmem_pool) {
 			ret = hcd_alloc_coherent(
 					urb->dev->bus, mem_flags,
diff --git a/drivers/usb/core/usb.c b/drivers/usb/core/usb.c
index 118fa4c93a79..fca7735fc660 100644
--- a/drivers/usb/core/usb.c
+++ b/drivers/usb/core/usb.c
@@ -1030,6 +1030,86 @@ void usb_free_coherent(struct usb_device *dev, size_t size, void *addr,
 }
 EXPORT_SYMBOL_GPL(usb_free_coherent);
 
+/**
+ * usb_alloc_noncoherent - allocate dma-noncoherent buffer for URB_NO_xxx_DMA_MAP
+ * @dev: device the buffer will be used with
+ * @size: requested buffer size
+ * @mem_flags: affect whether allocation may block
+ * @dma: used to return DMA address of buffer
+ * @dir: DMA transfer direction
+ * @table: used to return sg_table of allocated memory
+ *
+ * To explicit manage the memory ownership for the kernel vs the device by
+ * USB core, the user needs save sg_table to urb->sgt. Then USB core will
+ * do DMA sync for CPU and device properly.
+ *
+ * When the buffer is no longer used, free it with usb_free_noncoherent().
+ *
+ * Return: Either null (indicating no buffer could be allocated), or the
+ * cpu-space pointer to a buffer that may be used to perform DMA to the
+ * specified device.  Such cpu-space buffers are returned along with the DMA
+ * address (through the pointer provided).
+ */
+void *usb_alloc_noncoherent(struct usb_device *dev, size_t size,
+			    gfp_t mem_flags, dma_addr_t *dma,
+			    enum dma_data_direction dir,
+			    struct sg_table **table)
+{
+	struct device *dmadev;
+	struct sg_table *sgt;
+	void *buffer;
+
+	if (!dev || !dev->bus)
+		return NULL;
+
+	dmadev = bus_to_hcd(dev->bus)->self.sysdev;
+
+	sgt = dma_alloc_noncontiguous(dmadev, size, dir, mem_flags, 0);
+	if (!sgt)
+		return NULL;
+
+	buffer = dma_vmap_noncontiguous(dmadev, size, sgt);
+	if (!buffer) {
+		dma_free_noncontiguous(dmadev, size, sgt, dir);
+		return NULL;
+	}
+
+	*table = sgt;
+	*dma = sg_dma_address(sgt->sgl);
+
+	return buffer;
+}
+EXPORT_SYMBOL_GPL(usb_alloc_noncoherent);
+
+/**
+ * usb_free_noncoherent - free memory allocated with usb_alloc_noncoherent()
+ * @dev: device the buffer was used with
+ * @size: requested buffer size
+ * @addr: CPU address of buffer
+ * @dir: DMA transfer direction
+ * @table: describe the allocated and DMA mapped memory,
+ *
+ * This reclaims an I/O buffer, letting it be reused.  The memory must have
+ * been allocated using usb_alloc_noncoherent(), and the parameters must match
+ * those provided in that allocation request.
+ */
+void usb_free_noncoherent(struct usb_device *dev, size_t size,
+			  void *addr, enum dma_data_direction dir,
+			  struct sg_table *table)
+{
+	struct device *dmadev;
+
+	if (!dev || !dev->bus)
+		return;
+	if (!addr)
+		return;
+
+	dmadev = bus_to_hcd(dev->bus)->self.sysdev;
+	dma_vunmap_noncontiguous(dmadev, addr);
+	dma_free_noncontiguous(dmadev, size, table, dir);
+}
+EXPORT_SYMBOL_GPL(usb_free_noncoherent);
+
 /*
  * Notifications of device and interface registration
  */
diff --git a/include/linux/usb.h b/include/linux/usb.h
index 68166718ab30..535ac37198a1 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1621,6 +1621,7 @@ struct urb {
 	void *transfer_buffer;		/* (in) associated data buffer */
 	dma_addr_t transfer_dma;	/* (in) dma addr for transfer_buffer */
 	struct scatterlist *sg;		/* (in) scatter gather buffer list */
+	struct sg_table *sgt;		/* (in) scatter gather table for noncoherent buffer */
 	int num_mapped_sgs;		/* (internal) mapped sg entries */
 	int num_sgs;			/* (in) number of entries in the sg list */
 	u32 transfer_buffer_length;	/* (in) data buffer length */
@@ -1826,6 +1827,16 @@ void *usb_alloc_coherent(struct usb_device *dev, size_t size,
 void usb_free_coherent(struct usb_device *dev, size_t size,
 	void *addr, dma_addr_t dma);
 
+enum dma_data_direction;
+
+void *usb_alloc_noncoherent(struct usb_device *dev, size_t size,
+			    gfp_t mem_flags, dma_addr_t *dma,
+			    enum dma_data_direction dir,
+			    struct sg_table **table);
+void usb_free_noncoherent(struct usb_device *dev, size_t size,
+			  void *addr, enum dma_data_direction dir,
+			  struct sg_table *table);
+
 /*-------------------------------------------------------------------*
  *                         SYNCHRONOUS CALL SUPPORT                  *
  *-------------------------------------------------------------------*/
-- 
cgit v1.2.3


From f393a761763c542761abcf978252d431269366d6 Mon Sep 17 00:00:00 2001
From: Gerd Hoffmann <kraxel@redhat.com>
Date: Tue, 8 Jul 2025 14:56:23 +0200
Subject: efi: add ovmf debug log driver

Recent OVMF versions (edk2-stable202508 + newer) can write their debug
log to a memory buffer.  This driver exposes the log content via sysfs
(/sys/firmware/efi/ovmf_debug_log).

Signed-off-by: Gerd Hoffmann <kraxel@redhat.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 drivers/firmware/efi/Kconfig          |   8 +++
 drivers/firmware/efi/Makefile         |   1 +
 drivers/firmware/efi/efi.c            |   8 +++
 drivers/firmware/efi/ovmf-debug-log.c | 111 ++++++++++++++++++++++++++++++++++
 include/linux/efi.h                   |   4 ++
 5 files changed, 132 insertions(+)
 create mode 100644 drivers/firmware/efi/ovmf-debug-log.c

(limited to 'include/linux')

diff --git a/drivers/firmware/efi/Kconfig b/drivers/firmware/efi/Kconfig
index db8c5c03d3a2..eb1bff6968a5 100644
--- a/drivers/firmware/efi/Kconfig
+++ b/drivers/firmware/efi/Kconfig
@@ -263,6 +263,14 @@ config EFI_COCO_SECRET
 	  virt/coco/efi_secret module to access the secrets, which in turn
 	  allows userspace programs to access the injected secrets.
 
+config OVMF_DEBUG_LOG
+	bool "Expose OVMF firmware debug log via sysfs"
+	depends on EFI
+	help
+	  Recent OVMF versions (edk2-stable202508 + newer) can write
+	  their debug log to a memory buffer.  This driver exposes the
+	  log content via sysfs (/sys/firmware/efi/ovmf_debug_log).
+
 config UNACCEPTED_MEMORY
 	bool
 	depends on EFI_STUB
diff --git a/drivers/firmware/efi/Makefile b/drivers/firmware/efi/Makefile
index a2d0009560d0..8efbcf699e4f 100644
--- a/drivers/firmware/efi/Makefile
+++ b/drivers/firmware/efi/Makefile
@@ -29,6 +29,7 @@ obj-$(CONFIG_APPLE_PROPERTIES)		+= apple-properties.o
 obj-$(CONFIG_EFI_RCI2_TABLE)		+= rci2-table.o
 obj-$(CONFIG_EFI_EMBEDDED_FIRMWARE)	+= embedded-firmware.o
 obj-$(CONFIG_LOAD_UEFI_KEYS)		+= mokvar-table.o
+obj-$(CONFIG_OVMF_DEBUG_LOG)		+= ovmf-debug-log.o
 
 obj-$(CONFIG_SYSFB)			+= sysfb_efi.o
 
diff --git a/drivers/firmware/efi/efi.c b/drivers/firmware/efi/efi.c
index e57bff702b5f..1ce428e2ac8a 100644
--- a/drivers/firmware/efi/efi.c
+++ b/drivers/firmware/efi/efi.c
@@ -45,6 +45,7 @@ struct efi __read_mostly efi = {
 	.esrt			= EFI_INVALID_TABLE_ADDR,
 	.tpm_log		= EFI_INVALID_TABLE_ADDR,
 	.tpm_final_log		= EFI_INVALID_TABLE_ADDR,
+	.ovmf_debug_log         = EFI_INVALID_TABLE_ADDR,
 #ifdef CONFIG_LOAD_UEFI_KEYS
 	.mokvar_table		= EFI_INVALID_TABLE_ADDR,
 #endif
@@ -473,6 +474,10 @@ static int __init efisubsys_init(void)
 		platform_device_register_simple("efi_secret", 0, NULL, 0);
 #endif
 
+	if (IS_ENABLED(CONFIG_OVMF_DEBUG_LOG) &&
+	    efi.ovmf_debug_log != EFI_INVALID_TABLE_ADDR)
+		ovmf_log_probe(efi.ovmf_debug_log);
+
 	return 0;
 
 err_remove_group:
@@ -617,6 +622,9 @@ static const efi_config_table_type_t common_tables[] __initconst = {
 	{LINUX_EFI_MEMRESERVE_TABLE_GUID,	&mem_reserve,		"MEMRESERVE"	},
 	{LINUX_EFI_INITRD_MEDIA_GUID,		&initrd,		"INITRD"	},
 	{EFI_RT_PROPERTIES_TABLE_GUID,		&rt_prop,		"RTPROP"	},
+#ifdef CONFIG_OVMF_DEBUG_LOG
+	{OVMF_MEMORY_LOG_TABLE_GUID,		&efi.ovmf_debug_log,	"OvmfDebugLog"	},
+#endif
 #ifdef CONFIG_EFI_RCI2_TABLE
 	{DELLEMC_EFI_RCI2_TABLE_GUID,		&rci2_table_phys			},
 #endif
diff --git a/drivers/firmware/efi/ovmf-debug-log.c b/drivers/firmware/efi/ovmf-debug-log.c
new file mode 100644
index 000000000000..5b2471ffaeed
--- /dev/null
+++ b/drivers/firmware/efi/ovmf-debug-log.c
@@ -0,0 +1,111 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#include <linux/efi.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/kobject.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/sysfs.h>
+
+#define OVMF_DEBUG_LOG_MAGIC1  0x3167646d666d766f  // "ovmfmdg1"
+#define OVMF_DEBUG_LOG_MAGIC2  0x3267646d666d766f  // "ovmfmdg2"
+
+struct ovmf_debug_log_header {
+	u64    magic1;
+	u64    magic2;
+	u64    hdr_size;
+	u64    log_size;
+	u64    lock; // edk2 spinlock
+	u64    head_off;
+	u64    tail_off;
+	u64    truncated;
+	u8     fw_version[128];
+};
+
+static struct ovmf_debug_log_header *hdr;
+static u8 *logbuf;
+static u64 logbufsize;
+
+static ssize_t ovmf_log_read(struct file *filp, struct kobject *kobj,
+			     const struct bin_attribute *attr, char *buf,
+			     loff_t offset, size_t count)
+{
+	u64 start, end;
+
+	start = hdr->head_off + offset;
+	if (hdr->head_off > hdr->tail_off && start >= hdr->log_size)
+		start -= hdr->log_size;
+
+	end = start + count;
+	if (start > hdr->tail_off) {
+		if (end > hdr->log_size)
+			end = hdr->log_size;
+	} else {
+		if (end > hdr->tail_off)
+			end = hdr->tail_off;
+	}
+
+	if (start > logbufsize || end > logbufsize)
+		return 0;
+	if (start >= end)
+		return 0;
+
+	memcpy(buf, logbuf + start, end - start);
+	return end - start;
+}
+
+static struct bin_attribute ovmf_log_bin_attr = {
+	.attr = {
+		.name = "ovmf_debug_log",
+		.mode = 0444,
+	},
+	.read = ovmf_log_read,
+};
+
+int __init ovmf_log_probe(unsigned long ovmf_debug_log_table)
+{
+	int ret = -EINVAL;
+	u64 size;
+
+	/* map + verify header */
+	hdr = memremap(ovmf_debug_log_table, sizeof(*hdr), MEMREMAP_WB);
+	if (!hdr) {
+		pr_err("OVMF debug log: header map failed\n");
+		return -EINVAL;
+	}
+
+	if (hdr->magic1 != OVMF_DEBUG_LOG_MAGIC1 ||
+	    hdr->magic2 != OVMF_DEBUG_LOG_MAGIC2) {
+		printk(KERN_ERR "OVMF debug log: magic mismatch\n");
+		goto err_unmap;
+	}
+
+	size = hdr->hdr_size + hdr->log_size;
+	pr_info("OVMF debug log: firmware version: \"%s\"\n", hdr->fw_version);
+	pr_info("OVMF debug log: buffer size: %lluk\n", size / 1024);
+
+	/* map complete log buffer */
+	memunmap(hdr);
+	hdr = memremap(ovmf_debug_log_table, size, MEMREMAP_WB);
+	if (!hdr) {
+		pr_err("OVMF debug log: buffer map failed\n");
+		return -EINVAL;
+	}
+	logbuf = (void *)hdr + hdr->hdr_size;
+	logbufsize = hdr->log_size;
+
+	ovmf_log_bin_attr.size = size;
+	ret = sysfs_create_bin_file(efi_kobj, &ovmf_log_bin_attr);
+	if (ret != 0) {
+		pr_err("OVMF debug log: sysfs register failed\n");
+		goto err_unmap;
+	}
+
+	return 0;
+
+err_unmap:
+	memunmap(hdr);
+	return ret;
+}
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 7d63d1d75f22..50db7df0efab 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -439,6 +439,7 @@ void efi_native_runtime_setup(void);
 
 /* OVMF protocol GUIDs */
 #define OVMF_SEV_MEMORY_ACCEPTANCE_PROTOCOL_GUID	EFI_GUID(0xc5a010fe, 0x38a7, 0x4531,  0x8a, 0x4a, 0x05, 0x00, 0xd2, 0xfd, 0x16, 0x49)
+#define OVMF_MEMORY_LOG_TABLE_GUID		EFI_GUID(0x95305139, 0xb20f, 0x4723,  0x84, 0x25, 0x62, 0x7c, 0x88, 0x8f, 0xf1, 0x21)
 
 typedef struct {
 	efi_guid_t guid;
@@ -642,6 +643,7 @@ extern struct efi {
 	unsigned long			esrt;			/* ESRT table */
 	unsigned long			tpm_log;		/* TPM2 Event Log table */
 	unsigned long			tpm_final_log;		/* TPM2 Final Events Log table */
+	unsigned long                   ovmf_debug_log;
 	unsigned long			mokvar_table;		/* MOK variable config table */
 	unsigned long			coco_secret;		/* Confidential computing secret table */
 	unsigned long			unaccepted;		/* Unaccepted memory table */
@@ -1344,6 +1346,8 @@ bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table)
 
 umode_t efi_attr_is_visible(struct kobject *kobj, struct attribute *attr, int n);
 
+int ovmf_log_probe(unsigned long ovmf_debug_log_table);
+
 /*
  * efivar ops event type
  */
-- 
cgit v1.2.3


From 6c3b746fd536b7612b23e5c2041365014b85082e Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 1 Jul 2025 13:47:09 +0200
Subject: pmdomain: core: Export a common ->sync_state() helper for genpd
 providers

In some cases the typical platform driver that act as genpd provider, may
need its own ->sync_state() callback to manage various things. In this
regards, the provider most likely wants to allow its corresponding genpds
to be powered-off.

For this reason, let's introduce a new genpd helper function,
of_genpd_sync_state() that helps genpd provider drivers to achieve this.

Suggested-by: Saravana Kannan <saravanak@google.com>
Reviewed-by: Abel Vesa <abel.vesa@linaro.org>
Tested-by: Hiago De Franco <hiago.franco@toradex.com> # Colibri iMX8X
Tested-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com> # TI AM62A,Xilinx ZynqMP ZCU106
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250701114733.636510-8-ulf.hansson@linaro.org
---
 drivers/pmdomain/core.c   | 27 +++++++++++++++++++++++++++
 include/linux/pm_domain.h |  3 +++
 2 files changed, 30 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index 79dc0bf406f0..0a6593a1b1c8 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -3396,6 +3396,33 @@ int of_genpd_parse_idle_states(struct device_node *dn,
 }
 EXPORT_SYMBOL_GPL(of_genpd_parse_idle_states);
 
+/**
+ * of_genpd_sync_state() - A common sync_state function for genpd providers
+ * @np: The device node the genpd provider is associated with.
+ *
+ * The @np that corresponds to a genpd provider may provide one or multiple
+ * genpds. This function makes use @np to find the genpds that belongs to the
+ * provider. For each genpd we try a power-off.
+ */
+void of_genpd_sync_state(struct device_node *np)
+{
+	struct generic_pm_domain *genpd;
+
+	if (!np)
+		return;
+
+	mutex_lock(&gpd_list_lock);
+	list_for_each_entry(genpd, &gpd_list, gpd_list_node) {
+		if (genpd->provider == of_fwnode_handle(np)) {
+			genpd_lock(genpd);
+			genpd_power_off(genpd, false, 0);
+			genpd_unlock(genpd);
+		}
+	}
+	mutex_unlock(&gpd_list_lock);
+}
+EXPORT_SYMBOL_GPL(of_genpd_sync_state);
+
 static int genpd_provider_probe(struct device *dev)
 {
 	return 0;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 0b18160901a2..3578196e6626 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -431,6 +431,7 @@ int of_genpd_remove_subdomain(const struct of_phandle_args *parent_spec,
 struct generic_pm_domain *of_genpd_remove_last(struct device_node *np);
 int of_genpd_parse_idle_states(struct device_node *dn,
 			       struct genpd_power_state **states, int *n);
+void of_genpd_sync_state(struct device_node *np);
 
 int genpd_dev_pm_attach(struct device *dev);
 struct device *genpd_dev_pm_attach_by_id(struct device *dev,
@@ -476,6 +477,8 @@ static inline int of_genpd_parse_idle_states(struct device_node *dn,
 	return -ENODEV;
 }
 
+static inline void of_genpd_sync_state(struct device_node *np) {}
+
 static inline int genpd_dev_pm_attach(struct device *dev)
 {
 	return 0;
-- 
cgit v1.2.3


From c8c196220ce5eba9b7d4aca37a7fd4bbb965d2ed Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 1 Jul 2025 13:47:10 +0200
Subject: pmdomain: core: Prepare to add the common ->sync_state() support

Before we can implement the common ->sync_state() support in genpd, we need
to allow a few specific genpd providers to opt out from the new behaviour.

Let's introduce GENPD_FLAG_NO_SYNC_STATE as a new genpd config option, to
allow providers to opt out.

Suggested-by: Saravana Kannan <saravanak@google.com>
Tested-by: Hiago De Franco <hiago.franco@toradex.com> # Colibri iMX8X
Tested-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com> # TI AM62A,Xilinx ZynqMP ZCU106
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250701114733.636510-9-ulf.hansson@linaro.org
---
 include/linux/pm_domain.h | 6 ++++++
 1 file changed, 6 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 3578196e6626..9329554b9c4a 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -104,6 +104,11 @@ struct dev_pm_domain_list {
  * GENPD_FLAG_DEV_NAME_FW:	Instructs genpd to generate an unique device name
  *				using ida. It is used by genpd providers which
  *				get their genpd-names directly from FW.
+ *
+ * GENPD_FLAG_NO_SYNC_STATE:	The ->sync_state() support is implemented in a
+ *				genpd provider specific way, likely through a
+ *				parent device node. This flag makes genpd to
+ *				skip its internal support for this.
  */
 #define GENPD_FLAG_PM_CLK	 (1U << 0)
 #define GENPD_FLAG_IRQ_SAFE	 (1U << 1)
@@ -114,6 +119,7 @@ struct dev_pm_domain_list {
 #define GENPD_FLAG_MIN_RESIDENCY (1U << 6)
 #define GENPD_FLAG_OPP_TABLE_FW	 (1U << 7)
 #define GENPD_FLAG_DEV_NAME_FW	 (1U << 8)
+#define GENPD_FLAG_NO_SYNC_STATE (1U << 9)
 
 enum gpd_status {
 	GENPD_STATE_ON = 0,	/* PM domain is on */
-- 
cgit v1.2.3


From 10086a4f391f4b9c969a21e785e7fa0fa6c023e5 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 1 Jul 2025 13:47:17 +0200
Subject: firmware: xilinx: Don't share zynqmp_pm_init_finalize()

As there no longer any users outside the zynqmp firmware driver of
zynqmp_pm_init_finalize(), let's turn into a local static function.

Cc: Michal Simek <michal.simek@amd.com>
Tested-by: Hiago De Franco <hiago.franco@toradex.com> # Colibri iMX8X
Tested-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com> # TI AM62A,Xilinx ZynqMP ZCU106
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250701114733.636510-16-ulf.hansson@linaro.org
---
 drivers/firmware/xilinx/zynqmp.c     | 3 +--
 include/linux/firmware/xlnx-zynqmp.h | 6 ------
 2 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/xilinx/zynqmp.c b/drivers/firmware/xilinx/zynqmp.c
index a91a0191c689..87ddbb7d11c2 100644
--- a/drivers/firmware/xilinx/zynqmp.c
+++ b/drivers/firmware/xilinx/zynqmp.c
@@ -1299,11 +1299,10 @@ EXPORT_SYMBOL_GPL(zynqmp_pm_bootmode_write);
  * This API function is to be used for notify the power management controller
  * about the completed power management initialization.
  */
-int zynqmp_pm_init_finalize(void)
+static int zynqmp_pm_init_finalize(void)
 {
 	return zynqmp_pm_invoke_fn(PM_PM_INIT_FINALIZE, NULL, 0);
 }
-EXPORT_SYMBOL_GPL(zynqmp_pm_init_finalize);
 
 /**
  * zynqmp_pm_set_suspend_mode()	- Set system suspend mode
diff --git a/include/linux/firmware/xlnx-zynqmp.h b/include/linux/firmware/xlnx-zynqmp.h
index 6d4dbc196b93..ae48d619c4e0 100644
--- a/include/linux/firmware/xlnx-zynqmp.h
+++ b/include/linux/firmware/xlnx-zynqmp.h
@@ -585,7 +585,6 @@ int zynqmp_pm_reset_assert(const u32 reset,
 int zynqmp_pm_reset_get_status(const u32 reset, u32 *status);
 unsigned int zynqmp_pm_bootmode_read(u32 *ps_mode);
 int zynqmp_pm_bootmode_write(u32 ps_mode);
-int zynqmp_pm_init_finalize(void);
 int zynqmp_pm_set_suspend_mode(u32 mode);
 int zynqmp_pm_request_node(const u32 node, const u32 capabilities,
 			   const u32 qos, const enum zynqmp_pm_request_ack ack);
@@ -746,11 +745,6 @@ static inline int zynqmp_pm_bootmode_write(u32 ps_mode)
 	return -ENODEV;
 }
 
-static inline int zynqmp_pm_init_finalize(void)
-{
-	return -ENODEV;
-}
-
 static inline int zynqmp_pm_set_suspend_mode(u32 mode)
 {
 	return -ENODEV;
-- 
cgit v1.2.3


From 9a4681a485ee1203ac968065490a8eeaa6615503 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 1 Jul 2025 13:47:19 +0200
Subject: driver core: Export get_dev_from_fwnode()

It has turned out get_dev_from_fwnode() is useful at a few other places
outside of the driver core, as in gpiolib.c for example. Therefore let's
make it available as a common helper function.

Suggested-by: Saravana Kannan <saravanak@google.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Tested-by: Hiago De Franco <hiago.franco@toradex.com> # Colibri iMX8X
Tested-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com> # TI AM62A,Xilinx ZynqMP ZCU106
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250701114733.636510-18-ulf.hansson@linaro.org
---
 drivers/base/core.c    | 8 ++++++--
 include/linux/device.h | 1 +
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/core.c b/drivers/base/core.c
index cbc0099d8ef2..6f91ece7c06a 100644
--- a/drivers/base/core.c
+++ b/drivers/base/core.c
@@ -1881,8 +1881,6 @@ static void fw_devlink_unblock_consumers(struct device *dev)
 	device_links_write_unlock();
 }
 
-#define get_dev_from_fwnode(fwnode)	get_device((fwnode)->dev)
-
 static bool fwnode_init_without_drv(struct fwnode_handle *fwnode)
 {
 	struct device *dev;
@@ -5281,6 +5279,12 @@ void device_set_node(struct device *dev, struct fwnode_handle *fwnode)
 }
 EXPORT_SYMBOL_GPL(device_set_node);
 
+struct device *get_dev_from_fwnode(struct fwnode_handle *fwnode)
+{
+	return get_device((fwnode)->dev);
+}
+EXPORT_SYMBOL_GPL(get_dev_from_fwnode);
+
 int device_match_name(struct device *dev, const void *name)
 {
 	return sysfs_streq(dev_name(dev), name);
diff --git a/include/linux/device.h b/include/linux/device.h
index 4940db137fff..315b00171335 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -1048,6 +1048,7 @@ void device_set_node(struct device *dev, struct fwnode_handle *fwnode);
 int device_add_of_node(struct device *dev, struct device_node *of_node);
 void device_remove_of_node(struct device *dev);
 void device_set_of_node_from_dev(struct device *dev, const struct device *dev2);
+struct device *get_dev_from_fwnode(struct fwnode_handle *fwnode);
 
 static inline struct device_node *dev_of_node(struct device *dev)
 {
-- 
cgit v1.2.3


From 3b7b8acacf372945b4855a136634775c064a57f8 Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 1 Jul 2025 13:47:20 +0200
Subject: pmdomain: core: Add common ->sync_state() support for genpd providers

If the genpd provider's fwnode doesn't have an associated struct device
with it, we can make use of the generic genpd->dev and it corresponding
driver internally in genpd to manage ->sync_state().

More precisely, while adding a genpd OF provider let's check if the fwnode
has a device and if not, make the preparation to handle ->sync_state()
internally through the genpd_provider_driver and the genpd_provider_bus.

Note that, genpd providers may opt out from this behaviour by setting the
GENPD_FLAG_NO_SYNC_STATE config options for the genpds in question.

Suggested-by: Saravana Kannan <saravanak@google.com>
Tested-by: Hiago De Franco <hiago.franco@toradex.com> # Colibri iMX8X
Tested-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com> # TI AM62A,Xilinx ZynqMP ZCU106
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250701114733.636510-19-ulf.hansson@linaro.org
---
 drivers/pmdomain/core.c   | 52 +++++++++++++++++++++++++++++++++++++++++++++--
 include/linux/pm_domain.h |  7 +++++++
 2 files changed, 57 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index 0a6593a1b1c8..ca47f91b9e91 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -186,6 +186,7 @@ static const struct genpd_lock_ops genpd_raw_spin_ops = {
 #define genpd_is_rpm_always_on(genpd)	(genpd->flags & GENPD_FLAG_RPM_ALWAYS_ON)
 #define genpd_is_opp_table_fw(genpd)	(genpd->flags & GENPD_FLAG_OPP_TABLE_FW)
 #define genpd_is_dev_name_fw(genpd)	(genpd->flags & GENPD_FLAG_DEV_NAME_FW)
+#define genpd_is_no_sync_state(genpd)	(genpd->flags & GENPD_FLAG_NO_SYNC_STATE)
 
 static inline bool irq_safe_dev_in_sleep_domain(struct device *dev,
 		const struct generic_pm_domain *genpd)
@@ -2351,6 +2352,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
 	atomic_set(&genpd->sd_count, 0);
 	genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON;
+	genpd->sync_state = GENPD_SYNC_STATE_OFF;
 	genpd->device_count = 0;
 	genpd->provider = NULL;
 	genpd->device_id = -ENXIO;
@@ -2606,6 +2608,8 @@ static bool genpd_present(const struct generic_pm_domain *genpd)
 int of_genpd_add_provider_simple(struct device_node *np,
 				 struct generic_pm_domain *genpd)
 {
+	struct fwnode_handle *fwnode;
+	struct device *dev;
 	int ret;
 
 	if (!np || !genpd)
@@ -2619,6 +2623,15 @@ int of_genpd_add_provider_simple(struct device_node *np,
 
 	genpd->dev.of_node = np;
 
+	fwnode = of_fwnode_handle(np);
+	dev = get_dev_from_fwnode(fwnode);
+	if (!dev && !genpd_is_no_sync_state(genpd)) {
+		genpd->sync_state = GENPD_SYNC_STATE_SIMPLE;
+		device_set_node(&genpd->dev, fwnode);
+	}
+
+	put_device(dev);
+
 	ret = device_add(&genpd->dev);
 	if (ret)
 		return ret;
@@ -2643,7 +2656,7 @@ int of_genpd_add_provider_simple(struct device_node *np,
 	if (ret)
 		goto err_opp;
 
-	genpd->provider = &np->fwnode;
+	genpd->provider = fwnode;
 	genpd->has_provider = true;
 
 	return 0;
@@ -2668,8 +2681,11 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 				  struct genpd_onecell_data *data)
 {
 	struct generic_pm_domain *genpd;
+	struct fwnode_handle *fwnode;
+	struct device *dev;
 	unsigned int i;
 	int ret = -EINVAL;
+	bool sync_state = false;
 
 	if (!np || !data)
 		return -EINVAL;
@@ -2680,6 +2696,13 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 	if (!data->xlate)
 		data->xlate = genpd_xlate_onecell;
 
+	fwnode = of_fwnode_handle(np);
+	dev = get_dev_from_fwnode(fwnode);
+	if (!dev)
+		sync_state = true;
+
+	put_device(dev);
+
 	for (i = 0; i < data->num_domains; i++) {
 		genpd = data->domains[i];
 
@@ -2690,6 +2713,12 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 
 		genpd->dev.of_node = np;
 
+		if (sync_state && !genpd_is_no_sync_state(genpd)) {
+			genpd->sync_state = GENPD_SYNC_STATE_ONECELL;
+			device_set_node(&genpd->dev, fwnode);
+			sync_state = false;
+		}
+
 		ret = device_add(&genpd->dev);
 		if (ret)
 			goto error;
@@ -2712,7 +2741,7 @@ int of_genpd_add_provider_onecell(struct device_node *np,
 			WARN_ON(IS_ERR(genpd->opp_table));
 		}
 
-		genpd->provider = &np->fwnode;
+		genpd->provider = fwnode;
 		genpd->has_provider = true;
 	}
 
@@ -3430,6 +3459,25 @@ static int genpd_provider_probe(struct device *dev)
 
 static void genpd_provider_sync_state(struct device *dev)
 {
+	struct generic_pm_domain *genpd = container_of(dev, struct generic_pm_domain, dev);
+
+	switch (genpd->sync_state) {
+	case GENPD_SYNC_STATE_OFF:
+		break;
+
+	case GENPD_SYNC_STATE_ONECELL:
+		of_genpd_sync_state(dev->of_node);
+		break;
+
+	case GENPD_SYNC_STATE_SIMPLE:
+		genpd_lock(genpd);
+		genpd_power_off(genpd, false, 0);
+		genpd_unlock(genpd);
+		break;
+
+	default:
+		break;
+	}
 }
 
 static struct device_driver genpd_provider_drv = {
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 9329554b9c4a..d68e07dadc99 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -133,6 +133,12 @@ enum genpd_notication {
 	GENPD_NOTIFY_ON,
 };
 
+enum genpd_sync_state {
+	GENPD_SYNC_STATE_OFF = 0,
+	GENPD_SYNC_STATE_SIMPLE,
+	GENPD_SYNC_STATE_ONECELL,
+};
+
 struct dev_power_governor {
 	bool (*power_down_ok)(struct dev_pm_domain *domain);
 	bool (*suspend_ok)(struct device *dev);
@@ -193,6 +199,7 @@ struct generic_pm_domain {
 	unsigned int performance_state;	/* Aggregated max performance state */
 	cpumask_var_t cpus;		/* A cpumask of the attached CPUs */
 	bool synced_poweroff;		/* A consumer needs a synced poweroff */
+	enum genpd_sync_state sync_state; /* How sync_state is managed. */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
 	struct raw_notifier_head power_notifiers; /* Power on/off notifiers */
-- 
cgit v1.2.3


From 2b5630e9886f9121535d421ebfb240a9535f3f1e Mon Sep 17 00:00:00 2001
From: Saravana Kannan <saravanak@google.com>
Date: Tue, 1 Jul 2025 13:47:21 +0200
Subject: driver core: Add dev_set_drv_sync_state()

This can be used by frameworks to set the sync_state() helper functions
for drivers that don't already have them set.

Signed-off-by: Saravana Kannan <saravanak@google.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Reviewed-by: Abel Vesa <abel.vesa@linaro.org>
Tested-by: Hiago De Franco <hiago.franco@toradex.com> # Colibri iMX8X
Tested-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com> # TI AM62A,Xilinx ZynqMP ZCU106
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250701114733.636510-20-ulf.hansson@linaro.org
---
 include/linux/device.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/device.h b/include/linux/device.h
index 315b00171335..686f2a578fbd 100644
--- a/include/linux/device.h
+++ b/include/linux/device.h
@@ -917,6 +917,18 @@ static inline bool dev_has_sync_state(struct device *dev)
 	return false;
 }
 
+static inline int dev_set_drv_sync_state(struct device *dev,
+					 void (*fn)(struct device *dev))
+{
+	if (!dev || !dev->driver)
+		return 0;
+	if (dev->driver->sync_state && dev->driver->sync_state != fn)
+		return -EBUSY;
+	if (!dev->driver->sync_state)
+		dev->driver->sync_state = fn;
+	return 0;
+}
+
 static inline void dev_set_removable(struct device *dev,
 				     enum device_removable removable)
 {
-- 
cgit v1.2.3


From 13a4b7fb62600e1c0738fdb0b7176555ff05aadf Mon Sep 17 00:00:00 2001
From: Ulf Hansson <ulf.hansson@linaro.org>
Date: Tue, 1 Jul 2025 13:47:23 +0200
Subject: pmdomain: core: Leave powered-on genpds on until late_initcall_sync

Powering-off a genpd that was on during boot, before all of its consumer
devices have been probed, is certainly prone to problems.

As a step to improve this situation, let's prevent these genpds from being
powered-off until genpd_power_off_unused() gets called, which is a
late_initcall_sync().

Note that, this still doesn't guarantee that all the consumer devices has
been probed before we allow to power-off the genpds. Yet, this should be a
step in the right direction.

Suggested-by: Saravana Kannan <saravanak@google.com>
Tested-by: Hiago De Franco <hiago.franco@toradex.com> # Colibri iMX8X
Tested-by: Tomi Valkeinen <tomi.valkeinen@ideasonboard.com> # TI AM62A,Xilinx ZynqMP ZCU106
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
Link: https://lore.kernel.org/r/20250701114733.636510-22-ulf.hansson@linaro.org
---
 drivers/pmdomain/core.c   | 10 ++++++++--
 include/linux/pm_domain.h |  1 +
 2 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index 5cef6de60c72..18951ed6295d 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -931,11 +931,12 @@ static void genpd_power_off(struct generic_pm_domain *genpd, bool one_dev_on,
 	 * The domain is already in the "power off" state.
 	 * System suspend is in progress.
 	 * The domain is configured as always on.
+	 * The domain was on at boot and still need to stay on.
 	 * The domain has a subdomain being powered on.
 	 */
 	if (!genpd_status_on(genpd) || genpd->prepared_count > 0 ||
 	    genpd_is_always_on(genpd) || genpd_is_rpm_always_on(genpd) ||
-	    atomic_read(&genpd->sd_count) > 0)
+	    genpd->stay_on || atomic_read(&genpd->sd_count) > 0)
 		return;
 
 	/*
@@ -1346,8 +1347,12 @@ static int __init genpd_power_off_unused(void)
 	pr_info("genpd: Disabling unused power domains\n");
 	mutex_lock(&gpd_list_lock);
 
-	list_for_each_entry(genpd, &gpd_list, gpd_list_node)
+	list_for_each_entry(genpd, &gpd_list, gpd_list_node) {
+		genpd_lock(genpd);
+		genpd->stay_on = false;
+		genpd_unlock(genpd);
 		genpd_queue_power_off_work(genpd);
+	}
 
 	mutex_unlock(&gpd_list_lock);
 
@@ -2352,6 +2357,7 @@ int pm_genpd_init(struct generic_pm_domain *genpd,
 	INIT_WORK(&genpd->power_off_work, genpd_power_off_work_fn);
 	atomic_set(&genpd->sd_count, 0);
 	genpd->status = is_off ? GENPD_STATE_OFF : GENPD_STATE_ON;
+	genpd->stay_on = !is_off;
 	genpd->sync_state = GENPD_SYNC_STATE_OFF;
 	genpd->device_count = 0;
 	genpd->provider = NULL;
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index d68e07dadc99..99556589f45e 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -199,6 +199,7 @@ struct generic_pm_domain {
 	unsigned int performance_state;	/* Aggregated max performance state */
 	cpumask_var_t cpus;		/* A cpumask of the attached CPUs */
 	bool synced_poweroff;		/* A consumer needs a synced poweroff */
+	bool stay_on;			/* Stay powered-on during boot. */
 	enum genpd_sync_state sync_state; /* How sync_state is managed. */
 	int (*power_off)(struct generic_pm_domain *domain);
 	int (*power_on)(struct generic_pm_domain *domain);
-- 
cgit v1.2.3


From d9bc88aa54d6aa22ff1e850a86be7a37f0503889 Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 2 Jul 2025 22:24:19 +0100
Subject: debugfs: split short and full proxy wrappers, kill
 debugfs_real_fops()

All users outside of fs/debugfs/file.c are gone, in there we can just
fully split the wrappers for full and short cases and be done with that.

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/r/20250702212419.GG3406663@ZenIV
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 fs/debugfs/file.c       | 87 +++++++++++++++++++++----------------------------
 include/linux/debugfs.h |  2 --
 2 files changed, 38 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 69e9ddcb113d..77784091a10f 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -53,23 +53,6 @@ const void *debugfs_get_aux(const struct file *file)
 }
 EXPORT_SYMBOL_GPL(debugfs_get_aux);
 
-const struct file_operations *debugfs_real_fops(const struct file *filp)
-{
-	struct debugfs_fsdata *fsd = F_DENTRY(filp)->d_fsdata;
-
-	if (!fsd) {
-		/*
-		 * Urgh, we've been called w/o a protecting
-		 * debugfs_file_get().
-		 */
-		WARN_ON(1);
-		return NULL;
-	}
-
-	return fsd->real_fops;
-}
-EXPORT_SYMBOL_GPL(debugfs_real_fops);
-
 enum dbgfs_get_mode {
 	DBGFS_GET_ALREADY,
 	DBGFS_GET_REGULAR,
@@ -302,15 +285,13 @@ static int debugfs_locked_down(struct inode *inode,
 static int open_proxy_open(struct inode *inode, struct file *filp)
 {
 	struct dentry *dentry = F_DENTRY(filp);
-	const struct file_operations *real_fops = NULL;
+	const struct file_operations *real_fops = DEBUGFS_I(inode)->real_fops;
 	int r;
 
 	r = __debugfs_file_get(dentry, DBGFS_GET_REGULAR);
 	if (r)
 		return r == -EIO ? -ENOENT : r;
 
-	real_fops = debugfs_real_fops(filp);
-
 	r = debugfs_locked_down(inode, filp, real_fops);
 	if (r)
 		goto out;
@@ -352,7 +333,6 @@ static ret_type full_proxy_ ## name(proto)				\
 {									\
 	struct dentry *dentry = F_DENTRY(filp);				\
 	struct debugfs_fsdata *fsd = dentry->d_fsdata;			\
-	const struct file_operations *real_fops;			\
 	ret_type r;							\
 									\
 	if (!(fsd->methods & bit))					\
@@ -360,14 +340,13 @@ static ret_type full_proxy_ ## name(proto)				\
 	r = debugfs_file_get(dentry);					\
 	if (unlikely(r))						\
 		return r;						\
-	real_fops = debugfs_real_fops(filp);				\
-	r = real_fops->name(args);					\
+	r = fsd->real_fops->name(args);					\
 	debugfs_file_put(dentry);					\
 	return r;							\
 }
 
-#define FULL_PROXY_FUNC_BOTH(name, ret_type, filp, proto, args, bit, ret)	\
-static ret_type full_proxy_ ## name(proto)				\
+#define SHORT_PROXY_FUNC(name, ret_type, filp, proto, args, bit, ret)	\
+static ret_type short_proxy_ ## name(proto)				\
 {									\
 	struct dentry *dentry = F_DENTRY(filp);				\
 	struct debugfs_fsdata *fsd = dentry->d_fsdata;			\
@@ -378,27 +357,38 @@ static ret_type full_proxy_ ## name(proto)				\
 	r = debugfs_file_get(dentry);					\
 	if (unlikely(r))						\
 		return r;						\
-	if (fsd->real_fops)						\
-		r = fsd->real_fops->name(args);				\
-	else								\
-		r = fsd->short_fops->name(args);			\
+	r = fsd->short_fops->name(args);				\
 	debugfs_file_put(dentry);					\
 	return r;							\
 }
 
-FULL_PROXY_FUNC_BOTH(llseek, loff_t, filp,
-		     PROTO(struct file *filp, loff_t offset, int whence),
-		     ARGS(filp, offset, whence), HAS_LSEEK, -ESPIPE);
+SHORT_PROXY_FUNC(llseek, loff_t, filp,
+		PROTO(struct file *filp, loff_t offset, int whence),
+		ARGS(filp, offset, whence), HAS_LSEEK, -ESPIPE);
 
-FULL_PROXY_FUNC_BOTH(read, ssize_t, filp,
-		     PROTO(struct file *filp, char __user *buf, size_t size,
-			   loff_t *ppos),
-		     ARGS(filp, buf, size, ppos), HAS_READ, -EINVAL);
+FULL_PROXY_FUNC(llseek, loff_t, filp,
+		PROTO(struct file *filp, loff_t offset, int whence),
+		ARGS(filp, offset, whence), HAS_LSEEK, -ESPIPE);
 
-FULL_PROXY_FUNC_BOTH(write, ssize_t, filp,
-		     PROTO(struct file *filp, const char __user *buf,
-			   size_t size, loff_t *ppos),
-		     ARGS(filp, buf, size, ppos), HAS_WRITE, -EINVAL);
+SHORT_PROXY_FUNC(read, ssize_t, filp,
+		PROTO(struct file *filp, char __user *buf, size_t size,
+			loff_t *ppos),
+		ARGS(filp, buf, size, ppos), HAS_READ, -EINVAL);
+
+FULL_PROXY_FUNC(read, ssize_t, filp,
+		PROTO(struct file *filp, char __user *buf, size_t size,
+			loff_t *ppos),
+		ARGS(filp, buf, size, ppos), HAS_READ, -EINVAL);
+
+SHORT_PROXY_FUNC(write, ssize_t, filp,
+		PROTO(struct file *filp, const char __user *buf,
+			size_t size, loff_t *ppos),
+		ARGS(filp, buf, size, ppos), HAS_WRITE, -EINVAL);
+
+FULL_PROXY_FUNC(write, ssize_t, filp,
+		PROTO(struct file *filp, const char __user *buf,
+			size_t size, loff_t *ppos),
+		ARGS(filp, buf, size, ppos), HAS_WRITE, -EINVAL);
 
 FULL_PROXY_FUNC(unlocked_ioctl, long, filp,
 		PROTO(struct file *filp, unsigned int cmd, unsigned long arg),
@@ -410,22 +400,21 @@ static __poll_t full_proxy_poll(struct file *filp,
 	struct dentry *dentry = F_DENTRY(filp);
 	struct debugfs_fsdata *fsd = dentry->d_fsdata;
 	__poll_t r = 0;
-	const struct file_operations *real_fops;
 
 	if (!(fsd->methods & HAS_POLL))
 		return DEFAULT_POLLMASK;
 	if (debugfs_file_get(dentry))
 		return EPOLLHUP;
 
-	real_fops = debugfs_real_fops(filp);
-	r = real_fops->poll(filp, wait);
+	r = fsd->real_fops->poll(filp, wait);
 	debugfs_file_put(dentry);
 	return r;
 }
 
-static int full_proxy_release(struct inode *inode, struct file *filp)
+static int full_proxy_release(struct inode *inode, struct file *file)
 {
-	const struct file_operations *real_fops = debugfs_real_fops(filp);
+	struct debugfs_fsdata *fsd = F_DENTRY(file)->d_fsdata;
+	const struct file_operations *real_fops = fsd->real_fops;
 	int r = 0;
 
 	/*
@@ -435,7 +424,7 @@ static int full_proxy_release(struct inode *inode, struct file *filp)
 	 * ->i_private is still being meaningful here.
 	 */
 	if (real_fops->release)
-		r = real_fops->release(inode, filp);
+		r = real_fops->release(inode, file);
 
 	fops_put(real_fops);
 	return r;
@@ -517,9 +506,9 @@ static int full_proxy_open_short(struct inode *inode, struct file *filp)
 
 const struct file_operations debugfs_full_short_proxy_file_operations = {
 	.open = full_proxy_open_short,
-	.llseek = full_proxy_llseek,
-	.read = full_proxy_read,
-	.write = full_proxy_write,
+	.llseek = short_proxy_llseek,
+	.read = short_proxy_read,
+	.write = short_proxy_write,
 };
 
 ssize_t debugfs_attr_read(struct file *file, char __user *buf,
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index fa2568b4380d..a420152105d0 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -162,7 +162,6 @@ void debugfs_remove(struct dentry *dentry);
 
 void debugfs_lookup_and_remove(const char *name, struct dentry *parent);
 
-const struct file_operations *debugfs_real_fops(const struct file *filp);
 const void *debugfs_get_aux(const struct file *file);
 
 int debugfs_file_get(struct dentry *dentry);
@@ -329,7 +328,6 @@ static inline void debugfs_lookup_and_remove(const char *name,
 					     struct dentry *parent)
 { }
 
-const struct file_operations *debugfs_real_fops(const struct file *filp);
 void *debugfs_get_aux(const struct file *file);
 
 static inline int debugfs_file_get(struct dentry *dentry)
-- 
cgit v1.2.3


From 9d3b96be2ee81a7d6ad08cb5094753f06382db1b Mon Sep 17 00:00:00 2001
From: Al Viro <viro@zeniv.linux.org.uk>
Date: Wed, 2 Jul 2025 22:26:16 +0100
Subject: debugfs_get_aux(): allow storing non-const void *

typechecking is up to users, anyway...

Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Link: https://lore.kernel.org/r/20250702212616.GI3406663@ZenIV
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/staging/greybus/camera.c | 2 +-
 fs/debugfs/file.c                | 2 +-
 fs/debugfs/inode.c               | 2 +-
 fs/debugfs/internal.h            | 2 +-
 include/linux/debugfs.h          | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/staging/greybus/camera.c b/drivers/staging/greybus/camera.c
index ec9fddfc0b14..5ac19c0055d9 100644
--- a/drivers/staging/greybus/camera.c
+++ b/drivers/staging/greybus/camera.c
@@ -1128,7 +1128,7 @@ done:
 
 static int gb_camera_debugfs_open(struct inode *inode, struct file *file)
 {
-	file->private_data = (void *)debugfs_get_aux(file);
+	file->private_data = debugfs_get_aux(file);
 	return 0;
 }
 
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 77784091a10f..3ec3324c2060 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -47,7 +47,7 @@ const struct file_operations debugfs_noop_file_operations = {
 
 #define F_DENTRY(filp) ((filp)->f_path.dentry)
 
-const void *debugfs_get_aux(const struct file *file)
+void *debugfs_get_aux(const struct file *file)
 {
 	return DEBUGFS_I(file_inode(file))->aux;
 }
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index 30c4944e1862..43e5d1bf1f32 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -459,7 +459,7 @@ static struct dentry *__debugfs_create_file(const char *name, umode_t mode,
 		proxy_fops = &debugfs_noop_file_operations;
 	inode->i_fop = proxy_fops;
 	DEBUGFS_I(inode)->raw = real_fops;
-	DEBUGFS_I(inode)->aux = aux;
+	DEBUGFS_I(inode)->aux = (void *)aux;
 
 	d_instantiate(dentry, inode);
 	fsnotify_create(d_inode(dentry->d_parent), dentry);
diff --git a/fs/debugfs/internal.h b/fs/debugfs/internal.h
index 93483fe84425..427987f81571 100644
--- a/fs/debugfs/internal.h
+++ b/fs/debugfs/internal.h
@@ -19,7 +19,7 @@ struct debugfs_inode_info {
 		const struct debugfs_short_fops *short_fops;
 		debugfs_automount_t automount;
 	};
-	const void *aux;
+	void *aux;
 };
 
 static inline struct debugfs_inode_info *DEBUGFS_I(struct inode *inode)
diff --git a/include/linux/debugfs.h b/include/linux/debugfs.h
index a420152105d0..7cecda29447e 100644
--- a/include/linux/debugfs.h
+++ b/include/linux/debugfs.h
@@ -162,7 +162,7 @@ void debugfs_remove(struct dentry *dentry);
 
 void debugfs_lookup_and_remove(const char *name, struct dentry *parent);
 
-const void *debugfs_get_aux(const struct file *file);
+void *debugfs_get_aux(const struct file *file);
 
 int debugfs_file_get(struct dentry *dentry);
 void debugfs_file_put(struct dentry *dentry);
-- 
cgit v1.2.3


From 570c8efd5eb79c3725ba439ce105ed1bedc5acd9 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 23 May 2025 17:28:00 +0200
Subject: sched/psi: Optimize psi_group_change() cpu_clock() usage

Dietmar reported that commit 3840cbe24cf0 ("sched: psi: fix bogus
pressure spikes from aggregation race") caused a regression for him on
a high context switch rate benchmark (schbench) due to the now
repeating cpu_clock() calls.

In particular the problem is that get_recent_times() will extrapolate
the current state to 'now'. But if an update uses a timestamp from
before the start of the update, it is possible to get two reads
with inconsistent results. It is effectively back-dating an update.

(note that this all hard-relies on the clock being synchronized across
CPUs -- if this is not the case, all bets are off).

Combine this problem with the fact that there are per-group-per-cpu
seqcounts, the commit in question pushed the clock read into the group
iteration, causing tree-depth cpu_clock() calls. On architectures
where cpu_clock() has appreciable overhead, this hurts.

Instead move to a per-cpu seqcount, which allows us to have a single
clock read for all group updates, increasing internal consistency and
lowering update overhead. This comes at the cost of a longer update
side (proportional to the tree depth) which can cause the read side to
retry more often.

Fixes: 3840cbe24cf0 ("sched: psi: fix bogus pressure spikes from aggregation race")
Reported-by: Dietmar Eggemann <dietmar.eggemann@arm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Tested-by: Dietmar Eggemann <dietmar.eggemann@arm.com>,
Link: https://lkml.kernel.org/20250522084844.GC31726@noisy.programming.kicks-ass.net
---
 include/linux/psi_types.h |   6 +--
 kernel/sched/psi.c        | 121 +++++++++++++++++++++++++---------------------
 2 files changed, 68 insertions(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/psi_types.h b/include/linux/psi_types.h
index f1fd3a8044e0..dd10c22299ab 100644
--- a/include/linux/psi_types.h
+++ b/include/linux/psi_types.h
@@ -84,11 +84,9 @@ enum psi_aggregators {
 struct psi_group_cpu {
 	/* 1st cacheline updated by the scheduler */
 
-	/* Aggregator needs to know of concurrent changes */
-	seqcount_t seq ____cacheline_aligned_in_smp;
-
 	/* States of the tasks belonging to this group */
-	unsigned int tasks[NR_PSI_TASK_COUNTS];
+	unsigned int tasks[NR_PSI_TASK_COUNTS]
+			____cacheline_aligned_in_smp;
 
 	/* Aggregate pressure state derived from the tasks */
 	u32 state_mask;
diff --git a/kernel/sched/psi.c b/kernel/sched/psi.c
index 5837cd8e7b97..2024c1d36402 100644
--- a/kernel/sched/psi.c
+++ b/kernel/sched/psi.c
@@ -176,6 +176,28 @@ struct psi_group psi_system = {
 	.pcpu = &system_group_pcpu,
 };
 
+static DEFINE_PER_CPU(seqcount_t, psi_seq);
+
+static inline void psi_write_begin(int cpu)
+{
+	write_seqcount_begin(per_cpu_ptr(&psi_seq, cpu));
+}
+
+static inline void psi_write_end(int cpu)
+{
+	write_seqcount_end(per_cpu_ptr(&psi_seq, cpu));
+}
+
+static inline u32 psi_read_begin(int cpu)
+{
+	return read_seqcount_begin(per_cpu_ptr(&psi_seq, cpu));
+}
+
+static inline bool psi_read_retry(int cpu, u32 seq)
+{
+	return read_seqcount_retry(per_cpu_ptr(&psi_seq, cpu), seq);
+}
+
 static void psi_avgs_work(struct work_struct *work);
 
 static void poll_timer_fn(struct timer_list *t);
@@ -186,7 +208,7 @@ static void group_init(struct psi_group *group)
 
 	group->enabled = true;
 	for_each_possible_cpu(cpu)
-		seqcount_init(&per_cpu_ptr(group->pcpu, cpu)->seq);
+		seqcount_init(per_cpu_ptr(&psi_seq, cpu));
 	group->avg_last_update = sched_clock();
 	group->avg_next_update = group->avg_last_update + psi_period;
 	mutex_init(&group->avgs_lock);
@@ -266,14 +288,14 @@ static void get_recent_times(struct psi_group *group, int cpu,
 
 	/* Snapshot a coherent view of the CPU state */
 	do {
-		seq = read_seqcount_begin(&groupc->seq);
+		seq = psi_read_begin(cpu);
 		now = cpu_clock(cpu);
 		memcpy(times, groupc->times, sizeof(groupc->times));
 		state_mask = groupc->state_mask;
 		state_start = groupc->state_start;
 		if (cpu == current_cpu)
 			memcpy(tasks, groupc->tasks, sizeof(groupc->tasks));
-	} while (read_seqcount_retry(&groupc->seq, seq));
+	} while (psi_read_retry(cpu, seq));
 
 	/* Calculate state time deltas against the previous snapshot */
 	for (s = 0; s < NR_PSI_STATES; s++) {
@@ -772,30 +794,20 @@ static void record_times(struct psi_group_cpu *groupc, u64 now)
 		groupc->times[PSI_NONIDLE] += delta;
 }
 
+#define for_each_group(iter, group) \
+	for (typeof(group) iter = group; iter; iter = iter->parent)
+
 static void psi_group_change(struct psi_group *group, int cpu,
 			     unsigned int clear, unsigned int set,
-			     bool wake_clock)
+			     u64 now, bool wake_clock)
 {
 	struct psi_group_cpu *groupc;
 	unsigned int t, m;
 	u32 state_mask;
-	u64 now;
 
 	lockdep_assert_rq_held(cpu_rq(cpu));
 	groupc = per_cpu_ptr(group->pcpu, cpu);
 
-	/*
-	 * First we update the task counts according to the state
-	 * change requested through the @clear and @set bits.
-	 *
-	 * Then if the cgroup PSI stats accounting enabled, we
-	 * assess the aggregate resource states this CPU's tasks
-	 * have been in since the last change, and account any
-	 * SOME and FULL time these may have resulted in.
-	 */
-	write_seqcount_begin(&groupc->seq);
-	now = cpu_clock(cpu);
-
 	/*
 	 * Start with TSK_ONCPU, which doesn't have a corresponding
 	 * task count - it's just a boolean flag directly encoded in
@@ -847,7 +859,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
 
 		groupc->state_mask = state_mask;
 
-		write_seqcount_end(&groupc->seq);
 		return;
 	}
 
@@ -868,8 +879,6 @@ static void psi_group_change(struct psi_group *group, int cpu,
 
 	groupc->state_mask = state_mask;
 
-	write_seqcount_end(&groupc->seq);
-
 	if (state_mask & group->rtpoll_states)
 		psi_schedule_rtpoll_work(group, 1, false);
 
@@ -904,24 +913,29 @@ static void psi_flags_change(struct task_struct *task, int clear, int set)
 void psi_task_change(struct task_struct *task, int clear, int set)
 {
 	int cpu = task_cpu(task);
-	struct psi_group *group;
+	u64 now;
 
 	if (!task->pid)
 		return;
 
 	psi_flags_change(task, clear, set);
 
-	group = task_psi_group(task);
-	do {
-		psi_group_change(group, cpu, clear, set, true);
-	} while ((group = group->parent));
+	psi_write_begin(cpu);
+	now = cpu_clock(cpu);
+	for_each_group(group, task_psi_group(task))
+		psi_group_change(group, cpu, clear, set, now, true);
+	psi_write_end(cpu);
 }
 
 void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		     bool sleep)
 {
-	struct psi_group *group, *common = NULL;
+	struct psi_group *common = NULL;
 	int cpu = task_cpu(prev);
+	u64 now;
+
+	psi_write_begin(cpu);
+	now = cpu_clock(cpu);
 
 	if (next->pid) {
 		psi_flags_change(next, 0, TSK_ONCPU);
@@ -930,16 +944,15 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		 * ancestors with @prev, those will already have @prev's
 		 * TSK_ONCPU bit set, and we can stop the iteration there.
 		 */
-		group = task_psi_group(next);
-		do {
-			if (per_cpu_ptr(group->pcpu, cpu)->state_mask &
-			    PSI_ONCPU) {
+		for_each_group(group, task_psi_group(next)) {
+			struct psi_group_cpu *groupc = per_cpu_ptr(group->pcpu, cpu);
+
+			if (groupc->state_mask & PSI_ONCPU) {
 				common = group;
 				break;
 			}
-
-			psi_group_change(group, cpu, 0, TSK_ONCPU, true);
-		} while ((group = group->parent));
+			psi_group_change(group, cpu, 0, TSK_ONCPU, now, true);
+		}
 	}
 
 	if (prev->pid) {
@@ -972,12 +985,11 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 
 		psi_flags_change(prev, clear, set);
 
-		group = task_psi_group(prev);
-		do {
+		for_each_group(group, task_psi_group(prev)) {
 			if (group == common)
 				break;
-			psi_group_change(group, cpu, clear, set, wake_clock);
-		} while ((group = group->parent));
+			psi_group_change(group, cpu, clear, set, now, wake_clock);
+		}
 
 		/*
 		 * TSK_ONCPU is handled up to the common ancestor. If there are
@@ -987,20 +999,21 @@ void psi_task_switch(struct task_struct *prev, struct task_struct *next,
 		 */
 		if ((prev->psi_flags ^ next->psi_flags) & ~TSK_ONCPU) {
 			clear &= ~TSK_ONCPU;
-			for (; group; group = group->parent)
-				psi_group_change(group, cpu, clear, set, wake_clock);
+			for_each_group(group, common)
+				psi_group_change(group, cpu, clear, set, now, wake_clock);
 		}
 	}
+	psi_write_end(cpu);
 }
 
 #ifdef CONFIG_IRQ_TIME_ACCOUNTING
 void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_struct *prev)
 {
 	int cpu = task_cpu(curr);
-	struct psi_group *group;
 	struct psi_group_cpu *groupc;
 	s64 delta;
 	u64 irq;
+	u64 now;
 
 	if (static_branch_likely(&psi_disabled) || !irqtime_enabled())
 		return;
@@ -1009,8 +1022,7 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st
 		return;
 
 	lockdep_assert_rq_held(rq);
-	group = task_psi_group(curr);
-	if (prev && task_psi_group(prev) == group)
+	if (prev && task_psi_group(prev) == task_psi_group(curr))
 		return;
 
 	irq = irq_time_read(cpu);
@@ -1019,25 +1031,22 @@ void psi_account_irqtime(struct rq *rq, struct task_struct *curr, struct task_st
 		return;
 	rq->psi_irq_time = irq;
 
-	do {
-		u64 now;
+	psi_write_begin(cpu);
+	now = cpu_clock(cpu);
 
+	for_each_group(group, task_psi_group(curr)) {
 		if (!group->enabled)
 			continue;
 
 		groupc = per_cpu_ptr(group->pcpu, cpu);
 
-		write_seqcount_begin(&groupc->seq);
-		now = cpu_clock(cpu);
-
 		record_times(groupc, now);
 		groupc->times[PSI_IRQ_FULL] += delta;
 
-		write_seqcount_end(&groupc->seq);
-
 		if (group->rtpoll_states & (1 << PSI_IRQ_FULL))
 			psi_schedule_rtpoll_work(group, 1, false);
-	} while ((group = group->parent));
+	}
+	psi_write_end(cpu);
 }
 #endif /* CONFIG_IRQ_TIME_ACCOUNTING */
 
@@ -1225,12 +1234,14 @@ void psi_cgroup_restart(struct psi_group *group)
 		return;
 
 	for_each_possible_cpu(cpu) {
-		struct rq *rq = cpu_rq(cpu);
-		struct rq_flags rf;
+		u64 now;
 
-		rq_lock_irq(rq, &rf);
-		psi_group_change(group, cpu, 0, 0, true);
-		rq_unlock_irq(rq, &rf);
+		guard(rq_lock_irq)(cpu_rq(cpu));
+
+		psi_write_begin(cpu);
+		now = cpu_clock(cpu);
+		psi_group_change(group, cpu, 0, 0, now, true);
+		psi_write_end(cpu);
 	}
 }
 #endif /* CONFIG_CGROUPS */
-- 
cgit v1.2.3


From cccb45d7c4295bbfeba616582d0249f2d21e6df5 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Tue, 20 May 2025 11:19:30 +0200
Subject: sched/deadline: Less agressive dl_server handling

Chris reported that commit 5f6bd380c7bd ("sched/rt: Remove default
bandwidth control") caused a significant dip in his favourite
benchmark of the day. Simply disabling dl_server cured things.

His workload hammers the 0->1, 1->0 transitions, and the
dl_server_{start,stop}() overhead kills it -- fairly obviously a bad
idea in hind sight and all that.

Change things around to only disable the dl_server when there has not
been a fair task around for a whole period. Since the default period
is 1 second, this ensures the benchmark never trips this, overhead
gone.

Fixes: 557a6bfc662c ("sched/fair: Add trivial fair server")
Reported-by: Chris Mason <clm@meta.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Juri Lelli <juri.lelli@redhat.com>
Acked-by: Juri Lelli <juri.lelli@redhat.com>
Link: https://lkml.kernel.org/r/20250702121158.465086194@infradead.org
---
 include/linux/sched.h   |  1 +
 kernel/sched/deadline.c | 25 ++++++++++++++++++++++---
 kernel/sched/fair.c     |  9 ---------
 3 files changed, 23 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index eec6b225e9d1..4802fcf738cd 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -698,6 +698,7 @@ struct sched_dl_entity {
 	unsigned int			dl_defer	  : 1;
 	unsigned int			dl_defer_armed	  : 1;
 	unsigned int			dl_defer_running  : 1;
+	unsigned int			dl_server_idle    : 1;
 
 	/*
 	 * Bandwidth enforcement timer. Each -deadline task has its
diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
index 0f30697ad795..23668fc60bd3 100644
--- a/kernel/sched/deadline.c
+++ b/kernel/sched/deadline.c
@@ -1150,6 +1150,8 @@ static void __push_dl_task(struct rq *rq, struct rq_flags *rf)
 /* a defer timer will not be reset if the runtime consumed was < dl_server_min_res */
 static const u64 dl_server_min_res = 1 * NSEC_PER_MSEC;
 
+static bool dl_server_stopped(struct sched_dl_entity *dl_se);
+
 static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_dl_entity *dl_se)
 {
 	struct rq *rq = rq_of_dl_se(dl_se);
@@ -1169,6 +1171,7 @@ static enum hrtimer_restart dl_server_timer(struct hrtimer *timer, struct sched_
 
 		if (!dl_se->server_has_tasks(dl_se)) {
 			replenish_dl_entity(dl_se);
+			dl_server_stopped(dl_se);
 			return HRTIMER_NORESTART;
 		}
 
@@ -1572,8 +1575,10 @@ void dl_server_update_idle_time(struct rq *rq, struct task_struct *p)
 void dl_server_update(struct sched_dl_entity *dl_se, s64 delta_exec)
 {
 	/* 0 runtime = fair server disabled */
-	if (dl_se->dl_runtime)
+	if (dl_se->dl_runtime) {
+		dl_se->dl_server_idle = 0;
 		update_curr_dl_se(dl_se->rq, dl_se, delta_exec);
+	}
 }
 
 void dl_server_start(struct sched_dl_entity *dl_se)
@@ -1596,7 +1601,7 @@ void dl_server_start(struct sched_dl_entity *dl_se)
 		setup_new_dl_entity(dl_se);
 	}
 
-	if (!dl_se->dl_runtime)
+	if (!dl_se->dl_runtime || dl_se->dl_server_active)
 		return;
 
 	dl_se->dl_server_active = 1;
@@ -1617,6 +1622,20 @@ void dl_server_stop(struct sched_dl_entity *dl_se)
 	dl_se->dl_server_active = 0;
 }
 
+static bool dl_server_stopped(struct sched_dl_entity *dl_se)
+{
+	if (!dl_se->dl_server_active)
+		return false;
+
+	if (dl_se->dl_server_idle) {
+		dl_server_stop(dl_se);
+		return true;
+	}
+
+	dl_se->dl_server_idle = 1;
+	return false;
+}
+
 void dl_server_init(struct sched_dl_entity *dl_se, struct rq *rq,
 		    dl_server_has_tasks_f has_tasks,
 		    dl_server_pick_f pick_task)
@@ -2354,7 +2373,7 @@ again:
 	if (dl_server(dl_se)) {
 		p = dl_se->server_pick_task(dl_se);
 		if (!p) {
-			if (dl_server_active(dl_se)) {
+			if (!dl_server_stopped(dl_se)) {
 				dl_se->dl_yielded = 1;
 				update_curr_dl_se(rq, dl_se, 0);
 			}
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index ab0822cc51c2..a1350c513a87 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -5802,7 +5802,6 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 	struct cfs_bandwidth *cfs_b = tg_cfs_bandwidth(cfs_rq->tg);
 	struct sched_entity *se;
 	long queued_delta, runnable_delta, idle_delta, dequeue = 1;
-	long rq_h_nr_queued = rq->cfs.h_nr_queued;
 
 	raw_spin_lock(&cfs_b->lock);
 	/* This will start the period timer if necessary */
@@ -5886,10 +5885,6 @@ static bool throttle_cfs_rq(struct cfs_rq *cfs_rq)
 
 	/* At this point se is NULL and we are at root level*/
 	sub_nr_running(rq, queued_delta);
-
-	/* Stop the fair server if throttling resulted in no runnable tasks */
-	if (rq_h_nr_queued && !rq->cfs.h_nr_queued)
-		dl_server_stop(&rq->fair_server);
 done:
 	/*
 	 * Note: distribution will already see us throttled via the
@@ -6966,7 +6961,6 @@ static void set_next_buddy(struct sched_entity *se);
 static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 {
 	bool was_sched_idle = sched_idle_rq(rq);
-	int rq_h_nr_queued = rq->cfs.h_nr_queued;
 	bool task_sleep = flags & DEQUEUE_SLEEP;
 	bool task_delayed = flags & DEQUEUE_DELAYED;
 	struct task_struct *p = NULL;
@@ -7050,9 +7044,6 @@ static int dequeue_entities(struct rq *rq, struct sched_entity *se, int flags)
 
 	sub_nr_running(rq, h_nr_queued);
 
-	if (rq_h_nr_queued && !rq->cfs.h_nr_queued)
-		dl_server_stop(&rq->fair_server);
-
 	/* balance early to pull high priority tasks */
 	if (unlikely(!was_sched_idle && sched_idle_rq(rq)))
 		rq->next_balance = jiffies;
-- 
cgit v1.2.3


From 74eec63661d46a7153d04c2e0249eeb76cc76d44 Mon Sep 17 00:00:00 2001
From: Vincent Guittot <vincent.guittot@linaro.org>
Date: Tue, 8 Jul 2025 18:56:26 +0200
Subject: sched/fair: Fix NO_RUN_TO_PARITY case

EEVDF expects the scheduler to allocate a time quantum to the selected
entity and then pick a new entity for next quantum.
Although this notion of time quantum is not strictly doable in our case,
we can ensure a minimum runtime for each task most of the time and pick a
new entity after a minimum time has elapsed.
Reuse the slice protection of run to parity to ensure such runtime
quantum.

Signed-off-by: Vincent Guittot <vincent.guittot@linaro.org>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20250708165630.1948751-3-vincent.guittot@linaro.org
---
 include/linux/sched.h | 10 +++++++++-
 kernel/sched/fair.c   | 31 ++++++++++++++++++++-----------
 2 files changed, 29 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4802fcf738cd..55921385927d 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -583,7 +583,15 @@ struct sched_entity {
 	u64				sum_exec_runtime;
 	u64				prev_sum_exec_runtime;
 	u64				vruntime;
-	s64				vlag;
+	union {
+		/*
+		 * When !@on_rq this field is vlag.
+		 * When cfs_rq->curr == se (which implies @on_rq)
+		 * this field is vprot. See protect_slice().
+		 */
+		s64                     vlag;
+		u64                     vprot;
+	};
 	u64				slice;
 
 	u64				nr_migrations;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 43fe5c831dd5..8d288df79a6b 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -882,23 +882,35 @@ struct sched_entity *__pick_first_entity(struct cfs_rq *cfs_rq)
 }
 
 /*
- * HACK, stash a copy of deadline at the point of pick in vlag,
- * which isn't used until dequeue.
+ * Set the vruntime up to which an entity can run before looking
+ * for another entity to pick.
+ * In case of run to parity, we protect the entity up to its deadline.
+ * When run to parity is disabled, we give a minimum quantum to the running
+ * entity to ensure progress.
  */
 static inline void set_protect_slice(struct sched_entity *se)
 {
-	se->vlag = se->deadline;
+	u64 slice = se->slice;
+	u64 vprot = se->deadline;
+
+	if (!sched_feat(RUN_TO_PARITY))
+		slice = min(slice, normalized_sysctl_sched_base_slice);
+
+	if (slice != se->slice)
+		vprot = min_vruntime(vprot, se->vruntime + calc_delta_fair(slice, se));
+
+	se->vprot = vprot;
 }
 
 static inline bool protect_slice(struct sched_entity *se)
 {
-	return se->vlag == se->deadline;
+	return ((s64)(se->vprot - se->vruntime) > 0);
 }
 
 static inline void cancel_protect_slice(struct sched_entity *se)
 {
 	if (protect_slice(se))
-		se->vlag = se->deadline + 1;
+		se->vprot = se->vruntime;
 }
 
 /*
@@ -937,7 +949,7 @@ static struct sched_entity *pick_eevdf(struct cfs_rq *cfs_rq)
 	if (curr && (!curr->on_rq || !entity_eligible(cfs_rq, curr)))
 		curr = NULL;
 
-	if (sched_feat(RUN_TO_PARITY) && curr && protect_slice(curr))
+	if (curr && protect_slice(curr))
 		return curr;
 
 	/* Pick the leftmost entity if it's eligible */
@@ -1156,11 +1168,8 @@ static inline void update_curr_task(struct task_struct *p, s64 delta_exec)
 	cgroup_account_cputime(p, delta_exec);
 }
 
-static inline bool did_preempt_short(struct cfs_rq *cfs_rq, struct sched_entity *curr)
+static inline bool resched_next_slice(struct cfs_rq *cfs_rq, struct sched_entity *curr)
 {
-	if (!sched_feat(PREEMPT_SHORT))
-		return false;
-
 	if (protect_slice(curr))
 		return false;
 
@@ -1248,7 +1257,7 @@ static void update_curr(struct cfs_rq *cfs_rq)
 	if (cfs_rq->nr_queued == 1)
 		return;
 
-	if (resched || did_preempt_short(cfs_rq, curr)) {
+	if (resched || resched_next_slice(cfs_rq, curr)) {
 		resched_curr_lazy(rq);
 		clear_buddies(cfs_rq, curr);
 	}
-- 
cgit v1.2.3


From 0af3ecdde58676f6c42eeec07d6816d5bf87ff88 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 9 Jul 2025 21:21:13 +0200
Subject: printk: Make vprintk_deferred() public

vprintk_deferred() is useful for implementing runtime verification
reactors. Make it public.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/printk.h   | 7 +++++++
 kernel/printk/internal.h | 1 -
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/printk.h b/include/linux/printk.h
index 5b462029d03c..5d22b803f51e 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -154,6 +154,8 @@ int vprintk_emit(int facility, int level,
 
 asmlinkage __printf(1, 0)
 int vprintk(const char *fmt, va_list args);
+__printf(1, 0)
+int vprintk_deferred(const char *fmt, va_list args);
 
 asmlinkage __printf(1, 2) __cold
 int _printk(const char *fmt, ...);
@@ -214,6 +216,11 @@ int vprintk(const char *s, va_list args)
 {
 	return 0;
 }
+static inline __printf(1, 0)
+int vprintk_deferred(const char *fmt, va_list args)
+{
+	return 0;
+}
 static inline __printf(1, 2) __cold
 int _printk(const char *s, ...)
 {
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index 48a24e7b309d..bbed41ad29cf 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -72,7 +72,6 @@ int vprintk_store(int facility, int level,
 		  const char *fmt, va_list args);
 
 __printf(1, 0) int vprintk_default(const char *fmt, va_list args);
-__printf(1, 0) int vprintk_deferred(const char *fmt, va_list args);
 
 void __printk_safe_enter(void);
 void __printk_safe_exit(void);
-- 
cgit v1.2.3


From 3f045de7f557850ca6b3632c6d45c2cdaf948694 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 9 Jul 2025 21:21:14 +0200
Subject: panic: Add vpanic()

vpanic() is useful for implementing runtime verification reactors. Add it.

Signed-off-by: Nam Cao <namcao@linutronix.de>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/panic.h |  3 +++
 kernel/panic.c        | 16 ++++++++++++----
 2 files changed, 15 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/panic.h b/include/linux/panic.h
index 4adc65766935..0332c6d6771f 100644
--- a/include/linux/panic.h
+++ b/include/linux/panic.h
@@ -3,6 +3,7 @@
 #define _LINUX_PANIC_H
 
 #include <linux/compiler_attributes.h>
+#include <linux/stdarg.h>
 #include <linux/types.h>
 
 struct pt_regs;
@@ -10,6 +11,8 @@ struct pt_regs;
 extern long (*panic_blink)(int state);
 __printf(1, 2)
 void panic(const char *fmt, ...) __noreturn __cold;
+__printf(1, 0)
+void vpanic(const char *fmt, va_list args) __noreturn __cold;
 void nmi_panic(struct pt_regs *regs, const char *msg);
 void check_panic_on_warn(const char *origin);
 extern void oops_enter(void);
diff --git a/kernel/panic.c b/kernel/panic.c
index b0b9a8bf4560..6a1823c383d0 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -309,13 +309,13 @@ static void panic_other_cpus_shutdown(bool crash_kexec)
 /**
  * panic - halt the system
  * @fmt: The text string to print
+ * @args: Arguments for the format string
  *
  * Display a message, then perform cleanups. This function never returns.
  */
-void panic(const char *fmt, ...)
+void vpanic(const char *fmt, va_list args)
 {
 	static char buf[1024];
-	va_list args;
 	long i, i_next = 0, len;
 	int state = 0;
 	int old_cpu, this_cpu;
@@ -366,9 +366,7 @@ void panic(const char *fmt, ...)
 
 	console_verbose();
 	bust_spinlocks(1);
-	va_start(args, fmt);
 	len = vscnprintf(buf, sizeof(buf), fmt, args);
-	va_end(args);
 
 	if (len && buf[len - 1] == '\n')
 		buf[len - 1] = '\0';
@@ -505,7 +503,17 @@ void panic(const char *fmt, ...)
 		mdelay(PANIC_TIMER_STEP);
 	}
 }
+EXPORT_SYMBOL(vpanic);
 
+/* Identical to vpanic(), except it takes variadic arguments instead of va_list */
+void panic(const char *fmt, ...)
+{
+	va_list args;
+
+	va_start(args, fmt);
+	vpanic(fmt, args);
+	va_end(args);
+}
 EXPORT_SYMBOL(panic);
 
 #define TAINT_FLAG(taint, _c_true, _c_false, _module)			\
-- 
cgit v1.2.3


From ff4e233d8ab70fe6ae460ecc8c0e5b24dd0fedb0 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 9 Jul 2025 21:21:15 +0200
Subject: rv: Let the reactors take care of buffers

Each RV monitor has one static buffer to send to the reactors. If multiple
errors are detected simultaneously, the one buffer could be overwritten.

Instead, leave it to the reactors to handle buffering.

Reviewed-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/rv.h               |  9 ++++++--
 include/rv/da_monitor.h          | 45 +++++++++-------------------------------
 kernel/trace/rv/reactor_panic.c  |  8 +++++--
 kernel/trace/rv/reactor_printk.c |  8 +++++--
 kernel/trace/rv/rv_reactors.c    |  2 +-
 5 files changed, 30 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rv.h b/include/linux/rv.h
index 3452b5e4b29e..9428e62eb8e9 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -38,7 +38,7 @@ union rv_task_monitor {
 struct rv_reactor {
 	const char		*name;
 	const char		*description;
-	void			(*react)(char *msg);
+	__printf(1, 2) void	(*react)(const char *msg, ...);
 };
 #endif
 
@@ -50,7 +50,7 @@ struct rv_monitor {
 	void			(*disable)(void);
 	void			(*reset)(void);
 #ifdef CONFIG_RV_REACTORS
-	void			(*react)(char *msg);
+	__printf(1, 2) void	(*react)(const char *msg, ...);
 #endif
 };
 
@@ -64,6 +64,11 @@ void rv_put_task_monitor_slot(int slot);
 bool rv_reacting_on(void);
 int rv_unregister_reactor(struct rv_reactor *reactor);
 int rv_register_reactor(struct rv_reactor *reactor);
+#else
+static inline bool rv_reacting_on(void)
+{
+	return false;
+}
 #endif /* CONFIG_RV_REACTORS */
 
 #endif /* CONFIG_RV */
diff --git a/include/rv/da_monitor.h b/include/rv/da_monitor.h
index 510c88bfabd4..15f9ed4e4bb6 100644
--- a/include/rv/da_monitor.h
+++ b/include/rv/da_monitor.h
@@ -19,45 +19,22 @@
 #ifdef CONFIG_RV_REACTORS
 
 #define DECLARE_RV_REACTING_HELPERS(name, type)							\
-static char REACT_MSG_##name[1024];								\
-												\
-static inline char *format_react_msg_##name(type curr_state, type event)			\
-{												\
-	snprintf(REACT_MSG_##name, 1024,							\
-		 "rv: monitor %s does not allow event %s on state %s\n",			\
-		 #name,										\
-		 model_get_event_name_##name(event),						\
-		 model_get_state_name_##name(curr_state));					\
-	return REACT_MSG_##name;								\
-}												\
-												\
-static void cond_react_##name(char *msg)							\
+static void cond_react_##name(type curr_state, type event)					\
 {												\
-	if (rv_##name.react)									\
-		rv_##name.react(msg);								\
-}												\
-												\
-static bool rv_reacting_on_##name(void)								\
-{												\
-	return rv_reacting_on();								\
+	if (!rv_reacting_on() || !rv_##name.react)						\
+		return;										\
+	rv_##name.react("rv: monitor %s does not allow event %s on state %s\n",			\
+			#name,									\
+			model_get_event_name_##name(event),					\
+			model_get_state_name_##name(curr_state));				\
 }
 
 #else /* CONFIG_RV_REACTOR */
 
 #define DECLARE_RV_REACTING_HELPERS(name, type)							\
-static inline char *format_react_msg_##name(type curr_state, type event)			\
-{												\
-	return NULL;										\
-}												\
-												\
-static void cond_react_##name(char *msg)							\
+static void cond_react_##name(type curr_state, type event)					\
 {												\
 	return;											\
-}												\
-												\
-static bool rv_reacting_on_##name(void)								\
-{												\
-	return 0;										\
 }
 #endif
 
@@ -170,8 +147,7 @@ da_event_##name(struct da_monitor *da_mon, enum events_##name event)				\
 		return true;									\
 	}											\
 												\
-	if (rv_reacting_on_##name())								\
-		cond_react_##name(format_react_msg_##name(curr_state, event));			\
+	cond_react_##name(curr_state, event);							\
 												\
 	trace_error_##name(model_get_state_name_##name(curr_state),				\
 			   model_get_event_name_##name(event));					\
@@ -202,8 +178,7 @@ static inline bool da_event_##name(struct da_monitor *da_mon, struct task_struct
 		return true;									\
 	}											\
 												\
-	if (rv_reacting_on_##name())								\
-		cond_react_##name(format_react_msg_##name(curr_state, event));			\
+	cond_react_##name(curr_state, event);							\
 												\
 	trace_error_##name(tsk->pid,								\
 			   model_get_state_name_##name(curr_state),				\
diff --git a/kernel/trace/rv/reactor_panic.c b/kernel/trace/rv/reactor_panic.c
index 0186ff4cbd0b..74c6bcc2c749 100644
--- a/kernel/trace/rv/reactor_panic.c
+++ b/kernel/trace/rv/reactor_panic.c
@@ -13,9 +13,13 @@
 #include <linux/init.h>
 #include <linux/rv.h>
 
-static void rv_panic_reaction(char *msg)
+__printf(1, 2) static void rv_panic_reaction(const char *msg, ...)
 {
-	panic(msg);
+	va_list args;
+
+	va_start(args, msg);
+	vpanic(msg, args);
+	va_end(args);
 }
 
 static struct rv_reactor rv_panic = {
diff --git a/kernel/trace/rv/reactor_printk.c b/kernel/trace/rv/reactor_printk.c
index 178759dbf89f..2dae2916c05f 100644
--- a/kernel/trace/rv/reactor_printk.c
+++ b/kernel/trace/rv/reactor_printk.c
@@ -12,9 +12,13 @@
 #include <linux/init.h>
 #include <linux/rv.h>
 
-static void rv_printk_reaction(char *msg)
+__printf(1, 2) static void rv_printk_reaction(const char *msg, ...)
 {
-	printk_deferred(msg);
+	va_list args;
+
+	va_start(args, msg);
+	vprintk_deferred(msg, args);
+	va_end(args);
 }
 
 static struct rv_reactor rv_printk = {
diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c
index 9501ca886d83..740603670dd1 100644
--- a/kernel/trace/rv/rv_reactors.c
+++ b/kernel/trace/rv/rv_reactors.c
@@ -490,7 +490,7 @@ void reactor_cleanup_monitor(struct rv_monitor_def *mdef)
 /*
  * Nop reactor register
  */
-static void rv_nop_reaction(char *msg)
+__printf(1, 2) static void rv_nop_reaction(const char *msg, ...)
 {
 }
 
-- 
cgit v1.2.3


From a9769a5b987838f03f3dd57b097794cd4c691098 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 9 Jul 2025 21:21:17 +0200
Subject: rv: Add support for LTL monitors

While attempting to implement DA monitors for some complex specifications,
deterministic automaton is found to be inappropriate as the specification
language. The automaton is complicated, hard to understand, and
error-prone.

For these cases, linear temporal logic is more suitable as the
specification language.

Add support for linear temporal logic runtime verification monitor.

Cc: John Ogness <john.ogness@linutronix.de>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Gabriele Monaco <gmonaco@redhat.com>
Link: https://lore.kernel.org/d366c1fed60ed4e8f6451f3c15a99755f2740b5f.1752088709.git.namcao@linutronix.de
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/rv.h         |  63 +++++++++++++++-
 include/rv/ltl_monitor.h   | 184 +++++++++++++++++++++++++++++++++++++++++++++
 kernel/fork.c              |   5 +-
 kernel/trace/rv/Kconfig    |   7 ++
 kernel/trace/rv/rv_trace.h |  47 ++++++++++++
 5 files changed, 298 insertions(+), 8 deletions(-)
 create mode 100644 include/rv/ltl_monitor.h

(limited to 'include/linux')

diff --git a/include/linux/rv.h b/include/linux/rv.h
index 9428e62eb8e9..1d5579f9b75a 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -10,6 +10,10 @@
 #define MAX_DA_NAME_LEN	32
 
 #ifdef CONFIG_RV
+#include <linux/bitops.h>
+#include <linux/types.h>
+#include <linux/array_size.h>
+
 /*
  * Deterministic automaton per-object variables.
  */
@@ -18,6 +22,59 @@ struct da_monitor {
 	unsigned int	curr_state;
 };
 
+#ifdef CONFIG_RV_LTL_MONITOR
+
+/*
+ * In the future, if the number of atomic propositions or the size of Buchi
+ * automaton is larger, we can switch to dynamic allocation. For now, the code
+ * is simpler this way.
+ */
+#define RV_MAX_LTL_ATOM 32
+#define RV_MAX_BA_STATES 32
+
+/**
+ * struct ltl_monitor - A linear temporal logic runtime verification monitor
+ * @states:	States in the Buchi automaton. As Buchi automaton is a
+ *		non-deterministic state machine, the monitor can be in multiple
+ *		states simultaneously. This is a bitmask of all possible states.
+ *		If this is zero, that means either:
+ *		    - The monitor has not started yet (e.g. because not all
+ *		      atomic propositions are known).
+ *		    - There is no possible state to be in. In other words, a
+ *		      violation of the LTL property is detected.
+ * @atoms:	The values of atomic propositions.
+ * @unknown_atoms: Atomic propositions which are still unknown.
+ */
+struct ltl_monitor {
+	DECLARE_BITMAP(states, RV_MAX_BA_STATES);
+	DECLARE_BITMAP(atoms, RV_MAX_LTL_ATOM);
+	DECLARE_BITMAP(unknown_atoms, RV_MAX_LTL_ATOM);
+};
+
+static inline bool rv_ltl_valid_state(struct ltl_monitor *mon)
+{
+	for (int i = 0; i < ARRAY_SIZE(mon->states); ++i) {
+		if (mon->states[i])
+			return true;
+	}
+	return false;
+}
+
+static inline bool rv_ltl_all_atoms_known(struct ltl_monitor *mon)
+{
+	for (int i = 0; i < ARRAY_SIZE(mon->unknown_atoms); ++i) {
+		if (mon->unknown_atoms[i])
+			return false;
+	}
+	return true;
+}
+
+#else
+
+struct ltl_monitor {};
+
+#endif /* CONFIG_RV_LTL_MONITOR */
+
 /*
  * Per-task RV monitors count. Nowadays fixed in RV_PER_TASK_MONITORS.
  * If we find justification for more monitors, we can think about
@@ -27,11 +84,9 @@ struct da_monitor {
 #define RV_PER_TASK_MONITORS		1
 #define RV_PER_TASK_MONITOR_INIT	(RV_PER_TASK_MONITORS)
 
-/*
- * Futher monitor types are expected, so make this a union.
- */
 union rv_task_monitor {
-	struct da_monitor da_mon;
+	struct da_monitor	da_mon;
+	struct ltl_monitor	ltl_mon;
 };
 
 #ifdef CONFIG_RV_REACTORS
diff --git a/include/rv/ltl_monitor.h b/include/rv/ltl_monitor.h
new file mode 100644
index 000000000000..9a583125b566
--- /dev/null
+++ b/include/rv/ltl_monitor.h
@@ -0,0 +1,184 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/**
+ * This file must be combined with the $(MODEL_NAME).h file generated by
+ * tools/verification/rvgen.
+ */
+
+#include <linux/args.h>
+#include <linux/rv.h>
+#include <linux/stringify.h>
+#include <linux/seq_buf.h>
+#include <rv/instrumentation.h>
+#include <trace/events/task.h>
+#include <trace/events/sched.h>
+
+#ifndef MONITOR_NAME
+#error "Please include $(MODEL_NAME).h generated by rvgen"
+#endif
+
+#ifdef CONFIG_RV_REACTORS
+#define RV_MONITOR_NAME CONCATENATE(rv_, MONITOR_NAME)
+static struct rv_monitor RV_MONITOR_NAME;
+
+static void rv_cond_react(struct task_struct *task)
+{
+	if (!rv_reacting_on() || !RV_MONITOR_NAME.react)
+		return;
+	RV_MONITOR_NAME.react("rv: "__stringify(MONITOR_NAME)": %s[%d]: violation detected\n",
+			      task->comm, task->pid);
+}
+#else
+static void rv_cond_react(struct task_struct *task)
+{
+}
+#endif
+
+static int ltl_monitor_slot = RV_PER_TASK_MONITOR_INIT;
+
+static void ltl_atoms_fetch(struct task_struct *task, struct ltl_monitor *mon);
+static void ltl_atoms_init(struct task_struct *task, struct ltl_monitor *mon, bool task_creation);
+
+static struct ltl_monitor *ltl_get_monitor(struct task_struct *task)
+{
+	return &task->rv[ltl_monitor_slot].ltl_mon;
+}
+
+static void ltl_task_init(struct task_struct *task, bool task_creation)
+{
+	struct ltl_monitor *mon = ltl_get_monitor(task);
+
+	memset(&mon->states, 0, sizeof(mon->states));
+
+	for (int i = 0; i < LTL_NUM_ATOM; ++i)
+		__set_bit(i, mon->unknown_atoms);
+
+	ltl_atoms_init(task, mon, task_creation);
+	ltl_atoms_fetch(task, mon);
+}
+
+static void handle_task_newtask(void *data, struct task_struct *task, unsigned long flags)
+{
+	ltl_task_init(task, true);
+}
+
+static int ltl_monitor_init(void)
+{
+	struct task_struct *g, *p;
+	int ret, cpu;
+
+	ret = rv_get_task_monitor_slot();
+	if (ret < 0)
+		return ret;
+
+	ltl_monitor_slot = ret;
+
+	rv_attach_trace_probe(name, task_newtask, handle_task_newtask);
+
+	read_lock(&tasklist_lock);
+
+	for_each_process_thread(g, p)
+		ltl_task_init(p, false);
+
+	for_each_present_cpu(cpu)
+		ltl_task_init(idle_task(cpu), false);
+
+	read_unlock(&tasklist_lock);
+
+	return 0;
+}
+
+static void ltl_monitor_destroy(void)
+{
+	rv_detach_trace_probe(name, task_newtask, handle_task_newtask);
+
+	rv_put_task_monitor_slot(ltl_monitor_slot);
+	ltl_monitor_slot = RV_PER_TASK_MONITOR_INIT;
+}
+
+static void ltl_illegal_state(struct task_struct *task, struct ltl_monitor *mon)
+{
+	CONCATENATE(trace_error_, MONITOR_NAME)(task);
+	rv_cond_react(task);
+}
+
+static void ltl_attempt_start(struct task_struct *task, struct ltl_monitor *mon)
+{
+	if (rv_ltl_all_atoms_known(mon))
+		ltl_start(task, mon);
+}
+
+static inline void ltl_atom_set(struct ltl_monitor *mon, enum ltl_atom atom, bool value)
+{
+	__clear_bit(atom, mon->unknown_atoms);
+	if (value)
+		__set_bit(atom, mon->atoms);
+	else
+		__clear_bit(atom, mon->atoms);
+}
+
+static void
+ltl_trace_event(struct task_struct *task, struct ltl_monitor *mon, unsigned long *next_state)
+{
+	const char *format_str = "%s";
+	DECLARE_SEQ_BUF(atoms, 64);
+	char states[32], next[32];
+	int i;
+
+	if (!CONCATENATE(CONCATENATE(trace_event_, MONITOR_NAME), _enabled)())
+		return;
+
+	snprintf(states, sizeof(states), "%*pbl", RV_MAX_BA_STATES, mon->states);
+	snprintf(next, sizeof(next), "%*pbl", RV_MAX_BA_STATES, next_state);
+
+	for (i = 0; i < LTL_NUM_ATOM; ++i) {
+		if (test_bit(i, mon->atoms)) {
+			seq_buf_printf(&atoms, format_str, ltl_atom_str(i));
+			format_str = ",%s";
+		}
+	}
+
+	CONCATENATE(trace_event_, MONITOR_NAME)(task, states, atoms.buffer, next);
+}
+
+static void ltl_validate(struct task_struct *task, struct ltl_monitor *mon)
+{
+	DECLARE_BITMAP(next_states, RV_MAX_BA_STATES) = {0};
+
+	if (!rv_ltl_valid_state(mon))
+		return;
+
+	for (unsigned int i = 0; i < RV_NUM_BA_STATES; ++i) {
+		if (test_bit(i, mon->states))
+			ltl_possible_next_states(mon, i, next_states);
+	}
+
+	ltl_trace_event(task, mon, next_states);
+
+	memcpy(mon->states, next_states, sizeof(next_states));
+
+	if (!rv_ltl_valid_state(mon))
+		ltl_illegal_state(task, mon);
+}
+
+static void ltl_atom_update(struct task_struct *task, enum ltl_atom atom, bool value)
+{
+	struct ltl_monitor *mon = ltl_get_monitor(task);
+
+	ltl_atom_set(mon, atom, value);
+	ltl_atoms_fetch(task, mon);
+
+	if (!rv_ltl_valid_state(mon))
+		ltl_attempt_start(task, mon);
+
+	ltl_validate(task, mon);
+}
+
+static void __maybe_unused ltl_atom_pulse(struct task_struct *task, enum ltl_atom atom, bool value)
+{
+	struct ltl_monitor *mon = ltl_get_monitor(task);
+
+	ltl_atom_update(task, atom, value);
+
+	ltl_atom_set(mon, atom, !value);
+	ltl_validate(task, mon);
+}
diff --git a/kernel/fork.c b/kernel/fork.c
index 1ee8eb11f38b..1f06559d17bf 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1886,10 +1886,7 @@ static void copy_oom_score_adj(u64 clone_flags, struct task_struct *tsk)
 #ifdef CONFIG_RV
 static void rv_task_fork(struct task_struct *p)
 {
-	int i;
-
-	for (i = 0; i < RV_PER_TASK_MONITORS; i++)
-		p->rv[i].da_mon.monitoring = false;
+	memset(&p->rv, 0, sizeof(p->rv));
 }
 #else
 #define rv_task_fork(p) do {} while (0)
diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig
index 6cdffc04b73c..6e157f964991 100644
--- a/kernel/trace/rv/Kconfig
+++ b/kernel/trace/rv/Kconfig
@@ -11,6 +11,13 @@ config DA_MON_EVENTS_ID
 	select RV_MON_EVENTS
 	bool
 
+config LTL_MON_EVENTS_ID
+	select RV_MON_EVENTS
+	bool
+
+config RV_LTL_MONITOR
+	bool
+
 menuconfig RV
 	bool "Runtime Verification"
 	depends on TRACING
diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h
index 99c3801616d4..fd3111ad1d51 100644
--- a/kernel/trace/rv/rv_trace.h
+++ b/kernel/trace/rv/rv_trace.h
@@ -127,6 +127,53 @@ DECLARE_EVENT_CLASS(error_da_monitor_id,
 // Add new monitors based on CONFIG_DA_MON_EVENTS_ID here
 
 #endif /* CONFIG_DA_MON_EVENTS_ID */
+#ifdef CONFIG_LTL_MON_EVENTS_ID
+DECLARE_EVENT_CLASS(event_ltl_monitor_id,
+
+	TP_PROTO(struct task_struct *task, char *states, char *atoms, char *next),
+
+	TP_ARGS(task, states, atoms, next),
+
+	TP_STRUCT__entry(
+		__string(comm, task->comm)
+		__field(pid_t, pid)
+		__string(states, states)
+		__string(atoms, atoms)
+		__string(next, next)
+	),
+
+	TP_fast_assign(
+		__assign_str(comm);
+		__entry->pid = task->pid;
+		__assign_str(states);
+		__assign_str(atoms);
+		__assign_str(next);
+	),
+
+	TP_printk("%s[%d]: (%s) x (%s) -> (%s)", __get_str(comm), __entry->pid,
+		  __get_str(states), __get_str(atoms), __get_str(next))
+);
+
+DECLARE_EVENT_CLASS(error_ltl_monitor_id,
+
+	TP_PROTO(struct task_struct *task),
+
+	TP_ARGS(task),
+
+	TP_STRUCT__entry(
+		__string(comm, task->comm)
+		__field(pid_t, pid)
+	),
+
+	TP_fast_assign(
+		__assign_str(comm);
+		__entry->pid = task->pid;
+	),
+
+	TP_printk("%s[%d]: violation detected", __get_str(comm), __entry->pid)
+);
+// Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here
+#endif /* CONFIG_LTL_MON_EVENTS_ID */
 #endif /* _TRACE_RV_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From fac5493251a680cb74343895d0e76843624a90d8 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Wed, 9 Jul 2025 21:21:23 +0200
Subject: rv: Allow to configure the number of per-task monitor

Now that there are 2 monitors for real-time applications, users may want to
enable both of them simultaneously. Make the number of per-task monitor
configurable. Default it to 2 for now.

Cc: John Ogness <john.ogness@linutronix.de>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/93e83313fc4ba7f6e66f4abe80ca5f5494d658d0.1752088709.git.namcao@linutronix.de
Reviewed-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/rv.h                     | 9 +--------
 include/linux/sched.h                  | 8 +++-----
 kernel/trace/rv/Kconfig                | 9 +++++++++
 kernel/trace/rv/monitors/rtapp/Kconfig | 1 +
 kernel/trace/rv/rv.c                   | 8 ++++----
 5 files changed, 18 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rv.h b/include/linux/rv.h
index 1d5579f9b75a..97baf58d88b2 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -75,14 +75,7 @@ struct ltl_monitor {};
 
 #endif /* CONFIG_RV_LTL_MONITOR */
 
-/*
- * Per-task RV monitors count. Nowadays fixed in RV_PER_TASK_MONITORS.
- * If we find justification for more monitors, we can think about
- * adding more or developing a dynamic method. So far, none of
- * these are justified.
- */
-#define RV_PER_TASK_MONITORS		1
-#define RV_PER_TASK_MONITOR_INIT	(RV_PER_TASK_MONITORS)
+#define RV_PER_TASK_MONITOR_INIT	(CONFIG_RV_PER_TASK_MONITORS)
 
 union rv_task_monitor {
 	struct da_monitor	da_mon;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52..fabd7fe1a07a 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1642,12 +1642,10 @@ struct task_struct {
 
 #ifdef CONFIG_RV
 	/*
-	 * Per-task RV monitor. Nowadays fixed in RV_PER_TASK_MONITORS.
-	 * If we find justification for more monitors, we can think
-	 * about adding more or developing a dynamic method. So far,
-	 * none of these are justified.
+	 * Per-task RV monitor, fixed in CONFIG_RV_PER_TASK_MONITORS.
+	 * If memory becomes a concern, we can think about a dynamic method.
 	 */
-	union rv_task_monitor		rv[RV_PER_TASK_MONITORS];
+	union rv_task_monitor		rv[CONFIG_RV_PER_TASK_MONITORS];
 #endif
 
 #ifdef CONFIG_USER_EVENTS
diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig
index 942d57575e67..c11bf7e61ebf 100644
--- a/kernel/trace/rv/Kconfig
+++ b/kernel/trace/rv/Kconfig
@@ -32,6 +32,15 @@ menuconfig RV
 	  For further information, see:
 	    Documentation/trace/rv/runtime-verification.rst
 
+config RV_PER_TASK_MONITORS
+	int "Maximum number of per-task monitor"
+	depends on RV
+	range 1 8
+	default 2
+	help
+	  This option configures the maximum number of per-task RV monitors that can run
+	  simultaneously.
+
 source "kernel/trace/rv/monitors/wip/Kconfig"
 source "kernel/trace/rv/monitors/wwnr/Kconfig"
 source "kernel/trace/rv/monitors/sched/Kconfig"
diff --git a/kernel/trace/rv/monitors/rtapp/Kconfig b/kernel/trace/rv/monitors/rtapp/Kconfig
index b7415c3570bb..1ce9370a9ba8 100644
--- a/kernel/trace/rv/monitors/rtapp/Kconfig
+++ b/kernel/trace/rv/monitors/rtapp/Kconfig
@@ -1,5 +1,6 @@
 config RV_MON_RTAPP
 	depends on RV
+	depends on RV_PER_TASK_MONITORS >= 2
 	bool "rtapp monitor"
 	help
 	  Collection of monitors to check for common problems with real-time
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index e25d65fe432a..108429d16ec1 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -165,7 +165,7 @@ struct dentry *get_monitors_root(void)
 LIST_HEAD(rv_monitors_list);
 
 static int task_monitor_count;
-static bool task_monitor_slots[RV_PER_TASK_MONITORS];
+static bool task_monitor_slots[CONFIG_RV_PER_TASK_MONITORS];
 
 int rv_get_task_monitor_slot(void)
 {
@@ -173,12 +173,12 @@ int rv_get_task_monitor_slot(void)
 
 	lockdep_assert_held(&rv_interface_lock);
 
-	if (task_monitor_count == RV_PER_TASK_MONITORS)
+	if (task_monitor_count == CONFIG_RV_PER_TASK_MONITORS)
 		return -EBUSY;
 
 	task_monitor_count++;
 
-	for (i = 0; i < RV_PER_TASK_MONITORS; i++) {
+	for (i = 0; i < CONFIG_RV_PER_TASK_MONITORS; i++) {
 		if (task_monitor_slots[i] == false) {
 			task_monitor_slots[i] = true;
 			return i;
@@ -194,7 +194,7 @@ void rv_put_task_monitor_slot(int slot)
 {
 	lockdep_assert_held(&rv_interface_lock);
 
-	if (slot < 0 || slot >= RV_PER_TASK_MONITORS) {
+	if (slot < 0 || slot >= CONFIG_RV_PER_TASK_MONITORS) {
 		WARN_ONCE(1, "RV releasing an invalid slot!: %d\n", slot);
 		return;
 	}
-- 
cgit v1.2.3


From 67c0170566b55b1f6ee3567c94ff679104277e2d Mon Sep 17 00:00:00 2001
From: Kamil Horák - 2N <kamilh@axis.com>
Date: Tue, 8 Jul 2025 11:01:37 +0200
Subject: net: phy: MII-Lite PHY interface mode
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Some Broadcom PHYs are capable to operate in simplified MII mode,
without TXER, RXER, CRS and COL signals as defined for the MII.
The MII-Lite mode can be used on most Ethernet controllers with full
MII interface by just leaving the input signals (RXER, CRS, COL)
inactive. The absence of COL signal makes half-duplex link modes
impossible but does not interfere with BroadR-Reach link modes on
Broadcom PHYs, because they are all full-duplex only.

Add MII-Lite interface mode, especially for Broadcom two-wire PHYs.

Signed-off-by: Kamil Horák - 2N <kamilh@axis.com>
Reviewed-by: Maxime Chevallier <maxime.chevallier@bootlin.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250708090140.61355-2-kamilh@axis.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/phy.rst | 7 +++++++
 drivers/net/phy/phy-core.c       | 1 +
 drivers/net/phy/phy_caps.c       | 4 ++++
 drivers/net/phy/phylink.c        | 1 +
 include/linux/phy.h              | 4 ++++
 5 files changed, 17 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/networking/phy.rst b/Documentation/networking/phy.rst
index f64641417c54..7f159043ad5a 100644
--- a/Documentation/networking/phy.rst
+++ b/Documentation/networking/phy.rst
@@ -333,6 +333,13 @@ Some of the interface modes are described below:
     SerDes lane, each port having speeds of 2.5G / 1G / 100M / 10M achieved
     through symbol replication. The PCS expects the standard USXGMII code word.
 
+``PHY_INTERFACE_MODE_MIILITE``
+    Non-standard, simplified MII mode, without TXER, RXER, CRS and COL signals
+    as defined for the MII. The absence of COL signal makes half-duplex link
+    modes impossible but does not interfere with BroadR-Reach link modes on
+    Broadcom (and other two-wire Ethernet) PHYs, because they are full-duplex
+    only.
+
 Pause frames / flow control
 ===========================
 
diff --git a/drivers/net/phy/phy-core.c b/drivers/net/phy/phy-core.c
index c480bb40fa73..605ca20ae192 100644
--- a/drivers/net/phy/phy-core.c
+++ b/drivers/net/phy/phy-core.c
@@ -115,6 +115,7 @@ int phy_interface_num_ports(phy_interface_t interface)
 		return 0;
 	case PHY_INTERFACE_MODE_INTERNAL:
 	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_MIILITE:
 	case PHY_INTERFACE_MODE_GMII:
 	case PHY_INTERFACE_MODE_TBI:
 	case PHY_INTERFACE_MODE_REVMII:
diff --git a/drivers/net/phy/phy_caps.c b/drivers/net/phy/phy_caps.c
index d11ce1c7e712..2cc9ee97e867 100644
--- a/drivers/net/phy/phy_caps.c
+++ b/drivers/net/phy/phy_caps.c
@@ -316,6 +316,10 @@ unsigned long phy_caps_from_interface(phy_interface_t interface)
 		link_caps |= BIT(LINK_CAPA_100HD) | BIT(LINK_CAPA_100FD);
 		break;
 
+	case PHY_INTERFACE_MODE_MIILITE:
+		link_caps |= BIT(LINK_CAPA_10FD) | BIT(LINK_CAPA_100FD);
+		break;
+
 	case PHY_INTERFACE_MODE_TBI:
 	case PHY_INTERFACE_MODE_MOCA:
 	case PHY_INTERFACE_MODE_RTBI:
diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c
index f5473510b762..c7f867b361dd 100644
--- a/drivers/net/phy/phylink.c
+++ b/drivers/net/phy/phylink.c
@@ -237,6 +237,7 @@ static int phylink_interface_max_speed(phy_interface_t interface)
 	case PHY_INTERFACE_MODE_SMII:
 	case PHY_INTERFACE_MODE_REVMII:
 	case PHY_INTERFACE_MODE_MII:
+	case PHY_INTERFACE_MODE_MIILITE:
 		return SPEED_100;
 
 	case PHY_INTERFACE_MODE_TBI:
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 543a94751a6b..4c2b8b6e7187 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -106,6 +106,7 @@ extern const int phy_basic_ports_array[3];
  * @PHY_INTERFACE_MODE_50GBASER: 50GBase-R - with Clause 134 FEC
  * @PHY_INTERFACE_MODE_LAUI: 50 Gigabit Attachment Unit Interface
  * @PHY_INTERFACE_MODE_100GBASEP: 100GBase-P - with Clause 134 FEC
+ * @PHY_INTERFACE_MODE_MIILITE: MII-Lite - MII without RXER TXER CRS COL
  * @PHY_INTERFACE_MODE_MAX: Book keeping
  *
  * Describes the interface between the MAC and PHY.
@@ -150,6 +151,7 @@ typedef enum {
 	PHY_INTERFACE_MODE_50GBASER,
 	PHY_INTERFACE_MODE_LAUI,
 	PHY_INTERFACE_MODE_100GBASEP,
+	PHY_INTERFACE_MODE_MIILITE,
 	PHY_INTERFACE_MODE_MAX,
 } phy_interface_t;
 
@@ -272,6 +274,8 @@ static inline const char *phy_modes(phy_interface_t interface)
 		return "laui";
 	case PHY_INTERFACE_MODE_100GBASEP:
 		return "100gbase-p";
+	case PHY_INTERFACE_MODE_MIILITE:
+		return "mii-lite";
 	default:
 		return "unknown";
 	}
-- 
cgit v1.2.3


From 34bf222824f6c9ac03620ee18aaf93d3b6138db3 Mon Sep 17 00:00:00 2001
From: Kamil Horák - 2N <kamilh@axis.com>
Date: Tue, 8 Jul 2025 11:01:39 +0200
Subject: net: phy: bcm5481x: MII-Lite activation
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Broadcom PHYs featuring the BroadR-Reach two-wire link mode are usually
capable to operate in simplified MII mode, without TXER, RXER, CRS and
COL signals as defined for the MII. The absence of COL signal makes
half-duplex link modes impossible, however, the BroadR-Reach modes are
all full-duplex only.
Depending on the IC encapsulation, there exist MII-Lite-only PHYs such
as bcm54811 in MLP. The PHY itself is hardware-strapped to select among
multiple RGMII and MII-Lite modes, but the MII-Lite mode must be also
activated by software.

Add MII-Lite activation for bcm5481x PHYs.

Signed-off-by: Kamil Horák - 2N <kamilh@axis.com>
Reviewed-by: Florian Fainelli <florian.fainelli@broadcom.com>
Reviewed-by: Russell King (Oracle) <rmk+kernel@armlinux.org.uk>
Link: https://patch.msgid.link/20250708090140.61355-4-kamilh@axis.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/phy/broadcom.c | 14 +++++++++++++-
 include/linux/brcmphy.h    |  6 ++++++
 2 files changed, 19 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/phy/broadcom.c b/drivers/net/phy/broadcom.c
index 9b1de54fd483..8547983bd72f 100644
--- a/drivers/net/phy/broadcom.c
+++ b/drivers/net/phy/broadcom.c
@@ -407,7 +407,7 @@ static int bcm5481x_set_brrmode(struct phy_device *phydev, bool on)
 static int bcm54811_config_init(struct phy_device *phydev)
 {
 	struct bcm54xx_phy_priv *priv = phydev->priv;
-	int err, reg;
+	int err, reg, exp_sync_ethernet;
 
 	/* Enable CLK125 MUX on LED4 if ref clock is enabled. */
 	if (!(phydev->dev_flags & PHY_BRCM_RX_REFCLK_UNUSED)) {
@@ -424,6 +424,18 @@ static int bcm54811_config_init(struct phy_device *phydev)
 	if (priv->brr_mode)
 		phydev->autoneg = 0;
 
+	/* Enable MII Lite (No TXER, RXER, CRS, COL) if configured */
+	if (phydev->interface == PHY_INTERFACE_MODE_MIILITE)
+		exp_sync_ethernet = BCM_EXP_SYNC_ETHERNET_MII_LITE;
+	else
+		exp_sync_ethernet = 0;
+
+	err = bcm_phy_modify_exp(phydev, BCM_EXP_SYNC_ETHERNET,
+				 BCM_EXP_SYNC_ETHERNET_MII_LITE,
+				 exp_sync_ethernet);
+	if (err < 0)
+		return err;
+
 	return bcm5481x_set_brrmode(phydev, priv->brr_mode);
 }
 
diff --git a/include/linux/brcmphy.h b/include/linux/brcmphy.h
index 028b3e00378e..15c35655f482 100644
--- a/include/linux/brcmphy.h
+++ b/include/linux/brcmphy.h
@@ -182,6 +182,12 @@
 #define BCM_LED_MULTICOLOR_ACT		0x9
 #define BCM_LED_MULTICOLOR_PROGRAM	0xa
 
+/*
+ * Broadcom Synchronous Ethernet Controls (expansion register 0x0E)
+ */
+#define BCM_EXP_SYNC_ETHERNET		(MII_BCM54XX_EXP_SEL_ER + 0x0E)
+#define BCM_EXP_SYNC_ETHERNET_MII_LITE	BIT(11)
+
 /*
  * BCM5482: Shadow registers
  * Shadow values go into bits [14:10] of register 0x1c to select a shadow
-- 
cgit v1.2.3


From 82241a83cd15aaaf28200a40ad1a8b480012edaf Mon Sep 17 00:00:00 2001
From: Baolin Wang <baolin.wang@linux.alibaba.com>
Date: Thu, 5 Jun 2025 20:58:29 +0800
Subject: mm: fix the inaccurate memory statistics issue for users

On some large machines with a high number of CPUs running a 64K pagesize
kernel, we found that the 'RES' field is always 0 displayed by the top
command for some processes, which will cause a lot of confusion for users.

    PID USER      PR  NI    VIRT    RES    SHR S  %CPU  %MEM     TIME+ COMMAND
 875525 root      20   0   12480      0      0 R   0.3   0.0   0:00.08 top
      1 root      20   0  172800      0      0 S   0.0   0.0   0:04.52 systemd

The main reason is that the batch size of the percpu counter is quite
large on these machines, caching a significant percpu value, since
converting mm's rss stats into percpu_counter by commit f1a7941243c1 ("mm:
convert mm's rss stats into percpu_counter").  Intuitively, the batch
number should be optimized, but on some paths, performance may take
precedence over statistical accuracy.  Therefore, introducing a new
interface to add the percpu statistical count and display it to users,
which can remove the confusion.  In addition, this change is not expected
to be on a performance-critical path, so the modification should be
acceptable.

In addition, the 'mm->rss_stat' is updated by using add_mm_counter() and
dec/inc_mm_counter(), which are all wrappers around
percpu_counter_add_batch().  In percpu_counter_add_batch(), there is
percpu batch caching to avoid 'fbc->lock' contention.  This patch changes
task_mem() and task_statm() to get the accurate mm counters under the
'fbc->lock', but this should not exacerbate kernel 'mm->rss_stat' lock
contention due to the percpu batch caching of the mm counters.  The
following test also confirm the theoretical analysis.

I run the stress-ng that stresses anon page faults in 32 threads on my 32
cores machine, while simultaneously running a script that starts 32
threads to busy-loop pread each stress-ng thread's /proc/pid/status
interface.  From the following data, I did not observe any obvious impact
of this patch on the stress-ng tests.

w/o patch:
stress-ng: info:  [6848]          4,399,219,085,152 CPU Cycles          67.327 B/sec
stress-ng: info:  [6848]          1,616,524,844,832 Instructions          24.740 B/sec (0.367 instr. per cycle)
stress-ng: info:  [6848]          39,529,792 Page Faults Total           0.605 M/sec
stress-ng: info:  [6848]          39,529,792 Page Faults Minor           0.605 M/sec

w/patch:
stress-ng: info:  [2485]          4,462,440,381,856 CPU Cycles          68.382 B/sec
stress-ng: info:  [2485]          1,615,101,503,296 Instructions          24.750 B/sec (0.362 instr. per cycle)
stress-ng: info:  [2485]          39,439,232 Page Faults Total           0.604 M/sec
stress-ng: info:  [2485]          39,439,232 Page Faults Minor           0.604 M/sec

On comparing a very simple app which just allocates & touches some
memory against v6.1 (which doesn't have f1a7941243c1) and latest Linus
tree (4c06e63b9203) I can see that on latest Linus tree the values for
VmRSS, RssAnon and RssFile from /proc/self/status are all zeroes while
they do report values on v6.1 and a Linus tree with this patch.

Link: https://lkml.kernel.org/r/f4586b17f66f97c174f7fd1f8647374fdb53de1c.1749119050.git.baolin.wang@linux.alibaba.com
Fixes: f1a7941243c1 ("mm: convert mm's rss stats into percpu_counter")
Signed-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Tested-by: Aboorva Devarajan <aboorvad@linux.ibm.com>
Tested-by Donet Tom <donettom@linux.ibm.com>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: SeongJae Park <sj@kernel.org>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: David Hildenbrand <david@redhat.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/task_mmu.c | 14 +++++++-------
 include/linux/mm.h |  5 +++++
 2 files changed, 12 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 4be91eb6ea5c..751479eb128f 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -36,9 +36,9 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	unsigned long text, lib, swap, anon, file, shmem;
 	unsigned long hiwater_vm, total_vm, hiwater_rss, total_rss;
 
-	anon = get_mm_counter(mm, MM_ANONPAGES);
-	file = get_mm_counter(mm, MM_FILEPAGES);
-	shmem = get_mm_counter(mm, MM_SHMEMPAGES);
+	anon = get_mm_counter_sum(mm, MM_ANONPAGES);
+	file = get_mm_counter_sum(mm, MM_FILEPAGES);
+	shmem = get_mm_counter_sum(mm, MM_SHMEMPAGES);
 
 	/*
 	 * Note: to minimize their overhead, mm maintains hiwater_vm and
@@ -59,7 +59,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	text = min(text, mm->exec_vm << PAGE_SHIFT);
 	lib = (mm->exec_vm << PAGE_SHIFT) - text;
 
-	swap = get_mm_counter(mm, MM_SWAPENTS);
+	swap = get_mm_counter_sum(mm, MM_SWAPENTS);
 	SEQ_PUT_DEC("VmPeak:\t", hiwater_vm);
 	SEQ_PUT_DEC(" kB\nVmSize:\t", total_vm);
 	SEQ_PUT_DEC(" kB\nVmLck:\t", mm->locked_vm);
@@ -92,12 +92,12 @@ unsigned long task_statm(struct mm_struct *mm,
 			 unsigned long *shared, unsigned long *text,
 			 unsigned long *data, unsigned long *resident)
 {
-	*shared = get_mm_counter(mm, MM_FILEPAGES) +
-			get_mm_counter(mm, MM_SHMEMPAGES);
+	*shared = get_mm_counter_sum(mm, MM_FILEPAGES) +
+			get_mm_counter_sum(mm, MM_SHMEMPAGES);
 	*text = (PAGE_ALIGN(mm->end_code) - (mm->start_code & PAGE_MASK))
 								>> PAGE_SHIFT;
 	*data = mm->data_vm + mm->stack_vm;
-	*resident = *shared + get_mm_counter(mm, MM_ANONPAGES);
+	*resident = *shared + get_mm_counter_sum(mm, MM_ANONPAGES);
 	return mm->total_vm;
 }
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0ef2ba0c667a..fa538feaa8d9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2568,6 +2568,11 @@ static inline unsigned long get_mm_counter(struct mm_struct *mm, int member)
 	return percpu_counter_read_positive(&mm->rss_stat[member]);
 }
 
+static inline unsigned long get_mm_counter_sum(struct mm_struct *mm, int member)
+{
+	return percpu_counter_sum_positive(&mm->rss_stat[member]);
+}
+
 void mm_trace_rss_stat(struct mm_struct *mm, int member);
 
 static inline void add_mm_counter(struct mm_struct *mm, int member, long value)
-- 
cgit v1.2.3


From db6cc3f4ac2e6cdc898fc9cbc8b32ae1bf56bdad Mon Sep 17 00:00:00 2001
From: Chen Yu <yu.c.chen@intel.com>
Date: Fri, 4 Jul 2025 21:56:20 +0800
Subject: Revert "sched/numa: add statistics of numa balance task"

This reverts commit ad6b26b6a0a79166b53209df2ca1cf8636296382.

This commit introduces per-memcg/task NUMA balance statistics, but
unfortunately it introduced a NULL pointer exception due to the following
race condition: After a swap task candidate was chosen, its mm_struct
pointer was set to NULL due to task exit.  Later, when performing the
actual task swapping, the p->mm caused the problem.

CPU0                                   CPU1
:
...
task_numa_migrate
     task_numa_find_cpu
      task_numa_compare
        # a normal task p is chosen
        env->best_task = p

                                          # p exit:
                                          exit_signals(p);
                                             p->flags |= PF_EXITING
                                          exit_mm
                                             p->mm = NULL;

      migrate_swap_stop
        __migrate_swap_task((arg->src_task, arg->dst_cpu)
         count_memcg_event_mm(p->mm, NUMA_TASK_SWAP)# p->mm is NULL

task_lock() should be held and the PF_EXITING flag needs to be checked to
prevent this from happening.  After discussion, the conclusion was that
adding a lock is not worthwhile for some statistics calculations.  Revert
the change and rely on the tracepoint for this purpose.

Link: https://lkml.kernel.org/r/20250704135620.685752-1-yu.c.chen@intel.com
Link: https://lkml.kernel.org/r/20250708064917.BBD13C4CEED@smtp.kernel.org
Fixes: ad6b26b6a0a7 ("sched/numa: add statistics of numa balance task")
Signed-off-by: Chen Yu <yu.c.chen@intel.com>
Reported-by: Jirka Hladky <jhladky@redhat.com>
Closes: https://lore.kernel.org/all/CAE4VaGBLJxpd=NeRJXpSCuw=REhC5LWJpC29kDy-Zh2ZDyzQZA@mail.gmail.com/
Reported-by: Srikanth Aithal <Srikanth.Aithal@amd.com>
Reported-by: Suneeth D <Suneeth.D@amd.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Jiri Hladky <jhladky@redhat.com>
Cc: Libo Chen <libo.chen@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/cgroup-v2.rst | 6 ------
 include/linux/sched.h                   | 4 ----
 include/linux/vm_event_item.h           | 2 --
 kernel/sched/core.c                     | 9 ++-------
 kernel/sched/debug.c                    | 4 ----
 mm/memcontrol.c                         | 2 --
 mm/vmstat.c                             | 2 --
 7 files changed, 2 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index 0cc35a14afbe..bd98ea3175ec 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/Documentation/admin-guide/cgroup-v2.rst
@@ -1732,12 +1732,6 @@ The following nested keys are defined.
 	  numa_hint_faults (npn)
 		Number of NUMA hinting faults.
 
-	  numa_task_migrated (npn)
-		Number of task migration by NUMA balancing.
-
-	  numa_task_swapped (npn)
-		Number of task swap by NUMA balancing.
-
 	  pgdemote_kswapd
 		Number of pages demoted by kswapd.
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52..aa9c5be7a632 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -548,10 +548,6 @@ struct sched_statistics {
 	u64				nr_failed_migrations_running;
 	u64				nr_failed_migrations_hot;
 	u64				nr_forced_migrations;
-#ifdef CONFIG_NUMA_BALANCING
-	u64				numa_task_migrated;
-	u64				numa_task_swapped;
-#endif
 
 	u64				nr_wakeups;
 	u64				nr_wakeups_sync;
diff --git a/include/linux/vm_event_item.h b/include/linux/vm_event_item.h
index 91a3ce9a2687..9e15a088ba38 100644
--- a/include/linux/vm_event_item.h
+++ b/include/linux/vm_event_item.h
@@ -66,8 +66,6 @@ enum vm_event_item { PGPGIN, PGPGOUT, PSWPIN, PSWPOUT,
 		NUMA_HINT_FAULTS,
 		NUMA_HINT_FAULTS_LOCAL,
 		NUMA_PAGE_MIGRATE,
-		NUMA_TASK_MIGRATE,
-		NUMA_TASK_SWAP,
 #endif
 #ifdef CONFIG_MIGRATION
 		PGMIGRATE_SUCCESS, PGMIGRATE_FAIL,
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ec68fc686bd7..81c6df746df1 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -3362,10 +3362,6 @@ void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
 #ifdef CONFIG_NUMA_BALANCING
 static void __migrate_swap_task(struct task_struct *p, int cpu)
 {
-	__schedstat_inc(p->stats.numa_task_swapped);
-	count_vm_numa_event(NUMA_TASK_SWAP);
-	count_memcg_event_mm(p->mm, NUMA_TASK_SWAP);
-
 	if (task_on_rq_queued(p)) {
 		struct rq *src_rq, *dst_rq;
 		struct rq_flags srf, drf;
@@ -7939,9 +7935,8 @@ int migrate_task_to(struct task_struct *p, int target_cpu)
 	if (!cpumask_test_cpu(target_cpu, p->cpus_ptr))
 		return -EINVAL;
 
-	__schedstat_inc(p->stats.numa_task_migrated);
-	count_vm_numa_event(NUMA_TASK_MIGRATE);
-	count_memcg_event_mm(p->mm, NUMA_TASK_MIGRATE);
+	/* TODO: This is not properly updating schedstats */
+
 	trace_sched_move_numa(p, curr_cpu, target_cpu);
 	return stop_one_cpu(curr_cpu, migration_cpu_stop, &arg);
 }
diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
index 9d71baf08075..557246880a7e 100644
--- a/kernel/sched/debug.c
+++ b/kernel/sched/debug.c
@@ -1210,10 +1210,6 @@ void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
 		P_SCHEDSTAT(nr_failed_migrations_running);
 		P_SCHEDSTAT(nr_failed_migrations_hot);
 		P_SCHEDSTAT(nr_forced_migrations);
-#ifdef CONFIG_NUMA_BALANCING
-		P_SCHEDSTAT(numa_task_migrated);
-		P_SCHEDSTAT(numa_task_swapped);
-#endif
 		P_SCHEDSTAT(nr_wakeups);
 		P_SCHEDSTAT(nr_wakeups_sync);
 		P_SCHEDSTAT(nr_wakeups_migrate);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 902da8a9c643..70fdeda1120b 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -474,8 +474,6 @@ static const unsigned int memcg_vm_event_stat[] = {
 	NUMA_PAGE_MIGRATE,
 	NUMA_PTE_UPDATES,
 	NUMA_HINT_FAULTS,
-	NUMA_TASK_MIGRATE,
-	NUMA_TASK_SWAP,
 #endif
 };
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 429ae5339bfe..a78d70ddeacd 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1346,8 +1346,6 @@ const char * const vmstat_text[] = {
 	"numa_hint_faults",
 	"numa_hint_faults_local",
 	"numa_pages_migrated",
-	"numa_task_migrated",
-	"numa_task_swapped",
 #endif
 #ifdef CONFIG_MIGRATION
 	"pgmigrate_success",
-- 
cgit v1.2.3


From de195c67bfcbc770bb6327bbfd3010f1c371216a Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Thu, 29 May 2025 18:15:45 +0100
Subject: mm: ksm: have KSM VMA checks not require a VMA pointer

Patch series "mm: ksm: prevent KSM from breaking merging of new VMAs", v3.

When KSM-by-default is established using prctl(PR_SET_MEMORY_MERGE), this
defaults all newly mapped VMAs to having VM_MERGEABLE set, and thus makes
them available to KSM for samepage merging.  It also sets VM_MERGEABLE in
all existing VMAs.

However this causes an issue upon mapping of new VMAs - the initial flags
will never have VM_MERGEABLE set when attempting a merge with adjacent
VMAs (this is set later in the mmap() logic), and adjacent VMAs will
ALWAYS have VM_MERGEABLE set.

This renders all newly mapped VMAs unmergeable.

To avoid this, this series performs the check for PR_SET_MEMORY_MERGE far
earlier in the mmap() logic, prior to the merge being attempted.

However we run into complexity with the depreciated .mmap() callback - if
a driver hooks this, it might change flags which adjust KSM merge
eligibility.

We have to worry about this because, while KSM is only applicable to
private mappings, this includes both anonymous and MAP_PRIVATE-mapped
file-backed mappings.

This isn't a problem for brk(), where the VMA must be anonymous.  However
in mmap() we must be conservative - if the VMA is anonymous then we can
always proceed, however if not, we permit only shmem mappings (whose .mmap
hook does not affect KSM eligibility) and drivers which implement
.mmap_prepare() (invoked prior to the KSM eligibility check).

If we can't be sure of the driver changing things, then we maintain the
same behaviour of performing the KSM check later in the mmap() logic (and
thus losing new VMA mergeability).

A great many use-cases for this logic will use anonymous mappings any
rate, so this change should already cover the majority of actual KSM
use-cases.


This patch (of 4):

In subsequent commits we are going to determine KSM eligibility prior to a
VMA being constructed, at which point we will of course not yet have
access to a VMA pointer.

It is trivial to boil down the check logic to be parameterised on
mm_struct, file and VMA flags, so do so.

As a part of this change, additionally expose and use file_is_dax() to
determine whether a file is being mapped under a DAX inode.

Link: https://lkml.kernel.org/r/cover.1748537921.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/36ad13eb50cdbd8aac6dcfba22c65d5031667295.1748537921.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Xu Xin <xu.xin16@zte.com.cn>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Stefan Roesch <shr@devkernel.io>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/fs.h |  7 ++++++-
 mm/ksm.c           | 32 ++++++++++++++++++++------------
 2 files changed, 26 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 040c0036320f..62634af97da6 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -3726,9 +3726,14 @@ void setattr_copy(struct mnt_idmap *, struct inode *inode,
 
 extern int file_update_time(struct file *file);
 
+static inline bool file_is_dax(const struct file *file)
+{
+	return file && IS_DAX(file->f_mapping->host);
+}
+
 static inline bool vma_is_dax(const struct vm_area_struct *vma)
 {
-	return vma->vm_file && IS_DAX(vma->vm_file->f_mapping->host);
+	return file_is_dax(vma->vm_file);
 }
 
 static inline bool vma_is_fsdax(struct vm_area_struct *vma)
diff --git a/mm/ksm.c b/mm/ksm.c
index 8583fb91ef13..08d486f188ff 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -677,28 +677,33 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr, bool lock_v
 	return (ret & VM_FAULT_OOM) ? -ENOMEM : 0;
 }
 
-static bool vma_ksm_compatible(struct vm_area_struct *vma)
+static bool ksm_compatible(const struct file *file, vm_flags_t vm_flags)
 {
-	if (vma->vm_flags & (VM_SHARED  | VM_MAYSHARE   | VM_PFNMAP  |
-			     VM_IO      | VM_DONTEXPAND | VM_HUGETLB |
-			     VM_MIXEDMAP| VM_DROPPABLE))
+	if (vm_flags & (VM_SHARED   | VM_MAYSHARE   | VM_PFNMAP  |
+			VM_IO       | VM_DONTEXPAND | VM_HUGETLB |
+			VM_MIXEDMAP | VM_DROPPABLE))
 		return false;		/* just ignore the advice */
 
-	if (vma_is_dax(vma))
+	if (file_is_dax(file))
 		return false;
 
 #ifdef VM_SAO
-	if (vma->vm_flags & VM_SAO)
+	if (vm_flags & VM_SAO)
 		return false;
 #endif
 #ifdef VM_SPARC_ADI
-	if (vma->vm_flags & VM_SPARC_ADI)
+	if (vm_flags & VM_SPARC_ADI)
 		return false;
 #endif
 
 	return true;
 }
 
+static bool vma_ksm_compatible(struct vm_area_struct *vma)
+{
+	return ksm_compatible(vma->vm_file, vma->vm_flags);
+}
+
 static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm,
 		unsigned long addr)
 {
@@ -2696,14 +2701,17 @@ static int ksm_scan_thread(void *nothing)
 	return 0;
 }
 
-static void __ksm_add_vma(struct vm_area_struct *vma)
+static bool __ksm_should_add_vma(const struct file *file, vm_flags_t vm_flags)
 {
-	unsigned long vm_flags = vma->vm_flags;
-
 	if (vm_flags & VM_MERGEABLE)
-		return;
+		return false;
+
+	return ksm_compatible(file, vm_flags);
+}
 
-	if (vma_ksm_compatible(vma))
+static void __ksm_add_vma(struct vm_area_struct *vma)
+{
+	if (__ksm_should_add_vma(vma->vm_file, vma->vm_flags))
 		vm_flags_set(vma, VM_MERGEABLE);
 }
 
-- 
cgit v1.2.3


From cf7e7a3503df0b71afd68ee84e9a09d4514cc2dd Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Thu, 29 May 2025 18:15:47 +0100
Subject: mm: prevent KSM from breaking VMA merging for new VMAs

If a user wishes to enable KSM mergeability for an entire process and all
fork/exec'd processes that come after it, they use the prctl()
PR_SET_MEMORY_MERGE operation.

This defaults all newly mapped VMAs to have the VM_MERGEABLE VMA flag set
(in order to indicate they are KSM mergeable), as well as setting this
flag for all existing VMAs and propagating this across fork/exec.

However it also breaks VMA merging for new VMAs, both in the process and
all forked (and fork/exec'd) child processes.

This is because when a new mapping is proposed, the flags specified will
never have VM_MERGEABLE set.  However all adjacent VMAs will already have
VM_MERGEABLE set, rendering VMAs unmergeable by default.

To work around this, we try to set the VM_MERGEABLE flag prior to
attempting a merge.  In the case of brk() this can always be done.

However on mmap() things are more complicated - while KSM is not supported
for MAP_SHARED file-backed mappings, it is supported for MAP_PRIVATE
file-backed mappings.

These mappings may have deprecated .mmap() callbacks specified which
could, in theory, adjust flags and thus KSM eligibility.

So we check to determine whether this is possible.  If not, we set
VM_MERGEABLE prior to the merge attempt on mmap(), otherwise we retain the
previous behaviour.

This fixes VMA merging for all new anonymous mappings, which covers the
majority of real-world cases, so we should see a significant improvement
in VMA mergeability.

For MAP_PRIVATE file-backed mappings, those which implement the
.mmap_prepare() hook and shmem are both known to be safe, so we allow
these, disallowing all other cases.

Also add stubs for newly introduced function invocations to VMA userland
testing.

[lorenzo.stoakes@oracle.com: correctly invoke late KSM check after mmap hook]
  Link: https://lkml.kernel.org/r/5861f8f6-cf5a-4d82-a062-139fb3f9cddb@lucifer.local
Link: https://lkml.kernel.org/r/3ba660af716d87a18ca5b4e635f2101edeb56340.1748537921.git.lorenzo.stoakes@oracle.com
Fixes: d7597f59d1d3 ("mm: add new api to enable ksm per process") # please no backport!
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Chengming Zhou <chengming.zhou@linux.dev>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Xu Xin <xu.xin16@zte.com.cn>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Stefan Roesch <shr@devkernel.io>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/ksm.h              |  8 ++++---
 mm/ksm.c                         | 18 +++++++++-----
 mm/vma.c                         | 51 ++++++++++++++++++++++++++++++++++++++--
 tools/testing/vma/vma_internal.h | 11 +++++++++
 4 files changed, 77 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index d73095b5cd96..51787f0b0208 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -17,8 +17,8 @@
 #ifdef CONFIG_KSM
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
 		unsigned long end, int advice, unsigned long *vm_flags);
-
-void ksm_add_vma(struct vm_area_struct *vma);
+vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file,
+			 vm_flags_t vm_flags);
 int ksm_enable_merge_any(struct mm_struct *mm);
 int ksm_disable_merge_any(struct mm_struct *mm);
 int ksm_disable(struct mm_struct *mm);
@@ -97,8 +97,10 @@ bool ksm_process_mergeable(struct mm_struct *mm);
 
 #else  /* !CONFIG_KSM */
 
-static inline void ksm_add_vma(struct vm_area_struct *vma)
+static inline vm_flags_t ksm_vma_flags(const struct mm_struct *mm,
+		const struct file *file, vm_flags_t vm_flags)
 {
+	return vm_flags;
 }
 
 static inline int ksm_disable(struct mm_struct *mm)
diff --git a/mm/ksm.c b/mm/ksm.c
index d0c763abd499..18b3690bb69a 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2731,16 +2731,22 @@ static int __ksm_del_vma(struct vm_area_struct *vma)
 	return 0;
 }
 /**
- * ksm_add_vma - Mark vma as mergeable if compatible
+ * ksm_vma_flags - Update VMA flags to mark as mergeable if compatible
  *
- * @vma:  Pointer to vma
+ * @mm:       Proposed VMA's mm_struct
+ * @file:     Proposed VMA's file-backed mapping, if any.
+ * @vm_flags: Proposed VMA"s flags.
+ *
+ * Returns: @vm_flags possibly updated to mark mergeable.
  */
-void ksm_add_vma(struct vm_area_struct *vma)
+vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file,
+			 vm_flags_t vm_flags)
 {
-	struct mm_struct *mm = vma->vm_mm;
+	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags) &&
+	    __ksm_should_add_vma(file, vm_flags))
+		vm_flags |= VM_MERGEABLE;
 
-	if (test_bit(MMF_VM_MERGE_ANY, &mm->flags))
-		__ksm_add_vma(vma);
+	return vm_flags;
 }
 
 static void ksm_add_vmas(struct mm_struct *mm)
diff --git a/mm/vma.c b/mm/vma.c
index fef67a66a095..079540ebfb72 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -32,6 +32,9 @@ struct mmap_state {
 	struct vma_munmap_struct vms;
 	struct ma_state mas_detach;
 	struct maple_tree mt_detach;
+
+	/* Determine if we can check KSM flags early in mmap() logic. */
+	bool check_ksm_early;
 };
 
 #define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, flags_, file_) \
@@ -2320,6 +2323,11 @@ static void vms_abort_munmap_vmas(struct vma_munmap_struct *vms,
 	vms_complete_munmap_vmas(vms, mas_detach);
 }
 
+static void update_ksm_flags(struct mmap_state *map)
+{
+	map->flags = ksm_vma_flags(map->mm, map->file, map->flags);
+}
+
 /*
  * __mmap_prepare() - Prepare to gather any overlapping VMAs that need to be
  * unmapped once the map operation is completed, check limits, account mapping
@@ -2424,6 +2432,7 @@ static int __mmap_new_file_vma(struct mmap_state *map,
 			!(map->flags & VM_MAYWRITE) &&
 			(vma->vm_flags & VM_MAYWRITE));
 
+	map->file = vma->vm_file;
 	map->flags = vma->vm_flags;
 
 	return 0;
@@ -2473,6 +2482,11 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
 	if (error)
 		goto free_iter_vma;
 
+	if (!map->check_ksm_early) {
+		update_ksm_flags(map);
+		vm_flags_init(vma, map->flags);
+	}
+
 #ifdef CONFIG_SPARC64
 	/* TODO: Fix SPARC ADI! */
 	WARN_ON_ONCE(!arch_validate_flags(map->flags));
@@ -2490,7 +2504,6 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
 	 */
 	if (!vma_is_anonymous(vma))
 		khugepaged_enter_vma(vma, map->flags);
-	ksm_add_vma(vma);
 	*vmap = vma;
 	return 0;
 
@@ -2593,6 +2606,35 @@ static void set_vma_user_defined_fields(struct vm_area_struct *vma,
 	vma->vm_private_data = map->vm_private_data;
 }
 
+/*
+ * Are we guaranteed no driver can change state such as to preclude KSM merging?
+ * If so, let's set the KSM mergeable flag early so we don't break VMA merging.
+ */
+static bool can_set_ksm_flags_early(struct mmap_state *map)
+{
+	struct file *file = map->file;
+
+	/* Anonymous mappings have no driver which can change them. */
+	if (!file)
+		return true;
+
+	/*
+	 * If .mmap_prepare() is specified, then the driver will have already
+	 * manipulated state prior to updating KSM flags. So no need to worry
+	 * about mmap callbacks modifying VMA flags after the KSM flag has been
+	 * updated here, which could otherwise affect KSM eligibility.
+	 */
+	if (file->f_op->mmap_prepare)
+		return true;
+
+	/* shmem is safe. */
+	if (shmem_file(file))
+		return true;
+
+	/* Any other .mmap callback is not safe. */
+	return false;
+}
+
 static unsigned long __mmap_region(struct file *file, unsigned long addr,
 		unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
 		struct list_head *uf)
@@ -2604,12 +2646,17 @@ static unsigned long __mmap_region(struct file *file, unsigned long addr,
 	VMA_ITERATOR(vmi, mm, addr);
 	MMAP_STATE(map, mm, &vmi, addr, len, pgoff, vm_flags, file);
 
+	map.check_ksm_early = can_set_ksm_flags_early(&map);
+
 	error = __mmap_prepare(&map, uf);
 	if (!error && have_mmap_prepare)
 		error = call_mmap_prepare(&map);
 	if (error)
 		goto abort_munmap;
 
+	if (map.check_ksm_early)
+		update_ksm_flags(&map);
+
 	/* Attempt to merge with adjacent VMAs... */
 	if (map.prev || map.next) {
 		VMG_MMAP_STATE(vmg, &map, /* vma = */ NULL);
@@ -2721,6 +2768,7 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	 * Note: This happens *after* clearing old mappings in some code paths.
 	 */
 	flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
+	flags = ksm_vma_flags(mm, NULL, flags);
 	if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT))
 		return -ENOMEM;
 
@@ -2764,7 +2812,6 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 	mm->map_count++;
 	validate_mm(mm);
-	ksm_add_vma(vma);
 out:
 	perf_event_mmap(vma);
 	mm->total_vm += len >> PAGE_SHIFT;
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 14718ca23a05..0f013784da89 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -1484,4 +1484,15 @@ static inline void vma_set_file(struct vm_area_struct *vma, struct file *file)
 	fput(file);
 }
 
+static inline bool shmem_file(struct file *)
+{
+	return false;
+}
+
+static inline vm_flags_t ksm_vma_flags(const struct mm_struct *, const struct file *,
+			 vm_flags_t vm_flags)
+{
+	return vm_flags;
+}
+
 #endif	/* __MM_VMA_INTERNAL_H */
-- 
cgit v1.2.3


From 792b429db7e0217faf7bce9fe46e7708135cf83c Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Wed, 4 Jun 2025 16:05:44 +0200
Subject: mm/gup: remove (VM_)BUG_ONs

Especially once we hit one of the assertions in
sanity_check_pinned_pages(), observing follow-up assertions failing in
other code can give good clues about what went wrong, so use
VM_WARN_ON_ONCE instead.

While at it, let's just convert all VM_BUG_ON to VM_WARN_ON_ONCE as well.
Add one comment for the pfn_valid() check.

We have to introduce VM_WARN_ON_ONCE_VMA() to make that fly.

Drop the BUG_ON after mmap_read_lock_killable(), if that ever returns
something > 0 we're in bigger trouble.  Convert the other BUG_ON's into
VM_WARN_ON_ONCE as well, they are in a similar domain "should never
happen", but more reasonable to check for during early testing.

[david@redhat.com: use the _FOLIO variant where possible, per Lorenzo]
  Link: https://lkml.kernel.org/r/844bd929-a551-48e3-a12e-285cd65ba580@redhat.com
Link: https://lkml.kernel.org/r/20250604140544.688711-1-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: SeongJae Park <sj@kernel.org>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Acked-by: Michal Hocko <mhocko@suse.com>
Reviewed-by: John Hubbard <jhubbard@nvidia.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Peter Xu <peterx@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmdebug.h | 12 ++++++++++++
 mm/gup.c                | 41 +++++++++++++++++++----------------------
 2 files changed, 31 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmdebug.h b/include/linux/mmdebug.h
index a0a3894900ed..14a45979cccc 100644
--- a/include/linux/mmdebug.h
+++ b/include/linux/mmdebug.h
@@ -89,6 +89,17 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 	}								\
 	unlikely(__ret_warn_once);					\
 })
+#define VM_WARN_ON_ONCE_VMA(cond, vma)		({			\
+	static bool __section(".data..once") __warned;			\
+	int __ret_warn_once = !!(cond);					\
+									\
+	if (unlikely(__ret_warn_once && !__warned)) {			\
+		dump_vma(vma);						\
+		__warned = true;					\
+		WARN_ON(1);						\
+	}								\
+	unlikely(__ret_warn_once);					\
+})
 #define VM_WARN_ON_VMG(cond, vmg)		({			\
 	int __ret_warn = !!(cond);					\
 									\
@@ -115,6 +126,7 @@ void vma_iter_dump_tree(const struct vma_iterator *vmi);
 #define VM_WARN_ON_FOLIO(cond, folio)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE_FOLIO(cond, folio)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_ONCE_MM(cond, mm)  BUILD_BUG_ON_INVALID(cond)
+#define VM_WARN_ON_ONCE_VMA(cond, vma)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ON_VMG(cond, vmg)  BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN_ONCE(cond, format...) BUILD_BUG_ON_INVALID(cond)
 #define VM_WARN(cond, format...) BUILD_BUG_ON_INVALID(cond)
diff --git a/mm/gup.c b/mm/gup.c
index 3c39cbbeebef..7f2644a433a0 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -64,11 +64,11 @@ static inline void sanity_check_pinned_pages(struct page **pages,
 		    !folio_test_anon(folio))
 			continue;
 		if (!folio_test_large(folio) || folio_test_hugetlb(folio))
-			VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page), page);
+			VM_WARN_ON_ONCE_FOLIO(!PageAnonExclusive(&folio->page), folio);
 		else
 			/* Either a PTE-mapped or a PMD-mapped THP. */
-			VM_BUG_ON_PAGE(!PageAnonExclusive(&folio->page) &&
-				       !PageAnonExclusive(page), page);
+			VM_WARN_ON_ONCE_PAGE(!PageAnonExclusive(&folio->page) &&
+					     !PageAnonExclusive(page), page);
 	}
 }
 
@@ -760,8 +760,8 @@ static struct page *follow_huge_pmd(struct vm_area_struct *vma,
 	if (!pmd_write(pmdval) && gup_must_unshare(vma, flags, page))
 		return ERR_PTR(-EMLINK);
 
-	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
-			!PageAnonExclusive(page), page);
+	VM_WARN_ON_ONCE_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
+			     !PageAnonExclusive(page), page);
 
 	ret = try_grab_folio(page_folio(page), 1, flags);
 	if (ret)
@@ -899,8 +899,8 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		goto out;
 	}
 
-	VM_BUG_ON_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
-		       !PageAnonExclusive(page), page);
+	VM_WARN_ON_ONCE_PAGE((flags & FOLL_PIN) && PageAnon(page) &&
+			     !PageAnonExclusive(page), page);
 
 	/* try_grab_folio() does nothing unless FOLL_GET or FOLL_PIN is set. */
 	ret = try_grab_folio(folio, 1, flags);
@@ -1180,7 +1180,7 @@ static int faultin_page(struct vm_area_struct *vma,
 	if (unshare) {
 		fault_flags |= FAULT_FLAG_UNSHARE;
 		/* FAULT_FLAG_WRITE and FAULT_FLAG_UNSHARE are incompatible */
-		VM_BUG_ON(fault_flags & FAULT_FLAG_WRITE);
+		VM_WARN_ON_ONCE(fault_flags & FAULT_FLAG_WRITE);
 	}
 
 	ret = handle_mm_fault(vma, address, fault_flags, NULL);
@@ -1760,10 +1760,7 @@ static __always_inline long __get_user_pages_locked(struct mm_struct *mm,
 		}
 
 		/* VM_FAULT_RETRY or VM_FAULT_COMPLETED cannot return errors */
-		if (!*locked) {
-			BUG_ON(ret < 0);
-			BUG_ON(ret >= nr_pages);
-		}
+		VM_WARN_ON_ONCE(!*locked && (ret < 0 || ret >= nr_pages));
 
 		if (ret > 0) {
 			nr_pages -= ret;
@@ -1808,7 +1805,6 @@ retry:
 
 		ret = mmap_read_lock_killable(mm);
 		if (ret) {
-			BUG_ON(ret > 0);
 			if (!pages_done)
 				pages_done = ret;
 			break;
@@ -1819,11 +1815,11 @@ retry:
 				       pages, locked);
 		if (!*locked) {
 			/* Continue to retry until we succeeded */
-			BUG_ON(ret != 0);
+			VM_WARN_ON_ONCE(ret != 0);
 			goto retry;
 		}
 		if (ret != 1) {
-			BUG_ON(ret > 1);
+			VM_WARN_ON_ONCE(ret > 1);
 			if (!pages_done)
 				pages_done = ret;
 			break;
@@ -1885,10 +1881,10 @@ long populate_vma_page_range(struct vm_area_struct *vma,
 	int gup_flags;
 	long ret;
 
-	VM_BUG_ON(!PAGE_ALIGNED(start));
-	VM_BUG_ON(!PAGE_ALIGNED(end));
-	VM_BUG_ON_VMA(start < vma->vm_start, vma);
-	VM_BUG_ON_VMA(end   > vma->vm_end, vma);
+	VM_WARN_ON_ONCE(!PAGE_ALIGNED(start));
+	VM_WARN_ON_ONCE(!PAGE_ALIGNED(end));
+	VM_WARN_ON_ONCE_VMA(start < vma->vm_start, vma);
+	VM_WARN_ON_ONCE_VMA(end   > vma->vm_end, vma);
 	mmap_assert_locked(mm);
 
 	/*
@@ -1957,8 +1953,8 @@ long faultin_page_range(struct mm_struct *mm, unsigned long start,
 	int gup_flags;
 	long ret;
 
-	VM_BUG_ON(!PAGE_ALIGNED(start));
-	VM_BUG_ON(!PAGE_ALIGNED(end));
+	VM_WARN_ON_ONCE(!PAGE_ALIGNED(start));
+	VM_WARN_ON_ONCE(!PAGE_ALIGNED(end));
 	mmap_assert_locked(mm);
 
 	/*
@@ -2914,7 +2910,8 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		} else if (pte_special(pte))
 			goto pte_unmap;
 
-		VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
+		/* If it's not marked as special it must have a valid memmap. */
+		VM_WARN_ON_ONCE(!pfn_valid(pte_pfn(pte)));
 		page = pte_page(pte);
 
 		folio = try_grab_folio_fast(page, 1, flags);
-- 
cgit v1.2.3


From 3800d55250976b7a4bd42c255b267bc242669709 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Wed, 4 Jun 2025 17:14:27 -0400
Subject: mm: rename CONFIG_PAGE_BLOCK_ORDER to CONFIG_PAGE_BLOCK_MAX_ORDER

The config is in fact an additional upper limit of pageblock_order, so
rename it to avoid confusion.

Link: https://lkml.kernel.org/r/20250604211427.1590859-1-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Juan Yescas <jyescas@google.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: "Isaac J. Manjarres" <isaacmanjarres@google.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Masahiro Yamada <masahiroy@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: T.J. Mercier <tjmercier@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h          | 14 +++++++-------
 include/linux/pageblock-flags.h |  8 ++++----
 mm/Kconfig                      | 15 ++++++++-------
 mm/mm_init.c                    |  2 +-
 4 files changed, 20 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 283913d42d7b..5bec8b1d0e66 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -38,19 +38,19 @@
 #define NR_PAGE_ORDERS (MAX_PAGE_ORDER + 1)
 
 /* Defines the order for the number of pages that have a migrate type. */
-#ifndef CONFIG_PAGE_BLOCK_ORDER
-#define PAGE_BLOCK_ORDER MAX_PAGE_ORDER
+#ifndef CONFIG_PAGE_BLOCK_MAX_ORDER
+#define PAGE_BLOCK_MAX_ORDER MAX_PAGE_ORDER
 #else
-#define PAGE_BLOCK_ORDER CONFIG_PAGE_BLOCK_ORDER
-#endif /* CONFIG_PAGE_BLOCK_ORDER */
+#define PAGE_BLOCK_MAX_ORDER CONFIG_PAGE_BLOCK_MAX_ORDER
+#endif /* CONFIG_PAGE_BLOCK_MAX_ORDER */
 
 /*
  * The MAX_PAGE_ORDER, which defines the max order of pages to be allocated
- * by the buddy allocator, has to be larger or equal to the PAGE_BLOCK_ORDER,
+ * by the buddy allocator, has to be larger or equal to the PAGE_BLOCK_MAX_ORDER,
  * which defines the order for the number of pages that can have a migrate type
  */
-#if (PAGE_BLOCK_ORDER > MAX_PAGE_ORDER)
-#error MAX_PAGE_ORDER must be >= PAGE_BLOCK_ORDER
+#if (PAGE_BLOCK_MAX_ORDER > MAX_PAGE_ORDER)
+#error MAX_PAGE_ORDER must be >= PAGE_BLOCK_MAX_ORDER
 #endif
 
 /*
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index e73a4292ef02..6297c6343c55 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -41,18 +41,18 @@ extern unsigned int pageblock_order;
  * Huge pages are a constant size, but don't exceed the maximum allocation
  * granularity.
  */
-#define pageblock_order		MIN_T(unsigned int, HUGETLB_PAGE_ORDER, PAGE_BLOCK_ORDER)
+#define pageblock_order		MIN_T(unsigned int, HUGETLB_PAGE_ORDER, PAGE_BLOCK_MAX_ORDER)
 
 #endif /* CONFIG_HUGETLB_PAGE_SIZE_VARIABLE */
 
 #elif defined(CONFIG_TRANSPARENT_HUGEPAGE)
 
-#define pageblock_order		MIN_T(unsigned int, HPAGE_PMD_ORDER, PAGE_BLOCK_ORDER)
+#define pageblock_order		MIN_T(unsigned int, HPAGE_PMD_ORDER, PAGE_BLOCK_MAX_ORDER)
 
 #else /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-/* If huge pages are not used, group by PAGE_BLOCK_ORDER */
-#define pageblock_order		PAGE_BLOCK_ORDER
+/* If huge pages are not used, group by PAGE_BLOCK_MAX_ORDER */
+#define pageblock_order		PAGE_BLOCK_MAX_ORDER
 
 #endif /* CONFIG_HUGETLB_PAGE */
 
diff --git a/mm/Kconfig b/mm/Kconfig
index 15716b1a5e21..3b2060a61c05 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1005,8 +1005,8 @@ config ARCH_FORCE_MAX_ORDER
 # the default page block order is MAX_PAGE_ORDER (10) as per
 # include/linux/mmzone.h.
 #
-config PAGE_BLOCK_ORDER
-	int "Page Block Order"
+config PAGE_BLOCK_MAX_ORDER
+	int "Page Block Order Upper Limit"
 	range 1 10 if ARCH_FORCE_MAX_ORDER = 0
 	default 10 if ARCH_FORCE_MAX_ORDER = 0
 	range 1 ARCH_FORCE_MAX_ORDER if ARCH_FORCE_MAX_ORDER != 0
@@ -1014,12 +1014,13 @@ config PAGE_BLOCK_ORDER
 	help
 	  The page block order refers to the power of two number of pages that
 	  are physically contiguous and can have a migrate type associated to
-	  them. The maximum size of the page block order is limited by
-	  ARCH_FORCE_MAX_ORDER.
+	  them. The maximum size of the page block order is at least limited by
+	  ARCH_FORCE_MAX_ORDER/MAX_PAGE_ORDER.
 
-	  This config allows overriding the default page block order when the
-	  page block order is required to be smaller than ARCH_FORCE_MAX_ORDER
-	  or MAX_PAGE_ORDER.
+	  This config adds a new upper limit of default page block
+	  order when the page block order is required to be smaller than
+	  ARCH_FORCE_MAX_ORDER/MAX_PAGE_ORDER or other limits
+	  (see include/linux/pageblock-flags.h for details).
 
 	  Reducing pageblock order can negatively impact THP generation
 	  success rate. If your workloads use THP heavily, please use this
diff --git a/mm/mm_init.c b/mm/mm_init.c
index f2944748f526..02f41e2bdf60 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -1509,7 +1509,7 @@ static inline void setup_usemap(struct zone *zone) {}
 /* Initialise the number of pages represented by NR_PAGEBLOCK_BITS */
 void __init set_pageblock_order(void)
 {
-	unsigned int order = PAGE_BLOCK_ORDER;
+	unsigned int order = PAGE_BLOCK_MAX_ORDER;
 
 	/* Check that pageblock_nr_pages has not already been setup */
 	if (pageblock_order)
-- 
cgit v1.2.3


From 44b1b073eb36143ec65a918c0fbaa582f3ec2aa1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 10 Jun 2025 07:49:38 +0200
Subject: mm: stop passing a writeback_control structure to shmem_writeout

shmem_writeout only needs the swap_iocb cookie and the split folio list.
Pass those explicitly and remove the now unused list member from struct
writeback_control.

Link: https://lkml.kernel.org/r/20250610054959.2057526-3-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c |  2 +-
 drivers/gpu/drm/ttm/ttm_backup.c          |  9 +--------
 include/linux/shmem_fs.h                  |  5 ++++-
 include/linux/writeback.h                 |  3 ---
 mm/shmem.c                                | 26 +++++++++++++++-----------
 mm/vmscan.c                               | 12 +++++-------
 6 files changed, 26 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 19a3eb82dc6a..24d8daa4fdb3 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -317,7 +317,7 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
 		if (folio_mapped(folio))
 			folio_redirty_for_writepage(&wbc, folio);
 		else
-			error = shmem_writeout(folio, &wbc);
+			error = shmem_writeout(folio, NULL, NULL);
 	}
 }
 
diff --git a/drivers/gpu/drm/ttm/ttm_backup.c b/drivers/gpu/drm/ttm/ttm_backup.c
index ffaab68bd5dd..6f2e58be4f3e 100644
--- a/drivers/gpu/drm/ttm/ttm_backup.c
+++ b/drivers/gpu/drm/ttm/ttm_backup.c
@@ -112,15 +112,8 @@ ttm_backup_backup_page(struct file *backup, struct page *page,
 
 	if (writeback && !folio_mapped(to_folio) &&
 	    folio_clear_dirty_for_io(to_folio)) {
-		struct writeback_control wbc = {
-			.sync_mode = WB_SYNC_NONE,
-			.nr_to_write = SWAP_CLUSTER_MAX,
-			.range_start = 0,
-			.range_end = LLONG_MAX,
-			.for_reclaim = 1,
-		};
 		folio_set_reclaim(to_folio);
-		ret = shmem_writeout(to_folio, &wbc);
+		ret = shmem_writeout(to_folio, NULL, NULL);
 		if (!folio_test_writeback(to_folio))
 			folio_clear_reclaim(to_folio);
 		/*
diff --git a/include/linux/shmem_fs.h b/include/linux/shmem_fs.h
index 5f03a39a26f7..6d0f9c599ff7 100644
--- a/include/linux/shmem_fs.h
+++ b/include/linux/shmem_fs.h
@@ -11,6 +11,8 @@
 #include <linux/fs_parser.h>
 #include <linux/userfaultfd_k.h>
 
+struct swap_iocb;
+
 /* inode in-kernel data */
 
 #ifdef CONFIG_TMPFS_QUOTA
@@ -107,7 +109,8 @@ static inline bool shmem_mapping(struct address_space *mapping)
 void shmem_unlock_mapping(struct address_space *mapping);
 struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
 					pgoff_t index, gfp_t gfp_mask);
-int shmem_writeout(struct folio *folio, struct writeback_control *wbc);
+int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+		struct list_head *folio_list);
 void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end);
 int shmem_unuse(unsigned int type);
 
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index eda4b62511f7..82f217970092 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -79,9 +79,6 @@ struct writeback_control {
 	 */
 	struct swap_iocb **swap_plug;
 
-	/* Target list for splitting a large folio */
-	struct list_head *list;
-
 	/* internal fields used by the ->writepages implementation: */
 	struct folio_batch fbatch;
 	pgoff_t index;
diff --git a/mm/shmem.c b/mm/shmem.c
index 3a5a65b1f41a..ad8db487e721 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1540,11 +1540,13 @@ start_over:
 /**
  * shmem_writeout - Write the folio to swap
  * @folio: The folio to write
- * @wbc: How writeback is to be done
+ * @plug: swap plug
+ * @folio_list: list to put back folios on split
  *
  * Move the folio from the page cache to the swap cache.
  */
-int shmem_writeout(struct folio *folio, struct writeback_control *wbc)
+int shmem_writeout(struct folio *folio, struct swap_iocb **plug,
+		struct list_head *folio_list)
 {
 	struct address_space *mapping = folio->mapping;
 	struct inode *inode = mapping->host;
@@ -1554,9 +1556,6 @@ int shmem_writeout(struct folio *folio, struct writeback_control *wbc)
 	int nr_pages;
 	bool split = false;
 
-	if (WARN_ON_ONCE(!wbc->for_reclaim))
-		goto redirty;
-
 	if ((info->flags & VM_LOCKED) || sbinfo->noswap)
 		goto redirty;
 
@@ -1583,7 +1582,7 @@ int shmem_writeout(struct folio *folio, struct writeback_control *wbc)
 try_split:
 		/* Ensure the subpages are still dirty */
 		folio_test_set_dirty(folio);
-		if (split_folio_to_list(folio, wbc->list))
+		if (split_folio_to_list(folio, folio_list))
 			goto redirty;
 		folio_clear_dirty(folio);
 	}
@@ -1636,13 +1635,21 @@ try_split:
 		list_add(&info->swaplist, &shmem_swaplist);
 
 	if (!folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
+		struct writeback_control wbc = {
+			.sync_mode	= WB_SYNC_NONE,
+			.nr_to_write	= SWAP_CLUSTER_MAX,
+			.range_start	= 0,
+			.range_end	= LLONG_MAX,
+			.for_reclaim	= 1,
+			.swap_plug	= plug,
+		};
 		shmem_recalc_inode(inode, 0, nr_pages);
 		swap_shmem_alloc(folio->swap, nr_pages);
 		shmem_delete_from_page_cache(folio, swp_to_radix_entry(folio->swap));
 
 		mutex_unlock(&shmem_swaplist_mutex);
 		BUG_ON(folio_mapped(folio));
-		return swap_writeout(folio, wbc);
+		return swap_writeout(folio, &wbc);
 	}
 	if (!info->swapped)
 		list_del_init(&info->swaplist);
@@ -1651,10 +1658,7 @@ try_split:
 		goto try_split;
 redirty:
 	folio_mark_dirty(folio);
-	if (wbc->for_reclaim)
-		return AOP_WRITEPAGE_ACTIVATE;	/* Return with folio locked */
-	folio_unlock(folio);
-	return 0;
+	return AOP_WRITEPAGE_ACTIVATE;	/* Return with folio locked */
 }
 EXPORT_SYMBOL_GPL(shmem_writeout);
 
diff --git a/mm/vmscan.c b/mm/vmscan.c
index b6dd1708fe82..3cceb619a853 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -669,15 +669,13 @@ static pageout_t writeout(struct folio *folio, struct address_space *mapping,
 
 	/*
 	 * The large shmem folio can be split if CONFIG_THP_SWAP is not enabled
-	 * or we failed to allocate contiguous swap entries.
+	 * or we failed to allocate contiguous swap entries, in which case
+	 * the split out folios get added back to folio_list.
 	 */
-	if (shmem_mapping(mapping)) {
-		if (folio_test_large(folio))
-			wbc.list = folio_list;
-		res = shmem_writeout(folio, &wbc);
-	} else {
+	if (shmem_mapping(mapping))
+		res = shmem_writeout(folio, plug, folio_list);
+	else
 		res = swap_writeout(folio, &wbc);
-	}
 
 	if (res < 0)
 		handle_write_error(mapping, folio, res);
-- 
cgit v1.2.3


From 624043dbd5be03cc5a2b9175c3934e6fb0ef7c70 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 10 Jun 2025 07:49:41 +0200
Subject: mm: stop passing a writeback_control structure to swap_writeout

swap_writeout only needs the swap_iocb cookie from the writeback_control
structure, so pass it explicitly.

Link: https://lkml.kernel.org/r/20250610054959.2057526-6-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/writeback.h |  7 -------
 mm/page_io.c              |  4 ++--
 mm/shmem.c                | 10 +---------
 mm/swap.h                 |  7 +++++--
 mm/vmscan.c               | 10 +---------
 5 files changed, 9 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 82f217970092..9e960f2faf79 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -72,13 +72,6 @@ struct writeback_control {
 	 */
 	unsigned no_cgroup_owner:1;
 
-	/* To enable batching of swap writes to non-block-device backends,
-	 * "plug" can be set point to a 'struct swap_iocb *'.  When all swap
-	 * writes have been submitted, if with swap_iocb is not NULL,
-	 * swap_write_unplug() should be called.
-	 */
-	struct swap_iocb **swap_plug;
-
 	/* internal fields used by the ->writepages implementation: */
 	struct folio_batch fbatch;
 	pgoff_t index;
diff --git a/mm/page_io.c b/mm/page_io.c
index fb52bedcc966..a2056a5ecb13 100644
--- a/mm/page_io.c
+++ b/mm/page_io.c
@@ -237,7 +237,7 @@ static void swap_zeromap_folio_clear(struct folio *folio)
  * We may have stale swap cache pages in memory: notice
  * them here and get rid of the unnecessary final write.
  */
-int swap_writeout(struct folio *folio, struct writeback_control *wbc)
+int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug)
 {
 	int ret = 0;
 
@@ -281,7 +281,7 @@ int swap_writeout(struct folio *folio, struct writeback_control *wbc)
 		return AOP_WRITEPAGE_ACTIVATE;
 	}
 
-	__swap_writepage(folio, wbc->swap_plug);
+	__swap_writepage(folio, swap_plug);
 	return 0;
 out_unlock:
 	folio_unlock(folio);
diff --git a/mm/shmem.c b/mm/shmem.c
index ad8db487e721..eda35be2a8d9 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -1635,21 +1635,13 @@ try_split:
 		list_add(&info->swaplist, &shmem_swaplist);
 
 	if (!folio_alloc_swap(folio, __GFP_HIGH | __GFP_NOMEMALLOC | __GFP_NOWARN)) {
-		struct writeback_control wbc = {
-			.sync_mode	= WB_SYNC_NONE,
-			.nr_to_write	= SWAP_CLUSTER_MAX,
-			.range_start	= 0,
-			.range_end	= LLONG_MAX,
-			.for_reclaim	= 1,
-			.swap_plug	= plug,
-		};
 		shmem_recalc_inode(inode, 0, nr_pages);
 		swap_shmem_alloc(folio->swap, nr_pages);
 		shmem_delete_from_page_cache(folio, swp_to_radix_entry(folio->swap));
 
 		mutex_unlock(&shmem_swaplist_mutex);
 		BUG_ON(folio_mapped(folio));
-		return swap_writeout(folio, &wbc);
+		return swap_writeout(folio, plug);
 	}
 	if (!info->swapped)
 		list_del_init(&info->swaplist);
diff --git a/mm/swap.h b/mm/swap.h
index 911817f051c2..911ad5ff0f89 100644
--- a/mm/swap.h
+++ b/mm/swap.h
@@ -3,6 +3,8 @@
 #define _MM_SWAP_H
 
 struct mempolicy;
+struct swap_iocb;
+
 extern int page_cluster;
 
 #ifdef CONFIG_SWAP
@@ -20,7 +22,7 @@ static inline void swap_read_unplug(struct swap_iocb *plug)
 		__swap_read_unplug(plug);
 }
 void swap_write_unplug(struct swap_iocb *sio);
-int swap_writeout(struct folio *folio, struct writeback_control *wbc);
+int swap_writeout(struct folio *folio, struct swap_iocb **swap_plug);
 void __swap_writepage(struct folio *folio, struct swap_iocb **swap_plug);
 
 /* linux/mm/swap_state.c */
@@ -160,7 +162,8 @@ static inline struct folio *swapin_readahead(swp_entry_t swp, gfp_t gfp_mask,
 	return NULL;
 }
 
-static inline int swap_writeout(struct folio *f, struct writeback_control *wbc)
+static inline int swap_writeout(struct folio *folio,
+		struct swap_iocb **swap_plug)
 {
 	return 0;
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 3cceb619a853..a93a1ba9009e 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -655,14 +655,6 @@ typedef enum {
 static pageout_t writeout(struct folio *folio, struct address_space *mapping,
 		struct swap_iocb **plug, struct list_head *folio_list)
 {
-	struct writeback_control wbc = {
-		.sync_mode = WB_SYNC_NONE,
-		.nr_to_write = SWAP_CLUSTER_MAX,
-		.range_start = 0,
-		.range_end = LLONG_MAX,
-		.for_reclaim = 1,
-		.swap_plug = plug,
-	};
 	int res;
 
 	folio_set_reclaim(folio);
@@ -675,7 +667,7 @@ static pageout_t writeout(struct folio *folio, struct address_space *mapping,
 	if (shmem_mapping(mapping))
 		res = shmem_writeout(folio, plug, folio_list);
 	else
-		res = swap_writeout(folio, &wbc);
+		res = swap_writeout(folio, plug);
 
 	if (res < 0)
 		handle_write_error(mapping, folio, res);
-- 
cgit v1.2.3


From a8fb49c6abbbe5c71e1a8a888ef2c4b3e341d169 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Tue, 10 Jun 2025 07:49:42 +0200
Subject: mm: remove the for_reclaim field from struct writeback_control

This field is now only set to one in the i915 gem code that only calls
writeback_iter on it, which ignores the flag.  All other checks are thuse
dead code and the field can be removed.

Link: https://lkml.kernel.org/r/20250610054959.2057526-7-hch@lst.de
Signed-off-by: Christoph Hellwig <hch@lst.de>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Nhat Pham <nphamcs@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/gpu/drm/i915/gem/i915_gem_shmem.c |  1 -
 fs/fuse/file.c                            | 11 -----------
 fs/nfs/write.c                            |  2 +-
 include/linux/writeback.h                 |  1 -
 include/trace/events/btrfs.h              |  7 ++-----
 include/trace/events/writeback.h          |  8 ++------
 6 files changed, 5 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
index 24d8daa4fdb3..f263615f6ece 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_shmem.c
@@ -302,7 +302,6 @@ void __shmem_writeback(size_t size, struct address_space *mapping)
 		.nr_to_write = SWAP_CLUSTER_MAX,
 		.range_start = 0,
 		.range_end = LLONG_MAX,
-		.for_reclaim = 1,
 	};
 	struct folio *folio = NULL;
 	int error = 0;
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 47006d0753f1..95a657a57786 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -1927,17 +1927,6 @@ int fuse_write_inode(struct inode *inode, struct writeback_control *wbc)
 	struct fuse_file *ff;
 	int err;
 
-	/*
-	 * Inode is always written before the last reference is dropped and
-	 * hence this should not be reached from reclaim.
-	 *
-	 * Writing back the inode from reclaim can deadlock if the request
-	 * processing itself needs an allocation.  Allocations triggering
-	 * reclaim while serving a request can't be prevented, because it can
-	 * involve any number of unrelated userspace processes.
-	 */
-	WARN_ON(wbc->for_reclaim);
-
 	ff = __fuse_write_file_get(fi);
 	err = fuse_flush_times(inode, ff);
 	if (ff)
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index 374fc6b34c79..cf1d720b8251 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -720,7 +720,7 @@ int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
 	if (!(mntflags & NFS_MOUNT_WRITE_EAGER) || wbc->for_kupdate ||
-	    wbc->for_background || wbc->for_sync || wbc->for_reclaim) {
+	    wbc->for_background || wbc->for_sync) {
 		ioc = nfs_io_completion_alloc(GFP_KERNEL);
 		if (ioc)
 			nfs_io_completion_init(ioc, nfs_io_completion_commit,
diff --git a/include/linux/writeback.h b/include/linux/writeback.h
index 9e960f2faf79..a2848d731a46 100644
--- a/include/linux/writeback.h
+++ b/include/linux/writeback.h
@@ -59,7 +59,6 @@ struct writeback_control {
 	unsigned for_kupdate:1;		/* A kupdate writeback */
 	unsigned for_background:1;	/* A background writeback */
 	unsigned tagged_writepages:1;	/* tag-and-write to avoid livelock */
-	unsigned for_reclaim:1;		/* Invoked from the page allocator */
 	unsigned range_cyclic:1;	/* range_start is cyclic */
 	unsigned for_sync:1;		/* sync(2) WB_SYNC_ALL writeback */
 	unsigned unpinned_netfs_wb:1;	/* Cleared I_PINNING_NETFS_WB */
diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
index bebc252db865..0adc40f5e72b 100644
--- a/include/trace/events/btrfs.h
+++ b/include/trace/events/btrfs.h
@@ -686,7 +686,6 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 		__field(	loff_t, range_start		)
 		__field(	loff_t, range_end		)
 		__field(	char,   for_kupdate		)
-		__field(	char,   for_reclaim		)
 		__field(	char,   range_cyclic		)
 		__field(	unsigned long,  writeback_index	)
 		__field(	u64,    root_objectid		)
@@ -700,7 +699,6 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 		__entry->range_start	= wbc->range_start;
 		__entry->range_end	= wbc->range_end;
 		__entry->for_kupdate	= wbc->for_kupdate;
-		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
 		__entry->writeback_index = inode->i_mapping->writeback_index;
 		__entry->root_objectid	= btrfs_root_id(BTRFS_I(inode)->root);
@@ -709,13 +707,12 @@ DECLARE_EVENT_CLASS(btrfs__writepage,
 	TP_printk_btrfs("root=%llu(%s) ino=%llu page_index=%lu "
 		  "nr_to_write=%ld pages_skipped=%ld range_start=%llu "
 		  "range_end=%llu for_kupdate=%d "
-		  "for_reclaim=%d range_cyclic=%d writeback_index=%lu",
+		  "range_cyclic=%d writeback_index=%lu",
 		  show_root_type(__entry->root_objectid),
 		  __entry->ino, __entry->index,
 		  __entry->nr_to_write, __entry->pages_skipped,
 		  __entry->range_start, __entry->range_end,
-		  __entry->for_kupdate,
-		  __entry->for_reclaim, __entry->range_cyclic,
+		  __entry->for_kupdate, __entry->range_cyclic,
 		  __entry->writeback_index)
 );
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index 0ff388131fc9..1e23919c0da9 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -459,7 +459,6 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__field(int, sync_mode)
 		__field(int, for_kupdate)
 		__field(int, for_background)
-		__field(int, for_reclaim)
 		__field(int, range_cyclic)
 		__field(long, range_start)
 		__field(long, range_end)
@@ -473,23 +472,20 @@ DECLARE_EVENT_CLASS(wbc_class,
 		__entry->sync_mode	= wbc->sync_mode;
 		__entry->for_kupdate	= wbc->for_kupdate;
 		__entry->for_background	= wbc->for_background;
-		__entry->for_reclaim	= wbc->for_reclaim;
 		__entry->range_cyclic	= wbc->range_cyclic;
 		__entry->range_start	= (long)wbc->range_start;
 		__entry->range_end	= (long)wbc->range_end;
 		__entry->cgroup_ino	= __trace_wbc_assign_cgroup(wbc);
 	),
 
-	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d "
-		"bgrd=%d reclm=%d cyclic=%d "
-		"start=0x%lx end=0x%lx cgroup_ino=%lu",
+	TP_printk("bdi %s: towrt=%ld skip=%ld mode=%d kupd=%d bgrd=%d "
+		"cyclic=%d start=0x%lx end=0x%lx cgroup_ino=%lu",
 		__entry->name,
 		__entry->nr_to_write,
 		__entry->pages_skipped,
 		__entry->sync_mode,
 		__entry->for_kupdate,
 		__entry->for_background,
-		__entry->for_reclaim,
 		__entry->range_cyclic,
 		__entry->range_start,
 		__entry->range_end,
-- 
cgit v1.2.3


From 4f745def815d86eece3614aa0cd10a25cf94fed4 Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Wed, 28 May 2025 12:18:00 -0500
Subject: drivers/base/node: optimize memory block registration to reduce boot
 time
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Patch series "drivers/base/node.c: optimization and cleanups", v7.


This patch (of 7)

During node device initialization, `memory blocks` are registered under
each NUMA node.  The `memory blocks` to be registered are identified using
the node's start and end PFNs, which are obtained from the node's pg_data

However, not all PFNs within this range necessarily belong to the same
node—some may belong to other nodes.  Additionally, due to the
discontiguous nature of physical memory, certain sections within a `memory
block` may be absent.

As a result, `memory blocks` that fall between a node's start and end PFNs
may span across multiple nodes, and some sections within those blocks may
be missing.  `Memory blocks` have a fixed size, which is architecture
dependent.

Due to these considerations, the memory block registration is currently
performed as follows:

for_each_online_node(nid):
    start_pfn = pgdat->node_start_pfn;
    end_pfn = pgdat->node_start_pfn + node_spanned_pages;
    for_each_memory_block_between(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn))
        mem_blk = memory_block_id(pfn_to_section_nr(pfn));
        pfn_mb_start=section_nr_to_pfn(mem_blk->start_section_nr)
        pfn_mb_end = pfn_start + memory_block_pfns - 1
        for (pfn = pfn_mb_start; pfn < pfn_mb_end; pfn++):
            if (get_nid_for_pfn(pfn) != nid):
                continue;
            else
                do_register_memory_block_under_node(nid, mem_blk,
                                                        MEMINIT_EARLY);

Here, we derive the start and end PFNs from the node's pg_data, then
determine the memory blocks that may belong to the node.  For each `memory
block` in this range, we inspect all PFNs it contains and check their
associated NUMA node ID.  If a PFN within the block matches the current
node, the memory block is registered under that node.

If CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, get_nid_for_pfn() performs
a binary search in the `memblock regions` to determine the NUMA node ID
for a given PFN.  If it is not enabled, the node ID is retrieved directly
from the struct page.

On large systems, this process can become time-consuming, especially since
we iterate over each `memory block` and all PFNs within it until a match
is found.  When CONFIG_DEFERRED_STRUCT_PAGE_INIT is enabled, the
additional overhead of the binary search increases the execution time
significantly, potentially leading to soft lockups during boot.

In this patch, we iterate over `memblock region` to identify the `memory
blocks` that belong to the current NUMA node.  `memblock regions` are
contiguous memory ranges, each associated with a single NUMA node, and
they do not span across multiple nodes.

for_each_memory_region(r): // r => region
  if (!node_online(r->nid)):
    continue;
  else
    for_each_memory_block_between(r->base, r->base + r->size - 1):
      do_register_memory_block_under_node(r->nid, mem_blk, MEMINIT_EARLY);

We iterate over all memblock regions, and if the node associated with the
region is online, we calculate the start and end memory blocks based on
the region's start and end PFNs.  We then register all the memory blocks
within that range under the region node.

Test Results on My system with 32TB RAM
=======================================
1. Boot time with CONFIG_DEFERRED_STRUCT_PAGE_INIT enabled.

Without this patch
------------------
Startup finished in 1min 16.528s (kernel)

With this patch
---------------
Startup finished in 17.236s (kernel) - 78% Improvement

2. Boot time with CONFIG_DEFERRED_STRUCT_PAGE_INIT disabled.

Without this patch
------------------
Startup finished in 28.320s (kernel)

With this patch
---------------
Startup finished in 15.621s (kernel) - 46% Improvement

[donettom@linux.ibm.com: restore removed extra line]
  Link: https://lkml.kernel.org/r/20250609140354.467908-1-donettom@linux.ibm.com
Link: https://lkml.kernel.org/r/2a0a05c2dffc62a742bf1dd030098be4ce99be28.1748452241.git.donettom@linux.ibm.com
Link: https://lkml.kernel.org/r/2a0a05c2dffc62a742bf1dd030098be4ce99be28.1748452241.git.donettom@linux.ibm.com
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/base/memory.c  | 21 ++++-----------------
 drivers/base/node.c    | 35 +++++++++++++++++++++++++++++++++--
 include/linux/memory.h | 18 ++++++++++++++++++
 include/linux/node.h   |  3 +++
 4 files changed, 58 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index ed3e69dc785c..5c6c1d6bb59f 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -22,6 +22,7 @@
 #include <linux/stat.h>
 #include <linux/slab.h>
 #include <linux/xarray.h>
+#include <linux/export.h>
 
 #include <linux/atomic.h>
 #include <linux/uaccess.h>
@@ -48,22 +49,8 @@ int mhp_online_type_from_str(const char *str)
 
 #define to_memory_block(dev) container_of(dev, struct memory_block, dev)
 
-static int sections_per_block;
-
-static inline unsigned long memory_block_id(unsigned long section_nr)
-{
-	return section_nr / sections_per_block;
-}
-
-static inline unsigned long pfn_to_block_id(unsigned long pfn)
-{
-	return memory_block_id(pfn_to_section_nr(pfn));
-}
-
-static inline unsigned long phys_to_block_id(unsigned long phys)
-{
-	return pfn_to_block_id(PFN_DOWN(phys));
-}
+int sections_per_block;
+EXPORT_SYMBOL(sections_per_block);
 
 static int memory_subsys_online(struct device *dev);
 static int memory_subsys_offline(struct device *dev);
@@ -683,7 +670,7 @@ int __weak arch_get_memory_phys_device(unsigned long start_pfn)
  *
  * Called under device_hotplug_lock.
  */
-static struct memory_block *find_memory_block_by_id(unsigned long block_id)
+struct memory_block *find_memory_block_by_id(unsigned long block_id)
 {
 	struct memory_block *mem;
 
diff --git a/drivers/base/node.c b/drivers/base/node.c
index c19094481630..a854d04cea5d 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -21,6 +21,7 @@
 #include <linux/pm_runtime.h>
 #include <linux/swap.h>
 #include <linux/slab.h>
+#include <linux/memblock.h>
 
 static const struct bus_type node_subsys = {
 	.name = "node",
@@ -859,6 +860,34 @@ void unregister_memory_block_under_nodes(struct memory_block *mem_blk)
 			  kobject_name(&node_devices[mem_blk->nid]->dev.kobj));
 }
 
+/* register all memory blocks under the corresponding nodes */
+static void register_memory_blocks_under_nodes(void)
+{
+	struct memblock_region *r;
+
+	for_each_mem_region(r) {
+		const unsigned long start_block_id = phys_to_block_id(r->base);
+		const unsigned long end_block_id = phys_to_block_id(r->base + r->size - 1);
+		const int nid = memblock_get_region_node(r);
+		unsigned long block_id;
+
+		if (!node_online(nid))
+			continue;
+
+		for (block_id = start_block_id; block_id <= end_block_id; block_id++) {
+			struct memory_block *mem;
+
+			mem = find_memory_block_by_id(block_id);
+			if (!mem)
+				continue;
+
+			do_register_memory_block_under_node(nid, mem, MEMINIT_EARLY);
+			put_device(&mem->dev);
+		}
+
+	}
+}
+
 void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
 				       unsigned long end_pfn,
 				       enum meminit_context context)
@@ -980,11 +1009,13 @@ void __init node_dev_init(void)
 
 	/*
 	 * Create all node devices, which will properly link the node
-	 * to applicable memory block devices and already created cpu devices.
+	 * to already created cpu devices.
 	 */
 	for_each_online_node(i) {
-		ret = register_one_node(i);
+		ret =  __register_one_node(i);
 		if (ret)
 			panic("%s() failed to add node: %d\n", __func__, ret);
 	}
+
+	register_memory_blocks_under_nodes();
 }
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 5ec4e6d209b9..bd4440bc4a57 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -179,12 +179,30 @@ struct memory_group *memory_group_find_by_id(int mgid);
 typedef int (*walk_memory_groups_func_t)(struct memory_group *, void *);
 int walk_dynamic_memory_groups(int nid, walk_memory_groups_func_t func,
 			       struct memory_group *excluded, void *arg);
+struct memory_block *find_memory_block_by_id(unsigned long block_id);
 #define hotplug_memory_notifier(fn, pri) ({		\
 	static __meminitdata struct notifier_block fn##_mem_nb =\
 		{ .notifier_call = fn, .priority = pri };\
 	register_memory_notifier(&fn##_mem_nb);			\
 })
 
+extern int sections_per_block;
+
+static inline unsigned long memory_block_id(unsigned long section_nr)
+{
+	return section_nr / sections_per_block;
+}
+
+static inline unsigned long pfn_to_block_id(unsigned long pfn)
+{
+	return memory_block_id(pfn_to_section_nr(pfn));
+}
+
+static inline unsigned long phys_to_block_id(unsigned long phys)
+{
+	return pfn_to_block_id(PFN_DOWN(phys));
+}
+
 #ifdef CONFIG_NUMA
 void memory_block_add_nid(struct memory_block *mem, int nid,
 			  enum meminit_context context);
diff --git a/include/linux/node.h b/include/linux/node.h
index 2b7517892230..485370f3bc17 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -120,6 +120,9 @@ static inline void register_memory_blocks_under_node(int nid, unsigned long star
 						     enum meminit_context context)
 {
 }
+static inline void register_memory_blocks_under_nodes(void)
+{
+}
 #endif
 
 extern void unregister_node(struct node *node);
-- 
cgit v1.2.3


From ac24f6cd87d88150fc6c1fef904794571f62dc5e Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Wed, 28 May 2025 12:18:02 -0500
Subject: drivers/base/node: remove register_memory_blocks_under_node()
 function call from register_one_node
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

register_one_node() is now only called via cpu_up() →
__try_online_node() during CPU hotplug operations to online a node.

At this stage, the node has not yet had any memory added.  As a result,
there are no memory blocks to walk or register, so calling
register_memory_blocks_under_node() is unnecessary.

Therefore, the call to register_memory_blocks_under_node() has been
removed from register_one_node().

Link: https://lkml.kernel.org/r/ecf07075b1a41015fcf58823997d5c2ed7b8c18f.1748452242.git.donettom@linux.ibm.com
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/node.h | 16 +---------------
 1 file changed, 1 insertion(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/node.h b/include/linux/node.h
index 485370f3bc17..b15de78e0408 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -134,21 +134,7 @@ extern int __register_one_node(int nid);
 /* Registers an online node */
 static inline int register_one_node(int nid)
 {
-	int error = 0;
-
-	if (node_online(nid)) {
-		struct pglist_data *pgdat = NODE_DATA(nid);
-		unsigned long start_pfn = pgdat->node_start_pfn;
-		unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages;
-
-		error = __register_one_node(nid);
-		if (error)
-			return error;
-		register_memory_blocks_under_node(nid, start_pfn, end_pfn,
-						  MEMINIT_EARLY);
-	}
-
-	return error;
+	return __register_one_node(nid);
 }
 
 extern void unregister_one_node(int nid);
-- 
cgit v1.2.3


From 10f09d82f8b7c25bbd0b6d5142ff6df6e634132d Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Wed, 28 May 2025 12:18:03 -0500
Subject: drivers/base/node: rename register_memory_blocks_under_node() and
 remove context argument

The function register_memory_blocks_under_node() is now only called from
the memory hotplug path, as register_memory_blocks_under_node_early()
handles registration during early boot.  Therefore, the context argument
used to differentiate between early boot and hotplug is no longer needed
and was removed.

Since the function is only called from the hotplug path, we renamed
register_memory_blocks_under_node() to
register_memory_blocks_under_node_hotplug()

Link: https://lkml.kernel.org/r/907c22292b0ee4975107876efc875c75c11badd9.1748452242.git.donettom@linux.ibm.com
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Acked-by: Oscar Salvador <osalvador@suse.de>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/base/node.c  |  5 ++---
 include/linux/node.h | 11 +++++------
 mm/memory_hotplug.c  |  5 ++---
 3 files changed, 9 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/base/node.c b/drivers/base/node.c
index 24c32cdbe97d..302cb99853dd 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -839,9 +839,8 @@ static void register_memory_blocks_under_nodes(void)
 	}
 }
 
-void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
-				       unsigned long end_pfn,
-				       enum meminit_context context)
+void register_memory_blocks_under_node_hotplug(int nid, unsigned long start_pfn,
+					       unsigned long end_pfn)
 {
 	walk_memory_blocks(PFN_PHYS(start_pfn), PFN_PHYS(end_pfn - start_pfn),
 			   (void *)&nid, register_mem_block_under_node_hotplug);
diff --git a/include/linux/node.h b/include/linux/node.h
index b15de78e0408..75b036a100d2 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -111,13 +111,12 @@ struct memory_block;
 extern struct node *node_devices[];
 
 #if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA)
-void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
-				       unsigned long end_pfn,
-				       enum meminit_context context);
+void register_memory_blocks_under_node_hotplug(int nid, unsigned long start_pfn,
+					       unsigned long end_pfn);
 #else
-static inline void register_memory_blocks_under_node(int nid, unsigned long start_pfn,
-						     unsigned long end_pfn,
-						     enum meminit_context context)
+static inline void register_memory_blocks_under_node_hotplug(int nid,
+							     unsigned long start_pfn,
+							     unsigned long end_pfn)
 {
 }
 static inline void register_memory_blocks_under_nodes(void)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index b1caedbade5b..c6ce1aba64e6 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1575,9 +1575,8 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 		BUG_ON(ret);
 	}
 
-	register_memory_blocks_under_node(nid, PFN_DOWN(start),
-					  PFN_UP(start + size - 1),
-					  MEMINIT_HOTPLUG);
+	register_memory_blocks_under_node_hotplug(nid, PFN_DOWN(start),
+					  PFN_UP(start + size - 1));
 
 	/* create new memmap entry */
 	if (!strcmp(res->name, "System RAM"))
-- 
cgit v1.2.3


From a5352f8a40a8d1b385abeca0b2cff5d2468e31a1 Mon Sep 17 00:00:00 2001
From: Donet Tom <donettom@linux.ibm.com>
Date: Wed, 28 May 2025 12:18:04 -0500
Subject: drivers/base/node: rename __register_one_node() to
 register_one_node()

The register_one_node() function was a simple wrapper around
__register_one_node().  To simplify the code, register_one_node() has been
removed, and __register_one_node() has been renamed to
register_one_node().

Link: https://lkml.kernel.org/r/8262cd0f44eeb048a1fcd3ac8382760d7f7dea60.1748452242.git.donettom@linux.ibm.com
Signed-off-by: Donet Tom <donettom@linux.ibm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/powerpc/platforms/pseries/pci_dlpar.c |  2 +-
 drivers/base/node.c                        |  4 ++--
 include/linux/node.h                       | 13 +------------
 mm/memory_hotplug.c                        |  2 +-
 4 files changed, 5 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/platforms/pseries/pci_dlpar.c b/arch/powerpc/platforms/pseries/pci_dlpar.c
index 52e2623a741d..aeb8633a3d00 100644
--- a/arch/powerpc/platforms/pseries/pci_dlpar.c
+++ b/arch/powerpc/platforms/pseries/pci_dlpar.c
@@ -29,7 +29,7 @@ struct pci_controller *init_phb_dynamic(struct device_node *dn)
 	nid = of_node_to_nid(dn);
 	if (likely((nid) >= 0)) {
 		if (!node_online(nid)) {
-			if (__register_one_node(nid)) {
+			if (register_one_node(nid)) {
 				pr_err("PCI: Failed to register node %d\n", nid);
 			} else {
 				update_numa_distance(dn);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 302cb99853dd..6cbeca45c451 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -848,7 +848,7 @@ void register_memory_blocks_under_node_hotplug(int nid, unsigned long start_pfn,
 }
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
-int __register_one_node(int nid)
+int register_one_node(int nid)
 {
 	int error;
 	int cpu;
@@ -955,7 +955,7 @@ void __init node_dev_init(void)
 	 * to already created cpu devices.
 	 */
 	for_each_online_node(i) {
-		ret =  __register_one_node(i);
+		ret =  register_one_node(i);
 		if (ret)
 			panic("%s() failed to add node: %d\n", __func__, ret);
 	}
diff --git a/include/linux/node.h b/include/linux/node.h
index 75b036a100d2..88bceebcbfa5 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -128,14 +128,7 @@ extern void unregister_node(struct node *node);
 #ifdef CONFIG_NUMA
 extern void node_dev_init(void);
 /* Core of the node registration - only memory hotplug should use this */
-extern int __register_one_node(int nid);
-
-/* Registers an online node */
-static inline int register_one_node(int nid)
-{
-	return __register_one_node(nid);
-}
-
+extern int register_one_node(int nid);
 extern void unregister_one_node(int nid);
 extern int register_cpu_under_node(unsigned int cpu, unsigned int nid);
 extern int unregister_cpu_under_node(unsigned int cpu, unsigned int nid);
@@ -148,10 +141,6 @@ extern int register_memory_node_under_compute_node(unsigned int mem_nid,
 static inline void node_dev_init(void)
 {
 }
-static inline int __register_one_node(int nid)
-{
-	return 0;
-}
 static inline int register_one_node(int nid)
 {
 	return 0;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index c6ce1aba64e6..bec20a91e757 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1571,7 +1571,7 @@ int add_memory_resource(int nid, struct resource *res, mhp_t mhp_flags)
 		 * We online node here. We can't roll back from here.
 		 */
 		node_set_online(nid);
-		ret = __register_one_node(nid);
+		ret = register_one_node(nid);
 		BUG_ON(ret);
 	}
 
-- 
cgit v1.2.3


From 7208cc6497c2615ed5a334b52c92ae98bda91198 Mon Sep 17 00:00:00 2001
From: Tal Zussman <tz2294@columbia.edu>
Date: Thu, 19 Jun 2025 21:24:23 -0400
Subject: userfaultfd: correctly prevent registering VM_DROPPABLE regions

Patch series "mm: userfaultfd: assorted fixes and cleanups", v3.

Two fixes and two cleanups for userfaultfd.

Note that the third patch yields a small change in the ABI, but we seem to
have concluded that it is acceptable in this case.


This patch (of 4):

vma_can_userfault() masks off non-userfaultfd VM flags from vm_flags.  The
vm_flags & VM_DROPPABLE test will then always be false, incorrectly
allowing VM_DROPPABLE regions to be registered with userfaultfd.

Additionally, vm_flags is not guaranteed to correspond to the actual VMA's
flags.  Fix this test by checking the VMA's flags directly.

Link: https://lkml.kernel.org/r/20250619-uffd-fixes-v3-0-a7274d3bd5e4@columbia.edu
Link: https://lore.kernel.org/linux-mm/5a875a3a-2243-4eab-856f-bc53ccfec3ea@redhat.com/
Link: https://lkml.kernel.org/r/20250619-uffd-fixes-v3-1-a7274d3bd5e4@columbia.edu
Fixes: 9651fcedf7b9 ("mm: add MAP_DROPPABLE for designating always lazily freeable mappings")
Signed-off-by: Tal Zussman <tz2294@columbia.edu>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Acked-by: Jason A. Donenfeld <Jason@zx2c4.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/userfaultfd_k.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index 75342022d144..f3b3d2c9dd5e 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -218,7 +218,7 @@ static inline bool vma_can_userfault(struct vm_area_struct *vma,
 {
 	vm_flags &= __VM_UFFD_FLAGS;
 
-	if (vm_flags & VM_DROPPABLE)
+	if (vma->vm_flags & VM_DROPPABLE)
 		return false;
 
 	if ((vm_flags & VM_UFFD_MINOR) &&
-- 
cgit v1.2.3


From 5e00e31867d16e235bb693b900c85e86dc2c3464 Mon Sep 17 00:00:00 2001
From: Tal Zussman <tz2294@columbia.edu>
Date: Thu, 19 Jun 2025 21:24:26 -0400
Subject: userfaultfd: remove UFFD_CLOEXEC, UFFD_NONBLOCK, and UFFD_FLAGS_SET

UFFD_CLOEXEC, UFFD_NONBLOCK, and UFFD_FLAGS_SET have been unused since
they were added in commit 932b18e0aec6 ("userfaultfd:
linux/userfaultfd_k.h").  Remove them and the associated BUILD_BUG_ON()
checks.

Link: https://lkml.kernel.org/r/20250619-uffd-fixes-v3-4-a7274d3bd5e4@columbia.edu
Signed-off-by: Tal Zussman <tz2294@columbia.edu>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Peter Xu <peterx@redhat.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason A. Donenfeld <Jason@zx2c4.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/userfaultfd.c              | 2 --
 include/linux/userfaultfd_k.h | 4 ----
 2 files changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 771e81ea4ef6..a2928b0aec6f 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -2114,8 +2114,6 @@ static int new_userfaultfd(int flags)
 
 	/* Check the UFFD_* constants for consistency.  */
 	BUILD_BUG_ON(UFFD_USER_MODE_ONLY & UFFD_SHARED_FCNTL_FLAGS);
-	BUILD_BUG_ON(UFFD_CLOEXEC != O_CLOEXEC);
-	BUILD_BUG_ON(UFFD_NONBLOCK != O_NONBLOCK);
 
 	if (flags & ~(UFFD_SHARED_FCNTL_FLAGS | UFFD_USER_MODE_ONLY))
 		return -EINVAL;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index f3b3d2c9dd5e..ccad58602846 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -30,11 +30,7 @@
  * from userfaultfd, in order to leave a free define-space for
  * shared O_* flags.
  */
-#define UFFD_CLOEXEC O_CLOEXEC
-#define UFFD_NONBLOCK O_NONBLOCK
-
 #define UFFD_SHARED_FCNTL_FLAGS (O_CLOEXEC | O_NONBLOCK)
-#define UFFD_FLAGS_SET (EFD_SHARED_FCNTL_FLAGS)
 
 /*
  * Start with fault_pending_wqh and fault_wqh so they're more likely
-- 
cgit v1.2.3


From ff7ec8dc1b646296f8d94c39339e8d3833d16c05 Mon Sep 17 00:00:00 2001
From: wangzijie <wangzijie1@honor.com>
Date: Sat, 7 Jun 2025 10:13:53 +0800
Subject: proc: use the same treatment to check proc_lseek as ones for
 proc_read_iter et.al

Check pde->proc_ops->proc_lseek directly may cause UAF in rmmod scenario.
It's a gap in proc_reg_open() after commit 654b33ada4ab("proc: fix UAF in
proc_get_inode()").  Followed by AI Viro's suggestion, fix it in same
manner.

Link: https://lkml.kernel.org/r/20250607021353.1127963-1-wangzijie1@honor.com
Fixes: 3f61631d47f1 ("take care to handle NULL ->proc_lseek()")
Signed-off-by: wangzijie <wangzijie1@honor.com>
Reviewed-by: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: "Edgecombe, Rick P" <rick.p.edgecombe@intel.com>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/generic.c       | 2 ++
 fs/proc/inode.c         | 2 +-
 fs/proc/internal.h      | 5 +++++
 include/linux/proc_fs.h | 1 +
 4 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index a3e22803cddf..e0e50914ab25 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -569,6 +569,8 @@ static void pde_set_flags(struct proc_dir_entry *pde)
 	if (pde->proc_ops->proc_compat_ioctl)
 		pde->flags |= PROC_ENTRY_proc_compat_ioctl;
 #endif
+	if (pde->proc_ops->proc_lseek)
+		pde->flags |= PROC_ENTRY_proc_lseek;
 }
 
 struct proc_dir_entry *proc_create_data(const char *name, umode_t mode,
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 3604b616311c..129490151be1 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -473,7 +473,7 @@ static int proc_reg_open(struct inode *inode, struct file *file)
 	typeof_member(struct proc_ops, proc_open) open;
 	struct pde_opener *pdeo;
 
-	if (!pde->proc_ops->proc_lseek)
+	if (!pde_has_proc_lseek(pde))
 		file->f_mode &= ~FMODE_LSEEK;
 
 	if (pde_is_permanent(pde)) {
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 96122e91c645..3d48ffe72583 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -99,6 +99,11 @@ static inline bool pde_has_proc_compat_ioctl(const struct proc_dir_entry *pde)
 #endif
 }
 
+static inline bool pde_has_proc_lseek(const struct proc_dir_entry *pde)
+{
+	return pde->flags & PROC_ENTRY_proc_lseek;
+}
+
 extern struct kmem_cache *proc_dir_entry_cache;
 void pde_free(struct proc_dir_entry *pde);
 
diff --git a/include/linux/proc_fs.h b/include/linux/proc_fs.h
index ea62201c74c4..703d0c76cc9a 100644
--- a/include/linux/proc_fs.h
+++ b/include/linux/proc_fs.h
@@ -27,6 +27,7 @@ enum {
 
 	PROC_ENTRY_proc_read_iter	= 1U << 1,
 	PROC_ENTRY_proc_compat_ioctl	= 1U << 2,
+	PROC_ENTRY_proc_lseek		= 1U << 3,
 };
 
 struct proc_ops {
-- 
cgit v1.2.3


From f5e8b140cd1324cf2c9c17487b8f444098624797 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 9 Jun 2025 10:27:25 +0100
Subject: mm/readahead: make space in struct file_ra_state

We need to be able to store the preferred folio order associated with a
readahead request in the struct file_ra_state so that we can more
accurately increase the order across subsequent readahead requests.  But
struct file_ra_state is per-struct file, so we don't really want to
increase it's size.

mmap_miss is currently 32 bits but it is only counted up to 10 *
MMAP_LOTSAMISS, which is currently defined as 1000.  So 16 bits should be
plenty.  Redefine it to unsigned short, making room for order as unsigned
short in follow up commit.

Link: https://lkml.kernel.org/r/20250609092729.274960-4-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Chaitanya S Prakash <chaitanyas.prakash@arm.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/fs.h |  2 +-
 mm/filemap.c       | 11 ++++++-----
 2 files changed, 7 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index 62634af97da6..ef819b232d66 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1054,7 +1054,7 @@ struct file_ra_state {
 	unsigned int size;
 	unsigned int async_size;
 	unsigned int ra_pages;
-	unsigned int mmap_miss;
+	unsigned short mmap_miss;
 	loff_t prev_pos;
 };
 
diff --git a/mm/filemap.c b/mm/filemap.c
index a6459874bb2a..7bb4ffca8487 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3217,7 +3217,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
 	struct file *fpin = NULL;
 	unsigned long vm_flags = vmf->vma->vm_flags;
-	unsigned int mmap_miss;
+	unsigned short mmap_miss;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 	/* Use the readahead code, even if readahead is disabled */
@@ -3285,7 +3285,7 @@ static struct file *do_async_mmap_readahead(struct vm_fault *vmf,
 	struct file_ra_state *ra = &file->f_ra;
 	DEFINE_READAHEAD(ractl, file, ra, file->f_mapping, vmf->pgoff);
 	struct file *fpin = NULL;
-	unsigned int mmap_miss;
+	unsigned short mmap_miss;
 
 	/* If we don't want any read-ahead, don't bother */
 	if (vmf->vma->vm_flags & VM_RAND_READ || !ra->ra_pages)
@@ -3605,7 +3605,7 @@ skip:
 static vm_fault_t filemap_map_folio_range(struct vm_fault *vmf,
 			struct folio *folio, unsigned long start,
 			unsigned long addr, unsigned int nr_pages,
-			unsigned long *rss, unsigned int *mmap_miss)
+			unsigned long *rss, unsigned short *mmap_miss)
 {
 	vm_fault_t ret = 0;
 	struct page *page = folio_page(folio, start);
@@ -3667,7 +3667,7 @@ skip:
 
 static vm_fault_t filemap_map_order0_folio(struct vm_fault *vmf,
 		struct folio *folio, unsigned long addr,
-		unsigned long *rss, unsigned int *mmap_miss)
+		unsigned long *rss, unsigned short *mmap_miss)
 {
 	vm_fault_t ret = 0;
 	struct page *page = &folio->page;
@@ -3709,7 +3709,8 @@ vm_fault_t filemap_map_pages(struct vm_fault *vmf,
 	struct folio *folio;
 	vm_fault_t ret = 0;
 	unsigned long rss = 0;
-	unsigned int nr_pages = 0, mmap_miss = 0, mmap_miss_saved, folio_type;
+	unsigned int nr_pages = 0, folio_type;
+	unsigned short mmap_miss = 0, mmap_miss_saved;
 
 	rcu_read_lock();
 	folio = next_uptodate_folio(&xas, mapping, end_pgoff);
-- 
cgit v1.2.3


From c4602f9fa77fc6bb956ca51a23e7a39439e75cb6 Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 9 Jun 2025 10:27:26 +0100
Subject: mm/readahead: store folio order in struct file_ra_state

Previously the folio order of the previous readahead request was inferred
from the folio who's readahead marker was hit.  But due to the way we have
to round to non-natural boundaries sometimes, this first folio in the
readahead block is often smaller than the preferred order for that
request.  This means that for cases where the initial sync readahead is
poorly aligned, the folio order will ramp up much more slowly.

So instead, let's store the order in struct file_ra_state so we are not
affected by any required alignment.  We previously made enough room in the
struct for a 16 order field.  This should be plenty big enough since we
are limited to MAX_PAGECACHE_ORDER anyway, which is certainly never larger
than ~20.

Since we now pass order in struct file_ra_state, page_cache_ra_order() no
longer needs it's new_order parameter, so let's remove that.

Worked example:

Here we are touching pages 17-256 sequentially just as we did in the
previous commit, but now that we are remembering the preferred order
explicitly, we no longer have the slow ramp up problem.  Note specifically
that we no longer have 2 rounds (2x ~128K) of order-2 folios:

TYPE    STARTOFFS     ENDOFFS        SIZE  STARTPG    ENDPG   NRPG  ORDER  RA
-----  ----------  ----------  ----------  -------  -------  -----  -----  --
HOLE   0x00000000  0x00001000        4096        0        1      1
FOLIO  0x00001000  0x00002000        4096        1        2      1      0
FOLIO  0x00002000  0x00003000        4096        2        3      1      0
FOLIO  0x00003000  0x00004000        4096        3        4      1      0
FOLIO  0x00004000  0x00005000        4096        4        5      1      0
FOLIO  0x00005000  0x00006000        4096        5        6      1      0
FOLIO  0x00006000  0x00007000        4096        6        7      1      0
FOLIO  0x00007000  0x00008000        4096        7        8      1      0
FOLIO  0x00008000  0x00009000        4096        8        9      1      0
FOLIO  0x00009000  0x0000a000        4096        9       10      1      0
FOLIO  0x0000a000  0x0000b000        4096       10       11      1      0
FOLIO  0x0000b000  0x0000c000        4096       11       12      1      0
FOLIO  0x0000c000  0x0000d000        4096       12       13      1      0
FOLIO  0x0000d000  0x0000e000        4096       13       14      1      0
FOLIO  0x0000e000  0x0000f000        4096       14       15      1      0
FOLIO  0x0000f000  0x00010000        4096       15       16      1      0
FOLIO  0x00010000  0x00011000        4096       16       17      1      0
FOLIO  0x00011000  0x00012000        4096       17       18      1      0
FOLIO  0x00012000  0x00013000        4096       18       19      1      0
FOLIO  0x00013000  0x00014000        4096       19       20      1      0
FOLIO  0x00014000  0x00015000        4096       20       21      1      0
FOLIO  0x00015000  0x00016000        4096       21       22      1      0
FOLIO  0x00016000  0x00017000        4096       22       23      1      0
FOLIO  0x00017000  0x00018000        4096       23       24      1      0
FOLIO  0x00018000  0x00019000        4096       24       25      1      0
FOLIO  0x00019000  0x0001a000        4096       25       26      1      0
FOLIO  0x0001a000  0x0001b000        4096       26       27      1      0
FOLIO  0x0001b000  0x0001c000        4096       27       28      1      0
FOLIO  0x0001c000  0x0001d000        4096       28       29      1      0
FOLIO  0x0001d000  0x0001e000        4096       29       30      1      0
FOLIO  0x0001e000  0x0001f000        4096       30       31      1      0
FOLIO  0x0001f000  0x00020000        4096       31       32      1      0
FOLIO  0x00020000  0x00021000        4096       32       33      1      0
FOLIO  0x00021000  0x00022000        4096       33       34      1      0
FOLIO  0x00022000  0x00024000        8192       34       36      2      1
FOLIO  0x00024000  0x00028000       16384       36       40      4      2
FOLIO  0x00028000  0x0002c000       16384       40       44      4      2
FOLIO  0x0002c000  0x00030000       16384       44       48      4      2
FOLIO  0x00030000  0x00034000       16384       48       52      4      2
FOLIO  0x00034000  0x00038000       16384       52       56      4      2
FOLIO  0x00038000  0x0003c000       16384       56       60      4      2
FOLIO  0x0003c000  0x00040000       16384       60       64      4      2
FOLIO  0x00040000  0x00050000       65536       64       80     16      4
FOLIO  0x00050000  0x00060000       65536       80       96     16      4
FOLIO  0x00060000  0x00080000      131072       96      128     32      5
FOLIO  0x00080000  0x000a0000      131072      128      160     32      5
FOLIO  0x000a0000  0x000c0000      131072      160      192     32      5
FOLIO  0x000c0000  0x000e0000      131072      192      224     32      5
FOLIO  0x000e0000  0x00100000      131072      224      256     32      5
FOLIO  0x00100000  0x00120000      131072      256      288     32      5
FOLIO  0x00120000  0x00140000      131072      288      320     32      5  Y
HOLE   0x00140000  0x00800000     7077888      320     2048   1728

Link: https://lkml.kernel.org/r/20250609092729.274960-5-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Chaitanya S Prakash <chaitanyas.prakash@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/fs.h |  2 ++
 mm/filemap.c       |  6 ++++--
 mm/internal.h      |  3 +--
 mm/readahead.c     | 21 +++++++++++++--------
 4 files changed, 20 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/fs.h b/include/linux/fs.h
index ef819b232d66..e14e9d11ca0f 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1043,6 +1043,7 @@ struct fown_struct {
  *      and so were/are genuinely "ahead".  Start next readahead when
  *      the first of these pages is accessed.
  * @ra_pages: Maximum size of a readahead request, copied from the bdi.
+ * @order: Preferred folio order used for most recent readahead.
  * @mmap_miss: How many mmap accesses missed in the page cache.
  * @prev_pos: The last byte in the most recent read request.
  *
@@ -1054,6 +1055,7 @@ struct file_ra_state {
 	unsigned int size;
 	unsigned int async_size;
 	unsigned int ra_pages;
+	unsigned short order;
 	unsigned short mmap_miss;
 	loff_t prev_pos;
 };
diff --git a/mm/filemap.c b/mm/filemap.c
index 7bb4ffca8487..4b5c8d69f04c 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3232,7 +3232,8 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 		if (!(vm_flags & VM_RAND_READ))
 			ra->size *= 2;
 		ra->async_size = HPAGE_PMD_NR;
-		page_cache_ra_order(&ractl, ra, HPAGE_PMD_ORDER);
+		ra->order = HPAGE_PMD_ORDER;
+		page_cache_ra_order(&ractl, ra);
 		return fpin;
 	}
 #endif
@@ -3268,8 +3269,9 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
 	ra->size = ra->ra_pages;
 	ra->async_size = ra->ra_pages / 4;
+	ra->order = 0;
 	ractl._index = ra->start;
-	page_cache_ra_order(&ractl, ra, 0);
+	page_cache_ra_order(&ractl, ra);
 	return fpin;
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index 6b8ed2017743..f91688e2894f 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -436,8 +436,7 @@ void zap_page_range_single_batched(struct mmu_gather *tlb,
 int folio_unmap_invalidate(struct address_space *mapping, struct folio *folio,
 			   gfp_t gfp);
 
-void page_cache_ra_order(struct readahead_control *, struct file_ra_state *,
-		unsigned int order);
+void page_cache_ra_order(struct readahead_control *, struct file_ra_state *);
 void force_page_cache_ra(struct readahead_control *, unsigned long nr);
 static inline void force_page_cache_readahead(struct address_space *mapping,
 		struct file *file, pgoff_t index, unsigned long nr_to_read)
diff --git a/mm/readahead.c b/mm/readahead.c
index 87be20ae00d0..95a24f12d1e7 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -457,7 +457,7 @@ static inline int ra_alloc_folio(struct readahead_control *ractl, pgoff_t index,
 }
 
 void page_cache_ra_order(struct readahead_control *ractl,
-		struct file_ra_state *ra, unsigned int new_order)
+		struct file_ra_state *ra)
 {
 	struct address_space *mapping = ractl->mapping;
 	pgoff_t start = readahead_index(ractl);
@@ -468,9 +468,12 @@ void page_cache_ra_order(struct readahead_control *ractl,
 	unsigned int nofs;
 	int err = 0;
 	gfp_t gfp = readahead_gfp_mask(mapping);
+	unsigned int new_order = ra->order;
 
-	if (!mapping_large_folio_support(mapping))
+	if (!mapping_large_folio_support(mapping)) {
+		ra->order = 0;
 		goto fallback;
+	}
 
 	limit = min(limit, index + ra->size - 1);
 
@@ -478,6 +481,8 @@ void page_cache_ra_order(struct readahead_control *ractl,
 	new_order = min_t(unsigned int, new_order, ilog2(ra->size));
 	new_order = max(new_order, min_order);
 
+	ra->order = new_order;
+
 	/* See comment in page_cache_ra_unbounded() */
 	nofs = memalloc_nofs_save();
 	filemap_invalidate_lock_shared(mapping);
@@ -609,8 +614,9 @@ void page_cache_sync_ra(struct readahead_control *ractl,
 	ra->size = min(contig_count + req_count, max_pages);
 	ra->async_size = 1;
 readit:
+	ra->order = 0;
 	ractl->_index = ra->start;
-	page_cache_ra_order(ractl, ra, 0);
+	page_cache_ra_order(ractl, ra);
 }
 EXPORT_SYMBOL_GPL(page_cache_sync_ra);
 
@@ -621,7 +627,6 @@ void page_cache_async_ra(struct readahead_control *ractl,
 	struct file_ra_state *ra = ractl->ra;
 	pgoff_t index = readahead_index(ractl);
 	pgoff_t expected, start, end, aligned_end, align;
-	unsigned int order = folio_order(folio);
 
 	/* no readahead */
 	if (!ra->ra_pages)
@@ -644,7 +649,7 @@ void page_cache_async_ra(struct readahead_control *ractl,
 	 * Ramp up sizes, and push forward the readahead window.
 	 */
 	expected = round_down(ra->start + ra->size - ra->async_size,
-			1UL << order);
+			1UL << folio_order(folio));
 	if (index == expected) {
 		ra->start += ra->size;
 		/*
@@ -673,15 +678,15 @@ void page_cache_async_ra(struct readahead_control *ractl,
 	ra->size += req_count;
 	ra->size = get_next_ra_size(ra, max_pages);
 readit:
-	order += 2;
-	align = 1UL << min(order, ffs(max_pages) - 1);
+	ra->order += 2;
+	align = 1UL << min(ra->order, ffs(max_pages) - 1);
 	end = ra->start + ra->size;
 	aligned_end = round_down(end, align);
 	if (aligned_end > ra->start)
 		ra->size -= end - aligned_end;
 	ra->async_size = ra->size;
 	ractl->_index = ra->start;
-	page_cache_ra_order(ractl, ra, order);
+	page_cache_ra_order(ractl, ra);
 }
 EXPORT_SYMBOL_GPL(page_cache_async_ra);
 
-- 
cgit v1.2.3


From 38b0ece6d76374b989928021b5d310be11b99b5c Mon Sep 17 00:00:00 2001
From: Ryan Roberts <ryan.roberts@arm.com>
Date: Mon, 9 Jun 2025 10:27:27 +0100
Subject: mm/filemap: allow arch to request folio size for exec memory

Change the readahead config so that if it is being requested for an
executable mapping, do a synchronous read into a set of folios with an
arch-specified order and in a naturally aligned manner.  We no longer
center the read on the faulting page but simply align it down to the
previous natural boundary.  Additionally, we don't bother with an
asynchronous part.

On arm64 if memory is physically contiguous and naturally aligned to the
"contpte" size, we can use contpte mappings, which improves utilization of
the TLB.  When paired with the "multi-size THP" feature, this works well
to reduce dTLB pressure.  However iTLB pressure is still high due to
executable mappings having a low likelihood of being in the required folio
size and mapping alignment, even when the filesystem supports readahead
into large folios (e.g.  XFS).

The reason for the low likelihood is that the current readahead algorithm
starts with an order-0 folio and increases the folio order by 2 every time
the readahead mark is hit.  But most executable memory tends to be
accessed randomly and so the readahead mark is rarely hit and most
executable folios remain order-0.

So let's special-case the read(ahead) logic for executable mappings.  The
trade-off is performance improvement (due to more efficient storage of the
translations in iTLB) vs potential for making reclaim more difficult (due
to the folios being larger so if a part of the folio is hot the whole
thing is considered hot).  But executable memory is a small portion of the
overall system memory so I doubt this will even register from a reclaim
perspective.

I've chosen 64K folio size for arm64 which benefits both the 4K and 16K
base page size configs.  Crucially the same amount of data is still read
(usually 128K) so I'm not expecting any read amplification issues.  I
don't anticipate any write amplification because text is always RO.

Note that the text region of an ELF file could be populated into the page
cache for other reasons than taking a fault in a mmapped area.  The most
common case is due to the loader read()ing the header which can be shared
with the beginning of text.  So some text will still remain in small
folios, but this simple, best effort change provides good performance
improvements as is.

Confine this special-case approach to the bounds of the VMA.  This
prevents wasting memory for any padding that might exist in the file
between sections.  Previously the padding would have been contained in
order-0 folios and would be easy to reclaim.  But now it would be part of
a larger folio so more difficult to reclaim.  Solve this by simply not
reading it into memory in the first place.

Benchmarking
============

The below shows pgbench and redis benchmarks on Graviton3 arm64 system.

First, confirmation that this patch causes more text to be contained in
64K folios:

+----------------------+---------------+---------------+---------------+
| File-backed folios by|  system boot  |    pgbench    |     redis     |
| size as percentage of+-------+-------+-------+-------+-------+-------+
| all mapped text mem  |before | after |before | after |before | after |
+======================+=======+=======+=======+=======+=======+=======+
| base-page-4kB        |   78% |   30% |   78% |   11% |   73% |   14% |
| thp-aligned-8kB      |    1% |    0% |    0% |    0% |    1% |    0% |
| thp-aligned-16kB     |   17% |    4% |   17% |    3% |   20% |    4% |
| thp-aligned-32kB     |    1% |    1% |    1% |    2% |    1% |    1% |
| thp-aligned-64kB     |    3% |   63% |    3% |   81% |    4% |   77% |
| thp-aligned-128kB    |    0% |    1% |    1% |    1% |    1% |    2% |
| thp-unaligned-64kB   |    0% |    0% |    0% |    1% |    0% |    1% |
| thp-unaligned-128kB  |    0% |    1% |    0% |    0% |    0% |    0% |
| thp-partial          |    0% |    0% |    0% |    1% |    0% |    1% |
+----------------------+-------+-------+-------+-------+-------+-------+
| cont-aligned-64kB    |    4% |   65% |    4% |   83% |    6% |   79% |
+----------------------+-------+-------+-------+-------+-------+-------+

The above shows that for both workloads (each isolated with cgroups) as
well as the general system state after boot, the amount of text backed by
4K and 16K folios reduces and the amount backed by 64K folios increases
significantly.  And the amount of text that is contpte-mapped
significantly increases (see last row).

And this is reflected in performance improvement.  "(I)" indicates a
statistically significant improvement.  Note TPS and Reqs/sec are rates so
bigger is better, ms is time so smaller is better:

+-------------+-------------------------------------------+------------+
| Benchmark   | Result Class                              | Improvemnt |
+=============+===========================================+============+
| pts/pgbench | Scale: 1 Clients: 1 RO (TPS)              |  (I) 3.47% |
|             | Scale: 1 Clients: 1 RO - Latency (ms)     |     -2.88% |
|             | Scale: 1 Clients: 250 RO (TPS)            |  (I) 5.02% |
|             | Scale: 1 Clients: 250 RO - Latency (ms)   | (I) -4.79% |
|             | Scale: 1 Clients: 1000 RO (TPS)           |  (I) 6.16% |
|             | Scale: 1 Clients: 1000 RO - Latency (ms)  | (I) -5.82% |
|             | Scale: 100 Clients: 1 RO (TPS)            |      2.51% |
|             | Scale: 100 Clients: 1 RO - Latency (ms)   |     -3.51% |
|             | Scale: 100 Clients: 250 RO (TPS)          |  (I) 4.75% |
|             | Scale: 100 Clients: 250 RO - Latency (ms) | (I) -4.44% |
|             | Scale: 100 Clients: 1000 RO (TPS)         |  (I) 6.34% |
|             | Scale: 100 Clients: 1000 RO - Latency (ms)| (I) -5.95% |
+-------------+-------------------------------------------+------------+
| pts/redis   | Test: GET Connections: 50 (Reqs/sec)      |  (I) 3.20% |
|             | Test: GET Connections: 1000 (Reqs/sec)    |  (I) 2.55% |
|             | Test: LPOP Connections: 50 (Reqs/sec)     |  (I) 4.59% |
|             | Test: LPOP Connections: 1000 (Reqs/sec)   |  (I) 4.81% |
|             | Test: LPUSH Connections: 50 (Reqs/sec)    |  (I) 5.31% |
|             | Test: LPUSH Connections: 1000 (Reqs/sec)  |  (I) 4.36% |
|             | Test: SADD Connections: 50 (Reqs/sec)     |  (I) 2.64% |
|             | Test: SADD Connections: 1000 (Reqs/sec)   |  (I) 4.15% |
|             | Test: SET Connections: 50 (Reqs/sec)      |  (I) 3.11% |
|             | Test: SET Connections: 1000 (Reqs/sec)    |  (I) 3.36% |
+-------------+-------------------------------------------+------------+

[ryan.roberts@arm.com: fix use-after-free]
  Link: https://lkml.kernel.org/r/ea7f9da7-9a9f-4b85-9d0a-35b320f5ed25@arm.com
[ryan.roberts@arm.com: use the vma_pages() helper instead of open-coding]
  Link: https://lkml.kernel.org/r/0e0f674b-3b7e-494f-ae7a-fc9dbb98dad4@arm.com
Link: https://lkml.kernel.org/r/20250609092729.274960-6-ryan.roberts@arm.com
Signed-off-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Acked-by: Will Deacon <will@kernel.org>
Cc: Chaitanya S Prakash <chaitanyas.prakash@arm.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm64/include/asm/pgtable.h |  8 +++++++
 include/linux/pgtable.h          | 11 +++++++++
 mm/filemap.c                     | 48 ++++++++++++++++++++++++++++++++--------
 3 files changed, 58 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index 192d86e1cc76..e511f909f63c 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -1643,6 +1643,14 @@ static inline void update_mmu_cache_range(struct vm_fault *vmf,
  */
 #define arch_wants_old_prefaulted_pte	cpu_has_hw_af
 
+/*
+ * Request exec memory is read into pagecache in at least 64K folios. This size
+ * can be contpte-mapped when 4K base pages are in use (16 pages into 1 iTLB
+ * entry), and HPA can coalesce it (4 pages into 1 TLB entry) when 16K base
+ * pages are in use.
+ */
+#define exec_folio_order() ilog2(SZ_64K >> PAGE_SHIFT)
+
 static inline bool pud_sect_supported(void)
 {
 	return PAGE_SIZE == SZ_4K;
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 0b6e1f781d86..e4a3895c043b 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -456,6 +456,17 @@ static inline bool arch_has_hw_pte_young(void)
 }
 #endif
 
+#ifndef exec_folio_order
+/*
+ * Returns preferred minimum folio order for executable file-backed memory. Must
+ * be in range [0, PMD_ORDER). Default to order-0.
+ */
+static inline unsigned int exec_folio_order(void)
+{
+	return 0;
+}
+#endif
+
 #ifndef arch_check_zapped_pte
 static inline void arch_check_zapped_pte(struct vm_area_struct *vma,
 					 pte_t pte)
diff --git a/mm/filemap.c b/mm/filemap.c
index 4b5c8d69f04c..3cf955740148 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3238,8 +3238,11 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	}
 #endif
 
-	/* If we don't want any read-ahead, don't bother */
-	if (vm_flags & VM_RAND_READ)
+	/*
+	 * If we don't want any read-ahead, don't bother. VM_EXEC case below is
+	 * already intended for random access.
+	 */
+	if ((vm_flags & (VM_RAND_READ | VM_EXEC)) == VM_RAND_READ)
 		return fpin;
 	if (!ra->ra_pages)
 		return fpin;
@@ -3262,14 +3265,41 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	if (mmap_miss > MMAP_LOTSAMISS)
 		return fpin;
 
-	/*
-	 * mmap read-around
-	 */
+	if (vm_flags & VM_EXEC) {
+		/*
+		 * Allow arch to request a preferred minimum folio order for
+		 * executable memory. This can often be beneficial to
+		 * performance if (e.g.) arm64 can contpte-map the folio.
+		 * Executable memory rarely benefits from readahead, due to its
+		 * random access nature, so set async_size to 0.
+		 *
+		 * Limit to the boundaries of the VMA to avoid reading in any
+		 * pad that might exist between sections, which would be a waste
+		 * of memory.
+		 */
+		struct vm_area_struct *vma = vmf->vma;
+		unsigned long start = vma->vm_pgoff;
+		unsigned long end = start + vma_pages(vma);
+		unsigned long ra_end;
+
+		ra->order = exec_folio_order();
+		ra->start = round_down(vmf->pgoff, 1UL << ra->order);
+		ra->start = max(ra->start, start);
+		ra_end = round_up(ra->start + ra->ra_pages, 1UL << ra->order);
+		ra_end = min(ra_end, end);
+		ra->size = ra_end - ra->start;
+		ra->async_size = 0;
+	} else {
+		/*
+		 * mmap read-around
+		 */
+		ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
+		ra->size = ra->ra_pages;
+		ra->async_size = ra->ra_pages / 4;
+		ra->order = 0;
+	}
+
 	fpin = maybe_unlock_mmap_for_io(vmf, fpin);
-	ra->start = max_t(long, 0, vmf->pgoff - ra->ra_pages / 2);
-	ra->size = ra->ra_pages;
-	ra->async_size = ra->ra_pages / 4;
-	ra->order = 0;
 	ractl._index = ra->start;
 	page_cache_ra_order(&ractl, ra);
 	return fpin;
-- 
cgit v1.2.3


From 96d81e4766f9e88b66a0502b5a7f34a4c20ac754 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Thu, 5 Jun 2025 14:51:04 +0100
Subject: mm/pagewalk: split walk_page_range_novma() into kernel/user parts

walk_page_range_novma() is rather confusing - it supports two modes, one
used often, the other used only for debugging.

The first mode is the common case of traversal of kernel page tables,
which is what nearly all callers use this for.

Secondly it provides an unusual debugging interface that allows for the
traversal of page tables in a userland range of memory even for that
memory which is not described by a VMA.

It is far from certain that such page tables should even exist, but
perhaps this is precisely why it is useful as a debugging mechanism.

As a result, this is utilised by ptdump only.  Historically, things were
reversed - ptdump was the only user, and other parts of the kernel evolved
to use the kernel page table walking here.

Since we have some complicated and confusing locking rules for the novma
case, it makes sense to separate the two usages into their own functions.

Doing this also provide self-documentation as to the intent of the caller
- are they doing something rather unusual or are they simply doing a
standard kernel page table walk?

We therefore establish two separate functions - walk_page_range_debug()
for this single usage, and walk_kernel_page_table_range() for general
kernel page table walking.

The walk_page_range_debug() function is currently used to traverse both
userland and kernel mappings, so we maintain this and in the case of
kernel mappings being traversed, we have walk_page_range_debug() invoke
walk_kernel_page_table_range() internally.

We additionally make walk_page_range_debug() internal to mm.

Link: https://lkml.kernel.org/r/20250605135104.90720-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Qi Zheng <zhengqi.arch@bytedance.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Alexandre Ghiti <alex@ghiti.fr>
Cc: Barry Song <baohua@kernel.org>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Jann Horn <jannh@google.com>
Cc: Jonas Bonn <jonas@southpole.se>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Stafford Horne <shorne@gmail.com>
Cc: Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
Cc: WANG Xuerui <kernel@xen0n.name>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/loongarch/mm/pageattr.c |  2 +-
 arch/openrisc/kernel/dma.c   |  4 +--
 arch/riscv/mm/pageattr.c     |  8 ++---
 include/linux/pagewalk.h     |  7 ++--
 mm/hugetlb_vmemmap.c         |  2 +-
 mm/internal.h                |  3 ++
 mm/pagewalk.c                | 77 +++++++++++++++++++++++++++++++-------------
 mm/ptdump.c                  |  3 +-
 8 files changed, 71 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/arch/loongarch/mm/pageattr.c b/arch/loongarch/mm/pageattr.c
index 99165903908a..f5e910b68229 100644
--- a/arch/loongarch/mm/pageattr.c
+++ b/arch/loongarch/mm/pageattr.c
@@ -118,7 +118,7 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask, pgp
 		return 0;
 
 	mmap_write_lock(&init_mm);
-	ret = walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL, &masks);
+	ret = walk_kernel_page_table_range(start, end, &pageattr_ops, NULL, &masks);
 	mmap_write_unlock(&init_mm);
 
 	flush_tlb_kernel_range(start, end);
diff --git a/arch/openrisc/kernel/dma.c b/arch/openrisc/kernel/dma.c
index 3a7b5baaa450..af932a4ad306 100644
--- a/arch/openrisc/kernel/dma.c
+++ b/arch/openrisc/kernel/dma.c
@@ -72,7 +72,7 @@ void *arch_dma_set_uncached(void *cpu_addr, size_t size)
 	 * them and setting the cache-inhibit bit.
 	 */
 	mmap_write_lock(&init_mm);
-	error = walk_page_range_novma(&init_mm, va, va + size,
+	error = walk_kernel_page_table_range(va, va + size,
 			&set_nocache_walk_ops, NULL, NULL);
 	mmap_write_unlock(&init_mm);
 
@@ -87,7 +87,7 @@ void arch_dma_clear_uncached(void *cpu_addr, size_t size)
 
 	mmap_write_lock(&init_mm);
 	/* walk_page_range shouldn't be able to fail here */
-	WARN_ON(walk_page_range_novma(&init_mm, va, va + size,
+	WARN_ON(walk_kernel_page_table_range(va, va + size,
 			&clear_nocache_walk_ops, NULL, NULL));
 	mmap_write_unlock(&init_mm);
 }
diff --git a/arch/riscv/mm/pageattr.c b/arch/riscv/mm/pageattr.c
index d815448758a1..3f76db3d2769 100644
--- a/arch/riscv/mm/pageattr.c
+++ b/arch/riscv/mm/pageattr.c
@@ -299,7 +299,7 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 			if (ret)
 				goto unlock;
 
-			ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+			ret = walk_kernel_page_table_range(lm_start, lm_end,
 						    &pageattr_ops, NULL, &masks);
 			if (ret)
 				goto unlock;
@@ -317,13 +317,13 @@ static int __set_memory(unsigned long addr, int numpages, pgprot_t set_mask,
 		if (ret)
 			goto unlock;
 
-		ret = walk_page_range_novma(&init_mm, lm_start, lm_end,
+		ret = walk_kernel_page_table_range(lm_start, lm_end,
 					    &pageattr_ops, NULL, &masks);
 		if (ret)
 			goto unlock;
 	}
 
-	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+	ret =  walk_kernel_page_table_range(start, end, &pageattr_ops, NULL,
 				     &masks);
 
 unlock:
@@ -335,7 +335,7 @@ unlock:
 	 */
 	flush_tlb_all();
 #else
-	ret =  walk_page_range_novma(&init_mm, start, end, &pageattr_ops, NULL,
+	ret =  walk_kernel_page_table_range(start, end, &pageattr_ops, NULL,
 				     &masks);
 
 	mmap_write_unlock(&init_mm);
diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 9700a29f8afb..8ac2f6d6d2a3 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -129,10 +129,9 @@ struct mm_walk {
 int walk_page_range(struct mm_struct *mm, unsigned long start,
 		unsigned long end, const struct mm_walk_ops *ops,
 		void *private);
-int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
-			  unsigned long end, const struct mm_walk_ops *ops,
-			  pgd_t *pgd,
-			  void *private);
+int walk_kernel_page_table_range(unsigned long start,
+		unsigned long end, const struct mm_walk_ops *ops,
+		pgd_t *pgd, void *private);
 int walk_page_range_vma(struct vm_area_struct *vma, unsigned long start,
 			unsigned long end, const struct mm_walk_ops *ops,
 			void *private);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 27245e86df25..ba0fb1b6a5a8 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -166,7 +166,7 @@ static int vmemmap_remap_range(unsigned long start, unsigned long end,
 	VM_BUG_ON(!PAGE_ALIGNED(start | end));
 
 	mmap_read_lock(&init_mm);
-	ret = walk_page_range_novma(&init_mm, start, end, &vmemmap_remap_ops,
+	ret = walk_kernel_page_table_range(start, end, &vmemmap_remap_ops,
 				    NULL, walk);
 	mmap_read_unlock(&init_mm);
 	if (ret)
diff --git a/mm/internal.h b/mm/internal.h
index f91688e2894f..2c0d9f197d81 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1604,6 +1604,9 @@ static inline void accept_page(struct page *page)
 int walk_page_range_mm(struct mm_struct *mm, unsigned long start,
 		unsigned long end, const struct mm_walk_ops *ops,
 		void *private);
+int walk_page_range_debug(struct mm_struct *mm, unsigned long start,
+			  unsigned long end, const struct mm_walk_ops *ops,
+			  pgd_t *pgd, void *private);
 
 /* pt_reclaim.c */
 bool try_get_and_clear_pmd(struct mm_struct *mm, pmd_t *pmd, pmd_t *pmdval);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index e478777c86e1..ff5299eca687 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -585,8 +585,7 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
 }
 
 /**
- * walk_page_range_novma - walk a range of pagetables not backed by a vma
- * @mm:		mm_struct representing the target process of page table walk
+ * walk_kernel_page_table_range - walk a range of kernel pagetables.
  * @start:	start address of the virtual address range
  * @end:	end address of the virtual address range
  * @ops:	operation to call during the walk
@@ -596,17 +595,61 @@ int walk_page_range(struct mm_struct *mm, unsigned long start,
  * Similar to walk_page_range() but can walk any page tables even if they are
  * not backed by VMAs. Because 'unusual' entries may be walked this function
  * will also not lock the PTEs for the pte_entry() callback. This is useful for
- * walking the kernel pages tables or page tables for firmware.
+ * walking kernel pages tables or page tables for firmware.
  *
  * Note: Be careful to walk the kernel pages tables, the caller may be need to
  * take other effective approaches (mmap lock may be insufficient) to prevent
  * the intermediate kernel page tables belonging to the specified address range
  * from being freed (e.g. memory hot-remove).
  */
-int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
+int walk_kernel_page_table_range(unsigned long start, unsigned long end,
+		const struct mm_walk_ops *ops, pgd_t *pgd, void *private)
+{
+	struct mm_struct *mm = &init_mm;
+	struct mm_walk walk = {
+		.ops		= ops,
+		.mm		= mm,
+		.pgd		= pgd,
+		.private	= private,
+		.no_vma		= true
+	};
+
+	if (start >= end)
+		return -EINVAL;
+	if (!check_ops_valid(ops))
+		return -EINVAL;
+
+	/*
+	 * Kernel intermediate page tables are usually not freed, so the mmap
+	 * read lock is sufficient. But there are some exceptions.
+	 * E.g. memory hot-remove. In which case, the mmap lock is insufficient
+	 * to prevent the intermediate kernel pages tables belonging to the
+	 * specified address range from being freed. The caller should take
+	 * other actions to prevent this race.
+	 */
+	mmap_assert_locked(mm);
+
+	return walk_pgd_range(start, end, &walk);
+}
+
+/**
+ * walk_page_range_debug - walk a range of pagetables not backed by a vma
+ * @mm:		mm_struct representing the target process of page table walk
+ * @start:	start address of the virtual address range
+ * @end:	end address of the virtual address range
+ * @ops:	operation to call during the walk
+ * @pgd:	pgd to walk if different from mm->pgd
+ * @private:	private data for callbacks' usage
+ *
+ * Similar to walk_page_range() but can walk any page tables even if they are
+ * not backed by VMAs. Because 'unusual' entries may be walked this function
+ * will also not lock the PTEs for the pte_entry() callback.
+ *
+ * This is for debugging purposes ONLY.
+ */
+int walk_page_range_debug(struct mm_struct *mm, unsigned long start,
 			  unsigned long end, const struct mm_walk_ops *ops,
-			  pgd_t *pgd,
-			  void *private)
+			  pgd_t *pgd, void *private)
 {
 	struct mm_walk walk = {
 		.ops		= ops,
@@ -616,34 +659,24 @@ int walk_page_range_novma(struct mm_struct *mm, unsigned long start,
 		.no_vma		= true
 	};
 
+	/* For convenience, we allow traversal of kernel mappings. */
+	if (mm == &init_mm)
+		return walk_kernel_page_table_range(start, end, ops,
+						    pgd, private);
 	if (start >= end || !walk.mm)
 		return -EINVAL;
 	if (!check_ops_valid(ops))
 		return -EINVAL;
 
 	/*
-	 * 1) For walking the user virtual address space:
-	 *
 	 * The mmap lock protects the page walker from changes to the page
 	 * tables during the walk.  However a read lock is insufficient to
 	 * protect those areas which don't have a VMA as munmap() detaches
 	 * the VMAs before downgrading to a read lock and actually tearing
 	 * down PTEs/page tables. In which case, the mmap write lock should
-	 * be hold.
-	 *
-	 * 2) For walking the kernel virtual address space:
-	 *
-	 * The kernel intermediate page tables usually do not be freed, so
-	 * the mmap map read lock is sufficient. But there are some exceptions.
-	 * E.g. memory hot-remove. In which case, the mmap lock is insufficient
-	 * to prevent the intermediate kernel pages tables belonging to the
-	 * specified address range from being freed. The caller should take
-	 * other actions to prevent this race.
+	 * be held.
 	 */
-	if (mm == &init_mm)
-		mmap_assert_locked(walk.mm);
-	else
-		mmap_assert_write_locked(walk.mm);
+	mmap_assert_write_locked(mm);
 
 	return walk_pgd_range(start, end, &walk);
 }
diff --git a/mm/ptdump.c b/mm/ptdump.c
index 9374f29cdc6f..61a352aa12ed 100644
--- a/mm/ptdump.c
+++ b/mm/ptdump.c
@@ -4,6 +4,7 @@
 #include <linux/debugfs.h>
 #include <linux/ptdump.h>
 #include <linux/kasan.h>
+#include "internal.h"
 
 #if defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KASAN_SW_TAGS)
 /*
@@ -177,7 +178,7 @@ void ptdump_walk_pgd(struct ptdump_state *st, struct mm_struct *mm, pgd_t *pgd)
 
 	mmap_write_lock(mm);
 	while (range->start != range->end) {
-		walk_page_range_novma(mm, range->start, range->end,
+		walk_page_range_debug(mm, range->start, range->end,
 				      &ptdump_ops, pgd, st);
 		range++;
 	}
-- 
cgit v1.2.3


From b0da7709c28c35e0a51d4b1b350c9028358dfb14 Mon Sep 17 00:00:00 2001
From: David Wang <00107082@163.com>
Date: Mon, 9 Jun 2025 14:42:00 +0800
Subject: alloc_tag: add sequence number for module and iterator

Codetag iterator use <id,address> pair to guarantee the validness.  But
both id and address can be reused, there is theoretical possibility when
module inserted right after another module removed, kmalloc returns an
address same as the address kfree by previous module and IDR key reuses
the key recently removed.

Add a sequence number to codetag_module and code_iterator, the sequence
number is strickly incremented whenever a module is loaded.  An iterator
is valid if and only if its sequence number match codetag_module's.

Link: https://lkml.kernel.org/r/20250609064200.112639-1-00107082@163.com
Signed-off-by: David Wang <00107082@163.com>
Acked-by: Suren Baghdasaryan <surenb@google.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/codetag.h |  1 +
 lib/codetag.c           | 17 ++++++++++++++---
 2 files changed, 15 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/codetag.h b/include/linux/codetag.h
index 5f2b9a1f722c..457ed8fd3214 100644
--- a/include/linux/codetag.h
+++ b/include/linux/codetag.h
@@ -54,6 +54,7 @@ struct codetag_iterator {
 	struct codetag_module *cmod;
 	unsigned long mod_id;
 	struct codetag *ct;
+	unsigned long mod_seq;
 };
 
 #ifdef MODULE
diff --git a/lib/codetag.c b/lib/codetag.c
index 650d54d7e14d..545911cebd25 100644
--- a/lib/codetag.c
+++ b/lib/codetag.c
@@ -11,8 +11,14 @@ struct codetag_type {
 	struct list_head link;
 	unsigned int count;
 	struct idr mod_idr;
-	struct rw_semaphore mod_lock; /* protects mod_idr */
+	/*
+	 * protects mod_idr, next_mod_seq,
+	 * iter->mod_seq and cmod->mod_seq
+	 */
+	struct rw_semaphore mod_lock;
 	struct codetag_type_desc desc;
+	/* generates unique sequence number for module load */
+	unsigned long next_mod_seq;
 };
 
 struct codetag_range {
@@ -23,6 +29,7 @@ struct codetag_range {
 struct codetag_module {
 	struct module *mod;
 	struct codetag_range range;
+	unsigned long mod_seq;
 };
 
 static DEFINE_MUTEX(codetag_lock);
@@ -48,6 +55,7 @@ struct codetag_iterator codetag_get_ct_iter(struct codetag_type *cttype)
 		.cmod = NULL,
 		.mod_id = 0,
 		.ct = NULL,
+		.mod_seq = 0,
 	};
 
 	return iter;
@@ -91,11 +99,13 @@ struct codetag *codetag_next_ct(struct codetag_iterator *iter)
 		if (!cmod)
 			break;
 
-		if (cmod != iter->cmod) {
+		if (!iter->cmod || iter->mod_seq != cmod->mod_seq) {
 			iter->cmod = cmod;
+			iter->mod_seq = cmod->mod_seq;
 			ct = get_first_module_ct(cmod);
-		} else
+		} else {
 			ct = get_next_module_ct(iter);
+		}
 
 		if (ct)
 			break;
@@ -191,6 +201,7 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
 	cmod->range = range;
 
 	down_write(&cttype->mod_lock);
+	cmod->mod_seq = ++cttype->next_mod_seq;
 	mod_id = idr_alloc(&cttype->mod_idr, cmod, 0, 0, GFP_KERNEL);
 	if (mod_id >= 0) {
 		if (cttype->desc.module_load) {
-- 
cgit v1.2.3


From cce35103135c7ffc7bebc32ebfc74fe1f2c3cb5d Mon Sep 17 00:00:00 2001
From: Li Zhijian <lizhijian@fujitsu.com>
Date: Tue, 10 Jun 2025 14:27:51 +0800
Subject: mm/memory-tier: fix abstract distance calculation overflow

In mt_perf_to_adistance(), the calculation of abstract distance (adist)
involves multiplying several int values including
MEMTIER_ADISTANCE_DRAM.

*adist = MEMTIER_ADISTANCE_DRAM *
		(perf->read_latency + perf->write_latency) /
		(default_dram_perf.read_latency + default_dram_perf.write_latency) *
		(default_dram_perf.read_bandwidth + default_dram_perf.write_bandwidth) /
		(perf->read_bandwidth + perf->write_bandwidth);

Since these values can be large, the multiplication may exceed the
maximum value of an int (INT_MAX) and overflow (Our platform did),
leading to an incorrect adist.

User-visible impact:
The memory tiering subsystem will misinterpret slow memory (like CXL)
as faster than DRAM, causing inappropriate demotion of pages from
CXL (slow memory) to DRAM (fast memory).

For example, we will see the following demotion chains from the dmesg, where
Node0,1 are DRAM, and Node2,3 are CXL node:
 Demotion targets for Node 0: null
 Demotion targets for Node 1: null
 Demotion targets for Node 2: preferred: 0-1, fallback: 0-1
 Demotion targets for Node 3: preferred: 0-1, fallback: 0-1

Change MEMTIER_ADISTANCE_DRAM to be a long constant by writing it with
the 'L' suffix.  This prevents the overflow because the multiplication
will then be done in the long type which has a larger range.

Link: https://lkml.kernel.org/r/20250611023439.2845785-1-lizhijian@fujitsu.com
Link: https://lkml.kernel.org/r/20250610062751.2365436-1-lizhijian@fujitsu.com
Fixes: 3718c02dbd4c ("acpi, hmat: calculate abstract distance with HMAT")
Signed-off-by: Li Zhijian <lizhijian@fujitsu.com>
Reviewed-by: Huang Ying <ying.huang@linux.alibaba.com>
Acked-by: Balbir Singh <balbirs@nvidia.com>
Reviewed-by: Donet Tom <donettom@linux.ibm.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memory-tiers.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/memory-tiers.h b/include/linux/memory-tiers.h
index 0dc0cf2863e2..7a805796fcfd 100644
--- a/include/linux/memory-tiers.h
+++ b/include/linux/memory-tiers.h
@@ -18,7 +18,7 @@
  * adistance value (slightly faster) than default DRAM adistance to be part of
  * the same memory tier.
  */
-#define MEMTIER_ADISTANCE_DRAM	((4 * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1))
+#define MEMTIER_ADISTANCE_DRAM	((4L * MEMTIER_CHUNK_SIZE) + (MEMTIER_CHUNK_SIZE >> 1))
 
 struct memory_tier;
 struct memory_dev_type {
-- 
cgit v1.2.3


From 4f8ba33bbdfc475fdc1ac5de6a93f5de93203ed5 Mon Sep 17 00:00:00 2001
From: Barry Song <v-songbaohua@oppo.com>
Date: Wed, 11 Jun 2025 22:47:45 +1200
Subject: mm: madvise: use per_vma lock for MADV_FREE
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

MADV_FREE is another option, besides MADV_DONTNEED, for dynamic memory
freeing in user-space native or Java heap memory management.  For example,
jemalloc can be configured to use MADV_FREE, and recent versions of the
Android Java heap have also increasingly adopted MADV_FREE.  Supporting
per-VMA locking for MADV_FREE thus appears increasingly necessary.

We have replaced walk_page_range() with walk_page_range_vma().  Along with
the proposed madvise_lock_mode by Lorenzo, the necessary infrastructure is
now in place to begin exploring per-VMA locking support for MADV_FREE and
potentially other madvise using walk_page_range_vma().

This patch adds support for the PGWALK_VMA_RDLOCK walk_lock mode in
walk_page_range_vma(), and leverages madvise_lock_mode from madv_behavior
to select the appropriate walk_lock—either mmap_lock or per-VMA
lock—based on the context.

Because we now dynamically update the walk_ops->walk_lock field, we must
ensure this is thread-safe.  The madvise_free_walk_ops is now defined as a
stack variable instead of a global constant.

Link: https://lkml.kernel.org/r/20250611104745.57405-1-21cnbao@gmail.com
Signed-off-by: Barry Song <v-songbaohua@oppo.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: SeongJae Park <sj@kernel.org>
Cc: "Liam R. Howlett" <Liam.Howlett@oracle.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Lokesh Gidra <lokeshgidra@google.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Tangquan Zheng <zhengtangquan@oppo.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pagewalk.h |  2 ++
 mm/madvise.c             | 25 +++++++++++++++++++------
 mm/pagewalk.c            |  5 ++++-
 3 files changed, 25 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagewalk.h b/include/linux/pagewalk.h
index 8ac2f6d6d2a3..682472c15495 100644
--- a/include/linux/pagewalk.h
+++ b/include/linux/pagewalk.h
@@ -14,6 +14,8 @@ enum page_walk_lock {
 	PGWALK_WRLOCK = 1,
 	/* vma is expected to be already write-locked during the walk */
 	PGWALK_WRLOCK_VERIFY = 2,
+	/* vma is expected to be already read-locked during the walk */
+	PGWALK_VMA_RDLOCK_VERIFY = 3,
 };
 
 /**
diff --git a/mm/madvise.c b/mm/madvise.c
index 7d78d4b5fb18..d451438af999 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -777,10 +777,19 @@ static int madvise_free_pte_range(pmd_t *pmd, unsigned long addr,
 	return 0;
 }
 
-static const struct mm_walk_ops madvise_free_walk_ops = {
-	.pmd_entry		= madvise_free_pte_range,
-	.walk_lock		= PGWALK_RDLOCK,
-};
+static inline enum page_walk_lock get_walk_lock(enum madvise_lock_mode mode)
+{
+	switch (mode) {
+	case MADVISE_VMA_READ_LOCK:
+		return PGWALK_VMA_RDLOCK_VERIFY;
+	case MADVISE_MMAP_READ_LOCK:
+		return PGWALK_RDLOCK;
+	default:
+		/* Other modes don't require fixing up the walk_lock */
+		WARN_ON_ONCE(1);
+		return PGWALK_RDLOCK;
+	}
+}
 
 static int madvise_free_single_vma(struct madvise_behavior *madv_behavior,
 			struct vm_area_struct *vma,
@@ -789,6 +798,9 @@ static int madvise_free_single_vma(struct madvise_behavior *madv_behavior,
 	struct mm_struct *mm = vma->vm_mm;
 	struct mmu_notifier_range range;
 	struct mmu_gather *tlb = madv_behavior->tlb;
+	struct mm_walk_ops walk_ops = {
+		.pmd_entry		= madvise_free_pte_range,
+	};
 
 	/* MADV_FREE works for only anon vma at the moment */
 	if (!vma_is_anonymous(vma))
@@ -808,8 +820,9 @@ static int madvise_free_single_vma(struct madvise_behavior *madv_behavior,
 
 	mmu_notifier_invalidate_range_start(&range);
 	tlb_start_vma(tlb, vma);
+	walk_ops.walk_lock = get_walk_lock(madv_behavior->lock_mode);
 	walk_page_range_vma(vma, range.start, range.end,
-			&madvise_free_walk_ops, tlb);
+			&walk_ops, tlb);
 	tlb_end_vma(tlb, vma);
 	mmu_notifier_invalidate_range_end(&range);
 	return 0;
@@ -1658,7 +1671,6 @@ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavi
 	case MADV_WILLNEED:
 	case MADV_COLD:
 	case MADV_PAGEOUT:
-	case MADV_FREE:
 	case MADV_POPULATE_READ:
 	case MADV_POPULATE_WRITE:
 	case MADV_COLLAPSE:
@@ -1667,6 +1679,7 @@ static enum madvise_lock_mode get_lock_mode(struct madvise_behavior *madv_behavi
 		return MADVISE_MMAP_READ_LOCK;
 	case MADV_DONTNEED:
 	case MADV_DONTNEED_LOCKED:
+	case MADV_FREE:
 		return MADVISE_VMA_READ_LOCK;
 	default:
 		return MADVISE_MMAP_WRITE_LOCK;
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index ff5299eca687..a214a2b40ab9 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -422,7 +422,7 @@ static inline void process_mm_walk_lock(struct mm_struct *mm,
 {
 	if (walk_lock == PGWALK_RDLOCK)
 		mmap_assert_locked(mm);
-	else
+	else if (walk_lock != PGWALK_VMA_RDLOCK_VERIFY)
 		mmap_assert_write_locked(mm);
 }
 
@@ -437,6 +437,9 @@ static inline void process_vma_walk_lock(struct vm_area_struct *vma,
 	case PGWALK_WRLOCK_VERIFY:
 		vma_assert_write_locked(vma);
 		break;
+	case PGWALK_VMA_RDLOCK_VERIFY:
+		vma_assert_locked(vma);
+		break;
 	case PGWALK_RDLOCK:
 		/* PGWALK_RDLOCK is handled by process_mm_walk_lock */
 		break;
-- 
cgit v1.2.3


From 234dda7a49ff94154b527784687f549b9f1417c1 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Thu, 12 Jun 2025 15:34:41 +0100
Subject: mm: remove zero_user()

All users have now been converted to either memzero_page() or
folio_zero_range().

Link: https://lkml.kernel.org/r/20250612143443.2848197-6-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Ilya Dryomov <idryomov@gmail.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Xiubo Li <xiubli@redhat.com>
Cc: Dan Carpenter <dan.carpenter@linaro.org>
Cc: Viacheslav Dubeyko <Slava.Dubeyko@ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/highmem.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index e48d7f27b0b9..a30526cc53a7 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -292,12 +292,6 @@ static inline void zero_user_segment(struct page *page,
 	zero_user_segments(page, start, end, 0, 0);
 }
 
-static inline void zero_user(struct page *page,
-	unsigned start, unsigned size)
-{
-	zero_user_segments(page, start, start + size, 0, 0);
-}
-
 #ifndef __HAVE_ARCH_COPY_USER_HIGHPAGE
 
 static inline void copy_user_highpage(struct page *to, struct page *from,
-- 
cgit v1.2.3


From 02825c0925fbd53c085e88a1b7603eee8c9c6751 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 13 Jun 2025 11:27:02 +0200
Subject: mm/huge_memory: don't mark refcounted folios special in
 vmf_insert_folio_pud()

Marking PUDs that map a "normal" refcounted folios as special is against
our rules documented for vm_normal_page().  normal (refcounted) folios
shall never have the page table mapping marked as special.

Fortunately, there are not that many pud_special() check that can be
mislead and are right now rather harmless: e.g., none so far bases
decisions whether to grab a folio reference on that decision.

Well, and GUP-fast will fallback to GUP-slow.  All in all, so far no big
implications as it seems.

Getting this right will get more important as we introduce
folio_normal_page_pud() and start using it in more place where we
currently special-case based on other VMA flags.

Fix it just like we fixed vmf_insert_folio_pmd().

Add folio_mk_pud() to mimic what we do with folio_mk_pmd().

Link: https://lkml.kernel.org/r/20250613092702.1943533-4-david@redhat.com
Fixes: dbe54153296d ("mm/huge_memory: add vmf_insert_folio_pud()")
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Tested-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 19 ++++++++++++++++++-
 mm/huge_memory.c   | 52 +++++++++++++++++++++++++++++-----------------------
 2 files changed, 47 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0ef2ba0c667a..b7e2abd8ce0d 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1816,7 +1816,24 @@ static inline pmd_t folio_mk_pmd(struct folio *folio, pgprot_t pgprot)
 {
 	return pmd_mkhuge(pfn_pmd(folio_pfn(folio), pgprot));
 }
-#endif
+
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+/**
+ * folio_mk_pud - Create a PUD for this folio
+ * @folio: The folio to create a PUD for
+ * @pgprot: The page protection bits to use
+ *
+ * Create a page table entry for the first page of this folio.
+ * This is suitable for passing to set_pud_at().
+ *
+ * Return: A page table entry suitable for mapping this folio.
+ */
+static inline pud_t folio_mk_pud(struct folio *folio, pgprot_t pgprot)
+{
+	return pud_mkhuge(pfn_pud(folio_pfn(folio), pgprot));
+}
+#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 #endif /* CONFIG_MMU */
 
 static inline bool folio_has_pincount(const struct folio *folio)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index d1e3e253c714..bbc1dab98f2f 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1536,15 +1536,18 @@ static pud_t maybe_pud_mkwrite(pud_t pud, struct vm_area_struct *vma)
 	return pud;
 }
 
-static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
-		pud_t *pud, pfn_t pfn, pgprot_t prot, bool write)
+static void insert_pud(struct vm_area_struct *vma, unsigned long addr,
+		pud_t *pud, struct folio_or_pfn fop, pgprot_t prot, bool write)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pud_t entry;
 
 	if (!pud_none(*pud)) {
+		const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) :
+					  pfn_t_to_pfn(fop.pfn);
+
 		if (write) {
-			if (WARN_ON_ONCE(pud_pfn(*pud) != pfn_t_to_pfn(pfn)))
+			if (WARN_ON_ONCE(pud_pfn(*pud) != pfn))
 				return;
 			entry = pud_mkyoung(*pud);
 			entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
@@ -1554,11 +1557,20 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
 		return;
 	}
 
-	entry = pud_mkhuge(pfn_t_pud(pfn, prot));
-	if (pfn_t_devmap(pfn))
-		entry = pud_mkdevmap(entry);
-	else
-		entry = pud_mkspecial(entry);
+	if (fop.is_folio) {
+		entry = folio_mk_pud(fop.folio, vma->vm_page_prot);
+
+		folio_get(fop.folio);
+		folio_add_file_rmap_pud(fop.folio, &fop.folio->page, vma);
+		add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PUD_NR);
+	} else {
+		entry = pud_mkhuge(pfn_t_pud(fop.pfn, prot));
+
+		if (pfn_t_devmap(fop.pfn))
+			entry = pud_mkdevmap(entry);
+		else
+			entry = pud_mkspecial(entry);
+	}
 	if (write) {
 		entry = pud_mkyoung(pud_mkdirty(entry));
 		entry = maybe_pud_mkwrite(entry, vma);
@@ -1582,6 +1594,9 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
 	unsigned long addr = vmf->address & PUD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
 	pgprot_t pgprot = vma->vm_page_prot;
+	struct folio_or_pfn fop = {
+		.pfn = pfn,
+	};
 	spinlock_t *ptl;
 
 	/*
@@ -1601,7 +1616,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
 	pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot);
 
 	ptl = pud_lock(vma->vm_mm, vmf->pud);
-	insert_pfn_pud(vma, addr, vmf->pud, pfn, pgprot, write);
+	insert_pud(vma, addr, vmf->pud, fop, pgprot, write);
 	spin_unlock(ptl);
 
 	return VM_FAULT_NOPAGE;
@@ -1623,6 +1638,10 @@ vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
 	unsigned long addr = vmf->address & PUD_MASK;
 	pud_t *pud = vmf->pud;
 	struct mm_struct *mm = vma->vm_mm;
+	struct folio_or_pfn fop = {
+		.folio = folio,
+		.is_folio = true,
+	};
 	spinlock_t *ptl;
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
@@ -1632,20 +1651,7 @@ vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
 		return VM_FAULT_SIGBUS;
 
 	ptl = pud_lock(mm, pud);
-
-	/*
-	 * If there is already an entry present we assume the folio is
-	 * already mapped, hence no need to take another reference. We
-	 * still call insert_pfn_pud() though in case the mapping needs
-	 * upgrading to writeable.
-	 */
-	if (pud_none(*vmf->pud)) {
-		folio_get(folio);
-		folio_add_file_rmap_pud(folio, &folio->page, vma);
-		add_mm_counter(mm, mm_counter_file(folio), HPAGE_PUD_NR);
-	}
-	insert_pfn_pud(vma, addr, vmf->pud, pfn_to_pfn_t(folio_pfn(folio)),
-		       vma->vm_page_prot, write);
+	insert_pud(vma, addr, vmf->pud, fop, vma->vm_page_prot, write);
 	spin_unlock(ptl);
 
 	return VM_FAULT_NOPAGE;
-- 
cgit v1.2.3


From 9e82db9c0cdafa068969373b4bad140f72988e32 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Fri, 13 Jun 2025 20:48:23 +0100
Subject: highmem: remove a use of folio->page

Call folio_address() instead of page_address().

Link: https://lkml.kernel.org/r/20250613194825.3175276-1-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/highmem-internal.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem-internal.h b/include/linux/highmem-internal.h
index 9a7683d79a4b..36053c3d6d64 100644
--- a/include/linux/highmem-internal.h
+++ b/include/linux/highmem-internal.h
@@ -195,7 +195,7 @@ static inline void *kmap_local_page_try_from_panic(struct page *page)
 
 static inline void *kmap_local_folio(struct folio *folio, size_t offset)
 {
-	return page_address(&folio->page) + offset;
+	return folio_address(folio) + offset;
 }
 
 static inline void *kmap_local_page_prot(struct page *page, pgprot_t prot)
-- 
cgit v1.2.3


From 78ddaa358ec4cdd60bd0e243ced1c83a52c30241 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Wed, 18 Jun 2025 20:42:52 +0100
Subject: mm: change vm_get_page_prot() to accept vm_flags_t argument

Patch series "use vm_flags_t consistently".

The VMA flags field vma->vm_flags is of type vm_flags_t.  Right now this
is exactly equivalent to unsigned long, but it should not be assumed to
be.

Much code that references vma->vm_flags already correctly uses vm_flags_t,
but a fairly large chunk of code simply uses unsigned long and assumes
that the two are equivalent.

This series corrects that and has us use vm_flags_t consistently.

This series is motivated by the desire to, in a future series, adjust
vm_flags_t to be a u64 regardless of whether the kernel is 32-bit or
64-bit in order to deal with the VMA flag exhaustion issue and avoid all
the various problems that arise from it (being unable to use certain
features in 32-bit, being unable to add new flags except for 64-bit, etc.)

This is therefore a critical first step towards that goal.  At any rate,
using the correct type is of value regardless.

We additionally take the opportunity to refer to VMA flags as vm_flags
where possible to make clear what we're referring to.

Overall, this series does not introduce any functional change.


This patch (of 3):

We abstract the type of the VMA flags to vm_flags_t, however in may places
it is simply assumed this is unsigned long, which is simply incorrect.

At the moment this is simply an incongruity, however in future we plan to
change this type and therefore this change is a critical requirement for
doing so.

Overall, this patch does not introduce any functional change.

[lorenzo.stoakes@oracle.com: add missing vm_get_page_prot() instance, remove include]
  Link: https://lkml.kernel.org/r/552f88e1-2df8-4e95-92b8-812f7c8db829@lucifer.local
Link: https://lkml.kernel.org/r/cover.1750274467.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/a12769720a2743f235643b158c4f4f0a9911daf0.1750274467.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Acked-by: Catalin Marinas <catalin.marinas@arm.com>	[arm64]
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm64/mm/mmap.c                       | 2 +-
 arch/powerpc/include/asm/book3s/64/pkeys.h | 2 +-
 arch/powerpc/mm/book3s64/pgtable.c         | 2 +-
 arch/sparc/mm/init_64.c                    | 2 +-
 arch/x86/mm/pgprot.c                       | 2 +-
 include/linux/mm.h                         | 4 ++--
 include/linux/pgtable.h                    | 2 +-
 tools/testing/vma/vma_internal.h           | 2 +-
 8 files changed, 9 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/mm/mmap.c b/arch/arm64/mm/mmap.c
index c86c348857c4..08ee177432c2 100644
--- a/arch/arm64/mm/mmap.c
+++ b/arch/arm64/mm/mmap.c
@@ -81,7 +81,7 @@ static int __init adjust_protection_map(void)
 }
 arch_initcall(adjust_protection_map);
 
-pgprot_t vm_get_page_prot(unsigned long vm_flags)
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 {
 	ptdesc_t prot;
 
diff --git a/arch/powerpc/include/asm/book3s/64/pkeys.h b/arch/powerpc/include/asm/book3s/64/pkeys.h
index 5b178139f3c0..ff911b4251d9 100644
--- a/arch/powerpc/include/asm/book3s/64/pkeys.h
+++ b/arch/powerpc/include/asm/book3s/64/pkeys.h
@@ -5,7 +5,7 @@
 
 #include <asm/book3s/64/hash-pkey.h>
 
-static inline u64 vmflag_to_pte_pkey_bits(u64 vm_flags)
+static inline u64 vmflag_to_pte_pkey_bits(vm_flags_t vm_flags)
 {
 	if (!mmu_has_feature(MMU_FTR_PKEY))
 		return 0x0UL;
diff --git a/arch/powerpc/mm/book3s64/pgtable.c b/arch/powerpc/mm/book3s64/pgtable.c
index 0db01e10a3f8..a89ef89101fc 100644
--- a/arch/powerpc/mm/book3s64/pgtable.c
+++ b/arch/powerpc/mm/book3s64/pgtable.c
@@ -644,7 +644,7 @@ unsigned long memremap_compat_align(void)
 EXPORT_SYMBOL_GPL(memremap_compat_align);
 #endif
 
-pgprot_t vm_get_page_prot(unsigned long vm_flags)
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 {
 	unsigned long prot;
 
diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 25ae4c897aae..7ed58bf3aaca 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -3201,7 +3201,7 @@ void copy_highpage(struct page *to, struct page *from)
 }
 EXPORT_SYMBOL(copy_highpage);
 
-pgprot_t vm_get_page_prot(unsigned long vm_flags)
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 {
 	unsigned long prot = pgprot_val(protection_map[vm_flags &
 					(VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
diff --git a/arch/x86/mm/pgprot.c b/arch/x86/mm/pgprot.c
index c84bd9540b16..dc1afd5c839d 100644
--- a/arch/x86/mm/pgprot.c
+++ b/arch/x86/mm/pgprot.c
@@ -32,7 +32,7 @@ void add_encrypt_protection_map(void)
 		protection_map[i] = pgprot_encrypted(protection_map[i]);
 }
 
-pgprot_t vm_get_page_prot(unsigned long vm_flags)
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 {
 	unsigned long val = pgprot_val(protection_map[vm_flags &
 				      (VM_READ|VM_WRITE|VM_EXEC|VM_SHARED)]);
diff --git a/include/linux/mm.h b/include/linux/mm.h
index b7e2abd8ce0d..78bb177ba55f 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3489,10 +3489,10 @@ static inline bool range_in_vma(struct vm_area_struct *vma,
 }
 
 #ifdef CONFIG_MMU
-pgprot_t vm_get_page_prot(unsigned long vm_flags);
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags);
 void vma_set_page_prot(struct vm_area_struct *vma);
 #else
-static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
+static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 {
 	return __pgprot(0);
 }
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e4a3895c043b..d05e35a0facf 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -2016,7 +2016,7 @@ typedef unsigned int pgtbl_mod_mask;
  *								x: (yes) yes
  */
 #define DECLARE_VM_GET_PAGE_PROT					\
-pgprot_t vm_get_page_prot(unsigned long vm_flags)			\
+pgprot_t vm_get_page_prot(vm_flags_t vm_flags)				\
 {									\
 		return protection_map[vm_flags &			\
 			(VM_READ | VM_WRITE | VM_EXEC | VM_SHARED)];	\
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 0f013784da89..3b1b45256d56 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -576,7 +576,7 @@ static inline pgprot_t pgprot_modify(pgprot_t oldprot, pgprot_t newprot)
 	return __pgprot(pgprot_val(oldprot) | pgprot_val(newprot));
 }
 
-static inline pgprot_t vm_get_page_prot(unsigned long vm_flags)
+static inline pgprot_t vm_get_page_prot(vm_flags_t vm_flags)
 {
 	return __pgprot(vm_flags);
 }
-- 
cgit v1.2.3


From bfbe71109fa40e8cc05a0f99e6734b7d76ee00b0 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Wed, 18 Jun 2025 20:42:53 +0100
Subject: mm: update core kernel code to use vm_flags_t consistently

The core kernel code is currently very inconsistent in its use of
vm_flags_t vs.  unsigned long.  This prevents us from changing the type of
vm_flags_t in the future and is simply not correct, so correct this.

While this results in rather a lot of churn, it is a critical
pre-requisite for a future planned change to VMA flag type.

Additionally, update VMA userland tests to account for the changes.

To make review easier and to break things into smaller parts, driver and
architecture-specific changes is left for a subsequent commit.

The code has been adjusted to cascade the changes across all calling code
as far as is needed.

We will adjust architecture-specific and driver code in a subsequent patch.

Overall, this patch does not introduce any functional change.

Link: https://lkml.kernel.org/r/d1588e7bb96d1ea3fe7b9df2c699d5b4592d901d.1750274467.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Kees Cook <kees@kernel.org>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Jan Kara <jack@suse.cz>
Acked-by: Christian Brauner <brauner@kernel.org>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/exec.c                        |   2 +-
 fs/userfaultfd.c                 |   2 +-
 include/linux/coredump.h         |   2 +-
 include/linux/huge_mm.h          |  12 +-
 include/linux/khugepaged.h       |   4 +-
 include/linux/ksm.h              |   4 +-
 include/linux/memfd.h            |   4 +-
 include/linux/mm.h               |   6 +-
 include/linux/mm_types.h         |   2 +-
 include/linux/mman.h             |   4 +-
 include/linux/rmap.h             |   4 +-
 include/linux/userfaultfd_k.h    |   4 +-
 include/trace/events/fs_dax.h    |   6 +-
 mm/debug.c                       |   2 +-
 mm/execmem.c                     |   8 +-
 mm/filemap.c                     |   2 +-
 mm/gup.c                         |   2 +-
 mm/huge_memory.c                 |   2 +-
 mm/hugetlb.c                     |   4 +-
 mm/internal.h                    |   4 +-
 mm/khugepaged.c                  |   4 +-
 mm/ksm.c                         |   2 +-
 mm/madvise.c                     |   4 +-
 mm/mapping_dirty_helpers.c       |   2 +-
 mm/memfd.c                       |   8 +-
 mm/memory.c                      |   4 +-
 mm/mmap.c                        |  16 +--
 mm/mprotect.c                    |   8 +-
 mm/mremap.c                      |   2 +-
 mm/nommu.c                       |  12 +-
 mm/rmap.c                        |   4 +-
 mm/shmem.c                       |   6 +-
 mm/userfaultfd.c                 |  14 +--
 mm/vma.c                         |  80 ++++++------
 mm/vma.h                         |  16 +--
 mm/vmscan.c                      |   4 +-
 tools/testing/vma/vma.c          | 266 +++++++++++++++++++--------------------
 tools/testing/vma/vma_internal.h |   8 +-
 38 files changed, 270 insertions(+), 270 deletions(-)

(limited to 'include/linux')

diff --git a/fs/exec.c b/fs/exec.c
index ba400aafd640..9faf9052bed9 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -604,7 +604,7 @@ int setup_arg_pages(struct linux_binprm *bprm,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma = bprm->vma;
 	struct vm_area_struct *prev = NULL;
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 	unsigned long stack_base;
 	unsigned long stack_size;
 	unsigned long stack_expand;
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index a2928b0aec6f..48e82e19d831 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -1242,7 +1242,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	int ret;
 	struct uffdio_register uffdio_register;
 	struct uffdio_register __user *user_uffdio_register;
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 	bool found;
 	bool basic_ioctls;
 	unsigned long start, end;
diff --git a/include/linux/coredump.h b/include/linux/coredump.h
index 76e41805b92d..c504b0faecc2 100644
--- a/include/linux/coredump.h
+++ b/include/linux/coredump.h
@@ -10,7 +10,7 @@
 #ifdef CONFIG_COREDUMP
 struct core_vma_metadata {
 	unsigned long start, end;
-	unsigned long flags;
+	vm_flags_t flags;
 	unsigned long dump_size;
 	unsigned long pgoff;
 	struct file   *file;
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 2f190c90192d..7753daac49f7 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -261,7 +261,7 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
 }
 
 unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
-					 unsigned long vm_flags,
+					 vm_flags_t vm_flags,
 					 unsigned long tva_flags,
 					 unsigned long orders);
 
@@ -282,7 +282,7 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
  */
 static inline
 unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
-				       unsigned long vm_flags,
+				       vm_flags_t vm_flags,
 				       unsigned long tva_flags,
 				       unsigned long orders)
 {
@@ -317,7 +317,7 @@ struct thpsize {
 	 (1<<TRANSPARENT_HUGEPAGE_USE_ZERO_PAGE_FLAG))
 
 static inline bool vma_thp_disabled(struct vm_area_struct *vma,
-		unsigned long vm_flags)
+		vm_flags_t vm_flags)
 {
 	/*
 	 * Explicitly disabled through madvise or prctl, or some
@@ -431,7 +431,7 @@ change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 			__split_huge_pud(__vma, __pud, __address);	\
 	}  while (0)
 
-int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags,
+int hugepage_madvise(struct vm_area_struct *vma, vm_flags_t *vm_flags,
 		     int advice);
 int madvise_collapse(struct vm_area_struct *vma,
 		     struct vm_area_struct **prev,
@@ -524,7 +524,7 @@ static inline unsigned long thp_vma_suitable_orders(struct vm_area_struct *vma,
 }
 
 static inline unsigned long thp_vma_allowable_orders(struct vm_area_struct *vma,
-					unsigned long vm_flags,
+					vm_flags_t vm_flags,
 					unsigned long tva_flags,
 					unsigned long orders)
 {
@@ -593,7 +593,7 @@ static inline bool unmap_huge_pmd_locked(struct vm_area_struct *vma,
 	do { } while (0)
 
 static inline int hugepage_madvise(struct vm_area_struct *vma,
-				   unsigned long *vm_flags, int advice)
+				   vm_flags_t *vm_flags, int advice)
 {
 	return -EINVAL;
 }
diff --git a/include/linux/khugepaged.h b/include/linux/khugepaged.h
index b8d69cfbb58b..ff6120463745 100644
--- a/include/linux/khugepaged.h
+++ b/include/linux/khugepaged.h
@@ -12,7 +12,7 @@ extern int start_stop_khugepaged(void);
 extern void __khugepaged_enter(struct mm_struct *mm);
 extern void __khugepaged_exit(struct mm_struct *mm);
 extern void khugepaged_enter_vma(struct vm_area_struct *vma,
-				 unsigned long vm_flags);
+				 vm_flags_t vm_flags);
 extern void khugepaged_min_free_kbytes_update(void);
 extern bool current_is_khugepaged(void);
 extern int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
@@ -37,7 +37,7 @@ static inline void khugepaged_exit(struct mm_struct *mm)
 {
 }
 static inline void khugepaged_enter_vma(struct vm_area_struct *vma,
-					unsigned long vm_flags)
+					vm_flags_t vm_flags)
 {
 }
 static inline int collapse_pte_mapped_thp(struct mm_struct *mm,
diff --git a/include/linux/ksm.h b/include/linux/ksm.h
index 51787f0b0208..c17b955e7b0b 100644
--- a/include/linux/ksm.h
+++ b/include/linux/ksm.h
@@ -16,7 +16,7 @@
 
 #ifdef CONFIG_KSM
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
-		unsigned long end, int advice, unsigned long *vm_flags);
+		unsigned long end, int advice, vm_flags_t *vm_flags);
 vm_flags_t ksm_vma_flags(const struct mm_struct *mm, const struct file *file,
 			 vm_flags_t vm_flags);
 int ksm_enable_merge_any(struct mm_struct *mm);
@@ -133,7 +133,7 @@ static inline void collect_procs_ksm(const struct folio *folio,
 
 #ifdef CONFIG_MMU
 static inline int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
-		unsigned long end, int advice, unsigned long *vm_flags)
+		unsigned long end, int advice, vm_flags_t *vm_flags)
 {
 	return 0;
 }
diff --git a/include/linux/memfd.h b/include/linux/memfd.h
index 246daadbfde8..6f606d9573c3 100644
--- a/include/linux/memfd.h
+++ b/include/linux/memfd.h
@@ -14,7 +14,7 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx);
  * We also update VMA flags if appropriate by manipulating the VMA flags pointed
  * to by vm_flags_ptr.
  */
-int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr);
+int memfd_check_seals_mmap(struct file *file, vm_flags_t *vm_flags_ptr);
 #else
 static inline long memfd_fcntl(struct file *f, unsigned int c, unsigned int a)
 {
@@ -25,7 +25,7 @@ static inline struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 	return ERR_PTR(-EINVAL);
 }
 static inline int memfd_check_seals_mmap(struct file *file,
-					 unsigned long *vm_flags_ptr)
+					 vm_flags_t *vm_flags_ptr)
 {
 	return 0;
 }
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 78bb177ba55f..fc365420dfa8 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2564,7 +2564,7 @@ extern long change_protection(struct mmu_gather *tlb,
 			      unsigned long end, unsigned long cp_flags);
 extern int mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
 	  struct vm_area_struct *vma, struct vm_area_struct **pprev,
-	  unsigned long start, unsigned long end, unsigned long newflags);
+	  unsigned long start, unsigned long end, vm_flags_t newflags);
 
 /*
  * doesn't attempt to fault and will return short.
@@ -3323,9 +3323,9 @@ extern void vm_stat_account(struct mm_struct *, vm_flags_t, long npages);
 
 extern bool vma_is_special_mapping(const struct vm_area_struct *vma,
 				   const struct vm_special_mapping *sm);
-extern struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
+struct vm_area_struct *_install_special_mapping(struct mm_struct *mm,
 				   unsigned long addr, unsigned long len,
-				   unsigned long flags,
+				   vm_flags_t vm_flags,
 				   const struct vm_special_mapping *spec);
 
 unsigned long randomize_stack_top(unsigned long stack_top);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d6b91e8a66d6..804d269a4f5e 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1081,7 +1081,7 @@ struct mm_struct {
 		unsigned long data_vm;	   /* VM_WRITE & ~VM_SHARED & ~VM_STACK */
 		unsigned long exec_vm;	   /* VM_EXEC & ~VM_WRITE & ~VM_STACK */
 		unsigned long stack_vm;	   /* VM_STACK */
-		unsigned long def_flags;
+		vm_flags_t def_flags;
 
 		/**
 		 * @write_protect_seq: Locked when any thread is write
diff --git a/include/linux/mman.h b/include/linux/mman.h
index f4c6346a8fcd..de9e8e6229a4 100644
--- a/include/linux/mman.h
+++ b/include/linux/mman.h
@@ -137,7 +137,7 @@ static inline bool arch_validate_flags(unsigned long flags)
 /*
  * Combine the mmap "prot" argument into "vm_flags" used internally.
  */
-static inline unsigned long
+static inline vm_flags_t
 calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
 {
 	return _calc_vm_trans(prot, PROT_READ,  VM_READ ) |
@@ -149,7 +149,7 @@ calc_vm_prot_bits(unsigned long prot, unsigned long pkey)
 /*
  * Combine the mmap "flags" argument into "vm_flags" used internally.
  */
-static inline unsigned long
+static inline vm_flags_t
 calc_vm_flag_bits(struct file *file, unsigned long flags)
 {
 	return _calc_vm_trans(flags, MAP_GROWSDOWN,  VM_GROWSDOWN ) |
diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index c4f4903b1088..20803fcb49a7 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -893,7 +893,7 @@ static inline int folio_try_share_anon_rmap_pmd(struct folio *folio,
  * Called from mm/vmscan.c to handle paging out
  */
 int folio_referenced(struct folio *, int is_locked,
-			struct mem_cgroup *memcg, unsigned long *vm_flags);
+			struct mem_cgroup *memcg, vm_flags_t *vm_flags);
 
 void try_to_migrate(struct folio *folio, enum ttu_flags flags);
 void try_to_unmap(struct folio *, enum ttu_flags flags);
@@ -1025,7 +1025,7 @@ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio,
 
 static inline int folio_referenced(struct folio *folio, int is_locked,
 				  struct mem_cgroup *memcg,
-				  unsigned long *vm_flags)
+				  vm_flags_t *vm_flags)
 {
 	*vm_flags = 0;
 	return 0;
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index ccad58602846..df85330bcfa6 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -209,7 +209,7 @@ static inline bool userfaultfd_armed(struct vm_area_struct *vma)
 }
 
 static inline bool vma_can_userfault(struct vm_area_struct *vma,
-				     unsigned long vm_flags,
+				     vm_flags_t vm_flags,
 				     bool wp_async)
 {
 	vm_flags &= __VM_UFFD_FLAGS;
@@ -281,7 +281,7 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi,
 
 int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 			       struct vm_area_struct *vma,
-			       unsigned long vm_flags,
+			       vm_flags_t vm_flags,
 			       unsigned long start, unsigned long end,
 			       bool wp_async);
 
diff --git a/include/trace/events/fs_dax.h b/include/trace/events/fs_dax.h
index 76b56f78abb0..50ebc1290ab0 100644
--- a/include/trace/events/fs_dax.h
+++ b/include/trace/events/fs_dax.h
@@ -15,7 +15,7 @@ DECLARE_EVENT_CLASS(dax_pmd_fault_class,
 		__field(unsigned long, ino)
 		__field(unsigned long, vm_start)
 		__field(unsigned long, vm_end)
-		__field(unsigned long, vm_flags)
+		__field(vm_flags_t, vm_flags)
 		__field(unsigned long, address)
 		__field(pgoff_t, pgoff)
 		__field(pgoff_t, max_pgoff)
@@ -67,7 +67,7 @@ DECLARE_EVENT_CLASS(dax_pmd_load_hole_class,
 	TP_ARGS(inode, vmf, zero_folio, radix_entry),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
-		__field(unsigned long, vm_flags)
+		__field(vm_flags_t, vm_flags)
 		__field(unsigned long, address)
 		__field(struct folio *, zero_folio)
 		__field(void *, radix_entry)
@@ -107,7 +107,7 @@ DECLARE_EVENT_CLASS(dax_pte_fault_class,
 	TP_ARGS(inode, vmf, result),
 	TP_STRUCT__entry(
 		__field(unsigned long, ino)
-		__field(unsigned long, vm_flags)
+		__field(vm_flags_t, vm_flags)
 		__field(unsigned long, address)
 		__field(pgoff_t, pgoff)
 		__field(dev_t, dev)
diff --git a/mm/debug.c b/mm/debug.c
index 907382257062..e2973e1b3812 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -290,7 +290,7 @@ void dump_vmg(const struct vma_merge_struct *vmg, const char *reason)
 		vmg->vmi, vmg->vmi ? vma_iter_addr(vmg->vmi) : 0,
 		vmg->vmi ? vma_iter_end(vmg->vmi) : 0,
 		vmg->prev, vmg->middle, vmg->next, vmg->target,
-		vmg->start, vmg->end, vmg->flags,
+		vmg->start, vmg->end, vmg->vm_flags,
 		vmg->file, vmg->anon_vma, vmg->policy,
 #ifdef CONFIG_USERFAULTFD
 		vmg->uffd_ctx.ctx,
diff --git a/mm/execmem.c b/mm/execmem.c
index 2b683e7d864d..627e6cf64f4f 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -26,7 +26,7 @@ static struct execmem_info default_execmem_info __ro_after_init;
 
 #ifdef CONFIG_MMU
 static void *execmem_vmalloc(struct execmem_range *range, size_t size,
-			     pgprot_t pgprot, unsigned long vm_flags)
+			     pgprot_t pgprot, vm_flags_t vm_flags)
 {
 	bool kasan = range->flags & EXECMEM_KASAN_SHADOW;
 	gfp_t gfp_flags = GFP_KERNEL | __GFP_NOWARN;
@@ -82,7 +82,7 @@ struct vm_struct *execmem_vmap(size_t size)
 }
 #else
 static void *execmem_vmalloc(struct execmem_range *range, size_t size,
-			     pgprot_t pgprot, unsigned long vm_flags)
+			     pgprot_t pgprot, vm_flags_t vm_flags)
 {
 	return vmalloc(size);
 }
@@ -256,7 +256,7 @@ out_unlock:
 
 static int execmem_cache_populate(struct execmem_range *range, size_t size)
 {
-	unsigned long vm_flags = VM_ALLOW_HUGE_VMAP;
+	vm_flags_t vm_flags = VM_ALLOW_HUGE_VMAP;
 	struct vm_struct *vm;
 	size_t alloc_size;
 	int err = -ENOMEM;
@@ -373,7 +373,7 @@ void *execmem_alloc(enum execmem_type type, size_t size)
 {
 	struct execmem_range *range = &execmem_info->ranges[type];
 	bool use_cache = range->flags & EXECMEM_ROX_CACHE;
-	unsigned long vm_flags = VM_FLUSH_RESET_PERMS;
+	vm_flags_t vm_flags = VM_FLUSH_RESET_PERMS;
 	pgprot_t pgprot = range->pgprot;
 	void *p;
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 3cf955740148..0d0369fb5fa1 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -3216,7 +3216,7 @@ static struct file *do_sync_mmap_readahead(struct vm_fault *vmf)
 	struct address_space *mapping = file->f_mapping;
 	DEFINE_READAHEAD(ractl, file, ra, mapping, vmf->pgoff);
 	struct file *fpin = NULL;
-	unsigned long vm_flags = vmf->vma->vm_flags;
+	vm_flags_t vm_flags = vmf->vma->vm_flags;
 	unsigned short mmap_miss;
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/mm/gup.c b/mm/gup.c
index cbe8e4b9845b..c08b97e0d344 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2044,7 +2044,7 @@ static long __get_user_pages_locked(struct mm_struct *mm, unsigned long start,
 {
 	struct vm_area_struct *vma;
 	bool must_unlock = false;
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 	long i;
 
 	if (!nr_pages)
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 1b31985cef11..6411f3107af1 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -99,7 +99,7 @@ static inline bool file_thp_enabled(struct vm_area_struct *vma)
 }
 
 unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
-					 unsigned long vm_flags,
+					 vm_flags_t vm_flags,
 					 unsigned long tva_flags,
 					 unsigned long orders)
 {
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 7a7df0b2a561..c7ba95030241 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7465,8 +7465,8 @@ static unsigned long page_table_shareable(struct vm_area_struct *svma,
 	unsigned long s_end = sbase + PUD_SIZE;
 
 	/* Allow segments to share if only one is marked locked */
-	unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED_MASK;
-	unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED_MASK;
+	vm_flags_t vm_flags = vma->vm_flags & ~VM_LOCKED_MASK;
+	vm_flags_t svm_flags = svma->vm_flags & ~VM_LOCKED_MASK;
 
 	/*
 	 * match the virtual addresses, permission and the alignment of the
diff --git a/mm/internal.h b/mm/internal.h
index 3eb51c31a041..fe83dfca3c72 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -928,7 +928,7 @@ extern long populate_vma_page_range(struct vm_area_struct *vma,
 		unsigned long start, unsigned long end, int *locked);
 extern long faultin_page_range(struct mm_struct *mm, unsigned long start,
 		unsigned long end, bool write, int *locked);
-extern bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
+extern bool mlock_future_ok(struct mm_struct *mm, vm_flags_t vm_flags,
 			       unsigned long bytes);
 
 /*
@@ -1358,7 +1358,7 @@ int migrate_device_coherent_folio(struct folio *folio);
 
 struct vm_struct *__get_vm_area_node(unsigned long size,
 				     unsigned long align, unsigned long shift,
-				     unsigned long flags, unsigned long start,
+				     vm_flags_t vm_flags, unsigned long start,
 				     unsigned long end, int node, gfp_t gfp_mask,
 				     const void *caller);
 
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 15203ea7d007..6b09b09c8f82 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -347,7 +347,7 @@ struct attribute_group khugepaged_attr_group = {
 #endif /* CONFIG_SYSFS */
 
 int hugepage_madvise(struct vm_area_struct *vma,
-		     unsigned long *vm_flags, int advice)
+		     vm_flags_t *vm_flags, int advice)
 {
 	switch (advice) {
 	case MADV_HUGEPAGE:
@@ -470,7 +470,7 @@ void __khugepaged_enter(struct mm_struct *mm)
 }
 
 void khugepaged_enter_vma(struct vm_area_struct *vma,
-			  unsigned long vm_flags)
+			  vm_flags_t vm_flags)
 {
 	if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
 	    hugepage_pmd_enabled()) {
diff --git a/mm/ksm.c b/mm/ksm.c
index 18b3690bb69a..ef73b25fd65a 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -2840,7 +2840,7 @@ int ksm_disable(struct mm_struct *mm)
 }
 
 int ksm_madvise(struct vm_area_struct *vma, unsigned long start,
-		unsigned long end, int advice, unsigned long *vm_flags)
+		unsigned long end, int advice, vm_flags_t *vm_flags)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	int err;
diff --git a/mm/madvise.c b/mm/madvise.c
index d451438af999..92f427b1b330 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -130,7 +130,7 @@ static int replace_anon_vma_name(struct vm_area_struct *vma,
  */
 static int madvise_update_vma(struct vm_area_struct *vma,
 			      struct vm_area_struct **prev, unsigned long start,
-			      unsigned long end, unsigned long new_flags,
+			      unsigned long end, vm_flags_t new_flags,
 			      struct anon_vma_name *anon_name)
 {
 	struct mm_struct *mm = vma->vm_mm;
@@ -1258,7 +1258,7 @@ static int madvise_vma_behavior(struct vm_area_struct *vma,
 	int behavior = arg->behavior;
 	int error;
 	struct anon_vma_name *anon_name;
-	unsigned long new_flags = vma->vm_flags;
+	vm_flags_t new_flags = vma->vm_flags;
 
 	if (unlikely(!can_modify_vma_madv(vma, behavior)))
 		return -EPERM;
diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c
index 2f8829b3541a..dc1692ff9e58 100644
--- a/mm/mapping_dirty_helpers.c
+++ b/mm/mapping_dirty_helpers.c
@@ -218,7 +218,7 @@ static void wp_clean_post_vma(struct mm_walk *walk)
 static int wp_clean_test_walk(unsigned long start, unsigned long end,
 			      struct mm_walk *walk)
 {
-	unsigned long vm_flags = READ_ONCE(walk->vma->vm_flags);
+	vm_flags_t vm_flags = READ_ONCE(walk->vma->vm_flags);
 
 	/* Skip non-applicable VMAs */
 	if ((vm_flags & (VM_SHARED | VM_MAYWRITE | VM_HUGETLB)) !=
diff --git a/mm/memfd.c b/mm/memfd.c
index 65a107f72e39..b558c4c3bd27 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -332,10 +332,10 @@ static inline bool is_write_sealed(unsigned int seals)
 	return seals & (F_SEAL_WRITE | F_SEAL_FUTURE_WRITE);
 }
 
-static int check_write_seal(unsigned long *vm_flags_ptr)
+static int check_write_seal(vm_flags_t *vm_flags_ptr)
 {
-	unsigned long vm_flags = *vm_flags_ptr;
-	unsigned long mask = vm_flags & (VM_SHARED | VM_WRITE);
+	vm_flags_t vm_flags = *vm_flags_ptr;
+	vm_flags_t mask = vm_flags & (VM_SHARED | VM_WRITE);
 
 	/* If a private mapping then writability is irrelevant. */
 	if (!(mask & VM_SHARED))
@@ -357,7 +357,7 @@ static int check_write_seal(unsigned long *vm_flags_ptr)
 	return 0;
 }
 
-int memfd_check_seals_mmap(struct file *file, unsigned long *vm_flags_ptr)
+int memfd_check_seals_mmap(struct file *file, vm_flags_t *vm_flags_ptr)
 {
 	int err = 0;
 	unsigned int *seals_ptr = memfd_file_seals_ptr(file);
diff --git a/mm/memory.c b/mm/memory.c
index b0cda5aab398..833426fa5fe0 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -797,7 +797,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		pte_t *dst_pte, pte_t *src_pte, struct vm_area_struct *dst_vma,
 		struct vm_area_struct *src_vma, unsigned long addr, int *rss)
 {
-	unsigned long vm_flags = dst_vma->vm_flags;
+	vm_flags_t vm_flags = dst_vma->vm_flags;
 	pte_t orig_pte = ptep_get(src_pte);
 	pte_t pte = orig_pte;
 	struct folio *folio;
@@ -6128,7 +6128,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
 		.gfp_mask = __get_fault_gfp_mask(vma),
 	};
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long vm_flags = vma->vm_flags;
+	vm_flags_t vm_flags = vma->vm_flags;
 	pgd_t *pgd;
 	p4d_t *p4d;
 	vm_fault_t ret;
diff --git a/mm/mmap.c b/mm/mmap.c
index 09c563c95112..8f92cf10b656 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -80,7 +80,7 @@ core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644);
 /* Update vma->vm_page_prot to reflect vma->vm_flags. */
 void vma_set_page_prot(struct vm_area_struct *vma)
 {
-	unsigned long vm_flags = vma->vm_flags;
+	vm_flags_t vm_flags = vma->vm_flags;
 	pgprot_t vm_page_prot;
 
 	vm_page_prot = vm_pgprot_modify(vma->vm_page_prot, vm_flags);
@@ -228,12 +228,12 @@ static inline unsigned long round_hint_to_min(unsigned long hint)
 	return hint;
 }
 
-bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
+bool mlock_future_ok(struct mm_struct *mm, vm_flags_t vm_flags,
 			unsigned long bytes)
 {
 	unsigned long locked_pages, limit_pages;
 
-	if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
+	if (!(vm_flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
 		return true;
 
 	locked_pages = bytes >> PAGE_SHIFT;
@@ -1207,7 +1207,7 @@ out:
 	return ret;
 }
 
-int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
+int vm_brk_flags(unsigned long addr, unsigned long request, vm_flags_t vm_flags)
 {
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma = NULL;
@@ -1224,7 +1224,7 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 		return 0;
 
 	/* Until we need other flags, refuse anything except VM_EXEC. */
-	if ((flags & (~VM_EXEC)) != 0)
+	if ((vm_flags & (~VM_EXEC)) != 0)
 		return -EINVAL;
 
 	if (mmap_write_lock_killable(mm))
@@ -1239,7 +1239,7 @@ int vm_brk_flags(unsigned long addr, unsigned long request, unsigned long flags)
 		goto munmap_failed;
 
 	vma = vma_prev(&vmi);
-	ret = do_brk_flags(&vmi, vma, addr, len, flags);
+	ret = do_brk_flags(&vmi, vma, addr, len, vm_flags);
 	populate = ((mm->def_flags & VM_LOCKED) != 0);
 	mmap_write_unlock(mm);
 	userfaultfd_unmap_complete(mm, &uf);
@@ -1444,7 +1444,7 @@ static vm_fault_t special_mapping_fault(struct vm_fault *vmf)
 static struct vm_area_struct *__install_special_mapping(
 	struct mm_struct *mm,
 	unsigned long addr, unsigned long len,
-	unsigned long vm_flags, void *priv,
+	vm_flags_t vm_flags, void *priv,
 	const struct vm_operations_struct *ops)
 {
 	int ret;
@@ -1496,7 +1496,7 @@ bool vma_is_special_mapping(const struct vm_area_struct *vma,
 struct vm_area_struct *_install_special_mapping(
 	struct mm_struct *mm,
 	unsigned long addr, unsigned long len,
-	unsigned long vm_flags, const struct vm_special_mapping *spec)
+	vm_flags_t vm_flags, const struct vm_special_mapping *spec)
 {
 	return __install_special_mapping(mm, addr, len, vm_flags, (void *)spec,
 					&special_mapping_vmops);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 88608d0dc2c2..b873b98ab705 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -596,10 +596,10 @@ static const struct mm_walk_ops prot_none_walk_ops = {
 int
 mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
 	       struct vm_area_struct *vma, struct vm_area_struct **pprev,
-	       unsigned long start, unsigned long end, unsigned long newflags)
+	       unsigned long start, unsigned long end, vm_flags_t newflags)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	unsigned long oldflags = READ_ONCE(vma->vm_flags);
+	vm_flags_t oldflags = READ_ONCE(vma->vm_flags);
 	long nrpages = (end - start) >> PAGE_SHIFT;
 	unsigned int mm_cp_flags = 0;
 	unsigned long charged = 0;
@@ -774,8 +774,8 @@ static int do_mprotect_pkey(unsigned long start, size_t len,
 	nstart = start;
 	tmp = vma->vm_start;
 	for_each_vma_range(vmi, vma, end) {
-		unsigned long mask_off_old_flags;
-		unsigned long newflags;
+		vm_flags_t mask_off_old_flags;
+		vm_flags_t newflags;
 		int new_vma_pkey;
 
 		if (vma->vm_start != tmp) {
diff --git a/mm/mremap.c b/mm/mremap.c
index 18b215521ada..7e93d3344828 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -1025,7 +1025,7 @@ static unsigned long prep_move_vma(struct vma_remap_struct *vrm)
 	struct vm_area_struct *vma = vrm->vma;
 	unsigned long old_addr = vrm->addr;
 	unsigned long old_len = vrm->old_len;
-	unsigned long dummy = vma->vm_flags;
+	vm_flags_t dummy = vma->vm_flags;
 
 	/*
 	 * We'd prefer to avoid failure later on in do_munmap:
diff --git a/mm/nommu.c b/mm/nommu.c
index b624acec6d2e..87e1acab0d64 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -126,7 +126,7 @@ void *vrealloc_noprof(const void *p, size_t size, gfp_t flags)
 
 void *__vmalloc_node_range_noprof(unsigned long size, unsigned long align,
 		unsigned long start, unsigned long end, gfp_t gfp_mask,
-		pgprot_t prot, unsigned long vm_flags, int node,
+		pgprot_t prot, vm_flags_t vm_flags, int node,
 		const void *caller)
 {
 	return __vmalloc_noprof(size, gfp_mask);
@@ -844,12 +844,12 @@ static int validate_mmap_request(struct file *file,
  * we've determined that we can make the mapping, now translate what we
  * now know into VMA flags
  */
-static unsigned long determine_vm_flags(struct file *file,
-					unsigned long prot,
-					unsigned long flags,
-					unsigned long capabilities)
+static vm_flags_t determine_vm_flags(struct file *file,
+		unsigned long prot,
+		unsigned long flags,
+		unsigned long capabilities)
 {
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 
 	vm_flags = calc_vm_prot_bits(prot, 0) | calc_vm_flag_bits(file, flags);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index fb63d9256f09..a312cae16bb5 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -839,7 +839,7 @@ out:
 struct folio_referenced_arg {
 	int mapcount;
 	int referenced;
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 	struct mem_cgroup *memcg;
 };
 
@@ -984,7 +984,7 @@ static bool invalid_folio_referenced_vma(struct vm_area_struct *vma, void *arg)
  * the function bailed out due to rmap lock contention.
  */
 int folio_referenced(struct folio *folio, int is_locked,
-		     struct mem_cgroup *memcg, unsigned long *vm_flags)
+		     struct mem_cgroup *memcg, vm_flags_t *vm_flags)
 {
 	bool we_locked = false;
 	struct folio_referenced_arg pra = {
diff --git a/mm/shmem.c b/mm/shmem.c
index eda35be2a8d9..334b7b4a61a0 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -615,7 +615,7 @@ static unsigned int shmem_get_orders_within_size(struct inode *inode,
 static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t index,
 					      loff_t write_end, bool shmem_huge_force,
 					      struct vm_area_struct *vma,
-					      unsigned long vm_flags)
+					      vm_flags_t vm_flags)
 {
 	unsigned int maybe_pmd_order = HPAGE_PMD_ORDER > MAX_PAGECACHE_ORDER ?
 		0 : BIT(HPAGE_PMD_ORDER);
@@ -862,7 +862,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo,
 static unsigned int shmem_huge_global_enabled(struct inode *inode, pgoff_t index,
 					      loff_t write_end, bool shmem_huge_force,
 					      struct vm_area_struct *vma,
-					      unsigned long vm_flags)
+					      vm_flags_t vm_flags)
 {
 	return 0;
 }
@@ -1753,7 +1753,7 @@ unsigned long shmem_allowable_huge_orders(struct inode *inode,
 {
 	unsigned long mask = READ_ONCE(huge_shmem_orders_always);
 	unsigned long within_size_orders = READ_ONCE(huge_shmem_orders_within_size);
-	unsigned long vm_flags = vma ? vma->vm_flags : 0;
+	vm_flags_t vm_flags = vma ? vma->vm_flags : 0;
 	unsigned int global_orders;
 
 	if (thp_disabled_by_hw() || (vma && vma_thp_disabled(vma, vm_flags)))
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index 9ff970980496..95dd8dea6ee4 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -1901,11 +1901,11 @@ out:
 }
 
 static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
-				     vm_flags_t flags)
+				     vm_flags_t vm_flags)
 {
-	const bool uffd_wp_changed = (vma->vm_flags ^ flags) & VM_UFFD_WP;
+	const bool uffd_wp_changed = (vma->vm_flags ^ vm_flags) & VM_UFFD_WP;
 
-	vm_flags_reset(vma, flags);
+	vm_flags_reset(vma, vm_flags);
 	/*
 	 * For shared mappings, we want to enable writenotify while
 	 * userfaultfd-wp is enabled (see vma_wants_writenotify()). We'll simply
@@ -1917,12 +1917,12 @@ static void userfaultfd_set_vm_flags(struct vm_area_struct *vma,
 
 static void userfaultfd_set_ctx(struct vm_area_struct *vma,
 				struct userfaultfd_ctx *ctx,
-				unsigned long flags)
+				vm_flags_t vm_flags)
 {
 	vma_start_write(vma);
 	vma->vm_userfaultfd_ctx = (struct vm_userfaultfd_ctx){ctx};
 	userfaultfd_set_vm_flags(vma,
-				 (vma->vm_flags & ~__VM_UFFD_FLAGS) | flags);
+				 (vma->vm_flags & ~__VM_UFFD_FLAGS) | vm_flags);
 }
 
 void userfaultfd_reset_ctx(struct vm_area_struct *vma)
@@ -1968,14 +1968,14 @@ struct vm_area_struct *userfaultfd_clear_vma(struct vma_iterator *vmi,
 /* Assumes mmap write lock taken, and mm_struct pinned. */
 int userfaultfd_register_range(struct userfaultfd_ctx *ctx,
 			       struct vm_area_struct *vma,
-			       unsigned long vm_flags,
+			       vm_flags_t vm_flags,
 			       unsigned long start, unsigned long end,
 			       bool wp_async)
 {
 	VMA_ITERATOR(vmi, ctx->mm, start);
 	struct vm_area_struct *prev = vma_prev(&vmi);
 	unsigned long vma_end;
-	unsigned long new_flags;
+	vm_flags_t new_flags;
 
 	if (vma->vm_start < start)
 		prev = vma;
diff --git a/mm/vma.c b/mm/vma.c
index 4b6d0be9ba39..b3d880652359 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -15,7 +15,7 @@ struct mmap_state {
 	unsigned long end;
 	pgoff_t pgoff;
 	unsigned long pglen;
-	unsigned long flags;
+	vm_flags_t vm_flags;
 	struct file *file;
 	pgprot_t page_prot;
 
@@ -37,7 +37,7 @@ struct mmap_state {
 	bool check_ksm_early;
 };
 
-#define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, flags_, file_) \
+#define MMAP_STATE(name, mm_, vmi_, addr_, len_, pgoff_, vm_flags_, file_) \
 	struct mmap_state name = {					\
 		.mm = mm_,						\
 		.vmi = vmi_,						\
@@ -45,9 +45,9 @@ struct mmap_state {
 		.end = (addr_) + (len_),				\
 		.pgoff = pgoff_,					\
 		.pglen = PHYS_PFN(len_),				\
-		.flags = flags_,					\
+		.vm_flags = vm_flags_,					\
 		.file = file_,						\
-		.page_prot = vm_get_page_prot(flags_),			\
+		.page_prot = vm_get_page_prot(vm_flags_),		\
 	}
 
 #define VMG_MMAP_STATE(name, map_, vma_)				\
@@ -56,7 +56,7 @@ struct mmap_state {
 		.vmi = (map_)->vmi,					\
 		.start = (map_)->addr,					\
 		.end = (map_)->end,					\
-		.flags = (map_)->flags,					\
+		.vm_flags = (map_)->vm_flags,				\
 		.pgoff = (map_)->pgoff,					\
 		.file = (map_)->file,					\
 		.prev = (map_)->prev,					\
@@ -95,7 +95,7 @@ static inline bool is_mergeable_vma(struct vma_merge_struct *vmg, bool merge_nex
 	 * the kernel to generate new VMAs when old one could be
 	 * extended instead.
 	 */
-	if ((vma->vm_flags ^ vmg->flags) & ~VM_SOFTDIRTY)
+	if ((vma->vm_flags ^ vmg->vm_flags) & ~VM_SOFTDIRTY)
 		return false;
 	if (vma->vm_file != vmg->file)
 		return false;
@@ -843,7 +843,7 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
 	 * furthermost left or right side of the VMA, then we have no chance of
 	 * merging and should abort.
 	 */
-	if (vmg->flags & VM_SPECIAL || (!left_side && !right_side))
+	if (vmg->vm_flags & VM_SPECIAL || (!left_side && !right_side))
 		return NULL;
 
 	if (left_side)
@@ -973,7 +973,7 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
 	if (err || commit_merge(vmg))
 		goto abort;
 
-	khugepaged_enter_vma(vmg->target, vmg->flags);
+	khugepaged_enter_vma(vmg->target, vmg->vm_flags);
 	vmg->state = VMA_MERGE_SUCCESS;
 	return vmg->target;
 
@@ -1055,7 +1055,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
 	vmg->state = VMA_MERGE_NOMERGE;
 
 	/* Special VMAs are unmergeable, also if no prev/next. */
-	if ((vmg->flags & VM_SPECIAL) || (!prev && !next))
+	if ((vmg->vm_flags & VM_SPECIAL) || (!prev && !next))
 		return NULL;
 
 	can_merge_left = can_vma_merge_left(vmg);
@@ -1093,7 +1093,7 @@ struct vm_area_struct *vma_merge_new_range(struct vma_merge_struct *vmg)
 	 * following VMA if we have VMAs on both sides.
 	 */
 	if (vmg->target && !vma_expand(vmg)) {
-		khugepaged_enter_vma(vmg->target, vmg->flags);
+		khugepaged_enter_vma(vmg->target, vmg->vm_flags);
 		vmg->state = VMA_MERGE_SUCCESS;
 		return vmg->target;
 	}
@@ -1640,11 +1640,11 @@ static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg)
 struct vm_area_struct *vma_modify_flags(
 	struct vma_iterator *vmi, struct vm_area_struct *prev,
 	struct vm_area_struct *vma, unsigned long start, unsigned long end,
-	unsigned long new_flags)
+	vm_flags_t vm_flags)
 {
 	VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
 
-	vmg.flags = new_flags;
+	vmg.vm_flags = vm_flags;
 
 	return vma_modify(&vmg);
 }
@@ -1655,12 +1655,12 @@ struct vm_area_struct
 		       struct vm_area_struct *vma,
 		       unsigned long start,
 		       unsigned long end,
-		       unsigned long new_flags,
+		       vm_flags_t vm_flags,
 		       struct anon_vma_name *new_name)
 {
 	VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
 
-	vmg.flags = new_flags;
+	vmg.vm_flags = vm_flags;
 	vmg.anon_name = new_name;
 
 	return vma_modify(&vmg);
@@ -1685,13 +1685,13 @@ struct vm_area_struct
 		       struct vm_area_struct *prev,
 		       struct vm_area_struct *vma,
 		       unsigned long start, unsigned long end,
-		       unsigned long new_flags,
+		       vm_flags_t vm_flags,
 		       struct vm_userfaultfd_ctx new_ctx,
 		       bool give_up_on_oom)
 {
 	VMG_VMA_STATE(vmg, vmi, prev, vma, start, end);
 
-	vmg.flags = new_flags;
+	vmg.vm_flags = vm_flags;
 	vmg.uffd_ctx = new_ctx;
 	if (give_up_on_oom)
 		vmg.give_up_on_oom = true;
@@ -2327,7 +2327,7 @@ static void vms_abort_munmap_vmas(struct vma_munmap_struct *vms,
 
 static void update_ksm_flags(struct mmap_state *map)
 {
-	map->flags = ksm_vma_flags(map->mm, map->file, map->flags);
+	map->vm_flags = ksm_vma_flags(map->mm, map->file, map->vm_flags);
 }
 
 /*
@@ -2372,11 +2372,11 @@ static int __mmap_prepare(struct mmap_state *map, struct list_head *uf)
 	}
 
 	/* Check against address space limit. */
-	if (!may_expand_vm(map->mm, map->flags, map->pglen - vms->nr_pages))
+	if (!may_expand_vm(map->mm, map->vm_flags, map->pglen - vms->nr_pages))
 		return -ENOMEM;
 
 	/* Private writable mapping: check memory availability. */
-	if (accountable_mapping(map->file, map->flags)) {
+	if (accountable_mapping(map->file, map->vm_flags)) {
 		map->charged = map->pglen;
 		map->charged -= vms->nr_accounted;
 		if (map->charged) {
@@ -2386,7 +2386,7 @@ static int __mmap_prepare(struct mmap_state *map, struct list_head *uf)
 		}
 
 		vms->nr_accounted = 0;
-		map->flags |= VM_ACCOUNT;
+		map->vm_flags |= VM_ACCOUNT;
 	}
 
 	/*
@@ -2430,12 +2430,12 @@ static int __mmap_new_file_vma(struct mmap_state *map,
 	 * Drivers should not permit writability when previously it was
 	 * disallowed.
 	 */
-	VM_WARN_ON_ONCE(map->flags != vma->vm_flags &&
-			!(map->flags & VM_MAYWRITE) &&
+	VM_WARN_ON_ONCE(map->vm_flags != vma->vm_flags &&
+			!(map->vm_flags & VM_MAYWRITE) &&
 			(vma->vm_flags & VM_MAYWRITE));
 
 	map->file = vma->vm_file;
-	map->flags = vma->vm_flags;
+	map->vm_flags = vma->vm_flags;
 
 	return 0;
 }
@@ -2466,7 +2466,7 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
 
 	vma_iter_config(vmi, map->addr, map->end);
 	vma_set_range(vma, map->addr, map->end, map->pgoff);
-	vm_flags_init(vma, map->flags);
+	vm_flags_init(vma, map->vm_flags);
 	vma->vm_page_prot = map->page_prot;
 
 	if (vma_iter_prealloc(vmi, vma)) {
@@ -2476,7 +2476,7 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
 
 	if (map->file)
 		error = __mmap_new_file_vma(map, vma);
-	else if (map->flags & VM_SHARED)
+	else if (map->vm_flags & VM_SHARED)
 		error = shmem_zero_setup(vma);
 	else
 		vma_set_anonymous(vma);
@@ -2486,12 +2486,12 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
 
 	if (!map->check_ksm_early) {
 		update_ksm_flags(map);
-		vm_flags_init(vma, map->flags);
+		vm_flags_init(vma, map->vm_flags);
 	}
 
 #ifdef CONFIG_SPARC64
 	/* TODO: Fix SPARC ADI! */
-	WARN_ON_ONCE(!arch_validate_flags(map->flags));
+	WARN_ON_ONCE(!arch_validate_flags(map->vm_flags));
 #endif
 
 	/* Lock the VMA since it is modified after insertion into VMA tree */
@@ -2505,7 +2505,7 @@ static int __mmap_new_vma(struct mmap_state *map, struct vm_area_struct **vmap)
 	 * call covers the non-merge case.
 	 */
 	if (!vma_is_anonymous(vma))
-		khugepaged_enter_vma(vma, map->flags);
+		khugepaged_enter_vma(vma, map->vm_flags);
 	*vmap = vma;
 	return 0;
 
@@ -2526,7 +2526,7 @@ free_vma:
 static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma)
 {
 	struct mm_struct *mm = map->mm;
-	unsigned long vm_flags = vma->vm_flags;
+	vm_flags_t vm_flags = vma->vm_flags;
 
 	perf_event_mmap(vma);
 
@@ -2579,7 +2579,7 @@ static int call_mmap_prepare(struct mmap_state *map)
 
 		.pgoff = map->pgoff,
 		.file = map->file,
-		.vm_flags = map->flags,
+		.vm_flags = map->vm_flags,
 		.page_prot = map->page_prot,
 	};
 
@@ -2591,7 +2591,7 @@ static int call_mmap_prepare(struct mmap_state *map)
 	/* Update fields permitted to be changed. */
 	map->pgoff = desc.pgoff;
 	map->file = desc.file;
-	map->flags = desc.vm_flags;
+	map->vm_flags = desc.vm_flags;
 	map->page_prot = desc.page_prot;
 	/* User-defined fields. */
 	map->vm_ops = desc.vm_ops;
@@ -2754,14 +2754,14 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
  * @addr: The start address
  * @len: The length of the increase
  * @vma: The vma,
- * @flags: The VMA Flags
+ * @vm_flags: The VMA Flags
  *
  * Extend the brk VMA from addr to addr + len.  If the VMA is NULL or the flags
  * do not match then create a new anonymous VMA.  Eventually we may be able to
  * do some brk-specific accounting here.
  */
 int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
-		 unsigned long addr, unsigned long len, unsigned long flags)
+		 unsigned long addr, unsigned long len, vm_flags_t vm_flags)
 {
 	struct mm_struct *mm = current->mm;
 
@@ -2769,9 +2769,9 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	 * Check against address space limits by the changed size
 	 * Note: This happens *after* clearing old mappings in some code paths.
 	 */
-	flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
-	flags = ksm_vma_flags(mm, NULL, flags);
-	if (!may_expand_vm(mm, flags, len >> PAGE_SHIFT))
+	vm_flags |= VM_DATA_DEFAULT_FLAGS | VM_ACCOUNT | mm->def_flags;
+	vm_flags = ksm_vma_flags(mm, NULL, vm_flags);
+	if (!may_expand_vm(mm, vm_flags, len >> PAGE_SHIFT))
 		return -ENOMEM;
 
 	if (mm->map_count > sysctl_max_map_count)
@@ -2785,7 +2785,7 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	 * occur after forking, so the expand will only happen on new VMAs.
 	 */
 	if (vma && vma->vm_end == addr) {
-		VMG_STATE(vmg, mm, vmi, addr, addr + len, flags, PHYS_PFN(addr));
+		VMG_STATE(vmg, mm, vmi, addr, addr + len, vm_flags, PHYS_PFN(addr));
 
 		vmg.prev = vma;
 		/* vmi is positioned at prev, which this mode expects. */
@@ -2806,8 +2806,8 @@ int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *vma,
 
 	vma_set_anonymous(vma);
 	vma_set_range(vma, addr, addr + len, addr >> PAGE_SHIFT);
-	vm_flags_init(vma, flags);
-	vma->vm_page_prot = vm_get_page_prot(flags);
+	vm_flags_init(vma, vm_flags);
+	vma->vm_page_prot = vm_get_page_prot(vm_flags);
 	vma_start_write(vma);
 	if (vma_iter_store_gfp(vmi, vma, GFP_KERNEL))
 		goto mas_store_fail;
@@ -2818,7 +2818,7 @@ out:
 	perf_event_mmap(vma);
 	mm->total_vm += len >> PAGE_SHIFT;
 	mm->data_vm += len >> PAGE_SHIFT;
-	if (flags & VM_LOCKED)
+	if (vm_flags & VM_LOCKED)
 		mm->locked_vm += (len >> PAGE_SHIFT);
 	vm_flags_set(vma, VM_SOFTDIRTY);
 	return 0;
diff --git a/mm/vma.h b/mm/vma.h
index f47112a352db..cf6e3a6371b6 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -98,7 +98,7 @@ struct vma_merge_struct {
 	unsigned long end;
 	pgoff_t pgoff;
 
-	unsigned long flags;
+	vm_flags_t vm_flags;
 	struct file *file;
 	struct anon_vma *anon_vma;
 	struct mempolicy *policy;
@@ -164,13 +164,13 @@ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma,
 	return vma->vm_pgoff + PHYS_PFN(addr - vma->vm_start);
 }
 
-#define VMG_STATE(name, mm_, vmi_, start_, end_, flags_, pgoff_)	\
+#define VMG_STATE(name, mm_, vmi_, start_, end_, vm_flags_, pgoff_)	\
 	struct vma_merge_struct name = {				\
 		.mm = mm_,						\
 		.vmi = vmi_,						\
 		.start = start_,					\
 		.end = end_,						\
-		.flags = flags_,					\
+		.vm_flags = vm_flags_,					\
 		.pgoff = pgoff_,					\
 		.state = VMA_MERGE_START,				\
 	}
@@ -184,7 +184,7 @@ static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma,
 		.next = NULL,					\
 		.start = start_,				\
 		.end = end_,					\
-		.flags = vma_->vm_flags,			\
+		.vm_flags = vma_->vm_flags,			\
 		.pgoff = vma_pgoff_offset(vma_, start_),	\
 		.file = vma_->vm_file,				\
 		.anon_vma = vma_->anon_vma,			\
@@ -288,7 +288,7 @@ __must_check struct vm_area_struct
 *vma_modify_flags(struct vma_iterator *vmi,
 		struct vm_area_struct *prev, struct vm_area_struct *vma,
 		unsigned long start, unsigned long end,
-		unsigned long new_flags);
+		vm_flags_t vm_flags);
 
 /* We are about to modify the VMA's flags and/or anon_name. */
 __must_check struct vm_area_struct
@@ -297,7 +297,7 @@ __must_check struct vm_area_struct
 		       struct vm_area_struct *vma,
 		       unsigned long start,
 		       unsigned long end,
-		       unsigned long new_flags,
+		       vm_flags_t vm_flags,
 		       struct anon_vma_name *new_name);
 
 /* We are about to modify the VMA's memory policy. */
@@ -314,7 +314,7 @@ __must_check struct vm_area_struct
 		       struct vm_area_struct *prev,
 		       struct vm_area_struct *vma,
 		       unsigned long start, unsigned long end,
-		       unsigned long new_flags,
+		       vm_flags_t vm_flags,
 		       struct vm_userfaultfd_ctx new_ctx,
 		       bool give_up_on_oom);
 
@@ -375,7 +375,7 @@ static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma
 }
 
 #ifdef CONFIG_MMU
-static inline pgprot_t vm_pgprot_modify(pgprot_t oldprot, unsigned long vm_flags)
+static inline pgprot_t vm_pgprot_modify(pgprot_t oldprot, vm_flags_t vm_flags)
 {
 	return pgprot_modify(oldprot, vm_get_page_prot(vm_flags));
 }
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 620dce753b64..56d540b8a1d0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -907,7 +907,7 @@ static enum folio_references folio_check_references(struct folio *folio,
 						  struct scan_control *sc)
 {
 	int referenced_ptes, referenced_folio;
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 
 	referenced_ptes = folio_referenced(folio, 1, sc->target_mem_cgroup,
 					   &vm_flags);
@@ -2120,7 +2120,7 @@ static void shrink_active_list(unsigned long nr_to_scan,
 {
 	unsigned long nr_taken;
 	unsigned long nr_scanned;
-	unsigned long vm_flags;
+	vm_flags_t vm_flags;
 	LIST_HEAD(l_hold);	/* The folios which were snipped off */
 	LIST_HEAD(l_active);
 	LIST_HEAD(l_inactive);
diff --git a/tools/testing/vma/vma.c b/tools/testing/vma/vma.c
index 7fec5b3de83f..656e1c75b711 100644
--- a/tools/testing/vma/vma.c
+++ b/tools/testing/vma/vma.c
@@ -65,7 +65,7 @@ static struct vm_area_struct *alloc_vma(struct mm_struct *mm,
 					unsigned long start,
 					unsigned long end,
 					pgoff_t pgoff,
-					vm_flags_t flags)
+					vm_flags_t vm_flags)
 {
 	struct vm_area_struct *ret = vm_area_alloc(mm);
 
@@ -75,7 +75,7 @@ static struct vm_area_struct *alloc_vma(struct mm_struct *mm,
 	ret->vm_start = start;
 	ret->vm_end = end;
 	ret->vm_pgoff = pgoff;
-	ret->__vm_flags = flags;
+	ret->__vm_flags = vm_flags;
 	vma_assert_detached(ret);
 
 	return ret;
@@ -103,9 +103,9 @@ static struct vm_area_struct *alloc_and_link_vma(struct mm_struct *mm,
 						 unsigned long start,
 						 unsigned long end,
 						 pgoff_t pgoff,
-						 vm_flags_t flags)
+						 vm_flags_t vm_flags)
 {
-	struct vm_area_struct *vma = alloc_vma(mm, start, end, pgoff, flags);
+	struct vm_area_struct *vma = alloc_vma(mm, start, end, pgoff, vm_flags);
 
 	if (vma == NULL)
 		return NULL;
@@ -172,7 +172,7 @@ static int expand_existing(struct vma_merge_struct *vmg)
  * specified new range.
  */
 static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start,
-			  unsigned long end, pgoff_t pgoff, vm_flags_t flags)
+			  unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags)
 {
 	vma_iter_set(vmg->vmi, start);
 
@@ -184,7 +184,7 @@ static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start,
 	vmg->start = start;
 	vmg->end = end;
 	vmg->pgoff = pgoff;
-	vmg->flags = flags;
+	vmg->vm_flags = vm_flags;
 
 	vmg->just_expand = false;
 	vmg->__remove_middle = false;
@@ -195,10 +195,10 @@ static void vmg_set_range(struct vma_merge_struct *vmg, unsigned long start,
 
 /* Helper function to set both the VMG range and its anon_vma. */
 static void vmg_set_range_anon_vma(struct vma_merge_struct *vmg, unsigned long start,
-				   unsigned long end, pgoff_t pgoff, vm_flags_t flags,
+				   unsigned long end, pgoff_t pgoff, vm_flags_t vm_flags,
 				   struct anon_vma *anon_vma)
 {
-	vmg_set_range(vmg, start, end, pgoff, flags);
+	vmg_set_range(vmg, start, end, pgoff, vm_flags);
 	vmg->anon_vma = anon_vma;
 }
 
@@ -211,12 +211,12 @@ static void vmg_set_range_anon_vma(struct vma_merge_struct *vmg, unsigned long s
 static struct vm_area_struct *try_merge_new_vma(struct mm_struct *mm,
 						struct vma_merge_struct *vmg,
 						unsigned long start, unsigned long end,
-						pgoff_t pgoff, vm_flags_t flags,
+						pgoff_t pgoff, vm_flags_t vm_flags,
 						bool *was_merged)
 {
 	struct vm_area_struct *merged;
 
-	vmg_set_range(vmg, start, end, pgoff, flags);
+	vmg_set_range(vmg, start, end, pgoff, vm_flags);
 
 	merged = merge_new(vmg);
 	if (merged) {
@@ -229,7 +229,7 @@ static struct vm_area_struct *try_merge_new_vma(struct mm_struct *mm,
 
 	ASSERT_EQ(vmg->state, VMA_MERGE_NOMERGE);
 
-	return alloc_and_link_vma(mm, start, end, pgoff, flags);
+	return alloc_and_link_vma(mm, start, end, pgoff, vm_flags);
 }
 
 /*
@@ -301,17 +301,17 @@ static void vma_set_dummy_anon_vma(struct vm_area_struct *vma,
 static bool test_simple_merge(void)
 {
 	struct vm_area_struct *vma;
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
-	struct vm_area_struct *vma_left = alloc_vma(&mm, 0, 0x1000, 0, flags);
-	struct vm_area_struct *vma_right = alloc_vma(&mm, 0x2000, 0x3000, 2, flags);
+	struct vm_area_struct *vma_left = alloc_vma(&mm, 0, 0x1000, 0, vm_flags);
+	struct vm_area_struct *vma_right = alloc_vma(&mm, 0x2000, 0x3000, 2, vm_flags);
 	VMA_ITERATOR(vmi, &mm, 0x1000);
 	struct vma_merge_struct vmg = {
 		.mm = &mm,
 		.vmi = &vmi,
 		.start = 0x1000,
 		.end = 0x2000,
-		.flags = flags,
+		.vm_flags = vm_flags,
 		.pgoff = 1,
 	};
 
@@ -324,7 +324,7 @@ static bool test_simple_merge(void)
 	ASSERT_EQ(vma->vm_start, 0);
 	ASSERT_EQ(vma->vm_end, 0x3000);
 	ASSERT_EQ(vma->vm_pgoff, 0);
-	ASSERT_EQ(vma->vm_flags, flags);
+	ASSERT_EQ(vma->vm_flags, vm_flags);
 
 	detach_free_vma(vma);
 	mtree_destroy(&mm.mm_mt);
@@ -335,9 +335,9 @@ static bool test_simple_merge(void)
 static bool test_simple_modify(void)
 {
 	struct vm_area_struct *vma;
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
-	struct vm_area_struct *init_vma = alloc_vma(&mm, 0, 0x3000, 0, flags);
+	struct vm_area_struct *init_vma = alloc_vma(&mm, 0, 0x3000, 0, vm_flags);
 	VMA_ITERATOR(vmi, &mm, 0x1000);
 
 	ASSERT_FALSE(attach_vma(&mm, init_vma));
@@ -394,9 +394,9 @@ static bool test_simple_modify(void)
 
 static bool test_simple_expand(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
-	struct vm_area_struct *vma = alloc_vma(&mm, 0, 0x1000, 0, flags);
+	struct vm_area_struct *vma = alloc_vma(&mm, 0, 0x1000, 0, vm_flags);
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vma_merge_struct vmg = {
 		.vmi = &vmi,
@@ -422,9 +422,9 @@ static bool test_simple_expand(void)
 
 static bool test_simple_shrink(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
-	struct vm_area_struct *vma = alloc_vma(&mm, 0, 0x3000, 0, flags);
+	struct vm_area_struct *vma = alloc_vma(&mm, 0, 0x3000, 0, vm_flags);
 	VMA_ITERATOR(vmi, &mm, 0);
 
 	ASSERT_FALSE(attach_vma(&mm, vma));
@@ -443,7 +443,7 @@ static bool test_simple_shrink(void)
 
 static bool test_merge_new(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vma_merge_struct vmg = {
@@ -473,18 +473,18 @@ static bool test_merge_new(void)
 	 * 0123456789abc
 	 * AA B       CC
 	 */
-	vma_a = alloc_and_link_vma(&mm, 0, 0x2000, 0, flags);
+	vma_a = alloc_and_link_vma(&mm, 0, 0x2000, 0, vm_flags);
 	ASSERT_NE(vma_a, NULL);
 	/* We give each VMA a single avc so we can test anon_vma duplication. */
 	INIT_LIST_HEAD(&vma_a->anon_vma_chain);
 	list_add(&dummy_anon_vma_chain_a.same_vma, &vma_a->anon_vma_chain);
 
-	vma_b = alloc_and_link_vma(&mm, 0x3000, 0x4000, 3, flags);
+	vma_b = alloc_and_link_vma(&mm, 0x3000, 0x4000, 3, vm_flags);
 	ASSERT_NE(vma_b, NULL);
 	INIT_LIST_HEAD(&vma_b->anon_vma_chain);
 	list_add(&dummy_anon_vma_chain_b.same_vma, &vma_b->anon_vma_chain);
 
-	vma_c = alloc_and_link_vma(&mm, 0xb000, 0xc000, 0xb, flags);
+	vma_c = alloc_and_link_vma(&mm, 0xb000, 0xc000, 0xb, vm_flags);
 	ASSERT_NE(vma_c, NULL);
 	INIT_LIST_HEAD(&vma_c->anon_vma_chain);
 	list_add(&dummy_anon_vma_chain_c.same_vma, &vma_c->anon_vma_chain);
@@ -495,7 +495,7 @@ static bool test_merge_new(void)
 	 * 0123456789abc
 	 * AA B   **  CC
 	 */
-	vma_d = try_merge_new_vma(&mm, &vmg, 0x7000, 0x9000, 7, flags, &merged);
+	vma_d = try_merge_new_vma(&mm, &vmg, 0x7000, 0x9000, 7, vm_flags, &merged);
 	ASSERT_NE(vma_d, NULL);
 	INIT_LIST_HEAD(&vma_d->anon_vma_chain);
 	list_add(&dummy_anon_vma_chain_d.same_vma, &vma_d->anon_vma_chain);
@@ -510,7 +510,7 @@ static bool test_merge_new(void)
 	 */
 	vma_a->vm_ops = &vm_ops; /* This should have no impact. */
 	vma_b->anon_vma = &dummy_anon_vma;
-	vma = try_merge_new_vma(&mm, &vmg, 0x2000, 0x3000, 2, flags, &merged);
+	vma = try_merge_new_vma(&mm, &vmg, 0x2000, 0x3000, 2, vm_flags, &merged);
 	ASSERT_EQ(vma, vma_a);
 	/* Merge with A, delete B. */
 	ASSERT_TRUE(merged);
@@ -527,7 +527,7 @@ static bool test_merge_new(void)
 	 * 0123456789abc
 	 * AAAA*  DD  CC
 	 */
-	vma = try_merge_new_vma(&mm, &vmg, 0x4000, 0x5000, 4, flags, &merged);
+	vma = try_merge_new_vma(&mm, &vmg, 0x4000, 0x5000, 4, vm_flags, &merged);
 	ASSERT_EQ(vma, vma_a);
 	/* Extend A. */
 	ASSERT_TRUE(merged);
@@ -546,7 +546,7 @@ static bool test_merge_new(void)
 	 */
 	vma_d->anon_vma = &dummy_anon_vma;
 	vma_d->vm_ops = &vm_ops; /* This should have no impact. */
-	vma = try_merge_new_vma(&mm, &vmg, 0x6000, 0x7000, 6, flags, &merged);
+	vma = try_merge_new_vma(&mm, &vmg, 0x6000, 0x7000, 6, vm_flags, &merged);
 	ASSERT_EQ(vma, vma_d);
 	/* Prepend. */
 	ASSERT_TRUE(merged);
@@ -564,7 +564,7 @@ static bool test_merge_new(void)
 	 * AAAAA*DDD  CC
 	 */
 	vma_d->vm_ops = NULL; /* This would otherwise degrade the merge. */
-	vma = try_merge_new_vma(&mm, &vmg, 0x5000, 0x6000, 5, flags, &merged);
+	vma = try_merge_new_vma(&mm, &vmg, 0x5000, 0x6000, 5, vm_flags, &merged);
 	ASSERT_EQ(vma, vma_a);
 	/* Merge with A, delete D. */
 	ASSERT_TRUE(merged);
@@ -582,7 +582,7 @@ static bool test_merge_new(void)
 	 * AAAAAAAAA *CC
 	 */
 	vma_c->anon_vma = &dummy_anon_vma;
-	vma = try_merge_new_vma(&mm, &vmg, 0xa000, 0xb000, 0xa, flags, &merged);
+	vma = try_merge_new_vma(&mm, &vmg, 0xa000, 0xb000, 0xa, vm_flags, &merged);
 	ASSERT_EQ(vma, vma_c);
 	/* Prepend C. */
 	ASSERT_TRUE(merged);
@@ -599,7 +599,7 @@ static bool test_merge_new(void)
 	 * 0123456789abc
 	 * AAAAAAAAA*CCC
 	 */
-	vma = try_merge_new_vma(&mm, &vmg, 0x9000, 0xa000, 0x9, flags, &merged);
+	vma = try_merge_new_vma(&mm, &vmg, 0x9000, 0xa000, 0x9, vm_flags, &merged);
 	ASSERT_EQ(vma, vma_a);
 	/* Extend A and delete C. */
 	ASSERT_TRUE(merged);
@@ -639,7 +639,7 @@ static bool test_merge_new(void)
 
 static bool test_vma_merge_special_flags(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vma_merge_struct vmg = {
@@ -661,7 +661,7 @@ static bool test_vma_merge_special_flags(void)
 	 * 01234
 	 * AAA
 	 */
-	vma_left = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
+	vma_left = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
 	ASSERT_NE(vma_left, NULL);
 
 	/* 1. Set up new VMA with special flag that would otherwise merge. */
@@ -672,12 +672,12 @@ static bool test_vma_merge_special_flags(void)
 	 *
 	 * This should merge if not for the VM_SPECIAL flag.
 	 */
-	vmg_set_range(&vmg, 0x3000, 0x4000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x4000, 3, vm_flags);
 	for (i = 0; i < ARRAY_SIZE(special_flags); i++) {
 		vm_flags_t special_flag = special_flags[i];
 
-		vma_left->__vm_flags = flags | special_flag;
-		vmg.flags = flags | special_flag;
+		vma_left->__vm_flags = vm_flags | special_flag;
+		vmg.vm_flags = vm_flags | special_flag;
 		vma = merge_new(&vmg);
 		ASSERT_EQ(vma, NULL);
 		ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
@@ -691,15 +691,15 @@ static bool test_vma_merge_special_flags(void)
 	 *
 	 * Create a VMA to modify.
 	 */
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x4000, 3, flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x4000, 3, vm_flags);
 	ASSERT_NE(vma, NULL);
 	vmg.middle = vma;
 
 	for (i = 0; i < ARRAY_SIZE(special_flags); i++) {
 		vm_flags_t special_flag = special_flags[i];
 
-		vma_left->__vm_flags = flags | special_flag;
-		vmg.flags = flags | special_flag;
+		vma_left->__vm_flags = vm_flags | special_flag;
+		vmg.vm_flags = vm_flags | special_flag;
 		vma = merge_existing(&vmg);
 		ASSERT_EQ(vma, NULL);
 		ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
@@ -711,7 +711,7 @@ static bool test_vma_merge_special_flags(void)
 
 static bool test_vma_merge_with_close(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vma_merge_struct vmg = {
@@ -791,11 +791,11 @@ static bool test_vma_merge_with_close(void)
 	 * PPPPPPNNN
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x9000, 5, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x9000, 5, vm_flags);
 	vma_next->vm_ops = &vm_ops;
 
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	ASSERT_EQ(merge_new(&vmg), vma_prev);
 	ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
 	ASSERT_EQ(vma_prev->vm_start, 0);
@@ -816,11 +816,11 @@ static bool test_vma_merge_with_close(void)
 	 * proceed.
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
 	vma->vm_ops = &vm_ops;
 
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 
@@ -844,11 +844,11 @@ static bool test_vma_merge_with_close(void)
 	 * proceed.
 	 */
 
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x9000, 5, flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x9000, 5, vm_flags);
 	vma->vm_ops = &vm_ops;
 
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	vmg.middle = vma;
 	ASSERT_EQ(merge_existing(&vmg), NULL);
 	/*
@@ -872,12 +872,12 @@ static bool test_vma_merge_with_close(void)
 	 * PPPVVNNNN
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x9000, 5, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x9000, 5, vm_flags);
 	vma->vm_ops = &vm_ops;
 
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 
@@ -898,12 +898,12 @@ static bool test_vma_merge_with_close(void)
 	 * PPPPPNNNN
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x9000, 5, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x9000, 5, vm_flags);
 	vma_next->vm_ops = &vm_ops;
 
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 
@@ -920,15 +920,15 @@ static bool test_vma_merge_with_close(void)
 
 static bool test_vma_merge_new_with_close(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vma_merge_struct vmg = {
 		.mm = &mm,
 		.vmi = &vmi,
 	};
-	struct vm_area_struct *vma_prev = alloc_and_link_vma(&mm, 0, 0x2000, 0, flags);
-	struct vm_area_struct *vma_next = alloc_and_link_vma(&mm, 0x5000, 0x7000, 5, flags);
+	struct vm_area_struct *vma_prev = alloc_and_link_vma(&mm, 0, 0x2000, 0, vm_flags);
+	struct vm_area_struct *vma_next = alloc_and_link_vma(&mm, 0x5000, 0x7000, 5, vm_flags);
 	const struct vm_operations_struct vm_ops = {
 		.close = dummy_close,
 	};
@@ -958,7 +958,7 @@ static bool test_vma_merge_new_with_close(void)
 	vma_prev->vm_ops = &vm_ops;
 	vma_next->vm_ops = &vm_ops;
 
-	vmg_set_range(&vmg, 0x2000, 0x5000, 2, flags);
+	vmg_set_range(&vmg, 0x2000, 0x5000, 2, vm_flags);
 	vma = merge_new(&vmg);
 	ASSERT_NE(vma, NULL);
 	ASSERT_EQ(vmg.state, VMA_MERGE_SUCCESS);
@@ -975,7 +975,7 @@ static bool test_vma_merge_new_with_close(void)
 
 static bool test_merge_existing(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vm_area_struct *vma, *vma_prev, *vma_next;
@@ -998,11 +998,11 @@ static bool test_merge_existing(void)
 	 * 0123456789
 	 *   VNNNNNN
 	 */
-	vma = alloc_and_link_vma(&mm, 0x2000, 0x6000, 2, flags);
+	vma = alloc_and_link_vma(&mm, 0x2000, 0x6000, 2, vm_flags);
 	vma->vm_ops = &vm_ops; /* This should have no impact. */
-	vma_next = alloc_and_link_vma(&mm, 0x6000, 0x9000, 6, flags);
+	vma_next = alloc_and_link_vma(&mm, 0x6000, 0x9000, 6, vm_flags);
 	vma_next->vm_ops = &vm_ops; /* This should have no impact. */
-	vmg_set_range_anon_vma(&vmg, 0x3000, 0x6000, 3, flags, &dummy_anon_vma);
+	vmg_set_range_anon_vma(&vmg, 0x3000, 0x6000, 3, vm_flags, &dummy_anon_vma);
 	vmg.middle = vma;
 	vmg.prev = vma;
 	vma_set_dummy_anon_vma(vma, &avc);
@@ -1032,10 +1032,10 @@ static bool test_merge_existing(void)
 	 * 0123456789
 	 *   NNNNNNN
 	 */
-	vma = alloc_and_link_vma(&mm, 0x2000, 0x6000, 2, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x6000, 0x9000, 6, flags);
+	vma = alloc_and_link_vma(&mm, 0x2000, 0x6000, 2, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x6000, 0x9000, 6, vm_flags);
 	vma_next->vm_ops = &vm_ops; /* This should have no impact. */
-	vmg_set_range_anon_vma(&vmg, 0x2000, 0x6000, 2, flags, &dummy_anon_vma);
+	vmg_set_range_anon_vma(&vmg, 0x2000, 0x6000, 2, vm_flags, &dummy_anon_vma);
 	vmg.middle = vma;
 	vma_set_dummy_anon_vma(vma, &avc);
 	ASSERT_EQ(merge_existing(&vmg), vma_next);
@@ -1060,11 +1060,11 @@ static bool test_merge_existing(void)
 	 * 0123456789
 	 * PPPPPPV
 	 */
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
 	vma_prev->vm_ops = &vm_ops; /* This should have no impact. */
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, vm_flags);
 	vma->vm_ops = &vm_ops; /* This should have no impact. */
-	vmg_set_range_anon_vma(&vmg, 0x3000, 0x6000, 3, flags, &dummy_anon_vma);
+	vmg_set_range_anon_vma(&vmg, 0x3000, 0x6000, 3, vm_flags, &dummy_anon_vma);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 	vma_set_dummy_anon_vma(vma, &avc);
@@ -1094,10 +1094,10 @@ static bool test_merge_existing(void)
 	 * 0123456789
 	 * PPPPPPP
 	 */
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
 	vma_prev->vm_ops = &vm_ops; /* This should have no impact. */
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, flags);
-	vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, flags, &dummy_anon_vma);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, vm_flags);
+	vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, vm_flags, &dummy_anon_vma);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 	vma_set_dummy_anon_vma(vma, &avc);
@@ -1123,11 +1123,11 @@ static bool test_merge_existing(void)
 	 * 0123456789
 	 * PPPPPPPPPP
 	 */
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
 	vma_prev->vm_ops = &vm_ops; /* This should have no impact. */
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, flags);
-	vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, flags, &dummy_anon_vma);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, vm_flags);
+	vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, vm_flags, &dummy_anon_vma);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 	vma_set_dummy_anon_vma(vma, &avc);
@@ -1158,41 +1158,41 @@ static bool test_merge_existing(void)
 	 * PPPVVVVVNNN
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x8000, 3, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x8000, 0xa000, 8, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x8000, 3, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x8000, 0xa000, 8, vm_flags);
 
-	vmg_set_range(&vmg, 0x4000, 0x5000, 4, flags);
+	vmg_set_range(&vmg, 0x4000, 0x5000, 4, vm_flags);
 	vmg.prev = vma;
 	vmg.middle = vma;
 	ASSERT_EQ(merge_existing(&vmg), NULL);
 	ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
 
-	vmg_set_range(&vmg, 0x5000, 0x6000, 5, flags);
+	vmg_set_range(&vmg, 0x5000, 0x6000, 5, vm_flags);
 	vmg.prev = vma;
 	vmg.middle = vma;
 	ASSERT_EQ(merge_existing(&vmg), NULL);
 	ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
 
-	vmg_set_range(&vmg, 0x6000, 0x7000, 6, flags);
+	vmg_set_range(&vmg, 0x6000, 0x7000, 6, vm_flags);
 	vmg.prev = vma;
 	vmg.middle = vma;
 	ASSERT_EQ(merge_existing(&vmg), NULL);
 	ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
 
-	vmg_set_range(&vmg, 0x4000, 0x7000, 4, flags);
+	vmg_set_range(&vmg, 0x4000, 0x7000, 4, vm_flags);
 	vmg.prev = vma;
 	vmg.middle = vma;
 	ASSERT_EQ(merge_existing(&vmg), NULL);
 	ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
 
-	vmg_set_range(&vmg, 0x4000, 0x6000, 4, flags);
+	vmg_set_range(&vmg, 0x4000, 0x6000, 4, vm_flags);
 	vmg.prev = vma;
 	vmg.middle = vma;
 	ASSERT_EQ(merge_existing(&vmg), NULL);
 	ASSERT_EQ(vmg.state, VMA_MERGE_NOMERGE);
 
-	vmg_set_range(&vmg, 0x5000, 0x6000, 5, flags);
+	vmg_set_range(&vmg, 0x5000, 0x6000, 5, vm_flags);
 	vmg.prev = vma;
 	vmg.middle = vma;
 	ASSERT_EQ(merge_existing(&vmg), NULL);
@@ -1205,7 +1205,7 @@ static bool test_merge_existing(void)
 
 static bool test_anon_vma_non_mergeable(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vm_area_struct *vma, *vma_prev, *vma_next;
@@ -1229,9 +1229,9 @@ static bool test_anon_vma_non_mergeable(void)
 	 * 0123456789
 	 * PPPPPPPNNN
 	 */
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x7000, 3, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, vm_flags);
 
 	/*
 	 * Give both prev and next single anon_vma_chain fields, so they will
@@ -1239,7 +1239,7 @@ static bool test_anon_vma_non_mergeable(void)
 	 *
 	 * However, when prev is compared to next, the merge should fail.
 	 */
-	vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, flags, NULL);
+	vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, vm_flags, NULL);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 	vma_set_dummy_anon_vma(vma_prev, &dummy_anon_vma_chain_1);
@@ -1267,10 +1267,10 @@ static bool test_anon_vma_non_mergeable(void)
 	 * 0123456789
 	 * PPPPPPPNNN
 	 */
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x7000, 0x9000, 7, vm_flags);
 
-	vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, flags, NULL);
+	vmg_set_range_anon_vma(&vmg, 0x3000, 0x7000, 3, vm_flags, NULL);
 	vmg.prev = vma_prev;
 	vma_set_dummy_anon_vma(vma_prev, &dummy_anon_vma_chain_1);
 	__vma_set_dummy_anon_vma(vma_next, &dummy_anon_vma_chain_2, &dummy_anon_vma_2);
@@ -1292,7 +1292,7 @@ static bool test_anon_vma_non_mergeable(void)
 
 static bool test_dup_anon_vma(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vma_merge_struct vmg = {
@@ -1313,11 +1313,11 @@ static bool test_dup_anon_vma(void)
 	 * This covers new VMA merging, as these operations amount to a VMA
 	 * expand.
 	 */
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
 	vma_next->anon_vma = &dummy_anon_vma;
 
-	vmg_set_range(&vmg, 0, 0x5000, 0, flags);
+	vmg_set_range(&vmg, 0, 0x5000, 0, vm_flags);
 	vmg.target = vma_prev;
 	vmg.next = vma_next;
 
@@ -1339,16 +1339,16 @@ static bool test_dup_anon_vma(void)
 	 *  extend   delete  delete
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x8000, 5, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x8000, 5, vm_flags);
 
 	/* Initialise avc so mergeability check passes. */
 	INIT_LIST_HEAD(&vma_next->anon_vma_chain);
 	list_add(&dummy_anon_vma_chain.same_vma, &vma_next->anon_vma_chain);
 
 	vma_next->anon_vma = &dummy_anon_vma;
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 
@@ -1372,12 +1372,12 @@ static bool test_dup_anon_vma(void)
 	 *  extend   delete  delete
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x8000, 5, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x8000, 5, vm_flags);
 	vmg.anon_vma = &dummy_anon_vma;
 	vma_set_dummy_anon_vma(vma, &dummy_anon_vma_chain);
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 
@@ -1401,11 +1401,11 @@ static bool test_dup_anon_vma(void)
 	 *  extend shrink/delete
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x8000, 3, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x8000, 3, vm_flags);
 
 	vma_set_dummy_anon_vma(vma, &dummy_anon_vma_chain);
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 
@@ -1429,11 +1429,11 @@ static bool test_dup_anon_vma(void)
 	 * shrink/delete extend
 	 */
 
-	vma = alloc_and_link_vma(&mm, 0, 0x5000, 0, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x8000, 5, flags);
+	vma = alloc_and_link_vma(&mm, 0, 0x5000, 0, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x5000, 0x8000, 5, vm_flags);
 
 	vma_set_dummy_anon_vma(vma, &dummy_anon_vma_chain);
-	vmg_set_range(&vmg, 0x3000, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0x3000, 0x5000, 3, vm_flags);
 	vmg.prev = vma;
 	vmg.middle = vma;
 
@@ -1452,7 +1452,7 @@ static bool test_dup_anon_vma(void)
 
 static bool test_vmi_prealloc_fail(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vma_merge_struct vmg = {
@@ -1468,11 +1468,11 @@ static bool test_vmi_prealloc_fail(void)
 	 * the duplicated anon_vma is unlinked.
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
 	vma->anon_vma = &dummy_anon_vma;
 
-	vmg_set_range_anon_vma(&vmg, 0x3000, 0x5000, 3, flags, &dummy_anon_vma);
+	vmg_set_range_anon_vma(&vmg, 0x3000, 0x5000, 3, vm_flags, &dummy_anon_vma);
 	vmg.prev = vma_prev;
 	vmg.middle = vma;
 	vma_set_dummy_anon_vma(vma, &avc);
@@ -1496,11 +1496,11 @@ static bool test_vmi_prealloc_fail(void)
 	 * performed in this case too.
 	 */
 
-	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, flags);
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0, 0x3000, 0, vm_flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
 	vma->anon_vma = &dummy_anon_vma;
 
-	vmg_set_range(&vmg, 0, 0x5000, 3, flags);
+	vmg_set_range(&vmg, 0, 0x5000, 3, vm_flags);
 	vmg.target = vma_prev;
 	vmg.next = vma;
 
@@ -1518,13 +1518,13 @@ static bool test_vmi_prealloc_fail(void)
 
 static bool test_merge_extend(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0x1000);
 	struct vm_area_struct *vma;
 
-	vma = alloc_and_link_vma(&mm, 0, 0x1000, 0, flags);
-	alloc_and_link_vma(&mm, 0x3000, 0x4000, 3, flags);
+	vma = alloc_and_link_vma(&mm, 0, 0x1000, 0, vm_flags);
+	alloc_and_link_vma(&mm, 0x3000, 0x4000, 3, vm_flags);
 
 	/*
 	 * Extend a VMA into the gap between itself and the following VMA.
@@ -1548,7 +1548,7 @@ static bool test_merge_extend(void)
 
 static bool test_copy_vma(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	bool need_locks = false;
 	VMA_ITERATOR(vmi, &mm, 0);
@@ -1556,7 +1556,7 @@ static bool test_copy_vma(void)
 
 	/* Move backwards and do not merge. */
 
-	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
+	vma = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
 	vma_new = copy_vma(&vma, 0, 0x2000, 0, &need_locks);
 	ASSERT_NE(vma_new, vma);
 	ASSERT_EQ(vma_new->vm_start, 0);
@@ -1568,8 +1568,8 @@ static bool test_copy_vma(void)
 
 	/* Move a VMA into position next to another and merge the two. */
 
-	vma = alloc_and_link_vma(&mm, 0, 0x2000, 0, flags);
-	vma_next = alloc_and_link_vma(&mm, 0x6000, 0x8000, 6, flags);
+	vma = alloc_and_link_vma(&mm, 0, 0x2000, 0, vm_flags);
+	vma_next = alloc_and_link_vma(&mm, 0x6000, 0x8000, 6, vm_flags);
 	vma_new = copy_vma(&vma, 0x4000, 0x2000, 4, &need_locks);
 	vma_assert_attached(vma_new);
 
@@ -1581,11 +1581,11 @@ static bool test_copy_vma(void)
 
 static bool test_expand_only_mode(void)
 {
-	unsigned long flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
+	vm_flags_t vm_flags = VM_READ | VM_WRITE | VM_MAYREAD | VM_MAYWRITE;
 	struct mm_struct mm = {};
 	VMA_ITERATOR(vmi, &mm, 0);
 	struct vm_area_struct *vma_prev, *vma;
-	VMG_STATE(vmg, &mm, &vmi, 0x5000, 0x9000, flags, 5);
+	VMG_STATE(vmg, &mm, &vmi, 0x5000, 0x9000, vm_flags, 5);
 
 	/*
 	 * Place a VMA prior to the one we're expanding so we assert that we do
@@ -1593,14 +1593,14 @@ static bool test_expand_only_mode(void)
 	 * have, through the use of the just_expand flag, indicated we do not
 	 * need to do so.
 	 */
-	alloc_and_link_vma(&mm, 0, 0x2000, 0, flags);
+	alloc_and_link_vma(&mm, 0, 0x2000, 0, vm_flags);
 
 	/*
 	 * We will be positioned at the prev VMA, but looking to expand to
 	 * 0x9000.
 	 */
 	vma_iter_set(&vmi, 0x3000);
-	vma_prev = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, flags);
+	vma_prev = alloc_and_link_vma(&mm, 0x3000, 0x5000, 3, vm_flags);
 	vmg.prev = vma_prev;
 	vmg.just_expand = true;
 
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 3b1b45256d56..f684649b1008 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -1084,7 +1084,7 @@ static inline bool mpol_equal(struct mempolicy *, struct mempolicy *)
 }
 
 static inline void khugepaged_enter_vma(struct vm_area_struct *vma,
-			  unsigned long vm_flags)
+			  vm_flags_t vm_flags)
 {
 	(void)vma;
 	(void)vm_flags;
@@ -1200,7 +1200,7 @@ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot);
 /* Update vma->vm_page_prot to reflect vma->vm_flags. */
 static inline void vma_set_page_prot(struct vm_area_struct *vma)
 {
-	unsigned long vm_flags = vma->vm_flags;
+	vm_flags_t vm_flags = vma->vm_flags;
 	pgprot_t vm_page_prot;
 
 	/* testing: we inline vm_pgprot_modify() to avoid clash with vma.h. */
@@ -1280,12 +1280,12 @@ static inline bool capable(int cap)
 	return true;
 }
 
-static inline bool mlock_future_ok(struct mm_struct *mm, unsigned long flags,
+static inline bool mlock_future_ok(struct mm_struct *mm, vm_flags_t vm_flags,
 			unsigned long bytes)
 {
 	unsigned long locked_pages, limit_pages;
 
-	if (!(flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
+	if (!(vm_flags & VM_LOCKED) || capable(CAP_IPC_LOCK))
 		return true;
 
 	locked_pages = bytes >> PAGE_SHIFT;
-- 
cgit v1.2.3


From f9550e1fcf3bef802c18fadc5c65485b66b28a63 Mon Sep 17 00:00:00 2001
From: Nathan Gao <zcgao@amazon.com>
Date: Wed, 18 Jun 2025 09:33:31 -0700
Subject: mm/damon: fix minor typos in damon header

Fix typos in include/linux/damon.h.

Link: https://lkml.kernel.org/r/20250618163331.54910-1-sj@kernel.org
Signed-off-by: Nathan Gao <zcgao@amazon.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index a4011726cb3b..bb58e36f019e 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -450,7 +450,7 @@ struct damos_access_pattern {
 /**
  * struct damos - Represents a Data Access Monitoring-based Operation Scheme.
  * @pattern:		Access pattern of target regions.
- * @action:		&damo_action to be applied to the target regions.
+ * @action:		&damos_action to be applied to the target regions.
  * @apply_interval_us:	The time between applying the @action.
  * @quota:		Control the aggressiveness of this scheme.
  * @wmarks:		Watermarks for automated (in)activation of this scheme.
@@ -656,7 +656,7 @@ struct damon_call_control {
  * struct damon_intervals_goal - Monitoring intervals auto-tuning goal.
  *
  * @access_bp:		Access events observation ratio to achieve in bp.
- * @aggrs:		Number of aggregations to acheive @access_bp within.
+ * @aggrs:		Number of aggregations to achieve @access_bp within.
  * @min_sample_us:	Minimum resulting sampling interval in microseconds.
  * @max_sample_us:	Maximum resulting sampling interval in microseconds.
  *
-- 
cgit v1.2.3


From 986f5f2b4be3b7eab9ecd85c472d03a2191d6fc0 Mon Sep 17 00:00:00 2001
From: Vivek Kasireddy <vivek.kasireddy@intel.com>
Date: Tue, 17 Jun 2025 22:30:53 -0700
Subject: mm/hugetlb: make hugetlb_reserve_pages() return nr of entries updated

Patch series "mm/memfd: Reserve hugetlb folios before allocation", v4.

There are cases when we try to pin a folio but discover that it has not
been faulted-in.  So, we try to allocate it in memfd_alloc_folio() but the
allocation request may not succeed if there are no active reservations in
the system at that instant.

Therefore, making a reservation (by calling hugetlb_reserve_pages())
associated with the allocation will ensure that our request would not fail
due to lack of reservations.  This will also ensure that proper
region/subpool accounting is done with our allocation.


This patch (of 3):

Currently, hugetlb_reserve_pages() returns a bool to indicate whether the
reservation map update for the range [from, to] was successful or not.
This is not sufficient for the case where the caller needs to determine
how many entries were updated for the range.

Therefore, have hugetlb_reserve_pages() return the number of entries
updated in the reservation map associated with the range [from, to].
Also, update the callers of hugetlb_reserve_pages() to handle the new
return value.

Link: https://lkml.kernel.org/r/20250618053415.1036185-1-vivek.kasireddy@intel.com
Link: https://lkml.kernel.org/r/20250618053415.1036185-2-vivek.kasireddy@intel.com
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
Cc: Steve Sistare <steven.sistare@oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/hugetlbfs/inode.c    |  8 ++++----
 include/linux/hugetlb.h |  2 +-
 mm/hugetlb.c            | 19 +++++++++++++------
 3 files changed, 18 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index e4de5425838d..00b2d1a032fd 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -150,10 +150,10 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	if (inode->i_flags & S_PRIVATE)
 		vm_flags |= VM_NORESERVE;
 
-	if (!hugetlb_reserve_pages(inode,
+	if (hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
-				vm_flags))
+				vm_flags) < 0)
 		goto out;
 
 	ret = 0;
@@ -1561,9 +1561,9 @@ struct file *hugetlb_file_setup(const char *name, size_t size,
 	inode->i_size = size;
 	clear_nlink(inode);
 
-	if (!hugetlb_reserve_pages(inode, 0,
+	if (hugetlb_reserve_pages(inode, 0,
 			size >> huge_page_shift(hstate_inode(inode)), NULL,
-			acctflag))
+			acctflag) < 0)
 		file = ERR_PTR(-ENOMEM);
 	else
 		file = alloc_file_pseudo(inode, mnt, name, O_RDWR,
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 42f374e828a2..d8310b0f36dd 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -149,7 +149,7 @@ int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 			     uffd_flags_t flags,
 			     struct folio **foliop);
 #endif /* CONFIG_USERFAULTFD */
-bool hugetlb_reserve_pages(struct inode *inode, long from, long to,
+long hugetlb_reserve_pages(struct inode *inode, long from, long to,
 						struct vm_area_struct *vma,
 						vm_flags_t vm_flags);
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c7ba95030241..e1570735012a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7244,8 +7244,15 @@ long hugetlb_change_protection(struct vm_area_struct *vma,
 	return pages > 0 ? (pages << h->order) : pages;
 }
 
-/* Return true if reservation was successful, false otherwise.  */
-bool hugetlb_reserve_pages(struct inode *inode,
+/*
+ * Update the reservation map for the range [from, to].
+ *
+ * Returns the number of entries that would be added to the reservation map
+ * associated with the range [from, to].  This number is greater or equal to
+ * zero. -EINVAL or -ENOMEM is returned in case of any errors.
+ */
+
+long hugetlb_reserve_pages(struct inode *inode,
 					long from, long to,
 					struct vm_area_struct *vma,
 					vm_flags_t vm_flags)
@@ -7260,7 +7267,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
 	/* This should never happen */
 	if (from > to) {
 		VM_WARN(1, "%s called with a negative range\n", __func__);
-		return false;
+		return -EINVAL;
 	}
 
 	/*
@@ -7275,7 +7282,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
 	 * without using reserves
 	 */
 	if (vm_flags & VM_NORESERVE)
-		return true;
+		return 0;
 
 	/*
 	 * Shared mappings base their reservation on the number of pages that
@@ -7382,7 +7389,7 @@ bool hugetlb_reserve_pages(struct inode *inode,
 			hugetlb_cgroup_put_rsvd_cgroup(h_cg);
 		}
 	}
-	return true;
+	return chg;
 
 out_put_pages:
 	spool_resv = chg - gbl_reserve;
@@ -7410,7 +7417,7 @@ out_err:
 		kref_put(&resv_map->refs, resv_map_release);
 		set_vma_resv_map(vma, NULL);
 	}
-	return false;
+	return chg < 0 ? chg : add < 0 ? add : -EINVAL;
 }
 
 long hugetlb_unreserve_pages(struct inode *inode, long start, long end,
-- 
cgit v1.2.3


From 717cf9357325055ab6b41c4e0581f4d67601eb58 Mon Sep 17 00:00:00 2001
From: Vivek Kasireddy <vivek.kasireddy@intel.com>
Date: Tue, 17 Jun 2025 22:30:54 -0700
Subject: mm/memfd: reserve hugetlb folios before allocation

When we try to allocate a folio via alloc_hugetlb_folio_reserve(), we need
to ensure that there is an active reservation associated with the
allocation.  Otherwise, our allocation request would fail if there are no
active reservations made at that moment against any other allocations.
This is because alloc_hugetlb_folio_reserve() checks h->resv_huge_pages
before proceeding with the allocation.

Therefore, to address this issue, we just need to make a reservation (by
calling hugetlb_reserve_pages()) before we try to allocate the folio.
This will also ensure that proper region/subpool accounting is done
associated with our allocation.

Link: https://lkml.kernel.org/r/20250618053415.1036185-3-vivek.kasireddy@intel.com
Signed-off-by: Vivek Kasireddy <vivek.kasireddy@intel.com>
Cc: Steve Sistare <steven.sistare@oracle.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: David Hildenbrand <david@redhat.com>
Cc: Gerd Hoffmann <kraxel@redhat.com>
Cc: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hugetlb.h |  5 +++++
 mm/hugetlb.c            |  5 -----
 mm/memfd.c              | 17 ++++++++++++++---
 3 files changed, 19 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d8310b0f36dd..c6c87eae4a8d 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -740,6 +740,11 @@ extern unsigned int default_hstate_idx;
 
 #define default_hstate (hstates[default_hstate_idx])
 
+static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
+{
+	return HUGETLBFS_SB(inode->i_sb)->spool;
+}
+
 static inline struct hugepage_subpool *hugetlb_folio_subpool(struct folio *folio)
 {
 	return folio->_hugetlb_subpool;
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index e1570735012a..da9f10710c27 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -284,11 +284,6 @@ static long hugepage_subpool_put_pages(struct hugepage_subpool *spool,
 	return ret;
 }
 
-static inline struct hugepage_subpool *subpool_inode(struct inode *inode)
-{
-	return HUGETLBFS_SB(inode->i_sb)->spool;
-}
-
 static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma)
 {
 	return subpool_inode(file_inode(vma->vm_file));
diff --git a/mm/memfd.c b/mm/memfd.c
index b558c4c3bd27..32fa6bfe57d1 100644
--- a/mm/memfd.c
+++ b/mm/memfd.c
@@ -70,7 +70,6 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 #ifdef CONFIG_HUGETLB_PAGE
 	struct folio *folio;
 	gfp_t gfp_mask;
-	int err;
 
 	if (is_file_hugepages(memfd)) {
 		/*
@@ -79,12 +78,19 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 		 * alloc from. Also, the folio will be pinned for an indefinite
 		 * amount of time, so it is not expected to be migrated away.
 		 */
+		struct inode *inode = file_inode(memfd);
 		struct hstate *h = hstate_file(memfd);
+		int err = -ENOMEM;
+		long nr_resv;
 
 		gfp_mask = htlb_alloc_mask(h);
 		gfp_mask &= ~(__GFP_HIGHMEM | __GFP_MOVABLE);
 		idx >>= huge_page_order(h);
 
+		nr_resv = hugetlb_reserve_pages(inode, idx, idx + 1, NULL, 0);
+		if (nr_resv < 0)
+			return ERR_PTR(nr_resv);
+
 		folio = alloc_hugetlb_folio_reserve(h,
 						    numa_node_id(),
 						    NULL,
@@ -95,12 +101,17 @@ struct folio *memfd_alloc_folio(struct file *memfd, pgoff_t idx)
 							idx);
 			if (err) {
 				folio_put(folio);
-				return ERR_PTR(err);
+				goto err_unresv;
 			}
+
+			hugetlb_set_folio_subpool(folio, subpool_inode(inode));
 			folio_unlock(folio);
 			return folio;
 		}
-		return ERR_PTR(-ENOMEM);
+err_unresv:
+		if (nr_resv > 0)
+			hugetlb_unreserve_pages(inode, idx, idx + 1, 0);
+		return ERR_PTR(err);
 	}
 #endif
 	return shmem_read_folio(memfd->f_mapping, idx);
-- 
cgit v1.2.3


From 59b5ed409d03bc8b7bb153d78afcd7cea9d7bbfa Mon Sep 17 00:00:00 2001
From: Hao Ge <gehao@kylinos.cn>
Date: Wed, 18 Jun 2025 09:58:09 +0800
Subject: mm/percpu: conditionally define _shared_alloc_tag via
 CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU

Recently discovered this entry while checking kallsyms on ARM64:
ffff800083e509c0 D _shared_alloc_tag

If ARCH_NEEDS_WEAK_PER_CPU is not defined(it is only defined for s390 and
alpha architectures), there's no need to statically define the percpu
variable _shared_alloc_tag.

Therefore, we need to implement isolation for this purpose.

When building the core kernel code for s390 or alpha architectures,
ARCH_NEEDS_WEAK_PER_CPU remains undefined (as it is gated by #if
defined(MODULE)).  However, when building modules for these architectures,
the macro is explicitly defined.

Therefore, we remove all instances of ARCH_NEEDS_WEAK_PER_CPU from the
code and introduced CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU to replace the
relevant logic.  We can now conditionally define the perpcu variable
_shared_alloc_tag based on CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU.  This
allows architectures (such as s390/alpha) that require weak definitions
for percpu variables in modules to include the definition, while others
can omit it via compile-time exclusion.

Link: https://lkml.kernel.org/r/20250618015809.1235761-1-hao.ge@linux.dev
Signed-off-by: Hao Ge <gehao@kylinos.cn>
Suggested-by: Suren Baghdasaryan <surenb@google.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com>	[s390]
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Cc: Chistoph Lameter <cl@linux.com>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dennis Zhou <dennis@kernel.org>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Richard Henderson <richard.henderson@linaro.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/alpha/Kconfig              | 1 +
 arch/alpha/include/asm/percpu.h | 5 ++---
 arch/s390/Kconfig               | 1 +
 arch/s390/include/asm/percpu.h  | 5 ++---
 include/linux/alloc_tag.h       | 6 +++---
 include/linux/percpu-defs.h     | 7 ++++---
 lib/alloc_tag.c                 | 2 ++
 mm/Kconfig                      | 7 +++++++
 8 files changed, 22 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 109a4cddcd13..80367f2cf821 100644
--- a/arch/alpha/Kconfig
+++ b/arch/alpha/Kconfig
@@ -7,6 +7,7 @@ config ALPHA
 	select ARCH_HAS_DMA_OPS if PCI
 	select ARCH_MIGHT_HAVE_PC_PARPORT
 	select ARCH_MIGHT_HAVE_PC_SERIO
+	select ARCH_MODULE_NEEDS_WEAK_PER_CPU if SMP
 	select ARCH_NO_PREEMPT
 	select ARCH_NO_SG_CHAIN
 	select ARCH_USE_CMPXCHG_LOCKREF
diff --git a/arch/alpha/include/asm/percpu.h b/arch/alpha/include/asm/percpu.h
index 6923249f2d49..4383d66341dc 100644
--- a/arch/alpha/include/asm/percpu.h
+++ b/arch/alpha/include/asm/percpu.h
@@ -9,10 +9,9 @@
  * way above 4G.
  *
  * Always use weak definitions for percpu variables in modules.
+ * Therefore, we have enabled CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU
+ * in the Kconfig.
  */
-#if defined(MODULE) && defined(CONFIG_SMP)
-#define ARCH_NEEDS_WEAK_PER_CPU
-#endif
 
 #include <asm-generic/percpu.h>
 
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 0c16dc443e2f..b652cb952f31 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -132,6 +132,7 @@ config S390
 	select ARCH_INLINE_WRITE_UNLOCK_IRQ
 	select ARCH_INLINE_WRITE_UNLOCK_IRQRESTORE
 	select ARCH_MHP_MEMMAP_ON_MEMORY_ENABLE
+	select ARCH_MODULE_NEEDS_WEAK_PER_CPU
 	select ARCH_STACKWALK
 	select ARCH_SUPPORTS_ATOMIC_RMW
 	select ARCH_SUPPORTS_DEBUG_PAGEALLOC
diff --git a/arch/s390/include/asm/percpu.h b/arch/s390/include/asm/percpu.h
index 84f6b8357b45..96af7d964014 100644
--- a/arch/s390/include/asm/percpu.h
+++ b/arch/s390/include/asm/percpu.h
@@ -16,10 +16,9 @@
  * For 64 bit module code, the module may be more than 4G above the
  * per cpu area, use weak definitions to force the compiler to
  * generate external references.
+ * Therefore, we have enabled CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU
+ * in the Kconfig.
  */
-#if defined(MODULE)
-#define ARCH_NEEDS_WEAK_PER_CPU
-#endif
 
 /*
  * We use a compare-and-swap loop since that uses less cpu cycles than
diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
index 8f7931eb7d16..9ef2633e2c08 100644
--- a/include/linux/alloc_tag.h
+++ b/include/linux/alloc_tag.h
@@ -88,7 +88,7 @@ static inline struct alloc_tag *ct_to_alloc_tag(struct codetag *ct)
 	return container_of(ct, struct alloc_tag, ct);
 }
 
-#ifdef ARCH_NEEDS_WEAK_PER_CPU
+#if defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) && defined(MODULE)
 /*
  * When percpu variables are required to be defined as weak, static percpu
  * variables can't be used inside a function (see comments for DECLARE_PER_CPU_SECTION).
@@ -102,7 +102,7 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
 		.ct = CODE_TAG_INIT,						\
 		.counters = &_shared_alloc_tag };
 
-#else /* ARCH_NEEDS_WEAK_PER_CPU */
+#else /* CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU && MODULE */
 
 #ifdef MODULE
 
@@ -123,7 +123,7 @@ DECLARE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
 
 #endif /* MODULE */
 
-#endif /* ARCH_NEEDS_WEAK_PER_CPU */
+#endif /* CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU && MODULE */
 
 DECLARE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
 			mem_alloc_profiling_key);
diff --git a/include/linux/percpu-defs.h b/include/linux/percpu-defs.h
index c16cdeaa505e..12d90360f6db 100644
--- a/include/linux/percpu-defs.h
+++ b/include/linux/percpu-defs.h
@@ -63,14 +63,15 @@
  * 1. The symbol must be globally unique, even the static ones.
  * 2. Static percpu variables cannot be defined inside a function.
  *
- * Archs which need weak percpu definitions should define
- * ARCH_NEEDS_WEAK_PER_CPU in asm/percpu.h when necessary.
+ * Archs which need weak percpu definitions should set
+ * CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU when necessary.
  *
  * To ensure that the generic code observes the above two
  * restrictions, if CONFIG_DEBUG_FORCE_WEAK_PER_CPU is set weak
  * definition is used for all cases.
  */
-#if defined(ARCH_NEEDS_WEAK_PER_CPU) || defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU)
+#if (defined(CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU) && defined(MODULE)) || \
+	defined(CONFIG_DEBUG_FORCE_WEAK_PER_CPU)
 /*
  * __pcpu_scope_* dummy variable is used to enforce scope.  It
  * receives the static modifier when it's used in front of
diff --git a/lib/alloc_tag.c b/lib/alloc_tag.c
index 36f07dc95069..41ccfb035b7b 100644
--- a/lib/alloc_tag.c
+++ b/lib/alloc_tag.c
@@ -25,8 +25,10 @@ static bool mem_profiling_support;
 
 static struct codetag_type *alloc_tag_cttype;
 
+#ifdef CONFIG_ARCH_MODULE_NEEDS_WEAK_PER_CPU
 DEFINE_PER_CPU(struct alloc_tag_counters, _shared_alloc_tag);
 EXPORT_SYMBOL(_shared_alloc_tag);
+#endif
 
 DEFINE_STATIC_KEY_MAYBE(CONFIG_MEM_ALLOC_PROFILING_ENABLED_BY_DEFAULT,
 			mem_alloc_profiling_key);
diff --git a/mm/Kconfig b/mm/Kconfig
index 3b2060a61c05..065b1f19dd99 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -933,6 +933,13 @@ config ARCH_SUPPORTS_PUD_PFNMAP
 	def_bool y
 	depends on ARCH_SUPPORTS_HUGE_PFNMAP && HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 
+#
+# Architectures that always use weak definitions for percpu
+# variables in modules should set this.
+#
+config ARCH_MODULE_NEEDS_WEAK_PER_CPU
+       bool
+
 #
 # UP and nommu archs use km based percpu allocator
 #
-- 
cgit v1.2.3


From fd2825b0760a10a9626986cca64f5664302ffdfc Mon Sep 17 00:00:00 2001
From: Alistair Popple <apopple@nvidia.com>
Date: Thu, 19 Jun 2025 18:57:57 +1000
Subject: mm/gup: remove pXX_devmap usage from get_user_pages()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

GUP uses pXX_devmap() calls to see if it needs to a get a reference on the
associated pgmap data structure to ensure the pages won't go away.
However it's a driver responsibility to ensure that if pages are mapped
(ie.  discoverable by GUP) that they are not offlined or removed from the
memmap so there is no need to hold a reference on the pgmap data structure
to ensure this.

Furthermore mappings with PFN_DEV are no longer created, hence this
effectively dead code anyway so can be removed.

Link: https://lkml.kernel.org/r/708b2be76876659ec5261fe5d059b07268b98b36.1750323463.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Björn Töpel <bjorn@kernel.org>
Cc: Björn Töpel <bjorn@rivosinc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chunyan Zhang <zhang.lyra@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Inki Dae <m.szyprowski@samsung.com>
Cc: John Groves <john@groves.net>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/huge_mm.h |   3 -
 mm/gup.c                | 160 ++----------------------------------------------
 mm/huge_memory.c        |  40 ------------
 3 files changed, 5 insertions(+), 198 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 7753daac49f7..a2df2308cb2c 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -473,9 +473,6 @@ static inline bool folio_test_pmd_mappable(struct folio *folio)
 	return folio_order(folio) >= HPAGE_PMD_ORDER;
 }
 
-struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, int flags, struct dev_pagemap **pgmap);
-
 vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf);
 
 extern struct folio *huge_zero_folio;
diff --git a/mm/gup.c b/mm/gup.c
index c08b97e0d344..30d320719fa2 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -679,31 +679,9 @@ static struct page *follow_huge_pud(struct vm_area_struct *vma,
 		return NULL;
 
 	pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
-
-	if (IS_ENABLED(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD) &&
-	    pud_devmap(pud)) {
-		/*
-		 * device mapped pages can only be returned if the caller
-		 * will manage the page reference count.
-		 *
-		 * At least one of FOLL_GET | FOLL_PIN must be set, so
-		 * assert that here:
-		 */
-		if (!(flags & (FOLL_GET | FOLL_PIN)))
-			return ERR_PTR(-EEXIST);
-
-		if (flags & FOLL_TOUCH)
-			touch_pud(vma, addr, pudp, flags & FOLL_WRITE);
-
-		ctx->pgmap = get_dev_pagemap(pfn, ctx->pgmap);
-		if (!ctx->pgmap)
-			return ERR_PTR(-EFAULT);
-	}
-
 	page = pfn_to_page(pfn);
 
-	if (!pud_devmap(pud) && !pud_write(pud) &&
-	    gup_must_unshare(vma, flags, page))
+	if (!pud_write(pud) && gup_must_unshare(vma, flags, page))
 		return ERR_PTR(-EMLINK);
 
 	ret = try_grab_folio(page_folio(page), 1, flags);
@@ -857,8 +835,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 	page = vm_normal_page(vma, address, pte);
 
 	/*
-	 * We only care about anon pages in can_follow_write_pte() and don't
-	 * have to worry about pte_devmap() because they are never anon.
+	 * We only care about anon pages in can_follow_write_pte().
 	 */
 	if ((flags & FOLL_WRITE) &&
 	    !can_follow_write_pte(pte, page, vma, flags)) {
@@ -866,18 +843,7 @@ static struct page *follow_page_pte(struct vm_area_struct *vma,
 		goto out;
 	}
 
-	if (!page && pte_devmap(pte) && (flags & (FOLL_GET | FOLL_PIN))) {
-		/*
-		 * Only return device mapping pages in the FOLL_GET or FOLL_PIN
-		 * case since they are only valid while holding the pgmap
-		 * reference.
-		 */
-		*pgmap = get_dev_pagemap(pte_pfn(pte), *pgmap);
-		if (*pgmap)
-			page = pte_page(pte);
-		else
-			goto no_page;
-	} else if (unlikely(!page)) {
+	if (unlikely(!page)) {
 		if (flags & FOLL_DUMP) {
 			/* Avoid special (like zero) pages in core dumps */
 			page = ERR_PTR(-EFAULT);
@@ -959,14 +925,6 @@ static struct page *follow_pmd_mask(struct vm_area_struct *vma,
 		return no_page_table(vma, flags, address);
 	if (!pmd_present(pmdval))
 		return no_page_table(vma, flags, address);
-	if (pmd_devmap(pmdval)) {
-		ptl = pmd_lock(mm, pmd);
-		page = follow_devmap_pmd(vma, address, pmd, flags, &ctx->pgmap);
-		spin_unlock(ptl);
-		if (page)
-			return page;
-		return no_page_table(vma, flags, address);
-	}
 	if (likely(!pmd_leaf(pmdval)))
 		return follow_page_pte(vma, address, pmd, flags, &ctx->pgmap);
 
@@ -2896,7 +2854,7 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		int *nr)
 {
 	struct dev_pagemap *pgmap = NULL;
-	int nr_start = *nr, ret = 0;
+	int ret = 0;
 	pte_t *ptep, *ptem;
 
 	ptem = ptep = pte_offset_map(&pmd, addr);
@@ -2920,16 +2878,7 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 		if (!pte_access_permitted(pte, flags & FOLL_WRITE))
 			goto pte_unmap;
 
-		if (pte_devmap(pte)) {
-			if (unlikely(flags & FOLL_LONGTERM))
-				goto pte_unmap;
-
-			pgmap = get_dev_pagemap(pte_pfn(pte), pgmap);
-			if (unlikely(!pgmap)) {
-				gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-				goto pte_unmap;
-			}
-		} else if (pte_special(pte))
+		if (pte_special(pte))
 			goto pte_unmap;
 
 		/* If it's not marked as special it must have a valid memmap. */
@@ -3001,91 +2950,6 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
 }
 #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
 
-#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static int gup_fast_devmap_leaf(unsigned long pfn, unsigned long addr,
-	unsigned long end, unsigned int flags, struct page **pages, int *nr)
-{
-	int nr_start = *nr;
-	struct dev_pagemap *pgmap = NULL;
-
-	do {
-		struct folio *folio;
-		struct page *page = pfn_to_page(pfn);
-
-		pgmap = get_dev_pagemap(pfn, pgmap);
-		if (unlikely(!pgmap)) {
-			gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-			break;
-		}
-
-		folio = try_grab_folio_fast(page, 1, flags);
-		if (!folio) {
-			gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-			break;
-		}
-		folio_set_referenced(folio);
-		pages[*nr] = page;
-		(*nr)++;
-		pfn++;
-	} while (addr += PAGE_SIZE, addr != end);
-
-	put_dev_pagemap(pgmap);
-	return addr == end;
-}
-
-static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
-{
-	unsigned long fault_pfn;
-	int nr_start = *nr;
-
-	fault_pfn = pmd_pfn(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr))
-		return 0;
-
-	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-		return 0;
-	}
-	return 1;
-}
-
-static int gup_fast_devmap_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
-{
-	unsigned long fault_pfn;
-	int nr_start = *nr;
-
-	fault_pfn = pud_pfn(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	if (!gup_fast_devmap_leaf(fault_pfn, addr, end, flags, pages, nr))
-		return 0;
-
-	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		gup_fast_undo_dev_pagemap(nr, nr_start, flags, pages);
-		return 0;
-	}
-	return 1;
-}
-#else
-static int gup_fast_devmap_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
-{
-	BUILD_BUG();
-	return 0;
-}
-
-static int gup_fast_devmap_pud_leaf(pud_t pud, pud_t *pudp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
-{
-	BUILD_BUG();
-	return 0;
-}
-#endif
-
 static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		unsigned long end, unsigned int flags, struct page **pages,
 		int *nr)
@@ -3100,13 +2964,6 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 	if (pmd_special(orig))
 		return 0;
 
-	if (pmd_devmap(orig)) {
-		if (unlikely(flags & FOLL_LONGTERM))
-			return 0;
-		return gup_fast_devmap_pmd_leaf(orig, pmdp, addr, end, flags,
-					        pages, nr);
-	}
-
 	page = pmd_page(orig);
 	refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
 
@@ -3147,13 +3004,6 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
 	if (pud_special(orig))
 		return 0;
 
-	if (pud_devmap(orig)) {
-		if (unlikely(flags & FOLL_LONGTERM))
-			return 0;
-		return gup_fast_devmap_pud_leaf(orig, pudp, addr, end, flags,
-					        pages, nr);
-	}
-
 	page = pud_page(orig);
 	refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
 
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 6411f3107af1..7434d177b97c 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1672,46 +1672,6 @@ void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
 		update_mmu_cache_pmd(vma, addr, pmd);
 }
 
-struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
-{
-	unsigned long pfn = pmd_pfn(*pmd);
-	struct mm_struct *mm = vma->vm_mm;
-	struct page *page;
-	int ret;
-
-	assert_spin_locked(pmd_lockptr(mm, pmd));
-
-	if (flags & FOLL_WRITE && !pmd_write(*pmd))
-		return NULL;
-
-	if (pmd_present(*pmd) && pmd_devmap(*pmd))
-		/* pass */;
-	else
-		return NULL;
-
-	if (flags & FOLL_TOUCH)
-		touch_pmd(vma, addr, pmd, flags & FOLL_WRITE);
-
-	/*
-	 * device mapped pages can only be returned if the
-	 * caller will manage the page reference count.
-	 */
-	if (!(flags & (FOLL_GET | FOLL_PIN)))
-		return ERR_PTR(-EEXIST);
-
-	pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
-	*pgmap = get_dev_pagemap(pfn, *pgmap);
-	if (!*pgmap)
-		return ERR_PTR(-EFAULT);
-	page = pfn_to_page(pfn);
-	ret = try_grab_folio(page_folio(page), 1, flags);
-	if (ret)
-		page = ERR_PTR(ret);
-
-	return page;
-}
-
 int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		  pmd_t *dst_pmd, pmd_t *src_pmd, unsigned long addr,
 		  struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
-- 
cgit v1.2.3


From 8a6a984c2e0ea406459b445a3910a454bece3aa1 Mon Sep 17 00:00:00 2001
From: Alistair Popple <apopple@nvidia.com>
Date: Thu, 19 Jun 2025 18:57:59 +1000
Subject: mm: remove redundant pXd_devmap calls
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

DAX was the only thing that created pmd_devmap and pud_devmap entries
however it no longer does as DAX pages are now refcounted normally and
pXd_trans_huge() returns true for those.  Therefore checking both
pXd_devmap and pXd_trans_huge() is redundant and the former can be removed
without changing behaviour as it will always be false.

Link: https://lkml.kernel.org/r/d58f089dc16b7feb7c6728164f37dea65d64a0d3.1750323463.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Björn Töpel <bjorn@kernel.org>
Cc: Björn Töpel <bjorn@rivosinc.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Chunyan Zhang <zhang.lyra@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Inki Dae <m.szyprowski@samsung.com>
Cc: Jason Gunthorpe <jgg@nvidia.com>
Cc: John Groves <john@groves.net>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/dax.c                   |  5 ++---
 include/linux/huge_mm.h    | 10 ++++------
 include/linux/pgtable.h    |  2 +-
 mm/hmm.c                   |  4 ++--
 mm/huge_memory.c           | 23 +++++++++--------------
 mm/mapping_dirty_helpers.c |  4 ++--
 mm/memory.c                | 15 ++++++---------
 mm/migrate_device.c        |  2 +-
 mm/mprotect.c              |  2 +-
 mm/mremap.c                |  5 ++---
 mm/page_vma_mapped.c       |  5 ++---
 mm/pagewalk.c              |  8 +++-----
 mm/pgtable-generic.c       |  7 +++----
 mm/userfaultfd.c           |  4 ++--
 mm/vmscan.c                |  3 ---
 15 files changed, 40 insertions(+), 59 deletions(-)

(limited to 'include/linux')

diff --git a/fs/dax.c b/fs/dax.c
index ea0c35794bf9..7d4ecb9d23af 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -1937,7 +1937,7 @@ static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * the PTE we need to set up.  If so just return and the fault will be
 	 * retried.
 	 */
-	if (pmd_trans_huge(*vmf->pmd) || pmd_devmap(*vmf->pmd)) {
+	if (pmd_trans_huge(*vmf->pmd)) {
 		ret = VM_FAULT_NOPAGE;
 		goto unlock_entry;
 	}
@@ -2060,8 +2060,7 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
 	 * the PMD we need to set up.  If so just return and the fault will be
 	 * retried.
 	 */
-	if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) &&
-			!pmd_devmap(*vmf->pmd)) {
+	if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd)) {
 		ret = 0;
 		goto unlock_entry;
 	}
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index a2df2308cb2c..26607f2c65fb 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -400,8 +400,7 @@ void __split_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd,
 #define split_huge_pmd(__vma, __pmd, __address)				\
 	do {								\
 		pmd_t *____pmd = (__pmd);				\
-		if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd)	\
-					|| pmd_devmap(*____pmd))	\
+		if (is_swap_pmd(*____pmd) || pmd_trans_huge(*____pmd))	\
 			__split_huge_pmd(__vma, __pmd, __address,	\
 					 false);			\
 	}  while (0)
@@ -426,8 +425,7 @@ change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 #define split_huge_pud(__vma, __pud, __address)				\
 	do {								\
 		pud_t *____pud = (__pud);				\
-		if (pud_trans_huge(*____pud)				\
-					|| pud_devmap(*____pud))	\
+		if (pud_trans_huge(*____pud))				\
 			__split_huge_pud(__vma, __pud, __address);	\
 	}  while (0)
 
@@ -450,7 +448,7 @@ static inline int is_swap_pmd(pmd_t pmd)
 static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 		struct vm_area_struct *vma)
 {
-	if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd))
+	if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd))
 		return __pmd_trans_huge_lock(pmd, vma);
 	else
 		return NULL;
@@ -458,7 +456,7 @@ static inline spinlock_t *pmd_trans_huge_lock(pmd_t *pmd,
 static inline spinlock_t *pud_trans_huge_lock(pud_t *pud,
 		struct vm_area_struct *vma)
 {
-	if (pud_trans_huge(*pud) || pud_devmap(*pud))
+	if (pud_trans_huge(*pud))
 		return __pud_trans_huge_lock(pud, vma);
 	else
 		return NULL;
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index d05e35a0facf..ffcd966cf2d4 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1672,7 +1672,7 @@ static inline int pud_trans_unstable(pud_t *pud)
 	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 	pud_t pudval = READ_ONCE(*pud);
 
-	if (pud_none(pudval) || pud_trans_huge(pudval) || pud_devmap(pudval))
+	if (pud_none(pudval) || pud_trans_huge(pudval))
 		return 1;
 	if (unlikely(pud_bad(pudval))) {
 		pud_clear_bad(pud);
diff --git a/mm/hmm.c b/mm/hmm.c
index 14914da98416..62d3082dc55c 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -360,7 +360,7 @@ again:
 		return hmm_pfns_fill(start, end, range, HMM_PFN_ERROR);
 	}
 
-	if (pmd_devmap(pmd) || pmd_trans_huge(pmd)) {
+	if (pmd_trans_huge(pmd)) {
 		/*
 		 * No need to take pmd_lock here, even if some other thread
 		 * is splitting the huge pmd we will get that event through
@@ -371,7 +371,7 @@ again:
 		 * values.
 		 */
 		pmd = pmdp_get_lockless(pmdp);
-		if (!pmd_devmap(pmd) && !pmd_trans_huge(pmd))
+		if (!pmd_trans_huge(pmd))
 			goto again;
 
 		return hmm_vma_handle_pmd(walk, addr, end, hmm_pfns, pmd);
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 54b5c37d9515..cf808b2eea29 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1459,8 +1459,7 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
 	 * but we need to be consistent with PTEs and architectures that
 	 * can't support a 'special' bit.
 	 */
-	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
-			!pfn_t_devmap(pfn));
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
 	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
 						(VM_PFNMAP|VM_MIXEDMAP));
 	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
@@ -1596,8 +1595,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
 	 * but we need to be consistent with PTEs and architectures that
 	 * can't support a 'special' bit.
 	 */
-	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) &&
-			!pfn_t_devmap(pfn));
+	BUG_ON(!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)));
 	BUG_ON((vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) ==
 						(VM_PFNMAP|VM_MIXEDMAP));
 	BUG_ON((vma->vm_flags & VM_PFNMAP) && is_cow_mapping(vma->vm_flags));
@@ -1815,7 +1813,7 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 	ret = -EAGAIN;
 	pud = *src_pud;
-	if (unlikely(!pud_trans_huge(pud) && !pud_devmap(pud)))
+	if (unlikely(!pud_trans_huge(pud)))
 		goto out_unlock;
 
 	/*
@@ -2677,8 +2675,7 @@ spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma)
 {
 	spinlock_t *ptl;
 	ptl = pmd_lock(vma->vm_mm, pmd);
-	if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) ||
-			pmd_devmap(*pmd)))
+	if (likely(is_swap_pmd(*pmd) || pmd_trans_huge(*pmd)))
 		return ptl;
 	spin_unlock(ptl);
 	return NULL;
@@ -2695,7 +2692,7 @@ spinlock_t *__pud_trans_huge_lock(pud_t *pud, struct vm_area_struct *vma)
 	spinlock_t *ptl;
 
 	ptl = pud_lock(vma->vm_mm, pud);
-	if (likely(pud_trans_huge(*pud) || pud_devmap(*pud)))
+	if (likely(pud_trans_huge(*pud)))
 		return ptl;
 	spin_unlock(ptl);
 	return NULL;
@@ -2747,7 +2744,7 @@ static void __split_huge_pud_locked(struct vm_area_struct *vma, pud_t *pud,
 	VM_BUG_ON(haddr & ~HPAGE_PUD_MASK);
 	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
 	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PUD_SIZE, vma);
-	VM_BUG_ON(!pud_trans_huge(*pud) && !pud_devmap(*pud));
+	VM_BUG_ON(!pud_trans_huge(*pud));
 
 	count_vm_event(THP_SPLIT_PUD);
 
@@ -2780,7 +2777,7 @@ void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
 				(address & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE);
 	mmu_notifier_invalidate_range_start(&range);
 	ptl = pud_lock(vma->vm_mm, pud);
-	if (unlikely(!pud_trans_huge(*pud) && !pud_devmap(*pud)))
+	if (unlikely(!pud_trans_huge(*pud)))
 		goto out;
 	__split_huge_pud_locked(vma, pud, range.start);
 
@@ -2853,8 +2850,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd,
 	VM_BUG_ON(haddr & ~HPAGE_PMD_MASK);
 	VM_BUG_ON_VMA(vma->vm_start > haddr, vma);
 	VM_BUG_ON_VMA(vma->vm_end < haddr + HPAGE_PMD_SIZE, vma);
-	VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd)
-				&& !pmd_devmap(*pmd));
+	VM_BUG_ON(!is_pmd_migration_entry(*pmd) && !pmd_trans_huge(*pmd));
 
 	count_vm_event(THP_SPLIT_PMD);
 
@@ -3062,8 +3058,7 @@ void split_huge_pmd_locked(struct vm_area_struct *vma, unsigned long address,
 			   pmd_t *pmd, bool freeze)
 {
 	VM_WARN_ON_ONCE(!IS_ALIGNED(address, HPAGE_PMD_SIZE));
-	if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd) ||
-	    is_pmd_migration_entry(*pmd))
+	if (pmd_trans_huge(*pmd) || is_pmd_migration_entry(*pmd))
 		__split_huge_pmd_locked(vma, pmd, address, freeze);
 }
 
diff --git a/mm/mapping_dirty_helpers.c b/mm/mapping_dirty_helpers.c
index dc1692ff9e58..c193de6cb23a 100644
--- a/mm/mapping_dirty_helpers.c
+++ b/mm/mapping_dirty_helpers.c
@@ -129,7 +129,7 @@ static int wp_clean_pmd_entry(pmd_t *pmd, unsigned long addr, unsigned long end,
 	pmd_t pmdval = pmdp_get_lockless(pmd);
 
 	/* Do not split a huge pmd, present or migrated */
-	if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval)) {
+	if (pmd_trans_huge(pmdval)) {
 		WARN_ON(pmd_write(pmdval) || pmd_dirty(pmdval));
 		walk->action = ACTION_CONTINUE;
 	}
@@ -152,7 +152,7 @@ static int wp_clean_pud_entry(pud_t *pud, unsigned long addr, unsigned long end,
 	pud_t pudval = READ_ONCE(*pud);
 
 	/* Do not split a huge pud */
-	if (pud_trans_huge(pudval) || pud_devmap(pudval)) {
+	if (pud_trans_huge(pudval)) {
 		WARN_ON(pud_write(pudval) || pud_dirty(pudval));
 		walk->action = ACTION_CONTINUE;
 	}
diff --git a/mm/memory.c b/mm/memory.c
index 01d51bd95197..150bb62855b1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -675,8 +675,6 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 		}
 	}
 
-	if (pmd_devmap(pmd))
-		return NULL;
 	if (is_huge_zero_pmd(pmd))
 		return NULL;
 	if (unlikely(pfn > highest_memmap_pfn))
@@ -1240,8 +1238,7 @@ copy_pmd_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	src_pmd = pmd_offset(src_pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)
-			|| pmd_devmap(*src_pmd)) {
+		if (is_swap_pmd(*src_pmd) || pmd_trans_huge(*src_pmd)) {
 			int err;
 			VM_BUG_ON_VMA(next-addr != HPAGE_PMD_SIZE, src_vma);
 			err = copy_huge_pmd(dst_mm, src_mm, dst_pmd, src_pmd,
@@ -1277,7 +1274,7 @@ copy_pud_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	src_pud = pud_offset(src_p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
-		if (pud_trans_huge(*src_pud) || pud_devmap(*src_pud)) {
+		if (pud_trans_huge(*src_pud)) {
 			int err;
 
 			VM_BUG_ON_VMA(next-addr != HPAGE_PUD_SIZE, src_vma);
@@ -1791,7 +1788,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
+		if (is_swap_pmd(*pmd) || pmd_trans_huge(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE)
 				__split_huge_pmd(vma, pmd, addr, false);
 			else if (zap_huge_pmd(tlb, vma, pmd, addr)) {
@@ -1833,7 +1830,7 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb,
 	pud = pud_offset(p4d, addr);
 	do {
 		next = pud_addr_end(addr, end);
-		if (pud_trans_huge(*pud) || pud_devmap(*pud)) {
+		if (pud_trans_huge(*pud)) {
 			if (next - addr != HPAGE_PUD_SIZE) {
 				mmap_assert_locked(tlb->mm);
 				split_huge_pud(vma, pud, addr);
@@ -6136,7 +6133,7 @@ retry_pud:
 		pud_t orig_pud = *vmf.pud;
 
 		barrier();
-		if (pud_trans_huge(orig_pud) || pud_devmap(orig_pud)) {
+		if (pud_trans_huge(orig_pud)) {
 
 			/*
 			 * TODO once we support anonymous PUDs: NUMA case and
@@ -6177,7 +6174,7 @@ retry_pud:
 				pmd_migration_entry_wait(mm, vmf.pmd);
 			return 0;
 		}
-		if (pmd_trans_huge(vmf.orig_pmd) || pmd_devmap(vmf.orig_pmd)) {
+		if (pmd_trans_huge(vmf.orig_pmd)) {
 			if (pmd_protnone(vmf.orig_pmd) && vma_is_accessible(vma))
 				return do_huge_pmd_numa_page(&vmf);
 
diff --git a/mm/migrate_device.c b/mm/migrate_device.c
index 3158afe7eb23..e05e14d6eacd 100644
--- a/mm/migrate_device.c
+++ b/mm/migrate_device.c
@@ -615,7 +615,7 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate,
 	pmdp = pmd_alloc(mm, pudp, addr);
 	if (!pmdp)
 		goto abort;
-	if (pmd_trans_huge(*pmdp) || pmd_devmap(*pmdp))
+	if (pmd_trans_huge(*pmdp))
 		goto abort;
 	if (pte_alloc(mm, pmdp))
 		goto abort;
diff --git a/mm/mprotect.c b/mm/mprotect.c
index b873b98ab705..88709c01177b 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -376,7 +376,7 @@ again:
 			goto next;
 
 		_pmd = pmdp_get_lockless(pmd);
-		if (is_swap_pmd(_pmd) || pmd_trans_huge(_pmd) || pmd_devmap(_pmd)) {
+		if (is_swap_pmd(_pmd) || pmd_trans_huge(_pmd)) {
 			if ((next - addr != HPAGE_PMD_SIZE) ||
 			    pgtable_split_needed(vma, cp_flags)) {
 				__split_huge_pmd(vma, pmd, addr, false);
diff --git a/mm/mremap.c b/mm/mremap.c
index 7e93d3344828..36585041c760 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -820,7 +820,7 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc)
 		new_pud = alloc_new_pud(mm, pmc->new_addr);
 		if (!new_pud)
 			break;
-		if (pud_trans_huge(*old_pud) || pud_devmap(*old_pud)) {
+		if (pud_trans_huge(*old_pud)) {
 			if (extent == HPAGE_PUD_SIZE) {
 				move_pgt_entry(pmc, HPAGE_PUD, old_pud, new_pud);
 				/* We ignore and continue on error? */
@@ -839,8 +839,7 @@ unsigned long move_page_tables(struct pagetable_move_control *pmc)
 		if (!new_pmd)
 			break;
 again:
-		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd) ||
-		    pmd_devmap(*old_pmd)) {
+		if (is_swap_pmd(*old_pmd) || pmd_trans_huge(*old_pmd)) {
 			if (extent == HPAGE_PMD_SIZE &&
 			    move_pgt_entry(pmc, HPAGE_PMD, old_pmd, new_pmd))
 				continue;
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index e463c3be934a..e981a1a292d2 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -246,8 +246,7 @@ restart:
 		 */
 		pmde = pmdp_get_lockless(pvmw->pmd);
 
-		if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde) ||
-		    (pmd_present(pmde) && pmd_devmap(pmde))) {
+		if (pmd_trans_huge(pmde) || is_pmd_migration_entry(pmde)) {
 			pvmw->ptl = pmd_lock(mm, pvmw->pmd);
 			pmde = *pvmw->pmd;
 			if (!pmd_present(pmde)) {
@@ -262,7 +261,7 @@ restart:
 					return not_found(pvmw);
 				return true;
 			}
-			if (likely(pmd_trans_huge(pmde) || pmd_devmap(pmde))) {
+			if (likely(pmd_trans_huge(pmde))) {
 				if (pvmw->flags & PVMW_MIGRATION)
 					return not_found(pvmw);
 				if (!check_pmd(pmd_pfn(pmde), pvmw))
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index a214a2b40ab9..648038247a8d 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -143,8 +143,7 @@ again:
 			 * We are ONLY installing, so avoid unnecessarily
 			 * splitting a present huge page.
 			 */
-			if (pmd_present(*pmd) &&
-			    (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
+			if (pmd_present(*pmd) && pmd_trans_huge(*pmd))
 				continue;
 		}
 
@@ -210,8 +209,7 @@ static int walk_pud_range(p4d_t *p4d, unsigned long addr, unsigned long end,
 			 * We are ONLY installing, so avoid unnecessarily
 			 * splitting a present huge page.
 			 */
-			if (pud_present(*pud) &&
-			    (pud_trans_huge(*pud) || pud_devmap(*pud)))
+			if (pud_present(*pud) && pud_trans_huge(*pud))
 				continue;
 		}
 
@@ -908,7 +906,7 @@ struct folio *folio_walk_start(struct folio_walk *fw,
 		 * TODO: FW_MIGRATION support for PUD migration entries
 		 * once there are relevant users.
 		 */
-		if (!pud_present(pud) || pud_devmap(pud) || pud_special(pud)) {
+		if (!pud_present(pud) || pud_special(pud)) {
 			spin_unlock(ptl);
 			goto not_found;
 		} else if (!pud_leaf(pud)) {
diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
index 5a882f2b10f9..567e2d084071 100644
--- a/mm/pgtable-generic.c
+++ b/mm/pgtable-generic.c
@@ -139,8 +139,7 @@ pmd_t pmdp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
 {
 	pmd_t pmd;
 	VM_BUG_ON(address & ~HPAGE_PMD_MASK);
-	VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp) &&
-			   !pmd_devmap(*pmdp));
+	VM_BUG_ON(pmd_present(*pmdp) && !pmd_trans_huge(*pmdp));
 	pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp);
 	flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
 	return pmd;
@@ -153,7 +152,7 @@ pud_t pudp_huge_clear_flush(struct vm_area_struct *vma, unsigned long address,
 	pud_t pud;
 
 	VM_BUG_ON(address & ~HPAGE_PUD_MASK);
-	VM_BUG_ON(!pud_trans_huge(*pudp) && !pud_devmap(*pudp));
+	VM_BUG_ON(!pud_trans_huge(*pudp));
 	pud = pudp_huge_get_and_clear(vma->vm_mm, address, pudp);
 	flush_pud_tlb_range(vma, address, address + HPAGE_PUD_SIZE);
 	return pud;
@@ -293,7 +292,7 @@ pte_t *___pte_offset_map(pmd_t *pmd, unsigned long addr, pmd_t *pmdvalp)
 		*pmdvalp = pmdval;
 	if (unlikely(pmd_none(pmdval) || is_pmd_migration_entry(pmdval)))
 		goto nomap;
-	if (unlikely(pmd_trans_huge(pmdval) || pmd_devmap(pmdval)))
+	if (unlikely(pmd_trans_huge(pmdval)))
 		goto nomap;
 	if (unlikely(pmd_bad(pmdval))) {
 		pmd_clear_bad(pmd);
diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
index dd2a25fafb82..cbed91b09640 100644
--- a/mm/userfaultfd.c
+++ b/mm/userfaultfd.c
@@ -795,8 +795,8 @@ retry:
 		 * (This includes the case where the PMD used to be THP and
 		 * changed back to none after __pte_alloc().)
 		 */
-		if (unlikely(!pmd_present(dst_pmdval) || pmd_trans_huge(dst_pmdval) ||
-			     pmd_devmap(dst_pmdval))) {
+		if (unlikely(!pmd_present(dst_pmdval) ||
+				pmd_trans_huge(dst_pmdval))) {
 			err = -EEXIST;
 			break;
 		}
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 6698fadf5d04..c86a2495138a 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3450,9 +3450,6 @@ static unsigned long get_pmd_pfn(pmd_t pmd, struct vm_area_struct *vma, unsigned
 	if (!pmd_present(pmd) || is_huge_zero_pmd(pmd))
 		return -1;
 
-	if (WARN_ON_ONCE(pmd_devmap(pmd)))
-		return -1;
-
 	if (!pmd_young(pmd) && !mm_has_notifiers(vma->vm_mm))
 		return -1;
 
-- 
cgit v1.2.3


From d438d273417055241ebaaf1ba3be23459fc27cba Mon Sep 17 00:00:00 2001
From: Alistair Popple <apopple@nvidia.com>
Date: Thu, 19 Jun 2025 18:58:03 +1000
Subject: mm: remove devmap related functions and page table bits
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that DAX and all other reference counts to ZONE_DEVICE pages are
managed normally there is no need for the special devmap PTE/PMD/PUD page
table bits.  So drop all references to these, freeing up a software
defined page table bit on architectures supporting it.

Link: https://lkml.kernel.org/r/6389398c32cc9daa3dfcaa9f79c7972525d310ce.1750323463.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Acked-by: Will Deacon <will@kernel.org> # arm64
Acked-by: David Hildenbrand <david@redhat.com>
Suggested-by: Chunyan Zhang <zhang.lyra@gmail.com>
Reviewed-by: Björn Töpel <bjorn@rivosinc.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Björn Töpel <bjorn@kernel.org>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Inki Dae <m.szyprowski@samsung.com>
Cc: John Groves <john@groves.net>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/mm/arch_pgtable_helpers.rst     |  6 ---
 arch/arm64/Kconfig                            |  1 -
 arch/arm64/include/asm/pgtable-prot.h         |  1 -
 arch/arm64/include/asm/pgtable.h              | 24 -----------
 arch/loongarch/Kconfig                        |  1 -
 arch/loongarch/include/asm/pgtable-bits.h     |  6 +--
 arch/loongarch/include/asm/pgtable.h          | 19 ---------
 arch/powerpc/Kconfig                          |  1 -
 arch/powerpc/include/asm/book3s/64/hash-4k.h  |  6 ---
 arch/powerpc/include/asm/book3s/64/hash-64k.h |  7 +---
 arch/powerpc/include/asm/book3s/64/pgtable.h  | 53 +-----------------------
 arch/powerpc/include/asm/book3s/64/radix.h    | 14 +------
 arch/riscv/Kconfig                            |  1 -
 arch/riscv/include/asm/pgtable-64.h           | 16 --------
 arch/riscv/include/asm/pgtable-bits.h         |  1 -
 arch/riscv/include/asm/pgtable.h              | 22 ----------
 arch/x86/Kconfig                              |  1 -
 arch/x86/include/asm/pgtable.h                | 51 +----------------------
 arch/x86/include/asm/pgtable_types.h          |  5 +--
 include/linux/mm.h                            |  7 ----
 include/linux/pgtable.h                       | 19 +--------
 mm/Kconfig                                    |  4 --
 mm/debug_vm_pgtable.c                         | 59 ---------------------------
 mm/hmm.c                                      |  3 +-
 mm/madvise.c                                  |  8 ++--
 25 files changed, 17 insertions(+), 319 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/mm/arch_pgtable_helpers.rst b/Documentation/mm/arch_pgtable_helpers.rst
index af245161d8e7..c88c7fa665d6 100644
--- a/Documentation/mm/arch_pgtable_helpers.rst
+++ b/Documentation/mm/arch_pgtable_helpers.rst
@@ -30,8 +30,6 @@ PTE Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pte_protnone              | Tests a PROT_NONE PTE                            |
 +---------------------------+--------------------------------------------------+
-| pte_devmap                | Tests a ZONE_DEVICE mapped PTE                   |
-+---------------------------+--------------------------------------------------+
 | pte_soft_dirty            | Tests a soft dirty PTE                           |
 +---------------------------+--------------------------------------------------+
 | pte_swp_soft_dirty        | Tests a soft dirty swapped PTE                   |
@@ -104,8 +102,6 @@ PMD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pmd_protnone              | Tests a PROT_NONE PMD                            |
 +---------------------------+--------------------------------------------------+
-| pmd_devmap                | Tests a ZONE_DEVICE mapped PMD                   |
-+---------------------------+--------------------------------------------------+
 | pmd_soft_dirty            | Tests a soft dirty PMD                           |
 +---------------------------+--------------------------------------------------+
 | pmd_swp_soft_dirty        | Tests a soft dirty swapped PMD                   |
@@ -177,8 +173,6 @@ PUD Page Table Helpers
 +---------------------------+--------------------------------------------------+
 | pud_write                 | Tests a writable PUD                             |
 +---------------------------+--------------------------------------------------+
-| pud_devmap                | Tests a ZONE_DEVICE mapped PUD                   |
-+---------------------------+--------------------------------------------------+
 | pud_mkyoung               | Creates a young PUD                              |
 +---------------------------+--------------------------------------------------+
 | pud_mkold                 | Creates an old PUD                               |
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 55fc331af337..94b48b1dae71 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -44,7 +44,6 @@ config ARM64
 	select ARCH_HAS_NONLEAF_PMD_YOUNG if ARM64_HAFT
 	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PTDUMP
-	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_HW_PTE_YOUNG
 	select ARCH_HAS_SETUP_DMA_OPS
diff --git a/arch/arm64/include/asm/pgtable-prot.h b/arch/arm64/include/asm/pgtable-prot.h
index 7830d031742e..85dceb1c66f4 100644
--- a/arch/arm64/include/asm/pgtable-prot.h
+++ b/arch/arm64/include/asm/pgtable-prot.h
@@ -17,7 +17,6 @@
 #define PTE_SWP_EXCLUSIVE	(_AT(pteval_t, 1) << 2)	 /* only for swp ptes */
 #define PTE_DIRTY		(_AT(pteval_t, 1) << 55)
 #define PTE_SPECIAL		(_AT(pteval_t, 1) << 56)
-#define PTE_DEVMAP		(_AT(pteval_t, 1) << 57)
 
 /*
  * PTE_PRESENT_INVALID=1 & PTE_VALID=0 indicates that the pte's fields should be
diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
index e511f909f63c..ba63c8736666 100644
--- a/arch/arm64/include/asm/pgtable.h
+++ b/arch/arm64/include/asm/pgtable.h
@@ -190,7 +190,6 @@ static inline pteval_t __phys_to_pte_val(phys_addr_t phys)
 #define pte_user(pte)		(!!(pte_val(pte) & PTE_USER))
 #define pte_user_exec(pte)	(!(pte_val(pte) & PTE_UXN))
 #define pte_cont(pte)		(!!(pte_val(pte) & PTE_CONT))
-#define pte_devmap(pte)		(!!(pte_val(pte) & PTE_DEVMAP))
 #define pte_tagged(pte)		((pte_val(pte) & PTE_ATTRINDX_MASK) == \
 				 PTE_ATTRINDX(MT_NORMAL_TAGGED))
 
@@ -372,11 +371,6 @@ static inline pmd_t pmd_mkcont(pmd_t pmd)
 	return __pmd(pmd_val(pmd) | PMD_SECT_CONT);
 }
 
-static inline pte_t pte_mkdevmap(pte_t pte)
-{
-	return set_pte_bit(pte, __pgprot(PTE_DEVMAP | PTE_SPECIAL));
-}
-
 #ifdef CONFIG_HAVE_ARCH_USERFAULTFD_WP
 static inline int pte_uffd_wp(pte_t pte)
 {
@@ -653,14 +647,6 @@ static inline pmd_t pmd_mkhuge(pmd_t pmd)
 	return __pmd((pmd_val(pmd) & ~mask) | val);
 }
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define pmd_devmap(pmd)		pte_devmap(pmd_pte(pmd))
-#endif
-static inline pmd_t pmd_mkdevmap(pmd_t pmd)
-{
-	return pte_pmd(set_pte_bit(pmd_pte(pmd), __pgprot(PTE_DEVMAP)));
-}
-
 #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
 #define pmd_special(pte)	(!!((pmd_val(pte) & PTE_SPECIAL)))
 static inline pmd_t pmd_mkspecial(pmd_t pmd)
@@ -1302,16 +1288,6 @@ static inline int pmdp_set_access_flags(struct vm_area_struct *vma,
 	return __ptep_set_access_flags(vma, address, (pte_t *)pmdp,
 							pmd_pte(entry), dirty);
 }
-
-static inline int pud_devmap(pud_t pud)
-{
-	return 0;
-}
-
-static inline int pgd_devmap(pgd_t pgd)
-{
-	return 0;
-}
 #endif
 
 #ifdef CONFIG_PAGE_TABLE_CHECK
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 4b19f93379a1..edb3db230bac 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -25,7 +25,6 @@ config LOONGARCH
 	select ARCH_HAS_NMI_SAFE_THIS_CPU_OPS
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PREEMPT_LAZY
-	select ARCH_HAS_PTE_DEVMAP
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_MEMORY
 	select ARCH_HAS_SET_DIRECT_MAP
diff --git a/arch/loongarch/include/asm/pgtable-bits.h b/arch/loongarch/include/asm/pgtable-bits.h
index 7bbfb04a54cc..2fc3789220ac 100644
--- a/arch/loongarch/include/asm/pgtable-bits.h
+++ b/arch/loongarch/include/asm/pgtable-bits.h
@@ -22,7 +22,6 @@
 #define	_PAGE_PFN_SHIFT		12
 #define	_PAGE_SWP_EXCLUSIVE_SHIFT 23
 #define	_PAGE_PFN_END_SHIFT	48
-#define	_PAGE_DEVMAP_SHIFT	59
 #define	_PAGE_PRESENT_INVALID_SHIFT 60
 #define	_PAGE_NO_READ_SHIFT	61
 #define	_PAGE_NO_EXEC_SHIFT	62
@@ -36,7 +35,6 @@
 #define _PAGE_MODIFIED		(_ULCAST_(1) << _PAGE_MODIFIED_SHIFT)
 #define _PAGE_PROTNONE		(_ULCAST_(1) << _PAGE_PROTNONE_SHIFT)
 #define _PAGE_SPECIAL		(_ULCAST_(1) << _PAGE_SPECIAL_SHIFT)
-#define _PAGE_DEVMAP		(_ULCAST_(1) << _PAGE_DEVMAP_SHIFT)
 
 /* We borrow bit 23 to store the exclusive marker in swap PTEs. */
 #define _PAGE_SWP_EXCLUSIVE	(_ULCAST_(1) << _PAGE_SWP_EXCLUSIVE_SHIFT)
@@ -76,8 +74,8 @@
 #define __READABLE	(_PAGE_VALID)
 #define __WRITEABLE	(_PAGE_DIRTY | _PAGE_WRITE)
 
-#define _PAGE_CHG_MASK	(_PAGE_MODIFIED | _PAGE_SPECIAL | _PAGE_DEVMAP | _PFN_MASK | _CACHE_MASK | _PAGE_PLV)
-#define _HPAGE_CHG_MASK	(_PAGE_MODIFIED | _PAGE_SPECIAL | _PAGE_DEVMAP | _PFN_MASK | _CACHE_MASK | _PAGE_PLV | _PAGE_HUGE)
+#define _PAGE_CHG_MASK	(_PAGE_MODIFIED | _PAGE_SPECIAL | _PFN_MASK | _CACHE_MASK | _PAGE_PLV)
+#define _HPAGE_CHG_MASK	(_PAGE_MODIFIED | _PAGE_SPECIAL | _PFN_MASK | _CACHE_MASK | _PAGE_PLV | _PAGE_HUGE)
 
 #define PAGE_NONE	__pgprot(_PAGE_PROTNONE | _PAGE_NO_READ | \
 				 _PAGE_USER | _CACHE_CC)
diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
index f2aeff544cee..bd128696e96d 100644
--- a/arch/loongarch/include/asm/pgtable.h
+++ b/arch/loongarch/include/asm/pgtable.h
@@ -409,9 +409,6 @@ static inline int pte_special(pte_t pte)	{ return pte_val(pte) & _PAGE_SPECIAL;
 static inline pte_t pte_mkspecial(pte_t pte)	{ pte_val(pte) |= _PAGE_SPECIAL; return pte; }
 #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
 
-static inline int pte_devmap(pte_t pte)		{ return !!(pte_val(pte) & _PAGE_DEVMAP); }
-static inline pte_t pte_mkdevmap(pte_t pte)	{ pte_val(pte) |= _PAGE_DEVMAP; return pte; }
-
 #define pte_accessible pte_accessible
 static inline unsigned long pte_accessible(struct mm_struct *mm, pte_t a)
 {
@@ -540,17 +537,6 @@ static inline pmd_t pmd_mkyoung(pmd_t pmd)
 	return pmd;
 }
 
-static inline int pmd_devmap(pmd_t pmd)
-{
-	return !!(pmd_val(pmd) & _PAGE_DEVMAP);
-}
-
-static inline pmd_t pmd_mkdevmap(pmd_t pmd)
-{
-	pmd_val(pmd) |= _PAGE_DEVMAP;
-	return pmd;
-}
-
 static inline struct page *pmd_page(pmd_t pmd)
 {
 	if (pmd_trans_huge(pmd))
@@ -606,11 +592,6 @@ static inline long pmd_protnone(pmd_t pmd)
 #define pmd_leaf(pmd)		((pmd_val(pmd) & _PAGE_HUGE) != 0)
 #define pud_leaf(pud)		((pud_val(pud) & _PAGE_HUGE) != 0)
 
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-#define pud_devmap(pud)		(0)
-#define pgd_devmap(pgd)		(0)
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-
 /*
  * We provide our own get_unmapped area to cope with the virtual aliasing
  * constraints placed on us by the cache architecture.
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c3e0cc83f120..7a555c1d3171 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -149,7 +149,6 @@ config PPC
 	select ARCH_HAS_PMEM_API
 	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PTDUMP
-	select ARCH_HAS_PTE_DEVMAP		if PPC_BOOK3S_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SCALED_CPUTIME		if VIRT_CPU_ACCOUNTING_NATIVE && PPC_BOOK3S_64
 	select ARCH_HAS_SET_MEMORY
diff --git a/arch/powerpc/include/asm/book3s/64/hash-4k.h b/arch/powerpc/include/asm/book3s/64/hash-4k.h
index aa90a048f319..7132392fa7cd 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-4k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-4k.h
@@ -168,12 +168,6 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 extern int hash__has_transparent_hugepage(void);
 #endif
 
-static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
-{
-	BUG();
-	return pmd;
-}
-
 #endif /* !__ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_4K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/hash-64k.h b/arch/powerpc/include/asm/book3s/64/hash-64k.h
index 0bf6fd0bf42a..0fb5b7da9478 100644
--- a/arch/powerpc/include/asm/book3s/64/hash-64k.h
+++ b/arch/powerpc/include/asm/book3s/64/hash-64k.h
@@ -259,7 +259,7 @@ static inline void mark_hpte_slot_valid(unsigned char *hpte_slot_array,
  */
 static inline int hash__pmd_trans_huge(pmd_t pmd)
 {
-	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP)) ==
+	return !!((pmd_val(pmd) & (_PAGE_PTE | H_PAGE_THP_HUGE)) ==
 		  (_PAGE_PTE | H_PAGE_THP_HUGE));
 }
 
@@ -281,11 +281,6 @@ extern pmd_t hash__pmdp_huge_get_and_clear(struct mm_struct *mm,
 extern int hash__has_transparent_hugepage(void);
 #endif /*  CONFIG_TRANSPARENT_HUGEPAGE */
 
-static inline pmd_t hash__pmd_mkdevmap(pmd_t pmd)
-{
-	return __pmd(pmd_val(pmd) | (_PAGE_PTE | H_PAGE_THP_HUGE | _PAGE_DEVMAP));
-}
-
 #endif	/* __ASSEMBLY__ */
 
 #endif /* _ASM_POWERPC_BOOK3S_64_HASH_64K_H */
diff --git a/arch/powerpc/include/asm/book3s/64/pgtable.h b/arch/powerpc/include/asm/book3s/64/pgtable.h
index a2ddcbb3fcb9..c19800365315 100644
--- a/arch/powerpc/include/asm/book3s/64/pgtable.h
+++ b/arch/powerpc/include/asm/book3s/64/pgtable.h
@@ -88,7 +88,6 @@
 
 #define _PAGE_SOFT_DIRTY	_RPAGE_SW3 /* software: software dirty tracking */
 #define _PAGE_SPECIAL		_RPAGE_SW2 /* software: special page */
-#define _PAGE_DEVMAP		_RPAGE_SW1 /* software: ZONE_DEVICE page */
 
 /*
  * Drivers request for cache inhibited pte mapping using _PAGE_NO_CACHE
@@ -109,7 +108,7 @@
  */
 #define _HPAGE_CHG_MASK (PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
 			 _PAGE_ACCESSED | H_PAGE_THP_HUGE | _PAGE_PTE | \
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+			 _PAGE_SOFT_DIRTY)
 /*
  * user access blocked by key
  */
@@ -123,7 +122,7 @@
  */
 #define _PAGE_CHG_MASK	(PTE_RPN_MASK | _PAGE_HPTEFLAGS | _PAGE_DIRTY | \
 			 _PAGE_ACCESSED | _PAGE_SPECIAL | _PAGE_PTE |	\
-			 _PAGE_SOFT_DIRTY | _PAGE_DEVMAP)
+			 _PAGE_SOFT_DIRTY)
 
 /*
  * We define 2 sets of base prot bits, one for basic pages (ie,
@@ -609,24 +608,6 @@ static inline pte_t pte_mkhuge(pte_t pte)
 	return pte;
 }
 
-static inline pte_t pte_mkdevmap(pte_t pte)
-{
-	return __pte_raw(pte_raw(pte) | cpu_to_be64(_PAGE_SPECIAL | _PAGE_DEVMAP));
-}
-
-/*
- * This is potentially called with a pmd as the argument, in which case it's not
- * safe to check _PAGE_DEVMAP unless we also confirm that _PAGE_PTE is set.
- * That's because the bit we use for _PAGE_DEVMAP is not reserved for software
- * use in page directory entries (ie. non-ptes).
- */
-static inline int pte_devmap(pte_t pte)
-{
-	__be64 mask = cpu_to_be64(_PAGE_DEVMAP | _PAGE_PTE);
-
-	return (pte_raw(pte) & mask) == mask;
-}
-
 static inline pte_t pte_modify(pte_t pte, pgprot_t newprot)
 {
 	/* FIXME!! check whether this need to be a conditional */
@@ -1379,36 +1360,6 @@ static inline bool arch_needs_pgtable_deposit(void)
 }
 extern void serialize_against_pte_lookup(struct mm_struct *mm);
 
-
-static inline pmd_t pmd_mkdevmap(pmd_t pmd)
-{
-	if (radix_enabled())
-		return radix__pmd_mkdevmap(pmd);
-	return hash__pmd_mkdevmap(pmd);
-}
-
-static inline pud_t pud_mkdevmap(pud_t pud)
-{
-	if (radix_enabled())
-		return radix__pud_mkdevmap(pud);
-	BUG();
-	return pud;
-}
-
-static inline int pmd_devmap(pmd_t pmd)
-{
-	return pte_devmap(pmd_pte(pmd));
-}
-
-static inline int pud_devmap(pud_t pud)
-{
-	return pte_devmap(pud_pte(pud));
-}
-
-static inline int pgd_devmap(pgd_t pgd)
-{
-	return 0;
-}
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 #define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
diff --git a/arch/powerpc/include/asm/book3s/64/radix.h b/arch/powerpc/include/asm/book3s/64/radix.h
index 8f55ff74bb68..df23a8267e4d 100644
--- a/arch/powerpc/include/asm/book3s/64/radix.h
+++ b/arch/powerpc/include/asm/book3s/64/radix.h
@@ -264,7 +264,7 @@ static inline int radix__p4d_bad(p4d_t p4d)
 
 static inline int radix__pmd_trans_huge(pmd_t pmd)
 {
-	return (pmd_val(pmd) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE;
+	return (pmd_val(pmd) & _PAGE_PTE) == _PAGE_PTE;
 }
 
 static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
@@ -274,7 +274,7 @@ static inline pmd_t radix__pmd_mkhuge(pmd_t pmd)
 
 static inline int radix__pud_trans_huge(pud_t pud)
 {
-	return (pud_val(pud) & (_PAGE_PTE | _PAGE_DEVMAP)) == _PAGE_PTE;
+	return (pud_val(pud) & _PAGE_PTE) == _PAGE_PTE;
 }
 
 static inline pud_t radix__pud_mkhuge(pud_t pud)
@@ -315,16 +315,6 @@ static inline int radix__has_transparent_pud_hugepage(void)
 }
 #endif
 
-static inline pmd_t radix__pmd_mkdevmap(pmd_t pmd)
-{
-	return __pmd(pmd_val(pmd) | (_PAGE_PTE | _PAGE_DEVMAP));
-}
-
-static inline pud_t radix__pud_mkdevmap(pud_t pud)
-{
-	return __pud(pud_val(pud) | (_PAGE_PTE | _PAGE_DEVMAP));
-}
-
 struct vmem_altmap;
 struct dev_pagemap;
 extern int __meminit radix__vmemmap_create_mapping(unsigned long start,
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d71ea0f4466f..23df26f39472 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -46,7 +46,6 @@ config RISCV
 	select ARCH_HAS_PREEMPT_LAZY
 	select ARCH_HAS_PREPARE_SYNC_CORE_CMD
 	select ARCH_HAS_PTDUMP if MMU
-	select ARCH_HAS_PTE_DEVMAP if 64BIT && MMU
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_SET_DIRECT_MAP if MMU
 	select ARCH_HAS_SET_MEMORY if MMU
diff --git a/arch/riscv/include/asm/pgtable-64.h b/arch/riscv/include/asm/pgtable-64.h
index 7de05db7d3bd..1018d2216901 100644
--- a/arch/riscv/include/asm/pgtable-64.h
+++ b/arch/riscv/include/asm/pgtable-64.h
@@ -397,24 +397,8 @@ static inline struct page *pgd_page(pgd_t pgd)
 p4d_t *p4d_offset(pgd_t *pgd, unsigned long address);
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline int pte_devmap(pte_t pte);
 static inline pte_t pmd_pte(pmd_t pmd);
 static inline pte_t pud_pte(pud_t pud);
-
-static inline int pmd_devmap(pmd_t pmd)
-{
-	return pte_devmap(pmd_pte(pmd));
-}
-
-static inline int pud_devmap(pud_t pud)
-{
-	return pte_devmap(pud_pte(pud));
-}
-
-static inline int pgd_devmap(pgd_t pgd)
-{
-	return 0;
-}
 #endif
 
 #endif /* _ASM_RISCV_PGTABLE_64_H */
diff --git a/arch/riscv/include/asm/pgtable-bits.h b/arch/riscv/include/asm/pgtable-bits.h
index a8f5205cea54..179bd4afece4 100644
--- a/arch/riscv/include/asm/pgtable-bits.h
+++ b/arch/riscv/include/asm/pgtable-bits.h
@@ -19,7 +19,6 @@
 #define _PAGE_SOFT      (3 << 8)    /* Reserved for software */
 
 #define _PAGE_SPECIAL   (1 << 8)    /* RSW: 0x1 */
-#define _PAGE_DEVMAP    (1 << 9)    /* RSW, devmap */
 #define _PAGE_TABLE     _PAGE_PRESENT
 
 /*
diff --git a/arch/riscv/include/asm/pgtable.h b/arch/riscv/include/asm/pgtable.h
index 5bd5aae60d53..91697fbf1f90 100644
--- a/arch/riscv/include/asm/pgtable.h
+++ b/arch/riscv/include/asm/pgtable.h
@@ -409,13 +409,6 @@ static inline int pte_special(pte_t pte)
 	return pte_val(pte) & _PAGE_SPECIAL;
 }
 
-#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
-static inline int pte_devmap(pte_t pte)
-{
-	return pte_val(pte) & _PAGE_DEVMAP;
-}
-#endif
-
 /* static inline pte_t pte_rdprotect(pte_t pte) */
 
 static inline pte_t pte_wrprotect(pte_t pte)
@@ -457,11 +450,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 	return __pte(pte_val(pte) | _PAGE_SPECIAL);
 }
 
-static inline pte_t pte_mkdevmap(pte_t pte)
-{
-	return __pte(pte_val(pte) | _PAGE_DEVMAP);
-}
-
 static inline pte_t pte_mkhuge(pte_t pte)
 {
 	return pte;
@@ -790,11 +778,6 @@ static inline pmd_t pmd_mkdirty(pmd_t pmd)
 	return pte_pmd(pte_mkdirty(pmd_pte(pmd)));
 }
 
-static inline pmd_t pmd_mkdevmap(pmd_t pmd)
-{
-	return pte_pmd(pte_mkdevmap(pmd_pte(pmd)));
-}
-
 #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
 static inline bool pmd_special(pmd_t pmd)
 {
@@ -946,11 +929,6 @@ static inline pud_t pud_mkhuge(pud_t pud)
 	return pud;
 }
 
-static inline pud_t pud_mkdevmap(pud_t pud)
-{
-	return pte_pud(pte_mkdevmap(pud_pte(pud)));
-}
-
 static inline int pudp_set_access_flags(struct vm_area_struct *vma,
 					unsigned long address, pud_t *pudp,
 					pud_t entry, int dirty)
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 71019b3b54ea..bb9b63d76a19 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -101,7 +101,6 @@ config X86
 	select ARCH_HAS_NON_OVERLAPPING_ADDRESS_SPACE
 	select ARCH_HAS_PMEM_API		if X86_64
 	select ARCH_HAS_PREEMPT_LAZY
-	select ARCH_HAS_PTE_DEVMAP		if X86_64
 	select ARCH_HAS_PTE_SPECIAL
 	select ARCH_HAS_HW_PTE_YOUNG
 	select ARCH_HAS_NONLEAF_PMD_YOUNG	if PGTABLE_LEVELS > 2
diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
index 97954c936c54..e33df3da6980 100644
--- a/arch/x86/include/asm/pgtable.h
+++ b/arch/x86/include/asm/pgtable.h
@@ -301,16 +301,15 @@ static inline bool pmd_leaf(pmd_t pte)
 }
 
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-/* NOTE: when predicate huge page, consider also pmd_devmap, or use pmd_leaf */
 static inline int pmd_trans_huge(pmd_t pmd)
 {
-	return (pmd_val(pmd) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
+	return (pmd_val(pmd) & _PAGE_PSE) == _PAGE_PSE;
 }
 
 #ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
 static inline int pud_trans_huge(pud_t pud)
 {
-	return (pud_val(pud) & (_PAGE_PSE|_PAGE_DEVMAP)) == _PAGE_PSE;
+	return (pud_val(pud) & _PAGE_PSE) == _PAGE_PSE;
 }
 #endif
 
@@ -320,24 +319,6 @@ static inline int has_transparent_hugepage(void)
 	return boot_cpu_has(X86_FEATURE_PSE);
 }
 
-#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
-static inline int pmd_devmap(pmd_t pmd)
-{
-	return !!(pmd_val(pmd) & _PAGE_DEVMAP);
-}
-
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static inline int pud_devmap(pud_t pud)
-{
-	return !!(pud_val(pud) & _PAGE_DEVMAP);
-}
-#else
-static inline int pud_devmap(pud_t pud)
-{
-	return 0;
-}
-#endif
-
 #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
 static inline bool pmd_special(pmd_t pmd)
 {
@@ -361,12 +342,6 @@ static inline pud_t pud_mkspecial(pud_t pud)
 	return pud_set_flags(pud, _PAGE_SPECIAL);
 }
 #endif	/* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */
-
-static inline int pgd_devmap(pgd_t pgd)
-{
-	return 0;
-}
-#endif
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
 static inline pte_t pte_set_flags(pte_t pte, pteval_t set)
@@ -527,11 +502,6 @@ static inline pte_t pte_mkspecial(pte_t pte)
 	return pte_set_flags(pte, _PAGE_SPECIAL);
 }
 
-static inline pte_t pte_mkdevmap(pte_t pte)
-{
-	return pte_set_flags(pte, _PAGE_SPECIAL|_PAGE_DEVMAP);
-}
-
 /* See comments above mksaveddirty_shift() */
 static inline pmd_t pmd_mksaveddirty(pmd_t pmd)
 {
@@ -603,11 +573,6 @@ static inline pmd_t pmd_mkwrite_shstk(pmd_t pmd)
 	return pmd_set_flags(pmd, _PAGE_DIRTY);
 }
 
-static inline pmd_t pmd_mkdevmap(pmd_t pmd)
-{
-	return pmd_set_flags(pmd, _PAGE_DEVMAP);
-}
-
 static inline pmd_t pmd_mkhuge(pmd_t pmd)
 {
 	return pmd_set_flags(pmd, _PAGE_PSE);
@@ -673,11 +638,6 @@ static inline pud_t pud_mkdirty(pud_t pud)
 	return pud_mksaveddirty(pud);
 }
 
-static inline pud_t pud_mkdevmap(pud_t pud)
-{
-	return pud_set_flags(pud, _PAGE_DEVMAP);
-}
-
 static inline pud_t pud_mkhuge(pud_t pud)
 {
 	return pud_set_flags(pud, _PAGE_PSE);
@@ -1008,13 +968,6 @@ static inline int pte_present(pte_t a)
 	return pte_flags(a) & (_PAGE_PRESENT | _PAGE_PROTNONE);
 }
 
-#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
-static inline int pte_devmap(pte_t a)
-{
-	return (pte_flags(a) & _PAGE_DEVMAP) == _PAGE_DEVMAP;
-}
-#endif
-
 #define pte_accessible pte_accessible
 static inline bool pte_accessible(struct mm_struct *mm, pte_t a)
 {
diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index b74ec5c3643b..f63ae8d0aac8 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -34,7 +34,6 @@
 #define _PAGE_BIT_UFFD_WP	_PAGE_BIT_SOFTW2 /* userfaultfd wrprotected */
 #define _PAGE_BIT_SOFT_DIRTY	_PAGE_BIT_SOFTW3 /* software dirty tracking */
 #define _PAGE_BIT_KERNEL_4K	_PAGE_BIT_SOFTW3 /* page must not be converted to large */
-#define _PAGE_BIT_DEVMAP	_PAGE_BIT_SOFTW4
 
 #ifdef CONFIG_X86_64
 #define _PAGE_BIT_SAVED_DIRTY	_PAGE_BIT_SOFTW5 /* Saved Dirty bit (leaf) */
@@ -121,11 +120,9 @@
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_PAE)
 #define _PAGE_NX	(_AT(pteval_t, 1) << _PAGE_BIT_NX)
-#define _PAGE_DEVMAP	(_AT(u64, 1) << _PAGE_BIT_DEVMAP)
 #define _PAGE_SOFTW4	(_AT(pteval_t, 1) << _PAGE_BIT_SOFTW4)
 #else
 #define _PAGE_NX	(_AT(pteval_t, 0))
-#define _PAGE_DEVMAP	(_AT(pteval_t, 0))
 #define _PAGE_SOFTW4	(_AT(pteval_t, 0))
 #endif
 
@@ -154,7 +151,7 @@
 #define _COMMON_PAGE_CHG_MASK	(PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT |	\
 				 _PAGE_SPECIAL | _PAGE_ACCESSED |	\
 				 _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY |	\
-				 _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP)
+				 _PAGE_CC | _PAGE_UFFD_WP)
 #define _PAGE_CHG_MASK	(_COMMON_PAGE_CHG_MASK | _PAGE_PAT)
 #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE)
 
diff --git a/include/linux/mm.h b/include/linux/mm.h
index fc365420dfa8..4d833f159988 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2704,13 +2704,6 @@ static inline pud_t pud_mkspecial(pud_t pud)
 }
 #endif	/* CONFIG_ARCH_SUPPORTS_PUD_PFNMAP */
 
-#ifndef CONFIG_ARCH_HAS_PTE_DEVMAP
-static inline int pte_devmap(pte_t pte)
-{
-	return 0;
-}
-#endif
-
 extern pte_t *__get_locked_pte(struct mm_struct *mm, unsigned long addr,
 			       spinlock_t **ptl);
 static inline pte_t *get_locked_pte(struct mm_struct *mm, unsigned long addr,
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index ffcd966cf2d4..cf1515c163e2 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1643,21 +1643,6 @@ static inline int pud_write(pud_t pud)
 }
 #endif /* pud_write */
 
-#if !defined(CONFIG_ARCH_HAS_PTE_DEVMAP) || !defined(CONFIG_TRANSPARENT_HUGEPAGE)
-static inline int pmd_devmap(pmd_t pmd)
-{
-	return 0;
-}
-static inline int pud_devmap(pud_t pud)
-{
-	return 0;
-}
-static inline int pgd_devmap(pgd_t pgd)
-{
-	return 0;
-}
-#endif
-
 #if !defined(CONFIG_TRANSPARENT_HUGEPAGE) || \
 	!defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 static inline int pud_trans_huge(pud_t pud)
@@ -1912,8 +1897,8 @@ typedef unsigned int pgtbl_mod_mask;
  * - It should contain a huge PFN, which points to a huge page larger than
  *   PAGE_SIZE of the platform.  The PFN format isn't important here.
  *
- * - It should cover all kinds of huge mappings (e.g., pXd_trans_huge(),
- *   pXd_devmap(), or hugetlb mappings).
+ * - It should cover all kinds of huge mappings (i.e. pXd_trans_huge()
+ *   or hugetlb mappings).
  */
 #ifndef pgd_leaf
 #define pgd_leaf(x)	false
diff --git a/mm/Kconfig b/mm/Kconfig
index 065b1f19dd99..d5d4eca947a6 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1117,9 +1117,6 @@ config ARCH_HAS_CURRENT_STACK_POINTER
 	  register alias named "current_stack_pointer", this config can be
 	  selected.
 
-config ARCH_HAS_PTE_DEVMAP
-	bool
-
 config ARCH_HAS_ZONE_DMA_SET
 	bool
 
@@ -1137,7 +1134,6 @@ config ZONE_DEVICE
 	depends on MEMORY_HOTPLUG
 	depends on MEMORY_HOTREMOVE
 	depends on SPARSEMEM_VMEMMAP
-	depends on ARCH_HAS_PTE_DEVMAP
 	select XARRAY_MULTI
 
 	help
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index 7731b238b534..d84d0c49012f 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -348,12 +348,6 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 	vaddr &= HPAGE_PUD_MASK;
 
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
-	/*
-	 * Some architectures have debug checks to make sure
-	 * huge pud mapping are only found with devmap entries
-	 * For now test with only devmap entries.
-	 */
-	pud = pud_mkdevmap(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
 	flush_dcache_page(page);
 	pudp_set_wrprotect(args->mm, vaddr, args->pudp);
@@ -366,7 +360,6 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 	WARN_ON(!pud_none(pud));
 #endif /* __PAGETABLE_PMD_FOLDED */
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
-	pud = pud_mkdevmap(pud);
 	pud = pud_wrprotect(pud);
 	pud = pud_mkclean(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
@@ -384,7 +377,6 @@ static void __init pud_advanced_tests(struct pgtable_debug_args *args)
 #endif /* __PAGETABLE_PMD_FOLDED */
 
 	pud = pfn_pud(args->pud_pfn, args->page_prot);
-	pud = pud_mkdevmap(pud);
 	pud = pud_mkyoung(pud);
 	set_pud_at(args->mm, vaddr, args->pudp, pud);
 	flush_dcache_page(page);
@@ -693,53 +685,6 @@ static void __init pmd_protnone_tests(struct pgtable_debug_args *args)
 static void __init pmd_protnone_tests(struct pgtable_debug_args *args) { }
 #endif /* CONFIG_TRANSPARENT_HUGEPAGE */
 
-#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
-static void __init pte_devmap_tests(struct pgtable_debug_args *args)
-{
-	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
-
-	pr_debug("Validating PTE devmap\n");
-	WARN_ON(!pte_devmap(pte_mkdevmap(pte)));
-}
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static void __init pmd_devmap_tests(struct pgtable_debug_args *args)
-{
-	pmd_t pmd;
-
-	if (!has_transparent_hugepage())
-		return;
-
-	pr_debug("Validating PMD devmap\n");
-	pmd = pfn_pmd(args->fixed_pmd_pfn, args->page_prot);
-	WARN_ON(!pmd_devmap(pmd_mkdevmap(pmd)));
-}
-
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static void __init pud_devmap_tests(struct pgtable_debug_args *args)
-{
-	pud_t pud;
-
-	if (!has_transparent_pud_hugepage())
-		return;
-
-	pr_debug("Validating PUD devmap\n");
-	pud = pfn_pud(args->fixed_pud_pfn, args->page_prot);
-	WARN_ON(!pud_devmap(pud_mkdevmap(pud)));
-}
-#else  /* !CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
-#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
-#else  /* CONFIG_TRANSPARENT_HUGEPAGE */
-static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { }
-static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
-#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
-#else
-static void __init pte_devmap_tests(struct pgtable_debug_args *args) { }
-static void __init pmd_devmap_tests(struct pgtable_debug_args *args) { }
-static void __init pud_devmap_tests(struct pgtable_debug_args *args) { }
-#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */
-
 static void __init pte_soft_dirty_tests(struct pgtable_debug_args *args)
 {
 	pte_t pte = pfn_pte(args->fixed_pte_pfn, args->page_prot);
@@ -1333,10 +1278,6 @@ static int __init debug_vm_pgtable(void)
 	pte_protnone_tests(&args);
 	pmd_protnone_tests(&args);
 
-	pte_devmap_tests(&args);
-	pmd_devmap_tests(&args);
-	pud_devmap_tests(&args);
-
 	pte_soft_dirty_tests(&args);
 	pmd_soft_dirty_tests(&args);
 	pte_swap_soft_dirty_tests(&args);
diff --git a/mm/hmm.c b/mm/hmm.c
index 62d3082dc55c..f2415b4b2cdd 100644
--- a/mm/hmm.c
+++ b/mm/hmm.c
@@ -405,8 +405,7 @@ again:
 	return 0;
 }
 
-#if defined(CONFIG_ARCH_HAS_PTE_DEVMAP) && \
-    defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
+#if defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
 static inline unsigned long pud_to_hmm_pfn_flags(struct hmm_range *range,
 						 pud_t pud)
 {
diff --git a/mm/madvise.c b/mm/madvise.c
index 92f427b1b330..070132f9842b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -1069,7 +1069,7 @@ static int guard_install_pud_entry(pud_t *pud, unsigned long addr,
 	pud_t pudval = pudp_get(pud);
 
 	/* If huge return >0 so we abort the operation + zap. */
-	return pud_trans_huge(pudval) || pud_devmap(pudval);
+	return pud_trans_huge(pudval);
 }
 
 static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr,
@@ -1078,7 +1078,7 @@ static int guard_install_pmd_entry(pmd_t *pmd, unsigned long addr,
 	pmd_t pmdval = pmdp_get(pmd);
 
 	/* If huge return >0 so we abort the operation + zap. */
-	return pmd_trans_huge(pmdval) || pmd_devmap(pmdval);
+	return pmd_trans_huge(pmdval);
 }
 
 static int guard_install_pte_entry(pte_t *pte, unsigned long addr,
@@ -1189,7 +1189,7 @@ static int guard_remove_pud_entry(pud_t *pud, unsigned long addr,
 	pud_t pudval = pudp_get(pud);
 
 	/* If huge, cannot have guard pages present, so no-op - skip. */
-	if (pud_trans_huge(pudval) || pud_devmap(pudval))
+	if (pud_trans_huge(pudval))
 		walk->action = ACTION_CONTINUE;
 
 	return 0;
@@ -1201,7 +1201,7 @@ static int guard_remove_pmd_entry(pmd_t *pmd, unsigned long addr,
 	pmd_t pmdval = pmdp_get(pmd);
 
 	/* If huge, cannot have guard pages present, so no-op - skip. */
-	if (pmd_trans_huge(pmdval) || pmd_devmap(pmdval))
+	if (pmd_trans_huge(pmdval))
 		walk->action = ACTION_CONTINUE;
 
 	return 0;
-- 
cgit v1.2.3


From 984921edea68bf24bcc87e1317bfc90451ff46c6 Mon Sep 17 00:00:00 2001
From: Alistair Popple <apopple@nvidia.com>
Date: Thu, 19 Jun 2025 18:58:04 +1000
Subject: mm: remove PFN_DEV, PFN_MAP, PFN_SPECIAL, PFN_SG_CHAIN and
 PFN_SG_LAST
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The PFN_MAP flag is no longer used for anything, so remove it.  The
PFN_SG_CHAIN and PFN_SG_LAST flags never appear to have been used so also
remove them.  The last user of PFN_SPECIAL was removed by 653d7825c149
("dcssblk: mark DAX broken, remove FS_DAX_LIMITED support").

Users of PFN_DEV were removed earlier in this series by "mm: Remove
remaining uses of PFN_DEV".

Link: https://lkml.kernel.org/r/670b3950d70b4d97b905bb597dadfd3633de4314.1750323463.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Dan Williams <dan.j.williams@intel.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Björn Töpel <bjorn@kernel.org>
Cc: Björn Töpel <bjorn@rivosinc.com>
Cc: Chunyan Zhang <zhang.lyra@gmail.com>
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Inki Dae <m.szyprowski@samsung.com>
Cc: John Groves <john@groves.net>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pfn_t.h             | 50 ++-------------------------------------
 mm/memory.c                       |  2 --
 tools/testing/nvdimm/test/iomap.c |  4 ----
 3 files changed, 2 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
index 2d9148221e9a..2c002936a0f6 100644
--- a/include/linux/pfn_t.h
+++ b/include/linux/pfn_t.h
@@ -5,26 +5,11 @@
 
 /*
  * PFN_FLAGS_MASK - mask of all the possible valid pfn_t flags
- * PFN_SG_CHAIN - pfn is a pointer to the next scatterlist entry
- * PFN_SG_LAST - pfn references a page and is the last scatterlist entry
- * PFN_DEV - pfn is not covered by system memmap by default
- * PFN_MAP - pfn has a dynamic page mapping established by a device driver
- * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not
- *		 get_user_pages
  */
 #define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
-#define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
-#define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
-#define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))
-#define PFN_MAP (1ULL << (BITS_PER_LONG_LONG - 4))
-#define PFN_SPECIAL (1ULL << (BITS_PER_LONG_LONG - 5))
 
 #define PFN_FLAGS_TRACE \
-	{ PFN_SPECIAL,	"SPECIAL" }, \
-	{ PFN_SG_CHAIN,	"SG_CHAIN" }, \
-	{ PFN_SG_LAST,	"SG_LAST" }, \
-	{ PFN_DEV,	"DEV" }, \
-	{ PFN_MAP,	"MAP" }
+	{ }
 
 static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
 {
@@ -46,7 +31,7 @@ static inline pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags)
 
 static inline bool pfn_t_has_page(pfn_t pfn)
 {
-	return (pfn.val & PFN_MAP) == PFN_MAP || (pfn.val & PFN_DEV) == 0;
+	return true;
 }
 
 static inline unsigned long pfn_t_to_pfn(pfn_t pfn)
@@ -97,35 +82,4 @@ static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot)
 #endif
 #endif
 
-#ifdef CONFIG_ARCH_HAS_PTE_DEVMAP
-static inline bool pfn_t_devmap(pfn_t pfn)
-{
-	const u64 flags = PFN_DEV|PFN_MAP;
-
-	return (pfn.val & flags) == flags;
-}
-#else
-static inline bool pfn_t_devmap(pfn_t pfn)
-{
-	return false;
-}
-pte_t pte_mkdevmap(pte_t pte);
-pmd_t pmd_mkdevmap(pmd_t pmd);
-#if defined(CONFIG_TRANSPARENT_HUGEPAGE) && \
-	defined(CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD)
-pud_t pud_mkdevmap(pud_t pud);
-#endif
-#endif /* CONFIG_ARCH_HAS_PTE_DEVMAP */
-
-#ifdef CONFIG_ARCH_HAS_PTE_SPECIAL
-static inline bool pfn_t_special(pfn_t pfn)
-{
-	return (pfn.val & PFN_SPECIAL) == PFN_SPECIAL;
-}
-#else
-static inline bool pfn_t_special(pfn_t pfn)
-{
-	return false;
-}
-#endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
 #endif /* _LINUX_PFN_T_H_ */
diff --git a/mm/memory.c b/mm/memory.c
index 150bb62855b1..e932a007af4c 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2581,8 +2581,6 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn, bool mkwrite)
 	/* these checks mirror the abort conditions in vm_normal_page */
 	if (vma->vm_flags & VM_MIXEDMAP)
 		return true;
-	if (pfn_t_special(pfn))
-		return true;
 	if (is_zero_pfn(pfn_t_to_pfn(pfn)))
 		return true;
 	return false;
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index e4313726fae3..ddceb04b4a9a 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -137,10 +137,6 @@ EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages);
 
 pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
 {
-	struct nfit_test_resource *nfit_res = get_nfit_res(addr);
-
-	if (nfit_res)
-		flags &= ~PFN_MAP;
         return phys_to_pfn_t(addr, flags);
 }
 EXPORT_SYMBOL(__wrap_phys_to_pfn_t);
-- 
cgit v1.2.3


From 21aa65bf82a78c1e70447a45a85e533689b7f1a7 Mon Sep 17 00:00:00 2001
From: Alistair Popple <apopple@nvidia.com>
Date: Thu, 19 Jun 2025 18:58:05 +1000
Subject: mm: remove callers of pfn_t functionality
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

All PFN_* pfn_t flags have been removed.  Therefore there is no longer a
need for the pfn_t type and all uses can be replaced with normal pfns.

Link: https://lkml.kernel.org/r/bbedfa576c9822f8032494efbe43544628698b1f.1750323463.git-series.apopple@nvidia.com
Signed-off-by: Alistair Popple <apopple@nvidia.com>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Balbir Singh <balbirs@nvidia.com>
Cc: Björn Töpel <bjorn@kernel.org>
Cc: Björn Töpel <bjorn@rivosinc.com>
Cc: Chunyan Zhang <zhang.lyra@gmail.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Deepak Gupta <debug@rivosinc.com>
Cc: Gerald Schaefer <gerald.schaefer@linux.ibm.com>
Cc: Inki Dae <m.szyprowski@samsung.com>
Cc: John Groves <john@groves.net>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/mm/pat/memtype.c                |  1 -
 drivers/dax/device.c                     | 23 +++++----
 drivers/dax/hmem/hmem.c                  |  1 -
 drivers/dax/kmem.c                       |  1 -
 drivers/dax/pmem.c                       |  1 -
 drivers/dax/super.c                      |  3 +-
 drivers/gpu/drm/exynos/exynos_drm_gem.c  |  1 -
 drivers/gpu/drm/gma500/fbdev.c           |  3 +-
 drivers/gpu/drm/i915/gem/i915_gem_mman.c |  1 -
 drivers/gpu/drm/msm/msm_gem.c            |  1 -
 drivers/gpu/drm/omapdrm/omap_gem.c       |  6 +--
 drivers/gpu/drm/v3d/v3d_bo.c             |  1 -
 drivers/hwtracing/intel_th/msu.c         |  3 +-
 drivers/md/dm-linear.c                   |  2 +-
 drivers/md/dm-log-writes.c               |  2 +-
 drivers/md/dm-stripe.c                   |  2 +-
 drivers/md/dm-target.c                   |  2 +-
 drivers/md/dm-writecache.c               | 11 ++---
 drivers/md/dm.c                          |  2 +-
 drivers/nvdimm/pmem.c                    |  8 ++-
 drivers/nvdimm/pmem.h                    |  4 +-
 drivers/s390/block/dcssblk.c             |  9 ++--
 drivers/vfio/pci/vfio_pci_core.c         |  5 +-
 fs/cramfs/inode.c                        |  5 +-
 fs/dax.c                                 | 50 +++++++++----------
 fs/ext4/file.c                           |  2 +-
 fs/fuse/dax.c                            |  3 +-
 fs/fuse/virtio_fs.c                      |  5 +-
 fs/xfs/xfs_file.c                        |  2 +-
 include/linux/dax.h                      |  9 ++--
 include/linux/device-mapper.h            |  2 +-
 include/linux/huge_mm.h                  |  6 ++-
 include/linux/mm.h                       |  4 +-
 include/linux/pfn.h                      |  9 ----
 include/linux/pfn_t.h                    | 85 --------------------------------
 mm/debug_vm_pgtable.c                    |  1 -
 mm/huge_memory.c                         | 21 ++++----
 mm/memory.c                              | 31 ++++++------
 mm/memremap.c                            |  1 -
 mm/migrate.c                             |  1 -
 tools/testing/nvdimm/pmem-dax.c          |  6 +--
 tools/testing/nvdimm/test/iomap.c        |  7 ---
 tools/testing/nvdimm/test/nfit_test.h    |  1 -
 43 files changed, 109 insertions(+), 235 deletions(-)
 delete mode 100644 include/linux/pfn_t.h

(limited to 'include/linux')

diff --git a/arch/x86/mm/pat/memtype.c b/arch/x86/mm/pat/memtype.c
index 2e7923844afe..c09284302dd3 100644
--- a/arch/x86/mm/pat/memtype.c
+++ b/arch/x86/mm/pat/memtype.c
@@ -36,7 +36,6 @@
 #include <linux/debugfs.h>
 #include <linux/ioport.h>
 #include <linux/kernel.h>
-#include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/io.h>
 #include <linux/mm.h>
diff --git a/drivers/dax/device.c b/drivers/dax/device.c
index 328231cfb028..2bb40a6060af 100644
--- a/drivers/dax/device.c
+++ b/drivers/dax/device.c
@@ -4,7 +4,6 @@
 #include <linux/pagemap.h>
 #include <linux/module.h>
 #include <linux/device.h>
-#include <linux/pfn_t.h>
 #include <linux/cdev.h>
 #include <linux/slab.h>
 #include <linux/dax.h>
@@ -73,7 +72,7 @@ __weak phys_addr_t dax_pgoff_to_phys(struct dev_dax *dev_dax, pgoff_t pgoff,
 	return -1;
 }
 
-static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn,
+static void dax_set_mapping(struct vm_fault *vmf, unsigned long pfn,
 			      unsigned long fault_size)
 {
 	unsigned long i, nr_pages = fault_size / PAGE_SIZE;
@@ -89,7 +88,7 @@ static void dax_set_mapping(struct vm_fault *vmf, pfn_t pfn,
 			ALIGN_DOWN(vmf->address, fault_size));
 
 	for (i = 0; i < nr_pages; i++) {
-		struct folio *folio = pfn_folio(pfn_t_to_pfn(pfn) + i);
+		struct folio *folio = pfn_folio(pfn + i);
 
 		if (folio->mapping)
 			continue;
@@ -104,7 +103,7 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
 {
 	struct device *dev = &dev_dax->dev;
 	phys_addr_t phys;
-	pfn_t pfn;
+	unsigned long pfn;
 	unsigned int fault_size = PAGE_SIZE;
 
 	if (check_vma(dev_dax, vmf->vma, __func__))
@@ -125,11 +124,11 @@ static vm_fault_t __dev_dax_pte_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	pfn = phys_to_pfn_t(phys, 0);
+	pfn = PHYS_PFN(phys);
 
 	dax_set_mapping(vmf, pfn, fault_size);
 
-	return vmf_insert_page_mkwrite(vmf, pfn_t_to_page(pfn),
+	return vmf_insert_page_mkwrite(vmf, pfn_to_page(pfn),
 					vmf->flags & FAULT_FLAG_WRITE);
 }
 
@@ -140,7 +139,7 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 	struct device *dev = &dev_dax->dev;
 	phys_addr_t phys;
 	pgoff_t pgoff;
-	pfn_t pfn;
+	unsigned long pfn;
 	unsigned int fault_size = PMD_SIZE;
 
 	if (check_vma(dev_dax, vmf->vma, __func__))
@@ -169,11 +168,11 @@ static vm_fault_t __dev_dax_pmd_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	pfn = phys_to_pfn_t(phys, 0);
+	pfn = PHYS_PFN(phys);
 
 	dax_set_mapping(vmf, pfn, fault_size);
 
-	return vmf_insert_folio_pmd(vmf, page_folio(pfn_t_to_page(pfn)),
+	return vmf_insert_folio_pmd(vmf, page_folio(pfn_to_page(pfn)),
 				vmf->flags & FAULT_FLAG_WRITE);
 }
 
@@ -185,7 +184,7 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 	struct device *dev = &dev_dax->dev;
 	phys_addr_t phys;
 	pgoff_t pgoff;
-	pfn_t pfn;
+	unsigned long pfn;
 	unsigned int fault_size = PUD_SIZE;
 
 
@@ -215,11 +214,11 @@ static vm_fault_t __dev_dax_pud_fault(struct dev_dax *dev_dax,
 		return VM_FAULT_SIGBUS;
 	}
 
-	pfn = phys_to_pfn_t(phys, 0);
+	pfn = PHYS_PFN(phys);
 
 	dax_set_mapping(vmf, pfn, fault_size);
 
-	return vmf_insert_folio_pud(vmf, page_folio(pfn_t_to_page(pfn)),
+	return vmf_insert_folio_pud(vmf, page_folio(pfn_to_page(pfn)),
 				vmf->flags & FAULT_FLAG_WRITE);
 }
 #else
diff --git a/drivers/dax/hmem/hmem.c b/drivers/dax/hmem/hmem.c
index 5e7c53f18491..c18451a37e4f 100644
--- a/drivers/dax/hmem/hmem.c
+++ b/drivers/dax/hmem/hmem.c
@@ -2,7 +2,6 @@
 #include <linux/platform_device.h>
 #include <linux/memregion.h>
 #include <linux/module.h>
-#include <linux/pfn_t.h>
 #include <linux/dax.h>
 #include "../bus.h"
 
diff --git a/drivers/dax/kmem.c b/drivers/dax/kmem.c
index 584c70a34b52..c036e4d0b610 100644
--- a/drivers/dax/kmem.c
+++ b/drivers/dax/kmem.c
@@ -5,7 +5,6 @@
 #include <linux/memory.h>
 #include <linux/module.h>
 #include <linux/device.h>
-#include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/dax.h>
 #include <linux/fs.h>
diff --git a/drivers/dax/pmem.c b/drivers/dax/pmem.c
index c8ebf4e281f2..bee93066a849 100644
--- a/drivers/dax/pmem.c
+++ b/drivers/dax/pmem.c
@@ -2,7 +2,6 @@
 /* Copyright(c) 2016 - 2018 Intel Corporation. All rights reserved. */
 #include <linux/memremap.h>
 #include <linux/module.h>
-#include <linux/pfn_t.h>
 #include "../nvdimm/pfn.h"
 #include "../nvdimm/nd.h"
 #include "bus.h"
diff --git a/drivers/dax/super.c b/drivers/dax/super.c
index e16d1d40d773..54c480e874cb 100644
--- a/drivers/dax/super.c
+++ b/drivers/dax/super.c
@@ -7,7 +7,6 @@
 #include <linux/mount.h>
 #include <linux/pseudo_fs.h>
 #include <linux/magic.h>
-#include <linux/pfn_t.h>
 #include <linux/cdev.h>
 #include <linux/slab.h>
 #include <linux/uio.h>
@@ -148,7 +147,7 @@ enum dax_device_flags {
  * pages accessible at the device relative @pgoff.
  */
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		enum dax_access_mode mode, void **kaddr, pfn_t *pfn)
+		enum dax_access_mode mode, void **kaddr, unsigned long *pfn)
 {
 	long avail;
 
diff --git a/drivers/gpu/drm/exynos/exynos_drm_gem.c b/drivers/gpu/drm/exynos/exynos_drm_gem.c
index d44401a695e2..e3fbb45f37a2 100644
--- a/drivers/gpu/drm/exynos/exynos_drm_gem.c
+++ b/drivers/gpu/drm/exynos/exynos_drm_gem.c
@@ -7,7 +7,6 @@
 
 
 #include <linux/dma-buf.h>
-#include <linux/pfn_t.h>
 #include <linux/shmem_fs.h>
 #include <linux/module.h>
 
diff --git a/drivers/gpu/drm/gma500/fbdev.c b/drivers/gpu/drm/gma500/fbdev.c
index 109efdc96ac5..68b825fc056e 100644
--- a/drivers/gpu/drm/gma500/fbdev.c
+++ b/drivers/gpu/drm/gma500/fbdev.c
@@ -6,7 +6,6 @@
  **************************************************************************/
 
 #include <linux/fb.h>
-#include <linux/pfn_t.h>
 
 #include <drm/drm_crtc_helper.h>
 #include <drm/drm_drv.h>
@@ -33,7 +32,7 @@ static vm_fault_t psb_fbdev_vm_fault(struct vm_fault *vmf)
 	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
 
 	for (i = 0; i < page_num; ++i) {
-		err = vmf_insert_mixed(vma, address, __pfn_to_pfn_t(pfn, 0));
+		err = vmf_insert_mixed(vma, address, pfn);
 		if (unlikely(err & VM_FAULT_ERROR))
 			break;
 		address += PAGE_SIZE;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
index f6d37dff320d..75f5b0e871ef 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
@@ -5,7 +5,6 @@
 
 #include <linux/anon_inodes.h>
 #include <linux/mman.h>
-#include <linux/pfn_t.h>
 #include <linux/sizes.h>
 
 #include <drm/drm_cache.h>
diff --git a/drivers/gpu/drm/msm/msm_gem.c b/drivers/gpu/drm/msm/msm_gem.c
index 2995e80fec3b..20bf31fe799b 100644
--- a/drivers/gpu/drm/msm/msm_gem.c
+++ b/drivers/gpu/drm/msm/msm_gem.c
@@ -9,7 +9,6 @@
 #include <linux/spinlock.h>
 #include <linux/shmem_fs.h>
 #include <linux/dma-buf.h>
-#include <linux/pfn_t.h>
 
 #include <drm/drm_prime.h>
 #include <drm/drm_file.h>
diff --git a/drivers/gpu/drm/omapdrm/omap_gem.c b/drivers/gpu/drm/omapdrm/omap_gem.c
index 9df05b2b7ba0..381552bfb409 100644
--- a/drivers/gpu/drm/omapdrm/omap_gem.c
+++ b/drivers/gpu/drm/omapdrm/omap_gem.c
@@ -8,7 +8,6 @@
 #include <linux/seq_file.h>
 #include <linux/shmem_fs.h>
 #include <linux/spinlock.h>
-#include <linux/pfn_t.h>
 #include <linux/vmalloc.h>
 
 #include <drm/drm_prime.h>
@@ -371,7 +370,7 @@ static vm_fault_t omap_gem_fault_1d(struct drm_gem_object *obj,
 	VERB("Inserting %p pfn %lx, pa %lx", (void *)vmf->address,
 			pfn, pfn << PAGE_SHIFT);
 
-	return vmf_insert_mixed(vma, vmf->address, __pfn_to_pfn_t(pfn, 0));
+	return vmf_insert_mixed(vma, vmf->address, pfn);
 }
 
 /* Special handling for the case of faulting in 2d tiled buffers */
@@ -466,8 +465,7 @@ static vm_fault_t omap_gem_fault_2d(struct drm_gem_object *obj,
 			pfn, pfn << PAGE_SHIFT);
 
 	for (i = n; i > 0; i--) {
-		ret = vmf_insert_mixed(vma,
-			vaddr, __pfn_to_pfn_t(pfn, 0));
+		ret = vmf_insert_mixed(vma, vaddr, pfn);
 		if (ret & VM_FAULT_ERROR)
 			break;
 		pfn += priv->usergart[fmt].stride_pfn;
diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
index bb7815599435..c41476ddde68 100644
--- a/drivers/gpu/drm/v3d/v3d_bo.c
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -16,7 +16,6 @@
  */
 
 #include <linux/dma-buf.h>
-#include <linux/pfn_t.h>
 #include <linux/vmalloc.h>
 
 #include "v3d_drv.h"
diff --git a/drivers/hwtracing/intel_th/msu.c b/drivers/hwtracing/intel_th/msu.c
index 7163950eb371..f3a13b300835 100644
--- a/drivers/hwtracing/intel_th/msu.c
+++ b/drivers/hwtracing/intel_th/msu.c
@@ -19,7 +19,6 @@
 #include <linux/io.h>
 #include <linux/workqueue.h>
 #include <linux/dma-mapping.h>
-#include <linux/pfn_t.h>
 
 #ifdef CONFIG_X86
 #include <asm/set_memory.h>
@@ -1618,7 +1617,7 @@ static vm_fault_t msc_mmap_fault(struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 	get_page(page);
-	return vmf_insert_mixed(vmf->vma, vmf->address, page_to_pfn_t(page));
+	return vmf_insert_mixed(vmf->vma, vmf->address, page_to_pfn(page));
 }
 
 static const struct vm_operations_struct msc_mmap_ops = {
diff --git a/drivers/md/dm-linear.c b/drivers/md/dm-linear.c
index 15538ec58f8e..73bf290af181 100644
--- a/drivers/md/dm-linear.c
+++ b/drivers/md/dm-linear.c
@@ -170,7 +170,7 @@ static struct dax_device *linear_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 
 static long linear_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn)
+		unsigned long *pfn)
 {
 	struct dax_device *dax_dev = linear_dax_pgoff(ti, &pgoff);
 
diff --git a/drivers/md/dm-log-writes.c b/drivers/md/dm-log-writes.c
index d484e8e1d48a..679b07dee229 100644
--- a/drivers/md/dm-log-writes.c
+++ b/drivers/md/dm-log-writes.c
@@ -893,7 +893,7 @@ static struct dax_device *log_writes_dax_pgoff(struct dm_target *ti,
 
 static long log_writes_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn)
+		unsigned long *pfn)
 {
 	struct dax_device *dax_dev = log_writes_dax_pgoff(ti, &pgoff);
 
diff --git a/drivers/md/dm-stripe.c b/drivers/md/dm-stripe.c
index a7dc04bd55e5..366f46159785 100644
--- a/drivers/md/dm-stripe.c
+++ b/drivers/md/dm-stripe.c
@@ -316,7 +316,7 @@ static struct dax_device *stripe_dax_pgoff(struct dm_target *ti, pgoff_t *pgoff)
 
 static long stripe_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn)
+		unsigned long *pfn)
 {
 	struct dax_device *dax_dev = stripe_dax_pgoff(ti, &pgoff);
 
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 652627aea11b..2af5a9514c05 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -255,7 +255,7 @@ static void io_err_io_hints(struct dm_target *ti, struct queue_limits *limits)
 
 static long io_err_dax_direct_access(struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn)
+		unsigned long *pfn)
 {
 	return -EIO;
 }
diff --git a/drivers/md/dm-writecache.c b/drivers/md/dm-writecache.c
index a428e1cacf07..d8de4a3076a1 100644
--- a/drivers/md/dm-writecache.c
+++ b/drivers/md/dm-writecache.c
@@ -13,7 +13,6 @@
 #include <linux/dm-io.h>
 #include <linux/dm-kcopyd.h>
 #include <linux/dax.h>
-#include <linux/pfn_t.h>
 #include <linux/libnvdimm.h>
 #include <linux/delay.h>
 #include "dm-io-tracker.h"
@@ -256,7 +255,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 	int r;
 	loff_t s;
 	long p, da;
-	pfn_t pfn;
+	unsigned long pfn;
 	int id;
 	struct page **pages;
 	sector_t offset;
@@ -290,7 +289,7 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 		r = da;
 		goto err2;
 	}
-	if (!pfn_t_has_page(pfn)) {
+	if (!pfn_valid(pfn)) {
 		wc->memory_map = NULL;
 		r = -EOPNOTSUPP;
 		goto err2;
@@ -314,13 +313,13 @@ static int persistent_memory_claim(struct dm_writecache *wc)
 				r = daa ? daa : -EINVAL;
 				goto err3;
 			}
-			if (!pfn_t_has_page(pfn)) {
+			if (!pfn_valid(pfn)) {
 				r = -EOPNOTSUPP;
 				goto err3;
 			}
 			while (daa-- && i < p) {
-				pages[i++] = pfn_t_to_page(pfn);
-				pfn.val++;
+				pages[i++] = pfn_to_page(pfn);
+				pfn++;
 				if (!(i & 15))
 					cond_resched();
 			}
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 1726f0f828cc..4b9415f718e3 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -1218,7 +1218,7 @@ static struct dm_target *dm_dax_get_live_target(struct mapped_device *md,
 
 static long dm_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn)
+		unsigned long *pfn)
 {
 	struct mapped_device *md = dax_get_private(dax_dev);
 	sector_t sector = pgoff * PAGE_SECTORS;
diff --git a/drivers/nvdimm/pmem.c b/drivers/nvdimm/pmem.c
index aa50006b7616..05785ff21a8b 100644
--- a/drivers/nvdimm/pmem.c
+++ b/drivers/nvdimm/pmem.c
@@ -20,7 +20,6 @@
 #include <linux/kstrtox.h>
 #include <linux/vmalloc.h>
 #include <linux/blk-mq.h>
-#include <linux/pfn_t.h>
 #include <linux/slab.h>
 #include <linux/uio.h>
 #include <linux/dax.h>
@@ -242,7 +241,7 @@ static void pmem_submit_bio(struct bio *bio)
 /* see "strong" declaration in tools/testing/nvdimm/pmem-dax.c */
 __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn)
+		unsigned long *pfn)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
 	sector_t sector = PFN_PHYS(pgoff) >> SECTOR_SHIFT;
@@ -254,7 +253,7 @@ __weak long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
 	if (kaddr)
 		*kaddr = pmem->virt_addr + offset;
 	if (pfn)
-		*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
+		*pfn = PHYS_PFN(pmem->phys_addr + offset);
 
 	if (bb->count &&
 	    badblocks_check(bb, sector, num, &first_bad, &num_bad)) {
@@ -303,7 +302,7 @@ static int pmem_dax_zero_page_range(struct dax_device *dax_dev, pgoff_t pgoff,
 
 static long pmem_dax_direct_access(struct dax_device *dax_dev,
 		pgoff_t pgoff, long nr_pages, enum dax_access_mode mode,
-		void **kaddr, pfn_t *pfn)
+		void **kaddr, unsigned long *pfn)
 {
 	struct pmem_device *pmem = dax_get_private(dax_dev);
 
@@ -513,7 +512,6 @@ static int pmem_attach_disk(struct device *dev,
 
 	pmem->disk = disk;
 	pmem->pgmap.owner = pmem;
-	pmem->pfn_flags = 0;
 	if (is_nd_pfn(dev)) {
 		pmem->pgmap.type = MEMORY_DEVICE_FS_DAX;
 		pmem->pgmap.ops = &fsdax_pagemap_ops;
diff --git a/drivers/nvdimm/pmem.h b/drivers/nvdimm/pmem.h
index 392b0b38acb9..a48509f90196 100644
--- a/drivers/nvdimm/pmem.h
+++ b/drivers/nvdimm/pmem.h
@@ -5,7 +5,6 @@
 #include <linux/badblocks.h>
 #include <linux/memremap.h>
 #include <linux/types.h>
-#include <linux/pfn_t.h>
 #include <linux/fs.h>
 
 enum dax_access_mode;
@@ -16,7 +15,6 @@ struct pmem_device {
 	phys_addr_t		phys_addr;
 	/* when non-zero this device is hosting a 'pfn' instance */
 	phys_addr_t		data_offset;
-	u64			pfn_flags;
 	void			*virt_addr;
 	/* immutable base size of the namespace */
 	size_t			size;
@@ -31,7 +29,7 @@ struct pmem_device {
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn);
+		unsigned long *pfn);
 
 #ifdef CONFIG_MEMORY_FAILURE
 static inline bool test_and_clear_pmem_poison(struct page *page)
diff --git a/drivers/s390/block/dcssblk.c b/drivers/s390/block/dcssblk.c
index 249ae403f698..94fa5edecadd 100644
--- a/drivers/s390/block/dcssblk.c
+++ b/drivers/s390/block/dcssblk.c
@@ -17,7 +17,6 @@
 #include <linux/blkdev.h>
 #include <linux/completion.h>
 #include <linux/interrupt.h>
-#include <linux/pfn_t.h>
 #include <linux/uio.h>
 #include <linux/dax.h>
 #include <linux/io.h>
@@ -33,7 +32,7 @@ static void dcssblk_release(struct gendisk *disk);
 static void dcssblk_submit_bio(struct bio *bio);
 static long dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn);
+		unsigned long *pfn);
 
 static char dcssblk_segments[DCSSBLK_PARM_LEN] = "\0";
 
@@ -914,7 +913,7 @@ fail:
 
 static long
 __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
-		long nr_pages, void **kaddr, pfn_t *pfn)
+		long nr_pages, void **kaddr, unsigned long *pfn)
 {
 	resource_size_t offset = pgoff * PAGE_SIZE;
 	unsigned long dev_sz;
@@ -923,7 +922,7 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
 	if (kaddr)
 		*kaddr = __va(dev_info->start + offset);
 	if (pfn)
-		*pfn = __pfn_to_pfn_t(PFN_DOWN(dev_info->start + offset), 0);
+		*pfn = PFN_DOWN(dev_info->start + offset);
 
 	return (dev_sz - offset) / PAGE_SIZE;
 }
@@ -931,7 +930,7 @@ __dcssblk_direct_access(struct dcssblk_dev_info *dev_info, pgoff_t pgoff,
 static long
 dcssblk_dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn)
+		unsigned long *pfn)
 {
 	struct dcssblk_dev_info *dev_info = dax_get_private(dax_dev);
 
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 3f2ad5fb4c17..31bdb9110cc0 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -20,7 +20,6 @@
 #include <linux/mutex.h>
 #include <linux/notifier.h>
 #include <linux/pci.h>
-#include <linux/pfn_t.h>
 #include <linux/pm_runtime.h>
 #include <linux/slab.h>
 #include <linux/types.h>
@@ -1669,12 +1668,12 @@ static vm_fault_t vfio_pci_mmap_huge_fault(struct vm_fault *vmf,
 		break;
 #ifdef CONFIG_ARCH_SUPPORTS_PMD_PFNMAP
 	case PMD_ORDER:
-		ret = vmf_insert_pfn_pmd(vmf, __pfn_to_pfn_t(pfn, 0), false);
+		ret = vmf_insert_pfn_pmd(vmf, pfn, false);
 		break;
 #endif
 #ifdef CONFIG_ARCH_SUPPORTS_PUD_PFNMAP
 	case PUD_ORDER:
-		ret = vmf_insert_pfn_pud(vmf, __pfn_to_pfn_t(pfn, 0), false);
+		ret = vmf_insert_pfn_pud(vmf, pfn, false);
 		break;
 #endif
 	default:
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index 820a664cfec7..b002e9b734f9 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -17,7 +17,6 @@
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/pagemap.h>
-#include <linux/pfn_t.h>
 #include <linux/ramfs.h>
 #include <linux/init.h>
 #include <linux/string.h>
@@ -412,8 +411,8 @@ static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
 		for (i = 0; i < pages && !ret; i++) {
 			vm_fault_t vmf;
 			unsigned long off = i * PAGE_SIZE;
-			pfn_t pfn = phys_to_pfn_t(address + off, 0);
-			vmf = vmf_insert_mixed(vma, vma->vm_start + off, pfn);
+			vmf = vmf_insert_mixed(vma, vma->vm_start + off,
+					address + off);
 			if (vmf & VM_FAULT_ERROR)
 				ret = vm_fault_to_errno(vmf, 0);
 		}
diff --git a/fs/dax.c b/fs/dax.c
index f4ffb6982270..4229513806be 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -20,7 +20,6 @@
 #include <linux/sched/signal.h>
 #include <linux/uio.h>
 #include <linux/vmstat.h>
-#include <linux/pfn_t.h>
 #include <linux/sizes.h>
 #include <linux/mmu_notifier.h>
 #include <linux/iomap.h>
@@ -76,9 +75,9 @@ static struct folio *dax_to_folio(void *entry)
 	return page_folio(pfn_to_page(dax_to_pfn(entry)));
 }
 
-static void *dax_make_entry(pfn_t pfn, unsigned long flags)
+static void *dax_make_entry(unsigned long pfn, unsigned long flags)
 {
-	return xa_mk_value(flags | (pfn_t_to_pfn(pfn) << DAX_SHIFT));
+	return xa_mk_value(flags | (pfn << DAX_SHIFT));
 }
 
 static bool dax_is_locked(void *entry)
@@ -713,7 +712,7 @@ retry:
 
 		if (order > 0)
 			flags |= DAX_PMD;
-		entry = dax_make_entry(pfn_to_pfn_t(0), flags);
+		entry = dax_make_entry(0, flags);
 		dax_lock_entry(xas, entry);
 		if (xas_error(xas))
 			goto out_unlock;
@@ -1041,7 +1040,7 @@ static bool dax_fault_is_synchronous(const struct iomap_iter *iter,
  * appropriate.
  */
 static void *dax_insert_entry(struct xa_state *xas, struct vm_fault *vmf,
-		const struct iomap_iter *iter, void *entry, pfn_t pfn,
+		const struct iomap_iter *iter, void *entry, unsigned long pfn,
 		unsigned long flags)
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
@@ -1239,7 +1238,7 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
 
 static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
-		size_t size, void **kaddr, pfn_t *pfnp)
+		size_t size, void **kaddr, unsigned long *pfnp)
 {
 	pgoff_t pgoff = dax_iomap_pgoff(iomap, pos);
 	int id, rc = 0;
@@ -1257,7 +1256,7 @@ static int dax_iomap_direct_access(const struct iomap *iomap, loff_t pos,
 	rc = -EINVAL;
 	if (PFN_PHYS(length) < size)
 		goto out;
-	if (pfn_t_to_pfn(*pfnp) & (PHYS_PFN(size)-1))
+	if (*pfnp & (PHYS_PFN(size)-1))
 		goto out;
 
 	rc = 0;
@@ -1361,12 +1360,12 @@ static vm_fault_t dax_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 {
 	struct inode *inode = iter->inode;
 	unsigned long vaddr = vmf->address;
-	pfn_t pfn = pfn_to_pfn_t(my_zero_pfn(vaddr));
+	unsigned long pfn = my_zero_pfn(vaddr);
 	vm_fault_t ret;
 
 	*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn, DAX_ZERO_PAGE);
 
-	ret = vmf_insert_page_mkwrite(vmf, pfn_t_to_page(pfn), false);
+	ret = vmf_insert_page_mkwrite(vmf, pfn_to_page(pfn), false);
 	trace_dax_load_hole(inode, vmf, ret);
 	return ret;
 }
@@ -1383,14 +1382,14 @@ static vm_fault_t dax_pmd_load_hole(struct xa_state *xas, struct vm_fault *vmf,
 	struct folio *zero_folio;
 	spinlock_t *ptl;
 	pmd_t pmd_entry;
-	pfn_t pfn;
+	unsigned long pfn;
 
 	zero_folio = mm_get_huge_zero_folio(vmf->vma->vm_mm);
 
 	if (unlikely(!zero_folio))
 		goto fallback;
 
-	pfn = page_to_pfn_t(&zero_folio->page);
+	pfn = page_to_pfn(&zero_folio->page);
 	*entry = dax_insert_entry(xas, vmf, iter, *entry, pfn,
 				  DAX_PMD | DAX_ZERO_PAGE);
 
@@ -1779,7 +1778,8 @@ static vm_fault_t dax_fault_return(int error)
  * insertion for now and return the pfn so that caller can insert it after the
  * fsync is done.
  */
-static vm_fault_t dax_fault_synchronous_pfnp(pfn_t *pfnp, pfn_t pfn)
+static vm_fault_t dax_fault_synchronous_pfnp(unsigned long *pfnp,
+					unsigned long pfn)
 {
 	if (WARN_ON_ONCE(!pfnp))
 		return VM_FAULT_SIGBUS;
@@ -1827,7 +1827,7 @@ static vm_fault_t dax_fault_cow_page(struct vm_fault *vmf,
  * @pmd:	distinguish whether it is a pmd fault
  */
 static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
-		const struct iomap_iter *iter, pfn_t *pfnp,
+		const struct iomap_iter *iter, unsigned long *pfnp,
 		struct xa_state *xas, void **entry, bool pmd)
 {
 	const struct iomap *iomap = &iter->iomap;
@@ -1838,7 +1838,7 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
 	unsigned long entry_flags = pmd ? DAX_PMD : 0;
 	struct folio *folio;
 	int ret, err = 0;
-	pfn_t pfn;
+	unsigned long pfn;
 	void *kaddr;
 
 	if (!pmd && vmf->cow_page)
@@ -1875,16 +1875,15 @@ static vm_fault_t dax_fault_iter(struct vm_fault *vmf,
 
 	folio_ref_inc(folio);
 	if (pmd)
-		ret = vmf_insert_folio_pmd(vmf, pfn_folio(pfn_t_to_pfn(pfn)),
-					write);
+		ret = vmf_insert_folio_pmd(vmf, pfn_folio(pfn), write);
 	else
-		ret = vmf_insert_page_mkwrite(vmf, pfn_t_to_page(pfn), write);
+		ret = vmf_insert_page_mkwrite(vmf, pfn_to_page(pfn), write);
 	folio_put(folio);
 
 	return ret;
 }
 
-static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, pfn_t *pfnp,
+static vm_fault_t dax_iomap_pte_fault(struct vm_fault *vmf, unsigned long *pfnp,
 			       int *iomap_errp, const struct iomap_ops *ops)
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
@@ -1996,7 +1995,7 @@ static bool dax_fault_check_fallback(struct vm_fault *vmf, struct xa_state *xas,
 	return false;
 }
 
-static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
+static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, unsigned long *pfnp,
 			       const struct iomap_ops *ops)
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
@@ -2077,7 +2076,7 @@ out:
 	return ret;
 }
 #else
-static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
+static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, unsigned long *pfnp,
 			       const struct iomap_ops *ops)
 {
 	return VM_FAULT_FALLBACK;
@@ -2098,7 +2097,8 @@ static vm_fault_t dax_iomap_pmd_fault(struct vm_fault *vmf, pfn_t *pfnp,
  * successfully.
  */
 vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order,
-		    pfn_t *pfnp, int *iomap_errp, const struct iomap_ops *ops)
+			unsigned long *pfnp, int *iomap_errp,
+			const struct iomap_ops *ops)
 {
 	if (order == 0)
 		return dax_iomap_pte_fault(vmf, pfnp, iomap_errp, ops);
@@ -2118,8 +2118,8 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault);
  * This function inserts a writeable PTE or PMD entry into the page tables
  * for an mmaped DAX file.  It also marks the page cache entry as dirty.
  */
-static vm_fault_t
-dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
+static vm_fault_t dax_insert_pfn_mkwrite(struct vm_fault *vmf,
+					unsigned long pfn, unsigned int order)
 {
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	XA_STATE_ORDER(xas, &mapping->i_pages, vmf->pgoff, order);
@@ -2141,7 +2141,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
 	xas_set_mark(&xas, PAGECACHE_TAG_DIRTY);
 	dax_lock_entry(&xas, entry);
 	xas_unlock_irq(&xas);
-	folio = pfn_folio(pfn_t_to_pfn(pfn));
+	folio = pfn_folio(pfn);
 	folio_ref_inc(folio);
 	if (order == 0)
 		ret = vmf_insert_page_mkwrite(vmf, &folio->page, true);
@@ -2168,7 +2168,7 @@ dax_insert_pfn_mkwrite(struct vm_fault *vmf, pfn_t pfn, unsigned int order)
  * table entry.
  */
 vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf, unsigned int order,
-		pfn_t pfn)
+		unsigned long pfn)
 {
 	int err;
 	loff_t start = ((loff_t)vmf->pgoff) << PAGE_SHIFT;
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index 21df81347147..e6e962982319 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -747,7 +747,7 @@ static vm_fault_t ext4_dax_huge_fault(struct vm_fault *vmf, unsigned int order)
 	bool write = (vmf->flags & FAULT_FLAG_WRITE) &&
 		(vmf->vma->vm_flags & VM_SHARED);
 	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
-	pfn_t pfn;
+	unsigned long pfn;
 
 	if (write) {
 		sb_start_pagefault(sb);
diff --git a/fs/fuse/dax.c b/fs/fuse/dax.c
index 0502bf3cdf6a..ac6d4c1064cc 100644
--- a/fs/fuse/dax.c
+++ b/fs/fuse/dax.c
@@ -10,7 +10,6 @@
 #include <linux/dax.h>
 #include <linux/uio.h>
 #include <linux/pagemap.h>
-#include <linux/pfn_t.h>
 #include <linux/iomap.h>
 #include <linux/interval_tree.h>
 
@@ -757,7 +756,7 @@ static vm_fault_t __fuse_dax_fault(struct vm_fault *vmf, unsigned int order,
 	vm_fault_t ret;
 	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
-	pfn_t pfn;
+	unsigned long pfn;
 	int error = 0;
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	struct fuse_conn_dax *fcd = fc->dax;
diff --git a/fs/fuse/virtio_fs.c b/fs/fuse/virtio_fs.c
index 53c2626e90e7..aac914b2cd50 100644
--- a/fs/fuse/virtio_fs.c
+++ b/fs/fuse/virtio_fs.c
@@ -9,7 +9,6 @@
 #include <linux/pci.h>
 #include <linux/interrupt.h>
 #include <linux/group_cpus.h>
-#include <linux/pfn_t.h>
 #include <linux/memremap.h>
 #include <linux/module.h>
 #include <linux/virtio.h>
@@ -1008,7 +1007,7 @@ static void virtio_fs_cleanup_vqs(struct virtio_device *vdev)
  */
 static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 				    long nr_pages, enum dax_access_mode mode,
-				    void **kaddr, pfn_t *pfn)
+				    void **kaddr, unsigned long *pfn)
 {
 	struct virtio_fs *fs = dax_get_private(dax_dev);
 	phys_addr_t offset = PFN_PHYS(pgoff);
@@ -1017,7 +1016,7 @@ static long virtio_fs_direct_access(struct dax_device *dax_dev, pgoff_t pgoff,
 	if (kaddr)
 		*kaddr = fs->window_kaddr + offset;
 	if (pfn)
-		*pfn = phys_to_pfn_t(fs->window_phys_addr + offset, 0);
+		*pfn = fs->window_phys_addr + offset;
 	return nr_pages > max_nr_pages ? max_nr_pages : nr_pages;
 }
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 0b41b18debf3..314a9d9dd7db 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -1730,7 +1730,7 @@ xfs_dax_fault_locked(
 	bool			write_fault)
 {
 	vm_fault_t		ret;
-	pfn_t			pfn;
+	unsigned long		pfn;
 
 	if (!IS_ENABLED(CONFIG_FS_DAX)) {
 		ASSERT(0);
diff --git a/include/linux/dax.h b/include/linux/dax.h
index dcc9fcdf14e4..29eec755430b 100644
--- a/include/linux/dax.h
+++ b/include/linux/dax.h
@@ -26,7 +26,7 @@ struct dax_operations {
 	 * number of pages available for DAX at that pfn.
 	 */
 	long (*direct_access)(struct dax_device *, pgoff_t, long,
-			enum dax_access_mode, void **, pfn_t *);
+			enum dax_access_mode, void **, unsigned long *);
 	/* zero_page_range: required operation. Zero page range   */
 	int (*zero_page_range)(struct dax_device *, pgoff_t, size_t);
 	/*
@@ -241,7 +241,7 @@ static inline void dax_break_layout_final(struct inode *inode)
 bool dax_alive(struct dax_device *dax_dev);
 void *dax_get_private(struct dax_device *dax_dev);
 long dax_direct_access(struct dax_device *dax_dev, pgoff_t pgoff, long nr_pages,
-		enum dax_access_mode mode, void **kaddr, pfn_t *pfn);
+		enum dax_access_mode mode, void **kaddr, unsigned long *pfn);
 size_t dax_copy_from_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
 		size_t bytes, struct iov_iter *i);
 size_t dax_copy_to_iter(struct dax_device *dax_dev, pgoff_t pgoff, void *addr,
@@ -255,9 +255,10 @@ void dax_flush(struct dax_device *dax_dev, void *addr, size_t size);
 ssize_t dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
 		const struct iomap_ops *ops);
 vm_fault_t dax_iomap_fault(struct vm_fault *vmf, unsigned int order,
-		    pfn_t *pfnp, int *errp, const struct iomap_ops *ops);
+			unsigned long *pfnp, int *errp,
+			const struct iomap_ops *ops);
 vm_fault_t dax_finish_sync_fault(struct vm_fault *vmf,
-		unsigned int order, pfn_t pfn);
+		unsigned int order, unsigned long pfn);
 int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index);
 void dax_delete_mapping_range(struct address_space *mapping,
 				loff_t start, loff_t end);
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index cb95951547ab..84fdc3a6a19a 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -156,7 +156,7 @@ typedef int (*dm_busy_fn) (struct dm_target *ti);
  */
 typedef long (*dm_dax_direct_access_fn) (struct dm_target *ti, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode node, void **kaddr,
-		pfn_t *pfn);
+		unsigned long *pfn);
 typedef int (*dm_dax_zero_page_range_fn)(struct dm_target *ti, pgoff_t pgoff,
 		size_t nr_pages);
 
diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 26607f2c65fb..8f1b15213f61 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -37,8 +37,10 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
 		    pmd_t *pmd, unsigned long addr, pgprot_t newprot,
 		    unsigned long cp_flags);
 
-vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write);
-vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write);
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn,
+			      bool write);
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn,
+			      bool write);
 vm_fault_t vmf_insert_folio_pmd(struct vm_fault *vmf, struct folio *folio,
 				bool write);
 vm_fault_t vmf_insert_folio_pud(struct vm_fault *vmf, struct folio *folio,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4d833f159988..dccebf0abf06 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3522,9 +3522,9 @@ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn, pgprot_t pgprot);
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			pfn_t pfn);
+			unsigned long pfn);
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
-		unsigned long addr, pfn_t pfn);
+		unsigned long addr, unsigned long pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
 
 static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
diff --git a/include/linux/pfn.h b/include/linux/pfn.h
index 14bc053c53d8..b90ca0b6c331 100644
--- a/include/linux/pfn.h
+++ b/include/linux/pfn.h
@@ -4,15 +4,6 @@
 
 #ifndef __ASSEMBLY__
 #include <linux/types.h>
-
-/*
- * pfn_t: encapsulates a page-frame number that is optionally backed
- * by memmap (struct page).  Whether a pfn_t has a 'struct page'
- * backing is indicated by flags in the high bits of the value.
- */
-typedef struct {
-	u64 val;
-} pfn_t;
 #endif
 
 #define PFN_ALIGN(x)	(((unsigned long)(x) + (PAGE_SIZE - 1)) & PAGE_MASK)
diff --git a/include/linux/pfn_t.h b/include/linux/pfn_t.h
deleted file mode 100644
index 2c002936a0f6..000000000000
--- a/include/linux/pfn_t.h
+++ /dev/null
@@ -1,85 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_PFN_T_H_
-#define _LINUX_PFN_T_H_
-#include <linux/mm.h>
-
-/*
- * PFN_FLAGS_MASK - mask of all the possible valid pfn_t flags
- */
-#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
-
-#define PFN_FLAGS_TRACE \
-	{ }
-
-static inline pfn_t __pfn_to_pfn_t(unsigned long pfn, u64 flags)
-{
-	pfn_t pfn_t = { .val = pfn | (flags & PFN_FLAGS_MASK), };
-
-	return pfn_t;
-}
-
-/* a default pfn to pfn_t conversion assumes that @pfn is pfn_valid() */
-static inline pfn_t pfn_to_pfn_t(unsigned long pfn)
-{
-	return __pfn_to_pfn_t(pfn, 0);
-}
-
-static inline pfn_t phys_to_pfn_t(phys_addr_t addr, u64 flags)
-{
-	return __pfn_to_pfn_t(addr >> PAGE_SHIFT, flags);
-}
-
-static inline bool pfn_t_has_page(pfn_t pfn)
-{
-	return true;
-}
-
-static inline unsigned long pfn_t_to_pfn(pfn_t pfn)
-{
-	return pfn.val & ~PFN_FLAGS_MASK;
-}
-
-static inline struct page *pfn_t_to_page(pfn_t pfn)
-{
-	if (pfn_t_has_page(pfn))
-		return pfn_to_page(pfn_t_to_pfn(pfn));
-	return NULL;
-}
-
-static inline phys_addr_t pfn_t_to_phys(pfn_t pfn)
-{
-	return PFN_PHYS(pfn_t_to_pfn(pfn));
-}
-
-static inline pfn_t page_to_pfn_t(struct page *page)
-{
-	return pfn_to_pfn_t(page_to_pfn(page));
-}
-
-static inline int pfn_t_valid(pfn_t pfn)
-{
-	return pfn_valid(pfn_t_to_pfn(pfn));
-}
-
-#ifdef CONFIG_MMU
-static inline pte_t pfn_t_pte(pfn_t pfn, pgprot_t pgprot)
-{
-	return pfn_pte(pfn_t_to_pfn(pfn), pgprot);
-}
-#endif
-
-#ifdef CONFIG_TRANSPARENT_HUGEPAGE
-static inline pmd_t pfn_t_pmd(pfn_t pfn, pgprot_t pgprot)
-{
-	return pfn_pmd(pfn_t_to_pfn(pfn), pgprot);
-}
-
-#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
-static inline pud_t pfn_t_pud(pfn_t pfn, pgprot_t pgprot)
-{
-	return pfn_pud(pfn_t_to_pfn(pfn), pgprot);
-}
-#endif
-#endif
-
-#endif /* _LINUX_PFN_T_H_ */
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index d84d0c49012f..bd8f9317b025 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -20,7 +20,6 @@
 #include <linux/mman.h>
 #include <linux/mm_types.h>
 #include <linux/module.h>
-#include <linux/pfn_t.h>
 #include <linux/printk.h>
 #include <linux/pgtable.h>
 #include <linux/random.h>
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index cf808b2eea29..ce130225a8e5 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -22,7 +22,6 @@
 #include <linux/mm_types.h>
 #include <linux/khugepaged.h>
 #include <linux/freezer.h>
-#include <linux/pfn_t.h>
 #include <linux/mman.h>
 #include <linux/memremap.h>
 #include <linux/pagemap.h>
@@ -1375,7 +1374,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
 struct folio_or_pfn {
 	union {
 		struct folio *folio;
-		pfn_t pfn;
+		unsigned long pfn;
 	};
 	bool is_folio;
 };
@@ -1391,7 +1390,7 @@ static int insert_pmd(struct vm_area_struct *vma, unsigned long addr,
 
 	if (!pmd_none(*pmd)) {
 		const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) :
-					  pfn_t_to_pfn(fop.pfn);
+					  fop.pfn;
 
 		if (write) {
 			if (pmd_pfn(*pmd) != pfn) {
@@ -1414,7 +1413,7 @@ static int insert_pmd(struct vm_area_struct *vma, unsigned long addr,
 		folio_add_file_rmap_pmd(fop.folio, &fop.folio->page, vma);
 		add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PMD_NR);
 	} else {
-		entry = pmd_mkhuge(pfn_t_pmd(fop.pfn, prot));
+		entry = pmd_mkhuge(pfn_pmd(fop.pfn, prot));
 		entry = pmd_mkspecial(entry);
 	}
 	if (write) {
@@ -1442,7 +1441,8 @@ static int insert_pmd(struct vm_area_struct *vma, unsigned long addr,
  *
  * Return: vm_fault_t value.
  */
-vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
+vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, unsigned long pfn,
+			      bool write)
 {
 	unsigned long addr = vmf->address & PMD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
@@ -1473,7 +1473,7 @@ vm_fault_t vmf_insert_pfn_pmd(struct vm_fault *vmf, pfn_t pfn, bool write)
 			return VM_FAULT_OOM;
 	}
 
-	pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot);
+	pfnmap_setup_cachemode_pfn(pfn, &pgprot);
 
 	ptl = pmd_lock(vma->vm_mm, vmf->pmd);
 	error = insert_pmd(vma, addr, vmf->pmd, fop, pgprot, write,
@@ -1539,7 +1539,7 @@ static void insert_pud(struct vm_area_struct *vma, unsigned long addr,
 
 	if (!pud_none(*pud)) {
 		const unsigned long pfn = fop.is_folio ? folio_pfn(fop.folio) :
-					  pfn_t_to_pfn(fop.pfn);
+					  fop.pfn;
 
 		if (write) {
 			if (WARN_ON_ONCE(pud_pfn(*pud) != pfn))
@@ -1559,7 +1559,7 @@ static void insert_pud(struct vm_area_struct *vma, unsigned long addr,
 		folio_add_file_rmap_pud(fop.folio, &fop.folio->page, vma);
 		add_mm_counter(mm, mm_counter_file(fop.folio), HPAGE_PUD_NR);
 	} else {
-		entry = pud_mkhuge(pfn_t_pud(fop.pfn, prot));
+		entry = pud_mkhuge(pfn_pud(fop.pfn, prot));
 		entry = pud_mkspecial(entry);
 	}
 	if (write) {
@@ -1580,7 +1580,8 @@ static void insert_pud(struct vm_area_struct *vma, unsigned long addr,
  *
  * Return: vm_fault_t value.
  */
-vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
+vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, unsigned long pfn,
+			      bool write)
 {
 	unsigned long addr = vmf->address & PUD_MASK;
 	struct vm_area_struct *vma = vmf->vma;
@@ -1603,7 +1604,7 @@ vm_fault_t vmf_insert_pfn_pud(struct vm_fault *vmf, pfn_t pfn, bool write)
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return VM_FAULT_SIGBUS;
 
-	pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot);
+	pfnmap_setup_cachemode_pfn(pfn, &pgprot);
 
 	ptl = pud_lock(vma->vm_mm, vmf->pud);
 	insert_pud(vma, addr, vmf->pud, fop, pgprot, write);
diff --git a/mm/memory.c b/mm/memory.c
index e932a007af4c..0f9b32a20e5b 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -57,7 +57,6 @@
 #include <linux/export.h>
 #include <linux/delayacct.h>
 #include <linux/init.h>
-#include <linux/pfn_t.h>
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>
 #include <linux/mmu_notifier.h>
@@ -2435,7 +2434,7 @@ int vm_map_pages_zero(struct vm_area_struct *vma, struct page **pages,
 EXPORT_SYMBOL(vm_map_pages_zero);
 
 static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
-			pfn_t pfn, pgprot_t prot, bool mkwrite)
+			unsigned long pfn, pgprot_t prot, bool mkwrite)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	pte_t *pte, entry;
@@ -2457,7 +2456,7 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			 * allocation and mapping invalidation so just skip the
 			 * update.
 			 */
-			if (pte_pfn(entry) != pfn_t_to_pfn(pfn)) {
+			if (pte_pfn(entry) != pfn) {
 				WARN_ON_ONCE(!is_zero_pfn(pte_pfn(entry)));
 				goto out_unlock;
 			}
@@ -2470,7 +2469,7 @@ static vm_fault_t insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 	}
 
 	/* Ok, finally just insert the thing.. */
-	entry = pte_mkspecial(pfn_t_pte(pfn, prot));
+	entry = pte_mkspecial(pfn_pte(pfn, prot));
 
 	if (mkwrite) {
 		entry = pte_mkyoung(entry);
@@ -2541,8 +2540,7 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 
 	pfnmap_setup_cachemode_pfn(pfn, &pgprot);
 
-	return insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, 0), pgprot,
-			false);
+	return insert_pfn(vma, addr, pfn, pgprot, false);
 }
 EXPORT_SYMBOL(vmf_insert_pfn_prot);
 
@@ -2573,21 +2571,22 @@ vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 }
 EXPORT_SYMBOL(vmf_insert_pfn);
 
-static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn, bool mkwrite)
+static bool vm_mixed_ok(struct vm_area_struct *vma, unsigned long pfn,
+			bool mkwrite)
 {
-	if (unlikely(is_zero_pfn(pfn_t_to_pfn(pfn))) &&
+	if (unlikely(is_zero_pfn(pfn)) &&
 	    (mkwrite || !vm_mixed_zeropage_allowed(vma)))
 		return false;
 	/* these checks mirror the abort conditions in vm_normal_page */
 	if (vma->vm_flags & VM_MIXEDMAP)
 		return true;
-	if (is_zero_pfn(pfn_t_to_pfn(pfn)))
+	if (is_zero_pfn(pfn))
 		return true;
 	return false;
 }
 
 static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
-		unsigned long addr, pfn_t pfn, bool mkwrite)
+		unsigned long addr, unsigned long pfn, bool mkwrite)
 {
 	pgprot_t pgprot = vma->vm_page_prot;
 	int err;
@@ -2598,9 +2597,9 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return VM_FAULT_SIGBUS;
 
-	pfnmap_setup_cachemode_pfn(pfn_t_to_pfn(pfn), &pgprot);
+	pfnmap_setup_cachemode_pfn(pfn, &pgprot);
 
-	if (!pfn_modify_allowed(pfn_t_to_pfn(pfn), pgprot))
+	if (!pfn_modify_allowed(pfn, pgprot))
 		return VM_FAULT_SIGBUS;
 
 	/*
@@ -2610,7 +2609,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 	 * than insert_pfn).  If a zero_pfn were inserted into a VM_MIXEDMAP
 	 * without pte special, it would there be refcounted as a normal page.
 	 */
-	if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pfn_t_valid(pfn)) {
+	if (!IS_ENABLED(CONFIG_ARCH_HAS_PTE_SPECIAL) && pfn_valid(pfn)) {
 		struct page *page;
 
 		/*
@@ -2618,7 +2617,7 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 		 * regardless of whether the caller specified flags that
 		 * result in pfn_t_has_page() == false.
 		 */
-		page = pfn_to_page(pfn_t_to_pfn(pfn));
+		page = pfn_to_page(pfn);
 		err = insert_page(vma, addr, page, pgprot, mkwrite);
 	} else {
 		return insert_pfn(vma, addr, pfn, pgprot, mkwrite);
@@ -2653,7 +2652,7 @@ vm_fault_t vmf_insert_page_mkwrite(struct vm_fault *vmf, struct page *page,
 EXPORT_SYMBOL_GPL(vmf_insert_page_mkwrite);
 
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-		pfn_t pfn)
+		unsigned long pfn)
 {
 	return __vm_insert_mixed(vma, addr, pfn, false);
 }
@@ -2665,7 +2664,7 @@ EXPORT_SYMBOL(vmf_insert_mixed);
  *  the same entry was actually inserted.
  */
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
-		unsigned long addr, pfn_t pfn)
+		unsigned long addr, unsigned long pfn)
 {
 	return __vm_insert_mixed(vma, addr, pfn, true);
 }
diff --git a/mm/memremap.c b/mm/memremap.c
index c17e0a69cace..044a4550671a 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -5,7 +5,6 @@
 #include <linux/kasan.h>
 #include <linux/memory_hotplug.h>
 #include <linux/memremap.h>
-#include <linux/pfn_t.h>
 #include <linux/swap.h>
 #include <linux/mm.h>
 #include <linux/mmzone.h>
diff --git a/mm/migrate.c b/mm/migrate.c
index 8cf0f9c9599d..ea8c74d99659 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -35,7 +35,6 @@
 #include <linux/compat.h>
 #include <linux/hugetlb.h>
 #include <linux/gfp.h>
-#include <linux/pfn_t.h>
 #include <linux/page_idle.h>
 #include <linux/page_owner.h>
 #include <linux/sched/mm.h>
diff --git a/tools/testing/nvdimm/pmem-dax.c b/tools/testing/nvdimm/pmem-dax.c
index c1ec099a3b1d..05e763aab104 100644
--- a/tools/testing/nvdimm/pmem-dax.c
+++ b/tools/testing/nvdimm/pmem-dax.c
@@ -10,7 +10,7 @@
 
 long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
 		long nr_pages, enum dax_access_mode mode, void **kaddr,
-		pfn_t *pfn)
+		unsigned long *pfn)
 {
 	resource_size_t offset = PFN_PHYS(pgoff) + pmem->data_offset;
 
@@ -29,7 +29,7 @@ long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
 			*kaddr = pmem->virt_addr + offset;
 		page = vmalloc_to_page(pmem->virt_addr + offset);
 		if (pfn)
-			*pfn = page_to_pfn_t(page);
+			*pfn = page_to_pfn(page);
 		pr_debug_ratelimited("%s: pmem: %p pgoff: %#lx pfn: %#lx\n",
 				__func__, pmem, pgoff, page_to_pfn(page));
 
@@ -39,7 +39,7 @@ long __pmem_direct_access(struct pmem_device *pmem, pgoff_t pgoff,
 	if (kaddr)
 		*kaddr = pmem->virt_addr + offset;
 	if (pfn)
-		*pfn = phys_to_pfn_t(pmem->phys_addr + offset, pmem->pfn_flags);
+		*pfn = PHYS_PFN(pmem->phys_addr + offset);
 
 	/*
 	 * If badblocks are present, limit known good range to the
diff --git a/tools/testing/nvdimm/test/iomap.c b/tools/testing/nvdimm/test/iomap.c
index ddceb04b4a9a..f7e7bfe9bb85 100644
--- a/tools/testing/nvdimm/test/iomap.c
+++ b/tools/testing/nvdimm/test/iomap.c
@@ -8,7 +8,6 @@
 #include <linux/ioport.h>
 #include <linux/module.h>
 #include <linux/types.h>
-#include <linux/pfn_t.h>
 #include <linux/acpi.h>
 #include <linux/io.h>
 #include <linux/mm.h>
@@ -135,12 +134,6 @@ void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap)
 }
 EXPORT_SYMBOL_GPL(__wrap_devm_memremap_pages);
 
-pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags)
-{
-        return phys_to_pfn_t(addr, flags);
-}
-EXPORT_SYMBOL(__wrap_phys_to_pfn_t);
-
 void *__wrap_memremap(resource_size_t offset, size_t size,
 		unsigned long flags)
 {
diff --git a/tools/testing/nvdimm/test/nfit_test.h b/tools/testing/nvdimm/test/nfit_test.h
index b00583d1eace..b9047fb8ea4a 100644
--- a/tools/testing/nvdimm/test/nfit_test.h
+++ b/tools/testing/nvdimm/test/nfit_test.h
@@ -212,7 +212,6 @@ void __iomem *__wrap_devm_ioremap(struct device *dev,
 void *__wrap_devm_memremap(struct device *dev, resource_size_t offset,
 		size_t size, unsigned long flags);
 void *__wrap_devm_memremap_pages(struct device *dev, struct dev_pagemap *pgmap);
-pfn_t __wrap_phys_to_pfn_t(phys_addr_t addr, unsigned long flags);
 void *__wrap_memremap(resource_size_t offset, size_t size,
 		unsigned long flags);
 void __wrap_devm_memunmap(struct device *dev, void *addr);
-- 
cgit v1.2.3


From 50b4233a22b1ee9ccd0e847597de66ce21329ddb Mon Sep 17 00:00:00 2001
From: Julian Vetter <julian@outer-limits.org>
Date: Tue, 3 Jun 2025 15:21:21 +0200
Subject: include/linux/jhash.h: replace __get_unaligned_cpu32 in jhash
 function

__get_unaligned_cpu32() is deprecated.  So, replace it with the more
generic get_unaligned() and just cast the input parameter.

Link: https://lkml.kernel.org/r/20250603132121.3674066-1-julian@outer-limits.org
Signed-off-by: Julian Vetter <julian@outer-limits.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Wei-Hsin Yeh <weihsinyeh168@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/jhash.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/jhash.h b/include/linux/jhash.h
index fa26a2dd3b52..7c1c1821c694 100644
--- a/include/linux/jhash.h
+++ b/include/linux/jhash.h
@@ -24,7 +24,7 @@
  * Jozsef
  */
 #include <linux/bitops.h>
-#include <linux/unaligned/packed_struct.h>
+#include <linux/unaligned.h>
 
 /* Best hash sizes are of power of two */
 #define jhash_size(n)   ((u32)1<<(n))
@@ -77,9 +77,9 @@ static inline u32 jhash(const void *key, u32 length, u32 initval)
 
 	/* All but the last block: affect some 32 bits of (a,b,c) */
 	while (length > 12) {
-		a += __get_unaligned_cpu32(k);
-		b += __get_unaligned_cpu32(k + 4);
-		c += __get_unaligned_cpu32(k + 8);
+		a += get_unaligned((u32 *)k);
+		b += get_unaligned((u32 *)(k + 4));
+		c += get_unaligned((u32 *)(k + 8));
 		__jhash_mix(a, b, c);
 		length -= 12;
 		k += 12;
-- 
cgit v1.2.3


From 2489e958129ff7cbf26a34ee33cdc9ccbd68fe3c Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Thu, 12 Jun 2025 14:11:57 +0800
Subject: relayfs: abolish prev_padding

Patch series "relayfs: misc changes", v5.

The series mostly focuses on the error counters which helps every user
debug their own kernel module.


This patch (of 5):

prev_padding represents the unused space of certain subbuffer.  If the
content of a call of relay_write() exceeds the limit of the remainder of
this subbuffer, it will skip storing in the rest space and record the
start point as buf->prev_padding in relay_switch_subbuf().  Since the buf
is a per-cpu big buffer, the point of prev_padding as a global value for
the whole buffer instead of a single subbuffer (whose padding info is
stored in buf->padding[]) seems meaningless from the real use cases, so we
don't bother to record it any more.

Link: https://lkml.kernel.org/r/20250612061201.34272-1-kerneljasonxing@gmail.com
Link: https://lkml.kernel.org/r/20250612061201.34272-2-kerneljasonxing@gmail.com
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Yushan Zhou <katrinzhou@tencent.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/gpu/drm/i915/gt/uc/intel_guc_log.c |  3 +--
 drivers/net/wwan/iosm/iosm_ipc_trace.c     |  3 +--
 drivers/net/wwan/t7xx/t7xx_port_trace.c    |  2 +-
 include/linux/relay.h                      |  5 +----
 kernel/relay.c                             | 14 ++++++++------
 kernel/trace/blktrace.c                    |  2 +-
 6 files changed, 13 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
index e8a04e476c57..09a64f224c49 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_log.c
@@ -220,8 +220,7 @@ static int guc_action_control_log(struct intel_guc *guc, bool enable,
  */
 static int subbuf_start_callback(struct rchan_buf *buf,
 				 void *subbuf,
-				 void *prev_subbuf,
-				 size_t prev_padding)
+				 void *prev_subbuf)
 {
 	/*
 	 * Use no-overwrite mode by default, where relay will stop accepting
diff --git a/drivers/net/wwan/iosm/iosm_ipc_trace.c b/drivers/net/wwan/iosm/iosm_ipc_trace.c
index eeecfa3d10c5..9656254c1c6c 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_trace.c
+++ b/drivers/net/wwan/iosm/iosm_ipc_trace.c
@@ -51,8 +51,7 @@ static int ipc_trace_remove_buf_file_handler(struct dentry *dentry)
 }
 
 static int ipc_trace_subbuf_start_handler(struct rchan_buf *buf, void *subbuf,
-					  void *prev_subbuf,
-					  size_t prev_padding)
+					  void *prev_subbuf)
 {
 	if (relay_buf_full(buf)) {
 		pr_err_ratelimited("Relay_buf full dropping traces");
diff --git a/drivers/net/wwan/t7xx/t7xx_port_trace.c b/drivers/net/wwan/t7xx/t7xx_port_trace.c
index 4ed8b4e29bf1..f16d3b01302c 100644
--- a/drivers/net/wwan/t7xx/t7xx_port_trace.c
+++ b/drivers/net/wwan/t7xx/t7xx_port_trace.c
@@ -33,7 +33,7 @@ static int t7xx_trace_remove_buf_file_handler(struct dentry *dentry)
 }
 
 static int t7xx_trace_subbuf_start_handler(struct rchan_buf *buf, void *subbuf,
-					   void *prev_subbuf, size_t prev_padding)
+					   void *prev_subbuf)
 {
 	if (relay_buf_full(buf)) {
 		pr_err_ratelimited("Relay_buf full dropping traces");
diff --git a/include/linux/relay.h b/include/linux/relay.h
index b3224111d074..e10a0fdf4325 100644
--- a/include/linux/relay.h
+++ b/include/linux/relay.h
@@ -47,7 +47,6 @@ struct rchan_buf
 	unsigned int page_count;	/* number of current buffer pages */
 	unsigned int finalized;		/* buffer has been finalized */
 	size_t *padding;		/* padding counts per sub-buffer */
-	size_t prev_padding;		/* temporary variable */
 	size_t bytes_consumed;		/* bytes consumed in cur read subbuf */
 	size_t early_bytes;		/* bytes consumed before VFS inited */
 	unsigned int cpu;		/* this buf's cpu */
@@ -84,7 +83,6 @@ struct rchan_callbacks
 	 * @buf: the channel buffer containing the new sub-buffer
 	 * @subbuf: the start of the new sub-buffer
 	 * @prev_subbuf: the start of the previous sub-buffer
-	 * @prev_padding: unused space at the end of previous sub-buffer
 	 *
 	 * The client should return 1 to continue logging, 0 to stop
 	 * logging.
@@ -100,8 +98,7 @@ struct rchan_callbacks
 	 */
 	int (*subbuf_start) (struct rchan_buf *buf,
 			     void *subbuf,
-			     void *prev_subbuf,
-			     size_t prev_padding);
+			     void *prev_subbuf);
 
 	/*
 	 * create_buf_file - create file to represent a relay channel buffer
diff --git a/kernel/relay.c b/kernel/relay.c
index 3ee5b038d0d9..fc6ad76b789d 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -249,13 +249,13 @@ EXPORT_SYMBOL_GPL(relay_buf_full);
  */
 
 static int relay_subbuf_start(struct rchan_buf *buf, void *subbuf,
-			      void *prev_subbuf, size_t prev_padding)
+			      void *prev_subbuf)
 {
 	if (!buf->chan->cb->subbuf_start)
 		return !relay_buf_full(buf);
 
 	return buf->chan->cb->subbuf_start(buf, subbuf,
-					   prev_subbuf, prev_padding);
+					   prev_subbuf);
 }
 
 /**
@@ -301,7 +301,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init)
 	for (i = 0; i < buf->chan->n_subbufs; i++)
 		buf->padding[i] = 0;
 
-	relay_subbuf_start(buf, buf->data, NULL, 0);
+	relay_subbuf_start(buf, buf->data, NULL);
 }
 
 /**
@@ -554,9 +554,11 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 		goto toobig;
 
 	if (buf->offset != buf->chan->subbuf_size + 1) {
-		buf->prev_padding = buf->chan->subbuf_size - buf->offset;
+		size_t prev_padding;
+
+		prev_padding = buf->chan->subbuf_size - buf->offset;
 		old_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
-		buf->padding[old_subbuf] = buf->prev_padding;
+		buf->padding[old_subbuf] = prev_padding;
 		buf->subbufs_produced++;
 		if (buf->dentry)
 			d_inode(buf->dentry)->i_size +=
@@ -581,7 +583,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 	new_subbuf = buf->subbufs_produced % buf->chan->n_subbufs;
 	new = buf->start + new_subbuf * buf->chan->subbuf_size;
 	buf->offset = 0;
-	if (!relay_subbuf_start(buf, new, old, buf->prev_padding)) {
+	if (!relay_subbuf_start(buf, new, old)) {
 		buf->offset = buf->chan->subbuf_size + 1;
 		return 0;
 	}
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 3f6a7bdc6edf..d3083c88474e 100644
--- a/kernel/trace/blktrace.c
+++ b/kernel/trace/blktrace.c
@@ -461,7 +461,7 @@ static const struct file_operations blk_msg_fops = {
  * the user space app in telling how many lost events there were.
  */
 static int blk_subbuf_start_callback(struct rchan_buf *buf, void *subbuf,
-				     void *prev_subbuf, size_t prev_padding)
+				     void *prev_subbuf)
 {
 	struct blk_trace *bt;
 
-- 
cgit v1.2.3


From ca01a90ae7bf9bb22137e719366bdc0f387675c2 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Thu, 12 Jun 2025 14:11:58 +0800
Subject: relayfs: support a counter tracking if per-cpu buffers is full

When using relay mechanism, we often encounter the case where new data are
lost or old unconsumed data are overwritten because of slow reader.

Add 'full' field in per-cpu buffer structure to detect if the above case
is happening.  Relay has two modes: 1) non-overwrite mode, 2) overwrite
mode.  So buffer being full here respectively means: 1) relayfs doesn't
intend to accept new data and then simply drop them, or 2) relayfs is
going to start over again and overwrite old unread data with new data.

Note: this counter doesn't need any explicit lock to protect from being
modified by different threads for the better performance consideration.
Writers calling __relay_write/relay_write should consider how to use the
lock and ensure it performs under the lock protection, thus it's not
necessary to add a new small lock here.

Link: https://lkml.kernel.org/r/20250612061201.34272-3-kerneljasonxing@gmail.com
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Yushan Zhou <katrinzhou@tencent.com>
Reviewed-by: Jens Axboe <axboe@kernel.dk>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/relay.h | 9 +++++++++
 kernel/relay.c        | 8 +++++++-
 2 files changed, 16 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/relay.h b/include/linux/relay.h
index e10a0fdf4325..cd77eb285a48 100644
--- a/include/linux/relay.h
+++ b/include/linux/relay.h
@@ -28,6 +28,14 @@
  */
 #define RELAYFS_CHANNEL_VERSION		7
 
+/*
+ * Relay buffer statistics
+ */
+struct rchan_buf_stats
+{
+	unsigned int full_count;	/* counter for buffer full */
+};
+
 /*
  * Per-cpu relay channel buffer
  */
@@ -43,6 +51,7 @@ struct rchan_buf
 	struct irq_work wakeup_work;	/* reader wakeup */
 	struct dentry *dentry;		/* channel file dentry */
 	struct kref kref;		/* channel buffer refcount */
+	struct rchan_buf_stats stats;	/* buffer stats */
 	struct page **page_array;	/* array of current buffer pages */
 	unsigned int page_count;	/* number of current buffer pages */
 	unsigned int finalized;		/* buffer has been finalized */
diff --git a/kernel/relay.c b/kernel/relay.c
index fc6ad76b789d..4b07efddc2cf 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -251,8 +251,13 @@ EXPORT_SYMBOL_GPL(relay_buf_full);
 static int relay_subbuf_start(struct rchan_buf *buf, void *subbuf,
 			      void *prev_subbuf)
 {
+	int full = relay_buf_full(buf);
+
+	if (full)
+		buf->stats.full_count++;
+
 	if (!buf->chan->cb->subbuf_start)
-		return !relay_buf_full(buf);
+		return !full;
 
 	return buf->chan->cb->subbuf_start(buf, subbuf,
 					   prev_subbuf);
@@ -297,6 +302,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init)
 	buf->finalized = 0;
 	buf->data = buf->start;
 	buf->offset = 0;
+	buf->stats.full_count = 0;
 
 	for (i = 0; i < buf->chan->n_subbufs; i++)
 		buf->padding[i] = 0;
-- 
cgit v1.2.3


From a53202ce7fbafd24f854865b02eff891e246c550 Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Thu, 12 Jun 2025 14:11:59 +0800
Subject: relayfs: introduce getting relayfs statistics function

In this version, only support getting the counter for buffer full and
implement the framework of how it works.

Users can pass certain flag to fetch what field/statistics they expect to
know.  Each time it only returns one result.  So do not pass multiple
flags.

Link: https://lkml.kernel.org/r/20250612061201.34272-4-kerneljasonxing@gmail.com
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Yushan Zhou <katrinzhou@tencent.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/relay.h |  7 +++++++
 kernel/relay.c        | 30 ++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/relay.h b/include/linux/relay.h
index cd77eb285a48..5310967f9d74 100644
--- a/include/linux/relay.h
+++ b/include/linux/relay.h
@@ -31,6 +31,12 @@
 /*
  * Relay buffer statistics
  */
+enum {
+	RELAY_STATS_BUF_FULL = (1 << 0),
+
+	RELAY_STATS_LAST = RELAY_STATS_BUF_FULL,
+};
+
 struct rchan_buf_stats
 {
 	unsigned int full_count;	/* counter for buffer full */
@@ -167,6 +173,7 @@ struct rchan *relay_open(const char *base_filename,
 			 void *private_data);
 extern void relay_close(struct rchan *chan);
 extern void relay_flush(struct rchan *chan);
+size_t relay_stats(struct rchan *chan, int flags);
 extern void relay_subbufs_consumed(struct rchan *chan,
 				   unsigned int cpu,
 				   size_t consumed);
diff --git a/kernel/relay.c b/kernel/relay.c
index 4b07efddc2cf..2fc27c0e771e 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -700,6 +700,36 @@ void relay_flush(struct rchan *chan)
 }
 EXPORT_SYMBOL_GPL(relay_flush);
 
+/**
+ *	relay_stats - get channel buffer statistics
+ *	@chan: the channel
+ *	@flags: select particular information to get
+ *
+ *	Returns the count of certain field that caller specifies.
+ */
+size_t relay_stats(struct rchan *chan, int flags)
+{
+	unsigned int i, count = 0;
+	struct rchan_buf *rbuf;
+
+	if (!chan || flags > RELAY_STATS_LAST)
+		return 0;
+
+	if (chan->is_global) {
+		rbuf = *per_cpu_ptr(chan->buf, 0);
+		if (flags & RELAY_STATS_BUF_FULL)
+			count = rbuf->stats.full_count;
+	} else {
+		for_each_online_cpu(i) {
+			rbuf = *per_cpu_ptr(chan->buf, i);
+			if (rbuf && flags & RELAY_STATS_BUF_FULL)
+				count += rbuf->stats.full_count;
+		}
+	}
+
+	return count;
+}
+
 /**
  *	relay_file_open - open file op for relay files
  *	@inode: the inode
-- 
cgit v1.2.3


From 19f3cb64a25b80db667a00182785577fae465b3e Mon Sep 17 00:00:00 2001
From: Jason Xing <kernelxing@tencent.com>
Date: Thu, 12 Jun 2025 14:12:01 +0800
Subject: relayfs: support a counter tracking if data is too big to write

It really doesn't matter if the user/admin knows what the last too big
value is.  Record how many times this case is triggered would be helpful.

Solve the existing issue where relay_reset() doesn't restore the value.

Store the counter in the per-cpu buffer structure instead of the global
buffer structure.  It also solves the racy condition which is likely to
happen when a few of per-cpu buffers encounter the too big data case and
then access the global field last_toobig without lock protection.

Remove the printk in relay_close() since kernel module can directly call
relay_stats() as they want.

Link: https://lkml.kernel.org/r/20250612061201.34272-6-kerneljasonxing@gmail.com
Signed-off-by: Jason Xing <kernelxing@tencent.com>
Reviewed-by: Yushan Zhou <katrinzhou@tencent.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/relay.h |  5 +++--
 kernel/relay.c        | 18 ++++++++++--------
 2 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/relay.h b/include/linux/relay.h
index 5310967f9d74..6772a7075840 100644
--- a/include/linux/relay.h
+++ b/include/linux/relay.h
@@ -33,13 +33,15 @@
  */
 enum {
 	RELAY_STATS_BUF_FULL = (1 << 0),
+	RELAY_STATS_WRT_BIG = (1 << 1),
 
-	RELAY_STATS_LAST = RELAY_STATS_BUF_FULL,
+	RELAY_STATS_LAST = RELAY_STATS_WRT_BIG,
 };
 
 struct rchan_buf_stats
 {
 	unsigned int full_count;	/* counter for buffer full */
+	unsigned int big_count;		/* counter for too big to write */
 };
 
 /*
@@ -79,7 +81,6 @@ struct rchan
 	const struct rchan_callbacks *cb; /* client callbacks */
 	struct kref kref;		/* channel refcount */
 	void *private_data;		/* for user-defined data */
-	size_t last_toobig;		/* tried to log event > subbuf size */
 	struct rchan_buf * __percpu *buf; /* per-cpu channel buffers */
 	int is_global;			/* One global buffer ? */
 	struct list_head list;		/* for channel list */
diff --git a/kernel/relay.c b/kernel/relay.c
index 2fc27c0e771e..8d915fe98198 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -303,6 +303,7 @@ static void __relay_reset(struct rchan_buf *buf, unsigned int init)
 	buf->data = buf->start;
 	buf->offset = 0;
 	buf->stats.full_count = 0;
+	buf->stats.big_count = 0;
 
 	for (i = 0; i < buf->chan->n_subbufs; i++)
 		buf->padding[i] = 0;
@@ -602,7 +603,7 @@ size_t relay_switch_subbuf(struct rchan_buf *buf, size_t length)
 	return length;
 
 toobig:
-	buf->chan->last_toobig = length;
+	buf->stats.big_count++;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(relay_switch_subbuf);
@@ -662,11 +663,6 @@ void relay_close(struct rchan *chan)
 			if ((buf = *per_cpu_ptr(chan->buf, i)))
 				relay_close_buf(buf);
 
-	if (chan->last_toobig)
-		printk(KERN_WARNING "relay: one or more items not logged "
-		       "[item size (%zd) > sub-buffer size (%zd)]\n",
-		       chan->last_toobig, chan->subbuf_size);
-
 	list_del(&chan->list);
 	kref_put(&chan->kref, relay_destroy_channel);
 	mutex_unlock(&relay_channels_mutex);
@@ -719,11 +715,17 @@ size_t relay_stats(struct rchan *chan, int flags)
 		rbuf = *per_cpu_ptr(chan->buf, 0);
 		if (flags & RELAY_STATS_BUF_FULL)
 			count = rbuf->stats.full_count;
+		else if (flags & RELAY_STATS_WRT_BIG)
+			count = rbuf->stats.big_count;
 	} else {
 		for_each_online_cpu(i) {
 			rbuf = *per_cpu_ptr(chan->buf, i);
-			if (rbuf && flags & RELAY_STATS_BUF_FULL)
-				count += rbuf->stats.full_count;
+			if (rbuf) {
+				if (flags & RELAY_STATS_BUF_FULL)
+					count += rbuf->stats.full_count;
+				else if (flags & RELAY_STATS_WRT_BIG)
+					count += rbuf->stats.big_count;
+			}
 		}
 	}
 
-- 
cgit v1.2.3


From 1857fcc847443b0238cb64584b43d8c3a9049a0a Mon Sep 17 00:00:00 2001
From: Herbert Xu <herbert@gondor.apana.org.au>
Date: Mon, 17 Mar 2025 17:02:28 +0800
Subject: lib/raid6: replace custom zero page with ZERO_PAGE

Use the system-wide zero page instead of a custom zero page.

[herbert@gondor.apana.org.au: update lib/raid6/recov_rvv.c, per Klara]
  Link: https://lkml.kernel.org/r/aFkUnXWtxcgOTVkw@gondor.apana.org.au
Link: https://lkml.kernel.org/r/Z9flJNkWQICx0PXk@gondor.apana.org.au
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Song Liu <song@kernel.org>
Cc: Yu Kuai <yukuai3@huawei.com>
Cc: Klara Modin <klarasmodin@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 crypto/async_tx/async_pq.c          |  2 +-
 crypto/async_tx/async_raid6_recov.c |  4 ++--
 include/linux/raid/pq.h             | 12 +++++++++++-
 lib/raid6/algos.c                   |  3 ---
 lib/raid6/recov.c                   |  6 +++---
 lib/raid6/recov_avx2.c              |  6 +++---
 lib/raid6/recov_avx512.c            |  6 +++---
 lib/raid6/recov_loongarch_simd.c    | 12 ++++++------
 lib/raid6/recov_neon.c              |  6 +++---
 lib/raid6/recov_s390xc.c            |  6 +++---
 lib/raid6/recov_ssse3.c             |  6 +++---
 11 files changed, 38 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/crypto/async_tx/async_pq.c b/crypto/async_tx/async_pq.c
index 5e2b2680d7db..9e4bb7fbde25 100644
--- a/crypto/async_tx/async_pq.c
+++ b/crypto/async_tx/async_pq.c
@@ -119,7 +119,7 @@ do_sync_gen_syndrome(struct page **blocks, unsigned int *offsets, int disks,
 	for (i = 0; i < disks; i++) {
 		if (blocks[i] == NULL) {
 			BUG_ON(i > disks - 3); /* P or Q can't be zero */
-			srcs[i] = (void*)raid6_empty_zero_page;
+			srcs[i] = raid6_get_zero_page();
 		} else {
 			srcs[i] = page_address(blocks[i]) + offsets[i];
 
diff --git a/crypto/async_tx/async_raid6_recov.c b/crypto/async_tx/async_raid6_recov.c
index 354b8cd5537f..539ea5b378dc 100644
--- a/crypto/async_tx/async_raid6_recov.c
+++ b/crypto/async_tx/async_raid6_recov.c
@@ -414,7 +414,7 @@ async_raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 		async_tx_quiesce(&submit->depend_tx);
 		for (i = 0; i < disks; i++)
 			if (blocks[i] == NULL)
-				ptrs[i] = (void *) raid6_empty_zero_page;
+				ptrs[i] = raid6_get_zero_page();
 			else
 				ptrs[i] = page_address(blocks[i]) + offs[i];
 
@@ -497,7 +497,7 @@ async_raid6_datap_recov(int disks, size_t bytes, int faila,
 		async_tx_quiesce(&submit->depend_tx);
 		for (i = 0; i < disks; i++)
 			if (blocks[i] == NULL)
-				ptrs[i] = (void*)raid6_empty_zero_page;
+				ptrs[i] = raid6_get_zero_page();
 			else
 				ptrs[i] = page_address(blocks[i]) + offs[i];
 
diff --git a/include/linux/raid/pq.h b/include/linux/raid/pq.h
index 72ff44cca864..2467b3be15c9 100644
--- a/include/linux/raid/pq.h
+++ b/include/linux/raid/pq.h
@@ -11,8 +11,13 @@
 #ifdef __KERNEL__
 
 #include <linux/blkdev.h>
+#include <linux/mm.h>
 
-extern const char raid6_empty_zero_page[PAGE_SIZE];
+/* This should be const but the raid6 code is too convoluted for that. */
+static inline void *raid6_get_zero_page(void)
+{
+	return page_address(ZERO_PAGE(0));
+}
 
 #else /* ! __KERNEL__ */
 /* Used for testing in user space */
@@ -191,6 +196,11 @@ static inline uint32_t raid6_jiffies(void)
 	return tv.tv_sec*1000 + tv.tv_usec/1000;
 }
 
+static inline void *raid6_get_zero_page(void)
+{
+	return raid6_empty_zero_page;
+}
+
 #endif /* ! __KERNEL__ */
 
 #endif /* LINUX_RAID_RAID6_H */
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index 75ce3e134b7c..799e0e5eac26 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -18,9 +18,6 @@
 #else
 #include <linux/module.h>
 #include <linux/gfp.h>
-/* In .bss so it's zeroed */
-const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
-EXPORT_SYMBOL(raid6_empty_zero_page);
 #endif
 
 struct raid6_calls raid6_call;
diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c
index a7c1b2bbe40d..b5e47c008b41 100644
--- a/lib/raid6/recov.c
+++ b/lib/raid6/recov.c
@@ -31,10 +31,10 @@ static void raid6_2data_recov_intx1(int disks, size_t bytes, int faila,
 	   Use the dead data pages as temporary storage for
 	   delta p and delta q */
 	dp = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-2] = dp;
 	dq = (u8 *)ptrs[failb];
-	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[failb] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -72,7 +72,7 @@ static void raid6_datap_recov_intx1(int disks, size_t bytes, int faila,
 	/* Compute syndrome with zero for the missing data page
 	   Use the dead data page as temporary storage for delta q */
 	dq = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
diff --git a/lib/raid6/recov_avx2.c b/lib/raid6/recov_avx2.c
index 4e8095403ee2..97d598d2535c 100644
--- a/lib/raid6/recov_avx2.c
+++ b/lib/raid6/recov_avx2.c
@@ -28,10 +28,10 @@ static void raid6_2data_recov_avx2(int disks, size_t bytes, int faila,
 	   Use the dead data pages as temporary storage for
 	   delta p and delta q */
 	dp = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-2] = dp;
 	dq = (u8 *)ptrs[failb];
-	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[failb] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -196,7 +196,7 @@ static void raid6_datap_recov_avx2(int disks, size_t bytes, int faila,
 	/* Compute syndrome with zero for the missing data page
 	   Use the dead data page as temporary storage for delta q */
 	dq = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
diff --git a/lib/raid6/recov_avx512.c b/lib/raid6/recov_avx512.c
index 310c715db313..7986120ca444 100644
--- a/lib/raid6/recov_avx512.c
+++ b/lib/raid6/recov_avx512.c
@@ -37,10 +37,10 @@ static void raid6_2data_recov_avx512(int disks, size_t bytes, int faila,
 	 */
 
 	dp = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-2] = dp;
 	dq = (u8 *)ptrs[failb];
-	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[failb] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -238,7 +238,7 @@ static void raid6_datap_recov_avx512(int disks, size_t bytes, int faila,
 	 */
 
 	dq = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
diff --git a/lib/raid6/recov_loongarch_simd.c b/lib/raid6/recov_loongarch_simd.c
index 94aeac85e6f7..93dc515997a1 100644
--- a/lib/raid6/recov_loongarch_simd.c
+++ b/lib/raid6/recov_loongarch_simd.c
@@ -42,10 +42,10 @@ static void raid6_2data_recov_lsx(int disks, size_t bytes, int faila,
 	 * delta p and delta q
 	 */
 	dp = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks - 2] = dp;
 	dq = (u8 *)ptrs[failb];
-	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[failb] = raid6_get_zero_page();
 	ptrs[disks - 1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -197,7 +197,7 @@ static void raid6_datap_recov_lsx(int disks, size_t bytes, int faila,
 	 * Use the dead data page as temporary storage for delta q
 	 */
 	dq = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks - 1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -316,10 +316,10 @@ static void raid6_2data_recov_lasx(int disks, size_t bytes, int faila,
 	 * delta p and delta q
 	 */
 	dp = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks - 2] = dp;
 	dq = (u8 *)ptrs[failb];
-	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[failb] = raid6_get_zero_page();
 	ptrs[disks - 1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -436,7 +436,7 @@ static void raid6_datap_recov_lasx(int disks, size_t bytes, int faila,
 	 * Use the dead data page as temporary storage for delta q
 	 */
 	dq = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks - 1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
diff --git a/lib/raid6/recov_neon.c b/lib/raid6/recov_neon.c
index 1bfc14174d4d..70e1404c1512 100644
--- a/lib/raid6/recov_neon.c
+++ b/lib/raid6/recov_neon.c
@@ -36,10 +36,10 @@ static void raid6_2data_recov_neon(int disks, size_t bytes, int faila,
 	 * delta p and delta q
 	 */
 	dp = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks - 2] = dp;
 	dq = (u8 *)ptrs[failb];
-	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[failb] = raid6_get_zero_page();
 	ptrs[disks - 1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -74,7 +74,7 @@ static void raid6_datap_recov_neon(int disks, size_t bytes, int faila,
 	 * Use the dead data page as temporary storage for delta q
 	 */
 	dq = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks - 1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
diff --git a/lib/raid6/recov_s390xc.c b/lib/raid6/recov_s390xc.c
index 179eec900cea..1d32c01261be 100644
--- a/lib/raid6/recov_s390xc.c
+++ b/lib/raid6/recov_s390xc.c
@@ -35,10 +35,10 @@ static void raid6_2data_recov_s390xc(int disks, size_t bytes, int faila,
 	   Use the dead data pages as temporary storage for
 	   delta p and delta q */
 	dp = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-2] = dp;
 	dq = (u8 *)ptrs[failb];
-	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[failb] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -82,7 +82,7 @@ static void raid6_datap_recov_s390xc(int disks, size_t bytes, int faila,
 	/* Compute syndrome with zero for the missing data page
 	   Use the dead data page as temporary storage for delta q */
 	dq = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c
index 4bfa3c6b60de..2e849185c32b 100644
--- a/lib/raid6/recov_ssse3.c
+++ b/lib/raid6/recov_ssse3.c
@@ -30,10 +30,10 @@ static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila,
 	   Use the dead data pages as temporary storage for
 	   delta p and delta q */
 	dp = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-2] = dp;
 	dq = (u8 *)ptrs[failb];
-	ptrs[failb] = (void *)raid6_empty_zero_page;
+	ptrs[failb] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
@@ -203,7 +203,7 @@ static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila,
 	/* Compute syndrome with zero for the missing data page
 	   Use the dead data page as temporary storage for delta q */
 	dq = (u8 *)ptrs[faila];
-	ptrs[faila] = (void *)raid6_empty_zero_page;
+	ptrs[faila] = raid6_get_zero_page();
 	ptrs[disks-1] = dq;
 
 	raid6_call.gen_syndrome(disks, bytes, ptrs);
-- 
cgit v1.2.3


From 76fdb7eb4e1c91086ce9c3db6972c2ed48c96afb Mon Sep 17 00:00:00 2001
From: Aleksa Sarai <cyphar@cyphar.com>
Date: Tue, 8 Jul 2025 23:21:51 +1000
Subject: uapi: export PROCFS_ROOT_INO

The root inode of /proc having a fixed inode number has been part of the
core kernel ABI since its inception, and recently some userspace
programs (mainly container runtimes) have started to explicitly depend
on this behaviour.

The main reason this is useful to userspace is that by checking that a
suspect /proc handle has fstype PROC_SUPER_MAGIC and is PROCFS_ROOT_INO,
they can then use openat2(RESOLVE_{NO_{XDEV,MAGICLINK},BENEATH}) to
ensure that there isn't a bind-mount that replaces some procfs file with
a different one. This kind of attack has lead to security issues in
container runtimes in the past (such as CVE-2019-19921) and libraries
like libpathrs[1] use this feature of procfs to provide safe procfs
handling functions.

There was also some trailing whitespace in the "struct proc_dir_entry"
initialiser, so fix that up as well.

[1]: https://github.com/openSUSE/libpathrs

Signed-off-by: Aleksa Sarai <cyphar@cyphar.com>
Link: https://lore.kernel.org/20250708-uapi-procfs-root-ino-v1-1-6ae61e97c79b@cyphar.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/proc/root.c          | 10 +++++-----
 include/linux/proc_ns.h |  1 -
 include/uapi/linux/fs.h | 11 +++++++++++
 3 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/root.c b/fs/proc/root.c
index 06a297a27ba3..ed86ac710384 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -363,12 +363,12 @@ static const struct inode_operations proc_root_inode_operations = {
  * This is the root "inode" in the /proc tree..
  */
 struct proc_dir_entry proc_root = {
-	.low_ino	= PROC_ROOT_INO, 
-	.namelen	= 5, 
-	.mode		= S_IFDIR | S_IRUGO | S_IXUGO, 
-	.nlink		= 2, 
+	.low_ino	= PROCFS_ROOT_INO,
+	.namelen	= 5,
+	.mode		= S_IFDIR | S_IRUGO | S_IXUGO,
+	.nlink		= 2,
 	.refcnt		= REFCOUNT_INIT(1),
-	.proc_iops	= &proc_root_inode_operations, 
+	.proc_iops	= &proc_root_inode_operations,
 	.proc_dir_ops	= &proc_root_operations,
 	.parent		= &proc_root,
 	.subdir		= RB_ROOT,
diff --git a/include/linux/proc_ns.h b/include/linux/proc_ns.h
index 6258455e49a4..4b20375f3783 100644
--- a/include/linux/proc_ns.h
+++ b/include/linux/proc_ns.h
@@ -40,7 +40,6 @@ extern const struct proc_ns_operations timens_for_children_operations;
  * We always define these enumerators
  */
 enum {
-	PROC_ROOT_INO		= 1,
 	PROC_IPC_INIT_INO	= IPC_NS_INIT_INO,
 	PROC_UTS_INIT_INO	= UTS_NS_INIT_INO,
 	PROC_USER_INIT_INO	= USER_NS_INIT_INO,
diff --git a/include/uapi/linux/fs.h b/include/uapi/linux/fs.h
index 0098b0ce8ccb..28238a3edbc1 100644
--- a/include/uapi/linux/fs.h
+++ b/include/uapi/linux/fs.h
@@ -60,6 +60,17 @@
 #define RENAME_EXCHANGE		(1 << 1)	/* Exchange source and dest */
 #define RENAME_WHITEOUT		(1 << 2)	/* Whiteout source */
 
+/*
+ * The root inode of procfs is guaranteed to always have the same inode number.
+ * For programs that make heavy use of procfs, verifying that the root is a
+ * real procfs root and using openat2(RESOLVE_{NO_{XDEV,MAGICLINKS},BENEATH})
+ * will allow you to make sure you are never tricked into operating on the
+ * wrong procfs file.
+ */
+enum procfs_ino {
+	PROCFS_ROOT_INO = 1,
+};
+
 struct file_clone_range {
 	__s64 src_fd;
 	__u64 src_offset;
-- 
cgit v1.2.3


From 626bb0a45584d544d84eab909795ccb355062bcc Mon Sep 17 00:00:00 2001
From: Michael Walle <mwalle@kernel.org>
Date: Fri, 13 Jun 2025 13:45:12 +0200
Subject: mfd: tps6594: Add TI TPS652G1 support

The TPS652G1 is a stripped down version of the TPS65224. From a software
point of view, it lacks any voltage monitoring, the watchdog, the ESM
and the ADC.

Signed-off-by: Michael Walle <mwalle@kernel.org>
Link: https://lore.kernel.org/r/20250613114518.1772109-2-mwalle@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/tps6594-core.c  | 88 +++++++++++++++++++++++++++++++++++++++++----
 drivers/mfd/tps6594-i2c.c   | 10 ++++--
 drivers/mfd/tps6594-spi.c   | 10 ++++--
 include/linux/mfd/tps6594.h |  1 +
 4 files changed, 99 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/tps6594-core.c b/drivers/mfd/tps6594-core.c
index a7223e873cd1..c16c37e36617 100644
--- a/drivers/mfd/tps6594-core.c
+++ b/drivers/mfd/tps6594-core.c
@@ -1,6 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * Core functions for TI TPS65224/TPS6594/TPS6593/LP8764 PMICs
+ * Core functions for following TI PMICs:
+ *  - LP8764
+ *  - TPS65224
+ *  - TPS652G1
+ *  - TPS6593
+ *  - TPS6594
  *
  * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/
  */
@@ -414,6 +419,61 @@ static const unsigned int tps65224_irq_reg[] = {
 	TPS6594_REG_INT_FSM_ERR,
 };
 
+/* TPS652G1 Resources */
+
+static const struct mfd_cell tps652g1_common_cells[] = {
+	MFD_CELL_RES("tps6594-pfsm", tps65224_pfsm_resources),
+	MFD_CELL_RES("tps6594-pinctrl", tps65224_pinctrl_resources),
+	MFD_CELL_NAME("tps6594-regulator"),
+};
+
+static const struct regmap_irq tps652g1_irqs[] = {
+	/* INT_GPIO register */
+	REGMAP_IRQ_REG(TPS65224_IRQ_GPIO1, 2, TPS65224_BIT_GPIO1_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_GPIO2, 2, TPS65224_BIT_GPIO2_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_GPIO3, 2, TPS65224_BIT_GPIO3_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_GPIO4, 2, TPS65224_BIT_GPIO4_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_GPIO5, 2, TPS65224_BIT_GPIO5_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_GPIO6, 2, TPS65224_BIT_GPIO6_INT),
+
+	/* INT_STARTUP register */
+	REGMAP_IRQ_REG(TPS65224_IRQ_VSENSE, 3, TPS65224_BIT_VSENSE_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_ENABLE, 3, TPS6594_BIT_ENABLE_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_PB_SHORT, 3, TPS65224_BIT_PB_SHORT_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_FSD, 3, TPS6594_BIT_FSD_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_SOFT_REBOOT, 3, TPS6594_BIT_SOFT_REBOOT_INT),
+
+	/* INT_MISC register */
+	REGMAP_IRQ_REG(TPS65224_IRQ_BIST_PASS, 4, TPS6594_BIT_BIST_PASS_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_EXT_CLK, 4, TPS6594_BIT_EXT_CLK_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_REG_UNLOCK, 4, TPS65224_BIT_REG_UNLOCK_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_TWARN, 4, TPS6594_BIT_TWARN_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_PB_LONG, 4, TPS65224_BIT_PB_LONG_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_PB_FALL, 4, TPS65224_BIT_PB_FALL_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_PB_RISE, 4, TPS65224_BIT_PB_RISE_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_ADC_CONV_READY, 4, TPS65224_BIT_ADC_CONV_READY_INT),
+
+	/* INT_MODERATE_ERR register */
+	REGMAP_IRQ_REG(TPS65224_IRQ_TSD_ORD, 5, TPS6594_BIT_TSD_ORD_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_BIST_FAIL, 5, TPS6594_BIT_BIST_FAIL_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_REG_CRC_ERR, 5, TPS6594_BIT_REG_CRC_ERR_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_RECOV_CNT, 5, TPS6594_BIT_RECOV_CNT_INT),
+
+	/* INT_SEVERE_ERR register */
+	REGMAP_IRQ_REG(TPS65224_IRQ_TSD_IMM, 6, TPS6594_BIT_TSD_IMM_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_VCCA_OVP, 6, TPS6594_BIT_VCCA_OVP_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_PFSM_ERR, 6, TPS6594_BIT_PFSM_ERR_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_BG_XMON, 6, TPS65224_BIT_BG_XMON_INT),
+
+	/* INT_FSM_ERR register */
+	REGMAP_IRQ_REG(TPS65224_IRQ_IMM_SHUTDOWN, 7, TPS6594_BIT_IMM_SHUTDOWN_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_ORD_SHUTDOWN, 7, TPS6594_BIT_ORD_SHUTDOWN_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_MCU_PWR_ERR, 7, TPS6594_BIT_MCU_PWR_ERR_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_SOC_PWR_ERR, 7, TPS6594_BIT_SOC_PWR_ERR_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_COMM_ERR, 7, TPS6594_BIT_COMM_ERR_INT),
+	REGMAP_IRQ_REG(TPS65224_IRQ_I2C2_ERR, 7, TPS65224_BIT_I2C2_ERR_INT),
+};
+
 static inline unsigned int tps6594_get_irq_reg(struct regmap_irq_chip_data *data,
 					       unsigned int base, int index)
 {
@@ -443,7 +503,7 @@ static int tps6594_handle_post_irq(void *irq_drv_data)
 	 * a new interrupt.
 	 */
 	if (tps->use_crc) {
-		if (tps->chip_id == TPS65224) {
+		if (tps->chip_id == TPS65224 || tps->chip_id == TPS652G1) {
 			regmap_reg = TPS6594_REG_INT_FSM_ERR;
 			mask_val = TPS6594_BIT_COMM_ERR_INT;
 		} else {
@@ -481,6 +541,18 @@ static struct regmap_irq_chip tps65224_irq_chip = {
 	.handle_post_irq = tps6594_handle_post_irq,
 };
 
+static struct regmap_irq_chip tps652g1_irq_chip = {
+	.ack_base = TPS6594_REG_INT_BUCK,
+	.ack_invert = 1,
+	.clear_ack = 1,
+	.init_ack_masked = 1,
+	.num_regs = ARRAY_SIZE(tps65224_irq_reg),
+	.irqs = tps652g1_irqs,
+	.num_irqs = ARRAY_SIZE(tps652g1_irqs),
+	.get_irq_reg = tps65224_get_irq_reg,
+	.handle_post_irq = tps6594_handle_post_irq,
+};
+
 static const struct regmap_range tps6594_volatile_ranges[] = {
 	regmap_reg_range(TPS6594_REG_INT_TOP, TPS6594_REG_STAT_READBACK_ERR),
 	regmap_reg_range(TPS6594_REG_RTC_STATUS, TPS6594_REG_RTC_STATUS),
@@ -507,7 +579,7 @@ static int tps6594_check_crc_mode(struct tps6594 *tps, bool primary_pmic)
 	int ret;
 	unsigned int regmap_reg, mask_val;
 
-	if (tps->chip_id == TPS65224) {
+	if (tps->chip_id == TPS65224 || tps->chip_id == TPS652G1) {
 		regmap_reg = TPS6594_REG_CONFIG_2;
 		mask_val = TPS65224_BIT_I2C1_SPI_CRC_EN;
 	} else {
@@ -537,7 +609,7 @@ static int tps6594_set_crc_feature(struct tps6594 *tps)
 	int ret;
 	unsigned int regmap_reg, mask_val;
 
-	if (tps->chip_id == TPS65224) {
+	if (tps->chip_id == TPS65224 || tps->chip_id == TPS652G1) {
 		regmap_reg = TPS6594_REG_CONFIG_2;
 		mask_val = TPS65224_BIT_I2C1_SPI_CRC_EN;
 	} else {
@@ -628,6 +700,10 @@ int tps6594_device_init(struct tps6594 *tps, bool enable_crc)
 		irq_chip = &tps65224_irq_chip;
 		n_cells = ARRAY_SIZE(tps65224_common_cells);
 		cells = tps65224_common_cells;
+	} else if (tps->chip_id == TPS652G1) {
+		irq_chip = &tps652g1_irq_chip;
+		n_cells = ARRAY_SIZE(tps652g1_common_cells);
+		cells = tps652g1_common_cells;
 	} else {
 		irq_chip = &tps6594_irq_chip;
 		n_cells = ARRAY_SIZE(tps6594_common_cells);
@@ -651,8 +727,8 @@ int tps6594_device_init(struct tps6594 *tps, bool enable_crc)
 	if (ret)
 		return dev_err_probe(dev, ret, "Failed to add common child devices\n");
 
-	/* No RTC for LP8764 and TPS65224 */
-	if (tps->chip_id != LP8764 && tps->chip_id != TPS65224) {
+	/* No RTC for LP8764, TPS65224 and TPS652G1 */
+	if (tps->chip_id != LP8764 && tps->chip_id != TPS65224 && tps->chip_id != TPS652G1) {
 		ret = devm_mfd_add_devices(dev, PLATFORM_DEVID_AUTO, tps6594_rtc_cells,
 					   ARRAY_SIZE(tps6594_rtc_cells), NULL, 0,
 					   regmap_irq_get_domain(tps->irq_data));
diff --git a/drivers/mfd/tps6594-i2c.c b/drivers/mfd/tps6594-i2c.c
index 4ab91c34d9fb..7ff7516286fd 100644
--- a/drivers/mfd/tps6594-i2c.c
+++ b/drivers/mfd/tps6594-i2c.c
@@ -1,6 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * I2C access driver for TI TPS65224/TPS6594/TPS6593/LP8764 PMICs
+ * I2C access driver for the following TI PMICs:
+ *  - LP8764
+ *  - TPS65224
+ *  - TPS652G1
+ *  - TPS6593
+ *  - TPS6594
  *
  * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/
  */
@@ -197,6 +202,7 @@ static const struct of_device_id tps6594_i2c_of_match_table[] = {
 	{ .compatible = "ti,tps6593-q1", .data = (void *)TPS6593, },
 	{ .compatible = "ti,lp8764-q1",  .data = (void *)LP8764,  },
 	{ .compatible = "ti,tps65224-q1", .data = (void *)TPS65224, },
+	{ .compatible = "ti,tps652g1", .data = (void *)TPS652G1, },
 	{}
 };
 MODULE_DEVICE_TABLE(of, tps6594_i2c_of_match_table);
@@ -222,7 +228,7 @@ static int tps6594_i2c_probe(struct i2c_client *client)
 		return dev_err_probe(dev, -EINVAL, "Failed to find matching chip ID\n");
 	tps->chip_id = (unsigned long)match->data;
 
-	if (tps->chip_id == TPS65224)
+	if (tps->chip_id == TPS65224 || tps->chip_id == TPS652G1)
 		tps6594_i2c_regmap_config.volatile_table = &tps65224_volatile_table;
 
 	tps->regmap = devm_regmap_init(dev, NULL, client, &tps6594_i2c_regmap_config);
diff --git a/drivers/mfd/tps6594-spi.c b/drivers/mfd/tps6594-spi.c
index 6ebccb79f0cc..944b7313a1d9 100644
--- a/drivers/mfd/tps6594-spi.c
+++ b/drivers/mfd/tps6594-spi.c
@@ -1,6 +1,11 @@
 // SPDX-License-Identifier: GPL-2.0
 /*
- * SPI access driver for TI TPS65224/TPS6594/TPS6593/LP8764 PMICs
+ * SPI access driver for the following TI PMICs:
+ *  - LP8764
+ *  - TPS65224
+ *  - TPS652G1
+ *  - TPS6593
+ *  - TPS6594
  *
  * Copyright (C) 2023 BayLibre Incorporated - https://www.baylibre.com/
  */
@@ -82,6 +87,7 @@ static const struct of_device_id tps6594_spi_of_match_table[] = {
 	{ .compatible = "ti,tps6593-q1", .data = (void *)TPS6593, },
 	{ .compatible = "ti,lp8764-q1",  .data = (void *)LP8764,  },
 	{ .compatible = "ti,tps65224-q1", .data = (void *)TPS65224, },
+	{ .compatible = "ti,tps652g1", .data = (void *)TPS652G1, },
 	{}
 };
 MODULE_DEVICE_TABLE(of, tps6594_spi_of_match_table);
@@ -107,7 +113,7 @@ static int tps6594_spi_probe(struct spi_device *spi)
 		return dev_err_probe(dev, -EINVAL, "Failed to find matching chip ID\n");
 	tps->chip_id = (unsigned long)match->data;
 
-	if (tps->chip_id == TPS65224)
+	if (tps->chip_id == TPS65224 || tps->chip_id == TPS652G1)
 		tps6594_spi_regmap_config.volatile_table = &tps65224_volatile_table;
 
 	tps->regmap = devm_regmap_init(dev, NULL, spi, &tps6594_spi_regmap_config);
diff --git a/include/linux/mfd/tps6594.h b/include/linux/mfd/tps6594.h
index 16543fd4d83e..021db8875963 100644
--- a/include/linux/mfd/tps6594.h
+++ b/include/linux/mfd/tps6594.h
@@ -19,6 +19,7 @@ enum pmic_id {
 	TPS6593,
 	LP8764,
 	TPS65224,
+	TPS652G1,
 };
 
 /* Macro to get page index from register address */
-- 
cgit v1.2.3


From 4b57c057f9e6668ae442b19902dab8a73fe7b209 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:58:56 -0700
Subject: iommu: Use enum iommu_hw_info_type for type in hw_info op

Replace u32 to make it clear. No functional changes.

Also simplify the kdoc since the type itself is clear enough.

Link: https://patch.msgid.link/r/651c50dee8ab900f691202ef0204cd5a43fdd6a2.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 3 ++-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h         | 3 ++-
 drivers/iommu/intel/iommu.c                         | 3 ++-
 drivers/iommu/iommufd/selftest.c                    | 3 ++-
 include/linux/iommu.h                               | 6 +++---
 5 files changed, 11 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
index 9f59c95a254c..69bbe39e28de 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
@@ -7,7 +7,8 @@
 
 #include "arm-smmu-v3.h"
 
-void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type)
+void *arm_smmu_hw_info(struct device *dev, u32 *length,
+		       enum iommu_hw_info_type *type)
 {
 	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 	struct iommu_hw_info_arm_smmuv3 *info;
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index bb39af84e6b0..04463a4aaa26 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -1033,7 +1033,8 @@ struct arm_vsmmu {
 };
 
 #if IS_ENABLED(CONFIG_ARM_SMMU_V3_IOMMUFD)
-void *arm_smmu_hw_info(struct device *dev, u32 *length, u32 *type);
+void *arm_smmu_hw_info(struct device *dev, u32 *length,
+		       enum iommu_hw_info_type *type);
 size_t arm_smmu_get_viommu_size(struct device *dev,
 				enum iommu_viommu_type viommu_type);
 int arm_vsmmu_init(struct iommufd_viommu *viommu,
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 7aa3932251b2..850f1a6f548c 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4091,7 +4091,8 @@ out_remove_dev_pasid:
 	return ret;
 }
 
-static void *intel_iommu_hw_info(struct device *dev, u32 *length, u32 *type)
+static void *intel_iommu_hw_info(struct device *dev, u32 *length,
+				 enum iommu_hw_info_type *type)
 {
 	struct device_domain_info *info = dev_iommu_priv_get(dev);
 	struct intel_iommu *iommu = info->iommu;
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 74ca955a766e..7a9abe3f47d5 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -287,7 +287,8 @@ static struct iommu_domain mock_blocking_domain = {
 	.ops = &mock_blocking_ops,
 };
 
-static void *mock_domain_hw_info(struct device *dev, u32 *length, u32 *type)
+static void *mock_domain_hw_info(struct device *dev, u32 *length,
+				 enum iommu_hw_info_type *type)
 {
 	struct iommu_test_hw_info *info;
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 04548b18df28..b87c2841e6bc 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -563,8 +563,7 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
  * @capable: check capability
  * @hw_info: report iommu hardware information. The data buffer returned by this
  *           op is allocated in the iommu driver and freed by the caller after
- *           use. The information type is one of enum iommu_hw_info_type defined
- *           in include/uapi/linux/iommufd.h.
+ *           use.
  * @domain_alloc: Do not use in new drivers
  * @domain_alloc_identity: allocate an IDENTITY domain. Drivers should prefer to
  *                         use identity_domain instead. This should only be used
@@ -623,7 +622,8 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
  */
 struct iommu_ops {
 	bool (*capable)(struct device *dev, enum iommu_cap);
-	void *(*hw_info)(struct device *dev, u32 *length, u32 *type);
+	void *(*hw_info)(struct device *dev, u32 *length,
+			 enum iommu_hw_info_type *type);
 
 	/* Domain allocation and freeing by the iommu driver */
 #if IS_ENABLED(CONFIG_FSL_PAMU)
-- 
cgit v1.2.3


From 3fcf56a2393b399f289a473181ce6b19f716b59d Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:58:57 -0700
Subject: iommu: Add iommu_copy_struct_to_user helper

Similar to the iommu_copy_struct_from_user helper receiving data from the
user space, add an iommu_copy_struct_to_user helper to report output data
back to the user space data pointer.

Link: https://patch.msgid.link/r/fa292c2a730aadd77085ec3a8272360c96eabb9c.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/iommu.h | 40 ++++++++++++++++++++++++++++++++++++++++
 1 file changed, 40 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index b87c2841e6bc..fd7319706684 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -558,6 +558,46 @@ iommu_copy_struct_from_full_user_array(void *kdst, size_t kdst_entry_size,
 	return 0;
 }
 
+/**
+ * __iommu_copy_struct_to_user - Report iommu driver specific user space data
+ * @dst_data: Pointer to a struct iommu_user_data for user space data location
+ * @src_data: Pointer to an iommu driver specific user data that is defined in
+ *            include/uapi/linux/iommufd.h
+ * @data_type: The data type of the @src_data. Must match with @dst_data.type
+ * @data_len: Length of current user data structure, i.e. sizeof(struct _src)
+ * @min_len: Initial length of user data structure for backward compatibility.
+ *           This should be offsetofend using the last member in the user data
+ *           struct that was initially added to include/uapi/linux/iommufd.h
+ */
+static inline int
+__iommu_copy_struct_to_user(const struct iommu_user_data *dst_data,
+			    void *src_data, unsigned int data_type,
+			    size_t data_len, size_t min_len)
+{
+	if (WARN_ON(!dst_data || !src_data))
+		return -EINVAL;
+	if (dst_data->type != data_type)
+		return -EINVAL;
+	if (dst_data->len < min_len || data_len < dst_data->len)
+		return -EINVAL;
+	return copy_struct_to_user(dst_data->uptr, dst_data->len, src_data,
+				   data_len, NULL);
+}
+
+/**
+ * iommu_copy_struct_to_user - Report iommu driver specific user space data
+ * @user_data: Pointer to a struct iommu_user_data for user space data location
+ * @ksrc: Pointer to an iommu driver specific user data that is defined in
+ *        include/uapi/linux/iommufd.h
+ * @data_type: The data type of the @ksrc. Must match with @user_data->type
+ * @min_last: The last member of the data structure @ksrc points in the initial
+ *            version.
+ * Return 0 for success, otherwise -error.
+ */
+#define iommu_copy_struct_to_user(user_data, ksrc, data_type, min_last)        \
+	__iommu_copy_struct_to_user(user_data, ksrc, data_type, sizeof(*ksrc), \
+				    offsetofend(typeof(*ksrc), min_last))
+
 /**
  * struct iommu_ops - iommu ops and capabilities
  * @capable: check capability
-- 
cgit v1.2.3


From c3436d42f812faffac94f8fb3fb246ab43ffdffe Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:58:58 -0700
Subject: iommu: Pass in a driver-level user data structure to viommu_init op

The new type of vIOMMU for tegra241-cmdqv allows user space VM to use one
of its virtual command queue HW resources exclusively. This requires user
space to mmap the corresponding MMIO page from kernel space for direct HW
control.

To forward the mmap info (offset and length), iommufd should add a driver
specific data structure to the IOMMUFD_CMD_VIOMMU_ALLOC ioctl, for driver
to output the info during the vIOMMU initialization back to user space.

Similar to the existing ioctls and their IOMMU handlers, add a user_data
to viommu_init op to bridge between iommufd and drivers.

Link: https://patch.msgid.link/r/90bd5637dab7f5507c7a64d2c4826e70431e45a4.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 3 ++-
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h         | 3 ++-
 drivers/iommu/iommufd/selftest.c                    | 3 ++-
 drivers/iommu/iommufd/viommu.c                      | 2 +-
 include/linux/iommu.h                               | 3 ++-
 5 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
index 69bbe39e28de..170d69162848 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
@@ -419,7 +419,8 @@ size_t arm_smmu_get_viommu_size(struct device *dev,
 }
 
 int arm_vsmmu_init(struct iommufd_viommu *viommu,
-		   struct iommu_domain *parent_domain)
+		   struct iommu_domain *parent_domain,
+		   const struct iommu_user_data *user_data)
 {
 	struct arm_vsmmu *vsmmu = container_of(viommu, struct arm_vsmmu, core);
 	struct arm_smmu_device *smmu =
diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
index 04463a4aaa26..c1ced4d4b6d1 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.h
@@ -1038,7 +1038,8 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length,
 size_t arm_smmu_get_viommu_size(struct device *dev,
 				enum iommu_viommu_type viommu_type);
 int arm_vsmmu_init(struct iommufd_viommu *viommu,
-		   struct iommu_domain *parent_domain);
+		   struct iommu_domain *parent_domain,
+		   const struct iommu_user_data *user_data);
 int arm_smmu_attach_prepare_vmaster(struct arm_smmu_attach_state *state,
 				    struct arm_smmu_nested_domain *nested_domain);
 void arm_smmu_attach_commit_vmaster(struct arm_smmu_attach_state *state);
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 7a9abe3f47d5..0d896a89ace7 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -779,7 +779,8 @@ static size_t mock_get_viommu_size(struct device *dev,
 }
 
 static int mock_viommu_init(struct iommufd_viommu *viommu,
-			    struct iommu_domain *parent_domain)
+			    struct iommu_domain *parent_domain,
+			    const struct iommu_user_data *user_data)
 {
 	struct mock_iommu_device *mock_iommu = container_of(
 		viommu->iommu_dev, struct mock_iommu_device, iommu_dev);
diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index bc8796e6684e..2009a421efae 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -84,7 +84,7 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd)
 	 */
 	viommu->iommu_dev = __iommu_get_iommu_dev(idev->dev);
 
-	rc = ops->viommu_init(viommu, hwpt_paging->common.domain);
+	rc = ops->viommu_init(viommu, hwpt_paging->common.domain, NULL);
 	if (rc)
 		goto out_put_hwpt;
 
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fd7319706684..e06a0fbe4bc7 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -700,7 +700,8 @@ struct iommu_ops {
 	size_t (*get_viommu_size)(struct device *dev,
 				  enum iommu_viommu_type viommu_type);
 	int (*viommu_init)(struct iommufd_viommu *viommu,
-			   struct iommu_domain *parent_domain);
+			   struct iommu_domain *parent_domain,
+			   const struct iommu_user_data *user_data);
 
 	const struct iommu_domain_ops *default_domain_ops;
 	unsigned long pgsize_bitmap;
-- 
cgit v1.2.3


From c2aaddbd2deded9d3301f1bafed242a0f71baba8 Mon Sep 17 00:00:00 2001
From: Samuel Zhang <guoqing.zhang@amd.com>
Date: Thu, 10 Jul 2025 14:23:12 +0800
Subject: PM: hibernate: add new api pm_hibernate_is_recovering()

dev_pm_ops.thaw() is called in following cases:
* normal case: after hibernation image has been created.
* error case 1: creation of a hibernation image has failed.
* error case 2: restoration from a hibernation image has failed.

For normal case, it is called mainly for resume storage devices for
saving the hibernation image. Other devices that are not involved
in the image saving do not need to resume the device. But since there's
no api to know which case thaw() is called, device drivers can't
conditionally resume device in thaw().

The new pm_hibernate_is_recovering() is such a api to query if thaw() is
called in normal case.

Signed-off-by: Samuel Zhang <guoqing.zhang@amd.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Link: https://lore.kernel.org/r/20250710062313.3226149-5-guoqing.zhang@amd.com
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 drivers/base/power/main.c | 14 ++++++++++++++
 include/linux/suspend.h   |  2 ++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/base/power/main.c b/drivers/base/power/main.c
index eebe699fdf4f..63f3a48f434c 100644
--- a/drivers/base/power/main.c
+++ b/drivers/base/power/main.c
@@ -66,6 +66,20 @@ static pm_message_t pm_transition;
 static DEFINE_MUTEX(async_wip_mtx);
 static int async_error;
 
+/**
+ * pm_hibernate_is_recovering - if recovering from hibernate due to error.
+ *
+ * Used to query if dev_pm_ops.thaw() is called for normal hibernation case or
+ * recovering from some error.
+ *
+ * Return: true for error case, false for normal case.
+ */
+bool pm_hibernate_is_recovering(void)
+{
+	return pm_transition.event == PM_EVENT_RECOVER;
+}
+EXPORT_SYMBOL_GPL(pm_hibernate_is_recovering);
+
 static const char *pm_verb(int event)
 {
 	switch (event) {
diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index b1c76c8f2c82..293137210fdf 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -426,6 +426,8 @@ int is_hibernate_resume_dev(dev_t dev);
 static inline int is_hibernate_resume_dev(dev_t dev) { return 0; }
 #endif
 
+bool pm_hibernate_is_recovering(void);
+
 /* Hibernation and suspend events */
 #define PM_HIBERNATION_PREPARE	0x0001 /* Going to hibernate */
 #define PM_POST_HIBERNATION	0x0002 /* Hibernation finished */
-- 
cgit v1.2.3


From 47462586f91358499897fddb20f6bb9cec5f4213 Mon Sep 17 00:00:00 2001
From: Eric Biggers <ebiggers@kernel.org>
Date: Wed, 9 Jul 2025 23:07:52 -0700
Subject: fscrypt: Remove gfp_t argument from fscrypt_encrypt_block_inplace()

This argument is no longer used, so remove it.

Reviewed-by: Alex Markuze <amarkuze@redhat.com>
Link: https://lore.kernel.org/r/20250710060754.637098-6-ebiggers@kernel.org
Signed-off-by: Eric Biggers <ebiggers@kernel.org>
---
 fs/ceph/crypto.c        | 3 +--
 fs/crypto/crypto.c      | 3 +--
 fs/ubifs/crypto.c       | 2 +-
 include/linux/fscrypt.h | 5 ++---
 4 files changed, 5 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/fs/ceph/crypto.c b/fs/ceph/crypto.c
index 3b3c4d8d401e..6d04d528ed03 100644
--- a/fs/ceph/crypto.c
+++ b/fs/ceph/crypto.c
@@ -523,8 +523,7 @@ int ceph_fscrypt_encrypt_block_inplace(const struct inode *inode,
 
 	doutc(cl, "%p %llx.%llx len %u offs %u blk %llu\n", inode,
 	      ceph_vinop(inode), len, offs, lblk_num);
-	return fscrypt_encrypt_block_inplace(inode, page, len, offs, lblk_num,
-					     gfp_flags);
+	return fscrypt_encrypt_block_inplace(inode, page, len, offs, lblk_num);
 }
 
 /**
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index bab0aacd4da3..b6ccab524fde 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -217,7 +217,6 @@ EXPORT_SYMBOL(fscrypt_encrypt_pagecache_blocks);
  * @offs:      Byte offset within @page at which the block to encrypt begins
  * @lblk_num:  Filesystem logical block number of the block, i.e. the 0-based
  *		number of the block within the file
- * @gfp_flags: Memory allocation flags
  *
  * Encrypt a possibly-compressed filesystem block that is located in an
  * arbitrary page, not necessarily in the original pagecache page.  The @inode
@@ -229,7 +228,7 @@ EXPORT_SYMBOL(fscrypt_encrypt_pagecache_blocks);
  */
 int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page,
 				  unsigned int len, unsigned int offs,
-				  u64 lblk_num, gfp_t gfp_flags)
+				  u64 lblk_num)
 {
 	if (WARN_ON_ONCE(inode->i_sb->s_cop->supports_subblock_data_units))
 		return -EOPNOTSUPP;
diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c
index 921f9033d0d2..fb5ac358077b 100644
--- a/fs/ubifs/crypto.c
+++ b/fs/ubifs/crypto.c
@@ -51,7 +51,7 @@ int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn,
 		memset(p + in_len, 0, pad_len - in_len);
 
 	err = fscrypt_encrypt_block_inplace(inode, virt_to_page(p), pad_len,
-					    offset_in_page(p), block, GFP_NOFS);
+					    offset_in_page(p), block);
 	if (err) {
 		ubifs_err(c, "fscrypt_encrypt_block_inplace() failed: %d", err);
 		return err;
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 56fad33043d5..8d0e3ad89b94 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -314,7 +314,7 @@ struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio,
 		size_t len, size_t offs, gfp_t gfp_flags);
 int fscrypt_encrypt_block_inplace(const struct inode *inode, struct page *page,
 				  unsigned int len, unsigned int offs,
-				  u64 lblk_num, gfp_t gfp_flags);
+				  u64 lblk_num);
 
 int fscrypt_decrypt_pagecache_blocks(struct folio *folio, size_t len,
 				     size_t offs);
@@ -487,8 +487,7 @@ static inline struct page *fscrypt_encrypt_pagecache_blocks(struct folio *folio,
 static inline int fscrypt_encrypt_block_inplace(const struct inode *inode,
 						struct page *page,
 						unsigned int len,
-						unsigned int offs, u64 lblk_num,
-						gfp_t gfp_flags)
+						unsigned int offs, u64 lblk_num)
 {
 	return -EOPNOTSUPP;
 }
-- 
cgit v1.2.3


From a8b289f0f2dcbadd8c207ad8f33cf7ba2b4eb088 Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Thu, 10 Jul 2025 10:00:12 +0200
Subject: irqchip/irq-msi-lib: Fix build with PCI disabled

The armada-370-xp irqchip fails in some randconfig builds because
of a missing declaration:

In file included from drivers/irqchip/irq-armada-370-xp.c:23:
include/linux/irqchip/irq-msi-lib.h:25:39: error: 'struct msi_domain_info' declared inside parameter list will not be visible outside of this definition or declaration [-Werror]

Add a forward declaration for the msi_domain_info structure.

[ tglx: Fixed up the subsystem prefix. Is it really that hard to get right? ]

Fixes: e51b27438a10 ("irqchip: Make irq-msi-lib.h globally available")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Marc Zyngier <maz@kernel.org>
Link: https://lore.kernel.org/all/20250710080021.2303640-1-arnd@kernel.org
---
 include/linux/irqchip/irq-msi-lib.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/irqchip/irq-msi-lib.h b/include/linux/irqchip/irq-msi-lib.h
index dd8d1d138544..224ac28e88d7 100644
--- a/include/linux/irqchip/irq-msi-lib.h
+++ b/include/linux/irqchip/irq-msi-lib.h
@@ -17,6 +17,7 @@
 
 #define MATCH_PLATFORM_MSI	BIT(DOMAIN_BUS_PLATFORM_MSI)
 
+struct msi_domain_info;
 int msi_lib_irq_domain_select(struct irq_domain *d, struct irq_fwspec *fwspec,
 			      enum irq_domain_bus_token bus_token);
 
-- 
cgit v1.2.3


From 5c21c5f22d0701ac6c1cafc0e8de4bf42e5c53e5 Mon Sep 17 00:00:00 2001
From: Christian Brauner <brauner@kernel.org>
Date: Fri, 11 Jul 2025 15:47:48 +0200
Subject: cleanup: add a scoped version of CLASS()

This will make it possible to use:

scoped_class() {
}

constructs to limit variables to certain scopes and still perform
auto-cleanup.

Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/cleanup.h | 8 ++++++++
 1 file changed, 8 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 7093e1d08af0..bee606bebaca 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -277,6 +277,14 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
 	class_##_name##_t var __cleanup(class_##_name##_destructor) =	\
 		class_##_name##_constructor
 
+#define scoped_class(_name, var, args)                          \
+	for (CLASS(_name, var)(args);                           \
+	     __guard_ptr(_name)(&var) || !__is_cond_ptr(_name); \
+	     ({ goto _label; }))                                \
+		if (0) {                                        \
+_label:                                                         \
+			break;                                  \
+		} else
 
 /*
  * DEFINE_GUARD(name, type, lock, unlock):
-- 
cgit v1.2.3


From 56180dd20c19e5b0fa34822997a9ac66b517e7b3 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Thu, 10 Jul 2025 13:00:07 +0200
Subject: futex: Use RCU-based per-CPU reference counting instead of rcuref_t

The use of rcuref_t for reference counting introduces a performance bottleneck
when accessed concurrently by multiple threads during futex operations.

Replace rcuref_t with special crafted per-CPU reference counters. The
lifetime logic remains the same.

The newly allocate private hash starts in FR_PERCPU state. In this state, each
futex operation that requires the private hash uses a per-CPU counter (an
unsigned int) for incrementing or decrementing the reference count.

When the private hash is about to be replaced, the per-CPU counters are
migrated to a atomic_t counter mm_struct::futex_atomic.
The migration process:
- Waiting for one RCU grace period to ensure all users observe the
  current private hash. This can be skipped if a grace period elapsed
  since the private hash was assigned.

- futex_private_hash::state is set to FR_ATOMIC, forcing all users to
  use mm_struct::futex_atomic for reference counting.

- After a RCU grace period, all users are guaranteed to be using the
  atomic counter. The per-CPU counters can now be summed up and added to
  the atomic_t counter. If the resulting count is zero, the hash can be
  safely replaced. Otherwise, active users still hold a valid reference.

- Once the atomic reference count drops to zero, the next futex
  operation will switch to the new private hash.

call_rcu_hurry() is used to speed up transition which otherwise might be
delay with RCU_LAZY. There is nothing wrong with using call_rcu(). The
side effects would be that on auto scaling the new hash is used later
and the SET_SLOTS prctl() will block longer.

[bigeasy: commit description + mm get/ put_async]

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20250710110011.384614-3-bigeasy@linutronix.de
---
 include/linux/futex.h    |  16 +---
 include/linux/mm_types.h |   5 +
 include/linux/sched/mm.h |   2 +-
 init/Kconfig             |   4 -
 kernel/fork.c            |   8 +-
 kernel/futex/core.c      | 243 +++++++++++++++++++++++++++++++++++++++++++----
 6 files changed, 243 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/futex.h b/include/linux/futex.h
index b37193653e6b..9e9750f04980 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -85,18 +85,12 @@ int futex_hash_prctl(unsigned long arg2, unsigned long arg3, unsigned long arg4)
 #ifdef CONFIG_FUTEX_PRIVATE_HASH
 int futex_hash_allocate_default(void);
 void futex_hash_free(struct mm_struct *mm);
-
-static inline void futex_mm_init(struct mm_struct *mm)
-{
-	RCU_INIT_POINTER(mm->futex_phash, NULL);
-	mm->futex_phash_new = NULL;
-	mutex_init(&mm->futex_hash_lock);
-}
+int futex_mm_init(struct mm_struct *mm);
 
 #else /* !CONFIG_FUTEX_PRIVATE_HASH */
 static inline int futex_hash_allocate_default(void) { return 0; }
-static inline void futex_hash_free(struct mm_struct *mm) { }
-static inline void futex_mm_init(struct mm_struct *mm) { }
+static inline int futex_hash_free(struct mm_struct *mm) { return 0; }
+static inline int futex_mm_init(struct mm_struct *mm) { return 0; }
 #endif /* CONFIG_FUTEX_PRIVATE_HASH */
 
 #else /* !CONFIG_FUTEX */
@@ -118,8 +112,8 @@ static inline int futex_hash_allocate_default(void)
 {
 	return 0;
 }
-static inline void futex_hash_free(struct mm_struct *mm) { }
-static inline void futex_mm_init(struct mm_struct *mm) { }
+static inline int futex_hash_free(struct mm_struct *mm) { return 0; }
+static inline int futex_mm_init(struct mm_struct *mm) { return 0; }
 
 #endif
 
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index d6b91e8a66d6..0f0662157066 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -1070,6 +1070,11 @@ struct mm_struct {
 		struct mutex			futex_hash_lock;
 		struct futex_private_hash	__rcu *futex_phash;
 		struct futex_private_hash	*futex_phash_new;
+		/* futex-ref */
+		unsigned long			futex_batches;
+		struct rcu_head			futex_rcu;
+		atomic_long_t			futex_atomic;
+		unsigned int			__percpu *futex_ref;
 #endif
 
 		unsigned long hiwater_rss; /* High-watermark of RSS usage */
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index b13474825130..2201da0afecc 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -140,7 +140,7 @@ static inline bool mmget_not_zero(struct mm_struct *mm)
 
 /* mmput gets rid of the mappings and all user-space */
 extern void mmput(struct mm_struct *);
-#ifdef CONFIG_MMU
+#if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH)
 /* same as above but performs the slow path from the async context. Can
  * be called from the atomic context as well
  */
diff --git a/init/Kconfig b/init/Kconfig
index 666783eb50ab..af4c2f085455 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1716,13 +1716,9 @@ config FUTEX_PI
 	depends on FUTEX && RT_MUTEXES
 	default y
 
-#
-# marked broken for performance reasons; gives us one more cycle to sort things out.
-#
 config FUTEX_PRIVATE_HASH
 	bool
 	depends on FUTEX && !BASE_SMALL && MMU
-	depends on BROKEN
 	default y
 
 config FUTEX_MPOL
diff --git a/kernel/fork.c b/kernel/fork.c
index 1ee8eb11f38b..0b885dcbde9a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1046,7 +1046,6 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 	RCU_INIT_POINTER(mm->exe_file, NULL);
 	mmu_notifier_subscriptions_init(mm);
 	init_tlb_flush_pending(mm);
-	futex_mm_init(mm);
 #if defined(CONFIG_TRANSPARENT_HUGEPAGE) && !defined(CONFIG_SPLIT_PMD_PTLOCKS)
 	mm->pmd_huge_pte = NULL;
 #endif
@@ -1061,6 +1060,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
 		mm->def_flags = 0;
 	}
 
+	if (futex_mm_init(mm))
+		goto fail_mm_init;
+
 	if (mm_alloc_pgd(mm))
 		goto fail_nopgd;
 
@@ -1090,6 +1092,8 @@ fail_nocontext:
 fail_noid:
 	mm_free_pgd(mm);
 fail_nopgd:
+	futex_hash_free(mm);
+fail_mm_init:
 	free_mm(mm);
 	return NULL;
 }
@@ -1145,7 +1149,7 @@ void mmput(struct mm_struct *mm)
 }
 EXPORT_SYMBOL_GPL(mmput);
 
-#ifdef CONFIG_MMU
+#if defined(CONFIG_MMU) || defined(CONFIG_FUTEX_PRIVATE_HASH)
 static void mmput_async_fn(struct work_struct *work)
 {
 	struct mm_struct *mm = container_of(work, struct mm_struct,
diff --git a/kernel/futex/core.c b/kernel/futex/core.c
index 90d53fb0ee9e..1dcb4c8a2585 100644
--- a/kernel/futex/core.c
+++ b/kernel/futex/core.c
@@ -42,7 +42,6 @@
 #include <linux/fault-inject.h>
 #include <linux/slab.h>
 #include <linux/prctl.h>
-#include <linux/rcuref.h>
 #include <linux/mempolicy.h>
 #include <linux/mmap_lock.h>
 
@@ -65,7 +64,7 @@ static struct {
 #define futex_queues	(__futex_data.queues)
 
 struct futex_private_hash {
-	rcuref_t	users;
+	int		state;
 	unsigned int	hash_mask;
 	struct rcu_head	rcu;
 	void		*mm;
@@ -129,6 +128,12 @@ static struct futex_hash_bucket *
 __futex_hash(union futex_key *key, struct futex_private_hash *fph);
 
 #ifdef CONFIG_FUTEX_PRIVATE_HASH
+static bool futex_ref_get(struct futex_private_hash *fph);
+static bool futex_ref_put(struct futex_private_hash *fph);
+static bool futex_ref_is_dead(struct futex_private_hash *fph);
+
+enum { FR_PERCPU = 0, FR_ATOMIC };
+
 static inline bool futex_key_is_private(union futex_key *key)
 {
 	/*
@@ -142,15 +147,14 @@ bool futex_private_hash_get(struct futex_private_hash *fph)
 {
 	if (fph->immutable)
 		return true;
-	return rcuref_get(&fph->users);
+	return futex_ref_get(fph);
 }
 
 void futex_private_hash_put(struct futex_private_hash *fph)
 {
-	/* Ignore return value, last put is verified via rcuref_is_dead() */
 	if (fph->immutable)
 		return;
-	if (rcuref_put(&fph->users))
+	if (futex_ref_put(fph))
 		wake_up_var(fph->mm);
 }
 
@@ -243,14 +247,18 @@ static bool __futex_pivot_hash(struct mm_struct *mm,
 	fph = rcu_dereference_protected(mm->futex_phash,
 					lockdep_is_held(&mm->futex_hash_lock));
 	if (fph) {
-		if (!rcuref_is_dead(&fph->users)) {
+		if (!futex_ref_is_dead(fph)) {
 			mm->futex_phash_new = new;
 			return false;
 		}
 
 		futex_rehash_private(fph, new);
 	}
-	rcu_assign_pointer(mm->futex_phash, new);
+	new->state = FR_PERCPU;
+	scoped_guard(rcu) {
+		mm->futex_batches = get_state_synchronize_rcu();
+		rcu_assign_pointer(mm->futex_phash, new);
+	}
 	kvfree_rcu(fph, rcu);
 	return true;
 }
@@ -289,9 +297,7 @@ again:
 		if (!fph)
 			return NULL;
 
-		if (fph->immutable)
-			return fph;
-		if (rcuref_get(&fph->users))
+		if (futex_private_hash_get(fph))
 			return fph;
 	}
 	futex_pivot_hash(mm);
@@ -1527,16 +1533,219 @@ static void futex_hash_bucket_init(struct futex_hash_bucket *fhb,
 #define FH_IMMUTABLE	0x02
 
 #ifdef CONFIG_FUTEX_PRIVATE_HASH
+
+/*
+ * futex-ref
+ *
+ * Heavily inspired by percpu-rwsem/percpu-refcount; not reusing any of that
+ * code because it just doesn't fit right.
+ *
+ * Dual counter, per-cpu / atomic approach like percpu-refcount, except it
+ * re-initializes the state automatically, such that the fph swizzle is also a
+ * transition back to per-cpu.
+ */
+
+static void futex_ref_rcu(struct rcu_head *head);
+
+static void __futex_ref_atomic_begin(struct futex_private_hash *fph)
+{
+	struct mm_struct *mm = fph->mm;
+
+	/*
+	 * The counter we're about to switch to must have fully switched;
+	 * otherwise it would be impossible for it to have reported success
+	 * from futex_ref_is_dead().
+	 */
+	WARN_ON_ONCE(atomic_long_read(&mm->futex_atomic) != 0);
+
+	/*
+	 * Set the atomic to the bias value such that futex_ref_{get,put}()
+	 * will never observe 0. Will be fixed up in __futex_ref_atomic_end()
+	 * when folding in the percpu count.
+	 */
+	atomic_long_set(&mm->futex_atomic, LONG_MAX);
+	smp_store_release(&fph->state, FR_ATOMIC);
+
+	call_rcu_hurry(&mm->futex_rcu, futex_ref_rcu);
+}
+
+static void __futex_ref_atomic_end(struct futex_private_hash *fph)
+{
+	struct mm_struct *mm = fph->mm;
+	unsigned int count = 0;
+	long ret;
+	int cpu;
+
+	/*
+	 * Per __futex_ref_atomic_begin() the state of the fph must be ATOMIC
+	 * and per this RCU callback, everybody must now observe this state and
+	 * use the atomic variable.
+	 */
+	WARN_ON_ONCE(fph->state != FR_ATOMIC);
+
+	/*
+	 * Therefore the per-cpu counter is now stable, sum and reset.
+	 */
+	for_each_possible_cpu(cpu) {
+		unsigned int *ptr = per_cpu_ptr(mm->futex_ref, cpu);
+		count += *ptr;
+		*ptr = 0;
+	}
+
+	/*
+	 * Re-init for the next cycle.
+	 */
+	this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */
+
+	/*
+	 * Add actual count, subtract bias and initial refcount.
+	 *
+	 * The moment this atomic operation happens, futex_ref_is_dead() can
+	 * become true.
+	 */
+	ret = atomic_long_add_return(count - LONG_MAX - 1, &mm->futex_atomic);
+	if (!ret)
+		wake_up_var(mm);
+
+	WARN_ON_ONCE(ret < 0);
+	mmput_async(mm);
+}
+
+static void futex_ref_rcu(struct rcu_head *head)
+{
+	struct mm_struct *mm = container_of(head, struct mm_struct, futex_rcu);
+	struct futex_private_hash *fph = rcu_dereference_raw(mm->futex_phash);
+
+	if (fph->state == FR_PERCPU) {
+		/*
+		 * Per this extra grace-period, everybody must now observe
+		 * fph as the current fph and no previously observed fph's
+		 * are in-flight.
+		 *
+		 * Notably, nobody will now rely on the atomic
+		 * futex_ref_is_dead() state anymore so we can begin the
+		 * migration of the per-cpu counter into the atomic.
+		 */
+		__futex_ref_atomic_begin(fph);
+		return;
+	}
+
+	__futex_ref_atomic_end(fph);
+}
+
+/*
+ * Drop the initial refcount and transition to atomics.
+ */
+static void futex_ref_drop(struct futex_private_hash *fph)
+{
+	struct mm_struct *mm = fph->mm;
+
+	/*
+	 * Can only transition the current fph;
+	 */
+	WARN_ON_ONCE(rcu_dereference_raw(mm->futex_phash) != fph);
+	/*
+	 * We enqueue at least one RCU callback. Ensure mm stays if the task
+	 * exits before the transition is completed.
+	 */
+	mmget(mm);
+
+	/*
+	 * In order to avoid the following scenario:
+	 *
+	 * futex_hash()			__futex_pivot_hash()
+	 *   guard(rcu);		  guard(mm->futex_hash_lock);
+	 *   fph = mm->futex_phash;
+	 *				  rcu_assign_pointer(&mm->futex_phash, new);
+	 *				futex_hash_allocate()
+	 *				  futex_ref_drop()
+	 *				    fph->state = FR_ATOMIC;
+	 *				    atomic_set(, BIAS);
+	 *
+	 *   futex_private_hash_get(fph); // OOPS
+	 *
+	 * Where an old fph (which is FR_ATOMIC) and should fail on
+	 * inc_not_zero, will succeed because a new transition is started and
+	 * the atomic is bias'ed away from 0.
+	 *
+	 * There must be at least one full grace-period between publishing a
+	 * new fph and trying to replace it.
+	 */
+	if (poll_state_synchronize_rcu(mm->futex_batches)) {
+		/*
+		 * There was a grace-period, we can begin now.
+		 */
+		__futex_ref_atomic_begin(fph);
+		return;
+	}
+
+	call_rcu_hurry(&mm->futex_rcu, futex_ref_rcu);
+}
+
+static bool futex_ref_get(struct futex_private_hash *fph)
+{
+	struct mm_struct *mm = fph->mm;
+
+	guard(rcu)();
+
+	if (smp_load_acquire(&fph->state) == FR_PERCPU) {
+		this_cpu_inc(*mm->futex_ref);
+		return true;
+	}
+
+	return atomic_long_inc_not_zero(&mm->futex_atomic);
+}
+
+static bool futex_ref_put(struct futex_private_hash *fph)
+{
+	struct mm_struct *mm = fph->mm;
+
+	guard(rcu)();
+
+	if (smp_load_acquire(&fph->state) == FR_PERCPU) {
+		this_cpu_dec(*mm->futex_ref);
+		return false;
+	}
+
+	return atomic_long_dec_and_test(&mm->futex_atomic);
+}
+
+static bool futex_ref_is_dead(struct futex_private_hash *fph)
+{
+	struct mm_struct *mm = fph->mm;
+
+	guard(rcu)();
+
+	if (smp_load_acquire(&fph->state) == FR_PERCPU)
+		return false;
+
+	return atomic_long_read(&mm->futex_atomic) == 0;
+}
+
+int futex_mm_init(struct mm_struct *mm)
+{
+	mutex_init(&mm->futex_hash_lock);
+	RCU_INIT_POINTER(mm->futex_phash, NULL);
+	mm->futex_phash_new = NULL;
+	/* futex-ref */
+	atomic_long_set(&mm->futex_atomic, 0);
+	mm->futex_batches = get_state_synchronize_rcu();
+	mm->futex_ref = alloc_percpu(unsigned int);
+	if (!mm->futex_ref)
+		return -ENOMEM;
+	this_cpu_inc(*mm->futex_ref); /* 0 -> 1 */
+	return 0;
+}
+
 void futex_hash_free(struct mm_struct *mm)
 {
 	struct futex_private_hash *fph;
 
+	free_percpu(mm->futex_ref);
 	kvfree(mm->futex_phash_new);
 	fph = rcu_dereference_raw(mm->futex_phash);
-	if (fph) {
-		WARN_ON_ONCE(rcuref_read(&fph->users) > 1);
+	if (fph)
 		kvfree(fph);
-	}
 }
 
 static bool futex_pivot_pending(struct mm_struct *mm)
@@ -1549,7 +1758,7 @@ static bool futex_pivot_pending(struct mm_struct *mm)
 		return true;
 
 	fph = rcu_dereference(mm->futex_phash);
-	return rcuref_is_dead(&fph->users);
+	return futex_ref_is_dead(fph);
 }
 
 static bool futex_hash_less(struct futex_private_hash *a,
@@ -1598,11 +1807,11 @@ static int futex_hash_allocate(unsigned int hash_slots, unsigned int flags)
 		}
 	}
 
-	fph = kvzalloc(struct_size(fph, queues, hash_slots), GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
+	fph = kvzalloc(struct_size(fph, queues, hash_slots),
+		       GFP_KERNEL_ACCOUNT | __GFP_NOWARN);
 	if (!fph)
 		return -ENOMEM;
 
-	rcuref_init(&fph->users, 1);
 	fph->hash_mask = hash_slots ? hash_slots - 1 : 0;
 	fph->custom = custom;
 	fph->immutable = !!(flags & FH_IMMUTABLE);
@@ -1645,7 +1854,7 @@ again:
 				 * allocated a replacement hash, drop the initial
 				 * reference on the existing hash.
 				 */
-				futex_private_hash_put(cur);
+				futex_ref_drop(cur);
 			}
 
 			if (new) {
-- 
cgit v1.2.3


From ed42eee797ff3dc889ade63c1dd7c4f430699e23 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:59:04 -0700
Subject: iommufd/viommu: Add driver-defined vDEVICE support

NVIDIA VCMDQ driver will have a driver-defined vDEVICE structure and do
some HW configurations with that.

To allow IOMMU drivers to define their own vDEVICE structures, move the
struct iommufd_vdevice to the public header and provide a pair of viommu
ops, similar to get_viommu_size and viommu_init.

Doing this, however, creates a new window between the vDEVICE allocation
and its driver-level initialization, during which an abort could happen
but it can't invoke a driver destroy function from the struct viommu_ops
since the driver structure isn't initialized yet. vIOMMU object doesn't
have this problem, since its destroy op is set via the viommu_ops by the
driver viommu_init function. Thus, vDEVICE should do something similar:
add a destroy function pointer inside the struct iommufd_vdevice instead
of the struct iommufd_viommu_ops.

Note that there is unlikely a use case for a type dependent vDEVICE, so
a static vdevice_size is probably enough for the near term instead of a
get_vdevice_size function op.

Link: https://patch.msgid.link/r/1e751c01da7863c669314d8e27fdb89eabcf5605.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/iommufd_private.h | 12 ------------
 drivers/iommu/iommufd/viommu.c          | 26 +++++++++++++++++++++++++-
 include/linux/iommufd.h                 | 31 +++++++++++++++++++++++++++++++
 3 files changed, 56 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 9fdbf5f21f2e..06b8c2e2d9e6 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -653,18 +653,6 @@ void iommufd_viommu_destroy(struct iommufd_object *obj);
 int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd);
 void iommufd_vdevice_destroy(struct iommufd_object *obj);
 
-struct iommufd_vdevice {
-	struct iommufd_object obj;
-	struct iommufd_viommu *viommu;
-	struct device *dev;
-
-	/*
-	 * Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID of
-	 * AMD IOMMU, and vRID of Intel VT-d
-	 */
-	u64 virt_id;
-};
-
 #ifdef CONFIG_IOMMUFD_TEST
 int iommufd_test(struct iommufd_ucmd *ucmd);
 void iommufd_selftest_destroy(struct iommufd_object *obj);
diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index c0365849f849..081ee6697a11 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -116,6 +116,8 @@ void iommufd_vdevice_destroy(struct iommufd_object *obj)
 		container_of(obj, struct iommufd_vdevice, obj);
 	struct iommufd_viommu *viommu = vdev->viommu;
 
+	if (vdev->destroy)
+		vdev->destroy(vdev);
 	/* xa_cmpxchg is okay to fail if alloc failed xa_cmpxchg previously */
 	xa_cmpxchg(&viommu->vdevs, vdev->virt_id, vdev, NULL, GFP_KERNEL);
 	refcount_dec(&viommu->obj.users);
@@ -126,6 +128,7 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_vdevice_alloc *cmd = ucmd->cmd;
 	struct iommufd_vdevice *vdev, *curr;
+	size_t vdev_size = sizeof(*vdev);
 	struct iommufd_viommu *viommu;
 	struct iommufd_device *idev;
 	u64 virt_id = cmd->virt_id;
@@ -150,7 +153,22 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 		goto out_put_idev;
 	}
 
-	vdev = iommufd_object_alloc_ucmd(ucmd, vdev, IOMMUFD_OBJ_VDEVICE);
+	if (viommu->ops && viommu->ops->vdevice_size) {
+		/*
+		 * It is a driver bug for:
+		 * - ops->vdevice_size smaller than the core structure size
+		 * - not implementing a pairing ops->vdevice_init op
+		 */
+		if (WARN_ON_ONCE(viommu->ops->vdevice_size < vdev_size ||
+				 !viommu->ops->vdevice_init)) {
+			rc = -EOPNOTSUPP;
+			goto out_put_idev;
+		}
+		vdev_size = viommu->ops->vdevice_size;
+	}
+
+	vdev = (struct iommufd_vdevice *)_iommufd_object_alloc_ucmd(
+		ucmd, vdev_size, IOMMUFD_OBJ_VDEVICE);
 	if (IS_ERR(vdev)) {
 		rc = PTR_ERR(vdev);
 		goto out_put_idev;
@@ -168,6 +186,12 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 		goto out_put_idev;
 	}
 
+	if (viommu->ops && viommu->ops->vdevice_init) {
+		rc = viommu->ops->vdevice_init(vdev);
+		if (rc)
+			goto out_put_idev;
+	}
+
 	cmd->out_vdevice_id = vdev->obj.id;
 	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
 
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 2d1bf2f97ee3..bdd10a85eeef 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -104,6 +104,21 @@ struct iommufd_viommu {
 	enum iommu_viommu_type type;
 };
 
+struct iommufd_vdevice {
+	struct iommufd_object obj;
+	struct iommufd_viommu *viommu;
+	struct device *dev;
+
+	/*
+	 * Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID of
+	 * AMD IOMMU, and vRID of Intel VT-d
+	 */
+	u64 virt_id;
+
+	/* Clean up all driver-specific parts of an iommufd_vdevice */
+	void (*destroy)(struct iommufd_vdevice *vdev);
+};
+
 /**
  * struct iommufd_viommu_ops - vIOMMU specific operations
  * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory
@@ -120,6 +135,14 @@ struct iommufd_viommu {
  *                    array->entry_num to report the number of handled requests.
  *                    The data structure of the array entry must be defined in
  *                    include/uapi/linux/iommufd.h
+ * @vdevice_size: Size of the driver-defined vDEVICE structure per this vIOMMU
+ * @vdevice_init: Initialize the driver-level structure of a vDEVICE object, or
+ *                related HW procedure. @vdev is already initialized by iommufd
+ *                core: vdev->dev and vdev->viommu pointers; vdev->id carries a
+ *                per-vIOMMU virtual ID (refer to struct iommu_vdevice_alloc in
+ *                include/uapi/linux/iommufd.h)
+ *                If driver has a deinit function to revert what vdevice_init op
+ *                does, it should set it to the @vdev->destroy function pointer
  */
 struct iommufd_viommu_ops {
 	void (*destroy)(struct iommufd_viommu *viommu);
@@ -128,6 +151,8 @@ struct iommufd_viommu_ops {
 		const struct iommu_user_data *user_data);
 	int (*cache_invalidate)(struct iommufd_viommu *viommu,
 				struct iommu_user_data_array *array);
+	const size_t vdevice_size;
+	int (*vdevice_init)(struct iommufd_vdevice *vdev);
 };
 
 #if IS_ENABLED(CONFIG_IOMMUFD)
@@ -224,4 +249,10 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
 	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_viommu,                 \
 					((drv_struct *)NULL)->member)))
+
+#define VDEVICE_STRUCT_SIZE(drv_struct, member)                                \
+	(sizeof(drv_struct) +                                                  \
+	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
+	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_vdevice,                \
+					((drv_struct *)NULL)->member)))
 #endif
-- 
cgit v1.2.3


From e2e9360022585c21dc30d2b19f5866c252f40806 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:59:05 -0700
Subject: iommufd/viommu: Introduce IOMMUFD_OBJ_HW_QUEUE and its related struct

Add IOMMUFD_OBJ_HW_QUEUE with an iommufd_hw_queue structure, representing
a HW-accelerated queue type of IOMMU's physical queue that can be passed
through to a user space VM for direct hardware control, such as:
 - NVIDIA's Virtual Command Queue
 - AMD vIOMMU's Command Buffer, Event Log Buffers, and PPR Log Buffers

Add new viommu ops for iommufd to communicate with IOMMU drivers to fetch
supported HW queue structure size and to forward user space ioctls to the
IOMMU drivers for initialization/destroy.

As the existing HWs, NVIDIA's VCMDQs access the guest memory via physical
addresses, while AMD's Buffers access the guest memory via guest physical
addresses (i.e. iova of the nesting parent HWPT). Separate two mutually
exclusive hw_queue_init and hw_queue_init_phys ops to indicate whether a
vIOMMU HW accesses the guest queue in the guest physical space (via iova)
or the host physical space (via pa).

In a latter case, the iommufd core will validate the physical pages of a
given guest queue, to ensure the underlying physical pages are contiguous
and pinned.

Since this is introduced with NVIDIA's VCMDQs, add hw_queue_init_phys for
now, and leave some notes for hw_queue_init in the near future (for AMD).

Either NVIDIA's or AMD's HW is a multi-queue model: NVIDIA's will be only
one type in enum iommu_hw_queue_type, while AMD's will be three different
types (two of which will have multi queues). Compared to letting the core
manage multiple queues with three types per vIOMMU object, it'd be easier
for the driver to manage that by having three different driver-structure
arrays per vIOMMU object. Thus, pass in the index to the init op.

Link: https://patch.msgid.link/r/6939b73699e278e60ce167e911b3d9be68882bad.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Vasant Hegde <vasant.hegde@amd.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 include/linux/iommufd.h      | 42 ++++++++++++++++++++++++++++++++++++++++++
 include/uapi/linux/iommufd.h |  9 +++++++++
 2 files changed, 51 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index bdd10a85eeef..f13f3ca6adb5 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -37,6 +37,7 @@ enum iommufd_object_type {
 	IOMMUFD_OBJ_VIOMMU,
 	IOMMUFD_OBJ_VDEVICE,
 	IOMMUFD_OBJ_VEVENTQ,
+	IOMMUFD_OBJ_HW_QUEUE,
 #ifdef CONFIG_IOMMUFD_TEST
 	IOMMUFD_OBJ_SELFTEST,
 #endif
@@ -119,6 +120,19 @@ struct iommufd_vdevice {
 	void (*destroy)(struct iommufd_vdevice *vdev);
 };
 
+struct iommufd_hw_queue {
+	struct iommufd_object obj;
+	struct iommufd_viommu *viommu;
+
+	u64 base_addr; /* in guest physical address space */
+	size_t length;
+
+	enum iommu_hw_queue_type type;
+
+	/* Clean up all driver-specific parts of an iommufd_hw_queue */
+	void (*destroy)(struct iommufd_hw_queue *hw_queue);
+};
+
 /**
  * struct iommufd_viommu_ops - vIOMMU specific operations
  * @destroy: Clean up all driver-specific parts of an iommufd_viommu. The memory
@@ -143,6 +157,22 @@ struct iommufd_vdevice {
  *                include/uapi/linux/iommufd.h)
  *                If driver has a deinit function to revert what vdevice_init op
  *                does, it should set it to the @vdev->destroy function pointer
+ * @get_hw_queue_size: Get the size of a driver-defined HW queue structure for a
+ *                     given @viommu corresponding to @queue_type. Driver should
+ *                     return 0 if HW queue aren't supported accordingly. It is
+ *                     required for driver to use the HW_QUEUE_STRUCT_SIZE macro
+ *                     to sanitize the driver-level HW queue structure related
+ *                     to the core one
+ * @hw_queue_init_phys: Initialize the driver-level structure of a HW queue that
+ *                      is initialized with its core-level structure that holds
+ *                      all the info about a guest queue memory.
+ *                      Driver providing this op indicates that HW accesses the
+ *                      guest queue memory via physical addresses.
+ *                      @index carries the logical HW QUEUE ID per vIOMMU in a
+ *                      guest VM, for a multi-queue model. @base_addr_pa carries
+ *                      the physical location of the guest queue
+ *                      If driver has a deinit function to revert what this op
+ *                      does, it should set it to the @hw_queue->destroy pointer
  */
 struct iommufd_viommu_ops {
 	void (*destroy)(struct iommufd_viommu *viommu);
@@ -153,6 +183,11 @@ struct iommufd_viommu_ops {
 				struct iommu_user_data_array *array);
 	const size_t vdevice_size;
 	int (*vdevice_init)(struct iommufd_vdevice *vdev);
+	size_t (*get_hw_queue_size)(struct iommufd_viommu *viommu,
+				    enum iommu_hw_queue_type queue_type);
+	/* AMD's HW will add hw_queue_init simply using @hw_queue->base_addr */
+	int (*hw_queue_init_phys)(struct iommufd_hw_queue *hw_queue, u32 index,
+				  phys_addr_t base_addr_pa);
 };
 
 #if IS_ENABLED(CONFIG_IOMMUFD)
@@ -255,4 +290,11 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
 	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_vdevice,                \
 					((drv_struct *)NULL)->member)))
+
+#define HW_QUEUE_STRUCT_SIZE(drv_struct, member)                               \
+	(sizeof(drv_struct) +                                                  \
+	 BUILD_BUG_ON_ZERO(offsetof(drv_struct, member)) +                     \
+	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_hw_queue,               \
+					((drv_struct *)NULL)->member)))
+
 #endif
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 04eee77335cf..640a8b5147c2 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -1147,4 +1147,13 @@ struct iommu_veventq_alloc {
 	__u32 __reserved;
 };
 #define IOMMU_VEVENTQ_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_VEVENTQ_ALLOC)
+
+/**
+ * enum iommu_hw_queue_type - HW Queue Type
+ * @IOMMU_HW_QUEUE_TYPE_DEFAULT: Reserved for future use
+ */
+enum iommu_hw_queue_type {
+	IOMMU_HW_QUEUE_TYPE_DEFAULT = 0,
+};
+
 #endif
-- 
cgit v1.2.3


From 2238ddc2b0560734c2dabb1c1fb4b342b5193625 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:59:06 -0700
Subject: iommufd/viommu: Add IOMMUFD_CMD_HW_QUEUE_ALLOC ioctl

Introduce a new IOMMUFD_CMD_HW_QUEUE_ALLOC ioctl for user space to allocate
a HW QUEUE object for a vIOMMU specific HW-accelerated queue, e.g.:
 - NVIDIA's Virtual Command Queue
 - AMD vIOMMU's Command Buffer, Event Log Buffers, and PPR Log Buffers

Since this is introduced with NVIDIA's VCMDQs that access the guest memory
in the physical address space, add an iommufd_hw_queue_alloc_phys() helper
that will create an access object to the queue memory in the IOAS, to avoid
the mappings of the guest memory from being unmapped, during the life cycle
of the HW queue object.

AMD's HW will need an hw_queue_init op that is mutually exclusive with the
hw_queue_init_phys op, and their case will bypass the access part, i.e. no
iommufd_hw_queue_alloc_phys() call.

Link: https://patch.msgid.link/r/dab4ace747deb46c1fe70a5c663307f46990ae56.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/iommufd_private.h |   2 +
 drivers/iommu/iommufd/main.c            |   6 ++
 drivers/iommu/iommufd/viommu.c          | 180 ++++++++++++++++++++++++++++++++
 include/linux/iommufd.h                 |   1 +
 include/uapi/linux/iommufd.h            |  34 ++++++
 5 files changed, 223 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 06b8c2e2d9e6..dcd609573244 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -652,6 +652,8 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd);
 void iommufd_viommu_destroy(struct iommufd_object *obj);
 int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd);
 void iommufd_vdevice_destroy(struct iommufd_object *obj);
+int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd);
+void iommufd_hw_queue_destroy(struct iommufd_object *obj);
 
 #ifdef CONFIG_IOMMUFD_TEST
 int iommufd_test(struct iommufd_ucmd *ucmd);
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 778694d7c207..4e8dbbfac890 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -354,6 +354,7 @@ union ucmd_buffer {
 	struct iommu_destroy destroy;
 	struct iommu_fault_alloc fault;
 	struct iommu_hw_info info;
+	struct iommu_hw_queue_alloc hw_queue;
 	struct iommu_hwpt_alloc hwpt;
 	struct iommu_hwpt_get_dirty_bitmap get_dirty_bitmap;
 	struct iommu_hwpt_invalidate cache;
@@ -396,6 +397,8 @@ static const struct iommufd_ioctl_op iommufd_ioctl_ops[] = {
 		 struct iommu_fault_alloc, out_fault_fd),
 	IOCTL_OP(IOMMU_GET_HW_INFO, iommufd_get_hw_info, struct iommu_hw_info,
 		 __reserved),
+	IOCTL_OP(IOMMU_HW_QUEUE_ALLOC, iommufd_hw_queue_alloc_ioctl,
+		 struct iommu_hw_queue_alloc, length),
 	IOCTL_OP(IOMMU_HWPT_ALLOC, iommufd_hwpt_alloc, struct iommu_hwpt_alloc,
 		 __reserved),
 	IOCTL_OP(IOMMU_HWPT_GET_DIRTY_BITMAP, iommufd_hwpt_get_dirty_bitmap,
@@ -559,6 +562,9 @@ static const struct iommufd_object_ops iommufd_object_ops[] = {
 	[IOMMUFD_OBJ_FAULT] = {
 		.destroy = iommufd_fault_destroy,
 	},
+	[IOMMUFD_OBJ_HW_QUEUE] = {
+		.destroy = iommufd_hw_queue_destroy,
+	},
 	[IOMMUFD_OBJ_HWPT_PAGING] = {
 		.destroy = iommufd_hwpt_paging_destroy,
 		.abort = iommufd_hwpt_paging_abort,
diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index 081ee6697a11..91339f799916 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -201,3 +201,183 @@ out_put_viommu:
 	iommufd_put_object(ucmd->ictx, &viommu->obj);
 	return rc;
 }
+
+static void iommufd_hw_queue_destroy_access(struct iommufd_ctx *ictx,
+					    struct iommufd_access *access,
+					    u64 base_iova, size_t length)
+{
+	u64 aligned_iova = PAGE_ALIGN_DOWN(base_iova);
+	u64 offset = base_iova - aligned_iova;
+
+	iommufd_access_unpin_pages(access, aligned_iova,
+				   PAGE_ALIGN(length + offset));
+	iommufd_access_detach_internal(access);
+	iommufd_access_destroy_internal(ictx, access);
+}
+
+void iommufd_hw_queue_destroy(struct iommufd_object *obj)
+{
+	struct iommufd_hw_queue *hw_queue =
+		container_of(obj, struct iommufd_hw_queue, obj);
+
+	if (hw_queue->destroy)
+		hw_queue->destroy(hw_queue);
+	if (hw_queue->access)
+		iommufd_hw_queue_destroy_access(hw_queue->viommu->ictx,
+						hw_queue->access,
+						hw_queue->base_addr,
+						hw_queue->length);
+	if (hw_queue->viommu)
+		refcount_dec(&hw_queue->viommu->obj.users);
+}
+
+/*
+ * When the HW accesses the guest queue via physical addresses, the underlying
+ * physical pages of the guest queue must be contiguous. Also, for the security
+ * concern that IOMMUFD_CMD_IOAS_UNMAP could potentially remove the mappings of
+ * the guest queue from the nesting parent iopt while the HW is still accessing
+ * the guest queue memory physically, such a HW queue must require an access to
+ * pin the underlying pages and prevent that from happening.
+ */
+static struct iommufd_access *
+iommufd_hw_queue_alloc_phys(struct iommu_hw_queue_alloc *cmd,
+			    struct iommufd_viommu *viommu, phys_addr_t *base_pa)
+{
+	u64 aligned_iova = PAGE_ALIGN_DOWN(cmd->nesting_parent_iova);
+	u64 offset = cmd->nesting_parent_iova - aligned_iova;
+	struct iommufd_access *access;
+	struct page **pages;
+	size_t max_npages;
+	size_t length;
+	size_t i;
+	int rc;
+
+	/* max_npages = DIV_ROUND_UP(offset + cmd->length, PAGE_SIZE) */
+	if (check_add_overflow(offset, cmd->length, &length))
+		return ERR_PTR(-ERANGE);
+	if (check_add_overflow(length, PAGE_SIZE - 1, &length))
+		return ERR_PTR(-ERANGE);
+	max_npages = length / PAGE_SIZE;
+	/* length needs to be page aligned too */
+	length = max_npages * PAGE_SIZE;
+
+	/*
+	 * Use kvcalloc() to avoid memory fragmentation for a large page array.
+	 * Set __GFP_NOWARN to avoid syzkaller blowups
+	 */
+	pages = kvcalloc(max_npages, sizeof(*pages), GFP_KERNEL | __GFP_NOWARN);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
+
+	access = iommufd_access_create_internal(viommu->ictx);
+	if (IS_ERR(access)) {
+		rc = PTR_ERR(access);
+		goto out_free;
+	}
+
+	rc = iommufd_access_attach_internal(access, viommu->hwpt->ioas);
+	if (rc)
+		goto out_destroy;
+
+	rc = iommufd_access_pin_pages(access, aligned_iova, length, pages, 0);
+	if (rc)
+		goto out_detach;
+
+	/* Validate if the underlying physical pages are contiguous */
+	for (i = 1; i < max_npages; i++) {
+		if (page_to_pfn(pages[i]) == page_to_pfn(pages[i - 1]) + 1)
+			continue;
+		rc = -EFAULT;
+		goto out_unpin;
+	}
+
+	*base_pa = (page_to_pfn(pages[0]) << PAGE_SHIFT) + offset;
+	kfree(pages);
+	return access;
+
+out_unpin:
+	iommufd_access_unpin_pages(access, aligned_iova, length);
+out_detach:
+	iommufd_access_detach_internal(access);
+out_destroy:
+	iommufd_access_destroy_internal(viommu->ictx, access);
+out_free:
+	kfree(pages);
+	return ERR_PTR(rc);
+}
+
+int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd)
+{
+	struct iommu_hw_queue_alloc *cmd = ucmd->cmd;
+	struct iommufd_hw_queue *hw_queue;
+	struct iommufd_viommu *viommu;
+	struct iommufd_access *access;
+	size_t hw_queue_size;
+	phys_addr_t base_pa;
+	u64 last;
+	int rc;
+
+	if (cmd->flags || cmd->type == IOMMU_HW_QUEUE_TYPE_DEFAULT)
+		return -EOPNOTSUPP;
+	if (!cmd->length)
+		return -EINVAL;
+	if (check_add_overflow(cmd->nesting_parent_iova, cmd->length - 1,
+			       &last))
+		return -EOVERFLOW;
+
+	viommu = iommufd_get_viommu(ucmd, cmd->viommu_id);
+	if (IS_ERR(viommu))
+		return PTR_ERR(viommu);
+
+	if (!viommu->ops || !viommu->ops->get_hw_queue_size ||
+	    !viommu->ops->hw_queue_init_phys) {
+		rc = -EOPNOTSUPP;
+		goto out_put_viommu;
+	}
+
+	hw_queue_size = viommu->ops->get_hw_queue_size(viommu, cmd->type);
+	if (!hw_queue_size) {
+		rc = -EOPNOTSUPP;
+		goto out_put_viommu;
+	}
+
+	/*
+	 * It is a driver bug for providing a hw_queue_size smaller than the
+	 * core HW queue structure size
+	 */
+	if (WARN_ON_ONCE(hw_queue_size < sizeof(*hw_queue))) {
+		rc = -EOPNOTSUPP;
+		goto out_put_viommu;
+	}
+
+	hw_queue = (struct iommufd_hw_queue *)_iommufd_object_alloc_ucmd(
+		ucmd, hw_queue_size, IOMMUFD_OBJ_HW_QUEUE);
+	if (IS_ERR(hw_queue)) {
+		rc = PTR_ERR(hw_queue);
+		goto out_put_viommu;
+	}
+
+	access = iommufd_hw_queue_alloc_phys(cmd, viommu, &base_pa);
+	if (IS_ERR(access)) {
+		rc = PTR_ERR(access);
+		goto out_put_viommu;
+	}
+
+	hw_queue->viommu = viommu;
+	refcount_inc(&viommu->obj.users);
+	hw_queue->access = access;
+	hw_queue->type = cmd->type;
+	hw_queue->length = cmd->length;
+	hw_queue->base_addr = cmd->nesting_parent_iova;
+
+	rc = viommu->ops->hw_queue_init_phys(hw_queue, cmd->index, base_pa);
+	if (rc)
+		goto out_put_viommu;
+
+	cmd->out_hw_queue_id = hw_queue->obj.id;
+	rc = iommufd_ucmd_respond(ucmd, sizeof(*cmd));
+
+out_put_viommu:
+	iommufd_put_object(ucmd->ictx, &viommu->obj);
+	return rc;
+}
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index f13f3ca6adb5..ce4011a2fc27 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -123,6 +123,7 @@ struct iommufd_vdevice {
 struct iommufd_hw_queue {
 	struct iommufd_object obj;
 	struct iommufd_viommu *viommu;
+	struct iommufd_access *access;
 
 	u64 base_addr; /* in guest physical address space */
 	size_t length;
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 640a8b5147c2..b928c1ed2395 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -56,6 +56,7 @@ enum {
 	IOMMUFD_CMD_VDEVICE_ALLOC = 0x91,
 	IOMMUFD_CMD_IOAS_CHANGE_PROCESS = 0x92,
 	IOMMUFD_CMD_VEVENTQ_ALLOC = 0x93,
+	IOMMUFD_CMD_HW_QUEUE_ALLOC = 0x94,
 };
 
 /**
@@ -1156,4 +1157,37 @@ enum iommu_hw_queue_type {
 	IOMMU_HW_QUEUE_TYPE_DEFAULT = 0,
 };
 
+/**
+ * struct iommu_hw_queue_alloc - ioctl(IOMMU_HW_QUEUE_ALLOC)
+ * @size: sizeof(struct iommu_hw_queue_alloc)
+ * @flags: Must be 0
+ * @viommu_id: Virtual IOMMU ID to associate the HW queue with
+ * @type: One of enum iommu_hw_queue_type
+ * @index: The logical index to the HW queue per virtual IOMMU for a multi-queue
+ *         model
+ * @out_hw_queue_id: The ID of the new HW queue
+ * @nesting_parent_iova: Base address of the queue memory in the guest physical
+ *                       address space
+ * @length: Length of the queue memory
+ *
+ * Allocate a HW queue object for a vIOMMU-specific HW-accelerated queue, which
+ * allows HW to access a guest queue memory described using @nesting_parent_iova
+ * and @length.
+ *
+ * A vIOMMU can allocate multiple queues, but it must use a different @index per
+ * type to separate each allocation, e.g::
+ *
+ *     Type1 HW queue0, Type1 HW queue1, Type2 HW queue0, ...
+ */
+struct iommu_hw_queue_alloc {
+	__u32 size;
+	__u32 flags;
+	__u32 viommu_id;
+	__u32 type;
+	__u32 index;
+	__u32 out_hw_queue_id;
+	__aligned_u64 nesting_parent_iova;
+	__aligned_u64 length;
+};
+#define IOMMU_HW_QUEUE_ALLOC _IO(IOMMUFD_TYPE, IOMMUFD_CMD_HW_QUEUE_ALLOC)
 #endif
-- 
cgit v1.2.3


From 0b37d892d0425811618a737037b0212884cc25ae Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:59:07 -0700
Subject: iommufd/driver: Add iommufd_hw_queue_depend/undepend() helpers

NVIDIA Virtual Command Queue is one of the iommufd users exposing vIOMMU
features to user space VMs. Its hardware has a strict rule when mapping
and unmapping multiple global CMDQVs to/from a VM-owned VINTF, requiring
mappings in ascending order and unmappings in descending order.

The tegra241-cmdqv driver can apply the rule for a mapping in the LVCMDQ
allocation handler. However, it can't do the same for an unmapping since
user space could start random destroy calls breaking the rule, while the
destroy op in the driver level can't reject a destroy call as it returns
void.

Add iommufd_hw_queue_depend/undepend for-driver helpers, allowing LVCMDQ
allocator to refcount_inc() a sibling LVCMDQ object and LVCMDQ destroyer
to refcount_dec(), so that iommufd core will help block a random destroy
call that breaks the rule.

This is a bit of compromise, because a driver might end up with abusing
the API that deadlocks the objects. So restrict the API to a dependency
between two driver-allocated objects of the same type, as iommufd would
unlikely build any core-level dependency in this case. And encourage to
use the macro version that currently supports the HW QUEUE objects only.

Link: https://patch.msgid.link/r/2735c32e759c82f2e6c87cb32134eaf09b7589b5.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/driver.c | 28 +++++++++++++++++++++++++++
 include/linux/iommufd.h        | 44 ++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c
index 887719016804..e578ef32d30c 100644
--- a/drivers/iommu/iommufd/driver.c
+++ b/drivers/iommu/iommufd/driver.c
@@ -3,6 +3,34 @@
  */
 #include "iommufd_private.h"
 
+/* Driver should use a per-structure helper in include/linux/iommufd.h */
+int _iommufd_object_depend(struct iommufd_object *obj_dependent,
+			   struct iommufd_object *obj_depended)
+{
+	/* Reject self dependency that dead locks */
+	if (obj_dependent == obj_depended)
+		return -EINVAL;
+	/* Only support dependency between two objects of the same type */
+	if (obj_dependent->type != obj_depended->type)
+		return -EINVAL;
+
+	refcount_inc(&obj_depended->users);
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(_iommufd_object_depend, "IOMMUFD");
+
+/* Driver should use a per-structure helper in include/linux/iommufd.h */
+void _iommufd_object_undepend(struct iommufd_object *obj_dependent,
+			      struct iommufd_object *obj_depended)
+{
+	if (WARN_ON_ONCE(obj_dependent == obj_depended ||
+			 obj_dependent->type != obj_depended->type))
+		return;
+
+	refcount_dec(&obj_depended->users);
+}
+EXPORT_SYMBOL_NS_GPL(_iommufd_object_undepend, "IOMMUFD");
+
 /* Caller should xa_lock(&viommu->vdevs) to protect the return value */
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id)
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index ce4011a2fc27..fa23439fa483 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -251,6 +251,10 @@ static inline int iommufd_vfio_compat_set_no_iommu(struct iommufd_ctx *ictx)
 #endif /* CONFIG_IOMMUFD */
 
 #if IS_ENABLED(CONFIG_IOMMUFD_DRIVER_CORE)
+int _iommufd_object_depend(struct iommufd_object *obj_dependent,
+			   struct iommufd_object *obj_depended);
+void _iommufd_object_undepend(struct iommufd_object *obj_dependent,
+			      struct iommufd_object *obj_depended);
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id);
 int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
@@ -259,6 +263,18 @@ int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 				enum iommu_veventq_type type, void *event_data,
 				size_t data_len);
 #else /* !CONFIG_IOMMUFD_DRIVER_CORE */
+static inline int _iommufd_object_depend(struct iommufd_object *obj_dependent,
+					 struct iommufd_object *obj_depended)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void
+_iommufd_object_undepend(struct iommufd_object *obj_dependent,
+			 struct iommufd_object *obj_depended)
+{
+}
+
 static inline struct device *
 iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)
 {
@@ -298,4 +314,32 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 	 BUILD_BUG_ON_ZERO(!__same_type(struct iommufd_hw_queue,               \
 					((drv_struct *)NULL)->member)))
 
+/*
+ * Helpers for IOMMU driver to build/destroy a dependency between two sibling
+ * structures created by one of the allocators above
+ */
+#define iommufd_hw_queue_depend(dependent, depended, member)                   \
+	({                                                                     \
+		int ret = -EINVAL;                                             \
+									       \
+		static_assert(__same_type(struct iommufd_hw_queue,             \
+					  dependent->member));                 \
+		static_assert(__same_type(typeof(*dependent), *depended));     \
+		if (!WARN_ON_ONCE(dependent->member.viommu !=                  \
+				  depended->member.viommu))                    \
+			ret = _iommufd_object_depend(&dependent->member.obj,   \
+						     &depended->member.obj);   \
+		ret;                                                           \
+	})
+
+#define iommufd_hw_queue_undepend(dependent, depended, member)                 \
+	({                                                                     \
+		static_assert(__same_type(struct iommufd_hw_queue,             \
+					  dependent->member));                 \
+		static_assert(__same_type(typeof(*dependent), *depended));     \
+		WARN_ON_ONCE(dependent->member.viommu !=                       \
+			     depended->member.viommu);                         \
+		_iommufd_object_undepend(&dependent->member.obj,               \
+					 &depended->member.obj);               \
+	})
 #endif
-- 
cgit v1.2.3


From 19c24f7ee39af503b9731067b91add627b70ecb6 Mon Sep 17 00:00:00 2001
From: David Kaplan <david.kaplan@amd.com>
Date: Mon, 7 Jul 2025 13:32:57 -0500
Subject: cpu: Define attack vectors

Define 4 new attack vectors that are used for controlling CPU speculation
mitigations.  These may be individually disabled as part of the
mitigations= command line.  Attack vector controls are combined with global
options like 'auto' or 'auto,nosmt' like 'mitigations=auto,no_user_kernel'.
The global options come first in the mitigations= string.

Cross-thread mitigations can either remain enabled fully, including
potentially disabling SMT ('auto,nosmt'), remain enabled except for
disabling SMT ('auto'), or entirely disabled through the new
'no_cross_thread' attack vector option.

The default settings for these attack vectors are consistent with existing
kernel defaults, other than the automatic disabling of VM-based attack
vectors if KVM support is not present.

Signed-off-by: David Kaplan <david.kaplan@amd.com>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Link: https://lore.kernel.org/20250707183316.1349127-3-david.kaplan@amd.com
---
 include/linux/cpu.h |  21 +++++++++
 kernel/cpu.c        | 130 +++++++++++++++++++++++++++++++++++++++++++++++-----
 2 files changed, 140 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 6378370a952f..1fb143ee1ffa 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -198,9 +198,25 @@ void cpuhp_report_idle_dead(void);
 static inline void cpuhp_report_idle_dead(void) { }
 #endif /* #ifdef CONFIG_HOTPLUG_CPU */
 
+enum cpu_attack_vectors {
+	CPU_MITIGATE_USER_KERNEL,
+	CPU_MITIGATE_USER_USER,
+	CPU_MITIGATE_GUEST_HOST,
+	CPU_MITIGATE_GUEST_GUEST,
+	NR_CPU_ATTACK_VECTORS,
+};
+
+enum smt_mitigations {
+	SMT_MITIGATIONS_OFF,
+	SMT_MITIGATIONS_AUTO,
+	SMT_MITIGATIONS_ON,
+};
+
 #ifdef CONFIG_CPU_MITIGATIONS
 extern bool cpu_mitigations_off(void);
 extern bool cpu_mitigations_auto_nosmt(void);
+extern bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v);
+extern enum smt_mitigations smt_mitigations;
 #else
 static inline bool cpu_mitigations_off(void)
 {
@@ -210,6 +226,11 @@ static inline bool cpu_mitigations_auto_nosmt(void)
 {
 	return false;
 }
+static inline bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v)
+{
+	return false;
+}
+#define smt_mitigations SMT_MITIGATIONS_OFF
 #endif
 
 #endif /* _LINUX_CPU_H_ */
diff --git a/kernel/cpu.c b/kernel/cpu.c
index a59e009e0be4..faf0f23fc5d8 100644
--- a/kernel/cpu.c
+++ b/kernel/cpu.c
@@ -37,6 +37,7 @@
 #include <linux/cpuset.h>
 #include <linux/random.h>
 #include <linux/cc_platform.h>
+#include <linux/parser.h>
 
 #include <trace/events/power.h>
 #define CREATE_TRACE_POINTS
@@ -3174,8 +3175,38 @@ void __init boot_cpu_hotplug_init(void)
 
 #ifdef CONFIG_CPU_MITIGATIONS
 /*
- * These are used for a global "mitigations=" cmdline option for toggling
- * optional CPU mitigations.
+ * All except the cross-thread attack vector are mitigated by default.
+ * Cross-thread mitigation often requires disabling SMT which is expensive
+ * so cross-thread mitigations are only partially enabled by default.
+ *
+ * Guest-to-Host and Guest-to-Guest vectors are only needed if KVM support is
+ * present.
+ */
+static bool attack_vectors[NR_CPU_ATTACK_VECTORS] __ro_after_init = {
+	[CPU_MITIGATE_USER_KERNEL] = true,
+	[CPU_MITIGATE_USER_USER] = true,
+	[CPU_MITIGATE_GUEST_HOST] = IS_ENABLED(CONFIG_KVM),
+	[CPU_MITIGATE_GUEST_GUEST] = IS_ENABLED(CONFIG_KVM),
+};
+
+bool cpu_attack_vector_mitigated(enum cpu_attack_vectors v)
+{
+	if (v < NR_CPU_ATTACK_VECTORS)
+		return attack_vectors[v];
+
+	WARN_ONCE(1, "Invalid attack vector %d\n", v);
+	return false;
+}
+
+/*
+ * There are 3 global options, 'off', 'auto', 'auto,nosmt'. These may optionally
+ * be combined with attack-vector disables which follow them.
+ *
+ * Examples:
+ *   mitigations=auto,no_user_kernel,no_user_user,no_cross_thread
+ *   mitigations=auto,nosmt,no_guest_host,no_guest_guest
+ *
+ * mitigations=off is equivalent to disabling all attack vectors.
  */
 enum cpu_mitigations {
 	CPU_MITIGATIONS_OFF,
@@ -3183,19 +3214,96 @@ enum cpu_mitigations {
 	CPU_MITIGATIONS_AUTO_NOSMT,
 };
 
+enum {
+	NO_USER_KERNEL,
+	NO_USER_USER,
+	NO_GUEST_HOST,
+	NO_GUEST_GUEST,
+	NO_CROSS_THREAD,
+	NR_VECTOR_PARAMS,
+};
+
+enum smt_mitigations smt_mitigations __ro_after_init = SMT_MITIGATIONS_AUTO;
 static enum cpu_mitigations cpu_mitigations __ro_after_init = CPU_MITIGATIONS_AUTO;
 
+static const match_table_t global_mitigations = {
+	{ CPU_MITIGATIONS_AUTO_NOSMT,	"auto,nosmt"},
+	{ CPU_MITIGATIONS_AUTO,		"auto"},
+	{ CPU_MITIGATIONS_OFF,		"off"},
+};
+
+static const match_table_t vector_mitigations = {
+	{ NO_USER_KERNEL,	"no_user_kernel"},
+	{ NO_USER_USER,		"no_user_user"},
+	{ NO_GUEST_HOST,	"no_guest_host"},
+	{ NO_GUEST_GUEST,	"no_guest_guest"},
+	{ NO_CROSS_THREAD,	"no_cross_thread"},
+	{ NR_VECTOR_PARAMS,	NULL},
+};
+
+static int __init mitigations_parse_global_opt(char *arg)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(global_mitigations); i++) {
+		const char *pattern = global_mitigations[i].pattern;
+
+		if (!strncmp(arg, pattern, strlen(pattern))) {
+			cpu_mitigations = global_mitigations[i].token;
+			return strlen(pattern);
+		}
+	}
+
+	return 0;
+}
+
 static int __init mitigations_parse_cmdline(char *arg)
 {
-	if (!strcmp(arg, "off"))
-		cpu_mitigations = CPU_MITIGATIONS_OFF;
-	else if (!strcmp(arg, "auto"))
-		cpu_mitigations = CPU_MITIGATIONS_AUTO;
-	else if (!strcmp(arg, "auto,nosmt"))
-		cpu_mitigations = CPU_MITIGATIONS_AUTO_NOSMT;
-	else
-		pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n",
-			arg);
+	char *s, *p;
+	int len;
+
+	len = mitigations_parse_global_opt(arg);
+
+	if (cpu_mitigations_off()) {
+		memset(attack_vectors, 0, sizeof(attack_vectors));
+		smt_mitigations = SMT_MITIGATIONS_OFF;
+	} else if (cpu_mitigations_auto_nosmt()) {
+		smt_mitigations = SMT_MITIGATIONS_ON;
+	}
+
+	p = arg + len;
+
+	if (!*p)
+		return 0;
+
+	/* Attack vector controls may come after the ',' */
+	if (*p++ != ',' || !IS_ENABLED(CONFIG_ARCH_HAS_CPU_ATTACK_VECTORS)) {
+		pr_crit("Unsupported mitigations=%s, system may still be vulnerable\n",	arg);
+		return 0;
+	}
+
+	while ((s = strsep(&p, ",")) != NULL) {
+		switch (match_token(s, vector_mitigations, NULL)) {
+		case NO_USER_KERNEL:
+			attack_vectors[CPU_MITIGATE_USER_KERNEL] = false;
+			break;
+		case NO_USER_USER:
+			attack_vectors[CPU_MITIGATE_USER_USER] = false;
+			break;
+		case NO_GUEST_HOST:
+			attack_vectors[CPU_MITIGATE_GUEST_HOST] = false;
+			break;
+		case NO_GUEST_GUEST:
+			attack_vectors[CPU_MITIGATE_GUEST_GUEST] = false;
+			break;
+		case NO_CROSS_THREAD:
+			smt_mitigations = SMT_MITIGATIONS_OFF;
+			break;
+		default:
+			pr_crit("Unsupported mitigations options %s\n",	s);
+			return 0;
+		}
+	}
 
 	return 0;
 }
-- 
cgit v1.2.3


From 6cb786f040ad35b23b4a7bff8b9d772f22909d48 Mon Sep 17 00:00:00 2001
From: Ricardo Ribalda <ribalda@chromium.org>
Date: Mon, 7 Jul 2025 18:34:05 +0000
Subject: media: uvcvideo: Auto-set UVC_QUIRK_MSXU_META

If the camera supports the MSXU_CONTROL_METADATA control, auto set the
MSXU_META quirk.

Reviewed-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Ricardo Ribalda <ribalda@chromium.org>
Link: https://lore.kernel.org/r/20250707-uvc-meta-v8-5-ed17f8b1218b@chromium.org
Signed-off-by: Hans de Goede <hansg@kernel.org>
Signed-off-by: Hans Verkuil <hverkuil@xs4all.nl>
---
 drivers/media/usb/uvc/uvc_driver.c   |  7 +++-
 drivers/media/usb/uvc/uvc_metadata.c | 75 +++++++++++++++++++++++++++++++++++-
 drivers/media/usb/uvc/uvcvideo.h     |  2 +-
 include/linux/usb/uvc.h              |  3 ++
 4 files changed, 84 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
index b12c95fe8b0a..775bede0d93d 100644
--- a/drivers/media/usb/uvc/uvc_driver.c
+++ b/drivers/media/usb/uvc/uvc_driver.c
@@ -2293,7 +2293,12 @@ static int uvc_probe(struct usb_interface *intf,
 		goto error;
 	}
 
-	uvc_meta_init(dev);
+	ret = uvc_meta_init(dev);
+	if (ret < 0) {
+		dev_err(&dev->udev->dev,
+			"Error initializing the metadata formats (%d)\n", ret);
+		goto error;
+	}
 
 	if (dev->quirks & UVC_QUIRK_NO_RESET_RESUME)
 		udev->quirks &= ~USB_QUIRK_RESET_RESUME;
diff --git a/drivers/media/usb/uvc/uvc_metadata.c b/drivers/media/usb/uvc/uvc_metadata.c
index d0ee139dbda7..12972527ab8d 100644
--- a/drivers/media/usb/uvc/uvc_metadata.c
+++ b/drivers/media/usb/uvc/uvc_metadata.c
@@ -10,6 +10,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/usb.h>
+#include <linux/usb/uvc.h>
 #include <linux/videodev2.h>
 
 #include <media/v4l2-ioctl.h>
@@ -166,6 +167,71 @@ static const struct v4l2_file_operations uvc_meta_fops = {
 	.mmap = vb2_fop_mmap,
 };
 
+static struct uvc_entity *uvc_meta_find_msxu(struct uvc_device *dev)
+{
+	static const u8 uvc_msxu_guid[16] = UVC_GUID_MSXU_1_5;
+	struct uvc_entity *entity;
+
+	list_for_each_entry(entity, &dev->entities, list) {
+		if (!memcmp(entity->guid, uvc_msxu_guid, sizeof(entity->guid)))
+			return entity;
+	}
+
+	return NULL;
+}
+
+#define MSXU_CONTROL_METADATA 0x9
+static int uvc_meta_detect_msxu(struct uvc_device *dev)
+{
+	u32 *data __free(kfree) = NULL;
+	struct uvc_entity *entity;
+	int ret;
+
+	entity = uvc_meta_find_msxu(dev);
+	if (!entity)
+		return 0;
+
+	/*
+	 * USB requires buffers aligned in a special way, simplest way is to
+	 * make sure that query_ctrl will work is to kmalloc() them.
+	 */
+	data = kmalloc(sizeof(*data), GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	/* Check if the metadata is already enabled. */
+	ret = uvc_query_ctrl(dev, UVC_GET_CUR, entity->id, dev->intfnum,
+			     MSXU_CONTROL_METADATA, data, sizeof(*data));
+	if (ret)
+		return 0;
+
+	if (*data) {
+		dev->quirks |= UVC_QUIRK_MSXU_META;
+		return 0;
+	}
+
+	/*
+	 * We have seen devices that require 1 to enable the metadata, others
+	 * requiring a value != 1 and others requiring a value >1. Luckily for
+	 * us, the value from GET_MAX seems to work all the time.
+	 */
+	ret = uvc_query_ctrl(dev, UVC_GET_MAX, entity->id, dev->intfnum,
+			     MSXU_CONTROL_METADATA, data, sizeof(*data));
+	if (ret || !*data)
+		return 0;
+
+	/*
+	 * If we can set MSXU_CONTROL_METADATA, the device will report
+	 * metadata.
+	 */
+	ret = uvc_query_ctrl(dev, UVC_SET_CUR, entity->id, dev->intfnum,
+			     MSXU_CONTROL_METADATA, data, sizeof(*data));
+	if (!ret)
+		dev->quirks |= UVC_QUIRK_MSXU_META;
+
+	return 0;
+}
+
 int uvc_meta_register(struct uvc_streaming *stream)
 {
 	struct uvc_device *dev = stream->dev;
@@ -179,9 +245,14 @@ int uvc_meta_register(struct uvc_streaming *stream)
 					 &uvc_meta_fops, &uvc_meta_ioctl_ops);
 }
 
-void uvc_meta_init(struct uvc_device *dev)
+int uvc_meta_init(struct uvc_device *dev)
 {
 	unsigned int i = 0;
+	int ret;
+
+	ret = uvc_meta_detect_msxu(dev);
+	if (ret)
+		return ret;
 
 	dev->meta_formats[i++] = V4L2_META_FMT_UVC;
 
@@ -195,4 +266,6 @@ void uvc_meta_init(struct uvc_device *dev)
 
 	 /* IMPORTANT: for new meta-formats update UVC_MAX_META_DATA_FORMATS. */
 	dev->meta_formats[i++] = 0;
+
+	return 0;
 }
diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
index eb164d063199..b34c1914ff39 100644
--- a/drivers/media/usb/uvc/uvcvideo.h
+++ b/drivers/media/usb/uvc/uvcvideo.h
@@ -728,7 +728,7 @@ int uvc_query_ctrl(struct uvc_device *dev, u8 query, u8 unit,
 void uvc_video_clock_update(struct uvc_streaming *stream,
 			    struct vb2_v4l2_buffer *vbuf,
 			    struct uvc_buffer *buf);
-void uvc_meta_init(struct uvc_device *dev);
+int uvc_meta_init(struct uvc_device *dev);
 int uvc_meta_register(struct uvc_streaming *stream);
 
 int uvc_register_video_device(struct uvc_device *dev,
diff --git a/include/linux/usb/uvc.h b/include/linux/usb/uvc.h
index bce95153e5a6..ee19e9f915b8 100644
--- a/include/linux/usb/uvc.h
+++ b/include/linux/usb/uvc.h
@@ -29,6 +29,9 @@
 #define UVC_GUID_EXT_GPIO_CONTROLLER \
 	{0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, \
 	 0x00, 0x00, 0x00, 0x00, 0x00, 0x00, 0x01, 0x03}
+#define UVC_GUID_MSXU_1_5 \
+	{0xdc, 0x95, 0x3f, 0x0f, 0x32, 0x26, 0x4e, 0x4c, \
+	 0x92, 0xc9, 0xa0, 0x47, 0x82, 0xf4, 0x3b, 0xc8}
 
 #define UVC_GUID_FORMAT_MJPEG \
 	{ 'M',  'J',  'P',  'G', 0x00, 0x00, 0x10, 0x00, \
-- 
cgit v1.2.3


From 56e9a0d8e53f56f313d332888a32a44a71f3a9ab Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:59:09 -0700
Subject: iommufd: Add mmap interface

For vIOMMU passing through HW resources to user space (VMs), allowing a VM
to control the passed through HW directly by accessing hardware registers,
add an mmap infrastructure to map the physical MMIO pages to user space.

Maintain a maple tree per ictx as a translation table managing mmappable
regions, from an allocated for-user mmap offset to an iommufd_mmap struct,
where it stores the real physical address range for io_remap_pfn_range().

Keep track of the lifecycle of the mmappable region by taking refcount of
its owner, so as to enforce user space to unmap the region first before it
can destroy its owner object.

To allow an IOMMU driver to add and delete mmappable regions onto/from the
maple tree, add iommufd_viommu_alloc/destroy_mmap helpers.

Link: https://patch.msgid.link/r/9a888a326b12aa5fe940083eae1156304e210fe0.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/driver.c          | 52 +++++++++++++++++++++++++++
 drivers/iommu/iommufd/iommufd_private.h | 14 ++++++++
 drivers/iommu/iommufd/main.c            | 63 +++++++++++++++++++++++++++++++++
 include/linux/iommufd.h                 | 42 ++++++++++++++++++++++
 4 files changed, 171 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c
index e578ef32d30c..e4eae20bcd4e 100644
--- a/drivers/iommu/iommufd/driver.c
+++ b/drivers/iommu/iommufd/driver.c
@@ -31,6 +31,58 @@ void _iommufd_object_undepend(struct iommufd_object *obj_dependent,
 }
 EXPORT_SYMBOL_NS_GPL(_iommufd_object_undepend, "IOMMUFD");
 
+/*
+ * Allocate an @offset to return to user space to use for an mmap() syscall
+ *
+ * Driver should use a per-structure helper in include/linux/iommufd.h
+ */
+int _iommufd_alloc_mmap(struct iommufd_ctx *ictx, struct iommufd_object *owner,
+			phys_addr_t mmio_addr, size_t length,
+			unsigned long *offset)
+{
+	struct iommufd_mmap *immap;
+	unsigned long startp;
+	int rc;
+
+	if (!PAGE_ALIGNED(mmio_addr))
+		return -EINVAL;
+	if (!length || !PAGE_ALIGNED(length))
+		return -EINVAL;
+
+	immap = kzalloc(sizeof(*immap), GFP_KERNEL);
+	if (!immap)
+		return -ENOMEM;
+	immap->owner = owner;
+	immap->length = length;
+	immap->mmio_addr = mmio_addr;
+
+	/* Skip the first page to ease caller identifying the returned offset */
+	rc = mtree_alloc_range(&ictx->mt_mmap, &startp, immap, immap->length,
+			       PAGE_SIZE, ULONG_MAX, GFP_KERNEL);
+	if (rc < 0) {
+		kfree(immap);
+		return rc;
+	}
+
+	/* mmap() syscall will right-shift the offset in vma->vm_pgoff too */
+	immap->vm_pgoff = startp >> PAGE_SHIFT;
+	*offset = startp;
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(_iommufd_alloc_mmap, "IOMMUFD");
+
+/* Driver should use a per-structure helper in include/linux/iommufd.h */
+void _iommufd_destroy_mmap(struct iommufd_ctx *ictx,
+			   struct iommufd_object *owner, unsigned long offset)
+{
+	struct iommufd_mmap *immap;
+
+	immap = mtree_erase(&ictx->mt_mmap, offset);
+	WARN_ON_ONCE(!immap || immap->owner != owner);
+	kfree(immap);
+}
+EXPORT_SYMBOL_NS_GPL(_iommufd_destroy_mmap, "IOMMUFD");
+
 /* Caller should xa_lock(&viommu->vdevs) to protect the return value */
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id)
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index dcd609573244..cd14163abdd1 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -7,6 +7,7 @@
 #include <linux/iommu.h>
 #include <linux/iommufd.h>
 #include <linux/iova_bitmap.h>
+#include <linux/maple_tree.h>
 #include <linux/rwsem.h>
 #include <linux/uaccess.h>
 #include <linux/xarray.h>
@@ -44,6 +45,7 @@ struct iommufd_ctx {
 	struct xarray groups;
 	wait_queue_head_t destroy_wait;
 	struct rw_semaphore ioas_creation_lock;
+	struct maple_tree mt_mmap;
 
 	struct mutex sw_msi_lock;
 	struct list_head sw_msi_list;
@@ -55,6 +57,18 @@ struct iommufd_ctx {
 	struct iommufd_ioas *vfio_ioas;
 };
 
+/* Entry for iommufd_ctx::mt_mmap */
+struct iommufd_mmap {
+	struct iommufd_object *owner;
+
+	/* Page-shifted start position in mt_mmap to validate vma->vm_pgoff */
+	unsigned long vm_pgoff;
+
+	/* Physical range for io_remap_pfn_range() */
+	phys_addr_t mmio_addr;
+	size_t length;
+};
+
 /*
  * The IOVA to PFN map. The map automatically copies the PFNs into multiple
  * domains and permits sharing of PFNs between io_pagetable instances. This
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 4e8dbbfac890..0fb81a905cb1 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -275,6 +275,7 @@ static int iommufd_fops_open(struct inode *inode, struct file *filp)
 	xa_init_flags(&ictx->objects, XA_FLAGS_ALLOC1 | XA_FLAGS_ACCOUNT);
 	xa_init(&ictx->groups);
 	ictx->file = filp;
+	mt_init_flags(&ictx->mt_mmap, MT_FLAGS_ALLOC_RANGE);
 	init_waitqueue_head(&ictx->destroy_wait);
 	mutex_init(&ictx->sw_msi_lock);
 	INIT_LIST_HEAD(&ictx->sw_msi_list);
@@ -479,11 +480,73 @@ static long iommufd_fops_ioctl(struct file *filp, unsigned int cmd,
 	return ret;
 }
 
+static void iommufd_fops_vma_open(struct vm_area_struct *vma)
+{
+	struct iommufd_mmap *immap = vma->vm_private_data;
+
+	refcount_inc(&immap->owner->users);
+}
+
+static void iommufd_fops_vma_close(struct vm_area_struct *vma)
+{
+	struct iommufd_mmap *immap = vma->vm_private_data;
+
+	refcount_dec(&immap->owner->users);
+}
+
+static const struct vm_operations_struct iommufd_vma_ops = {
+	.open = iommufd_fops_vma_open,
+	.close = iommufd_fops_vma_close,
+};
+
+/* The vm_pgoff must be pre-allocated from mt_mmap, and given to user space */
+static int iommufd_fops_mmap(struct file *filp, struct vm_area_struct *vma)
+{
+	struct iommufd_ctx *ictx = filp->private_data;
+	size_t length = vma->vm_end - vma->vm_start;
+	struct iommufd_mmap *immap;
+	int rc;
+
+	if (!PAGE_ALIGNED(length))
+		return -EINVAL;
+	if (!(vma->vm_flags & VM_SHARED))
+		return -EINVAL;
+	if (vma->vm_flags & VM_EXEC)
+		return -EPERM;
+
+	/* vma->vm_pgoff carries a page-shifted start position to an immap */
+	immap = mtree_load(&ictx->mt_mmap, vma->vm_pgoff << PAGE_SHIFT);
+	if (!immap)
+		return -ENXIO;
+	/*
+	 * mtree_load() returns the immap for any contained mmio_addr, so only
+	 * allow the exact immap thing to be mapped
+	 */
+	if (vma->vm_pgoff != immap->vm_pgoff || length != immap->length)
+		return -ENXIO;
+
+	vma->vm_pgoff = 0;
+	vma->vm_private_data = immap;
+	vma->vm_ops = &iommufd_vma_ops;
+	vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+
+	rc = io_remap_pfn_range(vma, vma->vm_start,
+				immap->mmio_addr >> PAGE_SHIFT, length,
+				vma->vm_page_prot);
+	if (rc)
+		return rc;
+
+	/* vm_ops.open won't be called for mmap itself. */
+	refcount_inc(&immap->owner->users);
+	return rc;
+}
+
 static const struct file_operations iommufd_fops = {
 	.owner = THIS_MODULE,
 	.open = iommufd_fops_open,
 	.release = iommufd_fops_release,
 	.unlocked_ioctl = iommufd_fops_ioctl,
+	.mmap = iommufd_fops_mmap,
 };
 
 /**
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index fa23439fa483..e3a0cd47384d 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -255,6 +255,11 @@ int _iommufd_object_depend(struct iommufd_object *obj_dependent,
 			   struct iommufd_object *obj_depended);
 void _iommufd_object_undepend(struct iommufd_object *obj_dependent,
 			      struct iommufd_object *obj_depended);
+int _iommufd_alloc_mmap(struct iommufd_ctx *ictx, struct iommufd_object *owner,
+			phys_addr_t mmio_addr, size_t length,
+			unsigned long *offset);
+void _iommufd_destroy_mmap(struct iommufd_ctx *ictx,
+			   struct iommufd_object *owner, unsigned long offset);
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id);
 int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
@@ -275,6 +280,20 @@ _iommufd_object_undepend(struct iommufd_object *obj_dependent,
 {
 }
 
+static inline int _iommufd_alloc_mmap(struct iommufd_ctx *ictx,
+				      struct iommufd_object *owner,
+				      phys_addr_t mmio_addr, size_t length,
+				      unsigned long *offset)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline void _iommufd_destroy_mmap(struct iommufd_ctx *ictx,
+					 struct iommufd_object *owner,
+					 unsigned long offset)
+{
+}
+
 static inline struct device *
 iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)
 {
@@ -342,4 +361,27 @@ static inline int iommufd_viommu_report_event(struct iommufd_viommu *viommu,
 		_iommufd_object_undepend(&dependent->member.obj,               \
 					 &depended->member.obj);               \
 	})
+
+/*
+ * Helpers for IOMMU driver to alloc/destroy an mmapable area for a structure.
+ *
+ * To support an mmappable MMIO region, kernel driver must first register it to
+ * iommufd core to allocate an @offset, during a driver-structure initialization
+ * (e.g. viommu_init op). Then, it should report to user space this @offset and
+ * the @length of the MMIO region for mmap syscall.
+ */
+static inline int iommufd_viommu_alloc_mmap(struct iommufd_viommu *viommu,
+					    phys_addr_t mmio_addr,
+					    size_t length,
+					    unsigned long *offset)
+{
+	return _iommufd_alloc_mmap(viommu->ictx, &viommu->obj, mmio_addr,
+				   length, offset);
+}
+
+static inline void iommufd_viommu_destroy_mmap(struct iommufd_viommu *viommu,
+					       unsigned long offset)
+{
+	_iommufd_destroy_mmap(viommu->ictx, &viommu->obj, offset);
+}
 #endif
-- 
cgit v1.2.3


From 62622a8753fa6af3c104f9552863e6473b92fb31 Mon Sep 17 00:00:00 2001
From: Nicolin Chen <nicolinc@nvidia.com>
Date: Wed, 9 Jul 2025 22:59:12 -0700
Subject: iommu: Allow an input type in hw_info op

The hw_info uAPI will support a bidirectional data_type field that can be
used as an input field for user space to request for a specific info data.

To prepare for the uAPI update, change the iommu layer first:
 - Add a new IOMMU_HW_INFO_TYPE_DEFAULT as an input, for which driver can
   output its only (or firstly) supported type
 - Update the kdoc accordingly
 - Roll out the type validation in the existing drivers

Link: https://patch.msgid.link/r/00f4a2d3d930721f61367014717b3ba2d1e82a81.1752126748.git.nicolinc@nvidia.com
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Pranjal Shrivastava <praan@google.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c | 4 ++++
 drivers/iommu/intel/iommu.c                         | 4 ++++
 drivers/iommu/iommufd/device.c                      | 3 +++
 drivers/iommu/iommufd/selftest.c                    | 4 ++++
 include/linux/iommu.h                               | 3 ++-
 include/uapi/linux/iommufd.h                        | 4 +++-
 6 files changed, 20 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
index 170d69162848..eb9fe1f6311a 100644
--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
+++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3-iommufd.c
@@ -15,6 +15,10 @@ void *arm_smmu_hw_info(struct device *dev, u32 *length,
 	u32 __iomem *base_idr;
 	unsigned int i;
 
+	if (*type != IOMMU_HW_INFO_TYPE_DEFAULT &&
+	    *type != IOMMU_HW_INFO_TYPE_ARM_SMMUV3)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 850f1a6f548c..5f75faffca15 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -4098,6 +4098,10 @@ static void *intel_iommu_hw_info(struct device *dev, u32 *length,
 	struct intel_iommu *iommu = info->iommu;
 	struct iommu_hw_info_vtd *vtd;
 
+	if (*type != IOMMU_HW_INFO_TYPE_DEFAULT &&
+	    *type != IOMMU_HW_INFO_TYPE_INTEL_VTD)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	vtd = kzalloc(sizeof(*vtd), GFP_KERNEL);
 	if (!vtd)
 		return ERR_PTR(-ENOMEM);
diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index 0567faff5680..14955dc43892 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -1512,6 +1512,9 @@ int iommufd_get_hw_info(struct iommufd_ucmd *ucmd)
 	    cmd->__reserved[2])
 		return -EOPNOTSUPP;
 
+	/* Clear the type field since drivers don't support a random input */
+	cmd->out_data_type = IOMMU_HW_INFO_TYPE_DEFAULT;
+
 	idev = iommufd_get_device(ucmd, cmd->dev_id);
 	if (IS_ERR(idev))
 		return PTR_ERR(idev);
diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
index 8b2c44b32530..a5dc36219a90 100644
--- a/drivers/iommu/iommufd/selftest.c
+++ b/drivers/iommu/iommufd/selftest.c
@@ -310,6 +310,10 @@ static void *mock_domain_hw_info(struct device *dev, u32 *length,
 {
 	struct iommu_test_hw_info *info;
 
+	if (*type != IOMMU_HW_INFO_TYPE_DEFAULT &&
+	    *type != IOMMU_HW_INFO_TYPE_SELFTEST)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	info = kzalloc(sizeof(*info), GFP_KERNEL);
 	if (!info)
 		return ERR_PTR(-ENOMEM);
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index e06a0fbe4bc7..e8b59ef54e48 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -603,7 +603,8 @@ __iommu_copy_struct_to_user(const struct iommu_user_data *dst_data,
  * @capable: check capability
  * @hw_info: report iommu hardware information. The data buffer returned by this
  *           op is allocated in the iommu driver and freed by the caller after
- *           use.
+ *           use. @type can input a requested type and output a supported type.
+ *           Driver should reject an unsupported data @type input
  * @domain_alloc: Do not use in new drivers
  * @domain_alloc_identity: allocate an IDENTITY domain. Drivers should prefer to
  *                         use identity_domain instead. This should only be used
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index b928c1ed2395..9c8c304b5de2 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -593,13 +593,15 @@ struct iommu_hw_info_arm_smmuv3 {
 
 /**
  * enum iommu_hw_info_type - IOMMU Hardware Info Types
- * @IOMMU_HW_INFO_TYPE_NONE: Used by the drivers that do not report hardware
+ * @IOMMU_HW_INFO_TYPE_NONE: Output by the drivers that do not report hardware
  *                           info
+ * @IOMMU_HW_INFO_TYPE_DEFAULT: Input to request for a default type
  * @IOMMU_HW_INFO_TYPE_INTEL_VTD: Intel VT-d iommu info type
  * @IOMMU_HW_INFO_TYPE_ARM_SMMUV3: ARM SMMUv3 iommu info type
  */
 enum iommu_hw_info_type {
 	IOMMU_HW_INFO_TYPE_NONE = 0,
+	IOMMU_HW_INFO_TYPE_DEFAULT = 0,
 	IOMMU_HW_INFO_TYPE_INTEL_VTD = 1,
 	IOMMU_HW_INFO_TYPE_ARM_SMMUV3 = 2,
 };
-- 
cgit v1.2.3


From b725441f02c2b31c04a95d0e9ca5420fa029a767 Mon Sep 17 00:00:00 2001
From: Tao Chen <chen.dylane@linux.dev>
Date: Thu, 10 Jul 2025 11:20:32 +0800
Subject: bpf: Add attach_type field to bpf_link

Attach_type will be set when a link is created by user. It is better to
record attach_type in bpf_link generically and have it available
universally for all link types. So add the attach_type field in bpf_link
and move the sleepable field to avoid unnecessary gap padding.

Signed-off-by: Tao Chen <chen.dylane@linux.dev>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20250710032038.888700-2-chen.dylane@linux.dev
---
 drivers/net/netkit.c           |  2 +-
 include/linux/bpf.h            | 28 +++++++++++++++++-----------
 kernel/bpf/bpf_iter.c          |  3 ++-
 kernel/bpf/bpf_struct_ops.c    |  5 +++--
 kernel/bpf/cgroup.c            |  4 ++--
 kernel/bpf/net_namespace.c     |  2 +-
 kernel/bpf/syscall.c           | 35 ++++++++++++++++++++++-------------
 kernel/bpf/tcx.c               |  3 ++-
 kernel/bpf/trampoline.c        | 10 ++++++----
 kernel/trace/bpf_trace.c       |  4 ++--
 net/bpf/bpf_dummy_struct_ops.c |  3 ++-
 net/core/dev.c                 |  3 ++-
 net/core/sock_map.c            |  3 ++-
 net/netfilter/nf_bpf_link.c    |  3 ++-
 14 files changed, 66 insertions(+), 42 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/netkit.c b/drivers/net/netkit.c
index d072a7968f56..5928c99eac73 100644
--- a/drivers/net/netkit.c
+++ b/drivers/net/netkit.c
@@ -775,7 +775,7 @@ static int netkit_link_init(struct netkit_link *nkl,
 			    struct bpf_prog *prog)
 {
 	bpf_link_init(&nkl->link, BPF_LINK_TYPE_NETKIT,
-		      &netkit_link_lops, prog);
+		      &netkit_link_lops, prog, attr->link_create.attach_type);
 	nkl->location = attr->link_create.attach_type;
 	nkl->dev = dev;
 	return bpf_link_prime(&nkl->link, link_primer);
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 34dd90ec7fad..a9ee9c14b486 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1729,12 +1729,10 @@ struct bpf_link {
 	enum bpf_link_type type;
 	const struct bpf_link_ops *ops;
 	struct bpf_prog *prog;
-	/* whether BPF link itself has "sleepable" semantics, which can differ
-	 * from underlying BPF program having a "sleepable" semantics, as BPF
-	 * link's semantics is determined by target attach hook
-	 */
-	bool sleepable;
+
 	u32 flags;
+	enum bpf_attach_type attach_type;
+
 	/* rcu is used before freeing, work can be used to schedule that
 	 * RCU-based freeing before that, so they never overlap
 	 */
@@ -1742,6 +1740,11 @@ struct bpf_link {
 		struct rcu_head rcu;
 		struct work_struct work;
 	};
+	/* whether BPF link itself has "sleepable" semantics, which can differ
+	 * from underlying BPF program having a "sleepable" semantics, as BPF
+	 * link's semantics is determined by target attach hook
+	 */
+	bool sleepable;
 };
 
 struct bpf_link_ops {
@@ -2034,11 +2037,13 @@ int bpf_prog_ctx_arg_info_init(struct bpf_prog *prog,
 
 #if defined(CONFIG_CGROUP_BPF) && defined(CONFIG_BPF_LSM)
 int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
-				    int cgroup_atype);
+				    int cgroup_atype,
+				    enum bpf_attach_type attach_type);
 void bpf_trampoline_unlink_cgroup_shim(struct bpf_prog *prog);
 #else
 static inline int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
-						  int cgroup_atype)
+						  int cgroup_atype,
+						  enum bpf_attach_type attach_type)
 {
 	return -EOPNOTSUPP;
 }
@@ -2528,10 +2533,11 @@ int bpf_map_new_fd(struct bpf_map *map, int flags);
 int bpf_prog_new_fd(struct bpf_prog *prog);
 
 void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
-		   const struct bpf_link_ops *ops, struct bpf_prog *prog);
+		   const struct bpf_link_ops *ops, struct bpf_prog *prog,
+		   enum bpf_attach_type attach_type);
 void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
 			     const struct bpf_link_ops *ops, struct bpf_prog *prog,
-			     bool sleepable);
+			     enum bpf_attach_type attach_type, bool sleepable);
 int bpf_link_prime(struct bpf_link *link, struct bpf_link_primer *primer);
 int bpf_link_settle(struct bpf_link_primer *primer);
 void bpf_link_cleanup(struct bpf_link_primer *primer);
@@ -2883,13 +2889,13 @@ bpf_prog_inc_not_zero(struct bpf_prog *prog)
 
 static inline void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
 				 const struct bpf_link_ops *ops,
-				 struct bpf_prog *prog)
+				 struct bpf_prog *prog, enum bpf_attach_type attach_type)
 {
 }
 
 static inline void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
 					   const struct bpf_link_ops *ops, struct bpf_prog *prog,
-					   bool sleepable)
+					   enum bpf_attach_type attach_type, bool sleepable)
 {
 }
 
diff --git a/kernel/bpf/bpf_iter.c b/kernel/bpf/bpf_iter.c
index 303ab1f42d3a..0cbcae727079 100644
--- a/kernel/bpf/bpf_iter.c
+++ b/kernel/bpf/bpf_iter.c
@@ -552,7 +552,8 @@ int bpf_iter_link_attach(const union bpf_attr *attr, bpfptr_t uattr,
 	if (!link)
 		return -ENOMEM;
 
-	bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_ITER, &bpf_iter_link_lops, prog,
+		      attr->link_create.attach_type);
 	link->tinfo = tinfo;
 
 	err = bpf_link_prime(&link->link, &link_primer);
diff --git a/kernel/bpf/bpf_struct_ops.c b/kernel/bpf/bpf_struct_ops.c
index 96113633e391..687a3e9c76f5 100644
--- a/kernel/bpf/bpf_struct_ops.c
+++ b/kernel/bpf/bpf_struct_ops.c
@@ -808,7 +808,7 @@ static long bpf_struct_ops_map_update_elem(struct bpf_map *map, void *key,
 			goto reset_unlock;
 		}
 		bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS,
-			      &bpf_struct_ops_link_lops, prog);
+			      &bpf_struct_ops_link_lops, prog, prog->expected_attach_type);
 		*plink++ = &link->link;
 
 		ksym = kzalloc(sizeof(*ksym), GFP_USER);
@@ -1351,7 +1351,8 @@ int bpf_struct_ops_link_create(union bpf_attr *attr)
 		err = -ENOMEM;
 		goto err_out;
 	}
-	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_map_lops, NULL);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_map_lops, NULL,
+		      attr->link_create.attach_type);
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err)
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index cd220e861d67..bacdd0ca7419 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -867,7 +867,7 @@ static int __cgroup_bpf_attach(struct cgroup *cgrp,
 	cgrp->bpf.flags[atype] = saved_flags;
 
 	if (type == BPF_LSM_CGROUP) {
-		err = bpf_trampoline_link_cgroup_shim(new_prog, atype);
+		err = bpf_trampoline_link_cgroup_shim(new_prog, atype, type);
 		if (err)
 			goto cleanup;
 	}
@@ -1495,7 +1495,7 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		goto out_put_cgroup;
 	}
 	bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops,
-		      prog);
+		      prog, attr->link_create.attach_type);
 	link->cgroup = cgrp;
 	link->type = attr->link_create.attach_type;
 
diff --git a/kernel/bpf/net_namespace.c b/kernel/bpf/net_namespace.c
index 868cc2c43899..63702c862757 100644
--- a/kernel/bpf/net_namespace.c
+++ b/kernel/bpf/net_namespace.c
@@ -501,7 +501,7 @@ int netns_bpf_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
 		goto out_put_net;
 	}
 	bpf_link_init(&net_link->link, BPF_LINK_TYPE_NETNS,
-		      &bpf_netns_link_ops, prog);
+		      &bpf_netns_link_ops, prog, type);
 	net_link->net = net;
 	net_link->type = type;
 	net_link->netns_type = netns_type;
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 3f36bfe13266..cd7321fe0ba3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3069,7 +3069,7 @@ static int bpf_obj_get(const union bpf_attr *attr)
  */
 void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
 			     const struct bpf_link_ops *ops, struct bpf_prog *prog,
-			     bool sleepable)
+			     enum bpf_attach_type attach_type, bool sleepable)
 {
 	WARN_ON(ops->dealloc && ops->dealloc_deferred);
 	atomic64_set(&link->refcnt, 1);
@@ -3078,12 +3078,14 @@ void bpf_link_init_sleepable(struct bpf_link *link, enum bpf_link_type type,
 	link->id = 0;
 	link->ops = ops;
 	link->prog = prog;
+	link->attach_type = attach_type;
 }
 
 void bpf_link_init(struct bpf_link *link, enum bpf_link_type type,
-		   const struct bpf_link_ops *ops, struct bpf_prog *prog)
+		   const struct bpf_link_ops *ops, struct bpf_prog *prog,
+		   enum bpf_attach_type attach_type)
 {
-	bpf_link_init_sleepable(link, type, ops, prog, false);
+	bpf_link_init_sleepable(link, type, ops, prog, attach_type, false);
 }
 
 static void bpf_link_free_id(int id)
@@ -3443,7 +3445,8 @@ static const struct bpf_link_ops bpf_tracing_link_lops = {
 static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 				   int tgt_prog_fd,
 				   u32 btf_id,
-				   u64 bpf_cookie)
+				   u64 bpf_cookie,
+				   enum bpf_attach_type attach_type)
 {
 	struct bpf_link_primer link_primer;
 	struct bpf_prog *tgt_prog = NULL;
@@ -3511,7 +3514,8 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 		goto out_put_prog;
 	}
 	bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING,
-		      &bpf_tracing_link_lops, prog);
+		      &bpf_tracing_link_lops, prog, attach_type);
+
 	link->attach_type = prog->expected_attach_type;
 	link->link.cookie = bpf_cookie;
 
@@ -4049,7 +4053,8 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro
 		err = -ENOMEM;
 		goto out_put_file;
 	}
-	bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_PERF_EVENT, &bpf_perf_link_lops, prog,
+		      attr->link_create.attach_type);
 	link->perf_file = perf_file;
 
 	err = bpf_link_prime(&link->link, &link_primer);
@@ -4081,7 +4086,8 @@ static int bpf_perf_link_attach(const union bpf_attr *attr, struct bpf_prog *pro
 #endif /* CONFIG_PERF_EVENTS */
 
 static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
-				  const char __user *user_tp_name, u64 cookie)
+				  const char __user *user_tp_name, u64 cookie,
+				  enum bpf_attach_type attach_type)
 {
 	struct bpf_link_primer link_primer;
 	struct bpf_raw_tp_link *link;
@@ -4104,7 +4110,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
 			tp_name = prog->aux->attach_func_name;
 			break;
 		}
-		return bpf_tracing_prog_attach(prog, 0, 0, 0);
+		return bpf_tracing_prog_attach(prog, 0, 0, 0, attach_type);
 	case BPF_PROG_TYPE_RAW_TRACEPOINT:
 	case BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE:
 		if (strncpy_from_user(buf, user_tp_name, sizeof(buf) - 1) < 0)
@@ -4126,7 +4132,7 @@ static int bpf_raw_tp_link_attach(struct bpf_prog *prog,
 		goto out_put_btp;
 	}
 	bpf_link_init_sleepable(&link->link, BPF_LINK_TYPE_RAW_TRACEPOINT,
-				&bpf_raw_tp_link_lops, prog,
+				&bpf_raw_tp_link_lops, prog, attach_type,
 				tracepoint_is_faultable(btp->tp));
 	link->btp = btp;
 	link->cookie = cookie;
@@ -4168,7 +4174,7 @@ static int bpf_raw_tracepoint_open(const union bpf_attr *attr)
 
 	tp_name = u64_to_user_ptr(attr->raw_tracepoint.name);
 	cookie = attr->raw_tracepoint.cookie;
-	fd = bpf_raw_tp_link_attach(prog, tp_name, cookie);
+	fd = bpf_raw_tp_link_attach(prog, tp_name, cookie, prog->expected_attach_type);
 	if (fd < 0)
 		bpf_prog_put(prog);
 	return fd;
@@ -5525,7 +5531,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 		ret = bpf_tracing_prog_attach(prog,
 					      attr->link_create.target_fd,
 					      attr->link_create.target_btf_id,
-					      attr->link_create.tracing.cookie);
+					      attr->link_create.tracing.cookie,
+					      attr->link_create.attach_type);
 		break;
 	case BPF_PROG_TYPE_LSM:
 	case BPF_PROG_TYPE_TRACING:
@@ -5534,7 +5541,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 			goto out;
 		}
 		if (prog->expected_attach_type == BPF_TRACE_RAW_TP)
-			ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie);
+			ret = bpf_raw_tp_link_attach(prog, NULL, attr->link_create.tracing.cookie,
+						     attr->link_create.attach_type);
 		else if (prog->expected_attach_type == BPF_TRACE_ITER)
 			ret = bpf_iter_link_attach(attr, uattr, prog);
 		else if (prog->expected_attach_type == BPF_LSM_CGROUP)
@@ -5543,7 +5551,8 @@ static int link_create(union bpf_attr *attr, bpfptr_t uattr)
 			ret = bpf_tracing_prog_attach(prog,
 						      attr->link_create.target_fd,
 						      attr->link_create.target_btf_id,
-						      attr->link_create.tracing.cookie);
+						      attr->link_create.tracing.cookie,
+						      attr->link_create.attach_type);
 		break;
 	case BPF_PROG_TYPE_FLOW_DISSECTOR:
 	case BPF_PROG_TYPE_SK_LOOKUP:
diff --git a/kernel/bpf/tcx.c b/kernel/bpf/tcx.c
index 2e4885e7781f..e6a14f408d94 100644
--- a/kernel/bpf/tcx.c
+++ b/kernel/bpf/tcx.c
@@ -301,7 +301,8 @@ static int tcx_link_init(struct tcx_link *tcx,
 			 struct net_device *dev,
 			 struct bpf_prog *prog)
 {
-	bpf_link_init(&tcx->link, BPF_LINK_TYPE_TCX, &tcx_link_lops, prog);
+	bpf_link_init(&tcx->link, BPF_LINK_TYPE_TCX, &tcx_link_lops, prog,
+		      attr->link_create.attach_type);
 	tcx->location = attr->link_create.attach_type;
 	tcx->dev = dev;
 	return bpf_link_prime(&tcx->link, link_primer);
diff --git a/kernel/bpf/trampoline.c b/kernel/bpf/trampoline.c
index b1e358c16eeb..0e364614c3a2 100644
--- a/kernel/bpf/trampoline.c
+++ b/kernel/bpf/trampoline.c
@@ -674,7 +674,8 @@ static const struct bpf_link_ops bpf_shim_tramp_link_lops = {
 
 static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog,
 						     bpf_func_t bpf_func,
-						     int cgroup_atype)
+						     int cgroup_atype,
+						     enum bpf_attach_type attach_type)
 {
 	struct bpf_shim_tramp_link *shim_link = NULL;
 	struct bpf_prog *p;
@@ -701,7 +702,7 @@ static struct bpf_shim_tramp_link *cgroup_shim_alloc(const struct bpf_prog *prog
 	p->expected_attach_type = BPF_LSM_MAC;
 	bpf_prog_inc(p);
 	bpf_link_init(&shim_link->link.link, BPF_LINK_TYPE_UNSPEC,
-		      &bpf_shim_tramp_link_lops, p);
+		      &bpf_shim_tramp_link_lops, p, attach_type);
 	bpf_cgroup_atype_get(p->aux->attach_btf_id, cgroup_atype);
 
 	return shim_link;
@@ -726,7 +727,8 @@ static struct bpf_shim_tramp_link *cgroup_shim_find(struct bpf_trampoline *tr,
 }
 
 int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
-				    int cgroup_atype)
+				    int cgroup_atype,
+				    enum bpf_attach_type attach_type)
 {
 	struct bpf_shim_tramp_link *shim_link = NULL;
 	struct bpf_attach_target_info tgt_info = {};
@@ -763,7 +765,7 @@ int bpf_trampoline_link_cgroup_shim(struct bpf_prog *prog,
 
 	/* Allocate and install new shim. */
 
-	shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype);
+	shim_link = cgroup_shim_alloc(prog, bpf_func, cgroup_atype, attach_type);
 	if (!shim_link) {
 		err = -ENOMEM;
 		goto err;
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index e7f97a9a8bbd..ffdde840abb8 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2986,7 +2986,7 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	}
 
 	bpf_link_init(&link->link, BPF_LINK_TYPE_KPROBE_MULTI,
-		      &bpf_kprobe_multi_link_lops, prog);
+		      &bpf_kprobe_multi_link_lops, prog, attr->link_create.attach_type);
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err)
@@ -3441,7 +3441,7 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 	link->link.flags = flags;
 
 	bpf_link_init(&link->link, BPF_LINK_TYPE_UPROBE_MULTI,
-		      &bpf_uprobe_multi_link_lops, prog);
+		      &bpf_uprobe_multi_link_lops, prog, attr->link_create.attach_type);
 
 	for (i = 0; i < cnt; i++) {
 		uprobes[i].uprobe = uprobe_register(d_real_inode(link->path.dentry),
diff --git a/net/bpf/bpf_dummy_struct_ops.c b/net/bpf/bpf_dummy_struct_ops.c
index f71f67c6896b..812457819b5a 100644
--- a/net/bpf/bpf_dummy_struct_ops.c
+++ b/net/bpf/bpf_dummy_struct_ops.c
@@ -171,7 +171,8 @@ int bpf_struct_ops_test_run(struct bpf_prog *prog, const union bpf_attr *kattr,
 	}
 	/* prog doesn't take the ownership of the reference from caller */
 	bpf_prog_inc(prog);
-	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_link_lops, prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_STRUCT_OPS, &bpf_struct_ops_link_lops, prog,
+		      prog->expected_attach_type);
 
 	op_idx = prog->expected_attach_type;
 	err = bpf_struct_ops_prepare_trampoline(tlinks, link,
diff --git a/net/core/dev.c b/net/core/dev.c
index be97c440ecd5..7969fddc94e3 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10364,7 +10364,8 @@ int bpf_xdp_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 		goto unlock;
 	}
 
-	bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_XDP, &bpf_xdp_link_lops, prog,
+		      attr->link_create.attach_type);
 	link->dev = dev;
 	link->flags = attr->link_create.flags;
 
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index 82a14f131d00..fbe9a33ddf18 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -1866,7 +1866,8 @@ int sock_map_link_create(const union bpf_attr *attr, struct bpf_prog *prog)
 	}
 
 	attach_type = attr->link_create.attach_type;
-	bpf_link_init(&sockmap_link->link, BPF_LINK_TYPE_SOCKMAP, &sock_map_link_ops, prog);
+	bpf_link_init(&sockmap_link->link, BPF_LINK_TYPE_SOCKMAP, &sock_map_link_ops, prog,
+		      attach_type);
 	sockmap_link->map = map;
 	sockmap_link->attach_type = attach_type;
 
diff --git a/net/netfilter/nf_bpf_link.c b/net/netfilter/nf_bpf_link.c
index 06b084844700..a054d3b216d8 100644
--- a/net/netfilter/nf_bpf_link.c
+++ b/net/netfilter/nf_bpf_link.c
@@ -225,7 +225,8 @@ int bpf_nf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	if (!link)
 		return -ENOMEM;
 
-	bpf_link_init(&link->link, BPF_LINK_TYPE_NETFILTER, &bpf_nf_link_lops, prog);
+	bpf_link_init(&link->link, BPF_LINK_TYPE_NETFILTER, &bpf_nf_link_lops, prog,
+		      attr->link_create.attach_type);
 
 	link->hook_ops.hook = nf_hook_run_bpf;
 	link->hook_ops.hook_ops_type = NF_HOOK_OP_BPF;
-- 
cgit v1.2.3


From 9b8d543dc2bbf5d3a1e2d60049df94ae2bc68b28 Mon Sep 17 00:00:00 2001
From: Tao Chen <chen.dylane@linux.dev>
Date: Thu, 10 Jul 2025 11:20:33 +0800
Subject: bpf: Remove attach_type in bpf_cgroup_link

Use attach_type in bpf_link, and remove it in bpf_cgroup_link.

Signed-off-by: Tao Chen <chen.dylane@linux.dev>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20250710032038.888700-3-chen.dylane@linux.dev
---
 include/linux/bpf-cgroup.h |  1 -
 kernel/bpf/cgroup.c        | 13 ++++++-------
 2 files changed, 6 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 70c8b94e797a..082ccd8ad96b 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -103,7 +103,6 @@ struct bpf_cgroup_storage {
 struct bpf_cgroup_link {
 	struct bpf_link link;
 	struct cgroup *cgroup;
-	enum bpf_attach_type type;
 };
 
 struct bpf_prog_list {
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index bacdd0ca7419..72c8b50dca0a 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -984,7 +984,7 @@ static int __cgroup_bpf_replace(struct cgroup *cgrp,
 	struct hlist_head *progs;
 	bool found = false;
 
-	atype = bpf_cgroup_atype_find(link->type, new_prog->aux->attach_btf_id);
+	atype = bpf_cgroup_atype_find(link->link.attach_type, new_prog->aux->attach_btf_id);
 	if (atype < 0)
 		return -EINVAL;
 
@@ -1396,8 +1396,8 @@ static void bpf_cgroup_link_release(struct bpf_link *link)
 	}
 
 	WARN_ON(__cgroup_bpf_detach(cg_link->cgroup, NULL, cg_link,
-				    cg_link->type, 0));
-	if (cg_link->type == BPF_LSM_CGROUP)
+				    link->attach_type, 0));
+	if (link->attach_type == BPF_LSM_CGROUP)
 		bpf_trampoline_unlink_cgroup_shim(cg_link->link.prog);
 
 	cg = cg_link->cgroup;
@@ -1439,7 +1439,7 @@ static void bpf_cgroup_link_show_fdinfo(const struct bpf_link *link,
 		   "cgroup_id:\t%llu\n"
 		   "attach_type:\t%d\n",
 		   cg_id,
-		   cg_link->type);
+		   link->attach_type);
 }
 
 static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link,
@@ -1455,7 +1455,7 @@ static int bpf_cgroup_link_fill_link_info(const struct bpf_link *link,
 	cgroup_unlock();
 
 	info->cgroup.cgroup_id = cg_id;
-	info->cgroup.attach_type = cg_link->type;
+	info->cgroup.attach_type = link->attach_type;
 	return 0;
 }
 
@@ -1497,7 +1497,6 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	bpf_link_init(&link->link, BPF_LINK_TYPE_CGROUP, &bpf_cgroup_link_lops,
 		      prog, attr->link_create.attach_type);
 	link->cgroup = cgrp;
-	link->type = attr->link_create.attach_type;
 
 	err = bpf_link_prime(&link->link, &link_primer);
 	if (err) {
@@ -1506,7 +1505,7 @@ int cgroup_bpf_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 	}
 
 	err = cgroup_bpf_attach(cgrp, NULL, NULL, link,
-				link->type, BPF_F_ALLOW_MULTI | attr->link_create.flags,
+				link->link.attach_type, BPF_F_ALLOW_MULTI | attr->link_create.flags,
 				attr->link_create.cgroup.relative_fd,
 				attr->link_create.cgroup.expected_revision);
 	if (err) {
-- 
cgit v1.2.3


From 0eeeebdcc5feeec48118f7a3df2ac818e694ccc7 Mon Sep 17 00:00:00 2001
From: Tao Chen <chen.dylane@linux.dev>
Date: Thu, 10 Jul 2025 11:20:37 +0800
Subject: bpf: Remove attach_type in bpf_tracing_link

Use attach_type in bpf_link, and remove it in bpf_tracing_link.

Signed-off-by: Tao Chen <chen.dylane@linux.dev>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Jiri Olsa <jolsa@kernel.org>
Link: https://lore.kernel.org/bpf/20250710032038.888700-7-chen.dylane@linux.dev
---
 include/linux/bpf.h  | 1 -
 kernel/bpf/syscall.c | 5 ++---
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a9ee9c14b486..bc887831eaa5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1784,7 +1784,6 @@ struct bpf_shim_tramp_link {
 
 struct bpf_tracing_link {
 	struct bpf_tramp_link link;
-	enum bpf_attach_type attach_type;
 	struct bpf_trampoline *trampoline;
 	struct bpf_prog *tgt_prog;
 };
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index cd7321fe0ba3..1a26d17536be 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -3414,7 +3414,7 @@ static void bpf_tracing_link_show_fdinfo(const struct bpf_link *link,
 		   "target_obj_id:\t%u\n"
 		   "target_btf_id:\t%u\n"
 		   "cookie:\t%llu\n",
-		   tr_link->attach_type,
+		   link->attach_type,
 		   target_obj_id,
 		   target_btf_id,
 		   tr_link->link.cookie);
@@ -3426,7 +3426,7 @@ static int bpf_tracing_link_fill_link_info(const struct bpf_link *link,
 	struct bpf_tracing_link *tr_link =
 		container_of(link, struct bpf_tracing_link, link.link);
 
-	info->tracing.attach_type = tr_link->attach_type;
+	info->tracing.attach_type = link->attach_type;
 	info->tracing.cookie = tr_link->link.cookie;
 	bpf_trampoline_unpack_key(tr_link->trampoline->key,
 				  &info->tracing.target_obj_id,
@@ -3516,7 +3516,6 @@ static int bpf_tracing_prog_attach(struct bpf_prog *prog,
 	bpf_link_init(&link->link.link, BPF_LINK_TYPE_TRACING,
 		      &bpf_tracing_link_lops, prog, attach_type);
 
-	link->attach_type = prog->expected_attach_type;
 	link->link.cookie = bpf_cookie;
 
 	mutex_lock(&prog->aux->dst_mutex);
-- 
cgit v1.2.3


From daec29dcc8731b7596690ab9f647839e4584a86d Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <linux@weissschuh.net>
Date: Tue, 17 Jun 2025 19:08:14 +0200
Subject: locking/mutex: Mark devm_mutex_init() as __must_check
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

devm_mutex_init() can fail. With CONFIG_DEBUG_MUTEXES=y the mutex will be
marked as unusable and trigger errors on usage.
Enforce all callers check the return value through the compiler.

As devm_mutex_init() itself is a macro, it can not be annotated
directly. Annotate __devm_mutex_init() instead.
Unfortunately __must_check/warn_unused_result don't propagate through
statement expression. So move the statement expression into the argument
list of the call to __devm_mutex_init() through a helper macro.

Suggested-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Thomas Weißschuh <linux@weissschuh.net>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Link: https://lore.kernel.org/r/20250617-must_check-devm_mutex_init-v7-3-d9e449f4d224@weissschuh.net
---
 include/linux/mutex.h | 11 +++++++----
 1 file changed, 7 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index a039fa8c1780..00afd341d293 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -126,11 +126,11 @@ do {							\
 
 #ifdef CONFIG_DEBUG_MUTEXES
 
-int __devm_mutex_init(struct device *dev, struct mutex *lock);
+int __must_check __devm_mutex_init(struct device *dev, struct mutex *lock);
 
 #else
 
-static inline int __devm_mutex_init(struct device *dev, struct mutex *lock)
+static inline int __must_check __devm_mutex_init(struct device *dev, struct mutex *lock)
 {
 	/*
 	 * When CONFIG_DEBUG_MUTEXES is off mutex_destroy() is just a nop so
@@ -141,14 +141,17 @@ static inline int __devm_mutex_init(struct device *dev, struct mutex *lock)
 
 #endif
 
-#define devm_mutex_init(dev, mutex)			\
+#define __mutex_init_ret(mutex)				\
 ({							\
 	typeof(mutex) mutex_ = (mutex);			\
 							\
 	mutex_init(mutex_);				\
-	__devm_mutex_init(dev, mutex_);			\
+	mutex_;						\
 })
 
+#define devm_mutex_init(dev, mutex) \
+	__devm_mutex_init(dev, __mutex_init_ret(mutex))
+
 /*
  * See kernel/locking/mutex.c for detailed documentation of these APIs.
  * Also see Documentation/locking/mutex-design.rst.
-- 
cgit v1.2.3


From 8feaf9832be52be16e588029366e27940f6b88ea Mon Sep 17 00:00:00 2001
From: Michael Guralnik <michaelgur@nvidia.com>
Date: Wed, 9 Jul 2025 09:42:08 +0300
Subject: net/mlx5: Expose HCA capability bits for mkey max page size

Expose the HCA capability for maximal page size that can be configured
for an mkey. Used for enforcing capabilities when working with highly
contiguous memory and using large page sizes.

Signed-off-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/3e4d3fda37934430f65f72601519e22bf396fd05.1751979184.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 0e93f342be09..a1bd92ed8f3a 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2171,7 +2171,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   min_mkey_log_entity_size_fixed_buffer[0x5];
 	u8	   ec_vf_vport_base[0x10];
 
-	u8	   reserved_at_3a0[0xa];
+	u8	   reserved_at_3a0[0x2];
+	u8	   max_mkey_log_entity_size_fixed_buffer[0x6];
+	u8	   reserved_at_3a8[0x2];
 	u8	   max_mkey_log_entity_size_mtt[0x6];
 	u8	   max_rqt_vhca_id[0x10];
 
-- 
cgit v1.2.3


From c4f96972c3c206ac8f6770b5ecd5320b561d0058 Mon Sep 17 00:00:00 2001
From: Edward Srouji <edwards@nvidia.com>
Date: Wed, 9 Jul 2025 09:42:09 +0300
Subject: RDMA/mlx5: Fix UMR modifying of mkey page size

When changing the page size on an mkey, the driver needs to set the
appropriate bits in the mkey mask to indicate which fields are being
modified.
The 6th bit of a page size in mlx5 driver is considered an extension,
and this bit has a dedicated capability and mask bits.

Previously, the driver was not setting this mask in the mkey mask when
performing page size changes, regardless of its hardware support,
potentially leading to an incorrect page size updates.

This fixes the issue by setting the relevant bit in the mkey mask when
performing page size changes on an mkey and the 6th bit of this field is
supported by the hardware.

Fixes: cef7dde8836a ("net/mlx5: Expand mkey page size to support 6 bits")
Signed-off-by: Edward Srouji <edwards@nvidia.com>
Reviewed-by: Michael Guralnik <michaelgur@nvidia.com>
Link: https://patch.msgid.link/9f43a9c73bf2db6085a99dc836f7137e76579f09.1751979184.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/infiniband/hw/mlx5/umr.c | 6 ++++--
 include/linux/mlx5/device.h      | 1 +
 2 files changed, 5 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/mlx5/umr.c b/drivers/infiniband/hw/mlx5/umr.c
index 5be4426a2884..25601dea9e30 100644
--- a/drivers/infiniband/hw/mlx5/umr.c
+++ b/drivers/infiniband/hw/mlx5/umr.c
@@ -32,13 +32,15 @@ static __be64 get_umr_disable_mr_mask(void)
 	return cpu_to_be64(result);
 }
 
-static __be64 get_umr_update_translation_mask(void)
+static __be64 get_umr_update_translation_mask(struct mlx5_ib_dev *dev)
 {
 	u64 result;
 
 	result = MLX5_MKEY_MASK_LEN |
 		 MLX5_MKEY_MASK_PAGE_SIZE |
 		 MLX5_MKEY_MASK_START_ADDR;
+	if (MLX5_CAP_GEN_2(dev->mdev, umr_log_entity_size_5))
+		result |= MLX5_MKEY_MASK_PAGE_SIZE_5;
 
 	return cpu_to_be64(result);
 }
@@ -654,7 +656,7 @@ static void mlx5r_umr_final_update_xlt(struct mlx5_ib_dev *dev,
 		flags & MLX5_IB_UPD_XLT_ENABLE || flags & MLX5_IB_UPD_XLT_ADDR;
 
 	if (update_translation) {
-		wqe->ctrl_seg.mkey_mask |= get_umr_update_translation_mask();
+		wqe->ctrl_seg.mkey_mask |= get_umr_update_translation_mask(dev);
 		if (!mr->ibmr.length)
 			MLX5_SET(mkc, &wqe->mkey_seg, length64, 1);
 	}
diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
index 6822cfa5f4ad..9d2467f982ad 100644
--- a/include/linux/mlx5/device.h
+++ b/include/linux/mlx5/device.h
@@ -280,6 +280,7 @@ enum {
 	MLX5_MKEY_MASK_SMALL_FENCE	= 1ull << 23,
 	MLX5_MKEY_MASK_RELAXED_ORDERING_WRITE	= 1ull << 25,
 	MLX5_MKEY_MASK_FREE			= 1ull << 29,
+	MLX5_MKEY_MASK_PAGE_SIZE_5		= 1ull << 42,
 	MLX5_MKEY_MASK_RELAXED_ORDERING_READ	= 1ull << 47,
 };
 
-- 
cgit v1.2.3


From cbe080f931f48bc7b054008fc2567d1c8c247a89 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Wed, 9 Jul 2025 15:41:06 +0300
Subject: net/mlx5: Expose disciplined_fr_counter through HCA capabilities in
 mlx5_ifc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Introduce the `disciplined_fr_counter` capability bit to indicate that
the device’s free-running cycle counter is disciplined to real-time.

Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1752064867-16874-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index a1bd92ed8f3a..d7684bb28a3a 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1846,7 +1846,8 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 
 	u8         log_bf_reg_size[0x5];
 
-	u8         reserved_at_270[0x3];
+	u8         disciplined_fr_counter[0x1];
+	u8         reserved_at_271[0x2];
 	u8	   qp_error_syndrome[0x1];
 	u8	   reserved_at_274[0x2];
 	u8         lag_dct[0x2];
-- 
cgit v1.2.3


From cd1746cb6555a2238c4aae9f9d60b637a61bf177 Mon Sep 17 00:00:00 2001
From: Daniel Jurgens <danielj@nvidia.com>
Date: Wed, 9 Jul 2025 15:41:07 +0300
Subject: net/mlx5: IFC updates for disabled host PF

The port 2 host PF can be disabled, this bit reflects that setting.

Signed-off-by: Daniel Jurgens <danielj@nvidia.com>
Reviewed-by: William Tu <witu@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1752064867-16874-3-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index d7684bb28a3a..639dd0b56655 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -12383,7 +12383,9 @@ struct mlx5_ifc_mtrc_ctrl_bits {
 
 struct mlx5_ifc_host_params_context_bits {
 	u8         host_number[0x8];
-	u8         reserved_at_8[0x7];
+	u8         reserved_at_8[0x5];
+	u8         host_pf_not_exist[0x1];
+	u8         reserved_at_14[0x1];
 	u8         host_pf_disabled[0x1];
 	u8         host_num_of_vfs[0x10];
 
-- 
cgit v1.2.3


From a6cfa4c8833944f8912c1fa7f95795753f6376ea Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Sat, 12 Jul 2025 18:37:12 -0500
Subject: PM: hibernate: Add stub for pm_hibernate_is_recovering()

Randy reports that amdgpu fails to compile with the following error:
ERROR: modpost: "pm_hibernate_is_recovering" [drivers/gpu/drm/amd/amdgpu/amdgpu.ko] undefined!

This happens because pm_hibernate_is_recovering() is only compiled when
CONFIG_PM_SLEEP is set.  Add a stub for it so that drivers don't need
to depend upon CONFIG_PM.

Cc: Samuel Zhang <guoqing.zhang@amd.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Closes: https://lore.kernel.org/dri-devel/CAJZ5v0h1CX+aTu7dFy6vB-9LM6t5J4rt7Su3qVnq1xx-BFAm=Q@mail.gmail.com/T/#m2b9fe212b35fde11d58fcbc4e0727bc02ebba7b0
Fixes: c2aaddbd2dede ("PM: hibernate: add new api pm_hibernate_is_recovering()")
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://lore.kernel.org/r/20250712233715.821424-1-superm1@kernel.org
Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
---
 include/linux/suspend.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/suspend.h b/include/linux/suspend.h
index 293137210fdf..fcb150ee83b6 100644
--- a/include/linux/suspend.h
+++ b/include/linux/suspend.h
@@ -426,8 +426,6 @@ int is_hibernate_resume_dev(dev_t dev);
 static inline int is_hibernate_resume_dev(dev_t dev) { return 0; }
 #endif
 
-bool pm_hibernate_is_recovering(void);
-
 /* Hibernation and suspend events */
 #define PM_HIBERNATION_PREPARE	0x0001 /* Going to hibernate */
 #define PM_POST_HIBERNATION	0x0002 /* Hibernation finished */
@@ -478,6 +476,7 @@ extern unsigned int lock_system_sleep(void);
 extern void unlock_system_sleep(unsigned int);
 
 extern bool pm_sleep_transition_in_progress(void);
+bool pm_hibernate_is_recovering(void);
 
 #else /* !CONFIG_PM_SLEEP */
 
@@ -508,6 +507,7 @@ static inline unsigned int lock_system_sleep(void) { return 0; }
 static inline void unlock_system_sleep(unsigned int flags) {}
 
 static inline bool pm_sleep_transition_in_progress(void) { return false; }
+static inline bool pm_hibernate_is_recovering(void) { return false; }
 
 #endif /* !CONFIG_PM_SLEEP */
 
-- 
cgit v1.2.3


From 11d58620dfd0c52b0c49b04d28707c7a5a2d00ae Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Tue, 1 Jul 2025 16:37:51 -0500
Subject: iio: adc: ad_sigma_delta: use u8 instead of uint8_t
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Replace uint8_t with u8 in the ad_sigma_delta driver.

Technically, uint8_t comes from the C standard library, while u8 is a
Linux kernel type. Since we don't use the C standard library in the
kernel, we should use the kernel types instead.

There is also one instance where int64_t is replaced with s64.

Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Link: https://patch.msgid.link/20250701-iio-adc-ad7173-add-spi-offload-support-v3-3-42abb83e3dac@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad_sigma_delta.c       | 17 +++++++++--------
 include/linux/iio/adc/ad_sigma_delta.h | 10 +++++-----
 2 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index 5cdd73160c6d..5362157966d8 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -14,6 +14,7 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/spi/spi.h>
+#include <linux/types.h>
 #include <linux/unaligned.h>
 
 #include <linux/iio/adc/ad_sigma_delta.h>
@@ -38,7 +39,7 @@
  * @sigma_delta: The sigma delta device
  * @comm: New value for the communications register
  */
-void ad_sd_set_comm(struct ad_sigma_delta *sigma_delta, uint8_t comm)
+void ad_sd_set_comm(struct ad_sigma_delta *sigma_delta, u8 comm)
 {
 	/* Some variants use the lower two bits of the communications register
 	 * to select the channel */
@@ -59,7 +60,7 @@ EXPORT_SYMBOL_NS_GPL(ad_sd_set_comm, "IIO_AD_SIGMA_DELTA");
 int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 	unsigned int size, unsigned int val)
 {
-	uint8_t *data = sigma_delta->tx_buf;
+	u8 *data = sigma_delta->tx_buf;
 	struct spi_transfer t = {
 		.tx_buf		= data,
 		.len		= size + 1,
@@ -99,9 +100,9 @@ int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 EXPORT_SYMBOL_NS_GPL(ad_sd_write_reg, "IIO_AD_SIGMA_DELTA");
 
 static int ad_sd_read_reg_raw(struct ad_sigma_delta *sigma_delta,
-	unsigned int reg, unsigned int size, uint8_t *val)
+			      unsigned int reg, unsigned int size, u8 *val)
 {
-	uint8_t *data = sigma_delta->tx_buf;
+	u8 *data = sigma_delta->tx_buf;
 	int ret;
 	struct spi_transfer t[] = {
 		{
@@ -185,8 +186,8 @@ EXPORT_SYMBOL_NS_GPL(ad_sd_read_reg, "IIO_AD_SIGMA_DELTA");
 int ad_sd_reset(struct ad_sigma_delta *sigma_delta)
 {
 	unsigned int reset_length = sigma_delta->info->num_resetclks;
-	uint8_t *buf;
 	unsigned int size;
+	u8 *buf;
 	int ret;
 
 	size = DIV_ROUND_UP(reset_length, 8);
@@ -454,7 +455,7 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
 	unsigned int i, slot, samples_buf_size;
 	unsigned int channel;
-	uint8_t *samples_buf;
+	u8 *samples_buf;
 	int ret;
 
 	if (sigma_delta->num_slots == 1) {
@@ -488,7 +489,7 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 	}
 
 	samples_buf_size = ALIGN(slot * indio_dev->channels[0].scan_type.storagebits / 8, 8);
-	samples_buf_size += sizeof(int64_t);
+	samples_buf_size += sizeof(s64);
 	samples_buf = devm_krealloc(&sigma_delta->spi->dev, sigma_delta->samples_buf,
 				    samples_buf_size, GFP_KERNEL);
 	if (!samples_buf)
@@ -543,7 +544,7 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 	struct iio_poll_func *pf = p;
 	struct iio_dev *indio_dev = pf->indio_dev;
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
-	uint8_t *data = sigma_delta->rx_buf;
+	u8 *data = sigma_delta->rx_buf;
 	unsigned int transfer_size;
 	unsigned int sample_size;
 	unsigned int sample_pos;
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index f242b285081b..5056677c9941 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -94,7 +94,7 @@ struct ad_sigma_delta {
 	bool			bus_locked;
 	bool			keep_cs_asserted;
 
-	uint8_t			comm;
+	u8			comm;
 
 	const struct ad_sigma_delta_info *info;
 	unsigned int		active_slots;
@@ -105,7 +105,7 @@ struct ad_sigma_delta {
 	bool			status_appended;
 	/* map slots to channels in order to know what to expect from devices */
 	unsigned int		*slots;
-	uint8_t			*samples_buf;
+	u8			*samples_buf;
 
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
@@ -114,8 +114,8 @@ struct ad_sigma_delta {
 	 * 'rx_buf' is up to 32 bits per sample + 64 bit timestamp,
 	 * rounded to 16 bytes to take into account padding.
 	 */
-	uint8_t				tx_buf[4] __aligned(IIO_DMA_MINALIGN);
-	uint8_t				rx_buf[16] __aligned(8);
+	u8				tx_buf[4] __aligned(IIO_DMA_MINALIGN);
+	u8				rx_buf[16] __aligned(8);
 };
 
 static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd,
@@ -177,7 +177,7 @@ static inline int ad_sigma_delta_postprocess_sample(struct ad_sigma_delta *sd,
 	return 0;
 }
 
-void ad_sd_set_comm(struct ad_sigma_delta *sigma_delta, uint8_t comm);
+void ad_sd_set_comm(struct ad_sigma_delta *sigma_delta, u8 comm);
 int ad_sd_write_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
 	unsigned int size, unsigned int val);
 int ad_sd_read_reg(struct ad_sigma_delta *sigma_delta, unsigned int reg,
-- 
cgit v1.2.3


From db63e45a7da0678652c69f7cbed2cbf2a9922b39 Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Tue, 1 Jul 2025 16:37:56 -0500
Subject: iio: adc: ad_sigma_delta: use spi_optimize_message()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Use spi_optimize_message() to improve the performance of buffered reads.

By setting up the SPI message and pre-optimizing it in the buffer
postenable callback, we can reduce overhead during each sample read.

A rough estimate shows that this reduced the CPU usage of the interrupt
handler thread from 22% to 16% using an EVAL-AD4112ARDZ board on a
DE10-Nano (measuring a single channel at the default 6.2 kHz sample
rate).

Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Link: https://patch.msgid.link/20250701-iio-adc-ad7173-add-spi-offload-support-v3-8-42abb83e3dac@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad_sigma_delta.c       | 72 ++++++++++++++++------------------
 include/linux/iio/adc/ad_sigma_delta.h |  3 ++
 2 files changed, 37 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index ce549775ac3d..124c42e19f2e 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -466,8 +466,9 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 {
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
 	const struct iio_scan_type *scan_type = &indio_dev->channels[0].scan_type;
+	struct spi_transfer *xfer = sigma_delta->sample_xfer;
 	unsigned int i, slot, samples_buf_size;
-	unsigned int channel;
+	unsigned int channel, scan_size;
 	u8 *samples_buf;
 	int ret;
 
@@ -510,6 +511,28 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 		return -ENOMEM;
 
 	sigma_delta->samples_buf = samples_buf;
+	scan_size = BITS_TO_BYTES(scan_type->realbits + scan_type->shift);
+	/* For 24-bit data, there is an extra byte of padding. */
+	xfer[1].rx_buf = &sigma_delta->rx_buf[scan_size == 3 ? 1 : 0];
+	xfer[1].len = scan_size + (sigma_delta->status_appended ? 1 : 0);
+	xfer[1].cs_change = 1;
+
+	if (sigma_delta->info->has_registers) {
+		xfer[0].tx_buf = &sigma_delta->sample_addr;
+		xfer[0].len = 1;
+
+		ad_sd_set_read_reg_addr(sigma_delta,
+					sigma_delta->info->data_reg ?: AD_SD_REG_DATA,
+					&sigma_delta->sample_addr);
+		spi_message_init_with_transfers(&sigma_delta->sample_msg, xfer, 2);
+	} else {
+		spi_message_init_with_transfers(&sigma_delta->sample_msg,
+						&xfer[1], 1);
+	}
+
+	ret = spi_optimize_message(sigma_delta->spi, &sigma_delta->sample_msg);
+	if (ret)
+		return ret;
 
 	spi_bus_lock(sigma_delta->spi->controller);
 	sigma_delta->bus_locked = true;
@@ -529,6 +552,7 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 
 err_unlock:
 	spi_bus_unlock(sigma_delta->spi->controller);
+	spi_unoptimize_message(&sigma_delta->sample_msg);
 
 	return ret;
 }
@@ -550,7 +574,10 @@ static int ad_sd_buffer_postdisable(struct iio_dev *indio_dev)
 
 	ad_sigma_delta_disable_all(sigma_delta);
 	sigma_delta->bus_locked = false;
-	return spi_bus_unlock(sigma_delta->spi->controller);
+	spi_bus_unlock(sigma_delta->spi->controller);
+	spi_unoptimize_message(&sigma_delta->sample_msg);
+
+	return 0;
 }
 
 static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
@@ -560,50 +587,19 @@ static irqreturn_t ad_sd_trigger_handler(int irq, void *p)
 	const struct iio_scan_type *scan_type = &indio_dev->channels[0].scan_type;
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
 	u8 *data = sigma_delta->rx_buf;
-	unsigned int transfer_size;
 	unsigned int sample_size;
 	unsigned int sample_pos;
 	unsigned int status_pos;
 	unsigned int reg_size;
-	unsigned int data_reg;
+	int ret;
 
 	reg_size = BITS_TO_BYTES(scan_type->realbits + scan_type->shift);
+	/* For 24-bit data, there is an extra byte of padding. */
+	status_pos = reg_size + (reg_size == 3 ? 1 : 0);
 
-	if (sigma_delta->info->data_reg != 0)
-		data_reg = sigma_delta->info->data_reg;
-	else
-		data_reg = AD_SD_REG_DATA;
-
-	/* Status word will be appended to the sample during transfer */
-	if (sigma_delta->status_appended)
-		transfer_size = reg_size + 1;
-	else
-		transfer_size = reg_size;
-
-	switch (reg_size) {
-	case 4:
-	case 2:
-	case 1:
-		status_pos = reg_size;
-		ad_sd_read_reg_raw(sigma_delta, data_reg, transfer_size, &data[0]);
-		break;
-	case 3:
-		/*
-		 * Data array after transfer will look like (if status is appended):
-		 * data[] = { [0][sample][sample][sample][status] }
-		 * Keeping the first byte 0 shifts the status position by 1 byte to the right.
-		 */
-		status_pos = reg_size + 1;
-
-		/* We store 24 bit samples in a 32 bit word. Keep the upper
-		 * byte set to zero. */
-		ad_sd_read_reg_raw(sigma_delta, data_reg, transfer_size, &data[1]);
-		break;
-
-	default:
-		dev_err_ratelimited(&indio_dev->dev, "Unsupported reg_size: %u\n", reg_size);
+	ret = spi_sync_locked(sigma_delta->spi, &sigma_delta->sample_msg);
+	if (ret)
 		goto irq_handled;
-	}
 
 	/*
 	 * For devices sampling only one channel at
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index 5056677c9941..2037bb68b441 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -105,6 +105,8 @@ struct ad_sigma_delta {
 	bool			status_appended;
 	/* map slots to channels in order to know what to expect from devices */
 	unsigned int		*slots;
+	struct spi_message	sample_msg;
+	struct spi_transfer	sample_xfer[2];
 	u8			*samples_buf;
 
 	/*
@@ -116,6 +118,7 @@ struct ad_sigma_delta {
 	 */
 	u8				tx_buf[4] __aligned(IIO_DMA_MINALIGN);
 	u8				rx_buf[16] __aligned(8);
+	u8				sample_addr;
 };
 
 static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd,
-- 
cgit v1.2.3


From 219da3ea842a156e5808176e11db256db9798f6c Mon Sep 17 00:00:00 2001
From: David Lechner <dlechner@baylibre.com>
Date: Tue, 1 Jul 2025 16:37:59 -0500
Subject: iio: adc: ad_sigma_delta: add SPI offload support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Add SPI offload support to the ad_sigma_delta module.

When the SPI controller has SPI offload capabilities, the module will
now use that for buffered reads instead of the RDY interrupt trigger.

Drivers that use the ad_sigma_delta module will have to opt into this
by setting supports_spi_offload since each driver will likely need
additional changes before SPI offload can be used. This will allow us
to gradually enable SPI offload support for each driver.

Signed-off-by: David Lechner <dlechner@baylibre.com>
Reviewed-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Nuno Sá <nuno.sa@analog.com>
Link: https://patch.msgid.link/20250701-iio-adc-ad7173-add-spi-offload-support-v3-11-42abb83e3dac@baylibre.com
Signed-off-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
---
 drivers/iio/adc/ad_sigma_delta.c       | 165 +++++++++++++++++++++++----------
 include/linux/iio/adc/ad_sigma_delta.h |  14 +++
 2 files changed, 132 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
index 124c42e19f2e..9d2dba0a0ee6 100644
--- a/drivers/iio/adc/ad_sigma_delta.c
+++ b/drivers/iio/adc/ad_sigma_delta.c
@@ -20,6 +20,7 @@
 #include <linux/module.h>
 #include <linux/property.h>
 #include <linux/slab.h>
+#include <linux/spi/offload/consumer.h>
 #include <linux/spi/spi.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
@@ -27,6 +28,7 @@
 #include <linux/unaligned.h>
 
 #include <linux/iio/adc/ad_sigma_delta.h>
+#include <linux/iio/buffer-dmaengine.h>
 #include <linux/iio/buffer.h>
 #include <linux/iio/iio.h>
 #include <linux/iio/trigger_consumer.h>
@@ -467,8 +469,7 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
 	const struct iio_scan_type *scan_type = &indio_dev->channels[0].scan_type;
 	struct spi_transfer *xfer = sigma_delta->sample_xfer;
-	unsigned int i, slot, samples_buf_size;
-	unsigned int channel, scan_size;
+	unsigned int i, slot, channel;
 	u8 *samples_buf;
 	int ret;
 
@@ -496,25 +497,35 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 	sigma_delta->active_slots = slot;
 	sigma_delta->current_slot = 0;
 
-	if (sigma_delta->active_slots > 1) {
-		ret = ad_sigma_delta_append_status(sigma_delta, true);
-		if (ret)
-			return ret;
-	}
+	if (ad_sigma_delta_has_spi_offload(sigma_delta)) {
+		xfer[1].offload_flags = SPI_OFFLOAD_XFER_RX_STREAM;
+		xfer[1].bits_per_word = scan_type->realbits;
+		xfer[1].len = spi_bpw_to_bytes(scan_type->realbits);
+	} else {
+		unsigned int samples_buf_size, scan_size;
 
-	samples_buf_size = ALIGN(slot * BITS_TO_BYTES(scan_type->storagebits),
-				 sizeof(s64));
-	samples_buf_size += sizeof(s64);
-	samples_buf = devm_krealloc(&sigma_delta->spi->dev, sigma_delta->samples_buf,
-				    samples_buf_size, GFP_KERNEL);
-	if (!samples_buf)
-		return -ENOMEM;
+		if (sigma_delta->active_slots > 1) {
+			ret = ad_sigma_delta_append_status(sigma_delta, true);
+			if (ret)
+				return ret;
+		}
 
-	sigma_delta->samples_buf = samples_buf;
-	scan_size = BITS_TO_BYTES(scan_type->realbits + scan_type->shift);
-	/* For 24-bit data, there is an extra byte of padding. */
-	xfer[1].rx_buf = &sigma_delta->rx_buf[scan_size == 3 ? 1 : 0];
-	xfer[1].len = scan_size + (sigma_delta->status_appended ? 1 : 0);
+		samples_buf_size =
+			ALIGN(slot * BITS_TO_BYTES(scan_type->storagebits),
+			      sizeof(s64));
+		samples_buf_size += sizeof(s64);
+		samples_buf = devm_krealloc(&sigma_delta->spi->dev,
+					    sigma_delta->samples_buf,
+					    samples_buf_size, GFP_KERNEL);
+		if (!samples_buf)
+			return -ENOMEM;
+
+		sigma_delta->samples_buf = samples_buf;
+		scan_size = BITS_TO_BYTES(scan_type->realbits + scan_type->shift);
+		/* For 24-bit data, there is an extra byte of padding. */
+		xfer[1].rx_buf = &sigma_delta->rx_buf[scan_size == 3 ? 1 : 0];
+		xfer[1].len = scan_size + (sigma_delta->status_appended ? 1 : 0);
+	}
 	xfer[1].cs_change = 1;
 
 	if (sigma_delta->info->has_registers) {
@@ -530,6 +541,8 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 						&xfer[1], 1);
 	}
 
+	sigma_delta->sample_msg.offload = sigma_delta->offload;
+
 	ret = spi_optimize_message(sigma_delta->spi, &sigma_delta->sample_msg);
 	if (ret)
 		return ret;
@@ -546,7 +559,19 @@ static int ad_sd_buffer_postenable(struct iio_dev *indio_dev)
 	if (ret)
 		goto err_unlock;
 
-	ad_sd_enable_irq(sigma_delta);
+	if (ad_sigma_delta_has_spi_offload(sigma_delta)) {
+		struct spi_offload_trigger_config config = {
+			.type = SPI_OFFLOAD_TRIGGER_DATA_READY,
+		};
+
+		ret = spi_offload_trigger_enable(sigma_delta->offload,
+						 sigma_delta->offload_trigger,
+						 &config);
+		if (ret)
+			goto err_unlock;
+	} else {
+		ad_sd_enable_irq(sigma_delta);
+	}
 
 	return 0;
 
@@ -561,10 +586,15 @@ static int ad_sd_buffer_postdisable(struct iio_dev *indio_dev)
 {
 	struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
 
-	reinit_completion(&sigma_delta->completion);
-	wait_for_completion_timeout(&sigma_delta->completion, HZ);
+	if (ad_sigma_delta_has_spi_offload(sigma_delta)) {
+		spi_offload_trigger_disable(sigma_delta->offload,
+					    sigma_delta->offload_trigger);
+	} else {
+		reinit_completion(&sigma_delta->completion);
+		wait_for_completion_timeout(&sigma_delta->completion, HZ);
 
-	ad_sd_disable_irq(sigma_delta);
+		ad_sd_disable_irq(sigma_delta);
+	}
 
 	sigma_delta->keep_cs_asserted = false;
 	ad_sigma_delta_set_mode(sigma_delta, AD_SD_MODE_IDLE);
@@ -679,7 +709,8 @@ static irqreturn_t ad_sd_data_rdy_trig_poll(int irq, void *private)
 	if ((!sigma_delta->rdy_gpiod || gpiod_get_value(sigma_delta->rdy_gpiod)) &&
 	    ad_sd_disable_irq(sigma_delta)) {
 		complete(&sigma_delta->completion);
-		iio_trigger_poll(sigma_delta->trig);
+		if (sigma_delta->trig)
+			iio_trigger_poll(sigma_delta->trig);
 
 		return IRQ_HANDLED;
 	}
@@ -712,17 +743,6 @@ static int devm_ad_sd_probe_trigger(struct device *dev, struct iio_dev *indio_de
 	unsigned long irq_flags = irq_get_trigger_type(sigma_delta->irq_line);
 	int ret;
 
-	if (dev != &sigma_delta->spi->dev) {
-		dev_err(dev, "Trigger parent should be '%s', got '%s'\n",
-			dev_name(dev), dev_name(&sigma_delta->spi->dev));
-		return -EFAULT;
-	}
-
-	sigma_delta->trig = devm_iio_trigger_alloc(dev, "%s-dev%d", indio_dev->name,
-						   iio_device_id(indio_dev));
-	if (sigma_delta->trig == NULL)
-		return -ENOMEM;
-
 	init_completion(&sigma_delta->completion);
 
 	sigma_delta->irq_dis = true;
@@ -742,14 +762,33 @@ static int devm_ad_sd_probe_trigger(struct device *dev, struct iio_dev *indio_de
 	if (ret)
 		return ret;
 
-	iio_trigger_set_drvdata(sigma_delta->trig, sigma_delta);
+	if (ad_sigma_delta_has_spi_offload(sigma_delta)) {
+		sigma_delta->offload_trigger =
+			devm_spi_offload_trigger_get(dev, sigma_delta->offload,
+						     SPI_OFFLOAD_TRIGGER_DATA_READY);
+		if (IS_ERR(sigma_delta->offload_trigger))
+			return dev_err_probe(dev, PTR_ERR(sigma_delta->offload_trigger),
+					     "Failed to get SPI offload trigger\n");
+	} else {
+		if (dev != &sigma_delta->spi->dev)
+			return dev_err_probe(dev, -EFAULT,
+				"Trigger parent should be '%s', got '%s'\n",
+				dev_name(dev), dev_name(&sigma_delta->spi->dev));
 
-	ret = devm_iio_trigger_register(dev, sigma_delta->trig);
-	if (ret)
-		return ret;
+		sigma_delta->trig = devm_iio_trigger_alloc(dev, "%s-dev%d",
+			indio_dev->name, iio_device_id(indio_dev));
+		if (!sigma_delta->trig)
+			return -ENOMEM;
 
-	/* select default trigger */
-	indio_dev->trig = iio_trigger_get(sigma_delta->trig);
+		iio_trigger_set_drvdata(sigma_delta->trig, sigma_delta);
+
+		ret = devm_iio_trigger_register(dev, sigma_delta->trig);
+		if (ret)
+			return ret;
+
+		/* select default trigger */
+		indio_dev->trig = iio_trigger_get(sigma_delta->trig);
+	}
 
 	return 0;
 }
@@ -769,12 +808,29 @@ int devm_ad_sd_setup_buffer_and_trigger(struct device *dev, struct iio_dev *indi
 	if (!sigma_delta->slots)
 		return -ENOMEM;
 
-	ret = devm_iio_triggered_buffer_setup(dev, indio_dev,
-					      &iio_pollfunc_store_time,
-					      &ad_sd_trigger_handler,
-					      &ad_sd_buffer_setup_ops);
-	if (ret)
-		return ret;
+	if (ad_sigma_delta_has_spi_offload(sigma_delta)) {
+		struct dma_chan *rx_dma;
+
+		rx_dma = devm_spi_offload_rx_stream_request_dma_chan(dev,
+			sigma_delta->offload);
+		if (IS_ERR(rx_dma))
+			return dev_err_probe(dev, PTR_ERR(rx_dma),
+					     "Failed to get RX DMA channel\n");
+
+		ret = devm_iio_dmaengine_buffer_setup_with_handle(dev, indio_dev,
+			rx_dma, IIO_BUFFER_DIRECTION_IN);
+		if (ret)
+			return dev_err_probe(dev, ret, "Cannot setup DMA buffer\n");
+
+		indio_dev->setup_ops = &ad_sd_buffer_setup_ops;
+	} else {
+		ret = devm_iio_triggered_buffer_setup(dev, indio_dev,
+						      &iio_pollfunc_store_time,
+						      &ad_sd_trigger_handler,
+						      &ad_sd_buffer_setup_ops);
+		if (ret)
+			return ret;
+	}
 
 	return devm_ad_sd_probe_trigger(dev, indio_dev);
 }
@@ -837,6 +893,20 @@ int ad_sd_init(struct ad_sigma_delta *sigma_delta, struct iio_dev *indio_dev,
 			return sigma_delta->irq_line;
 	}
 
+	if (info->supports_spi_offload) {
+		struct spi_offload_config offload_config = {
+			.capability_flags = SPI_OFFLOAD_CAP_TRIGGER |
+					    SPI_OFFLOAD_CAP_RX_STREAM_DMA,
+		};
+		int ret;
+
+		sigma_delta->offload = devm_spi_offload_get(&spi->dev, spi,
+							    &offload_config);
+		ret = PTR_ERR_OR_ZERO(sigma_delta->offload);
+		if (ret && ret != -ENODEV)
+			return dev_err_probe(&spi->dev, ret, "Failed to get SPI offload\n");
+	}
+
 	iio_device_set_drvdata(indio_dev, sigma_delta);
 
 	return 0;
@@ -846,3 +916,4 @@ EXPORT_SYMBOL_NS_GPL(ad_sd_init, "IIO_AD_SIGMA_DELTA");
 MODULE_AUTHOR("Lars-Peter Clausen <lars@metafoo.de>");
 MODULE_DESCRIPTION("Analog Devices Sigma-Delta ADCs");
 MODULE_LICENSE("GPL v2");
+MODULE_IMPORT_NS("IIO_DMAENGINE_BUFFER");
diff --git a/include/linux/iio/adc/ad_sigma_delta.h b/include/linux/iio/adc/ad_sigma_delta.h
index 2037bb68b441..6e70a412e218 100644
--- a/include/linux/iio/adc/ad_sigma_delta.h
+++ b/include/linux/iio/adc/ad_sigma_delta.h
@@ -31,6 +31,8 @@ struct ad_sigma_delta;
 struct device;
 struct gpio_desc;
 struct iio_dev;
+struct spi_offload;
+struct spi_offload_trigger;
 
 /**
  * struct ad_sigma_delta_info - Sigma Delta driver specific callbacks and options
@@ -47,6 +49,10 @@ struct iio_dev;
  * @has_registers: true if the device has writable and readable registers, false
  *		if there is just one read-only sample data shift register.
  * @has_named_irqs: Set to true if there is more than one IRQ line.
+ * @supports_spi_offload: Set to true if the driver supports SPI offload. Often
+ *		special considerations are needed for scan_type and other channel
+ *		info, so individual drivers have to set this to let the core
+ *		code know that it can use SPI offload if it is available.
  * @addr_shift: Shift of the register address in the communications register.
  * @read_mask: Mask for the communications register having the read bit set.
  * @status_ch_mask: Mask for the channel number stored in status register.
@@ -65,6 +71,7 @@ struct ad_sigma_delta_info {
 	int (*postprocess_sample)(struct ad_sigma_delta *, unsigned int raw_sample);
 	bool has_registers;
 	bool has_named_irqs;
+	bool supports_spi_offload;
 	unsigned int addr_shift;
 	unsigned int read_mask;
 	unsigned int status_ch_mask;
@@ -108,6 +115,8 @@ struct ad_sigma_delta {
 	struct spi_message	sample_msg;
 	struct spi_transfer	sample_xfer[2];
 	u8			*samples_buf;
+	struct spi_offload	*offload;
+	struct spi_offload_trigger *offload_trigger;
 
 	/*
 	 * DMA (thus cache coherency maintenance) requires the
@@ -121,6 +130,11 @@ struct ad_sigma_delta {
 	u8				sample_addr;
 };
 
+static inline bool ad_sigma_delta_has_spi_offload(struct ad_sigma_delta *sd)
+{
+	return sd->offload != NULL;
+}
+
 static inline int ad_sigma_delta_set_channel(struct ad_sigma_delta *sd,
 	unsigned int channel)
 {
-- 
cgit v1.2.3


From e24d552a17e92714d4f62e112d536babd6428acb Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Fri, 20 Jun 2025 16:33:05 +0100
Subject: mm/madvise: eliminate very confusing manipulation of prev VMA

The madvise code has for the longest time had very confusing code around
the 'prev' VMA pointer passed around various functions which, in all cases
except madvise_update_vma(), is unused and instead simply updated as soon
as the function is invoked.

To compound the confusion, the prev pointer is also used to indicate to
the caller that the mmap lock has been dropped and that we can therefore
not safely access the end of the current VMA (which might have been
updated by madvise_update_vma()).

Clear up this confusion by not setting prev = vma anywhere except in
madvise_walk_vmas(), update all references to prev which will always be
equal to vma after madvise_vma_behavior() is invoked, and adding a flag to
indicate that the lock has been dropped to make this explicit.

Additionally, drop a redundant BUG_ON() from madvise_collapse(), which is
simply reiterating the BUG_ON(mmap_locked) above it (note that BUG_ON() is
not appropriate here, but we leave existing code as-is).

We finally adjust the madvise_walk_vmas() logic to be a little clearer -
delaying the assignment of the end of the range to the start of the new
range until the last moment and handling the lock being dropped scenario
immediately.

Additionally add some explanatory comments.

[lorenzo.stoakes@oracle.com: fix very subtle bug]
  Link: https://lkml.kernel.org/r/dca94cde-8afb-4eab-8e57-3f508624d670@lucifer.local
Link: https://lkml.kernel.org/r/63d281c5df2e64225ab5b4bda398b45e22818701.1750433500.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Barry Song <baohua@kernel.org>
Cc: David Hildenbrand <david@redhat.com>
Cc: Dev Jain <dev.jain@arm.com>
Cc: Jann Horn <jannh@google.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/huge_mm.h |  9 +++---
 mm/khugepaged.c         |  9 ++----
 mm/madvise.c            | 77 +++++++++++++++++++++++++------------------------
 3 files changed, 47 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 8f1b15213f61..4d5bb67dc4ec 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -433,9 +433,8 @@ change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
 
 int hugepage_madvise(struct vm_area_struct *vma, vm_flags_t *vm_flags,
 		     int advice);
-int madvise_collapse(struct vm_area_struct *vma,
-		     struct vm_area_struct **prev,
-		     unsigned long start, unsigned long end);
+int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end, bool *lock_dropped);
 void vma_adjust_trans_huge(struct vm_area_struct *vma, unsigned long start,
 			   unsigned long end, struct vm_area_struct *next);
 spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma);
@@ -596,8 +595,8 @@ static inline int hugepage_madvise(struct vm_area_struct *vma,
 }
 
 static inline int madvise_collapse(struct vm_area_struct *vma,
-				   struct vm_area_struct **prev,
-				   unsigned long start, unsigned long end)
+				   unsigned long start,
+				   unsigned long end, bool *lock_dropped)
 {
 	return -EINVAL;
 }
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 3495a20cef5e..1aa7ca67c756 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -2727,8 +2727,8 @@ static int madvise_collapse_errno(enum scan_result r)
 	}
 }
 
-int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
-		     unsigned long start, unsigned long end)
+int madvise_collapse(struct vm_area_struct *vma, unsigned long start,
+		     unsigned long end, bool *lock_dropped)
 {
 	struct collapse_control *cc;
 	struct mm_struct *mm = vma->vm_mm;
@@ -2739,8 +2739,6 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 	BUG_ON(vma->vm_start > start);
 	BUG_ON(vma->vm_end < end);
 
-	*prev = vma;
-
 	if (!thp_vma_allowable_order(vma, vma->vm_flags, 0, PMD_ORDER))
 		return -EINVAL;
 
@@ -2788,7 +2786,7 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
 							 &mmap_locked, cc);
 		}
 		if (!mmap_locked)
-			*prev = NULL;  /* Tell caller we dropped mmap_lock */
+			*lock_dropped = true;
 
 handle_result:
 		switch (result) {
@@ -2798,7 +2796,6 @@ handle_result:
 			break;
 		case SCAN_PTE_MAPPED_HUGEPAGE:
 			BUG_ON(mmap_locked);
-			BUG_ON(*prev);
 			mmap_read_lock(mm);
 			result = collapse_pte_mapped_thp(mm, addr, true);
 			mmap_read_unlock(mm);
diff --git a/mm/madvise.c b/mm/madvise.c
index f04b8165e2ab..c467ee42596f 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -75,7 +75,9 @@ struct madvise_behavior {
 	 */
 	struct madvise_behavior_range range;
 	/* The VMA and VMA preceding it (if applicable) currently targeted. */
-	struct vm_area_struct *prev, *vma;
+	struct vm_area_struct *prev;
+	struct vm_area_struct *vma;
+	bool lock_dropped;
 };
 
 #ifdef CONFIG_ANON_VMA_NAME
@@ -188,10 +190,8 @@ static int madvise_update_vma(vm_flags_t new_flags,
 	struct anon_vma_name *anon_name = madv_behavior->anon_name;
 	VMA_ITERATOR(vmi, madv_behavior->mm, range->start);
 
-	if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) {
-		madv_behavior->prev = vma;
+	if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name))
 		return 0;
-	}
 
 	vma = vma_modify_flags_name(&vmi, madv_behavior->prev, vma,
 			range->start, range->end, new_flags, anon_name);
@@ -199,7 +199,6 @@ static int madvise_update_vma(vm_flags_t new_flags,
 		return PTR_ERR(vma);
 
 	madv_behavior->vma = vma;
-	madv_behavior->prev = vma;
 
 	/* vm_flags is protected by the mmap_lock held in write mode. */
 	vma_start_write(vma);
@@ -301,6 +300,12 @@ static void shmem_swapin_range(struct vm_area_struct *vma,
 }
 #endif		/* CONFIG_SWAP */
 
+static void mark_mmap_lock_dropped(struct madvise_behavior *madv_behavior)
+{
+	VM_WARN_ON_ONCE(madv_behavior->lock_mode == MADVISE_VMA_READ_LOCK);
+	madv_behavior->lock_dropped = true;
+}
+
 /*
  * Schedule all required I/O operations.  Do not wait for completion.
  */
@@ -313,7 +318,6 @@ static long madvise_willneed(struct madvise_behavior *madv_behavior)
 	unsigned long end = madv_behavior->range.end;
 	loff_t offset;
 
-	madv_behavior->prev = vma;
 #ifdef CONFIG_SWAP
 	if (!file) {
 		walk_page_range_vma(vma, start, end, &swapin_walk_ops, vma);
@@ -342,7 +346,7 @@ static long madvise_willneed(struct madvise_behavior *madv_behavior)
 	 * vma's reference to the file) can go away as soon as we drop
 	 * mmap_lock.
 	 */
-	madv_behavior->prev = NULL;	/* tell sys_madvise we drop mmap_lock */
+	mark_mmap_lock_dropped(madv_behavior);
 	get_file(file);
 	offset = (loff_t)(start - vma->vm_start)
 			+ ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
@@ -633,7 +637,6 @@ static long madvise_cold(struct madvise_behavior *madv_behavior)
 	struct vm_area_struct *vma = madv_behavior->vma;
 	struct mmu_gather tlb;
 
-	madv_behavior->prev = vma;
 	if (!can_madv_lru_vma(vma))
 		return -EINVAL;
 
@@ -665,7 +668,6 @@ static long madvise_pageout(struct madvise_behavior *madv_behavior)
 	struct mmu_gather tlb;
 	struct vm_area_struct *vma = madv_behavior->vma;
 
-	madv_behavior->prev = vma;
 	if (!can_madv_lru_vma(vma))
 		return -EINVAL;
 
@@ -954,7 +956,6 @@ static long madvise_dontneed_free(struct madvise_behavior *madv_behavior)
 	struct madvise_behavior_range *range = &madv_behavior->range;
 	int behavior = madv_behavior->behavior;
 
-	madv_behavior->prev = madv_behavior->vma;
 	if (!madvise_dontneed_free_valid_vma(madv_behavior))
 		return -EINVAL;
 
@@ -964,8 +965,7 @@ static long madvise_dontneed_free(struct madvise_behavior *madv_behavior)
 	if (!userfaultfd_remove(madv_behavior->vma, range->start, range->end)) {
 		struct vm_area_struct *vma;
 
-		madv_behavior->prev = NULL; /* mmap_lock has been dropped, prev is stale */
-
+		mark_mmap_lock_dropped(madv_behavior);
 		mmap_read_lock(mm);
 		madv_behavior->vma = vma = vma_lookup(mm, range->start);
 		if (!vma)
@@ -1064,7 +1064,7 @@ static long madvise_remove(struct madvise_behavior *madv_behavior)
 	unsigned long start = madv_behavior->range.start;
 	unsigned long end = madv_behavior->range.end;
 
-	madv_behavior->prev = NULL; /* tell sys_madvise we drop mmap_lock */
+	mark_mmap_lock_dropped(madv_behavior);
 
 	if (vma->vm_flags & VM_LOCKED)
 		return -EINVAL;
@@ -1183,7 +1183,6 @@ static long madvise_guard_install(struct madvise_behavior *madv_behavior)
 	long err;
 	int i;
 
-	madv_behavior->prev = vma;
 	if (!is_valid_guard_vma(vma, /* allow_locked = */false))
 		return -EINVAL;
 
@@ -1293,7 +1292,6 @@ static long madvise_guard_remove(struct madvise_behavior *madv_behavior)
 	struct vm_area_struct *vma = madv_behavior->vma;
 	struct madvise_behavior_range *range = &madv_behavior->range;
 
-	madv_behavior->prev = vma;
 	/*
 	 * We're ok with removing guards in mlock()'d ranges, as this is a
 	 * non-destructive action.
@@ -1336,8 +1334,8 @@ static int madvise_vma_behavior(struct madvise_behavior *madv_behavior)
 	case MADV_DONTNEED_LOCKED:
 		return madvise_dontneed_free(madv_behavior);
 	case MADV_COLLAPSE:
-		return madvise_collapse(vma, &madv_behavior->prev,
-					range->start, range->end);
+		return madvise_collapse(vma, range->start, range->end,
+			&madv_behavior->lock_dropped);
 	case MADV_GUARD_INSTALL:
 		return madvise_guard_install(madv_behavior);
 	case MADV_GUARD_REMOVE:
@@ -1589,7 +1587,6 @@ static bool try_vma_read_lock(struct madvise_behavior *madv_behavior)
 		vma_end_read(vma);
 		goto take_mmap_read_lock;
 	}
-	madv_behavior->prev = vma; /* Not currently required. */
 	madv_behavior->vma = vma;
 	return true;
 
@@ -1617,7 +1614,7 @@ int madvise_walk_vmas(struct madvise_behavior *madv_behavior)
 	unsigned long last_end = range->end;
 	int unmapped_error = 0;
 	int error;
-	struct vm_area_struct *vma;
+	struct vm_area_struct *prev, *vma;
 
 	/*
 	 * If VMA read lock is supported, apply madvise to a single VMA
@@ -1630,24 +1627,23 @@ int madvise_walk_vmas(struct madvise_behavior *madv_behavior)
 		return error;
 	}
 
-	/*
-	 * If the interval [start,end) covers some unmapped address
-	 * ranges, just ignore them, but return -ENOMEM at the end.
-	 * - different from the way of handling in mlock etc.
-	 */
-	vma = find_vma_prev(mm, range->start, &madv_behavior->prev);
+	vma = find_vma_prev(mm, range->start, &prev);
 	if (vma && range->start > vma->vm_start)
-		madv_behavior->prev = vma;
+		prev = vma;
 
 	for (;;) {
-		struct vm_area_struct *prev;
-
 		/* Still start < end. */
 		if (!vma)
 			return -ENOMEM;
 
 		/* Here start < (last_end|vma->vm_end). */
 		if (range->start < vma->vm_start) {
+			/*
+			 * This indicates a gap between VMAs in the input
+			 * range. This does not cause the operation to abort,
+			 * rather we simply return -ENOMEM to indicate that this
+			 * has happened, but carry on.
+			 */
 			unmapped_error = -ENOMEM;
 			range->start = vma->vm_start;
 			if (range->start >= last_end)
@@ -1658,21 +1654,28 @@ int madvise_walk_vmas(struct madvise_behavior *madv_behavior)
 		range->end = min(vma->vm_end, last_end);
 
 		/* Here vma->vm_start <= range->start < range->end <= (last_end|vma->vm_end). */
+		madv_behavior->prev = prev;
 		madv_behavior->vma = vma;
 		error = madvise_vma_behavior(madv_behavior);
 		if (error)
 			return error;
-		prev = madv_behavior->prev;
+		if (madv_behavior->lock_dropped) {
+			/* We dropped the mmap lock, we can't ref the VMA. */
+			prev = NULL;
+			vma = NULL;
+			madv_behavior->lock_dropped = false;
+		} else {
+			vma = madv_behavior->vma;
+			prev = vma;
+		}
 
-		range->start = range->end;
-		if (prev && range->start < prev->vm_end)
-			range->start = prev->vm_end;
-		if (range->start >= last_end)
+		if (vma && range->end < vma->vm_end)
+			range->end = vma->vm_end;
+		if (range->end >= last_end)
 			break;
-		if (prev)
-			vma = find_vma(mm, prev->vm_end);
-		else	/* madvise_remove dropped mmap_lock */
-			vma = find_vma(mm, range->start);
+
+		vma = find_vma(mm, vma ? vma->vm_end : range->end);
+		range->start = range->end;
 	}
 
 	return unmapped_error;
-- 
cgit v1.2.3


From 6b233784b198e0d6dbfd526341b6ec51ffd30020 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Tue, 24 Jun 2025 15:03:46 +0200
Subject: mm, madvise: extract mm code from prctl_set_vma() to mm/madvise.c

Setting anon_name is done via madvise_set_anon_name() and behaves a lot of
like other madvise operations.  However, apparently because madvise() has
lacked the 4th argument and prctl() not, the userspace entry point has
been implemented via prctl(PR_SET_VMA, ...) and handled first by
prctl_set_vma().

Currently prctl_set_vma() lives in kernel/sys.c but setting the
vma->anon_name is mm-specific code so extract it to a new
set_anon_vma_name() function under mm.  mm/madvise.c seems to be the most
straightforward place as that's where madvise_set_anon_name() lives.  Stop
declaring the latter in mm.h and instead declare set_anon_vma_name().

Link: https://lkml.kernel.org/r/20250624-anon_name_cleanup-v2-2-600075462a11@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Tested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Colin Cross <ccross@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 14 +++++++-------
 kernel/sys.c       | 50 +-------------------------------------------------
 mm/madvise.c       | 52 ++++++++++++++++++++++++++++++++++++++++++++++++++--
 3 files changed, 58 insertions(+), 58 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0e0549f3d681..ef40f68c1183 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4059,14 +4059,14 @@ unsigned long wp_shared_mapping_range(struct address_space *mapping,
 #endif
 
 #ifdef CONFIG_ANON_VMA_NAME
-int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
-			  unsigned long len_in,
-			  struct anon_vma_name *anon_name);
+int set_anon_vma_name(unsigned long addr, unsigned long size,
+		      const char __user *uname);
 #else
-static inline int
-madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
-		      unsigned long len_in, struct anon_vma_name *anon_name) {
-	return 0;
+static inline
+int set_anon_vma_name(unsigned long addr, unsigned long size,
+		      const char __user *uname)
+{
+	return -EINVAL;
 }
 #endif
 
diff --git a/kernel/sys.c b/kernel/sys.c
index adc0de0aa364..b153fb345ada 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -2343,54 +2343,14 @@ int __weak arch_lock_shadow_stack_status(struct task_struct *t, unsigned long st
 
 #define PR_IO_FLUSHER (PF_MEMALLOC_NOIO | PF_LOCAL_THROTTLE)
 
-#ifdef CONFIG_ANON_VMA_NAME
-
-#define ANON_VMA_NAME_MAX_LEN		80
-#define ANON_VMA_NAME_INVALID_CHARS	"\\`$[]"
-
-static inline bool is_valid_name_char(char ch)
-{
-	/* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */
-	return ch > 0x1f && ch < 0x7f &&
-		!strchr(ANON_VMA_NAME_INVALID_CHARS, ch);
-}
-
 static int prctl_set_vma(unsigned long opt, unsigned long addr,
 			 unsigned long size, unsigned long arg)
 {
-	struct mm_struct *mm = current->mm;
-	const char __user *uname;
-	struct anon_vma_name *anon_name = NULL;
 	int error;
 
 	switch (opt) {
 	case PR_SET_VMA_ANON_NAME:
-		uname = (const char __user *)arg;
-		if (uname) {
-			char *name, *pch;
-
-			name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN);
-			if (IS_ERR(name))
-				return PTR_ERR(name);
-
-			for (pch = name; *pch != '\0'; pch++) {
-				if (!is_valid_name_char(*pch)) {
-					kfree(name);
-					return -EINVAL;
-				}
-			}
-			/* anon_vma has its own copy */
-			anon_name = anon_vma_name_alloc(name);
-			kfree(name);
-			if (!anon_name)
-				return -ENOMEM;
-
-		}
-
-		mmap_write_lock(mm);
-		error = madvise_set_anon_name(mm, addr, size, anon_name);
-		mmap_write_unlock(mm);
-		anon_vma_name_put(anon_name);
+		error = set_anon_vma_name(addr, size, (const char __user *)arg);
 		break;
 	default:
 		error = -EINVAL;
@@ -2399,14 +2359,6 @@ static int prctl_set_vma(unsigned long opt, unsigned long addr,
 	return error;
 }
 
-#else /* CONFIG_ANON_VMA_NAME */
-static int prctl_set_vma(unsigned long opt, unsigned long start,
-			 unsigned long size, unsigned long arg)
-{
-	return -EINVAL;
-}
-#endif /* CONFIG_ANON_VMA_NAME */
-
 static inline unsigned long get_current_mdwe(void)
 {
 	unsigned long ret = 0;
diff --git a/mm/madvise.c b/mm/madvise.c
index 0ca405017b37..a2294bc1cc7b 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -134,8 +134,8 @@ static int replace_anon_vma_name(struct vm_area_struct *vma,
 	return 0;
 }
 
-int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
-			  unsigned long len_in, struct anon_vma_name *anon_name)
+static int madvise_set_anon_name(struct mm_struct *mm, unsigned long start,
+		unsigned long len_in, struct anon_vma_name *anon_name)
 {
 	unsigned long end;
 	unsigned long len;
@@ -2096,3 +2096,51 @@ free_iov:
 out:
 	return ret;
 }
+
+#ifdef CONFIG_ANON_VMA_NAME
+
+#define ANON_VMA_NAME_MAX_LEN		80
+#define ANON_VMA_NAME_INVALID_CHARS	"\\`$[]"
+
+static inline bool is_valid_name_char(char ch)
+{
+	/* printable ascii characters, excluding ANON_VMA_NAME_INVALID_CHARS */
+	return ch > 0x1f && ch < 0x7f &&
+		!strchr(ANON_VMA_NAME_INVALID_CHARS, ch);
+}
+
+int set_anon_vma_name(unsigned long addr, unsigned long size,
+		      const char __user *uname)
+{
+	struct anon_vma_name *anon_name = NULL;
+	struct mm_struct *mm = current->mm;
+	int error;
+
+	if (uname) {
+		char *name, *pch;
+
+		name = strndup_user(uname, ANON_VMA_NAME_MAX_LEN);
+		if (IS_ERR(name))
+			return PTR_ERR(name);
+
+		for (pch = name; *pch != '\0'; pch++) {
+			if (!is_valid_name_char(*pch)) {
+				kfree(name);
+				return -EINVAL;
+			}
+		}
+		/* anon_vma has its own copy */
+		anon_name = anon_vma_name_alloc(name);
+		kfree(name);
+		if (!anon_name)
+			return -ENOMEM;
+	}
+
+	mmap_write_lock(mm);
+	error = madvise_set_anon_name(mm, addr, size, anon_name);
+	mmap_write_unlock(mm);
+	anon_vma_name_put(anon_name);
+
+	return error;
+}
+#endif
-- 
cgit v1.2.3


From 8d2882a8edb8621d37fd8931e0686070cc6cc189 Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Mon, 16 Jun 2025 15:51:45 +0200
Subject: mm,memory_hotplug: remove status_change_nid_normal and update
 documentation

Now that the last user of status_change_nid_normal is gone, we can remove
it.  Update documentation accordingly.

Link: https://lkml.kernel.org/r/20250616135158.450136-3-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Joanthan Cameron <Jonathan.Cameron@huawei.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/core-api/memory-hotplug.rst                    |  3 ---
 Documentation/translations/zh_CN/core-api/memory-hotplug.rst |  3 ---
 include/linux/memory.h                                       |  1 -
 mm/memory_hotplug.c                                          | 12 ------------
 4 files changed, 19 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/memory-hotplug.rst b/Documentation/core-api/memory-hotplug.rst
index 682259ee633a..d1b8eb9add8a 100644
--- a/Documentation/core-api/memory-hotplug.rst
+++ b/Documentation/core-api/memory-hotplug.rst
@@ -56,14 +56,11 @@ The third argument (arg) passes a pointer of struct memory_notify::
 	struct memory_notify {
 		unsigned long start_pfn;
 		unsigned long nr_pages;
-		int status_change_nid_normal;
 		int status_change_nid;
 	}
 
 - start_pfn is start_pfn of online/offline memory.
 - nr_pages is # of pages of online/offline memory.
-- status_change_nid_normal is set node id when N_NORMAL_MEMORY of nodemask
-  is (will be) set/clear, if this is -1, then nodemask status is not changed.
 - status_change_nid is set node id when N_MEMORY of nodemask is (will be)
   set/clear. It means a new(memoryless) node gets new memory by online and a
   node loses all memory. If this is -1, then nodemask status is not changed.
diff --git a/Documentation/translations/zh_CN/core-api/memory-hotplug.rst b/Documentation/translations/zh_CN/core-api/memory-hotplug.rst
index 9b2841fb9a5f..c2a4122ae221 100644
--- a/Documentation/translations/zh_CN/core-api/memory-hotplug.rst
+++ b/Documentation/translations/zh_CN/core-api/memory-hotplug.rst
@@ -62,7 +62,6 @@ memory_notify结构体的指针::
 	struct memory_notify {
 		unsigned long start_pfn;
 		unsigned long nr_pages;
-		int status_change_nid_normal;
 		int status_change_nid;
 	}
 
@@ -70,8 +69,6 @@ memory_notify结构体的指针::
 
 - nr_pages是在线/离线内存的页数。
 
-- status_change_nid_normal是当nodemask的N_NORMAL_MEMORY被设置/清除时设置节
-  点id，如果是-1，则nodemask状态不改变。
 
 - status_change_nid是当nodemask的N_MEMORY被（将）设置/清除时设置的节点id。这
   意味着一个新的（没上线的）节点通过联机获得新的内存，而一个节点失去了所有的内
diff --git a/include/linux/memory.h b/include/linux/memory.h
index bd4440bc4a57..a8284d41e452 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -109,7 +109,6 @@ struct memory_notify {
 	unsigned long altmap_nr_pages;
 	unsigned long start_pfn;
 	unsigned long nr_pages;
-	int status_change_nid_normal;
 	int status_change_nid;
 };
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index bec20a91e757..d11278c3840d 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -706,19 +706,13 @@ static void node_states_check_changes_online(unsigned long nr_pages,
 	int nid = zone_to_nid(zone);
 
 	arg->status_change_nid = NUMA_NO_NODE;
-	arg->status_change_nid_normal = NUMA_NO_NODE;
 
 	if (!node_state(nid, N_MEMORY))
 		arg->status_change_nid = nid;
-	if (zone_idx(zone) <= ZONE_NORMAL && !node_state(nid, N_NORMAL_MEMORY))
-		arg->status_change_nid_normal = nid;
 }
 
 static void node_states_set_node(int node, struct memory_notify *arg)
 {
-	if (arg->status_change_nid_normal >= 0)
-		node_set_state(node, N_NORMAL_MEMORY);
-
 	if (arg->status_change_nid >= 0)
 		node_set_state(node, N_MEMORY);
 }
@@ -1894,7 +1888,6 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
 	enum zone_type zt;
 
 	arg->status_change_nid = NUMA_NO_NODE;
-	arg->status_change_nid_normal = NUMA_NO_NODE;
 
 	/*
 	 * Check whether node_states[N_NORMAL_MEMORY] will be changed.
@@ -1906,8 +1899,6 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
 	 */
 	for (zt = 0; zt <= ZONE_NORMAL; zt++)
 		present_pages += pgdat->node_zones[zt].present_pages;
-	if (zone_idx(zone) <= ZONE_NORMAL && nr_pages >= present_pages)
-		arg->status_change_nid_normal = zone_to_nid(zone);
 
 	/*
 	 * We have accounted the pages from [0..ZONE_NORMAL); ZONE_HIGHMEM
@@ -1926,9 +1917,6 @@ static void node_states_check_changes_offline(unsigned long nr_pages,
 
 static void node_states_clear_node(int node, struct memory_notify *arg)
 {
-	if (arg->status_change_nid_normal >= 0)
-		node_clear_state(node, N_NORMAL_MEMORY);
-
 	if (arg->status_change_nid >= 0)
 		node_clear_state(node, N_MEMORY);
 }
-- 
cgit v1.2.3


From 67929de108479dbb78496b61af5c24072fc16d8d Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Mon, 16 Jun 2025 15:51:46 +0200
Subject: mm,memory_hotplug: implement numa node notifier

There are at least six consumers of hotplug_memory_notifier that what they
really are interested in is whether any numa node changed its state, e.g:
going from having memory to not having memory and vice versa.

Implement a specific notifier for numa nodes when their state gets
changed, which will later be used by those consumers that are only
interested in numa node state changes.

Add documentation as well.

[dan.carpenter@linaro.org: set failure reason in offline_pages()]
  Link: https://lkml.kernel.org/r/be4fd31b-7d09-46b0-8329-6d0464ffa7a5@sabinyo.mountain
Link: https://lkml.kernel.org/r/20250616135158.450136-4-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/core-api/memory-hotplug.rst |  83 +++++++++++++++++
 drivers/base/node.c                       |  21 +++++
 include/linux/node.h                      |  40 ++++++++
 mm/memory_hotplug.c                       | 146 ++++++++++++++----------------
 4 files changed, 210 insertions(+), 80 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/memory-hotplug.rst b/Documentation/core-api/memory-hotplug.rst
index d1b8eb9add8a..fb84e78968b2 100644
--- a/Documentation/core-api/memory-hotplug.rst
+++ b/Documentation/core-api/memory-hotplug.rst
@@ -9,6 +9,9 @@ Memory hotplug event notifier
 
 Hotplugging events are sent to a notification queue.
 
+Memory notifier
+----------------
+
 There are six types of notification defined in ``include/linux/memory.h``:
 
 MEM_GOING_ONLINE
@@ -68,6 +71,14 @@ The third argument (arg) passes a pointer of struct memory_notify::
   If status_changed_nid* >= 0, callback should create/discard structures for the
   node if necessary.
 
+It is possible to get notified for MEM_CANCEL_ONLINE without having been notified
+for MEM_GOING_ONLINE, and the same applies to MEM_CANCEL_OFFLINE and
+MEM_GOING_OFFLINE.
+This can happen when a consumer fails, meaning we break the callchain and we
+stop calling the remaining consumers of the notifier.
+It is then important that users of memory_notify make no assumptions and get
+prepared to handle such cases.
+
 The callback routine shall return one of the values
 NOTIFY_DONE, NOTIFY_OK, NOTIFY_BAD, NOTIFY_STOP
 defined in ``include/linux/notifier.h``
@@ -80,6 +91,78 @@ further processing of the notification queue.
 
 NOTIFY_STOP stops further processing of the notification queue.
 
+Numa node notifier
+------------------
+
+There are six types of notification defined in ``include/linux/node.h``:
+
+NODE_ADDING_FIRST_MEMORY
+ Generated before memory becomes available to this node for the first time.
+
+NODE_CANCEL_ADDING_FIRST_MEMORY
+ Generated if NODE_ADDING_FIRST_MEMORY fails.
+
+NODE_ADDED_FIRST_MEMORY
+ Generated when memory has become available fo this node for the first time.
+
+NODE_REMOVING_LAST_MEMORY
+ Generated when the last memory available to this node is about to be offlined.
+
+NODE_CANCEL_REMOVING_LAST_MEMORY
+ Generated when NODE_CANCEL_REMOVING_LAST_MEMORY fails.
+
+NODE_REMOVED_LAST_MEMORY
+ Generated when the last memory available to this node has been offlined.
+
+A callback routine can be registered by calling::
+
+  hotplug_node_notifier(callback_func, priority)
+
+Callback functions with higher values of priority are called before callback
+functions with lower values.
+
+A callback function must have the following prototype::
+
+  int callback_func(
+
+    struct notifier_block *self, unsigned long action, void *arg);
+
+The first argument of the callback function (self) is a pointer to the block
+of the notifier chain that points to the callback function itself.
+The second argument (action) is one of the event types described above.
+The third argument (arg) passes a pointer of struct node_notify::
+
+        struct node_notify {
+                int nid;
+        }
+
+- nid is the node we are adding or removing memory to.
+
+It is possible to get notified for NODE_CANCEL_ADDING_FIRST_MEMORY without
+having been notified for NODE_ADDING_FIRST_MEMORY, and the same applies to
+NODE_CANCEL_REMOVING_LAST_MEMORY and NODE_REMOVING_LAST_MEMORY.
+This can happen when a consumer fails, meaning we break the callchain and we
+stop calling the remaining consumers of the notifier.
+It is then important that users of node_notify make no assumptions and get
+prepared to handle such cases.
+
+The callback routine shall return one of the values
+NOTIFY_DONE, NOTIFY_OK, NOTIFY_BAD, NOTIFY_STOP
+defined in ``include/linux/notifier.h``
+
+NOTIFY_DONE and NOTIFY_OK have no effect on the further processing.
+
+NOTIFY_BAD is used as response to the NODE_ADDING_FIRST_MEMORY,
+NODE_REMOVING_LAST_MEMORY, NODE_ADDED_FIRST_MEMORY or
+NODE_REMOVED_LAST_MEMORY action to cancel hotplugging.
+It stops further processing of the notification queue.
+
+NOTIFY_STOP stops further processing of the notification queue.
+
+Please note that we should not fail for NODE_ADDED_FIRST_MEMORY /
+NODE_REMOVED_FIRST_MEMORY, as memory_hotplug code cannot rollback at that
+point anymore.
+
 Locking Internals
 =================
 
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 6cbeca45c451..6d66382dae65 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -112,6 +112,27 @@ static const struct attribute_group *node_access_node_groups[] = {
 	NULL,
 };
 
+#ifdef CONFIG_MEMORY_HOTPLUG
+static BLOCKING_NOTIFIER_HEAD(node_chain);
+
+int register_node_notifier(struct notifier_block *nb)
+{
+	return blocking_notifier_chain_register(&node_chain, nb);
+}
+EXPORT_SYMBOL(register_node_notifier);
+
+void unregister_node_notifier(struct notifier_block *nb)
+{
+	blocking_notifier_chain_unregister(&node_chain, nb);
+}
+EXPORT_SYMBOL(unregister_node_notifier);
+
+int node_notify(unsigned long val, void *v)
+{
+	return blocking_notifier_call_chain(&node_chain, val, v);
+}
+#endif
+
 static void node_remove_accesses(struct node *node)
 {
 	struct node_access_nodes *c, *cnext;
diff --git a/include/linux/node.h b/include/linux/node.h
index 88bceebcbfa5..2c7529335b21 100644
--- a/include/linux/node.h
+++ b/include/linux/node.h
@@ -125,6 +125,46 @@ static inline void register_memory_blocks_under_nodes(void)
 #endif
 
 extern void unregister_node(struct node *node);
+
+struct node_notify {
+	int nid;
+};
+
+#define NODE_ADDING_FIRST_MEMORY                (1<<0)
+#define NODE_ADDED_FIRST_MEMORY                 (1<<1)
+#define NODE_CANCEL_ADDING_FIRST_MEMORY         (1<<2)
+#define NODE_REMOVING_LAST_MEMORY               (1<<3)
+#define NODE_REMOVED_LAST_MEMORY                (1<<4)
+#define NODE_CANCEL_REMOVING_LAST_MEMORY        (1<<5)
+
+#if defined(CONFIG_MEMORY_HOTPLUG) && defined(CONFIG_NUMA)
+extern int register_node_notifier(struct notifier_block *nb);
+extern void unregister_node_notifier(struct notifier_block *nb);
+extern int node_notify(unsigned long val, void *v);
+
+#define hotplug_node_notifier(fn, pri) ({		\
+	static __meminitdata struct notifier_block fn##_node_nb =\
+		{ .notifier_call = fn, .priority = pri };\
+	register_node_notifier(&fn##_node_nb);			\
+})
+#else
+static inline int register_node_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+static inline void unregister_node_notifier(struct notifier_block *nb)
+{
+}
+static inline int node_notify(unsigned long val, void *v)
+{
+	return 0;
+}
+static inline int hotplug_node_notifier(notifier_fn_t fn, int pri)
+{
+	return 0;
+}
+#endif
+
 #ifdef CONFIG_NUMA
 extern void node_dev_init(void);
 /* Core of the node registration - only memory hotplug should use this */
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index d11278c3840d..0d54a01985ba 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -35,6 +35,7 @@
 #include <linux/compaction.h>
 #include <linux/rmap.h>
 #include <linux/module.h>
+#include <linux/node.h>
 
 #include <asm/tlbflush.h>
 
@@ -699,24 +700,6 @@ static void online_pages_range(unsigned long start_pfn, unsigned long nr_pages)
 	online_mem_sections(start_pfn, end_pfn);
 }
 
-/* check which state of node_states will be changed when online memory */
-static void node_states_check_changes_online(unsigned long nr_pages,
-	struct zone *zone, struct memory_notify *arg)
-{
-	int nid = zone_to_nid(zone);
-
-	arg->status_change_nid = NUMA_NO_NODE;
-
-	if (!node_state(nid, N_MEMORY))
-		arg->status_change_nid = nid;
-}
-
-static void node_states_set_node(int node, struct memory_notify *arg)
-{
-	if (arg->status_change_nid >= 0)
-		node_set_state(node, N_MEMORY);
-}
-
 static void __meminit resize_zone_range(struct zone *zone, unsigned long start_pfn,
 		unsigned long nr_pages)
 {
@@ -1167,11 +1150,18 @@ void mhp_deinit_memmap_on_memory(unsigned long pfn, unsigned long nr_pages)
 int online_pages(unsigned long pfn, unsigned long nr_pages,
 		       struct zone *zone, struct memory_group *group)
 {
-	unsigned long flags;
-	int need_zonelists_rebuild = 0;
+	struct memory_notify mem_arg = {
+		.start_pfn = pfn,
+		.nr_pages = nr_pages,
+		.status_change_nid = NUMA_NO_NODE,
+	};
+	struct node_notify node_arg = {
+		.nid = NUMA_NO_NODE,
+	};
 	const int nid = zone_to_nid(zone);
+	int need_zonelists_rebuild = 0;
+	unsigned long flags;
 	int ret;
-	struct memory_notify arg;
 
 	/*
 	 * {on,off}lining is constrained to full memory sections (or more
@@ -1188,11 +1178,17 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 	/* associate pfn range with the zone */
 	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);
 
-	arg.start_pfn = pfn;
-	arg.nr_pages = nr_pages;
-	node_states_check_changes_online(nr_pages, zone, &arg);
+	if (!node_state(nid, N_MEMORY)) {
+		/* Adding memory to the node for the first time */
+		node_arg.nid = nid;
+		mem_arg.status_change_nid = nid;
+		ret = node_notify(NODE_ADDING_FIRST_MEMORY, &node_arg);
+		ret = notifier_to_errno(ret);
+		if (ret)
+			goto failed_addition;
+	}
 
-	ret = memory_notify(MEM_GOING_ONLINE, &arg);
+	ret = memory_notify(MEM_GOING_ONLINE, &mem_arg);
 	ret = notifier_to_errno(ret);
 	if (ret)
 		goto failed_addition;
@@ -1218,7 +1214,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 	online_pages_range(pfn, nr_pages);
 	adjust_present_page_count(pfn_to_page(pfn), group, nr_pages);
 
-	node_states_set_node(nid, &arg);
+	if (node_arg.nid >= 0)
+		node_set_state(nid, N_MEMORY);
 	if (need_zonelists_rebuild)
 		build_all_zonelists(NULL);
 
@@ -1239,16 +1236,22 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 	kswapd_run(nid);
 	kcompactd_run(nid);
 
+	if (node_arg.nid >= 0)
+		/* First memory added successfully. Notify consumers. */
+		node_notify(NODE_ADDED_FIRST_MEMORY, &node_arg);
+
 	writeback_set_ratelimit();
 
-	memory_notify(MEM_ONLINE, &arg);
+	memory_notify(MEM_ONLINE, &mem_arg);
 	return 0;
 
 failed_addition:
 	pr_debug("online_pages [mem %#010llx-%#010llx] failed\n",
 		 (unsigned long long) pfn << PAGE_SHIFT,
 		 (((unsigned long long) pfn + nr_pages) << PAGE_SHIFT) - 1);
-	memory_notify(MEM_CANCEL_ONLINE, &arg);
+	memory_notify(MEM_CANCEL_ONLINE, &mem_arg);
+	if (node_arg.nid != NUMA_NO_NODE)
+		node_notify(NODE_CANCEL_ADDING_FIRST_MEMORY, &node_arg);
 	remove_pfn_range_from_zone(zone, pfn, nr_pages);
 	return ret;
 }
@@ -1879,48 +1882,6 @@ static int __init cmdline_parse_movable_node(char *p)
 }
 early_param("movable_node", cmdline_parse_movable_node);
 
-/* check which state of node_states will be changed when offline memory */
-static void node_states_check_changes_offline(unsigned long nr_pages,
-		struct zone *zone, struct memory_notify *arg)
-{
-	struct pglist_data *pgdat = zone->zone_pgdat;
-	unsigned long present_pages = 0;
-	enum zone_type zt;
-
-	arg->status_change_nid = NUMA_NO_NODE;
-
-	/*
-	 * Check whether node_states[N_NORMAL_MEMORY] will be changed.
-	 * If the memory to be offline is within the range
-	 * [0..ZONE_NORMAL], and it is the last present memory there,
-	 * the zones in that range will become empty after the offlining,
-	 * thus we can determine that we need to clear the node from
-	 * node_states[N_NORMAL_MEMORY].
-	 */
-	for (zt = 0; zt <= ZONE_NORMAL; zt++)
-		present_pages += pgdat->node_zones[zt].present_pages;
-
-	/*
-	 * We have accounted the pages from [0..ZONE_NORMAL); ZONE_HIGHMEM
-	 * does not apply as we don't support 32bit.
-	 * Here we count the possible pages from ZONE_MOVABLE.
-	 * If after having accounted all the pages, we see that the nr_pages
-	 * to be offlined is over or equal to the accounted pages,
-	 * we know that the node will become empty, and so, we can clear
-	 * it for N_MEMORY as well.
-	 */
-	present_pages += pgdat->node_zones[ZONE_MOVABLE].present_pages;
-
-	if (nr_pages >= present_pages)
-		arg->status_change_nid = zone_to_nid(zone);
-}
-
-static void node_states_clear_node(int node, struct memory_notify *arg)
-{
-	if (arg->status_change_nid >= 0)
-		node_clear_state(node, N_MEMORY);
-}
-
 static int count_system_ram_pages_cb(unsigned long start_pfn,
 				     unsigned long nr_pages, void *data)
 {
@@ -1936,11 +1897,19 @@ static int count_system_ram_pages_cb(unsigned long start_pfn,
 int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			struct zone *zone, struct memory_group *group)
 {
-	const unsigned long end_pfn = start_pfn + nr_pages;
 	unsigned long pfn, managed_pages, system_ram_pages = 0;
+	const unsigned long end_pfn = start_pfn + nr_pages;
+	struct pglist_data *pgdat = zone->zone_pgdat;
 	const int node = zone_to_nid(zone);
+	struct memory_notify mem_arg = {
+		.start_pfn = start_pfn,
+		.nr_pages = nr_pages,
+		.status_change_nid = NUMA_NO_NODE,
+	};
+	struct node_notify node_arg = {
+		.nid = NUMA_NO_NODE,
+	};
 	unsigned long flags;
-	struct memory_notify arg;
 	char *reason;
 	int ret;
 
@@ -1999,11 +1968,23 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 		goto failed_removal_pcplists_disabled;
 	}
 
-	arg.start_pfn = start_pfn;
-	arg.nr_pages = nr_pages;
-	node_states_check_changes_offline(nr_pages, zone, &arg);
+	/*
+	 * Check whether the node will have no present pages after we offline
+	 * 'nr_pages' more. If so, we know that the node will become empty, and
+	 * so we will clear N_MEMORY for it.
+	 */
+	if (nr_pages >= pgdat->node_present_pages) {
+		node_arg.nid = node;
+		mem_arg.status_change_nid = node;
+		ret = node_notify(NODE_REMOVING_LAST_MEMORY, &node_arg);
+		ret = notifier_to_errno(ret);
+		if (ret) {
+			reason = "node notifier failure";
+			goto failed_removal_isolated;
+		}
+	}
 
-	ret = memory_notify(MEM_GOING_OFFLINE, &arg);
+	ret = memory_notify(MEM_GOING_OFFLINE, &mem_arg);
 	ret = notifier_to_errno(ret);
 	if (ret) {
 		reason = "notifier failure";
@@ -2083,27 +2064,32 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	 * Make sure to mark the node as memory-less before rebuilding the zone
 	 * list. Otherwise this node would still appear in the fallback lists.
 	 */
-	node_states_clear_node(node, &arg);
+	if (node_arg.nid >= 0)
+		node_clear_state(node, N_MEMORY);
 	if (!populated_zone(zone)) {
 		zone_pcp_reset(zone);
 		build_all_zonelists(NULL);
 	}
 
-	if (arg.status_change_nid >= 0) {
+	if (node_arg.nid >= 0) {
 		kcompactd_stop(node);
 		kswapd_stop(node);
+		/* Node went memoryless. Notify consumers */
+		node_notify(NODE_REMOVED_LAST_MEMORY, &node_arg);
 	}
 
 	writeback_set_ratelimit();
 
-	memory_notify(MEM_OFFLINE, &arg);
+	memory_notify(MEM_OFFLINE, &mem_arg);
 	remove_pfn_range_from_zone(zone, start_pfn, nr_pages);
 	return 0;
 
 failed_removal_isolated:
 	/* pushback to free area */
 	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
-	memory_notify(MEM_CANCEL_OFFLINE, &arg);
+	memory_notify(MEM_CANCEL_OFFLINE, &mem_arg);
+	if (node_arg.nid != NUMA_NO_NODE)
+		node_notify(NODE_CANCEL_REMOVING_LAST_MEMORY, &node_arg);
 failed_removal_pcplists_disabled:
 	lru_cache_enable();
 	zone_pcp_enable(zone);
-- 
cgit v1.2.3


From d2a9721d807de405b198291badcc807700746781 Mon Sep 17 00:00:00 2001
From: Oscar Salvador <osalvador@suse.de>
Date: Mon, 16 Jun 2025 15:51:54 +0200
Subject: mm,memory_hotplug: drop status_change_nid parameter from
 memory_notify

There no users left of status_change_nid, so drop it from memory_notify
struct.

Link: https://lkml.kernel.org/r/20250616135158.450136-12-osalvador@suse.de
Signed-off-by: Oscar Salvador <osalvador@suse.de>
Suggested-by: David Hildenbrand <david@redhat.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: Hyeonggon Yoo <42.hyeyoo@gmail.com>
Cc: Joanthan Cameron <Jonathan.Cameron@huawei.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/core-api/memory-hotplug.rst | 7 -------
 include/linux/memory.h                    | 1 -
 mm/memory_hotplug.c                       | 4 ----
 3 files changed, 12 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/core-api/memory-hotplug.rst b/Documentation/core-api/memory-hotplug.rst
index fb84e78968b2..8fc97c2379de 100644
--- a/Documentation/core-api/memory-hotplug.rst
+++ b/Documentation/core-api/memory-hotplug.rst
@@ -59,17 +59,10 @@ The third argument (arg) passes a pointer of struct memory_notify::
 	struct memory_notify {
 		unsigned long start_pfn;
 		unsigned long nr_pages;
-		int status_change_nid;
 	}
 
 - start_pfn is start_pfn of online/offline memory.
 - nr_pages is # of pages of online/offline memory.
-- status_change_nid is set node id when N_MEMORY of nodemask is (will be)
-  set/clear. It means a new(memoryless) node gets new memory by online and a
-  node loses all memory. If this is -1, then nodemask status is not changed.
-
-  If status_changed_nid* >= 0, callback should create/discard structures for the
-  node if necessary.
 
 It is possible to get notified for MEM_CANCEL_ONLINE without having been notified
 for MEM_GOING_ONLINE, and the same applies to MEM_CANCEL_OFFLINE and
diff --git a/include/linux/memory.h b/include/linux/memory.h
index a8284d41e452..40eb70ccb09d 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -109,7 +109,6 @@ struct memory_notify {
 	unsigned long altmap_nr_pages;
 	unsigned long start_pfn;
 	unsigned long nr_pages;
-	int status_change_nid;
 };
 
 struct notifier_block;
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0d54a01985ba..a371d59cc718 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1153,7 +1153,6 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 	struct memory_notify mem_arg = {
 		.start_pfn = pfn,
 		.nr_pages = nr_pages,
-		.status_change_nid = NUMA_NO_NODE,
 	};
 	struct node_notify node_arg = {
 		.nid = NUMA_NO_NODE,
@@ -1181,7 +1180,6 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 	if (!node_state(nid, N_MEMORY)) {
 		/* Adding memory to the node for the first time */
 		node_arg.nid = nid;
-		mem_arg.status_change_nid = nid;
 		ret = node_notify(NODE_ADDING_FIRST_MEMORY, &node_arg);
 		ret = notifier_to_errno(ret);
 		if (ret)
@@ -1904,7 +1902,6 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	struct memory_notify mem_arg = {
 		.start_pfn = start_pfn,
 		.nr_pages = nr_pages,
-		.status_change_nid = NUMA_NO_NODE,
 	};
 	struct node_notify node_arg = {
 		.nid = NUMA_NO_NODE,
@@ -1975,7 +1972,6 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 	 */
 	if (nr_pages >= pgdat->node_present_pages) {
 		node_arg.nid = node;
-		mem_arg.status_change_nid = node;
 		ret = node_notify(NODE_REMOVING_LAST_MEMORY, &node_arg);
 		ret = notifier_to_errno(ret);
 		if (ret) {
-- 
cgit v1.2.3


From 42f46ed99ac6c07adf7f3bcbe9040b0c52d62d0f Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 16 Jun 2025 22:11:09 -0400
Subject: mm/page_alloc: pageblock flags functions clean up

Patch series "Make MIGRATE_ISOLATE a standalone bit", v10.

This patchset moves MIGRATE_ISOLATE to a standalone bit to avoid being
overwritten during pageblock isolation process.  Currently,
MIGRATE_ISOLATE is part of enum migratetype (in include/linux/mmzone.h),
thus, setting a pageblock to MIGRATE_ISOLATE overwrites its original
migratetype.  This causes pageblock migratetype loss during
alloc_contig_range() and memory offline, especially when the process fails
due to a failed pageblock isolation and the code tries to undo the
finished pageblock isolations.

In terms of performance for changing pageblock types, no performance
change is observed:

1. I used perf to collect stats of offlining and onlining all memory
   of a 40GB VM 10 times and see that get_pfnblock_flags_mask() and
   set_pfnblock_flags_mask() take about 0.12% and 0.02% of the whole
   process respectively with and without this patchset across 3 runs.

2. I used perf to collect stats of dd from /dev/random to a 40GB tmpfs
   file and find get_pfnblock_flags_mask() takes about 0.05% of the
   process with and without this patchset across 3 runs.


This patch (of 6):

No functional change is intended.

1. Add __NR_PAGEBLOCK_BITS for the number of pageblock flag bits and use
   roundup_pow_of_two(__NR_PAGEBLOCK_BITS) as NR_PAGEBLOCK_BITS to take
   right amount of bits for pageblock flags.
2. Rename PB_migrate_skip to PB_compact_skip.
3. Add {get,set,clear}_pfnblock_bit() to operate one a standalone bit,
   like PB_compact_skip.
3. Make {get,set}_pfnblock_flags_mask() internal functions and use
   {get,set}_pfnblock_migratetype() for pageblock migratetype operations.
4. Move pageblock flags common code to get_pfnblock_bitmap_bitidx().
3. Use MIGRATETYPE_MASK to get the migratetype of a pageblock from its
   flags.
4. Use PB_migrate_end in the definition of MIGRATETYPE_MASK instead of
   PB_migrate_bits.
5. Add a comment on is_migrate_cma_folio() to prevent one from changing it
   to use get_pageblock_migratetype() and causing issues.

Link: https://lkml.kernel.org/r/20250617021115.2331563-1-ziy@nvidia.com
Link: https://lkml.kernel.org/r/20250617021115.2331563-2-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Richard Chang <richardycc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/mm/physical_memory.rst |   2 +-
 include/linux/mmzone.h               |  18 ++--
 include/linux/page-isolation.h       |   2 +-
 include/linux/pageblock-flags.h      |  34 +++----
 mm/memory_hotplug.c                  |   2 +-
 mm/page_alloc.c                      | 171 +++++++++++++++++++++++++++--------
 6 files changed, 162 insertions(+), 67 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/mm/physical_memory.rst b/Documentation/mm/physical_memory.rst
index d3ac106e6b14..9af11b5bd145 100644
--- a/Documentation/mm/physical_memory.rst
+++ b/Documentation/mm/physical_memory.rst
@@ -584,7 +584,7 @@ Compaction control
 
 ``compact_blockskip_flush``
   Set to true when compaction migration scanner and free scanner meet, which
-  means the ``PB_migrate_skip`` bits should be cleared.
+  means the ``PB_compact_skip`` bits should be cleared.
 
 ``contiguous``
   Set to true when the zone is contiguous (in other words, no hole).
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 5bec8b1d0e66..76d66c07b673 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -92,8 +92,12 @@ extern const char * const migratetype_names[MIGRATE_TYPES];
 #ifdef CONFIG_CMA
 #  define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA)
 #  define is_migrate_cma_page(_page) (get_pageblock_migratetype(_page) == MIGRATE_CMA)
-#  define is_migrate_cma_folio(folio, pfn)	(MIGRATE_CMA ==		\
-	get_pfnblock_flags_mask(&folio->page, pfn, MIGRATETYPE_MASK))
+/*
+ * __dump_folio() in mm/debug.c passes a folio pointer to on-stack struct folio,
+ * so folio_pfn() cannot be used and pfn is needed.
+ */
+#  define is_migrate_cma_folio(folio, pfn) \
+	(get_pfnblock_migratetype(&folio->page, pfn) == MIGRATE_CMA)
 #else
 #  define is_migrate_cma(migratetype) false
 #  define is_migrate_cma_page(_page) false
@@ -122,14 +126,12 @@ static inline bool migratetype_is_mergeable(int mt)
 
 extern int page_group_by_mobility_disabled;
 
-#define MIGRATETYPE_MASK ((1UL << PB_migratetype_bits) - 1)
+#define get_pageblock_migratetype(page) \
+	get_pfnblock_migratetype(page, page_to_pfn(page))
 
-#define get_pageblock_migratetype(page)					\
-	get_pfnblock_flags_mask(page, page_to_pfn(page), MIGRATETYPE_MASK)
+#define folio_migratetype(folio) \
+	get_pageblock_migratetype(&folio->page)
 
-#define folio_migratetype(folio)				\
-	get_pfnblock_flags_mask(&folio->page, folio_pfn(folio),		\
-			MIGRATETYPE_MASK)
 struct free_area {
 	struct list_head	free_list[MIGRATE_TYPES];
 	unsigned long		nr_free;
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 898bb788243b..277d8d92980c 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -25,7 +25,7 @@ static inline bool is_migrate_isolate(int migratetype)
 #define MEMORY_OFFLINE	0x1
 #define REPORT_FAILURE	0x2
 
-void set_pageblock_migratetype(struct page *page, int migratetype);
+void set_pageblock_migratetype(struct page *page, enum migratetype migratetype);
 
 bool move_freepages_block_isolate(struct zone *zone, struct page *page,
 				  int migratetype);
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index 6297c6343c55..c240c7a1fb03 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -19,15 +19,19 @@ enum pageblock_bits {
 	PB_migrate,
 	PB_migrate_end = PB_migrate + PB_migratetype_bits - 1,
 			/* 3 bits required for migrate types */
-	PB_migrate_skip,/* If set the block is skipped by compaction */
+	PB_compact_skip,/* If set the block is skipped by compaction */
 
 	/*
 	 * Assume the bits will always align on a word. If this assumption
 	 * changes then get/set pageblock needs updating.
 	 */
-	NR_PAGEBLOCK_BITS
+	__NR_PAGEBLOCK_BITS
 };
 
+#define NR_PAGEBLOCK_BITS (roundup_pow_of_two(__NR_PAGEBLOCK_BITS))
+
+#define MIGRATETYPE_MASK ((1UL << (PB_migrate_end + 1)) - 1)
+
 #if defined(CONFIG_HUGETLB_PAGE)
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
@@ -65,27 +69,23 @@ extern unsigned int pageblock_order;
 /* Forward declaration */
 struct page;
 
-unsigned long get_pfnblock_flags_mask(const struct page *page,
-				unsigned long pfn,
-				unsigned long mask);
-
-void set_pfnblock_flags_mask(struct page *page,
-				unsigned long flags,
-				unsigned long pfn,
-				unsigned long mask);
+enum migratetype get_pfnblock_migratetype(const struct page *page,
+					  unsigned long pfn);
+bool get_pfnblock_bit(const struct page *page, unsigned long pfn,
+		      enum pageblock_bits pb_bit);
+void set_pfnblock_bit(const struct page *page, unsigned long pfn,
+		      enum pageblock_bits pb_bit);
+void clear_pfnblock_bit(const struct page *page, unsigned long pfn,
+			enum pageblock_bits pb_bit);
 
 /* Declarations for getting and setting flags. See mm/page_alloc.c */
 #ifdef CONFIG_COMPACTION
 #define get_pageblock_skip(page) \
-	get_pfnblock_flags_mask(page, page_to_pfn(page),	\
-			(1 << (PB_migrate_skip)))
+	get_pfnblock_bit(page, page_to_pfn(page), PB_compact_skip)
 #define clear_pageblock_skip(page) \
-	set_pfnblock_flags_mask(page, 0, page_to_pfn(page),	\
-			(1 << PB_migrate_skip))
+	clear_pfnblock_bit(page, page_to_pfn(page), PB_compact_skip)
 #define set_pageblock_skip(page) \
-	set_pfnblock_flags_mask(page, (1 << PB_migrate_skip),	\
-			page_to_pfn(page),			\
-			(1 << PB_migrate_skip))
+	set_pfnblock_bit(page, page_to_pfn(page), PB_compact_skip)
 #else
 static inline bool get_pageblock_skip(struct page *page)
 {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a371d59cc718..403221982c2e 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -774,7 +774,7 @@ void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 
 	/*
 	 * TODO now we have a visible range of pages which are not associated
-	 * with their zone properly. Not nice but set_pfnblock_flags_mask
+	 * with their zone properly. Not nice but set_pfnblock_migratetype()
 	 * expects the zone spans the pfn range. All the pages in the range
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 31041e2aa33a..43a4c1532721 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -353,81 +353,174 @@ static inline int pfn_to_bitidx(const struct page *page, unsigned long pfn)
 	return (pfn >> pageblock_order) * NR_PAGEBLOCK_BITS;
 }
 
+static __always_inline bool is_standalone_pb_bit(enum pageblock_bits pb_bit)
+{
+	return pb_bit > PB_migrate_end && pb_bit < __NR_PAGEBLOCK_BITS;
+}
+
+static __always_inline void
+get_pfnblock_bitmap_bitidx(const struct page *page, unsigned long pfn,
+			   unsigned long **bitmap_word, unsigned long *bitidx)
+{
+	unsigned long *bitmap;
+	unsigned long word_bitidx;
+
+	BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
+	BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits));
+	VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
+
+	bitmap = get_pageblock_bitmap(page, pfn);
+	*bitidx = pfn_to_bitidx(page, pfn);
+	word_bitidx = *bitidx / BITS_PER_LONG;
+	*bitidx &= (BITS_PER_LONG - 1);
+	*bitmap_word = &bitmap[word_bitidx];
+}
+
+
 /**
- * get_pfnblock_flags_mask - Return the requested group of flags for the pageblock_nr_pages block of pages
+ * __get_pfnblock_flags_mask - Return the requested group of flags for
+ * a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
  * @pfn: The target page frame number
  * @mask: mask of bits that the caller is interested in
  *
  * Return: pageblock_bits flags
  */
-unsigned long get_pfnblock_flags_mask(const struct page *page,
-					unsigned long pfn, unsigned long mask)
+static unsigned long __get_pfnblock_flags_mask(const struct page *page,
+					       unsigned long pfn,
+					       unsigned long mask)
 {
-	unsigned long *bitmap;
-	unsigned long bitidx, word_bitidx;
+	unsigned long *bitmap_word;
+	unsigned long bitidx;
 	unsigned long word;
 
-	bitmap = get_pageblock_bitmap(page, pfn);
-	bitidx = pfn_to_bitidx(page, pfn);
-	word_bitidx = bitidx / BITS_PER_LONG;
-	bitidx &= (BITS_PER_LONG-1);
+	get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
 	/*
-	 * This races, without locks, with set_pfnblock_flags_mask(). Ensure
+	 * This races, without locks, with set_pfnblock_migratetype(). Ensure
 	 * a consistent read of the memory array, so that results, even though
 	 * racy, are not corrupted.
 	 */
-	word = READ_ONCE(bitmap[word_bitidx]);
+	word = READ_ONCE(*bitmap_word);
 	return (word >> bitidx) & mask;
 }
 
-static __always_inline int get_pfnblock_migratetype(const struct page *page,
-					unsigned long pfn)
+/**
+ * get_pfnblock_bit - Check if a standalone bit of a pageblock is set
+ * @page: The page within the block of interest
+ * @pfn: The target page frame number
+ * @pb_bit: pageblock bit to check
+ *
+ * Return: true if the bit is set, otherwise false
+ */
+bool get_pfnblock_bit(const struct page *page, unsigned long pfn,
+		      enum pageblock_bits pb_bit)
 {
-	return get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
+	unsigned long *bitmap_word;
+	unsigned long bitidx;
+
+	if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit)))
+		return false;
+
+	get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
+
+	return test_bit(bitidx + pb_bit, bitmap_word);
 }
 
 /**
- * set_pfnblock_flags_mask - Set the requested group of flags for a pageblock_nr_pages block of pages
+ * get_pfnblock_migratetype - Return the migratetype of a pageblock
+ * @page: The page within the block of interest
+ * @pfn: The target page frame number
+ *
+ * Return: The migratetype of the pageblock
+ *
+ * Use get_pfnblock_migratetype() if caller already has both @page and @pfn
+ * to save a call to page_to_pfn().
+ */
+__always_inline enum migratetype
+get_pfnblock_migratetype(const struct page *page, unsigned long pfn)
+{
+	return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
+}
+
+/**
+ * __set_pfnblock_flags_mask - Set the requested group of flags for
+ * a pageblock_nr_pages block of pages
  * @page: The page within the block of interest
- * @flags: The flags to set
  * @pfn: The target page frame number
+ * @flags: The flags to set
  * @mask: mask of bits that the caller is interested in
  */
-void set_pfnblock_flags_mask(struct page *page, unsigned long flags,
-					unsigned long pfn,
-					unsigned long mask)
+static void __set_pfnblock_flags_mask(struct page *page, unsigned long pfn,
+				      unsigned long flags, unsigned long mask)
 {
-	unsigned long *bitmap;
-	unsigned long bitidx, word_bitidx;
+	unsigned long *bitmap_word;
+	unsigned long bitidx;
 	unsigned long word;
 
-	BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
-	BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits));
-
-	bitmap = get_pageblock_bitmap(page, pfn);
-	bitidx = pfn_to_bitidx(page, pfn);
-	word_bitidx = bitidx / BITS_PER_LONG;
-	bitidx &= (BITS_PER_LONG-1);
-
-	VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
+	get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
 
 	mask <<= bitidx;
 	flags <<= bitidx;
 
-	word = READ_ONCE(bitmap[word_bitidx]);
+	word = READ_ONCE(*bitmap_word);
 	do {
-	} while (!try_cmpxchg(&bitmap[word_bitidx], &word, (word & ~mask) | flags));
+	} while (!try_cmpxchg(bitmap_word, &word, (word & ~mask) | flags));
+}
+
+/**
+ * set_pfnblock_bit - Set a standalone bit of a pageblock
+ * @page: The page within the block of interest
+ * @pfn: The target page frame number
+ * @pb_bit: pageblock bit to set
+ */
+void set_pfnblock_bit(const struct page *page, unsigned long pfn,
+		      enum pageblock_bits pb_bit)
+{
+	unsigned long *bitmap_word;
+	unsigned long bitidx;
+
+	if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit)))
+		return;
+
+	get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
+
+	set_bit(bitidx + pb_bit, bitmap_word);
 }
 
-void set_pageblock_migratetype(struct page *page, int migratetype)
+/**
+ * clear_pfnblock_bit - Clear a standalone bit of a pageblock
+ * @page: The page within the block of interest
+ * @pfn: The target page frame number
+ * @pb_bit: pageblock bit to clear
+ */
+void clear_pfnblock_bit(const struct page *page, unsigned long pfn,
+			enum pageblock_bits pb_bit)
+{
+	unsigned long *bitmap_word;
+	unsigned long bitidx;
+
+	if (WARN_ON_ONCE(!is_standalone_pb_bit(pb_bit)))
+		return;
+
+	get_pfnblock_bitmap_bitidx(page, pfn, &bitmap_word, &bitidx);
+
+	clear_bit(bitidx + pb_bit, bitmap_word);
+}
+
+/**
+ * set_pageblock_migratetype - Set the migratetype of a pageblock
+ * @page: The page within the block of interest
+ * @migratetype: migratetype to set
+ */
+__always_inline void set_pageblock_migratetype(struct page *page,
+					       enum migratetype migratetype)
 {
 	if (unlikely(page_group_by_mobility_disabled &&
 		     migratetype < MIGRATE_PCPTYPES))
 		migratetype = MIGRATE_UNMOVABLE;
 
-	set_pfnblock_flags_mask(page, (unsigned long)migratetype,
-				page_to_pfn(page), MIGRATETYPE_MASK);
+	__set_pfnblock_flags_mask(page, page_to_pfn(page),
+				  (unsigned long)migratetype, MIGRATETYPE_MASK);
 }
 
 #ifdef CONFIG_DEBUG_VM
@@ -667,7 +760,7 @@ static inline void __add_to_free_list(struct page *page, struct zone *zone,
 	int nr_pages = 1 << order;
 
 	VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype,
-		     "page type is %lu, passed migratetype is %d (nr=%d)\n",
+		     "page type is %d, passed migratetype is %d (nr=%d)\n",
 		     get_pageblock_migratetype(page), migratetype, nr_pages);
 
 	if (tail)
@@ -693,7 +786,7 @@ static inline void move_to_free_list(struct page *page, struct zone *zone,
 
 	/* Free page moving can fail, so it happens before the type update */
 	VM_WARN_ONCE(get_pageblock_migratetype(page) != old_mt,
-		     "page type is %lu, passed migratetype is %d (nr=%d)\n",
+		     "page type is %d, passed migratetype is %d (nr=%d)\n",
 		     get_pageblock_migratetype(page), old_mt, nr_pages);
 
 	list_move_tail(&page->buddy_list, &area->free_list[new_mt]);
@@ -715,7 +808,7 @@ static inline void __del_page_from_free_list(struct page *page, struct zone *zon
 	int nr_pages = 1 << order;
 
         VM_WARN_ONCE(get_pageblock_migratetype(page) != migratetype,
-		     "page type is %lu, passed migratetype is %d (nr=%d)\n",
+		     "page type is %d, passed migratetype is %d (nr=%d)\n",
 		     get_pageblock_migratetype(page), migratetype, nr_pages);
 
 	/* clear reported state and update reported page count */
@@ -3123,7 +3216,7 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
 
 /*
  * Do not instrument rmqueue() with KMSAN. This function may call
- * __msan_poison_alloca() through a call to set_pfnblock_flags_mask().
+ * __msan_poison_alloca() through a call to set_pfnblock_migratetype().
  * If __msan_poison_alloca() attempts to allocate pages for the stack depot, it
  * may call rmqueue() again, which will result in a deadlock.
  */
-- 
cgit v1.2.3


From e904bce2d9d43e0f370e238457a13847d161570b Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 16 Jun 2025 22:11:10 -0400
Subject: mm/page_isolation: make page isolation a standalone bit

During page isolation, the original migratetype is overwritten, since
MIGRATE_* are enums and stored in pageblock bitmaps.  Change
MIGRATE_ISOLATE to be stored a standalone bit, PB_migrate_isolate, like
PB_compact_skip, so that migratetype is not lost during pageblock
isolation.

Link: https://lkml.kernel.org/r/20250617021115.2331563-3-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Richard Chang <richardycc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmzone.h          |  3 +++
 include/linux/page-isolation.h  | 16 ++++++++++++++++
 include/linux/pageblock-flags.h | 14 ++++++++++++++
 mm/page_alloc.c                 | 27 ++++++++++++++++++++++++---
 4 files changed, 57 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 76d66c07b673..1d1bb2b7f40d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -79,6 +79,9 @@ enum migratetype {
 	 * __free_pageblock_cma() function.
 	 */
 	MIGRATE_CMA,
+	__MIGRATE_TYPE_END = MIGRATE_CMA,
+#else
+	__MIGRATE_TYPE_END = MIGRATE_HIGHATOMIC,
 #endif
 #ifdef CONFIG_MEMORY_ISOLATION
 	MIGRATE_ISOLATE,	/* can't allocate from here */
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 277d8d92980c..fc021d3f95ca 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -11,6 +11,12 @@ static inline bool is_migrate_isolate(int migratetype)
 {
 	return migratetype == MIGRATE_ISOLATE;
 }
+#define get_pageblock_isolate(page) \
+	get_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate)
+#define clear_pageblock_isolate(page) \
+	clear_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate)
+#define set_pageblock_isolate(page) \
+	set_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate)
 #else
 static inline bool is_migrate_isolate_page(struct page *page)
 {
@@ -20,6 +26,16 @@ static inline bool is_migrate_isolate(int migratetype)
 {
 	return false;
 }
+static inline bool get_pageblock_isolate(struct page *page)
+{
+	return false;
+}
+static inline void clear_pageblock_isolate(struct page *page)
+{
+}
+static inline void set_pageblock_isolate(struct page *page)
+{
+}
 #endif
 
 #define MEMORY_OFFLINE	0x1
diff --git a/include/linux/pageblock-flags.h b/include/linux/pageblock-flags.h
index c240c7a1fb03..6a44be0f39f4 100644
--- a/include/linux/pageblock-flags.h
+++ b/include/linux/pageblock-flags.h
@@ -21,6 +21,13 @@ enum pageblock_bits {
 			/* 3 bits required for migrate types */
 	PB_compact_skip,/* If set the block is skipped by compaction */
 
+#ifdef CONFIG_MEMORY_ISOLATION
+	/*
+	 * Pageblock isolation is represented with a separate bit, so that
+	 * the migratetype of a block is not overwritten by isolation.
+	 */
+	PB_migrate_isolate, /* If set the block is isolated */
+#endif
 	/*
 	 * Assume the bits will always align on a word. If this assumption
 	 * changes then get/set pageblock needs updating.
@@ -32,6 +39,13 @@ enum pageblock_bits {
 
 #define MIGRATETYPE_MASK ((1UL << (PB_migrate_end + 1)) - 1)
 
+#ifdef CONFIG_MEMORY_ISOLATION
+#define MIGRATETYPE_AND_ISO_MASK \
+	(((1UL << (PB_migrate_end + 1)) - 1) | BIT(PB_migrate_isolate))
+#else
+#define MIGRATETYPE_AND_ISO_MASK MIGRATETYPE_MASK
+#endif
+
 #if defined(CONFIG_HUGETLB_PAGE)
 
 #ifdef CONFIG_HUGETLB_PAGE_SIZE_VARIABLE
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 43a4c1532721..61dd34102c14 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -365,8 +365,12 @@ get_pfnblock_bitmap_bitidx(const struct page *page, unsigned long pfn,
 	unsigned long *bitmap;
 	unsigned long word_bitidx;
 
+#ifdef CONFIG_MEMORY_ISOLATION
+	BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 8);
+#else
 	BUILD_BUG_ON(NR_PAGEBLOCK_BITS != 4);
-	BUILD_BUG_ON(MIGRATE_TYPES > (1 << PB_migratetype_bits));
+#endif
+	BUILD_BUG_ON(__MIGRATE_TYPE_END >= (1 << PB_migratetype_bits));
 	VM_BUG_ON_PAGE(!zone_spans_pfn(page_zone(page), pfn), page);
 
 	bitmap = get_pageblock_bitmap(page, pfn);
@@ -439,7 +443,16 @@ bool get_pfnblock_bit(const struct page *page, unsigned long pfn,
 __always_inline enum migratetype
 get_pfnblock_migratetype(const struct page *page, unsigned long pfn)
 {
-	return __get_pfnblock_flags_mask(page, pfn, MIGRATETYPE_MASK);
+	unsigned long mask = MIGRATETYPE_AND_ISO_MASK;
+	unsigned long flags;
+
+	flags = __get_pfnblock_flags_mask(page, pfn, mask);
+
+#ifdef CONFIG_MEMORY_ISOLATION
+	if (flags & BIT(PB_migrate_isolate))
+		return MIGRATE_ISOLATE;
+#endif
+	return flags & MIGRATETYPE_MASK;
 }
 
 /**
@@ -519,8 +532,16 @@ __always_inline void set_pageblock_migratetype(struct page *page,
 		     migratetype < MIGRATE_PCPTYPES))
 		migratetype = MIGRATE_UNMOVABLE;
 
+#ifdef CONFIG_MEMORY_ISOLATION
+	if (migratetype == MIGRATE_ISOLATE) {
+		set_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate);
+		return;
+	}
+	/* MIGRATETYPE_AND_ISO_MASK clears PB_migrate_isolate if it is set */
+#endif
 	__set_pfnblock_flags_mask(page, page_to_pfn(page),
-				  (unsigned long)migratetype, MIGRATETYPE_MASK);
+				  (unsigned long)migratetype,
+				  MIGRATETYPE_AND_ISO_MASK);
 }
 
 #ifdef CONFIG_DEBUG_VM
-- 
cgit v1.2.3


From 1bc3587a88d291a37dab12d6c14aa7da53304251 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 16 Jun 2025 22:11:11 -0400
Subject: mm/page_alloc: add support for initializing pageblock as isolated

MIGRATE_ISOLATE is a standalone bit, so a pageblock cannot be initialized
to just MIGRATE_ISOLATE.  Add init_pageblock_migratetype() to enable
initialize a pageblock with a migratetype and isolated.

Link: https://lkml.kernel.org/r/20250617021115.2331563-4-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Richard Chang <richardycc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memory_hotplug.h |  3 ++-
 include/linux/page-isolation.h |  3 +++
 kernel/kexec_handover.c        |  4 ++--
 mm/hugetlb.c                   |  4 ++--
 mm/internal.h                  |  3 ++-
 mm/memory_hotplug.c            | 12 ++++++++----
 mm/memremap.c                  |  2 +-
 mm/mm_init.c                   | 24 +++++++++++++++---------
 mm/page_alloc.c                | 26 ++++++++++++++++++++++++++
 9 files changed, 61 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index eaac5ae8c05c..23f038a16231 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -314,7 +314,8 @@ extern int add_memory_driver_managed(int nid, u64 start, u64 size,
 				     mhp_t mhp_flags);
 extern void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 				   unsigned long nr_pages,
-				   struct vmem_altmap *altmap, int migratetype);
+				   struct vmem_altmap *altmap, int migratetype,
+				   bool isolate_pageblock);
 extern void remove_pfn_range_from_zone(struct zone *zone,
 				       unsigned long start_pfn,
 				       unsigned long nr_pages);
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index fc021d3f95ca..14c6a5f691c2 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -41,6 +41,9 @@ static inline void set_pageblock_isolate(struct page *page)
 #define MEMORY_OFFLINE	0x1
 #define REPORT_FAILURE	0x2
 
+void __meminit init_pageblock_migratetype(struct page *page,
+					  enum migratetype migratetype,
+					  bool isolate);
 void set_pageblock_migratetype(struct page *page, enum migratetype migratetype);
 
 bool move_freepages_block_isolate(struct zone *zone, struct page *page,
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 5a21dbe17950..49634cc3fb43 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -1100,8 +1100,8 @@ static void __init kho_release_scratch(void)
 		ulong pfn;
 
 		for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages)
-			set_pageblock_migratetype(pfn_to_page(pfn),
-						  MIGRATE_CMA);
+			init_pageblock_migratetype(pfn_to_page(pfn),
+						   MIGRATE_CMA, false);
 	}
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index c03896375749..11d5668ff6e7 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -3297,8 +3297,8 @@ static void __init hugetlb_bootmem_init_migratetype(struct folio *folio,
 		if (folio_test_hugetlb_cma(folio))
 			init_cma_pageblock(folio_page(folio, i));
 		else
-			set_pageblock_migratetype(folio_page(folio, i),
-					  MIGRATE_MOVABLE);
+			init_pageblock_migratetype(folio_page(folio, i),
+					  MIGRATE_MOVABLE, false);
 	}
 }
 
diff --git a/mm/internal.h b/mm/internal.h
index fe83dfca3c72..22a95a2b7fa1 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -820,7 +820,8 @@ extern void *memmap_alloc(phys_addr_t size, phys_addr_t align,
 			  int nid, bool exact_nid);
 
 void memmap_init_range(unsigned long, int, unsigned long, unsigned long,
-		unsigned long, enum meminit_context, struct vmem_altmap *, int);
+		unsigned long, enum meminit_context, struct vmem_altmap *, int,
+		bool);
 
 #if defined CONFIG_COMPACTION || defined CONFIG_CMA
 
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 403221982c2e..a3c2b0784070 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -747,7 +747,8 @@ static inline void section_taint_zone_device(unsigned long pfn)
  */
 void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 				  unsigned long nr_pages,
-				  struct vmem_altmap *altmap, int migratetype)
+				  struct vmem_altmap *altmap, int migratetype,
+				  bool isolate_pageblock)
 {
 	struct pglist_data *pgdat = zone->zone_pgdat;
 	int nid = pgdat->node_id;
@@ -779,7 +780,8 @@ void move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn,
 	 * are reserved so nobody should be touching them so we should be safe
 	 */
 	memmap_init_range(nr_pages, nid, zone_idx(zone), start_pfn, 0,
-			 MEMINIT_HOTPLUG, altmap, migratetype);
+			 MEMINIT_HOTPLUG, altmap, migratetype,
+			 isolate_pageblock);
 
 	set_zone_contiguous(zone);
 }
@@ -1104,7 +1106,8 @@ int mhp_init_memmap_on_memory(unsigned long pfn, unsigned long nr_pages,
 	if (mhp_off_inaccessible)
 		page_init_poison(pfn_to_page(pfn), sizeof(struct page) * nr_pages);
 
-	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE);
+	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_UNMOVABLE,
+			       false);
 
 	for (i = 0; i < nr_pages; i++) {
 		struct page *page = pfn_to_page(pfn + i);
@@ -1175,7 +1178,8 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 
 
 	/* associate pfn range with the zone */
-	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_ISOLATE);
+	move_pfn_range_to_zone(zone, pfn, nr_pages, NULL, MIGRATE_MOVABLE,
+			       true);
 
 	if (!node_state(nid, N_MEMORY)) {
 		/* Adding memory to the node for the first time */
diff --git a/mm/memremap.c b/mm/memremap.c
index f75078c14839..b0ce0d8254bd 100644
--- a/mm/memremap.c
+++ b/mm/memremap.c
@@ -228,7 +228,7 @@ static int pagemap_range(struct dev_pagemap *pgmap, struct mhp_params *params,
 		zone = &NODE_DATA(nid)->node_zones[ZONE_DEVICE];
 		move_pfn_range_to_zone(zone, PHYS_PFN(range->start),
 				PHYS_PFN(range_len(range)), params->altmap,
-				MIGRATE_MOVABLE);
+				MIGRATE_MOVABLE, false);
 	}
 
 	mem_hotplug_done();
diff --git a/mm/mm_init.c b/mm/mm_init.c
index 02f41e2bdf60..5c21b3af216b 100644
--- a/mm/mm_init.c
+++ b/mm/mm_init.c
@@ -685,7 +685,8 @@ void __meminit __init_page_from_nid(unsigned long pfn, int nid)
 	__init_single_page(pfn_to_page(pfn), pfn, zid, nid);
 
 	if (pageblock_aligned(pfn))
-		set_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE);
+		init_pageblock_migratetype(pfn_to_page(pfn), MIGRATE_MOVABLE,
+				false);
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
@@ -874,7 +875,8 @@ static void __init init_unavailable_range(unsigned long spfn,
 void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone,
 		unsigned long start_pfn, unsigned long zone_end_pfn,
 		enum meminit_context context,
-		struct vmem_altmap *altmap, int migratetype)
+		struct vmem_altmap *altmap, int migratetype,
+		bool isolate_pageblock)
 {
 	unsigned long pfn, end_pfn = start_pfn + size;
 	struct page *page;
@@ -931,7 +933,8 @@ void __meminit memmap_init_range(unsigned long size, int nid, unsigned long zone
 		 * over the place during system boot.
 		 */
 		if (pageblock_aligned(pfn)) {
-			set_pageblock_migratetype(page, migratetype);
+			init_pageblock_migratetype(page, migratetype,
+					isolate_pageblock);
 			cond_resched();
 		}
 		pfn++;
@@ -954,7 +957,8 @@ static void __init memmap_init_zone_range(struct zone *zone,
 		return;
 
 	memmap_init_range(end_pfn - start_pfn, nid, zone_id, start_pfn,
-			  zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE);
+			  zone_end_pfn, MEMINIT_EARLY, NULL, MIGRATE_MOVABLE,
+			  false);
 
 	if (*hole_pfn < start_pfn)
 		init_unavailable_range(*hole_pfn, start_pfn, zone_id, nid);
@@ -1035,7 +1039,7 @@ static void __ref __init_zone_device_page(struct page *page, unsigned long pfn,
 	 * because this is done early in section_activate()
 	 */
 	if (pageblock_aligned(pfn)) {
-		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+		init_pageblock_migratetype(page, MIGRATE_MOVABLE, false);
 		cond_resched();
 	}
 
@@ -1996,7 +2000,8 @@ static void __init deferred_free_pages(unsigned long pfn,
 	/* Free a large naturally-aligned chunk if possible */
 	if (nr_pages == MAX_ORDER_NR_PAGES && IS_MAX_ORDER_ALIGNED(pfn)) {
 		for (i = 0; i < nr_pages; i += pageblock_nr_pages)
-			set_pageblock_migratetype(page + i, MIGRATE_MOVABLE);
+			init_pageblock_migratetype(page + i, MIGRATE_MOVABLE,
+					false);
 		__free_pages_core(page, MAX_PAGE_ORDER, MEMINIT_EARLY);
 		return;
 	}
@@ -2006,7 +2011,8 @@ static void __init deferred_free_pages(unsigned long pfn,
 
 	for (i = 0; i < nr_pages; i++, page++, pfn++) {
 		if (pageblock_aligned(pfn))
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
+			init_pageblock_migratetype(page, MIGRATE_MOVABLE,
+					false);
 		__free_pages_core(page, 0, MEMINIT_EARLY);
 	}
 }
@@ -2305,7 +2311,7 @@ void __init init_cma_reserved_pageblock(struct page *page)
 		set_page_count(p, 0);
 	} while (++p, --i);
 
-	set_pageblock_migratetype(page, MIGRATE_CMA);
+	init_pageblock_migratetype(page, MIGRATE_CMA, false);
 	set_page_refcounted(page);
 	/* pages were reserved and not allocated */
 	clear_page_tag_ref(page);
@@ -2319,7 +2325,7 @@ void __init init_cma_reserved_pageblock(struct page *page)
  */
 void __init init_cma_pageblock(struct page *page)
 {
-	set_pageblock_migratetype(page, MIGRATE_CMA);
+	init_pageblock_migratetype(page, MIGRATE_CMA, false);
 	adjust_managed_page_count(page, pageblock_nr_pages);
 	page_zone(page)->cma_pages += pageblock_nr_pages;
 }
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 61dd34102c14..c7730264bf5f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -544,6 +544,32 @@ __always_inline void set_pageblock_migratetype(struct page *page,
 				  MIGRATETYPE_AND_ISO_MASK);
 }
 
+void __meminit init_pageblock_migratetype(struct page *page,
+					  enum migratetype migratetype,
+					  bool isolate)
+{
+	unsigned long flags;
+
+	if (unlikely(page_group_by_mobility_disabled &&
+		     migratetype < MIGRATE_PCPTYPES))
+		migratetype = MIGRATE_UNMOVABLE;
+
+	flags = migratetype;
+
+#ifdef CONFIG_MEMORY_ISOLATION
+	if (migratetype == MIGRATE_ISOLATE) {
+		VM_WARN_ONCE(
+			1,
+			"Set isolate=true to isolate pageblock with a migratetype");
+		return;
+	}
+	if (isolate)
+		flags |= BIT(PB_migrate_isolate);
+#endif
+	__set_pfnblock_flags_mask(page, page_to_pfn(page), flags,
+				  MIGRATETYPE_AND_ISO_MASK);
+}
+
 #ifdef CONFIG_DEBUG_VM
 static int page_outside_zone_boundaries(struct zone *zone, struct page *page)
 {
-- 
cgit v1.2.3


From b1df9c5713dc41229667aa44eaea2399e8de9470 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 16 Jun 2025 22:11:12 -0400
Subject: mm/page_isolation: remove migratetype from
 move_freepages_block_isolate()

Since migratetype is no longer overwritten during pageblock isolation,
moving a pageblock out of MIGRATE_ISOLATE no longer needs a new
migratetype.

Add pageblock_isolate_and_move_free_pages() and
pageblock_unisolate_and_move_free_pages() to be explicit about the page
isolation operations.  Both share the common code in
__move_freepages_block_isolate(), which is renamed from
move_freepages_block_isolate().

Add toggle_pageblock_isolate() to flip pageblock isolation bit in
__move_freepages_block_isolate().

Make set_pageblock_migratetype() only accept non MIGRATE_ISOLATE types, so
that one should use set_pageblock_isolate() to isolate pageblocks.  As a
result, move pageblock migratetype code out of __move_freepages_block().

Link: https://lkml.kernel.org/r/20250617021115.2331563-5-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Richard Chang <richardycc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-isolation.h |  5 ++-
 mm/page_alloc.c                | 80 +++++++++++++++++++++++++++++++++---------
 mm/page_isolation.c            | 21 ++++++-----
 3 files changed, 75 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 14c6a5f691c2..7241a6719618 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -44,10 +44,9 @@ static inline void set_pageblock_isolate(struct page *page)
 void __meminit init_pageblock_migratetype(struct page *page,
 					  enum migratetype migratetype,
 					  bool isolate);
-void set_pageblock_migratetype(struct page *page, enum migratetype migratetype);
 
-bool move_freepages_block_isolate(struct zone *zone, struct page *page,
-				  int migratetype);
+bool pageblock_isolate_and_move_free_pages(struct zone *zone, struct page *page);
+bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *page);
 
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			     int migratetype, int flags);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c7730264bf5f..938b01bed1f6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -525,8 +525,8 @@ void clear_pfnblock_bit(const struct page *page, unsigned long pfn,
  * @page: The page within the block of interest
  * @migratetype: migratetype to set
  */
-__always_inline void set_pageblock_migratetype(struct page *page,
-					       enum migratetype migratetype)
+static void set_pageblock_migratetype(struct page *page,
+				      enum migratetype migratetype)
 {
 	if (unlikely(page_group_by_mobility_disabled &&
 		     migratetype < MIGRATE_PCPTYPES))
@@ -534,9 +534,13 @@ __always_inline void set_pageblock_migratetype(struct page *page,
 
 #ifdef CONFIG_MEMORY_ISOLATION
 	if (migratetype == MIGRATE_ISOLATE) {
-		set_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate);
+		VM_WARN_ONCE(1,
+			"Use set_pageblock_isolate() for pageblock isolation");
 		return;
 	}
+	VM_WARN_ONCE(get_pfnblock_bit(page, page_to_pfn(page),
+				      PB_migrate_isolate),
+		     "Use clear_pageblock_isolate() to unisolate pageblock");
 	/* MIGRATETYPE_AND_ISO_MASK clears PB_migrate_isolate if it is set */
 #endif
 	__set_pfnblock_flags_mask(page, page_to_pfn(page),
@@ -1921,8 +1925,8 @@ static inline struct page *__rmqueue_cma_fallback(struct zone *zone,
 #endif
 
 /*
- * Change the type of a block and move all its free pages to that
- * type's freelist.
+ * Move all free pages of a block to new type's freelist. Caller needs to
+ * change the block type.
  */
 static int __move_freepages_block(struct zone *zone, unsigned long start_pfn,
 				  int old_mt, int new_mt)
@@ -1954,8 +1958,6 @@ static int __move_freepages_block(struct zone *zone, unsigned long start_pfn,
 		pages_moved += 1 << order;
 	}
 
-	set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt);
-
 	return pages_moved;
 }
 
@@ -2013,11 +2015,16 @@ static int move_freepages_block(struct zone *zone, struct page *page,
 				int old_mt, int new_mt)
 {
 	unsigned long start_pfn;
+	int res;
 
 	if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL))
 		return -1;
 
-	return __move_freepages_block(zone, start_pfn, old_mt, new_mt);
+	res = __move_freepages_block(zone, start_pfn, old_mt, new_mt);
+	set_pageblock_migratetype(pfn_to_page(start_pfn), new_mt);
+
+	return res;
+
 }
 
 #ifdef CONFIG_MEMORY_ISOLATION
@@ -2045,11 +2052,19 @@ static unsigned long find_large_buddy(unsigned long start_pfn)
 	return start_pfn;
 }
 
+static inline void toggle_pageblock_isolate(struct page *page, bool isolate)
+{
+	if (isolate)
+		set_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate);
+	else
+		clear_pfnblock_bit(page, page_to_pfn(page), PB_migrate_isolate);
+}
+
 /**
- * move_freepages_block_isolate - move free pages in block for page isolation
+ * __move_freepages_block_isolate - move free pages in block for page isolation
  * @zone: the zone
  * @page: the pageblock page
- * @migratetype: migratetype to set on the pageblock
+ * @isolate: to isolate the given pageblock or unisolate it
  *
  * This is similar to move_freepages_block(), but handles the special
  * case encountered in page isolation, where the block of interest
@@ -2064,10 +2079,18 @@ static unsigned long find_large_buddy(unsigned long start_pfn)
  *
  * Returns %true if pages could be moved, %false otherwise.
  */
-bool move_freepages_block_isolate(struct zone *zone, struct page *page,
-				  int migratetype)
+static bool __move_freepages_block_isolate(struct zone *zone,
+		struct page *page, bool isolate)
 {
 	unsigned long start_pfn, pfn;
+	int from_mt;
+	int to_mt;
+
+	if (isolate == get_pageblock_isolate(page)) {
+		VM_WARN_ONCE(1, "%s a pageblock that is already in that state",
+			     isolate ? "Isolate" : "Unisolate");
+		return false;
+	}
 
 	if (!prep_move_freepages_block(zone, page, &start_pfn, NULL, NULL))
 		return false;
@@ -2084,7 +2107,7 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page,
 
 		del_page_from_free_list(buddy, zone, order,
 					get_pfnblock_migratetype(buddy, pfn));
-		set_pageblock_migratetype(page, migratetype);
+		toggle_pageblock_isolate(page, isolate);
 		split_large_buddy(zone, buddy, pfn, order, FPI_NONE);
 		return true;
 	}
@@ -2095,16 +2118,38 @@ bool move_freepages_block_isolate(struct zone *zone, struct page *page,
 
 		del_page_from_free_list(page, zone, order,
 					get_pfnblock_migratetype(page, pfn));
-		set_pageblock_migratetype(page, migratetype);
+		toggle_pageblock_isolate(page, isolate);
 		split_large_buddy(zone, page, pfn, order, FPI_NONE);
 		return true;
 	}
 move:
-	__move_freepages_block(zone, start_pfn,
-			       get_pfnblock_migratetype(page, start_pfn),
-			       migratetype);
+	/* Use MIGRATETYPE_MASK to get non-isolate migratetype */
+	if (isolate) {
+		from_mt = __get_pfnblock_flags_mask(page, page_to_pfn(page),
+						    MIGRATETYPE_MASK);
+		to_mt = MIGRATE_ISOLATE;
+	} else {
+		from_mt = MIGRATE_ISOLATE;
+		to_mt = __get_pfnblock_flags_mask(page, page_to_pfn(page),
+						  MIGRATETYPE_MASK);
+	}
+
+	__move_freepages_block(zone, start_pfn, from_mt, to_mt);
+	toggle_pageblock_isolate(pfn_to_page(start_pfn), isolate);
+
 	return true;
 }
+
+bool pageblock_isolate_and_move_free_pages(struct zone *zone, struct page *page)
+{
+	return __move_freepages_block_isolate(zone, page, true);
+}
+
+bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *page)
+{
+	return __move_freepages_block_isolate(zone, page, false);
+}
+
 #endif /* CONFIG_MEMORY_ISOLATION */
 
 static void change_pageblock_range(struct page *pageblock_page,
@@ -2296,6 +2341,7 @@ try_to_claim_block(struct zone *zone, struct page *page,
 	if (free_pages + alike_pages >= (1 << (pageblock_order-1)) ||
 			page_group_by_mobility_disabled) {
 		__move_freepages_block(zone, start_pfn, block_type, start_type);
+		set_pageblock_migratetype(pfn_to_page(start_pfn), start_type);
 		return __rmqueue_smallest(zone, order, start_type);
 	}
 
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index b2fc5266e3d2..08f627a5032f 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -188,7 +188,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end,
 			migratetype, isol_flags);
 	if (!unmovable) {
-		if (!move_freepages_block_isolate(zone, page, MIGRATE_ISOLATE)) {
+		if (!pageblock_isolate_and_move_free_pages(zone, page)) {
 			spin_unlock_irqrestore(&zone->lock, flags);
 			return -EBUSY;
 		}
@@ -209,7 +209,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	return -EBUSY;
 }
 
-static void unset_migratetype_isolate(struct page *page, int migratetype)
+static void unset_migratetype_isolate(struct page *page)
 {
 	struct zone *zone;
 	unsigned long flags;
@@ -262,10 +262,10 @@ static void unset_migratetype_isolate(struct page *page, int migratetype)
 		 * Isolating this block already succeeded, so this
 		 * should not fail on zone boundaries.
 		 */
-		WARN_ON_ONCE(!move_freepages_block_isolate(zone, page, migratetype));
+		WARN_ON_ONCE(!pageblock_unisolate_and_move_free_pages(zone, page));
 	} else {
-		set_pageblock_migratetype(page, migratetype);
-		__putback_isolated_page(page, order, migratetype);
+		clear_pageblock_isolate(page);
+		__putback_isolated_page(page, order, get_pageblock_migratetype(page));
 	}
 	zone->nr_isolate_pageblock--;
 out:
@@ -383,7 +383,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 		if (PageBuddy(page)) {
 			int order = buddy_order(page);
 
-			/* move_freepages_block_isolate() handled this */
+			/* pageblock_isolate_and_move_free_pages() handled this */
 			VM_WARN_ON_ONCE(pfn + (1 << order) > boundary_pfn);
 
 			pfn += 1UL << order;
@@ -433,7 +433,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 failed:
 	/* restore the original migratetype */
 	if (!skip_isolation)
-		unset_migratetype_isolate(pfn_to_page(isolate_pageblock), migratetype);
+		unset_migratetype_isolate(pfn_to_page(isolate_pageblock));
 	return -EBUSY;
 }
 
@@ -504,7 +504,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	ret = isolate_single_pageblock(isolate_end, flags, true,
 			skip_isolation, migratetype);
 	if (ret) {
-		unset_migratetype_isolate(pfn_to_page(isolate_start), migratetype);
+		unset_migratetype_isolate(pfn_to_page(isolate_start));
 		return ret;
 	}
 
@@ -517,8 +517,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 					start_pfn, end_pfn)) {
 			undo_isolate_page_range(isolate_start, pfn, migratetype);
 			unset_migratetype_isolate(
-				pfn_to_page(isolate_end - pageblock_nr_pages),
-				migratetype);
+				pfn_to_page(isolate_end - pageblock_nr_pages));
 			return -EBUSY;
 		}
 	}
@@ -548,7 +547,7 @@ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 		page = __first_valid_page(pfn, pageblock_nr_pages);
 		if (!page || !is_migrate_isolate_page(page))
 			continue;
-		unset_migratetype_isolate(page, migratetype);
+		unset_migratetype_isolate(page);
 	}
 }
 /*
-- 
cgit v1.2.3


From 7a3324eb66f616408fdaaff8a1289c0a9b333748 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 16 Jun 2025 22:11:13 -0400
Subject: mm/page_isolation: remove migratetype from undo_isolate_page_range()

Since migratetype is no longer overwritten during pageblock isolation,
undoing pageblock isolation no longer needs which migratetype to restore.

Link: https://lkml.kernel.org/r/20250617021115.2331563-6-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Richard Chang <richardycc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-isolation.h | 3 +--
 mm/memory_hotplug.c            | 4 ++--
 mm/page_alloc.c                | 2 +-
 mm/page_isolation.c            | 9 +++------
 4 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 7241a6719618..7a681a49e73c 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -51,8 +51,7 @@ bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *pag
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 			     int migratetype, int flags);
 
-void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     int migratetype);
+void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn);
 
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 			int isol_flags);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index a3c2b0784070..6e3380ad1bf5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1222,7 +1222,7 @@ int online_pages(unsigned long pfn, unsigned long nr_pages,
 		build_all_zonelists(NULL);
 
 	/* Basic onlining is complete, allow allocation of onlined pages. */
-	undo_isolate_page_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE);
+	undo_isolate_page_range(pfn, pfn + nr_pages);
 
 	/*
 	 * Freshly onlined pages aren't shuffled (e.g., all pages are placed to
@@ -2086,7 +2086,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 failed_removal_isolated:
 	/* pushback to free area */
-	undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);
+	undo_isolate_page_range(start_pfn, end_pfn);
 	memory_notify(MEM_CANCEL_OFFLINE, &mem_arg);
 	if (node_arg.nid != NUMA_NO_NODE)
 		node_notify(NODE_CANCEL_REMOVING_LAST_MEMORY, &node_arg);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 938b01bed1f6..8d4b3f12b9a6 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6984,7 +6984,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 		     start, end, outer_start, outer_end);
 	}
 done:
-	undo_isolate_page_range(start, end, migratetype);
+	undo_isolate_page_range(start, end);
 	return ret;
 }
 EXPORT_SYMBOL(alloc_contig_range_noprof);
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 08f627a5032f..1edfef408faf 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -515,7 +515,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 		page = __first_valid_page(pfn, pageblock_nr_pages);
 		if (page && set_migratetype_isolate(page, migratetype, flags,
 					start_pfn, end_pfn)) {
-			undo_isolate_page_range(isolate_start, pfn, migratetype);
+			undo_isolate_page_range(isolate_start, pfn);
 			unset_migratetype_isolate(
 				pfn_to_page(isolate_end - pageblock_nr_pages));
 			return -EBUSY;
@@ -528,13 +528,10 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
  * undo_isolate_page_range - undo effects of start_isolate_page_range()
  * @start_pfn:		The first PFN of the isolated range
  * @end_pfn:		The last PFN of the isolated range
- * @migratetype:	New migrate type to set on the range
  *
- * This finds every MIGRATE_ISOLATE page block in the given range
- * and switches it to @migratetype.
+ * This finds and unsets every MIGRATE_ISOLATE page block in the given range
  */
-void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			    int migratetype)
+void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn)
 {
 	unsigned long pfn;
 	struct page *page;
-- 
cgit v1.2.3


From d1554fb6302093d353c8bf4601f9bf994b836904 Mon Sep 17 00:00:00 2001
From: Zi Yan <ziy@nvidia.com>
Date: Mon, 16 Jun 2025 22:11:14 -0400
Subject: mm/page_isolation: remove migratetype parameter from more functions

migratetype is no longer overwritten during pageblock isolation,
start_isolate_page_range(), has_unmovable_pages(), and
set_migratetype_isolate() no longer need which migratetype to restore
during isolation failure.

For has_unmoable_pages(), it needs to know if the isolation is for CMA
allocation, so adding PB_ISOLATE_MODE_CMA_ALLOC provide the information.
At the same time change isolation flags to enum pb_isolate_mode
(PB_ISOLATE_MODE_MEM_OFFLINE, PB_ISOLATE_MODE_CMA_ALLOC,
PB_ISOLATE_MODE_OTHER).  Remove REPORT_FAILURE and check
PB_ISOLATE_MODE_MEM_OFFLINE, since only PB_ISOLATE_MODE_MEM_OFFLINE
reports isolation failures.

alloc_contig_range() no longer needs migratetype.  Replace it with a newly
defined acr_flags_t to tell if an allocation is for CMA.  So does
__alloc_contig_migrate_range().  Add ACR_FLAGS_NONE (set to 0) to indicate
ordinary allocations.

Link: https://lkml.kernel.org/r/20250617021115.2331563-7-ziy@nvidia.com
Signed-off-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Baolin Wang <baolin.wang@linux.alibaba.com>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Mel Gorman <mgorman@techsingularity.net>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Richard Chang <richardycc@google.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 drivers/virtio/virtio_mem.c    |  2 +-
 include/linux/gfp.h            |  7 ++++-
 include/linux/page-isolation.h | 20 +++++++++---
 include/trace/events/kmem.h    | 14 +++++----
 mm/cma.c                       |  2 +-
 mm/memory_hotplug.c            |  6 ++--
 mm/page_alloc.c                | 27 ++++++++--------
 mm/page_isolation.c            | 70 +++++++++++++++++++-----------------------
 8 files changed, 80 insertions(+), 68 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/virtio/virtio_mem.c b/drivers/virtio/virtio_mem.c
index 56d0dbe62163..1688ecd69a04 100644
--- a/drivers/virtio/virtio_mem.c
+++ b/drivers/virtio/virtio_mem.c
@@ -1243,7 +1243,7 @@ static int virtio_mem_fake_offline(struct virtio_mem *vm, unsigned long pfn,
 		if (atomic_read(&vm->config_changed))
 			return -EAGAIN;
 
-		rc = alloc_contig_range(pfn, pfn + nr_pages, MIGRATE_MOVABLE,
+		rc = alloc_contig_range(pfn, pfn + nr_pages, ACR_FLAGS_NONE,
 					GFP_KERNEL);
 		if (rc == -ENOMEM)
 			/* whoops, out of memory */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index be160e8d8bcb..5ebf26fcdcfa 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -423,9 +423,14 @@ static inline bool gfp_compaction_allowed(gfp_t gfp_mask)
 extern gfp_t vma_thp_gfp_mask(struct vm_area_struct *vma);
 
 #ifdef CONFIG_CONTIG_ALLOC
+
+typedef unsigned int __bitwise acr_flags_t;
+#define ACR_FLAGS_NONE ((__force acr_flags_t)0) // ordinary allocation request
+#define ACR_FLAGS_CMA ((__force acr_flags_t)BIT(0)) // allocate for CMA
+
 /* The below functions must be run on a range from a single zone. */
 extern int alloc_contig_range_noprof(unsigned long start, unsigned long end,
-			      unsigned migratetype, gfp_t gfp_mask);
+				     acr_flags_t alloc_flags, gfp_t gfp_mask);
 #define alloc_contig_range(...)			alloc_hooks(alloc_contig_range_noprof(__VA_ARGS__))
 
 extern struct page *alloc_contig_pages_noprof(unsigned long nr_pages, gfp_t gfp_mask,
diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h
index 7a681a49e73c..3e2f960e166c 100644
--- a/include/linux/page-isolation.h
+++ b/include/linux/page-isolation.h
@@ -38,8 +38,20 @@ static inline void set_pageblock_isolate(struct page *page)
 }
 #endif
 
-#define MEMORY_OFFLINE	0x1
-#define REPORT_FAILURE	0x2
+/*
+ * Pageblock isolation modes:
+ * PB_ISOLATE_MODE_MEM_OFFLINE - isolate to offline (!allocate) memory
+ *				 e.g., skip over PageHWPoison() pages and
+ *				 PageOffline() pages. Unmovable pages will be
+ *				 reported in this mode.
+ * PB_ISOLATE_MODE_CMA_ALLOC   - isolate for CMA allocations
+ * PB_ISOLATE_MODE_OTHER       - isolate for other purposes
+ */
+enum pb_isolate_mode {
+	PB_ISOLATE_MODE_MEM_OFFLINE,
+	PB_ISOLATE_MODE_CMA_ALLOC,
+	PB_ISOLATE_MODE_OTHER,
+};
 
 void __meminit init_pageblock_migratetype(struct page *page,
 					  enum migratetype migratetype,
@@ -49,10 +61,10 @@ bool pageblock_isolate_and_move_free_pages(struct zone *zone, struct page *page)
 bool pageblock_unisolate_and_move_free_pages(struct zone *zone, struct page *page);
 
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     int migratetype, int flags);
+			     enum pb_isolate_mode mode);
 
 void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn);
 
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
-			int isol_flags);
+			enum pb_isolate_mode mode);
 #endif
diff --git a/include/trace/events/kmem.h b/include/trace/events/kmem.h
index f74925a6cf69..efffcf578217 100644
--- a/include/trace/events/kmem.h
+++ b/include/trace/events/kmem.h
@@ -304,6 +304,7 @@ TRACE_EVENT(mm_page_alloc_extfrag,
 		__entry->change_ownership)
 );
 
+#ifdef CONFIG_CONTIG_ALLOC
 TRACE_EVENT(mm_alloc_contig_migrate_range_info,
 
 	TP_PROTO(unsigned long start,
@@ -311,9 +312,9 @@ TRACE_EVENT(mm_alloc_contig_migrate_range_info,
 		 unsigned long nr_migrated,
 		 unsigned long nr_reclaimed,
 		 unsigned long nr_mapped,
-		 int migratetype),
+		 acr_flags_t alloc_flags),
 
-	TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, migratetype),
+	TP_ARGS(start, end, nr_migrated, nr_reclaimed, nr_mapped, alloc_flags),
 
 	TP_STRUCT__entry(
 		__field(unsigned long, start)
@@ -321,7 +322,7 @@ TRACE_EVENT(mm_alloc_contig_migrate_range_info,
 		__field(unsigned long, nr_migrated)
 		__field(unsigned long, nr_reclaimed)
 		__field(unsigned long, nr_mapped)
-		__field(int, migratetype)
+		__field(acr_flags_t, alloc_flags)
 	),
 
 	TP_fast_assign(
@@ -330,17 +331,18 @@ TRACE_EVENT(mm_alloc_contig_migrate_range_info,
 		__entry->nr_migrated = nr_migrated;
 		__entry->nr_reclaimed = nr_reclaimed;
 		__entry->nr_mapped = nr_mapped;
-		__entry->migratetype = migratetype;
+		__entry->alloc_flags = alloc_flags;
 	),
 
-	TP_printk("start=0x%lx end=0x%lx migratetype=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu",
+	TP_printk("start=0x%lx end=0x%lx alloc_flags=%d nr_migrated=%lu nr_reclaimed=%lu nr_mapped=%lu",
 		  __entry->start,
 		  __entry->end,
-		  __entry->migratetype,
+		  __entry->alloc_flags,
 		  __entry->nr_migrated,
 		  __entry->nr_reclaimed,
 		  __entry->nr_mapped)
 );
+#endif
 
 TRACE_EVENT(mm_setup_per_zone_wmarks,
 
diff --git a/mm/cma.c b/mm/cma.c
index bd3772773736..c0b2630a1b81 100644
--- a/mm/cma.c
+++ b/mm/cma.c
@@ -822,7 +822,7 @@ static int cma_range_alloc(struct cma *cma, struct cma_memrange *cmr,
 
 		pfn = cmr->base_pfn + (bitmap_no << cma->order_per_bit);
 		mutex_lock(&cma->alloc_mutex);
-		ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA, gfp);
+		ret = alloc_contig_range(pfn, pfn + count, ACR_FLAGS_CMA, gfp);
 		mutex_unlock(&cma->alloc_mutex);
 		if (ret == 0) {
 			page = pfn_to_page(pfn);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 6e3380ad1bf5..e4009a44f883 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1962,8 +1962,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 	/* set above range as isolated */
 	ret = start_isolate_page_range(start_pfn, end_pfn,
-				       MIGRATE_MOVABLE,
-				       MEMORY_OFFLINE | REPORT_FAILURE);
+				       PB_ISOLATE_MODE_MEM_OFFLINE);
 	if (ret) {
 		reason = "failure to isolate range";
 		goto failed_removal_pcplists_disabled;
@@ -2033,7 +2032,8 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 			goto failed_removal_isolated;
 		}
 
-		ret = test_pages_isolated(start_pfn, end_pfn, MEMORY_OFFLINE);
+		ret = test_pages_isolated(start_pfn, end_pfn,
+					  PB_ISOLATE_MODE_MEM_OFFLINE);
 
 	} while (ret);
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 8d4b3f12b9a6..4f55f8ed65c7 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -6693,11 +6693,12 @@ static void alloc_contig_dump_pages(struct list_head *page_list)
 
 /*
  * [start, end) must belong to a single zone.
- * @migratetype: using migratetype to filter the type of migration in
+ * @alloc_flags: using acr_flags_t to filter the type of migration in
  *		trace_mm_alloc_contig_migrate_range_info.
  */
 static int __alloc_contig_migrate_range(struct compact_control *cc,
-		unsigned long start, unsigned long end, int migratetype)
+					unsigned long start, unsigned long end,
+					acr_flags_t alloc_flags)
 {
 	/* This function is based on compact_zone() from compaction.c. */
 	unsigned int nr_reclaimed;
@@ -6769,7 +6770,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
 		putback_movable_pages(&cc->migratepages);
 	}
 
-	trace_mm_alloc_contig_migrate_range_info(start, end, migratetype,
+	trace_mm_alloc_contig_migrate_range_info(start, end, alloc_flags,
 						 total_migrated,
 						 total_reclaimed,
 						 total_mapped);
@@ -6840,10 +6841,7 @@ static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask)
  * alloc_contig_range() -- tries to allocate given range of pages
  * @start:	start PFN to allocate
  * @end:	one-past-the-last PFN to allocate
- * @migratetype:	migratetype of the underlying pageblocks (either
- *			#MIGRATE_MOVABLE or #MIGRATE_CMA).  All pageblocks
- *			in range must have the same migratetype and it must
- *			be either of the two.
+ * @alloc_flags:	allocation information
  * @gfp_mask:	GFP mask. Node/zone/placement hints are ignored; only some
  *		action and reclaim modifiers are supported. Reclaim modifiers
  *		control allocation behavior during compaction/migration/reclaim.
@@ -6860,7 +6858,7 @@ static int __alloc_contig_verify_gfp_mask(gfp_t gfp_mask, gfp_t *gfp_cc_mask)
  * need to be freed with free_contig_range().
  */
 int alloc_contig_range_noprof(unsigned long start, unsigned long end,
-		       unsigned migratetype, gfp_t gfp_mask)
+			      acr_flags_t alloc_flags, gfp_t gfp_mask)
 {
 	unsigned long outer_start, outer_end;
 	int ret = 0;
@@ -6875,6 +6873,9 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 		.alloc_contig = true,
 	};
 	INIT_LIST_HEAD(&cc.migratepages);
+	enum pb_isolate_mode mode = (alloc_flags & ACR_FLAGS_CMA) ?
+					    PB_ISOLATE_MODE_CMA_ALLOC :
+					    PB_ISOLATE_MODE_OTHER;
 
 	gfp_mask = current_gfp_context(gfp_mask);
 	if (__alloc_contig_verify_gfp_mask(gfp_mask, (gfp_t *)&cc.gfp_mask))
@@ -6901,7 +6902,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 	 * put back to page allocator so that buddy can use them.
 	 */
 
-	ret = start_isolate_page_range(start, end, migratetype, 0);
+	ret = start_isolate_page_range(start, end, mode);
 	if (ret)
 		goto done;
 
@@ -6917,7 +6918,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 	 * allocated.  So, if we fall through be sure to clear ret so that
 	 * -EBUSY is not accidentally used or returned to caller.
 	 */
-	ret = __alloc_contig_migrate_range(&cc, start, end, migratetype);
+	ret = __alloc_contig_migrate_range(&cc, start, end, alloc_flags);
 	if (ret && ret != -EBUSY)
 		goto done;
 
@@ -6951,7 +6952,7 @@ int alloc_contig_range_noprof(unsigned long start, unsigned long end,
 	outer_start = find_large_buddy(start);
 
 	/* Make sure the range is really isolated. */
-	if (test_pages_isolated(outer_start, end, 0)) {
+	if (test_pages_isolated(outer_start, end, mode)) {
 		ret = -EBUSY;
 		goto done;
 	}
@@ -6994,8 +6995,8 @@ static int __alloc_contig_pages(unsigned long start_pfn,
 {
 	unsigned long end_pfn = start_pfn + nr_pages;
 
-	return alloc_contig_range_noprof(start_pfn, end_pfn, MIGRATE_MOVABLE,
-				   gfp_mask);
+	return alloc_contig_range_noprof(start_pfn, end_pfn, ACR_FLAGS_NONE,
+					 gfp_mask);
 }
 
 static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn,
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index 1edfef408faf..ece3bfc56bcd 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -31,7 +31,7 @@
  *
  */
 static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long end_pfn,
-				int migratetype, int flags)
+				enum pb_isolate_mode mode)
 {
 	struct page *page = pfn_to_page(start_pfn);
 	struct zone *zone = page_zone(page);
@@ -46,7 +46,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
 		 * isolate CMA pageblocks even when they are not movable in fact
 		 * so consider them movable here.
 		 */
-		if (is_migrate_cma(migratetype))
+		if (mode == PB_ISOLATE_MODE_CMA_ALLOC)
 			return NULL;
 
 		return page;
@@ -117,7 +117,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
 		 * The HWPoisoned page may be not in buddy system, and
 		 * page_count() is not 0.
 		 */
-		if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
+		if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) && PageHWPoison(page))
 			continue;
 
 		/*
@@ -130,7 +130,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
 		 * move these pages that still have a reference count > 0.
 		 * (false negatives in this function only)
 		 */
-		if ((flags & MEMORY_OFFLINE) && PageOffline(page))
+		if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) && PageOffline(page))
 			continue;
 
 		if (__PageMovable(page) || PageLRU(page))
@@ -151,7 +151,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
  * present in [start_pfn, end_pfn). The pageblock must intersect with
  * [start_pfn, end_pfn).
  */
-static int set_migratetype_isolate(struct page *page, int migratetype, int isol_flags,
+static int set_migratetype_isolate(struct page *page, enum pb_isolate_mode mode,
 			unsigned long start_pfn, unsigned long end_pfn)
 {
 	struct zone *zone = page_zone(page);
@@ -186,7 +186,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 				  end_pfn);
 
 	unmovable = has_unmovable_pages(check_unmovable_start, check_unmovable_end,
-			migratetype, isol_flags);
+			mode);
 	if (!unmovable) {
 		if (!pageblock_isolate_and_move_free_pages(zone, page)) {
 			spin_unlock_irqrestore(&zone->lock, flags);
@@ -198,7 +198,7 @@ static int set_migratetype_isolate(struct page *page, int migratetype, int isol_
 	}
 
 	spin_unlock_irqrestore(&zone->lock, flags);
-	if (isol_flags & REPORT_FAILURE) {
+	if (mode == PB_ISOLATE_MODE_MEM_OFFLINE) {
 		/*
 		 * printk() with zone->lock held will likely trigger a
 		 * lockdep splat, so defer it here.
@@ -292,11 +292,10 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * isolate_single_pageblock() -- tries to isolate a pageblock that might be
  * within a free or in-use page.
  * @boundary_pfn:		pageblock-aligned pfn that a page might cross
- * @flags:			isolation flags
+ * @mode:			isolation mode
  * @isolate_before:	isolate the pageblock before the boundary_pfn
  * @skip_isolation:	the flag to skip the pageblock isolation in second
  *			isolate_single_pageblock()
- * @migratetype:	migrate type to set in error recovery.
  *
  * Free and in-use pages can be as big as MAX_PAGE_ORDER and contain more than one
  * pageblock. When not all pageblocks within a page are isolated at the same
@@ -311,8 +310,9 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages)
  * either. The function handles this by splitting the free page or migrating
  * the in-use page then splitting the free page.
  */
-static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
-		bool isolate_before, bool skip_isolation, int migratetype)
+static int isolate_single_pageblock(unsigned long boundary_pfn,
+			enum pb_isolate_mode mode, bool isolate_before,
+			bool skip_isolation)
 {
 	unsigned long start_pfn;
 	unsigned long isolate_pageblock;
@@ -338,12 +338,11 @@ static int isolate_single_pageblock(unsigned long boundary_pfn, int flags,
 				      zone->zone_start_pfn);
 
 	if (skip_isolation) {
-		int mt __maybe_unused = get_pageblock_migratetype(pfn_to_page(isolate_pageblock));
-
-		VM_BUG_ON(!is_migrate_isolate(mt));
+		VM_BUG_ON(!get_pageblock_isolate(pfn_to_page(isolate_pageblock)));
 	} else {
-		ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock), migratetype,
-				flags, isolate_pageblock, isolate_pageblock + pageblock_nr_pages);
+		ret = set_migratetype_isolate(pfn_to_page(isolate_pageblock),
+				mode, isolate_pageblock,
+				isolate_pageblock + pageblock_nr_pages);
 
 		if (ret)
 			return ret;
@@ -441,14 +440,7 @@ failed:
  * start_isolate_page_range() - mark page range MIGRATE_ISOLATE
  * @start_pfn:		The first PFN of the range to be isolated.
  * @end_pfn:		The last PFN of the range to be isolated.
- * @migratetype:	Migrate type to set in error recovery.
- * @flags:		The following flags are allowed (they can be combined in
- *			a bit mask)
- *			MEMORY_OFFLINE - isolate to offline (!allocate) memory
- *					 e.g., skip over PageHWPoison() pages
- *					 and PageOffline() pages.
- *			REPORT_FAILURE - report details about the failure to
- *			isolate the range
+ * @mode:		isolation mode
  *
  * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in
  * the range will never be allocated. Any free pages and pages freed in the
@@ -481,7 +473,7 @@ failed:
  * Return: 0 on success and -EBUSY if any part of range cannot be isolated.
  */
 int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
-			     int migratetype, int flags)
+			     enum pb_isolate_mode mode)
 {
 	unsigned long pfn;
 	struct page *page;
@@ -492,8 +484,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	bool skip_isolation = false;
 
 	/* isolate [isolate_start, isolate_start + pageblock_nr_pages) pageblock */
-	ret = isolate_single_pageblock(isolate_start, flags, false,
-			skip_isolation, migratetype);
+	ret = isolate_single_pageblock(isolate_start, mode, false,
+			skip_isolation);
 	if (ret)
 		return ret;
 
@@ -501,8 +493,7 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 		skip_isolation = true;
 
 	/* isolate [isolate_end - pageblock_nr_pages, isolate_end) pageblock */
-	ret = isolate_single_pageblock(isolate_end, flags, true,
-			skip_isolation, migratetype);
+	ret = isolate_single_pageblock(isolate_end, mode, true, skip_isolation);
 	if (ret) {
 		unset_migratetype_isolate(pfn_to_page(isolate_start));
 		return ret;
@@ -513,8 +504,8 @@ int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn,
 	     pfn < isolate_end - pageblock_nr_pages;
 	     pfn += pageblock_nr_pages) {
 		page = __first_valid_page(pfn, pageblock_nr_pages);
-		if (page && set_migratetype_isolate(page, migratetype, flags,
-					start_pfn, end_pfn)) {
+		if (page && set_migratetype_isolate(page, mode, start_pfn,
+					end_pfn)) {
 			undo_isolate_page_range(isolate_start, pfn);
 			unset_migratetype_isolate(
 				pfn_to_page(isolate_end - pageblock_nr_pages));
@@ -556,7 +547,7 @@ void undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn)
  */
 static unsigned long
 __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
-				  int flags)
+				  enum pb_isolate_mode mode)
 {
 	struct page *page;
 
@@ -569,11 +560,12 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
 			 * simple way to verify that as VM_BUG_ON(), though.
 			 */
 			pfn += 1 << buddy_order(page);
-		else if ((flags & MEMORY_OFFLINE) && PageHWPoison(page))
+		else if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) &&
+			 PageHWPoison(page))
 			/* A HWPoisoned page cannot be also PageBuddy */
 			pfn++;
-		else if ((flags & MEMORY_OFFLINE) && PageOffline(page) &&
-			 !page_count(page))
+		else if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) &&
+			 PageOffline(page) && !page_count(page))
 			/*
 			 * The responsible driver agreed to skip PageOffline()
 			 * pages when offlining memory by dropping its
@@ -591,11 +583,11 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
  * test_pages_isolated - check if pageblocks in range are isolated
  * @start_pfn:		The first PFN of the isolated range
  * @end_pfn:		The first PFN *after* the isolated range
- * @isol_flags:		Testing mode flags
+ * @mode:		Testing mode
  *
  * This tests if all in the specified range are free.
  *
- * If %MEMORY_OFFLINE is specified in @flags, it will consider
+ * If %PB_ISOLATE_MODE_MEM_OFFLINE specified in @mode, it will consider
  * poisoned and offlined pages free as well.
  *
  * Caller must ensure the requested range doesn't span zones.
@@ -603,7 +595,7 @@ __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn,
  * Returns 0 if true, -EBUSY if one or more pages are in use.
  */
 int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
-			int isol_flags)
+			enum pb_isolate_mode mode)
 {
 	unsigned long pfn, flags;
 	struct page *page;
@@ -639,7 +631,7 @@ int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn,
 	/* Check all pages are free or marked as ISOLATED */
 	zone = page_zone(page);
 	spin_lock_irqsave(&zone->lock, flags);
-	pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, isol_flags);
+	pfn = __test_page_isolated_in_pageblock(start_pfn, end_pfn, mode);
 	spin_unlock_irqrestore(&zone->lock, flags);
 
 	ret = pfn < end_pfn ? -EBUSY : 0;
-- 
cgit v1.2.3


From eff41389d8249a1a5a67faa440255ed8e526803a Mon Sep 17 00:00:00 2001
From: Peter Xu <peterx@redhat.com>
Date: Fri, 27 Jun 2025 12:07:07 -0400
Subject: mm/hugetlb: remove prepare_hugepage_range()

Only mips and loongarch implemented this API, however what it does was
checking against stack overflow for either len or addr.  That's already
done in arch's arch_get_unmapped_area*() functions, even though it may not
be 100% identical checks.

For example, for both of the architectures, there will be a trivial
difference on how stack top was defined.  The old code uses STACK_TOP
which may be slightly smaller than TASK_SIZE on either of them, but the
hope is that shouldn't be a problem.

It means the whole API is pretty much obsolete at least now, remove it
completely.

Link: https://lkml.kernel.org/r/20250627160707.2124580-1-peterx@redhat.com
Signed-off-by: Peter Xu <peterx@redhat.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Huacai Chen <chenhuacai@kernel.org>
Cc: Thomas Bogendoerfer <tsbogend@alpha.franken.de>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Jann Horn <jannh@google.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Pedro Falcato <pfalcato@suse.de>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/loongarch/include/asm/hugetlb.h | 14 --------------
 arch/mips/include/asm/hugetlb.h      | 14 --------------
 fs/hugetlbfs/inode.c                 |  8 ++------
 include/asm-generic/hugetlb.h        |  8 --------
 include/linux/hugetlb.h              |  6 ------
 5 files changed, 2 insertions(+), 48 deletions(-)

(limited to 'include/linux')

diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
index 4dc4b3e04225..ab68b594f889 100644
--- a/arch/loongarch/include/asm/hugetlb.h
+++ b/arch/loongarch/include/asm/hugetlb.h
@@ -10,20 +10,6 @@
 
 uint64_t pmd_to_entrylo(unsigned long pmd_val);
 
-#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
-static inline int prepare_hugepage_range(struct file *file,
-					 unsigned long addr,
-					 unsigned long len)
-{
-	unsigned long task_size = STACK_TOP;
-
-	if (len > task_size)
-		return -ENOMEM;
-	if (task_size - len < addr)
-		return -EINVAL;
-	return 0;
-}
-
 #define __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 				  pte_t *ptep, unsigned long sz)
diff --git a/arch/mips/include/asm/hugetlb.h b/arch/mips/include/asm/hugetlb.h
index fbc71ddcf0f6..8c460ce01ffe 100644
--- a/arch/mips/include/asm/hugetlb.h
+++ b/arch/mips/include/asm/hugetlb.h
@@ -11,20 +11,6 @@
 
 #include <asm/page.h>
 
-#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
-static inline int prepare_hugepage_range(struct file *file,
-					 unsigned long addr,
-					 unsigned long len)
-{
-	unsigned long task_size = STACK_TOP;
-
-	if (len > task_size)
-		return -ENOMEM;
-	if (task_size - len < addr)
-		return -EINVAL;
-	return 0;
-}
-
 #define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep,
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 00b2d1a032fd..81a6acddd690 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -179,12 +179,8 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 
 	if (len & ~huge_page_mask(h))
 		return -EINVAL;
-	if (flags & MAP_FIXED) {
-		if (addr & ~huge_page_mask(h))
-			return -EINVAL;
-		if (prepare_hugepage_range(file, addr, len))
-			return -EINVAL;
-	}
+	if ((flags & MAP_FIXED) && (addr & ~huge_page_mask(h)))
+		return -EINVAL;
 	if (addr)
 		addr0 = ALIGN(addr, huge_page_size(h));
 
diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 3e0a8fe9b108..4bce4f07f44f 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -114,14 +114,6 @@ static inline int huge_pte_none_mostly(pte_t pte)
 }
 #endif
 
-#ifndef __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
-static inline int prepare_hugepage_range(struct file *file,
-		unsigned long addr, unsigned long len)
-{
-	return 0;
-}
-#endif
-
 #ifndef __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 		unsigned long addr, pte_t *ptep)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index c6c87eae4a8d..474de8e2a8f2 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -359,12 +359,6 @@ static inline void hugetlb_show_meminfo_node(int nid)
 {
 }
 
-static inline int prepare_hugepage_range(struct file *file,
-				unsigned long addr, unsigned long len)
-{
-	return -EINVAL;
-}
-
 static inline void hugetlb_vma_lock_read(struct vm_area_struct *vma)
 {
 }
-- 
cgit v1.2.3


From 5bd3b163e374462c05c055ff091582d757929d3f Mon Sep 17 00:00:00 2001
From: Xuanye Liu <liuqiye2025@163.com>
Date: Wed, 2 Jul 2025 15:12:35 +0800
Subject: mm: fix spelling issue in swap.h

recliam -> reclaim

Link: https://lkml.kernel.org/r/20250702071235.212794-1-liuqiye2025@163.com
Signed-off-by: Xuanye Liu <liuqiye2025@163.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index bc0e1c275fc0..a49be950c485 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -415,7 +415,7 @@ extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,
 #define MIN_SWAPPINESS 0
 #define MAX_SWAPPINESS 200
 
-/* Just recliam from anon folios in proactive memory reclaim */
+/* Just reclaim from anon folios in proactive memory reclaim */
 #define SWAPPINESS_ANON_ONLY (MAX_SWAPPINESS + 1)
 
 extern unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg,
-- 
cgit v1.2.3


From 526f36f3f47b9ad29ffb1bf668b7f295287ee11b Mon Sep 17 00:00:00 2001
From: Dev Jain <dev.jain@arm.com>
Date: Thu, 3 Jul 2025 12:03:38 +0530
Subject: maple tree: add some comments

Add comments explaining the fields for maple_metadata, since "end" is
ambiguous and "gap" can be confused as the largest gap, whereas it is
actually the offset of the largest gap.

Add comment for mas_ascend() to explain, whose min and max we are trying
to find.  Explain that, for example, if we are already on offset zero,
then the parent min is mas->min, otherwise we need to walk up to find the
implied pivot min.

Link: https://lkml.kernel.org/r/20250703063338.51509-1-dev.jain@arm.com
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Cc: Wei Yang <richard.weiyang@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/maple_tree.h | 4 ++--
 lib/maple_tree.c           | 8 +++++++-
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/maple_tree.h b/include/linux/maple_tree.h
index 9ef129038224..bafe143b1f78 100644
--- a/include/linux/maple_tree.h
+++ b/include/linux/maple_tree.h
@@ -75,8 +75,8 @@
  * searching for gaps or any other code that needs to find the end of the data.
  */
 struct maple_metadata {
-	unsigned char end;
-	unsigned char gap;
+	unsigned char end;	/* end of data */
+	unsigned char gap;	/* offset of largest gap */
 };
 
 /*
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 0e85e92c5375..b4ee2d29d7a9 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -1053,7 +1053,7 @@ static inline void mte_set_gap(const struct maple_enode *mn,
  * mas_ascend() - Walk up a level of the tree.
  * @mas: The maple state
  *
- * Sets the @mas->max and @mas->min to the correct values when walking up.  This
+ * Sets the @mas->max and @mas->min for the parent node of mas->node.  This
  * may cause several levels of walking up to find the correct min and max.
  * May find a dead node which will cause a premature return.
  * Return: 1 on dead node, 0 otherwise
@@ -1098,6 +1098,12 @@ static int mas_ascend(struct ma_state *mas)
 
 	min = 0;
 	max = ULONG_MAX;
+
+	/*
+	 * !mas->offset implies that parent node min == mas->min.
+	 * mas->offset > 0 implies that we need to walk up to find the
+	 * implied pivot min.
+	 */
 	if (!mas->offset) {
 		min = mas->min;
 		set_min = true;
-- 
cgit v1.2.3


From 15504b1163007bbfbd9a63460d5c14737c16e96d Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:24:56 +0200
Subject: mm/balloon_compaction: convert balloon_page_delete() to
 balloon_page_finalize()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's move the removal of the page from the balloon list into the single
caller, to remove the dependency on the PG_isolated flag and clarify
locking requirements.

Note that for now, balloon_page_delete() was used on two paths:

(1) Removing a page from the balloon for deflation through
    balloon_page_list_dequeue()
(2) Removing an isolated page from the balloon for migration in the
    per-driver migration handlers. Isolated pages were already removed from
    the balloon list during isolation.

So instead of relying on the flag, we can just distinguish both cases
directly and handle it accordingly in the caller.

We'll shuffle the operations a bit such that they logically make more
sense (e.g., remove from the list before clearing flags).

In balloon migration functions we can now move the balloon_page_finalize()
out of the balloon lock and perform the finalization just before dropping
the balloon reference.

Document that the page lock is currently required when modifying the
movability aspects of a page; hopefully we can soon decouple this from the
page lock.

Link: https://lkml.kernel.org/r/20250704102524.326966-3-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/powerpc/platforms/pseries/cmm.c |  2 +-
 drivers/misc/vmw_balloon.c           |  3 +--
 drivers/virtio/virtio_balloon.c      |  4 +---
 include/linux/balloon_compaction.h   | 43 ++++++++++++++----------------------
 mm/balloon_compaction.c              |  3 ++-
 5 files changed, 21 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/platforms/pseries/cmm.c b/arch/powerpc/platforms/pseries/cmm.c
index 5f4037c1d7fe..5e0a718d1be7 100644
--- a/arch/powerpc/platforms/pseries/cmm.c
+++ b/arch/powerpc/platforms/pseries/cmm.c
@@ -532,7 +532,6 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info,
 
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 	balloon_page_insert(b_dev_info, newpage);
-	balloon_page_delete(page);
 	b_dev_info->isolated_pages--;
 	spin_unlock_irqrestore(&b_dev_info->pages_lock, flags);
 
@@ -542,6 +541,7 @@ static int cmm_migratepage(struct balloon_dev_info *b_dev_info,
 	 */
 	plpar_page_set_active(page);
 
+	balloon_page_finalize(page);
 	/* balloon page list reference */
 	put_page(page);
 
diff --git a/drivers/misc/vmw_balloon.c b/drivers/misc/vmw_balloon.c
index c817d8c21641..6653fc53c951 100644
--- a/drivers/misc/vmw_balloon.c
+++ b/drivers/misc/vmw_balloon.c
@@ -1778,8 +1778,7 @@ static int vmballoon_migratepage(struct balloon_dev_info *b_dev_info,
 	 * @pages_lock . We keep holding @comm_lock since we will need it in a
 	 * second.
 	 */
-	balloon_page_delete(page);
-
+	balloon_page_finalize(page);
 	put_page(page);
 
 	/* Inflate */
diff --git a/drivers/virtio/virtio_balloon.c b/drivers/virtio/virtio_balloon.c
index 89da052f4f68..e299e18346a3 100644
--- a/drivers/virtio/virtio_balloon.c
+++ b/drivers/virtio/virtio_balloon.c
@@ -866,15 +866,13 @@ static int virtballoon_migratepage(struct balloon_dev_info *vb_dev_info,
 	tell_host(vb, vb->inflate_vq);
 
 	/* balloon's page migration 2nd step -- deflate "page" */
-	spin_lock_irqsave(&vb_dev_info->pages_lock, flags);
-	balloon_page_delete(page);
-	spin_unlock_irqrestore(&vb_dev_info->pages_lock, flags);
 	vb->num_pfns = VIRTIO_BALLOON_PAGES_PER_PAGE;
 	set_page_pfns(vb, vb->pfns, page);
 	tell_host(vb, vb->deflate_vq);
 
 	mutex_unlock(&vb->balloon_lock);
 
+	balloon_page_finalize(page);
 	put_page(page); /* balloon reference */
 
 	return MIGRATEPAGE_SUCCESS;
diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index 5ca2d5699620..b9f19da37b08 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -97,27 +97,6 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 	list_add(&page->lru, &balloon->pages);
 }
 
-/*
- * balloon_page_delete - delete a page from balloon's page list and clear
- *			 the page->private assignement accordingly.
- * @page    : page to be released from balloon's page list
- *
- * Caller must ensure the page is locked and the spin_lock protecting balloon
- * pages list is held before deleting a page from the balloon device.
- */
-static inline void balloon_page_delete(struct page *page)
-{
-	__ClearPageOffline(page);
-	__ClearPageMovable(page);
-	set_page_private(page, 0);
-	/*
-	 * No touch page.lru field once @page has been isolated
-	 * because VM is using the field.
-	 */
-	if (!PageIsolated(page))
-		list_del(&page->lru);
-}
-
 /*
  * balloon_page_device - get the b_dev_info descriptor for the balloon device
  *			 that enqueues the given page.
@@ -141,12 +120,6 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 	list_add(&page->lru, &balloon->pages);
 }
 
-static inline void balloon_page_delete(struct page *page)
-{
-	__ClearPageOffline(page);
-	list_del(&page->lru);
-}
-
 static inline gfp_t balloon_mapping_gfp_mask(void)
 {
 	return GFP_HIGHUSER;
@@ -154,6 +127,22 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
 
 #endif /* CONFIG_BALLOON_COMPACTION */
 
+/*
+ * balloon_page_finalize - prepare a balloon page that was removed from the
+ *			   balloon list for release to the page allocator
+ * @page: page to be released to the page allocator
+ *
+ * Caller must ensure that the page is locked.
+ */
+static inline void balloon_page_finalize(struct page *page)
+{
+	if (IS_ENABLED(CONFIG_BALLOON_COMPACTION)) {
+		__ClearPageMovable(page);
+		set_page_private(page, 0);
+	}
+	__ClearPageOffline(page);
+}
+
 /*
  * balloon_page_push - insert a page into a page list.
  * @head : pointer to list
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index fcb60233aa35..ec176bdb8a78 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -94,7 +94,8 @@ size_t balloon_page_list_dequeue(struct balloon_dev_info *b_dev_info,
 		if (!trylock_page(page))
 			continue;
 
-		balloon_page_delete(page);
+		list_del(&page->lru);
+		balloon_page_finalize(page);
 		__count_vm_event(BALLOON_DEFLATE);
 		list_add(&page->lru, pages);
 		unlock_page(page);
-- 
cgit v1.2.3


From 65aabd88dffda68639808e0827cfef624a1cd55f Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:24:59 +0200
Subject: mm/balloon_compaction: make PageOffline sticky until the page is
 freed
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let the page freeing code handle clearing the page type.  Being able to
identify balloon pages until actually freed is a requirement for upcoming
movable_ops migration changes.

Link: https://lkml.kernel.org/r/20250704102524.326966-6-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Acked-by: Zi Yan <ziy@nvidia.com>
Acked-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/balloon_compaction.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index b9f19da37b08..bfc6e50bd004 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -140,7 +140,7 @@ static inline void balloon_page_finalize(struct page *page)
 		__ClearPageMovable(page);
 		set_page_private(page, 0);
 	}
-	__ClearPageOffline(page);
+	/* PageOffline is sticky until the page is freed to the buddy. */
 }
 
 /*
-- 
cgit v1.2.3


From 6ef0c1976b8fab938e732c2fb751fa8965153b2e Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:01 +0200
Subject: mm/migrate: rename isolate_movable_page() to
 isolate_movable_ops_page()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

...  and start moving back to per-page things that will absolutely not be
folio things in the future.  Add documentation and a comment that the
remaining folio stuff (lock, refcount) will have to be reworked as well.

While at it, convert the VM_BUG_ON() into a WARN_ON_ONCE() and handle it
gracefully (relevant with further changes), and convert a WARN_ON_ONCE()
into a VM_WARN_ON_ONCE_PAGE().

Note that we will leave anything that needs a rework (lock, refcount,
->lru) to be using folios for now: that perfectly highlights the
problematic bits.

Link: https://lkml.kernel.org/r/20250704102524.326966-8-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/migrate.h |  4 ++--
 mm/compaction.c         |  2 +-
 mm/migrate.c            | 39 +++++++++++++++++++++++++++++----------
 3 files changed, 32 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index aaa2114498d6..c0ec7422837b 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -69,7 +69,7 @@ int migrate_pages(struct list_head *l, new_folio_t new, free_folio_t free,
 		  unsigned long private, enum migrate_mode mode, int reason,
 		  unsigned int *ret_succeeded);
 struct folio *alloc_migration_target(struct folio *src, unsigned long private);
-bool isolate_movable_page(struct page *page, isolate_mode_t mode);
+bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode);
 bool isolate_folio_to_list(struct folio *folio, struct list_head *list);
 
 int migrate_huge_page_move_mapping(struct address_space *mapping,
@@ -90,7 +90,7 @@ static inline int migrate_pages(struct list_head *l, new_folio_t new,
 static inline struct folio *alloc_migration_target(struct folio *src,
 		unsigned long private)
 	{ return NULL; }
-static inline bool isolate_movable_page(struct page *page, isolate_mode_t mode)
+static inline bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
 	{ return false; }
 static inline bool isolate_folio_to_list(struct folio *folio, struct list_head *list)
 	{ return false; }
diff --git a/mm/compaction.c b/mm/compaction.c
index 3925cb61dbb8..17455c5a4be0 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1093,7 +1093,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 					locked = NULL;
 				}
 
-				if (isolate_movable_page(page, mode)) {
+				if (isolate_movable_ops_page(page, mode)) {
 					folio = page_folio(page);
 					goto isolate_success;
 				}
diff --git a/mm/migrate.c b/mm/migrate.c
index 208d2d4a2f8d..2e648d75248e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -51,8 +51,26 @@
 #include "internal.h"
 #include "swap.h"
 
-bool isolate_movable_page(struct page *page, isolate_mode_t mode)
+/**
+ * isolate_movable_ops_page - isolate a movable_ops page for migration
+ * @page: The page.
+ * @mode: The isolation mode.
+ *
+ * Try to isolate a movable_ops page for migration. Will fail if the page is
+ * not a movable_ops page, if the page is already isolated for migration
+ * or if the page was just was released by its owner.
+ *
+ * Once isolated, the page cannot get freed until it is either putback
+ * or migrated.
+ *
+ * Returns true if isolation succeeded, otherwise false.
+ */
+bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
 {
+	/*
+	 * TODO: these pages will not be folios in the future. All
+	 * folio dependencies will have to be removed.
+	 */
 	struct folio *folio = folio_get_nontail_page(page);
 	const struct movable_operations *mops;
 
@@ -73,7 +91,7 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode)
 	 * we use non-atomic bitops on newly allocated page flags so
 	 * unconditionally grabbing the lock ruins page's owner side.
 	 */
-	if (unlikely(!__folio_test_movable(folio)))
+	if (unlikely(!__PageMovable(page)))
 		goto out_putfolio;
 
 	/*
@@ -90,18 +108,19 @@ bool isolate_movable_page(struct page *page, isolate_mode_t mode)
 	if (unlikely(!folio_trylock(folio)))
 		goto out_putfolio;
 
-	if (!folio_test_movable(folio) || folio_test_isolated(folio))
+	if (!PageMovable(page) || PageIsolated(page))
 		goto out_no_isolated;
 
-	mops = folio_movable_ops(folio);
-	VM_BUG_ON_FOLIO(!mops, folio);
+	mops = page_movable_ops(page);
+	if (WARN_ON_ONCE(!mops))
+		goto out_no_isolated;
 
-	if (!mops->isolate_page(&folio->page, mode))
+	if (!mops->isolate_page(page, mode))
 		goto out_no_isolated;
 
 	/* Driver shouldn't use the isolated flag */
-	WARN_ON_ONCE(folio_test_isolated(folio));
-	folio_set_isolated(folio);
+	VM_WARN_ON_ONCE_PAGE(PageIsolated(page), page);
+	SetPageIsolated(page);
 	folio_unlock(folio);
 
 	return true;
@@ -175,8 +194,8 @@ bool isolate_folio_to_list(struct folio *folio, struct list_head *list)
 	if (lru)
 		isolated = folio_isolate_lru(folio);
 	else
-		isolated = isolate_movable_page(&folio->page,
-						ISOLATE_UNEVICTABLE);
+		isolated = isolate_movable_ops_page(&folio->page,
+						    ISOLATE_UNEVICTABLE);
 
 	if (!isolated)
 		return false;
-- 
cgit v1.2.3


From 07e5355eeead3a715bb48ffe13499dd3d0178e52 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:04 +0200
Subject: mm/migrate: remove folio_test_movable() and folio_movable_ops()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Folios will have nothing to do with movable_ops page migration.  These
functions are now unused, so let's remove them.

Note that __folio_test_movable() and friends will be removed separately
next, after more rework.

Link: https://lkml.kernel.org/r/20250704102524.326966-11-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/migrate.h | 14 --------------
 1 file changed, 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index c0ec7422837b..c99a00d4ca27 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -118,20 +118,6 @@ static inline void __ClearPageMovable(struct page *page)
 }
 #endif
 
-static inline bool folio_test_movable(struct folio *folio)
-{
-	return PageMovable(&folio->page);
-}
-
-static inline
-const struct movable_operations *folio_movable_ops(struct folio *folio)
-{
-	VM_BUG_ON(!__folio_test_movable(folio));
-
-	return (const struct movable_operations *)
-		((unsigned long)folio->mapping - PAGE_MAPPING_MOVABLE);
-}
-
 static inline
 const struct movable_operations *page_movable_ops(struct page *page)
 {
-- 
cgit v1.2.3


From 3544c4faccb8f0867bc65f8007ee70bfb5054305 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:07 +0200
Subject: mm/balloon_compaction: stop using __ClearPageMovable()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

We can just look at the balloon device (stored in page->private), to see
if the page is still part of the balloon.

As isolated balloon pages cannot get released (they are taken off the
balloon list while isolated), we don't have to worry about this case in
the putback and migration callback.  Add a WARN_ON_ONCE for now.

Link: https://lkml.kernel.org/r/20250704102524.326966-14-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/balloon_compaction.h |  4 +---
 mm/balloon_compaction.c            | 11 +++++++++++
 2 files changed, 12 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index bfc6e50bd004..9bce8e9f5018 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -136,10 +136,8 @@ static inline gfp_t balloon_mapping_gfp_mask(void)
  */
 static inline void balloon_page_finalize(struct page *page)
 {
-	if (IS_ENABLED(CONFIG_BALLOON_COMPACTION)) {
-		__ClearPageMovable(page);
+	if (IS_ENABLED(CONFIG_BALLOON_COMPACTION))
 		set_page_private(page, 0);
-	}
 	/* PageOffline is sticky until the page is freed to the buddy. */
 }
 
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index ec176bdb8a78..e4f1a122d786 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -206,6 +206,9 @@ static bool balloon_page_isolate(struct page *page, isolate_mode_t mode)
 	struct balloon_dev_info *b_dev_info = balloon_page_device(page);
 	unsigned long flags;
 
+	if (!b_dev_info)
+		return false;
+
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 	list_del(&page->lru);
 	b_dev_info->isolated_pages++;
@@ -219,6 +222,10 @@ static void balloon_page_putback(struct page *page)
 	struct balloon_dev_info *b_dev_info = balloon_page_device(page);
 	unsigned long flags;
 
+	/* Isolated balloon pages cannot get deflated. */
+	if (WARN_ON_ONCE(!b_dev_info))
+		return;
+
 	spin_lock_irqsave(&b_dev_info->pages_lock, flags);
 	list_add(&page->lru, &b_dev_info->pages);
 	b_dev_info->isolated_pages--;
@@ -234,6 +241,10 @@ static int balloon_page_migrate(struct page *newpage, struct page *page,
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
 	VM_BUG_ON_PAGE(!PageLocked(newpage), newpage);
 
+	/* Isolated balloon pages cannot get deflated. */
+	if (WARN_ON_ONCE(!balloon))
+		return -EAGAIN;
+
 	return balloon->migratepage(balloon, newpage, page, mode);
 }
 
-- 
cgit v1.2.3


From 34727dee04994c8ceb1bb8a927af0a88e52e103c Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:08 +0200
Subject: mm/migrate: remove __ClearPageMovable()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Unused, let's remove it.

The Chinese docs in Documentation/translations/zh_CN/mm/page_migration.rst
still mention it, but that whole docs is destined to get outdated and
updated by somebody that actually speaks that language.

Link: https://lkml.kernel.org/r/20250704102524.326966-15-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/migrate.h |  8 ++------
 mm/compaction.c         | 11 -----------
 2 files changed, 2 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index c99a00d4ca27..6eeda8eb1e0d 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -35,8 +35,8 @@ struct migration_target_control;
  * @src page.  The driver should copy the contents of the
  * @src page to the @dst page and set up the fields of @dst page.
  * Both pages are locked.
- * If page migration is successful, the driver should call
- * __ClearPageMovable(@src) and return MIGRATEPAGE_SUCCESS.
+ * If page migration is successful, the driver should
+ * return MIGRATEPAGE_SUCCESS.
  * If the driver cannot migrate the page at the moment, it can return
  * -EAGAIN.  The VM interprets this as a temporary migration failure and
  * will retry it later.  Any other error value is a permanent migration
@@ -106,16 +106,12 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #ifdef CONFIG_COMPACTION
 bool PageMovable(struct page *page);
 void __SetPageMovable(struct page *page, const struct movable_operations *ops);
-void __ClearPageMovable(struct page *page);
 #else
 static inline bool PageMovable(struct page *page) { return false; }
 static inline void __SetPageMovable(struct page *page,
 		const struct movable_operations *ops)
 {
 }
-static inline void __ClearPageMovable(struct page *page)
-{
-}
 #endif
 
 static inline
diff --git a/mm/compaction.c b/mm/compaction.c
index 17455c5a4be0..889ec696ba96 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -137,17 +137,6 @@ void __SetPageMovable(struct page *page, const struct movable_operations *mops)
 }
 EXPORT_SYMBOL(__SetPageMovable);
 
-void __ClearPageMovable(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageMovable(page), page);
-	/*
-	 * This page still has the type of a movable page, but it's
-	 * actually not movable any more.
-	 */
-	page->mapping = (void *)PAGE_MAPPING_MOVABLE;
-}
-EXPORT_SYMBOL(__ClearPageMovable);
-
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
 
-- 
cgit v1.2.3


From 22d103aef090dc688a88881fb955376dec1228d5 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:09 +0200
Subject: mm/migration: remove PageMovable()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Previously, if __ClearPageMovable() were invoked on a page, this would
cause __PageMovable() to return false, but due to the continued existence
of page movable ops, PageMovable() would have returned true.

With __ClearPageMovable() gone, the two are exactly equivalent.

So we can replace PageMovable() checks by __PageMovable().  In fact,
__PageMovable() cannot change until a page is freed, so we can turn some
PageMovable() into sanity checks for __PageMovable().

Link: https://lkml.kernel.org/r/20250704102524.326966-16-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/migrate.h |  2 --
 mm/compaction.c         | 15 ---------------
 mm/migrate.c            | 18 ++++++++++--------
 3 files changed, 10 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 6eeda8eb1e0d..25659a685e2a 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -104,10 +104,8 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_COMPACTION
-bool PageMovable(struct page *page);
 void __SetPageMovable(struct page *page, const struct movable_operations *ops);
 #else
-static inline bool PageMovable(struct page *page) { return false; }
 static inline void __SetPageMovable(struct page *page,
 		const struct movable_operations *ops)
 {
diff --git a/mm/compaction.c b/mm/compaction.c
index 889ec696ba96..5c3737301701 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -114,21 +114,6 @@ static unsigned long release_free_list(struct list_head *freepages)
 }
 
 #ifdef CONFIG_COMPACTION
-bool PageMovable(struct page *page)
-{
-	const struct movable_operations *mops;
-
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	if (!__PageMovable(page))
-		return false;
-
-	mops = page_movable_ops(page);
-	if (mops)
-		return true;
-
-	return false;
-}
-
 void __SetPageMovable(struct page *page, const struct movable_operations *mops)
 {
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
diff --git a/mm/migrate.c b/mm/migrate.c
index 61e98ed46f13..1f07c8f1fb74 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -87,9 +87,12 @@ bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
 		goto out;
 
 	/*
-	 * Check movable flag before taking the page lock because
+	 * Check for movable_ops pages before taking the page lock because
 	 * we use non-atomic bitops on newly allocated page flags so
 	 * unconditionally grabbing the lock ruins page's owner side.
+	 *
+	 * Note that once a page has movable_ops, it will stay that way
+	 * until the page was freed.
 	 */
 	if (unlikely(!__PageMovable(page)))
 		goto out_putfolio;
@@ -108,7 +111,8 @@ bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
 	if (unlikely(!folio_trylock(folio)))
 		goto out_putfolio;
 
-	if (!PageMovable(page) || PageIsolated(page))
+	VM_WARN_ON_ONCE_PAGE(!__PageMovable(page), page);
+	if (PageIsolated(page))
 		goto out_no_isolated;
 
 	mops = page_movable_ops(page);
@@ -149,11 +153,10 @@ static void putback_movable_ops_page(struct page *page)
 	 */
 	struct folio *folio = page_folio(page);
 
+	VM_WARN_ON_ONCE_PAGE(!__PageMovable(page), page);
 	VM_WARN_ON_ONCE_PAGE(!PageIsolated(page), page);
 	folio_lock(folio);
-	/* If the page was released by it's owner, there is nothing to do. */
-	if (PageMovable(page))
-		page_movable_ops(page)->putback_page(page);
+	page_movable_ops(page)->putback_page(page);
 	ClearPageIsolated(page);
 	folio_unlock(folio);
 	folio_put(folio);
@@ -191,10 +194,9 @@ static int migrate_movable_ops_page(struct page *dst, struct page *src,
 {
 	int rc = MIGRATEPAGE_SUCCESS;
 
+	VM_WARN_ON_ONCE_PAGE(!__PageMovable(src), src);
 	VM_WARN_ON_ONCE_PAGE(!PageIsolated(src), src);
-	/* If the page was released by it's owner, there is nothing to do. */
-	if (PageMovable(src))
-		rc = page_movable_ops(src)->migrate_page(dst, src, mode);
+	rc = page_movable_ops(src)->migrate_page(dst, src, mode);
 	if (rc == MIGRATEPAGE_SUCCESS)
 		ClearPageIsolated(src);
 	return rc;
-- 
cgit v1.2.3


From d4fb4587bd73b6b773397f5fed52a5e4bd4dec8b Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:10 +0200
Subject: mm: rename __PageMovable() to page_has_movable_ops()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's make it clearer that we are talking about movable_ops pages.

While at it, convert a VM_BUG_ON to a VM_WARN_ON_ONCE_PAGE.

Link: https://lkml.kernel.org/r/20250704102524.326966-17-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/migrate.h    |  2 +-
 include/linux/page-flags.h |  2 +-
 mm/compaction.c            |  7 ++-----
 mm/memory-failure.c        |  4 ++--
 mm/memory_hotplug.c        | 10 ++++------
 mm/migrate.c               |  8 ++++----
 mm/page_alloc.c            |  2 +-
 mm/page_isolation.c        | 10 +++++-----
 8 files changed, 20 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 25659a685e2a..e04035f70e36 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -115,7 +115,7 @@ static inline void __SetPageMovable(struct page *page,
 static inline
 const struct movable_operations *page_movable_ops(struct page *page)
 {
-	VM_BUG_ON(!__PageMovable(page));
+	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
 
 	return (const struct movable_operations *)
 		((unsigned long)page->mapping - PAGE_MAPPING_MOVABLE);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4fe5ee67535b..c67163b73c5e 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -750,7 +750,7 @@ static __always_inline bool __folio_test_movable(const struct folio *folio)
 			PAGE_MAPPING_MOVABLE;
 }
 
-static __always_inline bool __PageMovable(const struct page *page)
+static __always_inline bool page_has_movable_ops(const struct page *page)
 {
 	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
 				PAGE_MAPPING_MOVABLE;
diff --git a/mm/compaction.c b/mm/compaction.c
index 5c3737301701..41fd6a1fe9a3 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1056,11 +1056,8 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		 * Skip any other type of page
 		 */
 		if (!PageLRU(page)) {
-			/*
-			 * __PageMovable can return false positive so we need
-			 * to verify it under page_lock.
-			 */
-			if (unlikely(__PageMovable(page)) &&
+			/* Isolation code will deal with any races. */
+			if (unlikely(page_has_movable_ops(page)) &&
 					!PageIsolated(page)) {
 				if (locked) {
 					unlock_page_lruvec_irqrestore(locked, flags);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b91a33fb6c69..9e2cff199934 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -1388,8 +1388,8 @@ static inline bool HWPoisonHandlable(struct page *page, unsigned long flags)
 	if (PageSlab(page))
 		return false;
 
-	/* Soft offline could migrate non-LRU movable pages */
-	if ((flags & MF_SOFT_OFFLINE) && __PageMovable(page))
+	/* Soft offline could migrate movable_ops pages */
+	if ((flags & MF_SOFT_OFFLINE) && page_has_movable_ops(page))
 		return true;
 
 	return PageLRU(page) || is_free_buddy_page(page);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index e4009a44f883..1f15af712bc3 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1739,8 +1739,8 @@ bool mhp_range_allowed(u64 start, u64 size, bool need_mapping)
 
 #ifdef CONFIG_MEMORY_HOTREMOVE
 /*
- * Scan pfn range [start,end) to find movable/migratable pages (LRU pages,
- * non-lru movable pages and hugepages). Will skip over most unmovable
+ * Scan pfn range [start,end) to find movable/migratable pages (LRU and
+ * hugetlb folio, movable_ops pages). Will skip over most unmovable
  * pages (esp., pages that can be skipped when offlining), but bail out on
  * definitely unmovable pages.
  *
@@ -1759,13 +1759,11 @@ static int scan_movable_pages(unsigned long start, unsigned long end,
 		struct folio *folio;
 
 		page = pfn_to_page(pfn);
-		if (PageLRU(page))
-			goto found;
-		if (__PageMovable(page))
+		if (PageLRU(page) || page_has_movable_ops(page))
 			goto found;
 
 		/*
-		 * PageOffline() pages that are not marked __PageMovable() and
+		 * PageOffline() pages that do not have movable_ops and
 		 * have a reference count > 0 (after MEM_GOING_OFFLINE) are
 		 * definitely unmovable. If their reference count would be 0,
 		 * they could at least be skipped when offlining memory.
diff --git a/mm/migrate.c b/mm/migrate.c
index 1f07c8f1fb74..bf9cfdafc54c 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -94,7 +94,7 @@ bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
 	 * Note that once a page has movable_ops, it will stay that way
 	 * until the page was freed.
 	 */
-	if (unlikely(!__PageMovable(page)))
+	if (unlikely(!page_has_movable_ops(page)))
 		goto out_putfolio;
 
 	/*
@@ -111,7 +111,7 @@ bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
 	if (unlikely(!folio_trylock(folio)))
 		goto out_putfolio;
 
-	VM_WARN_ON_ONCE_PAGE(!__PageMovable(page), page);
+	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
 	if (PageIsolated(page))
 		goto out_no_isolated;
 
@@ -153,7 +153,7 @@ static void putback_movable_ops_page(struct page *page)
 	 */
 	struct folio *folio = page_folio(page);
 
-	VM_WARN_ON_ONCE_PAGE(!__PageMovable(page), page);
+	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
 	VM_WARN_ON_ONCE_PAGE(!PageIsolated(page), page);
 	folio_lock(folio);
 	page_movable_ops(page)->putback_page(page);
@@ -194,7 +194,7 @@ static int migrate_movable_ops_page(struct page *dst, struct page *src,
 {
 	int rc = MIGRATEPAGE_SUCCESS;
 
-	VM_WARN_ON_ONCE_PAGE(!__PageMovable(src), src);
+	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(src), src);
 	VM_WARN_ON_ONCE_PAGE(!PageIsolated(src), src);
 	rc = page_movable_ops(src)->migrate_page(dst, src, mode);
 	if (rc == MIGRATEPAGE_SUCCESS)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 6318c85d678e..036d9b7b01c0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2006,7 +2006,7 @@ static bool prep_move_freepages_block(struct zone *zone, struct page *page,
 			 * migration are movable. But we don't actually try
 			 * isolating, as that would be expensive.
 			 */
-			if (PageLRU(page) || __PageMovable(page))
+			if (PageLRU(page) || page_has_movable_ops(page))
 				(*num_movable)++;
 			pfn++;
 		}
diff --git a/mm/page_isolation.c b/mm/page_isolation.c
index ece3bfc56bcd..b97b965b3ed0 100644
--- a/mm/page_isolation.c
+++ b/mm/page_isolation.c
@@ -21,9 +21,9 @@
  * consequently belong to a single zone.
  *
  * PageLRU check without isolation or lru_lock could race so that
- * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable
- * check without lock_page also may miss some movable non-lru pages at
- * race condition. So you can't expect this function should be exact.
+ * MIGRATE_MOVABLE block might include unmovable pages. Similarly, pages
+ * with movable_ops can only be identified some time after they were
+ * allocated. So you can't expect this function should be exact.
  *
  * Returns a page without holding a reference. If the caller wants to
  * dereference that page (e.g., dumping), it has to make sure that it
@@ -133,7 +133,7 @@ static struct page *has_unmovable_pages(unsigned long start_pfn, unsigned long e
 		if ((mode == PB_ISOLATE_MODE_MEM_OFFLINE) && PageOffline(page))
 			continue;
 
-		if (__PageMovable(page) || PageLRU(page))
+		if (PageLRU(page) || page_has_movable_ops(page))
 			continue;
 
 		/*
@@ -421,7 +421,7 @@ static int isolate_single_pageblock(unsigned long boundary_pfn,
 			 * proper free and split handling for them.
 			 */
 			VM_WARN_ON_ONCE_PAGE(PageLRU(page), page);
-			VM_WARN_ON_ONCE_PAGE(__PageMovable(page), page);
+			VM_WARN_ON_ONCE_PAGE(page_has_movable_ops(page), page);
 
 			goto failed;
 		}
-- 
cgit v1.2.3


From 457d7b3adb11576ce5f3ae0d9a4987ace213bed2 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:12 +0200
Subject: mm: remove __folio_test_movable()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Convert to page_has_movable_ops().  While at it, cleanup relevant code a
bit.

The data_race() in migrate_folio_unmap() is questionable: we already hold
a page reference, and concurrent modifications can no longer happen (iow:
__ClearPageMovable() no longer exists).  Drop it for now, we'll rework
page_has_movable_ops() soon either way to no longer rely on page->mapping.

Wherever we cast from folio to page now is a clear sign that this code has
to be decoupled.

Link: https://lkml.kernel.org/r/20250704102524.326966-19-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h |  6 ------
 mm/migrate.c               | 43 +++++++++++++------------------------------
 mm/vmscan.c                |  6 ++++--
 3 files changed, 17 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index c67163b73c5e..4c27ebb689e3 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -744,12 +744,6 @@ static __always_inline bool PageAnon(const struct page *page)
 	return folio_test_anon(page_folio(page));
 }
 
-static __always_inline bool __folio_test_movable(const struct folio *folio)
-{
-	return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) ==
-			PAGE_MAPPING_MOVABLE;
-}
-
 static __always_inline bool page_has_movable_ops(const struct page *page)
 {
 	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
diff --git a/mm/migrate.c b/mm/migrate.c
index bf9cfdafc54c..aec0774d3da3 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -221,12 +221,7 @@ void putback_movable_pages(struct list_head *l)
 			continue;
 		}
 		list_del(&folio->lru);
-		/*
-		 * We isolated non-lru movable folio so here we can use
-		 * __folio_test_movable because LRU folio's mapping cannot
-		 * have PAGE_MAPPING_MOVABLE.
-		 */
-		if (unlikely(__folio_test_movable(folio))) {
+		if (unlikely(page_has_movable_ops(&folio->page))) {
 			putback_movable_ops_page(&folio->page);
 		} else {
 			node_stat_mod_folio(folio, NR_ISOLATED_ANON +
@@ -239,26 +234,20 @@ void putback_movable_pages(struct list_head *l)
 /* Must be called with an elevated refcount on the non-hugetlb folio */
 bool isolate_folio_to_list(struct folio *folio, struct list_head *list)
 {
-	bool isolated, lru;
-
 	if (folio_test_hugetlb(folio))
 		return folio_isolate_hugetlb(folio, list);
 
-	lru = !__folio_test_movable(folio);
-	if (lru)
-		isolated = folio_isolate_lru(folio);
-	else
-		isolated = isolate_movable_ops_page(&folio->page,
-						    ISOLATE_UNEVICTABLE);
-
-	if (!isolated)
-		return false;
-
-	list_add(&folio->lru, list);
-	if (lru)
+	if (page_has_movable_ops(&folio->page)) {
+		if (!isolate_movable_ops_page(&folio->page,
+					      ISOLATE_UNEVICTABLE))
+			return false;
+	} else {
+		if (!folio_isolate_lru(folio))
+			return false;
 		node_stat_add_folio(folio, NR_ISOLATED_ANON +
 				    folio_is_file_lru(folio));
-
+	}
+	list_add(&folio->lru, list);
 	return true;
 }
 
@@ -1142,12 +1131,7 @@ static void migrate_folio_undo_dst(struct folio *dst, bool locked,
 static void migrate_folio_done(struct folio *src,
 			       enum migrate_reason reason)
 {
-	/*
-	 * Compaction can migrate also non-LRU pages which are
-	 * not accounted to NR_ISOLATED_*. They can be recognized
-	 * as __folio_test_movable
-	 */
-	if (likely(!__folio_test_movable(src)) && reason != MR_DEMOTION)
+	if (likely(!page_has_movable_ops(&src->page)) && reason != MR_DEMOTION)
 		mod_node_page_state(folio_pgdat(src), NR_ISOLATED_ANON +
 				    folio_is_file_lru(src), -folio_nr_pages(src));
 
@@ -1166,7 +1150,6 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
 	int rc = -EAGAIN;
 	int old_page_state = 0;
 	struct anon_vma *anon_vma = NULL;
-	bool is_lru = data_race(!__folio_test_movable(src));
 	bool locked = false;
 	bool dst_locked = false;
 
@@ -1267,7 +1250,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
 		goto out;
 	dst_locked = true;
 
-	if (unlikely(!is_lru)) {
+	if (unlikely(page_has_movable_ops(&src->page))) {
 		__migrate_folio_record(dst, old_page_state, anon_vma);
 		return MIGRATEPAGE_UNMAP;
 	}
@@ -1332,7 +1315,7 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
 	prev = dst->lru.prev;
 	list_del(&dst->lru);
 
-	if (unlikely(__folio_test_movable(src))) {
+	if (unlikely(page_has_movable_ops(&src->page))) {
 		rc = migrate_movable_ops_page(&dst->page, &src->page, mode);
 		if (rc)
 			goto out;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c86a2495138a..b1b999734ee4 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1651,9 +1651,11 @@ unsigned int reclaim_clean_pages_from_list(struct zone *zone,
 	unsigned int noreclaim_flag;
 
 	list_for_each_entry_safe(folio, next, folio_list, lru) {
+		/* TODO: these pages should not even appear in this list. */
+		if (page_has_movable_ops(&folio->page))
+			continue;
 		if (!folio_test_hugetlb(folio) && folio_is_file_lru(folio) &&
-		    !folio_test_dirty(folio) && !__folio_test_movable(folio) &&
-		    !folio_test_unevictable(folio)) {
+		    !folio_test_dirty(folio) && !folio_test_unevictable(folio)) {
 			folio_clear_active(folio);
 			list_move(&folio->lru, &clean_folios);
 		}
-- 
cgit v1.2.3


From 84caf98838a3e5f4bdb344c13679e1067ffbf094 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:13 +0200
Subject: mm: stop storing migration_ops in page->mapping
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

...  instead, look them up statically based on the page type.  Maybe in
the future we want a registration interface?  At least for now, it can be
easily handled using the two page types that actually support page
migration.

The remaining usage of page->mapping is to flag such pages as actually
being movable (having movable_ops), which we will change next.

Link: https://lkml.kernel.org/r/20250704102524.326966-20-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/balloon_compaction.h |  2 +-
 include/linux/migrate.h            | 14 ++------------
 include/linux/zsmalloc.h           |  2 ++
 mm/balloon_compaction.c            |  1 -
 mm/compaction.c                    |  5 ++---
 mm/migrate.c                       | 23 +++++++++++++++++++++++
 mm/zpdesc.h                        |  5 ++---
 mm/zsmalloc.c                      |  8 +++-----
 8 files changed, 35 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index 9bce8e9f5018..a8a1706cc56f 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -92,7 +92,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 				       struct page *page)
 {
 	__SetPageOffline(page);
-	__SetPageMovable(page, &balloon_mops);
+	__SetPageMovable(page);
 	set_page_private(page, (unsigned long)balloon);
 	list_add(&page->lru, &balloon->pages);
 }
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index e04035f70e36..6aece3f3c8be 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -104,23 +104,13 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 #endif /* CONFIG_MIGRATION */
 
 #ifdef CONFIG_COMPACTION
-void __SetPageMovable(struct page *page, const struct movable_operations *ops);
+void __SetPageMovable(struct page *page);
 #else
-static inline void __SetPageMovable(struct page *page,
-		const struct movable_operations *ops)
+static inline void __SetPageMovable(struct page *page)
 {
 }
 #endif
 
-static inline
-const struct movable_operations *page_movable_ops(struct page *page)
-{
-	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
-
-	return (const struct movable_operations *)
-		((unsigned long)page->mapping - PAGE_MAPPING_MOVABLE);
-}
-
 #ifdef CONFIG_NUMA_BALANCING
 int migrate_misplaced_folio_prepare(struct folio *folio,
 		struct vm_area_struct *vma, int node);
diff --git a/include/linux/zsmalloc.h b/include/linux/zsmalloc.h
index 13e9cc5490f7..f3ccff2d966c 100644
--- a/include/linux/zsmalloc.h
+++ b/include/linux/zsmalloc.h
@@ -46,4 +46,6 @@ void zs_obj_read_end(struct zs_pool *pool, unsigned long handle,
 void zs_obj_write(struct zs_pool *pool, unsigned long handle,
 		  void *handle_mem, size_t mem_len);
 
+extern const struct movable_operations zsmalloc_mops;
+
 #endif
diff --git a/mm/balloon_compaction.c b/mm/balloon_compaction.c
index e4f1a122d786..2a4a649805c1 100644
--- a/mm/balloon_compaction.c
+++ b/mm/balloon_compaction.c
@@ -253,6 +253,5 @@ const struct movable_operations balloon_mops = {
 	.isolate_page = balloon_page_isolate,
 	.putback_page = balloon_page_putback,
 };
-EXPORT_SYMBOL_GPL(balloon_mops);
 
 #endif /* CONFIG_BALLOON_COMPACTION */
diff --git a/mm/compaction.c b/mm/compaction.c
index 41fd6a1fe9a3..348eb754cb22 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -114,11 +114,10 @@ static unsigned long release_free_list(struct list_head *freepages)
 }
 
 #ifdef CONFIG_COMPACTION
-void __SetPageMovable(struct page *page, const struct movable_operations *mops)
+void __SetPageMovable(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	VM_BUG_ON_PAGE((unsigned long)mops & PAGE_MAPPING_MOVABLE, page);
-	page->mapping = (void *)((unsigned long)mops | PAGE_MAPPING_MOVABLE);
+	page->mapping = (void *)(PAGE_MAPPING_MOVABLE);
 }
 EXPORT_SYMBOL(__SetPageMovable);
 
diff --git a/mm/migrate.c b/mm/migrate.c
index aec0774d3da3..90ddf906d706 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -43,6 +43,8 @@
 #include <linux/sched/sysctl.h>
 #include <linux/memory-tiers.h>
 #include <linux/pagewalk.h>
+#include <linux/balloon_compaction.h>
+#include <linux/zsmalloc.h>
 
 #include <asm/tlbflush.h>
 
@@ -51,6 +53,27 @@
 #include "internal.h"
 #include "swap.h"
 
+static const struct movable_operations *page_movable_ops(struct page *page)
+{
+	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
+
+	/*
+	 * If we enable page migration for a page of a certain type by marking
+	 * it as movable, the page type must be sticky until the page gets freed
+	 * back to the buddy.
+	 */
+#ifdef CONFIG_BALLOON_COMPACTION
+	if (PageOffline(page))
+		/* Only balloon compaction sets PageOffline pages movable. */
+		return &balloon_mops;
+#endif /* CONFIG_BALLOON_COMPACTION */
+#if defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION)
+	if (PageZsmalloc(page))
+		return &zsmalloc_mops;
+#endif /* defined(CONFIG_ZSMALLOC) && defined(CONFIG_COMPACTION) */
+	return NULL;
+}
+
 /**
  * isolate_movable_ops_page - isolate a movable_ops page for migration
  * @page: The page.
diff --git a/mm/zpdesc.h b/mm/zpdesc.h
index 5763f3603973..6855d9e2732d 100644
--- a/mm/zpdesc.h
+++ b/mm/zpdesc.h
@@ -152,10 +152,9 @@ static inline struct zpdesc *pfn_zpdesc(unsigned long pfn)
 	return page_zpdesc(pfn_to_page(pfn));
 }
 
-static inline void __zpdesc_set_movable(struct zpdesc *zpdesc,
-					const struct movable_operations *mops)
+static inline void __zpdesc_set_movable(struct zpdesc *zpdesc)
 {
-	__SetPageMovable(zpdesc_page(zpdesc), mops);
+	__SetPageMovable(zpdesc_page(zpdesc));
 }
 
 static inline void __zpdesc_set_zsmalloc(struct zpdesc *zpdesc)
diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c
index b12250e219bb..4aaff7c26ea9 100644
--- a/mm/zsmalloc.c
+++ b/mm/zsmalloc.c
@@ -1685,8 +1685,6 @@ static void lock_zspage(struct zspage *zspage)
 
 #ifdef CONFIG_COMPACTION
 
-static const struct movable_operations zsmalloc_mops;
-
 static void replace_sub_page(struct size_class *class, struct zspage *zspage,
 				struct zpdesc *newzpdesc, struct zpdesc *oldzpdesc)
 {
@@ -1709,7 +1707,7 @@ static void replace_sub_page(struct size_class *class, struct zspage *zspage,
 	set_first_obj_offset(newzpdesc, first_obj_offset);
 	if (unlikely(ZsHugePage(zspage)))
 		newzpdesc->handle = oldzpdesc->handle;
-	__zpdesc_set_movable(newzpdesc, &zsmalloc_mops);
+	__zpdesc_set_movable(newzpdesc);
 }
 
 static bool zs_page_isolate(struct page *page, isolate_mode_t mode)
@@ -1819,7 +1817,7 @@ static void zs_page_putback(struct page *page)
 {
 }
 
-static const struct movable_operations zsmalloc_mops = {
+const struct movable_operations zsmalloc_mops = {
 	.isolate_page = zs_page_isolate,
 	.migrate_page = zs_page_migrate,
 	.putback_page = zs_page_putback,
@@ -1882,7 +1880,7 @@ static void SetZsPageMovable(struct zs_pool *pool, struct zspage *zspage)
 
 	do {
 		WARN_ON(!zpdesc_trylock(zpdesc));
-		__zpdesc_set_movable(zpdesc, &zsmalloc_mops);
+		__zpdesc_set_movable(zpdesc);
 		zpdesc_unlock(zpdesc);
 	} while ((zpdesc = get_next_zpdesc(zpdesc)) != NULL);
 }
-- 
cgit v1.2.3


From 3d388584d59985e95f5bfb9dbd9776fa1bb1ec8a Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:14 +0200
Subject: mm: convert "movable" flag in page->mapping to a page flag
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Instead, let's use a page flag.  As the page flag can result in
false-positives, glue it to the page types for which we support/implement
movable_ops page migration.

We are reusing PG_uptodate, that is for example used to track file system
state and does not apply to movable_ops pages.  So warning in case it is
set in page_has_movable_ops() on other page types could result in
false-positive warnings.

Likely we could set the bit using a non-atomic update: in contrast to
page->mapping, we could have others trying to update the flags
concurrently when trying to lock the folio.  In
isolate_movable_ops_page(), we already take care of that by checking if
the page has movable_ops before locking it.  Let's start with the atomic
variant, we could later switch to the non-atomic variant once we are sure
other cases are similarly fine.  Once we perform the switch, we'll have to
introduce __SETPAGEFLAG_NOOP().

[david@redhat.com: add missing `:' in kerneldoc]
  Link: https://lkml.kernel.org/r/d96e2916-2c43-462c-b6a1-2375ef397d8b@redhat.com
Link: https://lkml.kernel.org/r/20250704102524.326966-21-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/balloon_compaction.h |  2 +-
 include/linux/migrate.h            |  8 ------
 include/linux/page-flags.h         | 54 +++++++++++++++++++++++++++++++-------
 mm/compaction.c                    |  6 -----
 mm/zpdesc.h                        |  2 +-
 5 files changed, 46 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index a8a1706cc56f..b222b0737c46 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -92,7 +92,7 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 				       struct page *page)
 {
 	__SetPageOffline(page);
-	__SetPageMovable(page);
+	SetPageMovableOps(page);
 	set_page_private(page, (unsigned long)balloon);
 	list_add(&page->lru, &balloon->pages);
 }
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
index 6aece3f3c8be..acadd41e0b5c 100644
--- a/include/linux/migrate.h
+++ b/include/linux/migrate.h
@@ -103,14 +103,6 @@ static inline int migrate_huge_page_move_mapping(struct address_space *mapping,
 
 #endif /* CONFIG_MIGRATION */
 
-#ifdef CONFIG_COMPACTION
-void __SetPageMovable(struct page *page);
-#else
-static inline void __SetPageMovable(struct page *page)
-{
-}
-#endif
-
 #ifdef CONFIG_NUMA_BALANCING
 int migrate_misplaced_folio_prepare(struct folio *folio,
 		struct vm_area_struct *vma, int node);
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 4c27ebb689e3..a02a12e51915 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -170,6 +170,11 @@ enum pageflags {
 	/* non-lru isolated movable page */
 	PG_isolated = PG_reclaim,
 
+#ifdef CONFIG_MIGRATION
+	/* this is a movable_ops page (for selected typed pages only) */
+	PG_movable_ops = PG_uptodate,
+#endif
+
 	/* Only valid for buddy pages. Used to track pages that are reported */
 	PG_reported = PG_uptodate,
 
@@ -698,9 +703,6 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
  * bit; and then folio->mapping points, not to an anon_vma, but to a private
  * structure which KSM associates with that merged page.  See ksm.h.
  *
- * PAGE_MAPPING_KSM without PAGE_MAPPING_ANON is used for non-lru movable
- * page and then folio->mapping points to a struct movable_operations.
- *
  * Please note that, confusingly, "folio_mapping" refers to the inode
  * address_space which maps the folio from disk; whereas "folio_mapped"
  * refers to user virtual address space into which the folio is mapped.
@@ -743,13 +745,6 @@ static __always_inline bool PageAnon(const struct page *page)
 {
 	return folio_test_anon(page_folio(page));
 }
-
-static __always_inline bool page_has_movable_ops(const struct page *page)
-{
-	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) ==
-				PAGE_MAPPING_MOVABLE;
-}
-
 #ifdef CONFIG_KSM
 /*
  * A KSM page is one of those write-protected "shared pages" or "merged pages"
@@ -1133,6 +1128,45 @@ bool is_free_buddy_page(const struct page *page);
 
 PAGEFLAG(Isolated, isolated, PF_ANY);
 
+#ifdef CONFIG_MIGRATION
+/*
+ * This page is migratable through movable_ops (for selected typed pages
+ * only).
+ *
+ * Page migration of such pages might fail, for example, if the page is
+ * already isolated by somebody else, or if the page is about to get freed.
+ *
+ * While a subsystem might set selected typed pages that support page migration
+ * as being movable through movable_ops, it must never clear this flag.
+ *
+ * This flag is only cleared when the page is freed back to the buddy.
+ *
+ * Only selected page types support this flag (see page_movable_ops()) and
+ * the flag might be used in other context for other pages. Always use
+ * page_has_movable_ops() instead.
+ */
+TESTPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL);
+SETPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL);
+#else /* !CONFIG_MIGRATION */
+TESTPAGEFLAG_FALSE(MovableOps, movable_ops);
+SETPAGEFLAG_NOOP(MovableOps, movable_ops);
+#endif /* CONFIG_MIGRATION */
+
+/**
+ * page_has_movable_ops - test for a movable_ops page
+ * @page: The page to test.
+ *
+ * Test whether this is a movable_ops page. Such pages will stay that
+ * way until freed.
+ *
+ * Returns true if this is a movable_ops page, otherwise false.
+ */
+static inline bool page_has_movable_ops(const struct page *page)
+{
+	return PageMovableOps(page) &&
+	       (PageOffline(page) || PageZsmalloc(page));
+}
+
 static __always_inline int PageAnonExclusive(const struct page *page)
 {
 	VM_BUG_ON_PGFLAGS(!PageAnon(page), page);
diff --git a/mm/compaction.c b/mm/compaction.c
index 348eb754cb22..349f4ea0ec3e 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -114,12 +114,6 @@ static unsigned long release_free_list(struct list_head *freepages)
 }
 
 #ifdef CONFIG_COMPACTION
-void __SetPageMovable(struct page *page)
-{
-	VM_BUG_ON_PAGE(!PageLocked(page), page);
-	page->mapping = (void *)(PAGE_MAPPING_MOVABLE);
-}
-EXPORT_SYMBOL(__SetPageMovable);
 
 /* Do not skip compaction more than 64 times */
 #define COMPACT_MAX_DEFER_SHIFT 6
diff --git a/mm/zpdesc.h b/mm/zpdesc.h
index 6855d9e2732d..25bf5ea0beb8 100644
--- a/mm/zpdesc.h
+++ b/mm/zpdesc.h
@@ -154,7 +154,7 @@ static inline struct zpdesc *pfn_zpdesc(unsigned long pfn)
 
 static inline void __zpdesc_set_movable(struct zpdesc *zpdesc)
 {
-	__SetPageMovable(zpdesc_page(zpdesc));
+	SetPageMovableOps(zpdesc_page(zpdesc));
 }
 
 static inline void __zpdesc_set_zsmalloc(struct zpdesc *zpdesc)
-- 
cgit v1.2.3


From 92f091769fde42509ca7685e67c9951f2350ceb7 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:15 +0200
Subject: mm: rename PG_isolated to PG_movable_ops_isolated
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's rename the flag to make it clearer where it applies (not folios
...).

While at it, define the flag only with CONFIG_MIGRATION.

Link: https://lkml.kernel.org/r/20250704102524.326966-22-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 16 +++++++++++-----
 mm/compaction.c            |  2 +-
 mm/migrate.c               | 14 +++++++-------
 3 files changed, 19 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a02a12e51915..92f7152a445e 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -167,10 +167,9 @@ enum pageflags {
 	/* Remapped by swiotlb-xen. */
 	PG_xen_remapped = PG_owner_priv_1,
 
-	/* non-lru isolated movable page */
-	PG_isolated = PG_reclaim,
-
 #ifdef CONFIG_MIGRATION
+	/* movable_ops page that is isolated for migration */
+	PG_movable_ops_isolated = PG_reclaim,
 	/* this is a movable_ops page (for selected typed pages only) */
 	PG_movable_ops = PG_uptodate,
 #endif
@@ -1126,8 +1125,6 @@ static inline bool folio_contain_hwpoisoned_page(struct folio *folio)
 
 bool is_free_buddy_page(const struct page *page);
 
-PAGEFLAG(Isolated, isolated, PF_ANY);
-
 #ifdef CONFIG_MIGRATION
 /*
  * This page is migratable through movable_ops (for selected typed pages
@@ -1147,9 +1144,18 @@ PAGEFLAG(Isolated, isolated, PF_ANY);
  */
 TESTPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL);
 SETPAGEFLAG(MovableOps, movable_ops, PF_NO_TAIL);
+/*
+ * A movable_ops page has this flag set while it is isolated for migration.
+ * This flag primarily protects against concurrent migration attempts.
+ *
+ * Once migration ended (success or failure), the flag is cleared. The
+ * flag is managed by the migration core.
+ */
+PAGEFLAG(MovableOpsIsolated, movable_ops_isolated, PF_NO_TAIL);
 #else /* !CONFIG_MIGRATION */
 TESTPAGEFLAG_FALSE(MovableOps, movable_ops);
 SETPAGEFLAG_NOOP(MovableOps, movable_ops);
+PAGEFLAG_FALSE(MovableOpsIsolated, movable_ops_isolated);
 #endif /* CONFIG_MIGRATION */
 
 /**
diff --git a/mm/compaction.c b/mm/compaction.c
index 349f4ea0ec3e..bf021b31c7ec 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1051,7 +1051,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
 		if (!PageLRU(page)) {
 			/* Isolation code will deal with any races. */
 			if (unlikely(page_has_movable_ops(page)) &&
-					!PageIsolated(page)) {
+			    !PageMovableOpsIsolated(page)) {
 				if (locked) {
 					unlock_page_lruvec_irqrestore(locked, flags);
 					locked = NULL;
diff --git a/mm/migrate.c b/mm/migrate.c
index 90ddf906d706..e4e05a98c84e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -135,7 +135,7 @@ bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
 		goto out_putfolio;
 
 	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
-	if (PageIsolated(page))
+	if (PageMovableOpsIsolated(page))
 		goto out_no_isolated;
 
 	mops = page_movable_ops(page);
@@ -146,8 +146,8 @@ bool isolate_movable_ops_page(struct page *page, isolate_mode_t mode)
 		goto out_no_isolated;
 
 	/* Driver shouldn't use the isolated flag */
-	VM_WARN_ON_ONCE_PAGE(PageIsolated(page), page);
-	SetPageIsolated(page);
+	VM_WARN_ON_ONCE_PAGE(PageMovableOpsIsolated(page), page);
+	SetPageMovableOpsIsolated(page);
 	folio_unlock(folio);
 
 	return true;
@@ -177,10 +177,10 @@ static void putback_movable_ops_page(struct page *page)
 	struct folio *folio = page_folio(page);
 
 	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(page), page);
-	VM_WARN_ON_ONCE_PAGE(!PageIsolated(page), page);
+	VM_WARN_ON_ONCE_PAGE(!PageMovableOpsIsolated(page), page);
 	folio_lock(folio);
 	page_movable_ops(page)->putback_page(page);
-	ClearPageIsolated(page);
+	ClearPageMovableOpsIsolated(page);
 	folio_unlock(folio);
 	folio_put(folio);
 }
@@ -218,10 +218,10 @@ static int migrate_movable_ops_page(struct page *dst, struct page *src,
 	int rc = MIGRATEPAGE_SUCCESS;
 
 	VM_WARN_ON_ONCE_PAGE(!page_has_movable_ops(src), src);
-	VM_WARN_ON_ONCE_PAGE(!PageIsolated(src), src);
+	VM_WARN_ON_ONCE_PAGE(!PageMovableOpsIsolated(src), src);
 	rc = page_movable_ops(src)->migrate_page(dst, src, mode);
 	if (rc == MIGRATEPAGE_SUCCESS)
-		ClearPageIsolated(src);
+		ClearPageMovableOpsIsolated(src);
 	return rc;
 }
 
-- 
cgit v1.2.3


From bd56d30242039826160d95a65cb14c1cd65e6488 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:16 +0200
Subject: mm/page-flags: rename PAGE_MAPPING_MOVABLE to PAGE_MAPPING_ANON_KSM
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

KSM is the only remaining user, let's rename the flag.  While at it,
adjust to remaining page -> folio in the doc.

Link: https://lkml.kernel.org/r/20250704102524.326966-23-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 92f7152a445e..22767499fb21 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -697,10 +697,10 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
  * folio->mapping points to its anon_vma, not to a struct address_space;
  * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
  *
- * On an anonymous page in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
- * the PAGE_MAPPING_MOVABLE bit may be set along with the PAGE_MAPPING_ANON
+ * On an anonymous folio in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
+ * the PAGE_MAPPING_ANON_KSM bit may be set along with the PAGE_MAPPING_ANON
  * bit; and then folio->mapping points, not to an anon_vma, but to a private
- * structure which KSM associates with that merged page.  See ksm.h.
+ * structure which KSM associates with that merged folio.  See ksm.h.
  *
  * Please note that, confusingly, "folio_mapping" refers to the inode
  * address_space which maps the folio from disk; whereas "folio_mapped"
@@ -714,9 +714,9 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
  * See mm/slab.h.
  */
 #define PAGE_MAPPING_ANON	0x1
-#define PAGE_MAPPING_MOVABLE	0x2
-#define PAGE_MAPPING_KSM	(PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
-#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_MOVABLE)
+#define PAGE_MAPPING_ANON_KSM	0x2
+#define PAGE_MAPPING_KSM	(PAGE_MAPPING_ANON | PAGE_MAPPING_ANON_KSM)
+#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_ANON_KSM)
 
 static __always_inline bool folio_mapping_flags(const struct folio *folio)
 {
-- 
cgit v1.2.3


From 5799c0ed0aff65989b04ca3f517401e4ee94da10 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:17 +0200
Subject: mm/page-alloc: remove PageMappingFlags()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

As PageMappingFlags() now only indicates anon (incl.  KSM) folios, we can
now simply check for PageAnon() and remove PageMappingFlags().

...  and while at it, use the folio instead and operate on folio->mapping.

Link: https://lkml.kernel.org/r/20250704102524.326966-24-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 5 -----
 mm/page_alloc.c            | 7 +++----
 2 files changed, 3 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 22767499fb21..a2151f6d96ae 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -723,11 +723,6 @@ static __always_inline bool folio_mapping_flags(const struct folio *folio)
 	return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0;
 }
 
-static __always_inline bool PageMappingFlags(const struct page *page)
-{
-	return ((unsigned long)page->mapping & PAGE_MAPPING_FLAGS) != 0;
-}
-
 static __always_inline bool folio_test_anon(const struct folio *folio)
 {
 	return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 036d9b7b01c0..fa09154a799c 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1375,10 +1375,9 @@ __always_inline bool free_pages_prepare(struct page *page,
 			(page + i)->flags &= ~PAGE_FLAGS_CHECK_AT_PREP;
 		}
 	}
-	if (PageMappingFlags(page)) {
-		if (PageAnon(page))
-			mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1);
-		page->mapping = NULL;
+	if (folio_test_anon(folio)) {
+		mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1);
+		folio->mapping = NULL;
 	}
 	if (unlikely(page_has_type(page)))
 		/* Reset the page_type (which overlays _mapcount) */
-- 
cgit v1.2.3


From beb2cdeed673150cdfad653dd2e7c9999c230f57 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:18 +0200
Subject: mm/page-flags: remove folio_mapping_flags()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

It's unused and the page counterpart is gone, so let's remove it.

Link: https://lkml.kernel.org/r/20250704102524.326966-25-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index a2151f6d96ae..ae2b80fcea6a 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -718,11 +718,6 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
 #define PAGE_MAPPING_KSM	(PAGE_MAPPING_ANON | PAGE_MAPPING_ANON_KSM)
 #define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_ANON_KSM)
 
-static __always_inline bool folio_mapping_flags(const struct folio *folio)
-{
-	return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) != 0;
-}
-
 static __always_inline bool folio_test_anon(const struct folio *folio)
 {
 	return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0;
-- 
cgit v1.2.3


From 78cb1a13c42a6d843e21389f74d1edb90ed07288 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:19 +0200
Subject: mm: simplify folio_expected_ref_count()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that PAGE_MAPPING_MOVABLE is gone, we can simplify and rely on the
folio_test_anon() test only.

... but staring at the users, this function should never even have been
called on movable_ops pages. E.g.,
* __buffer_migrate_folio() does not make sense for them
* folio_migrate_mapping() does not make sense for them
* migrate_huge_page_move_mapping() does not make sense for them
* __migrate_folio() does not make sense for them
* ... and khugepaged should never stumble over them

Let's simply refuse typed pages (which includes slab) except hugetlb, and
WARN.

Link: https://lkml.kernel.org/r/20250704102524.326966-26-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index ef40f68c1183..805108d7bbc3 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2167,13 +2167,13 @@ static inline int folio_expected_ref_count(const struct folio *folio)
 	const int order = folio_order(folio);
 	int ref_count = 0;
 
-	if (WARN_ON_ONCE(folio_test_slab(folio)))
+	if (WARN_ON_ONCE(page_has_type(&folio->page) && !folio_test_hugetlb(folio)))
 		return 0;
 
 	if (folio_test_anon(folio)) {
 		/* One reference per page from the swapcache. */
 		ref_count += folio_test_swapcache(folio) << order;
-	} else if (!((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS)) {
+	} else {
 		/* One reference per page from the pagecache. */
 		ref_count += !!folio->mapping << order;
 		/* One reference from PG_private. */
-- 
cgit v1.2.3


From df25569d401e36327b339c3f5b3265d74eae90f2 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:20 +0200
Subject: mm: rename PAGE_MAPPING_* to FOLIO_MAPPING_*
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Now that the mapping flags are only used for folios, let's rename the
defines.

Link: https://lkml.kernel.org/r/20250704102524.326966-27-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/page.c             |  4 ++--
 include/linux/fs.h         |  2 +-
 include/linux/mm_types.h   |  1 -
 include/linux/page-flags.h | 20 ++++++++++----------
 include/linux/pagemap.h    |  2 +-
 mm/gup.c                   |  4 ++--
 mm/internal.h              |  2 +-
 mm/ksm.c                   |  4 ++--
 mm/rmap.c                  | 16 ++++++++--------
 mm/util.c                  |  6 +++---
 10 files changed, 30 insertions(+), 31 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/page.c b/fs/proc/page.c
index 999af26c7298..0cdc78c0d23f 100644
--- a/fs/proc/page.c
+++ b/fs/proc/page.c
@@ -149,7 +149,7 @@ u64 stable_page_flags(const struct page *page)
 
 	k = folio->flags;
 	mapping = (unsigned long)folio->mapping;
-	is_anon = mapping & PAGE_MAPPING_ANON;
+	is_anon = mapping & FOLIO_MAPPING_ANON;
 
 	/*
 	 * pseudo flags for the well known (anonymous) memory mapped pages
@@ -158,7 +158,7 @@ u64 stable_page_flags(const struct page *page)
 		u |= 1 << KPF_MMAP;
 	if (is_anon) {
 		u |= 1 << KPF_ANON;
-		if (mapping & PAGE_MAPPING_KSM)
+		if (mapping & FOLIO_MAPPING_KSM)
 			u |= 1 << KPF_KSM;
 	}
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index e14e9d11ca0f..d3e7ad6941a8 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -526,7 +526,7 @@ struct address_space {
 	/*
 	 * On most architectures that alignment is already the case; but
 	 * must be enforced here for CRIS, to let the least significant bit
-	 * of struct page's "mapping" pointer be used for PAGE_MAPPING_ANON.
+	 * of struct folio's "mapping" pointer be used for FOLIO_MAPPING_ANON.
 	 */
 
 /* XArray tags, for tagging dirty and writeback pages in the pagecache. */
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 804d269a4f5e..1ec273b06691 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -105,7 +105,6 @@ struct page {
 					unsigned int order;
 				};
 			};
-			/* See page-flags.h for PAGE_MAPPING_FLAGS */
 			struct address_space *mapping;
 			union {
 				pgoff_t __folio_index;		/* Our offset within mapping. */
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index ae2b80fcea6a..8e4d6eda8a8d 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -695,10 +695,10 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
 /*
  * On an anonymous folio mapped into a user virtual memory area,
  * folio->mapping points to its anon_vma, not to a struct address_space;
- * with the PAGE_MAPPING_ANON bit set to distinguish it.  See rmap.h.
+ * with the FOLIO_MAPPING_ANON bit set to distinguish it.  See rmap.h.
  *
  * On an anonymous folio in a VM_MERGEABLE area, if CONFIG_KSM is enabled,
- * the PAGE_MAPPING_ANON_KSM bit may be set along with the PAGE_MAPPING_ANON
+ * the FOLIO_MAPPING_ANON_KSM bit may be set along with the FOLIO_MAPPING_ANON
  * bit; and then folio->mapping points, not to an anon_vma, but to a private
  * structure which KSM associates with that merged folio.  See ksm.h.
  *
@@ -713,21 +713,21 @@ PAGEFLAG_FALSE(VmemmapSelfHosted, vmemmap_self_hosted)
  * false before calling the following functions (e.g., folio_test_anon).
  * See mm/slab.h.
  */
-#define PAGE_MAPPING_ANON	0x1
-#define PAGE_MAPPING_ANON_KSM	0x2
-#define PAGE_MAPPING_KSM	(PAGE_MAPPING_ANON | PAGE_MAPPING_ANON_KSM)
-#define PAGE_MAPPING_FLAGS	(PAGE_MAPPING_ANON | PAGE_MAPPING_ANON_KSM)
+#define FOLIO_MAPPING_ANON	0x1
+#define FOLIO_MAPPING_ANON_KSM	0x2
+#define FOLIO_MAPPING_KSM	(FOLIO_MAPPING_ANON | FOLIO_MAPPING_ANON_KSM)
+#define FOLIO_MAPPING_FLAGS	(FOLIO_MAPPING_ANON | FOLIO_MAPPING_ANON_KSM)
 
 static __always_inline bool folio_test_anon(const struct folio *folio)
 {
-	return ((unsigned long)folio->mapping & PAGE_MAPPING_ANON) != 0;
+	return ((unsigned long)folio->mapping & FOLIO_MAPPING_ANON) != 0;
 }
 
 static __always_inline bool PageAnonNotKsm(const struct page *page)
 {
 	unsigned long flags = (unsigned long)page_folio(page)->mapping;
 
-	return (flags & PAGE_MAPPING_FLAGS) == PAGE_MAPPING_ANON;
+	return (flags & FOLIO_MAPPING_FLAGS) == FOLIO_MAPPING_ANON;
 }
 
 static __always_inline bool PageAnon(const struct page *page)
@@ -743,8 +743,8 @@ static __always_inline bool PageAnon(const struct page *page)
  */
 static __always_inline bool folio_test_ksm(const struct folio *folio)
 {
-	return ((unsigned long)folio->mapping & PAGE_MAPPING_FLAGS) ==
-				PAGE_MAPPING_KSM;
+	return ((unsigned long)folio->mapping & FOLIO_MAPPING_FLAGS) ==
+				FOLIO_MAPPING_KSM;
 }
 #else
 FOLIO_TEST_FLAG_FALSE(ksm)
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e63fbfbd5b0f..10a222e68b85 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -502,7 +502,7 @@ static inline pgoff_t mapping_align_index(struct address_space *mapping,
 static inline bool mapping_large_folio_support(struct address_space *mapping)
 {
 	/* AS_FOLIO_ORDER is only reasonable for pagecache folios */
-	VM_WARN_ONCE((unsigned long)mapping & PAGE_MAPPING_ANON,
+	VM_WARN_ONCE((unsigned long)mapping & FOLIO_MAPPING_ANON,
 			"Anonymous mapping always supports large folio");
 
 	return mapping_max_folio_order(mapping) > 0;
diff --git a/mm/gup.c b/mm/gup.c
index 30d320719fa2..adffe663594d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2804,9 +2804,9 @@ static bool gup_fast_folio_allowed(struct folio *folio, unsigned int flags)
 		return false;
 
 	/* Anonymous folios pose no problem. */
-	mapping_flags = (unsigned long)mapping & PAGE_MAPPING_FLAGS;
+	mapping_flags = (unsigned long)mapping & FOLIO_MAPPING_FLAGS;
 	if (mapping_flags)
-		return mapping_flags & PAGE_MAPPING_ANON;
+		return mapping_flags & FOLIO_MAPPING_ANON;
 
 	/*
 	 * At this point, we know the mapping is non-null and points to an
diff --git a/mm/internal.h b/mm/internal.h
index 22a95a2b7fa1..2e235740128a 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -149,7 +149,7 @@ static inline void *folio_raw_mapping(const struct folio *folio)
 {
 	unsigned long mapping = (unsigned long)folio->mapping;
 
-	return (void *)(mapping & ~PAGE_MAPPING_FLAGS);
+	return (void *)(mapping & ~FOLIO_MAPPING_FLAGS);
 }
 
 /*
diff --git a/mm/ksm.c b/mm/ksm.c
index ef73b25fd65a..2b0210d41c55 100644
--- a/mm/ksm.c
+++ b/mm/ksm.c
@@ -893,7 +893,7 @@ static struct folio *ksm_get_folio(struct ksm_stable_node *stable_node,
 	unsigned long kpfn;
 
 	expected_mapping = (void *)((unsigned long)stable_node |
-					PAGE_MAPPING_KSM);
+					FOLIO_MAPPING_KSM);
 again:
 	kpfn = READ_ONCE(stable_node->kpfn); /* Address dependency. */
 	folio = pfn_folio(kpfn);
@@ -1070,7 +1070,7 @@ static inline void folio_set_stable_node(struct folio *folio,
 					 struct ksm_stable_node *stable_node)
 {
 	VM_WARN_ON_FOLIO(folio_test_anon(folio) && PageAnonExclusive(&folio->page), folio);
-	folio->mapping = (void *)((unsigned long)stable_node | PAGE_MAPPING_KSM);
+	folio->mapping = (void *)((unsigned long)stable_node | FOLIO_MAPPING_KSM);
 }
 
 #ifdef CONFIG_SYSFS
diff --git a/mm/rmap.c b/mm/rmap.c
index bd83724d14b6..4b1a2a33e39f 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -503,12 +503,12 @@ struct anon_vma *folio_get_anon_vma(const struct folio *folio)
 
 	rcu_read_lock();
 	anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
-	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
+	if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON)
 		goto out;
 	if (!folio_mapped(folio))
 		goto out;
 
-	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
+	anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON);
 	if (!atomic_inc_not_zero(&anon_vma->refcount)) {
 		anon_vma = NULL;
 		goto out;
@@ -550,12 +550,12 @@ struct anon_vma *folio_lock_anon_vma_read(const struct folio *folio,
 retry:
 	rcu_read_lock();
 	anon_mapping = (unsigned long)READ_ONCE(folio->mapping);
-	if ((anon_mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
+	if ((anon_mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON)
 		goto out;
 	if (!folio_mapped(folio))
 		goto out;
 
-	anon_vma = (struct anon_vma *) (anon_mapping - PAGE_MAPPING_ANON);
+	anon_vma = (struct anon_vma *) (anon_mapping - FOLIO_MAPPING_ANON);
 	root_anon_vma = READ_ONCE(anon_vma->root);
 	if (down_read_trylock(&root_anon_vma->rwsem)) {
 		/*
@@ -1334,9 +1334,9 @@ void folio_move_anon_rmap(struct folio *folio, struct vm_area_struct *vma)
 	VM_BUG_ON_FOLIO(!folio_test_locked(folio), folio);
 	VM_BUG_ON_VMA(!anon_vma, vma);
 
-	anon_vma += PAGE_MAPPING_ANON;
+	anon_vma += FOLIO_MAPPING_ANON;
 	/*
-	 * Ensure that anon_vma and the PAGE_MAPPING_ANON bit are written
+	 * Ensure that anon_vma and the FOLIO_MAPPING_ANON bit are written
 	 * simultaneously, so a concurrent reader (eg folio_referenced()'s
 	 * folio_test_anon()) will not see one without the other.
 	 */
@@ -1367,10 +1367,10 @@ static void __folio_set_anon(struct folio *folio, struct vm_area_struct *vma,
 	/*
 	 * page_idle does a lockless/optimistic rmap scan on folio->mapping.
 	 * Make sure the compiler doesn't split the stores of anon_vma and
-	 * the PAGE_MAPPING_ANON type identifier, otherwise the rmap code
+	 * the FOLIO_MAPPING_ANON type identifier, otherwise the rmap code
 	 * could mistake the mapping for a struct address_space and crash.
 	 */
-	anon_vma = (void *) anon_vma + PAGE_MAPPING_ANON;
+	anon_vma = (void *) anon_vma + FOLIO_MAPPING_ANON;
 	WRITE_ONCE(folio->mapping, (struct address_space *) anon_vma);
 	folio->index = linear_page_index(vma, address);
 }
diff --git a/mm/util.c b/mm/util.c
index 0b270c43d7d1..20bbfe4ce1b8 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -670,9 +670,9 @@ struct anon_vma *folio_anon_vma(const struct folio *folio)
 {
 	unsigned long mapping = (unsigned long)folio->mapping;
 
-	if ((mapping & PAGE_MAPPING_FLAGS) != PAGE_MAPPING_ANON)
+	if ((mapping & FOLIO_MAPPING_FLAGS) != FOLIO_MAPPING_ANON)
 		return NULL;
-	return (void *)(mapping - PAGE_MAPPING_ANON);
+	return (void *)(mapping - FOLIO_MAPPING_ANON);
 }
 
 /**
@@ -699,7 +699,7 @@ struct address_space *folio_mapping(struct folio *folio)
 		return swap_address_space(folio->swap);
 
 	mapping = folio->mapping;
-	if ((unsigned long)mapping & PAGE_MAPPING_FLAGS)
+	if ((unsigned long)mapping & FOLIO_MAPPING_FLAGS)
 		return NULL;
 
 	return mapping;
-- 
cgit v1.2.3


From f5e43012b86aa6a0b0ad5881cb68bfb872826c22 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:22 +0200
Subject: mm/balloon_compaction: "movable_ops" doc updates
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's bring the docs up-to-date.  Setting PG_movable_ops + page->private
very likely still requires to be performed under documented locks: it's
complicated.

We will rework this in the future, as we will try avoiding using the page
lock.

Link: https://lkml.kernel.org/r/20250704102524.326966-29-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/balloon_compaction.h | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index b222b0737c46..2fecfead91d2 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -4,12 +4,13 @@
  *
  * Common interface definitions for making balloon pages movable by compaction.
  *
- * Balloon page migration makes use of the general non-lru movable page
+ * Balloon page migration makes use of the general "movable_ops page migration"
  * feature.
  *
  * page->private is used to reference the responsible balloon device.
- * page->mapping is used in context of non-lru page migration to reference
- * the address space operations for page isolation/migration/compaction.
+ * That these pages have movable_ops, and which movable_ops apply,
+ * is derived from the page type (PageOffline()) combined with the
+ * PG_movable_ops flag (PageMovableOps()).
  *
  * As the page isolation scanning step a compaction thread does is a lockless
  * procedure (from a page standpoint), it might bring some racy situations while
@@ -17,12 +18,10 @@
  * and safely perform balloon's page compaction and migration we must, always,
  * ensure following these simple rules:
  *
- *   i. when updating a balloon's page ->mapping element, strictly do it under
- *      the following lock order, independently of the far superior
- *      locking scheme (lru_lock, balloon_lock):
+ *   i. Setting the PG_movable_ops flag and page->private with the following
+ *	lock order
  *	    +-page_lock(page);
  *	      +--spin_lock_irq(&b_dev_info->pages_lock);
- *	            ... page->mapping updates here ...
  *
  *  ii. isolation or dequeueing procedure must remove the page from balloon
  *      device page list under b_dev_info->pages_lock.
-- 
cgit v1.2.3


From 9640b17a89a86f40df47bfc831a8afeff0c7eabc Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Fri, 4 Jul 2025 12:25:23 +0200
Subject: mm/balloon_compaction: provide single balloon_page_insert() and
 balloon_mapping_gfp_mask()
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Let's just special-case based on IS_ENABLED(CONFIG_BALLOON_COMPACTION)
like we did for balloon_page_finalize().

Link: https://lkml.kernel.org/r/20250704102524.326966-30-david@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Alistair Popple <apopple@nvidia.com>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Byungchul Park <byungchul@sk.com>
Cc: Chengming Zhou <chengming.zhou@linux.dev>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: Eugenio Pé rez <eperezma@redhat.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Gregory Price <gourry@gourry.net>
Cc: Harry Yoo <harry.yoo@oracle.com>
Cc: "Huang, Ying" <ying.huang@linux.alibaba.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jason Wang <jasowang@redhat.com>
Cc: Jerrin Shaji George <jerrin.shaji-george@broadcom.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: John Hubbard <jhubbard@nvidia.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Joshua Hahn <joshua.hahnjy@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Madhavan Srinivasan <maddy@linux.ibm.com>
Cc: Mathew Brost <matthew.brost@intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Miaohe Lin <linmiaohe@huawei.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: "Michael S. Tsirkin" <mst@redhat.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Naoya Horiguchi <nao.horiguchi@gmail.com>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: Peter Xu <peterx@redhat.com>
Cc: Qi Zheng <zhengqi.arch@bytedance.com>
Cc: Rakie Kim <rakie.kim@sk.com>
Cc: Rik van Riel <riel@surriel.com>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Xuan Zhuo <xuanzhuo@linux.alibaba.com>
Cc: xu xin <xu.xin16@zte.com.cn>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/balloon_compaction.h | 42 ++++++++++++++------------------------
 1 file changed, 15 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/balloon_compaction.h b/include/linux/balloon_compaction.h
index 2fecfead91d2..7cfe48769239 100644
--- a/include/linux/balloon_compaction.h
+++ b/include/linux/balloon_compaction.h
@@ -77,6 +77,15 @@ static inline void balloon_devinfo_init(struct balloon_dev_info *balloon)
 
 #ifdef CONFIG_BALLOON_COMPACTION
 extern const struct movable_operations balloon_mops;
+/*
+ * balloon_page_device - get the b_dev_info descriptor for the balloon device
+ *			 that enqueues the given page.
+ */
+static inline struct balloon_dev_info *balloon_page_device(struct page *page)
+{
+	return (struct balloon_dev_info *)page_private(page);
+}
+#endif /* CONFIG_BALLOON_COMPACTION */
 
 /*
  * balloon_page_insert - insert a page into the balloon's page list and make
@@ -91,41 +100,20 @@ static inline void balloon_page_insert(struct balloon_dev_info *balloon,
 				       struct page *page)
 {
 	__SetPageOffline(page);
-	SetPageMovableOps(page);
-	set_page_private(page, (unsigned long)balloon);
-	list_add(&page->lru, &balloon->pages);
-}
-
-/*
- * balloon_page_device - get the b_dev_info descriptor for the balloon device
- *			 that enqueues the given page.
- */
-static inline struct balloon_dev_info *balloon_page_device(struct page *page)
-{
-	return (struct balloon_dev_info *)page_private(page);
-}
-
-static inline gfp_t balloon_mapping_gfp_mask(void)
-{
-	return GFP_HIGHUSER_MOVABLE;
-}
-
-#else /* !CONFIG_BALLOON_COMPACTION */
-
-static inline void balloon_page_insert(struct balloon_dev_info *balloon,
-				       struct page *page)
-{
-	__SetPageOffline(page);
+	if (IS_ENABLED(CONFIG_BALLOON_COMPACTION)) {
+		SetPageMovableOps(page);
+		set_page_private(page, (unsigned long)balloon);
+	}
 	list_add(&page->lru, &balloon->pages);
 }
 
 static inline gfp_t balloon_mapping_gfp_mask(void)
 {
+	if (IS_ENABLED(CONFIG_BALLOON_COMPACTION))
+		return GFP_HIGHUSER_MOVABLE;
 	return GFP_HIGHUSER;
 }
 
-#endif /* CONFIG_BALLOON_COMPACTION */
-
 /*
  * balloon_page_finalize - prepare a balloon page that was removed from the
  *			   balloon list for release to the page allocator
-- 
cgit v1.2.3


From 67fd9615a782b11cd0c62823d722a815c9e1eb75 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 10 Jul 2025 15:33:26 +0200
Subject: iomap: pass more arguments using the iomap writeback context

Add inode and wpc fields to pass the inode and writeback context that
are needed in the entire writeback call chain, and let the callers
initialize all fields in the writeback context before calling
iomap_writepages to simplify the argument passing.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250710133343.399917-3-hch@lst.de
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Johannes Thumshirn <johannes.thumshirn@wdc.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 block/fops.c           |  8 ++++++--
 fs/gfs2/aops.c         |  8 ++++++--
 fs/iomap/buffered-io.c | 52 ++++++++++++++++++++++----------------------------
 fs/xfs/xfs_aops.c      | 24 ++++++++++++++++-------
 fs/zonefs/file.c       |  8 ++++++--
 include/linux/iomap.h  |  6 +++---
 6 files changed, 61 insertions(+), 45 deletions(-)

(limited to 'include/linux')

diff --git a/block/fops.c b/block/fops.c
index 1309861d4c2c..3394263d942b 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -558,9 +558,13 @@ static const struct iomap_writeback_ops blkdev_writeback_ops = {
 static int blkdev_writepages(struct address_space *mapping,
 		struct writeback_control *wbc)
 {
-	struct iomap_writepage_ctx wpc = { };
+	struct iomap_writepage_ctx wpc = {
+		.inode		= mapping->host,
+		.wbc		= wbc,
+		.ops		= &blkdev_writeback_ops
+	};
 
-	return iomap_writepages(mapping, wbc, &wpc, &blkdev_writeback_ops);
+	return iomap_writepages(&wpc);
 }
 
 const struct address_space_operations def_blk_aops = {
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 14f204cd5a82..47d74afd63ac 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -159,7 +159,11 @@ static int gfs2_writepages(struct address_space *mapping,
 			   struct writeback_control *wbc)
 {
 	struct gfs2_sbd *sdp = gfs2_mapping2sbd(mapping);
-	struct iomap_writepage_ctx wpc = { };
+	struct iomap_writepage_ctx wpc = {
+		.inode		= mapping->host,
+		.wbc		= wbc,
+		.ops		= &gfs2_writeback_ops,
+	};
 	int ret;
 
 	/*
@@ -168,7 +172,7 @@ static int gfs2_writepages(struct address_space *mapping,
 	 * want balance_dirty_pages() to loop indefinitely trying to write out
 	 * pages held in the ail that it can't find.
 	 */
-	ret = iomap_writepages(mapping, wbc, &wpc, &gfs2_writeback_ops);
+	ret = iomap_writepages(&wpc);
 	if (ret == 0 && wbc->nr_to_write > 0)
 		set_bit(SDF_FORCE_AIL_FLUSH, &sdp->sd_flags);
 	return ret;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index bbd722365404..77d44b691b81 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1618,20 +1618,19 @@ static int iomap_submit_ioend(struct iomap_writepage_ctx *wpc, int error)
 }
 
 static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct inode *inode, loff_t pos,
-		u16 ioend_flags)
+		loff_t pos, u16 ioend_flags)
 {
 	struct bio *bio;
 
 	bio = bio_alloc_bioset(wpc->iomap.bdev, BIO_MAX_VECS,
-			       REQ_OP_WRITE | wbc_to_write_flags(wbc),
+			       REQ_OP_WRITE | wbc_to_write_flags(wpc->wbc),
 			       GFP_NOFS, &iomap_ioend_bioset);
 	bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
 	bio->bi_end_io = iomap_writepage_end_bio;
-	bio->bi_write_hint = inode->i_write_hint;
-	wbc_init_bio(wbc, bio);
+	bio->bi_write_hint = wpc->inode->i_write_hint;
+	wbc_init_bio(wpc->wbc, bio);
 	wpc->nr_folios = 0;
-	return iomap_init_ioend(inode, bio, pos, ioend_flags);
+	return iomap_init_ioend(wpc->inode, bio, pos, ioend_flags);
 }
 
 static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
@@ -1670,9 +1669,7 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
  * writepage context that the caller will need to submit.
  */
 static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct folio *folio,
-		struct inode *inode, loff_t pos, loff_t end_pos,
-		unsigned len)
+		struct folio *folio, loff_t pos, loff_t end_pos, unsigned len)
 {
 	struct iomap_folio_state *ifs = folio->private;
 	size_t poff = offset_in_folio(folio, pos);
@@ -1693,8 +1690,7 @@ new_ioend:
 		error = iomap_submit_ioend(wpc, 0);
 		if (error)
 			return error;
-		wpc->ioend = iomap_alloc_ioend(wpc, wbc, inode, pos,
-				ioend_flags);
+		wpc->ioend = iomap_alloc_ioend(wpc, pos, ioend_flags);
 	}
 
 	if (!bio_add_folio(&wpc->ioend->io_bio, folio, len, poff))
@@ -1748,24 +1744,24 @@ new_ioend:
 	if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos)
 		wpc->ioend->io_size = end_pos - wpc->ioend->io_offset;
 
-	wbc_account_cgroup_owner(wbc, folio, len);
+	wbc_account_cgroup_owner(wpc->wbc, folio, len);
 	return 0;
 }
 
 static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct folio *folio,
-		struct inode *inode, u64 pos, u64 end_pos,
-		unsigned dirty_len, unsigned *count)
+		struct folio *folio, u64 pos, u64 end_pos, unsigned dirty_len,
+		unsigned *count)
 {
 	int error;
 
 	do {
 		unsigned map_len;
 
-		error = wpc->ops->map_blocks(wpc, inode, pos, dirty_len);
+		error = wpc->ops->map_blocks(wpc, wpc->inode, pos, dirty_len);
 		if (error)
 			break;
-		trace_iomap_writepage_map(inode, pos, dirty_len, &wpc->iomap);
+		trace_iomap_writepage_map(wpc->inode, pos, dirty_len,
+				&wpc->iomap);
 
 		map_len = min_t(u64, dirty_len,
 			wpc->iomap.offset + wpc->iomap.length - pos);
@@ -1779,8 +1775,8 @@ static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
 		case IOMAP_HOLE:
 			break;
 		default:
-			error = iomap_add_to_ioend(wpc, wbc, folio, inode, pos,
-					end_pos, map_len);
+			error = iomap_add_to_ioend(wpc, folio, pos, end_pos,
+					map_len);
 			if (!error)
 				(*count)++;
 			break;
@@ -1862,10 +1858,10 @@ static bool iomap_writepage_handle_eof(struct folio *folio, struct inode *inode,
 }
 
 static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
-		struct writeback_control *wbc, struct folio *folio)
+		struct folio *folio)
 {
 	struct iomap_folio_state *ifs = folio->private;
-	struct inode *inode = folio->mapping->host;
+	struct inode *inode = wpc->inode;
 	u64 pos = folio_pos(folio);
 	u64 end_pos = pos + folio_size(folio);
 	u64 end_aligned = 0;
@@ -1912,8 +1908,8 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	 */
 	end_aligned = round_up(end_pos, i_blocksize(inode));
 	while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) {
-		error = iomap_writepage_map_blocks(wpc, wbc, folio, inode,
-				pos, end_pos, rlen, &count);
+		error = iomap_writepage_map_blocks(wpc, folio, pos, end_pos,
+				rlen, &count);
 		if (error)
 			break;
 		pos += rlen;
@@ -1949,10 +1945,9 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 }
 
 int
-iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
-		struct iomap_writepage_ctx *wpc,
-		const struct iomap_writeback_ops *ops)
+iomap_writepages(struct iomap_writepage_ctx *wpc)
 {
+	struct address_space *mapping = wpc->inode->i_mapping;
 	struct folio *folio = NULL;
 	int error;
 
@@ -1964,9 +1959,8 @@ iomap_writepages(struct address_space *mapping, struct writeback_control *wbc,
 			PF_MEMALLOC))
 		return -EIO;
 
-	wpc->ops = ops;
-	while ((folio = writeback_iter(mapping, wbc, folio, &error)))
-		error = iomap_writepage_map(wpc, wbc, folio);
+	while ((folio = writeback_iter(mapping, wpc->wbc, folio, &error)))
+		error = iomap_writepage_map(wpc, folio);
 	return iomap_submit_ioend(wpc, error);
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 63151feb9c3f..65485a52df3b 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -636,19 +636,29 @@ xfs_vm_writepages(
 	xfs_iflags_clear(ip, XFS_ITRUNCATED);
 
 	if (xfs_is_zoned_inode(ip)) {
-		struct xfs_zoned_writepage_ctx	xc = { };
+		struct xfs_zoned_writepage_ctx	xc = {
+			.ctx = {
+				.inode	= mapping->host,
+				.wbc	= wbc,
+				.ops	= &xfs_zoned_writeback_ops
+			},
+		};
 		int				error;
 
-		error = iomap_writepages(mapping, wbc, &xc.ctx,
-					 &xfs_zoned_writeback_ops);
+		error = iomap_writepages(&xc.ctx);
 		if (xc.open_zone)
 			xfs_open_zone_put(xc.open_zone);
 		return error;
 	} else {
-		struct xfs_writepage_ctx	wpc = { };
-
-		return iomap_writepages(mapping, wbc, &wpc.ctx,
-				&xfs_writeback_ops);
+		struct xfs_writepage_ctx	wpc = {
+			.ctx = {
+				.inode	= mapping->host,
+				.wbc	= wbc,
+				.ops	= &xfs_writeback_ops
+			},
+		};
+
+		return iomap_writepages(&wpc.ctx);
 	}
 }
 
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index 42e2c0065bb3..edca4bbe4b72 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -152,9 +152,13 @@ static const struct iomap_writeback_ops zonefs_writeback_ops = {
 static int zonefs_writepages(struct address_space *mapping,
 			     struct writeback_control *wbc)
 {
-	struct iomap_writepage_ctx wpc = { };
+	struct iomap_writepage_ctx wpc = {
+		.inode		= mapping->host,
+		.wbc		= wbc,
+		.ops		= &zonefs_writeback_ops,
+	};
 
-	return iomap_writepages(mapping, wbc, &wpc, &zonefs_writeback_ops);
+	return iomap_writepages(&wpc);
 }
 
 static int zonefs_swap_activate(struct swap_info_struct *sis,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 522644d62f30..00179c9387c5 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -448,6 +448,8 @@ struct iomap_writeback_ops {
 
 struct iomap_writepage_ctx {
 	struct iomap		iomap;
+	struct inode		*inode;
+	struct writeback_control *wbc;
 	struct iomap_ioend	*ioend;
 	const struct iomap_writeback_ops *ops;
 	u32			nr_folios;	/* folios added to the ioend */
@@ -461,9 +463,7 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
 void iomap_ioend_try_merge(struct iomap_ioend *ioend,
 		struct list_head *more_ioends);
 void iomap_sort_ioends(struct list_head *ioend_list);
-int iomap_writepages(struct address_space *mapping,
-		struct writeback_control *wbc, struct iomap_writepage_ctx *wpc,
-		const struct iomap_writeback_ops *ops);
+int iomap_writepages(struct iomap_writepage_ctx *wpc);
 
 /*
  * Flags for direct I/O ->end_io:
-- 
cgit v1.2.3


From fb7399cf2d0b33825b8039f95c45395c7deba25c Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 10 Jul 2025 15:33:28 +0200
Subject: iomap: refactor the writeback interface

Replace ->map_blocks with a new ->writeback_range, which differs in the
following ways:

 - it must also queue up the I/O for writeback, that is called into the
   slightly refactored and extended in scope iomap_add_to_ioend for
   each region
 - can handle only a part of the requested region, that is the retry
   loop for partial mappings moves to the caller
 - handles cleanup on failures as well, and thus also replaces the
   discard_folio method only implemented by XFS.

This will allow to use the iomap writeback code also for file systems
that are not block based like fuse.

Co-developed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250710133343.399917-5-hch@lst.de
Acked-by: Damien Le Moal <dlemoal@kernel.org>	# zonefs
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/iomap/operations.rst |  32 +++----
 block/fops.c                                   |  25 +++--
 fs/gfs2/bmap.c                                 |  26 ++---
 fs/iomap/buffered-io.c                         |  96 +++++++++----------
 fs/iomap/trace.h                               |   2 +-
 fs/xfs/xfs_aops.c                              | 128 ++++++++++++++++---------
 fs/zonefs/file.c                               |  28 +++---
 include/linux/iomap.h                          |  21 ++--
 8 files changed, 197 insertions(+), 161 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst
index 3b628e370d88..f07c8fdb2046 100644
--- a/Documentation/filesystems/iomap/operations.rst
+++ b/Documentation/filesystems/iomap/operations.rst
@@ -271,7 +271,7 @@ writeback.
 It does not lock ``i_rwsem`` or ``invalidate_lock``.
 
 The dirty bit will be cleared for all folios run through the
-``->map_blocks`` machinery described below even if the writeback fails.
+``->writeback_range`` machinery described below even if the writeback fails.
 This is to prevent dirty folio clots when storage devices fail; an
 ``-EIO`` is recorded for userspace to collect via ``fsync``.
 
@@ -283,15 +283,14 @@ The ``ops`` structure must be specified and is as follows:
 .. code-block:: c
 
  struct iomap_writeback_ops {
-     int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
-                       loff_t offset, unsigned len);
-     int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
-     void (*discard_folio)(struct folio *folio, loff_t pos);
+    int (*writeback_range)(struct iomap_writepage_ctx *wpc,
+         struct folio *folio, u64 pos, unsigned int len, u64 end_pos);
+    int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
  };
 
 The fields are as follows:
 
-  - ``map_blocks``: Sets ``wpc->iomap`` to the space mapping of the file
+  - ``writeback_range``: Sets ``wpc->iomap`` to the space mapping of the file
     range (in bytes) given by ``offset`` and ``len``.
     iomap calls this function for each dirty fs block in each dirty folio,
     though it will `reuse mappings
@@ -306,6 +305,15 @@ The fields are as follows:
     This revalidation must be open-coded by the filesystem; it is
     unclear if ``iomap::validity_cookie`` can be reused for this
     purpose.
+
+    If this methods fails to schedule I/O for any part of a dirty folio, it
+    should throw away any reservations that may have been made for the write.
+    The folio will be marked clean and an ``-EIO`` recorded in the
+    pagecache.
+    Filesystems can use this callback to `remove
+    <https://lore.kernel.org/all/20201029163313.1766967-1-bfoster@redhat.com/>`_
+    delalloc reservations to avoid having delalloc reservations for
+    clean pagecache.
     This function must be supplied by the filesystem.
 
   - ``submit_ioend``: Allows the file systems to hook into writeback bio
@@ -316,18 +324,6 @@ The fields are as follows:
     transactions from process context before submitting the bio.
     This function is optional.
 
-  - ``discard_folio``: iomap calls this function after ``->map_blocks``
-    fails to schedule I/O for any part of a dirty folio.
-    The function should throw away any reservations that may have been
-    made for the write.
-    The folio will be marked clean and an ``-EIO`` recorded in the
-    pagecache.
-    Filesystems can use this callback to `remove
-    <https://lore.kernel.org/all/20201029163313.1766967-1-bfoster@redhat.com/>`_
-    delalloc reservations to avoid having delalloc reservations for
-    clean pagecache.
-    This function is optional.
-
 Pagecache Writeback Completion
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
 
diff --git a/block/fops.c b/block/fops.c
index 3394263d942b..b500ff8f55dd 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -537,22 +537,29 @@ static void blkdev_readahead(struct readahead_control *rac)
 	iomap_readahead(rac, &blkdev_iomap_ops);
 }
 
-static int blkdev_map_blocks(struct iomap_writepage_ctx *wpc,
-		struct inode *inode, loff_t offset, unsigned int len)
+static ssize_t blkdev_writeback_range(struct iomap_writepage_ctx *wpc,
+		struct folio *folio, u64 offset, unsigned int len, u64 end_pos)
 {
-	loff_t isize = i_size_read(inode);
+	loff_t isize = i_size_read(wpc->inode);
 
 	if (WARN_ON_ONCE(offset >= isize))
 		return -EIO;
-	if (offset >= wpc->iomap.offset &&
-	    offset < wpc->iomap.offset + wpc->iomap.length)
-		return 0;
-	return blkdev_iomap_begin(inode, offset, isize - offset,
-				  IOMAP_WRITE, &wpc->iomap, NULL);
+
+	if (offset < wpc->iomap.offset ||
+	    offset >= wpc->iomap.offset + wpc->iomap.length) {
+		int error;
+
+		error = blkdev_iomap_begin(wpc->inode, offset, isize - offset,
+				IOMAP_WRITE, &wpc->iomap, NULL);
+		if (error)
+			return error;
+	}
+
+	return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
 }
 
 static const struct iomap_writeback_ops blkdev_writeback_ops = {
-	.map_blocks		= blkdev_map_blocks,
+	.writeback_range	= blkdev_writeback_range,
 };
 
 static int blkdev_writepages(struct address_space *mapping,
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 7703d0471139..0cc41de54aba 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -2469,23 +2469,25 @@ out:
 	return error;
 }
 
-static int gfs2_map_blocks(struct iomap_writepage_ctx *wpc, struct inode *inode,
-		loff_t offset, unsigned int len)
+static ssize_t gfs2_writeback_range(struct iomap_writepage_ctx *wpc,
+		struct folio *folio, u64 offset, unsigned int len, u64 end_pos)
 {
-	int ret;
-
-	if (WARN_ON_ONCE(gfs2_is_stuffed(GFS2_I(inode))))
+	if (WARN_ON_ONCE(gfs2_is_stuffed(GFS2_I(wpc->inode))))
 		return -EIO;
 
-	if (offset >= wpc->iomap.offset &&
-	    offset < wpc->iomap.offset + wpc->iomap.length)
-		return 0;
+	if (offset < wpc->iomap.offset ||
+	    offset >= wpc->iomap.offset + wpc->iomap.length) {
+		int ret;
 
-	memset(&wpc->iomap, 0, sizeof(wpc->iomap));
-	ret = gfs2_iomap_get(inode, offset, INT_MAX, &wpc->iomap);
-	return ret;
+		memset(&wpc->iomap, 0, sizeof(wpc->iomap));
+		ret = gfs2_iomap_get(wpc->inode, offset, INT_MAX, &wpc->iomap);
+		if (ret)
+			return ret;
+	}
+
+	return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
 }
 
 const struct iomap_writeback_ops gfs2_writeback_ops = {
-	.map_blocks		= gfs2_map_blocks,
+	.writeback_range	= gfs2_writeback_range,
 };
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 93b2a90e6867..c558ac15bc87 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1668,14 +1668,30 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
  * At the end of a writeback pass, there will be a cached ioend remaining on the
  * writepage context that the caller will need to submit.
  */
-static int iomap_add_to_ioend(struct iomap_writepage_ctx *wpc,
-		struct folio *folio, loff_t pos, loff_t end_pos, unsigned len)
+ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
+		loff_t pos, loff_t end_pos, unsigned int dirty_len)
 {
 	struct iomap_folio_state *ifs = folio->private;
 	size_t poff = offset_in_folio(folio, pos);
 	unsigned int ioend_flags = 0;
+	unsigned int map_len = min_t(u64, dirty_len,
+		wpc->iomap.offset + wpc->iomap.length - pos);
 	int error;
 
+	trace_iomap_add_to_ioend(wpc->inode, pos, dirty_len, &wpc->iomap);
+
+	WARN_ON_ONCE(!folio->private && map_len < dirty_len);
+
+	switch (wpc->iomap.type) {
+	case IOMAP_INLINE:
+		WARN_ON_ONCE(1);
+		return -EIO;
+	case IOMAP_HOLE:
+		return map_len;
+	default:
+		break;
+	}
+
 	if (wpc->iomap.type == IOMAP_UNWRITTEN)
 		ioend_flags |= IOMAP_IOEND_UNWRITTEN;
 	if (wpc->iomap.flags & IOMAP_F_SHARED)
@@ -1693,11 +1709,11 @@ new_ioend:
 		wpc->ioend = iomap_alloc_ioend(wpc, pos, ioend_flags);
 	}
 
-	if (!bio_add_folio(&wpc->ioend->io_bio, folio, len, poff))
+	if (!bio_add_folio(&wpc->ioend->io_bio, folio, map_len, poff))
 		goto new_ioend;
 
 	if (ifs)
-		atomic_add(len, &ifs->write_bytes_pending);
+		atomic_add(map_len, &ifs->write_bytes_pending);
 
 	/*
 	 * Clamp io_offset and io_size to the incore EOF so that ondisk
@@ -1740,63 +1756,39 @@ new_ioend:
 	 * Note that this defeats the ability to chain the ioends of
 	 * appending writes.
 	 */
-	wpc->ioend->io_size += len;
+	wpc->ioend->io_size += map_len;
 	if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos)
 		wpc->ioend->io_size = end_pos - wpc->ioend->io_offset;
 
-	wbc_account_cgroup_owner(wpc->wbc, folio, len);
-	return 0;
+	wbc_account_cgroup_owner(wpc->wbc, folio, map_len);
+	return map_len;
 }
+EXPORT_SYMBOL_GPL(iomap_add_to_ioend);
 
-static int iomap_writepage_map_blocks(struct iomap_writepage_ctx *wpc,
-		struct folio *folio, u64 pos, u64 end_pos, unsigned dirty_len,
+static int iomap_writeback_range(struct iomap_writepage_ctx *wpc,
+		struct folio *folio, u64 pos, u32 rlen, u64 end_pos,
 		bool *wb_pending)
 {
-	int error;
-
 	do {
-		unsigned map_len;
-
-		error = wpc->ops->map_blocks(wpc, wpc->inode, pos, dirty_len);
-		if (error)
-			break;
-		trace_iomap_writepage_map(wpc->inode, pos, dirty_len,
-				&wpc->iomap);
+		ssize_t ret;
 
-		map_len = min_t(u64, dirty_len,
-			wpc->iomap.offset + wpc->iomap.length - pos);
-		WARN_ON_ONCE(!folio->private && map_len < dirty_len);
+		ret = wpc->ops->writeback_range(wpc, folio, pos, rlen, end_pos);
+		if (WARN_ON_ONCE(ret == 0 || ret > rlen))
+			return -EIO;
+		if (ret < 0)
+			return ret;
+		rlen -= ret;
+		pos += ret;
 
-		switch (wpc->iomap.type) {
-		case IOMAP_INLINE:
-			WARN_ON_ONCE(1);
-			error = -EIO;
-			break;
-		case IOMAP_HOLE:
-			break;
-		default:
-			error = iomap_add_to_ioend(wpc, folio, pos, end_pos,
-					map_len);
-			if (!error)
-				*wb_pending = true;
-			break;
-		}
-		dirty_len -= map_len;
-		pos += map_len;
-	} while (dirty_len && !error);
+		/*
+		 * Holes are not be written back by ->writeback_range, so track
+		 * if we did handle anything that is not a hole here.
+		 */
+		if (wpc->iomap.type != IOMAP_HOLE)
+			*wb_pending = true;
+	} while (rlen);
 
-	/*
-	 * We cannot cancel the ioend directly here on error.  We may have
-	 * already set other pages under writeback and hence we have to run I/O
-	 * completion to mark the error state of the pages under writeback
-	 * appropriately.
-	 *
-	 * Just let the file system know what portion of the folio failed to
-	 * map.
-	 */
-	if (error && wpc->ops->discard_folio)
-		wpc->ops->discard_folio(folio, pos);
-	return error;
+	return 0;
 }
 
 /*
@@ -1908,8 +1900,8 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 	 */
 	end_aligned = round_up(end_pos, i_blocksize(inode));
 	while ((rlen = iomap_find_dirty_range(folio, &pos, end_aligned))) {
-		error = iomap_writepage_map_blocks(wpc, folio, pos, end_pos,
-				rlen, &wb_pending);
+		error = iomap_writeback_range(wpc, folio, pos, rlen, end_pos,
+				&wb_pending);
 		if (error)
 			break;
 		pos += rlen;
diff --git a/fs/iomap/trace.h b/fs/iomap/trace.h
index 455cc6f90be0..aaea02c9560a 100644
--- a/fs/iomap/trace.h
+++ b/fs/iomap/trace.h
@@ -169,7 +169,7 @@ DEFINE_EVENT(iomap_class, name,	\
 DEFINE_IOMAP_EVENT(iomap_iter_dstmap);
 DEFINE_IOMAP_EVENT(iomap_iter_srcmap);
 
-TRACE_EVENT(iomap_writepage_map,
+TRACE_EVENT(iomap_add_to_ioend,
 	TP_PROTO(struct inode *inode, u64 pos, unsigned int dirty_len,
 		 struct iomap *iomap),
 	TP_ARGS(inode, pos, dirty_len, iomap),
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 65485a52df3b..f6d44ab78442 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -233,6 +233,47 @@ xfs_end_bio(
 	spin_unlock_irqrestore(&ip->i_ioend_lock, flags);
 }
 
+/*
+ * We cannot cancel the ioend directly on error.  We may have already set other
+ * pages under writeback and hence we have to run I/O completion to mark the
+ * error state of the pages under writeback appropriately.
+ *
+ * If the folio has delalloc blocks on it, the caller is asking us to punch them
+ * out. If we don't, we can leave a stale delalloc mapping covered by a clean
+ * page that needs to be dirtied again before the delalloc mapping can be
+ * converted. This stale delalloc mapping can trip up a later direct I/O read
+ * operation on the same region.
+ *
+ * We prevent this by truncating away the delalloc regions on the folio. Because
+ * they are delalloc, we can do this without needing a transaction. Indeed - if
+ * we get ENOSPC errors, we have to be able to do this truncation without a
+ * transaction as there is no space left for block reservation (typically why
+ * we see a ENOSPC in writeback).
+ */
+static void
+xfs_discard_folio(
+	struct folio		*folio,
+	loff_t			pos)
+{
+	struct xfs_inode	*ip = XFS_I(folio->mapping->host);
+	struct xfs_mount	*mp = ip->i_mount;
+
+	if (xfs_is_shutdown(mp))
+		return;
+
+	xfs_alert_ratelimited(mp,
+		"page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
+			folio, ip->i_ino, pos);
+
+	/*
+	 * The end of the punch range is always the offset of the first
+	 * byte of the next folio. Hence the end offset is only dependent on the
+	 * folio itself and not the start offset that is passed in.
+	 */
+	xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
+				folio_pos(folio) + folio_size(folio), NULL);
+}
+
 /*
  * Fast revalidation of the cached writeback mapping. Return true if the current
  * mapping is valid, false otherwise.
@@ -278,13 +319,12 @@ xfs_imap_valid(
 static int
 xfs_map_blocks(
 	struct iomap_writepage_ctx *wpc,
-	struct inode		*inode,
 	loff_t			offset,
 	unsigned int		len)
 {
-	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_inode	*ip = XFS_I(wpc->inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	ssize_t			count = i_blocksize(inode);
+	ssize_t			count = i_blocksize(wpc->inode);
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
 	xfs_fileoff_t		cow_fsb;
@@ -436,6 +476,24 @@ allocate_blocks:
 	return 0;
 }
 
+static ssize_t
+xfs_writeback_range(
+	struct iomap_writepage_ctx *wpc,
+	struct folio		*folio,
+	u64			offset,
+	unsigned int		len,
+	u64			end_pos)
+{
+	ssize_t			ret;
+
+	ret = xfs_map_blocks(wpc, offset, len);
+	if (!ret)
+		ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+	if (ret < 0)
+		xfs_discard_folio(folio, offset);
+	return ret;
+}
+
 static bool
 xfs_ioend_needs_wq_completion(
 	struct iomap_ioend	*ioend)
@@ -488,47 +546,9 @@ xfs_submit_ioend(
 	return 0;
 }
 
-/*
- * If the folio has delalloc blocks on it, the caller is asking us to punch them
- * out. If we don't, we can leave a stale delalloc mapping covered by a clean
- * page that needs to be dirtied again before the delalloc mapping can be
- * converted. This stale delalloc mapping can trip up a later direct I/O read
- * operation on the same region.
- *
- * We prevent this by truncating away the delalloc regions on the folio. Because
- * they are delalloc, we can do this without needing a transaction. Indeed - if
- * we get ENOSPC errors, we have to be able to do this truncation without a
- * transaction as there is no space left for block reservation (typically why
- * we see a ENOSPC in writeback).
- */
-static void
-xfs_discard_folio(
-	struct folio		*folio,
-	loff_t			pos)
-{
-	struct xfs_inode	*ip = XFS_I(folio->mapping->host);
-	struct xfs_mount	*mp = ip->i_mount;
-
-	if (xfs_is_shutdown(mp))
-		return;
-
-	xfs_alert_ratelimited(mp,
-		"page discard on page "PTR_FMT", inode 0x%llx, pos %llu.",
-			folio, ip->i_ino, pos);
-
-	/*
-	 * The end of the punch range is always the offset of the first
-	 * byte of the next folio. Hence the end offset is only dependent on the
-	 * folio itself and not the start offset that is passed in.
-	 */
-	xfs_bmap_punch_delalloc_range(ip, XFS_DATA_FORK, pos,
-				folio_pos(folio) + folio_size(folio), NULL);
-}
-
 static const struct iomap_writeback_ops xfs_writeback_ops = {
-	.map_blocks		= xfs_map_blocks,
+	.writeback_range	= xfs_writeback_range,
 	.submit_ioend		= xfs_submit_ioend,
-	.discard_folio		= xfs_discard_folio,
 };
 
 struct xfs_zoned_writepage_ctx {
@@ -545,11 +565,10 @@ XFS_ZWPC(struct iomap_writepage_ctx *ctx)
 static int
 xfs_zoned_map_blocks(
 	struct iomap_writepage_ctx *wpc,
-	struct inode		*inode,
 	loff_t			offset,
 	unsigned int		len)
 {
-	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_inode	*ip = XFS_I(wpc->inode);
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + len);
@@ -608,6 +627,24 @@ xfs_zoned_map_blocks(
 	return 0;
 }
 
+static ssize_t
+xfs_zoned_writeback_range(
+	struct iomap_writepage_ctx *wpc,
+	struct folio		*folio,
+	u64			offset,
+	unsigned int		len,
+	u64			end_pos)
+{
+	ssize_t			ret;
+
+	ret = xfs_zoned_map_blocks(wpc, offset, len);
+	if (!ret)
+		ret = iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
+	if (ret < 0)
+		xfs_discard_folio(folio, offset);
+	return ret;
+}
+
 static int
 xfs_zoned_submit_ioend(
 	struct iomap_writepage_ctx *wpc,
@@ -621,9 +658,8 @@ xfs_zoned_submit_ioend(
 }
 
 static const struct iomap_writeback_ops xfs_zoned_writeback_ops = {
-	.map_blocks		= xfs_zoned_map_blocks,
+	.writeback_range	= xfs_zoned_writeback_range,
 	.submit_ioend		= xfs_zoned_submit_ioend,
-	.discard_folio		= xfs_discard_folio,
 };
 
 STATIC int
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index edca4bbe4b72..c88e2c851753 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -124,29 +124,33 @@ static void zonefs_readahead(struct readahead_control *rac)
  * Map blocks for page writeback. This is used only on conventional zone files,
  * which implies that the page range can only be within the fixed inode size.
  */
-static int zonefs_write_map_blocks(struct iomap_writepage_ctx *wpc,
-				   struct inode *inode, loff_t offset,
-				   unsigned int len)
+static ssize_t zonefs_writeback_range(struct iomap_writepage_ctx *wpc,
+		struct folio *folio, u64 offset, unsigned len, u64 end_pos)
 {
-	struct zonefs_zone *z = zonefs_inode_zone(inode);
+	struct zonefs_zone *z = zonefs_inode_zone(wpc->inode);
 
 	if (WARN_ON_ONCE(zonefs_zone_is_seq(z)))
 		return -EIO;
-	if (WARN_ON_ONCE(offset >= i_size_read(inode)))
+	if (WARN_ON_ONCE(offset >= i_size_read(wpc->inode)))
 		return -EIO;
 
 	/* If the mapping is already OK, nothing needs to be done */
-	if (offset >= wpc->iomap.offset &&
-	    offset < wpc->iomap.offset + wpc->iomap.length)
-		return 0;
+	if (offset < wpc->iomap.offset ||
+	    offset >= wpc->iomap.offset + wpc->iomap.length) {
+		int error;
+
+		error = zonefs_write_iomap_begin(wpc->inode, offset,
+				z->z_capacity - offset, IOMAP_WRITE,
+				&wpc->iomap, NULL);
+		if (error)
+			return error;
+	}
 
-	return zonefs_write_iomap_begin(inode, offset,
-					z->z_capacity - offset,
-					IOMAP_WRITE, &wpc->iomap, NULL);
+	return iomap_add_to_ioend(wpc, folio, offset, end_pos, len);
 }
 
 static const struct iomap_writeback_ops zonefs_writeback_ops = {
-	.map_blocks		= zonefs_write_map_blocks,
+	.writeback_range	= zonefs_writeback_range,
 };
 
 static int zonefs_writepages(struct address_space *mapping,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 00179c9387c5..625d7911a2b5 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -416,18 +416,20 @@ static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
 
 struct iomap_writeback_ops {
 	/*
-	 * Required, maps the blocks so that writeback can be performed on
-	 * the range starting at offset.
+	 * Required, performs writeback on the passed in range
 	 *
-	 * Can return arbitrarily large regions, but we need to call into it at
+	 * Can map arbitrarily large regions, but we need to call into it at
 	 * least once per folio to allow the file systems to synchronize with
 	 * the write path that could be invalidating mappings.
 	 *
 	 * An existing mapping from a previous call to this method can be reused
 	 * by the file system if it is still valid.
+	 *
+	 * Returns the number of bytes processed or a negative errno.
 	 */
-	int (*map_blocks)(struct iomap_writepage_ctx *wpc, struct inode *inode,
-			  loff_t offset, unsigned len);
+	ssize_t (*writeback_range)(struct iomap_writepage_ctx *wpc,
+			struct folio *folio, u64 pos, unsigned int len,
+			u64 end_pos);
 
 	/*
 	 * Optional, allows the file systems to hook into bio submission,
@@ -438,12 +440,6 @@ struct iomap_writeback_ops {
 	 * the bio could not be submitted.
 	 */
 	int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
-
-	/*
-	 * Optional, allows the file system to discard state on a page where
-	 * we failed to submit any I/O.
-	 */
-	void (*discard_folio)(struct folio *folio, loff_t pos);
 };
 
 struct iomap_writepage_ctx {
@@ -463,6 +459,9 @@ void iomap_finish_ioends(struct iomap_ioend *ioend, int error);
 void iomap_ioend_try_merge(struct iomap_ioend *ioend,
 		struct list_head *more_ioends);
 void iomap_sort_ioends(struct list_head *ioend_list);
+ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
+		loff_t pos, loff_t end_pos, unsigned int dirty_len);
+
 int iomap_writepages(struct iomap_writepage_ctx *wpc);
 
 /*
-- 
cgit v1.2.3


From f4fa7981fa26c664cc540cbce9bcb7ffe02a8912 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 10 Jul 2025 15:33:29 +0200
Subject: iomap: hide ioends from the generic writeback code

Replace the ioend pointer in iomap_writeback_ctx with a void *wb_ctx
one to facilitate non-block, non-ioend writeback for use.  Rename
the submit_ioend method to writeback_submit and make it mandatory so
that the generic writeback code stops seeing ioends and bios.

Co-developed-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250710133343.399917-6-hch@lst.de
Acked-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/iomap/operations.rst | 17 ++---
 block/fops.c                                   |  1 +
 fs/gfs2/bmap.c                                 |  1 +
 fs/iomap/buffered-io.c                         | 91 +++++++++++++-------------
 fs/xfs/xfs_aops.c                              | 60 +++++++++--------
 fs/zonefs/file.c                               |  1 +
 include/linux/iomap.h                          | 19 +++---
 7 files changed, 100 insertions(+), 90 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst
index f07c8fdb2046..4b93c5f7841a 100644
--- a/Documentation/filesystems/iomap/operations.rst
+++ b/Documentation/filesystems/iomap/operations.rst
@@ -284,8 +284,8 @@ The ``ops`` structure must be specified and is as follows:
 
  struct iomap_writeback_ops {
     int (*writeback_range)(struct iomap_writepage_ctx *wpc,
-         struct folio *folio, u64 pos, unsigned int len, u64 end_pos);
-    int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
+        struct folio *folio, u64 pos, unsigned int len, u64 end_pos);
+    int (*writeback_submit)(struct iomap_writepage_ctx *wpc, int error);
  };
 
 The fields are as follows:
@@ -316,13 +316,15 @@ The fields are as follows:
     clean pagecache.
     This function must be supplied by the filesystem.
 
-  - ``submit_ioend``: Allows the file systems to hook into writeback bio
-    submission.
+  - ``writeback_submit``: Submit the previous built writeback context.
+    Block based file systems should use the iomap_ioend_writeback_submit
+    helper, other file system can implement their own.
+    File systems can optionall to hook into writeback bio submission.
     This might include pre-write space accounting updates, or installing
     a custom ``->bi_end_io`` function for internal purposes, such as
     deferring the ioend completion to a workqueue to run metadata update
     transactions from process context before submitting the bio.
-    This function is optional.
+    This function must be supplied by the filesystem.
 
 Pagecache Writeback Completion
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
@@ -336,10 +338,9 @@ If the write failed, it will also set the error bits on the folios and
 the address space.
 This can happen in interrupt or process context, depending on the
 storage device.
-
 Filesystems that need to update internal bookkeeping (e.g. unwritten
-extent conversions) should provide a ``->submit_ioend`` function to
-set ``struct iomap_end::bio::bi_end_io`` to its own function.
+extent conversions) should set their own bi_end_io on the bios
+submitted by ``->submit_writeback``
 This function should call ``iomap_finish_ioends`` after finishing its
 own work (e.g. unwritten extent conversion).
 
diff --git a/block/fops.c b/block/fops.c
index b500ff8f55dd..0845737c0320 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -560,6 +560,7 @@ static ssize_t blkdev_writeback_range(struct iomap_writepage_ctx *wpc,
 
 static const struct iomap_writeback_ops blkdev_writeback_ops = {
 	.writeback_range	= blkdev_writeback_range,
+	.writeback_submit	= iomap_ioend_writeback_submit,
 };
 
 static int blkdev_writepages(struct address_space *mapping,
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 0cc41de54aba..86045d3577b7 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -2490,4 +2490,5 @@ static ssize_t gfs2_writeback_range(struct iomap_writepage_ctx *wpc,
 
 const struct iomap_writeback_ops gfs2_writeback_ops = {
 	.writeback_range	= gfs2_writeback_range,
+	.writeback_submit	= iomap_ioend_writeback_submit,
 };
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index c558ac15bc87..650a67b7d223 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1571,7 +1571,7 @@ u32 iomap_finish_ioend_buffered(struct iomap_ioend *ioend)
 	return folio_count;
 }
 
-static void iomap_writepage_end_bio(struct bio *bio)
+static void ioend_writeback_end_bio(struct bio *bio)
 {
 	struct iomap_ioend *ioend = iomap_ioend_from_bio(bio);
 
@@ -1580,42 +1580,30 @@ static void iomap_writepage_end_bio(struct bio *bio)
 }
 
 /*
- * Submit an ioend.
- *
- * If @error is non-zero, it means that we have a situation where some part of
- * the submission process has failed after we've marked pages for writeback.
- * We cannot cancel ioend directly in that case, so call the bio end I/O handler
- * with the error status here to run the normal I/O completion handler to clear
- * the writeback bit and let the file system proess the errors.
+ * We cannot cancel the ioend directly in case of an error, so call the bio end
+ * I/O handler with the error status here to run the normal I/O completion
+ * handler.
  */
-static int iomap_submit_ioend(struct iomap_writepage_ctx *wpc, int error)
+int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error)
 {
-	if (!wpc->ioend)
-		return error;
+	struct iomap_ioend *ioend = wpc->wb_ctx;
 
-	/*
-	 * Let the file systems prepare the I/O submission and hook in an I/O
-	 * comletion handler.  This also needs to happen in case after a
-	 * failure happened so that the file system end I/O handler gets called
-	 * to clean up.
-	 */
-	if (wpc->ops->submit_ioend) {
-		error = wpc->ops->submit_ioend(wpc, error);
-	} else {
-		if (WARN_ON_ONCE(wpc->iomap.flags & IOMAP_F_ANON_WRITE))
-			error = -EIO;
-		if (!error)
-			submit_bio(&wpc->ioend->io_bio);
-	}
+	if (!ioend->io_bio.bi_end_io)
+		ioend->io_bio.bi_end_io = ioend_writeback_end_bio;
+
+	if (WARN_ON_ONCE(wpc->iomap.flags & IOMAP_F_ANON_WRITE))
+		error = -EIO;
 
 	if (error) {
-		wpc->ioend->io_bio.bi_status = errno_to_blk_status(error);
-		bio_endio(&wpc->ioend->io_bio);
+		ioend->io_bio.bi_status = errno_to_blk_status(error);
+		bio_endio(&ioend->io_bio);
+		return error;
 	}
 
-	wpc->ioend = NULL;
-	return error;
+	submit_bio(&ioend->io_bio);
+	return 0;
 }
+EXPORT_SYMBOL_GPL(iomap_ioend_writeback_submit);
 
 static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
 		loff_t pos, u16 ioend_flags)
@@ -1626,7 +1614,6 @@ static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
 			       REQ_OP_WRITE | wbc_to_write_flags(wpc->wbc),
 			       GFP_NOFS, &iomap_ioend_bioset);
 	bio->bi_iter.bi_sector = iomap_sector(&wpc->iomap, pos);
-	bio->bi_end_io = iomap_writepage_end_bio;
 	bio->bi_write_hint = wpc->inode->i_write_hint;
 	wbc_init_bio(wpc->wbc, bio);
 	wpc->nr_folios = 0;
@@ -1636,16 +1623,17 @@ static struct iomap_ioend *iomap_alloc_ioend(struct iomap_writepage_ctx *wpc,
 static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
 		u16 ioend_flags)
 {
+	struct iomap_ioend *ioend = wpc->wb_ctx;
+
 	if (ioend_flags & IOMAP_IOEND_BOUNDARY)
 		return false;
 	if ((ioend_flags & IOMAP_IOEND_NOMERGE_FLAGS) !=
-	    (wpc->ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS))
+	    (ioend->io_flags & IOMAP_IOEND_NOMERGE_FLAGS))
 		return false;
-	if (pos != wpc->ioend->io_offset + wpc->ioend->io_size)
+	if (pos != ioend->io_offset + ioend->io_size)
 		return false;
 	if (!(wpc->iomap.flags & IOMAP_F_ANON_WRITE) &&
-	    iomap_sector(&wpc->iomap, pos) !=
-	    bio_end_sector(&wpc->ioend->io_bio))
+	    iomap_sector(&wpc->iomap, pos) != bio_end_sector(&ioend->io_bio))
 		return false;
 	/*
 	 * Limit ioend bio chain lengths to minimise IO completion latency. This
@@ -1671,6 +1659,7 @@ static bool iomap_can_add_to_ioend(struct iomap_writepage_ctx *wpc, loff_t pos,
 ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 		loff_t pos, loff_t end_pos, unsigned int dirty_len)
 {
+	struct iomap_ioend *ioend = wpc->wb_ctx;
 	struct iomap_folio_state *ifs = folio->private;
 	size_t poff = offset_in_folio(folio, pos);
 	unsigned int ioend_flags = 0;
@@ -1701,15 +1690,17 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 	if (pos == wpc->iomap.offset && (wpc->iomap.flags & IOMAP_F_BOUNDARY))
 		ioend_flags |= IOMAP_IOEND_BOUNDARY;
 
-	if (!wpc->ioend || !iomap_can_add_to_ioend(wpc, pos, ioend_flags)) {
+	if (!ioend || !iomap_can_add_to_ioend(wpc, pos, ioend_flags)) {
 new_ioend:
-		error = iomap_submit_ioend(wpc, 0);
-		if (error)
-			return error;
-		wpc->ioend = iomap_alloc_ioend(wpc, pos, ioend_flags);
+		if (ioend) {
+			error = wpc->ops->writeback_submit(wpc, 0);
+			if (error)
+				return error;
+		}
+		wpc->wb_ctx = ioend = iomap_alloc_ioend(wpc, pos, ioend_flags);
 	}
 
-	if (!bio_add_folio(&wpc->ioend->io_bio, folio, map_len, poff))
+	if (!bio_add_folio(&ioend->io_bio, folio, map_len, poff))
 		goto new_ioend;
 
 	if (ifs)
@@ -1756,9 +1747,9 @@ new_ioend:
 	 * Note that this defeats the ability to chain the ioends of
 	 * appending writes.
 	 */
-	wpc->ioend->io_size += map_len;
-	if (wpc->ioend->io_offset + wpc->ioend->io_size > end_pos)
-		wpc->ioend->io_size = end_pos - wpc->ioend->io_offset;
+	ioend->io_size += map_len;
+	if (ioend->io_offset + ioend->io_size > end_pos)
+		ioend->io_size = end_pos - ioend->io_offset;
 
 	wbc_account_cgroup_owner(wpc->wbc, folio, map_len);
 	return map_len;
@@ -1953,6 +1944,18 @@ iomap_writepages(struct iomap_writepage_ctx *wpc)
 
 	while ((folio = writeback_iter(mapping, wpc->wbc, folio, &error)))
 		error = iomap_writepage_map(wpc, folio);
-	return iomap_submit_ioend(wpc, error);
+
+	/*
+	 * If @error is non-zero, it means that we have a situation where some
+	 * part of the submission process has failed after we've marked pages
+	 * for writeback.
+	 *
+	 * We cannot cancel the writeback directly in that case, so always call
+	 * ->writeback_submit to run the I/O completion handler to clear the
+	 * writeback bit and let the file system proess the errors.
+	 */
+	if (wpc->wb_ctx)
+		return wpc->ops->writeback_submit(wpc, error);
+	return error;
 }
 EXPORT_SYMBOL_GPL(iomap_writepages);
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index f6d44ab78442..1ee4f835ac3c 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -514,41 +514,40 @@ xfs_ioend_needs_wq_completion(
 }
 
 static int
-xfs_submit_ioend(
-	struct iomap_writepage_ctx *wpc,
-	int			status)
+xfs_writeback_submit(
+	struct iomap_writepage_ctx	*wpc,
+	int				error)
 {
-	struct iomap_ioend	*ioend = wpc->ioend;
-	unsigned int		nofs_flag;
+	struct iomap_ioend		*ioend = wpc->wb_ctx;
 
 	/*
-	 * We can allocate memory here while doing writeback on behalf of
-	 * memory reclaim.  To avoid memory allocation deadlocks set the
-	 * task-wide nofs context for the following operations.
+	 * Convert CoW extents to regular.
+	 *
+	 * We can allocate memory here while doing writeback on behalf of memory
+	 * reclaim.  To avoid memory allocation deadlocks, set the task-wide
+	 * nofs context.
 	 */
-	nofs_flag = memalloc_nofs_save();
+	if (!error && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
+		unsigned int		nofs_flag;
 
-	/* Convert CoW extents to regular */
-	if (!status && (ioend->io_flags & IOMAP_IOEND_SHARED)) {
-		status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
+		nofs_flag = memalloc_nofs_save();
+		error = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
 				ioend->io_offset, ioend->io_size);
+		memalloc_nofs_restore(nofs_flag);
 	}
 
-	memalloc_nofs_restore(nofs_flag);
-
-	/* send ioends that might require a transaction to the completion wq */
+	/*
+	 * Send ioends that might require a transaction to the completion wq.
+	 */
 	if (xfs_ioend_needs_wq_completion(ioend))
 		ioend->io_bio.bi_end_io = xfs_end_bio;
 
-	if (status)
-		return status;
-	submit_bio(&ioend->io_bio);
-	return 0;
+	return iomap_ioend_writeback_submit(wpc, error);
 }
 
 static const struct iomap_writeback_ops xfs_writeback_ops = {
 	.writeback_range	= xfs_writeback_range,
-	.submit_ioend		= xfs_submit_ioend,
+	.writeback_submit	= xfs_writeback_submit,
 };
 
 struct xfs_zoned_writepage_ctx {
@@ -646,20 +645,25 @@ xfs_zoned_writeback_range(
 }
 
 static int
-xfs_zoned_submit_ioend(
-	struct iomap_writepage_ctx *wpc,
-	int			status)
+xfs_zoned_writeback_submit(
+	struct iomap_writepage_ctx	*wpc,
+	int				error)
 {
-	wpc->ioend->io_bio.bi_end_io = xfs_end_bio;
-	if (status)
-		return status;
-	xfs_zone_alloc_and_submit(wpc->ioend, &XFS_ZWPC(wpc)->open_zone);
+	struct iomap_ioend		*ioend = wpc->wb_ctx;
+
+	ioend->io_bio.bi_end_io = xfs_end_bio;
+	if (error) {
+		ioend->io_bio.bi_status = errno_to_blk_status(error);
+		bio_endio(&ioend->io_bio);
+		return error;
+	}
+	xfs_zone_alloc_and_submit(ioend, &XFS_ZWPC(wpc)->open_zone);
 	return 0;
 }
 
 static const struct iomap_writeback_ops xfs_zoned_writeback_ops = {
 	.writeback_range	= xfs_zoned_writeback_range,
-	.submit_ioend		= xfs_zoned_submit_ioend,
+	.writeback_submit	= xfs_zoned_writeback_submit,
 };
 
 STATIC int
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index c88e2c851753..fee9403ad49b 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -151,6 +151,7 @@ static ssize_t zonefs_writeback_range(struct iomap_writepage_ctx *wpc,
 
 static const struct iomap_writeback_ops zonefs_writeback_ops = {
 	.writeback_range	= zonefs_writeback_range,
+	.writeback_submit	= iomap_ioend_writeback_submit,
 };
 
 static int zonefs_writepages(struct address_space *mapping,
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 625d7911a2b5..9f32dd8dc075 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -391,8 +391,7 @@ sector_t iomap_bmap(struct address_space *mapping, sector_t bno,
 /*
  * Structure for writeback I/O completions.
  *
- * File systems implementing ->submit_ioend (for buffered I/O) or ->submit_io
- * for direct I/O) can split a bio generated by iomap.  In that case the parent
+ * File systems can split a bio generated by iomap.  In that case the parent
  * ioend it was split from is recorded in ioend->io_parent.
  */
 struct iomap_ioend {
@@ -416,7 +415,7 @@ static inline struct iomap_ioend *iomap_ioend_from_bio(struct bio *bio)
 
 struct iomap_writeback_ops {
 	/*
-	 * Required, performs writeback on the passed in range
+	 * Performs writeback on the passed in range
 	 *
 	 * Can map arbitrarily large regions, but we need to call into it at
 	 * least once per folio to allow the file systems to synchronize with
@@ -432,23 +431,22 @@ struct iomap_writeback_ops {
 			u64 end_pos);
 
 	/*
-	 * Optional, allows the file systems to hook into bio submission,
-	 * including overriding the bi_end_io handler.
+	 * Submit a writeback context previously build up by ->writeback_range.
 	 *
-	 * Returns 0 if the bio was successfully submitted, or a negative
-	 * error code if status was non-zero or another error happened and
-	 * the bio could not be submitted.
+	 * Returns 0 if the context was successfully submitted, or a negative
+	 * error code if not.  If @error is non-zero a failure occurred, and
+	 * the writeback context should be completed with an error.
 	 */
-	int (*submit_ioend)(struct iomap_writepage_ctx *wpc, int status);
+	int (*writeback_submit)(struct iomap_writepage_ctx *wpc, int error);
 };
 
 struct iomap_writepage_ctx {
 	struct iomap		iomap;
 	struct inode		*inode;
 	struct writeback_control *wbc;
-	struct iomap_ioend	*ioend;
 	const struct iomap_writeback_ops *ops;
 	u32			nr_folios;	/* folios added to the ioend */
+	void			*wb_ctx;	/* pending writeback context */
 };
 
 struct iomap_ioend *iomap_init_ioend(struct inode *inode, struct bio *bio,
@@ -461,6 +459,7 @@ void iomap_ioend_try_merge(struct iomap_ioend *ioend,
 void iomap_sort_ioends(struct list_head *ioend_list);
 ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 		loff_t pos, loff_t end_pos, unsigned int dirty_len);
+int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error);
 
 int iomap_writepages(struct iomap_writepage_ctx *wpc);
 
-- 
cgit v1.2.3


From 9caf1ea80cedf7d35d9371c44fbe5f84b0da667a Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Thu, 10 Jul 2025 15:33:30 +0200
Subject: iomap: add public helpers for uptodate state manipulation

Add a new iomap_start_folio_write helper to abstract away the
write_bytes_pending handling, and export it and the existing
iomap_finish_folio_write for non-iomap writeback in fuse.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
[hch: split from a larger patch]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250710133343.399917-7-hch@lst.de
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 20 +++++++++++++++-----
 include/linux/iomap.h  |  5 +++++
 2 files changed, 20 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 650a67b7d223..060bfcc353da 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1527,7 +1527,18 @@ out_unlock:
 }
 EXPORT_SYMBOL_GPL(iomap_page_mkwrite);
 
-static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
+void iomap_start_folio_write(struct inode *inode, struct folio *folio,
+		size_t len)
+{
+	struct iomap_folio_state *ifs = folio->private;
+
+	WARN_ON_ONCE(i_blocks_per_folio(inode, folio) > 1 && !ifs);
+	if (ifs)
+		atomic_add(len, &ifs->write_bytes_pending);
+}
+EXPORT_SYMBOL_GPL(iomap_start_folio_write);
+
+void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
 		size_t len)
 {
 	struct iomap_folio_state *ifs = folio->private;
@@ -1538,6 +1549,7 @@ static void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
 	if (!ifs || atomic_sub_and_test(len, &ifs->write_bytes_pending))
 		folio_end_writeback(folio);
 }
+EXPORT_SYMBOL_GPL(iomap_finish_folio_write);
 
 /*
  * We're now finished for good with this ioend structure.  Update the page
@@ -1660,7 +1672,6 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 		loff_t pos, loff_t end_pos, unsigned int dirty_len)
 {
 	struct iomap_ioend *ioend = wpc->wb_ctx;
-	struct iomap_folio_state *ifs = folio->private;
 	size_t poff = offset_in_folio(folio, pos);
 	unsigned int ioend_flags = 0;
 	unsigned int map_len = min_t(u64, dirty_len,
@@ -1703,8 +1714,7 @@ new_ioend:
 	if (!bio_add_folio(&ioend->io_bio, folio, map_len, poff))
 		goto new_ioend;
 
-	if (ifs)
-		atomic_add(map_len, &ifs->write_bytes_pending);
+	iomap_start_folio_write(wpc->inode, folio, map_len);
 
 	/*
 	 * Clamp io_offset and io_size to the incore EOF so that ondisk
@@ -1877,7 +1887,7 @@ static int iomap_writepage_map(struct iomap_writepage_ctx *wpc,
 		 * all blocks.
 		 */
 		WARN_ON_ONCE(atomic_read(&ifs->write_bytes_pending) != 0);
-		atomic_inc(&ifs->write_bytes_pending);
+		iomap_start_folio_write(inode, folio, 1);
 	}
 
 	/*
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 9f32dd8dc075..cbf9d299a616 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -461,6 +461,11 @@ ssize_t iomap_add_to_ioend(struct iomap_writepage_ctx *wpc, struct folio *folio,
 		loff_t pos, loff_t end_pos, unsigned int dirty_len);
 int iomap_ioend_writeback_submit(struct iomap_writepage_ctx *wpc, int error);
 
+void iomap_start_folio_write(struct inode *inode, struct folio *folio,
+		size_t len);
+void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
+		size_t len);
+
 int iomap_writepages(struct iomap_writepage_ctx *wpc);
 
 /*
-- 
cgit v1.2.3


From 8b217cf779cba2b10112f6845dcbbb7e6f4b3d75 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 10 Jul 2025 15:33:34 +0200
Subject: iomap: export iomap_writeback_folio

Allow fuse to use iomap_writeback_folio for folio laundering.  Note
that the caller needs to manually submit the pending writeback context.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250710133343.399917-11-hch@lst.de
Reviewed-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/iomap/buffered-io.c | 4 ++--
 include/linux/iomap.h  | 1 +
 2 files changed, 3 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index ca45a6d1cb68..b4b398e8bd54 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -1634,8 +1634,7 @@ static bool iomap_writeback_handle_eof(struct folio *folio, struct inode *inode,
 	return true;
 }
 
-static int iomap_writeback_folio(struct iomap_writepage_ctx *wpc,
-		struct folio *folio)
+int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio)
 {
 	struct iomap_folio_state *ifs = folio->private;
 	struct inode *inode = wpc->inode;
@@ -1717,6 +1716,7 @@ static int iomap_writeback_folio(struct iomap_writepage_ctx *wpc,
 	mapping_set_error(inode->i_mapping, error);
 	return error;
 }
+EXPORT_SYMBOL_GPL(iomap_writeback_folio);
 
 int
 iomap_writepages(struct iomap_writepage_ctx *wpc)
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index cbf9d299a616..b65d3f063bb0 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -466,6 +466,7 @@ void iomap_start_folio_write(struct inode *inode, struct folio *folio,
 void iomap_finish_folio_write(struct inode *inode, struct folio *folio,
 		size_t len);
 
+int iomap_writeback_folio(struct iomap_writepage_ctx *wpc, struct folio *folio);
 int iomap_writepages(struct iomap_writepage_ctx *wpc);
 
 /*
-- 
cgit v1.2.3


From 2a5574fc57d13031f869c409181bdeadd75770e1 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 10 Jul 2025 15:33:35 +0200
Subject: iomap: replace iomap_folio_ops with iomap_write_ops

The iomap_folio_ops are only used for buffered writes, including the zero
and unshare variants.  Rename them to iomap_write_ops to better describe
the usage, and pass them through the call chain like the other operation
specific methods instead of through the iomap.

xfs_iomap_valid grows a IOMAP_HOLE check to keep the existing behavior
that never attached the folio_ops to a iomap representing a hole.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250710133343.399917-12-hch@lst.de
Acked-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Brian Foster <bfoster@redhat.com>
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/iomap/design.rst     |  3 -
 Documentation/filesystems/iomap/operations.rst |  8 +--
 block/fops.c                                   |  3 +-
 fs/gfs2/bmap.c                                 | 21 ++++---
 fs/gfs2/bmap.h                                 |  1 +
 fs/gfs2/file.c                                 |  3 +-
 fs/iomap/buffered-io.c                         | 79 ++++++++++++++------------
 fs/xfs/xfs_file.c                              |  6 +-
 fs/xfs/xfs_iomap.c                             | 12 ++--
 fs/xfs/xfs_iomap.h                             |  1 +
 fs/xfs/xfs_reflink.c                           |  3 +-
 fs/zonefs/file.c                               |  3 +-
 include/linux/iomap.h                          | 22 +++----
 13 files changed, 89 insertions(+), 76 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/iomap/design.rst b/Documentation/filesystems/iomap/design.rst
index f2df9b6df988..0f7672676c0b 100644
--- a/Documentation/filesystems/iomap/design.rst
+++ b/Documentation/filesystems/iomap/design.rst
@@ -167,7 +167,6 @@ structure below:
      struct dax_device   *dax_dev;
      void                *inline_data;
      void                *private;
-     const struct iomap_folio_ops *folio_ops;
      u64                 validity_cookie;
  };
 
@@ -292,8 +291,6 @@ The fields are as follows:
    <https://lore.kernel.org/all/20180619164137.13720-7-hch@lst.de/>`_.
    This value will be passed unchanged to ``->iomap_end``.
 
- * ``folio_ops`` will be covered in the section on pagecache operations.
-
  * ``validity_cookie`` is a magic freshness value set by the filesystem
    that should be used to detect stale mappings.
    For pagecache operations this is critical for correct operation
diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst
index 4b93c5f7841a..a9b48ce4af92 100644
--- a/Documentation/filesystems/iomap/operations.rst
+++ b/Documentation/filesystems/iomap/operations.rst
@@ -57,16 +57,12 @@ The following address space operations can be wrapped easily:
  * ``bmap``
  * ``swap_activate``
 
-``struct iomap_folio_ops``
+``struct iomap_write_ops``
 --------------------------
 
-The ``->iomap_begin`` function for pagecache operations may set the
-``struct iomap::folio_ops`` field to an ops structure to override
-default behaviors of iomap:
-
 .. code-block:: c
 
- struct iomap_folio_ops {
+ struct iomap_write_ops {
      struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos,
                                 unsigned len);
      void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied,
diff --git a/block/fops.c b/block/fops.c
index 0845737c0320..0c2c010ff303 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -723,7 +723,8 @@ blkdev_direct_write(struct kiocb *iocb, struct iov_iter *from)
 
 static ssize_t blkdev_buffered_write(struct kiocb *iocb, struct iov_iter *from)
 {
-	return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL);
+	return iomap_file_buffered_write(iocb, from, &blkdev_iomap_ops, NULL,
+			NULL);
 }
 
 /*
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index 86045d3577b7..131091520de6 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -963,12 +963,16 @@ static struct folio *
 gfs2_iomap_get_folio(struct iomap_iter *iter, loff_t pos, unsigned len)
 {
 	struct inode *inode = iter->inode;
+	struct gfs2_inode *ip = GFS2_I(inode);
 	unsigned int blockmask = i_blocksize(inode) - 1;
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	unsigned int blocks;
 	struct folio *folio;
 	int status;
 
+	if (!gfs2_is_jdata(ip) && !gfs2_is_stuffed(ip))
+		return iomap_get_folio(iter, pos, len);
+
 	blocks = ((pos & blockmask) + len + blockmask) >> inode->i_blkbits;
 	status = gfs2_trans_begin(sdp, RES_DINODE + blocks, 0);
 	if (status)
@@ -987,7 +991,7 @@ static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos,
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 
-	if (!gfs2_is_stuffed(ip))
+	if (gfs2_is_jdata(ip) && !gfs2_is_stuffed(ip))
 		gfs2_trans_add_databufs(ip->i_gl, folio,
 					offset_in_folio(folio, pos),
 					copied);
@@ -995,13 +999,14 @@ static void gfs2_iomap_put_folio(struct inode *inode, loff_t pos,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	if (tr->tr_num_buf_new)
-		__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
-
-	gfs2_trans_end(sdp);
+	if (gfs2_is_jdata(ip) || gfs2_is_stuffed(ip)) {
+		if (tr->tr_num_buf_new)
+			__mark_inode_dirty(inode, I_DIRTY_DATASYNC);
+		gfs2_trans_end(sdp);
+	}
 }
 
-static const struct iomap_folio_ops gfs2_iomap_folio_ops = {
+const struct iomap_write_ops gfs2_iomap_write_ops = {
 	.get_folio = gfs2_iomap_get_folio,
 	.put_folio = gfs2_iomap_put_folio,
 };
@@ -1078,8 +1083,6 @@ static int gfs2_iomap_begin_write(struct inode *inode, loff_t pos,
 		gfs2_trans_end(sdp);
 	}
 
-	if (gfs2_is_stuffed(ip) || gfs2_is_jdata(ip))
-		iomap->folio_ops = &gfs2_iomap_folio_ops;
 	return 0;
 
 out_trans_end:
@@ -1304,7 +1307,7 @@ static int gfs2_block_zero_range(struct inode *inode, loff_t from, loff_t length
 		return 0;
 	length = min(length, inode->i_size - from);
 	return iomap_zero_range(inode, from, length, NULL, &gfs2_iomap_ops,
-			NULL);
+			&gfs2_iomap_write_ops, NULL);
 }
 
 #define GFS2_JTRUNC_REVOKES 8192
diff --git a/fs/gfs2/bmap.h b/fs/gfs2/bmap.h
index 4e8b1e8ebdf3..6cdc72dd55a3 100644
--- a/fs/gfs2/bmap.h
+++ b/fs/gfs2/bmap.h
@@ -44,6 +44,7 @@ static inline void gfs2_write_calc_reserv(const struct gfs2_inode *ip,
 }
 
 extern const struct iomap_ops gfs2_iomap_ops;
+extern const struct iomap_write_ops gfs2_iomap_write_ops;
 extern const struct iomap_writeback_ops gfs2_writeback_ops;
 
 int gfs2_unstuff_dinode(struct gfs2_inode *ip);
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index fd1147aa3891..2908f5bee21d 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -1058,7 +1058,8 @@ retry:
 	}
 
 	pagefault_disable();
-	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops, NULL);
+	ret = iomap_file_buffered_write(iocb, from, &gfs2_iomap_ops,
+			&gfs2_iomap_write_ops, NULL);
 	pagefault_enable();
 	if (ret > 0)
 		written += ret;
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index b4b398e8bd54..9f2cc5dd7e80 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -733,28 +733,27 @@ static int __iomap_write_begin(const struct iomap_iter *iter, size_t len,
 	return 0;
 }
 
-static struct folio *__iomap_get_folio(struct iomap_iter *iter, size_t len)
+static struct folio *__iomap_get_folio(struct iomap_iter *iter,
+		const struct iomap_write_ops *write_ops, size_t len)
 {
-	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
 	loff_t pos = iter->pos;
 
 	if (!mapping_large_folio_support(iter->inode->i_mapping))
 		len = min_t(size_t, len, PAGE_SIZE - offset_in_page(pos));
 
-	if (folio_ops && folio_ops->get_folio)
-		return folio_ops->get_folio(iter, pos, len);
-	else
-		return iomap_get_folio(iter, pos, len);
+	if (write_ops && write_ops->get_folio)
+		return write_ops->get_folio(iter, pos, len);
+	return iomap_get_folio(iter, pos, len);
 }
 
-static void __iomap_put_folio(struct iomap_iter *iter, size_t ret,
+static void __iomap_put_folio(struct iomap_iter *iter,
+		const struct iomap_write_ops *write_ops, size_t ret,
 		struct folio *folio)
 {
-	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
 	loff_t pos = iter->pos;
 
-	if (folio_ops && folio_ops->put_folio) {
-		folio_ops->put_folio(iter->inode, pos, ret, folio);
+	if (write_ops && write_ops->put_folio) {
+		write_ops->put_folio(iter->inode, pos, ret, folio);
 	} else {
 		folio_unlock(folio);
 		folio_put(folio);
@@ -791,10 +790,10 @@ static int iomap_write_begin_inline(const struct iomap_iter *iter,
  * offset, and length. Callers can optionally pass a max length *plen,
  * otherwise init to zero.
  */
-static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
+static int iomap_write_begin(struct iomap_iter *iter,
+		const struct iomap_write_ops *write_ops, struct folio **foliop,
 		size_t *poffset, u64 *plen)
 {
-	const struct iomap_folio_ops *folio_ops = iter->iomap.folio_ops;
 	const struct iomap *srcmap = iomap_iter_srcmap(iter);
 	loff_t pos = iter->pos;
 	u64 len = min_t(u64, SIZE_MAX, iomap_length(iter));
@@ -809,7 +808,7 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
 	if (fatal_signal_pending(current))
 		return -EINTR;
 
-	folio = __iomap_get_folio(iter, len);
+	folio = __iomap_get_folio(iter, write_ops, len);
 	if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
@@ -823,8 +822,8 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
 	 * could do the wrong thing here (zero a page range incorrectly or fail
 	 * to zero) and corrupt data.
 	 */
-	if (folio_ops && folio_ops->iomap_valid) {
-		bool iomap_valid = folio_ops->iomap_valid(iter->inode,
+	if (write_ops && write_ops->iomap_valid) {
+		bool iomap_valid = write_ops->iomap_valid(iter->inode,
 							 &iter->iomap);
 		if (!iomap_valid) {
 			iter->iomap.flags |= IOMAP_F_STALE;
@@ -850,8 +849,7 @@ static int iomap_write_begin(struct iomap_iter *iter, struct folio **foliop,
 	return 0;
 
 out_unlock:
-	__iomap_put_folio(iter, 0, folio);
-
+	__iomap_put_folio(iter, write_ops, 0, folio);
 	return status;
 }
 
@@ -923,7 +921,8 @@ static bool iomap_write_end(struct iomap_iter *iter, size_t len, size_t copied,
 	return __iomap_write_end(iter->inode, pos, len, copied, folio);
 }
 
-static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i)
+static int iomap_write_iter(struct iomap_iter *iter, struct iov_iter *i,
+		const struct iomap_write_ops *write_ops)
 {
 	ssize_t total_written = 0;
 	int status = 0;
@@ -967,7 +966,8 @@ retry:
 			break;
 		}
 
-		status = iomap_write_begin(iter, &folio, &offset, &bytes);
+		status = iomap_write_begin(iter, write_ops, &folio, &offset,
+				&bytes);
 		if (unlikely(status)) {
 			iomap_write_failed(iter->inode, iter->pos, bytes);
 			break;
@@ -996,7 +996,7 @@ retry:
 			i_size_write(iter->inode, pos + written);
 			iter->iomap.flags |= IOMAP_F_SIZE_CHANGED;
 		}
-		__iomap_put_folio(iter, written, folio);
+		__iomap_put_folio(iter, write_ops, written, folio);
 
 		if (old_size < pos)
 			pagecache_isize_extended(iter->inode, old_size, pos);
@@ -1029,7 +1029,8 @@ retry:
 
 ssize_t
 iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
-		const struct iomap_ops *ops, void *private)
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private)
 {
 	struct iomap_iter iter = {
 		.inode		= iocb->ki_filp->f_mapping->host,
@@ -1046,7 +1047,7 @@ iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *i,
 		iter.flags |= IOMAP_DONTCACHE;
 
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.status = iomap_write_iter(&iter, i);
+		iter.status = iomap_write_iter(&iter, i, write_ops);
 
 	if (unlikely(iter.pos == iocb->ki_pos))
 		return ret;
@@ -1280,7 +1281,8 @@ void iomap_write_delalloc_release(struct inode *inode, loff_t start_byte,
 }
 EXPORT_SYMBOL_GPL(iomap_write_delalloc_release);
 
-static int iomap_unshare_iter(struct iomap_iter *iter)
+static int iomap_unshare_iter(struct iomap_iter *iter,
+		const struct iomap_write_ops *write_ops)
 {
 	struct iomap *iomap = &iter->iomap;
 	u64 bytes = iomap_length(iter);
@@ -1295,14 +1297,15 @@ static int iomap_unshare_iter(struct iomap_iter *iter)
 		bool ret;
 
 		bytes = min_t(u64, SIZE_MAX, bytes);
-		status = iomap_write_begin(iter, &folio, &offset, &bytes);
+		status = iomap_write_begin(iter, write_ops, &folio, &offset,
+				&bytes);
 		if (unlikely(status))
 			return status;
 		if (iomap->flags & IOMAP_F_STALE)
 			break;
 
 		ret = iomap_write_end(iter, bytes, bytes, folio);
-		__iomap_put_folio(iter, bytes, folio);
+		__iomap_put_folio(iter, write_ops, bytes, folio);
 		if (WARN_ON_ONCE(!ret))
 			return -EIO;
 
@@ -1320,7 +1323,8 @@ static int iomap_unshare_iter(struct iomap_iter *iter)
 
 int
 iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
-		const struct iomap_ops *ops)
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops)
 {
 	struct iomap_iter iter = {
 		.inode		= inode,
@@ -1335,7 +1339,7 @@ iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
 
 	iter.len = min(len, size - pos);
 	while ((ret = iomap_iter(&iter, ops)) > 0)
-		iter.status = iomap_unshare_iter(&iter);
+		iter.status = iomap_unshare_iter(&iter, write_ops);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(iomap_file_unshare);
@@ -1354,7 +1358,8 @@ static inline int iomap_zero_iter_flush_and_stale(struct iomap_iter *i)
 	return filemap_write_and_wait_range(mapping, i->pos, end);
 }
 
-static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
+static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero,
+		const struct iomap_write_ops *write_ops)
 {
 	u64 bytes = iomap_length(iter);
 	int status;
@@ -1365,7 +1370,8 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		bool ret;
 
 		bytes = min_t(u64, SIZE_MAX, bytes);
-		status = iomap_write_begin(iter, &folio, &offset, &bytes);
+		status = iomap_write_begin(iter, write_ops, &folio, &offset,
+				&bytes);
 		if (status)
 			return status;
 		if (iter->iomap.flags & IOMAP_F_STALE)
@@ -1378,7 +1384,7 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 		folio_mark_accessed(folio);
 
 		ret = iomap_write_end(iter, bytes, bytes, folio);
-		__iomap_put_folio(iter, bytes, folio);
+		__iomap_put_folio(iter, write_ops, bytes, folio);
 		if (WARN_ON_ONCE(!ret))
 			return -EIO;
 
@@ -1394,7 +1400,8 @@ static int iomap_zero_iter(struct iomap_iter *iter, bool *did_zero)
 
 int
 iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
-		const struct iomap_ops *ops, void *private)
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private)
 {
 	struct iomap_iter iter = {
 		.inode		= inode,
@@ -1424,7 +1431,8 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 	    filemap_range_needs_writeback(mapping, pos, pos + plen - 1)) {
 		iter.len = plen;
 		while ((ret = iomap_iter(&iter, ops)) > 0)
-			iter.status = iomap_zero_iter(&iter, did_zero);
+			iter.status = iomap_zero_iter(&iter, did_zero,
+					write_ops);
 
 		iter.len = len - (iter.pos - pos);
 		if (ret || !iter.len)
@@ -1455,7 +1463,7 @@ iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
 			continue;
 		}
 
-		iter.status = iomap_zero_iter(&iter, did_zero);
+		iter.status = iomap_zero_iter(&iter, did_zero, write_ops);
 	}
 	return ret;
 }
@@ -1463,7 +1471,8 @@ EXPORT_SYMBOL_GPL(iomap_zero_range);
 
 int
 iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		const struct iomap_ops *ops, void *private)
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private)
 {
 	unsigned int blocksize = i_blocksize(inode);
 	unsigned int off = pos & (blocksize - 1);
@@ -1472,7 +1481,7 @@ iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 	if (!off)
 		return 0;
 	return iomap_zero_range(inode, pos, blocksize - off, did_zero, ops,
-			private);
+			write_ops, private);
 }
 EXPORT_SYMBOL_GPL(iomap_truncate_page);
 
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index 48254a72071b..6e0970f24df5 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -979,7 +979,8 @@ write_retry:
 
 	trace_xfs_file_buffered_write(iocb, from);
 	ret = iomap_file_buffered_write(iocb, from,
-			&xfs_buffered_write_iomap_ops, NULL);
+			&xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+			NULL);
 
 	/*
 	 * If we hit a space limit, try to free up some lingering preallocated
@@ -1059,7 +1060,8 @@ xfs_file_buffered_write_zoned(
 retry:
 	trace_xfs_file_buffered_write(iocb, from);
 	ret = iomap_file_buffered_write(iocb, from,
-			&xfs_buffered_write_iomap_ops, &ac);
+			&xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+			&ac);
 	if (ret == -ENOSPC && !cleared_space) {
 		/*
 		 * Kick off writeback to convert delalloc space and release the
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index ff05e6b1b0bb..2e94a9435002 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -79,6 +79,9 @@ xfs_iomap_valid(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 
+	if (iomap->type == IOMAP_HOLE)
+		return true;
+
 	if (iomap->validity_cookie !=
 			xfs_iomap_inode_sequence(ip, iomap->flags)) {
 		trace_xfs_iomap_invalid(ip, iomap);
@@ -89,7 +92,7 @@ xfs_iomap_valid(
 	return true;
 }
 
-static const struct iomap_folio_ops xfs_iomap_folio_ops = {
+const struct iomap_write_ops xfs_iomap_write_ops = {
 	.iomap_valid		= xfs_iomap_valid,
 };
 
@@ -151,7 +154,6 @@ xfs_bmbt_to_iomap(
 		iomap->flags |= IOMAP_F_DIRTY;
 
 	iomap->validity_cookie = sequence_cookie;
-	iomap->folio_ops = &xfs_iomap_folio_ops;
 	return 0;
 }
 
@@ -2198,7 +2200,8 @@ xfs_zero_range(
 		return dax_zero_range(inode, pos, len, did_zero,
 				      &xfs_dax_write_iomap_ops);
 	return iomap_zero_range(inode, pos, len, did_zero,
-				&xfs_buffered_write_iomap_ops, ac);
+			&xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+			ac);
 }
 
 int
@@ -2214,5 +2217,6 @@ xfs_truncate_page(
 		return dax_truncate_page(inode, pos, did_zero,
 					&xfs_dax_write_iomap_ops);
 	return iomap_truncate_page(inode, pos, did_zero,
-				   &xfs_buffered_write_iomap_ops, ac);
+			&xfs_buffered_write_iomap_ops, &xfs_iomap_write_ops,
+			ac);
 }
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 674f8ac1b9bd..ebcce7d49446 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -57,5 +57,6 @@ extern const struct iomap_ops xfs_seek_iomap_ops;
 extern const struct iomap_ops xfs_xattr_iomap_ops;
 extern const struct iomap_ops xfs_dax_write_iomap_ops;
 extern const struct iomap_ops xfs_atomic_write_cow_iomap_ops;
+extern const struct iomap_write_ops xfs_iomap_write_ops;
 
 #endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index ad3bcb76d805..3f177b4ec131 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -1881,7 +1881,8 @@ xfs_reflink_unshare(
 				&xfs_dax_write_iomap_ops);
 	else
 		error = iomap_file_unshare(inode, offset, len,
-				&xfs_buffered_write_iomap_ops);
+				&xfs_buffered_write_iomap_ops,
+				&xfs_iomap_write_ops);
 	if (error)
 		goto out;
 
diff --git a/fs/zonefs/file.c b/fs/zonefs/file.c
index fee9403ad49b..24c29c10e27f 100644
--- a/fs/zonefs/file.c
+++ b/fs/zonefs/file.c
@@ -572,7 +572,8 @@ static ssize_t zonefs_file_buffered_write(struct kiocb *iocb,
 	if (ret <= 0)
 		goto inode_unlock;
 
-	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops, NULL);
+	ret = iomap_file_buffered_write(iocb, from, &zonefs_write_iomap_ops,
+			NULL, NULL);
 	if (ret == -EIO)
 		zonefs_io_error(inode, true);
 
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index b65d3f063bb0..80f543cc4fe8 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -101,8 +101,6 @@ struct vm_fault;
  */
 #define IOMAP_NULL_ADDR -1ULL	/* addr is not valid */
 
-struct iomap_folio_ops;
-
 struct iomap {
 	u64			addr; /* disk offset of mapping, bytes */
 	loff_t			offset;	/* file offset of mapping, bytes */
@@ -113,7 +111,6 @@ struct iomap {
 	struct dax_device	*dax_dev; /* dax_dev for dax operations */
 	void			*inline_data;
 	void			*private; /* filesystem private */
-	const struct iomap_folio_ops *folio_ops;
 	u64			validity_cookie; /* used with .iomap_valid() */
 };
 
@@ -143,16 +140,11 @@ static inline bool iomap_inline_data_valid(const struct iomap *iomap)
 }
 
 /*
- * When a filesystem sets folio_ops in an iomap mapping it returns, get_folio
- * and put_folio will be called for each folio written to.  This only applies
- * to buffered writes as unbuffered writes will not typically have folios
- * associated with them.
- *
  * When get_folio succeeds, put_folio will always be called to do any
  * cleanup work necessary.  put_folio is responsible for unlocking and putting
  * @folio.
  */
-struct iomap_folio_ops {
+struct iomap_write_ops {
 	struct folio *(*get_folio)(struct iomap_iter *iter, loff_t pos,
 			unsigned len);
 	void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied,
@@ -335,7 +327,8 @@ static inline bool iomap_want_unshare_iter(const struct iomap_iter *iter)
 }
 
 ssize_t iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *from,
-		const struct iomap_ops *ops, void *private);
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private);
 int iomap_read_folio(struct folio *folio, const struct iomap_ops *ops);
 void iomap_readahead(struct readahead_control *, const struct iomap_ops *ops);
 bool iomap_is_partially_uptodate(struct folio *, size_t from, size_t count);
@@ -344,11 +337,14 @@ bool iomap_release_folio(struct folio *folio, gfp_t gfp_flags);
 void iomap_invalidate_folio(struct folio *folio, size_t offset, size_t len);
 bool iomap_dirty_folio(struct address_space *mapping, struct folio *folio);
 int iomap_file_unshare(struct inode *inode, loff_t pos, loff_t len,
-		const struct iomap_ops *ops);
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops);
 int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
-		bool *did_zero, const struct iomap_ops *ops, void *private);
+		bool *did_zero, const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		const struct iomap_ops *ops, void *private);
+		const struct iomap_ops *ops,
+		const struct iomap_write_ops *write_ops, void *private);
 vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops,
 		void *private);
 typedef void (*iomap_punch_t)(struct inode *inode, loff_t offset, loff_t length,
-- 
cgit v1.2.3


From c5690dd0197809bc5305f474a71b2e71e7eac0ff Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 10 Jul 2025 15:33:37 +0200
Subject: iomap: add read_folio_range() handler for buffered writes

Add a read_folio_range() handler for buffered writes that filesystems
may pass in if they wish to provide a custom handler for synchronously
reading in the contents of a folio.

Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
[hch: renamed to read_folio_range, pass less arguments]
Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/20250710133343.399917-14-hch@lst.de
Reviewed-by: Darrick J. Wong <djwong@kernel.org>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/iomap/operations.rst |  6 ++++++
 fs/iomap/buffered-io.c                         | 13 +++++++++----
 include/linux/iomap.h                          | 10 ++++++++++
 3 files changed, 25 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/iomap/operations.rst b/Documentation/filesystems/iomap/operations.rst
index a9b48ce4af92..067ed8e14ef3 100644
--- a/Documentation/filesystems/iomap/operations.rst
+++ b/Documentation/filesystems/iomap/operations.rst
@@ -68,6 +68,8 @@ The following address space operations can be wrapped easily:
      void (*put_folio)(struct inode *inode, loff_t pos, unsigned copied,
                        struct folio *folio);
      bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap);
+     int (*read_folio_range)(const struct iomap_iter *iter,
+     			struct folio *folio, loff_t pos, size_t len);
  };
 
 iomap calls these functions:
@@ -123,6 +125,10 @@ iomap calls these functions:
     ``->iomap_valid``, then the iomap should considered stale and the
     validation failed.
 
+  - ``read_folio_range``: Called to synchronously read in the range that will
+    be written to. If this function is not provided, iomap will default to
+    submitting a bio read request.
+
 These ``struct kiocb`` flags are significant for buffered I/O with iomap:
 
  * ``IOCB_NOWAIT``: Turns on ``IOMAP_NOWAIT``.
diff --git a/fs/iomap/buffered-io.c b/fs/iomap/buffered-io.c
index 8a44f56a3a80..aed4fc30a849 100644
--- a/fs/iomap/buffered-io.c
+++ b/fs/iomap/buffered-io.c
@@ -671,7 +671,8 @@ static int iomap_read_folio_range(const struct iomap_iter *iter,
 	return submit_bio_wait(&bio);
 }
 
-static int __iomap_write_begin(const struct iomap_iter *iter, size_t len,
+static int __iomap_write_begin(const struct iomap_iter *iter,
+		const struct iomap_write_ops *write_ops, size_t len,
 		struct folio *folio)
 {
 	struct iomap_folio_state *ifs;
@@ -722,8 +723,12 @@ static int __iomap_write_begin(const struct iomap_iter *iter, size_t len,
 			if (iter->flags & IOMAP_NOWAIT)
 				return -EAGAIN;
 
-			status = iomap_read_folio_range(iter, folio,
-					block_start, plen);
+			if (write_ops && write_ops->read_folio_range)
+				status = write_ops->read_folio_range(iter,
+						folio, block_start, plen);
+			else
+				status = iomap_read_folio_range(iter,
+						folio, block_start, plen);
 			if (status)
 				return status;
 		}
@@ -839,7 +844,7 @@ static int iomap_write_begin(struct iomap_iter *iter,
 	else if (srcmap->flags & IOMAP_F_BUFFER_HEAD)
 		status = __block_write_begin_int(folio, pos, len, NULL, srcmap);
 	else
-		status = __iomap_write_begin(iter, len, folio);
+		status = __iomap_write_begin(iter, write_ops, len, folio);
 
 	if (unlikely(status))
 		goto out_unlock;
diff --git a/include/linux/iomap.h b/include/linux/iomap.h
index 80f543cc4fe8..73dceabc21c8 100644
--- a/include/linux/iomap.h
+++ b/include/linux/iomap.h
@@ -166,6 +166,16 @@ struct iomap_write_ops {
 	 * locked by the iomap code.
 	 */
 	bool (*iomap_valid)(struct inode *inode, const struct iomap *iomap);
+
+	/*
+	 * Optional if the filesystem wishes to provide a custom handler for
+	 * reading in the contents of a folio, otherwise iomap will default to
+	 * submitting a bio read request.
+	 *
+	 * The read must be done synchronously.
+	 */
+	int (*read_folio_range)(const struct iomap_iter *iter,
+			struct folio *folio, loff_t pos, size_t len);
 };
 
 /*
-- 
cgit v1.2.3


From e075f4360931263f5ec006ea5dadc065e5e98eb8 Mon Sep 17 00:00:00 2001
From: Li Chen <chenl311@chinatelecom.cn>
Date: Thu, 10 Jul 2025 18:57:07 +0800
Subject: smpboot: introduce SDTL_INIT() helper to tidy sched topology setup

Define a small SDTL_INIT(maskfn, flagsfn, name) macro and use it to build the
sched_domain_topology_level array. Purely a cleanup; behaviour is unchanged.

Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Li Chen <chenl311@chinatelecom.cn>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lore.kernel.org/r/20250710105715.66594-2-me@linux.beauty
---
 arch/powerpc/kernel/smp.c      | 25 ++++++++++---------------
 arch/s390/kernel/topology.c    | 10 +++++-----
 arch/x86/kernel/smpboot.c      | 21 ++++++---------------
 include/linux/sched/topology.h |  4 ++--
 kernel/sched/topology.c        | 24 ++++++++----------------
 5 files changed, 31 insertions(+), 53 deletions(-)

(limited to 'include/linux')

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 5ac7084eebc0..f59e4b9cc207 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -1700,28 +1700,23 @@ static void __init build_sched_topology(void)
 #ifdef CONFIG_SCHED_SMT
 	if (has_big_cores) {
 		pr_info("Big cores detected but using small core scheduling\n");
-		powerpc_topology[i++] = (struct sched_domain_topology_level){
-			smallcore_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
-		};
+		powerpc_topology[i++] =
+			SDTL_INIT(smallcore_smt_mask, powerpc_smt_flags, SMT);
 	} else {
-		powerpc_topology[i++] = (struct sched_domain_topology_level){
-			cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
-		};
+		powerpc_topology[i++] = SDTL_INIT(cpu_smt_mask, powerpc_smt_flags, SMT);
 	}
 #endif
 	if (shared_caches) {
-		powerpc_topology[i++] = (struct sched_domain_topology_level){
-			shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE)
-		};
+		powerpc_topology[i++] =
+			SDTL_INIT(shared_cache_mask, powerpc_shared_cache_flags, CACHE);
 	}
+
 	if (has_coregroup_support()) {
-		powerpc_topology[i++] = (struct sched_domain_topology_level){
-			cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC)
-		};
+		powerpc_topology[i++] =
+			SDTL_INIT(cpu_mc_mask, powerpc_shared_proc_flags, MC);
 	}
-	powerpc_topology[i++] = (struct sched_domain_topology_level){
-		cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG)
-	};
+
+	powerpc_topology[i++] = SDTL_INIT(cpu_cpu_mask, powerpc_shared_proc_flags, PKG);
 
 	/* There must be one trailing NULL entry left.  */
 	BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);
diff --git a/arch/s390/kernel/topology.c b/arch/s390/kernel/topology.c
index 3df048e190b1..46569b8e47dd 100644
--- a/arch/s390/kernel/topology.c
+++ b/arch/s390/kernel/topology.c
@@ -531,11 +531,11 @@ static const struct cpumask *cpu_drawer_mask(int cpu)
 }
 
 static struct sched_domain_topology_level s390_topology[] = {
-	{ cpu_thread_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
-	{ cpu_book_mask, SD_INIT_NAME(BOOK) },
-	{ cpu_drawer_mask, SD_INIT_NAME(DRAWER) },
-	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
+	SDTL_INIT(cpu_thread_mask, cpu_smt_flags, SMT),
+	SDTL_INIT(cpu_coregroup_mask, cpu_core_flags, MC),
+	SDTL_INIT(cpu_book_mask, NULL, BOOK),
+	SDTL_INIT(cpu_drawer_mask, NULL, DRAWER),
+	SDTL_INIT(cpu_cpu_mask, NULL, PKG),
 	{ NULL, },
 };
 
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index fc78c2325fd2..e0adf75f617a 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -485,35 +485,26 @@ static void __init build_sched_topology(void)
 	int i = 0;
 
 #ifdef CONFIG_SCHED_SMT
-	x86_topology[i++] = (struct sched_domain_topology_level){
-		cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT)
-	};
+	x86_topology[i++] = SDTL_INIT(cpu_smt_mask, cpu_smt_flags, SMT);
 #endif
 #ifdef CONFIG_SCHED_CLUSTER
-	x86_topology[i++] = (struct sched_domain_topology_level){
-		cpu_clustergroup_mask, x86_cluster_flags, SD_INIT_NAME(CLS)
-	};
+	x86_topology[i++] = SDTL_INIT(cpu_clustergroup_mask, x86_cluster_flags, CLS);
 #endif
 #ifdef CONFIG_SCHED_MC
-	x86_topology[i++] = (struct sched_domain_topology_level){
-		cpu_coregroup_mask, x86_core_flags, SD_INIT_NAME(MC)
-	};
+	x86_topology[i++] = SDTL_INIT(cpu_coregroup_mask, x86_core_flags, MC);
 #endif
 	/*
 	 * When there is NUMA topology inside the package skip the PKG domain
 	 * since the NUMA domains will auto-magically create the right spanning
 	 * domains based on the SLIT.
 	 */
-	if (!x86_has_numa_in_package) {
-		x86_topology[i++] = (struct sched_domain_topology_level){
-			cpu_cpu_mask, x86_sched_itmt_flags, SD_INIT_NAME(PKG)
-		};
-	}
+	if (!x86_has_numa_in_package)
+		x86_topology[i++] = SDTL_INIT(cpu_cpu_mask, x86_sched_itmt_flags, PKG);
 
 	/*
 	 * There must be one trailing NULL entry left.
 	 */
-	BUG_ON(i >= ARRAY_SIZE(x86_topology)-1);
+	BUG_ON(i >= ARRAY_SIZE(x86_topology) - 1);
 
 	set_sched_topology(x86_topology);
 }
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index e54e7fa76ba6..0d5daaa277b7 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -196,8 +196,8 @@ struct sched_domain_topology_level {
 extern void __init set_sched_topology(struct sched_domain_topology_level *tl);
 extern void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio);
 
-
-# define SD_INIT_NAME(type)		.name = #type
+#define SDTL_INIT(maskfn, flagsfn, dname) ((struct sched_domain_topology_level) \
+	    { .mask = maskfn, .sd_flags = flagsfn, .name = #dname })
 
 #if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
 extern void rebuild_sched_domains_energy(void);
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index 8e06b1d22e91..d01f5a49f2e7 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -1737,17 +1737,17 @@ sd_init(struct sched_domain_topology_level *tl,
  */
 static struct sched_domain_topology_level default_topology[] = {
 #ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, cpu_smt_flags, SD_INIT_NAME(SMT) },
+	SDTL_INIT(cpu_smt_mask, cpu_smt_flags, SMT),
 #endif
 
 #ifdef CONFIG_SCHED_CLUSTER
-	{ cpu_clustergroup_mask, cpu_cluster_flags, SD_INIT_NAME(CLS) },
+	SDTL_INIT(cpu_clustergroup_mask, cpu_cluster_flags, CLS),
 #endif
 
 #ifdef CONFIG_SCHED_MC
-	{ cpu_coregroup_mask, cpu_core_flags, SD_INIT_NAME(MC) },
+	SDTL_INIT(cpu_coregroup_mask, cpu_core_flags, MC),
 #endif
-	{ cpu_cpu_mask, SD_INIT_NAME(PKG) },
+	SDTL_INIT(cpu_cpu_mask, NULL, PKG),
 	{ NULL, },
 };
 
@@ -2008,23 +2008,15 @@ void sched_init_numa(int offline_node)
 	/*
 	 * Add the NUMA identity distance, aka single NODE.
 	 */
-	tl[i++] = (struct sched_domain_topology_level){
-		.mask = sd_numa_mask,
-		.numa_level = 0,
-		SD_INIT_NAME(NODE)
-	};
+	tl[i++] = SDTL_INIT(sd_numa_mask, NULL, NODE);
 
 	/*
 	 * .. and append 'j' levels of NUMA goodness.
 	 */
 	for (j = 1; j < nr_levels; i++, j++) {
-		tl[i] = (struct sched_domain_topology_level){
-			.mask = sd_numa_mask,
-			.sd_flags = cpu_numa_flags,
-			.flags = SDTL_OVERLAP,
-			.numa_level = j,
-			SD_INIT_NAME(NUMA)
-		};
+		tl[i] = SDTL_INIT(sd_numa_mask, cpu_numa_flags, NUMA);
+		tl[i].numa_level = j;
+		tl[i].flags = SDTL_OVERLAP;
 	}
 
 	sched_domain_topology_saved = sched_domain_topology;
-- 
cgit v1.2.3


From 1eec89a671413ce38df9fe9e70f5130a9eb79a59 Mon Sep 17 00:00:00 2001
From: K Prateek Nayak <kprateek.nayak@amd.com>
Date: Fri, 11 Jul 2025 11:20:30 +0530
Subject: sched/topology: Remove sched_domain_topology_level::flags

Support for overlapping domains added in commit e3589f6c81e4 ("sched:
Allow for overlapping sched_domain spans") also allowed forcefully
setting SD_OVERLAP for !NUMA domains via FORCE_SD_OVERLAP sched_feat().

Since NUMA domains had to be presumed overlapping to ensure correct
behavior, "sched_domain_topology_level::flags" was introduced. NUMA
domains added the SDTL_OVERLAP flag would ensure SD_OVERLAP was always
added during build_sched_domains() for these domains, even when
FORCE_SD_OVERLAP was off.

Condition for adding the SD_OVERLAP flag at the aforementioned commit
was as follows:

    if (tl->flags & SDTL_OVERLAP || sched_feat(FORCE_SD_OVERLAP))
            sd->flags |= SD_OVERLAP;

The FORCE_SD_OVERLAP debug feature was removed in commit af85596c74de
("sched/topology: Remove FORCE_SD_OVERLAP") which left the NUMA domains
as the exclusive users of SDTL_OVERLAP, SD_OVERLAP, and SD_NUMA flags.

Get rid of SDTL_OVERLAP and SD_OVERLAP as they have become redundant
and instead rely on SD_NUMA to detect the only overlapping domain
currently supported. Since SDTL_OVERLAP was the only user of
"tl->flags", get rid of "sched_domain_topology_level::flags" too.

Signed-off-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/ba4dbdf8-bc37-493d-b2e0-2efb00ea3e19@amd.com
---
 include/linux/sched/sd_flags.h |  8 --------
 include/linux/sched/topology.h |  3 ---
 kernel/sched/fair.c            |  6 +++---
 kernel/sched/topology.c        | 19 ++++++++++---------
 4 files changed, 13 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/sd_flags.h b/include/linux/sched/sd_flags.h
index b04a5d04dee9..42839cfa2778 100644
--- a/include/linux/sched/sd_flags.h
+++ b/include/linux/sched/sd_flags.h
@@ -153,14 +153,6 @@ SD_FLAG(SD_ASYM_PACKING, SDF_NEEDS_GROUPS)
  */
 SD_FLAG(SD_PREFER_SIBLING, SDF_NEEDS_GROUPS)
 
-/*
- * sched_groups of this level overlap
- *
- * SHARED_PARENT: Set for all NUMA levels above NODE.
- * NEEDS_GROUPS: Overlaps can only exist with more than one group.
- */
-SD_FLAG(SD_OVERLAP, SDF_SHARED_PARENT | SDF_NEEDS_GROUPS)
-
 /*
  * Cross-node balancing
  *
diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
index 0d5daaa277b7..5263746b63e8 100644
--- a/include/linux/sched/topology.h
+++ b/include/linux/sched/topology.h
@@ -175,8 +175,6 @@ bool cpus_share_resources(int this_cpu, int that_cpu);
 typedef const struct cpumask *(*sched_domain_mask_f)(int cpu);
 typedef int (*sched_domain_flags_f)(void);
 
-#define SDTL_OVERLAP	0x01
-
 struct sd_data {
 	struct sched_domain *__percpu *sd;
 	struct sched_domain_shared *__percpu *sds;
@@ -187,7 +185,6 @@ struct sd_data {
 struct sched_domain_topology_level {
 	sched_domain_mask_f mask;
 	sched_domain_flags_f sd_flags;
-	int		    flags;
 	int		    numa_level;
 	struct sd_data      data;
 	char                *name;
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index 20a845697c1d..b9b4bbbf0af6 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -9926,9 +9926,9 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 	min_capacity = ULONG_MAX;
 	max_capacity = 0;
 
-	if (child->flags & SD_OVERLAP) {
+	if (child->flags & SD_NUMA) {
 		/*
-		 * SD_OVERLAP domains cannot assume that child groups
+		 * SD_NUMA domains cannot assume that child groups
 		 * span the current group.
 		 */
 
@@ -9941,7 +9941,7 @@ void update_group_capacity(struct sched_domain *sd, int cpu)
 		}
 	} else  {
 		/*
-		 * !SD_OVERLAP domains can assume that child groups
+		 * !SD_NUMA domains can assume that child groups
 		 * span the current group.
 		 */
 
diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
index d01f5a49f2e7..977e133bb8a4 100644
--- a/kernel/sched/topology.c
+++ b/kernel/sched/topology.c
@@ -89,7 +89,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 			break;
 		}
 
-		if (!(sd->flags & SD_OVERLAP) &&
+		if (!(sd->flags & SD_NUMA) &&
 		    cpumask_intersects(groupmask, sched_group_span(group))) {
 			printk(KERN_CONT "\n");
 			printk(KERN_ERR "ERROR: repeated CPUs\n");
@@ -102,7 +102,7 @@ static int sched_domain_debug_one(struct sched_domain *sd, int cpu, int level,
 				group->sgc->id,
 				cpumask_pr_args(sched_group_span(group)));
 
-		if ((sd->flags & SD_OVERLAP) &&
+		if ((sd->flags & SD_NUMA) &&
 		    !cpumask_equal(group_balance_mask(group), sched_group_span(group))) {
 			printk(KERN_CONT " mask=%*pbl",
 				cpumask_pr_args(group_balance_mask(group)));
@@ -1344,7 +1344,7 @@ void sched_update_asym_prefer_cpu(int cpu, int old_prio, int new_prio)
 		 * "sg->asym_prefer_cpu" to "sg->sgc->asym_prefer_cpu"
 		 * which is shared by all the overlapping groups.
 		 */
-		WARN_ON_ONCE(sd->flags & SD_OVERLAP);
+		WARN_ON_ONCE(sd->flags & SD_NUMA);
 
 		sg = sd->groups;
 		if (cpu != sg->asym_prefer_cpu) {
@@ -2016,7 +2016,6 @@ void sched_init_numa(int offline_node)
 	for (j = 1; j < nr_levels; i++, j++) {
 		tl[i] = SDTL_INIT(sd_numa_mask, cpu_numa_flags, NUMA);
 		tl[i].numa_level = j;
-		tl[i].flags = SDTL_OVERLAP;
 	}
 
 	sched_domain_topology_saved = sched_domain_topology;
@@ -2327,7 +2326,7 @@ static void __sdt_free(const struct cpumask *cpu_map)
 
 			if (sdd->sd) {
 				sd = *per_cpu_ptr(sdd->sd, j);
-				if (sd && (sd->flags & SD_OVERLAP))
+				if (sd && (sd->flags & SD_NUMA))
 					free_sched_groups(sd->groups, 0);
 				kfree(*per_cpu_ptr(sdd->sd, j));
 			}
@@ -2393,9 +2392,13 @@ static bool topology_span_sane(const struct cpumask *cpu_map)
 	id_seen = sched_domains_tmpmask2;
 
 	for_each_sd_topology(tl) {
+		int tl_common_flags = 0;
+
+		if (tl->sd_flags)
+			tl_common_flags = (*tl->sd_flags)();
 
 		/* NUMA levels are allowed to overlap */
-		if (tl->flags & SDTL_OVERLAP)
+		if (tl_common_flags & SD_NUMA)
 			continue;
 
 		cpumask_clear(covered);
@@ -2466,8 +2469,6 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 
 			if (tl == sched_domain_topology)
 				*per_cpu_ptr(d.sd, i) = sd;
-			if (tl->flags & SDTL_OVERLAP)
-				sd->flags |= SD_OVERLAP;
 			if (cpumask_equal(cpu_map, sched_domain_span(sd)))
 				break;
 		}
@@ -2480,7 +2481,7 @@ build_sched_domains(const struct cpumask *cpu_map, struct sched_domain_attr *att
 	for_each_cpu(i, cpu_map) {
 		for (sd = *per_cpu_ptr(d.sd, i); sd; sd = sd->parent) {
 			sd->span_weight = cpumask_weight(sched_domain_span(sd));
-			if (sd->flags & SD_OVERLAP) {
+			if (sd->flags & SD_NUMA) {
 				if (build_overlap_sched_groups(sd, i))
 					goto error;
 			} else {
-- 
cgit v1.2.3


From 45b9d1da6ca0d0285140f8779793b537e4560d45 Mon Sep 17 00:00:00 2001
From: Jie Zhan <zhanjie9@hisilicon.com>
Date: Mon, 23 Jun 2025 22:34:00 +0800
Subject: PM / devfreq: Allow devfreq driver to add custom sysfs ABIs

Extend the devfreq_dev_profile to allow drivers optionally create
device-specific sysfs ABIs together with other common devfreq ABIs under
the devfreq device path.

Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Huisong Li <lihuisong@huawei.com>
Signed-off-by: Jie Zhan <zhanjie9@hisilicon.com>
Signed-off-by: Chanwoo Choi <cw00.choi@samsung.com>
Link: https://patchwork.kernel.org/project/linux-pm/patch/20250623143401.4095045-2-zhanjie9@hisilicon.com/
---
 drivers/devfreq/devfreq.c | 1 +
 include/linux/devfreq.h   | 4 ++++
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/devfreq/devfreq.c b/drivers/devfreq/devfreq.c
index c5f5960e643b..2e8d01d47f69 100644
--- a/drivers/devfreq/devfreq.c
+++ b/drivers/devfreq/devfreq.c
@@ -831,6 +831,7 @@ struct devfreq *devfreq_add_device(struct device *dev,
 	mutex_lock(&devfreq->lock);
 	devfreq->dev.parent = dev;
 	devfreq->dev.class = devfreq_class;
+	devfreq->dev.groups = profile->dev_groups;
 	devfreq->dev.release = devfreq_dev_release;
 	INIT_LIST_HEAD(&devfreq->node);
 	devfreq->profile = profile;
diff --git a/include/linux/devfreq.h b/include/linux/devfreq.h
index d312ffbac4dd..dc1075dc3446 100644
--- a/include/linux/devfreq.h
+++ b/include/linux/devfreq.h
@@ -103,6 +103,8 @@ struct devfreq_dev_status {
  *
  * @is_cooling_device: A self-explanatory boolean giving the device a
  *                     cooling effect property.
+ * @dev_groups:		Optional device-specific sysfs attribute groups that to
+ *			be attached to the devfreq device.
  */
 struct devfreq_dev_profile {
 	unsigned long initial_freq;
@@ -119,6 +121,8 @@ struct devfreq_dev_profile {
 	unsigned int max_state;
 
 	bool is_cooling_device;
+
+	const struct attribute_group **dev_groups;
 };
 
 /**
-- 
cgit v1.2.3


From 25c411fce735dda29de26f58d3fce52d4824380c Mon Sep 17 00:00:00 2001
From: John Stultz <jstultz@google.com>
Date: Sat, 12 Jul 2025 03:33:42 +0000
Subject: sched: Add CONFIG_SCHED_PROXY_EXEC & boot argument to enable/disable

Add a CONFIG_SCHED_PROXY_EXEC option, along with a boot argument
sched_proxy_exec= that can be used to disable the feature at boot
time if CONFIG_SCHED_PROXY_EXEC was enabled.

Also uses this option to allow the rq->donor to be different from
rq->curr.

Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lkml.kernel.org/r/20250712033407.2383110-2-jstultz@google.com
---
 Documentation/admin-guide/kernel-parameters.txt |  5 +++++
 include/linux/sched.h                           | 13 +++++++++++
 init/Kconfig                                    | 12 ++++++++++
 kernel/sched/core.c                             | 29 +++++++++++++++++++++++++
 kernel/sched/sched.h                            | 12 ++++++++++
 5 files changed, 71 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 07e22ba5bfe3..00b835717860 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -6387,6 +6387,11 @@
 	sa1100ir	[NET]
 			See drivers/net/irda/sa1100_ir.c.
 
+	sched_proxy_exec= [KNL]
+			Enables or disables "proxy execution" style
+			solution to mutex-based priority inversion.
+			Format: <bool>
+
 	sched_verbose	[KNL,EARLY] Enables verbose scheduler debug messages.
 
 	schedstats=	[KNL,X86] Enable or disable scheduled statistics.
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 54a91261e99b..f225b6b1baa3 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1656,6 +1656,19 @@ struct task_struct {
 	randomized_struct_fields_end
 } __attribute__ ((aligned (64)));
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+DECLARE_STATIC_KEY_TRUE(__sched_proxy_exec);
+static inline bool sched_proxy_exec(void)
+{
+	return static_branch_likely(&__sched_proxy_exec);
+}
+#else
+static inline bool sched_proxy_exec(void)
+{
+	return false;
+}
+#endif
+
 #define TASK_REPORT_IDLE	(TASK_REPORT + 1)
 #define TASK_REPORT_MAX		(TASK_REPORT_IDLE << 1)
 
diff --git a/init/Kconfig b/init/Kconfig
index 965699c0a6d9..24dd42d3808d 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -878,6 +878,18 @@ config UCLAMP_BUCKETS_COUNT
 
 	  If in doubt, use the default value.
 
+config SCHED_PROXY_EXEC
+	bool "Proxy Execution"
+	# Avoid some build failures w/ PREEMPT_RT until it can be fixed
+	depends on !PREEMPT_RT
+	# Need to investigate how to inform sched_ext of split contexts
+	depends on !SCHED_CLASS_EXT
+	# Not particularly useful until we get to multi-rq proxying
+	depends on EXPERT
+	help
+	  This option enables proxy execution, a mechanism for mutex-owning
+	  tasks to inherit the scheduling context of higher priority waiters.
+
 endmenu
 
 #
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index e9c8bda84d80..dd9f5c08b563 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -119,6 +119,35 @@ EXPORT_TRACEPOINT_SYMBOL_GPL(sched_compute_energy_tp);
 
 DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+DEFINE_STATIC_KEY_TRUE(__sched_proxy_exec);
+static int __init setup_proxy_exec(char *str)
+{
+	bool proxy_enable = true;
+
+	if (*str && kstrtobool(str + 1, &proxy_enable)) {
+		pr_warn("Unable to parse sched_proxy_exec=\n");
+		return 0;
+	}
+
+	if (proxy_enable) {
+		pr_info("sched_proxy_exec enabled via boot arg\n");
+		static_branch_enable(&__sched_proxy_exec);
+	} else {
+		pr_info("sched_proxy_exec disabled via boot arg\n");
+		static_branch_disable(&__sched_proxy_exec);
+	}
+	return 1;
+}
+#else
+static int __init setup_proxy_exec(char *str)
+{
+	pr_warn("CONFIG_SCHED_PROXY_EXEC=n, so it cannot be enabled or disabled at boot time\n");
+	return 0;
+}
+#endif
+__setup("sched_proxy_exec", setup_proxy_exec);
+
 /*
  * Debugging: various feature bits
  *
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index ac953fad8c21..e53d0b87f780 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1142,10 +1142,15 @@ struct rq {
 	 */
 	unsigned long 		nr_uninterruptible;
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+	struct task_struct __rcu	*donor;  /* Scheduling context */
+	struct task_struct __rcu	*curr;   /* Execution context */
+#else
 	union {
 		struct task_struct __rcu *donor; /* Scheduler context */
 		struct task_struct __rcu *curr;  /* Execution context */
 	};
+#endif
 	struct sched_dl_entity	*dl_server;
 	struct task_struct	*idle;
 	struct task_struct	*stop;
@@ -1326,10 +1331,17 @@ DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
 #define cpu_curr(cpu)		(cpu_rq(cpu)->curr)
 #define raw_rq()		raw_cpu_ptr(&runqueues)
 
+#ifdef CONFIG_SCHED_PROXY_EXEC
+static inline void rq_set_donor(struct rq *rq, struct task_struct *t)
+{
+	rcu_assign_pointer(rq->donor, t);
+}
+#else
 static inline void rq_set_donor(struct rq *rq, struct task_struct *t)
 {
 	/* Do nothing */
 }
+#endif
 
 #ifdef CONFIG_SCHED_CORE
 static inline struct cpumask *sched_group_span(struct sched_group *sg);
-- 
cgit v1.2.3


From 44e4e0297c3c01987399bb9973f4d22a096a62c2 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Sat, 12 Jul 2025 03:33:43 +0000
Subject: locking/mutex: Rework task_struct::blocked_on

Track the blocked-on relation for mutexes, to allow following this
relation at schedule time.

   task
     | blocked-on
     v
   mutex
     | owner
     v
   task

This all will be used for tracking blocked-task/mutex chains
with the prox-execution patch in a similar fashion to how
priority inheritance is done with rt_mutexes.

For serialization, blocked-on is only set by the task itself
(current). And both when setting or clearing (potentially by
others), is done while holding the mutex::wait_lock.

[minor changes while rebasing]
[jstultz: Fix blocked_on tracking in __mutex_lock_common in error paths]
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Juri Lelli <juri.lelli@redhat.com>
Signed-off-by: Connor O'Brien <connoro@google.com>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lkml.kernel.org/r/20250712033407.2383110-3-jstultz@google.com
---
 include/linux/sched.h        |  5 +----
 kernel/fork.c                |  3 +--
 kernel/locking/mutex-debug.c |  9 +++++----
 kernel/locking/mutex.c       | 22 ++++++++++++++++++++++
 kernel/locking/ww_mutex.h    | 18 ++++++++++++++++--
 5 files changed, 45 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index f225b6b1baa3..33ad240ec900 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1230,10 +1230,7 @@ struct task_struct {
 	struct rt_mutex_waiter		*pi_blocked_on;
 #endif
 
-#ifdef CONFIG_DEBUG_MUTEXES
-	/* Mutex deadlock detection: */
-	struct mutex_waiter		*blocked_on;
-#endif
+	struct mutex			*blocked_on;	/* lock we're blocked on */
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 	/*
diff --git a/kernel/fork.c b/kernel/fork.c
index 1ee8eb11f38b..5f87f05aff4a 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -2123,9 +2123,8 @@ __latent_entropy struct task_struct *copy_process(
 	lockdep_init_task(p);
 #endif
 
-#ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
-#endif
+
 #ifdef CONFIG_BCACHE
 	p->sequential_io	= 0;
 	p->sequential_io_avg	= 0;
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 6e6f6071cfa2..758b7a6792b0 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -53,17 +53,18 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 {
 	lockdep_assert_held(&lock->wait_lock);
 
-	/* Mark the current thread as blocked on the lock: */
-	task->blocked_on = waiter;
+	/* Current thread can't be already blocked (since it's executing!) */
+	DEBUG_LOCKS_WARN_ON(task->blocked_on);
 }
 
 void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 			 struct task_struct *task)
 {
+	struct mutex *blocked_on = READ_ONCE(task->blocked_on);
+
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
 	DEBUG_LOCKS_WARN_ON(waiter->task != task);
-	DEBUG_LOCKS_WARN_ON(task->blocked_on != waiter);
-	task->blocked_on = NULL;
+	DEBUG_LOCKS_WARN_ON(blocked_on && blocked_on != lock);
 
 	INIT_LIST_HEAD(&waiter->list);
 	waiter->task = NULL;
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index a39ecccbd106..e2f59863a866 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -644,6 +644,8 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 			goto err_early_kill;
 	}
 
+	WARN_ON(current->blocked_on);
+	current->blocked_on = lock;
 	set_current_state(state);
 	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
@@ -680,6 +682,12 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		first = __mutex_waiter_is_first(lock, &waiter);
 
+		/*
+		 * As we likely have been woken up by task
+		 * that has cleared our blocked_on state, re-set
+		 * it to the lock we are trying to aquire.
+		 */
+		current->blocked_on = lock;
 		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
@@ -691,8 +699,11 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		if (first) {
 			trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
+			/* clear blocked_on as mutex_optimistic_spin may schedule() */
+			current->blocked_on = NULL;
 			if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
 				break;
+			current->blocked_on = lock;
 			trace_contention_begin(lock, LCB_F_MUTEX);
 		}
 
@@ -700,6 +711,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	}
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 acquired:
+	current->blocked_on = NULL;
 	__set_current_state(TASK_RUNNING);
 
 	if (ww_ctx) {
@@ -729,9 +741,11 @@ skip_wait:
 	return 0;
 
 err:
+	current->blocked_on = NULL;
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
 err_early_kill:
+	WARN_ON(current->blocked_on);
 	trace_contention_end(lock, ret);
 	raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
 	debug_mutex_free_waiter(&waiter);
@@ -942,6 +956,14 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		next = waiter->task;
 
 		debug_mutex_wake_waiter(lock, waiter);
+		/*
+		 * Unlock wakeups can be happening in parallel
+		 * (when optimistic spinners steal and release
+		 * the lock), so blocked_on may already be
+		 * cleared here.
+		 */
+		WARN_ON(next->blocked_on && next->blocked_on != lock);
+		next->blocked_on = NULL;
 		wake_q_add(&wake_q, next);
 	}
 
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 37f025a096c9..45fe05e51db1 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -283,7 +283,15 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
 	if (waiter->ww_ctx->acquired > 0 && __ww_ctx_less(waiter->ww_ctx, ww_ctx)) {
 #ifndef WW_RT
 		debug_mutex_wake_waiter(lock, waiter);
+		/*
+		 * When waking up the task to die, be sure to clear the
+		 * blocked_on pointer. Otherwise we can see circular
+		 * blocked_on relationships that can't resolve.
+		 */
+		WARN_ON(waiter->task->blocked_on &&
+			waiter->task->blocked_on != lock);
 #endif
+		waiter->task->blocked_on = NULL;
 		wake_q_add(wake_q, waiter->task);
 	}
 
@@ -331,9 +339,15 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
 		 * it's wounded in __ww_mutex_check_kill() or has a
 		 * wakeup pending to re-read the wounded state.
 		 */
-		if (owner != current)
+		if (owner != current) {
+			/*
+			 * When waking up the task to wound, be sure to clear the
+			 * blocked_on pointer. Otherwise we can see circular
+			 * blocked_on relationships that can't resolve.
+			 */
+			owner->blocked_on = NULL;
 			wake_q_add(wake_q, owner);
-
+		}
 		return true;
 	}
 
-- 
cgit v1.2.3


From a4f0b6fef4b08e9928449206390133e48ac185a7 Mon Sep 17 00:00:00 2001
From: Valentin Schneider <valentin.schneider@arm.com>
Date: Sat, 12 Jul 2025 03:33:44 +0000
Subject: locking/mutex: Add p->blocked_on wrappers for correctness checks

This lets us assert mutex::wait_lock is held whenever we access
p->blocked_on, as well as warn us for unexpected state changes.

[fix conflicts, call in more places]
[jstultz: tweaked commit subject, reworked a good bit]
Signed-off-by: Valentin Schneider <valentin.schneider@arm.com>
Signed-off-by: Connor O'Brien <connoro@google.com>
Signed-off-by: John Stultz <jstultz@google.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Link: https://lkml.kernel.org/r/20250712033407.2383110-4-jstultz@google.com
---
 include/linux/sched.h        | 64 ++++++++++++++++++++++++++++++++++++++++++--
 kernel/locking/mutex-debug.c |  4 +--
 kernel/locking/mutex.c       | 32 ++++++++++------------
 kernel/locking/ww_mutex.h    |  8 +++---
 4 files changed, 81 insertions(+), 27 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 33ad240ec900..5b4e1cd52e27 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -34,6 +34,7 @@
 #include <linux/sched/prio.h>
 #include <linux/sched/types.h>
 #include <linux/signal_types.h>
+#include <linux/spinlock.h>
 #include <linux/syscall_user_dispatch_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/netdevice_xmit.h>
@@ -2129,6 +2130,67 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
 	__cond_resched_rwlock_write(lock);					\
 })
 
+#ifndef CONFIG_PREEMPT_RT
+static inline struct mutex *__get_task_blocked_on(struct task_struct *p)
+{
+	struct mutex *m = p->blocked_on;
+
+	if (m)
+		lockdep_assert_held_once(&m->wait_lock);
+	return m;
+}
+
+static inline void __set_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	WARN_ON_ONCE(!m);
+	/* The task should only be setting itself as blocked */
+	WARN_ON_ONCE(p != current);
+	/* Currently we serialize blocked_on under the mutex::wait_lock */
+	lockdep_assert_held_once(&m->wait_lock);
+	/*
+	 * Check ensure we don't overwrite existing mutex value
+	 * with a different mutex. Note, setting it to the same
+	 * lock repeatedly is ok.
+	 */
+	WARN_ON_ONCE(p->blocked_on && p->blocked_on != m);
+	p->blocked_on = m;
+}
+
+static inline void set_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	guard(raw_spinlock_irqsave)(&m->wait_lock);
+	__set_task_blocked_on(p, m);
+}
+
+static inline void __clear_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	WARN_ON_ONCE(!m);
+	/* Currently we serialize blocked_on under the mutex::wait_lock */
+	lockdep_assert_held_once(&m->wait_lock);
+	/*
+	 * There may be cases where we re-clear already cleared
+	 * blocked_on relationships, but make sure we are not
+	 * clearing the relationship with a different lock.
+	 */
+	WARN_ON_ONCE(m && p->blocked_on && p->blocked_on != m);
+	p->blocked_on = NULL;
+}
+
+static inline void clear_task_blocked_on(struct task_struct *p, struct mutex *m)
+{
+	guard(raw_spinlock_irqsave)(&m->wait_lock);
+	__clear_task_blocked_on(p, m);
+}
+#else
+static inline void __clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m)
+{
+}
+
+static inline void clear_task_blocked_on(struct task_struct *p, struct rt_mutex *m)
+{
+}
+#endif /* !CONFIG_PREEMPT_RT */
+
 static __always_inline bool need_resched(void)
 {
 	return unlikely(tif_need_resched());
@@ -2168,8 +2230,6 @@ extern bool sched_task_on_rq(struct task_struct *p);
 extern unsigned long get_wchan(struct task_struct *p);
 extern struct task_struct *cpu_curr_snapshot(int cpu);
 
-#include <linux/spinlock.h>
-
 /*
  * In order to reduce various lock holder preemption latencies provide an
  * interface to see if a vCPU is currently running or not.
diff --git a/kernel/locking/mutex-debug.c b/kernel/locking/mutex-debug.c
index 758b7a6792b0..949103fd8e9b 100644
--- a/kernel/locking/mutex-debug.c
+++ b/kernel/locking/mutex-debug.c
@@ -54,13 +54,13 @@ void debug_mutex_add_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 	lockdep_assert_held(&lock->wait_lock);
 
 	/* Current thread can't be already blocked (since it's executing!) */
-	DEBUG_LOCKS_WARN_ON(task->blocked_on);
+	DEBUG_LOCKS_WARN_ON(__get_task_blocked_on(task));
 }
 
 void debug_mutex_remove_waiter(struct mutex *lock, struct mutex_waiter *waiter,
 			 struct task_struct *task)
 {
-	struct mutex *blocked_on = READ_ONCE(task->blocked_on);
+	struct mutex *blocked_on = __get_task_blocked_on(task);
 
 	DEBUG_LOCKS_WARN_ON(list_empty(&waiter->list));
 	DEBUG_LOCKS_WARN_ON(waiter->task != task);
diff --git a/kernel/locking/mutex.c b/kernel/locking/mutex.c
index e2f59863a866..80d778fedd60 100644
--- a/kernel/locking/mutex.c
+++ b/kernel/locking/mutex.c
@@ -644,8 +644,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 			goto err_early_kill;
 	}
 
-	WARN_ON(current->blocked_on);
-	current->blocked_on = lock;
+	__set_task_blocked_on(current, lock);
 	set_current_state(state);
 	trace_contention_begin(lock, LCB_F_MUTEX);
 	for (;;) {
@@ -685,9 +684,9 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 		/*
 		 * As we likely have been woken up by task
 		 * that has cleared our blocked_on state, re-set
-		 * it to the lock we are trying to aquire.
+		 * it to the lock we are trying to acquire.
 		 */
-		current->blocked_on = lock;
+		set_task_blocked_on(current, lock);
 		set_current_state(state);
 		/*
 		 * Here we order against unlock; we must either see it change
@@ -699,11 +698,15 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 
 		if (first) {
 			trace_contention_begin(lock, LCB_F_MUTEX | LCB_F_SPIN);
-			/* clear blocked_on as mutex_optimistic_spin may schedule() */
-			current->blocked_on = NULL;
+			/*
+			 * mutex_optimistic_spin() can call schedule(), so
+			 * clear blocked on so we don't become unselectable
+			 * to run.
+			 */
+			clear_task_blocked_on(current, lock);
 			if (mutex_optimistic_spin(lock, ww_ctx, &waiter))
 				break;
-			current->blocked_on = lock;
+			set_task_blocked_on(current, lock);
 			trace_contention_begin(lock, LCB_F_MUTEX);
 		}
 
@@ -711,7 +714,7 @@ __mutex_lock_common(struct mutex *lock, unsigned int state, unsigned int subclas
 	}
 	raw_spin_lock_irqsave(&lock->wait_lock, flags);
 acquired:
-	current->blocked_on = NULL;
+	__clear_task_blocked_on(current, lock);
 	__set_current_state(TASK_RUNNING);
 
 	if (ww_ctx) {
@@ -741,11 +744,11 @@ skip_wait:
 	return 0;
 
 err:
-	current->blocked_on = NULL;
+	__clear_task_blocked_on(current, lock);
 	__set_current_state(TASK_RUNNING);
 	__mutex_remove_waiter(lock, &waiter);
 err_early_kill:
-	WARN_ON(current->blocked_on);
+	WARN_ON(__get_task_blocked_on(current));
 	trace_contention_end(lock, ret);
 	raw_spin_unlock_irqrestore_wake(&lock->wait_lock, flags, &wake_q);
 	debug_mutex_free_waiter(&waiter);
@@ -956,14 +959,7 @@ static noinline void __sched __mutex_unlock_slowpath(struct mutex *lock, unsigne
 		next = waiter->task;
 
 		debug_mutex_wake_waiter(lock, waiter);
-		/*
-		 * Unlock wakeups can be happening in parallel
-		 * (when optimistic spinners steal and release
-		 * the lock), so blocked_on may already be
-		 * cleared here.
-		 */
-		WARN_ON(next->blocked_on && next->blocked_on != lock);
-		next->blocked_on = NULL;
+		__clear_task_blocked_on(next, lock);
 		wake_q_add(&wake_q, next);
 	}
 
diff --git a/kernel/locking/ww_mutex.h b/kernel/locking/ww_mutex.h
index 45fe05e51db1..086fd5487ca7 100644
--- a/kernel/locking/ww_mutex.h
+++ b/kernel/locking/ww_mutex.h
@@ -283,15 +283,13 @@ __ww_mutex_die(struct MUTEX *lock, struct MUTEX_WAITER *waiter,
 	if (waiter->ww_ctx->acquired > 0 && __ww_ctx_less(waiter->ww_ctx, ww_ctx)) {
 #ifndef WW_RT
 		debug_mutex_wake_waiter(lock, waiter);
+#endif
 		/*
 		 * When waking up the task to die, be sure to clear the
 		 * blocked_on pointer. Otherwise we can see circular
 		 * blocked_on relationships that can't resolve.
 		 */
-		WARN_ON(waiter->task->blocked_on &&
-			waiter->task->blocked_on != lock);
-#endif
-		waiter->task->blocked_on = NULL;
+		__clear_task_blocked_on(waiter->task, lock);
 		wake_q_add(wake_q, waiter->task);
 	}
 
@@ -345,7 +343,7 @@ static bool __ww_mutex_wound(struct MUTEX *lock,
 			 * blocked_on pointer. Otherwise we can see circular
 			 * blocked_on relationships that can't resolve.
 			 */
-			owner->blocked_on = NULL;
+			__clear_task_blocked_on(owner, lock);
 			wake_q_add(wake_q, owner);
 		}
 		return true;
-- 
cgit v1.2.3


From 8671bad873ebeb082afcf7b4501395c374da6023 Mon Sep 17 00:00:00 2001
From: "Luis Claudio R. Goncalves" <lgoncalv@redhat.com>
Date: Mon, 7 Jul 2025 11:03:59 -0300
Subject: sched: Do not call __put_task_struct() on rt if pi_blocked_on is set

With PREEMPT_RT enabled, some of the calls to put_task_struct() coming
from rt_mutex_adjust_prio_chain() could happen in preemptible context and
with a mutex enqueued. That could lead to this sequence:

        rt_mutex_adjust_prio_chain()
          put_task_struct()
            __put_task_struct()
              sched_ext_free()
                spin_lock_irqsave()
                  rtlock_lock() --->  TRIGGERS
                                      lockdep_assert(!current->pi_blocked_on);

This is not a SCHED_EXT bug. The first cleanup function called by
__put_task_struct() is sched_ext_free() and it happens to take a
(RT) spin_lock, which in the scenario described above, would trigger
the lockdep assertion of "!current->pi_blocked_on".

Crystal Wood was able to identify the problem as __put_task_struct()
being called during rt_mutex_adjust_prio_chain(), in the context of
a process with a mutex enqueued.

Instead of adding more complex conditions to decide when to directly
call __put_task_struct() and when to defer the call, unconditionally
resort to the deferred call on PREEMPT_RT to simplify the code.

Fixes: 893cdaaa3977 ("sched: avoid false lockdep splat in put_task_struct()")
Suggested-by: Crystal Wood <crwood@redhat.com>
Signed-off-by: Luis Claudio R. Goncalves <lgoncalv@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Wander Lairson Costa <wander@redhat.com>
Reviewed-by: Valentin Schneider <vschneid@redhat.com>
Reviewed-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Link: https://lore.kernel.org/r/aGvTz5VaPFyj0pBV@uudg.org
---
 include/linux/sched/task.h | 27 ++++++++++-----------------
 1 file changed, 10 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/task.h b/include/linux/sched/task.h
index c517dbc242f7..ea41795a352b 100644
--- a/include/linux/sched/task.h
+++ b/include/linux/sched/task.h
@@ -131,24 +131,17 @@ static inline void put_task_struct(struct task_struct *t)
 		return;
 
 	/*
-	 * In !RT, it is always safe to call __put_task_struct().
-	 * Under RT, we can only call it in preemptible context.
-	 */
-	if (!IS_ENABLED(CONFIG_PREEMPT_RT) || preemptible()) {
-		static DEFINE_WAIT_OVERRIDE_MAP(put_task_map, LD_WAIT_SLEEP);
-
-		lock_map_acquire_try(&put_task_map);
-		__put_task_struct(t);
-		lock_map_release(&put_task_map);
-		return;
-	}
-
-	/*
-	 * under PREEMPT_RT, we can't call put_task_struct
+	 * Under PREEMPT_RT, we can't call __put_task_struct
 	 * in atomic context because it will indirectly
-	 * acquire sleeping locks.
+	 * acquire sleeping locks. The same is true if the
+	 * current process has a mutex enqueued (blocked on
+	 * a PI chain).
+	 *
+	 * In !RT, it is always safe to call __put_task_struct().
+	 * Though, in order to simplify the code, resort to the
+	 * deferred call too.
 	 *
-	 * call_rcu() will schedule delayed_put_task_struct_rcu()
+	 * call_rcu() will schedule __put_task_struct_rcu_cb()
 	 * to be called in process context.
 	 *
 	 * __put_task_struct() is called when
@@ -161,7 +154,7 @@ static inline void put_task_struct(struct task_struct *t)
 	 *
 	 * delayed_free_task() also uses ->rcu, but it is only called
 	 * when it fails to fork a process. Therefore, there is no
-	 * way it can conflict with put_task_struct().
+	 * way it can conflict with __put_task_struct().
 	 */
 	call_rcu(&t->rcu, __put_task_struct_rcu_cb);
 }
-- 
cgit v1.2.3


From 8d43417e93073699b521f603286140415b24968b Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Thu, 15 May 2025 13:48:45 +0200
Subject: sunrpc: simplify xdr_init_encode_pages

The rqst argument to xdr_init_encode_pages is set to NULL by all callers,
and pages is always set to buf->pages.  Remove the two arguments and
hardcode the assignments.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 fs/nfsd/nfs3proc.c         |  2 +-
 fs/nfsd/nfsproc.c          |  2 +-
 include/linux/sunrpc/xdr.h |  3 +--
 net/sunrpc/xdr.c           | 11 ++++-------
 4 files changed, 7 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index a817d8485d21..b6d03e1ef5f7 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -561,7 +561,7 @@ static void nfsd3_init_dirlist_pages(struct svc_rqst *rqstp,
 	buf->pages = rqstp->rq_next_page;
 	rqstp->rq_next_page += (buf->buflen + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	xdr_init_encode_pages(xdr, buf, buf->pages,  NULL);
+	xdr_init_encode_pages(xdr, buf);
 }
 
 /*
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index c10fa8128a8a..8f71f5748c75 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -575,7 +575,7 @@ static void nfsd_init_dirlist_pages(struct svc_rqst *rqstp,
 	buf->pages = rqstp->rq_next_page;
 	rqstp->rq_next_page++;
 
-	xdr_init_encode_pages(xdr, buf, buf->pages,  NULL);
+	xdr_init_encode_pages(xdr, buf);
 }
 
 /*
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index a2ab813a9800..29d3a7659727 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -242,8 +242,7 @@ typedef int	(*kxdrdproc_t)(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
 
 extern void xdr_init_encode(struct xdr_stream *xdr, struct xdr_buf *buf,
 			    __be32 *p, struct rpc_rqst *rqst);
-extern void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
-			   struct page **pages, struct rpc_rqst *rqst);
+void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf);
 extern __be32 *xdr_reserve_space(struct xdr_stream *xdr, size_t nbytes);
 extern int xdr_reserve_space_vec(struct xdr_stream *xdr, size_t nbytes);
 extern void __xdr_commit_encode(struct xdr_stream *xdr);
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 2ea00e354ba6..1346fdf33835 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -993,21 +993,18 @@ EXPORT_SYMBOL_GPL(xdr_init_encode);
  * xdr_init_encode_pages - Initialize an xdr_stream for encoding into pages
  * @xdr: pointer to xdr_stream struct
  * @buf: pointer to XDR buffer into which to encode data
- * @pages: list of pages to decode into
- * @rqst: pointer to controlling rpc_rqst, for debugging
  *
  */
-void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf,
-			   struct page **pages, struct rpc_rqst *rqst)
+void xdr_init_encode_pages(struct xdr_stream *xdr, struct xdr_buf *buf)
 {
 	xdr_reset_scratch_buffer(xdr);
 
 	xdr->buf = buf;
-	xdr->page_ptr = pages;
+	xdr->page_ptr = buf->pages;
 	xdr->iov = NULL;
-	xdr->p = page_address(*pages);
+	xdr->p = page_address(*xdr->page_ptr);
 	xdr->end = (void *)xdr->p + min_t(u32, buf->buflen, PAGE_SIZE);
-	xdr->rqst = rqst;
+	xdr->rqst = NULL;
 }
 EXPORT_SYMBOL_GPL(xdr_init_encode_pages);
 
-- 
cgit v1.2.3


From d49afc90a3ba3af4507049fb43cb128d9a9c66d5 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 20 Jun 2025 08:16:01 -0400
Subject: sunrpc: fix handling of unknown auth status codes

In the case of an unknown error code from svc_authenticate or
pg_authenticate, return AUTH_ERROR with a status of AUTH_FAILED. Also
add the other auth_stat value from RFC 5531, and document all the status
codes.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/msg_prot.h | 18 ++++++++++--------
 include/linux/sunrpc/xdr.h      |  2 ++
 net/sunrpc/svc.c                |  3 ++-
 3 files changed, 14 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/msg_prot.h b/include/linux/sunrpc/msg_prot.h
index c4b0eb2b2f04..ada17b57ca44 100644
--- a/include/linux/sunrpc/msg_prot.h
+++ b/include/linux/sunrpc/msg_prot.h
@@ -69,15 +69,17 @@ enum rpc_reject_stat {
 };
 
 enum rpc_auth_stat {
-	RPC_AUTH_OK = 0,
-	RPC_AUTH_BADCRED = 1,
-	RPC_AUTH_REJECTEDCRED = 2,
-	RPC_AUTH_BADVERF = 3,
-	RPC_AUTH_REJECTEDVERF = 4,
-	RPC_AUTH_TOOWEAK = 5,
+	RPC_AUTH_OK = 0,		/* success */
+	RPC_AUTH_BADCRED = 1,		/* bad credential (seal broken) */
+	RPC_AUTH_REJECTEDCRED = 2,	/* client must begin new session */
+	RPC_AUTH_BADVERF = 3,		/* bad verifier (seal broken) */
+	RPC_AUTH_REJECTEDVERF = 4,	/* verifier expired or replayed */
+	RPC_AUTH_TOOWEAK = 5,		/* rejected for security reasons */
+	RPC_AUTH_INVALIDRESP = 6,	/* bogus response verifier */
+	RPC_AUTH_FAILED = 7,		/* reason unknown */
 	/* RPCSEC_GSS errors */
-	RPCSEC_GSS_CREDPROBLEM = 13,
-	RPCSEC_GSS_CTXPROBLEM = 14
+	RPCSEC_GSS_CREDPROBLEM = 13,	/* no credentials for user */
+	RPCSEC_GSS_CTXPROBLEM = 14	/* problem with context */
 };
 
 #define RPC_MAXNETNAMELEN	256
diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index 29d3a7659727..e3358c630ba1 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -119,6 +119,8 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
 #define	rpc_autherr_badverf	cpu_to_be32(RPC_AUTH_BADVERF)
 #define	rpc_autherr_rejectedverf cpu_to_be32(RPC_AUTH_REJECTEDVERF)
 #define	rpc_autherr_tooweak	cpu_to_be32(RPC_AUTH_TOOWEAK)
+#define	rpc_autherr_invalidresp	cpu_to_be32(RPC_AUTH_INVALIDRESP)
+#define	rpc_autherr_failed	cpu_to_be32(RPC_AUTH_FAILED)
 #define	rpcsec_gsserr_credproblem	cpu_to_be32(RPCSEC_GSS_CREDPROBLEM)
 #define	rpcsec_gsserr_ctxproblem	cpu_to_be32(RPCSEC_GSS_CTXPROBLEM)
 
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 9abdbcbf2473..195fb0bea841 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1387,7 +1387,8 @@ svc_process_common(struct svc_rqst *rqstp)
 		goto sendit;
 	default:
 		pr_warn_once("Unexpected svc_auth_status (%d)\n", auth_res);
-		goto err_system_err;
+		rqstp->rq_auth_stat = rpc_autherr_failed;
+		goto err_bad_auth;
 	}
 
 	if (progp == NULL)
-- 
cgit v1.2.3


From 6f0e26243b02f440938ab7a3782eb730f2247fb1 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 20 Jun 2025 08:16:02 -0400
Subject: sunrpc: remove SVC_SYSERR

Nothing returns this error code.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svcauth.h | 1 -
 include/trace/events/sunrpc.h  | 2 --
 net/sunrpc/svc.c               | 8 --------
 3 files changed, 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svcauth.h b/include/linux/sunrpc/svcauth.h
index 2e111153f7cd..4b92fec23a49 100644
--- a/include/linux/sunrpc/svcauth.h
+++ b/include/linux/sunrpc/svcauth.h
@@ -86,7 +86,6 @@ struct auth_domain {
 
 enum svc_auth_status {
 	SVC_GARBAGE = 1,
-	SVC_SYSERR,
 	SVC_VALID,
 	SVC_NEGATIVE,
 	SVC_OK,
diff --git a/include/trace/events/sunrpc.h b/include/trace/events/sunrpc.h
index ff11fa07cbe3..750ecce56930 100644
--- a/include/trace/events/sunrpc.h
+++ b/include/trace/events/sunrpc.h
@@ -1691,7 +1691,6 @@ SVC_RQST_FLAG_LIST
 		__print_flags(flags, "|", SVC_RQST_FLAG_LIST)
 
 TRACE_DEFINE_ENUM(SVC_GARBAGE);
-TRACE_DEFINE_ENUM(SVC_SYSERR);
 TRACE_DEFINE_ENUM(SVC_VALID);
 TRACE_DEFINE_ENUM(SVC_NEGATIVE);
 TRACE_DEFINE_ENUM(SVC_OK);
@@ -1704,7 +1703,6 @@ TRACE_DEFINE_ENUM(SVC_COMPLETE);
 #define show_svc_auth_status(status)			\
 	__print_symbolic(status,			\
 		{ SVC_GARBAGE,	"SVC_GARBAGE" },	\
-		{ SVC_SYSERR,	"SVC_SYSERR" },		\
 		{ SVC_VALID,	"SVC_VALID" },		\
 		{ SVC_NEGATIVE,	"SVC_NEGATIVE" },	\
 		{ SVC_OK,	"SVC_OK" },		\
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 195fb0bea841..c6ceacedae28 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -1375,8 +1375,6 @@ svc_process_common(struct svc_rqst *rqstp)
 	case SVC_GARBAGE:
 		rqstp->rq_auth_stat = rpc_autherr_badcred;
 		goto err_bad_auth;
-	case SVC_SYSERR:
-		goto err_system_err;
 	case SVC_DENIED:
 		goto err_bad_auth;
 	case SVC_CLOSE:
@@ -1515,12 +1513,6 @@ err_bad_proc:
 		serv->sv_stats->rpcbadfmt++;
 	*rqstp->rq_accept_statp = rpc_proc_unavail;
 	goto sendit;
-
-err_system_err:
-	if (serv->sv_stats)
-		serv->sv_stats->rpcbadfmt++;
-	*rqstp->rq_accept_statp = rpc_system_err;
-	goto sendit;
 }
 
 /*
-- 
cgit v1.2.3


From 2bac9a4c5f452d42a78ce07596ef88f75978b536 Mon Sep 17 00:00:00 2001
From: Jeff Layton <jlayton@kernel.org>
Date: Fri, 20 Jun 2025 08:16:05 -0400
Subject: sunrpc: rearrange struct svc_rqst for fewer cachelines

This shrinks the struct by 4 bytes, but also takes it from 19 to 18
cachelines on x86_64.

Signed-off-by: Jeff Layton <jlayton@kernel.org>
Signed-off-by: Chuck Lever <chuck.lever@oracle.com>
---
 include/linux/sunrpc/svc.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/svc.h b/include/linux/sunrpc/svc.h
index 48666b83fe68..40cbe81360ed 100644
--- a/include/linux/sunrpc/svc.h
+++ b/include/linux/sunrpc/svc.h
@@ -245,10 +245,10 @@ struct svc_rqst {
 						 * initialisation success.
 						 */
 
-	unsigned long	bc_to_initval;
-	unsigned int	bc_to_retries;
-	void **			rq_lease_breaker; /* The v4 client breaking a lease */
+	unsigned long		bc_to_initval;
+	unsigned int		bc_to_retries;
 	unsigned int		rq_status_counter; /* RPC processing counter */
+	void			**rq_lease_breaker; /* The v4 client breaking a lease */
 };
 
 /* bits for rq_flags */
-- 
cgit v1.2.3


From f4312e6bfa2a98e94dacc75f96f916b76bdf4259 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Tue, 8 Jul 2025 16:05:50 -0500
Subject: idpf: implement core RDMA auxiliary dev create, init, and destroy

Add the initial idpf_idc.c file with the functions to kick off the IDC
initialization, create and initialize a core RDMA auxiliary device, and
destroy said device.

The RDMA core has a dependency on the vports being created by the
control plane before it can be initialized. Therefore, once all the
vports are up after a hard reset (either during driver load a function
level reset), the core RDMA device info will be created. It is populated
with the function type (as distinguished by the IDC initialization
function pointer), the core idc_ops function points (just stubs for
now), the reserved RDMA MSIX table, and various other info the core RDMA
auxiliary driver will need. It is then plugged on to the bus.

During a function level reset or driver unload, the device will be
unplugged from the bus and destroyed.

Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/Makefile        |   1 +
 drivers/net/ethernet/intel/idpf/idpf.h          |  12 ++
 drivers/net/ethernet/intel/idpf/idpf_dev.c      |  13 ++
 drivers/net/ethernet/intel/idpf/idpf_idc.c      | 227 ++++++++++++++++++++++++
 drivers/net/ethernet/intel/idpf/idpf_lib.c      |   4 +
 drivers/net/ethernet/intel/idpf/idpf_vf_dev.c   |  13 ++
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.c |  21 +++
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.h |   3 +
 include/linux/net/intel/iidc_rdma_idpf.h        |  28 +++
 9 files changed, 322 insertions(+)
 create mode 100644 drivers/net/ethernet/intel/idpf/idpf_idc.c
 create mode 100644 include/linux/net/intel/iidc_rdma_idpf.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/idpf/Makefile b/drivers/net/ethernet/intel/idpf/Makefile
index 83ac5e296382..4ef4b2b5e37a 100644
--- a/drivers/net/ethernet/intel/idpf/Makefile
+++ b/drivers/net/ethernet/intel/idpf/Makefile
@@ -10,6 +10,7 @@ idpf-y := \
 	idpf_controlq_setup.o	\
 	idpf_dev.o		\
 	idpf_ethtool.o		\
+	idpf_idc.o		\
 	idpf_lib.o		\
 	idpf_main.o		\
 	idpf_txrx.o		\
diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index d9f06764aba0..dd2aa515a31b 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -18,6 +18,9 @@ struct idpf_vport_max_q;
 #include <linux/ethtool_netlink.h>
 #include <net/gro.h>
 
+#include <linux/net/intel/iidc_rdma.h>
+#include <linux/net/intel/iidc_rdma_idpf.h>
+
 #include "virtchnl2.h"
 #include "idpf_txrx.h"
 #include "idpf_controlq.h"
@@ -206,9 +209,12 @@ struct idpf_reg_ops {
 /**
  * struct idpf_dev_ops - Device specific operations
  * @reg_ops: Register operations
+ * @idc_init: IDC initialization
  */
 struct idpf_dev_ops {
 	struct idpf_reg_ops reg_ops;
+
+	int (*idc_init)(struct idpf_adapter *adapter);
 };
 
 /**
@@ -540,6 +546,7 @@ struct idpf_vc_xn_manager;
  * @caps: Negotiated capabilities with device
  * @vcxn_mngr: Virtchnl transaction manager
  * @dev_ops: See idpf_dev_ops
+ * @cdev_info: IDC core device info pointer
  * @num_vfs: Number of allocated VFs through sysfs. PF does not directly talk
  *	     to VFs but is used to initialize them
  * @crc_enable: Enable CRC insertion offload
@@ -599,6 +606,7 @@ struct idpf_adapter {
 	struct idpf_vc_xn_manager *vcxn_mngr;
 
 	struct idpf_dev_ops dev_ops;
+	struct iidc_rdma_core_dev_info *cdev_info;
 	int num_vfs;
 	bool crc_enable;
 	bool req_tx_splitq;
@@ -877,5 +885,9 @@ int idpf_sriov_configure(struct pci_dev *pdev, int num_vfs);
 
 u8 idpf_vport_get_hsplit(const struct idpf_vport *vport);
 bool idpf_vport_set_hsplit(const struct idpf_vport *vport, u8 val);
+int idpf_idc_init(struct idpf_adapter *adapter);
+int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter,
+			       enum iidc_function_type ftype);
+void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info);
 
 #endif /* !_IDPF_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c
index 3fae81f1f988..dd227a4368fb 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c
@@ -161,6 +161,17 @@ static void idpf_ptp_reg_init(const struct idpf_adapter *adapter)
 	adapter->ptp->cmd.exec_cmd_mask = PF_GLTSYN_CMD_SYNC_EXEC_CMD_M;
 }
 
+/**
+ * idpf_idc_register - register for IDC callbacks
+ * @adapter: Driver specific private structure
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_idc_register(struct idpf_adapter *adapter)
+{
+	return idpf_idc_init_aux_core_dev(adapter, IIDC_FUNCTION_TYPE_PF);
+}
+
 /**
  * idpf_reg_ops_init - Initialize register API function pointers
  * @adapter: Driver specific private structure
@@ -182,4 +193,6 @@ static void idpf_reg_ops_init(struct idpf_adapter *adapter)
 void idpf_dev_ops_init(struct idpf_adapter *adapter)
 {
 	idpf_reg_ops_init(adapter);
+
+	adapter->dev_ops.idc_init = idpf_idc_register;
 }
diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c
new file mode 100644
index 000000000000..bc90699f22c5
--- /dev/null
+++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c
@@ -0,0 +1,227 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#include <linux/export.h>
+
+#include "idpf.h"
+#include "idpf_virtchnl.h"
+
+static DEFINE_IDA(idpf_idc_ida);
+
+#define IDPF_IDC_MAX_ADEV_NAME_LEN	15
+
+/**
+ * idpf_idc_init - Called to initialize IDC
+ * @adapter: driver private data structure
+ *
+ * Return: 0 on success or cap not enabled, error code on failure.
+ */
+int idpf_idc_init(struct idpf_adapter *adapter)
+{
+	int err;
+
+	if (!idpf_is_rdma_cap_ena(adapter) ||
+	    !adapter->dev_ops.idc_init)
+		return 0;
+
+	err = adapter->dev_ops.idc_init(adapter);
+	if (err)
+		dev_err(&adapter->pdev->dev, "failed to initialize idc: %d\n",
+			err);
+
+	return err;
+}
+
+/**
+ * idpf_core_adev_release - function to be mapped to aux dev's release op
+ * @dev: pointer to device to free
+ */
+static void idpf_core_adev_release(struct device *dev)
+{
+	struct iidc_rdma_core_auxiliary_dev *iadev;
+
+	iadev = container_of(dev, struct iidc_rdma_core_auxiliary_dev, adev.dev);
+	kfree(iadev);
+	iadev = NULL;
+}
+
+/**
+ * idpf_plug_core_aux_dev - allocate and register an Auxiliary device
+ * @cdev_info: IDC core device info pointer
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_plug_core_aux_dev(struct iidc_rdma_core_dev_info *cdev_info)
+{
+	struct iidc_rdma_core_auxiliary_dev *iadev;
+	char name[IDPF_IDC_MAX_ADEV_NAME_LEN];
+	struct auxiliary_device *adev;
+	int ret;
+
+	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
+	if (!iadev)
+		return -ENOMEM;
+
+	adev = &iadev->adev;
+	cdev_info->adev = adev;
+	iadev->cdev_info = cdev_info;
+
+	ret = ida_alloc(&idpf_idc_ida, GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("failed to allocate unique device ID for Auxiliary driver\n");
+		goto err_ida_alloc;
+	}
+	adev->id = ret;
+	adev->dev.release = idpf_core_adev_release;
+	adev->dev.parent = &cdev_info->pdev->dev;
+	sprintf(name, "%04x.rdma.core", cdev_info->pdev->vendor);
+	adev->name = name;
+
+	ret = auxiliary_device_init(adev);
+	if (ret)
+		goto err_aux_dev_init;
+
+	ret = auxiliary_device_add(adev);
+	if (ret)
+		goto err_aux_dev_add;
+
+	return 0;
+
+err_aux_dev_add:
+	auxiliary_device_uninit(adev);
+err_aux_dev_init:
+	ida_free(&idpf_idc_ida, adev->id);
+err_ida_alloc:
+	cdev_info->adev = NULL;
+	kfree(iadev);
+
+	return ret;
+}
+
+/**
+ * idpf_unplug_aux_dev - unregister and free an Auxiliary device
+ * @adev: auxiliary device struct
+ */
+static void idpf_unplug_aux_dev(struct auxiliary_device *adev)
+{
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+
+	ida_free(&idpf_idc_ida, adev->id);
+}
+
+/**
+ * idpf_idc_vport_dev_ctrl - Called by an Auxiliary Driver
+ * @cdev_info: IDC core device info pointer
+ * @up: RDMA core driver status
+ *
+ * This callback function is accessed by an Auxiliary Driver to indicate
+ * whether core driver is ready to support vport driver load or if vport
+ * drivers need to be taken down.
+ *
+ * Return: 0 on success or error code on failure.
+ */
+int idpf_idc_vport_dev_ctrl(struct iidc_rdma_core_dev_info *cdev_info, bool up)
+{
+	return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL_GPL(idpf_idc_vport_dev_ctrl);
+
+/**
+ * idpf_idc_request_reset - Called by an Auxiliary Driver
+ * @cdev_info: IDC core device info pointer
+ * @reset_type: function, core or other
+ *
+ * This callback function is accessed by an Auxiliary Driver to request a reset
+ * on the Auxiliary Device.
+ *
+ * Return: 0 on success or error code on failure.
+ */
+int idpf_idc_request_reset(struct iidc_rdma_core_dev_info *cdev_info,
+			   enum iidc_rdma_reset_type __always_unused reset_type)
+{
+	return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL_GPL(idpf_idc_request_reset);
+
+/**
+ * idpf_idc_init_msix_data - initialize MSIX data for the cdev_info structure
+ * @adapter: driver private data structure
+ */
+static void
+idpf_idc_init_msix_data(struct idpf_adapter *adapter)
+{
+	struct iidc_rdma_core_dev_info *cdev_info;
+	struct iidc_rdma_priv_dev_info *privd;
+
+	if (!adapter->rdma_msix_entries)
+		return;
+
+	cdev_info = adapter->cdev_info;
+	privd = cdev_info->iidc_priv;
+
+	privd->msix_entries = adapter->rdma_msix_entries;
+	privd->msix_count = adapter->num_rdma_msix_entries;
+}
+
+/**
+ * idpf_idc_init_aux_core_dev - initialize Auxiliary Device(s)
+ * @adapter: driver private data structure
+ * @ftype: PF or VF
+ *
+ * Return: 0 on success or error code on failure.
+ */
+int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter,
+			       enum iidc_function_type ftype)
+{
+	struct iidc_rdma_core_dev_info *cdev_info;
+	struct iidc_rdma_priv_dev_info *privd;
+	int err;
+
+	adapter->cdev_info = kzalloc(sizeof(*cdev_info), GFP_KERNEL);
+	if (!adapter->cdev_info)
+		return -ENOMEM;
+	cdev_info = adapter->cdev_info;
+
+	privd = kzalloc(sizeof(*privd), GFP_KERNEL);
+	if (!privd) {
+		err = -ENOMEM;
+		goto err_privd_alloc;
+	}
+
+	cdev_info->iidc_priv = privd;
+	cdev_info->pdev = adapter->pdev;
+	cdev_info->rdma_protocol = IIDC_RDMA_PROTOCOL_ROCEV2;
+	privd->ftype = ftype;
+
+	idpf_idc_init_msix_data(adapter);
+
+	err = idpf_plug_core_aux_dev(cdev_info);
+	if (err)
+		goto err_plug_aux_dev;
+
+	return 0;
+
+err_plug_aux_dev:
+	kfree(privd);
+err_privd_alloc:
+	kfree(cdev_info);
+	adapter->cdev_info = NULL;
+
+	return err;
+}
+
+/**
+ * idpf_idc_deinit_core_aux_device - de-initialize Auxiliary Device(s)
+ * @cdev_info: IDC core device info pointer
+ */
+void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info)
+{
+	if (!cdev_info)
+		return;
+
+	idpf_unplug_aux_dev(cdev_info->adev);
+
+	kfree(cdev_info->iidc_priv);
+	kfree(cdev_info);
+}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index 7dcb3a7bbc35..b9e04ea2cbd4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -1834,6 +1834,10 @@ static int idpf_init_hard_reset(struct idpf_adapter *adapter)
 unlock_mutex:
 	mutex_unlock(&adapter->vport_ctrl_lock);
 
+	/* Wait until all vports are created to init RDMA CORE AUX */
+	if (!err)
+		err = idpf_idc_init(adapter);
+
 	return err;
 }
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
index aba828abcb17..2f84bd596ae4 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
@@ -147,6 +147,17 @@ static void idpf_vf_trigger_reset(struct idpf_adapter *adapter,
 		idpf_send_mb_msg(adapter, VIRTCHNL2_OP_RESET_VF, 0, NULL, 0);
 }
 
+/**
+ * idpf_idc_vf_register - register for IDC callbacks
+ * @adapter: Driver specific private structure
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_idc_vf_register(struct idpf_adapter *adapter)
+{
+	return idpf_idc_init_aux_core_dev(adapter, IIDC_FUNCTION_TYPE_VF);
+}
+
 /**
  * idpf_vf_reg_ops_init - Initialize register API function pointers
  * @adapter: Driver specific private structure
@@ -167,4 +178,6 @@ static void idpf_vf_reg_ops_init(struct idpf_adapter *adapter)
 void idpf_vf_dev_ops_init(struct idpf_adapter *adapter)
 {
 	idpf_vf_reg_ops_init(adapter);
+
+	adapter->dev_ops.idc_init = idpf_idc_vf_register;
 }
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 24febaaa8fbb..f7e105c67baf 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -1,6 +1,7 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /* Copyright (C) 2023 Intel Corporation */
 
+#include <linux/export.h>
 #include <net/libeth/rx.h>
 
 #include "idpf.h"
@@ -868,6 +869,7 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 
 	caps.other_caps =
 		cpu_to_le64(VIRTCHNL2_CAP_SRIOV			|
+			    VIRTCHNL2_CAP_RDMA                  |
 			    VIRTCHNL2_CAP_MACFILTER		|
 			    VIRTCHNL2_CAP_SPLITQ_QSCHED		|
 			    VIRTCHNL2_CAP_PROMISC		|
@@ -3070,6 +3072,7 @@ void idpf_vc_core_deinit(struct idpf_adapter *adapter)
 
 	idpf_ptp_release(adapter);
 	idpf_deinit_task(adapter);
+	idpf_idc_deinit_core_aux_device(adapter->cdev_info);
 	idpf_intr_rel(adapter);
 
 	if (remove_in_prog)
@@ -3728,3 +3731,21 @@ int idpf_set_promiscuous(struct idpf_adapter *adapter,
 
 	return reply_sz < 0 ? reply_sz : 0;
 }
+
+/**
+ * idpf_idc_rdma_vc_send_sync - virtchnl send callback for IDC registered drivers
+ * @cdev_info: IDC core device info pointer
+ * @send_msg: message to send
+ * @msg_size: size of message to send
+ * @recv_msg: message to populate on reception of response
+ * @recv_len: length of message copied into recv_msg or 0 on error
+ *
+ * Return: 0 on success or error code on failure.
+ */
+int idpf_idc_rdma_vc_send_sync(struct iidc_rdma_core_dev_info *cdev_info,
+			       u8 *send_msg, u16 msg_size,
+			       u8 *recv_msg, u16 *recv_len)
+{
+	return -EOPNOTSUPP;
+}
+EXPORT_SYMBOL_GPL(idpf_idc_rdma_vc_send_sync);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
index 77578206bada..7bae09483aed 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.h
@@ -151,5 +151,8 @@ int idpf_send_set_sriov_vfs_msg(struct idpf_adapter *adapter, u16 num_vfs);
 int idpf_send_get_set_rss_key_msg(struct idpf_vport *vport, bool get);
 int idpf_send_get_set_rss_lut_msg(struct idpf_vport *vport, bool get);
 void idpf_vc_xn_shutdown(struct idpf_vc_xn_manager *vcxn_mngr);
+int idpf_idc_rdma_vc_send_sync(struct iidc_rdma_core_dev_info *cdev_info,
+			       u8 *send_msg, u16 msg_size,
+			       u8 *recv_msg, u16 *recv_len);
 
 #endif /* _IDPF_VIRTCHNL_H_ */
diff --git a/include/linux/net/intel/iidc_rdma_idpf.h b/include/linux/net/intel/iidc_rdma_idpf.h
new file mode 100644
index 000000000000..f2fe1844f660
--- /dev/null
+++ b/include/linux/net/intel/iidc_rdma_idpf.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (C) 2025 Intel Corporation. */
+
+#ifndef _IIDC_RDMA_IDPF_H_
+#define _IIDC_RDMA_IDPF_H_
+
+#include <linux/auxiliary_bus.h>
+
+/* struct to be populated by core LAN PCI driver */
+enum iidc_function_type {
+	IIDC_FUNCTION_TYPE_PF,
+	IIDC_FUNCTION_TYPE_VF,
+};
+
+struct iidc_rdma_priv_dev_info {
+	struct msix_entry *msix_entries;
+	u16 msix_count; /* How many vectors are reserved for this device */
+	enum iidc_function_type ftype;
+};
+
+int idpf_idc_vport_dev_ctrl(struct iidc_rdma_core_dev_info *cdev_info, bool up);
+int idpf_idc_request_reset(struct iidc_rdma_core_dev_info *cdev_info,
+			   enum iidc_rdma_reset_type __always_unused reset_type);
+int idpf_idc_rdma_vc_send_sync(struct iidc_rdma_core_dev_info *cdev_info,
+			       u8 *send_msg, u16 msg_size,
+			       u8 *recv_msg, u16 *recv_len);
+
+#endif /* _IIDC_RDMA_IDPF_H_ */
-- 
cgit v1.2.3


From be91128c579c86d295da4325f6ac4710e4e6d2b4 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Tue, 8 Jul 2025 16:05:51 -0500
Subject: idpf: implement RDMA vport auxiliary dev create, init, and destroy

Implement the functions to create, initialize, and destroy an RDMA vport
auxiliary device. The vport aux dev creation is dependent on the
core aux device to call idpf_idc_vport_dev_ctrl to signal that it is
ready for vport aux devices. Implement that core callback to either
create and initialize the vport aux dev or deinitialize.

RDMA vport aux dev creation is also dependent on the control plane to
tell us the vport is RDMA enabled. Add a flag in the create vport
message to signal individual vport RDMA capabilities.

Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf.h      |   4 +
 drivers/net/ethernet/intel/idpf/idpf_idc.c  | 180 +++++++++++++++++++++++++++-
 drivers/net/ethernet/intel/idpf/idpf_lib.c  |   2 +
 drivers/net/ethernet/intel/idpf/virtchnl2.h |   3 +
 include/linux/net/intel/iidc_rdma_idpf.h    |  19 +++
 5 files changed, 207 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index dd2aa515a31b..7103cf551bb8 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -281,6 +281,7 @@ struct idpf_port_stats {
  *	      group will yield total number of RX queues.
  * @rxq_model: Splitq queue or single queue queuing model
  * @rx_ptype_lkup: Lookup table for ptypes on RX
+ * @vdev_info: IDC vport device info pointer
  * @adapter: back pointer to associated adapter
  * @netdev: Associated net_device. Each vport should have one and only one
  *	    associated netdev.
@@ -326,6 +327,8 @@ struct idpf_vport {
 	u32 rxq_model;
 	struct libeth_rx_pt *rx_ptype_lkup;
 
+	struct iidc_rdma_vport_dev_info *vdev_info;
+
 	struct idpf_adapter *adapter;
 	struct net_device *netdev;
 	DECLARE_BITMAP(flags, IDPF_VPORT_FLAGS_NBITS);
@@ -889,5 +892,6 @@ int idpf_idc_init(struct idpf_adapter *adapter);
 int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter,
 			       enum iidc_function_type ftype);
 void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info);
+void idpf_idc_deinit_vport_aux_device(struct iidc_rdma_vport_dev_info *vdev_info);
 
 #endif /* !_IDPF_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c
index bc90699f22c5..237dfe1ac06d 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_idc.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c
@@ -32,6 +32,115 @@ int idpf_idc_init(struct idpf_adapter *adapter)
 	return err;
 }
 
+/**
+ * idpf_vport_adev_release - function to be mapped to aux dev's release op
+ * @dev: pointer to device to free
+ */
+static void idpf_vport_adev_release(struct device *dev)
+{
+	struct iidc_rdma_vport_auxiliary_dev *iadev;
+
+	iadev = container_of(dev, struct iidc_rdma_vport_auxiliary_dev, adev.dev);
+	kfree(iadev);
+	iadev = NULL;
+}
+
+/**
+ * idpf_plug_vport_aux_dev - allocate and register a vport Auxiliary device
+ * @cdev_info: IDC core device info pointer
+ * @vdev_info: IDC vport device info pointer
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_plug_vport_aux_dev(struct iidc_rdma_core_dev_info *cdev_info,
+				   struct iidc_rdma_vport_dev_info *vdev_info)
+{
+	struct iidc_rdma_vport_auxiliary_dev *iadev;
+	char name[IDPF_IDC_MAX_ADEV_NAME_LEN];
+	struct auxiliary_device *adev;
+	int ret;
+
+	iadev = kzalloc(sizeof(*iadev), GFP_KERNEL);
+	if (!iadev)
+		return -ENOMEM;
+
+	adev = &iadev->adev;
+	vdev_info->adev = &iadev->adev;
+	iadev->vdev_info = vdev_info;
+
+	ret = ida_alloc(&idpf_idc_ida, GFP_KERNEL);
+	if (ret < 0) {
+		pr_err("failed to allocate unique device ID for Auxiliary driver\n");
+		goto err_ida_alloc;
+	}
+	adev->id = ret;
+	adev->dev.release = idpf_vport_adev_release;
+	adev->dev.parent = &cdev_info->pdev->dev;
+	sprintf(name, "%04x.rdma.vdev", cdev_info->pdev->vendor);
+	adev->name = name;
+
+	ret = auxiliary_device_init(adev);
+	if (ret)
+		goto err_aux_dev_init;
+
+	ret = auxiliary_device_add(adev);
+	if (ret)
+		goto err_aux_dev_add;
+
+	return 0;
+
+err_aux_dev_add:
+	auxiliary_device_uninit(adev);
+err_aux_dev_init:
+	ida_free(&idpf_idc_ida, adev->id);
+err_ida_alloc:
+	vdev_info->adev = NULL;
+	kfree(iadev);
+
+	return ret;
+}
+
+/**
+ * idpf_idc_init_aux_vport_dev - initialize vport Auxiliary Device(s)
+ * @vport: virtual port data struct
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_idc_init_aux_vport_dev(struct idpf_vport *vport)
+{
+	struct idpf_adapter *adapter = vport->adapter;
+	struct iidc_rdma_vport_dev_info *vdev_info;
+	struct iidc_rdma_core_dev_info *cdev_info;
+	struct virtchnl2_create_vport *vport_msg;
+	int err;
+
+	vport_msg = (struct virtchnl2_create_vport *)
+			adapter->vport_params_recvd[vport->idx];
+
+	if (!(le16_to_cpu(vport_msg->vport_flags) & VIRTCHNL2_VPORT_ENABLE_RDMA))
+		return 0;
+
+	vport->vdev_info = kzalloc(sizeof(*vdev_info), GFP_KERNEL);
+	if (!vport->vdev_info)
+		return -ENOMEM;
+
+	cdev_info = vport->adapter->cdev_info;
+
+	vdev_info = vport->vdev_info;
+	vdev_info->vport_id = vport->vport_id;
+	vdev_info->netdev = vport->netdev;
+	vdev_info->core_adev = cdev_info->adev;
+
+	err = idpf_plug_vport_aux_dev(cdev_info, vdev_info);
+	if (err) {
+		vport->vdev_info = NULL;
+		kfree(vdev_info);
+		return err;
+	}
+
+	return 0;
+}
+
 /**
  * idpf_core_adev_release - function to be mapped to aux dev's release op
  * @dev: pointer to device to free
@@ -104,12 +213,60 @@ err_ida_alloc:
  */
 static void idpf_unplug_aux_dev(struct auxiliary_device *adev)
 {
+	if (!adev)
+		return;
+
 	auxiliary_device_delete(adev);
 	auxiliary_device_uninit(adev);
 
 	ida_free(&idpf_idc_ida, adev->id);
 }
 
+/**
+ * idpf_idc_vport_dev_up - called when CORE is ready for vport aux devs
+ * @adapter: private data struct
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_idc_vport_dev_up(struct idpf_adapter *adapter)
+{
+	int i, err = 0;
+
+	for (i = 0; i < adapter->num_alloc_vports; i++) {
+		struct idpf_vport *vport = adapter->vports[i];
+
+		if (!vport)
+			continue;
+
+		if (!vport->vdev_info)
+			err = idpf_idc_init_aux_vport_dev(vport);
+		else
+			err = idpf_plug_vport_aux_dev(vport->adapter->cdev_info,
+						      vport->vdev_info);
+	}
+
+	return err;
+}
+
+/**
+ * idpf_idc_vport_dev_down - called CORE is leaving vport aux dev support state
+ * @adapter: private data struct
+ */
+static void idpf_idc_vport_dev_down(struct idpf_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_alloc_vports; i++) {
+		struct idpf_vport *vport = adapter->vports[i];
+
+		if (!vport)
+			continue;
+
+		idpf_unplug_aux_dev(vport->vdev_info->adev);
+		vport->vdev_info->adev = NULL;
+	}
+}
+
 /**
  * idpf_idc_vport_dev_ctrl - Called by an Auxiliary Driver
  * @cdev_info: IDC core device info pointer
@@ -123,7 +280,14 @@ static void idpf_unplug_aux_dev(struct auxiliary_device *adev)
  */
 int idpf_idc_vport_dev_ctrl(struct iidc_rdma_core_dev_info *cdev_info, bool up)
 {
-	return -EOPNOTSUPP;
+	struct idpf_adapter *adapter = pci_get_drvdata(cdev_info->pdev);
+
+	if (up)
+		return idpf_idc_vport_dev_up(adapter);
+
+	idpf_idc_vport_dev_down(adapter);
+
+	return 0;
 }
 EXPORT_SYMBOL_GPL(idpf_idc_vport_dev_ctrl);
 
@@ -225,3 +389,17 @@ void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info)
 	kfree(cdev_info->iidc_priv);
 	kfree(cdev_info);
 }
+
+/**
+ * idpf_idc_deinit_vport_aux_device - de-initialize Auxiliary Device(s)
+ * @vdev_info: IDC vport device info pointer
+ */
+void idpf_idc_deinit_vport_aux_device(struct iidc_rdma_vport_dev_info *vdev_info)
+{
+	if (!vdev_info)
+		return;
+
+	idpf_unplug_aux_dev(vdev_info->adev);
+
+	kfree(vdev_info);
+}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
index b9e04ea2cbd4..30a7beb23155 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
@@ -1021,6 +1021,8 @@ static void idpf_vport_dealloc(struct idpf_vport *vport)
 	struct idpf_adapter *adapter = vport->adapter;
 	unsigned int i = vport->idx;
 
+	idpf_idc_deinit_vport_aux_device(vport->vdev_info);
+
 	idpf_deinit_mac_addr(vport);
 	idpf_vport_stop(vport);
 
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index a2881979c7f8..82a3c307307e 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -575,9 +575,12 @@ VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_queue_reg_chunks);
 /**
  * enum virtchnl2_vport_flags - Vport flags that indicate vport capabilities.
  * @VIRTCHNL2_VPORT_UPLINK_PORT: Representatives of underlying physical ports
+ * @VIRTCHNL2_VPORT_ENABLE_RDMA: RDMA is enabled for this vport
  */
 enum virtchnl2_vport_flags {
 	VIRTCHNL2_VPORT_UPLINK_PORT	= BIT(0),
+	/* VIRTCHNL2_VPORT_* bits [1:3] rsvd */
+	VIRTCHNL2_VPORT_ENABLE_RDMA             = BIT(4),
 };
 
 /**
diff --git a/include/linux/net/intel/iidc_rdma_idpf.h b/include/linux/net/intel/iidc_rdma_idpf.h
index f2fe1844f660..16c970dd4c6e 100644
--- a/include/linux/net/intel/iidc_rdma_idpf.h
+++ b/include/linux/net/intel/iidc_rdma_idpf.h
@@ -6,6 +6,25 @@
 
 #include <linux/auxiliary_bus.h>
 
+/* struct to be populated by core LAN PCI driver */
+struct iidc_rdma_vport_dev_info {
+	struct auxiliary_device *adev;
+	struct auxiliary_device *core_adev;
+	struct net_device *netdev;
+	u16 vport_id;
+};
+
+struct iidc_rdma_vport_auxiliary_dev {
+	struct auxiliary_device adev;
+	struct iidc_rdma_vport_dev_info *vdev_info;
+};
+
+struct iidc_rdma_vport_auxiliary_drv {
+	struct auxiliary_driver adrv;
+	void (*event_handler)(struct iidc_rdma_vport_dev_info *vdev,
+			      struct iidc_rdma_event *event);
+};
+
 /* struct to be populated by core LAN PCI driver */
 enum iidc_function_type {
 	IIDC_FUNCTION_TYPE_PF,
-- 
cgit v1.2.3


From 6aa53e861c1a0c042690c9b7c5c153088ae61079 Mon Sep 17 00:00:00 2001
From: Joshua Hay <joshua.a.hay@intel.com>
Date: Tue, 8 Jul 2025 16:05:54 -0500
Subject: idpf: implement get LAN MMIO memory regions

The RDMA driver needs to map its own MMIO regions for the sake of
performance, meaning the IDPF needs to avoid mapping portions of the BAR
space. However, to be HW agnostic, the IDPF cannot assume where
these are and must avoid mapping hard coded regions as much as possible.

The IDPF maps the bare minimum to load and communicate with the
control plane, i.e., the mailbox registers and the reset state
registers. Because of how and when mailbox register offsets are
initialized, it is easier to adjust the existing defines to be relative
to the mailbox region starting address. Use a specific mailbox register
write function that uses these relative offsets. The reset state
register addresses are calculated the same way as for other registers,
described below.

The IDPF then calls a new virtchnl op to fetch a list of MMIO regions
that it should map. The addresses for the registers in these regions are
calculated by determining what region the register resides in, adjusting
the offset to be relative to that region, and then adding the
register's offset to that region's mapped address.

If the new virtchnl op is not supported, the IDPF will fallback to
mapping the whole bar. However, it will still map them as separate
regions outside the mailbox and reset state registers. This way we can
use the same logic in both cases to access the MMIO space.

Reviewed-by: Madhu Chittim <madhu.chittim@intel.com>
Signed-off-by: Joshua Hay <joshua.a.hay@intel.com>
Signed-off-by: Tatyana Nikolova <tatyana.e.nikolova@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/idpf/idpf.h          |  69 ++++++++++-
 drivers/net/ethernet/intel/idpf/idpf_controlq.c |  14 +--
 drivers/net/ethernet/intel/idpf/idpf_controlq.h |  18 ++-
 drivers/net/ethernet/intel/idpf/idpf_dev.c      |  36 +++---
 drivers/net/ethernet/intel/idpf/idpf_idc.c      |  32 ++++-
 drivers/net/ethernet/intel/idpf/idpf_main.c     |  32 ++++-
 drivers/net/ethernet/intel/idpf/idpf_mem.h      |   8 +-
 drivers/net/ethernet/intel/idpf/idpf_vf_dev.c   |  32 +++--
 drivers/net/ethernet/intel/idpf/idpf_virtchnl.c | 149 +++++++++++++++++++++++-
 drivers/net/ethernet/intel/idpf/virtchnl2.h     |  30 ++++-
 include/linux/net/intel/iidc_rdma_idpf.h        |   8 ++
 11 files changed, 376 insertions(+), 52 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
index 79379d6db015..0cf9120d1f97 100644
--- a/drivers/net/ethernet/intel/idpf/idpf.h
+++ b/drivers/net/ethernet/intel/idpf/idpf.h
@@ -12,6 +12,7 @@ struct idpf_vport_max_q;
 #include <net/pkt_sched.h>
 #include <linux/aer.h>
 #include <linux/etherdevice.h>
+#include <linux/ioport.h>
 #include <linux/pci.h>
 #include <linux/bitfield.h>
 #include <linux/sctp.h>
@@ -197,7 +198,8 @@ struct idpf_vport_max_q {
  * @ptp_reg_init: PTP register initialization
  */
 struct idpf_reg_ops {
-	void (*ctlq_reg_init)(struct idpf_ctlq_create_info *cq);
+	void (*ctlq_reg_init)(struct idpf_adapter *adapter,
+			      struct idpf_ctlq_create_info *cq);
 	int (*intr_reg_init)(struct idpf_vport *vport);
 	void (*mb_intr_reg_init)(struct idpf_adapter *adapter);
 	void (*reset_reg_init)(struct idpf_adapter *adapter);
@@ -206,15 +208,25 @@ struct idpf_reg_ops {
 	void (*ptp_reg_init)(const struct idpf_adapter *adapter);
 };
 
+#define IDPF_MMIO_REG_NUM_STATIC	2
+#define IDPF_PF_MBX_REGION_SZ		4096
+#define IDPF_PF_RSTAT_REGION_SZ		2048
+#define IDPF_VF_MBX_REGION_SZ		10240
+#define IDPF_VF_RSTAT_REGION_SZ		2048
+
 /**
  * struct idpf_dev_ops - Device specific operations
  * @reg_ops: Register operations
  * @idc_init: IDC initialization
+ * @static_reg_info: array of mailbox and rstat register info
  */
 struct idpf_dev_ops {
 	struct idpf_reg_ops reg_ops;
 
 	int (*idc_init)(struct idpf_adapter *adapter);
+
+	/* static_reg_info[0] is mailbox region, static_reg_info[1] is rstat */
+	struct resource static_reg_info[IDPF_MMIO_REG_NUM_STATIC];
 };
 
 /**
@@ -755,6 +767,34 @@ static inline u8 idpf_get_min_tx_pkt_len(struct idpf_adapter *adapter)
 	return pkt_len ? pkt_len : IDPF_TX_MIN_PKT_LEN;
 }
 
+/**
+ * idpf_get_mbx_reg_addr - Get BAR0 mailbox register address
+ * @adapter: private data struct
+ * @reg_offset: register offset value
+ *
+ * Return: BAR0 mailbox register address based on register offset.
+ */
+static inline void __iomem *idpf_get_mbx_reg_addr(struct idpf_adapter *adapter,
+						  resource_size_t reg_offset)
+{
+	return adapter->hw.mbx.vaddr + reg_offset;
+}
+
+/**
+ * idpf_get_rstat_reg_addr - Get BAR0 rstat register address
+ * @adapter: private data struct
+ * @reg_offset: register offset value
+ *
+ * Return: BAR0 rstat register address based on register offset.
+ */
+static inline void __iomem *idpf_get_rstat_reg_addr(struct idpf_adapter *adapter,
+						    resource_size_t reg_offset)
+{
+	reg_offset -= adapter->dev_ops.static_reg_info[1].start;
+
+	return adapter->hw.rstat.vaddr + reg_offset;
+}
+
 /**
  * idpf_get_reg_addr - Get BAR0 register address
  * @adapter: private data struct
@@ -765,7 +805,30 @@ static inline u8 idpf_get_min_tx_pkt_len(struct idpf_adapter *adapter)
 static inline void __iomem *idpf_get_reg_addr(struct idpf_adapter *adapter,
 					      resource_size_t reg_offset)
 {
-	return (void __iomem *)(adapter->hw.hw_addr + reg_offset);
+	struct idpf_hw *hw = &adapter->hw;
+
+	for (int i = 0; i < hw->num_lan_regs; i++) {
+		struct idpf_mmio_reg *region = &hw->lan_regs[i];
+
+		if (reg_offset >= region->addr_start &&
+		    reg_offset < (region->addr_start + region->addr_len)) {
+			/* Convert the offset so that it is relative to the
+			 * start of the region.  Then add the base address of
+			 * the region to get the final address.
+			 */
+			reg_offset -= region->addr_start;
+
+			return region->vaddr + reg_offset;
+		}
+	}
+
+	/* It's impossible to hit this case with offsets from the CP. But if we
+	 * do for any other reason, the kernel will panic on that register
+	 * access. Might as well do it here to make it clear what's happening.
+	 */
+	BUG();
+
+	return NULL;
 }
 
 /**
@@ -779,7 +842,7 @@ static inline bool idpf_is_reset_detected(struct idpf_adapter *adapter)
 	if (!adapter->hw.arq)
 		return true;
 
-	return !(readl(idpf_get_reg_addr(adapter, adapter->hw.arq->reg.len)) &
+	return !(readl(idpf_get_mbx_reg_addr(adapter, adapter->hw.arq->reg.len)) &
 		 adapter->hw.arq->reg.len_mask);
 }
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.c b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
index b28991dd1870..9c5c628eb469 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.c
@@ -36,19 +36,19 @@ static void idpf_ctlq_init_regs(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 {
 	/* Update tail to post pre-allocated buffers for rx queues */
 	if (is_rxq)
-		wr32(hw, cq->reg.tail, (u32)(cq->ring_size - 1));
+		idpf_mbx_wr32(hw, cq->reg.tail, (u32)(cq->ring_size - 1));
 
 	/* For non-Mailbox control queues only TAIL need to be set */
 	if (cq->q_id != -1)
 		return;
 
 	/* Clear Head for both send or receive */
-	wr32(hw, cq->reg.head, 0);
+	idpf_mbx_wr32(hw, cq->reg.head, 0);
 
 	/* set starting point */
-	wr32(hw, cq->reg.bal, lower_32_bits(cq->desc_ring.pa));
-	wr32(hw, cq->reg.bah, upper_32_bits(cq->desc_ring.pa));
-	wr32(hw, cq->reg.len, (cq->ring_size | cq->reg.len_ena_mask));
+	idpf_mbx_wr32(hw, cq->reg.bal, lower_32_bits(cq->desc_ring.pa));
+	idpf_mbx_wr32(hw, cq->reg.bah, upper_32_bits(cq->desc_ring.pa));
+	idpf_mbx_wr32(hw, cq->reg.len, (cq->ring_size | cq->reg.len_ena_mask));
 }
 
 /**
@@ -329,7 +329,7 @@ int idpf_ctlq_send(struct idpf_hw *hw, struct idpf_ctlq_info *cq,
 	 */
 	dma_wmb();
 
-	wr32(hw, cq->reg.tail, cq->next_to_use);
+	idpf_mbx_wr32(hw, cq->reg.tail, cq->next_to_use);
 
 err_unlock:
 	mutex_unlock(&cq->cq_lock);
@@ -521,7 +521,7 @@ post_buffs_out:
 
 		dma_wmb();
 
-		wr32(hw, cq->reg.tail, cq->next_to_post);
+		idpf_mbx_wr32(hw, cq->reg.tail, cq->next_to_post);
 	}
 
 	mutex_unlock(&cq->cq_lock);
diff --git a/drivers/net/ethernet/intel/idpf/idpf_controlq.h b/drivers/net/ethernet/intel/idpf/idpf_controlq.h
index c1aba09e9856..de4ece40c2ff 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_controlq.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_controlq.h
@@ -94,12 +94,26 @@ struct idpf_mbxq_desc {
 	u32 pf_vf_id;		/* used by CP when sending to PF */
 };
 
+/* Max number of MMIO regions not including the mailbox and rstat regions in
+ * the fallback case when the whole bar is mapped.
+ */
+#define IDPF_MMIO_MAP_FALLBACK_MAX_REMAINING		3
+
+struct idpf_mmio_reg {
+	void __iomem *vaddr;
+	resource_size_t addr_start;
+	resource_size_t addr_len;
+};
+
 /* Define the driver hardware struct to replace other control structs as needed
  * Align to ctlq_hw_info
  */
 struct idpf_hw {
-	void __iomem *hw_addr;
-	resource_size_t hw_addr_len;
+	struct idpf_mmio_reg mbx;
+	struct idpf_mmio_reg rstat;
+	/* Array of remaining LAN BAR regions */
+	int num_lan_regs;
+	struct idpf_mmio_reg *lan_regs;
 
 	struct idpf_adapter *back;
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_dev.c
index dd227a4368fb..bfa60f7d43de 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_dev.c
@@ -10,10 +10,13 @@
 
 /**
  * idpf_ctlq_reg_init - initialize default mailbox registers
+ * @adapter: adapter structure
  * @cq: pointer to the array of create control queues
  */
-static void idpf_ctlq_reg_init(struct idpf_ctlq_create_info *cq)
+static void idpf_ctlq_reg_init(struct idpf_adapter *adapter,
+			       struct idpf_ctlq_create_info *cq)
 {
+	resource_size_t mbx_start = adapter->dev_ops.static_reg_info[0].start;
 	int i;
 
 	for (i = 0; i < IDPF_NUM_DFLT_MBX_Q; i++) {
@@ -22,22 +25,22 @@ static void idpf_ctlq_reg_init(struct idpf_ctlq_create_info *cq)
 		switch (ccq->type) {
 		case IDPF_CTLQ_TYPE_MAILBOX_TX:
 			/* set head and tail registers in our local struct */
-			ccq->reg.head = PF_FW_ATQH;
-			ccq->reg.tail = PF_FW_ATQT;
-			ccq->reg.len = PF_FW_ATQLEN;
-			ccq->reg.bah = PF_FW_ATQBAH;
-			ccq->reg.bal = PF_FW_ATQBAL;
+			ccq->reg.head = PF_FW_ATQH - mbx_start;
+			ccq->reg.tail = PF_FW_ATQT - mbx_start;
+			ccq->reg.len = PF_FW_ATQLEN - mbx_start;
+			ccq->reg.bah = PF_FW_ATQBAH - mbx_start;
+			ccq->reg.bal = PF_FW_ATQBAL - mbx_start;
 			ccq->reg.len_mask = PF_FW_ATQLEN_ATQLEN_M;
 			ccq->reg.len_ena_mask = PF_FW_ATQLEN_ATQENABLE_M;
 			ccq->reg.head_mask = PF_FW_ATQH_ATQH_M;
 			break;
 		case IDPF_CTLQ_TYPE_MAILBOX_RX:
 			/* set head and tail registers in our local struct */
-			ccq->reg.head = PF_FW_ARQH;
-			ccq->reg.tail = PF_FW_ARQT;
-			ccq->reg.len = PF_FW_ARQLEN;
-			ccq->reg.bah = PF_FW_ARQBAH;
-			ccq->reg.bal = PF_FW_ARQBAL;
+			ccq->reg.head = PF_FW_ARQH - mbx_start;
+			ccq->reg.tail = PF_FW_ARQT - mbx_start;
+			ccq->reg.len = PF_FW_ARQLEN - mbx_start;
+			ccq->reg.bah = PF_FW_ARQBAH - mbx_start;
+			ccq->reg.bal = PF_FW_ARQBAL - mbx_start;
 			ccq->reg.len_mask = PF_FW_ARQLEN_ARQLEN_M;
 			ccq->reg.len_ena_mask = PF_FW_ARQLEN_ARQENABLE_M;
 			ccq->reg.head_mask = PF_FW_ARQH_ARQH_M;
@@ -130,7 +133,7 @@ free_reg_vals:
  */
 static void idpf_reset_reg_init(struct idpf_adapter *adapter)
 {
-	adapter->reset_reg.rstat = idpf_get_reg_addr(adapter, PFGEN_RSTAT);
+	adapter->reset_reg.rstat = idpf_get_rstat_reg_addr(adapter, PFGEN_RSTAT);
 	adapter->reset_reg.rstat_m = PFGEN_RSTAT_PFR_STATE_M;
 }
 
@@ -144,9 +147,9 @@ static void idpf_trigger_reset(struct idpf_adapter *adapter,
 {
 	u32 reset_reg;
 
-	reset_reg = readl(idpf_get_reg_addr(adapter, PFGEN_CTRL));
+	reset_reg = readl(idpf_get_rstat_reg_addr(adapter, PFGEN_CTRL));
 	writel(reset_reg | PFGEN_CTRL_PFSWR,
-	       idpf_get_reg_addr(adapter, PFGEN_CTRL));
+	       idpf_get_rstat_reg_addr(adapter, PFGEN_CTRL));
 }
 
 /**
@@ -195,4 +198,9 @@ void idpf_dev_ops_init(struct idpf_adapter *adapter)
 	idpf_reg_ops_init(adapter);
 
 	adapter->dev_ops.idc_init = idpf_idc_register;
+
+	resource_set_range(&adapter->dev_ops.static_reg_info[0],
+			   PF_FW_BASE, IDPF_PF_MBX_REGION_SZ);
+	resource_set_range(&adapter->dev_ops.static_reg_info[1],
+			   PFGEN_RTRIG, IDPF_PF_RSTAT_REGION_SZ);
 }
diff --git a/drivers/net/ethernet/intel/idpf/idpf_idc.c b/drivers/net/ethernet/intel/idpf/idpf_idc.c
index 2443337c83de..4d2905103215 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_idc.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_idc.c
@@ -412,7 +412,7 @@ int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter,
 {
 	struct iidc_rdma_core_dev_info *cdev_info;
 	struct iidc_rdma_priv_dev_info *privd;
-	int err;
+	int err, i;
 
 	adapter->cdev_info = kzalloc(sizeof(*cdev_info), GFP_KERNEL);
 	if (!adapter->cdev_info)
@@ -430,14 +430,36 @@ int idpf_idc_init_aux_core_dev(struct idpf_adapter *adapter,
 	cdev_info->rdma_protocol = IIDC_RDMA_PROTOCOL_ROCEV2;
 	privd->ftype = ftype;
 
+	privd->mapped_mem_regions =
+		kcalloc(adapter->hw.num_lan_regs,
+			sizeof(struct iidc_rdma_lan_mapped_mem_region),
+			GFP_KERNEL);
+	if (!privd->mapped_mem_regions) {
+		err = -ENOMEM;
+		goto err_plug_aux_dev;
+	}
+
+	privd->num_memory_regions = cpu_to_le16(adapter->hw.num_lan_regs);
+	for (i = 0; i < adapter->hw.num_lan_regs; i++) {
+		privd->mapped_mem_regions[i].region_addr =
+			adapter->hw.lan_regs[i].vaddr;
+		privd->mapped_mem_regions[i].size =
+			cpu_to_le64(adapter->hw.lan_regs[i].addr_len);
+		privd->mapped_mem_regions[i].start_offset =
+			cpu_to_le64(adapter->hw.lan_regs[i].addr_start);
+	}
+
 	idpf_idc_init_msix_data(adapter);
 
 	err = idpf_plug_core_aux_dev(cdev_info);
 	if (err)
-		goto err_plug_aux_dev;
+		goto err_free_mem_regions;
 
 	return 0;
 
+err_free_mem_regions:
+	kfree(privd->mapped_mem_regions);
+	privd->mapped_mem_regions = NULL;
 err_plug_aux_dev:
 	kfree(privd);
 err_privd_alloc:
@@ -453,12 +475,16 @@ err_privd_alloc:
  */
 void idpf_idc_deinit_core_aux_device(struct iidc_rdma_core_dev_info *cdev_info)
 {
+	struct iidc_rdma_priv_dev_info *privd;
+
 	if (!cdev_info)
 		return;
 
 	idpf_unplug_aux_dev(cdev_info->adev);
 
-	kfree(cdev_info->iidc_priv);
+	privd = cdev_info->iidc_priv;
+	kfree(privd->mapped_mem_regions);
+	kfree(privd);
 	kfree(cdev_info);
 }
 
diff --git a/drivers/net/ethernet/intel/idpf/idpf_main.c b/drivers/net/ethernet/intel/idpf/idpf_main.c
index 0efd9c0c7a90..b7422be3e967 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_main.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_main.c
@@ -106,15 +106,37 @@ static void idpf_shutdown(struct pci_dev *pdev)
  */
 static int idpf_cfg_hw(struct idpf_adapter *adapter)
 {
+	resource_size_t res_start, mbx_start, rstat_start;
 	struct pci_dev *pdev = adapter->pdev;
 	struct idpf_hw *hw = &adapter->hw;
+	struct device *dev = &pdev->dev;
+	long len;
+
+	res_start = pci_resource_start(pdev, 0);
+
+	/* Map mailbox space for virtchnl communication */
+	mbx_start = res_start + adapter->dev_ops.static_reg_info[0].start;
+	len = resource_size(&adapter->dev_ops.static_reg_info[0]);
+	hw->mbx.vaddr = devm_ioremap(dev, mbx_start, len);
+	if (!hw->mbx.vaddr) {
+		pci_err(pdev, "failed to allocate BAR0 mbx region\n");
+
+		return -ENOMEM;
+	}
+	hw->mbx.addr_start = adapter->dev_ops.static_reg_info[0].start;
+	hw->mbx.addr_len = len;
 
-	hw->hw_addr = pcim_iomap_table(pdev)[0];
-	if (!hw->hw_addr) {
-		pci_err(pdev, "failed to allocate PCI iomap table\n");
+	/* Map rstat space for resets */
+	rstat_start = res_start + adapter->dev_ops.static_reg_info[1].start;
+	len = resource_size(&adapter->dev_ops.static_reg_info[1]);
+	hw->rstat.vaddr = devm_ioremap(dev, rstat_start, len);
+	if (!hw->rstat.vaddr) {
+		pci_err(pdev, "failed to allocate BAR0 rstat region\n");
 
 		return -ENOMEM;
 	}
+	hw->rstat.addr_start = adapter->dev_ops.static_reg_info[1].start;
+	hw->rstat.addr_len = len;
 
 	hw->back = adapter;
 
@@ -161,9 +183,9 @@ static int idpf_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (err)
 		goto err_free;
 
-	err = pcim_iomap_regions(pdev, BIT(0), pci_name(pdev));
+	err = pcim_request_region(pdev, 0, pci_name(pdev));
 	if (err) {
-		pci_err(pdev, "pcim_iomap_regions failed %pe\n", ERR_PTR(err));
+		pci_err(pdev, "pcim_request_region failed %pe\n", ERR_PTR(err));
 
 		goto err_free;
 	}
diff --git a/drivers/net/ethernet/intel/idpf/idpf_mem.h b/drivers/net/ethernet/intel/idpf/idpf_mem.h
index b21a04fccf0f..2aaabdc02dd2 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_mem.h
+++ b/drivers/net/ethernet/intel/idpf/idpf_mem.h
@@ -12,9 +12,9 @@ struct idpf_dma_mem {
 	size_t size;
 };
 
-#define wr32(a, reg, value)	writel((value), ((a)->hw_addr + (reg)))
-#define rd32(a, reg)		readl((a)->hw_addr + (reg))
-#define wr64(a, reg, value)	writeq((value), ((a)->hw_addr + (reg)))
-#define rd64(a, reg)		readq((a)->hw_addr + (reg))
+#define idpf_mbx_wr32(a, reg, value)	writel((value), ((a)->mbx.vaddr + (reg)))
+#define idpf_mbx_rd32(a, reg)		readl((a)->mbx.vaddr + (reg))
+#define idpf_mbx_wr64(a, reg, value)	writeq((value), ((a)->mbx.vaddr + (reg)))
+#define idpf_mbx_rd64(a, reg)		readq((a)->mbx.vaddr + (reg))
 
 #endif /* _IDPF_MEM_H_ */
diff --git a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
index 2f84bd596ae4..259d50fded67 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_vf_dev.c
@@ -9,10 +9,13 @@
 
 /**
  * idpf_vf_ctlq_reg_init - initialize default mailbox registers
+ * @adapter: adapter structure
  * @cq: pointer to the array of create control queues
  */
-static void idpf_vf_ctlq_reg_init(struct idpf_ctlq_create_info *cq)
+static void idpf_vf_ctlq_reg_init(struct idpf_adapter *adapter,
+				  struct idpf_ctlq_create_info *cq)
 {
+	resource_size_t mbx_start = adapter->dev_ops.static_reg_info[0].start;
 	int i;
 
 	for (i = 0; i < IDPF_NUM_DFLT_MBX_Q; i++) {
@@ -21,22 +24,22 @@ static void idpf_vf_ctlq_reg_init(struct idpf_ctlq_create_info *cq)
 		switch (ccq->type) {
 		case IDPF_CTLQ_TYPE_MAILBOX_TX:
 			/* set head and tail registers in our local struct */
-			ccq->reg.head = VF_ATQH;
-			ccq->reg.tail = VF_ATQT;
-			ccq->reg.len = VF_ATQLEN;
-			ccq->reg.bah = VF_ATQBAH;
-			ccq->reg.bal = VF_ATQBAL;
+			ccq->reg.head = VF_ATQH - mbx_start;
+			ccq->reg.tail = VF_ATQT - mbx_start;
+			ccq->reg.len = VF_ATQLEN - mbx_start;
+			ccq->reg.bah = VF_ATQBAH - mbx_start;
+			ccq->reg.bal = VF_ATQBAL - mbx_start;
 			ccq->reg.len_mask = VF_ATQLEN_ATQLEN_M;
 			ccq->reg.len_ena_mask = VF_ATQLEN_ATQENABLE_M;
 			ccq->reg.head_mask = VF_ATQH_ATQH_M;
 			break;
 		case IDPF_CTLQ_TYPE_MAILBOX_RX:
 			/* set head and tail registers in our local struct */
-			ccq->reg.head = VF_ARQH;
-			ccq->reg.tail = VF_ARQT;
-			ccq->reg.len = VF_ARQLEN;
-			ccq->reg.bah = VF_ARQBAH;
-			ccq->reg.bal = VF_ARQBAL;
+			ccq->reg.head = VF_ARQH - mbx_start;
+			ccq->reg.tail = VF_ARQT - mbx_start;
+			ccq->reg.len = VF_ARQLEN - mbx_start;
+			ccq->reg.bah = VF_ARQBAH - mbx_start;
+			ccq->reg.bal = VF_ARQBAL - mbx_start;
 			ccq->reg.len_mask = VF_ARQLEN_ARQLEN_M;
 			ccq->reg.len_ena_mask = VF_ARQLEN_ARQENABLE_M;
 			ccq->reg.head_mask = VF_ARQH_ARQH_M;
@@ -129,7 +132,7 @@ free_reg_vals:
  */
 static void idpf_vf_reset_reg_init(struct idpf_adapter *adapter)
 {
-	adapter->reset_reg.rstat = idpf_get_reg_addr(adapter, VFGEN_RSTAT);
+	adapter->reset_reg.rstat = idpf_get_rstat_reg_addr(adapter, VFGEN_RSTAT);
 	adapter->reset_reg.rstat_m = VFGEN_RSTAT_VFR_STATE_M;
 }
 
@@ -180,4 +183,9 @@ void idpf_vf_dev_ops_init(struct idpf_adapter *adapter)
 	idpf_vf_reg_ops_init(adapter);
 
 	adapter->dev_ops.idc_init = idpf_idc_vf_register;
+
+	resource_set_range(&adapter->dev_ops.static_reg_info[0],
+			   VF_BASE, IDPF_VF_MBX_REGION_SZ);
+	resource_set_range(&adapter->dev_ops.static_reg_info[1],
+			   VFGEN_RSTAT, IDPF_VF_RSTAT_REGION_SZ);
 }
diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
index 957b3b77700a..0d2199ac5c3e 100644
--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
@@ -870,6 +870,7 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 	caps.other_caps =
 		cpu_to_le64(VIRTCHNL2_CAP_SRIOV			|
 			    VIRTCHNL2_CAP_RDMA                  |
+			    VIRTCHNL2_CAP_LAN_MEMORY_REGIONS	|
 			    VIRTCHNL2_CAP_MACFILTER		|
 			    VIRTCHNL2_CAP_SPLITQ_QSCHED		|
 			    VIRTCHNL2_CAP_PROMISC		|
@@ -892,6 +893,128 @@ static int idpf_send_get_caps_msg(struct idpf_adapter *adapter)
 	return 0;
 }
 
+/**
+ * idpf_send_get_lan_memory_regions - Send virtchnl get LAN memory regions msg
+ * @adapter: Driver specific private struct
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_send_get_lan_memory_regions(struct idpf_adapter *adapter)
+{
+	struct virtchnl2_get_lan_memory_regions *rcvd_regions __free(kfree);
+	struct idpf_vc_xn_params xn_params = {
+		.vc_op = VIRTCHNL2_OP_GET_LAN_MEMORY_REGIONS,
+		.recv_buf.iov_len = IDPF_CTLQ_MAX_BUF_LEN,
+		.timeout_ms = IDPF_VC_XN_DEFAULT_TIMEOUT_MSEC,
+	};
+	int num_regions, size;
+	struct idpf_hw *hw;
+	ssize_t reply_sz;
+	int err = 0;
+
+	rcvd_regions = kzalloc(IDPF_CTLQ_MAX_BUF_LEN, GFP_KERNEL);
+	if (!rcvd_regions)
+		return -ENOMEM;
+
+	xn_params.recv_buf.iov_base = rcvd_regions;
+	reply_sz = idpf_vc_xn_exec(adapter, &xn_params);
+	if (reply_sz < 0)
+		return reply_sz;
+
+	num_regions = le16_to_cpu(rcvd_regions->num_memory_regions);
+	size = struct_size(rcvd_regions, mem_reg, num_regions);
+	if (reply_sz < size)
+		return -EIO;
+
+	if (size > IDPF_CTLQ_MAX_BUF_LEN)
+		return -EINVAL;
+
+	hw = &adapter->hw;
+	hw->lan_regs = kcalloc(num_regions, sizeof(*hw->lan_regs), GFP_KERNEL);
+	if (!hw->lan_regs)
+		return -ENOMEM;
+
+	for (int i = 0; i < num_regions; i++) {
+		hw->lan_regs[i].addr_len =
+			le64_to_cpu(rcvd_regions->mem_reg[i].size);
+		hw->lan_regs[i].addr_start =
+			le64_to_cpu(rcvd_regions->mem_reg[i].start_offset);
+	}
+	hw->num_lan_regs = num_regions;
+
+	return err;
+}
+
+/**
+ * idpf_calc_remaining_mmio_regs - calculate MMIO regions outside mbx and rstat
+ * @adapter: Driver specific private structure
+ *
+ * Called when idpf_send_get_lan_memory_regions is not supported. This will
+ * calculate the offsets and sizes for the regions before, in between, and
+ * after the mailbox and rstat MMIO mappings.
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_calc_remaining_mmio_regs(struct idpf_adapter *adapter)
+{
+	struct resource *rstat_reg = &adapter->dev_ops.static_reg_info[1];
+	struct resource *mbx_reg = &adapter->dev_ops.static_reg_info[0];
+	struct idpf_hw *hw = &adapter->hw;
+
+	hw->num_lan_regs = IDPF_MMIO_MAP_FALLBACK_MAX_REMAINING;
+	hw->lan_regs = kcalloc(hw->num_lan_regs, sizeof(*hw->lan_regs),
+			       GFP_KERNEL);
+	if (!hw->lan_regs)
+		return -ENOMEM;
+
+	/* Region preceding mailbox */
+	hw->lan_regs[0].addr_start = 0;
+	hw->lan_regs[0].addr_len = mbx_reg->start;
+	/* Region between mailbox and rstat */
+	hw->lan_regs[1].addr_start = mbx_reg->end + 1;
+	hw->lan_regs[1].addr_len = rstat_reg->start -
+					hw->lan_regs[1].addr_start;
+	/* Region after rstat */
+	hw->lan_regs[2].addr_start = rstat_reg->end + 1;
+	hw->lan_regs[2].addr_len = pci_resource_len(adapter->pdev, 0) -
+					hw->lan_regs[2].addr_start;
+
+	return 0;
+}
+
+/**
+ * idpf_map_lan_mmio_regs - map remaining LAN BAR regions
+ * @adapter: Driver specific private structure
+ *
+ * Return: 0 on success or error code on failure.
+ */
+static int idpf_map_lan_mmio_regs(struct idpf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct idpf_hw *hw = &adapter->hw;
+	resource_size_t res_start;
+
+	res_start = pci_resource_start(pdev, 0);
+
+	for (int i = 0; i < hw->num_lan_regs; i++) {
+		resource_size_t start;
+		long len;
+
+		len = hw->lan_regs[i].addr_len;
+		if (!len)
+			continue;
+		start = hw->lan_regs[i].addr_start + res_start;
+
+		hw->lan_regs[i].vaddr = devm_ioremap(&pdev->dev, start, len);
+		if (!hw->lan_regs[i].vaddr) {
+			pci_err(pdev, "failed to allocate BAR0 region\n");
+			return -ENOMEM;
+		}
+	}
+
+	return 0;
+}
+
 /**
  * idpf_vport_alloc_max_qs - Allocate max queues for a vport
  * @adapter: Driver specific private structure
@@ -2803,7 +2926,7 @@ int idpf_init_dflt_mbx(struct idpf_adapter *adapter)
 	struct idpf_hw *hw = &adapter->hw;
 	int err;
 
-	adapter->dev_ops.reg_ops.ctlq_reg_init(ctlq_info);
+	adapter->dev_ops.reg_ops.ctlq_reg_init(adapter, ctlq_info);
 
 	err = idpf_ctlq_init(hw, IDPF_NUM_DFLT_MBX_Q, ctlq_info);
 	if (err)
@@ -2963,6 +3086,30 @@ restart:
 		msleep(task_delay);
 	}
 
+	if (idpf_is_cap_ena(adapter, IDPF_OTHER_CAPS, VIRTCHNL2_CAP_LAN_MEMORY_REGIONS)) {
+		err = idpf_send_get_lan_memory_regions(adapter);
+		if (err) {
+			dev_err(&adapter->pdev->dev, "Failed to get LAN memory regions: %d\n",
+				err);
+			return -EINVAL;
+		}
+	} else {
+		/* Fallback to mapping the remaining regions of the entire BAR */
+		err = idpf_calc_remaining_mmio_regs(adapter);
+		if (err) {
+			dev_err(&adapter->pdev->dev, "Failed to allocate BAR0 region(s): %d\n",
+				err);
+			return -ENOMEM;
+		}
+	}
+
+	err = idpf_map_lan_mmio_regs(adapter);
+	if (err) {
+		dev_err(&adapter->pdev->dev, "Failed to map BAR0 region(s): %d\n",
+			err);
+		return -ENOMEM;
+	}
+
 	pci_sriov_set_totalvfs(adapter->pdev, idpf_get_max_vfs(adapter));
 	num_max_vports = idpf_get_max_vports(adapter);
 	adapter->max_vports = num_max_vports;
diff --git a/drivers/net/ethernet/intel/idpf/virtchnl2.h b/drivers/net/ethernet/intel/idpf/virtchnl2.h
index b82218d20909..48d3cc9236a4 100644
--- a/drivers/net/ethernet/intel/idpf/virtchnl2.h
+++ b/drivers/net/ethernet/intel/idpf/virtchnl2.h
@@ -79,6 +79,7 @@ enum virtchnl2_op {
 	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_FINE		= 546,
 	VIRTCHNL2_OP_PTP_ADJ_DEV_CLK_TIME		= 547,
 	VIRTCHNL2_OP_PTP_GET_VPORT_TX_TSTAMP_CAPS	= 548,
+	VIRTCHNL2_OP_GET_LAN_MEMORY_REGIONS		= 549,
 };
 
 /**
@@ -212,7 +213,8 @@ enum virtchnl2_cap_other {
 	VIRTCHNL2_CAP_RX_FLEX_DESC		= BIT_ULL(17),
 	VIRTCHNL2_CAP_PTYPE			= BIT_ULL(18),
 	VIRTCHNL2_CAP_LOOPBACK			= BIT_ULL(19),
-	/* Other capability 20 is reserved */
+	/* Other capability 20-21 is reserved */
+	VIRTCHNL2_CAP_LAN_MEMORY_REGIONS	= BIT_ULL(22),
 
 	/* this must be the last capability */
 	VIRTCHNL2_CAP_OEM			= BIT_ULL(63),
@@ -1587,4 +1589,30 @@ struct virtchnl2_ptp_adj_dev_clk_time {
 };
 VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_ptp_adj_dev_clk_time);
 
+/**
+ * struct virtchnl2_mem_region - MMIO memory region
+ * @start_offset: starting offset of the MMIO memory region
+ * @size: size of the MMIO memory region
+ */
+struct virtchnl2_mem_region {
+	__le64 start_offset;
+	__le64 size;
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(16, virtchnl2_mem_region);
+
+/**
+ * struct virtchnl2_get_lan_memory_regions - List of LAN MMIO memory regions
+ * @num_memory_regions: number of memory regions
+ * @pad: Padding
+ * @mem_reg: List with memory region info
+ *
+ * PF/VF sends this message to learn what LAN MMIO memory regions it should map.
+ */
+struct virtchnl2_get_lan_memory_regions {
+	__le16 num_memory_regions;
+	u8 pad[6];
+	struct virtchnl2_mem_region mem_reg[];
+};
+VIRTCHNL2_CHECK_STRUCT_LEN(8, virtchnl2_get_lan_memory_regions);
+
 #endif /* _VIRTCHNL_2_H_ */
diff --git a/include/linux/net/intel/iidc_rdma_idpf.h b/include/linux/net/intel/iidc_rdma_idpf.h
index 16c970dd4c6e..bab697e18fd6 100644
--- a/include/linux/net/intel/iidc_rdma_idpf.h
+++ b/include/linux/net/intel/iidc_rdma_idpf.h
@@ -31,10 +31,18 @@ enum iidc_function_type {
 	IIDC_FUNCTION_TYPE_VF,
 };
 
+struct iidc_rdma_lan_mapped_mem_region {
+	u8 __iomem *region_addr;
+	__le64 size;
+	__le64 start_offset;
+};
+
 struct iidc_rdma_priv_dev_info {
 	struct msix_entry *msix_entries;
 	u16 msix_count; /* How many vectors are reserved for this device */
 	enum iidc_function_type ftype;
+	__le16 num_memory_regions;
+	struct iidc_rdma_lan_mapped_mem_region *mapped_mem_regions;
 };
 
 int idpf_idc_vport_dev_ctrl(struct iidc_rdma_core_dev_info *cdev_info, bool up);
-- 
cgit v1.2.3


From 84f890414a12b8d1480045b92a5e4e6ac4ab3419 Mon Sep 17 00:00:00 2001
From: Michał Winiarski <michal.winiarski@intel.com>
Date: Wed, 2 Jul 2025 11:35:22 +0200
Subject: PCI/IOV: Allow drivers to control VF BAR size
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Drivers could leverage the fact that the VF BAR MMIO reservation is created
for total number of VFs supported by the device by resizing the BAR to
larger size when smaller number of VFs is enabled.

Add pci_iov_vf_bar_set_size() to control the size and a
pci_iov_vf_bar_get_sizes() helper to get the VF BAR sizes that will allow
up to num_vfs to be successfully enabled with the current underlying
reservation size.

Signed-off-by: Michał Winiarski <michal.winiarski@intel.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Ilpo Järvinen <ilpo.jarvinen@linux.intel.com>
Link: https://patch.msgid.link/20250702093522.518099-6-michal.winiarski@intel.com
---
 drivers/pci/iov.c   | 73 +++++++++++++++++++++++++++++++++++++++++++++++++++++
 include/linux/pci.h |  6 +++++
 2 files changed, 79 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c
index f34173c70b32..ac4375954c94 100644
--- a/drivers/pci/iov.c
+++ b/drivers/pci/iov.c
@@ -8,11 +8,15 @@
  */
 
 #include <linux/bitfield.h>
+#include <linux/bits.h>
+#include <linux/log2.h>
 #include <linux/pci.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/export.h>
 #include <linux/string.h>
 #include <linux/delay.h>
+#include <asm/div64.h>
 #include "pci.h"
 
 #define VIRTFN_ID_LEN	17	/* "virtfn%u\0" for 2^32 - 1 */
@@ -1313,3 +1317,72 @@ int pci_sriov_configure_simple(struct pci_dev *dev, int nr_virtfn)
 	return nr_virtfn;
 }
 EXPORT_SYMBOL_GPL(pci_sriov_configure_simple);
+
+/**
+ * pci_iov_vf_bar_set_size - set a new size for a VF BAR
+ * @dev: the PCI device
+ * @resno: the resource number
+ * @size: new size as defined in the spec (0=1MB, 31=128TB)
+ *
+ * Set the new size of a VF BAR that supports VF resizable BAR capability.
+ * Unlike pci_resize_resource(), this does not cause the resource that
+ * reserves the MMIO space (originally up to total_VFs) to be resized, which
+ * means that following calls to pci_enable_sriov() can fail if the resources
+ * no longer fit.
+ *
+ * Return: 0 on success, or negative on failure.
+ */
+int pci_iov_vf_bar_set_size(struct pci_dev *dev, int resno, int size)
+{
+	u32 sizes;
+	int ret;
+
+	if (!pci_resource_is_iov(resno))
+		return -EINVAL;
+
+	if (pci_iov_is_memory_decoding_enabled(dev))
+		return -EBUSY;
+
+	sizes = pci_rebar_get_possible_sizes(dev, resno);
+	if (!sizes)
+		return -ENOTSUPP;
+
+	if (!(sizes & BIT(size)))
+		return -EINVAL;
+
+	ret = pci_rebar_set_size(dev, resno, size);
+	if (ret)
+		return ret;
+
+	pci_iov_resource_set_size(dev, resno, pci_rebar_size_to_bytes(size));
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_iov_vf_bar_set_size);
+
+/**
+ * pci_iov_vf_bar_get_sizes - get VF BAR sizes allowing to create up to num_vfs
+ * @dev: the PCI device
+ * @resno: the resource number
+ * @num_vfs: number of VFs
+ *
+ * Get the sizes of a VF resizable BAR that can accommodate @num_vfs within
+ * the currently assigned size of the resource @resno.
+ *
+ * Return: A bitmask of sizes in format defined in the spec (bit 0=1MB,
+ * bit 31=128TB).
+ */
+u32 pci_iov_vf_bar_get_sizes(struct pci_dev *dev, int resno, int num_vfs)
+{
+	u64 vf_len = pci_resource_len(dev, resno);
+	u32 sizes;
+
+	if (!num_vfs)
+		return 0;
+
+	do_div(vf_len, num_vfs);
+	sizes = (roundup_pow_of_two(vf_len + 1) - 1) >> ilog2(SZ_1M);
+
+	return sizes & pci_rebar_get_possible_sizes(dev, resno);
+}
+EXPORT_SYMBOL_GPL(pci_iov_vf_bar_get_sizes);
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 05e68f35f392..28f06045ab20 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -2438,6 +2438,8 @@ int pci_sriov_set_totalvfs(struct pci_dev *dev, u16 numvfs);
 int pci_sriov_get_totalvfs(struct pci_dev *dev);
 int pci_sriov_configure_simple(struct pci_dev *dev, int nr_virtfn);
 resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno);
+int pci_iov_vf_bar_set_size(struct pci_dev *dev, int resno, int size);
+u32 pci_iov_vf_bar_get_sizes(struct pci_dev *dev, int resno, int num_vfs);
 void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool probe);
 
 /* Arch may override these (weak) */
@@ -2490,6 +2492,10 @@ static inline int pci_sriov_get_totalvfs(struct pci_dev *dev)
 #define pci_sriov_configure_simple	NULL
 static inline resource_size_t pci_iov_resource_size(struct pci_dev *dev, int resno)
 { return 0; }
+static inline int pci_iov_vf_bar_set_size(struct pci_dev *dev, int resno, int size)
+{ return -ENODEV; }
+static inline u32 pci_iov_vf_bar_get_sizes(struct pci_dev *dev, int resno, int num_vfs)
+{ return 0; }
 static inline void pci_vf_drivers_autoprobe(struct pci_dev *dev, bool probe) { }
 #endif
 
-- 
cgit v1.2.3


From ce60ab3964782df9ba34f0a64c0bc766dd508bde Mon Sep 17 00:00:00 2001
From: Trond Myklebust <trond.myklebust@primarydata.com>
Date: Thu, 29 May 2025 06:45:45 -0400
Subject: Expand the type of nfs_fattr->valid

We need to be able to track more than 32 attributes per inode.

Signed-off-by: Trond Myklebust <trond.myklebust@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/1e3405fca54efd0be7c91c1da77917b94f5dfcc4.1748515333.git.bcodding@redhat.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/inode.c            |  2 +-
 include/linux/nfs_fs_sb.h |  2 +-
 include/linux/nfs_xdr.h   | 54 +++++++++++++++++++++++------------------------
 3 files changed, 29 insertions(+), 29 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index a2fa6bc4d74e..17f5dcda2a00 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -2209,7 +2209,7 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 	bool attr_changed = false;
 	bool have_delegation;
 
-	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%x)\n",
+	dfprintk(VFS, "NFS: %s(%s/%lu fh_crc=0x%08x ct=%d info=0x%llx)\n",
 			__func__, inode->i_sb->s_id, inode->i_ino,
 			nfs_display_fhandle_hash(NFS_FH(inode)),
 			atomic_read(&inode->i_count), fattr->valid);
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 63141320c2a8..d7895eeccea3 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -172,8 +172,8 @@ struct nfs_server {
 #define NFS_MOUNT_FORCE_RDIRPLUS	0x20000000
 #define NFS_MOUNT_NETUNREACH_FATAL	0x40000000
 
-	unsigned int		fattr_valid;	/* Valid attributes */
 	unsigned int		caps;		/* server capabilities */
+	__u64			fattr_valid;	/* Valid attributes */
 	unsigned int		rsize;		/* read size */
 	unsigned int		rpages;		/* read size (in pages) */
 	unsigned int		wsize;		/* write size */
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 67f6632f723b..9cacbbd14787 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -45,7 +45,7 @@ struct nfs4_threshold {
 };
 
 struct nfs_fattr {
-	unsigned int		valid;		/* which fields are valid */
+	__u64			valid;		/* which fields are valid */
 	umode_t			mode;
 	__u32			nlink;
 	kuid_t			uid;
@@ -80,32 +80,32 @@ struct nfs_fattr {
 	struct nfs4_label	*label;
 };
 
-#define NFS_ATTR_FATTR_TYPE		(1U << 0)
-#define NFS_ATTR_FATTR_MODE		(1U << 1)
-#define NFS_ATTR_FATTR_NLINK		(1U << 2)
-#define NFS_ATTR_FATTR_OWNER		(1U << 3)
-#define NFS_ATTR_FATTR_GROUP		(1U << 4)
-#define NFS_ATTR_FATTR_RDEV		(1U << 5)
-#define NFS_ATTR_FATTR_SIZE		(1U << 6)
-#define NFS_ATTR_FATTR_PRESIZE		(1U << 7)
-#define NFS_ATTR_FATTR_BLOCKS_USED	(1U << 8)
-#define NFS_ATTR_FATTR_SPACE_USED	(1U << 9)
-#define NFS_ATTR_FATTR_FSID		(1U << 10)
-#define NFS_ATTR_FATTR_FILEID		(1U << 11)
-#define NFS_ATTR_FATTR_ATIME		(1U << 12)
-#define NFS_ATTR_FATTR_MTIME		(1U << 13)
-#define NFS_ATTR_FATTR_CTIME		(1U << 14)
-#define NFS_ATTR_FATTR_PREMTIME		(1U << 15)
-#define NFS_ATTR_FATTR_PRECTIME		(1U << 16)
-#define NFS_ATTR_FATTR_CHANGE		(1U << 17)
-#define NFS_ATTR_FATTR_PRECHANGE	(1U << 18)
-#define NFS_ATTR_FATTR_V4_LOCATIONS	(1U << 19)
-#define NFS_ATTR_FATTR_V4_REFERRAL	(1U << 20)
-#define NFS_ATTR_FATTR_MOUNTPOINT	(1U << 21)
-#define NFS_ATTR_FATTR_MOUNTED_ON_FILEID (1U << 22)
-#define NFS_ATTR_FATTR_OWNER_NAME	(1U << 23)
-#define NFS_ATTR_FATTR_GROUP_NAME	(1U << 24)
-#define NFS_ATTR_FATTR_V4_SECURITY_LABEL (1U << 25)
+#define NFS_ATTR_FATTR_TYPE		BIT_ULL(0)
+#define NFS_ATTR_FATTR_MODE		BIT_ULL(1)
+#define NFS_ATTR_FATTR_NLINK		BIT_ULL(2)
+#define NFS_ATTR_FATTR_OWNER		BIT_ULL(3)
+#define NFS_ATTR_FATTR_GROUP		BIT_ULL(4)
+#define NFS_ATTR_FATTR_RDEV		BIT_ULL(5)
+#define NFS_ATTR_FATTR_SIZE		BIT_ULL(6)
+#define NFS_ATTR_FATTR_PRESIZE		BIT_ULL(7)
+#define NFS_ATTR_FATTR_BLOCKS_USED	BIT_ULL(8)
+#define NFS_ATTR_FATTR_SPACE_USED	BIT_ULL(9)
+#define NFS_ATTR_FATTR_FSID		BIT_ULL(10)
+#define NFS_ATTR_FATTR_FILEID		BIT_ULL(11)
+#define NFS_ATTR_FATTR_ATIME		BIT_ULL(12)
+#define NFS_ATTR_FATTR_MTIME		BIT_ULL(13)
+#define NFS_ATTR_FATTR_CTIME		BIT_ULL(14)
+#define NFS_ATTR_FATTR_PREMTIME		BIT_ULL(15)
+#define NFS_ATTR_FATTR_PRECTIME		BIT_ULL(16)
+#define NFS_ATTR_FATTR_CHANGE		BIT_ULL(17)
+#define NFS_ATTR_FATTR_PRECHANGE	BIT_ULL(18)
+#define NFS_ATTR_FATTR_V4_LOCATIONS	BIT_ULL(19)
+#define NFS_ATTR_FATTR_V4_REFERRAL	BIT_ULL(20)
+#define NFS_ATTR_FATTR_MOUNTPOINT	BIT_ULL(21)
+#define NFS_ATTR_FATTR_MOUNTED_ON_FILEID BIT_ULL(22)
+#define NFS_ATTR_FATTR_OWNER_NAME	BIT_ULL(23)
+#define NFS_ATTR_FATTR_GROUP_NAME	BIT_ULL(24)
+#define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25)
 
 #define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \
 		| NFS_ATTR_FATTR_MODE \
-- 
cgit v1.2.3


From 1c7ae2dd3f0e6d07ec0a5a348f2561f2171b9c81 Mon Sep 17 00:00:00 2001
From: Anne Marie Merritt <annemarie.merritt@primarydata.com>
Date: Thu, 29 May 2025 06:45:46 -0400
Subject: nfs: Add timecreate to nfs inode

Add tracking of the create time (a.k.a. btime) along with corresponding
bitfields, request, and decode xdr routines.

Signed-off-by: Anne Marie Merritt <annemarie.merritt@primarydata.com>
Signed-off-by: Lance Shelton <lance.shelton@hammerspace.com>
Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/1e3677b0655fa2bbaba0817b41d111d94a06e5ee.1748515333.git.bcodding@redhat.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/inode.c          | 17 +++++++++++++++--
 fs/nfs/nfs4proc.c       | 14 +++++++++++++-
 fs/nfs/nfs4xdr.c        | 24 ++++++++++++++++++++++++
 fs/nfs/nfstrace.h       |  3 ++-
 include/linux/nfs_fs.h  |  8 ++++++++
 include/linux/nfs_xdr.h |  3 +++
 6 files changed, 65 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 17f5dcda2a00..c5462aed6bf5 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -197,6 +197,7 @@ void nfs_set_cache_invalid(struct inode *inode, unsigned long flags)
 		if (!(flags & NFS_INO_REVAL_FORCED))
 			flags &= ~(NFS_INO_INVALID_MODE |
 				   NFS_INO_INVALID_OTHER |
+				   NFS_INO_INVALID_BTIME |
 				   NFS_INO_INVALID_XATTR);
 		flags &= ~(NFS_INO_INVALID_CHANGE | NFS_INO_INVALID_SIZE);
 	}
@@ -522,6 +523,7 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		inode_set_atime(inode, 0, 0);
 		inode_set_mtime(inode, 0, 0);
 		inode_set_ctime(inode, 0, 0);
+		memset(&nfsi->btime, 0, sizeof(nfsi->btime));
 		inode_set_iversion_raw(inode, 0);
 		inode->i_size = 0;
 		clear_nlink(inode);
@@ -545,6 +547,10 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 			inode_set_ctime_to_ts(inode, fattr->ctime);
 		else if (fattr_supported & NFS_ATTR_FATTR_CTIME)
 			nfs_set_cache_invalid(inode, NFS_INO_INVALID_CTIME);
+		if (fattr->valid & NFS_ATTR_FATTR_BTIME)
+			nfsi->btime = fattr->btime;
+		else if (fattr_supported & NFS_ATTR_FATTR_BTIME)
+			nfs_set_cache_invalid(inode, NFS_INO_INVALID_BTIME);
 		if (fattr->valid & NFS_ATTR_FATTR_CHANGE)
 			inode_set_iversion_raw(inode, fattr->change_attr);
 		else
@@ -1943,7 +1949,7 @@ static int nfs_inode_finish_partial_attr_update(const struct nfs_fattr *fattr,
 		NFS_INO_INVALID_ATIME | NFS_INO_INVALID_CTIME |
 		NFS_INO_INVALID_MTIME | NFS_INO_INVALID_SIZE |
 		NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_OTHER |
-		NFS_INO_INVALID_NLINK;
+		NFS_INO_INVALID_NLINK | NFS_INO_INVALID_BTIME;
 	unsigned long cache_validity = NFS_I(inode)->cache_validity;
 	enum nfs4_change_attr_type ctype = NFS_SERVER(inode)->change_attr_type;
 
@@ -2304,7 +2310,8 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 					| NFS_INO_INVALID_BLOCKS
 					| NFS_INO_INVALID_NLINK
 					| NFS_INO_INVALID_MODE
-					| NFS_INO_INVALID_OTHER;
+					| NFS_INO_INVALID_OTHER
+					| NFS_INO_INVALID_BTIME;
 				if (S_ISDIR(inode->i_mode))
 					nfs_force_lookup_revalidate(inode);
 				attr_changed = true;
@@ -2338,6 +2345,12 @@ static int nfs_update_inode(struct inode *inode, struct nfs_fattr *fattr)
 		nfsi->cache_validity |=
 			save_cache_validity & NFS_INO_INVALID_CTIME;
 
+	if (fattr->valid & NFS_ATTR_FATTR_BTIME)
+		nfsi->btime = fattr->btime;
+	else if (fattr_supported & NFS_ATTR_FATTR_BTIME)
+		nfsi->cache_validity |=
+			save_cache_validity & NFS_INO_INVALID_BTIME;
+
 	/* Check if our cached file size is stale */
 	if (fattr->valid & NFS_ATTR_FATTR_SIZE) {
 		new_isize = nfs_size_to_loff_t(fattr->size);
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 341740fa293d..92f1b2601b67 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -222,6 +222,7 @@ const u32 nfs4_fattr_bitmap[3] = {
 	| FATTR4_WORD1_RAWDEV
 	| FATTR4_WORD1_SPACE_USED
 	| FATTR4_WORD1_TIME_ACCESS
+	| FATTR4_WORD1_TIME_CREATE
 	| FATTR4_WORD1_TIME_METADATA
 	| FATTR4_WORD1_TIME_MODIFY
 	| FATTR4_WORD1_MOUNTED_ON_FILEID,
@@ -243,6 +244,7 @@ static const u32 nfs4_pnfs_open_bitmap[3] = {
 	| FATTR4_WORD1_RAWDEV
 	| FATTR4_WORD1_SPACE_USED
 	| FATTR4_WORD1_TIME_ACCESS
+	| FATTR4_WORD1_TIME_CREATE
 	| FATTR4_WORD1_TIME_METADATA
 	| FATTR4_WORD1_TIME_MODIFY,
 	FATTR4_WORD2_MDSTHRESHOLD
@@ -323,6 +325,9 @@ static void nfs4_bitmap_copy_adjust(__u32 *dst, const __u32 *src,
 	if (!(cache_validity & NFS_INO_INVALID_OTHER))
 		dst[1] &= ~(FATTR4_WORD1_OWNER | FATTR4_WORD1_OWNER_GROUP);
 
+	if (!(cache_validity & NFS_INO_INVALID_BTIME))
+		dst[1] &= ~FATTR4_WORD1_TIME_CREATE;
+
 	if (nfs_have_delegated_mtime(inode)) {
 		if (!(cache_validity & NFS_INO_INVALID_ATIME))
 			dst[1] &= ~(FATTR4_WORD1_TIME_ACCESS|FATTR4_WORD1_TIME_ACCESS_SET);
@@ -1307,7 +1312,8 @@ nfs4_update_changeattr_locked(struct inode *inode,
 				NFS_INO_INVALID_ACCESS | NFS_INO_INVALID_ACL |
 				NFS_INO_INVALID_SIZE | NFS_INO_INVALID_OTHER |
 				NFS_INO_INVALID_BLOCKS | NFS_INO_INVALID_NLINK |
-				NFS_INO_INVALID_MODE | NFS_INO_INVALID_XATTR;
+				NFS_INO_INVALID_MODE | NFS_INO_INVALID_BTIME |
+				NFS_INO_INVALID_XATTR;
 		nfsi->attrtimeo = NFS_MINATTRTIMEO(inode);
 	}
 	nfsi->attrtimeo_timestamp = jiffies;
@@ -4047,6 +4053,10 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 			server->fattr_valid &= ~NFS_ATTR_FATTR_CTIME;
 		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY))
 			server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_MODIFY))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_MTIME;
+		if (!(res.attr_bitmask[1] & FATTR4_WORD1_TIME_CREATE))
+			server->fattr_valid &= ~NFS_ATTR_FATTR_BTIME;
 		memcpy(server->attr_bitmask_nl, res.attr_bitmask,
 				sizeof(server->attr_bitmask));
 		server->attr_bitmask_nl[2] &= ~FATTR4_WORD2_SECURITY_LABEL;
@@ -5781,6 +5791,8 @@ void nfs4_bitmask_set(__u32 bitmask[], const __u32 src[],
 		bitmask[1] |= FATTR4_WORD1_TIME_MODIFY;
 	if (cache_validity & NFS_INO_INVALID_BLOCKS)
 		bitmask[1] |= FATTR4_WORD1_SPACE_USED;
+	if (cache_validity & NFS_INO_INVALID_BTIME)
+		bitmask[1] |= FATTR4_WORD1_TIME_CREATE;
 
 	if (cache_validity & NFS_INO_INVALID_SIZE)
 		bitmask[0] |= FATTR4_WORD0_SIZE;
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index 318afde38057..49ff98571fa5 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -1623,6 +1623,7 @@ static void encode_readdir(struct xdr_stream *xdr, const struct nfs4_readdir_arg
 			| FATTR4_WORD1_RAWDEV
 			| FATTR4_WORD1_SPACE_USED
 			| FATTR4_WORD1_TIME_ACCESS
+			| FATTR4_WORD1_TIME_CREATE
 			| FATTR4_WORD1_TIME_METADATA
 			| FATTR4_WORD1_TIME_MODIFY;
 		attrs[2] |= FATTR4_WORD2_SECURITY_LABEL;
@@ -4207,6 +4208,24 @@ static int decode_attr_time_access(struct xdr_stream *xdr, uint32_t *bitmap, str
 	return status;
 }
 
+static int decode_attr_time_create(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time)
+{
+	int status = 0;
+
+	time->tv_sec = 0;
+	time->tv_nsec = 0;
+	if (unlikely(bitmap[1] & (FATTR4_WORD1_TIME_CREATE - 1U)))
+		return -EIO;
+	if (likely(bitmap[1] & FATTR4_WORD1_TIME_CREATE)) {
+		status = decode_attr_time(xdr, time);
+		if (status == 0)
+			status = NFS_ATTR_FATTR_BTIME;
+		bitmap[1] &= ~FATTR4_WORD1_TIME_CREATE;
+	}
+	dprintk("%s: btime=%lld\n", __func__, time->tv_sec);
+	return status;
+}
+
 static int decode_attr_time_metadata(struct xdr_stream *xdr, uint32_t *bitmap, struct timespec64 *time)
 {
 	int status = 0;
@@ -4781,6 +4800,11 @@ static int decode_getfattr_attrs(struct xdr_stream *xdr, uint32_t *bitmap,
 		goto xdr_error;
 	fattr->valid |= status;
 
+	status = decode_attr_time_create(xdr, bitmap, &fattr->btime);
+	if (status < 0)
+		goto xdr_error;
+	fattr->valid |= status;
+
 	status = decode_attr_time_metadata(xdr, bitmap, &fattr->ctime);
 	if (status < 0)
 		goto xdr_error;
diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
index 7a058bd8c566..f49f064c5ee5 100644
--- a/fs/nfs/nfstrace.h
+++ b/fs/nfs/nfstrace.h
@@ -32,7 +32,8 @@
 			{ NFS_INO_INVALID_BLOCKS, "INVALID_BLOCKS" }, \
 			{ NFS_INO_INVALID_XATTR, "INVALID_XATTR" }, \
 			{ NFS_INO_INVALID_NLINK, "INVALID_NLINK" }, \
-			{ NFS_INO_INVALID_MODE, "INVALID_MODE" })
+			{ NFS_INO_INVALID_MODE, "INVALID_MODE" }, \
+			{ NFS_INO_INVALID_BTIME, "INVALID_BTIME" })
 
 #define nfs_show_nfsi_flags(v) \
 	__print_flags(v, "|", \
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index 67ae2c3f41d2..c585939b6cd6 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -160,6 +160,12 @@ struct nfs_inode {
 	unsigned long		flags;			/* atomic bit ops */
 	unsigned long		cache_validity;		/* bit mask */
 
+	/*
+	 * NFS Attributes not included in struct inode
+	 */
+
+	struct timespec64	btime;
+
 	/*
 	 * read_cache_jiffies is when we started read-caching this inode.
 	 * attrtimeo is for how long the cached information is assumed
@@ -316,10 +322,12 @@ struct nfs4_copy_state {
 #define NFS_INO_INVALID_XATTR	BIT(15)		/* xattrs are invalid */
 #define NFS_INO_INVALID_NLINK	BIT(16)		/* cached nlinks is invalid */
 #define NFS_INO_INVALID_MODE	BIT(17)		/* cached mode is invalid */
+#define NFS_INO_INVALID_BTIME	BIT(18)		/* cached btime is invalid */
 
 #define NFS_INO_INVALID_ATTR	(NFS_INO_INVALID_CHANGE \
 		| NFS_INO_INVALID_CTIME \
 		| NFS_INO_INVALID_MTIME \
+		| NFS_INO_INVALID_BTIME \
 		| NFS_INO_INVALID_SIZE \
 		| NFS_INO_INVALID_NLINK \
 		| NFS_INO_INVALID_MODE \
diff --git a/include/linux/nfs_xdr.h b/include/linux/nfs_xdr.h
index 9cacbbd14787..ac4bff6e9913 100644
--- a/include/linux/nfs_xdr.h
+++ b/include/linux/nfs_xdr.h
@@ -67,6 +67,7 @@ struct nfs_fattr {
 	struct timespec64	atime;
 	struct timespec64	mtime;
 	struct timespec64	ctime;
+	struct timespec64	btime;
 	__u64			change_attr;	/* NFSv4 change attribute */
 	__u64			pre_change_attr;/* pre-op NFSv4 change attribute */
 	__u64			pre_size;	/* pre_op_attr.size	  */
@@ -106,6 +107,7 @@ struct nfs_fattr {
 #define NFS_ATTR_FATTR_OWNER_NAME	BIT_ULL(23)
 #define NFS_ATTR_FATTR_GROUP_NAME	BIT_ULL(24)
 #define NFS_ATTR_FATTR_V4_SECURITY_LABEL BIT_ULL(25)
+#define NFS_ATTR_FATTR_BTIME		BIT_ULL(26)
 
 #define NFS_ATTR_FATTR (NFS_ATTR_FATTR_TYPE \
 		| NFS_ATTR_FATTR_MODE \
@@ -126,6 +128,7 @@ struct nfs_fattr {
 		| NFS_ATTR_FATTR_SPACE_USED)
 #define NFS_ATTR_FATTR_V4 (NFS_ATTR_FATTR \
 		| NFS_ATTR_FATTR_SPACE_USED \
+		| NFS_ATTR_FATTR_BTIME \
 		| NFS_ATTR_FATTR_V4_SECURITY_LABEL)
 
 /*
-- 
cgit v1.2.3


From 0715a72ee9a38461eac4b34388b772914f269119 Mon Sep 17 00:00:00 2001
From: Anthony Iliopoulos <ailiop@suse.com>
Date: Fri, 13 Jun 2025 11:44:37 +0200
Subject: NFS: remove unused wpages field from struct nfs_server

The wpages field is not serving any purpose since commit c63c7b051395
("NFS: Fix a race when doing NFS write coalescing") which was merged in
v2.6.22-rc1. Remove it completely.

Signed-off-by: Anthony Iliopoulos <ailiop@suse.com>
Link: https://lore.kernel.org/r/20250613094439.82338-2-ailiop@suse.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/client.c           | 1 -
 include/linux/nfs_fs_sb.h | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index cf35ad3f818a..23dafc590476 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -814,7 +814,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->wsize = max_rpc_payload;
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
 		server->wsize = NFS_MAX_FILE_IO_SIZE;
-	server->wpages = (server->wsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
 	server->wtmult = nfs_block_bits(fsinfo->wtmult, NULL);
 
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index d7895eeccea3..7048f9b867ab 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -177,7 +177,6 @@ struct nfs_server {
 	unsigned int		rsize;		/* read size */
 	unsigned int		rpages;		/* read size (in pages) */
 	unsigned int		wsize;		/* write size */
-	unsigned int		wpages;		/* write size (in pages) */
 	unsigned int		wtmult;		/* server disk block size */
 	unsigned int		dtsize;		/* readdir size */
 	unsigned short		port;		/* "port=" setting */
-- 
cgit v1.2.3


From 74a33326cfe8e62ebe0a65ba01ea8a8bceb532f8 Mon Sep 17 00:00:00 2001
From: Anthony Iliopoulos <ailiop@suse.com>
Date: Fri, 13 Jun 2025 11:44:38 +0200
Subject: NFS: remove unused time_delta field from struct nfs_server

The last code that was using this was removed via commit ca0daa277aca
("NFS: Cache aggressively when file is open for writing") which was
merged in v4.8-rc1, so it can be removed completely.

Signed-off-by: Anthony Iliopoulos <ailiop@suse.com>
Link: https://lore.kernel.org/r/20250613094439.82338-3-ailiop@suse.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/client.c           | 1 -
 include/linux/nfs_fs_sb.h | 1 -
 2 files changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 23dafc590476..47258dc3af70 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -830,7 +830,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 
 	server->maxfilesize = fsinfo->maxfilesize;
 
-	server->time_delta = fsinfo->time_delta;
 	server->change_attr_type = fsinfo->change_attr_type;
 
 	server->clone_blksize = fsinfo->clone_blksize;
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 7048f9b867ab..e1b2cf57e765 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -202,7 +202,6 @@ struct nfs_server {
 	struct nfs_fsid		fsid;
 	int			s_sysfs_id;	/* sysfs dentry index */
 	__u64			maxfilesize;	/* maximum file size */
-	struct timespec64	time_delta;	/* smallest time granularity */
 	unsigned long		mount_time;	/* when this fs was mounted */
 	struct super_block	*super;		/* VFS super block */
 	dev_t			s_dev;		/* superblock dev numbers */
-- 
cgit v1.2.3


From 2c665d91c2a2d8b5bdf1374d1253b3c89fca4ede Mon Sep 17 00:00:00 2001
From: Anthony Iliopoulos <ailiop@suse.com>
Date: Fri, 13 Jun 2025 11:44:39 +0200
Subject: NFS: remove unused pnfs_ld_data field from struct nfs_server

The last code that was using this was removed via commit 20d655d6197d
("pnfs/blocklayout: use the device id cache") which was merged in
v3.18-rc1, so it can be removed completely.

Signed-off-by: Anthony Iliopoulos <ailiop@suse.com>
Link: https://lore.kernel.org/r/20250613094439.82338-4-ailiop@suse.com
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/nfs_fs_sb.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index e1b2cf57e765..d2d36711a119 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -246,7 +246,6 @@ struct nfs_server {
 						   filesystem */
 	struct pnfs_layoutdriver_type  *pnfs_curr_ld; /* Active layout driver */
 	struct rpc_wait_queue	roc_rpcwaitq;
-	void			*pnfs_ld_data;	/* per mount point data */
 
 	/* the following fields are protected by nfs_client->cl_lock */
 	struct rb_root		state_owners;
-- 
cgit v1.2.3


From 48693d119b2114f8eaf8b8f972b29e05ae581ad4 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 13 Jul 2025 00:30:06 +0100
Subject: SUNRPC: Remove unused xdr functions

Remove a bunch of unused xdr_*decode* functions:
  The last use of xdr_decode_netobj() was removed in 2021 by:
commit 7cf96b6d0104 ("lockd: Update the NLMv4 SHARE arguments decoder to
use struct xdr_stream")
  The last use of xdr_decode_string_inplace() was removed in 2021 by:
commit 3049e974a7c7 ("lockd: Update the NLMv4 FREE_ALL arguments decoder
to use struct xdr_stream")
  The last use of xdr_stream_decode_opaque() was removed in 2024 by:
commit fed8a17c61ff ("xdrgen: typedefs should use the built-in string and
opaque functions")

  The functions xdr_stream_decode_string() and
xdr_stream_decode_opaque_dup() were both added in 2018 by the
commit 0e779aa70308 ("SUNRPC: Add helpers for decoding opaque and string
types")
but never used.

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Link: https://lore.kernel.org/r/20250712233006.403226-1-linux@treblig.org
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 include/linux/sunrpc/xdr.h |   9 ----
 net/sunrpc/xdr.c           | 110 ---------------------------------------------
 2 files changed, 119 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sunrpc/xdr.h b/include/linux/sunrpc/xdr.h
index a2ab813a9800..e370886632b0 100644
--- a/include/linux/sunrpc/xdr.h
+++ b/include/linux/sunrpc/xdr.h
@@ -128,10 +128,7 @@ xdr_buf_init(struct xdr_buf *buf, void *start, size_t len)
 __be32 *xdr_encode_opaque_fixed(__be32 *p, const void *ptr, unsigned int len);
 __be32 *xdr_encode_opaque(__be32 *p, const void *ptr, unsigned int len);
 __be32 *xdr_encode_string(__be32 *p, const char *s);
-__be32 *xdr_decode_string_inplace(__be32 *p, char **sp, unsigned int *lenp,
-			unsigned int maxlen);
 __be32 *xdr_encode_netobj(__be32 *p, const struct xdr_netobj *);
-__be32 *xdr_decode_netobj(__be32 *p, struct xdr_netobj *);
 
 void	xdr_inline_pages(struct xdr_buf *, unsigned int,
 			 struct page **, unsigned int, unsigned int);
@@ -341,12 +338,6 @@ xdr_stream_remaining(const struct xdr_stream *xdr)
 	return xdr->nwords << 2;
 }
 
-ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr,
-		size_t size);
-ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr,
-		size_t maxlen, gfp_t gfp_flags);
-ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str,
-		size_t size);
 ssize_t xdr_stream_decode_string_dup(struct xdr_stream *xdr, char **str,
 		size_t maxlen, gfp_t gfp_flags);
 ssize_t xdr_stream_decode_opaque_auth(struct xdr_stream *xdr, u32 *flavor,
diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c
index 2ea00e354ba6..a0aae1144212 100644
--- a/net/sunrpc/xdr.c
+++ b/net/sunrpc/xdr.c
@@ -37,19 +37,6 @@ xdr_encode_netobj(__be32 *p, const struct xdr_netobj *obj)
 }
 EXPORT_SYMBOL_GPL(xdr_encode_netobj);
 
-__be32 *
-xdr_decode_netobj(__be32 *p, struct xdr_netobj *obj)
-{
-	unsigned int	len;
-
-	if ((len = be32_to_cpu(*p++)) > XDR_MAX_NETOBJ)
-		return NULL;
-	obj->len  = len;
-	obj->data = (u8 *) p;
-	return p + XDR_QUADLEN(len);
-}
-EXPORT_SYMBOL_GPL(xdr_decode_netobj);
-
 /**
  * xdr_encode_opaque_fixed - Encode fixed length opaque data
  * @p: pointer to current position in XDR buffer.
@@ -102,21 +89,6 @@ xdr_encode_string(__be32 *p, const char *string)
 }
 EXPORT_SYMBOL_GPL(xdr_encode_string);
 
-__be32 *
-xdr_decode_string_inplace(__be32 *p, char **sp,
-			  unsigned int *lenp, unsigned int maxlen)
-{
-	u32 len;
-
-	len = be32_to_cpu(*p++);
-	if (len > maxlen)
-		return NULL;
-	*lenp = len;
-	*sp = (char *) p;
-	return p + XDR_QUADLEN(len);
-}
-EXPORT_SYMBOL_GPL(xdr_decode_string_inplace);
-
 /**
  * xdr_terminate_string - '\0'-terminate a string residing in an xdr_buf
  * @buf: XDR buffer where string resides
@@ -2247,88 +2219,6 @@ out:
 }
 EXPORT_SYMBOL_GPL(xdr_process_buf);
 
-/**
- * xdr_stream_decode_opaque - Decode variable length opaque
- * @xdr: pointer to xdr_stream
- * @ptr: location to store opaque data
- * @size: size of storage buffer @ptr
- *
- * Return values:
- *   On success, returns size of object stored in *@ptr
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE on overflow of storage buffer @ptr
- */
-ssize_t xdr_stream_decode_opaque(struct xdr_stream *xdr, void *ptr, size_t size)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, size);
-	if (ret <= 0)
-		return ret;
-	memcpy(ptr, p, ret);
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque);
-
-/**
- * xdr_stream_decode_opaque_dup - Decode and duplicate variable length opaque
- * @xdr: pointer to xdr_stream
- * @ptr: location to store pointer to opaque data
- * @maxlen: maximum acceptable object size
- * @gfp_flags: GFP mask to use
- *
- * Return values:
- *   On success, returns size of object stored in *@ptr
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE if the size of the object would exceed @maxlen
- *   %-ENOMEM on memory allocation failure
- */
-ssize_t xdr_stream_decode_opaque_dup(struct xdr_stream *xdr, void **ptr,
-		size_t maxlen, gfp_t gfp_flags)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, maxlen);
-	if (ret > 0) {
-		*ptr = kmemdup(p, ret, gfp_flags);
-		if (*ptr != NULL)
-			return ret;
-		ret = -ENOMEM;
-	}
-	*ptr = NULL;
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_opaque_dup);
-
-/**
- * xdr_stream_decode_string - Decode variable length string
- * @xdr: pointer to xdr_stream
- * @str: location to store string
- * @size: size of storage buffer @str
- *
- * Return values:
- *   On success, returns length of NUL-terminated string stored in *@str
- *   %-EBADMSG on XDR buffer overflow
- *   %-EMSGSIZE on overflow of storage buffer @str
- */
-ssize_t xdr_stream_decode_string(struct xdr_stream *xdr, char *str, size_t size)
-{
-	ssize_t ret;
-	void *p;
-
-	ret = xdr_stream_decode_opaque_inline(xdr, &p, size);
-	if (ret > 0) {
-		memcpy(str, p, ret);
-		str[ret] = '\0';
-		return strlen(str);
-	}
-	*str = '\0';
-	return ret;
-}
-EXPORT_SYMBOL_GPL(xdr_stream_decode_string);
-
 /**
  * xdr_stream_decode_string_dup - Decode and duplicate variable length string
  * @xdr: pointer to xdr_stream
-- 
cgit v1.2.3


From 2a683d005286018c6f47ef0e432829655a6a21a3 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Fri, 11 Jul 2025 05:10:59 +0000
Subject: dev: Pass netdevice_tracker to dev_get_by_flags_rcu().

This is a follow-up for commit eb1ac9ff6c4a5 ("ipv6: anycast: Don't
hold RTNL for IPV6_JOIN_ANYCAST.").

We should not add a new device lookup API without netdevice_tracker.

Let's pass netdevice_tracker to dev_get_by_flags_rcu() and rename it
with netdev_ prefix to match other newer APIs.

Note that we always use GFP_ATOMIC for netdev_hold() as it's expected
to be called under RCU.

Suggested-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/netdev/20250708184053.102109f6@kernel.org/
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250711051120.2866855-1-kuniyu@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netdevice.h |  4 ++--
 net/core/dev.c            | 11 ++++++-----
 net/ipv6/anycast.c        | 11 ++++++-----
 3 files changed, 14 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a80d21a14612..ec23cee5245d 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3332,8 +3332,6 @@ int dev_get_iflink(const struct net_device *dev);
 int dev_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb);
 int dev_fill_forward_path(const struct net_device *dev, const u8 *daddr,
 			  struct net_device_path_stack *stack);
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short flags,
-					unsigned short mask);
 struct net_device *dev_get_by_name(struct net *net, const char *name);
 struct net_device *dev_get_by_name_rcu(struct net *net, const char *name);
 struct net_device *__dev_get_by_name(struct net *net, const char *name);
@@ -3396,6 +3394,8 @@ struct net_device *netdev_get_by_index(struct net *net, int ifindex,
 				       netdevice_tracker *tracker, gfp_t gfp);
 struct net_device *netdev_get_by_name(struct net *net, const char *name,
 				      netdevice_tracker *tracker, gfp_t gfp);
+struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker,
+					   unsigned short flags, unsigned short mask);
 struct net_device *dev_get_by_index_rcu(struct net *net, int ifindex);
 void netdev_copy_name(struct net_device *dev, char *name);
 
diff --git a/net/core/dev.c b/net/core/dev.c
index e365b099484e..19ddc3e6990a 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1267,8 +1267,9 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type)
 EXPORT_SYMBOL(dev_getfirstbyhwtype);
 
 /**
- * dev_get_by_flags_rcu - find any device with given flags
+ * netdev_get_by_flags_rcu - find any device with given flags
  * @net: the applicable net namespace
+ * @tracker: tracking object for the acquired reference
  * @if_flags: IFF_* values
  * @mask: bitmask of bits in if_flags to check
  *
@@ -1277,21 +1278,21 @@ EXPORT_SYMBOL(dev_getfirstbyhwtype);
  * Context: rcu_read_lock() must be held.
  * Returns: NULL if a device is not found or a pointer to the device.
  */
-struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags,
-					unsigned short mask)
+struct net_device *netdev_get_by_flags_rcu(struct net *net, netdevice_tracker *tracker,
+					   unsigned short if_flags, unsigned short mask)
 {
 	struct net_device *dev;
 
 	for_each_netdev_rcu(net, dev) {
 		if (((READ_ONCE(dev->flags) ^ if_flags) & mask) == 0) {
-			dev_hold(dev);
+			netdev_hold(dev, tracker, GFP_ATOMIC);
 			return dev;
 		}
 	}
 
 	return NULL;
 }
-EXPORT_IPV6_MOD(dev_get_by_flags_rcu);
+EXPORT_IPV6_MOD(netdev_get_by_flags_rcu);
 
 /**
  *	dev_valid_name - check if name is okay for network device
diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c
index 53cf68e0242b..f8a8e46286b8 100644
--- a/net/ipv6/anycast.c
+++ b/net/ipv6/anycast.c
@@ -69,6 +69,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 	struct ipv6_pinfo *np = inet6_sk(sk);
 	struct ipv6_ac_socklist *pac = NULL;
 	struct net *net = sock_net(sk);
+	netdevice_tracker dev_tracker;
 	struct net_device *dev = NULL;
 	struct inet6_dev *idev;
 	int err = 0, ishost;
@@ -79,7 +80,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		return -EINVAL;
 
 	if (ifindex)
-		dev = dev_get_by_index(net, ifindex);
+		dev = netdev_get_by_index(net, ifindex, &dev_tracker, GFP_KERNEL);
 
 	if (ipv6_chk_addr_and_flags(net, addr, dev, true, 0, IFA_F_TENTATIVE)) {
 		err = -EINVAL;
@@ -104,7 +105,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 		rt = rt6_lookup(net, addr, NULL, 0, NULL, 0);
 		if (rt) {
 			dev = dst_dev(&rt->dst);
-			dev_hold(dev);
+			netdev_hold(dev, &dev_tracker, GFP_ATOMIC);
 			ip6_rt_put(rt);
 		} else if (ishost) {
 			rcu_read_unlock();
@@ -112,8 +113,8 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 			goto error;
 		} else {
 			/* router, no matching interface: just pick one */
-			dev = dev_get_by_flags_rcu(net, IFF_UP,
-						   IFF_UP | IFF_LOOPBACK);
+			dev = netdev_get_by_flags_rcu(net, &dev_tracker, IFF_UP,
+						      IFF_UP | IFF_LOOPBACK);
 		}
 		rcu_read_unlock();
 	}
@@ -159,7 +160,7 @@ int ipv6_sock_ac_join(struct sock *sk, int ifindex, const struct in6_addr *addr)
 error_idev:
 	in6_dev_put(idev);
 error:
-	dev_put(dev);
+	netdev_put(dev, &dev_tracker);
 
 	if (pac)
 		sock_kfree_s(sk, pac, sizeof(*pac));
-- 
cgit v1.2.3


From 2677010e7793451c20d895c477c4dc76f6e6a10e Mon Sep 17 00:00:00 2001
From: Samiullah Khawaja <skhawaja@google.com>
Date: Thu, 10 Jul 2025 21:12:03 +0000
Subject: Add support to set NAPI threaded for individual NAPI

A net device has a threaded sysctl that can be used to enable threaded
NAPI polling on all of the NAPI contexts under that device. Allow
enabling threaded NAPI polling at individual NAPI level using netlink.

Extend the netlink operation `napi-set` and allow setting the threaded
attribute of a NAPI. This will enable the threaded polling on a NAPI
context.

Add a test in `nl_netdev.py` that verifies various cases of threaded
NAPI being set at NAPI and at device level.

Tested
 ./tools/testing/selftests/net/nl_netdev.py
 TAP version 13
 1..7
 ok 1 nl_netdev.empty_check
 ok 2 nl_netdev.lo_check
 ok 3 nl_netdev.page_pool_check
 ok 4 nl_netdev.napi_list_check
 ok 5 nl_netdev.dev_set_threaded
 ok 6 nl_netdev.napi_set_threaded
 ok 7 nl_netdev.nsim_rxq_reset_down
 # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:0 error:0

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250710211203.3979655-1-skhawaja@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml  | 10 ++++
 Documentation/networking/napi.rst        |  9 +++-
 include/linux/netdevice.h                |  1 +
 include/uapi/linux/netdev.h              |  1 +
 net/core/dev.c                           | 30 +++++++++--
 net/core/dev.h                           |  7 +++
 net/core/netdev-genl-gen.c               |  5 +-
 net/core/netdev-genl.c                   | 14 +++++
 tools/include/uapi/linux/netdev.h        |  1 +
 tools/testing/selftests/net/nl_netdev.py | 91 +++++++++++++++++++++++++++++++-
 10 files changed, 162 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index ce4cfec82100..85d0ea6ac426 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -283,6 +283,14 @@ attribute-sets:
         doc: The timeout, in nanoseconds, of how long to suspend irq
              processing, if event polling finds events
         type: uint
+      -
+        name: threaded
+        doc: Whether the NAPI is configured to operate in threaded polling
+             mode. If this is set to 1 then the NAPI context operates in
+             threaded polling mode.
+        type: uint
+        checks:
+          max: 1
   -
     name: xsk-info
     attributes: []
@@ -694,6 +702,7 @@ operations:
             - defer-hard-irqs
             - gro-flush-timeout
             - irq-suspend-timeout
+            - threaded
       dump:
         request:
           attributes:
@@ -746,6 +755,7 @@ operations:
             - defer-hard-irqs
             - gro-flush-timeout
             - irq-suspend-timeout
+            - threaded
     -
       name: bind-tx
       doc: Bind dmabuf to netdev for TX
diff --git a/Documentation/networking/napi.rst b/Documentation/networking/napi.rst
index d0e3953cae6a..a15754adb041 100644
--- a/Documentation/networking/napi.rst
+++ b/Documentation/networking/napi.rst
@@ -444,7 +444,14 @@ dependent). The NAPI instance IDs will be assigned in the opposite
 order than the process IDs of the kernel threads.
 
 Threaded NAPI is controlled by writing 0/1 to the ``threaded`` file in
-netdev's sysfs directory.
+netdev's sysfs directory. It can also be enabled for a specific NAPI using
+netlink interface.
+
+For example, using the script:
+
+.. code-block:: bash
+
+  $ ynl --family netdev --do napi-set --json='{"id": 66, "threaded": 1}'
 
 .. rubric:: Footnotes
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ec23cee5245d..e49d8c98d284 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -369,6 +369,7 @@ struct napi_config {
 	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
 	cpumask_t affinity_mask;
+	bool threaded;
 	unsigned int napi_id;
 };
 
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 7eb9571786b8..1f3719a9a0eb 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -134,6 +134,7 @@ enum {
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+	NETDEV_A_NAPI_THREADED,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/net/core/dev.c b/net/core/dev.c
index 19ddc3e6990a..621a639aeba1 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6961,6 +6961,31 @@ static void napi_stop_kthread(struct napi_struct *napi)
 	napi->thread = NULL;
 }
 
+int napi_set_threaded(struct napi_struct *napi, bool threaded)
+{
+	if (threaded) {
+		if (!napi->thread) {
+			int err = napi_kthread_create(napi);
+
+			if (err)
+				return err;
+		}
+	}
+
+	if (napi->config)
+		napi->config->threaded = threaded;
+
+	if (!threaded && napi->thread) {
+		napi_stop_kthread(napi);
+	} else {
+		/* Make sure kthread is created before THREADED bit is set. */
+		smp_mb__before_atomic();
+		assign_bit(NAPI_STATE_THREADED, &napi->state, threaded);
+	}
+
+	return 0;
+}
+
 int dev_set_threaded(struct net_device *dev, bool threaded)
 {
 	struct napi_struct *napi;
@@ -6968,9 +6993,6 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 
 	netdev_assert_locked_or_invisible(dev);
 
-	if (dev->threaded == threaded)
-		return 0;
-
 	if (threaded) {
 		list_for_each_entry(napi, &dev->napi_list, dev_list) {
 			if (!napi->thread) {
@@ -7221,6 +7243,8 @@ static void napi_restore_config(struct napi_struct *n)
 		napi_hash_add(n);
 		n->config->napi_id = n->napi_id;
 	}
+
+	WARN_ON_ONCE(napi_set_threaded(n, n->config->threaded));
 }
 
 static void napi_save_config(struct napi_struct *n)
diff --git a/net/core/dev.h b/net/core/dev.h
index e93f36b7ddf3..a603387fb566 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -315,6 +315,13 @@ static inline void napi_set_irq_suspend_timeout(struct napi_struct *n,
 	WRITE_ONCE(n->irq_suspend_timeout, timeout);
 }
 
+static inline bool napi_get_threaded(struct napi_struct *n)
+{
+	return test_bit(NAPI_STATE_THREADED, &n->state);
+}
+
+int napi_set_threaded(struct napi_struct *n, bool threaded);
+
 int rps_cpumask_housekeeping(struct cpumask *mask);
 
 #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL)
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 4fc44587f493..0994bd68a7e6 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -92,11 +92,12 @@ static const struct nla_policy netdev_bind_rx_nl_policy[NETDEV_A_DMABUF_FD + 1]
 };
 
 /* NETDEV_CMD_NAPI_SET - do */
-static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT + 1] = {
+static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_THREADED + 1] = {
 	[NETDEV_A_NAPI_ID] = { .type = NLA_U32, },
 	[NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range),
 	[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, },
 	[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, },
+	[NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_UINT, 1),
 };
 
 /* NETDEV_CMD_BIND_TX - do */
@@ -193,7 +194,7 @@ static const struct genl_split_ops netdev_nl_ops[] = {
 		.cmd		= NETDEV_CMD_NAPI_SET,
 		.doit		= netdev_nl_napi_set_doit,
 		.policy		= netdev_napi_set_nl_policy,
-		.maxattr	= NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+		.maxattr	= NETDEV_A_NAPI_THREADED,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
 	{
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 2afa7b2141aa..5875df372415 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -184,6 +184,10 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 	if (napi->irq >= 0 && nla_put_u32(rsp, NETDEV_A_NAPI_IRQ, napi->irq))
 		goto nla_put_failure;
 
+	if (nla_put_uint(rsp, NETDEV_A_NAPI_THREADED,
+			 napi_get_threaded(napi)))
+		goto nla_put_failure;
+
 	if (napi->thread) {
 		pid = task_pid_nr(napi->thread);
 		if (nla_put_u32(rsp, NETDEV_A_NAPI_PID, pid))
@@ -322,8 +326,18 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 {
 	u64 irq_suspend_timeout = 0;
 	u64 gro_flush_timeout = 0;
+	u8 threaded = 0;
 	u32 defer = 0;
 
+	if (info->attrs[NETDEV_A_NAPI_THREADED]) {
+		int ret;
+
+		threaded = nla_get_uint(info->attrs[NETDEV_A_NAPI_THREADED]);
+		ret = napi_set_threaded(napi, !!threaded);
+		if (ret)
+			return ret;
+	}
+
 	if (info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]) {
 		defer = nla_get_u32(info->attrs[NETDEV_A_NAPI_DEFER_HARD_IRQS]);
 		napi_set_defer_hard_irqs(napi, defer);
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 7eb9571786b8..1f3719a9a0eb 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -134,6 +134,7 @@ enum {
 	NETDEV_A_NAPI_DEFER_HARD_IRQS,
 	NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT,
 	NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT,
+	NETDEV_A_NAPI_THREADED,
 
 	__NETDEV_A_NAPI_MAX,
 	NETDEV_A_NAPI_MAX = (__NETDEV_A_NAPI_MAX - 1)
diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py
index c9109627a741..c8ffade79a52 100755
--- a/tools/testing/selftests/net/nl_netdev.py
+++ b/tools/testing/selftests/net/nl_netdev.py
@@ -35,6 +35,91 @@ def napi_list_check(nf) -> None:
                 ksft_eq(len(napis), 100,
                         comment=f"queue count after reset queue {q} mode {i}")
 
+def napi_set_threaded(nf) -> None:
+    """
+    Test that verifies various cases of napi threaded
+    set and unset at napi and device level.
+    """
+    with NetdevSimDev(queue_count=2) as nsimdev:
+        nsim = nsimdev.nsims[0]
+
+        ip(f"link set dev {nsim.ifname} up")
+
+        napis = nf.napi_get({'ifindex': nsim.ifindex}, dump=True)
+        ksft_eq(len(napis), 2)
+
+        napi0_id = napis[0]['id']
+        napi1_id = napis[1]['id']
+
+        # set napi threaded and verify
+        nf.napi_set({'id': napi0_id, 'threaded': 1})
+        napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 1)
+        ksft_ne(napi0.get('pid'), None)
+
+        # check it is not set for napi1
+        napi1 = nf.napi_get({'id': napi1_id})
+        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1.get('pid'), None)
+
+        ip(f"link set dev {nsim.ifname} down")
+        ip(f"link set dev {nsim.ifname} up")
+
+        # verify if napi threaded is still set
+        napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 1)
+        ksft_ne(napi0.get('pid'), None)
+
+        # check it is still not set for napi1
+        napi1 = nf.napi_get({'id': napi1_id})
+        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1.get('pid'), None)
+
+        # unset napi threaded and verify
+        nf.napi_set({'id': napi0_id, 'threaded': 0})
+        napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 0)
+        ksft_eq(napi0.get('pid'), None)
+
+        # set threaded at device level
+        system(f"echo 1 > /sys/class/net/{nsim.ifname}/threaded")
+
+        # check napi threaded is set for both napis
+        napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 1)
+        ksft_ne(napi0.get('pid'), None)
+        napi1 = nf.napi_get({'id': napi1_id})
+        ksft_eq(napi1['threaded'], 1)
+        ksft_ne(napi1.get('pid'), None)
+
+        # unset threaded at device level
+        system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded")
+
+        # check napi threaded is unset for both napis
+        napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 0)
+        ksft_eq(napi0.get('pid'), None)
+        napi1 = nf.napi_get({'id': napi1_id})
+        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1.get('pid'), None)
+
+        # set napi threaded for napi0
+        nf.napi_set({'id': napi0_id, 'threaded': 1})
+        napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 1)
+        ksft_ne(napi0.get('pid'), None)
+
+        # unset threaded at device level
+        system(f"echo 0 > /sys/class/net/{nsim.ifname}/threaded")
+
+        # check napi threaded is unset for both napis
+        napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 0)
+        ksft_eq(napi0.get('pid'), None)
+        napi1 = nf.napi_get({'id': napi1_id})
+        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1.get('pid'), None)
+
 def dev_set_threaded(nf) -> None:
     """
     Test that verifies various cases of napi threaded
@@ -56,8 +141,10 @@ def dev_set_threaded(nf) -> None:
 
         # check napi threaded is set for both napis
         napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 1)
         ksft_ne(napi0.get('pid'), None)
         napi1 = nf.napi_get({'id': napi1_id})
+        ksft_eq(napi1['threaded'], 1)
         ksft_ne(napi1.get('pid'), None)
 
         # unset threaded
@@ -65,8 +152,10 @@ def dev_set_threaded(nf) -> None:
 
         # check napi threaded is unset for both napis
         napi0 = nf.napi_get({'id': napi0_id})
+        ksft_eq(napi0['threaded'], 0)
         ksft_eq(napi0.get('pid'), None)
         napi1 = nf.napi_get({'id': napi1_id})
+        ksft_eq(napi1['threaded'], 0)
         ksft_eq(napi1.get('pid'), None)
 
 def nsim_rxq_reset_down(nf) -> None:
@@ -156,7 +245,7 @@ def page_pool_check(nf) -> None:
 def main() -> None:
     nf = NetdevFamily()
     ksft_run([empty_check, lo_check, page_pool_check, napi_list_check,
-              dev_set_threaded, nsim_rxq_reset_down],
+              dev_set_threaded, napi_set_threaded, nsim_rxq_reset_down],
              args=(nf, ))
     ksft_exit()
 
-- 
cgit v1.2.3


From d7c36d6350b5a4b27256eaeeea3b72621a819c9a Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 10 Jun 2025 11:29:21 +0200
Subject: locking/lockdep: Avoid struct return in lock_stats()

Returning a large structure from the lock_stats() function causes clang
to have multiple copies of it on the stack and copy between them, which
can end up exceeding the frame size warning limit:

kernel/locking/lockdep.c:300:25: error: stack frame size (1464) exceeds limit (1280) in 'lock_stats' [-Werror,-Wframe-larger-than]
  300 | struct lock_class_stats lock_stats(struct lock_class *class)

Change the calling conventions to directly operate on the caller's copy,
which apparently is what gcc does already.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Boqun Feng <boqun.feng@gmail.com>
Link: https://lore.kernel.org/r/20250610092941.2642847-1-arnd@kernel.org
---
 include/linux/lockdep_types.h |  2 +-
 kernel/locking/lockdep.c      | 27 ++++++++++++---------------
 kernel/locking/lockdep_proc.c |  2 +-
 3 files changed, 14 insertions(+), 17 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/lockdep_types.h b/include/linux/lockdep_types.h
index 9f361d3ab9d9..eae115a26488 100644
--- a/include/linux/lockdep_types.h
+++ b/include/linux/lockdep_types.h
@@ -175,7 +175,7 @@ struct lock_class_stats {
 	unsigned long			bounces[nr_bounce_types];
 };
 
-struct lock_class_stats lock_stats(struct lock_class *class);
+void lock_stats(struct lock_class *class, struct lock_class_stats *stats);
 void clear_lock_stats(struct lock_class *class);
 #endif
 
diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
index dd2bbf73718b..0c941418a215 100644
--- a/kernel/locking/lockdep.c
+++ b/kernel/locking/lockdep.c
@@ -297,33 +297,30 @@ static inline void lock_time_add(struct lock_time *src, struct lock_time *dst)
 	dst->nr += src->nr;
 }
 
-struct lock_class_stats lock_stats(struct lock_class *class)
+void lock_stats(struct lock_class *class, struct lock_class_stats *stats)
 {
-	struct lock_class_stats stats;
 	int cpu, i;
 
-	memset(&stats, 0, sizeof(struct lock_class_stats));
+	memset(stats, 0, sizeof(struct lock_class_stats));
 	for_each_possible_cpu(cpu) {
 		struct lock_class_stats *pcs =
 			&per_cpu(cpu_lock_stats, cpu)[class - lock_classes];
 
-		for (i = 0; i < ARRAY_SIZE(stats.contention_point); i++)
-			stats.contention_point[i] += pcs->contention_point[i];
+		for (i = 0; i < ARRAY_SIZE(stats->contention_point); i++)
+			stats->contention_point[i] += pcs->contention_point[i];
 
-		for (i = 0; i < ARRAY_SIZE(stats.contending_point); i++)
-			stats.contending_point[i] += pcs->contending_point[i];
+		for (i = 0; i < ARRAY_SIZE(stats->contending_point); i++)
+			stats->contending_point[i] += pcs->contending_point[i];
 
-		lock_time_add(&pcs->read_waittime, &stats.read_waittime);
-		lock_time_add(&pcs->write_waittime, &stats.write_waittime);
+		lock_time_add(&pcs->read_waittime, &stats->read_waittime);
+		lock_time_add(&pcs->write_waittime, &stats->write_waittime);
 
-		lock_time_add(&pcs->read_holdtime, &stats.read_holdtime);
-		lock_time_add(&pcs->write_holdtime, &stats.write_holdtime);
+		lock_time_add(&pcs->read_holdtime, &stats->read_holdtime);
+		lock_time_add(&pcs->write_holdtime, &stats->write_holdtime);
 
-		for (i = 0; i < ARRAY_SIZE(stats.bounces); i++)
-			stats.bounces[i] += pcs->bounces[i];
+		for (i = 0; i < ARRAY_SIZE(stats->bounces); i++)
+			stats->bounces[i] += pcs->bounces[i];
 	}
-
-	return stats;
 }
 
 void clear_lock_stats(struct lock_class *class)
diff --git a/kernel/locking/lockdep_proc.c b/kernel/locking/lockdep_proc.c
index b52c07c4707c..1916db9aa46b 100644
--- a/kernel/locking/lockdep_proc.c
+++ b/kernel/locking/lockdep_proc.c
@@ -657,7 +657,7 @@ static int lock_stat_open(struct inode *inode, struct file *file)
 			if (!test_bit(idx, lock_classes_in_use))
 				continue;
 			iter->class = class;
-			iter->stats = lock_stats(class);
+			lock_stats(class, &iter->stats);
 			iter++;
 		}
 
-- 
cgit v1.2.3


From 6fd9e1aa078490ed6e79307465269629fcb43018 Mon Sep 17 00:00:00 2001
From: Dave Martin <Dave.Martin@arm.com>
Date: Tue, 1 Jul 2025 14:55:54 +0100
Subject: regset: Fix kerneldoc for struct regset_get() in user_regset

Commit 7717cb9bdd04 ("regset: new method and helpers for it") added a
new interface ->regset_get() for struct user_regset, and commit
1e6986c9db21 ("regset: kill ->get()") got rid of the old interface.

The kerneldoc comment block was never updated to take account of this
change, though.

Update it.

No functional change.

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Akihiko Odaki <akihiko.odaki@daynix.com>
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Link: https://lore.kernel.org/r/20250701135616.29630-2-Dave.Martin@arm.com
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/regset.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/regset.h b/include/linux/regset.h
index 9061266dd8de..02417e934845 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -151,7 +151,7 @@ typedef int user_regset_writeback_fn(struct task_struct *target,
  * @align:		Required alignment, in bytes.
  * @bias:		Bias from natural indexing.
  * @core_note_type:	ELF note @n_type value used in core dumps.
- * @get:		Function to fetch values.
+ * @regset_get:		Function to fetch values.
  * @set:		Function to store values.
  * @active:		Function to report if regset is active, or %NULL.
  * @writeback:		Function to write data back to user memory, or %NULL.
-- 
cgit v1.2.3


From 85a7f9cbf8a83cfe0aca04053a832206c4ad1272 Mon Sep 17 00:00:00 2001
From: Dave Martin <Dave.Martin@arm.com>
Date: Tue, 1 Jul 2025 14:55:55 +0100
Subject: regset: Add explicit core note name in struct user_regset

There is currently hard-coded logic spread around the tree for
determining the note name for regset notes emitted in coredumps.

Now that the names are declared explicitly in <uapi/elf.h>, this can be
simplified.

In preparation for getting rid of the special-case logic, add an
explicit core_note_name field in struct user_regset for specifying the
note name explicitly.  To help avoid mistakes, a convenience macro
USER_REGSET_NOTE_TYPE() is provided to set .core_note_type and
.core_note_name based on the note type.

When dumping core, use the new field to set the note name, if the
regset specifies it.

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Akihiko Odaki <akihiko.odaki@daynix.com>
Acked-by: Alexander Gordeev <agordeev@linux.ibm.com> # s390
Reviewed-by: Akihiko Odaki <odaki@rsg.ci.i.u-tokyo.ac.jp>
Link: https://lore.kernel.org/r/20250701135616.29630-3-Dave.Martin@arm.com
Signed-off-by: Kees Cook <kees@kernel.org>
---
 fs/binfmt_elf.c        |  8 ++++++--
 include/linux/regset.h | 10 ++++++++++
 2 files changed, 16 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index a43363d593e5..f1069103ca24 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -1727,6 +1727,7 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 	for (view_iter = 1; view_iter < view->n; ++view_iter) {
 		const struct user_regset *regset = &view->regsets[view_iter];
 		int note_type = regset->core_note_type;
+		const char *note_name = regset->core_note_name;
 		bool is_fpreg = note_type == NT_PRFPREG;
 		void *data;
 		int ret;
@@ -1747,8 +1748,11 @@ static int fill_thread_core_info(struct elf_thread_core_info *t,
 		if (is_fpreg)
 			SET_PR_FPVALID(&t->prstatus);
 
-		fill_note(&t->notes[note_iter], is_fpreg ? NN_PRFPREG : "LINUX",
-			  note_type, ret, data);
+		if (!note_name)
+			note_name = is_fpreg ? NN_PRFPREG : "LINUX";
+
+		fill_note(&t->notes[note_iter], note_name, note_type,
+			  ret, data);
 
 		info->size += notesize(&t->notes[note_iter]);
 		note_iter++;
diff --git a/include/linux/regset.h b/include/linux/regset.h
index 02417e934845..ad1ca6fe04f4 100644
--- a/include/linux/regset.h
+++ b/include/linux/regset.h
@@ -151,6 +151,7 @@ typedef int user_regset_writeback_fn(struct task_struct *target,
  * @align:		Required alignment, in bytes.
  * @bias:		Bias from natural indexing.
  * @core_note_type:	ELF note @n_type value used in core dumps.
+ * @core_note_name:	ELF note name to qualify the note type.
  * @regset_get:		Function to fetch values.
  * @set:		Function to store values.
  * @active:		Function to report if regset is active, or %NULL.
@@ -190,6 +191,10 @@ typedef int user_regset_writeback_fn(struct task_struct *target,
  *
  * If nonzero, @core_note_type gives the n_type field (NT_* value)
  * of the core file note in which this regset's data appears.
+ * @core_note_name specifies the note name.  The preferred way to
+ * specify these two fields is to use the @USER_REGSET_NOTE_TYPE()
+ * macro.
+ *
  * NT_PRSTATUS is a special case in that the regset data starts at
  * offsetof(struct elf_prstatus, pr_reg) into the note data; that is
  * part of the per-machine ELF formats userland knows about.  In
@@ -207,8 +212,13 @@ struct user_regset {
 	unsigned int 			align;
 	unsigned int 			bias;
 	unsigned int 			core_note_type;
+	const char			*core_note_name;
 };
 
+#define USER_REGSET_NOTE_TYPE(type) \
+	.core_note_type			= (NT_ ## type), \
+	.core_note_name			= (NN_ ## type)
+
 /**
  * struct user_regset_view - available regsets
  * @name:	Identifier, e.g. UTS_MACHINE string.
-- 
cgit v1.2.3


From d9c37a4904ec21ef7d45880fe023c11341869c28 Mon Sep 17 00:00:00 2001
From: Qu Wenruo <wqu@suse.com>
Date: Mon, 14 Jul 2025 14:55:57 +0930
Subject: fs: add a new remove_bdev() callback

Currently all filesystems which implement super_operations::shutdown()
can not afford losing a device.

Thus fs_bdev_mark_dead() will just call the ->shutdown() callback for the
involved filesystem.

But it will no longer be the case, as multi-device filesystems like
btrfs and bcachefs can handle certain device loss without the need to
shutdown the whole filesystem.

To allow those multi-device filesystems to be integrated to use
fs_holder_ops:

- Add a new super_operations::remove_bdev() callback

- Try ->remove_bdev() callback first inside fs_bdev_mark_dead()
  If the callback returned 0, meaning the fs can handling the device
  loss, then exit without doing anything else.

  If there is no such callback or the callback returned non-zero value,
  continue to shutdown the filesystem as usual.

This means the new remove_bdev() should only do the check on whether the
operation can continue, and if so do the fs specific handlings.
The shutdown handling should still be handled by the existing
->shutdown() callback.

For all existing filesystems with shutdown callback, there is no change
to the code nor behavior.

Btrfs is going to implement both the ->remove_bdev() and ->shutdown()
callbacks soon.

Signed-off-by: Qu Wenruo <wqu@suse.com>
Link: https://lore.kernel.org/09909fcff7f2763cc037fec97ac2482bdc0a12cb.1752470276.git.wqu@suse.com
Reviewed-by: Jan Kara <jack@suse.cz>
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/super.c         | 11 +++++++++++
 include/linux/fs.h |  9 +++++++++
 2 files changed, 20 insertions(+)

(limited to 'include/linux')

diff --git a/fs/super.c b/fs/super.c
index 21799e213fd7..53e135d84867 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -1457,6 +1457,17 @@ static void fs_bdev_mark_dead(struct block_device *bdev, bool surprise)
 	if (!sb)
 		return;
 
+	if (sb->s_op->remove_bdev) {
+		int ret;
+
+		ret = sb->s_op->remove_bdev(sb, bdev);
+		if (!ret) {
+			super_unlock_shared(sb);
+			return;
+		}
+		/* Fallback to shutdown. */
+	}
+
 	if (!surprise)
 		sync_filesystem(sb);
 	shrink_dcache_sb(sb);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 96c7925a6551..5150db41109a 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2363,6 +2363,15 @@ struct super_operations {
 				  struct shrink_control *);
 	long (*free_cached_objects)(struct super_block *,
 				    struct shrink_control *);
+	/*
+	 * If a filesystem can support graceful removal of a device and
+	 * continue read-write operations, implement this callback.
+	 *
+	 * Return 0 if the filesystem can continue read-write.
+	 * Non-zero return value or no such callback means the fs will be shutdown
+	 * as usual.
+	 */
+	int (*remove_bdev)(struct super_block *sb, struct block_device *bdev);
 	void (*shutdown)(struct super_block *sb);
 };
 
-- 
cgit v1.2.3


From 12f33ef6c2aaa410b7ccf039289fe2b04ab2252f Mon Sep 17 00:00:00 2001
From: Alan Stern <stern@rowland.harvard.edu>
Date: Sun, 13 Jul 2025 11:36:12 -0400
Subject: HID: core: Improve the kerneldoc for hid_report_len()

The kerneldoc for hid_report_len() needs to be improved.  The
description of the @report argument is ungrammatical, and the
documentation does not explain under what circumstances the report
length will include the byte reserved for the report ID.

Let's fix up the kerneldoc.

Signed-off-by: Alan Stern <stern@rowland.harvard.edu>
Link: https://patch.msgid.link/1c8416cb-7347-4a06-b00a-20518069d263@rowland.harvard.edu
Signed-off-by: Benjamin Tissoires <bentiss@kernel.org>
---
 include/linux/hid.h | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/hid.h b/include/linux/hid.h
index 7f260e0e2049..2cc4f1e4ea96 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -1216,7 +1216,11 @@ static inline void hid_hw_wait(struct hid_device *hdev)
 /**
  * hid_report_len - calculate the report length
  *
- * @report: the report we want to know the length
+ * @report: the report whose length we want to know
+ *
+ * The length counts the report ID byte, but only if the ID is nonzero
+ * and therefore is included in the report.  Reports whose ID is zero
+ * never include an ID byte.
  */
 static inline u32 hid_report_len(struct hid_report *report)
 {
-- 
cgit v1.2.3


From c34632dbb29ba7016f1cd2e629ac9dd07f84ce50 Mon Sep 17 00:00:00 2001
From: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Date: Mon, 14 Jul 2025 13:02:02 -0400
Subject: bnxt: move bnxt_hsi.h to include/linux/bnxt/hsi.h

This moves bnxt_hsi.h contents to a common location so it can be
properly referenced by bnxt_en, bnxt_re, and bnge.

Signed-off-by: Andy Gospodarek <gospo@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Reviewed-by: Vadim Fedorenko <vadim.fedorenko@linux.dev>
Link: https://patch.msgid.link/20250714170202.39688-1-gospo@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/infiniband/hw/bnxt_re/roce_hsi.h           |     4 +-
 drivers/net/ethernet/broadcom/bnge/bnge.h          |     2 +-
 drivers/net/ethernet/broadcom/bnge/bnge_hwrm.h     |     2 +-
 drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c |     2 +-
 drivers/net/ethernet/broadcom/bnge/bnge_netdev.h   |     2 +-
 drivers/net/ethernet/broadcom/bnge/bnge_rmem.c     |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt.c          |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c      |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c  |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h  |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c  |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c      |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c  |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h      | 10914 -------------------
 drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c    |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c     |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h     |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c      |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c    |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c       |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c      |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c      |     2 +-
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c      |     2 +-
 include/linux/bnxt/hsi.h                           | 10914 +++++++++++++++++++
 25 files changed, 10938 insertions(+), 10938 deletions(-)
 delete mode 100644 drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
 create mode 100644 include/linux/bnxt/hsi.h

(limited to 'include/linux')

diff --git a/drivers/infiniband/hw/bnxt_re/roce_hsi.h b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
index 7eceb3e9f4ce..024845f945ff 100644
--- a/drivers/infiniband/hw/bnxt_re/roce_hsi.h
+++ b/drivers/infiniband/hw/bnxt_re/roce_hsi.h
@@ -39,8 +39,8 @@
 #ifndef __BNXT_RE_HSI_H__
 #define __BNXT_RE_HSI_H__
 
-/* include bnxt_hsi.h from bnxt_en driver */
-#include "bnxt_hsi.h"
+/* include linux/bnxt/hsi.h */
+#include <linux/bnxt/hsi.h>
 
 /* tx_doorbell (size:32b/4B) */
 struct tx_doorbell {
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge.h b/drivers/net/ethernet/broadcom/bnge/bnge.h
index a1795302c15a..6fb3683b6b04 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge.h
+++ b/drivers/net/ethernet/broadcom/bnge/bnge.h
@@ -8,7 +8,7 @@
 #define DRV_SUMMARY	"Broadcom 800G Ethernet Linux Driver"
 
 #include <linux/etherdevice.h>
-#include "../bnxt/bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnge_rmem.h"
 #include "bnge_resc.h"
 
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.h b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.h
index 012aa4fa5aa9..83794a12cc81 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.h
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm.h
@@ -4,7 +4,7 @@
 #ifndef _BNGE_HWRM_H_
 #define _BNGE_HWRM_H_
 
-#include "../bnxt/bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 
 enum bnge_hwrm_ctx_flags {
 	BNGE_HWRM_INTERNAL_CTX_OWNED	= BIT(0),
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
index 19091318cfdd..5c178fade065 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_hwrm_lib.c
@@ -5,9 +5,9 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/pci.h>
+#include <linux/bnxt/hsi.h>
 
 #include "bnge.h"
-#include "../bnxt/bnxt_hsi.h"
 #include "bnge_hwrm.h"
 #include "bnge_hwrm_lib.h"
 #include "bnge_rmem.h"
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
index 96b77e44b552..a650d71a58db 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_netdev.h
@@ -4,7 +4,7 @@
 #ifndef _BNGE_NETDEV_H_
 #define _BNGE_NETDEV_H_
 
-#include "../bnxt/bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 
 struct tx_bd {
 	__le32 tx_bd_len_flags_type;
diff --git a/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c
index 0e935cc46da6..52ada65943a0 100644
--- a/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c
+++ b/drivers/net/ethernet/broadcom/bnge/bnge_rmem.c
@@ -9,9 +9,9 @@
 #include <linux/dma-mapping.h>
 #include <linux/vmalloc.h>
 #include <linux/crash_dump.h>
+#include <linux/bnxt/hsi.h>
 
 #include "bnge.h"
-#include "../bnxt/bnxt_hsi.h"
 #include "bnge_hwrm_lib.h"
 #include "bnge_rmem.h"
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index 6bbe875132b0..de8080df69a8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -58,8 +58,8 @@
 #include <net/netdev_queues.h>
 #include <net/netdev_rx_queue.h>
 #include <linux/pci-tph.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
index 67e70d3d0980..18d6c94d5cb8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_coredump.c
@@ -10,7 +10,7 @@
 #include <linux/types.h>
 #include <linux/errno.h>
 #include <linux/pci.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_coredump.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
index 71e14be2507e..a00b67334f9b 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c
@@ -16,7 +16,7 @@
 #include <linux/pci.h>
 #include <linux/etherdevice.h>
 #include <rdma/ib_verbs.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_dcb.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
index 127b7015f676..3324afbb3bec 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c
@@ -10,7 +10,7 @@
 #include <linux/debugfs.h>
 #include <linux/module.h>
 #include <linux/pci.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include <linux/dim.h>
 #include "bnxt.h"
 #include "bnxt_debugfs.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h
index d0bb4887acd0..a0a8d687dd99 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h
@@ -7,7 +7,7 @@
  * the Free Software Foundation.
  */
 
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 
 #ifdef CONFIG_DEBUG_FS
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
index 777880594a04..4c4581b0342e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c
@@ -12,7 +12,7 @@
 #include <linux/vmalloc.h>
 #include <net/devlink.h>
 #include <net/netdev_lock.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_vfr.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
index 6f6576dc417a..53a3bcb0efe0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c
@@ -8,7 +8,7 @@
  */
 
 #include <linux/dim.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 
 void bnxt_dim_work(struct work_struct *work)
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 4c10373abffd..1b37612b1c01 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -26,7 +26,7 @@
 #include <linux/timecounter.h>
 #include <net/netdev_queues.h>
 #include <net/netlink.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
deleted file mode 100644
index 549231703bce..000000000000
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hsi.h
+++ /dev/null
@@ -1,10914 +0,0 @@
-/* Broadcom NetXtreme-C/E network driver.
- *
- * Copyright (c) 2014-2016 Broadcom Corporation
- * Copyright (c) 2014-2018 Broadcom Limited
- * Copyright (c) 2018-2025 Broadcom Inc.
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License as published by
- * the Free Software Foundation.
- *
- * DO NOT MODIFY!!! This file is automatically generated.
- */
-
-#ifndef _BNXT_HSI_H_
-#define _BNXT_HSI_H_
-
-/* hwrm_cmd_hdr (size:128b/16B) */
-struct hwrm_cmd_hdr {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_resp_hdr (size:64b/8B) */
-struct hwrm_resp_hdr {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-};
-
-#define CMD_DISCR_TLV_ENCAP 0x8000UL
-#define CMD_DISCR_LAST     CMD_DISCR_TLV_ENCAP
-
-
-#define TLV_TYPE_HWRM_REQUEST                    0x1UL
-#define TLV_TYPE_HWRM_RESPONSE                   0x2UL
-#define TLV_TYPE_ROCE_SP_COMMAND                 0x3UL
-#define TLV_TYPE_QUERY_ROCE_CC_GEN1              0x4UL
-#define TLV_TYPE_MODIFY_ROCE_CC_GEN1             0x5UL
-#define TLV_TYPE_QUERY_ROCE_CC_GEN2              0x6UL
-#define TLV_TYPE_MODIFY_ROCE_CC_GEN2             0x7UL
-#define TLV_TYPE_QUERY_ROCE_CC_GEN1_EXT          0x8UL
-#define TLV_TYPE_MODIFY_ROCE_CC_GEN1_EXT         0x9UL
-#define TLV_TYPE_QUERY_ROCE_CC_GEN2_EXT          0xaUL
-#define TLV_TYPE_MODIFY_ROCE_CC_GEN2_EXT         0xbUL
-#define TLV_TYPE_ENGINE_CKV_ALIAS_ECC_PUBLIC_KEY 0x8001UL
-#define TLV_TYPE_ENGINE_CKV_IV                   0x8003UL
-#define TLV_TYPE_ENGINE_CKV_AUTH_TAG             0x8004UL
-#define TLV_TYPE_ENGINE_CKV_CIPHERTEXT           0x8005UL
-#define TLV_TYPE_ENGINE_CKV_HOST_ALGORITHMS      0x8006UL
-#define TLV_TYPE_ENGINE_CKV_HOST_ECC_PUBLIC_KEY  0x8007UL
-#define TLV_TYPE_ENGINE_CKV_ECDSA_SIGNATURE      0x8008UL
-#define TLV_TYPE_ENGINE_CKV_FW_ECC_PUBLIC_KEY    0x8009UL
-#define TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS        0x800aUL
-#define TLV_TYPE_LAST                           TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS
-
-
-/* tlv (size:64b/8B) */
-struct tlv {
-	__le16	cmd_discr;
-	u8	reserved_8b;
-	u8	flags;
-	#define TLV_FLAGS_MORE         0x1UL
-	#define TLV_FLAGS_MORE_LAST      0x0UL
-	#define TLV_FLAGS_MORE_NOT_LAST  0x1UL
-	#define TLV_FLAGS_REQUIRED     0x2UL
-	#define TLV_FLAGS_REQUIRED_NO    (0x0UL << 1)
-	#define TLV_FLAGS_REQUIRED_YES   (0x1UL << 1)
-	#define TLV_FLAGS_REQUIRED_LAST TLV_FLAGS_REQUIRED_YES
-	__le16	tlv_type;
-	__le16	length;
-};
-
-/* input (size:128b/16B) */
-struct input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* output (size:64b/8B) */
-struct output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-};
-
-/* hwrm_short_input (size:128b/16B) */
-struct hwrm_short_input {
-	__le16	req_type;
-	__le16	signature;
-	#define SHORT_REQ_SIGNATURE_SHORT_CMD 0x4321UL
-	#define SHORT_REQ_SIGNATURE_LAST     SHORT_REQ_SIGNATURE_SHORT_CMD
-	__le16	target_id;
-	#define SHORT_REQ_TARGET_ID_DEFAULT 0x0UL
-	#define SHORT_REQ_TARGET_ID_TOOLS   0xfffdUL
-	#define SHORT_REQ_TARGET_ID_LAST   SHORT_REQ_TARGET_ID_TOOLS
-	__le16	size;
-	__le64	req_addr;
-};
-
-/* cmd_nums (size:64b/8B) */
-struct cmd_nums {
-	__le16	req_type;
-	#define HWRM_VER_GET                              0x0UL
-	#define HWRM_FUNC_ECHO_RESPONSE                   0xbUL
-	#define HWRM_ERROR_RECOVERY_QCFG                  0xcUL
-	#define HWRM_FUNC_DRV_IF_CHANGE                   0xdUL
-	#define HWRM_FUNC_BUF_UNRGTR                      0xeUL
-	#define HWRM_FUNC_VF_CFG                          0xfUL
-	#define HWRM_RESERVED1                            0x10UL
-	#define HWRM_FUNC_RESET                           0x11UL
-	#define HWRM_FUNC_GETFID                          0x12UL
-	#define HWRM_FUNC_VF_ALLOC                        0x13UL
-	#define HWRM_FUNC_VF_FREE                         0x14UL
-	#define HWRM_FUNC_QCAPS                           0x15UL
-	#define HWRM_FUNC_QCFG                            0x16UL
-	#define HWRM_FUNC_CFG                             0x17UL
-	#define HWRM_FUNC_QSTATS                          0x18UL
-	#define HWRM_FUNC_CLR_STATS                       0x19UL
-	#define HWRM_FUNC_DRV_UNRGTR                      0x1aUL
-	#define HWRM_FUNC_VF_RESC_FREE                    0x1bUL
-	#define HWRM_FUNC_VF_VNIC_IDS_QUERY               0x1cUL
-	#define HWRM_FUNC_DRV_RGTR                        0x1dUL
-	#define HWRM_FUNC_DRV_QVER                        0x1eUL
-	#define HWRM_FUNC_BUF_RGTR                        0x1fUL
-	#define HWRM_PORT_PHY_CFG                         0x20UL
-	#define HWRM_PORT_MAC_CFG                         0x21UL
-	#define HWRM_PORT_TS_QUERY                        0x22UL
-	#define HWRM_PORT_QSTATS                          0x23UL
-	#define HWRM_PORT_LPBK_QSTATS                     0x24UL
-	#define HWRM_PORT_CLR_STATS                       0x25UL
-	#define HWRM_PORT_LPBK_CLR_STATS                  0x26UL
-	#define HWRM_PORT_PHY_QCFG                        0x27UL
-	#define HWRM_PORT_MAC_QCFG                        0x28UL
-	#define HWRM_PORT_MAC_PTP_QCFG                    0x29UL
-	#define HWRM_PORT_PHY_QCAPS                       0x2aUL
-	#define HWRM_PORT_PHY_I2C_WRITE                   0x2bUL
-	#define HWRM_PORT_PHY_I2C_READ                    0x2cUL
-	#define HWRM_PORT_LED_CFG                         0x2dUL
-	#define HWRM_PORT_LED_QCFG                        0x2eUL
-	#define HWRM_PORT_LED_QCAPS                       0x2fUL
-	#define HWRM_QUEUE_QPORTCFG                       0x30UL
-	#define HWRM_QUEUE_QCFG                           0x31UL
-	#define HWRM_QUEUE_CFG                            0x32UL
-	#define HWRM_FUNC_VLAN_CFG                        0x33UL
-	#define HWRM_FUNC_VLAN_QCFG                       0x34UL
-	#define HWRM_QUEUE_PFCENABLE_QCFG                 0x35UL
-	#define HWRM_QUEUE_PFCENABLE_CFG                  0x36UL
-	#define HWRM_QUEUE_PRI2COS_QCFG                   0x37UL
-	#define HWRM_QUEUE_PRI2COS_CFG                    0x38UL
-	#define HWRM_QUEUE_COS2BW_QCFG                    0x39UL
-	#define HWRM_QUEUE_COS2BW_CFG                     0x3aUL
-	#define HWRM_QUEUE_DSCP_QCAPS                     0x3bUL
-	#define HWRM_QUEUE_DSCP2PRI_QCFG                  0x3cUL
-	#define HWRM_QUEUE_DSCP2PRI_CFG                   0x3dUL
-	#define HWRM_VNIC_ALLOC                           0x40UL
-	#define HWRM_VNIC_FREE                            0x41UL
-	#define HWRM_VNIC_CFG                             0x42UL
-	#define HWRM_VNIC_QCFG                            0x43UL
-	#define HWRM_VNIC_TPA_CFG                         0x44UL
-	#define HWRM_VNIC_TPA_QCFG                        0x45UL
-	#define HWRM_VNIC_RSS_CFG                         0x46UL
-	#define HWRM_VNIC_RSS_QCFG                        0x47UL
-	#define HWRM_VNIC_PLCMODES_CFG                    0x48UL
-	#define HWRM_VNIC_PLCMODES_QCFG                   0x49UL
-	#define HWRM_VNIC_QCAPS                           0x4aUL
-	#define HWRM_VNIC_UPDATE                          0x4bUL
-	#define HWRM_RING_ALLOC                           0x50UL
-	#define HWRM_RING_FREE                            0x51UL
-	#define HWRM_RING_CMPL_RING_QAGGINT_PARAMS        0x52UL
-	#define HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS     0x53UL
-	#define HWRM_RING_AGGINT_QCAPS                    0x54UL
-	#define HWRM_RING_SCHQ_ALLOC                      0x55UL
-	#define HWRM_RING_SCHQ_CFG                        0x56UL
-	#define HWRM_RING_SCHQ_FREE                       0x57UL
-	#define HWRM_RING_RESET                           0x5eUL
-	#define HWRM_RING_GRP_ALLOC                       0x60UL
-	#define HWRM_RING_GRP_FREE                        0x61UL
-	#define HWRM_RING_CFG                             0x62UL
-	#define HWRM_RING_QCFG                            0x63UL
-	#define HWRM_RESERVED5                            0x64UL
-	#define HWRM_RESERVED6                            0x65UL
-	#define HWRM_VNIC_RSS_COS_LB_CTX_ALLOC            0x70UL
-	#define HWRM_VNIC_RSS_COS_LB_CTX_FREE             0x71UL
-	#define HWRM_QUEUE_MPLS_QCAPS                     0x80UL
-	#define HWRM_QUEUE_MPLSTC2PRI_QCFG                0x81UL
-	#define HWRM_QUEUE_MPLSTC2PRI_CFG                 0x82UL
-	#define HWRM_QUEUE_VLANPRI_QCAPS                  0x83UL
-	#define HWRM_QUEUE_VLANPRI2PRI_QCFG               0x84UL
-	#define HWRM_QUEUE_VLANPRI2PRI_CFG                0x85UL
-	#define HWRM_QUEUE_GLOBAL_CFG                     0x86UL
-	#define HWRM_QUEUE_GLOBAL_QCFG                    0x87UL
-	#define HWRM_QUEUE_ADPTV_QOS_RX_FEATURE_QCFG      0x88UL
-	#define HWRM_QUEUE_ADPTV_QOS_RX_FEATURE_CFG       0x89UL
-	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_QCFG      0x8aUL
-	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_CFG       0x8bUL
-	#define HWRM_QUEUE_QCAPS                          0x8cUL
-	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_QCFG       0x8dUL
-	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_CFG        0x8eUL
-	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_QCFG       0x8fUL
-	#define HWRM_CFA_L2_FILTER_ALLOC                  0x90UL
-	#define HWRM_CFA_L2_FILTER_FREE                   0x91UL
-	#define HWRM_CFA_L2_FILTER_CFG                    0x92UL
-	#define HWRM_CFA_L2_SET_RX_MASK                   0x93UL
-	#define HWRM_CFA_VLAN_ANTISPOOF_CFG               0x94UL
-	#define HWRM_CFA_TUNNEL_FILTER_ALLOC              0x95UL
-	#define HWRM_CFA_TUNNEL_FILTER_FREE               0x96UL
-	#define HWRM_CFA_ENCAP_RECORD_ALLOC               0x97UL
-	#define HWRM_CFA_ENCAP_RECORD_FREE                0x98UL
-	#define HWRM_CFA_NTUPLE_FILTER_ALLOC              0x99UL
-	#define HWRM_CFA_NTUPLE_FILTER_FREE               0x9aUL
-	#define HWRM_CFA_NTUPLE_FILTER_CFG                0x9bUL
-	#define HWRM_CFA_EM_FLOW_ALLOC                    0x9cUL
-	#define HWRM_CFA_EM_FLOW_FREE                     0x9dUL
-	#define HWRM_CFA_EM_FLOW_CFG                      0x9eUL
-	#define HWRM_TUNNEL_DST_PORT_QUERY                0xa0UL
-	#define HWRM_TUNNEL_DST_PORT_ALLOC                0xa1UL
-	#define HWRM_TUNNEL_DST_PORT_FREE                 0xa2UL
-	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_CFG        0xa3UL
-	#define HWRM_STAT_CTX_ENG_QUERY                   0xafUL
-	#define HWRM_STAT_CTX_ALLOC                       0xb0UL
-	#define HWRM_STAT_CTX_FREE                        0xb1UL
-	#define HWRM_STAT_CTX_QUERY                       0xb2UL
-	#define HWRM_STAT_CTX_CLR_STATS                   0xb3UL
-	#define HWRM_PORT_QSTATS_EXT                      0xb4UL
-	#define HWRM_PORT_PHY_MDIO_WRITE                  0xb5UL
-	#define HWRM_PORT_PHY_MDIO_READ                   0xb6UL
-	#define HWRM_PORT_PHY_MDIO_BUS_ACQUIRE            0xb7UL
-	#define HWRM_PORT_PHY_MDIO_BUS_RELEASE            0xb8UL
-	#define HWRM_PORT_QSTATS_EXT_PFC_WD               0xb9UL
-	#define HWRM_RESERVED7                            0xbaUL
-	#define HWRM_PORT_TX_FIR_CFG                      0xbbUL
-	#define HWRM_PORT_TX_FIR_QCFG                     0xbcUL
-	#define HWRM_PORT_ECN_QSTATS                      0xbdUL
-	#define HWRM_FW_LIVEPATCH_QUERY                   0xbeUL
-	#define HWRM_FW_LIVEPATCH                         0xbfUL
-	#define HWRM_FW_RESET                             0xc0UL
-	#define HWRM_FW_QSTATUS                           0xc1UL
-	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
-	#define HWRM_FW_SYNC                              0xc3UL
-	#define HWRM_FW_STATE_QCAPS                       0xc4UL
-	#define HWRM_FW_STATE_QUIESCE                     0xc5UL
-	#define HWRM_FW_STATE_BACKUP                      0xc6UL
-	#define HWRM_FW_STATE_RESTORE                     0xc7UL
-	#define HWRM_FW_SET_TIME                          0xc8UL
-	#define HWRM_FW_GET_TIME                          0xc9UL
-	#define HWRM_FW_SET_STRUCTURED_DATA               0xcaUL
-	#define HWRM_FW_GET_STRUCTURED_DATA               0xcbUL
-	#define HWRM_FW_IPC_MAILBOX                       0xccUL
-	#define HWRM_FW_ECN_CFG                           0xcdUL
-	#define HWRM_FW_ECN_QCFG                          0xceUL
-	#define HWRM_FW_SECURE_CFG                        0xcfUL
-	#define HWRM_EXEC_FWD_RESP                        0xd0UL
-	#define HWRM_REJECT_FWD_RESP                      0xd1UL
-	#define HWRM_FWD_RESP                             0xd2UL
-	#define HWRM_FWD_ASYNC_EVENT_CMPL                 0xd3UL
-	#define HWRM_OEM_CMD                              0xd4UL
-	#define HWRM_PORT_PRBS_TEST                       0xd5UL
-	#define HWRM_PORT_SFP_SIDEBAND_CFG                0xd6UL
-	#define HWRM_PORT_SFP_SIDEBAND_QCFG               0xd7UL
-	#define HWRM_FW_STATE_UNQUIESCE                   0xd8UL
-	#define HWRM_PORT_DSC_DUMP                        0xd9UL
-	#define HWRM_PORT_EP_TX_QCFG                      0xdaUL
-	#define HWRM_PORT_EP_TX_CFG                       0xdbUL
-	#define HWRM_PORT_CFG                             0xdcUL
-	#define HWRM_PORT_QCFG                            0xddUL
-	#define HWRM_PORT_MAC_QCAPS                       0xdfUL
-	#define HWRM_TEMP_MONITOR_QUERY                   0xe0UL
-	#define HWRM_REG_POWER_QUERY                      0xe1UL
-	#define HWRM_CORE_FREQUENCY_QUERY                 0xe2UL
-	#define HWRM_REG_POWER_HISTOGRAM                  0xe3UL
-	#define HWRM_WOL_FILTER_ALLOC                     0xf0UL
-	#define HWRM_WOL_FILTER_FREE                      0xf1UL
-	#define HWRM_WOL_FILTER_QCFG                      0xf2UL
-	#define HWRM_WOL_REASON_QCFG                      0xf3UL
-	#define HWRM_CFA_METER_QCAPS                      0xf4UL
-	#define HWRM_CFA_METER_PROFILE_ALLOC              0xf5UL
-	#define HWRM_CFA_METER_PROFILE_FREE               0xf6UL
-	#define HWRM_CFA_METER_PROFILE_CFG                0xf7UL
-	#define HWRM_CFA_METER_INSTANCE_ALLOC             0xf8UL
-	#define HWRM_CFA_METER_INSTANCE_FREE              0xf9UL
-	#define HWRM_CFA_METER_INSTANCE_CFG               0xfaUL
-	#define HWRM_CFA_VFR_ALLOC                        0xfdUL
-	#define HWRM_CFA_VFR_FREE                         0xfeUL
-	#define HWRM_CFA_VF_PAIR_ALLOC                    0x100UL
-	#define HWRM_CFA_VF_PAIR_FREE                     0x101UL
-	#define HWRM_CFA_VF_PAIR_INFO                     0x102UL
-	#define HWRM_CFA_FLOW_ALLOC                       0x103UL
-	#define HWRM_CFA_FLOW_FREE                        0x104UL
-	#define HWRM_CFA_FLOW_FLUSH                       0x105UL
-	#define HWRM_CFA_FLOW_STATS                       0x106UL
-	#define HWRM_CFA_FLOW_INFO                        0x107UL
-	#define HWRM_CFA_DECAP_FILTER_ALLOC               0x108UL
-	#define HWRM_CFA_DECAP_FILTER_FREE                0x109UL
-	#define HWRM_CFA_VLAN_ANTISPOOF_QCFG              0x10aUL
-	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_ALLOC       0x10bUL
-	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_FREE        0x10cUL
-	#define HWRM_CFA_PAIR_ALLOC                       0x10dUL
-	#define HWRM_CFA_PAIR_FREE                        0x10eUL
-	#define HWRM_CFA_PAIR_INFO                        0x10fUL
-	#define HWRM_FW_IPC_MSG                           0x110UL
-	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_INFO        0x111UL
-	#define HWRM_CFA_REDIRECT_QUERY_TUNNEL_TYPE       0x112UL
-	#define HWRM_CFA_FLOW_AGING_TIMER_RESET           0x113UL
-	#define HWRM_CFA_FLOW_AGING_CFG                   0x114UL
-	#define HWRM_CFA_FLOW_AGING_QCFG                  0x115UL
-	#define HWRM_CFA_FLOW_AGING_QCAPS                 0x116UL
-	#define HWRM_CFA_CTX_MEM_RGTR                     0x117UL
-	#define HWRM_CFA_CTX_MEM_UNRGTR                   0x118UL
-	#define HWRM_CFA_CTX_MEM_QCTX                     0x119UL
-	#define HWRM_CFA_CTX_MEM_QCAPS                    0x11aUL
-	#define HWRM_CFA_COUNTER_QCAPS                    0x11bUL
-	#define HWRM_CFA_COUNTER_CFG                      0x11cUL
-	#define HWRM_CFA_COUNTER_QCFG                     0x11dUL
-	#define HWRM_CFA_COUNTER_QSTATS                   0x11eUL
-	#define HWRM_CFA_TCP_FLAG_PROCESS_QCFG            0x11fUL
-	#define HWRM_CFA_EEM_QCAPS                        0x120UL
-	#define HWRM_CFA_EEM_CFG                          0x121UL
-	#define HWRM_CFA_EEM_QCFG                         0x122UL
-	#define HWRM_CFA_EEM_OP                           0x123UL
-	#define HWRM_CFA_ADV_FLOW_MGNT_QCAPS              0x124UL
-	#define HWRM_CFA_TFLIB                            0x125UL
-	#define HWRM_CFA_LAG_GROUP_MEMBER_RGTR            0x126UL
-	#define HWRM_CFA_LAG_GROUP_MEMBER_UNRGTR          0x127UL
-	#define HWRM_CFA_TLS_FILTER_ALLOC                 0x128UL
-	#define HWRM_CFA_TLS_FILTER_FREE                  0x129UL
-	#define HWRM_CFA_RELEASE_AFM_FUNC                 0x12aUL
-	#define HWRM_ENGINE_CKV_STATUS                    0x12eUL
-	#define HWRM_ENGINE_CKV_CKEK_ADD                  0x12fUL
-	#define HWRM_ENGINE_CKV_CKEK_DELETE               0x130UL
-	#define HWRM_ENGINE_CKV_KEY_ADD                   0x131UL
-	#define HWRM_ENGINE_CKV_KEY_DELETE                0x132UL
-	#define HWRM_ENGINE_CKV_FLUSH                     0x133UL
-	#define HWRM_ENGINE_CKV_RNG_GET                   0x134UL
-	#define HWRM_ENGINE_CKV_KEY_GEN                   0x135UL
-	#define HWRM_ENGINE_CKV_KEY_LABEL_CFG             0x136UL
-	#define HWRM_ENGINE_CKV_KEY_LABEL_QCFG            0x137UL
-	#define HWRM_ENGINE_QG_CONFIG_QUERY               0x13cUL
-	#define HWRM_ENGINE_QG_QUERY                      0x13dUL
-	#define HWRM_ENGINE_QG_METER_PROFILE_CONFIG_QUERY 0x13eUL
-	#define HWRM_ENGINE_QG_METER_PROFILE_QUERY        0x13fUL
-	#define HWRM_ENGINE_QG_METER_PROFILE_ALLOC        0x140UL
-	#define HWRM_ENGINE_QG_METER_PROFILE_FREE         0x141UL
-	#define HWRM_ENGINE_QG_METER_QUERY                0x142UL
-	#define HWRM_ENGINE_QG_METER_BIND                 0x143UL
-	#define HWRM_ENGINE_QG_METER_UNBIND               0x144UL
-	#define HWRM_ENGINE_QG_FUNC_BIND                  0x145UL
-	#define HWRM_ENGINE_SG_CONFIG_QUERY               0x146UL
-	#define HWRM_ENGINE_SG_QUERY                      0x147UL
-	#define HWRM_ENGINE_SG_METER_QUERY                0x148UL
-	#define HWRM_ENGINE_SG_METER_CONFIG               0x149UL
-	#define HWRM_ENGINE_SG_QG_BIND                    0x14aUL
-	#define HWRM_ENGINE_QG_SG_UNBIND                  0x14bUL
-	#define HWRM_ENGINE_CONFIG_QUERY                  0x154UL
-	#define HWRM_ENGINE_STATS_CONFIG                  0x155UL
-	#define HWRM_ENGINE_STATS_CLEAR                   0x156UL
-	#define HWRM_ENGINE_STATS_QUERY                   0x157UL
-	#define HWRM_ENGINE_STATS_QUERY_CONTINUOUS_ERROR  0x158UL
-	#define HWRM_ENGINE_RQ_ALLOC                      0x15eUL
-	#define HWRM_ENGINE_RQ_FREE                       0x15fUL
-	#define HWRM_ENGINE_CQ_ALLOC                      0x160UL
-	#define HWRM_ENGINE_CQ_FREE                       0x161UL
-	#define HWRM_ENGINE_NQ_ALLOC                      0x162UL
-	#define HWRM_ENGINE_NQ_FREE                       0x163UL
-	#define HWRM_ENGINE_ON_DIE_RQE_CREDITS            0x164UL
-	#define HWRM_ENGINE_FUNC_QCFG                     0x165UL
-	#define HWRM_FUNC_RESOURCE_QCAPS                  0x190UL
-	#define HWRM_FUNC_VF_RESOURCE_CFG                 0x191UL
-	#define HWRM_FUNC_BACKING_STORE_QCAPS             0x192UL
-	#define HWRM_FUNC_BACKING_STORE_CFG               0x193UL
-	#define HWRM_FUNC_BACKING_STORE_QCFG              0x194UL
-	#define HWRM_FUNC_VF_BW_CFG                       0x195UL
-	#define HWRM_FUNC_VF_BW_QCFG                      0x196UL
-	#define HWRM_FUNC_HOST_PF_IDS_QUERY               0x197UL
-	#define HWRM_FUNC_QSTATS_EXT                      0x198UL
-	#define HWRM_STAT_EXT_CTX_QUERY                   0x199UL
-	#define HWRM_FUNC_SPD_CFG                         0x19aUL
-	#define HWRM_FUNC_SPD_QCFG                        0x19bUL
-	#define HWRM_FUNC_PTP_PIN_QCFG                    0x19cUL
-	#define HWRM_FUNC_PTP_PIN_CFG                     0x19dUL
-	#define HWRM_FUNC_PTP_CFG                         0x19eUL
-	#define HWRM_FUNC_PTP_TS_QUERY                    0x19fUL
-	#define HWRM_FUNC_PTP_EXT_CFG                     0x1a0UL
-	#define HWRM_FUNC_PTP_EXT_QCFG                    0x1a1UL
-	#define HWRM_FUNC_KEY_CTX_ALLOC                   0x1a2UL
-	#define HWRM_FUNC_BACKING_STORE_CFG_V2            0x1a3UL
-	#define HWRM_FUNC_BACKING_STORE_QCFG_V2           0x1a4UL
-	#define HWRM_FUNC_DBR_PACING_CFG                  0x1a5UL
-	#define HWRM_FUNC_DBR_PACING_QCFG                 0x1a6UL
-	#define HWRM_FUNC_DBR_PACING_BROADCAST_EVENT      0x1a7UL
-	#define HWRM_FUNC_BACKING_STORE_QCAPS_V2          0x1a8UL
-	#define HWRM_FUNC_DBR_PACING_NQLIST_QUERY         0x1a9UL
-	#define HWRM_FUNC_DBR_RECOVERY_COMPLETED          0x1aaUL
-	#define HWRM_FUNC_SYNCE_CFG                       0x1abUL
-	#define HWRM_FUNC_SYNCE_QCFG                      0x1acUL
-	#define HWRM_FUNC_KEY_CTX_FREE                    0x1adUL
-	#define HWRM_FUNC_LAG_MODE_CFG                    0x1aeUL
-	#define HWRM_FUNC_LAG_MODE_QCFG                   0x1afUL
-	#define HWRM_FUNC_LAG_CREATE                      0x1b0UL
-	#define HWRM_FUNC_LAG_UPDATE                      0x1b1UL
-	#define HWRM_FUNC_LAG_FREE                        0x1b2UL
-	#define HWRM_FUNC_LAG_QCFG                        0x1b3UL
-	#define HWRM_FUNC_TIMEDTX_PACING_RATE_ADD         0x1c2UL
-	#define HWRM_FUNC_TIMEDTX_PACING_RATE_DELETE      0x1c3UL
-	#define HWRM_FUNC_TIMEDTX_PACING_RATE_QUERY       0x1c4UL
-	#define HWRM_SELFTEST_QLIST                       0x200UL
-	#define HWRM_SELFTEST_EXEC                        0x201UL
-	#define HWRM_SELFTEST_IRQ                         0x202UL
-	#define HWRM_SELFTEST_RETRIEVE_SERDES_DATA        0x203UL
-	#define HWRM_PCIE_QSTATS                          0x204UL
-	#define HWRM_MFG_FRU_WRITE_CONTROL                0x205UL
-	#define HWRM_MFG_TIMERS_QUERY                     0x206UL
-	#define HWRM_MFG_OTP_CFG                          0x207UL
-	#define HWRM_MFG_OTP_QCFG                         0x208UL
-	#define HWRM_MFG_HDMA_TEST                        0x209UL
-	#define HWRM_MFG_FRU_EEPROM_WRITE                 0x20aUL
-	#define HWRM_MFG_FRU_EEPROM_READ                  0x20bUL
-	#define HWRM_MFG_SOC_IMAGE                        0x20cUL
-	#define HWRM_MFG_SOC_QSTATUS                      0x20dUL
-	#define HWRM_MFG_PARAM_CRITICAL_DATA_FINALIZE     0x20eUL
-	#define HWRM_MFG_PARAM_CRITICAL_DATA_READ         0x20fUL
-	#define HWRM_MFG_PARAM_CRITICAL_DATA_HEALTH       0x210UL
-	#define HWRM_MFG_PRVSN_EXPORT_CSR                 0x211UL
-	#define HWRM_MFG_PRVSN_IMPORT_CERT                0x212UL
-	#define HWRM_MFG_PRVSN_GET_STATE                  0x213UL
-	#define HWRM_MFG_GET_NVM_MEASUREMENT              0x214UL
-	#define HWRM_MFG_PSOC_QSTATUS                     0x215UL
-	#define HWRM_MFG_SELFTEST_QLIST                   0x216UL
-	#define HWRM_MFG_SELFTEST_EXEC                    0x217UL
-	#define HWRM_STAT_GENERIC_QSTATS                  0x218UL
-	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
-	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
-	#define HWRM_MFG_TESTS                            0x21bUL
-	#define HWRM_MFG_WRITE_CERT_NVM                   0x21cUL
-	#define HWRM_PORT_POE_CFG                         0x230UL
-	#define HWRM_PORT_POE_QCFG                        0x231UL
-	#define HWRM_UDCC_QCAPS                           0x258UL
-	#define HWRM_UDCC_CFG                             0x259UL
-	#define HWRM_UDCC_QCFG                            0x25aUL
-	#define HWRM_UDCC_SESSION_CFG                     0x25bUL
-	#define HWRM_UDCC_SESSION_QCFG                    0x25cUL
-	#define HWRM_UDCC_SESSION_QUERY                   0x25dUL
-	#define HWRM_UDCC_COMP_CFG                        0x25eUL
-	#define HWRM_UDCC_COMP_QCFG                       0x25fUL
-	#define HWRM_UDCC_COMP_QUERY                      0x260UL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS            0x261UL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_CFG              0x262UL
-	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG             0x263UL
-	#define HWRM_TF                                   0x2bcUL
-	#define HWRM_TF_VERSION_GET                       0x2bdUL
-	#define HWRM_TF_SESSION_OPEN                      0x2c6UL
-	#define HWRM_TF_SESSION_REGISTER                  0x2c8UL
-	#define HWRM_TF_SESSION_UNREGISTER                0x2c9UL
-	#define HWRM_TF_SESSION_CLOSE                     0x2caUL
-	#define HWRM_TF_SESSION_QCFG                      0x2cbUL
-	#define HWRM_TF_SESSION_RESC_QCAPS                0x2ccUL
-	#define HWRM_TF_SESSION_RESC_ALLOC                0x2cdUL
-	#define HWRM_TF_SESSION_RESC_FREE                 0x2ceUL
-	#define HWRM_TF_SESSION_RESC_FLUSH                0x2cfUL
-	#define HWRM_TF_SESSION_RESC_INFO                 0x2d0UL
-	#define HWRM_TF_SESSION_HOTUP_STATE_SET           0x2d1UL
-	#define HWRM_TF_SESSION_HOTUP_STATE_GET           0x2d2UL
-	#define HWRM_TF_TBL_TYPE_GET                      0x2daUL
-	#define HWRM_TF_TBL_TYPE_SET                      0x2dbUL
-	#define HWRM_TF_TBL_TYPE_BULK_GET                 0x2dcUL
-	#define HWRM_TF_EM_INSERT                         0x2eaUL
-	#define HWRM_TF_EM_DELETE                         0x2ebUL
-	#define HWRM_TF_EM_HASH_INSERT                    0x2ecUL
-	#define HWRM_TF_EM_MOVE                           0x2edUL
-	#define HWRM_TF_TCAM_SET                          0x2f8UL
-	#define HWRM_TF_TCAM_GET                          0x2f9UL
-	#define HWRM_TF_TCAM_MOVE                         0x2faUL
-	#define HWRM_TF_TCAM_FREE                         0x2fbUL
-	#define HWRM_TF_GLOBAL_CFG_SET                    0x2fcUL
-	#define HWRM_TF_GLOBAL_CFG_GET                    0x2fdUL
-	#define HWRM_TF_IF_TBL_SET                        0x2feUL
-	#define HWRM_TF_IF_TBL_GET                        0x2ffUL
-	#define HWRM_TF_RESC_USAGE_SET                    0x300UL
-	#define HWRM_TF_RESC_USAGE_QUERY                  0x301UL
-	#define HWRM_TF_TBL_TYPE_ALLOC                    0x302UL
-	#define HWRM_TF_TBL_TYPE_FREE                     0x303UL
-	#define HWRM_TFC_TBL_SCOPE_QCAPS                  0x380UL
-	#define HWRM_TFC_TBL_SCOPE_ID_ALLOC               0x381UL
-	#define HWRM_TFC_TBL_SCOPE_CONFIG                 0x382UL
-	#define HWRM_TFC_TBL_SCOPE_DECONFIG               0x383UL
-	#define HWRM_TFC_TBL_SCOPE_FID_ADD                0x384UL
-	#define HWRM_TFC_TBL_SCOPE_FID_REM                0x385UL
-	#define HWRM_TFC_TBL_SCOPE_POOL_ALLOC             0x386UL
-	#define HWRM_TFC_TBL_SCOPE_POOL_FREE              0x387UL
-	#define HWRM_TFC_SESSION_ID_ALLOC                 0x388UL
-	#define HWRM_TFC_SESSION_FID_ADD                  0x389UL
-	#define HWRM_TFC_SESSION_FID_REM                  0x38aUL
-	#define HWRM_TFC_IDENT_ALLOC                      0x38bUL
-	#define HWRM_TFC_IDENT_FREE                       0x38cUL
-	#define HWRM_TFC_IDX_TBL_ALLOC                    0x38dUL
-	#define HWRM_TFC_IDX_TBL_ALLOC_SET                0x38eUL
-	#define HWRM_TFC_IDX_TBL_SET                      0x38fUL
-	#define HWRM_TFC_IDX_TBL_GET                      0x390UL
-	#define HWRM_TFC_IDX_TBL_FREE                     0x391UL
-	#define HWRM_TFC_GLOBAL_ID_ALLOC                  0x392UL
-	#define HWRM_TFC_TCAM_SET                         0x393UL
-	#define HWRM_TFC_TCAM_GET                         0x394UL
-	#define HWRM_TFC_TCAM_ALLOC                       0x395UL
-	#define HWRM_TFC_TCAM_ALLOC_SET                   0x396UL
-	#define HWRM_TFC_TCAM_FREE                        0x397UL
-	#define HWRM_TFC_IF_TBL_SET                       0x398UL
-	#define HWRM_TFC_IF_TBL_GET                       0x399UL
-	#define HWRM_TFC_TBL_SCOPE_CONFIG_GET             0x39aUL
-	#define HWRM_TFC_RESC_USAGE_QUERY                 0x39bUL
-	#define HWRM_TFC_GLOBAL_ID_FREE                   0x39cUL
-	#define HWRM_TFC_TCAM_PRI_UPDATE                  0x39dUL
-	#define HWRM_TFC_HOT_UPGRADE_PROCESS              0x3a0UL
-	#define HWRM_SV                                   0x400UL
-	#define HWRM_DBG_SERDES_TEST                      0xff0eUL
-	#define HWRM_DBG_LOG_BUFFER_FLUSH                 0xff0fUL
-	#define HWRM_DBG_READ_DIRECT                      0xff10UL
-	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
-	#define HWRM_DBG_WRITE_DIRECT                     0xff12UL
-	#define HWRM_DBG_WRITE_INDIRECT                   0xff13UL
-	#define HWRM_DBG_DUMP                             0xff14UL
-	#define HWRM_DBG_ERASE_NVM                        0xff15UL
-	#define HWRM_DBG_CFG                              0xff16UL
-	#define HWRM_DBG_COREDUMP_LIST                    0xff17UL
-	#define HWRM_DBG_COREDUMP_INITIATE                0xff18UL
-	#define HWRM_DBG_COREDUMP_RETRIEVE                0xff19UL
-	#define HWRM_DBG_FW_CLI                           0xff1aUL
-	#define HWRM_DBG_I2C_CMD                          0xff1bUL
-	#define HWRM_DBG_RING_INFO_GET                    0xff1cUL
-	#define HWRM_DBG_CRASHDUMP_HEADER                 0xff1dUL
-	#define HWRM_DBG_CRASHDUMP_ERASE                  0xff1eUL
-	#define HWRM_DBG_DRV_TRACE                        0xff1fUL
-	#define HWRM_DBG_QCAPS                            0xff20UL
-	#define HWRM_DBG_QCFG                             0xff21UL
-	#define HWRM_DBG_CRASHDUMP_MEDIUM_CFG             0xff22UL
-	#define HWRM_DBG_USEQ_ALLOC                       0xff23UL
-	#define HWRM_DBG_USEQ_FREE                        0xff24UL
-	#define HWRM_DBG_USEQ_FLUSH                       0xff25UL
-	#define HWRM_DBG_USEQ_QCAPS                       0xff26UL
-	#define HWRM_DBG_USEQ_CW_CFG                      0xff27UL
-	#define HWRM_DBG_USEQ_SCHED_CFG                   0xff28UL
-	#define HWRM_DBG_USEQ_RUN                         0xff29UL
-	#define HWRM_DBG_USEQ_DELIVERY_REQ                0xff2aUL
-	#define HWRM_DBG_USEQ_RESP_HDR                    0xff2bUL
-	#define HWRM_DBG_COREDUMP_CAPTURE                 0xff2cUL
-	#define HWRM_DBG_PTRACE                           0xff2dUL
-	#define HWRM_DBG_SIM_CABLE_STATE                  0xff2eUL
-	#define HWRM_NVM_GET_VPD_FIELD_INFO               0xffeaUL
-	#define HWRM_NVM_SET_VPD_FIELD_INFO               0xffebUL
-	#define HWRM_NVM_DEFRAG                           0xffecUL
-	#define HWRM_NVM_REQ_ARBITRATION                  0xffedUL
-	#define HWRM_NVM_FACTORY_DEFAULTS                 0xffeeUL
-	#define HWRM_NVM_VALIDATE_OPTION                  0xffefUL
-	#define HWRM_NVM_FLUSH                            0xfff0UL
-	#define HWRM_NVM_GET_VARIABLE                     0xfff1UL
-	#define HWRM_NVM_SET_VARIABLE                     0xfff2UL
-	#define HWRM_NVM_INSTALL_UPDATE                   0xfff3UL
-	#define HWRM_NVM_MODIFY                           0xfff4UL
-	#define HWRM_NVM_VERIFY_UPDATE                    0xfff5UL
-	#define HWRM_NVM_GET_DEV_INFO                     0xfff6UL
-	#define HWRM_NVM_ERASE_DIR_ENTRY                  0xfff7UL
-	#define HWRM_NVM_MOD_DIR_ENTRY                    0xfff8UL
-	#define HWRM_NVM_FIND_DIR_ENTRY                   0xfff9UL
-	#define HWRM_NVM_GET_DIR_ENTRIES                  0xfffaUL
-	#define HWRM_NVM_GET_DIR_INFO                     0xfffbUL
-	#define HWRM_NVM_RAW_DUMP                         0xfffcUL
-	#define HWRM_NVM_READ                             0xfffdUL
-	#define HWRM_NVM_WRITE                            0xfffeUL
-	#define HWRM_NVM_RAW_WRITE_BLK                    0xffffUL
-	#define HWRM_LAST                                HWRM_NVM_RAW_WRITE_BLK
-	__le16	unused_0[3];
-};
-
-/* ret_codes (size:64b/8B) */
-struct ret_codes {
-	__le16	error_code;
-	#define HWRM_ERR_CODE_SUCCESS                      0x0UL
-	#define HWRM_ERR_CODE_FAIL                         0x1UL
-	#define HWRM_ERR_CODE_INVALID_PARAMS               0x2UL
-	#define HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED       0x3UL
-	#define HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR         0x4UL
-	#define HWRM_ERR_CODE_INVALID_FLAGS                0x5UL
-	#define HWRM_ERR_CODE_INVALID_ENABLES              0x6UL
-	#define HWRM_ERR_CODE_UNSUPPORTED_TLV              0x7UL
-	#define HWRM_ERR_CODE_NO_BUFFER                    0x8UL
-	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR       0x9UL
-	#define HWRM_ERR_CODE_HOT_RESET_PROGRESS           0xaUL
-	#define HWRM_ERR_CODE_HOT_RESET_FAIL               0xbUL
-	#define HWRM_ERR_CODE_NO_FLOW_COUNTER_DURING_ALLOC 0xcUL
-	#define HWRM_ERR_CODE_KEY_HASH_COLLISION           0xdUL
-	#define HWRM_ERR_CODE_KEY_ALREADY_EXISTS           0xeUL
-	#define HWRM_ERR_CODE_HWRM_ERROR                   0xfUL
-	#define HWRM_ERR_CODE_BUSY                         0x10UL
-	#define HWRM_ERR_CODE_RESOURCE_LOCKED              0x11UL
-	#define HWRM_ERR_CODE_PF_UNAVAILABLE               0x12UL
-	#define HWRM_ERR_CODE_ENTITY_NOT_PRESENT           0x13UL
-	#define HWRM_ERR_CODE_SECURE_SOC_ERROR             0x14UL
-	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE    0x8000UL
-	#define HWRM_ERR_CODE_UNKNOWN_ERR                  0xfffeUL
-	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED            0xffffUL
-	#define HWRM_ERR_CODE_LAST                        HWRM_ERR_CODE_CMD_NOT_SUPPORTED
-	__le16	unused_0[3];
-};
-
-/* hwrm_err_output (size:128b/16B) */
-struct hwrm_err_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	opaque_0;
-	__le16	opaque_1;
-	u8	cmd_err;
-	u8	valid;
-};
-#define HWRM_NA_SIGNATURE ((__le32)(-1))
-#define HWRM_MAX_REQ_LEN 128
-#define HWRM_MAX_RESP_LEN 704
-#define HW_HASH_INDEX_SIZE 0x80
-#define HW_HASH_KEY_SIZE 40
-#define HWRM_RESP_VALID_KEY 1
-#define HWRM_TARGET_ID_BONO 0xFFF8
-#define HWRM_TARGET_ID_KONG 0xFFF9
-#define HWRM_TARGET_ID_APE 0xFFFA
-#define HWRM_TARGET_ID_TOOLS 0xFFFD
-#define HWRM_VERSION_MAJOR 1
-#define HWRM_VERSION_MINOR 10
-#define HWRM_VERSION_UPDATE 3
-#define HWRM_VERSION_RSVD 97
-#define HWRM_VERSION_STR "1.10.3.97"
-
-/* hwrm_ver_get_input (size:192b/24B) */
-struct hwrm_ver_get_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	hwrm_intf_maj;
-	u8	hwrm_intf_min;
-	u8	hwrm_intf_upd;
-	u8	unused_0[5];
-};
-
-/* hwrm_ver_get_output (size:1408b/176B) */
-struct hwrm_ver_get_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	hwrm_intf_maj_8b;
-	u8	hwrm_intf_min_8b;
-	u8	hwrm_intf_upd_8b;
-	u8	hwrm_intf_rsvd_8b;
-	u8	hwrm_fw_maj_8b;
-	u8	hwrm_fw_min_8b;
-	u8	hwrm_fw_bld_8b;
-	u8	hwrm_fw_rsvd_8b;
-	u8	mgmt_fw_maj_8b;
-	u8	mgmt_fw_min_8b;
-	u8	mgmt_fw_bld_8b;
-	u8	mgmt_fw_rsvd_8b;
-	u8	netctrl_fw_maj_8b;
-	u8	netctrl_fw_min_8b;
-	u8	netctrl_fw_bld_8b;
-	u8	netctrl_fw_rsvd_8b;
-	__le32	dev_caps_cfg;
-	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_FW_UPD_SUPPORTED                  0x1UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_FW_DCBX_AGENT_SUPPORTED                  0x2UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED                      0x4UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED                       0x8UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_KONG_MB_CHNL_SUPPORTED                   0x10UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_HANDLE_64BIT_SUPPORTED              0x20UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_L2_FILTER_TYPES_ROCE_OR_L2_SUPPORTED     0x40UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_VIRTIO_VSWITCH_OFFLOAD_SUPPORTED         0x80UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED                     0x100UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_AGING_SUPPORTED                     0x200UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_ADV_FLOW_COUNTERS_SUPPORTED              0x400UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_EEM_SUPPORTED                        0x800UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED              0x1000UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED                      0x2000UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED                    0x4000UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE                      0x8000UL
-	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_SOC_CAPABLE                       0x10000UL
-	u8	roce_fw_maj_8b;
-	u8	roce_fw_min_8b;
-	u8	roce_fw_bld_8b;
-	u8	roce_fw_rsvd_8b;
-	char	hwrm_fw_name[16];
-	char	mgmt_fw_name[16];
-	char	netctrl_fw_name[16];
-	char	active_pkg_name[16];
-	char	roce_fw_name[16];
-	__le16	chip_num;
-	u8	chip_rev;
-	u8	chip_metal;
-	u8	chip_bond_id;
-	u8	chip_platform_type;
-	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_ASIC      0x0UL
-	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_FPGA      0x1UL
-	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM 0x2UL
-	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_LAST     VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM
-	__le16	max_req_win_len;
-	__le16	max_resp_len;
-	__le16	def_req_timeout;
-	u8	flags;
-	#define VER_GET_RESP_FLAGS_DEV_NOT_RDY                   0x1UL
-	#define VER_GET_RESP_FLAGS_EXT_VER_AVAIL                 0x2UL
-	#define VER_GET_RESP_FLAGS_DEV_NOT_RDY_BACKING_STORE     0x4UL
-	u8	unused_0[2];
-	u8	always_1;
-	__le16	hwrm_intf_major;
-	__le16	hwrm_intf_minor;
-	__le16	hwrm_intf_build;
-	__le16	hwrm_intf_patch;
-	__le16	hwrm_fw_major;
-	__le16	hwrm_fw_minor;
-	__le16	hwrm_fw_build;
-	__le16	hwrm_fw_patch;
-	__le16	mgmt_fw_major;
-	__le16	mgmt_fw_minor;
-	__le16	mgmt_fw_build;
-	__le16	mgmt_fw_patch;
-	__le16	netctrl_fw_major;
-	__le16	netctrl_fw_minor;
-	__le16	netctrl_fw_build;
-	__le16	netctrl_fw_patch;
-	__le16	roce_fw_major;
-	__le16	roce_fw_minor;
-	__le16	roce_fw_build;
-	__le16	roce_fw_patch;
-	__le16	max_ext_req_len;
-	__le16	max_req_timeout;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* eject_cmpl (size:128b/16B) */
-struct eject_cmpl {
-	__le16	type;
-	#define EJECT_CMPL_TYPE_MASK       0x3fUL
-	#define EJECT_CMPL_TYPE_SFT        0
-	#define EJECT_CMPL_TYPE_STAT_EJECT   0x1aUL
-	#define EJECT_CMPL_TYPE_LAST        EJECT_CMPL_TYPE_STAT_EJECT
-	#define EJECT_CMPL_FLAGS_MASK      0xffc0UL
-	#define EJECT_CMPL_FLAGS_SFT       6
-	#define EJECT_CMPL_FLAGS_ERROR      0x40UL
-	__le16	len;
-	__le32	opaque;
-	__le16	v;
-	#define EJECT_CMPL_V                              0x1UL
-	#define EJECT_CMPL_ERRORS_MASK                    0xfffeUL
-	#define EJECT_CMPL_ERRORS_SFT                     1
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_MASK        0xeUL
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_SFT         1
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_NO_BUFFER     (0x0UL << 1)
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_DID_NOT_FIT   (0x1UL << 1)
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_BAD_FORMAT    (0x3UL << 1)
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH         (0x5UL << 1)
-	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_LAST         EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH
-	__le16	reserved16;
-	__le32	unused_2;
-};
-
-/* hwrm_cmpl (size:128b/16B) */
-struct hwrm_cmpl {
-	__le16	type;
-	#define CMPL_TYPE_MASK     0x3fUL
-	#define CMPL_TYPE_SFT      0
-	#define CMPL_TYPE_HWRM_DONE  0x20UL
-	#define CMPL_TYPE_LAST      CMPL_TYPE_HWRM_DONE
-	__le16	sequence_id;
-	__le32	unused_1;
-	__le32	v;
-	#define CMPL_V     0x1UL
-	__le32	unused_3;
-};
-
-/* hwrm_fwd_req_cmpl (size:128b/16B) */
-struct hwrm_fwd_req_cmpl {
-	__le16	req_len_type;
-	#define FWD_REQ_CMPL_TYPE_MASK        0x3fUL
-	#define FWD_REQ_CMPL_TYPE_SFT         0
-	#define FWD_REQ_CMPL_TYPE_HWRM_FWD_REQ  0x22UL
-	#define FWD_REQ_CMPL_TYPE_LAST         FWD_REQ_CMPL_TYPE_HWRM_FWD_REQ
-	#define FWD_REQ_CMPL_REQ_LEN_MASK     0xffc0UL
-	#define FWD_REQ_CMPL_REQ_LEN_SFT      6
-	__le16	source_id;
-	__le32	unused0;
-	__le32	req_buf_addr_v[2];
-	#define FWD_REQ_CMPL_V                0x1UL
-	#define FWD_REQ_CMPL_REQ_BUF_ADDR_MASK 0xfffffffeUL
-	#define FWD_REQ_CMPL_REQ_BUF_ADDR_SFT 1
-};
-
-/* hwrm_fwd_resp_cmpl (size:128b/16B) */
-struct hwrm_fwd_resp_cmpl {
-	__le16	type;
-	#define FWD_RESP_CMPL_TYPE_MASK         0x3fUL
-	#define FWD_RESP_CMPL_TYPE_SFT          0
-	#define FWD_RESP_CMPL_TYPE_HWRM_FWD_RESP  0x24UL
-	#define FWD_RESP_CMPL_TYPE_LAST          FWD_RESP_CMPL_TYPE_HWRM_FWD_RESP
-	__le16	source_id;
-	__le16	resp_len;
-	__le16	unused_1;
-	__le32	resp_buf_addr_v[2];
-	#define FWD_RESP_CMPL_V                 0x1UL
-	#define FWD_RESP_CMPL_RESP_BUF_ADDR_MASK 0xfffffffeUL
-	#define FWD_RESP_CMPL_RESP_BUF_ADDR_SFT 1
-};
-
-/* hwrm_async_event_cmpl (size:128b/16B) */
-struct hwrm_async_event_cmpl {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_TYPE_LAST             ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE              0x0UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_MTU_CHANGE                 0x1UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE               0x2UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE               0x3UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED           0x4UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_NOT_ALLOWED      0x5UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE           0x6UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE             0x7UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY                    0x8UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY                  0x9UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_RING_MONITOR_MSG                0xaUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD                0x10UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD                  0x11UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_FLR_PROC_CMPLT             0x12UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD                  0x20UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_LOAD                    0x21UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_FLR                          0x30UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_MAC_ADDR_CHANGE              0x31UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE        0x32UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE                   0x33UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE                 0x34UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE             0x35UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_FLOW_AGED                    0x36UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION              0x37UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_REQ             0x38UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_DONE            0x39UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE          0x3aUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE                 0x3bUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE                  0x3cUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_DEFAULT_VNIC_CHANGE       0x3dUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_LINK_STATUS_CHANGE        0x3eUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_QUIESCE_DONE                    0x3fUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE               0x40UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE         0x41UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST                    0x42UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE                      0x43UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP                   0x44UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT                    0x45UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_THRESHOLD       0x46UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_RSS_CHANGE                      0x47UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_NQ_UPDATE       0x48UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_DOORBELL_RECOVERY_READ_ERROR 0x49UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_CTX_ERROR                       0x4aUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE             0x4bUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER                0x4cUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE                0x4dUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_REPRESENTOR_PAIR_CHANGE         0x4eUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_STAT_CHANGE                  0x4fUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_HOST_COREDUMP                   0x50UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x51UL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG                    0xfeUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                      0xffUL
-	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                           ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_V          0x1UL
-	#define ASYNC_EVENT_CMPL_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_link_status_change (size:128b/16B) */
-struct hwrm_async_event_cmpl_link_status_change {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LINK_STATUS_CHANGE 0x0UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LAST              ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LINK_STATUS_CHANGE
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE     0x1UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_DOWN  0x0UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP    0x1UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_LAST ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_MASK       0xeUL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_SFT        1
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_MASK    0xffff0UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_SFT     4
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_MASK      0xff00000UL
-	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_SFT       20
-};
-
-/* hwrm_async_event_cmpl_port_conn_not_allowed (size:128b/16B) */
-struct hwrm_async_event_cmpl_port_conn_not_allowed {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_LAST             ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_PORT_CONN_NOT_ALLOWED 0x4UL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_LAST                 ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_PORT_CONN_NOT_ALLOWED
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_V          0x1UL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK                 0xffffUL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_SFT                  0
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_MASK      0xff0000UL
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_SFT       16
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_NONE        (0x0UL << 16)
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_DISABLETX   (0x1UL << 16)
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_WARNINGMSG  (0x2UL << 16)
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_PWRDOWN     (0x3UL << 16)
-	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_LAST       ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_PWRDOWN
-};
-
-/* hwrm_async_event_cmpl_link_speed_cfg_change (size:128b/16B) */
-struct hwrm_async_event_cmpl_link_speed_cfg_change {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LINK_SPEED_CFG_CHANGE 0x6UL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LAST                 ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LINK_SPEED_CFG_CHANGE
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_PORT_ID_MASK                     0xffffUL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_PORT_ID_SFT                      0
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_SUPPORTED_LINK_SPEEDS_CHANGE     0x10000UL
-	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_ILLEGAL_LINK_SPEED_CFG           0x20000UL
-};
-
-/* hwrm_async_event_cmpl_reset_notify (size:128b/16B) */
-struct hwrm_async_event_cmpl_reset_notify {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_LAST             ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY 0x8UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_LAST        ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_V          0x1UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_MASK                  0xffUL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_SFT                   0
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_STOP_TX_QUEUE    0x1UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN           0x2UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_LAST                   ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK                    0xff00UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_SFT                     8
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MANAGEMENT_RESET_REQUEST  (0x1UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL        (0x2UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL    (0x3UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FAST_RESET                (0x4UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION             (0x5UL << 8)
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST                     ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_MASK           0xffff0000UL
-	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT            16
-};
-
-/* hwrm_async_event_cmpl_error_recovery (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_recovery {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY 0x9UL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_LAST          ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASK                 0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_SFT                  0
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC           0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED      0x2UL
-};
-
-/* hwrm_async_event_cmpl_ring_monitor_msg (size:128b/16B) */
-struct hwrm_async_event_cmpl_ring_monitor_msg {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_LAST             ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG 0xaUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_LAST            ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_MASK 0xffUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_SFT 0
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_TX    0x0UL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_RX    0x1UL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL  0x2UL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_LAST ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_V          0x1UL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */
-struct hwrm_async_event_cmpl_vf_cfg_change {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE 0x33UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_LAST         ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_MTU_CHANGE                0x1UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_MRU_CHANGE                0x2UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_DFLT_MAC_ADDR_CHANGE      0x4UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_DFLT_VLAN_CHANGE          0x8UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TRUSTED_VF_CFG_CHANGE     0x10UL
-	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TF_OWNERSHIP_RELEASE      0x20UL
-};
-
-/* hwrm_async_event_cmpl_default_vnic_change (size:128b/16B) */
-struct hwrm_async_event_cmpl_default_vnic_change {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_MASK         0xffc0UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_SFT          6
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION 0x35UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_LAST                   ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_MASK          0x3UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_SFT           0
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_ALLOC  0x1UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE   0x2UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_LAST           ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_MASK                   0x3fcUL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_SFT                    2
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_MASK                   0x3fffc00UL
-	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_SFT                    10
-};
-
-/* hwrm_async_event_cmpl_hw_flow_aged (size:128b/16B) */
-struct hwrm_async_event_cmpl_hw_flow_aged {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_LAST             ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED 0x36UL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_V          0x1UL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_MASK       0x7fffffffUL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_SFT        0
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION     0x80000000UL
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_RX    (0x0UL << 31)
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX    (0x1UL << 31)
-	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_LAST ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX
-};
-
-/* hwrm_async_event_cmpl_eem_cache_flush_req (size:128b/16B) */
-struct hwrm_async_event_cmpl_eem_cache_flush_req {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ 0x38UL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_LAST               ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_V          0x1UL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_eem_cache_flush_done (size:128b/16B) */
-struct hwrm_async_event_cmpl_eem_cache_flush_done {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE 0x39UL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_LAST                ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_SFT 0
-};
-
-/* hwrm_async_event_cmpl_deferred_response (size:128b/16B) */
-struct hwrm_async_event_cmpl_deferred_response {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE 0x40UL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_echo_request (size:128b/16B) */
-struct hwrm_async_event_cmpl_echo_request {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_LAST             ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_ECHO_REQUEST 0x42UL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_ECHO_REQUEST
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-};
-
-/* hwrm_async_event_cmpl_phc_update (size:128b/16B) */
-struct hwrm_async_event_cmpl_phc_update {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_LAST             ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE 0x43UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_LAST      ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_SFT 0
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_MASK   0xffff0000UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_SFT    16
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK          0xfUL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT           0
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_MASTER      0x1UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_SECONDARY   0x2UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_FAILOVER    0x3UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE  0x4UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_LAST           ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK   0xffff0UL
-	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT    4
-};
-
-/* hwrm_async_event_cmpl_pps_timestamp (size:128b/16B) */
-struct hwrm_async_event_cmpl_pps_timestamp {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_LAST             ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP 0x44UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_LAST         ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE              0x1UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL       0x0UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL       0x1UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_LAST          ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_MASK         0xeUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_SFT          1
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_MASK 0xffff0UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_SFT 4
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_V          0x1UL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_MASK 0xffffffffUL
-	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_SFT 0
-};
-
-/* hwrm_async_event_cmpl_error_report (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_SFT 0
-};
-
-/* hwrm_async_event_cmpl_dbg_buf_producer (size:128b/16B) */
-struct hwrm_async_event_cmpl_dbg_buf_producer {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_LAST             ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_DBG_BUF_PRODUCER 0x4cUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_LAST            ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_DBG_BUF_PRODUCER
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA2_CURR_OFF_MASK 0xffffffffUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA2_CURR_OFF_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_V          0x1UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_MASK               0xffffUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SFT                0
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SRT_TRACE            0x0UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SRT2_TRACE           0x1UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CRT_TRACE            0x2UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CRT2_TRACE           0x3UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP0_TRACE          0x4UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_L2_HWRM_TRACE        0x5UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_ROCE_HWRM_TRACE      0x6UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA0_TRACE            0x7UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA1_TRACE            0x8UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA2_TRACE            0x9UL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP1_TRACE          0xaUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE  0xbUL
-	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_LAST                ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE
-};
-
-/* hwrm_async_event_cmpl_hwrm_error (size:128b/16B) */
-struct hwrm_async_event_cmpl_hwrm_error {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_LAST             ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR 0xffUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_LAST      ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_MASK    0xffUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_SFT     0
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_WARNING   0x0UL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_NONFATAL  0x1UL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL     0x2UL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_LAST     ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_V          0x1UL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA1_TIMESTAMP     0x1UL
-};
-
-/* hwrm_async_event_cmpl_error_report_base (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_base {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT                         0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED                      0x0UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM                   0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL                0x2UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM                           0x3UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD       0x4UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD             0x5UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
-};
-
-/* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_pause_storm {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_MASK       0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_SFT        0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM  0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM
-};
-
-/* hwrm_async_event_cmpl_error_report_invalid_signal (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_invalid_signal {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_MASK 0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_MASK          0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_SFT           0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL  0x2UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_LAST           ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL
-};
-
-/* hwrm_async_event_cmpl_error_report_nvm (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_nvm {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_MASK 0xffffffffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_SFT 0
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_MASK     0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_SFT      0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR  0x3UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_LAST      ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_MASK   0xff00UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_SFT    8
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_WRITE    (0x1UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE    (0x2UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_LAST    ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE
-};
-
-/* hwrm_async_event_cmpl_error_report_doorbell_drop_threshold (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_doorbell_drop_threshold {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_MASK                   0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_SFT                    0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD  0x4UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_LAST                    ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_EPOCH_MASK                        0xffffff00UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_EPOCH_SFT                         8
-};
-
-/* hwrm_async_event_cmpl_error_report_thermal (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_thermal {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_MASK  0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_SFT   0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_THRESHOLD_TEMP_MASK 0xff00UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_THRESHOLD_TEMP_SFT 8
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_MASK          0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_SFT           0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_THERMAL_EVENT   0x5UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_LAST           ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_THERMAL_EVENT
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_MASK      0x700UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SFT       8
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_WARN        (0x0UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_CRITICAL    (0x1UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_FATAL       (0x2UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SHUTDOWN    (0x3UL << 8)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SHUTDOWN
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR           0x800UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_DECREASING  (0x0UL << 11)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING  (0x1UL << 11)
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING
-};
-
-/* hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported (size:128b/16B) */
-struct hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported {
-	__le16	type;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_MASK            0x3fUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_SFT             0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT
-	__le16	event_id;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT 0x45UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT
-	__le32	event_data2;
-	u8	opaque_v;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_V          0x1UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_MASK 0xfeUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_SFT 1
-	u8	timestamp_lo;
-	__le16	timestamp_hi;
-	__le32	event_data1;
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_SFT                         0
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
-	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
-};
-
-/* hwrm_func_reset_input (size:192b/24B) */
-struct hwrm_func_reset_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_RESET_REQ_ENABLES_VF_ID_VALID     0x1UL
-	__le16	vf_id;
-	u8	func_reset_level;
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETALL      0x0UL
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETME       0x1UL
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETCHILDREN 0x2UL
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF       0x3UL
-	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_LAST         FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF
-	u8	unused_0;
-};
-
-/* hwrm_func_reset_output (size:128b/16B) */
-struct hwrm_func_reset_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_getfid_input (size:192b/24B) */
-struct hwrm_func_getfid_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_GETFID_REQ_ENABLES_PCI_ID     0x1UL
-	__le16	pci_id;
-	u8	unused_0[2];
-};
-
-/* hwrm_func_getfid_output (size:128b/16B) */
-struct hwrm_func_getfid_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_func_vf_alloc_input (size:192b/24B) */
-struct hwrm_func_vf_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_VF_ALLOC_REQ_ENABLES_FIRST_VF_ID     0x1UL
-	__le16	first_vf_id;
-	__le16	num_vfs;
-};
-
-/* hwrm_func_vf_alloc_output (size:128b/16B) */
-struct hwrm_func_vf_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	first_vf_id;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_func_vf_free_input (size:192b/24B) */
-struct hwrm_func_vf_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_VF_FREE_REQ_ENABLES_FIRST_VF_ID     0x1UL
-	__le16	first_vf_id;
-	__le16	num_vfs;
-};
-
-/* hwrm_func_vf_free_output (size:128b/16B) */
-struct hwrm_func_vf_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_vf_cfg_input (size:576b/72B) */
-struct hwrm_func_vf_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_VF_CFG_REQ_ENABLES_MTU                      0x1UL
-	#define FUNC_VF_CFG_REQ_ENABLES_GUEST_VLAN               0x2UL
-	#define FUNC_VF_CFG_REQ_ENABLES_ASYNC_EVENT_CR           0x4UL
-	#define FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR            0x8UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS          0x10UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS           0x20UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS             0x40UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS             0x80UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_L2_CTXS              0x100UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS                0x200UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS            0x400UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS         0x800UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_KTLS_TX_KEY_CTXS     0x1000UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_KTLS_RX_KEY_CTXS     0x2000UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_QUIC_TX_KEY_CTXS     0x4000UL
-	#define FUNC_VF_CFG_REQ_ENABLES_NUM_QUIC_RX_KEY_CTXS     0x8000UL
-	__le16	mtu;
-	__le16	guest_vlan;
-	__le16	async_event_cr;
-	u8	dflt_mac_addr[6];
-	__le32	flags;
-	#define FUNC_VF_CFG_REQ_FLAGS_TX_ASSETS_TEST             0x1UL
-	#define FUNC_VF_CFG_REQ_FLAGS_RX_ASSETS_TEST             0x2UL
-	#define FUNC_VF_CFG_REQ_FLAGS_CMPL_ASSETS_TEST           0x4UL
-	#define FUNC_VF_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST     0x8UL
-	#define FUNC_VF_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST       0x10UL
-	#define FUNC_VF_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST       0x20UL
-	#define FUNC_VF_CFG_REQ_FLAGS_VNIC_ASSETS_TEST           0x40UL
-	#define FUNC_VF_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST         0x80UL
-	#define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE       0x100UL
-	#define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE      0x200UL
-	__le16	num_rsscos_ctxs;
-	__le16	num_cmpl_rings;
-	__le16	num_tx_rings;
-	__le16	num_rx_rings;
-	__le16	num_l2_ctxs;
-	__le16	num_vnics;
-	__le16	num_stat_ctxs;
-	__le16	num_hw_ring_grps;
-	__le32	num_ktls_tx_key_ctxs;
-	__le32	num_ktls_rx_key_ctxs;
-	__le16	num_msix;
-	u8	unused[2];
-	__le32	num_quic_tx_key_ctxs;
-	__le32	num_quic_rx_key_ctxs;
-};
-
-/* hwrm_func_vf_cfg_output (size:128b/16B) */
-struct hwrm_func_vf_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_qcaps_input (size:192b/24B) */
-struct hwrm_func_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_qcaps_output (size:1152b/144B) */
-struct hwrm_func_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	__le16	port_id;
-	__le32	flags;
-	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED                   0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING               0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED                         0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED                     0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED                     0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED                0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED                     0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED                  0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED                   0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED               0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED                   0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED            0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED            0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED             0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED               0x4000UL
-	#define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED              0x8000UL
-	#define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED                  0x10000UL
-	#define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED                  0x20000UL
-	#define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED                    0x40000UL
-	#define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED           0x80000UL
-	#define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE                         0x100000UL
-	#define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC                 0x200000UL
-	#define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE                     0x400000UL
-	#define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE                0x800000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED                   0x1000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_ERR_RECOVER_RELOAD                    0x2000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_NOTIFY_VF_DEF_VNIC_CHNG_SUPPORTED     0x4000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_VLAN_ACCELERATION_TX_DISABLED         0x8000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_COREDUMP_CMD_SUPPORTED                0x10000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_CRASHDUMP_CMD_SUPPORTED               0x20000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_PFC_WD_STATS_SUPPORTED                0x40000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_DBG_QCAPS_CMD_SUPPORTED               0x80000000UL
-	u8	mac_address[6];
-	__le16	max_rsscos_ctx;
-	__le16	max_cmpl_rings;
-	__le16	max_tx_rings;
-	__le16	max_rx_rings;
-	__le16	max_l2_ctxs;
-	__le16	max_vnics;
-	__le16	first_vf_id;
-	__le16	max_vfs;
-	__le16	max_stat_ctx;
-	__le32	max_encap_records;
-	__le32	max_decap_records;
-	__le32	max_tx_em_flows;
-	__le32	max_tx_wm_flows;
-	__le32	max_rx_em_flows;
-	__le32	max_rx_wm_flows;
-	__le32	max_mcast_filters;
-	__le32	max_flow_id;
-	__le32	max_hw_ring_grps;
-	__le16	max_sp_tx_rings;
-	__le16	max_msix_vfs;
-	__le32	flags_ext;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_MARK_SUPPORTED                          0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_STATS_SUPPORTED                         0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED                      0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT                        0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PROXY_MODE_SUPPORT                          0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_PROXY_SRC_INTF_OVERRIDE_SUPPORT          0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_SCHQ_SUPPORTED                              0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PPP_PUSH_MODE_SUPPORTED                     0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_EVB_MODE_CFG_NOT_SUPPORTED                  0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_SOC_SPD_SUPPORTED                           0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED                      0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_FAST_RESET_CAPABLE                          0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_METADATA_CFG_CAPABLE                     0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_NVM_OPTION_ACTION_SUPPORTED                 0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_BD_METADATA_SUPPORTED                       0x4000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECHO_REQUEST_SUPPORTED                      0x8000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED                          0x10000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PTM_SUPPORTED                           0x20000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED                           0x40000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_VF_CFG_ASYNC_FOR_PF_SUPPORTED               0x80000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PARTITION_BW_SUPPORTED                      0x100000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED                0x200000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_KTLS_SUPPORTED                              0x400000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL                             0x800000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_MIN_BW_SUPPORTED                            0x1000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP                            0x2000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED                             0x4000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_REQUIRED                              0x8000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED                     0x10000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_DBR_PACING_SUPPORTED                        0x20000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_HW_DBR_DROP_RECOV_SUPPORTED                 0x40000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT_DISABLE_CQ_OVERFLOW_DETECTION_SUPPORTED     0x80000000UL
-	u8	max_schqs;
-	u8	mpc_chnls_cap;
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE         0x1UL
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RCE         0x2UL
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TE_CFA      0x4UL
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RE_CFA      0x8UL
-	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE     0x10UL
-	__le16	max_key_ctxs_alloc;
-	__le32	flags_ext2;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED      0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_QUIC_SUPPORTED                        0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KDNET_SUPPORTED                       0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED              0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED        0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED               0x20UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED                     0x40UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED                       0x80UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED               0x100UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED              0x200UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HW_LAG_SUPPORTED                      0x400UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ON_CHIP_CTX_SUPPORTED                 0x800UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_STEERING_TAG_SUPPORTED                0x1000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ENHANCED_VF_SCALE_SUPPORTED           0x2000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KEY_XID_PARTITION_SUPPORTED           0x4000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_CONCURRENT_KTLS_QUIC_SUPPORTED        0x8000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_CROSS_TC_CAP_SUPPORTED           0x10000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_CAP_SUPPORTED             0x20000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_RESERVATION_SUPPORTED     0x40000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DB_ERROR_STATS_SUPPORTED              0x80000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED       0x100000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDCC_SUPPORTED                        0x200000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_SO_TXTIME_SUPPORTED          0x400000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED      0x800000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_INGRESS_NIC_FLOW_SUPPORTED         0x1000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_LPBK_STATS_SUPPORTED                  0x2000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED          0x4000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED       0x8000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED                   0x10000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_PACING_SUPPORTED             0x20000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_VF_STAT_EJECTION_SUPPORTED            0x40000000UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HOST_COREDUMP_SUPPORTED               0x80000000UL
-	__le16	tunnel_disable_flag;
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN      0x1UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE        0x2UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NVGRE      0x4UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_L2GRE      0x8UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_GRE        0x10UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_IPINIP     0x20UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_MPLS       0x40UL
-	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_PPPOE      0x80UL
-	__le16	xid_partition_cap;
-	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_TX_CK     0x1UL
-	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_RX_CK     0x2UL
-	u8	device_serial_number[8];
-	__le16	ctxs_per_partition;
-	__le16	max_tso_segs;
-	__le32	roce_vf_max_av;
-	__le32	roce_vf_max_cq;
-	__le32	roce_vf_max_mrw;
-	__le32	roce_vf_max_qp;
-	__le32	roce_vf_max_srq;
-	__le32	roce_vf_max_gid;
-	__le32	flags_ext3;
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP            0x1UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_REQUIRE_L2_FILTER                 0x2UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MAX_ROCE_VFS_SUPPORTED            0x4UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RX_RATE_PROFILE_SEL_SUPPORTED     0x8UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_BIDI_OPT_SUPPORTED                0x10UL
-	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MIRROR_ON_ROCE_SUPPORTED          0x20UL
-	__le16	max_roce_vfs;
-	__le16	max_crypto_rx_flow_filters;
-	u8	unused_3[3];
-	u8	valid;
-};
-
-/* hwrm_func_qcfg_input (size:192b/24B) */
-struct hwrm_func_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_qcfg_output (size:1344b/168B) */
-struct hwrm_func_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	__le16	port_id;
-	__le16	vlan;
-	__le16	flags;
-	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_MAGICPKT_ENABLED     0x1UL
-	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED          0x2UL
-	#define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED        0x4UL
-	#define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED     0x8UL
-	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED        0x10UL
-	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST                   0x20UL
-	#define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF                   0x40UL
-	#define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED          0x80UL
-	#define FUNC_QCFG_RESP_FLAGS_PREBOOT_LEGACY_L2_RINGS      0x100UL
-	#define FUNC_QCFG_RESP_FLAGS_HOT_RESET_ALLOWED            0x200UL
-	#define FUNC_QCFG_RESP_FLAGS_PPP_PUSH_MODE_ENABLED        0x400UL
-	#define FUNC_QCFG_RESP_FLAGS_RING_MONITOR_ENABLED         0x800UL
-	#define FUNC_QCFG_RESP_FLAGS_FAST_RESET_ALLOWED           0x1000UL
-	#define FUNC_QCFG_RESP_FLAGS_MULTI_ROOT                   0x2000UL
-	#define FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV            0x4000UL
-	#define FUNC_QCFG_RESP_FLAGS_ROCE_VNIC_ID_VALID           0x8000UL
-	u8	mac_address[6];
-	__le16	pci_id;
-	__le16	alloc_rsscos_ctx;
-	__le16	alloc_cmpl_rings;
-	__le16	alloc_tx_rings;
-	__le16	alloc_rx_rings;
-	__le16	alloc_l2_ctx;
-	__le16	alloc_vnics;
-	__le16	admin_mtu;
-	__le16	mru;
-	__le16	stat_ctx_id;
-	u8	port_partition_type;
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_SPF     0x0UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_MPFS    0x1UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0 0x2UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5 0x3UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0 0x4UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2 0x5UL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN 0xffUL
-	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_LAST   FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN
-	u8	port_pf_cnt;
-	#define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL 0x0UL
-	#define FUNC_QCFG_RESP_PORT_PF_CNT_LAST   FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL
-	__le16	dflt_vnic_id;
-	__le16	max_mtu_configured;
-	__le32	min_bw;
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT              0
-	#define FUNC_QCFG_RESP_MIN_BW_SCALE                     0x10000000UL
-	#define FUNC_QCFG_RESP_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_QCFG_RESP_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_QCFG_RESP_MIN_BW_SCALE_LAST                 FUNC_QCFG_RESP_MIN_BW_SCALE_BYTES
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	max_bw;
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_SFT              0
-	#define FUNC_QCFG_RESP_MAX_BW_SCALE                     0x10000000UL
-	#define FUNC_QCFG_RESP_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_QCFG_RESP_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_QCFG_RESP_MAX_BW_SCALE_LAST                 FUNC_QCFG_RESP_MAX_BW_SCALE_BYTES
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	evb_mode;
-	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB 0x0UL
-	#define FUNC_QCFG_RESP_EVB_MODE_VEB    0x1UL
-	#define FUNC_QCFG_RESP_EVB_MODE_VEPA   0x2UL
-	#define FUNC_QCFG_RESP_EVB_MODE_LAST  FUNC_QCFG_RESP_EVB_MODE_VEPA
-	u8	options;
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT          0
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
-	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST          FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_SFT        2
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
-	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO
-	#define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK                   0xf0UL
-	#define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT                    4
-	__le16	alloc_vfs;
-	__le32	alloc_mcast_filters;
-	__le32	alloc_hw_ring_grps;
-	__le16	alloc_sp_tx_rings;
-	__le16	alloc_stat_ctx;
-	__le16	alloc_msix;
-	__le16	registered_vfs;
-	__le16	l2_doorbell_bar_size_kb;
-	u8	active_endpoints;
-	u8	always_1;
-	__le32	reset_addr_poll;
-	__le16	legacy_l2_db_size_kb;
-	__le16	svif_info;
-	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_MASK      0x7fffUL
-	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_SFT       0
-	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_VALID     0x8000UL
-	u8	mpc_chnls;
-	#define FUNC_QCFG_RESP_MPC_CHNLS_TCE_ENABLED         0x1UL
-	#define FUNC_QCFG_RESP_MPC_CHNLS_RCE_ENABLED         0x2UL
-	#define FUNC_QCFG_RESP_MPC_CHNLS_TE_CFA_ENABLED      0x4UL
-	#define FUNC_QCFG_RESP_MPC_CHNLS_RE_CFA_ENABLED      0x8UL
-	#define FUNC_QCFG_RESP_MPC_CHNLS_PRIMATE_ENABLED     0x10UL
-	u8	db_page_size;
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4KB   0x0UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_8KB   0x1UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_16KB  0x2UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_32KB  0x3UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_64KB  0x4UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_128KB 0x5UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_256KB 0x6UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_512KB 0x7UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_1MB   0x8UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_2MB   0x9UL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB   0xaUL
-	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_LAST FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB
-	__le16	roce_vnic_id;
-	__le32	partition_min_bw;
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_SFT              0
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE                     0x10000000UL
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_LAST                 FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100
-	__le32	partition_max_bw;
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_SFT              0
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE                     0x10000000UL
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_LAST                 FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
-	__le16	host_mtu;
-	__le16	flags2;
-	#define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED     0x1UL
-	__le16	stag_vid;
-	u8	port_kdnet_mode;
-	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL
-	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED  0x1UL
-	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_LAST    FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED
-	u8	kdnet_pcie_function;
-	__le16	port_kdnet_fid;
-	u8	unused_5;
-	u8	roce_bidi_opt_mode;
-	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DISABLED      0x1UL
-	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DEDICATED     0x2UL
-	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_SHARED        0x4UL
-	__le32	num_ktls_tx_key_ctxs;
-	__le32	num_ktls_rx_key_ctxs;
-	u8	lag_id;
-	u8	parif;
-	u8	fw_lag_id;
-	u8	unused_6;
-	__le32	num_quic_tx_key_ctxs;
-	__le32	num_quic_rx_key_ctxs;
-	__le32	roce_max_av_per_vf;
-	__le32	roce_max_cq_per_vf;
-	__le32	roce_max_mrw_per_vf;
-	__le32	roce_max_qp_per_vf;
-	__le32	roce_max_srq_per_vf;
-	__le32	roce_max_gid_per_vf;
-	__le16	xid_partition_cfg;
-	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_TX_CK     0x1UL
-	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_RX_CK     0x2UL
-	__le16	mirror_vnic_id;
-	u8	unused_7[7];
-	u8	valid;
-};
-
-/* hwrm_func_cfg_input (size:1280b/160B) */
-struct hwrm_func_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	__le16	num_msix;
-	__le32	flags;
-	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE     0x1UL
-	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE      0x2UL
-	#define FUNC_CFG_REQ_FLAGS_RSVD_MASK                      0x1fcUL
-	#define FUNC_CFG_REQ_FLAGS_RSVD_SFT                       2
-	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE        0x200UL
-	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE       0x400UL
-	#define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST               0x800UL
-	#define FUNC_CFG_REQ_FLAGS_NO_AUTOCLEAR_STATISTIC         0x1000UL
-	#define FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST                 0x2000UL
-	#define FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST                 0x4000UL
-	#define FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST               0x8000UL
-	#define FUNC_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST         0x10000UL
-	#define FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST           0x20000UL
-	#define FUNC_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST           0x40000UL
-	#define FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST               0x80000UL
-	#define FUNC_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST             0x100000UL
-	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE              0x200000UL
-	#define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC          0x400000UL
-	#define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST                 0x800000UL
-	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE             0x1000000UL
-	#define FUNC_CFG_REQ_FLAGS_PREBOOT_LEGACY_L2_RINGS        0x2000000UL
-	#define FUNC_CFG_REQ_FLAGS_HOT_RESET_IF_EN_DIS            0x4000000UL
-	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE           0x8000000UL
-	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE          0x10000000UL
-	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_ENABLE             0x20000000UL
-	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_DISABLE            0x40000000UL
-	__le32	enables;
-	#define FUNC_CFG_REQ_ENABLES_ADMIN_MTU                0x1UL
-	#define FUNC_CFG_REQ_ENABLES_MRU                      0x2UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS          0x4UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS           0x8UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS             0x10UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS             0x20UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS              0x40UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_VNICS                0x80UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS            0x100UL
-	#define FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR            0x200UL
-	#define FUNC_CFG_REQ_ENABLES_DFLT_VLAN                0x400UL
-	#define FUNC_CFG_REQ_ENABLES_DFLT_IP_ADDR             0x800UL
-	#define FUNC_CFG_REQ_ENABLES_MIN_BW                   0x1000UL
-	#define FUNC_CFG_REQ_ENABLES_MAX_BW                   0x2000UL
-	#define FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR           0x4000UL
-	#define FUNC_CFG_REQ_ENABLES_VLAN_ANTISPOOF_MODE      0x8000UL
-	#define FUNC_CFG_REQ_ENABLES_ALLOWED_VLAN_PRIS        0x10000UL
-	#define FUNC_CFG_REQ_ENABLES_EVB_MODE                 0x20000UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_MCAST_FILTERS        0x40000UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS         0x80000UL
-	#define FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE           0x100000UL
-	#define FUNC_CFG_REQ_ENABLES_NUM_MSIX                 0x200000UL
-	#define FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE         0x400000UL
-	#define FUNC_CFG_REQ_ENABLES_HOT_RESET_IF_SUPPORT     0x800000UL
-	#define FUNC_CFG_REQ_ENABLES_SCHQ_ID                  0x1000000UL
-	#define FUNC_CFG_REQ_ENABLES_MPC_CHNLS                0x2000000UL
-	#define FUNC_CFG_REQ_ENABLES_PARTITION_MIN_BW         0x4000000UL
-	#define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW         0x8000000UL
-	#define FUNC_CFG_REQ_ENABLES_TPID                     0x10000000UL
-	#define FUNC_CFG_REQ_ENABLES_HOST_MTU                 0x20000000UL
-	#define FUNC_CFG_REQ_ENABLES_KTLS_TX_KEY_CTXS         0x40000000UL
-	#define FUNC_CFG_REQ_ENABLES_KTLS_RX_KEY_CTXS         0x80000000UL
-	__le16	admin_mtu;
-	__le16	mru;
-	__le16	num_rsscos_ctxs;
-	__le16	num_cmpl_rings;
-	__le16	num_tx_rings;
-	__le16	num_rx_rings;
-	__le16	num_l2_ctxs;
-	__le16	num_vnics;
-	__le16	num_stat_ctxs;
-	__le16	num_hw_ring_grps;
-	u8	dflt_mac_addr[6];
-	__le16	dflt_vlan;
-	__be32	dflt_ip_addr[4];
-	__le32	min_bw;
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_SFT              0
-	#define FUNC_CFG_REQ_MIN_BW_SCALE                     0x10000000UL
-	#define FUNC_CFG_REQ_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_CFG_REQ_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_CFG_REQ_MIN_BW_SCALE_LAST                 FUNC_CFG_REQ_MIN_BW_SCALE_BYTES
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	max_bw;
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_SFT              0
-	#define FUNC_CFG_REQ_MAX_BW_SCALE                     0x10000000UL
-	#define FUNC_CFG_REQ_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_CFG_REQ_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_CFG_REQ_MAX_BW_SCALE_LAST                 FUNC_CFG_REQ_MAX_BW_SCALE_BYTES
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_INVALID
-	__le16	async_event_cr;
-	u8	vlan_antispoof_mode;
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_NOCHECK                 0x0UL
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_VALIDATE_VLAN           0x1UL
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_IF_VLANDNE       0x2UL
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN 0x3UL
-	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_LAST                   FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN
-	u8	allowed_vlan_pris;
-	u8	evb_mode;
-	#define FUNC_CFG_REQ_EVB_MODE_NO_EVB 0x0UL
-	#define FUNC_CFG_REQ_EVB_MODE_VEB    0x1UL
-	#define FUNC_CFG_REQ_EVB_MODE_VEPA   0x2UL
-	#define FUNC_CFG_REQ_EVB_MODE_LAST  FUNC_CFG_REQ_EVB_MODE_VEPA
-	u8	options;
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT          0
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
-	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST          FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_SFT        2
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
-	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO
-	#define FUNC_CFG_REQ_OPTIONS_RSVD_MASK                   0xf0UL
-	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT                    4
-	__le16	num_mcast_filters;
-	__le16	schq_id;
-	__le16	mpc_chnls;
-	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_ENABLE          0x1UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_DISABLE         0x2UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_ENABLE          0x4UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_DISABLE         0x8UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_ENABLE       0x10UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_DISABLE      0x20UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_ENABLE       0x40UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_DISABLE      0x80UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_ENABLE      0x100UL
-	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_DISABLE     0x200UL
-	__le32	partition_min_bw;
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_SFT              0
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE                     0x10000000UL
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_LAST                 FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100
-	__le32	partition_max_bw;
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_SFT              0
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE                     0x10000000UL
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_LAST                 FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
-	__be16	tpid;
-	__le16	host_mtu;
-	__le32	flags2;
-	#define FUNC_CFG_REQ_FLAGS2_KTLS_KEY_CTX_ASSETS_TEST     0x1UL
-	#define FUNC_CFG_REQ_FLAGS2_QUIC_KEY_CTX_ASSETS_TEST     0x2UL
-	__le32	enables2;
-	#define FUNC_CFG_REQ_ENABLES2_KDNET                    0x1UL
-	#define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE             0x2UL
-	#define FUNC_CFG_REQ_ENABLES2_QUIC_TX_KEY_CTXS         0x4UL
-	#define FUNC_CFG_REQ_ENABLES2_QUIC_RX_KEY_CTXS         0x8UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_AV_PER_VF       0x10UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_CQ_PER_VF       0x20UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_MRW_PER_VF      0x40UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_QP_PER_VF       0x80UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_SRQ_PER_VF      0x100UL
-	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_GID_PER_VF      0x200UL
-	#define FUNC_CFG_REQ_ENABLES2_XID_PARTITION_CFG        0x400UL
-	#define FUNC_CFG_REQ_ENABLES2_PHYSICAL_SLOT_NUMBER     0x800UL
-	u8	port_kdnet_mode;
-	#define FUNC_CFG_REQ_PORT_KDNET_MODE_DISABLED 0x0UL
-	#define FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED  0x1UL
-	#define FUNC_CFG_REQ_PORT_KDNET_MODE_LAST    FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED
-	u8	db_page_size;
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_4KB   0x0UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_8KB   0x1UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_16KB  0x2UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_32KB  0x3UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_64KB  0x4UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_128KB 0x5UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_256KB 0x6UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_512KB 0x7UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_1MB   0x8UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_2MB   0x9UL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_4MB   0xaUL
-	#define FUNC_CFG_REQ_DB_PAGE_SIZE_LAST FUNC_CFG_REQ_DB_PAGE_SIZE_4MB
-	__le16	physical_slot_number;
-	__le32	num_ktls_tx_key_ctxs;
-	__le32	num_ktls_rx_key_ctxs;
-	__le32	num_quic_tx_key_ctxs;
-	__le32	num_quic_rx_key_ctxs;
-	__le32	roce_max_av_per_vf;
-	__le32	roce_max_cq_per_vf;
-	__le32	roce_max_mrw_per_vf;
-	__le32	roce_max_qp_per_vf;
-	__le32	roce_max_srq_per_vf;
-	__le32	roce_max_gid_per_vf;
-	__le16	xid_partition_cfg;
-	#define FUNC_CFG_REQ_XID_PARTITION_CFG_TX_CK     0x1UL
-	#define FUNC_CFG_REQ_XID_PARTITION_CFG_RX_CK     0x2UL
-	__le16	unused_2;
-};
-
-/* hwrm_func_cfg_output (size:128b/16B) */
-struct hwrm_func_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_cfg_cmd_err (size:64b/8B) */
-struct hwrm_func_cfg_cmd_err {
-	u8	code;
-	#define FUNC_CFG_CMD_ERR_CODE_UNKNOWN                      0x0UL
-	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_RANGE       0x1UL
-	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_MORE_THAN_MAX  0x2UL
-	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_UNSUPPORTED 0x3UL
-	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT         0x4UL
-	#define FUNC_CFG_CMD_ERR_CODE_LAST                        FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT
-	u8	unused_0[7];
-};
-
-/* hwrm_func_qstats_input (size:192b/24B) */
-struct hwrm_func_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	flags;
-	#define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY        0x1UL
-	#define FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK     0x2UL
-	#define FUNC_QSTATS_REQ_FLAGS_L2_ONLY          0x4UL
-	u8	unused_0[5];
-};
-
-/* hwrm_func_qstats_output (size:1408b/176B) */
-struct hwrm_func_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_drop_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_drop_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	rx_agg_pkts;
-	__le64	rx_agg_bytes;
-	__le64	rx_agg_events;
-	__le64	rx_agg_aborts;
-	u8	clear_seq;
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_func_qstats_ext_input (size:256b/32B) */
-struct hwrm_func_qstats_ext_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	flags;
-	#define FUNC_QSTATS_EXT_REQ_FLAGS_ROCE_ONLY        0x1UL
-	#define FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK     0x2UL
-	u8	unused_0[1];
-	__le32	enables;
-	#define FUNC_QSTATS_EXT_REQ_ENABLES_SCHQ_ID     0x1UL
-	__le16	schq_id;
-	__le16	traffic_class;
-	u8	unused_1[4];
-};
-
-/* hwrm_func_qstats_ext_output (size:1536b/192B) */
-struct hwrm_func_qstats_ext_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_tpa_eligible_pkt;
-	__le64	rx_tpa_eligible_bytes;
-	__le64	rx_tpa_pkt;
-	__le64	rx_tpa_bytes;
-	__le64	rx_tpa_errors;
-	__le64	rx_tpa_events;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_clr_stats_input (size:192b/24B) */
-struct hwrm_func_clr_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_clr_stats_output (size:128b/16B) */
-struct hwrm_func_clr_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_vf_resc_free_input (size:192b/24B) */
-struct hwrm_func_vf_resc_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vf_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_vf_resc_free_output (size:128b/16B) */
-struct hwrm_func_vf_resc_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_drv_rgtr_input (size:896b/112B) */
-struct hwrm_func_drv_rgtr_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_ALL_MODE                     0x1UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_NONE_MODE                    0x2UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE                   0x4UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE           0x8UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT                0x10UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT           0x20UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT                   0x40UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT               0x80UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT     0x100UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT                 0x200UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_ASYM_QUEUE_CFG_SUPPORT           0x400UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_INGRESS_NIC_FLOW_MODE         0x800UL
-	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_EGRESS_NIC_FLOW_MODE          0x1000UL
-	__le32	enables;
-	#define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE             0x1UL
-	#define FUNC_DRV_RGTR_REQ_ENABLES_VER                 0x2UL
-	#define FUNC_DRV_RGTR_REQ_ENABLES_TIMESTAMP           0x4UL
-	#define FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD          0x8UL
-	#define FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD     0x10UL
-	__le16	os_type;
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_UNKNOWN   0x0UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_OTHER     0x1UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_MSDOS     0xeUL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WINDOWS   0x12UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_SOLARIS   0x1dUL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX     0x24UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_FREEBSD   0x2aUL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_ESXI      0x68UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN864    0x73UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN2012R2 0x74UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI      0x8000UL
-	#define FUNC_DRV_RGTR_REQ_OS_TYPE_LAST     FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI
-	u8	ver_maj_8b;
-	u8	ver_min_8b;
-	u8	ver_upd_8b;
-	u8	unused_0[3];
-	__le32	timestamp;
-	u8	unused_1[4];
-	__le32	vf_req_fwd[8];
-	__le32	async_event_fwd[8];
-	__le16	ver_maj;
-	__le16	ver_min;
-	__le16	ver_upd;
-	__le16	ver_patch;
-};
-
-/* hwrm_func_drv_rgtr_output (size:128b/16B) */
-struct hwrm_func_drv_rgtr_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED     0x1UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_func_drv_unrgtr_input (size:192b/24B) */
-struct hwrm_func_drv_unrgtr_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_DRV_UNRGTR_REQ_FLAGS_PREPARE_FOR_SHUTDOWN     0x1UL
-	u8	unused_0[4];
-};
-
-/* hwrm_func_drv_unrgtr_output (size:128b/16B) */
-struct hwrm_func_drv_unrgtr_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_buf_rgtr_input (size:1024b/128B) */
-struct hwrm_func_buf_rgtr_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_BUF_RGTR_REQ_ENABLES_VF_ID            0x1UL
-	#define FUNC_BUF_RGTR_REQ_ENABLES_ERR_BUF_ADDR     0x2UL
-	__le16	vf_id;
-	__le16	req_buf_num_pages;
-	__le16	req_buf_page_size;
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_16B 0x4UL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4K  0xcUL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_8K  0xdUL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_64K 0x10UL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_2M  0x15UL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4M  0x16UL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G  0x1eUL
-	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_LAST FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G
-	__le16	req_buf_len;
-	__le16	resp_buf_len;
-	u8	unused_0[2];
-	__le64	req_buf_page_addr0;
-	__le64	req_buf_page_addr1;
-	__le64	req_buf_page_addr2;
-	__le64	req_buf_page_addr3;
-	__le64	req_buf_page_addr4;
-	__le64	req_buf_page_addr5;
-	__le64	req_buf_page_addr6;
-	__le64	req_buf_page_addr7;
-	__le64	req_buf_page_addr8;
-	__le64	req_buf_page_addr9;
-	__le64	error_buf_addr;
-	__le64	resp_buf_addr;
-};
-
-/* hwrm_func_buf_rgtr_output (size:128b/16B) */
-struct hwrm_func_buf_rgtr_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_drv_qver_input (size:192b/24B) */
-struct hwrm_func_drv_qver_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	reserved;
-	__le16	fid;
-	u8	driver_type;
-	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_L2   0x0UL
-	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_ROCE 0x1UL
-	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_LAST FUNC_DRV_QVER_REQ_DRIVER_TYPE_ROCE
-	u8	unused_0;
-};
-
-/* hwrm_func_drv_qver_output (size:256b/32B) */
-struct hwrm_func_drv_qver_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	os_type;
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_UNKNOWN   0x0UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_OTHER     0x1UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_MSDOS     0xeUL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_WINDOWS   0x12UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_SOLARIS   0x1dUL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_LINUX     0x24UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_FREEBSD   0x2aUL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_ESXI      0x68UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_WIN864    0x73UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_WIN2012R2 0x74UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_UEFI      0x8000UL
-	#define FUNC_DRV_QVER_RESP_OS_TYPE_LAST     FUNC_DRV_QVER_RESP_OS_TYPE_UEFI
-	u8	ver_maj_8b;
-	u8	ver_min_8b;
-	u8	ver_upd_8b;
-	u8	unused_0[3];
-	__le16	ver_maj;
-	__le16	ver_min;
-	__le16	ver_upd;
-	__le16	ver_patch;
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* hwrm_func_resource_qcaps_input (size:192b/24B) */
-struct hwrm_func_resource_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_func_resource_qcaps_output (size:704b/88B) */
-struct hwrm_func_resource_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	max_vfs;
-	__le16	max_msix;
-	__le16	vf_reservation_strategy;
-	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MAXIMAL        0x0UL
-	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL        0x1UL
-	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL_STATIC 0x2UL
-	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_LAST          FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL_STATIC
-	__le16	min_rsscos_ctx;
-	__le16	max_rsscos_ctx;
-	__le16	min_cmpl_rings;
-	__le16	max_cmpl_rings;
-	__le16	min_tx_rings;
-	__le16	max_tx_rings;
-	__le16	min_rx_rings;
-	__le16	max_rx_rings;
-	__le16	min_l2_ctxs;
-	__le16	max_l2_ctxs;
-	__le16	min_vnics;
-	__le16	max_vnics;
-	__le16	min_stat_ctx;
-	__le16	max_stat_ctx;
-	__le16	min_hw_ring_grps;
-	__le16	max_hw_ring_grps;
-	__le16	max_tx_scheduler_inputs;
-	__le16	flags;
-	#define FUNC_RESOURCE_QCAPS_RESP_FLAGS_MIN_GUARANTEED     0x1UL
-	__le16	min_msix;
-	__le32	min_ktls_tx_key_ctxs;
-	__le32	max_ktls_tx_key_ctxs;
-	__le32	min_ktls_rx_key_ctxs;
-	__le32	max_ktls_rx_key_ctxs;
-	__le32	min_quic_tx_key_ctxs;
-	__le32	max_quic_tx_key_ctxs;
-	__le32	min_quic_rx_key_ctxs;
-	__le32	max_quic_rx_key_ctxs;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_func_vf_resource_cfg_input (size:704b/88B) */
-struct hwrm_func_vf_resource_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vf_id;
-	__le16	max_msix;
-	__le16	min_rsscos_ctx;
-	__le16	max_rsscos_ctx;
-	__le16	min_cmpl_rings;
-	__le16	max_cmpl_rings;
-	__le16	min_tx_rings;
-	__le16	max_tx_rings;
-	__le16	min_rx_rings;
-	__le16	max_rx_rings;
-	__le16	min_l2_ctxs;
-	__le16	max_l2_ctxs;
-	__le16	min_vnics;
-	__le16	max_vnics;
-	__le16	min_stat_ctx;
-	__le16	max_stat_ctx;
-	__le16	min_hw_ring_grps;
-	__le16	max_hw_ring_grps;
-	__le16	flags;
-	#define FUNC_VF_RESOURCE_CFG_REQ_FLAGS_MIN_GUARANTEED     0x1UL
-	__le16	min_msix;
-	__le32	min_ktls_tx_key_ctxs;
-	__le32	max_ktls_tx_key_ctxs;
-	__le32	min_ktls_rx_key_ctxs;
-	__le32	max_ktls_rx_key_ctxs;
-	__le32	min_quic_tx_key_ctxs;
-	__le32	max_quic_tx_key_ctxs;
-	__le32	min_quic_rx_key_ctxs;
-	__le32	max_quic_rx_key_ctxs;
-};
-
-/* hwrm_func_vf_resource_cfg_output (size:384b/48B) */
-struct hwrm_func_vf_resource_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	reserved_rsscos_ctx;
-	__le16	reserved_cmpl_rings;
-	__le16	reserved_tx_rings;
-	__le16	reserved_rx_rings;
-	__le16	reserved_l2_ctxs;
-	__le16	reserved_vnics;
-	__le16	reserved_stat_ctx;
-	__le16	reserved_hw_ring_grps;
-	__le32	reserved_ktls_tx_key_ctxs;
-	__le32	reserved_ktls_rx_key_ctxs;
-	__le32	reserved_quic_tx_key_ctxs;
-	__le32	reserved_quic_rx_key_ctxs;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_backing_store_qcaps_input (size:128b/16B) */
-struct hwrm_func_backing_store_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_func_backing_store_qcaps_output (size:832b/104B) */
-struct hwrm_func_backing_store_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	qp_max_entries;
-	__le16	qp_min_qp1_entries;
-	__le16	qp_max_l2_entries;
-	__le16	qp_entry_size;
-	__le16	srq_max_l2_entries;
-	__le32	srq_max_entries;
-	__le16	srq_entry_size;
-	__le16	cq_max_l2_entries;
-	__le32	cq_max_entries;
-	__le16	cq_entry_size;
-	__le16	vnic_max_vnic_entries;
-	__le16	vnic_max_ring_table_entries;
-	__le16	vnic_entry_size;
-	__le32	stat_max_entries;
-	__le16	stat_entry_size;
-	__le16	tqm_entry_size;
-	__le32	tqm_min_entries_per_ring;
-	__le32	tqm_max_entries_per_ring;
-	__le32	mrav_max_entries;
-	__le16	mrav_entry_size;
-	__le16	tim_entry_size;
-	__le32	tim_max_entries;
-	__le16	mrav_num_entries_units;
-	u8	tqm_entries_multiple;
-	u8	ctx_kind_initializer;
-	__le16	ctx_init_mask;
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_QP       0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_SRQ      0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_CQ       0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_VNIC     0x8UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_STAT     0x10UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_MRAV     0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_TKC      0x40UL
-	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_RKC      0x80UL
-	u8	qp_init_offset;
-	u8	srq_init_offset;
-	u8	cq_init_offset;
-	u8	vnic_init_offset;
-	u8	tqm_fp_rings_count;
-	u8	stat_init_offset;
-	u8	mrav_init_offset;
-	u8	tqm_fp_rings_count_ext;
-	u8	tkc_init_offset;
-	u8	rkc_init_offset;
-	__le16	tkc_entry_size;
-	__le16	rkc_entry_size;
-	__le32	tkc_max_entries;
-	__le32	rkc_max_entries;
-	__le16	fast_qpmd_qp_num_entries;
-	u8	rsvd1[5];
-	u8	valid;
-};
-
-/* tqm_fp_ring_cfg (size:128b/16B) */
-struct tqm_fp_ring_cfg {
-	u8	tqm_ring_pg_size_tqm_ring_lvl;
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_MASK      0xfUL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_SFT       0
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_0       0x0UL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_1       0x1UL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_2       0x2UL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LAST       TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_2
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_MASK  0xf0UL
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_SFT   4
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_LAST   TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_1G
-	u8	unused[3];
-	__le32	tqm_ring_num_entries;
-	__le64	tqm_ring_page_dir;
-};
-
-/* hwrm_func_backing_store_cfg_input (size:2688b/336B) */
-struct hwrm_func_backing_store_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE               0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT     0x2UL
-	__le32	enables;
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP               0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ              0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ               0x4UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC             0x8UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT             0x10UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP           0x20UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING0        0x40UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING1        0x80UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING2        0x100UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING3        0x200UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING4        0x400UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING5        0x800UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING6        0x1000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING7        0x2000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV             0x4000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM              0x8000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING8        0x10000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING9        0x20000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING10       0x40000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TKC              0x80000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_RKC              0x100000UL
-	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD     0x200000UL
-	u8	qpc_pg_size_qpc_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G
-	u8	srq_pg_size_srq_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G
-	u8	cq_pg_size_cq_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G
-	u8	vnic_pg_size_vnic_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G
-	u8	stat_pg_size_stat_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G
-	u8	tqm_sp_pg_size_tqm_sp_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G
-	u8	tqm_ring0_pg_size_tqm_ring0_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G
-	u8	tqm_ring1_pg_size_tqm_ring1_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G
-	u8	tqm_ring2_pg_size_tqm_ring2_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G
-	u8	tqm_ring3_pg_size_tqm_ring3_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G
-	u8	tqm_ring4_pg_size_tqm_ring4_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G
-	u8	tqm_ring5_pg_size_tqm_ring5_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G
-	u8	tqm_ring6_pg_size_tqm_ring6_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G
-	u8	tqm_ring7_pg_size_tqm_ring7_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G
-	u8	mrav_pg_size_mrav_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G
-	u8	tim_pg_size_tim_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G
-	__le64	qpc_page_dir;
-	__le64	srq_page_dir;
-	__le64	cq_page_dir;
-	__le64	vnic_page_dir;
-	__le64	stat_page_dir;
-	__le64	tqm_sp_page_dir;
-	__le64	tqm_ring0_page_dir;
-	__le64	tqm_ring1_page_dir;
-	__le64	tqm_ring2_page_dir;
-	__le64	tqm_ring3_page_dir;
-	__le64	tqm_ring4_page_dir;
-	__le64	tqm_ring5_page_dir;
-	__le64	tqm_ring6_page_dir;
-	__le64	tqm_ring7_page_dir;
-	__le64	mrav_page_dir;
-	__le64	tim_page_dir;
-	__le32	qp_num_entries;
-	__le32	srq_num_entries;
-	__le32	cq_num_entries;
-	__le32	stat_num_entries;
-	__le32	tqm_sp_num_entries;
-	__le32	tqm_ring0_num_entries;
-	__le32	tqm_ring1_num_entries;
-	__le32	tqm_ring2_num_entries;
-	__le32	tqm_ring3_num_entries;
-	__le32	tqm_ring4_num_entries;
-	__le32	tqm_ring5_num_entries;
-	__le32	tqm_ring6_num_entries;
-	__le32	tqm_ring7_num_entries;
-	__le32	mrav_num_entries;
-	__le32	tim_num_entries;
-	__le16	qp_num_qp1_entries;
-	__le16	qp_num_l2_entries;
-	__le16	qp_entry_size;
-	__le16	srq_num_l2_entries;
-	__le16	srq_entry_size;
-	__le16	cq_num_l2_entries;
-	__le16	cq_entry_size;
-	__le16	vnic_num_vnic_entries;
-	__le16	vnic_num_ring_table_entries;
-	__le16	vnic_entry_size;
-	__le16	stat_entry_size;
-	__le16	tqm_entry_size;
-	__le16	mrav_entry_size;
-	__le16	tim_entry_size;
-	u8	tqm_ring8_pg_size_tqm_ring_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_1G
-	u8	ring8_unused[3];
-	__le32	tqm_ring8_num_entries;
-	__le64	tqm_ring8_page_dir;
-	u8	tqm_ring9_pg_size_tqm_ring_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_1G
-	u8	ring9_unused[3];
-	__le32	tqm_ring9_num_entries;
-	__le64	tqm_ring9_page_dir;
-	u8	tqm_ring10_pg_size_tqm_ring_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_1G
-	u8	ring10_unused[3];
-	__le32	tqm_ring10_num_entries;
-	__le64	tqm_ring10_page_dir;
-	__le32	tkc_num_entries;
-	__le32	rkc_num_entries;
-	__le64	tkc_page_dir;
-	__le64	rkc_page_dir;
-	__le16	tkc_entry_size;
-	__le16	rkc_entry_size;
-	u8	tkc_pg_size_tkc_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G
-	u8	rkc_pg_size_rkc_lvl;
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_MASK      0xfUL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_SFT       0
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_0       0x0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_1       0x1UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2       0x2UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G
-	__le16	qp_num_fast_qpmd_entries;
-};
-
-/* hwrm_func_backing_store_cfg_output (size:128b/16B) */
-struct hwrm_func_backing_store_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_error_recovery_qcfg_input (size:192b/24B) */
-struct hwrm_error_recovery_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	unused_0[8];
-};
-
-/* hwrm_error_recovery_qcfg_output (size:1664b/208B) */
-struct hwrm_error_recovery_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU     0x2UL
-	__le32	driver_polling_freq;
-	__le32	master_func_wait_period;
-	__le32	normal_func_wait_period;
-	__le32	master_func_wait_period_after_reset;
-	__le32	max_bailout_time_after_reset;
-	__le32	fw_health_status_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SFT           2
-	__le32	fw_heartbeat_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SFT           2
-	__le32	fw_reset_cnt_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SFT           2
-	__le32	reset_inprogress_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SFT           2
-	__le32	reset_inprogress_reg_mask;
-	u8	unused_0[3];
-	u8	reg_array_cnt;
-	__le32	reset_reg[16];
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SFT           2
-	__le32	reset_reg_val[16];
-	u8	delay_after_reset[16];
-	__le32	err_recovery_cnt_reg;
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_MASK    0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_SFT     0
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_GRC       0x1UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR0      0x2UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1      0x3UL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_MASK          0xfffffffcUL
-	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SFT           2
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_func_echo_response_input (size:192b/24B) */
-struct hwrm_func_echo_response_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	event_data1;
-	__le32	event_data2;
-};
-
-/* hwrm_func_echo_response_output (size:128b/16B) */
-struct hwrm_func_echo_response_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_pin_qcfg_input (size:192b/24B) */
-struct hwrm_func_ptp_pin_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	unused_0[8];
-};
-
-/* hwrm_func_ptp_pin_qcfg_output (size:128b/16B) */
-struct hwrm_func_ptp_pin_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_pins;
-	u8	state;
-	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN0_ENABLED     0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN1_ENABLED     0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN2_ENABLED     0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN3_ENABLED     0x8UL
-	u8	pin0_usage;
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_NONE     0x0UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_IN   0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_OUT  0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_IN  0x3UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT 0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_LAST    FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT
-	u8	pin1_usage;
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_NONE     0x0UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_IN   0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_OUT  0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_IN  0x3UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT 0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_LAST    FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT
-	u8	pin2_usage;
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_NONE                      0x0UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_IN                    0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_OUT                   0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_IN                   0x3UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT                  0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_LAST                     FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT
-	u8	pin3_usage;
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_NONE                      0x0UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_IN                    0x1UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_OUT                   0x2UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_IN                   0x3UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT                  0x4UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
-	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_LAST                     FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_func_ptp_pin_cfg_input (size:256b/32B) */
-struct hwrm_func_ptp_pin_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_STATE     0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_USAGE     0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_STATE     0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_USAGE     0x8UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_STATE     0x10UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_USAGE     0x20UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_STATE     0x40UL
-	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_USAGE     0x80UL
-	u8	pin0_state;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_DISABLED 0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED  0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED
-	u8	pin0_usage;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_NONE     0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_IN   0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_OUT  0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_IN  0x3UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT 0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT
-	u8	pin1_state;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_DISABLED 0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED  0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED
-	u8	pin1_usage;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_NONE     0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_IN   0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_OUT  0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_IN  0x3UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT 0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT
-	u8	pin2_state;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_DISABLED 0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED  0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED
-	u8	pin2_usage;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_NONE                      0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_IN                    0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_OUT                   0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_IN                   0x3UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT                  0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_LAST                     FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT
-	u8	pin3_state;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_DISABLED 0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED  0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED
-	u8	pin3_usage;
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_NONE                      0x0UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_IN                    0x1UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_OUT                   0x2UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_IN                   0x3UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT                  0x4UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
-	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_LAST                     FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT
-	u8	unused_0[4];
-};
-
-/* hwrm_func_ptp_pin_cfg_output (size:128b/16B) */
-struct hwrm_func_ptp_pin_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_cfg_input (size:384b/48B) */
-struct hwrm_func_ptp_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	enables;
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_PPS_EVENT               0x1UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_SOURCE     0x2UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_PHASE      0x4UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD     0x8UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP         0x10UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE      0x20UL
-	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME                0x40UL
-	u8	ptp_pps_event;
-	#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_INTERNAL     0x1UL
-	#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_EXTERNAL     0x2UL
-	u8	ptp_freq_adj_dll_source;
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_NONE    0x0UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_0  0x1UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_1  0x2UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_2  0x3UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_3  0x4UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_0  0x5UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_1  0x6UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_2  0x7UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_3  0x8UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID 0xffUL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_LAST   FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID
-	u8	ptp_freq_adj_dll_phase;
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_NONE 0x0UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_4K   0x1UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_8K   0x2UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M  0x3UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M  0x4UL
-	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M
-	u8	unused_0[3];
-	__le32	ptp_freq_adj_ext_period;
-	__le32	ptp_freq_adj_ext_up;
-	__le32	ptp_freq_adj_ext_phase_lower;
-	__le32	ptp_freq_adj_ext_phase_upper;
-	__le64	ptp_set_time;
-};
-
-/* hwrm_func_ptp_cfg_output (size:128b/16B) */
-struct hwrm_func_ptp_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_ts_query_input (size:192b/24B) */
-struct hwrm_func_ptp_ts_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_PTP_TS_QUERY_REQ_FLAGS_PPS_TIME     0x1UL
-	#define FUNC_PTP_TS_QUERY_REQ_FLAGS_PTM_TIME     0x2UL
-	u8	unused_0[4];
-};
-
-/* hwrm_func_ptp_ts_query_output (size:320b/40B) */
-struct hwrm_func_ptp_ts_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	pps_event_ts;
-	__le64	ptm_local_ts;
-	__le64	ptm_system_ts;
-	__le32	ptm_link_delay;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_ext_cfg_input (size:256b/32B) */
-struct hwrm_func_ptp_ext_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	enables;
-	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_MASTER_FID     0x1UL
-	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_FID        0x2UL
-	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_MODE       0x4UL
-	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_FAILOVER_TIMER     0x8UL
-	__le16	phc_master_fid;
-	__le16	phc_sec_fid;
-	u8	phc_sec_mode;
-	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_SWITCH  0x0UL
-	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_ALL     0x1UL
-	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY 0x2UL
-	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_LAST   FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY
-	u8	unused_0;
-	__le32	failover_timer;
-	u8	unused_1[4];
-};
-
-/* hwrm_func_ptp_ext_cfg_output (size:128b/16B) */
-struct hwrm_func_ptp_ext_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_ptp_ext_qcfg_input (size:192b/24B) */
-struct hwrm_func_ptp_ext_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	unused_0[8];
-};
-
-/* hwrm_func_ptp_ext_qcfg_output (size:256b/32B) */
-struct hwrm_func_ptp_ext_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	phc_master_fid;
-	__le16	phc_sec_fid;
-	__le16	phc_active_fid0;
-	__le16	phc_active_fid1;
-	__le32	last_failover_event;
-	__le16	from_fid;
-	__le16	to_fid;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_func_backing_store_cfg_v2_input (size:512b/64B) */
-struct hwrm_func_backing_store_cfg_v2_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	type;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION       0x1dUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
-	__le16	instance;
-	__le32	flags;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE        0x1UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_CFG_ALL_DONE     0x2UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_EXTEND           0x4UL
-	__le64	page_dir;
-	__le32	num_entries;
-	__le16	entry_size;
-	u8	page_size_pbl_level;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_MASK  0xfUL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_SFT   0
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_0   0x0UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_1   0x1UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2   0x2UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LAST   FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_LAST   FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G
-	u8	subtype_valid_cnt;
-	__le32	split_entry_0;
-	__le32	split_entry_1;
-	__le32	split_entry_2;
-	__le32	split_entry_3;
-	__le32	enables;
-	#define FUNC_BACKING_STORE_CFG_V2_REQ_ENABLES_NEXT_BS_OFFSET     0x1UL
-	__le32	next_bs_offset;
-};
-
-/* hwrm_func_backing_store_cfg_v2_output (size:128b/16B) */
-struct hwrm_func_backing_store_cfg_v2_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	rsvd0[7];
-	u8	valid;
-};
-
-/* hwrm_func_backing_store_qcfg_v2_input (size:192b/24B) */
-struct hwrm_func_backing_store_qcfg_v2_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	type;
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_XID_PARTITION_TABLE 0x1dUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
-	__le16	instance;
-	u8	rsvd[4];
-};
-
-/* hwrm_func_backing_store_qcfg_v2_output (size:448b/56B) */
-struct hwrm_func_backing_store_qcfg_v2_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	type;
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION       0x1dUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
-	__le16	instance;
-	__le32	flags;
-	__le64	page_dir;
-	__le32	num_entries;
-	u8	page_size_pbl_level;
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_MASK  0xfUL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_SFT   0
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_0   0x0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_1   0x1UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2   0x2UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LAST   FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_MASK  0xf0UL
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_SFT   4
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_4K   (0x0UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8K   (0x1UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_64K  (0x2UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_2M   (0x3UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8M   (0x4UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G   (0x5UL << 4)
-	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_LAST   FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G
-	u8	subtype_valid_cnt;
-	u8	rsvd[2];
-	__le32	split_entry_0;
-	__le32	split_entry_1;
-	__le32	split_entry_2;
-	__le32	split_entry_3;
-	u8	rsvd2[7];
-	u8	valid;
-};
-
-/* qpc_split_entries (size:128b/16B) */
-struct qpc_split_entries {
-	__le32	qp_num_l2_entries;
-	__le32	qp_num_qp1_entries;
-	__le32	qp_num_fast_qpmd_entries;
-	__le32	rsvd;
-};
-
-/* srq_split_entries (size:128b/16B) */
-struct srq_split_entries {
-	__le32	srq_num_l2_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* cq_split_entries (size:128b/16B) */
-struct cq_split_entries {
-	__le32	cq_num_l2_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* vnic_split_entries (size:128b/16B) */
-struct vnic_split_entries {
-	__le32	vnic_num_vnic_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* mrav_split_entries (size:128b/16B) */
-struct mrav_split_entries {
-	__le32	mrav_num_av_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* ts_split_entries (size:128b/16B) */
-struct ts_split_entries {
-	__le32	region_num_entries;
-	u8	tsid;
-	u8	lkup_static_bkt_cnt_exp[2];
-	u8	locked;
-	__le32	rsvd2[2];
-};
-
-/* ck_split_entries (size:128b/16B) */
-struct ck_split_entries {
-	__le32	num_quic_entries;
-	__le32	rsvd;
-	__le32	rsvd2[2];
-};
-
-/* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */
-struct hwrm_func_backing_store_qcaps_v2_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	type;
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION       0x1dUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
-	u8	rsvd[6];
-};
-
-/* hwrm_func_backing_store_qcaps_v2_output (size:448b/56B) */
-struct hwrm_func_backing_store_qcaps_v2_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	type;
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP                  0x0UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ                 0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ                  0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC                0x3UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT                0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING         0x5UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING         0x6UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV                0xeUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM                 0xfUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK               0x13UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK               0x14UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING         0x15UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW        0x16UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW        0x17UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW       0x18UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW        0x19UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION       0x1dUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE           0x1eUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE           0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE          0x21UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA0_TRACE           0x26UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA1_TRACE           0x27UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA2_TRACE           0x28UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID             0xffffUL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
-	__le16	entry_size;
-	__le32	flags;
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT            0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID                      0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_DRIVER_MANAGED_MEMORY           0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ROCE_QP_PSEUDO_STATIC_ALLOC     0x8UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_DBG_TRACE                    0x10UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_BIN_DBG_TRACE                0x20UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_NEXT_BS_OFFSET                  0x40UL
-	__le32	instance_bit_map;
-	u8	ctx_init_value;
-	u8	ctx_init_offset;
-	u8	entry_multiple;
-	u8	rsvd;
-	__le32	max_num_entries;
-	__le32	min_num_entries;
-	__le16	next_valid_type;
-	u8	subtype_valid_cnt;
-	u8	exact_cnt_bit_map;
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_0_EXACT     0x1UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_1_EXACT     0x2UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_2_EXACT     0x4UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_3_EXACT     0x8UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_UNUSED_MASK             0xf0UL
-	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_UNUSED_SFT              4
-	__le32	split_entry_0;
-	__le32	split_entry_1;
-	__le32	split_entry_2;
-	__le32	split_entry_3;
-	__le16	max_instance_count;
-	u8	rsvd3;
-	u8	valid;
-};
-
-/* hwrm_func_dbr_pacing_qcfg_input (size:128b/16B) */
-struct hwrm_func_dbr_pacing_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_func_dbr_pacing_qcfg_output (size:512b/64B) */
-struct hwrm_func_dbr_pacing_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define FUNC_DBR_PACING_QCFG_RESP_FLAGS_DBR_NQ_EVENT_ENABLED     0x1UL
-	u8	unused_0[7];
-	__le32	dbr_stat_db_fifo_reg;
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_MASK    0x3UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_SFT     0
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_GRC       0x1UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR0      0x2UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1      0x3UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_MASK          0xfffffffcUL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SFT           2
-	__le32	dbr_stat_db_fifo_reg_watermark_mask;
-	u8	dbr_stat_db_fifo_reg_watermark_shift;
-	u8	unused_1[3];
-	__le32	dbr_stat_db_fifo_reg_fifo_room_mask;
-	u8	dbr_stat_db_fifo_reg_fifo_room_shift;
-	u8	unused_2[3];
-	__le32	dbr_throttling_aeq_arm_reg;
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_MASK    0x3UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_SFT     0
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_GRC       0x1UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR0      0x2UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1      0x3UL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_MASK          0xfffffffcUL
-	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SFT           2
-	u8	dbr_throttling_aeq_arm_reg_val;
-	u8	unused_3[3];
-	__le32	dbr_stat_db_max_fifo_depth;
-	__le32	primary_nq_id;
-	__le32	pacing_threshold;
-	u8	unused_4[7];
-	u8	valid;
-};
-
-/* hwrm_func_drv_if_change_input (size:192b/24B) */
-struct hwrm_func_drv_if_change_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP     0x1UL
-	__le32	unused;
-};
-
-/* hwrm_func_drv_if_change_output (size:128b/16B) */
-struct hwrm_func_drv_if_change_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE           0x1UL
-	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE     0x2UL
-	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE           0x4UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_port_phy_cfg_input (size:512b/64B) */
-struct hwrm_port_phy_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY                  0x1UL
-	#define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED                 0x2UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FORCE                      0x4UL
-	#define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG            0x8UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE                 0x10UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE                0x20UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE          0x40UL
-	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE         0x80UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE         0x100UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE        0x200UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE        0x400UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE       0x800UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE        0x1000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE       0x2000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN             0x4000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_ENABLE       0x8000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_DISABLE      0x10000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_ENABLE      0x20000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_DISABLE     0x40000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_ENABLE       0x80000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_DISABLE      0x100000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_ENABLE      0x200000UL
-	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_DISABLE     0x400000UL
-	__le32	enables;
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE                     0x1UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX                   0x2UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE                    0x4UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED               0x8UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK          0x10UL
-	#define PORT_PHY_CFG_REQ_ENABLES_WIRESPEED                     0x20UL
-	#define PORT_PHY_CFG_REQ_ENABLES_LPBK                          0x40UL
-	#define PORT_PHY_CFG_REQ_ENABLES_PREEMPHASIS                   0x80UL
-	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAUSE                   0x100UL
-	#define PORT_PHY_CFG_REQ_ENABLES_EEE_LINK_SPEED_MASK           0x200UL
-	#define PORT_PHY_CFG_REQ_ENABLES_TX_LPI_TIMER                  0x400UL
-	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED         0x800UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK     0x1000UL
-	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2            0x2000UL
-	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK        0x4000UL
-	__le16	port_id;
-	__le16	force_link_speed;
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB
-	u8	auto_mode;
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_NONE         0x0UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_ALL_SPEEDS   0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_ONE_SPEED    0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_ONE_OR_BELOW 0x3UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK   0x4UL
-	#define PORT_PHY_CFG_REQ_AUTO_MODE_LAST        PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK
-	u8	auto_duplex;
-	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_HALF 0x0UL
-	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_FULL 0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_BOTH 0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_LAST PORT_PHY_CFG_REQ_AUTO_DUPLEX_BOTH
-	u8	auto_pause;
-	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_TX                0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_RX                0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
-	u8	mgmt_flag;
-	#define PORT_PHY_CFG_REQ_MGMT_FLAG_LINK_RELEASE     0x1UL
-	#define PORT_PHY_CFG_REQ_MGMT_FLAG_MGMT_VALID       0x80UL
-	__le16	auto_link_speed;
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_LAST PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB
-	__le16	auto_link_speed_mask;
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100MBHD     0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100MB       0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_1GBHD       0x4UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_1GB         0x8UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_2GB         0x10UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_2_5GB       0x20UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10GB        0x40UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_20GB        0x80UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_25GB        0x100UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_40GB        0x200UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_50GB        0x400UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100GB       0x800UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MBHD      0x1000UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MB        0x2000UL
-	u8	wirespeed;
-	#define PORT_PHY_CFG_REQ_WIRESPEED_OFF 0x0UL
-	#define PORT_PHY_CFG_REQ_WIRESPEED_ON  0x1UL
-	#define PORT_PHY_CFG_REQ_WIRESPEED_LAST PORT_PHY_CFG_REQ_WIRESPEED_ON
-	u8	lpbk;
-	#define PORT_PHY_CFG_REQ_LPBK_NONE     0x0UL
-	#define PORT_PHY_CFG_REQ_LPBK_LOCAL    0x1UL
-	#define PORT_PHY_CFG_REQ_LPBK_REMOTE   0x2UL
-	#define PORT_PHY_CFG_REQ_LPBK_EXTERNAL 0x3UL
-	#define PORT_PHY_CFG_REQ_LPBK_LAST    PORT_PHY_CFG_REQ_LPBK_EXTERNAL
-	u8	force_pause;
-	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_TX     0x1UL
-	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_RX     0x2UL
-	u8	unused_1;
-	__le32	preemphasis;
-	__le16	eee_link_speed_mask;
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_100MB     0x2UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_1GB       0x8UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
-	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_10GB      0x40UL
-	__le16	force_pam4_link_speed;
-	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL
-	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB
-	__le32	tx_lpi_timer;
-	#define PORT_PHY_CFG_REQ_TX_LPI_TIMER_MASK 0xffffffUL
-	#define PORT_PHY_CFG_REQ_TX_LPI_TIMER_SFT 0
-	__le16	auto_link_pam4_speed_mask;
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_50G      0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_100G     0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_200G     0x4UL
-	__le16	force_link_speeds2;
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_1GB            0xaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_10GB           0x64UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_25GB           0xfaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_40GB           0x190UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
-	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112
-	__le16	auto_link_speeds2_mask;
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_1GB                0x1UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_10GB               0x2UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_25GB               0x4UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_40GB               0x8UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB               0x10UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB              0x20UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_800GB_PAM4_112     0x2000UL
-	u8	unused_2[6];
-};
-
-/* hwrm_port_phy_cfg_output (size:128b/16B) */
-struct hwrm_port_phy_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_phy_cfg_cmd_err (size:64b/8B) */
-struct hwrm_port_phy_cfg_cmd_err {
-	u8	code;
-	#define PORT_PHY_CFG_CMD_ERR_CODE_UNKNOWN       0x0UL
-	#define PORT_PHY_CFG_CMD_ERR_CODE_ILLEGAL_SPEED 0x1UL
-	#define PORT_PHY_CFG_CMD_ERR_CODE_RETRY         0x2UL
-	#define PORT_PHY_CFG_CMD_ERR_CODE_LAST         PORT_PHY_CFG_CMD_ERR_CODE_RETRY
-	u8	unused_0[7];
-};
-
-/* hwrm_port_phy_qcfg_input (size:192b/24B) */
-struct hwrm_port_phy_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_phy_qcfg_output (size:832b/104B) */
-struct hwrm_port_phy_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	link;
-	#define PORT_PHY_QCFG_RESP_LINK_NO_LINK 0x0UL
-	#define PORT_PHY_QCFG_RESP_LINK_SIGNAL  0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_LINK    0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_LAST   PORT_PHY_QCFG_RESP_LINK_LINK
-	u8	active_fec_signal_mode;
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_MASK                0xfUL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_SFT                 0
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ                   0x0UL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4                  0x1UL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112              0x2UL
-	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK                 0xf0UL
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_SFT                  4
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE        (0x0UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE74_ACTIVE    (0x1UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE91_ACTIVE    (0x2UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_1XN_ACTIVE   (0x3UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_IEEE_ACTIVE  (0x4UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_1XN_ACTIVE   (0x5UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE  (0x6UL << 4)
-	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_LAST                  PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE
-	__le16	link_speed;
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_200GB 0x7d0UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_400GB 0xfa0UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_800GB 0x1f40UL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_QCFG_RESP_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_LINK_SPEED_10MB
-	u8	duplex_cfg;
-	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_HALF 0x0UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL 0x1UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_LAST PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL
-	u8	pause;
-	#define PORT_PHY_QCFG_RESP_PAUSE_TX     0x1UL
-	#define PORT_PHY_QCFG_RESP_PAUSE_RX     0x2UL
-	__le16	support_speeds;
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MBHD     0x1UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB       0x2UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GBHD       0x4UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GB         0x8UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2GB         0x10UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2_5GB       0x20UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10GB        0x40UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_20GB        0x80UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_25GB        0x100UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB        0x200UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB        0x400UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100GB       0x800UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MBHD      0x1000UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MB        0x2000UL
-	__le16	force_link_speed;
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB
-	u8	auto_mode;
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_NONE         0x0UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ALL_SPEEDS   0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ONE_SPEED    0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ONE_OR_BELOW 0x3UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK   0x4UL
-	#define PORT_PHY_QCFG_RESP_AUTO_MODE_LAST        PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK
-	u8	auto_pause;
-	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_TX                0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_RX                0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
-	__le16	auto_link_speed;
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100MB 0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_1GB   0xaUL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_2GB   0x14UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_2_5GB 0x19UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10GB  0x64UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_20GB  0xc8UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_25GB  0xfaUL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_40GB  0x190UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB  0xffffUL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB
-	__le16	auto_link_speed_mask;
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100MBHD     0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100MB       0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_1GBHD       0x4UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_1GB         0x8UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_2GB         0x10UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_2_5GB       0x20UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10GB        0x40UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_20GB        0x80UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_25GB        0x100UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_40GB        0x200UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_50GB        0x400UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100GB       0x800UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MBHD      0x1000UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MB        0x2000UL
-	u8	wirespeed;
-	#define PORT_PHY_QCFG_RESP_WIRESPEED_OFF 0x0UL
-	#define PORT_PHY_QCFG_RESP_WIRESPEED_ON  0x1UL
-	#define PORT_PHY_QCFG_RESP_WIRESPEED_LAST PORT_PHY_QCFG_RESP_WIRESPEED_ON
-	u8	lpbk;
-	#define PORT_PHY_QCFG_RESP_LPBK_NONE     0x0UL
-	#define PORT_PHY_QCFG_RESP_LPBK_LOCAL    0x1UL
-	#define PORT_PHY_QCFG_RESP_LPBK_REMOTE   0x2UL
-	#define PORT_PHY_QCFG_RESP_LPBK_EXTERNAL 0x3UL
-	#define PORT_PHY_QCFG_RESP_LPBK_LAST    PORT_PHY_QCFG_RESP_LPBK_EXTERNAL
-	u8	force_pause;
-	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_TX     0x1UL
-	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_RX     0x2UL
-	u8	module_status;
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NONE          0x0UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_DISABLETX     0x1UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_WARNINGMSG    0x2UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN       0x3UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTINSERTED   0x4UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_CURRENTFAULT  0x5UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_OVERHEATED    0x6UL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE 0xffUL
-	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_LAST         PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE
-	__le32	preemphasis;
-	u8	phy_maj;
-	u8	phy_min;
-	u8	phy_bld;
-	u8	phy_type;
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_UNKNOWN          0x0UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASECR           0x1UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR4          0x2UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASELR           0x3UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASESR           0x4UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR2          0x5UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKX           0x6UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR           0x7UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASET            0x8UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE           0x9UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_SGMIIEXTPHY      0xaUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_L  0xbUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_S  0xcUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_N  0xdUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASESR       0xeUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR4     0xfUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR4     0x10UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR4     0x11UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER4     0x12UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR10    0x13UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASECR4      0x14UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASESR4      0x15UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASELR4      0x16UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASEER4      0x17UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_ACTIVE_CABLE 0x18UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASET         0x19UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASESX        0x1aUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASECX        0x1bUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR4     0x1cUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR4     0x1dUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR4     0x1eUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER4     0x1fUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASECR       0x20UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASESR       0x21UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASELR       0x22UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASEER       0x23UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR2     0x24UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2     0x25UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2     0x26UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2     0x27UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR      0x28UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR      0x29UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR      0x2aUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER      0x2bUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2     0x2cUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2     0x2dUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2     0x2eUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2     0x2fUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8     0x30UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8     0x31UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8     0x32UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8     0x33UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4     0x34UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4     0x35UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4     0x36UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4     0x37UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASECR8     0x38UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASESR8     0x39UL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASELR8     0x3aUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEER8     0x3bUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEFR8     0x3cUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8     0x3dUL
-	#define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST            PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8
-	u8	media_type;
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN   0x0UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP        0x1UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC       0x2UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_FIBRE     0x3UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_BACKPLANE 0x4UL
-	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_LAST     PORT_PHY_QCFG_RESP_MEDIA_TYPE_BACKPLANE
-	u8	xcvr_pkg_type;
-	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_INTERNAL 0x1UL
-	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_EXTERNAL 0x2UL
-	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_LAST         PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_EXTERNAL
-	u8	eee_config_phy_addr;
-	#define PORT_PHY_QCFG_RESP_PHY_ADDR_MASK              0x1fUL
-	#define PORT_PHY_QCFG_RESP_PHY_ADDR_SFT               0
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_MASK            0xe0UL
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_SFT             5
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_ENABLED      0x20UL
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_ACTIVE       0x40UL
-	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_TX_LPI       0x80UL
-	u8	parallel_detect;
-	#define PORT_PHY_QCFG_RESP_PARALLEL_DETECT     0x1UL
-	__le16	link_partner_adv_speeds;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100MBHD     0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100MB       0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_1GBHD       0x4UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_1GB         0x8UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_2GB         0x10UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_2_5GB       0x20UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10GB        0x40UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_20GB        0x80UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_25GB        0x100UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_40GB        0x200UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_50GB        0x400UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100GB       0x800UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10MBHD      0x1000UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10MB        0x2000UL
-	u8	link_partner_adv_auto_mode;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_NONE         0x0UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ALL_SPEEDS   0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ONE_SPEED    0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ONE_OR_BELOW 0x3UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_SPEED_MASK   0x4UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_LAST        PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_SPEED_MASK
-	u8	link_partner_adv_pause;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_PAUSE_TX     0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_PAUSE_RX     0x2UL
-	__le16	adv_eee_link_speed_mask;
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_100MB     0x2UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_1GB       0x8UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
-	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_10GB      0x40UL
-	__le16	link_partner_adv_eee_link_speed_mask;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_100MB     0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_1GB       0x8UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_10GB      0x40UL
-	__le32	xcvr_identifier_type_tx_lpi_timer;
-	#define PORT_PHY_QCFG_RESP_TX_LPI_TIMER_MASK            0xffffffUL
-	#define PORT_PHY_QCFG_RESP_TX_LPI_TIMER_SFT             0
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_MASK    0xff000000UL
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFT     24
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_UNKNOWN   (0x0UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFP       (0x3UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP      (0xcUL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPPLUS  (0xdUL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28    (0x11UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPDD    (0x18UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP112   (0x1eUL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFPDD     (0x1fUL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP      (0x20UL << 24)
-	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_LAST     PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP
-	__le16	fec_cfg;
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED           0x1UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED        0x2UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED          0x4UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED       0x8UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED         0x10UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED       0x20UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED         0x40UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_SUPPORTED      0x80UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED        0x100UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_SUPPORTED     0x200UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_ENABLED       0x400UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_SUPPORTED      0x800UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_ENABLED        0x1000UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_SUPPORTED     0x2000UL
-	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_ENABLED       0x4000UL
-	u8	duplex_state;
-	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF 0x0UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL 0x1UL
-	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_LAST PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL
-	u8	option_flags;
-	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_MEDIA_AUTO_DETECT     0x1UL
-	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SIGNAL_MODE_KNOWN     0x2UL
-	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SPEEDS2_SUPPORTED     0x4UL
-	char	phy_vendor_name[16];
-	char	phy_vendor_partnumber[16];
-	__le16	support_pam4_speeds;
-	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G      0x1UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G     0x2UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G     0x4UL
-	__le16	force_pam4_link_speed;
-	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_50GB  0x1f4UL
-	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL
-	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL
-	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB
-	__le16	auto_pam4_link_speed_mask;
-	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_50G      0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_100G     0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_200G     0x4UL
-	u8	link_partner_pam4_adv_speeds;
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_50GB      0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_100GB     0x2UL
-	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB     0x4UL
-	u8	link_down_reason;
-	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_RF                      0x1UL
-	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_OTP_SPEED_VIOLATION     0x2UL
-	__le16	support_speeds2;
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB                0x1UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB               0x2UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_25GB               0x4UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_40GB               0x8UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB               0x10UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB              0x20UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_800GB_PAM4_112     0x2000UL
-	__le16	force_link_speeds2;
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_1GB            0xaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_10GB           0x64UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_25GB           0xfaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_40GB           0x190UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
-	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112
-	__le16	auto_link_speeds2;
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_1GB                0x1UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_10GB               0x2UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_25GB               0x4UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_40GB               0x8UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB               0x10UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB              0x20UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_800GB_PAM4_112     0x2000UL
-	u8	active_lanes;
-	u8	valid;
-};
-
-/* hwrm_port_mac_cfg_input (size:448b/56B) */
-struct hwrm_port_mac_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define PORT_MAC_CFG_REQ_FLAGS_MATCH_LINK                    0x1UL
-	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_ENABLE           0x2UL
-	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_ENABLE         0x4UL
-	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_ENABLE            0x8UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_ENABLE      0x10UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE     0x20UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_ENABLE      0x40UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_DISABLE     0x80UL
-	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_ENABLE                0x100UL
-	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_DISABLE               0x200UL
-	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_DISABLE          0x400UL
-	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_DISABLE        0x800UL
-	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_DISABLE           0x1000UL
-	#define PORT_MAC_CFG_REQ_FLAGS_PTP_ONE_STEP_TX_TS            0x2000UL
-	#define PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE      0x4000UL
-	#define PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE     0x8000UL
-	__le32	enables;
-	#define PORT_MAC_CFG_REQ_ENABLES_IPG                            0x1UL
-	#define PORT_MAC_CFG_REQ_ENABLES_LPBK                           0x2UL
-	#define PORT_MAC_CFG_REQ_ENABLES_VLAN_PRI2COS_MAP_PRI           0x4UL
-	#define PORT_MAC_CFG_REQ_ENABLES_TUNNEL_PRI2COS_MAP_PRI         0x10UL
-	#define PORT_MAC_CFG_REQ_ENABLES_DSCP2COS_MAP_PRI               0x20UL
-	#define PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE     0x40UL
-	#define PORT_MAC_CFG_REQ_ENABLES_TX_TS_CAPTURE_PTP_MSG_TYPE     0x80UL
-	#define PORT_MAC_CFG_REQ_ENABLES_COS_FIELD_CFG                  0x100UL
-	#define PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB               0x200UL
-	#define PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE                  0x400UL
-	#define PORT_MAC_CFG_REQ_ENABLES_PTP_LOAD_CONTROL               0x800UL
-	__le16	port_id;
-	u8	ipg;
-	u8	lpbk;
-	#define PORT_MAC_CFG_REQ_LPBK_NONE   0x0UL
-	#define PORT_MAC_CFG_REQ_LPBK_LOCAL  0x1UL
-	#define PORT_MAC_CFG_REQ_LPBK_REMOTE 0x2UL
-	#define PORT_MAC_CFG_REQ_LPBK_LAST  PORT_MAC_CFG_REQ_LPBK_REMOTE
-	u8	vlan_pri2cos_map_pri;
-	u8	reserved1;
-	u8	tunnel_pri2cos_map_pri;
-	u8	dscp2pri_map_pri;
-	__le16	rx_ts_capture_ptp_msg_type;
-	__le16	tx_ts_capture_ptp_msg_type;
-	u8	cos_field_cfg;
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_RSVD1                     0x1UL
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_MASK         0x6UL
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_SFT          1
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_INNERMOST      (0x0UL << 1)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_OUTER          (0x1UL << 1)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_OUTERMOST      (0x2UL << 1)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_UNSPECIFIED    (0x3UL << 1)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_LAST          PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_UNSPECIFIED
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_MASK       0x18UL
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_SFT        3
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_INNERMOST    (0x0UL << 3)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_OUTER        (0x1UL << 3)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_OUTERMOST    (0x2UL << 3)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_UNSPECIFIED  (0x3UL << 3)
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_LAST        PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_UNSPECIFIED
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_MASK          0xe0UL
-	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT           5
-	u8	unused_0[3];
-	__le32	ptp_freq_adj_ppb;
-	u8	unused_1[3];
-	u8	ptp_load_control;
-	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_NONE      0x0UL
-	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_IMMEDIATE 0x1UL
-	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT 0x2UL
-	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_LAST     PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT
-	__le64	ptp_adj_phase;
-};
-
-/* hwrm_port_mac_cfg_output (size:128b/16B) */
-struct hwrm_port_mac_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	mru;
-	__le16	mtu;
-	u8	ipg;
-	u8	lpbk;
-	#define PORT_MAC_CFG_RESP_LPBK_NONE   0x0UL
-	#define PORT_MAC_CFG_RESP_LPBK_LOCAL  0x1UL
-	#define PORT_MAC_CFG_RESP_LPBK_REMOTE 0x2UL
-	#define PORT_MAC_CFG_RESP_LPBK_LAST  PORT_MAC_CFG_RESP_LPBK_REMOTE
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_port_mac_ptp_qcfg_input (size:192b/24B) */
-struct hwrm_port_mac_ptp_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_mac_ptp_qcfg_output (size:704b/88B) */
-struct hwrm_port_mac_ptp_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS                       0x1UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS                      0x4UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS                         0x8UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK     0x10UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED                      0x20UL
-	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_64B_PHC_TIME                        0x40UL
-	u8	unused_0[3];
-	__le32	rx_ts_reg_off_lower;
-	__le32	rx_ts_reg_off_upper;
-	__le32	rx_ts_reg_off_seq_id;
-	__le32	rx_ts_reg_off_src_id_0;
-	__le32	rx_ts_reg_off_src_id_1;
-	__le32	rx_ts_reg_off_src_id_2;
-	__le32	rx_ts_reg_off_domain_id;
-	__le32	rx_ts_reg_off_fifo;
-	__le32	rx_ts_reg_off_fifo_adv;
-	__le32	rx_ts_reg_off_granularity;
-	__le32	tx_ts_reg_off_lower;
-	__le32	tx_ts_reg_off_upper;
-	__le32	tx_ts_reg_off_seq_id;
-	__le32	tx_ts_reg_off_fifo;
-	__le32	tx_ts_reg_off_granularity;
-	__le32	ts_ref_clock_reg_lower;
-	__le32	ts_ref_clock_reg_upper;
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* tx_port_stats (size:3264b/408B) */
-struct tx_port_stats {
-	__le64	tx_64b_frames;
-	__le64	tx_65b_127b_frames;
-	__le64	tx_128b_255b_frames;
-	__le64	tx_256b_511b_frames;
-	__le64	tx_512b_1023b_frames;
-	__le64	tx_1024b_1518b_frames;
-	__le64	tx_good_vlan_frames;
-	__le64	tx_1519b_2047b_frames;
-	__le64	tx_2048b_4095b_frames;
-	__le64	tx_4096b_9216b_frames;
-	__le64	tx_9217b_16383b_frames;
-	__le64	tx_good_frames;
-	__le64	tx_total_frames;
-	__le64	tx_ucast_frames;
-	__le64	tx_mcast_frames;
-	__le64	tx_bcast_frames;
-	__le64	tx_pause_frames;
-	__le64	tx_pfc_frames;
-	__le64	tx_jabber_frames;
-	__le64	tx_fcs_err_frames;
-	__le64	tx_control_frames;
-	__le64	tx_oversz_frames;
-	__le64	tx_single_dfrl_frames;
-	__le64	tx_multi_dfrl_frames;
-	__le64	tx_single_coll_frames;
-	__le64	tx_multi_coll_frames;
-	__le64	tx_late_coll_frames;
-	__le64	tx_excessive_coll_frames;
-	__le64	tx_frag_frames;
-	__le64	tx_err;
-	__le64	tx_tagged_frames;
-	__le64	tx_dbl_tagged_frames;
-	__le64	tx_runt_frames;
-	__le64	tx_fifo_underruns;
-	__le64	tx_pfc_ena_frames_pri0;
-	__le64	tx_pfc_ena_frames_pri1;
-	__le64	tx_pfc_ena_frames_pri2;
-	__le64	tx_pfc_ena_frames_pri3;
-	__le64	tx_pfc_ena_frames_pri4;
-	__le64	tx_pfc_ena_frames_pri5;
-	__le64	tx_pfc_ena_frames_pri6;
-	__le64	tx_pfc_ena_frames_pri7;
-	__le64	tx_eee_lpi_events;
-	__le64	tx_eee_lpi_duration;
-	__le64	tx_llfc_logical_msgs;
-	__le64	tx_hcfc_msgs;
-	__le64	tx_total_collisions;
-	__le64	tx_bytes;
-	__le64	tx_xthol_frames;
-	__le64	tx_stat_discard;
-	__le64	tx_stat_error;
-};
-
-/* rx_port_stats (size:4224b/528B) */
-struct rx_port_stats {
-	__le64	rx_64b_frames;
-	__le64	rx_65b_127b_frames;
-	__le64	rx_128b_255b_frames;
-	__le64	rx_256b_511b_frames;
-	__le64	rx_512b_1023b_frames;
-	__le64	rx_1024b_1518b_frames;
-	__le64	rx_good_vlan_frames;
-	__le64	rx_1519b_2047b_frames;
-	__le64	rx_2048b_4095b_frames;
-	__le64	rx_4096b_9216b_frames;
-	__le64	rx_9217b_16383b_frames;
-	__le64	rx_total_frames;
-	__le64	rx_ucast_frames;
-	__le64	rx_mcast_frames;
-	__le64	rx_bcast_frames;
-	__le64	rx_fcs_err_frames;
-	__le64	rx_ctrl_frames;
-	__le64	rx_pause_frames;
-	__le64	rx_pfc_frames;
-	__le64	rx_unsupported_opcode_frames;
-	__le64	rx_unsupported_da_pausepfc_frames;
-	__le64	rx_wrong_sa_frames;
-	__le64	rx_align_err_frames;
-	__le64	rx_oor_len_frames;
-	__le64	rx_code_err_frames;
-	__le64	rx_false_carrier_frames;
-	__le64	rx_ovrsz_frames;
-	__le64	rx_jbr_frames;
-	__le64	rx_mtu_err_frames;
-	__le64	rx_match_crc_frames;
-	__le64	rx_promiscuous_frames;
-	__le64	rx_tagged_frames;
-	__le64	rx_double_tagged_frames;
-	__le64	rx_trunc_frames;
-	__le64	rx_good_frames;
-	__le64	rx_pfc_xon2xoff_frames_pri0;
-	__le64	rx_pfc_xon2xoff_frames_pri1;
-	__le64	rx_pfc_xon2xoff_frames_pri2;
-	__le64	rx_pfc_xon2xoff_frames_pri3;
-	__le64	rx_pfc_xon2xoff_frames_pri4;
-	__le64	rx_pfc_xon2xoff_frames_pri5;
-	__le64	rx_pfc_xon2xoff_frames_pri6;
-	__le64	rx_pfc_xon2xoff_frames_pri7;
-	__le64	rx_pfc_ena_frames_pri0;
-	__le64	rx_pfc_ena_frames_pri1;
-	__le64	rx_pfc_ena_frames_pri2;
-	__le64	rx_pfc_ena_frames_pri3;
-	__le64	rx_pfc_ena_frames_pri4;
-	__le64	rx_pfc_ena_frames_pri5;
-	__le64	rx_pfc_ena_frames_pri6;
-	__le64	rx_pfc_ena_frames_pri7;
-	__le64	rx_sch_crc_err_frames;
-	__le64	rx_undrsz_frames;
-	__le64	rx_frag_frames;
-	__le64	rx_eee_lpi_events;
-	__le64	rx_eee_lpi_duration;
-	__le64	rx_llfc_physical_msgs;
-	__le64	rx_llfc_logical_msgs;
-	__le64	rx_llfc_msgs_with_crc_err;
-	__le64	rx_hcfc_msgs;
-	__le64	rx_hcfc_msgs_with_crc_err;
-	__le64	rx_bytes;
-	__le64	rx_runt_bytes;
-	__le64	rx_runt_frames;
-	__le64	rx_stat_discard;
-	__le64	rx_stat_err;
-};
-
-/* hwrm_port_qstats_input (size:320b/40B) */
-struct hwrm_port_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	flags;
-	#define PORT_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[5];
-	__le64	tx_stat_host_addr;
-	__le64	rx_stat_host_addr;
-};
-
-/* hwrm_port_qstats_output (size:128b/16B) */
-struct hwrm_port_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	tx_stat_size;
-	__le16	rx_stat_size;
-	u8	flags;
-	#define PORT_QSTATS_RESP_FLAGS_CLEARED     0x1UL
-	u8	unused_0[2];
-	u8	valid;
-};
-
-/* tx_port_stats_ext (size:2048b/256B) */
-struct tx_port_stats_ext {
-	__le64	tx_bytes_cos0;
-	__le64	tx_bytes_cos1;
-	__le64	tx_bytes_cos2;
-	__le64	tx_bytes_cos3;
-	__le64	tx_bytes_cos4;
-	__le64	tx_bytes_cos5;
-	__le64	tx_bytes_cos6;
-	__le64	tx_bytes_cos7;
-	__le64	tx_packets_cos0;
-	__le64	tx_packets_cos1;
-	__le64	tx_packets_cos2;
-	__le64	tx_packets_cos3;
-	__le64	tx_packets_cos4;
-	__le64	tx_packets_cos5;
-	__le64	tx_packets_cos6;
-	__le64	tx_packets_cos7;
-	__le64	pfc_pri0_tx_duration_us;
-	__le64	pfc_pri0_tx_transitions;
-	__le64	pfc_pri1_tx_duration_us;
-	__le64	pfc_pri1_tx_transitions;
-	__le64	pfc_pri2_tx_duration_us;
-	__le64	pfc_pri2_tx_transitions;
-	__le64	pfc_pri3_tx_duration_us;
-	__le64	pfc_pri3_tx_transitions;
-	__le64	pfc_pri4_tx_duration_us;
-	__le64	pfc_pri4_tx_transitions;
-	__le64	pfc_pri5_tx_duration_us;
-	__le64	pfc_pri5_tx_transitions;
-	__le64	pfc_pri6_tx_duration_us;
-	__le64	pfc_pri6_tx_transitions;
-	__le64	pfc_pri7_tx_duration_us;
-	__le64	pfc_pri7_tx_transitions;
-};
-
-/* rx_port_stats_ext (size:3904b/488B) */
-struct rx_port_stats_ext {
-	__le64	link_down_events;
-	__le64	continuous_pause_events;
-	__le64	resume_pause_events;
-	__le64	continuous_roce_pause_events;
-	__le64	resume_roce_pause_events;
-	__le64	rx_bytes_cos0;
-	__le64	rx_bytes_cos1;
-	__le64	rx_bytes_cos2;
-	__le64	rx_bytes_cos3;
-	__le64	rx_bytes_cos4;
-	__le64	rx_bytes_cos5;
-	__le64	rx_bytes_cos6;
-	__le64	rx_bytes_cos7;
-	__le64	rx_packets_cos0;
-	__le64	rx_packets_cos1;
-	__le64	rx_packets_cos2;
-	__le64	rx_packets_cos3;
-	__le64	rx_packets_cos4;
-	__le64	rx_packets_cos5;
-	__le64	rx_packets_cos6;
-	__le64	rx_packets_cos7;
-	__le64	pfc_pri0_rx_duration_us;
-	__le64	pfc_pri0_rx_transitions;
-	__le64	pfc_pri1_rx_duration_us;
-	__le64	pfc_pri1_rx_transitions;
-	__le64	pfc_pri2_rx_duration_us;
-	__le64	pfc_pri2_rx_transitions;
-	__le64	pfc_pri3_rx_duration_us;
-	__le64	pfc_pri3_rx_transitions;
-	__le64	pfc_pri4_rx_duration_us;
-	__le64	pfc_pri4_rx_transitions;
-	__le64	pfc_pri5_rx_duration_us;
-	__le64	pfc_pri5_rx_transitions;
-	__le64	pfc_pri6_rx_duration_us;
-	__le64	pfc_pri6_rx_transitions;
-	__le64	pfc_pri7_rx_duration_us;
-	__le64	pfc_pri7_rx_transitions;
-	__le64	rx_bits;
-	__le64	rx_buffer_passed_threshold;
-	__le64	rx_pcs_symbol_err;
-	__le64	rx_corrected_bits;
-	__le64	rx_discard_bytes_cos0;
-	__le64	rx_discard_bytes_cos1;
-	__le64	rx_discard_bytes_cos2;
-	__le64	rx_discard_bytes_cos3;
-	__le64	rx_discard_bytes_cos4;
-	__le64	rx_discard_bytes_cos5;
-	__le64	rx_discard_bytes_cos6;
-	__le64	rx_discard_bytes_cos7;
-	__le64	rx_discard_packets_cos0;
-	__le64	rx_discard_packets_cos1;
-	__le64	rx_discard_packets_cos2;
-	__le64	rx_discard_packets_cos3;
-	__le64	rx_discard_packets_cos4;
-	__le64	rx_discard_packets_cos5;
-	__le64	rx_discard_packets_cos6;
-	__le64	rx_discard_packets_cos7;
-	__le64	rx_fec_corrected_blocks;
-	__le64	rx_fec_uncorrectable_blocks;
-	__le64	rx_filter_miss;
-	__le64	rx_fec_symbol_err;
-};
-
-/* hwrm_port_qstats_ext_input (size:320b/40B) */
-struct hwrm_port_qstats_ext_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	__le16	tx_stat_size;
-	__le16	rx_stat_size;
-	u8	flags;
-	#define PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0;
-	__le64	tx_stat_host_addr;
-	__le64	rx_stat_host_addr;
-};
-
-/* hwrm_port_qstats_ext_output (size:128b/16B) */
-struct hwrm_port_qstats_ext_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	tx_stat_size;
-	__le16	rx_stat_size;
-	__le16	total_active_cos_queues;
-	u8	flags;
-	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEAR_ROCE_COUNTERS_SUPPORTED     0x1UL
-	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEARED                           0x2UL
-	u8	valid;
-};
-
-/* hwrm_port_lpbk_qstats_input (size:256b/32B) */
-struct hwrm_port_lpbk_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	lpbk_stat_size;
-	u8	flags;
-	#define PORT_LPBK_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[5];
-	__le64	lpbk_stat_host_addr;
-};
-
-/* hwrm_port_lpbk_qstats_output (size:128b/16B) */
-struct hwrm_port_lpbk_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	lpbk_stat_size;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* port_lpbk_stats (size:640b/80B) */
-struct port_lpbk_stats {
-	__le64	lpbk_ucast_frames;
-	__le64	lpbk_mcast_frames;
-	__le64	lpbk_bcast_frames;
-	__le64	lpbk_ucast_bytes;
-	__le64	lpbk_mcast_bytes;
-	__le64	lpbk_bcast_bytes;
-	__le64	lpbk_tx_discards;
-	__le64	lpbk_tx_errors;
-	__le64	lpbk_rx_discards;
-	__le64	lpbk_rx_errors;
-};
-
-/* hwrm_port_ecn_qstats_input (size:256b/32B) */
-struct hwrm_port_ecn_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	__le16	ecn_stat_buf_size;
-	u8	flags;
-	#define PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[3];
-	__le64	ecn_stat_host_addr;
-};
-
-/* hwrm_port_ecn_qstats_output (size:128b/16B) */
-struct hwrm_port_ecn_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	ecn_stat_buf_size;
-	u8	mark_en;
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* port_stats_ecn (size:512b/64B) */
-struct port_stats_ecn {
-	__le64	mark_cnt_cos0;
-	__le64	mark_cnt_cos1;
-	__le64	mark_cnt_cos2;
-	__le64	mark_cnt_cos3;
-	__le64	mark_cnt_cos4;
-	__le64	mark_cnt_cos5;
-	__le64	mark_cnt_cos6;
-	__le64	mark_cnt_cos7;
-};
-
-/* hwrm_port_clr_stats_input (size:192b/24B) */
-struct hwrm_port_clr_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	flags;
-	#define PORT_CLR_STATS_REQ_FLAGS_ROCE_COUNTERS     0x1UL
-	u8	unused_0[5];
-};
-
-/* hwrm_port_clr_stats_output (size:128b/16B) */
-struct hwrm_port_clr_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_lpbk_clr_stats_input (size:192b/24B) */
-struct hwrm_port_lpbk_clr_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_lpbk_clr_stats_output (size:128b/16B) */
-struct hwrm_port_lpbk_clr_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_ts_query_input (size:320b/40B) */
-struct hwrm_port_ts_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define PORT_TS_QUERY_REQ_FLAGS_PATH             0x1UL
-	#define PORT_TS_QUERY_REQ_FLAGS_PATH_TX            0x0UL
-	#define PORT_TS_QUERY_REQ_FLAGS_PATH_RX            0x1UL
-	#define PORT_TS_QUERY_REQ_FLAGS_PATH_LAST         PORT_TS_QUERY_REQ_FLAGS_PATH_RX
-	#define PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME     0x2UL
-	__le16	port_id;
-	u8	unused_0[2];
-	__le16	enables;
-	#define PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT     0x1UL
-	#define PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID         0x2UL
-	#define PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET     0x4UL
-	__le16	ts_req_timeout;
-	__le32	ptp_seq_id;
-	__le16	ptp_hdr_offset;
-	u8	unused_1[6];
-};
-
-/* hwrm_port_ts_query_output (size:192b/24B) */
-struct hwrm_port_ts_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	ptp_msg_ts;
-	__le16	ptp_msg_seqid;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_port_phy_qcaps_input (size:192b/24B) */
-struct hwrm_port_phy_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_phy_qcaps_output (size:320b/40B) */
-struct hwrm_port_phy_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED                    0x1UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED          0x2UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_AUTONEG_LPBK_SUPPORTED           0x4UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_SHARED_PHY_CFG_SUPPORTED         0x8UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_CUMULATIVE_COUNTERS_ON_RESET     0x10UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED         0x20UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_FW_MANAGED_LINK_DOWN             0x40UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS_NO_FCS                           0x80UL
-	u8	port_cnt;
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1       0x1UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_2       0x2UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_3       0x3UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_4       0x4UL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_12      0xcUL
-	#define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST   PORT_PHY_QCAPS_RESP_PORT_CNT_12
-	__le16	supported_speeds_force_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD     0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB       0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_1GBHD       0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_1GB         0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_2GB         0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_2_5GB       0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10GB        0x40UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_20GB        0x80UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_25GB        0x100UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_40GB        0x200UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_50GB        0x400UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100GB       0x800UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MBHD      0x1000UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MB        0x2000UL
-	__le16	supported_speeds_auto_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MBHD     0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MB       0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_1GBHD       0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_1GB         0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_2GB         0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_2_5GB       0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10GB        0x40UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_20GB        0x80UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_25GB        0x100UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_40GB        0x200UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_50GB        0x400UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100GB       0x800UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MBHD      0x1000UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MB        0x2000UL
-	__le16	supported_speeds_eee_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD1     0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_100MB     0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD2     0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_1GB       0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD3     0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD4     0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_10GB      0x40UL
-	__le32	tx_lpi_timer_low;
-	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_MASK 0xffffffUL
-	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_SFT 0
-	#define PORT_PHY_QCAPS_RESP_RSVD2_MASK           0xff000000UL
-	#define PORT_PHY_QCAPS_RESP_RSVD2_SFT            24
-	__le32	valid_tx_lpi_timer_high;
-	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK 0xffffffUL
-	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_SFT 0
-	#define PORT_PHY_QCAPS_RESP_RSVD_MASK             0xff000000UL
-	#define PORT_PHY_QCAPS_RESP_RSVD_SFT              24
-	__le16	supported_pam4_speeds_auto_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_50G      0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_100G     0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_200G     0x4UL
-	__le16	supported_pam4_speeds_force_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_50G      0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G     0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G     0x4UL
-	__le16	flags2;
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED           0x1UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED             0x2UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED         0x4UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED           0x8UL
-	#define PORT_PHY_QCAPS_RESP_FLAGS2_REMOTE_LPBK_UNSUPPORTED     0x10UL
-	u8	internal_port_cnt;
-	u8	unused_0;
-	__le16	supported_speeds2_force_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_1GB                0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_10GB               0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_25GB               0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_40GB               0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB               0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB              0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_800GB_PAM4_112     0x2000UL
-	__le16	supported_speeds2_auto_mode;
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_1GB                0x1UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_10GB               0x2UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_25GB               0x4UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_40GB               0x8UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB               0x10UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB              0x20UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB_PAM4_56       0x40UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_56      0x80UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_56      0x100UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_56      0x200UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_112     0x400UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_112     0x800UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_112     0x1000UL
-	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_800GB_PAM4_112     0x2000UL
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_port_phy_i2c_write_input (size:832b/104B) */
-struct hwrm_port_phy_i2c_write_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	__le32	enables;
-	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_PAGE_OFFSET     0x1UL
-	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_BANK_NUMBER     0x2UL
-	__le16	port_id;
-	u8	i2c_slave_addr;
-	u8	bank_number;
-	__le16	page_number;
-	__le16	page_offset;
-	u8	data_length;
-	u8	unused_1[7];
-	__le32	data[16];
-};
-
-/* hwrm_port_phy_i2c_write_output (size:128b/16B) */
-struct hwrm_port_phy_i2c_write_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_phy_i2c_read_input (size:320b/40B) */
-struct hwrm_port_phy_i2c_read_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	__le32	enables;
-	#define PORT_PHY_I2C_READ_REQ_ENABLES_PAGE_OFFSET     0x1UL
-	#define PORT_PHY_I2C_READ_REQ_ENABLES_BANK_NUMBER     0x2UL
-	__le16	port_id;
-	u8	i2c_slave_addr;
-	u8	bank_number;
-	__le16	page_number;
-	__le16	page_offset;
-	u8	data_length;
-	u8	unused_1[7];
-};
-
-/* hwrm_port_phy_i2c_read_output (size:640b/80B) */
-struct hwrm_port_phy_i2c_read_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	data[16];
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_phy_mdio_write_input (size:320b/40B) */
-struct hwrm_port_phy_mdio_write_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	unused_0[2];
-	__le16	port_id;
-	u8	phy_addr;
-	u8	dev_addr;
-	__le16	reg_addr;
-	__le16	reg_data;
-	u8	cl45_mdio;
-	u8	unused_1[7];
-};
-
-/* hwrm_port_phy_mdio_write_output (size:128b/16B) */
-struct hwrm_port_phy_mdio_write_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_phy_mdio_read_input (size:256b/32B) */
-struct hwrm_port_phy_mdio_read_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	unused_0[2];
-	__le16	port_id;
-	u8	phy_addr;
-	u8	dev_addr;
-	__le16	reg_addr;
-	u8	cl45_mdio;
-	u8	unused_1;
-};
-
-/* hwrm_port_phy_mdio_read_output (size:128b/16B) */
-struct hwrm_port_phy_mdio_read_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	reg_data;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_port_led_cfg_input (size:512b/64B) */
-struct hwrm_port_led_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_ID            0x1UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_STATE         0x2UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_COLOR         0x4UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_BLINK_ON      0x8UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_BLINK_OFF     0x10UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED0_GROUP_ID      0x20UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_ID            0x40UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_STATE         0x80UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_COLOR         0x100UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_BLINK_ON      0x200UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_BLINK_OFF     0x400UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED1_GROUP_ID      0x800UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_ID            0x1000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_STATE         0x2000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_COLOR         0x4000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_BLINK_ON      0x8000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_BLINK_OFF     0x10000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED2_GROUP_ID      0x20000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_ID            0x40000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_STATE         0x80000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_COLOR         0x100000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_BLINK_ON      0x200000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_BLINK_OFF     0x400000UL
-	#define PORT_LED_CFG_REQ_ENABLES_LED3_GROUP_ID      0x800000UL
-	__le16	port_id;
-	u8	num_leds;
-	u8	rsvd;
-	u8	led0_id;
-	u8	led0_state;
-	#define PORT_LED_CFG_REQ_LED0_STATE_DEFAULT  0x0UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_OFF      0x1UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_ON       0x2UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_BLINK    0x3UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_BLINKALT 0x4UL
-	#define PORT_LED_CFG_REQ_LED0_STATE_LAST    PORT_LED_CFG_REQ_LED0_STATE_BLINKALT
-	u8	led0_color;
-	#define PORT_LED_CFG_REQ_LED0_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_CFG_REQ_LED0_COLOR_AMBER      0x1UL
-	#define PORT_LED_CFG_REQ_LED0_COLOR_GREEN      0x2UL
-	#define PORT_LED_CFG_REQ_LED0_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_CFG_REQ_LED0_COLOR_LAST      PORT_LED_CFG_REQ_LED0_COLOR_GREENAMBER
-	u8	unused_0;
-	__le16	led0_blink_on;
-	__le16	led0_blink_off;
-	u8	led0_group_id;
-	u8	rsvd0;
-	u8	led1_id;
-	u8	led1_state;
-	#define PORT_LED_CFG_REQ_LED1_STATE_DEFAULT  0x0UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_OFF      0x1UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_ON       0x2UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_BLINK    0x3UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_BLINKALT 0x4UL
-	#define PORT_LED_CFG_REQ_LED1_STATE_LAST    PORT_LED_CFG_REQ_LED1_STATE_BLINKALT
-	u8	led1_color;
-	#define PORT_LED_CFG_REQ_LED1_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_CFG_REQ_LED1_COLOR_AMBER      0x1UL
-	#define PORT_LED_CFG_REQ_LED1_COLOR_GREEN      0x2UL
-	#define PORT_LED_CFG_REQ_LED1_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_CFG_REQ_LED1_COLOR_LAST      PORT_LED_CFG_REQ_LED1_COLOR_GREENAMBER
-	u8	unused_1;
-	__le16	led1_blink_on;
-	__le16	led1_blink_off;
-	u8	led1_group_id;
-	u8	rsvd1;
-	u8	led2_id;
-	u8	led2_state;
-	#define PORT_LED_CFG_REQ_LED2_STATE_DEFAULT  0x0UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_OFF      0x1UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_ON       0x2UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_BLINK    0x3UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_BLINKALT 0x4UL
-	#define PORT_LED_CFG_REQ_LED2_STATE_LAST    PORT_LED_CFG_REQ_LED2_STATE_BLINKALT
-	u8	led2_color;
-	#define PORT_LED_CFG_REQ_LED2_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_CFG_REQ_LED2_COLOR_AMBER      0x1UL
-	#define PORT_LED_CFG_REQ_LED2_COLOR_GREEN      0x2UL
-	#define PORT_LED_CFG_REQ_LED2_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_CFG_REQ_LED2_COLOR_LAST      PORT_LED_CFG_REQ_LED2_COLOR_GREENAMBER
-	u8	unused_2;
-	__le16	led2_blink_on;
-	__le16	led2_blink_off;
-	u8	led2_group_id;
-	u8	rsvd2;
-	u8	led3_id;
-	u8	led3_state;
-	#define PORT_LED_CFG_REQ_LED3_STATE_DEFAULT  0x0UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_OFF      0x1UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_ON       0x2UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_BLINK    0x3UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_BLINKALT 0x4UL
-	#define PORT_LED_CFG_REQ_LED3_STATE_LAST    PORT_LED_CFG_REQ_LED3_STATE_BLINKALT
-	u8	led3_color;
-	#define PORT_LED_CFG_REQ_LED3_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_CFG_REQ_LED3_COLOR_AMBER      0x1UL
-	#define PORT_LED_CFG_REQ_LED3_COLOR_GREEN      0x2UL
-	#define PORT_LED_CFG_REQ_LED3_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_CFG_REQ_LED3_COLOR_LAST      PORT_LED_CFG_REQ_LED3_COLOR_GREENAMBER
-	u8	unused_3;
-	__le16	led3_blink_on;
-	__le16	led3_blink_off;
-	u8	led3_group_id;
-	u8	rsvd3;
-};
-
-/* hwrm_port_led_cfg_output (size:128b/16B) */
-struct hwrm_port_led_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_port_led_qcfg_input (size:192b/24B) */
-struct hwrm_port_led_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_led_qcfg_output (size:448b/56B) */
-struct hwrm_port_led_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_leds;
-	u8	led0_id;
-	u8	led0_type;
-	#define PORT_LED_QCFG_RESP_LED0_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCFG_RESP_LED0_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCFG_RESP_LED0_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCFG_RESP_LED0_TYPE_LAST    PORT_LED_QCFG_RESP_LED0_TYPE_INVALID
-	u8	led0_state;
-	#define PORT_LED_QCFG_RESP_LED0_STATE_DEFAULT  0x0UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_OFF      0x1UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_ON       0x2UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_BLINK    0x3UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_BLINKALT 0x4UL
-	#define PORT_LED_QCFG_RESP_LED0_STATE_LAST    PORT_LED_QCFG_RESP_LED0_STATE_BLINKALT
-	u8	led0_color;
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_AMBER      0x1UL
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_GREEN      0x2UL
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_QCFG_RESP_LED0_COLOR_LAST      PORT_LED_QCFG_RESP_LED0_COLOR_GREENAMBER
-	u8	unused_0;
-	__le16	led0_blink_on;
-	__le16	led0_blink_off;
-	u8	led0_group_id;
-	u8	led1_id;
-	u8	led1_type;
-	#define PORT_LED_QCFG_RESP_LED1_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCFG_RESP_LED1_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCFG_RESP_LED1_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCFG_RESP_LED1_TYPE_LAST    PORT_LED_QCFG_RESP_LED1_TYPE_INVALID
-	u8	led1_state;
-	#define PORT_LED_QCFG_RESP_LED1_STATE_DEFAULT  0x0UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_OFF      0x1UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_ON       0x2UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_BLINK    0x3UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_BLINKALT 0x4UL
-	#define PORT_LED_QCFG_RESP_LED1_STATE_LAST    PORT_LED_QCFG_RESP_LED1_STATE_BLINKALT
-	u8	led1_color;
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_AMBER      0x1UL
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_GREEN      0x2UL
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_QCFG_RESP_LED1_COLOR_LAST      PORT_LED_QCFG_RESP_LED1_COLOR_GREENAMBER
-	u8	unused_1;
-	__le16	led1_blink_on;
-	__le16	led1_blink_off;
-	u8	led1_group_id;
-	u8	led2_id;
-	u8	led2_type;
-	#define PORT_LED_QCFG_RESP_LED2_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCFG_RESP_LED2_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCFG_RESP_LED2_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCFG_RESP_LED2_TYPE_LAST    PORT_LED_QCFG_RESP_LED2_TYPE_INVALID
-	u8	led2_state;
-	#define PORT_LED_QCFG_RESP_LED2_STATE_DEFAULT  0x0UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_OFF      0x1UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_ON       0x2UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_BLINK    0x3UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_BLINKALT 0x4UL
-	#define PORT_LED_QCFG_RESP_LED2_STATE_LAST    PORT_LED_QCFG_RESP_LED2_STATE_BLINKALT
-	u8	led2_color;
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_AMBER      0x1UL
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_GREEN      0x2UL
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_QCFG_RESP_LED2_COLOR_LAST      PORT_LED_QCFG_RESP_LED2_COLOR_GREENAMBER
-	u8	unused_2;
-	__le16	led2_blink_on;
-	__le16	led2_blink_off;
-	u8	led2_group_id;
-	u8	led3_id;
-	u8	led3_type;
-	#define PORT_LED_QCFG_RESP_LED3_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCFG_RESP_LED3_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCFG_RESP_LED3_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCFG_RESP_LED3_TYPE_LAST    PORT_LED_QCFG_RESP_LED3_TYPE_INVALID
-	u8	led3_state;
-	#define PORT_LED_QCFG_RESP_LED3_STATE_DEFAULT  0x0UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_OFF      0x1UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_ON       0x2UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_BLINK    0x3UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_BLINKALT 0x4UL
-	#define PORT_LED_QCFG_RESP_LED3_STATE_LAST    PORT_LED_QCFG_RESP_LED3_STATE_BLINKALT
-	u8	led3_color;
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_DEFAULT    0x0UL
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_AMBER      0x1UL
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_GREEN      0x2UL
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_GREENAMBER 0x3UL
-	#define PORT_LED_QCFG_RESP_LED3_COLOR_LAST      PORT_LED_QCFG_RESP_LED3_COLOR_GREENAMBER
-	u8	unused_3;
-	__le16	led3_blink_on;
-	__le16	led3_blink_off;
-	u8	led3_group_id;
-	u8	unused_4[6];
-	u8	valid;
-};
-
-/* hwrm_port_led_qcaps_input (size:192b/24B) */
-struct hwrm_port_led_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_led_qcaps_output (size:384b/48B) */
-struct hwrm_port_led_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_leds;
-	u8	unused[3];
-	u8	led0_id;
-	u8	led0_type;
-	#define PORT_LED_QCAPS_RESP_LED0_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCAPS_RESP_LED0_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED0_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCAPS_RESP_LED0_TYPE_LAST    PORT_LED_QCAPS_RESP_LED0_TYPE_INVALID
-	u8	led0_group_id;
-	u8	unused_0;
-	__le16	led0_state_caps;
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_ENABLED                 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_OFF_SUPPORTED           0x2UL
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_ON_SUPPORTED            0x4UL
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_SUPPORTED         0x8UL
-	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
-	__le16	led0_color_caps;
-	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_RSVD                0x1UL
-	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
-	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
-	u8	led1_id;
-	u8	led1_type;
-	#define PORT_LED_QCAPS_RESP_LED1_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCAPS_RESP_LED1_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED1_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCAPS_RESP_LED1_TYPE_LAST    PORT_LED_QCAPS_RESP_LED1_TYPE_INVALID
-	u8	led1_group_id;
-	u8	unused_1;
-	__le16	led1_state_caps;
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_ENABLED                 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_OFF_SUPPORTED           0x2UL
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_ON_SUPPORTED            0x4UL
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_SUPPORTED         0x8UL
-	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
-	__le16	led1_color_caps;
-	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_RSVD                0x1UL
-	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
-	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
-	u8	led2_id;
-	u8	led2_type;
-	#define PORT_LED_QCAPS_RESP_LED2_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCAPS_RESP_LED2_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED2_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCAPS_RESP_LED2_TYPE_LAST    PORT_LED_QCAPS_RESP_LED2_TYPE_INVALID
-	u8	led2_group_id;
-	u8	unused_2;
-	__le16	led2_state_caps;
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_ENABLED                 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_OFF_SUPPORTED           0x2UL
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_ON_SUPPORTED            0x4UL
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_SUPPORTED         0x8UL
-	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
-	__le16	led2_color_caps;
-	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_RSVD                0x1UL
-	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
-	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
-	u8	led3_id;
-	u8	led3_type;
-	#define PORT_LED_QCAPS_RESP_LED3_TYPE_SPEED    0x0UL
-	#define PORT_LED_QCAPS_RESP_LED3_TYPE_ACTIVITY 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED3_TYPE_INVALID  0xffUL
-	#define PORT_LED_QCAPS_RESP_LED3_TYPE_LAST    PORT_LED_QCAPS_RESP_LED3_TYPE_INVALID
-	u8	led3_group_id;
-	u8	unused_3;
-	__le16	led3_state_caps;
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_ENABLED                 0x1UL
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_OFF_SUPPORTED           0x2UL
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_ON_SUPPORTED            0x4UL
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_SUPPORTED         0x8UL
-	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
-	__le16	led3_color_caps;
-	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_RSVD                0x1UL
-	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
-	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
-	u8	unused_4[3];
-	u8	valid;
-};
-
-/* hwrm_port_mac_qcaps_input (size:192b/24B) */
-struct hwrm_port_mac_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_port_mac_qcaps_output (size:128b/16B) */
-struct hwrm_port_mac_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define PORT_MAC_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED     0x1UL
-	#define PORT_MAC_QCAPS_RESP_FLAGS_REMOTE_LPBK_SUPPORTED        0x2UL
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_queue_qportcfg_input (size:192b/24B) */
-struct hwrm_queue_qportcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH     0x1UL
-	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_TX    0x0UL
-	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_RX    0x1UL
-	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_LAST QUEUE_QPORTCFG_REQ_FLAGS_PATH_RX
-	__le16	port_id;
-	u8	drv_qmap_cap;
-	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_DISABLED 0x0UL
-	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_ENABLED  0x1UL
-	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_LAST    QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_ENABLED
-	u8	unused_0;
-};
-
-/* hwrm_queue_qportcfg_output (size:1344b/168B) */
-struct hwrm_queue_qportcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	max_configurable_queues;
-	u8	max_configurable_lossless_queues;
-	u8	queue_cfg_allowed;
-	u8	queue_cfg_info;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG             0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_USE_PROFILE_TYPE     0x2UL
-	u8	queue_pfcenable_cfg_allowed;
-	u8	queue_pri2cos_cfg_allowed;
-	u8	queue_cos2bw_cfg_allowed;
-	u8	queue_id0;
-	u8	queue_id0_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id1;
-	u8	queue_id1_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id2;
-	u8	queue_id2_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id3;
-	u8	queue_id3_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id4;
-	u8	queue_id4_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id5;
-	u8	queue_id5_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id6;
-	u8	queue_id6_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id7;
-	u8	queue_id7_service_profile;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY          0x0UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS       0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN        0xffUL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN
-	u8	queue_id0_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	char	qid0_name[16];
-	char	qid1_name[16];
-	char	qid2_name[16];
-	char	qid3_name[16];
-	char	qid4_name[16];
-	char	qid5_name[16];
-	char	qid6_name[16];
-	char	qid7_name[16];
-	u8	queue_id1_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id2_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id3_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id4_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id5_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id6_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	queue_id7_service_profile_type;
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_ROCE     0x1UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_NIC      0x2UL
-	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_CNP      0x4UL
-	u8	valid;
-};
-
-/* hwrm_queue_qcfg_input (size:192b/24B) */
-struct hwrm_queue_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_QCFG_REQ_FLAGS_PATH     0x1UL
-	#define QUEUE_QCFG_REQ_FLAGS_PATH_TX    0x0UL
-	#define QUEUE_QCFG_REQ_FLAGS_PATH_RX    0x1UL
-	#define QUEUE_QCFG_REQ_FLAGS_PATH_LAST QUEUE_QCFG_REQ_FLAGS_PATH_RX
-	__le32	queue_id;
-};
-
-/* hwrm_queue_qcfg_output (size:128b/16B) */
-struct hwrm_queue_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	queue_len;
-	u8	service_profile;
-	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSY    0x0UL
-	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSLESS 0x1UL
-	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN  0xffUL
-	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LAST    QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN
-	u8	queue_cfg_info;
-	#define QUEUE_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG     0x1UL
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_queue_cfg_input (size:320b/40B) */
-struct hwrm_queue_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_CFG_REQ_FLAGS_PATH_MASK 0x3UL
-	#define QUEUE_CFG_REQ_FLAGS_PATH_SFT  0
-	#define QUEUE_CFG_REQ_FLAGS_PATH_TX     0x0UL
-	#define QUEUE_CFG_REQ_FLAGS_PATH_RX     0x1UL
-	#define QUEUE_CFG_REQ_FLAGS_PATH_BIDIR  0x2UL
-	#define QUEUE_CFG_REQ_FLAGS_PATH_LAST  QUEUE_CFG_REQ_FLAGS_PATH_BIDIR
-	__le32	enables;
-	#define QUEUE_CFG_REQ_ENABLES_DFLT_LEN            0x1UL
-	#define QUEUE_CFG_REQ_ENABLES_SERVICE_PROFILE     0x2UL
-	__le32	queue_id;
-	__le32	dflt_len;
-	u8	service_profile;
-	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSY    0x0UL
-	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSLESS 0x1UL
-	#define QUEUE_CFG_REQ_SERVICE_PROFILE_UNKNOWN  0xffUL
-	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LAST    QUEUE_CFG_REQ_SERVICE_PROFILE_UNKNOWN
-	u8	unused_0[7];
-};
-
-/* hwrm_queue_cfg_output (size:128b/16B) */
-struct hwrm_queue_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_queue_pfcenable_qcfg_input (size:192b/24B) */
-struct hwrm_queue_pfcenable_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_queue_pfcenable_qcfg_output (size:128b/16B) */
-struct hwrm_queue_pfcenable_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_ENABLED              0x1UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_ENABLED              0x2UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_ENABLED              0x4UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_ENABLED              0x8UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_ENABLED              0x10UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_ENABLED              0x20UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_ENABLED              0x40UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_ENABLED              0x80UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
-	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_queue_pfcenable_cfg_input (size:192b/24B) */
-struct hwrm_queue_pfcenable_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_ENABLED              0x1UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_ENABLED              0x2UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_ENABLED              0x4UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_ENABLED              0x8UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_ENABLED              0x10UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_ENABLED              0x20UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_ENABLED              0x40UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_ENABLED              0x80UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
-	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
-	__le16	port_id;
-	u8	unused_0[2];
-};
-
-/* hwrm_queue_pfcenable_cfg_output (size:128b/16B) */
-struct hwrm_queue_pfcenable_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_queue_pri2cos_qcfg_input (size:192b/24B) */
-struct hwrm_queue_pri2cos_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH      0x1UL
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_TX     0x0UL
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_RX     0x1UL
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_LAST  QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_RX
-	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN     0x2UL
-	u8	port_id;
-	u8	unused_0[3];
-};
-
-/* hwrm_queue_pri2cos_qcfg_output (size:192b/24B) */
-struct hwrm_queue_pri2cos_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	pri0_cos_queue_id;
-	u8	pri1_cos_queue_id;
-	u8	pri2_cos_queue_id;
-	u8	pri3_cos_queue_id;
-	u8	pri4_cos_queue_id;
-	u8	pri5_cos_queue_id;
-	u8	pri6_cos_queue_id;
-	u8	pri7_cos_queue_id;
-	u8	queue_cfg_info;
-	#define QUEUE_PRI2COS_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG     0x1UL
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_queue_pri2cos_cfg_input (size:320b/40B) */
-struct hwrm_queue_pri2cos_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_MASK 0x3UL
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_SFT  0
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_TX     0x0UL
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_RX     0x1UL
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR  0x2UL
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_LAST  QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR
-	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_IVLAN     0x4UL
-	__le32	enables;
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI0_COS_QUEUE_ID     0x1UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI1_COS_QUEUE_ID     0x2UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI2_COS_QUEUE_ID     0x4UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI3_COS_QUEUE_ID     0x8UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI4_COS_QUEUE_ID     0x10UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI5_COS_QUEUE_ID     0x20UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI6_COS_QUEUE_ID     0x40UL
-	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI7_COS_QUEUE_ID     0x80UL
-	u8	port_id;
-	u8	pri0_cos_queue_id;
-	u8	pri1_cos_queue_id;
-	u8	pri2_cos_queue_id;
-	u8	pri3_cos_queue_id;
-	u8	pri4_cos_queue_id;
-	u8	pri5_cos_queue_id;
-	u8	pri6_cos_queue_id;
-	u8	pri7_cos_queue_id;
-	u8	unused_0[7];
-};
-
-/* hwrm_queue_pri2cos_cfg_output (size:128b/16B) */
-struct hwrm_queue_pri2cos_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_queue_cos2bw_qcfg_input (size:192b/24B) */
-struct hwrm_queue_cos2bw_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_queue_cos2bw_qcfg_output (size:896b/112B) */
-struct hwrm_queue_cos2bw_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	queue_id0;
-	u8	unused_0;
-	__le16	unused_1;
-	__le32	queue_id0_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id0_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id0_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id0_pri_lvl;
-	u8	queue_id0_bw_weight;
-	struct {
-		u8	queue_id;
-		__le32	queue_id_min_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
-		__le32	queue_id_max_bw;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
-		u8	queue_id_tsa_assign;
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
-		u8	queue_id_pri_lvl;
-		u8	queue_id_bw_weight;
-	} __packed cfg[7];
-	u8	unused_2[4];
-	u8	valid;
-};
-
-/* hwrm_queue_cos2bw_cfg_input (size:1024b/128B) */
-struct hwrm_queue_cos2bw_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	__le32	enables;
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID     0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID1_VALID     0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID2_VALID     0x4UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID3_VALID     0x8UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID4_VALID     0x10UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID5_VALID     0x20UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID6_VALID     0x40UL
-	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID7_VALID     0x80UL
-	__le16	port_id;
-	u8	queue_id0;
-	u8	unused_0;
-	__le32	queue_id0_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID
-	__le32	queue_id0_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	queue_id0_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
-	u8	queue_id0_pri_lvl;
-	u8	queue_id0_bw_weight;
-	struct {
-		u8	queue_id;
-		__le32	queue_id_min_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
-		__le32	queue_id_max_bw;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
-		u8	queue_id_tsa_assign;
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
-	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
-		u8	queue_id_pri_lvl;
-		u8	queue_id_bw_weight;
-	} __packed cfg[7];
-	u8	unused_1[5];
-};
-
-/* hwrm_queue_cos2bw_cfg_output (size:128b/16B) */
-struct hwrm_queue_cos2bw_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_queue_dscp_qcaps_input (size:192b/24B) */
-struct hwrm_queue_dscp_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	port_id;
-	u8	unused_0[7];
-};
-
-/* hwrm_queue_dscp_qcaps_output (size:128b/16B) */
-struct hwrm_queue_dscp_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_dscp_bits;
-	u8	unused_0;
-	__le16	max_entries;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_queue_dscp2pri_qcfg_input (size:256b/32B) */
-struct hwrm_queue_dscp2pri_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	dest_data_addr;
-	u8	port_id;
-	u8	unused_0;
-	__le16	dest_data_buffer_size;
-	u8	unused_1[4];
-};
-
-/* hwrm_queue_dscp2pri_qcfg_output (size:128b/16B) */
-struct hwrm_queue_dscp2pri_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	entry_cnt;
-	u8	default_pri;
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* hwrm_queue_dscp2pri_cfg_input (size:320b/40B) */
-struct hwrm_queue_dscp2pri_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	src_data_addr;
-	__le32	flags;
-	#define QUEUE_DSCP2PRI_CFG_REQ_FLAGS_USE_HW_DEFAULT_PRI     0x1UL
-	__le32	enables;
-	#define QUEUE_DSCP2PRI_CFG_REQ_ENABLES_DEFAULT_PRI     0x1UL
-	u8	port_id;
-	u8	default_pri;
-	__le16	entry_cnt;
-	u8	unused_0[4];
-};
-
-/* hwrm_queue_dscp2pri_cfg_output (size:128b/16B) */
-struct hwrm_queue_dscp2pri_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_alloc_input (size:192b/24B) */
-struct hwrm_vnic_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define VNIC_ALLOC_REQ_FLAGS_DEFAULT                  0x1UL
-	#define VNIC_ALLOC_REQ_FLAGS_VIRTIO_NET_FID_VALID     0x2UL
-	#define VNIC_ALLOC_REQ_FLAGS_VNIC_ID_VALID            0x4UL
-	__le16	virtio_net_fid;
-	__le16	vnic_id;
-};
-
-/* hwrm_vnic_alloc_output (size:128b/16B) */
-struct hwrm_vnic_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	vnic_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_vnic_update_input (size:256b/32B) */
-struct hwrm_vnic_update_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	vnic_id;
-	__le32	enables;
-	#define VNIC_UPDATE_REQ_ENABLES_VNIC_STATE_VALID               0x1UL
-	#define VNIC_UPDATE_REQ_ENABLES_MRU_VALID                      0x2UL
-	#define VNIC_UPDATE_REQ_ENABLES_METADATA_FORMAT_TYPE_VALID     0x4UL
-	u8	vnic_state;
-	#define VNIC_UPDATE_REQ_VNIC_STATE_NORMAL 0x0UL
-	#define VNIC_UPDATE_REQ_VNIC_STATE_DROP   0x1UL
-	#define VNIC_UPDATE_REQ_VNIC_STATE_LAST  VNIC_UPDATE_REQ_VNIC_STATE_DROP
-	u8	metadata_format_type;
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_0 0x0UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_1 0x1UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_2 0x2UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_3 0x3UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 0x4UL
-	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_LAST VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4
-	__le16	mru;
-	u8	unused_1[4];
-};
-
-/* hwrm_vnic_update_output (size:128b/16B) */
-struct hwrm_vnic_update_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_free_input (size:192b/24B) */
-struct hwrm_vnic_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	vnic_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_vnic_free_output (size:128b/16B) */
-struct hwrm_vnic_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_cfg_input (size:384b/48B) */
-struct hwrm_vnic_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define VNIC_CFG_REQ_FLAGS_DEFAULT                              0x1UL
-	#define VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE                      0x2UL
-	#define VNIC_CFG_REQ_FLAGS_BD_STALL_MODE                        0x4UL
-	#define VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE                  0x8UL
-	#define VNIC_CFG_REQ_FLAGS_ROCE_ONLY_VNIC_MODE                  0x10UL
-	#define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE                     0x20UL
-	#define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE     0x40UL
-	#define VNIC_CFG_REQ_FLAGS_PORTCOS_MAPPING_MODE                 0x80UL
-	__le32	enables;
-	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP            0x1UL
-	#define VNIC_CFG_REQ_ENABLES_RSS_RULE                 0x2UL
-	#define VNIC_CFG_REQ_ENABLES_COS_RULE                 0x4UL
-	#define VNIC_CFG_REQ_ENABLES_LB_RULE                  0x8UL
-	#define VNIC_CFG_REQ_ENABLES_MRU                      0x10UL
-	#define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID       0x20UL
-	#define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID     0x40UL
-	#define VNIC_CFG_REQ_ENABLES_QUEUE_ID                 0x80UL
-	#define VNIC_CFG_REQ_ENABLES_RX_CSUM_V2_MODE          0x100UL
-	#define VNIC_CFG_REQ_ENABLES_L2_CQE_MODE              0x200UL
-	#define VNIC_CFG_REQ_ENABLES_RAW_QP_ID                0x400UL
-	__le16	vnic_id;
-	__le16	dflt_ring_grp;
-	__le16	rss_rule;
-	__le16	cos_rule;
-	__le16	lb_rule;
-	__le16	mru;
-	__le16	default_rx_ring_id;
-	__le16	default_cmpl_ring_id;
-	__le16	queue_id;
-	u8	rx_csum_v2_mode;
-	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_DEFAULT 0x0UL
-	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_ALL_OK  0x1UL
-	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX     0x2UL
-	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_LAST   VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX
-	u8	l2_cqe_mode;
-	#define VNIC_CFG_REQ_L2_CQE_MODE_DEFAULT    0x0UL
-	#define VNIC_CFG_REQ_L2_CQE_MODE_COMPRESSED 0x1UL
-	#define VNIC_CFG_REQ_L2_CQE_MODE_MIXED      0x2UL
-	#define VNIC_CFG_REQ_L2_CQE_MODE_LAST      VNIC_CFG_REQ_L2_CQE_MODE_MIXED
-	__le32	raw_qp_id;
-};
-
-/* hwrm_vnic_cfg_output (size:128b/16B) */
-struct hwrm_vnic_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_qcaps_input (size:192b/24B) */
-struct hwrm_vnic_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	u8	unused_0[4];
-};
-
-/* hwrm_vnic_qcaps_output (size:192b/24B) */
-struct hwrm_vnic_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	mru;
-	u8	unused_0[2];
-	__le32	flags;
-	#define VNIC_QCAPS_RESP_FLAGS_UNUSED                                  0x1UL
-	#define VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP                          0x2UL
-	#define VNIC_QCAPS_RESP_FLAGS_BD_STALL_CAP                            0x4UL
-	#define VNIC_QCAPS_RESP_FLAGS_ROCE_DUAL_VNIC_CAP                      0x8UL
-	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP                      0x10UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP                         0x20UL
-	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP         0x40UL
-	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP                       0x80UL
-	#define VNIC_QCAPS_RESP_FLAGS_COS_ASSIGNMENT_CAP                      0x100UL
-	#define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V2_CAP                          0x200UL
-	#define VNIC_QCAPS_RESP_FLAGS_VNIC_STATE_CAP                          0x400UL
-	#define VNIC_QCAPS_RESP_FLAGS_VIRTIO_NET_VNIC_ALLOC_CAP               0x800UL
-	#define VNIC_QCAPS_RESP_FLAGS_METADATA_FORMAT_CAP                     0x1000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_STRICT_HASH_TYPE_CAP                0x2000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP                 0x4000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_TOEPLITZ_CAP           0x8000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_XOR_CAP                0x10000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_TOEPLITZ_CHKSM_CAP     0x20000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPV6_FLOW_LABEL_CAP                 0x40000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V3_CAP                          0x80000UL
-	#define VNIC_QCAPS_RESP_FLAGS_L2_CQE_MODE_CAP                         0x100000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV4_CAP               0x200000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV4_CAP              0x400000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV6_CAP               0x800000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP              0x1000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_TRUSTED_VF_CAP            0x2000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_PORTCOS_MAPPING_MODE                    0x4000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED              0x8000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_VNIC_RSS_HASH_MODE_CAP                  0x10000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP                       0x20000000UL
-	#define VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP                            0x40000000UL
-	__le16	max_aggs_supported;
-	u8	unused_1[5];
-	u8	valid;
-};
-
-/* hwrm_vnic_tpa_cfg_input (size:384b/48B) */
-struct hwrm_vnic_tpa_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define VNIC_TPA_CFG_REQ_FLAGS_TPA                       0x1UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_ENCAP_TPA                 0x2UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_RSC_WND_UPDATE            0x4UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_GRO                       0x8UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_ECN              0x10UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_IPID_CHECK            0x40UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_TTL_CHECK             0x80UL
-	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_PACK_AS_GRO           0x100UL
-	__le32	enables;
-	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_SEGS      0x1UL
-	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS          0x2UL
-	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_TIMER     0x4UL
-	#define VNIC_TPA_CFG_REQ_ENABLES_MIN_AGG_LEN       0x8UL
-	#define VNIC_TPA_CFG_REQ_ENABLES_TNL_TPA_EN        0x10UL
-	__le16	vnic_id;
-	__le16	max_agg_segs;
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_1   0x0UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_2   0x1UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_4   0x2UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_8   0x3UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_MAX 0x1fUL
-	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_LAST VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_MAX
-	__le16	max_aggs;
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_1   0x0UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_2   0x1UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_4   0x2UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_8   0x3UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_16  0x4UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_MAX 0x7UL
-	#define VNIC_TPA_CFG_REQ_MAX_AGGS_LAST VNIC_TPA_CFG_REQ_MAX_AGGS_MAX
-	u8	unused_0[2];
-	__le32	max_agg_timer;
-	__le32	min_agg_len;
-	__le32	tnl_tpa_en_bitmap;
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN           0x1UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GENEVE          0x2UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_NVGRE           0x4UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE             0x8UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV4            0x10UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV6            0x20UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_GPE       0x40UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_CUST1     0x80UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE_CUST1       0x100UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR1           0x200UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR2           0x400UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR3           0x800UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR4           0x1000UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR5           0x2000UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR6           0x4000UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR7           0x8000UL
-	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR8           0x10000UL
-	u8	unused_1[4];
-};
-
-/* hwrm_vnic_tpa_cfg_output (size:128b/16B) */
-struct hwrm_vnic_tpa_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_tpa_qcfg_input (size:192b/24B) */
-struct hwrm_vnic_tpa_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vnic_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_vnic_tpa_qcfg_output (size:256b/32B) */
-struct hwrm_vnic_tpa_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define VNIC_TPA_QCFG_RESP_FLAGS_TPA                       0x1UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_ENCAP_TPA                 0x2UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_RSC_WND_UPDATE            0x4UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO                       0x8UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_AGG_WITH_ECN              0x10UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO_IPID_CHECK            0x40UL
-	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO_TTL_CHECK             0x80UL
-	__le16	max_agg_segs;
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_1   0x0UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_2   0x1UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_4   0x2UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_8   0x3UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_MAX 0x1fUL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_LAST VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_MAX
-	__le16	max_aggs;
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_1   0x0UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_2   0x1UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_4   0x2UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_8   0x3UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_16  0x4UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_MAX 0x7UL
-	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_LAST VNIC_TPA_QCFG_RESP_MAX_AGGS_MAX
-	__le32	max_agg_timer;
-	__le32	min_agg_len;
-	__le32	tnl_tpa_en_bitmap;
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN           0x1UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GENEVE          0x2UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_NVGRE           0x4UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GRE             0x8UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_IPV4            0x10UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_IPV6            0x20UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN_GPE       0x40UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN_CUST1     0x80UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GRE_CUST1       0x100UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR1           0x200UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR2           0x400UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR3           0x800UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR4           0x1000UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR5           0x2000UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR6           0x4000UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR7           0x8000UL
-	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR8           0x10000UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_vnic_rss_cfg_input (size:384b/48B) */
-struct hwrm_vnic_rss_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	hash_type;
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4                0x1UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4            0x2UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4            0x4UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6                0x8UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6            0x10UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6            0x20UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL     0x40UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV4         0x80UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV4        0x100UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV6         0x200UL
-	#define VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV6        0x400UL
-	__le16	vnic_id;
-	u8	ring_table_pair_index;
-	u8	hash_mode_flags;
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT         0x1UL
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
-	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
-	__le64	ring_grp_tbl_addr;
-	__le64	hash_key_tbl_addr;
-	__le16	rss_ctx_idx;
-	u8	flags;
-	#define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_INCLUDE               0x1UL
-	#define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_EXCLUDE               0x2UL
-	#define VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT     0x4UL
-	u8	ring_select_mode;
-	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ          0x0UL
-	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_XOR               0x1UL
-	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL
-	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_LAST             VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ_CHECKSUM
-	u8	unused_1[4];
-};
-
-/* hwrm_vnic_rss_cfg_output (size:128b/16B) */
-struct hwrm_vnic_rss_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_rss_cfg_cmd_err (size:64b/8B) */
-struct hwrm_vnic_rss_cfg_cmd_err {
-	u8	code;
-	#define VNIC_RSS_CFG_CMD_ERR_CODE_UNKNOWN             0x0UL
-	#define VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY 0x1UL
-	#define VNIC_RSS_CFG_CMD_ERR_CODE_LAST               VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY
-	u8	unused_0[7];
-};
-
-/* hwrm_vnic_rss_qcfg_input (size:192b/24B) */
-struct hwrm_vnic_rss_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	rss_ctx_idx;
-	__le16	vnic_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_vnic_rss_qcfg_output (size:512b/64B) */
-struct hwrm_vnic_rss_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	hash_type;
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV4                0x1UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV4            0x2UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV4            0x4UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6                0x8UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV6            0x10UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV6            0x20UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6_FLOW_LABEL     0x40UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV4         0x80UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV4        0x100UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV6         0x200UL
-	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV6        0x400UL
-	u8	unused_0[4];
-	__le32	hash_key[10];
-	u8	hash_mode_flags;
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_DEFAULT         0x1UL
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
-	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
-	u8	ring_select_mode;
-	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ          0x0UL
-	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_XOR               0x1UL
-	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL
-	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_LAST             VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM
-	u8	unused_1[5];
-	u8	valid;
-};
-
-/* hwrm_vnic_plcmodes_cfg_input (size:320b/40B) */
-struct hwrm_vnic_plcmodes_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_REGULAR_PLACEMENT     0x1UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT       0x2UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4              0x4UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6              0x8UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_FCOE              0x10UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_ROCE              0x20UL
-	#define VNIC_PLCMODES_CFG_REQ_FLAGS_VIRTIO_PLACEMENT      0x40UL
-	__le32	enables;
-	#define VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID      0x1UL
-	#define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_OFFSET_VALID        0x2UL
-	#define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID     0x4UL
-	#define VNIC_PLCMODES_CFG_REQ_ENABLES_MAX_BDS_VALID           0x8UL
-	__le32	vnic_id;
-	__le16	jumbo_thresh;
-	__le16	hds_offset;
-	__le16	hds_threshold;
-	__le16	max_bds;
-	u8	unused_0[4];
-};
-
-/* hwrm_vnic_plcmodes_cfg_output (size:128b/16B) */
-struct hwrm_vnic_plcmodes_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vnic_plcmodes_cfg_cmd_err (size:64b/8B) */
-struct hwrm_vnic_plcmodes_cfg_cmd_err {
-	u8	code;
-	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_UNKNOWN               0x0UL
-	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD 0x1UL
-	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_LAST                 VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD
-	u8	unused_0[7];
-};
-
-/* hwrm_vnic_rss_cos_lb_ctx_alloc_input (size:128b/16B) */
-struct hwrm_vnic_rss_cos_lb_ctx_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_vnic_rss_cos_lb_ctx_alloc_output (size:128b/16B) */
-struct hwrm_vnic_rss_cos_lb_ctx_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	rss_cos_lb_ctx_id;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_vnic_rss_cos_lb_ctx_free_input (size:192b/24B) */
-struct hwrm_vnic_rss_cos_lb_ctx_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	rss_cos_lb_ctx_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_vnic_rss_cos_lb_ctx_free_output (size:128b/16B) */
-struct hwrm_vnic_rss_cos_lb_ctx_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_ring_alloc_input (size:704b/88B) */
-struct hwrm_ring_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG              0x2UL
-	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID         0x8UL
-	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID              0x20UL
-	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID          0x40UL
-	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID          0x80UL
-	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID         0x100UL
-	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID                   0x200UL
-	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE            0x400UL
-	#define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID        0x800UL
-	#define RING_ALLOC_REQ_ENABLES_RX_RATE_PROFILE_VALID     0x1000UL
-	u8	ring_type;
-	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
-	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
-	#define RING_ALLOC_REQ_RING_TYPE_RX        0x2UL
-	#define RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_ALLOC_REQ_RING_TYPE_RX_AGG    0x4UL
-	#define RING_ALLOC_REQ_RING_TYPE_NQ        0x5UL
-	#define RING_ALLOC_REQ_RING_TYPE_LAST     RING_ALLOC_REQ_RING_TYPE_NQ
-	u8	cmpl_coal_cnt;
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_OFF 0x0UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_4   0x1UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_8   0x2UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_12  0x3UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_16  0x4UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_24  0x5UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_32  0x6UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_48  0x7UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_64  0x8UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_96  0x9UL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_128 0xaUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_192 0xbUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_256 0xcUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_320 0xdUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_384 0xeUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX 0xfUL
-	#define RING_ALLOC_REQ_CMPL_COAL_CNT_LAST    RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX
-	__le16	flags;
-	#define RING_ALLOC_REQ_FLAGS_RX_SOP_PAD                        0x1UL
-	#define RING_ALLOC_REQ_FLAGS_DISABLE_CQ_OVERFLOW_DETECTION     0x2UL
-	#define RING_ALLOC_REQ_FLAGS_NQ_DBR_PACING                     0x4UL
-	#define RING_ALLOC_REQ_FLAGS_TX_PKT_TS_CMPL_ENABLE             0x8UL
-	__le64	page_tbl_addr;
-	__le32	fbo;
-	u8	page_size;
-	u8	page_tbl_depth;
-	__le16	schq_id;
-	__le32	length;
-	__le16	logical_id;
-	__le16	cmpl_ring_id;
-	__le16	queue_id;
-	__le16	rx_buf_size;
-	__le16	rx_ring_id;
-	__le16	nq_ring_id;
-	__le16	ring_arb_cfg;
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_MASK      0xfUL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SFT       0
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SP          0x1UL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_WFQ         0x2UL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_LAST       RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_WFQ
-	#define RING_ALLOC_REQ_RING_ARB_CFG_RSVD_MASK            0xf0UL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_RSVD_SFT             4
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_PARAM_MASK 0xff00UL
-	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_PARAM_SFT 8
-	__le16	steering_tag;
-	__le32	reserved3;
-	__le32	stat_ctx_id;
-	__le32	reserved4;
-	__le32	max_bw;
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_MASK             0xfffffffUL
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_SFT              0
-	#define RING_ALLOC_REQ_MAX_BW_SCALE                     0x10000000UL
-	#define RING_ALLOC_REQ_MAX_BW_SCALE_BITS                  (0x0UL << 28)
-	#define RING_ALLOC_REQ_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
-	#define RING_ALLOC_REQ_MAX_BW_SCALE_LAST                 RING_ALLOC_REQ_MAX_BW_SCALE_BYTES
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_SFT         29
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
-	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_LAST         RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_INVALID
-	u8	int_mode;
-	#define RING_ALLOC_REQ_INT_MODE_LEGACY 0x0UL
-	#define RING_ALLOC_REQ_INT_MODE_RSVD   0x1UL
-	#define RING_ALLOC_REQ_INT_MODE_MSIX   0x2UL
-	#define RING_ALLOC_REQ_INT_MODE_POLL   0x3UL
-	#define RING_ALLOC_REQ_INT_MODE_LAST  RING_ALLOC_REQ_INT_MODE_POLL
-	u8	mpc_chnls_type;
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TCE     0x0UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RCE     0x1UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TE_CFA  0x2UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RE_CFA  0x3UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE 0x4UL
-	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_LAST   RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE
-	u8	rx_rate_profile_sel;
-	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_DEFAULT   0x0UL
-	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE 0x1UL
-	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_LAST     RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE
-	u8	unused_4;
-	__le64	cq_handle;
-};
-
-/* hwrm_ring_alloc_output (size:128b/16B) */
-struct hwrm_ring_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	ring_id;
-	__le16	logical_ring_id;
-	u8	push_buffer_index;
-	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL
-	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL
-	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_LAST       RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER
-	u8	unused_0[2];
-	u8	valid;
-};
-
-/* hwrm_ring_free_input (size:256b/32B) */
-struct hwrm_ring_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	ring_type;
-	#define RING_FREE_REQ_RING_TYPE_L2_CMPL   0x0UL
-	#define RING_FREE_REQ_RING_TYPE_TX        0x1UL
-	#define RING_FREE_REQ_RING_TYPE_RX        0x2UL
-	#define RING_FREE_REQ_RING_TYPE_ROCE_CMPL 0x3UL
-	#define RING_FREE_REQ_RING_TYPE_RX_AGG    0x4UL
-	#define RING_FREE_REQ_RING_TYPE_NQ        0x5UL
-	#define RING_FREE_REQ_RING_TYPE_LAST     RING_FREE_REQ_RING_TYPE_NQ
-	u8	flags;
-	#define RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID 0x1UL
-	#define RING_FREE_REQ_FLAGS_LAST             RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID
-	__le16	ring_id;
-	__le32	prod_idx;
-	__le32	opaque;
-	__le32	unused_1;
-};
-
-/* hwrm_ring_free_output (size:128b/16B) */
-struct hwrm_ring_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_ring_reset_input (size:192b/24B) */
-struct hwrm_ring_reset_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	ring_type;
-	#define RING_RESET_REQ_RING_TYPE_L2_CMPL     0x0UL
-	#define RING_RESET_REQ_RING_TYPE_TX          0x1UL
-	#define RING_RESET_REQ_RING_TYPE_RX          0x2UL
-	#define RING_RESET_REQ_RING_TYPE_ROCE_CMPL   0x3UL
-	#define RING_RESET_REQ_RING_TYPE_RX_RING_GRP 0x6UL
-	#define RING_RESET_REQ_RING_TYPE_LAST       RING_RESET_REQ_RING_TYPE_RX_RING_GRP
-	u8	unused_0;
-	__le16	ring_id;
-	u8	unused_1[4];
-};
-
-/* hwrm_ring_reset_output (size:128b/16B) */
-struct hwrm_ring_reset_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	push_buffer_index;
-	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL
-	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL
-	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_LAST       RING_RESET_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER
-	u8	unused_0[3];
-	u8	consumer_idx[3];
-	u8	valid;
-};
-
-/* hwrm_ring_aggint_qcaps_input (size:128b/16B) */
-struct hwrm_ring_aggint_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_ring_aggint_qcaps_output (size:384b/48B) */
-struct hwrm_ring_aggint_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	cmpl_params;
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MIN                  0x1UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MAX                  0x2UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_TIMER_RESET                      0x4UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_RING_IDLE                        0x8UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR                0x10UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR_DURING_INT     0x20UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR                0x40UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR_DURING_INT     0x80UL
-	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_AGGR_INT                0x100UL
-	__le32	nq_params;
-	#define RING_AGGINT_QCAPS_RESP_NQ_PARAMS_INT_LAT_TMR_MIN     0x1UL
-	__le16	num_cmpl_dma_aggr_min;
-	__le16	num_cmpl_dma_aggr_max;
-	__le16	num_cmpl_dma_aggr_during_int_min;
-	__le16	num_cmpl_dma_aggr_during_int_max;
-	__le16	cmpl_aggr_dma_tmr_min;
-	__le16	cmpl_aggr_dma_tmr_max;
-	__le16	cmpl_aggr_dma_tmr_during_int_min;
-	__le16	cmpl_aggr_dma_tmr_during_int_max;
-	__le16	int_lat_tmr_min_min;
-	__le16	int_lat_tmr_min_max;
-	__le16	int_lat_tmr_max_min;
-	__le16	int_lat_tmr_max_max;
-	__le16	num_cmpl_aggr_int_min;
-	__le16	num_cmpl_aggr_int_max;
-	__le16	timer_units;
-	u8	unused_0[1];
-	u8	valid;
-};
-
-/* hwrm_ring_cmpl_ring_qaggint_params_input (size:192b/24B) */
-struct hwrm_ring_cmpl_ring_qaggint_params_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	ring_id;
-	__le16	flags;
-	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_MASK 0x3UL
-	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_SFT 0
-	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_IS_NQ        0x4UL
-	u8	unused_0[4];
-};
-
-/* hwrm_ring_cmpl_ring_qaggint_params_output (size:256b/32B) */
-struct hwrm_ring_cmpl_ring_qaggint_params_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	flags;
-	#define RING_CMPL_RING_QAGGINT_PARAMS_RESP_FLAGS_TIMER_RESET     0x1UL
-	#define RING_CMPL_RING_QAGGINT_PARAMS_RESP_FLAGS_RING_IDLE       0x2UL
-	__le16	num_cmpl_dma_aggr;
-	__le16	num_cmpl_dma_aggr_during_int;
-	__le16	cmpl_aggr_dma_tmr;
-	__le16	cmpl_aggr_dma_tmr_during_int;
-	__le16	int_lat_tmr_min;
-	__le16	int_lat_tmr_max;
-	__le16	num_cmpl_aggr_int;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_ring_cmpl_ring_cfg_aggint_params_input (size:320b/40B) */
-struct hwrm_ring_cmpl_ring_cfg_aggint_params_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	ring_id;
-	__le16	flags;
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET     0x1UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE       0x2UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_IS_NQ           0x4UL
-	__le16	num_cmpl_dma_aggr;
-	__le16	num_cmpl_dma_aggr_during_int;
-	__le16	cmpl_aggr_dma_tmr;
-	__le16	cmpl_aggr_dma_tmr_during_int;
-	__le16	int_lat_tmr_min;
-	__le16	int_lat_tmr_max;
-	__le16	num_cmpl_aggr_int;
-	__le16	enables;
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR                0x1UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR_DURING_INT     0x2UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_CMPL_AGGR_DMA_TMR                0x4UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MIN                  0x8UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MAX                  0x10UL
-	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_AGGR_INT                0x20UL
-	u8	unused_0[4];
-};
-
-/* hwrm_ring_cmpl_ring_cfg_aggint_params_output (size:128b/16B) */
-struct hwrm_ring_cmpl_ring_cfg_aggint_params_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_ring_grp_alloc_input (size:192b/24B) */
-struct hwrm_ring_grp_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	cr;
-	__le16	rr;
-	__le16	ar;
-	__le16	sc;
-};
-
-/* hwrm_ring_grp_alloc_output (size:128b/16B) */
-struct hwrm_ring_grp_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	ring_group_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_ring_grp_free_input (size:192b/24B) */
-struct hwrm_ring_grp_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	ring_group_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_ring_grp_free_output (size:128b/16B) */
-struct hwrm_ring_grp_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-#define DEFAULT_FLOW_ID 0xFFFFFFFFUL
-#define ROCEV1_FLOW_ID 0xFFFFFFFEUL
-#define ROCEV2_FLOW_ID 0xFFFFFFFDUL
-#define ROCEV2_CNP_FLOW_ID 0xFFFFFFFCUL
-
-/* hwrm_cfa_l2_filter_alloc_input (size:768b/96B) */
-struct hwrm_cfa_l2_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH              0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_TX             0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX             0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_LAST          CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_LOOPBACK          0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_DROP              0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST         0x8UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_MASK      0x30UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_SFT       4
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_NO_ROCE_L2  (0x0UL << 4)
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_L2          (0x1UL << 4)
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE        (0x2UL << 4)
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_LAST       CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_XDP_DISABLE       0x40UL
-	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_SOURCE_VALID      0x80UL
-	__le32	enables;
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR             0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK        0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_OVLAN            0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_OVLAN_MASK       0x8UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN            0x10UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN_MASK       0x20UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_ADDR           0x40UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_ADDR_MASK      0x80UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_OVLAN          0x100UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_OVLAN_MASK     0x200UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_IVLAN          0x400UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_IVLAN_MASK     0x800UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_TYPE            0x1000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_ID              0x2000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE         0x4000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID              0x8000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID      0x10000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS           0x20000UL
-	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_NUM_VLANS         0x40000UL
-	u8	l2_addr[6];
-	u8	num_vlans;
-	u8	t_num_vlans;
-	u8	l2_addr_mask[6];
-	__le16	l2_ovlan;
-	__le16	l2_ovlan_mask;
-	__le16	l2_ivlan;
-	__le16	l2_ivlan_mask;
-	u8	unused_1[2];
-	u8	t_l2_addr[6];
-	u8	unused_2[2];
-	u8	t_l2_addr_mask[6];
-	__le16	t_l2_ovlan;
-	__le16	t_l2_ovlan_mask;
-	__le16	t_l2_ivlan;
-	__le16	t_l2_ivlan_mask;
-	u8	src_type;
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_NPORT 0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_PF    0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_VF    0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_VNIC  0x3UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_KONG  0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_APE   0x5UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_BONO  0x6UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_TANG  0x7UL
-	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_LAST CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_TANG
-	u8	unused_3;
-	__le32	src_id;
-	u8	tunnel_type;
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-	u8	unused_4;
-	__le16	dst_id;
-	__le16	mirror_vnic_id;
-	u8	pri_hint;
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER    0x0UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_ABOVE_FILTER 0x1UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_BELOW_FILTER 0x2UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MAX          0x3UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MIN          0x4UL
-	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_LAST        CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MIN
-	u8	unused_5;
-	__le32	unused_6;
-	__le64	l2_filter_id_hint;
-};
-
-/* hwrm_cfa_l2_filter_alloc_output (size:192b/24B) */
-struct hwrm_cfa_l2_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	l2_filter_id;
-	__le32	flow_id;
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
-	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_l2_filter_free_input (size:192b/24B) */
-struct hwrm_cfa_l2_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	l2_filter_id;
-};
-
-/* hwrm_cfa_l2_filter_free_output (size:128b/16B) */
-struct hwrm_cfa_l2_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_l2_filter_cfg_input (size:384b/48B) */
-struct hwrm_cfa_l2_filter_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH                  0x1UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX                 0x0UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX                 0x1UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST              CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP                  0x2UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK          0xcUL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT           2
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2      (0x0UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2              (0x1UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE            (0x2UL << 2)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST           CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK         0x30UL
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT          4
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE      (0x0UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP    (0x1UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP    (0x2UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP  (0x3UL << 4)
-	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST          CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP
-	__le32	enables;
-	#define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID                 0x1UL
-	#define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID     0x2UL
-	#define CFA_L2_FILTER_CFG_REQ_ENABLES_PROF_FUNC              0x4UL
-	#define CFA_L2_FILTER_CFG_REQ_ENABLES_L2_CONTEXT_ID          0x8UL
-	__le64	l2_filter_id;
-	__le32	dst_id;
-	__le32	new_mirror_vnic_id;
-	__le32	prof_func;
-	__le32	l2_context_id;
-};
-
-/* hwrm_cfa_l2_filter_cfg_output (size:128b/16B) */
-struct hwrm_cfa_l2_filter_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_l2_set_rx_mask_input (size:448b/56B) */
-struct hwrm_cfa_l2_set_rx_mask_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	vnic_id;
-	__le32	mask;
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_MCAST               0x2UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST           0x4UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_BCAST               0x8UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS         0x10UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_OUTERMOST           0x20UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLANONLY            0x40UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLAN_NONVLAN        0x80UL
-	#define CFA_L2_SET_RX_MASK_REQ_MASK_ANYVLAN_NONVLAN     0x100UL
-	__le64	mc_tbl_addr;
-	__le32	num_mc_entries;
-	u8	unused_0[4];
-	__le64	vlan_tag_tbl_addr;
-	__le32	num_vlan_tags;
-	u8	unused_1[4];
-};
-
-/* hwrm_cfa_l2_set_rx_mask_output (size:128b/16B) */
-struct hwrm_cfa_l2_set_rx_mask_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_l2_set_rx_mask_cmd_err (size:64b/8B) */
-struct hwrm_cfa_l2_set_rx_mask_cmd_err {
-	u8	code;
-	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_UNKNOWN                    0x0UL
-	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR 0x1UL
-	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_LAST                      CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR
-	u8	unused_0[7];
-};
-
-/* hwrm_cfa_tunnel_filter_alloc_input (size:704b/88B) */
-struct hwrm_cfa_tunnel_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
-	__le32	enables;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID       0x1UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_ADDR            0x2UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN           0x4UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L3_ADDR            0x8UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L3_ADDR_TYPE       0x10UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_T_L3_ADDR_TYPE     0x20UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_T_L3_ADDR          0x40UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE        0x80UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_VNI                0x100UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_DST_VNIC_ID        0x200UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x400UL
-	__le64	l2_filter_id;
-	u8	l2_addr[6];
-	__le16	l2_ivlan;
-	__le32	l3_addr[4];
-	__le32	t_l3_addr[4];
-	u8	l3_addr_type;
-	u8	t_l3_addr_type;
-	u8	tunnel_type;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-	u8	tunnel_flags;
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_OAM_CHECKSUM_EXPLHDR     0x1UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_CRITICAL_OPT_S1          0x2UL
-	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_EXTHDR_SEQNUM_S0         0x4UL
-	__le32	vni;
-	__le32	dst_vnic_id;
-	__le32	mirror_vnic_id;
-};
-
-/* hwrm_cfa_tunnel_filter_alloc_output (size:192b/24B) */
-struct hwrm_cfa_tunnel_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	tunnel_filter_id;
-	__le32	flow_id;
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
-	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_tunnel_filter_free_input (size:192b/24B) */
-struct hwrm_cfa_tunnel_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	tunnel_filter_id;
-};
-
-/* hwrm_cfa_tunnel_filter_free_output (size:128b/16B) */
-struct hwrm_cfa_tunnel_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_vxlan_ipv4_hdr (size:128b/16B) */
-struct hwrm_vxlan_ipv4_hdr {
-	u8	ver_hlen;
-	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_MASK 0xfUL
-	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT 0
-	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_MASK      0xf0UL
-	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT       4
-	u8	tos;
-	__be16	ip_id;
-	__be16	flags_frag_offset;
-	u8	ttl;
-	u8	protocol;
-	__be32	src_ip_addr;
-	__be32	dest_ip_addr;
-};
-
-/* hwrm_vxlan_ipv6_hdr (size:320b/40B) */
-struct hwrm_vxlan_ipv6_hdr {
-	__be32	ver_tc_flow_label;
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_SFT         0x1cUL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_MASK        0xf0000000UL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_SFT          0x14UL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_MASK         0xff00000UL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_SFT  0x0UL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK 0xfffffUL
-	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_LAST           VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK
-	__be16	payload_len;
-	u8	next_hdr;
-	u8	ttl;
-	__be32	src_ip_addr[4];
-	__be32	dest_ip_addr[4];
-};
-
-/* hwrm_cfa_encap_data_vxlan (size:640b/80B) */
-struct hwrm_cfa_encap_data_vxlan {
-	u8	src_mac_addr[6];
-	__le16	unused_0;
-	u8	dst_mac_addr[6];
-	u8	num_vlan_tags;
-	u8	unused_1;
-	__be16	ovlan_tpid;
-	__be16	ovlan_tci;
-	__be16	ivlan_tpid;
-	__be16	ivlan_tci;
-	__le32	l3[10];
-	#define CFA_ENCAP_DATA_VXLAN_L3_VER_MASK 0xfUL
-	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV4 0x4UL
-	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6 0x6UL
-	#define CFA_ENCAP_DATA_VXLAN_L3_LAST    CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6
-	__be16	src_port;
-	__be16	dst_port;
-	__be32	vni;
-	u8	hdr_rsvd0[3];
-	u8	hdr_rsvd1;
-	u8	hdr_flags;
-	u8	unused[3];
-};
-
-/* hwrm_cfa_encap_record_alloc_input (size:832b/104B) */
-struct hwrm_cfa_encap_record_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_EXTERNAL     0x2UL
-	u8	encap_type;
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN        0x1UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE        0x2UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE        0x3UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP         0x4UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE       0x5UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS         0x6UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN         0x7UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE        0x8UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4     0x9UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1     0xaUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE     0xbUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST        CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE
-	u8	unused_0[3];
-	__le32	encap_data[20];
-};
-
-/* hwrm_cfa_encap_record_alloc_output (size:128b/16B) */
-struct hwrm_cfa_encap_record_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	encap_record_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_encap_record_free_input (size:192b/24B) */
-struct hwrm_cfa_encap_record_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	encap_record_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_cfa_encap_record_free_output (size:128b/16B) */
-struct hwrm_cfa_encap_record_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_ntuple_filter_alloc_input (size:1024b/128B) */
-struct hwrm_cfa_ntuple_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_LOOPBACK              0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP                  0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_METER                 0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_FID              0x8UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_ARP_REPLY             0x10UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX     0x20UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_NO_L2_CONTEXT         0x40UL
-	__le32	enables;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID         0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE            0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE          0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR          0x8UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE          0x10UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR           0x20UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR_MASK      0x40UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR           0x80UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR_MASK      0x100UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL          0x200UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT             0x400UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT_MASK        0x800UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT             0x1000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT_MASK        0x2000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_PRI_HINT             0x4000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_NTUPLE_FILTER_ID     0x8000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_ID               0x10000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID       0x20000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR          0x40000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_RFS_RING_TBL_IDX     0x80000UL
-	__le64	l2_filter_id;
-	u8	src_macaddr[6];
-	__be16	ethertype;
-	u8	ip_addr_type;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN 0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4    0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6    0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6
-	u8	ip_protocol;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP     0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP     0x11UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMP    0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMPV6  0x3aUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD    0xffUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD
-	__le16	dst_id;
-	__le16	rfs_ring_tbl_idx;
-	u8	tunnel_type;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-	u8	pri_hint;
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER 0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_ABOVE     0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_BELOW     0x2UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_HIGHEST   0x3UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST    0x4UL
-	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LAST     CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST
-	__be32	src_ipaddr[4];
-	__be32	src_ipaddr_mask[4];
-	__be32	dst_ipaddr[4];
-	__be32	dst_ipaddr_mask[4];
-	__be16	src_port;
-	__be16	src_port_mask;
-	__be16	dst_port;
-	__be16	dst_port_mask;
-	__le64	ntuple_filter_id_hint;
-};
-
-/* hwrm_cfa_ntuple_filter_alloc_output (size:192b/24B) */
-struct hwrm_cfa_ntuple_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	ntuple_filter_id;
-	__le32	flow_id;
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
-	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_ntuple_filter_alloc_cmd_err (size:64b/8B) */
-struct hwrm_cfa_ntuple_filter_alloc_cmd_err {
-	u8	code;
-	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_UNKNOWN                   0x0UL
-	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR 0x1UL
-	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_LAST                     CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR
-	u8	unused_0[7];
-};
-
-/* hwrm_cfa_ntuple_filter_free_input (size:192b/24B) */
-struct hwrm_cfa_ntuple_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	ntuple_filter_id;
-};
-
-/* hwrm_cfa_ntuple_filter_free_output (size:128b/16B) */
-struct hwrm_cfa_ntuple_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_ntuple_filter_cfg_input (size:384b/48B) */
-struct hwrm_cfa_ntuple_filter_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_ID                0x1UL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID        0x2UL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_METER_INSTANCE_ID     0x4UL
-	__le32	flags;
-	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_FID              0x1UL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_RFS_RING_IDX     0x2UL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_NO_L2_CONTEXT         0x4UL
-	__le64	ntuple_filter_id;
-	__le32	new_dst_id;
-	__le32	new_mirror_vnic_id;
-	__le16	new_meter_instance_id;
-	#define CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_INVALID 0xffffUL
-	#define CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_LAST   CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_INVALID
-	u8	unused_1[6];
-};
-
-/* hwrm_cfa_ntuple_filter_cfg_output (size:128b/16B) */
-struct hwrm_cfa_ntuple_filter_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_decap_filter_alloc_input (size:832b/104B) */
-struct hwrm_cfa_decap_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL     0x1UL
-	__le32	enables;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE        0x1UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID          0x2UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR        0x4UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR        0x8UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_OVLAN_VID          0x10UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IVLAN_VID          0x20UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_OVLAN_VID        0x40UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID        0x80UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE          0x100UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR         0x200UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR         0x400UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE        0x800UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL        0x1000UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_PORT           0x2000UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT           0x4000UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_ID             0x8000UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x10000UL
-	__be32	tunnel_id;
-	u8	tunnel_type;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-	u8	unused_0;
-	__le16	unused_1;
-	u8	src_macaddr[6];
-	u8	unused_2[2];
-	u8	dst_macaddr[6];
-	__be16	ovlan_vid;
-	__be16	ivlan_vid;
-	__be16	t_ovlan_vid;
-	__be16	t_ivlan_vid;
-	__be16	ethertype;
-	u8	ip_addr_type;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN 0x0UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4    0x4UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6    0x6UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_LAST   CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6
-	u8	ip_protocol;
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP     0x6UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP     0x11UL
-	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP
-	__le16	unused_3;
-	__le32	unused_4;
-	__be32	src_ipaddr[4];
-	__be32	dst_ipaddr[4];
-	__be16	src_port;
-	__be16	dst_port;
-	__le16	dst_id;
-	__le16	l2_ctxt_ref_id;
-};
-
-/* hwrm_cfa_decap_filter_alloc_output (size:128b/16B) */
-struct hwrm_cfa_decap_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	decap_filter_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_decap_filter_free_input (size:192b/24B) */
-struct hwrm_cfa_decap_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	decap_filter_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_cfa_decap_filter_free_output (size:128b/16B) */
-struct hwrm_cfa_decap_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_flow_alloc_input (size:1024b/128B) */
-struct hwrm_cfa_flow_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	flags;
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL                 0x1UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_MASK          0x6UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_SFT           1
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_NONE            (0x0UL << 1)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE             (0x1UL << 1)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO             (0x2UL << 1)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_LAST           CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_MASK          0x38UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_SFT           3
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2              (0x0UL << 3)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4            (0x1UL << 3)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6            (0x2UL << 3)
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_LAST           CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_TX                0x40UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_RX                0x80UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_MATCH_VXLAN_IP_VNI     0x100UL
-	#define CFA_FLOW_ALLOC_REQ_FLAGS_VHOST_ID_USE_VLAN      0x200UL
-	__le16	src_fid;
-	__le32	tunnel_handle;
-	__le16	action_flags;
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                       0x1UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE                   0x2UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                      0x4UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                     0x8UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                    0x10UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC                   0x20UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST                  0x40UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS          0x80UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE         0x100UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT             0x200UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP                 0x400UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FLOW_AGING_ENABLED        0x800UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_PRI_HINT                  0x1000UL
-	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NO_FLOW_COUNTER_ALLOC     0x2000UL
-	__le16	dst_fid;
-	__be16	l2_rewrite_vlan_tpid;
-	__be16	l2_rewrite_vlan_tci;
-	__le16	act_meter_id;
-	__le16	ref_flow_handle;
-	__be16	ethertype;
-	__be16	outer_vlan_tci;
-	__be16	dmac[3];
-	__be16	inner_vlan_tci;
-	__be16	smac[3];
-	u8	ip_dst_mask_len;
-	u8	ip_src_mask_len;
-	__be32	ip_dst[4];
-	__be32	ip_src[4];
-	__be16	l4_src_port;
-	__be16	l4_src_port_mask;
-	__be16	l4_dst_port;
-	__be16	l4_dst_port_mask;
-	__be32	nat_ip_address[4];
-	__be16	l2_rewrite_dmac[3];
-	__be16	nat_port;
-	__be16	l2_rewrite_smac[3];
-	u8	ip_proto;
-	u8	tunnel_type;
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
-	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
-};
-
-/* hwrm_cfa_flow_alloc_output (size:256b/32B) */
-struct hwrm_cfa_flow_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	flow_handle;
-	u8	unused_0[2];
-	__le32	flow_id;
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
-	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX
-	__le64	ext_flow_handle;
-	__le32	flow_counter_id;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_flow_alloc_cmd_err (size:64b/8B) */
-struct hwrm_cfa_flow_alloc_cmd_err {
-	u8	code;
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_UNKNOWN         0x0UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_L2_CONTEXT_TCAM 0x1UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_ACTION_RECORD   0x2UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_COUNTER    0x3UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_WILD_CARD_TCAM  0x4UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_HASH_COLLISION  0x5UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_KEY_EXISTS      0x6UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB    0x7UL
-	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_LAST           CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB
-	u8	unused_0[7];
-};
-
-/* hwrm_cfa_flow_free_input (size:256b/32B) */
-struct hwrm_cfa_flow_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	flow_handle;
-	__le16	unused_0;
-	__le32	flow_counter_id;
-	__le64	ext_flow_handle;
-};
-
-/* hwrm_cfa_flow_free_output (size:256b/32B) */
-struct hwrm_cfa_flow_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	packet;
-	__le64	byte;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_flow_info_input (size:256b/32B) */
-struct hwrm_cfa_flow_info_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	flow_handle;
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK      0xfffUL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT       0x1000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT    0x2000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_NIC_TX        0x3000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT    0x4000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX        0x8000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT_RX    0x9000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT_RX 0xa000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_NIC_RX        0xb000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT_RX 0xc000UL
-	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_LAST         CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT_RX
-	u8	unused_0[6];
-	__le64	ext_flow_handle;
-};
-
-/* hwrm_cfa_flow_info_output (size:5632b/704B) */
-struct hwrm_cfa_flow_info_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_TX     0x1UL
-	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_RX     0x2UL
-	u8	profile;
-	__le16	src_fid;
-	__le16	dst_fid;
-	__le16	l2_ctxt_id;
-	__le64	em_info;
-	__le64	tcam_info;
-	__le64	vfp_tcam_info;
-	__le16	ar_id;
-	__le16	flow_handle;
-	__le32	tunnel_handle;
-	__le16	flow_timer;
-	u8	unused_0[6];
-	__le32	flow_key_data[130];
-	__le32	flow_action_info[30];
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_flow_stats_input (size:640b/80B) */
-struct hwrm_cfa_flow_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	num_flows;
-	__le16	flow_handle_0;
-	__le16	flow_handle_1;
-	__le16	flow_handle_2;
-	__le16	flow_handle_3;
-	__le16	flow_handle_4;
-	__le16	flow_handle_5;
-	__le16	flow_handle_6;
-	__le16	flow_handle_7;
-	__le16	flow_handle_8;
-	__le16	flow_handle_9;
-	u8	unused_0[2];
-	__le32	flow_id_0;
-	__le32	flow_id_1;
-	__le32	flow_id_2;
-	__le32	flow_id_3;
-	__le32	flow_id_4;
-	__le32	flow_id_5;
-	__le32	flow_id_6;
-	__le32	flow_id_7;
-	__le32	flow_id_8;
-	__le32	flow_id_9;
-};
-
-/* hwrm_cfa_flow_stats_output (size:1408b/176B) */
-struct hwrm_cfa_flow_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	packet_0;
-	__le64	packet_1;
-	__le64	packet_2;
-	__le64	packet_3;
-	__le64	packet_4;
-	__le64	packet_5;
-	__le64	packet_6;
-	__le64	packet_7;
-	__le64	packet_8;
-	__le64	packet_9;
-	__le64	byte_0;
-	__le64	byte_1;
-	__le64	byte_2;
-	__le64	byte_3;
-	__le64	byte_4;
-	__le64	byte_5;
-	__le64	byte_6;
-	__le64	byte_7;
-	__le64	byte_8;
-	__le64	byte_9;
-	__le16	flow_hits;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_cfa_vfr_alloc_input (size:448b/56B) */
-struct hwrm_cfa_vfr_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	vf_id;
-	__le16	reserved;
-	u8	unused_0[4];
-	char	vfr_name[32];
-};
-
-/* hwrm_cfa_vfr_alloc_output (size:128b/16B) */
-struct hwrm_cfa_vfr_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	rx_cfa_code;
-	__le16	tx_cfa_action;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_cfa_vfr_free_input (size:448b/56B) */
-struct hwrm_cfa_vfr_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	char	vfr_name[32];
-	__le16	vf_id;
-	__le16	reserved;
-	u8	unused_0[4];
-};
-
-/* hwrm_cfa_vfr_free_output (size:128b/16B) */
-struct hwrm_cfa_vfr_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_eem_qcaps_input (size:192b/24B) */
-struct hwrm_cfa_eem_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_TX               0x1UL
-	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_RX               0x2UL
-	#define CFA_EEM_QCAPS_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
-	__le32	unused_0;
-};
-
-/* hwrm_cfa_eem_qcaps_output (size:320b/40B) */
-struct hwrm_cfa_eem_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_TX                                         0x1UL
-	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_RX                                         0x2UL
-	#define CFA_EEM_QCAPS_RESP_FLAGS_CENTRALIZED_MEMORY_MODEL_SUPPORTED              0x4UL
-	#define CFA_EEM_QCAPS_RESP_FLAGS_DETACHED_CENTRALIZED_MEMORY_MODEL_SUPPORTED     0x8UL
-	__le32	unused_0;
-	__le32	supported;
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY0_TABLE                       0x1UL
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY1_TABLE                       0x2UL
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_RECORD_TABLE            0x4UL
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_FLOW_COUNTERS_TABLE     0x8UL
-	#define CFA_EEM_QCAPS_RESP_SUPPORTED_FID_TABLE                        0x10UL
-	__le32	max_entries_supported;
-	__le16	key_entry_size;
-	__le16	record_entry_size;
-	__le16	efc_entry_size;
-	__le16	fid_entry_size;
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_eem_cfg_input (size:384b/48B) */
-struct hwrm_cfa_eem_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_EEM_CFG_REQ_FLAGS_PATH_TX               0x1UL
-	#define CFA_EEM_CFG_REQ_FLAGS_PATH_RX               0x2UL
-	#define CFA_EEM_CFG_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
-	#define CFA_EEM_CFG_REQ_FLAGS_SECONDARY_PF          0x8UL
-	__le16	group_id;
-	__le16	unused_0;
-	__le32	num_entries;
-	__le32	unused_1;
-	__le16	key0_ctx_id;
-	__le16	key1_ctx_id;
-	__le16	record_ctx_id;
-	__le16	efc_ctx_id;
-	__le16	fid_ctx_id;
-	__le16	unused_2;
-	__le32	unused_3;
-};
-
-/* hwrm_cfa_eem_cfg_output (size:128b/16B) */
-struct hwrm_cfa_eem_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_eem_qcfg_input (size:192b/24B) */
-struct hwrm_cfa_eem_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_TX     0x1UL
-	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_RX     0x2UL
-	__le32	unused_0;
-};
-
-/* hwrm_cfa_eem_qcfg_output (size:256b/32B) */
-struct hwrm_cfa_eem_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_TX               0x1UL
-	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX               0x2UL
-	#define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD     0x4UL
-	__le32	num_entries;
-	__le16	key0_ctx_id;
-	__le16	key1_ctx_id;
-	__le16	record_ctx_id;
-	__le16	efc_ctx_id;
-	__le16	fid_ctx_id;
-	u8	unused_2[5];
-	u8	valid;
-};
-
-/* hwrm_cfa_eem_op_input (size:192b/24B) */
-struct hwrm_cfa_eem_op_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define CFA_EEM_OP_REQ_FLAGS_PATH_TX     0x1UL
-	#define CFA_EEM_OP_REQ_FLAGS_PATH_RX     0x2UL
-	__le16	unused_0;
-	__le16	op;
-	#define CFA_EEM_OP_REQ_OP_RESERVED    0x0UL
-	#define CFA_EEM_OP_REQ_OP_EEM_DISABLE 0x1UL
-	#define CFA_EEM_OP_REQ_OP_EEM_ENABLE  0x2UL
-	#define CFA_EEM_OP_REQ_OP_EEM_CLEANUP 0x3UL
-	#define CFA_EEM_OP_REQ_OP_LAST       CFA_EEM_OP_REQ_OP_EEM_CLEANUP
-};
-
-/* hwrm_cfa_eem_op_output (size:128b/16B) */
-struct hwrm_cfa_eem_op_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_cfa_adv_flow_mgnt_qcaps_input (size:256b/32B) */
-struct hwrm_cfa_adv_flow_mgnt_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	unused_0[4];
-};
-
-/* hwrm_cfa_adv_flow_mgnt_qcaps_output (size:128b/16B) */
-struct hwrm_cfa_adv_flow_mgnt_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	flags;
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_16BIT_SUPPORTED                     0x1UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_64BIT_SUPPORTED                     0x2UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_BATCH_DELETE_SUPPORTED                  0x4UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_RESET_ALL_SUPPORTED                     0x8UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_DEST_FUNC_SUPPORTED              0x10UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TX_EEM_FLOW_SUPPORTED                        0x20UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RX_EEM_FLOW_SUPPORTED                        0x40UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_COUNTER_ALLOC_SUPPORTED                 0x80UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_SUPPORTED                   0x100UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_UNTAGGED_VLAN_SUPPORTED                      0x200UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_XDP_SUPPORTED                                0x400UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_HEADER_SOURCE_FIELDS_SUPPORTED            0x800UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ARP_SUPPORTED                 0x1000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V2_SUPPORTED                0x2000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ETHERTYPE_IP_SUPPORTED        0x4000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TRUFLOW_CAPABLE                              0x8000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_FILTER_TRAFFIC_TYPE_L2_ROCE_SUPPORTED     0x10000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_LAG_SUPPORTED                                0x20000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_NO_L2CTX_SUPPORTED               0x40000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NIC_FLOW_STATS_SUPPORTED                     0x80000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_EXT_IP_PROTO_SUPPORTED        0x100000UL
-	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V3_SUPPORTED                0x200000UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_tunnel_dst_port_query_input (size:192b/24B) */
-struct hwrm_tunnel_dst_port_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN              0x1UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE             0x5UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI              0xeUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6               0xfUL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE                0x11UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
-	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
-	u8	tunnel_next_proto;
-	u8	unused_0[6];
-};
-
-/* hwrm_tunnel_dst_port_query_output (size:128b/16B) */
-struct hwrm_tunnel_dst_port_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	tunnel_dst_port_id;
-	__be16	tunnel_dst_port_val;
-	u8	upar_in_use;
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR0     0x1UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR1     0x2UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR2     0x4UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR3     0x8UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR4     0x10UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR5     0x20UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR6     0x40UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR7     0x80UL
-	u8	status;
-	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_CHIP_LEVEL     0x1UL
-	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_FUNC_LEVEL     0x2UL
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_tunnel_dst_port_alloc_input (size:192b/24B) */
-struct hwrm_tunnel_dst_port_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN              0x1UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE             0x5UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI              0xeUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6               0xfUL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE                0x11UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
-	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
-	u8	tunnel_next_proto;
-	__be16	tunnel_dst_port_val;
-	u8	unused_0[4];
-};
-
-/* hwrm_tunnel_dst_port_alloc_output (size:128b/16B) */
-struct hwrm_tunnel_dst_port_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	tunnel_dst_port_id;
-	u8	error_info;
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_SUCCESS         0x0UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ALLOCATED   0x1UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE 0x2UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED     0x3UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST           TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED
-	u8	upar_in_use;
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR0     0x1UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR1     0x2UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR2     0x4UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR3     0x8UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR4     0x10UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR5     0x20UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR6     0x40UL
-	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR7     0x80UL
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_tunnel_dst_port_free_input (size:192b/24B) */
-struct hwrm_tunnel_dst_port_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	tunnel_type;
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN              0x1UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE             0x5UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI              0xeUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6               0xfUL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE                0x11UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
-	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
-	u8	tunnel_next_proto;
-	__le16	tunnel_dst_port_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_tunnel_dst_port_free_output (size:128b/16B) */
-struct hwrm_tunnel_dst_port_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	error_info;
-	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_SUCCESS           0x0UL
-	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_OWNER     0x1UL
-	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED 0x2UL
-	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_LAST             TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED
-	u8	unused_1[6];
-	u8	valid;
-};
-
-/* ctx_hw_stats (size:1280b/160B) */
-struct ctx_hw_stats {
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	tpa_pkts;
-	__le64	tpa_bytes;
-	__le64	tpa_events;
-	__le64	tpa_aborts;
-};
-
-/* ctx_hw_stats_ext (size:1408b/176B) */
-struct ctx_hw_stats_ext {
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_tpa_eligible_pkt;
-	__le64	rx_tpa_eligible_bytes;
-	__le64	rx_tpa_pkt;
-	__le64	rx_tpa_bytes;
-	__le64	rx_tpa_errors;
-	__le64	rx_tpa_events;
-};
-
-/* hwrm_stat_ctx_alloc_input (size:384b/48B) */
-struct hwrm_stat_ctx_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	stats_dma_addr;
-	__le32	update_period_ms;
-	u8	stat_ctx_flags;
-	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE             0x1UL
-	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_DUP_HOST_BUF     0x2UL
-	u8	unused_0;
-	__le16	stats_dma_length;
-	__le16	flags;
-	#define STAT_CTX_ALLOC_REQ_FLAGS_STEERING_TAG_VALID     0x1UL
-	__le16	steering_tag;
-	__le32	stat_ctx_id;
-	__le16	alloc_seq_id;
-	u8	unused_1[6];
-};
-
-/* hwrm_stat_ctx_alloc_output (size:128b/16B) */
-struct hwrm_stat_ctx_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	stat_ctx_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_stat_ctx_free_input (size:192b/24B) */
-struct hwrm_stat_ctx_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	stat_ctx_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_stat_ctx_free_output (size:128b/16B) */
-struct hwrm_stat_ctx_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	stat_ctx_id;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_stat_ctx_query_input (size:192b/24B) */
-struct hwrm_stat_ctx_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	stat_ctx_id;
-	u8	flags;
-	#define STAT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[3];
-};
-
-/* hwrm_stat_ctx_query_output (size:1408b/176B) */
-struct hwrm_stat_ctx_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	rx_agg_pkts;
-	__le64	rx_agg_bytes;
-	__le64	rx_agg_events;
-	__le64	rx_agg_aborts;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_stat_ext_ctx_query_input (size:192b/24B) */
-struct hwrm_stat_ext_ctx_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	stat_ctx_id;
-	u8	flags;
-	#define STAT_EXT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[3];
-};
-
-/* hwrm_stat_ext_ctx_query_output (size:1536b/192B) */
-struct hwrm_stat_ext_ctx_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	rx_ucast_pkts;
-	__le64	rx_mcast_pkts;
-	__le64	rx_bcast_pkts;
-	__le64	rx_discard_pkts;
-	__le64	rx_error_pkts;
-	__le64	rx_ucast_bytes;
-	__le64	rx_mcast_bytes;
-	__le64	rx_bcast_bytes;
-	__le64	tx_ucast_pkts;
-	__le64	tx_mcast_pkts;
-	__le64	tx_bcast_pkts;
-	__le64	tx_error_pkts;
-	__le64	tx_discard_pkts;
-	__le64	tx_ucast_bytes;
-	__le64	tx_mcast_bytes;
-	__le64	tx_bcast_bytes;
-	__le64	rx_tpa_eligible_pkt;
-	__le64	rx_tpa_eligible_bytes;
-	__le64	rx_tpa_pkt;
-	__le64	rx_tpa_bytes;
-	__le64	rx_tpa_errors;
-	__le64	rx_tpa_events;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_stat_ctx_clr_stats_input (size:192b/24B) */
-struct hwrm_stat_ctx_clr_stats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	stat_ctx_id;
-	u8	unused_0[4];
-};
-
-/* hwrm_stat_ctx_clr_stats_output (size:128b/16B) */
-struct hwrm_stat_ctx_clr_stats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_pcie_qstats_input (size:256b/32B) */
-struct hwrm_pcie_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	pcie_stat_size;
-	u8	unused_0[6];
-	__le64	pcie_stat_host_addr;
-};
-
-/* hwrm_pcie_qstats_output (size:128b/16B) */
-struct hwrm_pcie_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	pcie_stat_size;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* pcie_ctx_hw_stats (size:768b/96B) */
-struct pcie_ctx_hw_stats {
-	__le64	pcie_pl_signal_integrity;
-	__le64	pcie_dl_signal_integrity;
-	__le64	pcie_tl_signal_integrity;
-	__le64	pcie_link_integrity;
-	__le64	pcie_tx_traffic_rate;
-	__le64	pcie_rx_traffic_rate;
-	__le64	pcie_tx_dllp_statistics;
-	__le64	pcie_rx_dllp_statistics;
-	__le64	pcie_equalization_time;
-	__le32	pcie_ltssm_histogram[4];
-	__le64	pcie_recovery_histogram;
-};
-
-/* pcie_ctx_hw_stats_v2 (size:4096b/512B) */
-struct pcie_ctx_hw_stats_v2 {
-	__le64	pcie_pl_signal_integrity;
-	__le64	pcie_dl_signal_integrity;
-	__le64	pcie_tl_signal_integrity;
-	__le64	pcie_link_integrity;
-	__le64	pcie_tx_traffic_rate;
-	__le64	pcie_rx_traffic_rate;
-	__le64	pcie_tx_dllp_statistics;
-	__le64	pcie_rx_dllp_statistics;
-	__le64	pcie_equalization_time;
-	__le32	pcie_ltssm_histogram[4];
-	__le64	pcie_recovery_histogram;
-	__le32	pcie_tl_credit_nph_histogram[8];
-	__le32	pcie_tl_credit_ph_histogram[8];
-	__le32	pcie_tl_credit_pd_histogram[8];
-	__le32	pcie_cmpl_latest_times[4];
-	__le32	pcie_cmpl_longest_time;
-	__le32	pcie_cmpl_shortest_time;
-	__le32	unused_0[2];
-	__le32	pcie_cmpl_latest_headers[4][4];
-	__le32	pcie_cmpl_longest_headers[4][4];
-	__le32	pcie_cmpl_shortest_headers[4][4];
-	__le32	pcie_wr_latency_histogram[12];
-	__le32	pcie_wr_latency_all_normal_count;
-	__le32	unused_1;
-	__le64	pcie_posted_packet_count;
-	__le64	pcie_non_posted_packet_count;
-	__le64	pcie_other_packet_count;
-	__le64	pcie_blocked_packet_count;
-	__le64	pcie_cmpl_packet_count;
-};
-
-/* hwrm_stat_generic_qstats_input (size:256b/32B) */
-struct hwrm_stat_generic_qstats_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	generic_stat_size;
-	u8	flags;
-	#define STAT_GENERIC_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
-	u8	unused_0[5];
-	__le64	generic_stat_host_addr;
-};
-
-/* hwrm_stat_generic_qstats_output (size:128b/16B) */
-struct hwrm_stat_generic_qstats_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	generic_stat_size;
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* generic_sw_hw_stats (size:1472b/184B) */
-struct generic_sw_hw_stats {
-	__le64	pcie_statistics_tx_tlp;
-	__le64	pcie_statistics_rx_tlp;
-	__le64	pcie_credit_fc_hdr_posted;
-	__le64	pcie_credit_fc_hdr_nonposted;
-	__le64	pcie_credit_fc_hdr_cmpl;
-	__le64	pcie_credit_fc_data_posted;
-	__le64	pcie_credit_fc_data_nonposted;
-	__le64	pcie_credit_fc_data_cmpl;
-	__le64	pcie_credit_fc_tgt_nonposted;
-	__le64	pcie_credit_fc_tgt_data_posted;
-	__le64	pcie_credit_fc_tgt_hdr_posted;
-	__le64	pcie_credit_fc_cmpl_hdr_posted;
-	__le64	pcie_credit_fc_cmpl_data_posted;
-	__le64	pcie_cmpl_longest;
-	__le64	pcie_cmpl_shortest;
-	__le64	cache_miss_count_cfcq;
-	__le64	cache_miss_count_cfcs;
-	__le64	cache_miss_count_cfcc;
-	__le64	cache_miss_count_cfcm;
-	__le64	hw_db_recov_dbs_dropped;
-	__le64	hw_db_recov_drops_serviced;
-	__le64	hw_db_recov_dbs_recovered;
-	__le64	hw_db_recov_oo_drop_count;
-};
-
-/* hwrm_fw_reset_input (size:192b/24B) */
-struct hwrm_fw_reset_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	embedded_proc_type;
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT                  0x0UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT                  0x1UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL               0x2UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE                  0x3UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST                  0x4UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP                    0x5UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP                  0x6UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST_RESOURCE_REINIT  0x7UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION 0x8UL
-	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_LAST                 FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION
-	u8	selfrst_status;
-	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE      0x0UL
-	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP      0x1UL
-	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST   0x2UL
-	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
-	#define FW_RESET_REQ_SELFRST_STATUS_LAST            FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE
-	u8	host_idx;
-	u8	flags;
-	#define FW_RESET_REQ_FLAGS_RESET_GRACEFUL     0x1UL
-	#define FW_RESET_REQ_FLAGS_FW_ACTIVATION      0x2UL
-	u8	unused_0[4];
-};
-
-/* hwrm_fw_reset_output (size:128b/16B) */
-struct hwrm_fw_reset_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	selfrst_status;
-	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTNONE      0x0UL
-	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTASAP      0x1UL
-	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTPCIERST   0x2UL
-	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
-	#define FW_RESET_RESP_SELFRST_STATUS_LAST            FW_RESET_RESP_SELFRST_STATUS_SELFRSTIMMEDIATE
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_fw_qstatus_input (size:192b/24B) */
-struct hwrm_fw_qstatus_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	embedded_proc_type;
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_BOOT    0x0UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_MGMT    0x1UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_NETCTRL 0x2UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_ROCE    0x3UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_HOST    0x4UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_AP      0x5UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP    0x6UL
-	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_LAST   FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP
-	u8	unused_0[7];
-};
-
-/* hwrm_fw_qstatus_output (size:128b/16B) */
-struct hwrm_fw_qstatus_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	selfrst_status;
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTNONE    0x0UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTASAP    0x1UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPCIERST 0x2UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER   0x3UL
-	#define FW_QSTATUS_RESP_SELFRST_STATUS_LAST          FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER
-	u8	nvm_option_action_status;
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_NONE     0x0UL
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_HOTRESET 0x1UL
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_WARMBOOT 0x2UL
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_COLDBOOT 0x3UL
-	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_LAST                  FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_COLDBOOT
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_fw_set_time_input (size:256b/32B) */
-struct hwrm_fw_set_time_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	year;
-	#define FW_SET_TIME_REQ_YEAR_UNKNOWN 0x0UL
-	#define FW_SET_TIME_REQ_YEAR_LAST   FW_SET_TIME_REQ_YEAR_UNKNOWN
-	u8	month;
-	u8	day;
-	u8	hour;
-	u8	minute;
-	u8	second;
-	u8	unused_0;
-	__le16	millisecond;
-	__le16	zone;
-	#define FW_SET_TIME_REQ_ZONE_UTC     0
-	#define FW_SET_TIME_REQ_ZONE_UNKNOWN 65535
-	#define FW_SET_TIME_REQ_ZONE_LAST   FW_SET_TIME_REQ_ZONE_UNKNOWN
-	u8	unused_1[4];
-};
-
-/* hwrm_fw_set_time_output (size:128b/16B) */
-struct hwrm_fw_set_time_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_struct_hdr (size:128b/16B) */
-struct hwrm_struct_hdr {
-	__le16	struct_id;
-	#define STRUCT_HDR_STRUCT_ID_LLDP_CFG              0x41bUL
-	#define STRUCT_HDR_STRUCT_ID_DCBX_ETS              0x41dUL
-	#define STRUCT_HDR_STRUCT_ID_DCBX_PFC              0x41fUL
-	#define STRUCT_HDR_STRUCT_ID_DCBX_APP              0x421UL
-	#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE    0x422UL
-	#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC          0x424UL
-	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE           0x426UL
-	#define STRUCT_HDR_STRUCT_ID_POWER_BKUP            0x427UL
-	#define STRUCT_HDR_STRUCT_ID_PEER_MMAP             0x429UL
-	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE            0x1UL
-	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION      0xaUL
-	#define STRUCT_HDR_STRUCT_ID_RSS_V2                0x64UL
-	#define STRUCT_HDR_STRUCT_ID_MSIX_PER_VF           0xc8UL
-	#define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_COUNT 0x12cUL
-	#define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND 0x12dUL
-	#define STRUCT_HDR_STRUCT_ID_LAST                 STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND
-	__le16	len;
-	u8	version;
-	#define STRUCT_HDR_VERSION_0 0x0UL
-	#define STRUCT_HDR_VERSION_1 0x1UL
-	#define STRUCT_HDR_VERSION_LAST STRUCT_HDR_VERSION_1
-	u8	count;
-	__le16	subtype;
-	__le16	next_offset;
-	#define STRUCT_HDR_NEXT_OFFSET_LAST 0x0UL
-	u8	unused_0[6];
-};
-
-/* hwrm_struct_data_dcbx_app (size:64b/8B) */
-struct hwrm_struct_data_dcbx_app {
-	__be16	protocol_id;
-	u8	protocol_selector;
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_ETHER_TYPE   0x1UL
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_PORT     0x2UL
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_UDP_PORT     0x3UL
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_UDP_PORT 0x4UL
-	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_LAST        STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_UDP_PORT
-	u8	priority;
-	u8	valid;
-	u8	unused_0[3];
-};
-
-/* hwrm_fw_set_structured_data_input (size:256b/32B) */
-struct hwrm_fw_set_structured_data_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	src_data_addr;
-	__le16	data_len;
-	u8	hdr_cnt;
-	u8	unused_0[5];
-};
-
-/* hwrm_fw_set_structured_data_output (size:128b/16B) */
-struct hwrm_fw_set_structured_data_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_fw_set_structured_data_cmd_err (size:64b/8B) */
-struct hwrm_fw_set_structured_data_cmd_err {
-	u8	code;
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN     0x0UL
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_HDR_CNT 0x1UL
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_FMT     0x2UL
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID      0x3UL
-	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_LAST       FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID
-	u8	unused_0[7];
-};
-
-/* hwrm_fw_get_structured_data_input (size:256b/32B) */
-struct hwrm_fw_get_structured_data_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	dest_data_addr;
-	__le16	data_len;
-	__le16	structure_id;
-	__le16	subtype;
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_UNUSED                  0x0UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_ALL                     0xffffUL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_ADMIN       0x100UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_PEER        0x101UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_OPERATIONAL 0x102UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_ADMIN          0x200UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_PEER           0x201UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_OPERATIONAL    0x202UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL        0x300UL
-	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_LAST                   FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL
-	u8	count;
-	u8	unused_0;
-};
-
-/* hwrm_fw_get_structured_data_output (size:128b/16B) */
-struct hwrm_fw_get_structured_data_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	hdr_cnt;
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_fw_get_structured_data_cmd_err (size:64b/8B) */
-struct hwrm_fw_get_structured_data_cmd_err {
-	u8	code;
-	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN 0x0UL
-	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID  0x3UL
-	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_LAST   FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID
-	u8	unused_0[7];
-};
-
-/* hwrm_fw_livepatch_query_input (size:192b/24B) */
-struct hwrm_fw_livepatch_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	fw_target;
-	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_COMMON_FW 0x1UL
-	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW 0x2UL
-	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_LAST     FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW
-	u8	unused_0[7];
-};
-
-/* hwrm_fw_livepatch_query_output (size:640b/80B) */
-struct hwrm_fw_livepatch_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	char	install_ver[32];
-	char	active_ver[32];
-	__le16	status_flags;
-	#define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL     0x1UL
-	#define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE      0x2UL
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_fw_livepatch_input (size:256b/32B) */
-struct hwrm_fw_livepatch_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	opcode;
-	#define FW_LIVEPATCH_REQ_OPCODE_ACTIVATE   0x1UL
-	#define FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE 0x2UL
-	#define FW_LIVEPATCH_REQ_OPCODE_LAST      FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE
-	u8	fw_target;
-	#define FW_LIVEPATCH_REQ_FW_TARGET_COMMON_FW 0x1UL
-	#define FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW 0x2UL
-	#define FW_LIVEPATCH_REQ_FW_TARGET_LAST     FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW
-	u8	loadtype;
-	#define FW_LIVEPATCH_REQ_LOADTYPE_NVM_INSTALL   0x1UL
-	#define FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT 0x2UL
-	#define FW_LIVEPATCH_REQ_LOADTYPE_LAST         FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT
-	u8	flags;
-	__le32	patch_len;
-	__le64	host_addr;
-};
-
-/* hwrm_fw_livepatch_output (size:128b/16B) */
-struct hwrm_fw_livepatch_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_fw_livepatch_cmd_err (size:64b/8B) */
-struct hwrm_fw_livepatch_cmd_err {
-	u8	code;
-	#define FW_LIVEPATCH_CMD_ERR_CODE_UNKNOWN         0x0UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_OPCODE  0x1UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_TARGET  0x2UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_SUPPORTED   0x3UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_INSTALLED   0x4UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_PATCHED     0x5UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_AUTH_FAIL       0x6UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_HEADER  0x7UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_SIZE    0x8UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED 0x9UL
-	#define FW_LIVEPATCH_CMD_ERR_CODE_LAST           FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED
-	u8	unused_0[7];
-};
-
-/* hwrm_exec_fwd_resp_input (size:1024b/128B) */
-struct hwrm_exec_fwd_resp_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	encap_request[26];
-	__le16	encap_resp_target_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_exec_fwd_resp_output (size:128b/16B) */
-struct hwrm_exec_fwd_resp_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_reject_fwd_resp_input (size:1024b/128B) */
-struct hwrm_reject_fwd_resp_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	encap_request[26];
-	__le16	encap_resp_target_id;
-	u8	unused_0[6];
-};
-
-/* hwrm_reject_fwd_resp_output (size:128b/16B) */
-struct hwrm_reject_fwd_resp_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_fwd_resp_input (size:1024b/128B) */
-struct hwrm_fwd_resp_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	encap_resp_target_id;
-	__le16	encap_resp_cmpl_ring;
-	__le16	encap_resp_len;
-	u8	unused_0;
-	u8	unused_1;
-	__le64	encap_resp_addr;
-	__le32	encap_resp[24];
-};
-
-/* hwrm_fwd_resp_output (size:128b/16B) */
-struct hwrm_fwd_resp_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_fwd_async_event_cmpl_input (size:320b/40B) */
-struct hwrm_fwd_async_event_cmpl_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	encap_async_event_target_id;
-	u8	unused_0[6];
-	__le32	encap_async_event_cmpl[4];
-};
-
-/* hwrm_fwd_async_event_cmpl_output (size:128b/16B) */
-struct hwrm_fwd_async_event_cmpl_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_temp_monitor_query_input (size:128b/16B) */
-struct hwrm_temp_monitor_query_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_temp_monitor_query_output (size:192b/24B) */
-struct hwrm_temp_monitor_query_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	temp;
-	u8	phy_temp;
-	u8	om_temp;
-	u8	flags;
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_TEMP_NOT_AVAILABLE             0x1UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_PHY_TEMP_NOT_AVAILABLE         0x2UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_NOT_PRESENT                 0x4UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_TEMP_NOT_AVAILABLE          0x8UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_EXT_TEMP_FIELDS_AVAILABLE      0x10UL
-	#define TEMP_MONITOR_QUERY_RESP_FLAGS_THRESHOLD_VALUES_AVAILABLE     0x20UL
-	u8	temp2;
-	u8	phy_temp2;
-	u8	om_temp2;
-	u8	warn_threshold;
-	u8	critical_threshold;
-	u8	fatal_threshold;
-	u8	shutdown_threshold;
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* hwrm_wol_filter_alloc_input (size:512b/64B) */
-struct hwrm_wol_filter_alloc_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	__le32	enables;
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS           0x1UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_OFFSET        0x2UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_SIZE      0x4UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_ADDR      0x8UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_ADDR     0x10UL
-	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_SIZE     0x20UL
-	__le16	port_id;
-	u8	wol_type;
-	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT 0x0UL
-	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_BMP      0x1UL
-	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID  0xffUL
-	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_LAST    WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID
-	u8	unused_0[5];
-	u8	mac_address[6];
-	__le16	pattern_offset;
-	__le16	pattern_buf_size;
-	__le16	pattern_mask_size;
-	u8	unused_1[4];
-	__le64	pattern_buf_addr;
-	__le64	pattern_mask_addr;
-};
-
-/* hwrm_wol_filter_alloc_output (size:128b/16B) */
-struct hwrm_wol_filter_alloc_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	wol_filter_id;
-	u8	unused_0[6];
-	u8	valid;
-};
-
-/* hwrm_wol_filter_free_input (size:256b/32B) */
-struct hwrm_wol_filter_free_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	flags;
-	#define WOL_FILTER_FREE_REQ_FLAGS_FREE_ALL_WOL_FILTERS     0x1UL
-	__le32	enables;
-	#define WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID     0x1UL
-	__le16	port_id;
-	u8	wol_filter_id;
-	u8	unused_0[5];
-};
-
-/* hwrm_wol_filter_free_output (size:128b/16B) */
-struct hwrm_wol_filter_free_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_wol_filter_qcfg_input (size:448b/56B) */
-struct hwrm_wol_filter_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	__le16	handle;
-	u8	unused_0[4];
-	__le64	pattern_buf_addr;
-	__le16	pattern_buf_size;
-	u8	unused_1[6];
-	__le64	pattern_mask_addr;
-	__le16	pattern_mask_size;
-	u8	unused_2[6];
-};
-
-/* hwrm_wol_filter_qcfg_output (size:256b/32B) */
-struct hwrm_wol_filter_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	next_handle;
-	u8	wol_filter_id;
-	u8	wol_type;
-	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_MAGICPKT 0x0UL
-	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_BMP      0x1UL
-	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID  0xffUL
-	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_LAST    WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID
-	__le32	unused_0;
-	u8	mac_address[6];
-	__le16	pattern_offset;
-	__le16	pattern_size;
-	__le16	pattern_mask_size;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_wol_reason_qcfg_input (size:320b/40B) */
-struct hwrm_wol_reason_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	port_id;
-	u8	unused_0[6];
-	__le64	wol_pkt_buf_addr;
-	__le16	wol_pkt_buf_size;
-	u8	unused_1[6];
-};
-
-/* hwrm_wol_reason_qcfg_output (size:128b/16B) */
-struct hwrm_wol_reason_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	wol_filter_id;
-	u8	wol_reason;
-	#define WOL_REASON_QCFG_RESP_WOL_REASON_MAGICPKT 0x0UL
-	#define WOL_REASON_QCFG_RESP_WOL_REASON_BMP      0x1UL
-	#define WOL_REASON_QCFG_RESP_WOL_REASON_INVALID  0xffUL
-	#define WOL_REASON_QCFG_RESP_WOL_REASON_LAST    WOL_REASON_QCFG_RESP_WOL_REASON_INVALID
-	u8	wol_pkt_len;
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* hwrm_dbg_read_direct_input (size:256b/32B) */
-struct hwrm_dbg_read_direct_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-	__le32	read_addr;
-	__le32	read_len32;
-};
-
-/* hwrm_dbg_read_direct_output (size:128b/16B) */
-struct hwrm_dbg_read_direct_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	crc32;
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_dbg_qcaps_input (size:192b/24B) */
-struct hwrm_dbg_qcaps_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	u8	unused_0[6];
-};
-
-/* hwrm_dbg_qcaps_output (size:192b/24B) */
-struct hwrm_dbg_qcaps_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	u8	unused_0[2];
-	__le32	coredump_component_disable_caps;
-	#define DBG_QCAPS_RESP_COREDUMP_COMPONENT_DISABLE_CAPS_NVRAM     0x1UL
-	__le32	flags;
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM             0x1UL
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR        0x2UL
-	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR         0x4UL
-	#define DBG_QCAPS_RESP_FLAGS_USEQ                      0x8UL
-	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_DDR         0x10UL
-	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_CAPTURE     0x20UL
-	#define DBG_QCAPS_RESP_FLAGS_PTRACE                    0x40UL
-	#define DBG_QCAPS_RESP_FLAGS_REG_ACCESS_RESTRICTED     0x80UL
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_dbg_qcfg_input (size:192b/24B) */
-struct hwrm_dbg_qcfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	fid;
-	__le16	flags;
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_MASK         0x3UL
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_SFT          0
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_NVM       0x0UL
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_HOST_DDR  0x1UL
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR   0x2UL
-	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_LAST          DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR
-	__le32	coredump_component_disable_flags;
-	#define DBG_QCFG_REQ_COREDUMP_COMPONENT_DISABLE_FLAGS_NVRAM     0x1UL
-};
-
-/* hwrm_dbg_qcfg_output (size:256b/32B) */
-struct hwrm_dbg_qcfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	fid;
-	u8	unused_0[2];
-	__le32	coredump_size;
-	__le32	flags;
-	#define DBG_QCFG_RESP_FLAGS_UART_LOG               0x1UL
-	#define DBG_QCFG_RESP_FLAGS_UART_LOG_SECONDARY     0x2UL
-	#define DBG_QCFG_RESP_FLAGS_FW_TRACE               0x4UL
-	#define DBG_QCFG_RESP_FLAGS_FW_TRACE_SECONDARY     0x8UL
-	#define DBG_QCFG_RESP_FLAGS_DEBUG_NOTIFY           0x10UL
-	#define DBG_QCFG_RESP_FLAGS_JTAG_DEBUG             0x20UL
-	__le16	async_cmpl_ring;
-	u8	unused_2[2];
-	__le32	crashdump_size;
-	u8	unused_3[3];
-	u8	valid;
-};
-
-/* hwrm_dbg_crashdump_medium_cfg_input (size:320b/40B) */
-struct hwrm_dbg_crashdump_medium_cfg_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	output_dest_flags;
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR     0x1UL
-	__le16	pg_size_lvl;
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_MASK      0x3UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_SFT       0
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_0       0x0UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_1       0x1UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2       0x2UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LAST       DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_MASK  0x1cUL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_SFT   2
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K   (0x0UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K   (0x1UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K  (0x2UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_2M   (0x3UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8M   (0x4UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G   (0x5UL << 2)
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_LAST   DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_MASK 0xffe0UL
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_SFT  5
-	__le32	size;
-	__le32	coredump_component_disable_flags;
-	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_NVRAM     0x1UL
-	__le32	unused_0;
-	__le64	pbl;
-};
-
-/* hwrm_dbg_crashdump_medium_cfg_output (size:128b/16B) */
-struct hwrm_dbg_crashdump_medium_cfg_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_1[7];
-	u8	valid;
-};
-
-/* coredump_segment_record (size:128b/16B) */
-struct coredump_segment_record {
-	__le16	component_id;
-	__le16	segment_id;
-	__le16	max_instances;
-	u8	version_hi;
-	u8	version_low;
-	u8	seg_flags;
-	u8	compress_flags;
-	#define SFLAG_COMPRESSED_ZLIB     0x1UL
-	u8	unused_0[2];
-	__le32	segment_len;
-};
-
-/* hwrm_dbg_coredump_list_input (size:256b/32B) */
-struct hwrm_dbg_coredump_list_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-	__le32	host_buf_len;
-	__le16	seq_no;
-	u8	flags;
-	#define DBG_COREDUMP_LIST_REQ_FLAGS_CRASHDUMP     0x1UL
-	u8	unused_0[1];
-};
-
-/* hwrm_dbg_coredump_list_output (size:128b/16B) */
-struct hwrm_dbg_coredump_list_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define DBG_COREDUMP_LIST_RESP_FLAGS_MORE     0x1UL
-	u8	unused_0;
-	__le16	total_segments;
-	__le16	data_len;
-	u8	unused_1;
-	u8	valid;
-};
-
-/* hwrm_dbg_coredump_initiate_input (size:256b/32B) */
-struct hwrm_dbg_coredump_initiate_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	component_id;
-	__le16	segment_id;
-	__le16	instance;
-	__le16	unused_0;
-	u8	seg_flags;
-	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_LIVE_DATA                0x1UL
-	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_CRASH_DATA               0x2UL
-	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE     0x4UL
-	u8	unused_1[7];
-};
-
-/* hwrm_dbg_coredump_initiate_output (size:128b/16B) */
-struct hwrm_dbg_coredump_initiate_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* coredump_data_hdr (size:128b/16B) */
-struct coredump_data_hdr {
-	__le32	address;
-	__le32	flags_length;
-	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_ACTUAL_LEN_MASK     0xffffffUL
-	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_ACTUAL_LEN_SFT      0
-	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_INDIRECT_ACCESS     0x1000000UL
-	__le32	instance;
-	__le32	next_offset;
-};
-
-/* hwrm_dbg_coredump_retrieve_input (size:448b/56B) */
-struct hwrm_dbg_coredump_retrieve_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-	__le32	host_buf_len;
-	__le32	unused_0;
-	__le16	component_id;
-	__le16	segment_id;
-	__le16	instance;
-	__le16	unused_1;
-	u8	seg_flags;
-	u8	unused_2;
-	__le16	unused_3;
-	__le32	unused_4;
-	__le32	seq_no;
-	__le32	unused_5;
-};
-
-/* hwrm_dbg_coredump_retrieve_output (size:128b/16B) */
-struct hwrm_dbg_coredump_retrieve_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	flags;
-	#define DBG_COREDUMP_RETRIEVE_RESP_FLAGS_MORE     0x1UL
-	u8	unused_0;
-	__le16	data_len;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_dbg_ring_info_get_input (size:192b/24B) */
-struct hwrm_dbg_ring_info_get_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	ring_type;
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_L2_CMPL 0x0UL
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_TX      0x1UL
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_RX      0x2UL
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_NQ      0x3UL
-	#define DBG_RING_INFO_GET_REQ_RING_TYPE_LAST   DBG_RING_INFO_GET_REQ_RING_TYPE_NQ
-	u8	unused_0[3];
-	__le32	fw_ring_id;
-};
-
-/* hwrm_dbg_ring_info_get_output (size:192b/24B) */
-struct hwrm_dbg_ring_info_get_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	producer_index;
-	__le32	consumer_index;
-	__le32	cag_vector_ctrl;
-	__le16	st_tag;
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_dbg_log_buffer_flush_input (size:192b/24B) */
-struct hwrm_dbg_log_buffer_flush_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	type;
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT_TRACE           0x0UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT2_TRACE          0x1UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT_TRACE           0x2UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT2_TRACE          0x3UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP0_TRACE         0x4UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_L2_HWRM_TRACE       0x5UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ROCE_HWRM_TRACE     0x6UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA0_TRACE           0x7UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA1_TRACE           0x8UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA2_TRACE           0x9UL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP1_TRACE         0xaUL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE 0xbUL
-	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_LAST               DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE
-	u8	unused_1[2];
-	__le32	flags;
-	#define DBG_LOG_BUFFER_FLUSH_REQ_FLAGS_FLUSH_ALL_BUFFERS     0x1UL
-};
-
-/* hwrm_dbg_log_buffer_flush_output (size:128b/16B) */
-struct hwrm_dbg_log_buffer_flush_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	current_buffer_offset;
-	u8	unused_1[3];
-	u8	valid;
-};
-
-/* hwrm_nvm_read_input (size:320b/40B) */
-struct hwrm_nvm_read_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-	__le16	dir_idx;
-	u8	unused_0[2];
-	__le32	offset;
-	__le32	len;
-	u8	unused_1[4];
-};
-
-/* hwrm_nvm_read_output (size:128b/16B) */
-struct hwrm_nvm_read_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_get_dir_entries_input (size:192b/24B) */
-struct hwrm_nvm_get_dir_entries_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_dest_addr;
-};
-
-/* hwrm_nvm_get_dir_entries_output (size:128b/16B) */
-struct hwrm_nvm_get_dir_entries_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_get_dir_info_input (size:128b/16B) */
-struct hwrm_nvm_get_dir_info_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_nvm_get_dir_info_output (size:192b/24B) */
-struct hwrm_nvm_get_dir_info_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	entries;
-	__le32	entry_length;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_write_input (size:448b/56B) */
-struct hwrm_nvm_write_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_src_addr;
-	__le16	dir_type;
-	__le16	dir_ordinal;
-	__le16	dir_ext;
-	__le16	dir_attr;
-	__le32	dir_data_length;
-	__le16	option;
-	__le16	flags;
-	#define NVM_WRITE_REQ_FLAGS_KEEP_ORIG_ACTIVE_IMG     0x1UL
-	#define NVM_WRITE_REQ_FLAGS_BATCH_MODE               0x2UL
-	#define NVM_WRITE_REQ_FLAGS_BATCH_LAST               0x4UL
-	#define NVM_WRITE_REQ_FLAGS_SKIP_CRID_CHECK          0x8UL
-	__le32	dir_item_length;
-	__le32	offset;
-	__le32	len;
-	__le32	unused_0;
-};
-
-/* hwrm_nvm_write_output (size:128b/16B) */
-struct hwrm_nvm_write_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	dir_item_length;
-	__le16	dir_idx;
-	u8	unused_0;
-	u8	valid;
-};
-
-/* hwrm_nvm_write_cmd_err (size:64b/8B) */
-struct hwrm_nvm_write_cmd_err {
-	u8	code;
-	#define NVM_WRITE_CMD_ERR_CODE_UNKNOWN  0x0UL
-	#define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR 0x1UL
-	#define NVM_WRITE_CMD_ERR_CODE_NO_SPACE 0x2UL
-	#define NVM_WRITE_CMD_ERR_CODE_LAST    NVM_WRITE_CMD_ERR_CODE_NO_SPACE
-	u8	unused_0[7];
-};
-
-/* hwrm_nvm_modify_input (size:320b/40B) */
-struct hwrm_nvm_modify_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	host_src_addr;
-	__le16	dir_idx;
-	__le16	flags;
-	#define NVM_MODIFY_REQ_FLAGS_BATCH_MODE     0x1UL
-	#define NVM_MODIFY_REQ_FLAGS_BATCH_LAST     0x2UL
-	__le32	offset;
-	__le32	len;
-	u8	unused_1[4];
-};
-
-/* hwrm_nvm_modify_output (size:128b/16B) */
-struct hwrm_nvm_modify_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_find_dir_entry_input (size:256b/32B) */
-struct hwrm_nvm_find_dir_entry_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define NVM_FIND_DIR_ENTRY_REQ_ENABLES_DIR_IDX_VALID     0x1UL
-	__le16	dir_idx;
-	__le16	dir_type;
-	__le16	dir_ordinal;
-	__le16	dir_ext;
-	u8	opt_ordinal;
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_MASK 0x3UL
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_SFT 0
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_EQ    0x0UL
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GE    0x1UL
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GT    0x2UL
-	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_LAST NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GT
-	u8	unused_0[3];
-};
-
-/* hwrm_nvm_find_dir_entry_output (size:256b/32B) */
-struct hwrm_nvm_find_dir_entry_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le32	dir_item_length;
-	__le32	dir_data_length;
-	__le32	fw_ver;
-	__le16	dir_ordinal;
-	__le16	dir_idx;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_erase_dir_entry_input (size:192b/24B) */
-struct hwrm_nvm_erase_dir_entry_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	dir_idx;
-	u8	unused_0[6];
-};
-
-/* hwrm_nvm_erase_dir_entry_output (size:128b/16B) */
-struct hwrm_nvm_erase_dir_entry_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_get_dev_info_input (size:192b/24B) */
-struct hwrm_nvm_get_dev_info_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	flags;
-	#define NVM_GET_DEV_INFO_REQ_FLAGS_SECURITY_SOC_NVM     0x1UL
-	u8	unused_0[7];
-};
-
-/* hwrm_nvm_get_dev_info_output (size:768b/96B) */
-struct hwrm_nvm_get_dev_info_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	manufacturer_id;
-	__le16	device_id;
-	__le32	sector_size;
-	__le32	nvram_size;
-	__le32	reserved_size;
-	__le32	available_size;
-	u8	nvm_cfg_ver_maj;
-	u8	nvm_cfg_ver_min;
-	u8	nvm_cfg_ver_upd;
-	u8	flags;
-	#define NVM_GET_DEV_INFO_RESP_FLAGS_FW_VER_VALID     0x1UL
-	char	pkg_name[16];
-	__le16	hwrm_fw_major;
-	__le16	hwrm_fw_minor;
-	__le16	hwrm_fw_build;
-	__le16	hwrm_fw_patch;
-	__le16	mgmt_fw_major;
-	__le16	mgmt_fw_minor;
-	__le16	mgmt_fw_build;
-	__le16	mgmt_fw_patch;
-	__le16	roce_fw_major;
-	__le16	roce_fw_minor;
-	__le16	roce_fw_build;
-	__le16	roce_fw_patch;
-	__le16	netctrl_fw_major;
-	__le16	netctrl_fw_minor;
-	__le16	netctrl_fw_build;
-	__le16	netctrl_fw_patch;
-	__le16	srt2_fw_major;
-	__le16	srt2_fw_minor;
-	__le16	srt2_fw_build;
-	__le16	srt2_fw_patch;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_mod_dir_entry_input (size:256b/32B) */
-struct hwrm_nvm_mod_dir_entry_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	enables;
-	#define NVM_MOD_DIR_ENTRY_REQ_ENABLES_CHECKSUM     0x1UL
-	__le16	dir_idx;
-	__le16	dir_ordinal;
-	__le16	dir_ext;
-	__le16	dir_attr;
-	__le32	checksum;
-};
-
-/* hwrm_nvm_mod_dir_entry_output (size:128b/16B) */
-struct hwrm_nvm_mod_dir_entry_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_verify_update_input (size:192b/24B) */
-struct hwrm_nvm_verify_update_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le16	dir_type;
-	__le16	dir_ordinal;
-	__le16	dir_ext;
-	u8	unused_0[2];
-};
-
-/* hwrm_nvm_verify_update_output (size:128b/16B) */
-struct hwrm_nvm_verify_update_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_install_update_input (size:192b/24B) */
-struct hwrm_nvm_install_update_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le32	install_type;
-	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_NORMAL 0x0UL
-	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_ALL    0xffffffffUL
-	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_LAST  NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_ALL
-	__le16	flags;
-	#define NVM_INSTALL_UPDATE_REQ_FLAGS_ERASE_UNUSED_SPACE     0x1UL
-	#define NVM_INSTALL_UPDATE_REQ_FLAGS_REMOVE_UNUSED_PKG      0x2UL
-	#define NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG      0x4UL
-	#define NVM_INSTALL_UPDATE_REQ_FLAGS_VERIFY_ONLY            0x8UL
-	u8	unused_0[2];
-};
-
-/* hwrm_nvm_install_update_output (size:192b/24B) */
-struct hwrm_nvm_install_update_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le64	installed_items;
-	u8	result;
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS                      0x0UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_FAILURE                      0xffUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_MALLOC_FAILURE               0xfdUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_INDEX_PARAMETER      0xfbUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TYPE_PARAMETER       0xf3UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PREREQUISITE         0xf2UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_FILE_HEADER          0xecUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_SIGNATURE            0xebUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_STREAM          0xeaUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_LENGTH          0xe9UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_MANIFEST             0xe8UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TRAILER              0xe7UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_CHECKSUM             0xe6UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_ITEM_CHECKSUM        0xe5UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DATA_LENGTH          0xe4UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DIRECTIVE            0xe1UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_CHIP_REV         0xceUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_DEVICE_ID        0xcdUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_VENDOR    0xccUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_ID        0xcbUL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_PLATFORM         0xc5UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_DUPLICATE_ITEM               0xc4UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_ZERO_LENGTH_ITEM             0xc3UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_CHECKSUM_ERROR       0xb9UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_DATA_ERROR           0xb8UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_AUTHENTICATION_ERROR 0xb7UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_NOT_FOUND               0xb0UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED                  0xa7UL
-	#define NVM_INSTALL_UPDATE_RESP_RESULT_LAST                        NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED
-	u8	problem_item;
-	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_NONE    0x0UL
-	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE 0xffUL
-	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_LAST   NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE
-	u8	reset_required;
-	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_NONE  0x0UL
-	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_PCI   0x1UL
-	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_POWER 0x2UL
-	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_LAST NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_POWER
-	u8	unused_0[4];
-	u8	valid;
-};
-
-/* hwrm_nvm_install_update_cmd_err (size:64b/8B) */
-struct hwrm_nvm_install_update_cmd_err {
-	u8	code;
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN            0x0UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR           0x1UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE           0x2UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_ANTI_ROLLBACK      0x3UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT 0x4UL
-	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_LAST              NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT
-	u8	unused_0[7];
-};
-
-/* hwrm_nvm_get_variable_input (size:320b/40B) */
-struct hwrm_nvm_get_variable_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	dest_data_addr;
-	__le16	data_len;
-	__le16	option_num;
-	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_0    0x0UL
-	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
-	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_LAST     NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF
-	__le16	dimensions;
-	__le16	index_0;
-	__le16	index_1;
-	__le16	index_2;
-	__le16	index_3;
-	u8	flags;
-	#define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT     0x1UL
-	u8	unused_0;
-};
-
-/* hwrm_nvm_get_variable_output (size:128b/16B) */
-struct hwrm_nvm_get_variable_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	__le16	data_len;
-	__le16	option_num;
-	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_0    0x0UL
-	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF 0xffffUL
-	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_LAST     NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF
-	u8	unused_0[3];
-	u8	valid;
-};
-
-/* hwrm_nvm_get_variable_cmd_err (size:64b/8B) */
-struct hwrm_nvm_get_variable_cmd_err {
-	u8	code;
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN       0x0UL
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR   0x2UL
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT 0x3UL
-	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LAST         NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT
-	u8	unused_0[7];
-};
-
-/* hwrm_nvm_set_variable_input (size:320b/40B) */
-struct hwrm_nvm_set_variable_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	__le64	src_data_addr;
-	__le16	data_len;
-	__le16	option_num;
-	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_0    0x0UL
-	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
-	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_LAST     NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF
-	__le16	dimensions;
-	__le16	index_0;
-	__le16	index_1;
-	__le16	index_2;
-	__le16	index_3;
-	u8	flags;
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH                0x1UL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK          0xeUL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT           1
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE            (0x0UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1       (0x1UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256          (0x2UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH  (0x3UL << 1)
-	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST           NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_MASK        0x70UL
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_SFT         4
-	#define NVM_SET_VARIABLE_REQ_FLAGS_FACTORY_DEFAULT            0x80UL
-	u8	unused_0;
-};
-
-/* hwrm_nvm_set_variable_output (size:128b/16B) */
-struct hwrm_nvm_set_variable_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* hwrm_nvm_set_variable_cmd_err (size:64b/8B) */
-struct hwrm_nvm_set_variable_cmd_err {
-	u8	code;
-	#define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN       0x0UL
-	#define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL
-	#define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR   0x2UL
-	#define NVM_SET_VARIABLE_CMD_ERR_CODE_LAST         NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR
-	u8	unused_0[7];
-};
-
-/* hwrm_selftest_qlist_input (size:128b/16B) */
-struct hwrm_selftest_qlist_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_selftest_qlist_output (size:2240b/280B) */
-struct hwrm_selftest_qlist_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	num_tests;
-	u8	available_tests;
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_NVM_TEST                 0x1UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST                0x2UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST            0x4UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST              0x8UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_SERDES_TEST     0x20UL
-	u8	offline_tests;
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST                 0x1UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST                0x2UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST            0x4UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST              0x8UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_SERDES_TEST     0x20UL
-	u8	unused_0;
-	__le16	test_timeout;
-	u8	unused_1[2];
-	char	test_name[8][32];
-	u8	eyescope_target_BER_support;
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E8_SUPPORTED  0x0UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E9_SUPPORTED  0x1UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E10_SUPPORTED 0x2UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E11_SUPPORTED 0x3UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED 0x4UL
-	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_LAST              SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED
-	u8	unused_2[6];
-	u8	valid;
-};
-
-/* hwrm_selftest_exec_input (size:192b/24B) */
-struct hwrm_selftest_exec_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-	u8	flags;
-	#define SELFTEST_EXEC_REQ_FLAGS_NVM_TEST                 0x1UL
-	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST                0x2UL
-	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST            0x4UL
-	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST              0x8UL
-	#define SELFTEST_EXEC_REQ_FLAGS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_SERDES_TEST     0x20UL
-	u8	unused_0[7];
-};
-
-/* hwrm_selftest_exec_output (size:128b/16B) */
-struct hwrm_selftest_exec_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	requested_tests;
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_NVM_TEST                 0x1UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST                0x2UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST            0x4UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST              0x8UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_SERDES_TEST     0x20UL
-	u8	test_success;
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST                 0x1UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST                0x2UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST            0x4UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST              0x8UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_SERDES_TEST         0x10UL
-	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_SERDES_TEST     0x20UL
-	u8	unused_0[5];
-	u8	valid;
-};
-
-/* hwrm_selftest_irq_input (size:128b/16B) */
-struct hwrm_selftest_irq_input {
-	__le16	req_type;
-	__le16	cmpl_ring;
-	__le16	seq_id;
-	__le16	target_id;
-	__le64	resp_addr;
-};
-
-/* hwrm_selftest_irq_output (size:128b/16B) */
-struct hwrm_selftest_irq_output {
-	__le16	error_code;
-	__le16	req_type;
-	__le16	seq_id;
-	__le16	resp_len;
-	u8	unused_0[7];
-	u8	valid;
-};
-
-/* dbc_dbc (size:64b/8B) */
-struct dbc_dbc {
-	__le32	index;
-	#define DBC_DBC_INDEX_MASK 0xffffffUL
-	#define DBC_DBC_INDEX_SFT  0
-	#define DBC_DBC_EPOCH      0x1000000UL
-	#define DBC_DBC_TOGGLE_MASK 0x6000000UL
-	#define DBC_DBC_TOGGLE_SFT 25
-	__le32	type_path_xid;
-	#define DBC_DBC_XID_MASK          0xfffffUL
-	#define DBC_DBC_XID_SFT           0
-	#define DBC_DBC_PATH_MASK         0x3000000UL
-	#define DBC_DBC_PATH_SFT          24
-	#define DBC_DBC_PATH_ROCE           (0x0UL << 24)
-	#define DBC_DBC_PATH_L2             (0x1UL << 24)
-	#define DBC_DBC_PATH_ENGINE         (0x2UL << 24)
-	#define DBC_DBC_PATH_LAST          DBC_DBC_PATH_ENGINE
-	#define DBC_DBC_VALID             0x4000000UL
-	#define DBC_DBC_DEBUG_TRACE       0x8000000UL
-	#define DBC_DBC_TYPE_MASK         0xf0000000UL
-	#define DBC_DBC_TYPE_SFT          28
-	#define DBC_DBC_TYPE_SQ             (0x0UL << 28)
-	#define DBC_DBC_TYPE_RQ             (0x1UL << 28)
-	#define DBC_DBC_TYPE_SRQ            (0x2UL << 28)
-	#define DBC_DBC_TYPE_SRQ_ARM        (0x3UL << 28)
-	#define DBC_DBC_TYPE_CQ             (0x4UL << 28)
-	#define DBC_DBC_TYPE_CQ_ARMSE       (0x5UL << 28)
-	#define DBC_DBC_TYPE_CQ_ARMALL      (0x6UL << 28)
-	#define DBC_DBC_TYPE_CQ_ARMENA      (0x7UL << 28)
-	#define DBC_DBC_TYPE_SRQ_ARMENA     (0x8UL << 28)
-	#define DBC_DBC_TYPE_CQ_CUTOFF_ACK  (0x9UL << 28)
-	#define DBC_DBC_TYPE_NQ             (0xaUL << 28)
-	#define DBC_DBC_TYPE_NQ_ARM         (0xbUL << 28)
-	#define DBC_DBC_TYPE_NQ_MASK        (0xeUL << 28)
-	#define DBC_DBC_TYPE_NULL           (0xfUL << 28)
-	#define DBC_DBC_TYPE_LAST          DBC_DBC_TYPE_NULL
-};
-
-/* db_push_start (size:64b/8B) */
-struct db_push_start {
-	u64	db;
-	#define DB_PUSH_START_DB_INDEX_MASK     0xffffffUL
-	#define DB_PUSH_START_DB_INDEX_SFT      0
-	#define DB_PUSH_START_DB_PI_LO_MASK     0xff000000UL
-	#define DB_PUSH_START_DB_PI_LO_SFT      24
-	#define DB_PUSH_START_DB_XID_MASK       0xfffff00000000ULL
-	#define DB_PUSH_START_DB_XID_SFT        32
-	#define DB_PUSH_START_DB_PI_HI_MASK     0xf0000000000000ULL
-	#define DB_PUSH_START_DB_PI_HI_SFT      52
-	#define DB_PUSH_START_DB_TYPE_MASK      0xf000000000000000ULL
-	#define DB_PUSH_START_DB_TYPE_SFT       60
-	#define DB_PUSH_START_DB_TYPE_PUSH_START  (0xcULL << 60)
-	#define DB_PUSH_START_DB_TYPE_PUSH_END    (0xdULL << 60)
-	#define DB_PUSH_START_DB_TYPE_LAST       DB_PUSH_START_DB_TYPE_PUSH_END
-};
-
-/* db_push_end (size:64b/8B) */
-struct db_push_end {
-	u64	db;
-	#define DB_PUSH_END_DB_INDEX_MASK      0xffffffUL
-	#define DB_PUSH_END_DB_INDEX_SFT       0
-	#define DB_PUSH_END_DB_PI_LO_MASK      0xff000000UL
-	#define DB_PUSH_END_DB_PI_LO_SFT       24
-	#define DB_PUSH_END_DB_XID_MASK        0xfffff00000000ULL
-	#define DB_PUSH_END_DB_XID_SFT         32
-	#define DB_PUSH_END_DB_PI_HI_MASK      0xf0000000000000ULL
-	#define DB_PUSH_END_DB_PI_HI_SFT       52
-	#define DB_PUSH_END_DB_PATH_MASK       0x300000000000000ULL
-	#define DB_PUSH_END_DB_PATH_SFT        56
-	#define DB_PUSH_END_DB_PATH_ROCE         (0x0ULL << 56)
-	#define DB_PUSH_END_DB_PATH_L2           (0x1ULL << 56)
-	#define DB_PUSH_END_DB_PATH_ENGINE       (0x2ULL << 56)
-	#define DB_PUSH_END_DB_PATH_LAST        DB_PUSH_END_DB_PATH_ENGINE
-	#define DB_PUSH_END_DB_DEBUG_TRACE     0x800000000000000ULL
-	#define DB_PUSH_END_DB_TYPE_MASK       0xf000000000000000ULL
-	#define DB_PUSH_END_DB_TYPE_SFT        60
-	#define DB_PUSH_END_DB_TYPE_PUSH_START   (0xcULL << 60)
-	#define DB_PUSH_END_DB_TYPE_PUSH_END     (0xdULL << 60)
-	#define DB_PUSH_END_DB_TYPE_LAST        DB_PUSH_END_DB_TYPE_PUSH_END
-};
-
-/* db_push_info (size:64b/8B) */
-struct db_push_info {
-	u32	push_size_push_index;
-	#define DB_PUSH_INFO_PUSH_INDEX_MASK 0xffffffUL
-	#define DB_PUSH_INFO_PUSH_INDEX_SFT 0
-	#define DB_PUSH_INFO_PUSH_SIZE_MASK 0x1f000000UL
-	#define DB_PUSH_INFO_PUSH_SIZE_SFT  24
-	u32	reserved32;
-};
-
-/* fw_status_reg (size:32b/4B) */
-struct fw_status_reg {
-	u32	fw_status;
-	#define FW_STATUS_REG_CODE_MASK              0xffffUL
-	#define FW_STATUS_REG_CODE_SFT               0
-	#define FW_STATUS_REG_CODE_READY               0x8000UL
-	#define FW_STATUS_REG_CODE_LAST               FW_STATUS_REG_CODE_READY
-	#define FW_STATUS_REG_IMAGE_DEGRADED         0x10000UL
-	#define FW_STATUS_REG_RECOVERABLE            0x20000UL
-	#define FW_STATUS_REG_CRASHDUMP_ONGOING      0x40000UL
-	#define FW_STATUS_REG_CRASHDUMP_COMPLETE     0x80000UL
-	#define FW_STATUS_REG_SHUTDOWN               0x100000UL
-	#define FW_STATUS_REG_CRASHED_NO_MASTER      0x200000UL
-	#define FW_STATUS_REG_RECOVERING             0x400000UL
-	#define FW_STATUS_REG_MANU_DEBUG_STATUS      0x800000UL
-};
-
-/* hcomm_status (size:64b/8B) */
-struct hcomm_status {
-	u32	sig_ver;
-	#define HCOMM_STATUS_VER_MASK      0xffUL
-	#define HCOMM_STATUS_VER_SFT       0
-	#define HCOMM_STATUS_VER_LATEST      0x1UL
-	#define HCOMM_STATUS_VER_LAST       HCOMM_STATUS_VER_LATEST
-	#define HCOMM_STATUS_SIGNATURE_MASK 0xffffff00UL
-	#define HCOMM_STATUS_SIGNATURE_SFT 8
-	#define HCOMM_STATUS_SIGNATURE_VAL   (0x484353UL << 8)
-	#define HCOMM_STATUS_SIGNATURE_LAST HCOMM_STATUS_SIGNATURE_VAL
-	u32	fw_status_loc;
-	#define HCOMM_STATUS_TRUE_ADDR_SPACE_MASK    0x3UL
-	#define HCOMM_STATUS_TRUE_ADDR_SPACE_SFT     0
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_PCIE_CFG  0x0UL
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_GRC       0x1UL
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR0      0x2UL
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1      0x3UL
-	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_LAST     HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1
-	#define HCOMM_STATUS_TRUE_OFFSET_MASK        0xfffffffcUL
-	#define HCOMM_STATUS_TRUE_OFFSET_SFT         2
-};
-#define HCOMM_STATUS_STRUCT_LOC 0x31001F0UL
-
-#endif /* _BNXT_HSI_H_ */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c
index 669d24ba0e87..de3427c6c6aa 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwmon.c
@@ -12,8 +12,8 @@
 #include <linux/hwmon.h>
 #include <linux/hwmon-sysfs.h>
 #include <linux/pci.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_hwmon.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
index d2fd2d04ed47..5ce190f50120 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.c
@@ -20,8 +20,8 @@
 #include <linux/netdevice.h>
 #include <linux/pci.h>
 #include <linux/skbuff.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
index fb5f5b063c3d..791b3a0cdb83 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_hwrm.h
@@ -10,7 +10,7 @@
 #ifndef BNXT_HWRM_H
 #define BNXT_HWRM_H
 
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 
 enum bnxt_hwrm_ctx_flags {
 	/* Update the HWRM_API_FLAGS right below for any new non-internal bit added here */
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
index 0669d43472f5..471b1393ce6c 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c
@@ -15,7 +15,7 @@
 #include <linux/timekeeping.h>
 #include <linux/ptp_classify.h>
 #include <linux/clocksource.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ptp.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
index bc0d80356568..ec14b51ba38e 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c
@@ -16,7 +16,7 @@
 #include <linux/interrupt.h>
 #include <linux/etherdevice.h>
 #include <net/dcbnl.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
index 0599d3016224..d72fd248f3aa 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c
@@ -19,8 +19,8 @@
 #include <net/tc_act/tc_pedit.h>
 #include <net/tc_act/tc_tunnel_key.h>
 #include <net/vxlan.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_sriov.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index 2450a369b792..61cf201bb0dc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -21,8 +21,8 @@
 #include <linux/bitmap.h>
 #include <linux/auxiliary_bus.h>
 #include <net/netdev_lock.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_ulp.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
index 619f0844e778..bd116fd578d8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_vfr.c
@@ -12,8 +12,8 @@
 #include <linux/rtnetlink.h>
 #include <linux/jhash.h>
 #include <net/pkt_cls.h>
+#include <linux/bnxt/hsi.h>
 
-#include "bnxt_hsi.h"
 #include "bnxt.h"
 #include "bnxt_hwrm.h"
 #include "bnxt_vfr.h"
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 09e7e8efa6fa..58d579dca3f1 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -17,7 +17,7 @@
 #include <linux/filter.h>
 #include <net/netdev_lock.h>
 #include <net/page_pool/helpers.h>
-#include "bnxt_hsi.h"
+#include <linux/bnxt/hsi.h>
 #include "bnxt.h"
 #include "bnxt_xdp.h"
 
diff --git a/include/linux/bnxt/hsi.h b/include/linux/bnxt/hsi.h
new file mode 100644
index 000000000000..549231703bce
--- /dev/null
+++ b/include/linux/bnxt/hsi.h
@@ -0,0 +1,10914 @@
+/* Broadcom NetXtreme-C/E network driver.
+ *
+ * Copyright (c) 2014-2016 Broadcom Corporation
+ * Copyright (c) 2014-2018 Broadcom Limited
+ * Copyright (c) 2018-2025 Broadcom Inc.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ *
+ * DO NOT MODIFY!!! This file is automatically generated.
+ */
+
+#ifndef _BNXT_HSI_H_
+#define _BNXT_HSI_H_
+
+/* hwrm_cmd_hdr (size:128b/16B) */
+struct hwrm_cmd_hdr {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_resp_hdr (size:64b/8B) */
+struct hwrm_resp_hdr {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+};
+
+#define CMD_DISCR_TLV_ENCAP 0x8000UL
+#define CMD_DISCR_LAST     CMD_DISCR_TLV_ENCAP
+
+
+#define TLV_TYPE_HWRM_REQUEST                    0x1UL
+#define TLV_TYPE_HWRM_RESPONSE                   0x2UL
+#define TLV_TYPE_ROCE_SP_COMMAND                 0x3UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN1              0x4UL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN1             0x5UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN2              0x6UL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN2             0x7UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN1_EXT          0x8UL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN1_EXT         0x9UL
+#define TLV_TYPE_QUERY_ROCE_CC_GEN2_EXT          0xaUL
+#define TLV_TYPE_MODIFY_ROCE_CC_GEN2_EXT         0xbUL
+#define TLV_TYPE_ENGINE_CKV_ALIAS_ECC_PUBLIC_KEY 0x8001UL
+#define TLV_TYPE_ENGINE_CKV_IV                   0x8003UL
+#define TLV_TYPE_ENGINE_CKV_AUTH_TAG             0x8004UL
+#define TLV_TYPE_ENGINE_CKV_CIPHERTEXT           0x8005UL
+#define TLV_TYPE_ENGINE_CKV_HOST_ALGORITHMS      0x8006UL
+#define TLV_TYPE_ENGINE_CKV_HOST_ECC_PUBLIC_KEY  0x8007UL
+#define TLV_TYPE_ENGINE_CKV_ECDSA_SIGNATURE      0x8008UL
+#define TLV_TYPE_ENGINE_CKV_FW_ECC_PUBLIC_KEY    0x8009UL
+#define TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS        0x800aUL
+#define TLV_TYPE_LAST                           TLV_TYPE_ENGINE_CKV_FW_ALGORITHMS
+
+
+/* tlv (size:64b/8B) */
+struct tlv {
+	__le16	cmd_discr;
+	u8	reserved_8b;
+	u8	flags;
+	#define TLV_FLAGS_MORE         0x1UL
+	#define TLV_FLAGS_MORE_LAST      0x0UL
+	#define TLV_FLAGS_MORE_NOT_LAST  0x1UL
+	#define TLV_FLAGS_REQUIRED     0x2UL
+	#define TLV_FLAGS_REQUIRED_NO    (0x0UL << 1)
+	#define TLV_FLAGS_REQUIRED_YES   (0x1UL << 1)
+	#define TLV_FLAGS_REQUIRED_LAST TLV_FLAGS_REQUIRED_YES
+	__le16	tlv_type;
+	__le16	length;
+};
+
+/* input (size:128b/16B) */
+struct input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* output (size:64b/8B) */
+struct output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+};
+
+/* hwrm_short_input (size:128b/16B) */
+struct hwrm_short_input {
+	__le16	req_type;
+	__le16	signature;
+	#define SHORT_REQ_SIGNATURE_SHORT_CMD 0x4321UL
+	#define SHORT_REQ_SIGNATURE_LAST     SHORT_REQ_SIGNATURE_SHORT_CMD
+	__le16	target_id;
+	#define SHORT_REQ_TARGET_ID_DEFAULT 0x0UL
+	#define SHORT_REQ_TARGET_ID_TOOLS   0xfffdUL
+	#define SHORT_REQ_TARGET_ID_LAST   SHORT_REQ_TARGET_ID_TOOLS
+	__le16	size;
+	__le64	req_addr;
+};
+
+/* cmd_nums (size:64b/8B) */
+struct cmd_nums {
+	__le16	req_type;
+	#define HWRM_VER_GET                              0x0UL
+	#define HWRM_FUNC_ECHO_RESPONSE                   0xbUL
+	#define HWRM_ERROR_RECOVERY_QCFG                  0xcUL
+	#define HWRM_FUNC_DRV_IF_CHANGE                   0xdUL
+	#define HWRM_FUNC_BUF_UNRGTR                      0xeUL
+	#define HWRM_FUNC_VF_CFG                          0xfUL
+	#define HWRM_RESERVED1                            0x10UL
+	#define HWRM_FUNC_RESET                           0x11UL
+	#define HWRM_FUNC_GETFID                          0x12UL
+	#define HWRM_FUNC_VF_ALLOC                        0x13UL
+	#define HWRM_FUNC_VF_FREE                         0x14UL
+	#define HWRM_FUNC_QCAPS                           0x15UL
+	#define HWRM_FUNC_QCFG                            0x16UL
+	#define HWRM_FUNC_CFG                             0x17UL
+	#define HWRM_FUNC_QSTATS                          0x18UL
+	#define HWRM_FUNC_CLR_STATS                       0x19UL
+	#define HWRM_FUNC_DRV_UNRGTR                      0x1aUL
+	#define HWRM_FUNC_VF_RESC_FREE                    0x1bUL
+	#define HWRM_FUNC_VF_VNIC_IDS_QUERY               0x1cUL
+	#define HWRM_FUNC_DRV_RGTR                        0x1dUL
+	#define HWRM_FUNC_DRV_QVER                        0x1eUL
+	#define HWRM_FUNC_BUF_RGTR                        0x1fUL
+	#define HWRM_PORT_PHY_CFG                         0x20UL
+	#define HWRM_PORT_MAC_CFG                         0x21UL
+	#define HWRM_PORT_TS_QUERY                        0x22UL
+	#define HWRM_PORT_QSTATS                          0x23UL
+	#define HWRM_PORT_LPBK_QSTATS                     0x24UL
+	#define HWRM_PORT_CLR_STATS                       0x25UL
+	#define HWRM_PORT_LPBK_CLR_STATS                  0x26UL
+	#define HWRM_PORT_PHY_QCFG                        0x27UL
+	#define HWRM_PORT_MAC_QCFG                        0x28UL
+	#define HWRM_PORT_MAC_PTP_QCFG                    0x29UL
+	#define HWRM_PORT_PHY_QCAPS                       0x2aUL
+	#define HWRM_PORT_PHY_I2C_WRITE                   0x2bUL
+	#define HWRM_PORT_PHY_I2C_READ                    0x2cUL
+	#define HWRM_PORT_LED_CFG                         0x2dUL
+	#define HWRM_PORT_LED_QCFG                        0x2eUL
+	#define HWRM_PORT_LED_QCAPS                       0x2fUL
+	#define HWRM_QUEUE_QPORTCFG                       0x30UL
+	#define HWRM_QUEUE_QCFG                           0x31UL
+	#define HWRM_QUEUE_CFG                            0x32UL
+	#define HWRM_FUNC_VLAN_CFG                        0x33UL
+	#define HWRM_FUNC_VLAN_QCFG                       0x34UL
+	#define HWRM_QUEUE_PFCENABLE_QCFG                 0x35UL
+	#define HWRM_QUEUE_PFCENABLE_CFG                  0x36UL
+	#define HWRM_QUEUE_PRI2COS_QCFG                   0x37UL
+	#define HWRM_QUEUE_PRI2COS_CFG                    0x38UL
+	#define HWRM_QUEUE_COS2BW_QCFG                    0x39UL
+	#define HWRM_QUEUE_COS2BW_CFG                     0x3aUL
+	#define HWRM_QUEUE_DSCP_QCAPS                     0x3bUL
+	#define HWRM_QUEUE_DSCP2PRI_QCFG                  0x3cUL
+	#define HWRM_QUEUE_DSCP2PRI_CFG                   0x3dUL
+	#define HWRM_VNIC_ALLOC                           0x40UL
+	#define HWRM_VNIC_FREE                            0x41UL
+	#define HWRM_VNIC_CFG                             0x42UL
+	#define HWRM_VNIC_QCFG                            0x43UL
+	#define HWRM_VNIC_TPA_CFG                         0x44UL
+	#define HWRM_VNIC_TPA_QCFG                        0x45UL
+	#define HWRM_VNIC_RSS_CFG                         0x46UL
+	#define HWRM_VNIC_RSS_QCFG                        0x47UL
+	#define HWRM_VNIC_PLCMODES_CFG                    0x48UL
+	#define HWRM_VNIC_PLCMODES_QCFG                   0x49UL
+	#define HWRM_VNIC_QCAPS                           0x4aUL
+	#define HWRM_VNIC_UPDATE                          0x4bUL
+	#define HWRM_RING_ALLOC                           0x50UL
+	#define HWRM_RING_FREE                            0x51UL
+	#define HWRM_RING_CMPL_RING_QAGGINT_PARAMS        0x52UL
+	#define HWRM_RING_CMPL_RING_CFG_AGGINT_PARAMS     0x53UL
+	#define HWRM_RING_AGGINT_QCAPS                    0x54UL
+	#define HWRM_RING_SCHQ_ALLOC                      0x55UL
+	#define HWRM_RING_SCHQ_CFG                        0x56UL
+	#define HWRM_RING_SCHQ_FREE                       0x57UL
+	#define HWRM_RING_RESET                           0x5eUL
+	#define HWRM_RING_GRP_ALLOC                       0x60UL
+	#define HWRM_RING_GRP_FREE                        0x61UL
+	#define HWRM_RING_CFG                             0x62UL
+	#define HWRM_RING_QCFG                            0x63UL
+	#define HWRM_RESERVED5                            0x64UL
+	#define HWRM_RESERVED6                            0x65UL
+	#define HWRM_VNIC_RSS_COS_LB_CTX_ALLOC            0x70UL
+	#define HWRM_VNIC_RSS_COS_LB_CTX_FREE             0x71UL
+	#define HWRM_QUEUE_MPLS_QCAPS                     0x80UL
+	#define HWRM_QUEUE_MPLSTC2PRI_QCFG                0x81UL
+	#define HWRM_QUEUE_MPLSTC2PRI_CFG                 0x82UL
+	#define HWRM_QUEUE_VLANPRI_QCAPS                  0x83UL
+	#define HWRM_QUEUE_VLANPRI2PRI_QCFG               0x84UL
+	#define HWRM_QUEUE_VLANPRI2PRI_CFG                0x85UL
+	#define HWRM_QUEUE_GLOBAL_CFG                     0x86UL
+	#define HWRM_QUEUE_GLOBAL_QCFG                    0x87UL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_FEATURE_QCFG      0x88UL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_FEATURE_CFG       0x89UL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_QCFG      0x8aUL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_FEATURE_CFG       0x8bUL
+	#define HWRM_QUEUE_QCAPS                          0x8cUL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_QCFG       0x8dUL
+	#define HWRM_QUEUE_ADPTV_QOS_RX_TUNING_CFG        0x8eUL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_QCFG       0x8fUL
+	#define HWRM_CFA_L2_FILTER_ALLOC                  0x90UL
+	#define HWRM_CFA_L2_FILTER_FREE                   0x91UL
+	#define HWRM_CFA_L2_FILTER_CFG                    0x92UL
+	#define HWRM_CFA_L2_SET_RX_MASK                   0x93UL
+	#define HWRM_CFA_VLAN_ANTISPOOF_CFG               0x94UL
+	#define HWRM_CFA_TUNNEL_FILTER_ALLOC              0x95UL
+	#define HWRM_CFA_TUNNEL_FILTER_FREE               0x96UL
+	#define HWRM_CFA_ENCAP_RECORD_ALLOC               0x97UL
+	#define HWRM_CFA_ENCAP_RECORD_FREE                0x98UL
+	#define HWRM_CFA_NTUPLE_FILTER_ALLOC              0x99UL
+	#define HWRM_CFA_NTUPLE_FILTER_FREE               0x9aUL
+	#define HWRM_CFA_NTUPLE_FILTER_CFG                0x9bUL
+	#define HWRM_CFA_EM_FLOW_ALLOC                    0x9cUL
+	#define HWRM_CFA_EM_FLOW_FREE                     0x9dUL
+	#define HWRM_CFA_EM_FLOW_CFG                      0x9eUL
+	#define HWRM_TUNNEL_DST_PORT_QUERY                0xa0UL
+	#define HWRM_TUNNEL_DST_PORT_ALLOC                0xa1UL
+	#define HWRM_TUNNEL_DST_PORT_FREE                 0xa2UL
+	#define HWRM_QUEUE_ADPTV_QOS_TX_TUNING_CFG        0xa3UL
+	#define HWRM_STAT_CTX_ENG_QUERY                   0xafUL
+	#define HWRM_STAT_CTX_ALLOC                       0xb0UL
+	#define HWRM_STAT_CTX_FREE                        0xb1UL
+	#define HWRM_STAT_CTX_QUERY                       0xb2UL
+	#define HWRM_STAT_CTX_CLR_STATS                   0xb3UL
+	#define HWRM_PORT_QSTATS_EXT                      0xb4UL
+	#define HWRM_PORT_PHY_MDIO_WRITE                  0xb5UL
+	#define HWRM_PORT_PHY_MDIO_READ                   0xb6UL
+	#define HWRM_PORT_PHY_MDIO_BUS_ACQUIRE            0xb7UL
+	#define HWRM_PORT_PHY_MDIO_BUS_RELEASE            0xb8UL
+	#define HWRM_PORT_QSTATS_EXT_PFC_WD               0xb9UL
+	#define HWRM_RESERVED7                            0xbaUL
+	#define HWRM_PORT_TX_FIR_CFG                      0xbbUL
+	#define HWRM_PORT_TX_FIR_QCFG                     0xbcUL
+	#define HWRM_PORT_ECN_QSTATS                      0xbdUL
+	#define HWRM_FW_LIVEPATCH_QUERY                   0xbeUL
+	#define HWRM_FW_LIVEPATCH                         0xbfUL
+	#define HWRM_FW_RESET                             0xc0UL
+	#define HWRM_FW_QSTATUS                           0xc1UL
+	#define HWRM_FW_HEALTH_CHECK                      0xc2UL
+	#define HWRM_FW_SYNC                              0xc3UL
+	#define HWRM_FW_STATE_QCAPS                       0xc4UL
+	#define HWRM_FW_STATE_QUIESCE                     0xc5UL
+	#define HWRM_FW_STATE_BACKUP                      0xc6UL
+	#define HWRM_FW_STATE_RESTORE                     0xc7UL
+	#define HWRM_FW_SET_TIME                          0xc8UL
+	#define HWRM_FW_GET_TIME                          0xc9UL
+	#define HWRM_FW_SET_STRUCTURED_DATA               0xcaUL
+	#define HWRM_FW_GET_STRUCTURED_DATA               0xcbUL
+	#define HWRM_FW_IPC_MAILBOX                       0xccUL
+	#define HWRM_FW_ECN_CFG                           0xcdUL
+	#define HWRM_FW_ECN_QCFG                          0xceUL
+	#define HWRM_FW_SECURE_CFG                        0xcfUL
+	#define HWRM_EXEC_FWD_RESP                        0xd0UL
+	#define HWRM_REJECT_FWD_RESP                      0xd1UL
+	#define HWRM_FWD_RESP                             0xd2UL
+	#define HWRM_FWD_ASYNC_EVENT_CMPL                 0xd3UL
+	#define HWRM_OEM_CMD                              0xd4UL
+	#define HWRM_PORT_PRBS_TEST                       0xd5UL
+	#define HWRM_PORT_SFP_SIDEBAND_CFG                0xd6UL
+	#define HWRM_PORT_SFP_SIDEBAND_QCFG               0xd7UL
+	#define HWRM_FW_STATE_UNQUIESCE                   0xd8UL
+	#define HWRM_PORT_DSC_DUMP                        0xd9UL
+	#define HWRM_PORT_EP_TX_QCFG                      0xdaUL
+	#define HWRM_PORT_EP_TX_CFG                       0xdbUL
+	#define HWRM_PORT_CFG                             0xdcUL
+	#define HWRM_PORT_QCFG                            0xddUL
+	#define HWRM_PORT_MAC_QCAPS                       0xdfUL
+	#define HWRM_TEMP_MONITOR_QUERY                   0xe0UL
+	#define HWRM_REG_POWER_QUERY                      0xe1UL
+	#define HWRM_CORE_FREQUENCY_QUERY                 0xe2UL
+	#define HWRM_REG_POWER_HISTOGRAM                  0xe3UL
+	#define HWRM_WOL_FILTER_ALLOC                     0xf0UL
+	#define HWRM_WOL_FILTER_FREE                      0xf1UL
+	#define HWRM_WOL_FILTER_QCFG                      0xf2UL
+	#define HWRM_WOL_REASON_QCFG                      0xf3UL
+	#define HWRM_CFA_METER_QCAPS                      0xf4UL
+	#define HWRM_CFA_METER_PROFILE_ALLOC              0xf5UL
+	#define HWRM_CFA_METER_PROFILE_FREE               0xf6UL
+	#define HWRM_CFA_METER_PROFILE_CFG                0xf7UL
+	#define HWRM_CFA_METER_INSTANCE_ALLOC             0xf8UL
+	#define HWRM_CFA_METER_INSTANCE_FREE              0xf9UL
+	#define HWRM_CFA_METER_INSTANCE_CFG               0xfaUL
+	#define HWRM_CFA_VFR_ALLOC                        0xfdUL
+	#define HWRM_CFA_VFR_FREE                         0xfeUL
+	#define HWRM_CFA_VF_PAIR_ALLOC                    0x100UL
+	#define HWRM_CFA_VF_PAIR_FREE                     0x101UL
+	#define HWRM_CFA_VF_PAIR_INFO                     0x102UL
+	#define HWRM_CFA_FLOW_ALLOC                       0x103UL
+	#define HWRM_CFA_FLOW_FREE                        0x104UL
+	#define HWRM_CFA_FLOW_FLUSH                       0x105UL
+	#define HWRM_CFA_FLOW_STATS                       0x106UL
+	#define HWRM_CFA_FLOW_INFO                        0x107UL
+	#define HWRM_CFA_DECAP_FILTER_ALLOC               0x108UL
+	#define HWRM_CFA_DECAP_FILTER_FREE                0x109UL
+	#define HWRM_CFA_VLAN_ANTISPOOF_QCFG              0x10aUL
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_ALLOC       0x10bUL
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_FREE        0x10cUL
+	#define HWRM_CFA_PAIR_ALLOC                       0x10dUL
+	#define HWRM_CFA_PAIR_FREE                        0x10eUL
+	#define HWRM_CFA_PAIR_INFO                        0x10fUL
+	#define HWRM_FW_IPC_MSG                           0x110UL
+	#define HWRM_CFA_REDIRECT_TUNNEL_TYPE_INFO        0x111UL
+	#define HWRM_CFA_REDIRECT_QUERY_TUNNEL_TYPE       0x112UL
+	#define HWRM_CFA_FLOW_AGING_TIMER_RESET           0x113UL
+	#define HWRM_CFA_FLOW_AGING_CFG                   0x114UL
+	#define HWRM_CFA_FLOW_AGING_QCFG                  0x115UL
+	#define HWRM_CFA_FLOW_AGING_QCAPS                 0x116UL
+	#define HWRM_CFA_CTX_MEM_RGTR                     0x117UL
+	#define HWRM_CFA_CTX_MEM_UNRGTR                   0x118UL
+	#define HWRM_CFA_CTX_MEM_QCTX                     0x119UL
+	#define HWRM_CFA_CTX_MEM_QCAPS                    0x11aUL
+	#define HWRM_CFA_COUNTER_QCAPS                    0x11bUL
+	#define HWRM_CFA_COUNTER_CFG                      0x11cUL
+	#define HWRM_CFA_COUNTER_QCFG                     0x11dUL
+	#define HWRM_CFA_COUNTER_QSTATS                   0x11eUL
+	#define HWRM_CFA_TCP_FLAG_PROCESS_QCFG            0x11fUL
+	#define HWRM_CFA_EEM_QCAPS                        0x120UL
+	#define HWRM_CFA_EEM_CFG                          0x121UL
+	#define HWRM_CFA_EEM_QCFG                         0x122UL
+	#define HWRM_CFA_EEM_OP                           0x123UL
+	#define HWRM_CFA_ADV_FLOW_MGNT_QCAPS              0x124UL
+	#define HWRM_CFA_TFLIB                            0x125UL
+	#define HWRM_CFA_LAG_GROUP_MEMBER_RGTR            0x126UL
+	#define HWRM_CFA_LAG_GROUP_MEMBER_UNRGTR          0x127UL
+	#define HWRM_CFA_TLS_FILTER_ALLOC                 0x128UL
+	#define HWRM_CFA_TLS_FILTER_FREE                  0x129UL
+	#define HWRM_CFA_RELEASE_AFM_FUNC                 0x12aUL
+	#define HWRM_ENGINE_CKV_STATUS                    0x12eUL
+	#define HWRM_ENGINE_CKV_CKEK_ADD                  0x12fUL
+	#define HWRM_ENGINE_CKV_CKEK_DELETE               0x130UL
+	#define HWRM_ENGINE_CKV_KEY_ADD                   0x131UL
+	#define HWRM_ENGINE_CKV_KEY_DELETE                0x132UL
+	#define HWRM_ENGINE_CKV_FLUSH                     0x133UL
+	#define HWRM_ENGINE_CKV_RNG_GET                   0x134UL
+	#define HWRM_ENGINE_CKV_KEY_GEN                   0x135UL
+	#define HWRM_ENGINE_CKV_KEY_LABEL_CFG             0x136UL
+	#define HWRM_ENGINE_CKV_KEY_LABEL_QCFG            0x137UL
+	#define HWRM_ENGINE_QG_CONFIG_QUERY               0x13cUL
+	#define HWRM_ENGINE_QG_QUERY                      0x13dUL
+	#define HWRM_ENGINE_QG_METER_PROFILE_CONFIG_QUERY 0x13eUL
+	#define HWRM_ENGINE_QG_METER_PROFILE_QUERY        0x13fUL
+	#define HWRM_ENGINE_QG_METER_PROFILE_ALLOC        0x140UL
+	#define HWRM_ENGINE_QG_METER_PROFILE_FREE         0x141UL
+	#define HWRM_ENGINE_QG_METER_QUERY                0x142UL
+	#define HWRM_ENGINE_QG_METER_BIND                 0x143UL
+	#define HWRM_ENGINE_QG_METER_UNBIND               0x144UL
+	#define HWRM_ENGINE_QG_FUNC_BIND                  0x145UL
+	#define HWRM_ENGINE_SG_CONFIG_QUERY               0x146UL
+	#define HWRM_ENGINE_SG_QUERY                      0x147UL
+	#define HWRM_ENGINE_SG_METER_QUERY                0x148UL
+	#define HWRM_ENGINE_SG_METER_CONFIG               0x149UL
+	#define HWRM_ENGINE_SG_QG_BIND                    0x14aUL
+	#define HWRM_ENGINE_QG_SG_UNBIND                  0x14bUL
+	#define HWRM_ENGINE_CONFIG_QUERY                  0x154UL
+	#define HWRM_ENGINE_STATS_CONFIG                  0x155UL
+	#define HWRM_ENGINE_STATS_CLEAR                   0x156UL
+	#define HWRM_ENGINE_STATS_QUERY                   0x157UL
+	#define HWRM_ENGINE_STATS_QUERY_CONTINUOUS_ERROR  0x158UL
+	#define HWRM_ENGINE_RQ_ALLOC                      0x15eUL
+	#define HWRM_ENGINE_RQ_FREE                       0x15fUL
+	#define HWRM_ENGINE_CQ_ALLOC                      0x160UL
+	#define HWRM_ENGINE_CQ_FREE                       0x161UL
+	#define HWRM_ENGINE_NQ_ALLOC                      0x162UL
+	#define HWRM_ENGINE_NQ_FREE                       0x163UL
+	#define HWRM_ENGINE_ON_DIE_RQE_CREDITS            0x164UL
+	#define HWRM_ENGINE_FUNC_QCFG                     0x165UL
+	#define HWRM_FUNC_RESOURCE_QCAPS                  0x190UL
+	#define HWRM_FUNC_VF_RESOURCE_CFG                 0x191UL
+	#define HWRM_FUNC_BACKING_STORE_QCAPS             0x192UL
+	#define HWRM_FUNC_BACKING_STORE_CFG               0x193UL
+	#define HWRM_FUNC_BACKING_STORE_QCFG              0x194UL
+	#define HWRM_FUNC_VF_BW_CFG                       0x195UL
+	#define HWRM_FUNC_VF_BW_QCFG                      0x196UL
+	#define HWRM_FUNC_HOST_PF_IDS_QUERY               0x197UL
+	#define HWRM_FUNC_QSTATS_EXT                      0x198UL
+	#define HWRM_STAT_EXT_CTX_QUERY                   0x199UL
+	#define HWRM_FUNC_SPD_CFG                         0x19aUL
+	#define HWRM_FUNC_SPD_QCFG                        0x19bUL
+	#define HWRM_FUNC_PTP_PIN_QCFG                    0x19cUL
+	#define HWRM_FUNC_PTP_PIN_CFG                     0x19dUL
+	#define HWRM_FUNC_PTP_CFG                         0x19eUL
+	#define HWRM_FUNC_PTP_TS_QUERY                    0x19fUL
+	#define HWRM_FUNC_PTP_EXT_CFG                     0x1a0UL
+	#define HWRM_FUNC_PTP_EXT_QCFG                    0x1a1UL
+	#define HWRM_FUNC_KEY_CTX_ALLOC                   0x1a2UL
+	#define HWRM_FUNC_BACKING_STORE_CFG_V2            0x1a3UL
+	#define HWRM_FUNC_BACKING_STORE_QCFG_V2           0x1a4UL
+	#define HWRM_FUNC_DBR_PACING_CFG                  0x1a5UL
+	#define HWRM_FUNC_DBR_PACING_QCFG                 0x1a6UL
+	#define HWRM_FUNC_DBR_PACING_BROADCAST_EVENT      0x1a7UL
+	#define HWRM_FUNC_BACKING_STORE_QCAPS_V2          0x1a8UL
+	#define HWRM_FUNC_DBR_PACING_NQLIST_QUERY         0x1a9UL
+	#define HWRM_FUNC_DBR_RECOVERY_COMPLETED          0x1aaUL
+	#define HWRM_FUNC_SYNCE_CFG                       0x1abUL
+	#define HWRM_FUNC_SYNCE_QCFG                      0x1acUL
+	#define HWRM_FUNC_KEY_CTX_FREE                    0x1adUL
+	#define HWRM_FUNC_LAG_MODE_CFG                    0x1aeUL
+	#define HWRM_FUNC_LAG_MODE_QCFG                   0x1afUL
+	#define HWRM_FUNC_LAG_CREATE                      0x1b0UL
+	#define HWRM_FUNC_LAG_UPDATE                      0x1b1UL
+	#define HWRM_FUNC_LAG_FREE                        0x1b2UL
+	#define HWRM_FUNC_LAG_QCFG                        0x1b3UL
+	#define HWRM_FUNC_TIMEDTX_PACING_RATE_ADD         0x1c2UL
+	#define HWRM_FUNC_TIMEDTX_PACING_RATE_DELETE      0x1c3UL
+	#define HWRM_FUNC_TIMEDTX_PACING_RATE_QUERY       0x1c4UL
+	#define HWRM_SELFTEST_QLIST                       0x200UL
+	#define HWRM_SELFTEST_EXEC                        0x201UL
+	#define HWRM_SELFTEST_IRQ                         0x202UL
+	#define HWRM_SELFTEST_RETRIEVE_SERDES_DATA        0x203UL
+	#define HWRM_PCIE_QSTATS                          0x204UL
+	#define HWRM_MFG_FRU_WRITE_CONTROL                0x205UL
+	#define HWRM_MFG_TIMERS_QUERY                     0x206UL
+	#define HWRM_MFG_OTP_CFG                          0x207UL
+	#define HWRM_MFG_OTP_QCFG                         0x208UL
+	#define HWRM_MFG_HDMA_TEST                        0x209UL
+	#define HWRM_MFG_FRU_EEPROM_WRITE                 0x20aUL
+	#define HWRM_MFG_FRU_EEPROM_READ                  0x20bUL
+	#define HWRM_MFG_SOC_IMAGE                        0x20cUL
+	#define HWRM_MFG_SOC_QSTATUS                      0x20dUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_FINALIZE     0x20eUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_READ         0x20fUL
+	#define HWRM_MFG_PARAM_CRITICAL_DATA_HEALTH       0x210UL
+	#define HWRM_MFG_PRVSN_EXPORT_CSR                 0x211UL
+	#define HWRM_MFG_PRVSN_IMPORT_CERT                0x212UL
+	#define HWRM_MFG_PRVSN_GET_STATE                  0x213UL
+	#define HWRM_MFG_GET_NVM_MEASUREMENT              0x214UL
+	#define HWRM_MFG_PSOC_QSTATUS                     0x215UL
+	#define HWRM_MFG_SELFTEST_QLIST                   0x216UL
+	#define HWRM_MFG_SELFTEST_EXEC                    0x217UL
+	#define HWRM_STAT_GENERIC_QSTATS                  0x218UL
+	#define HWRM_MFG_PRVSN_EXPORT_CERT                0x219UL
+	#define HWRM_STAT_DB_ERROR_QSTATS                 0x21aUL
+	#define HWRM_MFG_TESTS                            0x21bUL
+	#define HWRM_MFG_WRITE_CERT_NVM                   0x21cUL
+	#define HWRM_PORT_POE_CFG                         0x230UL
+	#define HWRM_PORT_POE_QCFG                        0x231UL
+	#define HWRM_UDCC_QCAPS                           0x258UL
+	#define HWRM_UDCC_CFG                             0x259UL
+	#define HWRM_UDCC_QCFG                            0x25aUL
+	#define HWRM_UDCC_SESSION_CFG                     0x25bUL
+	#define HWRM_UDCC_SESSION_QCFG                    0x25cUL
+	#define HWRM_UDCC_SESSION_QUERY                   0x25dUL
+	#define HWRM_UDCC_COMP_CFG                        0x25eUL
+	#define HWRM_UDCC_COMP_QCFG                       0x25fUL
+	#define HWRM_UDCC_COMP_QUERY                      0x260UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCAPS            0x261UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_CFG              0x262UL
+	#define HWRM_QUEUE_PFCWD_TIMEOUT_QCFG             0x263UL
+	#define HWRM_TF                                   0x2bcUL
+	#define HWRM_TF_VERSION_GET                       0x2bdUL
+	#define HWRM_TF_SESSION_OPEN                      0x2c6UL
+	#define HWRM_TF_SESSION_REGISTER                  0x2c8UL
+	#define HWRM_TF_SESSION_UNREGISTER                0x2c9UL
+	#define HWRM_TF_SESSION_CLOSE                     0x2caUL
+	#define HWRM_TF_SESSION_QCFG                      0x2cbUL
+	#define HWRM_TF_SESSION_RESC_QCAPS                0x2ccUL
+	#define HWRM_TF_SESSION_RESC_ALLOC                0x2cdUL
+	#define HWRM_TF_SESSION_RESC_FREE                 0x2ceUL
+	#define HWRM_TF_SESSION_RESC_FLUSH                0x2cfUL
+	#define HWRM_TF_SESSION_RESC_INFO                 0x2d0UL
+	#define HWRM_TF_SESSION_HOTUP_STATE_SET           0x2d1UL
+	#define HWRM_TF_SESSION_HOTUP_STATE_GET           0x2d2UL
+	#define HWRM_TF_TBL_TYPE_GET                      0x2daUL
+	#define HWRM_TF_TBL_TYPE_SET                      0x2dbUL
+	#define HWRM_TF_TBL_TYPE_BULK_GET                 0x2dcUL
+	#define HWRM_TF_EM_INSERT                         0x2eaUL
+	#define HWRM_TF_EM_DELETE                         0x2ebUL
+	#define HWRM_TF_EM_HASH_INSERT                    0x2ecUL
+	#define HWRM_TF_EM_MOVE                           0x2edUL
+	#define HWRM_TF_TCAM_SET                          0x2f8UL
+	#define HWRM_TF_TCAM_GET                          0x2f9UL
+	#define HWRM_TF_TCAM_MOVE                         0x2faUL
+	#define HWRM_TF_TCAM_FREE                         0x2fbUL
+	#define HWRM_TF_GLOBAL_CFG_SET                    0x2fcUL
+	#define HWRM_TF_GLOBAL_CFG_GET                    0x2fdUL
+	#define HWRM_TF_IF_TBL_SET                        0x2feUL
+	#define HWRM_TF_IF_TBL_GET                        0x2ffUL
+	#define HWRM_TF_RESC_USAGE_SET                    0x300UL
+	#define HWRM_TF_RESC_USAGE_QUERY                  0x301UL
+	#define HWRM_TF_TBL_TYPE_ALLOC                    0x302UL
+	#define HWRM_TF_TBL_TYPE_FREE                     0x303UL
+	#define HWRM_TFC_TBL_SCOPE_QCAPS                  0x380UL
+	#define HWRM_TFC_TBL_SCOPE_ID_ALLOC               0x381UL
+	#define HWRM_TFC_TBL_SCOPE_CONFIG                 0x382UL
+	#define HWRM_TFC_TBL_SCOPE_DECONFIG               0x383UL
+	#define HWRM_TFC_TBL_SCOPE_FID_ADD                0x384UL
+	#define HWRM_TFC_TBL_SCOPE_FID_REM                0x385UL
+	#define HWRM_TFC_TBL_SCOPE_POOL_ALLOC             0x386UL
+	#define HWRM_TFC_TBL_SCOPE_POOL_FREE              0x387UL
+	#define HWRM_TFC_SESSION_ID_ALLOC                 0x388UL
+	#define HWRM_TFC_SESSION_FID_ADD                  0x389UL
+	#define HWRM_TFC_SESSION_FID_REM                  0x38aUL
+	#define HWRM_TFC_IDENT_ALLOC                      0x38bUL
+	#define HWRM_TFC_IDENT_FREE                       0x38cUL
+	#define HWRM_TFC_IDX_TBL_ALLOC                    0x38dUL
+	#define HWRM_TFC_IDX_TBL_ALLOC_SET                0x38eUL
+	#define HWRM_TFC_IDX_TBL_SET                      0x38fUL
+	#define HWRM_TFC_IDX_TBL_GET                      0x390UL
+	#define HWRM_TFC_IDX_TBL_FREE                     0x391UL
+	#define HWRM_TFC_GLOBAL_ID_ALLOC                  0x392UL
+	#define HWRM_TFC_TCAM_SET                         0x393UL
+	#define HWRM_TFC_TCAM_GET                         0x394UL
+	#define HWRM_TFC_TCAM_ALLOC                       0x395UL
+	#define HWRM_TFC_TCAM_ALLOC_SET                   0x396UL
+	#define HWRM_TFC_TCAM_FREE                        0x397UL
+	#define HWRM_TFC_IF_TBL_SET                       0x398UL
+	#define HWRM_TFC_IF_TBL_GET                       0x399UL
+	#define HWRM_TFC_TBL_SCOPE_CONFIG_GET             0x39aUL
+	#define HWRM_TFC_RESC_USAGE_QUERY                 0x39bUL
+	#define HWRM_TFC_GLOBAL_ID_FREE                   0x39cUL
+	#define HWRM_TFC_TCAM_PRI_UPDATE                  0x39dUL
+	#define HWRM_TFC_HOT_UPGRADE_PROCESS              0x3a0UL
+	#define HWRM_SV                                   0x400UL
+	#define HWRM_DBG_SERDES_TEST                      0xff0eUL
+	#define HWRM_DBG_LOG_BUFFER_FLUSH                 0xff0fUL
+	#define HWRM_DBG_READ_DIRECT                      0xff10UL
+	#define HWRM_DBG_READ_INDIRECT                    0xff11UL
+	#define HWRM_DBG_WRITE_DIRECT                     0xff12UL
+	#define HWRM_DBG_WRITE_INDIRECT                   0xff13UL
+	#define HWRM_DBG_DUMP                             0xff14UL
+	#define HWRM_DBG_ERASE_NVM                        0xff15UL
+	#define HWRM_DBG_CFG                              0xff16UL
+	#define HWRM_DBG_COREDUMP_LIST                    0xff17UL
+	#define HWRM_DBG_COREDUMP_INITIATE                0xff18UL
+	#define HWRM_DBG_COREDUMP_RETRIEVE                0xff19UL
+	#define HWRM_DBG_FW_CLI                           0xff1aUL
+	#define HWRM_DBG_I2C_CMD                          0xff1bUL
+	#define HWRM_DBG_RING_INFO_GET                    0xff1cUL
+	#define HWRM_DBG_CRASHDUMP_HEADER                 0xff1dUL
+	#define HWRM_DBG_CRASHDUMP_ERASE                  0xff1eUL
+	#define HWRM_DBG_DRV_TRACE                        0xff1fUL
+	#define HWRM_DBG_QCAPS                            0xff20UL
+	#define HWRM_DBG_QCFG                             0xff21UL
+	#define HWRM_DBG_CRASHDUMP_MEDIUM_CFG             0xff22UL
+	#define HWRM_DBG_USEQ_ALLOC                       0xff23UL
+	#define HWRM_DBG_USEQ_FREE                        0xff24UL
+	#define HWRM_DBG_USEQ_FLUSH                       0xff25UL
+	#define HWRM_DBG_USEQ_QCAPS                       0xff26UL
+	#define HWRM_DBG_USEQ_CW_CFG                      0xff27UL
+	#define HWRM_DBG_USEQ_SCHED_CFG                   0xff28UL
+	#define HWRM_DBG_USEQ_RUN                         0xff29UL
+	#define HWRM_DBG_USEQ_DELIVERY_REQ                0xff2aUL
+	#define HWRM_DBG_USEQ_RESP_HDR                    0xff2bUL
+	#define HWRM_DBG_COREDUMP_CAPTURE                 0xff2cUL
+	#define HWRM_DBG_PTRACE                           0xff2dUL
+	#define HWRM_DBG_SIM_CABLE_STATE                  0xff2eUL
+	#define HWRM_NVM_GET_VPD_FIELD_INFO               0xffeaUL
+	#define HWRM_NVM_SET_VPD_FIELD_INFO               0xffebUL
+	#define HWRM_NVM_DEFRAG                           0xffecUL
+	#define HWRM_NVM_REQ_ARBITRATION                  0xffedUL
+	#define HWRM_NVM_FACTORY_DEFAULTS                 0xffeeUL
+	#define HWRM_NVM_VALIDATE_OPTION                  0xffefUL
+	#define HWRM_NVM_FLUSH                            0xfff0UL
+	#define HWRM_NVM_GET_VARIABLE                     0xfff1UL
+	#define HWRM_NVM_SET_VARIABLE                     0xfff2UL
+	#define HWRM_NVM_INSTALL_UPDATE                   0xfff3UL
+	#define HWRM_NVM_MODIFY                           0xfff4UL
+	#define HWRM_NVM_VERIFY_UPDATE                    0xfff5UL
+	#define HWRM_NVM_GET_DEV_INFO                     0xfff6UL
+	#define HWRM_NVM_ERASE_DIR_ENTRY                  0xfff7UL
+	#define HWRM_NVM_MOD_DIR_ENTRY                    0xfff8UL
+	#define HWRM_NVM_FIND_DIR_ENTRY                   0xfff9UL
+	#define HWRM_NVM_GET_DIR_ENTRIES                  0xfffaUL
+	#define HWRM_NVM_GET_DIR_INFO                     0xfffbUL
+	#define HWRM_NVM_RAW_DUMP                         0xfffcUL
+	#define HWRM_NVM_READ                             0xfffdUL
+	#define HWRM_NVM_WRITE                            0xfffeUL
+	#define HWRM_NVM_RAW_WRITE_BLK                    0xffffUL
+	#define HWRM_LAST                                HWRM_NVM_RAW_WRITE_BLK
+	__le16	unused_0[3];
+};
+
+/* ret_codes (size:64b/8B) */
+struct ret_codes {
+	__le16	error_code;
+	#define HWRM_ERR_CODE_SUCCESS                      0x0UL
+	#define HWRM_ERR_CODE_FAIL                         0x1UL
+	#define HWRM_ERR_CODE_INVALID_PARAMS               0x2UL
+	#define HWRM_ERR_CODE_RESOURCE_ACCESS_DENIED       0x3UL
+	#define HWRM_ERR_CODE_RESOURCE_ALLOC_ERROR         0x4UL
+	#define HWRM_ERR_CODE_INVALID_FLAGS                0x5UL
+	#define HWRM_ERR_CODE_INVALID_ENABLES              0x6UL
+	#define HWRM_ERR_CODE_UNSUPPORTED_TLV              0x7UL
+	#define HWRM_ERR_CODE_NO_BUFFER                    0x8UL
+	#define HWRM_ERR_CODE_UNSUPPORTED_OPTION_ERR       0x9UL
+	#define HWRM_ERR_CODE_HOT_RESET_PROGRESS           0xaUL
+	#define HWRM_ERR_CODE_HOT_RESET_FAIL               0xbUL
+	#define HWRM_ERR_CODE_NO_FLOW_COUNTER_DURING_ALLOC 0xcUL
+	#define HWRM_ERR_CODE_KEY_HASH_COLLISION           0xdUL
+	#define HWRM_ERR_CODE_KEY_ALREADY_EXISTS           0xeUL
+	#define HWRM_ERR_CODE_HWRM_ERROR                   0xfUL
+	#define HWRM_ERR_CODE_BUSY                         0x10UL
+	#define HWRM_ERR_CODE_RESOURCE_LOCKED              0x11UL
+	#define HWRM_ERR_CODE_PF_UNAVAILABLE               0x12UL
+	#define HWRM_ERR_CODE_ENTITY_NOT_PRESENT           0x13UL
+	#define HWRM_ERR_CODE_SECURE_SOC_ERROR             0x14UL
+	#define HWRM_ERR_CODE_TLV_ENCAPSULATED_RESPONSE    0x8000UL
+	#define HWRM_ERR_CODE_UNKNOWN_ERR                  0xfffeUL
+	#define HWRM_ERR_CODE_CMD_NOT_SUPPORTED            0xffffUL
+	#define HWRM_ERR_CODE_LAST                        HWRM_ERR_CODE_CMD_NOT_SUPPORTED
+	__le16	unused_0[3];
+};
+
+/* hwrm_err_output (size:128b/16B) */
+struct hwrm_err_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	opaque_0;
+	__le16	opaque_1;
+	u8	cmd_err;
+	u8	valid;
+};
+#define HWRM_NA_SIGNATURE ((__le32)(-1))
+#define HWRM_MAX_REQ_LEN 128
+#define HWRM_MAX_RESP_LEN 704
+#define HW_HASH_INDEX_SIZE 0x80
+#define HW_HASH_KEY_SIZE 40
+#define HWRM_RESP_VALID_KEY 1
+#define HWRM_TARGET_ID_BONO 0xFFF8
+#define HWRM_TARGET_ID_KONG 0xFFF9
+#define HWRM_TARGET_ID_APE 0xFFFA
+#define HWRM_TARGET_ID_TOOLS 0xFFFD
+#define HWRM_VERSION_MAJOR 1
+#define HWRM_VERSION_MINOR 10
+#define HWRM_VERSION_UPDATE 3
+#define HWRM_VERSION_RSVD 97
+#define HWRM_VERSION_STR "1.10.3.97"
+
+/* hwrm_ver_get_input (size:192b/24B) */
+struct hwrm_ver_get_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	hwrm_intf_maj;
+	u8	hwrm_intf_min;
+	u8	hwrm_intf_upd;
+	u8	unused_0[5];
+};
+
+/* hwrm_ver_get_output (size:1408b/176B) */
+struct hwrm_ver_get_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	hwrm_intf_maj_8b;
+	u8	hwrm_intf_min_8b;
+	u8	hwrm_intf_upd_8b;
+	u8	hwrm_intf_rsvd_8b;
+	u8	hwrm_fw_maj_8b;
+	u8	hwrm_fw_min_8b;
+	u8	hwrm_fw_bld_8b;
+	u8	hwrm_fw_rsvd_8b;
+	u8	mgmt_fw_maj_8b;
+	u8	mgmt_fw_min_8b;
+	u8	mgmt_fw_bld_8b;
+	u8	mgmt_fw_rsvd_8b;
+	u8	netctrl_fw_maj_8b;
+	u8	netctrl_fw_min_8b;
+	u8	netctrl_fw_bld_8b;
+	u8	netctrl_fw_rsvd_8b;
+	__le32	dev_caps_cfg;
+	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_FW_UPD_SUPPORTED                  0x1UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_FW_DCBX_AGENT_SUPPORTED                  0x2UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_SUPPORTED                      0x4UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_SHORT_CMD_REQUIRED                       0x8UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_KONG_MB_CHNL_SUPPORTED                   0x10UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_HANDLE_64BIT_SUPPORTED              0x20UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_L2_FILTER_TYPES_ROCE_OR_L2_SUPPORTED     0x40UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_VIRTIO_VSWITCH_OFFLOAD_SUPPORTED         0x80UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_TRUSTED_VF_SUPPORTED                     0x100UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_FLOW_AGING_SUPPORTED                     0x200UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_ADV_FLOW_COUNTERS_SUPPORTED              0x400UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_EEM_SUPPORTED                        0x800UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_ADV_FLOW_MGNT_SUPPORTED              0x1000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TFLIB_SUPPORTED                      0x2000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_CFA_TRUFLOW_SUPPORTED                    0x4000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_BOOT_CAPABLE                      0x8000UL
+	#define VER_GET_RESP_DEV_CAPS_CFG_SECURE_SOC_CAPABLE                       0x10000UL
+	u8	roce_fw_maj_8b;
+	u8	roce_fw_min_8b;
+	u8	roce_fw_bld_8b;
+	u8	roce_fw_rsvd_8b;
+	char	hwrm_fw_name[16];
+	char	mgmt_fw_name[16];
+	char	netctrl_fw_name[16];
+	char	active_pkg_name[16];
+	char	roce_fw_name[16];
+	__le16	chip_num;
+	u8	chip_rev;
+	u8	chip_metal;
+	u8	chip_bond_id;
+	u8	chip_platform_type;
+	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_ASIC      0x0UL
+	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_FPGA      0x1UL
+	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM 0x2UL
+	#define VER_GET_RESP_CHIP_PLATFORM_TYPE_LAST     VER_GET_RESP_CHIP_PLATFORM_TYPE_PALLADIUM
+	__le16	max_req_win_len;
+	__le16	max_resp_len;
+	__le16	def_req_timeout;
+	u8	flags;
+	#define VER_GET_RESP_FLAGS_DEV_NOT_RDY                   0x1UL
+	#define VER_GET_RESP_FLAGS_EXT_VER_AVAIL                 0x2UL
+	#define VER_GET_RESP_FLAGS_DEV_NOT_RDY_BACKING_STORE     0x4UL
+	u8	unused_0[2];
+	u8	always_1;
+	__le16	hwrm_intf_major;
+	__le16	hwrm_intf_minor;
+	__le16	hwrm_intf_build;
+	__le16	hwrm_intf_patch;
+	__le16	hwrm_fw_major;
+	__le16	hwrm_fw_minor;
+	__le16	hwrm_fw_build;
+	__le16	hwrm_fw_patch;
+	__le16	mgmt_fw_major;
+	__le16	mgmt_fw_minor;
+	__le16	mgmt_fw_build;
+	__le16	mgmt_fw_patch;
+	__le16	netctrl_fw_major;
+	__le16	netctrl_fw_minor;
+	__le16	netctrl_fw_build;
+	__le16	netctrl_fw_patch;
+	__le16	roce_fw_major;
+	__le16	roce_fw_minor;
+	__le16	roce_fw_build;
+	__le16	roce_fw_patch;
+	__le16	max_ext_req_len;
+	__le16	max_req_timeout;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* eject_cmpl (size:128b/16B) */
+struct eject_cmpl {
+	__le16	type;
+	#define EJECT_CMPL_TYPE_MASK       0x3fUL
+	#define EJECT_CMPL_TYPE_SFT        0
+	#define EJECT_CMPL_TYPE_STAT_EJECT   0x1aUL
+	#define EJECT_CMPL_TYPE_LAST        EJECT_CMPL_TYPE_STAT_EJECT
+	#define EJECT_CMPL_FLAGS_MASK      0xffc0UL
+	#define EJECT_CMPL_FLAGS_SFT       6
+	#define EJECT_CMPL_FLAGS_ERROR      0x40UL
+	__le16	len;
+	__le32	opaque;
+	__le16	v;
+	#define EJECT_CMPL_V                              0x1UL
+	#define EJECT_CMPL_ERRORS_MASK                    0xfffeUL
+	#define EJECT_CMPL_ERRORS_SFT                     1
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_MASK        0xeUL
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_SFT         1
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_NO_BUFFER     (0x0UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_DID_NOT_FIT   (0x1UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_BAD_FORMAT    (0x3UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH         (0x5UL << 1)
+	#define EJECT_CMPL_ERRORS_BUFFER_ERROR_LAST         EJECT_CMPL_ERRORS_BUFFER_ERROR_FLUSH
+	__le16	reserved16;
+	__le32	unused_2;
+};
+
+/* hwrm_cmpl (size:128b/16B) */
+struct hwrm_cmpl {
+	__le16	type;
+	#define CMPL_TYPE_MASK     0x3fUL
+	#define CMPL_TYPE_SFT      0
+	#define CMPL_TYPE_HWRM_DONE  0x20UL
+	#define CMPL_TYPE_LAST      CMPL_TYPE_HWRM_DONE
+	__le16	sequence_id;
+	__le32	unused_1;
+	__le32	v;
+	#define CMPL_V     0x1UL
+	__le32	unused_3;
+};
+
+/* hwrm_fwd_req_cmpl (size:128b/16B) */
+struct hwrm_fwd_req_cmpl {
+	__le16	req_len_type;
+	#define FWD_REQ_CMPL_TYPE_MASK        0x3fUL
+	#define FWD_REQ_CMPL_TYPE_SFT         0
+	#define FWD_REQ_CMPL_TYPE_HWRM_FWD_REQ  0x22UL
+	#define FWD_REQ_CMPL_TYPE_LAST         FWD_REQ_CMPL_TYPE_HWRM_FWD_REQ
+	#define FWD_REQ_CMPL_REQ_LEN_MASK     0xffc0UL
+	#define FWD_REQ_CMPL_REQ_LEN_SFT      6
+	__le16	source_id;
+	__le32	unused0;
+	__le32	req_buf_addr_v[2];
+	#define FWD_REQ_CMPL_V                0x1UL
+	#define FWD_REQ_CMPL_REQ_BUF_ADDR_MASK 0xfffffffeUL
+	#define FWD_REQ_CMPL_REQ_BUF_ADDR_SFT 1
+};
+
+/* hwrm_fwd_resp_cmpl (size:128b/16B) */
+struct hwrm_fwd_resp_cmpl {
+	__le16	type;
+	#define FWD_RESP_CMPL_TYPE_MASK         0x3fUL
+	#define FWD_RESP_CMPL_TYPE_SFT          0
+	#define FWD_RESP_CMPL_TYPE_HWRM_FWD_RESP  0x24UL
+	#define FWD_RESP_CMPL_TYPE_LAST          FWD_RESP_CMPL_TYPE_HWRM_FWD_RESP
+	__le16	source_id;
+	__le16	resp_len;
+	__le16	unused_1;
+	__le32	resp_buf_addr_v[2];
+	#define FWD_RESP_CMPL_V                 0x1UL
+	#define FWD_RESP_CMPL_RESP_BUF_ADDR_MASK 0xfffffffeUL
+	#define FWD_RESP_CMPL_RESP_BUF_ADDR_SFT 1
+};
+
+/* hwrm_async_event_cmpl (size:128b/16B) */
+struct hwrm_async_event_cmpl {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_TYPE_LAST             ASYNC_EVENT_CMPL_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_STATUS_CHANGE              0x0UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_MTU_CHANGE                 0x1UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CHANGE               0x2UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DCB_CONFIG_CHANGE               0x3UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_CONN_NOT_ALLOWED           0x4UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_NOT_ALLOWED      0x5UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LINK_SPEED_CFG_CHANGE           0x6UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PORT_PHY_CFG_CHANGE             0x7UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY                    0x8UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_RECOVERY                  0x9UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_RING_MONITOR_MSG                0xaUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_UNLOAD                0x10UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_DRVR_LOAD                  0x11UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FUNC_FLR_PROC_CMPLT             0x12UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_UNLOAD                  0x20UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_DRVR_LOAD                    0x21UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_FLR                          0x30UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_MAC_ADDR_CHANGE              0x31UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PF_VF_COMM_STATUS_CHANGE        0x32UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_CFG_CHANGE                   0x33UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LLFC_PFC_CHANGE                 0x34UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFAULT_VNIC_CHANGE             0x35UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_FLOW_AGED                    0x36UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEBUG_NOTIFICATION              0x37UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_REQ             0x38UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CACHE_FLUSH_DONE            0x39UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_TCP_FLAG_ACTION_CHANGE          0x3aUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_FLOW_ACTIVE                 0x3bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_EEM_CFG_CHANGE                  0x3cUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_DEFAULT_VNIC_CHANGE       0x3dUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_TFLIB_LINK_STATUS_CHANGE        0x3eUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_QUIESCE_DONE                    0x3fUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DEFERRED_RESPONSE               0x40UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PFC_WATCHDOG_CFG_CHANGE         0x41UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ECHO_REQUEST                    0x42UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PHC_UPDATE                      0x43UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PPS_TIMESTAMP                   0x44UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_ERROR_REPORT                    0x45UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_THRESHOLD       0x46UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_RSS_CHANGE                      0x47UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DOORBELL_PACING_NQ_UPDATE       0x48UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HW_DOORBELL_RECOVERY_READ_ERROR 0x49UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_CTX_ERROR                       0x4aUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_UDCC_SESSION_CHANGE             0x4bUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_DBG_BUF_PRODUCER                0x4cUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_PEER_MMAP_CHANGE                0x4dUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_REPRESENTOR_PAIR_CHANGE         0x4eUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_VF_STAT_CHANGE                  0x4fUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HOST_COREDUMP                   0x50UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_MAX_RGTR_EVENT_ID               0x51UL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_FW_TRACE_MSG                    0xfeUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR                      0xffUL
+	#define ASYNC_EVENT_CMPL_EVENT_ID_LAST                           ASYNC_EVENT_CMPL_EVENT_ID_HWRM_ERROR
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_V          0x1UL
+	#define ASYNC_EVENT_CMPL_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_link_status_change (size:128b/16B) */
+struct hwrm_async_event_cmpl_link_status_change {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LINK_STATUS_CHANGE 0x0UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LAST              ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_ID_LINK_STATUS_CHANGE
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE     0x1UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_DOWN  0x0UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP    0x1UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_LAST ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_LINK_CHANGE_UP
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_MASK       0xeUL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_SFT        1
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_MASK    0xffff0UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PORT_ID_SFT     4
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_MASK      0xff00000UL
+	#define ASYNC_EVENT_CMPL_LINK_STATUS_CHANGE_EVENT_DATA1_PF_ID_SFT       20
+};
+
+/* hwrm_async_event_cmpl_port_conn_not_allowed (size:128b/16B) */
+struct hwrm_async_event_cmpl_port_conn_not_allowed {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_LAST             ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_PORT_CONN_NOT_ALLOWED 0x4UL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_LAST                 ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_ID_PORT_CONN_NOT_ALLOWED
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_MASK                 0xffffUL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_PORT_ID_SFT                  0
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_MASK      0xff0000UL
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_SFT       16
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_NONE        (0x0UL << 16)
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_DISABLETX   (0x1UL << 16)
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_WARNINGMSG  (0x2UL << 16)
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_PWRDOWN     (0x3UL << 16)
+	#define ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_LAST       ASYNC_EVENT_CMPL_PORT_CONN_NOT_ALLOWED_EVENT_DATA1_ENFORCEMENT_POLICY_PWRDOWN
+};
+
+/* hwrm_async_event_cmpl_link_speed_cfg_change (size:128b/16B) */
+struct hwrm_async_event_cmpl_link_speed_cfg_change {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LINK_SPEED_CFG_CHANGE 0x6UL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LAST                 ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_ID_LINK_SPEED_CFG_CHANGE
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_PORT_ID_MASK                     0xffffUL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_PORT_ID_SFT                      0
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_SUPPORTED_LINK_SPEEDS_CHANGE     0x10000UL
+	#define ASYNC_EVENT_CMPL_LINK_SPEED_CFG_CHANGE_EVENT_DATA1_ILLEGAL_LINK_SPEED_CFG           0x20000UL
+};
+
+/* hwrm_async_event_cmpl_reset_notify (size:128b/16B) */
+struct hwrm_async_event_cmpl_reset_notify {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_LAST             ASYNC_EVENT_CMPL_RESET_NOTIFY_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY 0x8UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_LAST        ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_ID_RESET_NOTIFY
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA2_FW_STATUS_CODE_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_V          0x1UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_MASK                  0xffUL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_SFT                   0
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_STOP_TX_QUEUE    0x1UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN           0x2UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_LAST                   ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DRIVER_ACTION_DRIVER_IFDOWN
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MASK                    0xff00UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_SFT                     8
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_MANAGEMENT_RESET_REQUEST  (0x1UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_FATAL        (0x2UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_EXCEPTION_NON_FATAL    (0x3UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FAST_RESET                (0x4UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION             (0x5UL << 8)
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_LAST                     ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_REASON_CODE_FW_ACTIVATION
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_MASK           0xffff0000UL
+	#define ASYNC_EVENT_CMPL_RESET_NOTIFY_EVENT_DATA1_DELAY_IN_100MS_TICKS_SFT            16
+};
+
+/* hwrm_async_event_cmpl_error_recovery (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_recovery {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_RECOVERY_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY 0x9UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_LAST          ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_ID_ERROR_RECOVERY
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASK                 0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_SFT                  0
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_MASTER_FUNC           0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_RECOVERY_EVENT_DATA1_FLAGS_RECOVERY_ENABLED      0x2UL
+};
+
+/* hwrm_async_event_cmpl_ring_monitor_msg (size:128b/16B) */
+struct hwrm_async_event_cmpl_ring_monitor_msg {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_LAST             ASYNC_EVENT_CMPL_RING_MONITOR_MSG_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG 0xaUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_LAST            ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_ID_RING_MONITOR_MSG
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_MASK 0xffUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_SFT 0
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_TX    0x0UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_RX    0x1UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL  0x2UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_LAST ASYNC_EVENT_CMPL_RING_MONITOR_MSG_EVENT_DATA2_DISABLE_RING_TYPE_CMPL
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_V          0x1UL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_RING_MONITOR_MSG_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_vf_cfg_change (size:128b/16B) */
+struct hwrm_async_event_cmpl_vf_cfg_change {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_VF_CFG_CHANGE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE 0x33UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_LAST         ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_ID_VF_CFG_CHANGE
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA2_VF_ID_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_MTU_CHANGE                0x1UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_MRU_CHANGE                0x2UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_DFLT_MAC_ADDR_CHANGE      0x4UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_DFLT_VLAN_CHANGE          0x8UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TRUSTED_VF_CFG_CHANGE     0x10UL
+	#define ASYNC_EVENT_CMPL_VF_CFG_CHANGE_EVENT_DATA1_TF_OWNERSHIP_RELEASE      0x20UL
+};
+
+/* hwrm_async_event_cmpl_default_vnic_change (size:128b/16B) */
+struct hwrm_async_event_cmpl_default_vnic_change {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_TYPE_HWRM_ASYNC_EVENT
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_MASK         0xffc0UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_UNUSED1_SFT          6
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION 0x35UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_LAST                   ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_ID_ALLOC_FREE_NOTIFICATION
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_MASK          0x3UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_SFT           0
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_ALLOC  0x1UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE   0x2UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_LAST           ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_DEF_VNIC_STATE_DEF_VNIC_FREE
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_MASK                   0x3fcUL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_PF_ID_SFT                    2
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_MASK                   0x3fffc00UL
+	#define ASYNC_EVENT_CMPL_DEFAULT_VNIC_CHANGE_EVENT_DATA1_VF_ID_SFT                    10
+};
+
+/* hwrm_async_event_cmpl_hw_flow_aged (size:128b/16B) */
+struct hwrm_async_event_cmpl_hw_flow_aged {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_LAST             ASYNC_EVENT_CMPL_HW_FLOW_AGED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED 0x36UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_ID_HW_FLOW_AGED
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_MASK       0x7fffffffUL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_ID_SFT        0
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION     0x80000000UL
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_RX    (0x0UL << 31)
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX    (0x1UL << 31)
+	#define ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_LAST ASYNC_EVENT_CMPL_HW_FLOW_AGED_EVENT_DATA1_FLOW_DIRECTION_TX
+};
+
+/* hwrm_async_event_cmpl_eem_cache_flush_req (size:128b/16B) */
+struct hwrm_async_event_cmpl_eem_cache_flush_req {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ 0x38UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_LAST               ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_EVENT_ID_EEM_CACHE_FLUSH_REQ
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_V          0x1UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_REQ_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_eem_cache_flush_done (size:128b/16B) */
+struct hwrm_async_event_cmpl_eem_cache_flush_done {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_LAST             ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE 0x39UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_LAST                ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_ID_EEM_CACHE_FLUSH_DONE
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_EEM_CACHE_FLUSH_DONE_EVENT_DATA1_FID_SFT 0
+};
+
+/* hwrm_async_event_cmpl_deferred_response (size:128b/16B) */
+struct hwrm_async_event_cmpl_deferred_response {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE 0x40UL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_LAST             ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_ID_DEFERRED_RESPONSE
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_EVENT_DATA2_SEQ_ID_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_DEFERRED_RESPONSE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_echo_request (size:128b/16B) */
+struct hwrm_async_event_cmpl_echo_request {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_LAST             ASYNC_EVENT_CMPL_ECHO_REQUEST_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_ECHO_REQUEST 0x42UL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ECHO_REQUEST_EVENT_ID_ECHO_REQUEST
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ECHO_REQUEST_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+};
+
+/* hwrm_async_event_cmpl_phc_update (size:128b/16B) */
+struct hwrm_async_event_cmpl_phc_update {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_LAST             ASYNC_EVENT_CMPL_PHC_UPDATE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE 0x43UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_LAST      ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_ID_PHC_UPDATE
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_MASK 0xffffUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_MASTER_FID_SFT 0
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_MASK   0xffff0000UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA2_PHC_SEC_FID_SFT    16
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_MASK          0xfUL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_SFT           0
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_MASTER      0x1UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_SECONDARY   0x2UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_FAILOVER    0x3UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE  0x4UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_LAST           ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_FLAGS_PHC_RTC_UPDATE
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_MASK   0xffff0UL
+	#define ASYNC_EVENT_CMPL_PHC_UPDATE_EVENT_DATA1_PHC_TIME_MSB_SFT    4
+};
+
+/* hwrm_async_event_cmpl_pps_timestamp (size:128b/16B) */
+struct hwrm_async_event_cmpl_pps_timestamp {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_LAST             ASYNC_EVENT_CMPL_PPS_TIMESTAMP_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP 0x44UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_LAST         ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_ID_PPS_TIMESTAMP
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE              0x1UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_INTERNAL       0x0UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL       0x1UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_LAST          ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_EVENT_TYPE_EXTERNAL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_MASK         0xeUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PIN_NUMBER_SFT          1
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_MASK 0xffff0UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA2_PPS_TIMESTAMP_UPPER_SFT 4
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_V          0x1UL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_MASK 0xffffffffUL
+	#define ASYNC_EVENT_CMPL_PPS_TIMESTAMP_EVENT_DATA1_PPS_TIMESTAMP_LOWER_SFT 0
+};
+
+/* hwrm_async_event_cmpl_error_report (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_MASK 0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_EVENT_DATA1_ERROR_TYPE_SFT 0
+};
+
+/* hwrm_async_event_cmpl_dbg_buf_producer (size:128b/16B) */
+struct hwrm_async_event_cmpl_dbg_buf_producer {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_LAST             ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_DBG_BUF_PRODUCER 0x4cUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_LAST            ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_ID_DBG_BUF_PRODUCER
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA2_CURR_OFF_MASK 0xffffffffUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA2_CURR_OFF_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_V          0x1UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_MASK               0xffffUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SFT                0
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SRT_TRACE            0x0UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_SRT2_TRACE           0x1UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CRT_TRACE            0x2UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CRT2_TRACE           0x3UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP0_TRACE          0x4UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_L2_HWRM_TRACE        0x5UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_ROCE_HWRM_TRACE      0x6UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA0_TRACE            0x7UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA1_TRACE            0x8UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_CA2_TRACE            0x9UL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_RIGP1_TRACE          0xaUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE  0xbUL
+	#define ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_LAST                ASYNC_EVENT_CMPL_DBG_BUF_PRODUCER_EVENT_DATA1_TYPE_AFM_KONG_HWRM_TRACE
+};
+
+/* hwrm_async_event_cmpl_hwrm_error (size:128b/16B) */
+struct hwrm_async_event_cmpl_hwrm_error {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_LAST             ASYNC_EVENT_CMPL_HWRM_ERROR_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR 0xffUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_LAST      ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_ID_HWRM_ERROR
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_MASK    0xffUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_SFT     0
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_WARNING   0x0UL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_NONFATAL  0x1UL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL     0x2UL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_LAST     ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA2_SEVERITY_FATAL
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_V          0x1UL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_HWRM_ERROR_EVENT_DATA1_TIMESTAMP     0x1UL
+};
+
+/* hwrm_async_event_cmpl_error_report_base (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_base {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_SFT                         0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_RESERVED                      0x0UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM                   0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL                0x2UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_NVM                           0x3UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD       0x4UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_THERMAL_THRESHOLD             0x5UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_BASE_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
+};
+
+/* hwrm_async_event_cmpl_error_report_pause_storm (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_pause_storm {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_MASK       0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_SFT        0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM  0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_PAUSE_STORM_EVENT_DATA1_ERROR_TYPE_PAUSE_STORM
+};
+
+/* hwrm_async_event_cmpl_error_report_invalid_signal (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_invalid_signal {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_MASK 0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA2_PIN_ID_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_MASK          0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_SFT           0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL  0x2UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_LAST           ASYNC_EVENT_CMPL_ERROR_REPORT_INVALID_SIGNAL_EVENT_DATA1_ERROR_TYPE_INVALID_SIGNAL
+};
+
+/* hwrm_async_event_cmpl_error_report_nvm (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_nvm {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_MASK 0xffffffffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA2_ERR_ADDR_SFT 0
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_MASK     0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_SFT      0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR  0x3UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_LAST      ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_ERROR_TYPE_NVM_ERROR
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_MASK   0xff00UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_SFT    8
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_WRITE    (0x1UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE    (0x2UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_LAST    ASYNC_EVENT_CMPL_ERROR_REPORT_NVM_EVENT_DATA1_NVM_ERR_TYPE_ERASE
+};
+
+/* hwrm_async_event_cmpl_error_report_doorbell_drop_threshold (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_doorbell_drop_threshold {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_MASK                   0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_SFT                    0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD  0x4UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_LAST                    ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_ERROR_TYPE_DOORBELL_DROP_THRESHOLD
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_EPOCH_MASK                        0xffffff00UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DOORBELL_DROP_THRESHOLD_EVENT_DATA1_EPOCH_SFT                         8
+};
+
+/* hwrm_async_event_cmpl_error_report_thermal (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_thermal {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_MASK  0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_CURRENT_TEMP_SFT   0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_THRESHOLD_TEMP_MASK 0xff00UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA2_THRESHOLD_TEMP_SFT 8
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_MASK          0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_SFT           0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_THERMAL_EVENT   0x5UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_LAST           ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_ERROR_TYPE_THERMAL_EVENT
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_MASK      0x700UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SFT       8
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_WARN        (0x0UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_CRITICAL    (0x1UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_FATAL       (0x2UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SHUTDOWN    (0x3UL << 8)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_THRESHOLD_TYPE_SHUTDOWN
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR           0x800UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_DECREASING  (0x0UL << 11)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING  (0x1UL << 11)
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_LAST       ASYNC_EVENT_CMPL_ERROR_REPORT_THERMAL_EVENT_DATA1_TRANSITION_DIR_INCREASING
+};
+
+/* hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported (size:128b/16B) */
+struct hwrm_async_event_cmpl_error_report_dual_data_rate_not_supported {
+	__le16	type;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_MASK            0x3fUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_SFT             0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT  0x2eUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_LAST             ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_TYPE_HWRM_ASYNC_EVENT
+	__le16	event_id;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT 0x45UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_LAST        ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_ID_ERROR_REPORT
+	__le32	event_data2;
+	u8	opaque_v;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_V          0x1UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_MASK 0xfeUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_OPAQUE_SFT 1
+	u8	timestamp_lo;
+	__le16	timestamp_hi;
+	__le32	event_data1;
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_MASK                        0xffUL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_SFT                         0
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED  0x6UL
+	#define ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_LAST                         ASYNC_EVENT_CMPL_ERROR_REPORT_DUAL_DATA_RATE_NOT_SUPPORTED_EVENT_DATA1_ERROR_TYPE_DUAL_DATA_RATE_NOT_SUPPORTED
+};
+
+/* hwrm_func_reset_input (size:192b/24B) */
+struct hwrm_func_reset_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_RESET_REQ_ENABLES_VF_ID_VALID     0x1UL
+	__le16	vf_id;
+	u8	func_reset_level;
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETALL      0x0UL
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETME       0x1UL
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETCHILDREN 0x2UL
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF       0x3UL
+	#define FUNC_RESET_REQ_FUNC_RESET_LEVEL_LAST         FUNC_RESET_REQ_FUNC_RESET_LEVEL_RESETVF
+	u8	unused_0;
+};
+
+/* hwrm_func_reset_output (size:128b/16B) */
+struct hwrm_func_reset_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_getfid_input (size:192b/24B) */
+struct hwrm_func_getfid_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_GETFID_REQ_ENABLES_PCI_ID     0x1UL
+	__le16	pci_id;
+	u8	unused_0[2];
+};
+
+/* hwrm_func_getfid_output (size:128b/16B) */
+struct hwrm_func_getfid_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_func_vf_alloc_input (size:192b/24B) */
+struct hwrm_func_vf_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_VF_ALLOC_REQ_ENABLES_FIRST_VF_ID     0x1UL
+	__le16	first_vf_id;
+	__le16	num_vfs;
+};
+
+/* hwrm_func_vf_alloc_output (size:128b/16B) */
+struct hwrm_func_vf_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	first_vf_id;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_func_vf_free_input (size:192b/24B) */
+struct hwrm_func_vf_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_VF_FREE_REQ_ENABLES_FIRST_VF_ID     0x1UL
+	__le16	first_vf_id;
+	__le16	num_vfs;
+};
+
+/* hwrm_func_vf_free_output (size:128b/16B) */
+struct hwrm_func_vf_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_vf_cfg_input (size:576b/72B) */
+struct hwrm_func_vf_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_VF_CFG_REQ_ENABLES_MTU                      0x1UL
+	#define FUNC_VF_CFG_REQ_ENABLES_GUEST_VLAN               0x2UL
+	#define FUNC_VF_CFG_REQ_ENABLES_ASYNC_EVENT_CR           0x4UL
+	#define FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR            0x8UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS          0x10UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_CMPL_RINGS           0x20UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_TX_RINGS             0x40UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_RX_RINGS             0x80UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_L2_CTXS              0x100UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_VNICS                0x200UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_STAT_CTXS            0x400UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_HW_RING_GRPS         0x800UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_KTLS_TX_KEY_CTXS     0x1000UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_KTLS_RX_KEY_CTXS     0x2000UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_QUIC_TX_KEY_CTXS     0x4000UL
+	#define FUNC_VF_CFG_REQ_ENABLES_NUM_QUIC_RX_KEY_CTXS     0x8000UL
+	__le16	mtu;
+	__le16	guest_vlan;
+	__le16	async_event_cr;
+	u8	dflt_mac_addr[6];
+	__le32	flags;
+	#define FUNC_VF_CFG_REQ_FLAGS_TX_ASSETS_TEST             0x1UL
+	#define FUNC_VF_CFG_REQ_FLAGS_RX_ASSETS_TEST             0x2UL
+	#define FUNC_VF_CFG_REQ_FLAGS_CMPL_ASSETS_TEST           0x4UL
+	#define FUNC_VF_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST     0x8UL
+	#define FUNC_VF_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST       0x10UL
+	#define FUNC_VF_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST       0x20UL
+	#define FUNC_VF_CFG_REQ_FLAGS_VNIC_ASSETS_TEST           0x40UL
+	#define FUNC_VF_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST         0x80UL
+	#define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE       0x100UL
+	#define FUNC_VF_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE      0x200UL
+	__le16	num_rsscos_ctxs;
+	__le16	num_cmpl_rings;
+	__le16	num_tx_rings;
+	__le16	num_rx_rings;
+	__le16	num_l2_ctxs;
+	__le16	num_vnics;
+	__le16	num_stat_ctxs;
+	__le16	num_hw_ring_grps;
+	__le32	num_ktls_tx_key_ctxs;
+	__le32	num_ktls_rx_key_ctxs;
+	__le16	num_msix;
+	u8	unused[2];
+	__le32	num_quic_tx_key_ctxs;
+	__le32	num_quic_rx_key_ctxs;
+};
+
+/* hwrm_func_vf_cfg_output (size:128b/16B) */
+struct hwrm_func_vf_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_qcaps_input (size:192b/24B) */
+struct hwrm_func_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_qcaps_output (size:1152b/144B) */
+struct hwrm_func_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	__le16	port_id;
+	__le32	flags;
+	#define FUNC_QCAPS_RESP_FLAGS_PUSH_MODE_SUPPORTED                   0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_GLOBAL_MSIX_AUTOMASKING               0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_PTP_SUPPORTED                         0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V1_SUPPORTED                     0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_ROCE_V2_SUPPORTED                     0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_MAGICPKT_SUPPORTED                0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_WOL_BMP_SUPPORTED                     0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_TX_RING_RL_SUPPORTED                  0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_TX_BW_CFG_SUPPORTED                   0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_VF_TX_RING_RL_SUPPORTED               0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_VF_BW_CFG_SUPPORTED                   0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_STD_TX_RING_MODE_SUPPORTED            0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_GENEVE_TUN_FLAGS_SUPPORTED            0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_NVGRE_TUN_FLAGS_SUPPORTED             0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_GRE_TUN_FLAGS_SUPPORTED               0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_MPLS_TUN_FLAGS_SUPPORTED              0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PCIE_STATS_SUPPORTED                  0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ADOPTED_PF_SUPPORTED                  0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ADMIN_PF_SUPPORTED                    0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_LINK_ADMIN_STATUS_SUPPORTED           0x80000UL
+	#define FUNC_QCAPS_RESP_FLAGS_WCB_PUSH_MODE                         0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_DYNAMIC_TX_RING_ALLOC                 0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_HOT_RESET_CAPABLE                     0x400000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ERROR_RECOVERY_CAPABLE                0x800000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_STATS_SUPPORTED                   0x1000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_ERR_RECOVER_RELOAD                    0x2000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_NOTIFY_VF_DEF_VNIC_CHNG_SUPPORTED     0x4000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_VLAN_ACCELERATION_TX_DISABLED         0x8000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_COREDUMP_CMD_SUPPORTED                0x10000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_CRASHDUMP_CMD_SUPPORTED               0x20000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_PFC_WD_STATS_SUPPORTED                0x40000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_DBG_QCAPS_CMD_SUPPORTED               0x80000000UL
+	u8	mac_address[6];
+	__le16	max_rsscos_ctx;
+	__le16	max_cmpl_rings;
+	__le16	max_tx_rings;
+	__le16	max_rx_rings;
+	__le16	max_l2_ctxs;
+	__le16	max_vnics;
+	__le16	first_vf_id;
+	__le16	max_vfs;
+	__le16	max_stat_ctx;
+	__le32	max_encap_records;
+	__le32	max_decap_records;
+	__le32	max_tx_em_flows;
+	__le32	max_tx_wm_flows;
+	__le32	max_rx_em_flows;
+	__le32	max_rx_wm_flows;
+	__le32	max_mcast_filters;
+	__le32	max_flow_id;
+	__le32	max_hw_ring_grps;
+	__le16	max_sp_tx_rings;
+	__le16	max_msix_vfs;
+	__le32	flags_ext;
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_MARK_SUPPORTED                          0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECN_STATS_SUPPORTED                         0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_EXT_HW_STATS_SUPPORTED                      0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_HOT_RESET_IF_SUPPORT                        0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PROXY_MODE_SUPPORT                          0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_PROXY_SRC_INTF_OVERRIDE_SUPPORT          0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_SCHQ_SUPPORTED                              0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PPP_PUSH_MODE_SUPPORTED                     0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_EVB_MODE_CFG_NOT_SUPPORTED                  0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_SOC_SPD_SUPPORTED                           0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_FW_LIVEPATCH_SUPPORTED                      0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_FAST_RESET_CAPABLE                          0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_METADATA_CFG_CAPABLE                     0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_NVM_OPTION_ACTION_SUPPORTED                 0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_BD_METADATA_SUPPORTED                       0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_ECHO_REQUEST_SUPPORTED                      0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_NPAR_1_2_SUPPORTED                          0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PTM_SUPPORTED                           0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_PPS_SUPPORTED                           0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_VF_CFG_ASYNC_FOR_PF_SUPPORTED               0x80000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PARTITION_BW_SUPPORTED                      0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_DFLT_VLAN_TPID_PCP_SUPPORTED                0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_KTLS_SUPPORTED                              0x400000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_EP_RATE_CONTROL                             0x800000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_MIN_BW_SUPPORTED                            0x1000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_TX_COAL_CMPL_CAP                            0x2000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_SUPPORTED                             0x4000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_BS_V2_REQUIRED                              0x8000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_PTP_64BIT_RTC_SUPPORTED                     0x10000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_DBR_PACING_SUPPORTED                        0x20000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_HW_DBR_DROP_RECOV_SUPPORTED                 0x40000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT_DISABLE_CQ_OVERFLOW_DETECTION_SUPPORTED     0x80000000UL
+	u8	max_schqs;
+	u8	mpc_chnls_cap;
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TCE         0x1UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RCE         0x2UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_TE_CFA      0x4UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_RE_CFA      0x8UL
+	#define FUNC_QCAPS_RESP_MPC_CHNLS_CAP_PRIMATE     0x10UL
+	__le16	max_key_ctxs_alloc;
+	__le32	flags_ext2;
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_RX_ALL_PKTS_TIMESTAMPS_SUPPORTED      0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_QUIC_SUPPORTED                        0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KDNET_SUPPORTED                       0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_EXT_SUPPORTED              0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_DBR_DROP_RECOVERY_SUPPORTED        0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_GENERIC_STATS_SUPPORTED               0x20UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDP_GSO_SUPPORTED                     0x40UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SYNCE_SUPPORTED                       0x80UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DBR_PACING_V0_SUPPORTED               0x100UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TX_PKT_TS_CMPL_SUPPORTED              0x200UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HW_LAG_SUPPORTED                      0x400UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ON_CHIP_CTX_SUPPORTED                 0x800UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_STEERING_TAG_SUPPORTED                0x1000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ENHANCED_VF_SCALE_SUPPORTED           0x2000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_KEY_XID_PARTITION_SUPPORTED           0x4000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_CONCURRENT_KTLS_QUIC_SUPPORTED        0x8000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_CROSS_TC_CAP_SUPPORTED           0x10000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_CAP_SUPPORTED             0x20000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SCHQ_PER_TC_RESERVATION_SUPPORTED     0x40000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_DB_ERROR_STATS_SUPPORTED              0x80000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_ROCE_VF_RESOURCE_MGMT_SUPPORTED       0x100000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_UDCC_SUPPORTED                        0x200000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_SO_TXTIME_SUPPORTED          0x400000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_SW_MAX_RESOURCE_LIMITS_SUPPORTED      0x800000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_INGRESS_NIC_FLOW_SUPPORTED         0x1000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_LPBK_STATS_SUPPORTED                  0x2000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TF_EGRESS_NIC_FLOW_SUPPORTED          0x4000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_MULTI_LOSSLESS_QUEUES_SUPPORTED       0x8000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_PEER_MMAP_SUPPORTED                   0x10000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_TIMED_TX_PACING_SUPPORTED             0x20000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_VF_STAT_EJECTION_SUPPORTED            0x40000000UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT2_HOST_COREDUMP_SUPPORTED               0x80000000UL
+	__le16	tunnel_disable_flag;
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_VXLAN      0x1UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NGE        0x2UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_NVGRE      0x4UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_L2GRE      0x8UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_GRE        0x10UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_IPINIP     0x20UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_MPLS       0x40UL
+	#define FUNC_QCAPS_RESP_TUNNEL_DISABLE_FLAG_DISABLE_PPPOE      0x80UL
+	__le16	xid_partition_cap;
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_TX_CK     0x1UL
+	#define FUNC_QCAPS_RESP_XID_PARTITION_CAP_RX_CK     0x2UL
+	u8	device_serial_number[8];
+	__le16	ctxs_per_partition;
+	__le16	max_tso_segs;
+	__le32	roce_vf_max_av;
+	__le32	roce_vf_max_cq;
+	__le32	roce_vf_max_mrw;
+	__le32	roce_vf_max_qp;
+	__le32	roce_vf_max_srq;
+	__le32	roce_vf_max_gid;
+	__le32	flags_ext3;
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RM_RSV_WHILE_ALLOC_CAP            0x1UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_REQUIRE_L2_FILTER                 0x2UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MAX_ROCE_VFS_SUPPORTED            0x4UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_RX_RATE_PROFILE_SEL_SUPPORTED     0x8UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_BIDI_OPT_SUPPORTED                0x10UL
+	#define FUNC_QCAPS_RESP_FLAGS_EXT3_MIRROR_ON_ROCE_SUPPORTED          0x20UL
+	__le16	max_roce_vfs;
+	__le16	max_crypto_rx_flow_filters;
+	u8	unused_3[3];
+	u8	valid;
+};
+
+/* hwrm_func_qcfg_input (size:192b/24B) */
+struct hwrm_func_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_qcfg_output (size:1344b/168B) */
+struct hwrm_func_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	__le16	port_id;
+	__le16	vlan;
+	__le16	flags;
+	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_MAGICPKT_ENABLED     0x1UL
+	#define FUNC_QCFG_RESP_FLAGS_OOB_WOL_BMP_ENABLED          0x2UL
+	#define FUNC_QCFG_RESP_FLAGS_FW_DCBX_AGENT_ENABLED        0x4UL
+	#define FUNC_QCFG_RESP_FLAGS_STD_TX_RING_MODE_ENABLED     0x8UL
+	#define FUNC_QCFG_RESP_FLAGS_FW_LLDP_AGENT_ENABLED        0x10UL
+	#define FUNC_QCFG_RESP_FLAGS_MULTI_HOST                   0x20UL
+	#define FUNC_QCFG_RESP_FLAGS_TRUSTED_VF                   0x40UL
+	#define FUNC_QCFG_RESP_FLAGS_SECURE_MODE_ENABLED          0x80UL
+	#define FUNC_QCFG_RESP_FLAGS_PREBOOT_LEGACY_L2_RINGS      0x100UL
+	#define FUNC_QCFG_RESP_FLAGS_HOT_RESET_ALLOWED            0x200UL
+	#define FUNC_QCFG_RESP_FLAGS_PPP_PUSH_MODE_ENABLED        0x400UL
+	#define FUNC_QCFG_RESP_FLAGS_RING_MONITOR_ENABLED         0x800UL
+	#define FUNC_QCFG_RESP_FLAGS_FAST_RESET_ALLOWED           0x1000UL
+	#define FUNC_QCFG_RESP_FLAGS_MULTI_ROOT                   0x2000UL
+	#define FUNC_QCFG_RESP_FLAGS_ENABLE_RDMA_SRIOV            0x4000UL
+	#define FUNC_QCFG_RESP_FLAGS_ROCE_VNIC_ID_VALID           0x8000UL
+	u8	mac_address[6];
+	__le16	pci_id;
+	__le16	alloc_rsscos_ctx;
+	__le16	alloc_cmpl_rings;
+	__le16	alloc_tx_rings;
+	__le16	alloc_rx_rings;
+	__le16	alloc_l2_ctx;
+	__le16	alloc_vnics;
+	__le16	admin_mtu;
+	__le16	mru;
+	__le16	stat_ctx_id;
+	u8	port_partition_type;
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_SPF     0x0UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_MPFS    0x1UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_0 0x2UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_5 0x3UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR2_0 0x4UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_NPAR1_2 0x5UL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN 0xffUL
+	#define FUNC_QCFG_RESP_PORT_PARTITION_TYPE_LAST   FUNC_QCFG_RESP_PORT_PARTITION_TYPE_UNKNOWN
+	u8	port_pf_cnt;
+	#define FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL 0x0UL
+	#define FUNC_QCFG_RESP_PORT_PF_CNT_LAST   FUNC_QCFG_RESP_PORT_PF_CNT_UNAVAIL
+	__le16	dflt_vnic_id;
+	__le16	max_mtu_configured;
+	__le32	min_bw;
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_SFT              0
+	#define FUNC_QCFG_RESP_MIN_BW_SCALE                     0x10000000UL
+	#define FUNC_QCFG_RESP_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_QCFG_RESP_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_QCFG_RESP_MIN_BW_SCALE_LAST                 FUNC_QCFG_RESP_MIN_BW_SCALE_BYTES
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_MIN_BW_BW_VALUE_UNIT_INVALID
+	__le32	max_bw;
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_SFT              0
+	#define FUNC_QCFG_RESP_MAX_BW_SCALE                     0x10000000UL
+	#define FUNC_QCFG_RESP_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_QCFG_RESP_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_QCFG_RESP_MAX_BW_SCALE_LAST                 FUNC_QCFG_RESP_MAX_BW_SCALE_BYTES
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_MAX_BW_BW_VALUE_UNIT_INVALID
+	u8	evb_mode;
+	#define FUNC_QCFG_RESP_EVB_MODE_NO_EVB 0x0UL
+	#define FUNC_QCFG_RESP_EVB_MODE_VEB    0x1UL
+	#define FUNC_QCFG_RESP_EVB_MODE_VEPA   0x2UL
+	#define FUNC_QCFG_RESP_EVB_MODE_LAST  FUNC_QCFG_RESP_EVB_MODE_VEPA
+	u8	options;
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SFT          0
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
+	#define FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_LAST          FUNC_QCFG_RESP_OPTIONS_CACHE_LINESIZE_SIZE_128
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_SFT        2
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
+	#define FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_QCFG_RESP_OPTIONS_LINK_ADMIN_STATE_AUTO
+	#define FUNC_QCFG_RESP_OPTIONS_RSVD_MASK                   0xf0UL
+	#define FUNC_QCFG_RESP_OPTIONS_RSVD_SFT                    4
+	__le16	alloc_vfs;
+	__le32	alloc_mcast_filters;
+	__le32	alloc_hw_ring_grps;
+	__le16	alloc_sp_tx_rings;
+	__le16	alloc_stat_ctx;
+	__le16	alloc_msix;
+	__le16	registered_vfs;
+	__le16	l2_doorbell_bar_size_kb;
+	u8	active_endpoints;
+	u8	always_1;
+	__le32	reset_addr_poll;
+	__le16	legacy_l2_db_size_kb;
+	__le16	svif_info;
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_MASK      0x7fffUL
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_SFT       0
+	#define FUNC_QCFG_RESP_SVIF_INFO_SVIF_VALID     0x8000UL
+	u8	mpc_chnls;
+	#define FUNC_QCFG_RESP_MPC_CHNLS_TCE_ENABLED         0x1UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_RCE_ENABLED         0x2UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_TE_CFA_ENABLED      0x4UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_RE_CFA_ENABLED      0x8UL
+	#define FUNC_QCFG_RESP_MPC_CHNLS_PRIMATE_ENABLED     0x10UL
+	u8	db_page_size;
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4KB   0x0UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_8KB   0x1UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_16KB  0x2UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_32KB  0x3UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_64KB  0x4UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_128KB 0x5UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_256KB 0x6UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_512KB 0x7UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_1MB   0x8UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_2MB   0x9UL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB   0xaUL
+	#define FUNC_QCFG_RESP_DB_PAGE_SIZE_LAST FUNC_QCFG_RESP_DB_PAGE_SIZE_4MB
+	__le16	roce_vnic_id;
+	__le32	partition_min_bw;
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_SFT              0
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE                     0x10000000UL
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_LAST                 FUNC_QCFG_RESP_PARTITION_MIN_BW_SCALE_BYTES
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100
+	__le32	partition_max_bw;
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_SFT              0
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE                     0x10000000UL
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_LAST                 FUNC_QCFG_RESP_PARTITION_MAX_BW_SCALE_BYTES
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_QCFG_RESP_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
+	__le16	host_mtu;
+	__le16	flags2;
+	#define FUNC_QCFG_RESP_FLAGS2_SRIOV_DSCP_INSERT_ENABLED     0x1UL
+	__le16	stag_vid;
+	u8	port_kdnet_mode;
+	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_DISABLED 0x0UL
+	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED  0x1UL
+	#define FUNC_QCFG_RESP_PORT_KDNET_MODE_LAST    FUNC_QCFG_RESP_PORT_KDNET_MODE_ENABLED
+	u8	kdnet_pcie_function;
+	__le16	port_kdnet_fid;
+	u8	unused_5;
+	u8	roce_bidi_opt_mode;
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DISABLED      0x1UL
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_DEDICATED     0x2UL
+	#define FUNC_QCFG_RESP_ROCE_BIDI_OPT_MODE_SHARED        0x4UL
+	__le32	num_ktls_tx_key_ctxs;
+	__le32	num_ktls_rx_key_ctxs;
+	u8	lag_id;
+	u8	parif;
+	u8	fw_lag_id;
+	u8	unused_6;
+	__le32	num_quic_tx_key_ctxs;
+	__le32	num_quic_rx_key_ctxs;
+	__le32	roce_max_av_per_vf;
+	__le32	roce_max_cq_per_vf;
+	__le32	roce_max_mrw_per_vf;
+	__le32	roce_max_qp_per_vf;
+	__le32	roce_max_srq_per_vf;
+	__le32	roce_max_gid_per_vf;
+	__le16	xid_partition_cfg;
+	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_TX_CK     0x1UL
+	#define FUNC_QCFG_RESP_XID_PARTITION_CFG_RX_CK     0x2UL
+	__le16	mirror_vnic_id;
+	u8	unused_7[7];
+	u8	valid;
+};
+
+/* hwrm_func_cfg_input (size:1280b/160B) */
+struct hwrm_func_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	__le16	num_msix;
+	__le32	flags;
+	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_DISABLE     0x1UL
+	#define FUNC_CFG_REQ_FLAGS_SRC_MAC_ADDR_CHECK_ENABLE      0x2UL
+	#define FUNC_CFG_REQ_FLAGS_RSVD_MASK                      0x1fcUL
+	#define FUNC_CFG_REQ_FLAGS_RSVD_SFT                       2
+	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_ENABLE        0x200UL
+	#define FUNC_CFG_REQ_FLAGS_STD_TX_RING_MODE_DISABLE       0x400UL
+	#define FUNC_CFG_REQ_FLAGS_VIRT_MAC_PERSIST               0x800UL
+	#define FUNC_CFG_REQ_FLAGS_NO_AUTOCLEAR_STATISTIC         0x1000UL
+	#define FUNC_CFG_REQ_FLAGS_TX_ASSETS_TEST                 0x2000UL
+	#define FUNC_CFG_REQ_FLAGS_RX_ASSETS_TEST                 0x4000UL
+	#define FUNC_CFG_REQ_FLAGS_CMPL_ASSETS_TEST               0x8000UL
+	#define FUNC_CFG_REQ_FLAGS_RSSCOS_CTX_ASSETS_TEST         0x10000UL
+	#define FUNC_CFG_REQ_FLAGS_RING_GRP_ASSETS_TEST           0x20000UL
+	#define FUNC_CFG_REQ_FLAGS_STAT_CTX_ASSETS_TEST           0x40000UL
+	#define FUNC_CFG_REQ_FLAGS_VNIC_ASSETS_TEST               0x80000UL
+	#define FUNC_CFG_REQ_FLAGS_L2_CTX_ASSETS_TEST             0x100000UL
+	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_ENABLE              0x200000UL
+	#define FUNC_CFG_REQ_FLAGS_DYNAMIC_TX_RING_ALLOC          0x400000UL
+	#define FUNC_CFG_REQ_FLAGS_NQ_ASSETS_TEST                 0x800000UL
+	#define FUNC_CFG_REQ_FLAGS_TRUSTED_VF_DISABLE             0x1000000UL
+	#define FUNC_CFG_REQ_FLAGS_PREBOOT_LEGACY_L2_RINGS        0x2000000UL
+	#define FUNC_CFG_REQ_FLAGS_HOT_RESET_IF_EN_DIS            0x4000000UL
+	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_ENABLE           0x8000000UL
+	#define FUNC_CFG_REQ_FLAGS_PPP_PUSH_MODE_DISABLE          0x10000000UL
+	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_ENABLE             0x20000000UL
+	#define FUNC_CFG_REQ_FLAGS_BD_METADATA_DISABLE            0x40000000UL
+	__le32	enables;
+	#define FUNC_CFG_REQ_ENABLES_ADMIN_MTU                0x1UL
+	#define FUNC_CFG_REQ_ENABLES_MRU                      0x2UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS          0x4UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_CMPL_RINGS           0x8UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_TX_RINGS             0x10UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_RX_RINGS             0x20UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_L2_CTXS              0x40UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_VNICS                0x80UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_STAT_CTXS            0x100UL
+	#define FUNC_CFG_REQ_ENABLES_DFLT_MAC_ADDR            0x200UL
+	#define FUNC_CFG_REQ_ENABLES_DFLT_VLAN                0x400UL
+	#define FUNC_CFG_REQ_ENABLES_DFLT_IP_ADDR             0x800UL
+	#define FUNC_CFG_REQ_ENABLES_MIN_BW                   0x1000UL
+	#define FUNC_CFG_REQ_ENABLES_MAX_BW                   0x2000UL
+	#define FUNC_CFG_REQ_ENABLES_ASYNC_EVENT_CR           0x4000UL
+	#define FUNC_CFG_REQ_ENABLES_VLAN_ANTISPOOF_MODE      0x8000UL
+	#define FUNC_CFG_REQ_ENABLES_ALLOWED_VLAN_PRIS        0x10000UL
+	#define FUNC_CFG_REQ_ENABLES_EVB_MODE                 0x20000UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_MCAST_FILTERS        0x40000UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_HW_RING_GRPS         0x80000UL
+	#define FUNC_CFG_REQ_ENABLES_CACHE_LINESIZE           0x100000UL
+	#define FUNC_CFG_REQ_ENABLES_NUM_MSIX                 0x200000UL
+	#define FUNC_CFG_REQ_ENABLES_ADMIN_LINK_STATE         0x400000UL
+	#define FUNC_CFG_REQ_ENABLES_HOT_RESET_IF_SUPPORT     0x800000UL
+	#define FUNC_CFG_REQ_ENABLES_SCHQ_ID                  0x1000000UL
+	#define FUNC_CFG_REQ_ENABLES_MPC_CHNLS                0x2000000UL
+	#define FUNC_CFG_REQ_ENABLES_PARTITION_MIN_BW         0x4000000UL
+	#define FUNC_CFG_REQ_ENABLES_PARTITION_MAX_BW         0x8000000UL
+	#define FUNC_CFG_REQ_ENABLES_TPID                     0x10000000UL
+	#define FUNC_CFG_REQ_ENABLES_HOST_MTU                 0x20000000UL
+	#define FUNC_CFG_REQ_ENABLES_KTLS_TX_KEY_CTXS         0x40000000UL
+	#define FUNC_CFG_REQ_ENABLES_KTLS_RX_KEY_CTXS         0x80000000UL
+	__le16	admin_mtu;
+	__le16	mru;
+	__le16	num_rsscos_ctxs;
+	__le16	num_cmpl_rings;
+	__le16	num_tx_rings;
+	__le16	num_rx_rings;
+	__le16	num_l2_ctxs;
+	__le16	num_vnics;
+	__le16	num_stat_ctxs;
+	__le16	num_hw_ring_grps;
+	u8	dflt_mac_addr[6];
+	__le16	dflt_vlan;
+	__be32	dflt_ip_addr[4];
+	__le32	min_bw;
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_SFT              0
+	#define FUNC_CFG_REQ_MIN_BW_SCALE                     0x10000000UL
+	#define FUNC_CFG_REQ_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_CFG_REQ_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_CFG_REQ_MIN_BW_SCALE_LAST                 FUNC_CFG_REQ_MIN_BW_SCALE_BYTES
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_MIN_BW_BW_VALUE_UNIT_INVALID
+	__le32	max_bw;
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_SFT              0
+	#define FUNC_CFG_REQ_MAX_BW_SCALE                     0x10000000UL
+	#define FUNC_CFG_REQ_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_CFG_REQ_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_CFG_REQ_MAX_BW_SCALE_LAST                 FUNC_CFG_REQ_MAX_BW_SCALE_BYTES
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_MAX_BW_BW_VALUE_UNIT_INVALID
+	__le16	async_event_cr;
+	u8	vlan_antispoof_mode;
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_NOCHECK                 0x0UL
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_VALIDATE_VLAN           0x1UL
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_IF_VLANDNE       0x2UL
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN 0x3UL
+	#define FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_LAST                   FUNC_CFG_REQ_VLAN_ANTISPOOF_MODE_INSERT_OR_OVERRIDE_VLAN
+	u8	allowed_vlan_pris;
+	u8	evb_mode;
+	#define FUNC_CFG_REQ_EVB_MODE_NO_EVB 0x0UL
+	#define FUNC_CFG_REQ_EVB_MODE_VEB    0x1UL
+	#define FUNC_CFG_REQ_EVB_MODE_VEPA   0x2UL
+	#define FUNC_CFG_REQ_EVB_MODE_LAST  FUNC_CFG_REQ_EVB_MODE_VEPA
+	u8	options;
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_MASK         0x3UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SFT          0
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_64        0x0UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128       0x1UL
+	#define FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_LAST          FUNC_CFG_REQ_OPTIONS_CACHE_LINESIZE_SIZE_128
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_MASK       0xcUL
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_SFT        2
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_DOWN  (0x0UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_FORCED_UP    (0x1UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO         (0x2UL << 2)
+	#define FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_LAST        FUNC_CFG_REQ_OPTIONS_LINK_ADMIN_STATE_AUTO
+	#define FUNC_CFG_REQ_OPTIONS_RSVD_MASK                   0xf0UL
+	#define FUNC_CFG_REQ_OPTIONS_RSVD_SFT                    4
+	__le16	num_mcast_filters;
+	__le16	schq_id;
+	__le16	mpc_chnls;
+	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_ENABLE          0x1UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TCE_DISABLE         0x2UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_ENABLE          0x4UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RCE_DISABLE         0x8UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_ENABLE       0x10UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_TE_CFA_DISABLE      0x20UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_ENABLE       0x40UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_RE_CFA_DISABLE      0x80UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_ENABLE      0x100UL
+	#define FUNC_CFG_REQ_MPC_CHNLS_PRIMATE_DISABLE     0x200UL
+	__le32	partition_min_bw;
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_SFT              0
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE                     0x10000000UL
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_LAST                 FUNC_CFG_REQ_PARTITION_MIN_BW_SCALE_BYTES
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MIN_BW_BW_VALUE_UNIT_PERCENT1_100
+	__le32	partition_max_bw;
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_SFT              0
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE                     0x10000000UL
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_LAST                 FUNC_CFG_REQ_PARTITION_MAX_BW_SCALE_BYTES
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_LAST         FUNC_CFG_REQ_PARTITION_MAX_BW_BW_VALUE_UNIT_PERCENT1_100
+	__be16	tpid;
+	__le16	host_mtu;
+	__le32	flags2;
+	#define FUNC_CFG_REQ_FLAGS2_KTLS_KEY_CTX_ASSETS_TEST     0x1UL
+	#define FUNC_CFG_REQ_FLAGS2_QUIC_KEY_CTX_ASSETS_TEST     0x2UL
+	__le32	enables2;
+	#define FUNC_CFG_REQ_ENABLES2_KDNET                    0x1UL
+	#define FUNC_CFG_REQ_ENABLES2_DB_PAGE_SIZE             0x2UL
+	#define FUNC_CFG_REQ_ENABLES2_QUIC_TX_KEY_CTXS         0x4UL
+	#define FUNC_CFG_REQ_ENABLES2_QUIC_RX_KEY_CTXS         0x8UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_AV_PER_VF       0x10UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_CQ_PER_VF       0x20UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_MRW_PER_VF      0x40UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_QP_PER_VF       0x80UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_SRQ_PER_VF      0x100UL
+	#define FUNC_CFG_REQ_ENABLES2_ROCE_MAX_GID_PER_VF      0x200UL
+	#define FUNC_CFG_REQ_ENABLES2_XID_PARTITION_CFG        0x400UL
+	#define FUNC_CFG_REQ_ENABLES2_PHYSICAL_SLOT_NUMBER     0x800UL
+	u8	port_kdnet_mode;
+	#define FUNC_CFG_REQ_PORT_KDNET_MODE_DISABLED 0x0UL
+	#define FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED  0x1UL
+	#define FUNC_CFG_REQ_PORT_KDNET_MODE_LAST    FUNC_CFG_REQ_PORT_KDNET_MODE_ENABLED
+	u8	db_page_size;
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_4KB   0x0UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_8KB   0x1UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_16KB  0x2UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_32KB  0x3UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_64KB  0x4UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_128KB 0x5UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_256KB 0x6UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_512KB 0x7UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_1MB   0x8UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_2MB   0x9UL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_4MB   0xaUL
+	#define FUNC_CFG_REQ_DB_PAGE_SIZE_LAST FUNC_CFG_REQ_DB_PAGE_SIZE_4MB
+	__le16	physical_slot_number;
+	__le32	num_ktls_tx_key_ctxs;
+	__le32	num_ktls_rx_key_ctxs;
+	__le32	num_quic_tx_key_ctxs;
+	__le32	num_quic_rx_key_ctxs;
+	__le32	roce_max_av_per_vf;
+	__le32	roce_max_cq_per_vf;
+	__le32	roce_max_mrw_per_vf;
+	__le32	roce_max_qp_per_vf;
+	__le32	roce_max_srq_per_vf;
+	__le32	roce_max_gid_per_vf;
+	__le16	xid_partition_cfg;
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_TX_CK     0x1UL
+	#define FUNC_CFG_REQ_XID_PARTITION_CFG_RX_CK     0x2UL
+	__le16	unused_2;
+};
+
+/* hwrm_func_cfg_output (size:128b/16B) */
+struct hwrm_func_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_cfg_cmd_err (size:64b/8B) */
+struct hwrm_func_cfg_cmd_err {
+	u8	code;
+	#define FUNC_CFG_CMD_ERR_CODE_UNKNOWN                      0x0UL
+	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_RANGE       0x1UL
+	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_MORE_THAN_MAX  0x2UL
+	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_MIN_BW_UNSUPPORTED 0x3UL
+	#define FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT         0x4UL
+	#define FUNC_CFG_CMD_ERR_CODE_LAST                        FUNC_CFG_CMD_ERR_CODE_PARTITION_BW_PERCENT
+	u8	unused_0[7];
+};
+
+/* hwrm_func_qstats_input (size:192b/24B) */
+struct hwrm_func_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	flags;
+	#define FUNC_QSTATS_REQ_FLAGS_ROCE_ONLY        0x1UL
+	#define FUNC_QSTATS_REQ_FLAGS_COUNTER_MASK     0x2UL
+	#define FUNC_QSTATS_REQ_FLAGS_L2_ONLY          0x4UL
+	u8	unused_0[5];
+};
+
+/* hwrm_func_qstats_output (size:1408b/176B) */
+struct hwrm_func_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_drop_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_drop_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	rx_agg_pkts;
+	__le64	rx_agg_bytes;
+	__le64	rx_agg_events;
+	__le64	rx_agg_aborts;
+	u8	clear_seq;
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_func_qstats_ext_input (size:256b/32B) */
+struct hwrm_func_qstats_ext_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	flags;
+	#define FUNC_QSTATS_EXT_REQ_FLAGS_ROCE_ONLY        0x1UL
+	#define FUNC_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK     0x2UL
+	u8	unused_0[1];
+	__le32	enables;
+	#define FUNC_QSTATS_EXT_REQ_ENABLES_SCHQ_ID     0x1UL
+	__le16	schq_id;
+	__le16	traffic_class;
+	u8	unused_1[4];
+};
+
+/* hwrm_func_qstats_ext_output (size:1536b/192B) */
+struct hwrm_func_qstats_ext_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_tpa_eligible_pkt;
+	__le64	rx_tpa_eligible_bytes;
+	__le64	rx_tpa_pkt;
+	__le64	rx_tpa_bytes;
+	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_clr_stats_input (size:192b/24B) */
+struct hwrm_func_clr_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_clr_stats_output (size:128b/16B) */
+struct hwrm_func_clr_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_vf_resc_free_input (size:192b/24B) */
+struct hwrm_func_vf_resc_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	vf_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_vf_resc_free_output (size:128b/16B) */
+struct hwrm_func_vf_resc_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_drv_rgtr_input (size:896b/112B) */
+struct hwrm_func_drv_rgtr_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_ALL_MODE                     0x1UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_FWD_NONE_MODE                    0x2UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE                   0x4UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_FLOW_HANDLE_64BIT_MODE           0x8UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT                0x10UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT           0x20UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_MASTER_SUPPORT                   0x40UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_FAST_RESET_SUPPORT               0x80UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_RSS_STRICT_HASH_TYPE_SUPPORT     0x100UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_NPAR_1_2_SUPPORT                 0x200UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_ASYM_QUEUE_CFG_SUPPORT           0x400UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_INGRESS_NIC_FLOW_MODE         0x800UL
+	#define FUNC_DRV_RGTR_REQ_FLAGS_TF_EGRESS_NIC_FLOW_MODE          0x1000UL
+	__le32	enables;
+	#define FUNC_DRV_RGTR_REQ_ENABLES_OS_TYPE             0x1UL
+	#define FUNC_DRV_RGTR_REQ_ENABLES_VER                 0x2UL
+	#define FUNC_DRV_RGTR_REQ_ENABLES_TIMESTAMP           0x4UL
+	#define FUNC_DRV_RGTR_REQ_ENABLES_VF_REQ_FWD          0x8UL
+	#define FUNC_DRV_RGTR_REQ_ENABLES_ASYNC_EVENT_FWD     0x10UL
+	__le16	os_type;
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_UNKNOWN   0x0UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_OTHER     0x1UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_MSDOS     0xeUL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WINDOWS   0x12UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_SOLARIS   0x1dUL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX     0x24UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_FREEBSD   0x2aUL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_ESXI      0x68UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN864    0x73UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_WIN2012R2 0x74UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI      0x8000UL
+	#define FUNC_DRV_RGTR_REQ_OS_TYPE_LAST     FUNC_DRV_RGTR_REQ_OS_TYPE_UEFI
+	u8	ver_maj_8b;
+	u8	ver_min_8b;
+	u8	ver_upd_8b;
+	u8	unused_0[3];
+	__le32	timestamp;
+	u8	unused_1[4];
+	__le32	vf_req_fwd[8];
+	__le32	async_event_fwd[8];
+	__le16	ver_maj;
+	__le16	ver_min;
+	__le16	ver_upd;
+	__le16	ver_patch;
+};
+
+/* hwrm_func_drv_rgtr_output (size:128b/16B) */
+struct hwrm_func_drv_rgtr_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define FUNC_DRV_RGTR_RESP_FLAGS_IF_CHANGE_SUPPORTED     0x1UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_func_drv_unrgtr_input (size:192b/24B) */
+struct hwrm_func_drv_unrgtr_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_DRV_UNRGTR_REQ_FLAGS_PREPARE_FOR_SHUTDOWN     0x1UL
+	u8	unused_0[4];
+};
+
+/* hwrm_func_drv_unrgtr_output (size:128b/16B) */
+struct hwrm_func_drv_unrgtr_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_buf_rgtr_input (size:1024b/128B) */
+struct hwrm_func_buf_rgtr_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_BUF_RGTR_REQ_ENABLES_VF_ID            0x1UL
+	#define FUNC_BUF_RGTR_REQ_ENABLES_ERR_BUF_ADDR     0x2UL
+	__le16	vf_id;
+	__le16	req_buf_num_pages;
+	__le16	req_buf_page_size;
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_16B 0x4UL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4K  0xcUL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_8K  0xdUL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_64K 0x10UL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_2M  0x15UL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_4M  0x16UL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G  0x1eUL
+	#define FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_LAST FUNC_BUF_RGTR_REQ_REQ_BUF_PAGE_SIZE_1G
+	__le16	req_buf_len;
+	__le16	resp_buf_len;
+	u8	unused_0[2];
+	__le64	req_buf_page_addr0;
+	__le64	req_buf_page_addr1;
+	__le64	req_buf_page_addr2;
+	__le64	req_buf_page_addr3;
+	__le64	req_buf_page_addr4;
+	__le64	req_buf_page_addr5;
+	__le64	req_buf_page_addr6;
+	__le64	req_buf_page_addr7;
+	__le64	req_buf_page_addr8;
+	__le64	req_buf_page_addr9;
+	__le64	error_buf_addr;
+	__le64	resp_buf_addr;
+};
+
+/* hwrm_func_buf_rgtr_output (size:128b/16B) */
+struct hwrm_func_buf_rgtr_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_drv_qver_input (size:192b/24B) */
+struct hwrm_func_drv_qver_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	reserved;
+	__le16	fid;
+	u8	driver_type;
+	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_L2   0x0UL
+	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_ROCE 0x1UL
+	#define FUNC_DRV_QVER_REQ_DRIVER_TYPE_LAST FUNC_DRV_QVER_REQ_DRIVER_TYPE_ROCE
+	u8	unused_0;
+};
+
+/* hwrm_func_drv_qver_output (size:256b/32B) */
+struct hwrm_func_drv_qver_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	os_type;
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_UNKNOWN   0x0UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_OTHER     0x1UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_MSDOS     0xeUL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_WINDOWS   0x12UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_SOLARIS   0x1dUL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_LINUX     0x24UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_FREEBSD   0x2aUL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_ESXI      0x68UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_WIN864    0x73UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_WIN2012R2 0x74UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_UEFI      0x8000UL
+	#define FUNC_DRV_QVER_RESP_OS_TYPE_LAST     FUNC_DRV_QVER_RESP_OS_TYPE_UEFI
+	u8	ver_maj_8b;
+	u8	ver_min_8b;
+	u8	ver_upd_8b;
+	u8	unused_0[3];
+	__le16	ver_maj;
+	__le16	ver_min;
+	__le16	ver_upd;
+	__le16	ver_patch;
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* hwrm_func_resource_qcaps_input (size:192b/24B) */
+struct hwrm_func_resource_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_func_resource_qcaps_output (size:704b/88B) */
+struct hwrm_func_resource_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	max_vfs;
+	__le16	max_msix;
+	__le16	vf_reservation_strategy;
+	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MAXIMAL        0x0UL
+	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL        0x1UL
+	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL_STATIC 0x2UL
+	#define FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_LAST          FUNC_RESOURCE_QCAPS_RESP_VF_RESERVATION_STRATEGY_MINIMAL_STATIC
+	__le16	min_rsscos_ctx;
+	__le16	max_rsscos_ctx;
+	__le16	min_cmpl_rings;
+	__le16	max_cmpl_rings;
+	__le16	min_tx_rings;
+	__le16	max_tx_rings;
+	__le16	min_rx_rings;
+	__le16	max_rx_rings;
+	__le16	min_l2_ctxs;
+	__le16	max_l2_ctxs;
+	__le16	min_vnics;
+	__le16	max_vnics;
+	__le16	min_stat_ctx;
+	__le16	max_stat_ctx;
+	__le16	min_hw_ring_grps;
+	__le16	max_hw_ring_grps;
+	__le16	max_tx_scheduler_inputs;
+	__le16	flags;
+	#define FUNC_RESOURCE_QCAPS_RESP_FLAGS_MIN_GUARANTEED     0x1UL
+	__le16	min_msix;
+	__le32	min_ktls_tx_key_ctxs;
+	__le32	max_ktls_tx_key_ctxs;
+	__le32	min_ktls_rx_key_ctxs;
+	__le32	max_ktls_rx_key_ctxs;
+	__le32	min_quic_tx_key_ctxs;
+	__le32	max_quic_tx_key_ctxs;
+	__le32	min_quic_rx_key_ctxs;
+	__le32	max_quic_rx_key_ctxs;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_func_vf_resource_cfg_input (size:704b/88B) */
+struct hwrm_func_vf_resource_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	vf_id;
+	__le16	max_msix;
+	__le16	min_rsscos_ctx;
+	__le16	max_rsscos_ctx;
+	__le16	min_cmpl_rings;
+	__le16	max_cmpl_rings;
+	__le16	min_tx_rings;
+	__le16	max_tx_rings;
+	__le16	min_rx_rings;
+	__le16	max_rx_rings;
+	__le16	min_l2_ctxs;
+	__le16	max_l2_ctxs;
+	__le16	min_vnics;
+	__le16	max_vnics;
+	__le16	min_stat_ctx;
+	__le16	max_stat_ctx;
+	__le16	min_hw_ring_grps;
+	__le16	max_hw_ring_grps;
+	__le16	flags;
+	#define FUNC_VF_RESOURCE_CFG_REQ_FLAGS_MIN_GUARANTEED     0x1UL
+	__le16	min_msix;
+	__le32	min_ktls_tx_key_ctxs;
+	__le32	max_ktls_tx_key_ctxs;
+	__le32	min_ktls_rx_key_ctxs;
+	__le32	max_ktls_rx_key_ctxs;
+	__le32	min_quic_tx_key_ctxs;
+	__le32	max_quic_tx_key_ctxs;
+	__le32	min_quic_rx_key_ctxs;
+	__le32	max_quic_rx_key_ctxs;
+};
+
+/* hwrm_func_vf_resource_cfg_output (size:384b/48B) */
+struct hwrm_func_vf_resource_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	reserved_rsscos_ctx;
+	__le16	reserved_cmpl_rings;
+	__le16	reserved_tx_rings;
+	__le16	reserved_rx_rings;
+	__le16	reserved_l2_ctxs;
+	__le16	reserved_vnics;
+	__le16	reserved_stat_ctx;
+	__le16	reserved_hw_ring_grps;
+	__le32	reserved_ktls_tx_key_ctxs;
+	__le32	reserved_ktls_rx_key_ctxs;
+	__le32	reserved_quic_tx_key_ctxs;
+	__le32	reserved_quic_rx_key_ctxs;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_backing_store_qcaps_input (size:128b/16B) */
+struct hwrm_func_backing_store_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_func_backing_store_qcaps_output (size:832b/104B) */
+struct hwrm_func_backing_store_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	qp_max_entries;
+	__le16	qp_min_qp1_entries;
+	__le16	qp_max_l2_entries;
+	__le16	qp_entry_size;
+	__le16	srq_max_l2_entries;
+	__le32	srq_max_entries;
+	__le16	srq_entry_size;
+	__le16	cq_max_l2_entries;
+	__le32	cq_max_entries;
+	__le16	cq_entry_size;
+	__le16	vnic_max_vnic_entries;
+	__le16	vnic_max_ring_table_entries;
+	__le16	vnic_entry_size;
+	__le32	stat_max_entries;
+	__le16	stat_entry_size;
+	__le16	tqm_entry_size;
+	__le32	tqm_min_entries_per_ring;
+	__le32	tqm_max_entries_per_ring;
+	__le32	mrav_max_entries;
+	__le16	mrav_entry_size;
+	__le16	tim_entry_size;
+	__le32	tim_max_entries;
+	__le16	mrav_num_entries_units;
+	u8	tqm_entries_multiple;
+	u8	ctx_kind_initializer;
+	__le16	ctx_init_mask;
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_QP       0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_SRQ      0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_CQ       0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_VNIC     0x8UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_STAT     0x10UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_MRAV     0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_TKC      0x40UL
+	#define FUNC_BACKING_STORE_QCAPS_RESP_CTX_INIT_MASK_RKC      0x80UL
+	u8	qp_init_offset;
+	u8	srq_init_offset;
+	u8	cq_init_offset;
+	u8	vnic_init_offset;
+	u8	tqm_fp_rings_count;
+	u8	stat_init_offset;
+	u8	mrav_init_offset;
+	u8	tqm_fp_rings_count_ext;
+	u8	tkc_init_offset;
+	u8	rkc_init_offset;
+	__le16	tkc_entry_size;
+	__le16	rkc_entry_size;
+	__le32	tkc_max_entries;
+	__le32	rkc_max_entries;
+	__le16	fast_qpmd_qp_num_entries;
+	u8	rsvd1[5];
+	u8	valid;
+};
+
+/* tqm_fp_ring_cfg (size:128b/16B) */
+struct tqm_fp_ring_cfg {
+	u8	tqm_ring_pg_size_tqm_ring_lvl;
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_MASK      0xfUL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_SFT       0
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_0       0x0UL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_1       0x1UL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_2       0x2UL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LAST       TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_LVL_LVL_2
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_MASK  0xf0UL
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_SFT   4
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_LAST   TQM_FP_RING_CFG_TQM_RING_CFG_TQM_RING_PG_SIZE_PG_1G
+	u8	unused[3];
+	__le32	tqm_ring_num_entries;
+	__le64	tqm_ring_page_dir;
+};
+
+/* hwrm_func_backing_store_cfg_input (size:2688b/336B) */
+struct hwrm_func_backing_store_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_PREBOOT_MODE               0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_FLAGS_MRAV_RESERVATION_SPLIT     0x2UL
+	__le32	enables;
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP               0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_SRQ              0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_CQ               0x4UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_VNIC             0x8UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_STAT             0x10UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_SP           0x20UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING0        0x40UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING1        0x80UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING2        0x100UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING3        0x200UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING4        0x400UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING5        0x800UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING6        0x1000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING7        0x2000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_MRAV             0x4000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TIM              0x8000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING8        0x10000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING9        0x20000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TQM_RING10       0x40000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_TKC              0x80000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_RKC              0x100000UL
+	#define FUNC_BACKING_STORE_CFG_REQ_ENABLES_QP_FAST_QPMD     0x200000UL
+	u8	qpc_pg_size_qpc_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_QPC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_QPC_PG_SIZE_PG_1G
+	u8	srq_pg_size_srq_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_SRQ_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_SRQ_PG_SIZE_PG_1G
+	u8	cq_pg_size_cq_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_CQ_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_CQ_PG_SIZE_PG_1G
+	u8	vnic_pg_size_vnic_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_VNIC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_VNIC_PG_SIZE_PG_1G
+	u8	stat_pg_size_stat_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_STAT_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_STAT_PG_SIZE_PG_1G
+	u8	tqm_sp_pg_size_tqm_sp_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_SP_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_SP_PG_SIZE_PG_1G
+	u8	tqm_ring0_pg_size_tqm_ring0_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING0_PG_SIZE_PG_1G
+	u8	tqm_ring1_pg_size_tqm_ring1_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING1_PG_SIZE_PG_1G
+	u8	tqm_ring2_pg_size_tqm_ring2_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING2_PG_SIZE_PG_1G
+	u8	tqm_ring3_pg_size_tqm_ring3_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING3_PG_SIZE_PG_1G
+	u8	tqm_ring4_pg_size_tqm_ring4_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING4_PG_SIZE_PG_1G
+	u8	tqm_ring5_pg_size_tqm_ring5_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING5_PG_SIZE_PG_1G
+	u8	tqm_ring6_pg_size_tqm_ring6_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING6_PG_SIZE_PG_1G
+	u8	tqm_ring7_pg_size_tqm_ring7_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TQM_RING7_PG_SIZE_PG_1G
+	u8	mrav_pg_size_mrav_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_MRAV_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_MRAV_PG_SIZE_PG_1G
+	u8	tim_pg_size_tim_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TIM_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TIM_PG_SIZE_PG_1G
+	__le64	qpc_page_dir;
+	__le64	srq_page_dir;
+	__le64	cq_page_dir;
+	__le64	vnic_page_dir;
+	__le64	stat_page_dir;
+	__le64	tqm_sp_page_dir;
+	__le64	tqm_ring0_page_dir;
+	__le64	tqm_ring1_page_dir;
+	__le64	tqm_ring2_page_dir;
+	__le64	tqm_ring3_page_dir;
+	__le64	tqm_ring4_page_dir;
+	__le64	tqm_ring5_page_dir;
+	__le64	tqm_ring6_page_dir;
+	__le64	tqm_ring7_page_dir;
+	__le64	mrav_page_dir;
+	__le64	tim_page_dir;
+	__le32	qp_num_entries;
+	__le32	srq_num_entries;
+	__le32	cq_num_entries;
+	__le32	stat_num_entries;
+	__le32	tqm_sp_num_entries;
+	__le32	tqm_ring0_num_entries;
+	__le32	tqm_ring1_num_entries;
+	__le32	tqm_ring2_num_entries;
+	__le32	tqm_ring3_num_entries;
+	__le32	tqm_ring4_num_entries;
+	__le32	tqm_ring5_num_entries;
+	__le32	tqm_ring6_num_entries;
+	__le32	tqm_ring7_num_entries;
+	__le32	mrav_num_entries;
+	__le32	tim_num_entries;
+	__le16	qp_num_qp1_entries;
+	__le16	qp_num_l2_entries;
+	__le16	qp_entry_size;
+	__le16	srq_num_l2_entries;
+	__le16	srq_entry_size;
+	__le16	cq_num_l2_entries;
+	__le16	cq_entry_size;
+	__le16	vnic_num_vnic_entries;
+	__le16	vnic_num_ring_table_entries;
+	__le16	vnic_entry_size;
+	__le16	stat_entry_size;
+	__le16	tqm_entry_size;
+	__le16	mrav_entry_size;
+	__le16	tim_entry_size;
+	u8	tqm_ring8_pg_size_tqm_ring_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING8_TQM_RING_PG_SIZE_PG_1G
+	u8	ring8_unused[3];
+	__le32	tqm_ring8_num_entries;
+	__le64	tqm_ring8_page_dir;
+	u8	tqm_ring9_pg_size_tqm_ring_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING9_TQM_RING_PG_SIZE_PG_1G
+	u8	ring9_unused[3];
+	__le32	tqm_ring9_num_entries;
+	__le64	tqm_ring9_page_dir;
+	u8	tqm_ring10_pg_size_tqm_ring_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RING10_TQM_RING_PG_SIZE_PG_1G
+	u8	ring10_unused[3];
+	__le32	tqm_ring10_num_entries;
+	__le64	tqm_ring10_page_dir;
+	__le32	tkc_num_entries;
+	__le32	rkc_num_entries;
+	__le64	tkc_page_dir;
+	__le64	rkc_page_dir;
+	__le16	tkc_entry_size;
+	__le16	rkc_entry_size;
+	u8	tkc_pg_size_tkc_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_TKC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_TKC_PG_SIZE_PG_1G
+	u8	rkc_pg_size_rkc_lvl;
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_MASK      0xfUL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_SFT       0
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_0       0x0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_1       0x1UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2       0x2UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LAST       FUNC_BACKING_STORE_CFG_REQ_RKC_LVL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_LAST   FUNC_BACKING_STORE_CFG_REQ_RKC_PG_SIZE_PG_1G
+	__le16	qp_num_fast_qpmd_entries;
+};
+
+/* hwrm_func_backing_store_cfg_output (size:128b/16B) */
+struct hwrm_func_backing_store_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_error_recovery_qcfg_input (size:192b/24B) */
+struct hwrm_error_recovery_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	unused_0[8];
+};
+
+/* hwrm_error_recovery_qcfg_output (size:1664b/208B) */
+struct hwrm_error_recovery_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_HOST       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU     0x2UL
+	__le32	driver_polling_freq;
+	__le32	master_func_wait_period;
+	__le32	normal_func_wait_period;
+	__le32	master_func_wait_period_after_reset;
+	__le32	max_bailout_time_after_reset;
+	__le32	fw_health_status_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEALTH_STATUS_REG_ADDR_SFT           2
+	__le32	fw_heartbeat_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_HEARTBEAT_REG_ADDR_SFT           2
+	__le32	fw_reset_cnt_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_FW_RESET_CNT_REG_ADDR_SFT           2
+	__le32	reset_inprogress_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_INPROGRESS_REG_ADDR_SFT           2
+	__le32	reset_inprogress_reg_mask;
+	u8	unused_0[3];
+	u8	reg_array_cnt;
+	__le32	reset_reg[16];
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_RESET_REG_ADDR_SFT           2
+	__le32	reset_reg_val[16];
+	u8	delay_after_reset[16];
+	__le32	err_recovery_cnt_reg;
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_MASK    0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_SFT     0
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_GRC       0x1UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR0      0x2UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1      0x3UL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_LAST     ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SPACE_BAR1
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_MASK          0xfffffffcUL
+	#define ERROR_RECOVERY_QCFG_RESP_ERR_RECOVERY_CNT_REG_ADDR_SFT           2
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_func_echo_response_input (size:192b/24B) */
+struct hwrm_func_echo_response_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	event_data1;
+	__le32	event_data2;
+};
+
+/* hwrm_func_echo_response_output (size:128b/16B) */
+struct hwrm_func_echo_response_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_pin_qcfg_input (size:192b/24B) */
+struct hwrm_func_ptp_pin_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	unused_0[8];
+};
+
+/* hwrm_func_ptp_pin_qcfg_output (size:128b/16B) */
+struct hwrm_func_ptp_pin_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_pins;
+	u8	state;
+	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN0_ENABLED     0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN1_ENABLED     0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN2_ENABLED     0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_STATE_PIN3_ENABLED     0x8UL
+	u8	pin0_usage;
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_NONE     0x0UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_IN   0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_PPS_OUT  0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_IN  0x3UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT 0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_LAST    FUNC_PTP_PIN_QCFG_RESP_PIN0_USAGE_SYNC_OUT
+	u8	pin1_usage;
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_NONE     0x0UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_IN   0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_PPS_OUT  0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_IN  0x3UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT 0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_LAST    FUNC_PTP_PIN_QCFG_RESP_PIN1_USAGE_SYNC_OUT
+	u8	pin2_usage;
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_NONE                      0x0UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_IN                    0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_PPS_OUT                   0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_IN                   0x3UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNC_OUT                  0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_LAST                     FUNC_PTP_PIN_QCFG_RESP_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT
+	u8	pin3_usage;
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_NONE                      0x0UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_IN                    0x1UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_PPS_OUT                   0x2UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_IN                   0x3UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNC_OUT                  0x4UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
+	#define FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_LAST                     FUNC_PTP_PIN_QCFG_RESP_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_func_ptp_pin_cfg_input (size:256b/32B) */
+struct hwrm_func_ptp_pin_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_STATE     0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN0_USAGE     0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_STATE     0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN1_USAGE     0x8UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_STATE     0x10UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN2_USAGE     0x20UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_STATE     0x40UL
+	#define FUNC_PTP_PIN_CFG_REQ_ENABLES_PIN3_USAGE     0x80UL
+	u8	pin0_state;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_DISABLED 0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED  0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN0_STATE_ENABLED
+	u8	pin0_usage;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_NONE     0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_IN   0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_PPS_OUT  0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_IN  0x3UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT 0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN0_USAGE_SYNC_OUT
+	u8	pin1_state;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_DISABLED 0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED  0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN1_STATE_ENABLED
+	u8	pin1_usage;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_NONE     0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_IN   0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_PPS_OUT  0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_IN  0x3UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT 0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN1_USAGE_SYNC_OUT
+	u8	pin2_state;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_DISABLED 0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED  0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN2_STATE_ENABLED
+	u8	pin2_usage;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_NONE                      0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_IN                    0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_PPS_OUT                   0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_IN                   0x3UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNC_OUT                  0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_LAST                     FUNC_PTP_PIN_CFG_REQ_PIN2_USAGE_SYNCE_SECONDARY_CLOCK_OUT
+	u8	pin3_state;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_DISABLED 0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED  0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_LAST    FUNC_PTP_PIN_CFG_REQ_PIN3_STATE_ENABLED
+	u8	pin3_usage;
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_NONE                      0x0UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_IN                    0x1UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_PPS_OUT                   0x2UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_IN                   0x3UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNC_OUT                  0x4UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_PRIMARY_CLOCK_OUT   0x5UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT 0x6UL
+	#define FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_LAST                     FUNC_PTP_PIN_CFG_REQ_PIN3_USAGE_SYNCE_SECONDARY_CLOCK_OUT
+	u8	unused_0[4];
+};
+
+/* hwrm_func_ptp_pin_cfg_output (size:128b/16B) */
+struct hwrm_func_ptp_pin_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_cfg_input (size:384b/48B) */
+struct hwrm_func_ptp_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	enables;
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_PPS_EVENT               0x1UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_SOURCE     0x2UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_DLL_PHASE      0x4UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PERIOD     0x8UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_UP         0x10UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_FREQ_ADJ_EXT_PHASE      0x20UL
+	#define FUNC_PTP_CFG_REQ_ENABLES_PTP_SET_TIME                0x40UL
+	u8	ptp_pps_event;
+	#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_INTERNAL     0x1UL
+	#define FUNC_PTP_CFG_REQ_PTP_PPS_EVENT_EXTERNAL     0x2UL
+	u8	ptp_freq_adj_dll_source;
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_NONE    0x0UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_0  0x1UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_1  0x2UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_2  0x3UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_TSIO_3  0x4UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_0  0x5UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_1  0x6UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_2  0x7UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_PORT_3  0x8UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID 0xffUL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_LAST   FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_SOURCE_INVALID
+	u8	ptp_freq_adj_dll_phase;
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_NONE 0x0UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_4K   0x1UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_8K   0x2UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_10M  0x3UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M  0x4UL
+	#define FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_LAST FUNC_PTP_CFG_REQ_PTP_FREQ_ADJ_DLL_PHASE_25M
+	u8	unused_0[3];
+	__le32	ptp_freq_adj_ext_period;
+	__le32	ptp_freq_adj_ext_up;
+	__le32	ptp_freq_adj_ext_phase_lower;
+	__le32	ptp_freq_adj_ext_phase_upper;
+	__le64	ptp_set_time;
+};
+
+/* hwrm_func_ptp_cfg_output (size:128b/16B) */
+struct hwrm_func_ptp_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_ts_query_input (size:192b/24B) */
+struct hwrm_func_ptp_ts_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_PTP_TS_QUERY_REQ_FLAGS_PPS_TIME     0x1UL
+	#define FUNC_PTP_TS_QUERY_REQ_FLAGS_PTM_TIME     0x2UL
+	u8	unused_0[4];
+};
+
+/* hwrm_func_ptp_ts_query_output (size:320b/40B) */
+struct hwrm_func_ptp_ts_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	pps_event_ts;
+	__le64	ptm_local_ts;
+	__le64	ptm_system_ts;
+	__le32	ptm_link_delay;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_ext_cfg_input (size:256b/32B) */
+struct hwrm_func_ptp_ext_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	enables;
+	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_MASTER_FID     0x1UL
+	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_FID        0x2UL
+	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_PHC_SEC_MODE       0x4UL
+	#define FUNC_PTP_EXT_CFG_REQ_ENABLES_FAILOVER_TIMER     0x8UL
+	__le16	phc_master_fid;
+	__le16	phc_sec_fid;
+	u8	phc_sec_mode;
+	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_SWITCH  0x0UL
+	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_ALL     0x1UL
+	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY 0x2UL
+	#define FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_LAST   FUNC_PTP_EXT_CFG_REQ_PHC_SEC_MODE_PF_ONLY
+	u8	unused_0;
+	__le32	failover_timer;
+	u8	unused_1[4];
+};
+
+/* hwrm_func_ptp_ext_cfg_output (size:128b/16B) */
+struct hwrm_func_ptp_ext_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_ptp_ext_qcfg_input (size:192b/24B) */
+struct hwrm_func_ptp_ext_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	unused_0[8];
+};
+
+/* hwrm_func_ptp_ext_qcfg_output (size:256b/32B) */
+struct hwrm_func_ptp_ext_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	phc_master_fid;
+	__le16	phc_sec_fid;
+	__le16	phc_active_fid0;
+	__le16	phc_active_fid1;
+	__le32	last_failover_event;
+	__le16	from_fid;
+	__le16	to_fid;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_func_backing_store_cfg_v2_input (size:512b/64B) */
+struct hwrm_func_backing_store_cfg_v2_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	type;
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_CFG_V2_REQ_TYPE_INVALID
+	__le16	instance;
+	__le32	flags;
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_PREBOOT_MODE        0x1UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_CFG_ALL_DONE     0x2UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_FLAGS_BS_EXTEND           0x4UL
+	__le64	page_dir;
+	__le32	num_entries;
+	__le16	entry_size;
+	u8	page_size_pbl_level;
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_MASK  0xfUL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_SFT   0
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_0   0x0UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_1   0x1UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2   0x2UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LAST   FUNC_BACKING_STORE_CFG_V2_REQ_PBL_LEVEL_LVL_2
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_LAST   FUNC_BACKING_STORE_CFG_V2_REQ_PAGE_SIZE_PG_1G
+	u8	subtype_valid_cnt;
+	__le32	split_entry_0;
+	__le32	split_entry_1;
+	__le32	split_entry_2;
+	__le32	split_entry_3;
+	__le32	enables;
+	#define FUNC_BACKING_STORE_CFG_V2_REQ_ENABLES_NEXT_BS_OFFSET     0x1UL
+	__le32	next_bs_offset;
+};
+
+/* hwrm_func_backing_store_cfg_v2_output (size:128b/16B) */
+struct hwrm_func_backing_store_cfg_v2_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	rsvd0[7];
+	u8	valid;
+};
+
+/* hwrm_func_backing_store_qcfg_v2_input (size:192b/24B) */
+struct hwrm_func_backing_store_qcfg_v2_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	type;
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_XID_PARTITION_TABLE 0x1dUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_REQ_TYPE_INVALID
+	__le16	instance;
+	u8	rsvd[4];
+};
+
+/* hwrm_func_backing_store_qcfg_v2_output (size:448b/56B) */
+struct hwrm_func_backing_store_qcfg_v2_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	type;
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCFG_V2_RESP_TYPE_INVALID
+	__le16	instance;
+	__le32	flags;
+	__le64	page_dir;
+	__le32	num_entries;
+	u8	page_size_pbl_level;
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_MASK  0xfUL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_SFT   0
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_0   0x0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_1   0x1UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2   0x2UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LAST   FUNC_BACKING_STORE_QCFG_V2_RESP_PBL_LEVEL_LVL_2
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_MASK  0xf0UL
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_SFT   4
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_4K   (0x0UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8K   (0x1UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_64K  (0x2UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_2M   (0x3UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_8M   (0x4UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G   (0x5UL << 4)
+	#define FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_LAST   FUNC_BACKING_STORE_QCFG_V2_RESP_PAGE_SIZE_PG_1G
+	u8	subtype_valid_cnt;
+	u8	rsvd[2];
+	__le32	split_entry_0;
+	__le32	split_entry_1;
+	__le32	split_entry_2;
+	__le32	split_entry_3;
+	u8	rsvd2[7];
+	u8	valid;
+};
+
+/* qpc_split_entries (size:128b/16B) */
+struct qpc_split_entries {
+	__le32	qp_num_l2_entries;
+	__le32	qp_num_qp1_entries;
+	__le32	qp_num_fast_qpmd_entries;
+	__le32	rsvd;
+};
+
+/* srq_split_entries (size:128b/16B) */
+struct srq_split_entries {
+	__le32	srq_num_l2_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* cq_split_entries (size:128b/16B) */
+struct cq_split_entries {
+	__le32	cq_num_l2_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* vnic_split_entries (size:128b/16B) */
+struct vnic_split_entries {
+	__le32	vnic_num_vnic_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* mrav_split_entries (size:128b/16B) */
+struct mrav_split_entries {
+	__le32	mrav_num_av_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* ts_split_entries (size:128b/16B) */
+struct ts_split_entries {
+	__le32	region_num_entries;
+	u8	tsid;
+	u8	lkup_static_bkt_cnt_exp[2];
+	u8	locked;
+	__le32	rsvd2[2];
+};
+
+/* ck_split_entries (size:128b/16B) */
+struct ck_split_entries {
+	__le32	num_quic_entries;
+	__le32	rsvd;
+	__le32	rsvd2[2];
+};
+
+/* hwrm_func_backing_store_qcaps_v2_input (size:192b/24B) */
+struct hwrm_func_backing_store_qcaps_v2_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	type;
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_REQ_TYPE_INVALID
+	u8	rsvd[6];
+};
+
+/* hwrm_func_backing_store_qcaps_v2_output (size:448b/56B) */
+struct hwrm_func_backing_store_qcaps_v2_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	type;
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_QP                  0x0UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ                 0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ                  0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_VNIC                0x3UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_STAT                0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SP_TQM_RING         0x5UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_FP_TQM_RING         0x6UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MRAV                0xeUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TIM                 0xfUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TX_CK               0x13UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RX_CK               0x14UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_MP_TQM_RING         0x15UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SQ_DB_SHADOW        0x16UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RQ_DB_SHADOW        0x17UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRQ_DB_SHADOW       0x18UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CQ_DB_SHADOW        0x19UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TBL_SCOPE           0x1cUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_XID_PARTITION       0x1dUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT_TRACE           0x1eUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_SRT2_TRACE          0x1fUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT_TRACE           0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CRT2_TRACE          0x21UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP0_TRACE         0x22UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_L2_HWRM_TRACE       0x23UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_ROCE_HWRM_TRACE     0x24UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_TTX_PACING_TQM_RING 0x25UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA0_TRACE           0x26UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA1_TRACE           0x27UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_CA2_TRACE           0x28UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_RIGP1_TRACE         0x29UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_AFM_KONG_HWRM_TRACE 0x2aUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID             0xffffUL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_LAST               FUNC_BACKING_STORE_QCAPS_V2_RESP_TYPE_INVALID
+	__le16	entry_size;
+	__le32	flags;
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ENABLE_CTX_KIND_INIT            0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_TYPE_VALID                      0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_DRIVER_MANAGED_MEMORY           0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_ROCE_QP_PSEUDO_STATIC_ALLOC     0x8UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_DBG_TRACE                    0x10UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_FW_BIN_DBG_TRACE                0x20UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_FLAGS_NEXT_BS_OFFSET                  0x40UL
+	__le32	instance_bit_map;
+	u8	ctx_init_value;
+	u8	ctx_init_offset;
+	u8	entry_multiple;
+	u8	rsvd;
+	__le32	max_num_entries;
+	__le32	min_num_entries;
+	__le16	next_valid_type;
+	u8	subtype_valid_cnt;
+	u8	exact_cnt_bit_map;
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_0_EXACT     0x1UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_1_EXACT     0x2UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_2_EXACT     0x4UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_SPLIT_ENTRY_3_EXACT     0x8UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_UNUSED_MASK             0xf0UL
+	#define FUNC_BACKING_STORE_QCAPS_V2_RESP_EXACT_CNT_BIT_MAP_UNUSED_SFT              4
+	__le32	split_entry_0;
+	__le32	split_entry_1;
+	__le32	split_entry_2;
+	__le32	split_entry_3;
+	__le16	max_instance_count;
+	u8	rsvd3;
+	u8	valid;
+};
+
+/* hwrm_func_dbr_pacing_qcfg_input (size:128b/16B) */
+struct hwrm_func_dbr_pacing_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_func_dbr_pacing_qcfg_output (size:512b/64B) */
+struct hwrm_func_dbr_pacing_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define FUNC_DBR_PACING_QCFG_RESP_FLAGS_DBR_NQ_EVENT_ENABLED     0x1UL
+	u8	unused_0[7];
+	__le32	dbr_stat_db_fifo_reg;
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_MASK    0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_SFT     0
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_GRC       0x1UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR0      0x2UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1      0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SPACE_BAR1
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_MASK          0xfffffffcUL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_STAT_DB_FIFO_REG_ADDR_SFT           2
+	__le32	dbr_stat_db_fifo_reg_watermark_mask;
+	u8	dbr_stat_db_fifo_reg_watermark_shift;
+	u8	unused_1[3];
+	__le32	dbr_stat_db_fifo_reg_fifo_room_mask;
+	u8	dbr_stat_db_fifo_reg_fifo_room_shift;
+	u8	unused_2[3];
+	__le32	dbr_throttling_aeq_arm_reg;
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_MASK    0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_SFT     0
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_GRC       0x1UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR0      0x2UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1      0x3UL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_LAST     FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SPACE_BAR1
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_MASK          0xfffffffcUL
+	#define FUNC_DBR_PACING_QCFG_RESP_DBR_THROTTLING_AEQ_ARM_REG_ADDR_SFT           2
+	u8	dbr_throttling_aeq_arm_reg_val;
+	u8	unused_3[3];
+	__le32	dbr_stat_db_max_fifo_depth;
+	__le32	primary_nq_id;
+	__le32	pacing_threshold;
+	u8	unused_4[7];
+	u8	valid;
+};
+
+/* hwrm_func_drv_if_change_input (size:192b/24B) */
+struct hwrm_func_drv_if_change_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define FUNC_DRV_IF_CHANGE_REQ_FLAGS_UP     0x1UL
+	__le32	unused;
+};
+
+/* hwrm_func_drv_if_change_output (size:128b/16B) */
+struct hwrm_func_drv_if_change_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_RESC_CHANGE           0x1UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_HOT_FW_RESET_DONE     0x2UL
+	#define FUNC_DRV_IF_CHANGE_RESP_FLAGS_CAPS_CHANGE           0x4UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_port_phy_cfg_input (size:512b/64B) */
+struct hwrm_port_phy_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define PORT_PHY_CFG_REQ_FLAGS_RESET_PHY                  0x1UL
+	#define PORT_PHY_CFG_REQ_FLAGS_DEPRECATED                 0x2UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FORCE                      0x4UL
+	#define PORT_PHY_CFG_REQ_FLAGS_RESTART_AUTONEG            0x8UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_ENABLE                 0x10UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_DISABLE                0x20UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_ENABLE          0x40UL
+	#define PORT_PHY_CFG_REQ_FLAGS_EEE_TX_LPI_DISABLE         0x80UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_ENABLE         0x100UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_AUTONEG_DISABLE        0x200UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_ENABLE        0x400UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE74_DISABLE       0x800UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_ENABLE        0x1000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_CLAUSE91_DISABLE       0x2000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FORCE_LINK_DWN             0x4000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_ENABLE       0x8000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_1XN_DISABLE      0x10000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_ENABLE      0x20000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS544_IEEE_DISABLE     0x40000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_ENABLE       0x80000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_1XN_DISABLE      0x100000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_ENABLE      0x200000UL
+	#define PORT_PHY_CFG_REQ_FLAGS_FEC_RS272_IEEE_DISABLE     0x400000UL
+	__le32	enables;
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_MODE                     0x1UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_DUPLEX                   0x2UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAUSE                    0x4UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED               0x8UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEED_MASK          0x10UL
+	#define PORT_PHY_CFG_REQ_ENABLES_WIRESPEED                     0x20UL
+	#define PORT_PHY_CFG_REQ_ENABLES_LPBK                          0x40UL
+	#define PORT_PHY_CFG_REQ_ENABLES_PREEMPHASIS                   0x80UL
+	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAUSE                   0x100UL
+	#define PORT_PHY_CFG_REQ_ENABLES_EEE_LINK_SPEED_MASK           0x200UL
+	#define PORT_PHY_CFG_REQ_ENABLES_TX_LPI_TIMER                  0x400UL
+	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_PAM4_LINK_SPEED         0x800UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_PAM4_LINK_SPEED_MASK     0x1000UL
+	#define PORT_PHY_CFG_REQ_ENABLES_FORCE_LINK_SPEEDS2            0x2000UL
+	#define PORT_PHY_CFG_REQ_ENABLES_AUTO_LINK_SPEEDS2_MASK        0x4000UL
+	__le16	port_id;
+	__le16	force_link_speed;
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_LINK_SPEED_10MB
+	u8	auto_mode;
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_NONE         0x0UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_ALL_SPEEDS   0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_ONE_SPEED    0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_ONE_OR_BELOW 0x3UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK   0x4UL
+	#define PORT_PHY_CFG_REQ_AUTO_MODE_LAST        PORT_PHY_CFG_REQ_AUTO_MODE_SPEED_MASK
+	u8	auto_duplex;
+	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_HALF 0x0UL
+	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_FULL 0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_BOTH 0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_DUPLEX_LAST PORT_PHY_CFG_REQ_AUTO_DUPLEX_BOTH
+	u8	auto_pause;
+	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_TX                0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_RX                0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
+	u8	mgmt_flag;
+	#define PORT_PHY_CFG_REQ_MGMT_FLAG_LINK_RELEASE     0x1UL
+	#define PORT_PHY_CFG_REQ_MGMT_FLAG_MGMT_VALID       0x80UL
+	__le16	auto_link_speed;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_LAST PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_10MB
+	__le16	auto_link_speed_mask;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100MBHD     0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100MB       0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_1GBHD       0x4UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_1GB         0x8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_2GB         0x10UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_2_5GB       0x20UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10GB        0x40UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_20GB        0x80UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_25GB        0x100UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_40GB        0x200UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_50GB        0x400UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_100GB       0x800UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MBHD      0x1000UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEED_MASK_10MB        0x2000UL
+	u8	wirespeed;
+	#define PORT_PHY_CFG_REQ_WIRESPEED_OFF 0x0UL
+	#define PORT_PHY_CFG_REQ_WIRESPEED_ON  0x1UL
+	#define PORT_PHY_CFG_REQ_WIRESPEED_LAST PORT_PHY_CFG_REQ_WIRESPEED_ON
+	u8	lpbk;
+	#define PORT_PHY_CFG_REQ_LPBK_NONE     0x0UL
+	#define PORT_PHY_CFG_REQ_LPBK_LOCAL    0x1UL
+	#define PORT_PHY_CFG_REQ_LPBK_REMOTE   0x2UL
+	#define PORT_PHY_CFG_REQ_LPBK_EXTERNAL 0x3UL
+	#define PORT_PHY_CFG_REQ_LPBK_LAST    PORT_PHY_CFG_REQ_LPBK_EXTERNAL
+	u8	force_pause;
+	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_TX     0x1UL
+	#define PORT_PHY_CFG_REQ_FORCE_PAUSE_RX     0x2UL
+	u8	unused_1;
+	__le32	preemphasis;
+	__le16	eee_link_speed_mask;
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_100MB     0x2UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_1GB       0x8UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
+	#define PORT_PHY_CFG_REQ_EEE_LINK_SPEED_MASK_10GB      0x40UL
+	__le16	force_pam4_link_speed;
+	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL
+	#define PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_CFG_REQ_FORCE_PAM4_LINK_SPEED_200GB
+	__le32	tx_lpi_timer;
+	#define PORT_PHY_CFG_REQ_TX_LPI_TIMER_MASK 0xffffffUL
+	#define PORT_PHY_CFG_REQ_TX_LPI_TIMER_SFT 0
+	__le16	auto_link_pam4_speed_mask;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_50G      0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_100G     0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_PAM4_SPEED_MASK_200G     0x4UL
+	__le16	force_link_speeds2;
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_1GB            0xaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_10GB           0x64UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_25GB           0xfaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_40GB           0x190UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
+	#define PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_CFG_REQ_FORCE_LINK_SPEEDS2_800GB_PAM4_112
+	__le16	auto_link_speeds2_mask;
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_1GB                0x1UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_10GB               0x2UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_25GB               0x4UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_40GB               0x8UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB               0x10UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB              0x20UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_CFG_REQ_AUTO_LINK_SPEEDS2_MASK_800GB_PAM4_112     0x2000UL
+	u8	unused_2[6];
+};
+
+/* hwrm_port_phy_cfg_output (size:128b/16B) */
+struct hwrm_port_phy_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_cfg_cmd_err (size:64b/8B) */
+struct hwrm_port_phy_cfg_cmd_err {
+	u8	code;
+	#define PORT_PHY_CFG_CMD_ERR_CODE_UNKNOWN       0x0UL
+	#define PORT_PHY_CFG_CMD_ERR_CODE_ILLEGAL_SPEED 0x1UL
+	#define PORT_PHY_CFG_CMD_ERR_CODE_RETRY         0x2UL
+	#define PORT_PHY_CFG_CMD_ERR_CODE_LAST         PORT_PHY_CFG_CMD_ERR_CODE_RETRY
+	u8	unused_0[7];
+};
+
+/* hwrm_port_phy_qcfg_input (size:192b/24B) */
+struct hwrm_port_phy_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_phy_qcfg_output (size:832b/104B) */
+struct hwrm_port_phy_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	link;
+	#define PORT_PHY_QCFG_RESP_LINK_NO_LINK 0x0UL
+	#define PORT_PHY_QCFG_RESP_LINK_SIGNAL  0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_LINK    0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_LAST   PORT_PHY_QCFG_RESP_LINK_LINK
+	u8	active_fec_signal_mode;
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_MASK                0xfUL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_SFT                 0
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_NRZ                   0x0UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4                  0x1UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112              0x2UL
+	#define PORT_PHY_QCFG_RESP_SIGNAL_MODE_LAST                 PORT_PHY_QCFG_RESP_SIGNAL_MODE_PAM4_112
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_MASK                 0xf0UL
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_SFT                  4
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_NONE_ACTIVE        (0x0UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE74_ACTIVE    (0x1UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_CLAUSE91_ACTIVE    (0x2UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_1XN_ACTIVE   (0x3UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS544_IEEE_ACTIVE  (0x4UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_1XN_ACTIVE   (0x5UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE  (0x6UL << 4)
+	#define PORT_PHY_QCFG_RESP_ACTIVE_FEC_LAST                  PORT_PHY_QCFG_RESP_ACTIVE_FEC_FEC_RS272_IEEE_ACTIVE
+	__le16	link_speed;
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_200GB 0x7d0UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_400GB 0xfa0UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_800GB 0x1f40UL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_QCFG_RESP_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_LINK_SPEED_10MB
+	u8	duplex_cfg;
+	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_HALF 0x0UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL 0x1UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_CFG_LAST PORT_PHY_QCFG_RESP_DUPLEX_CFG_FULL
+	u8	pause;
+	#define PORT_PHY_QCFG_RESP_PAUSE_TX     0x1UL
+	#define PORT_PHY_QCFG_RESP_PAUSE_RX     0x2UL
+	__le16	support_speeds;
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MBHD     0x1UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100MB       0x2UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GBHD       0x4UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_1GB         0x8UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2GB         0x10UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_2_5GB       0x20UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10GB        0x40UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_20GB        0x80UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_25GB        0x100UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_40GB        0x200UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_50GB        0x400UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_100GB       0x800UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MBHD      0x1000UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS_10MB        0x2000UL
+	__le16	force_link_speed;
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_LINK_SPEED_10MB
+	u8	auto_mode;
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_NONE         0x0UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ALL_SPEEDS   0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ONE_SPEED    0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_ONE_OR_BELOW 0x3UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK   0x4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_MODE_LAST        PORT_PHY_QCFG_RESP_AUTO_MODE_SPEED_MASK
+	u8	auto_pause;
+	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_TX                0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_RX                0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_PAUSE_AUTONEG_PAUSE     0x4UL
+	__le16	auto_link_speed;
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100MB 0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_1GB   0xaUL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_2GB   0x14UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_2_5GB 0x19UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10GB  0x64UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_20GB  0xc8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_25GB  0xfaUL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_40GB  0x190UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB  0xffffUL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_10MB
+	__le16	auto_link_speed_mask;
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100MBHD     0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100MB       0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_1GBHD       0x4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_1GB         0x8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_2GB         0x10UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_2_5GB       0x20UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10GB        0x40UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_20GB        0x80UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_25GB        0x100UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_40GB        0x200UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_50GB        0x400UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_100GB       0x800UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MBHD      0x1000UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEED_MASK_10MB        0x2000UL
+	u8	wirespeed;
+	#define PORT_PHY_QCFG_RESP_WIRESPEED_OFF 0x0UL
+	#define PORT_PHY_QCFG_RESP_WIRESPEED_ON  0x1UL
+	#define PORT_PHY_QCFG_RESP_WIRESPEED_LAST PORT_PHY_QCFG_RESP_WIRESPEED_ON
+	u8	lpbk;
+	#define PORT_PHY_QCFG_RESP_LPBK_NONE     0x0UL
+	#define PORT_PHY_QCFG_RESP_LPBK_LOCAL    0x1UL
+	#define PORT_PHY_QCFG_RESP_LPBK_REMOTE   0x2UL
+	#define PORT_PHY_QCFG_RESP_LPBK_EXTERNAL 0x3UL
+	#define PORT_PHY_QCFG_RESP_LPBK_LAST    PORT_PHY_QCFG_RESP_LPBK_EXTERNAL
+	u8	force_pause;
+	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_TX     0x1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_PAUSE_RX     0x2UL
+	u8	module_status;
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NONE          0x0UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_DISABLETX     0x1UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_WARNINGMSG    0x2UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_PWRDOWN       0x3UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTINSERTED   0x4UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_CURRENTFAULT  0x5UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_OVERHEATED    0x6UL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE 0xffUL
+	#define PORT_PHY_QCFG_RESP_MODULE_STATUS_LAST         PORT_PHY_QCFG_RESP_MODULE_STATUS_NOTAPPLICABLE
+	__le32	preemphasis;
+	u8	phy_maj;
+	u8	phy_min;
+	u8	phy_bld;
+	u8	phy_type;
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_UNKNOWN          0x0UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASECR           0x1UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR4          0x2UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASELR           0x3UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASESR           0x4UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR2          0x5UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKX           0x6UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASEKR           0x7UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASET            0x8UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_BASETE           0x9UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_SGMIIEXTPHY      0xaUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_L  0xbUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_S  0xcUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASECR_CA_N  0xdUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_25G_BASESR       0xeUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR4     0xfUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR4     0x10UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR4     0x11UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER4     0x12UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR10    0x13UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASECR4      0x14UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASESR4      0x15UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASELR4      0x16UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_BASEER4      0x17UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_40G_ACTIVE_CABLE 0x18UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASET         0x19UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASESX        0x1aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_1G_BASECX        0x1bUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR4     0x1cUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR4     0x1dUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR4     0x1eUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER4     0x1fUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASECR       0x20UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASESR       0x21UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASELR       0x22UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_50G_BASEER       0x23UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR2     0x24UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR2     0x25UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR2     0x26UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER2     0x27UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASECR      0x28UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASESR      0x29UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASELR      0x2aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_100G_BASEER      0x2bUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASECR2     0x2cUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASESR2     0x2dUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASELR2     0x2eUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_200G_BASEER2     0x2fUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR8     0x30UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR8     0x31UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR8     0x32UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER8     0x33UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASECR4     0x34UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASESR4     0x35UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASELR4     0x36UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_400G_BASEER4     0x37UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASECR8     0x38UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASESR8     0x39UL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASELR8     0x3aUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEER8     0x3bUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEFR8     0x3cUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8     0x3dUL
+	#define PORT_PHY_QCFG_RESP_PHY_TYPE_LAST            PORT_PHY_QCFG_RESP_PHY_TYPE_800G_BASEDR8
+	u8	media_type;
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_UNKNOWN   0x0UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_TP        0x1UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_DAC       0x2UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_FIBRE     0x3UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_BACKPLANE 0x4UL
+	#define PORT_PHY_QCFG_RESP_MEDIA_TYPE_LAST     PORT_PHY_QCFG_RESP_MEDIA_TYPE_BACKPLANE
+	u8	xcvr_pkg_type;
+	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_INTERNAL 0x1UL
+	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_EXTERNAL 0x2UL
+	#define PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_LAST         PORT_PHY_QCFG_RESP_XCVR_PKG_TYPE_XCVR_EXTERNAL
+	u8	eee_config_phy_addr;
+	#define PORT_PHY_QCFG_RESP_PHY_ADDR_MASK              0x1fUL
+	#define PORT_PHY_QCFG_RESP_PHY_ADDR_SFT               0
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_MASK            0xe0UL
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_SFT             5
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_ENABLED      0x20UL
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_ACTIVE       0x40UL
+	#define PORT_PHY_QCFG_RESP_EEE_CONFIG_EEE_TX_LPI       0x80UL
+	u8	parallel_detect;
+	#define PORT_PHY_QCFG_RESP_PARALLEL_DETECT     0x1UL
+	__le16	link_partner_adv_speeds;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100MBHD     0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100MB       0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_1GBHD       0x4UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_1GB         0x8UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_2GB         0x10UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_2_5GB       0x20UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10GB        0x40UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_20GB        0x80UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_25GB        0x100UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_40GB        0x200UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_50GB        0x400UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_100GB       0x800UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10MBHD      0x1000UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_SPEEDS_10MB        0x2000UL
+	u8	link_partner_adv_auto_mode;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_NONE         0x0UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ALL_SPEEDS   0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ONE_SPEED    0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_ONE_OR_BELOW 0x3UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_SPEED_MASK   0x4UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_LAST        PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_AUTO_MODE_SPEED_MASK
+	u8	link_partner_adv_pause;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_PAUSE_TX     0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_PAUSE_RX     0x2UL
+	__le16	adv_eee_link_speed_mask;
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_100MB     0x2UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_1GB       0x8UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
+	#define PORT_PHY_QCFG_RESP_ADV_EEE_LINK_SPEED_MASK_10GB      0x40UL
+	__le16	link_partner_adv_eee_link_speed_mask;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD1     0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_100MB     0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD2     0x4UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_1GB       0x8UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD3     0x10UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_RSVD4     0x20UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_ADV_EEE_LINK_SPEED_MASK_10GB      0x40UL
+	__le32	xcvr_identifier_type_tx_lpi_timer;
+	#define PORT_PHY_QCFG_RESP_TX_LPI_TIMER_MASK            0xffffffUL
+	#define PORT_PHY_QCFG_RESP_TX_LPI_TIMER_SFT             0
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_MASK    0xff000000UL
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFT     24
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_UNKNOWN   (0x0UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFP       (0x3UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP      (0xcUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPPLUS  (0xdUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP28    (0x11UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFPDD    (0x18UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_QSFP112   (0x1eUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_SFPDD     (0x1fUL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP      (0x20UL << 24)
+	#define PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_LAST     PORT_PHY_QCFG_RESP_XCVR_IDENTIFIER_TYPE_CSFP
+	__le16	fec_cfg;
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_NONE_SUPPORTED           0x1UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_SUPPORTED        0x2UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_AUTONEG_ENABLED          0x4UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_SUPPORTED       0x8UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE74_ENABLED         0x10UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_SUPPORTED       0x20UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_CLAUSE91_ENABLED         0x40UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_SUPPORTED      0x80UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_1XN_ENABLED        0x100UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_SUPPORTED     0x200UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS544_IEEE_ENABLED       0x400UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_SUPPORTED      0x800UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_1XN_ENABLED        0x1000UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_SUPPORTED     0x2000UL
+	#define PORT_PHY_QCFG_RESP_FEC_CFG_FEC_RS272_IEEE_ENABLED       0x4000UL
+	u8	duplex_state;
+	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_HALF 0x0UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL 0x1UL
+	#define PORT_PHY_QCFG_RESP_DUPLEX_STATE_LAST PORT_PHY_QCFG_RESP_DUPLEX_STATE_FULL
+	u8	option_flags;
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_MEDIA_AUTO_DETECT     0x1UL
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SIGNAL_MODE_KNOWN     0x2UL
+	#define PORT_PHY_QCFG_RESP_OPTION_FLAGS_SPEEDS2_SUPPORTED     0x4UL
+	char	phy_vendor_name[16];
+	char	phy_vendor_partnumber[16];
+	__le16	support_pam4_speeds;
+	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_50G      0x1UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_100G     0x2UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_PAM4_SPEEDS_200G     0x4UL
+	__le16	force_pam4_link_speed;
+	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_50GB  0x1f4UL
+	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_100GB 0x3e8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB 0x7d0UL
+	#define PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_LAST PORT_PHY_QCFG_RESP_FORCE_PAM4_LINK_SPEED_200GB
+	__le16	auto_pam4_link_speed_mask;
+	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_50G      0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_100G     0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_PAM4_LINK_SPEED_MASK_200G     0x4UL
+	u8	link_partner_pam4_adv_speeds;
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_50GB      0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_100GB     0x2UL
+	#define PORT_PHY_QCFG_RESP_LINK_PARTNER_PAM4_ADV_SPEEDS_200GB     0x4UL
+	u8	link_down_reason;
+	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_RF                      0x1UL
+	#define PORT_PHY_QCFG_RESP_LINK_DOWN_REASON_OTP_SPEED_VIOLATION     0x2UL
+	__le16	support_speeds2;
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_1GB                0x1UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_10GB               0x2UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_25GB               0x4UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_40GB               0x8UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB               0x10UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB              0x20UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCFG_RESP_SUPPORT_SPEEDS2_800GB_PAM4_112     0x2000UL
+	__le16	force_link_speeds2;
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_1GB            0xaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_10GB           0x64UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_25GB           0xfaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_40GB           0x190UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB           0x1f4UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB          0x3e8UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_50GB_PAM4_56   0x1f5UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_56  0x3e9UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_56  0x7d1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_56  0xfa1UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_100GB_PAM4_112 0x3eaUL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_200GB_PAM4_112 0x7d2UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_400GB_PAM4_112 0xfa2UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112 0x1f42UL
+	#define PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_LAST          PORT_PHY_QCFG_RESP_FORCE_LINK_SPEEDS2_800GB_PAM4_112
+	__le16	auto_link_speeds2;
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_1GB                0x1UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_10GB               0x2UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_25GB               0x4UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_40GB               0x8UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB               0x10UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB              0x20UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCFG_RESP_AUTO_LINK_SPEEDS2_800GB_PAM4_112     0x2000UL
+	u8	active_lanes;
+	u8	valid;
+};
+
+/* hwrm_port_mac_cfg_input (size:448b/56B) */
+struct hwrm_port_mac_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define PORT_MAC_CFG_REQ_FLAGS_MATCH_LINK                    0x1UL
+	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_ENABLE           0x2UL
+	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_ENABLE         0x4UL
+	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_ENABLE            0x8UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_ENABLE      0x10UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_RX_TS_CAPTURE_DISABLE     0x20UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_ENABLE      0x40UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_TX_TS_CAPTURE_DISABLE     0x80UL
+	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_ENABLE                0x100UL
+	#define PORT_MAC_CFG_REQ_FLAGS_OOB_WOL_DISABLE               0x200UL
+	#define PORT_MAC_CFG_REQ_FLAGS_VLAN_PRI2COS_DISABLE          0x400UL
+	#define PORT_MAC_CFG_REQ_FLAGS_TUNNEL_PRI2COS_DISABLE        0x800UL
+	#define PORT_MAC_CFG_REQ_FLAGS_IP_DSCP2COS_DISABLE           0x1000UL
+	#define PORT_MAC_CFG_REQ_FLAGS_PTP_ONE_STEP_TX_TS            0x2000UL
+	#define PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_ENABLE      0x4000UL
+	#define PORT_MAC_CFG_REQ_FLAGS_ALL_RX_TS_CAPTURE_DISABLE     0x8000UL
+	__le32	enables;
+	#define PORT_MAC_CFG_REQ_ENABLES_IPG                            0x1UL
+	#define PORT_MAC_CFG_REQ_ENABLES_LPBK                           0x2UL
+	#define PORT_MAC_CFG_REQ_ENABLES_VLAN_PRI2COS_MAP_PRI           0x4UL
+	#define PORT_MAC_CFG_REQ_ENABLES_TUNNEL_PRI2COS_MAP_PRI         0x10UL
+	#define PORT_MAC_CFG_REQ_ENABLES_DSCP2COS_MAP_PRI               0x20UL
+	#define PORT_MAC_CFG_REQ_ENABLES_RX_TS_CAPTURE_PTP_MSG_TYPE     0x40UL
+	#define PORT_MAC_CFG_REQ_ENABLES_TX_TS_CAPTURE_PTP_MSG_TYPE     0x80UL
+	#define PORT_MAC_CFG_REQ_ENABLES_COS_FIELD_CFG                  0x100UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_FREQ_ADJ_PPB               0x200UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_ADJ_PHASE                  0x400UL
+	#define PORT_MAC_CFG_REQ_ENABLES_PTP_LOAD_CONTROL               0x800UL
+	__le16	port_id;
+	u8	ipg;
+	u8	lpbk;
+	#define PORT_MAC_CFG_REQ_LPBK_NONE   0x0UL
+	#define PORT_MAC_CFG_REQ_LPBK_LOCAL  0x1UL
+	#define PORT_MAC_CFG_REQ_LPBK_REMOTE 0x2UL
+	#define PORT_MAC_CFG_REQ_LPBK_LAST  PORT_MAC_CFG_REQ_LPBK_REMOTE
+	u8	vlan_pri2cos_map_pri;
+	u8	reserved1;
+	u8	tunnel_pri2cos_map_pri;
+	u8	dscp2pri_map_pri;
+	__le16	rx_ts_capture_ptp_msg_type;
+	__le16	tx_ts_capture_ptp_msg_type;
+	u8	cos_field_cfg;
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_RSVD1                     0x1UL
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_MASK         0x6UL
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_SFT          1
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_INNERMOST      (0x0UL << 1)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_OUTER          (0x1UL << 1)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_OUTERMOST      (0x2UL << 1)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_UNSPECIFIED    (0x3UL << 1)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_LAST          PORT_MAC_CFG_REQ_COS_FIELD_CFG_VLAN_PRI_SEL_UNSPECIFIED
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_MASK       0x18UL
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_SFT        3
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_INNERMOST    (0x0UL << 3)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_OUTER        (0x1UL << 3)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_OUTERMOST    (0x2UL << 3)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_UNSPECIFIED  (0x3UL << 3)
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_LAST        PORT_MAC_CFG_REQ_COS_FIELD_CFG_T_VLAN_PRI_SEL_UNSPECIFIED
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_MASK          0xe0UL
+	#define PORT_MAC_CFG_REQ_COS_FIELD_CFG_DEFAULT_COS_SFT           5
+	u8	unused_0[3];
+	__le32	ptp_freq_adj_ppb;
+	u8	unused_1[3];
+	u8	ptp_load_control;
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_NONE      0x0UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_IMMEDIATE 0x1UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT 0x2UL
+	#define PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_LAST     PORT_MAC_CFG_REQ_PTP_LOAD_CONTROL_PPS_EVENT
+	__le64	ptp_adj_phase;
+};
+
+/* hwrm_port_mac_cfg_output (size:128b/16B) */
+struct hwrm_port_mac_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	mru;
+	__le16	mtu;
+	u8	ipg;
+	u8	lpbk;
+	#define PORT_MAC_CFG_RESP_LPBK_NONE   0x0UL
+	#define PORT_MAC_CFG_RESP_LPBK_LOCAL  0x1UL
+	#define PORT_MAC_CFG_RESP_LPBK_REMOTE 0x2UL
+	#define PORT_MAC_CFG_RESP_LPBK_LAST  PORT_MAC_CFG_RESP_LPBK_REMOTE
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_port_mac_ptp_qcfg_input (size:192b/24B) */
+struct hwrm_port_mac_ptp_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_mac_ptp_qcfg_output (size:704b/88B) */
+struct hwrm_port_mac_ptp_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_DIRECT_ACCESS                       0x1UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_ONE_STEP_TX_TS                      0x4UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_HWRM_ACCESS                         0x8UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_PARTIAL_DIRECT_ACCESS_REF_CLOCK     0x10UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_RTC_CONFIGURED                      0x20UL
+	#define PORT_MAC_PTP_QCFG_RESP_FLAGS_64B_PHC_TIME                        0x40UL
+	u8	unused_0[3];
+	__le32	rx_ts_reg_off_lower;
+	__le32	rx_ts_reg_off_upper;
+	__le32	rx_ts_reg_off_seq_id;
+	__le32	rx_ts_reg_off_src_id_0;
+	__le32	rx_ts_reg_off_src_id_1;
+	__le32	rx_ts_reg_off_src_id_2;
+	__le32	rx_ts_reg_off_domain_id;
+	__le32	rx_ts_reg_off_fifo;
+	__le32	rx_ts_reg_off_fifo_adv;
+	__le32	rx_ts_reg_off_granularity;
+	__le32	tx_ts_reg_off_lower;
+	__le32	tx_ts_reg_off_upper;
+	__le32	tx_ts_reg_off_seq_id;
+	__le32	tx_ts_reg_off_fifo;
+	__le32	tx_ts_reg_off_granularity;
+	__le32	ts_ref_clock_reg_lower;
+	__le32	ts_ref_clock_reg_upper;
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* tx_port_stats (size:3264b/408B) */
+struct tx_port_stats {
+	__le64	tx_64b_frames;
+	__le64	tx_65b_127b_frames;
+	__le64	tx_128b_255b_frames;
+	__le64	tx_256b_511b_frames;
+	__le64	tx_512b_1023b_frames;
+	__le64	tx_1024b_1518b_frames;
+	__le64	tx_good_vlan_frames;
+	__le64	tx_1519b_2047b_frames;
+	__le64	tx_2048b_4095b_frames;
+	__le64	tx_4096b_9216b_frames;
+	__le64	tx_9217b_16383b_frames;
+	__le64	tx_good_frames;
+	__le64	tx_total_frames;
+	__le64	tx_ucast_frames;
+	__le64	tx_mcast_frames;
+	__le64	tx_bcast_frames;
+	__le64	tx_pause_frames;
+	__le64	tx_pfc_frames;
+	__le64	tx_jabber_frames;
+	__le64	tx_fcs_err_frames;
+	__le64	tx_control_frames;
+	__le64	tx_oversz_frames;
+	__le64	tx_single_dfrl_frames;
+	__le64	tx_multi_dfrl_frames;
+	__le64	tx_single_coll_frames;
+	__le64	tx_multi_coll_frames;
+	__le64	tx_late_coll_frames;
+	__le64	tx_excessive_coll_frames;
+	__le64	tx_frag_frames;
+	__le64	tx_err;
+	__le64	tx_tagged_frames;
+	__le64	tx_dbl_tagged_frames;
+	__le64	tx_runt_frames;
+	__le64	tx_fifo_underruns;
+	__le64	tx_pfc_ena_frames_pri0;
+	__le64	tx_pfc_ena_frames_pri1;
+	__le64	tx_pfc_ena_frames_pri2;
+	__le64	tx_pfc_ena_frames_pri3;
+	__le64	tx_pfc_ena_frames_pri4;
+	__le64	tx_pfc_ena_frames_pri5;
+	__le64	tx_pfc_ena_frames_pri6;
+	__le64	tx_pfc_ena_frames_pri7;
+	__le64	tx_eee_lpi_events;
+	__le64	tx_eee_lpi_duration;
+	__le64	tx_llfc_logical_msgs;
+	__le64	tx_hcfc_msgs;
+	__le64	tx_total_collisions;
+	__le64	tx_bytes;
+	__le64	tx_xthol_frames;
+	__le64	tx_stat_discard;
+	__le64	tx_stat_error;
+};
+
+/* rx_port_stats (size:4224b/528B) */
+struct rx_port_stats {
+	__le64	rx_64b_frames;
+	__le64	rx_65b_127b_frames;
+	__le64	rx_128b_255b_frames;
+	__le64	rx_256b_511b_frames;
+	__le64	rx_512b_1023b_frames;
+	__le64	rx_1024b_1518b_frames;
+	__le64	rx_good_vlan_frames;
+	__le64	rx_1519b_2047b_frames;
+	__le64	rx_2048b_4095b_frames;
+	__le64	rx_4096b_9216b_frames;
+	__le64	rx_9217b_16383b_frames;
+	__le64	rx_total_frames;
+	__le64	rx_ucast_frames;
+	__le64	rx_mcast_frames;
+	__le64	rx_bcast_frames;
+	__le64	rx_fcs_err_frames;
+	__le64	rx_ctrl_frames;
+	__le64	rx_pause_frames;
+	__le64	rx_pfc_frames;
+	__le64	rx_unsupported_opcode_frames;
+	__le64	rx_unsupported_da_pausepfc_frames;
+	__le64	rx_wrong_sa_frames;
+	__le64	rx_align_err_frames;
+	__le64	rx_oor_len_frames;
+	__le64	rx_code_err_frames;
+	__le64	rx_false_carrier_frames;
+	__le64	rx_ovrsz_frames;
+	__le64	rx_jbr_frames;
+	__le64	rx_mtu_err_frames;
+	__le64	rx_match_crc_frames;
+	__le64	rx_promiscuous_frames;
+	__le64	rx_tagged_frames;
+	__le64	rx_double_tagged_frames;
+	__le64	rx_trunc_frames;
+	__le64	rx_good_frames;
+	__le64	rx_pfc_xon2xoff_frames_pri0;
+	__le64	rx_pfc_xon2xoff_frames_pri1;
+	__le64	rx_pfc_xon2xoff_frames_pri2;
+	__le64	rx_pfc_xon2xoff_frames_pri3;
+	__le64	rx_pfc_xon2xoff_frames_pri4;
+	__le64	rx_pfc_xon2xoff_frames_pri5;
+	__le64	rx_pfc_xon2xoff_frames_pri6;
+	__le64	rx_pfc_xon2xoff_frames_pri7;
+	__le64	rx_pfc_ena_frames_pri0;
+	__le64	rx_pfc_ena_frames_pri1;
+	__le64	rx_pfc_ena_frames_pri2;
+	__le64	rx_pfc_ena_frames_pri3;
+	__le64	rx_pfc_ena_frames_pri4;
+	__le64	rx_pfc_ena_frames_pri5;
+	__le64	rx_pfc_ena_frames_pri6;
+	__le64	rx_pfc_ena_frames_pri7;
+	__le64	rx_sch_crc_err_frames;
+	__le64	rx_undrsz_frames;
+	__le64	rx_frag_frames;
+	__le64	rx_eee_lpi_events;
+	__le64	rx_eee_lpi_duration;
+	__le64	rx_llfc_physical_msgs;
+	__le64	rx_llfc_logical_msgs;
+	__le64	rx_llfc_msgs_with_crc_err;
+	__le64	rx_hcfc_msgs;
+	__le64	rx_hcfc_msgs_with_crc_err;
+	__le64	rx_bytes;
+	__le64	rx_runt_bytes;
+	__le64	rx_runt_frames;
+	__le64	rx_stat_discard;
+	__le64	rx_stat_err;
+};
+
+/* hwrm_port_qstats_input (size:320b/40B) */
+struct hwrm_port_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	flags;
+	#define PORT_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[5];
+	__le64	tx_stat_host_addr;
+	__le64	rx_stat_host_addr;
+};
+
+/* hwrm_port_qstats_output (size:128b/16B) */
+struct hwrm_port_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	tx_stat_size;
+	__le16	rx_stat_size;
+	u8	flags;
+	#define PORT_QSTATS_RESP_FLAGS_CLEARED     0x1UL
+	u8	unused_0[2];
+	u8	valid;
+};
+
+/* tx_port_stats_ext (size:2048b/256B) */
+struct tx_port_stats_ext {
+	__le64	tx_bytes_cos0;
+	__le64	tx_bytes_cos1;
+	__le64	tx_bytes_cos2;
+	__le64	tx_bytes_cos3;
+	__le64	tx_bytes_cos4;
+	__le64	tx_bytes_cos5;
+	__le64	tx_bytes_cos6;
+	__le64	tx_bytes_cos7;
+	__le64	tx_packets_cos0;
+	__le64	tx_packets_cos1;
+	__le64	tx_packets_cos2;
+	__le64	tx_packets_cos3;
+	__le64	tx_packets_cos4;
+	__le64	tx_packets_cos5;
+	__le64	tx_packets_cos6;
+	__le64	tx_packets_cos7;
+	__le64	pfc_pri0_tx_duration_us;
+	__le64	pfc_pri0_tx_transitions;
+	__le64	pfc_pri1_tx_duration_us;
+	__le64	pfc_pri1_tx_transitions;
+	__le64	pfc_pri2_tx_duration_us;
+	__le64	pfc_pri2_tx_transitions;
+	__le64	pfc_pri3_tx_duration_us;
+	__le64	pfc_pri3_tx_transitions;
+	__le64	pfc_pri4_tx_duration_us;
+	__le64	pfc_pri4_tx_transitions;
+	__le64	pfc_pri5_tx_duration_us;
+	__le64	pfc_pri5_tx_transitions;
+	__le64	pfc_pri6_tx_duration_us;
+	__le64	pfc_pri6_tx_transitions;
+	__le64	pfc_pri7_tx_duration_us;
+	__le64	pfc_pri7_tx_transitions;
+};
+
+/* rx_port_stats_ext (size:3904b/488B) */
+struct rx_port_stats_ext {
+	__le64	link_down_events;
+	__le64	continuous_pause_events;
+	__le64	resume_pause_events;
+	__le64	continuous_roce_pause_events;
+	__le64	resume_roce_pause_events;
+	__le64	rx_bytes_cos0;
+	__le64	rx_bytes_cos1;
+	__le64	rx_bytes_cos2;
+	__le64	rx_bytes_cos3;
+	__le64	rx_bytes_cos4;
+	__le64	rx_bytes_cos5;
+	__le64	rx_bytes_cos6;
+	__le64	rx_bytes_cos7;
+	__le64	rx_packets_cos0;
+	__le64	rx_packets_cos1;
+	__le64	rx_packets_cos2;
+	__le64	rx_packets_cos3;
+	__le64	rx_packets_cos4;
+	__le64	rx_packets_cos5;
+	__le64	rx_packets_cos6;
+	__le64	rx_packets_cos7;
+	__le64	pfc_pri0_rx_duration_us;
+	__le64	pfc_pri0_rx_transitions;
+	__le64	pfc_pri1_rx_duration_us;
+	__le64	pfc_pri1_rx_transitions;
+	__le64	pfc_pri2_rx_duration_us;
+	__le64	pfc_pri2_rx_transitions;
+	__le64	pfc_pri3_rx_duration_us;
+	__le64	pfc_pri3_rx_transitions;
+	__le64	pfc_pri4_rx_duration_us;
+	__le64	pfc_pri4_rx_transitions;
+	__le64	pfc_pri5_rx_duration_us;
+	__le64	pfc_pri5_rx_transitions;
+	__le64	pfc_pri6_rx_duration_us;
+	__le64	pfc_pri6_rx_transitions;
+	__le64	pfc_pri7_rx_duration_us;
+	__le64	pfc_pri7_rx_transitions;
+	__le64	rx_bits;
+	__le64	rx_buffer_passed_threshold;
+	__le64	rx_pcs_symbol_err;
+	__le64	rx_corrected_bits;
+	__le64	rx_discard_bytes_cos0;
+	__le64	rx_discard_bytes_cos1;
+	__le64	rx_discard_bytes_cos2;
+	__le64	rx_discard_bytes_cos3;
+	__le64	rx_discard_bytes_cos4;
+	__le64	rx_discard_bytes_cos5;
+	__le64	rx_discard_bytes_cos6;
+	__le64	rx_discard_bytes_cos7;
+	__le64	rx_discard_packets_cos0;
+	__le64	rx_discard_packets_cos1;
+	__le64	rx_discard_packets_cos2;
+	__le64	rx_discard_packets_cos3;
+	__le64	rx_discard_packets_cos4;
+	__le64	rx_discard_packets_cos5;
+	__le64	rx_discard_packets_cos6;
+	__le64	rx_discard_packets_cos7;
+	__le64	rx_fec_corrected_blocks;
+	__le64	rx_fec_uncorrectable_blocks;
+	__le64	rx_filter_miss;
+	__le64	rx_fec_symbol_err;
+};
+
+/* hwrm_port_qstats_ext_input (size:320b/40B) */
+struct hwrm_port_qstats_ext_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	__le16	tx_stat_size;
+	__le16	rx_stat_size;
+	u8	flags;
+	#define PORT_QSTATS_EXT_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0;
+	__le64	tx_stat_host_addr;
+	__le64	rx_stat_host_addr;
+};
+
+/* hwrm_port_qstats_ext_output (size:128b/16B) */
+struct hwrm_port_qstats_ext_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	tx_stat_size;
+	__le16	rx_stat_size;
+	__le16	total_active_cos_queues;
+	u8	flags;
+	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEAR_ROCE_COUNTERS_SUPPORTED     0x1UL
+	#define PORT_QSTATS_EXT_RESP_FLAGS_CLEARED                           0x2UL
+	u8	valid;
+};
+
+/* hwrm_port_lpbk_qstats_input (size:256b/32B) */
+struct hwrm_port_lpbk_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	lpbk_stat_size;
+	u8	flags;
+	#define PORT_LPBK_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[5];
+	__le64	lpbk_stat_host_addr;
+};
+
+/* hwrm_port_lpbk_qstats_output (size:128b/16B) */
+struct hwrm_port_lpbk_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	lpbk_stat_size;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* port_lpbk_stats (size:640b/80B) */
+struct port_lpbk_stats {
+	__le64	lpbk_ucast_frames;
+	__le64	lpbk_mcast_frames;
+	__le64	lpbk_bcast_frames;
+	__le64	lpbk_ucast_bytes;
+	__le64	lpbk_mcast_bytes;
+	__le64	lpbk_bcast_bytes;
+	__le64	lpbk_tx_discards;
+	__le64	lpbk_tx_errors;
+	__le64	lpbk_rx_discards;
+	__le64	lpbk_rx_errors;
+};
+
+/* hwrm_port_ecn_qstats_input (size:256b/32B) */
+struct hwrm_port_ecn_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	__le16	ecn_stat_buf_size;
+	u8	flags;
+	#define PORT_ECN_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[3];
+	__le64	ecn_stat_host_addr;
+};
+
+/* hwrm_port_ecn_qstats_output (size:128b/16B) */
+struct hwrm_port_ecn_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	ecn_stat_buf_size;
+	u8	mark_en;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* port_stats_ecn (size:512b/64B) */
+struct port_stats_ecn {
+	__le64	mark_cnt_cos0;
+	__le64	mark_cnt_cos1;
+	__le64	mark_cnt_cos2;
+	__le64	mark_cnt_cos3;
+	__le64	mark_cnt_cos4;
+	__le64	mark_cnt_cos5;
+	__le64	mark_cnt_cos6;
+	__le64	mark_cnt_cos7;
+};
+
+/* hwrm_port_clr_stats_input (size:192b/24B) */
+struct hwrm_port_clr_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	flags;
+	#define PORT_CLR_STATS_REQ_FLAGS_ROCE_COUNTERS     0x1UL
+	u8	unused_0[5];
+};
+
+/* hwrm_port_clr_stats_output (size:128b/16B) */
+struct hwrm_port_clr_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_lpbk_clr_stats_input (size:192b/24B) */
+struct hwrm_port_lpbk_clr_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_lpbk_clr_stats_output (size:128b/16B) */
+struct hwrm_port_lpbk_clr_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_ts_query_input (size:320b/40B) */
+struct hwrm_port_ts_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH             0x1UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_TX            0x0UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_RX            0x1UL
+	#define PORT_TS_QUERY_REQ_FLAGS_PATH_LAST         PORT_TS_QUERY_REQ_FLAGS_PATH_RX
+	#define PORT_TS_QUERY_REQ_FLAGS_CURRENT_TIME     0x2UL
+	__le16	port_id;
+	u8	unused_0[2];
+	__le16	enables;
+	#define PORT_TS_QUERY_REQ_ENABLES_TS_REQ_TIMEOUT     0x1UL
+	#define PORT_TS_QUERY_REQ_ENABLES_PTP_SEQ_ID         0x2UL
+	#define PORT_TS_QUERY_REQ_ENABLES_PTP_HDR_OFFSET     0x4UL
+	__le16	ts_req_timeout;
+	__le32	ptp_seq_id;
+	__le16	ptp_hdr_offset;
+	u8	unused_1[6];
+};
+
+/* hwrm_port_ts_query_output (size:192b/24B) */
+struct hwrm_port_ts_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	ptp_msg_ts;
+	__le16	ptp_msg_seqid;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_port_phy_qcaps_input (size:192b/24B) */
+struct hwrm_port_phy_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_phy_qcaps_output (size:320b/40B) */
+struct hwrm_port_phy_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EEE_SUPPORTED                    0x1UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_EXTERNAL_LPBK_SUPPORTED          0x2UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_AUTONEG_LPBK_SUPPORTED           0x4UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_SHARED_PHY_CFG_SUPPORTED         0x8UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_CUMULATIVE_COUNTERS_ON_RESET     0x10UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED         0x20UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_FW_MANAGED_LINK_DOWN             0x40UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS_NO_FCS                           0x80UL
+	u8	port_cnt;
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_UNKNOWN 0x0UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_1       0x1UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_2       0x2UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_3       0x3UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_4       0x4UL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_12      0xcUL
+	#define PORT_PHY_QCAPS_RESP_PORT_CNT_LAST   PORT_PHY_QCAPS_RESP_PORT_CNT_12
+	__le16	supported_speeds_force_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MBHD     0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100MB       0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_1GBHD       0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_1GB         0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_2GB         0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_2_5GB       0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10GB        0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_20GB        0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_25GB        0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_40GB        0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_50GB        0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_100GB       0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MBHD      0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_FORCE_MODE_10MB        0x2000UL
+	__le16	supported_speeds_auto_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MBHD     0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100MB       0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_1GBHD       0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_1GB         0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_2GB         0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_2_5GB       0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10GB        0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_20GB        0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_25GB        0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_40GB        0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_50GB        0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_100GB       0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MBHD      0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_AUTO_MODE_10MB        0x2000UL
+	__le16	supported_speeds_eee_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD1     0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_100MB     0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD2     0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_1GB       0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD3     0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_RSVD4     0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS_EEE_MODE_10GB      0x40UL
+	__le32	tx_lpi_timer_low;
+	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_MASK 0xffffffUL
+	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_LOW_SFT 0
+	#define PORT_PHY_QCAPS_RESP_RSVD2_MASK           0xff000000UL
+	#define PORT_PHY_QCAPS_RESP_RSVD2_SFT            24
+	__le32	valid_tx_lpi_timer_high;
+	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_MASK 0xffffffUL
+	#define PORT_PHY_QCAPS_RESP_TX_LPI_TIMER_HIGH_SFT 0
+	#define PORT_PHY_QCAPS_RESP_RSVD_MASK             0xff000000UL
+	#define PORT_PHY_QCAPS_RESP_RSVD_SFT              24
+	__le16	supported_pam4_speeds_auto_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_50G      0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_100G     0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_AUTO_MODE_200G     0x4UL
+	__le16	supported_pam4_speeds_force_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_50G      0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_100G     0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_PAM4_SPEEDS_FORCE_MODE_200G     0x4UL
+	__le16	flags2;
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_PAUSE_UNSUPPORTED           0x1UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_PFC_UNSUPPORTED             0x2UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_BANK_ADDR_SUPPORTED         0x4UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_SPEEDS2_SUPPORTED           0x8UL
+	#define PORT_PHY_QCAPS_RESP_FLAGS2_REMOTE_LPBK_UNSUPPORTED     0x10UL
+	u8	internal_port_cnt;
+	u8	unused_0;
+	__le16	supported_speeds2_force_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_1GB                0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_10GB               0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_25GB               0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_40GB               0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB               0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB              0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_FORCE_MODE_800GB_PAM4_112     0x2000UL
+	__le16	supported_speeds2_auto_mode;
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_1GB                0x1UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_10GB               0x2UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_25GB               0x4UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_40GB               0x8UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB               0x10UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB              0x20UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_50GB_PAM4_56       0x40UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_56      0x80UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_56      0x100UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_56      0x200UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_100GB_PAM4_112     0x400UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_200GB_PAM4_112     0x800UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_400GB_PAM4_112     0x1000UL
+	#define PORT_PHY_QCAPS_RESP_SUPPORTED_SPEEDS2_AUTO_MODE_800GB_PAM4_112     0x2000UL
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_port_phy_i2c_write_input (size:832b/104B) */
+struct hwrm_port_phy_i2c_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_PAGE_OFFSET     0x1UL
+	#define PORT_PHY_I2C_WRITE_REQ_ENABLES_BANK_NUMBER     0x2UL
+	__le16	port_id;
+	u8	i2c_slave_addr;
+	u8	bank_number;
+	__le16	page_number;
+	__le16	page_offset;
+	u8	data_length;
+	u8	unused_1[7];
+	__le32	data[16];
+};
+
+/* hwrm_port_phy_i2c_write_output (size:128b/16B) */
+struct hwrm_port_phy_i2c_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_i2c_read_input (size:320b/40B) */
+struct hwrm_port_phy_i2c_read_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define PORT_PHY_I2C_READ_REQ_ENABLES_PAGE_OFFSET     0x1UL
+	#define PORT_PHY_I2C_READ_REQ_ENABLES_BANK_NUMBER     0x2UL
+	__le16	port_id;
+	u8	i2c_slave_addr;
+	u8	bank_number;
+	__le16	page_number;
+	__le16	page_offset;
+	u8	data_length;
+	u8	unused_1[7];
+};
+
+/* hwrm_port_phy_i2c_read_output (size:640b/80B) */
+struct hwrm_port_phy_i2c_read_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	data[16];
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_mdio_write_input (size:320b/40B) */
+struct hwrm_port_phy_mdio_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[2];
+	__le16	port_id;
+	u8	phy_addr;
+	u8	dev_addr;
+	__le16	reg_addr;
+	__le16	reg_data;
+	u8	cl45_mdio;
+	u8	unused_1[7];
+};
+
+/* hwrm_port_phy_mdio_write_output (size:128b/16B) */
+struct hwrm_port_phy_mdio_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_phy_mdio_read_input (size:256b/32B) */
+struct hwrm_port_phy_mdio_read_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[2];
+	__le16	port_id;
+	u8	phy_addr;
+	u8	dev_addr;
+	__le16	reg_addr;
+	u8	cl45_mdio;
+	u8	unused_1;
+};
+
+/* hwrm_port_phy_mdio_read_output (size:128b/16B) */
+struct hwrm_port_phy_mdio_read_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	reg_data;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_port_led_cfg_input (size:512b/64B) */
+struct hwrm_port_led_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_ID            0x1UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_STATE         0x2UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_COLOR         0x4UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_BLINK_ON      0x8UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_BLINK_OFF     0x10UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED0_GROUP_ID      0x20UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_ID            0x40UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_STATE         0x80UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_COLOR         0x100UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_BLINK_ON      0x200UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_BLINK_OFF     0x400UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED1_GROUP_ID      0x800UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_ID            0x1000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_STATE         0x2000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_COLOR         0x4000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_BLINK_ON      0x8000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_BLINK_OFF     0x10000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED2_GROUP_ID      0x20000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_ID            0x40000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_STATE         0x80000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_COLOR         0x100000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_BLINK_ON      0x200000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_BLINK_OFF     0x400000UL
+	#define PORT_LED_CFG_REQ_ENABLES_LED3_GROUP_ID      0x800000UL
+	__le16	port_id;
+	u8	num_leds;
+	u8	rsvd;
+	u8	led0_id;
+	u8	led0_state;
+	#define PORT_LED_CFG_REQ_LED0_STATE_DEFAULT  0x0UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_OFF      0x1UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_ON       0x2UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_BLINK    0x3UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_BLINKALT 0x4UL
+	#define PORT_LED_CFG_REQ_LED0_STATE_LAST    PORT_LED_CFG_REQ_LED0_STATE_BLINKALT
+	u8	led0_color;
+	#define PORT_LED_CFG_REQ_LED0_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_CFG_REQ_LED0_COLOR_AMBER      0x1UL
+	#define PORT_LED_CFG_REQ_LED0_COLOR_GREEN      0x2UL
+	#define PORT_LED_CFG_REQ_LED0_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_CFG_REQ_LED0_COLOR_LAST      PORT_LED_CFG_REQ_LED0_COLOR_GREENAMBER
+	u8	unused_0;
+	__le16	led0_blink_on;
+	__le16	led0_blink_off;
+	u8	led0_group_id;
+	u8	rsvd0;
+	u8	led1_id;
+	u8	led1_state;
+	#define PORT_LED_CFG_REQ_LED1_STATE_DEFAULT  0x0UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_OFF      0x1UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_ON       0x2UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_BLINK    0x3UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_BLINKALT 0x4UL
+	#define PORT_LED_CFG_REQ_LED1_STATE_LAST    PORT_LED_CFG_REQ_LED1_STATE_BLINKALT
+	u8	led1_color;
+	#define PORT_LED_CFG_REQ_LED1_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_CFG_REQ_LED1_COLOR_AMBER      0x1UL
+	#define PORT_LED_CFG_REQ_LED1_COLOR_GREEN      0x2UL
+	#define PORT_LED_CFG_REQ_LED1_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_CFG_REQ_LED1_COLOR_LAST      PORT_LED_CFG_REQ_LED1_COLOR_GREENAMBER
+	u8	unused_1;
+	__le16	led1_blink_on;
+	__le16	led1_blink_off;
+	u8	led1_group_id;
+	u8	rsvd1;
+	u8	led2_id;
+	u8	led2_state;
+	#define PORT_LED_CFG_REQ_LED2_STATE_DEFAULT  0x0UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_OFF      0x1UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_ON       0x2UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_BLINK    0x3UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_BLINKALT 0x4UL
+	#define PORT_LED_CFG_REQ_LED2_STATE_LAST    PORT_LED_CFG_REQ_LED2_STATE_BLINKALT
+	u8	led2_color;
+	#define PORT_LED_CFG_REQ_LED2_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_CFG_REQ_LED2_COLOR_AMBER      0x1UL
+	#define PORT_LED_CFG_REQ_LED2_COLOR_GREEN      0x2UL
+	#define PORT_LED_CFG_REQ_LED2_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_CFG_REQ_LED2_COLOR_LAST      PORT_LED_CFG_REQ_LED2_COLOR_GREENAMBER
+	u8	unused_2;
+	__le16	led2_blink_on;
+	__le16	led2_blink_off;
+	u8	led2_group_id;
+	u8	rsvd2;
+	u8	led3_id;
+	u8	led3_state;
+	#define PORT_LED_CFG_REQ_LED3_STATE_DEFAULT  0x0UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_OFF      0x1UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_ON       0x2UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_BLINK    0x3UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_BLINKALT 0x4UL
+	#define PORT_LED_CFG_REQ_LED3_STATE_LAST    PORT_LED_CFG_REQ_LED3_STATE_BLINKALT
+	u8	led3_color;
+	#define PORT_LED_CFG_REQ_LED3_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_CFG_REQ_LED3_COLOR_AMBER      0x1UL
+	#define PORT_LED_CFG_REQ_LED3_COLOR_GREEN      0x2UL
+	#define PORT_LED_CFG_REQ_LED3_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_CFG_REQ_LED3_COLOR_LAST      PORT_LED_CFG_REQ_LED3_COLOR_GREENAMBER
+	u8	unused_3;
+	__le16	led3_blink_on;
+	__le16	led3_blink_off;
+	u8	led3_group_id;
+	u8	rsvd3;
+};
+
+/* hwrm_port_led_cfg_output (size:128b/16B) */
+struct hwrm_port_led_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_port_led_qcfg_input (size:192b/24B) */
+struct hwrm_port_led_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_led_qcfg_output (size:448b/56B) */
+struct hwrm_port_led_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_leds;
+	u8	led0_id;
+	u8	led0_type;
+	#define PORT_LED_QCFG_RESP_LED0_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCFG_RESP_LED0_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCFG_RESP_LED0_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCFG_RESP_LED0_TYPE_LAST    PORT_LED_QCFG_RESP_LED0_TYPE_INVALID
+	u8	led0_state;
+	#define PORT_LED_QCFG_RESP_LED0_STATE_DEFAULT  0x0UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_OFF      0x1UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_ON       0x2UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_BLINK    0x3UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_BLINKALT 0x4UL
+	#define PORT_LED_QCFG_RESP_LED0_STATE_LAST    PORT_LED_QCFG_RESP_LED0_STATE_BLINKALT
+	u8	led0_color;
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_AMBER      0x1UL
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_GREEN      0x2UL
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_QCFG_RESP_LED0_COLOR_LAST      PORT_LED_QCFG_RESP_LED0_COLOR_GREENAMBER
+	u8	unused_0;
+	__le16	led0_blink_on;
+	__le16	led0_blink_off;
+	u8	led0_group_id;
+	u8	led1_id;
+	u8	led1_type;
+	#define PORT_LED_QCFG_RESP_LED1_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCFG_RESP_LED1_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCFG_RESP_LED1_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCFG_RESP_LED1_TYPE_LAST    PORT_LED_QCFG_RESP_LED1_TYPE_INVALID
+	u8	led1_state;
+	#define PORT_LED_QCFG_RESP_LED1_STATE_DEFAULT  0x0UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_OFF      0x1UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_ON       0x2UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_BLINK    0x3UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_BLINKALT 0x4UL
+	#define PORT_LED_QCFG_RESP_LED1_STATE_LAST    PORT_LED_QCFG_RESP_LED1_STATE_BLINKALT
+	u8	led1_color;
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_AMBER      0x1UL
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_GREEN      0x2UL
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_QCFG_RESP_LED1_COLOR_LAST      PORT_LED_QCFG_RESP_LED1_COLOR_GREENAMBER
+	u8	unused_1;
+	__le16	led1_blink_on;
+	__le16	led1_blink_off;
+	u8	led1_group_id;
+	u8	led2_id;
+	u8	led2_type;
+	#define PORT_LED_QCFG_RESP_LED2_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCFG_RESP_LED2_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCFG_RESP_LED2_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCFG_RESP_LED2_TYPE_LAST    PORT_LED_QCFG_RESP_LED2_TYPE_INVALID
+	u8	led2_state;
+	#define PORT_LED_QCFG_RESP_LED2_STATE_DEFAULT  0x0UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_OFF      0x1UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_ON       0x2UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_BLINK    0x3UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_BLINKALT 0x4UL
+	#define PORT_LED_QCFG_RESP_LED2_STATE_LAST    PORT_LED_QCFG_RESP_LED2_STATE_BLINKALT
+	u8	led2_color;
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_AMBER      0x1UL
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_GREEN      0x2UL
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_QCFG_RESP_LED2_COLOR_LAST      PORT_LED_QCFG_RESP_LED2_COLOR_GREENAMBER
+	u8	unused_2;
+	__le16	led2_blink_on;
+	__le16	led2_blink_off;
+	u8	led2_group_id;
+	u8	led3_id;
+	u8	led3_type;
+	#define PORT_LED_QCFG_RESP_LED3_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCFG_RESP_LED3_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCFG_RESP_LED3_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCFG_RESP_LED3_TYPE_LAST    PORT_LED_QCFG_RESP_LED3_TYPE_INVALID
+	u8	led3_state;
+	#define PORT_LED_QCFG_RESP_LED3_STATE_DEFAULT  0x0UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_OFF      0x1UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_ON       0x2UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_BLINK    0x3UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_BLINKALT 0x4UL
+	#define PORT_LED_QCFG_RESP_LED3_STATE_LAST    PORT_LED_QCFG_RESP_LED3_STATE_BLINKALT
+	u8	led3_color;
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_DEFAULT    0x0UL
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_AMBER      0x1UL
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_GREEN      0x2UL
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_GREENAMBER 0x3UL
+	#define PORT_LED_QCFG_RESP_LED3_COLOR_LAST      PORT_LED_QCFG_RESP_LED3_COLOR_GREENAMBER
+	u8	unused_3;
+	__le16	led3_blink_on;
+	__le16	led3_blink_off;
+	u8	led3_group_id;
+	u8	unused_4[6];
+	u8	valid;
+};
+
+/* hwrm_port_led_qcaps_input (size:192b/24B) */
+struct hwrm_port_led_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_led_qcaps_output (size:384b/48B) */
+struct hwrm_port_led_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_leds;
+	u8	unused[3];
+	u8	led0_id;
+	u8	led0_type;
+	#define PORT_LED_QCAPS_RESP_LED0_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCAPS_RESP_LED0_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED0_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCAPS_RESP_LED0_TYPE_LAST    PORT_LED_QCAPS_RESP_LED0_TYPE_INVALID
+	u8	led0_group_id;
+	u8	unused_0;
+	__le16	led0_state_caps;
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_ENABLED                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_OFF_SUPPORTED           0x2UL
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_ON_SUPPORTED            0x4UL
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_SUPPORTED         0x8UL
+	#define PORT_LED_QCAPS_RESP_LED0_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
+	__le16	led0_color_caps;
+	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_RSVD                0x1UL
+	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
+	#define PORT_LED_QCAPS_RESP_LED0_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
+	u8	led1_id;
+	u8	led1_type;
+	#define PORT_LED_QCAPS_RESP_LED1_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCAPS_RESP_LED1_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED1_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCAPS_RESP_LED1_TYPE_LAST    PORT_LED_QCAPS_RESP_LED1_TYPE_INVALID
+	u8	led1_group_id;
+	u8	unused_1;
+	__le16	led1_state_caps;
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_ENABLED                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_OFF_SUPPORTED           0x2UL
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_ON_SUPPORTED            0x4UL
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_SUPPORTED         0x8UL
+	#define PORT_LED_QCAPS_RESP_LED1_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
+	__le16	led1_color_caps;
+	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_RSVD                0x1UL
+	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
+	#define PORT_LED_QCAPS_RESP_LED1_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
+	u8	led2_id;
+	u8	led2_type;
+	#define PORT_LED_QCAPS_RESP_LED2_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCAPS_RESP_LED2_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED2_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCAPS_RESP_LED2_TYPE_LAST    PORT_LED_QCAPS_RESP_LED2_TYPE_INVALID
+	u8	led2_group_id;
+	u8	unused_2;
+	__le16	led2_state_caps;
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_ENABLED                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_OFF_SUPPORTED           0x2UL
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_ON_SUPPORTED            0x4UL
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_SUPPORTED         0x8UL
+	#define PORT_LED_QCAPS_RESP_LED2_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
+	__le16	led2_color_caps;
+	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_RSVD                0x1UL
+	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
+	#define PORT_LED_QCAPS_RESP_LED2_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
+	u8	led3_id;
+	u8	led3_type;
+	#define PORT_LED_QCAPS_RESP_LED3_TYPE_SPEED    0x0UL
+	#define PORT_LED_QCAPS_RESP_LED3_TYPE_ACTIVITY 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED3_TYPE_INVALID  0xffUL
+	#define PORT_LED_QCAPS_RESP_LED3_TYPE_LAST    PORT_LED_QCAPS_RESP_LED3_TYPE_INVALID
+	u8	led3_group_id;
+	u8	unused_3;
+	__le16	led3_state_caps;
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_ENABLED                 0x1UL
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_OFF_SUPPORTED           0x2UL
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_ON_SUPPORTED            0x4UL
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_SUPPORTED         0x8UL
+	#define PORT_LED_QCAPS_RESP_LED3_STATE_CAPS_BLINK_ALT_SUPPORTED     0x10UL
+	__le16	led3_color_caps;
+	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_RSVD                0x1UL
+	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_AMBER_SUPPORTED     0x2UL
+	#define PORT_LED_QCAPS_RESP_LED3_COLOR_CAPS_GREEN_SUPPORTED     0x4UL
+	u8	unused_4[3];
+	u8	valid;
+};
+
+/* hwrm_port_mac_qcaps_input (size:192b/24B) */
+struct hwrm_port_mac_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_port_mac_qcaps_output (size:128b/16B) */
+struct hwrm_port_mac_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define PORT_MAC_QCAPS_RESP_FLAGS_LOCAL_LPBK_NOT_SUPPORTED     0x1UL
+	#define PORT_MAC_QCAPS_RESP_FLAGS_REMOTE_LPBK_SUPPORTED        0x2UL
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_queue_qportcfg_input (size:192b/24B) */
+struct hwrm_queue_qportcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH     0x1UL
+	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_TX    0x0UL
+	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_RX    0x1UL
+	#define QUEUE_QPORTCFG_REQ_FLAGS_PATH_LAST QUEUE_QPORTCFG_REQ_FLAGS_PATH_RX
+	__le16	port_id;
+	u8	drv_qmap_cap;
+	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_DISABLED 0x0UL
+	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_ENABLED  0x1UL
+	#define QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_LAST    QUEUE_QPORTCFG_REQ_DRV_QMAP_CAP_ENABLED
+	u8	unused_0;
+};
+
+/* hwrm_queue_qportcfg_output (size:1344b/168B) */
+struct hwrm_queue_qportcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	max_configurable_queues;
+	u8	max_configurable_lossless_queues;
+	u8	queue_cfg_allowed;
+	u8	queue_cfg_info;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG             0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_CFG_INFO_USE_PROFILE_TYPE     0x2UL
+	u8	queue_pfcenable_cfg_allowed;
+	u8	queue_pri2cos_cfg_allowed;
+	u8	queue_cos2bw_cfg_allowed;
+	u8	queue_id0;
+	u8	queue_id0_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id1;
+	u8	queue_id1_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id2;
+	u8	queue_id2_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id3;
+	u8	queue_id3_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id4;
+	u8	queue_id4_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id5;
+	u8	queue_id5_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id6;
+	u8	queue_id6_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id7;
+	u8	queue_id7_service_profile;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY          0x0UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS       0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_ROCE  0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSY_ROCE_CNP 0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LOSSLESS_NIC   0x3UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN        0xffUL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_LAST          QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_UNKNOWN
+	u8	queue_id0_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID0_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	char	qid0_name[16];
+	char	qid1_name[16];
+	char	qid2_name[16];
+	char	qid3_name[16];
+	char	qid4_name[16];
+	char	qid5_name[16];
+	char	qid6_name[16];
+	char	qid7_name[16];
+	u8	queue_id1_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID1_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id2_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID2_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id3_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID3_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id4_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID4_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id5_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID5_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id6_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID6_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	queue_id7_service_profile_type;
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_ROCE     0x1UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_NIC      0x2UL
+	#define QUEUE_QPORTCFG_RESP_QUEUE_ID7_SERVICE_PROFILE_TYPE_CNP      0x4UL
+	u8	valid;
+};
+
+/* hwrm_queue_qcfg_input (size:192b/24B) */
+struct hwrm_queue_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_QCFG_REQ_FLAGS_PATH     0x1UL
+	#define QUEUE_QCFG_REQ_FLAGS_PATH_TX    0x0UL
+	#define QUEUE_QCFG_REQ_FLAGS_PATH_RX    0x1UL
+	#define QUEUE_QCFG_REQ_FLAGS_PATH_LAST QUEUE_QCFG_REQ_FLAGS_PATH_RX
+	__le32	queue_id;
+};
+
+/* hwrm_queue_qcfg_output (size:128b/16B) */
+struct hwrm_queue_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	queue_len;
+	u8	service_profile;
+	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSY    0x0UL
+	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LOSSLESS 0x1UL
+	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN  0xffUL
+	#define QUEUE_QCFG_RESP_SERVICE_PROFILE_LAST    QUEUE_QCFG_RESP_SERVICE_PROFILE_UNKNOWN
+	u8	queue_cfg_info;
+	#define QUEUE_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG     0x1UL
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_queue_cfg_input (size:320b/40B) */
+struct hwrm_queue_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_CFG_REQ_FLAGS_PATH_MASK 0x3UL
+	#define QUEUE_CFG_REQ_FLAGS_PATH_SFT  0
+	#define QUEUE_CFG_REQ_FLAGS_PATH_TX     0x0UL
+	#define QUEUE_CFG_REQ_FLAGS_PATH_RX     0x1UL
+	#define QUEUE_CFG_REQ_FLAGS_PATH_BIDIR  0x2UL
+	#define QUEUE_CFG_REQ_FLAGS_PATH_LAST  QUEUE_CFG_REQ_FLAGS_PATH_BIDIR
+	__le32	enables;
+	#define QUEUE_CFG_REQ_ENABLES_DFLT_LEN            0x1UL
+	#define QUEUE_CFG_REQ_ENABLES_SERVICE_PROFILE     0x2UL
+	__le32	queue_id;
+	__le32	dflt_len;
+	u8	service_profile;
+	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSY    0x0UL
+	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSLESS 0x1UL
+	#define QUEUE_CFG_REQ_SERVICE_PROFILE_UNKNOWN  0xffUL
+	#define QUEUE_CFG_REQ_SERVICE_PROFILE_LAST    QUEUE_CFG_REQ_SERVICE_PROFILE_UNKNOWN
+	u8	unused_0[7];
+};
+
+/* hwrm_queue_cfg_output (size:128b/16B) */
+struct hwrm_queue_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_pfcenable_qcfg_input (size:192b/24B) */
+struct hwrm_queue_pfcenable_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_queue_pfcenable_qcfg_output (size:128b/16B) */
+struct hwrm_queue_pfcenable_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_ENABLED              0x1UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_ENABLED              0x2UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_ENABLED              0x4UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_ENABLED              0x8UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_ENABLED              0x10UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_ENABLED              0x20UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_ENABLED              0x40UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_ENABLED              0x80UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
+	#define QUEUE_PFCENABLE_QCFG_RESP_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_queue_pfcenable_cfg_input (size:192b/24B) */
+struct hwrm_queue_pfcenable_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_ENABLED              0x1UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_ENABLED              0x2UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_ENABLED              0x4UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_ENABLED              0x8UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_ENABLED              0x10UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_ENABLED              0x20UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_ENABLED              0x40UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_ENABLED              0x80UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI0_PFC_WATCHDOG_ENABLED     0x100UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI1_PFC_WATCHDOG_ENABLED     0x200UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI2_PFC_WATCHDOG_ENABLED     0x400UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI3_PFC_WATCHDOG_ENABLED     0x800UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI4_PFC_WATCHDOG_ENABLED     0x1000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI5_PFC_WATCHDOG_ENABLED     0x2000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI6_PFC_WATCHDOG_ENABLED     0x4000UL
+	#define QUEUE_PFCENABLE_CFG_REQ_FLAGS_PRI7_PFC_WATCHDOG_ENABLED     0x8000UL
+	__le16	port_id;
+	u8	unused_0[2];
+};
+
+/* hwrm_queue_pfcenable_cfg_output (size:128b/16B) */
+struct hwrm_queue_pfcenable_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_pri2cos_qcfg_input (size:192b/24B) */
+struct hwrm_queue_pri2cos_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH      0x1UL
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_TX     0x0UL
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_RX     0x1UL
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_LAST  QUEUE_PRI2COS_QCFG_REQ_FLAGS_PATH_RX
+	#define QUEUE_PRI2COS_QCFG_REQ_FLAGS_IVLAN     0x2UL
+	u8	port_id;
+	u8	unused_0[3];
+};
+
+/* hwrm_queue_pri2cos_qcfg_output (size:192b/24B) */
+struct hwrm_queue_pri2cos_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	pri0_cos_queue_id;
+	u8	pri1_cos_queue_id;
+	u8	pri2_cos_queue_id;
+	u8	pri3_cos_queue_id;
+	u8	pri4_cos_queue_id;
+	u8	pri5_cos_queue_id;
+	u8	pri6_cos_queue_id;
+	u8	pri7_cos_queue_id;
+	u8	queue_cfg_info;
+	#define QUEUE_PRI2COS_QCFG_RESP_QUEUE_CFG_INFO_ASYM_CFG     0x1UL
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_queue_pri2cos_cfg_input (size:320b/40B) */
+struct hwrm_queue_pri2cos_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_MASK 0x3UL
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_SFT  0
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_TX     0x0UL
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_RX     0x1UL
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR  0x2UL
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_LAST  QUEUE_PRI2COS_CFG_REQ_FLAGS_PATH_BIDIR
+	#define QUEUE_PRI2COS_CFG_REQ_FLAGS_IVLAN     0x4UL
+	__le32	enables;
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI0_COS_QUEUE_ID     0x1UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI1_COS_QUEUE_ID     0x2UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI2_COS_QUEUE_ID     0x4UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI3_COS_QUEUE_ID     0x8UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI4_COS_QUEUE_ID     0x10UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI5_COS_QUEUE_ID     0x20UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI6_COS_QUEUE_ID     0x40UL
+	#define QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI7_COS_QUEUE_ID     0x80UL
+	u8	port_id;
+	u8	pri0_cos_queue_id;
+	u8	pri1_cos_queue_id;
+	u8	pri2_cos_queue_id;
+	u8	pri3_cos_queue_id;
+	u8	pri4_cos_queue_id;
+	u8	pri5_cos_queue_id;
+	u8	pri6_cos_queue_id;
+	u8	pri7_cos_queue_id;
+	u8	unused_0[7];
+};
+
+/* hwrm_queue_pri2cos_cfg_output (size:128b/16B) */
+struct hwrm_queue_pri2cos_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_cos2bw_qcfg_input (size:192b/24B) */
+struct hwrm_queue_cos2bw_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_queue_cos2bw_qcfg_output (size:896b/112B) */
+struct hwrm_queue_cos2bw_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	queue_id0;
+	u8	unused_0;
+	__le16	unused_1;
+	__le32	queue_id0_min_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID
+	__le32	queue_id0_max_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID
+	u8	queue_id0_tsa_assign;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
+	u8	queue_id0_pri_lvl;
+	u8	queue_id0_bw_weight;
+	struct {
+		u8	queue_id;
+		__le32	queue_id_min_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
+		__le32	queue_id_max_bw;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
+		u8	queue_id_tsa_assign;
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_QCFG_RESP_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
+		u8	queue_id_pri_lvl;
+		u8	queue_id_bw_weight;
+	} __packed cfg[7];
+	u8	unused_2[4];
+	u8	valid;
+};
+
+/* hwrm_queue_cos2bw_cfg_input (size:1024b/128B) */
+struct hwrm_queue_cos2bw_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID     0x1UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID1_VALID     0x2UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID2_VALID     0x4UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID3_VALID     0x8UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID4_VALID     0x10UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID5_VALID     0x20UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID6_VALID     0x40UL
+	#define QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID7_VALID     0x80UL
+	__le16	port_id;
+	u8	queue_id0;
+	u8	unused_0;
+	__le32	queue_id0_min_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MIN_BW_BW_VALUE_UNIT_INVALID
+	__le32	queue_id0_max_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_MAX_BW_BW_VALUE_UNIT_INVALID
+	u8	queue_id0_tsa_assign;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID0_TSA_ASSIGN_RESERVED_LAST  0xffUL
+	u8	queue_id0_pri_lvl;
+	u8	queue_id0_bw_weight;
+	struct {
+		u8	queue_id;
+		__le32	queue_id_min_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MIN_BW_BW_VALUE_UNIT_INVALID
+		__le32	queue_id_max_bw;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_SFT              0
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE                     0x10000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_LAST                 QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_SCALE_BYTES
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_LAST         QUEUE_COS2BW_CFG_REQ_QUEUE_ID_MAX_BW_BW_VALUE_UNIT_INVALID
+		u8	queue_id_tsa_assign;
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_SP             0x0UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_ETS            0x1UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_FIRST 0x2UL
+	#define QUEUE_COS2BW_CFG_REQ_QUEUE_ID_TSA_ASSIGN_RESERVED_LAST  0xffUL
+		u8	queue_id_pri_lvl;
+		u8	queue_id_bw_weight;
+	} __packed cfg[7];
+	u8	unused_1[5];
+};
+
+/* hwrm_queue_cos2bw_cfg_output (size:128b/16B) */
+struct hwrm_queue_cos2bw_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_queue_dscp_qcaps_input (size:192b/24B) */
+struct hwrm_queue_dscp_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	port_id;
+	u8	unused_0[7];
+};
+
+/* hwrm_queue_dscp_qcaps_output (size:128b/16B) */
+struct hwrm_queue_dscp_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_dscp_bits;
+	u8	unused_0;
+	__le16	max_entries;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_queue_dscp2pri_qcfg_input (size:256b/32B) */
+struct hwrm_queue_dscp2pri_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	dest_data_addr;
+	u8	port_id;
+	u8	unused_0;
+	__le16	dest_data_buffer_size;
+	u8	unused_1[4];
+};
+
+/* hwrm_queue_dscp2pri_qcfg_output (size:128b/16B) */
+struct hwrm_queue_dscp2pri_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	entry_cnt;
+	u8	default_pri;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* hwrm_queue_dscp2pri_cfg_input (size:320b/40B) */
+struct hwrm_queue_dscp2pri_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	src_data_addr;
+	__le32	flags;
+	#define QUEUE_DSCP2PRI_CFG_REQ_FLAGS_USE_HW_DEFAULT_PRI     0x1UL
+	__le32	enables;
+	#define QUEUE_DSCP2PRI_CFG_REQ_ENABLES_DEFAULT_PRI     0x1UL
+	u8	port_id;
+	u8	default_pri;
+	__le16	entry_cnt;
+	u8	unused_0[4];
+};
+
+/* hwrm_queue_dscp2pri_cfg_output (size:128b/16B) */
+struct hwrm_queue_dscp2pri_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_alloc_input (size:192b/24B) */
+struct hwrm_vnic_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define VNIC_ALLOC_REQ_FLAGS_DEFAULT                  0x1UL
+	#define VNIC_ALLOC_REQ_FLAGS_VIRTIO_NET_FID_VALID     0x2UL
+	#define VNIC_ALLOC_REQ_FLAGS_VNIC_ID_VALID            0x4UL
+	__le16	virtio_net_fid;
+	__le16	vnic_id;
+};
+
+/* hwrm_vnic_alloc_output (size:128b/16B) */
+struct hwrm_vnic_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	vnic_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_vnic_update_input (size:256b/32B) */
+struct hwrm_vnic_update_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	vnic_id;
+	__le32	enables;
+	#define VNIC_UPDATE_REQ_ENABLES_VNIC_STATE_VALID               0x1UL
+	#define VNIC_UPDATE_REQ_ENABLES_MRU_VALID                      0x2UL
+	#define VNIC_UPDATE_REQ_ENABLES_METADATA_FORMAT_TYPE_VALID     0x4UL
+	u8	vnic_state;
+	#define VNIC_UPDATE_REQ_VNIC_STATE_NORMAL 0x0UL
+	#define VNIC_UPDATE_REQ_VNIC_STATE_DROP   0x1UL
+	#define VNIC_UPDATE_REQ_VNIC_STATE_LAST  VNIC_UPDATE_REQ_VNIC_STATE_DROP
+	u8	metadata_format_type;
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_0 0x0UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_1 0x1UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_2 0x2UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_3 0x3UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4 0x4UL
+	#define VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_LAST VNIC_UPDATE_REQ_METADATA_FORMAT_TYPE_4
+	__le16	mru;
+	u8	unused_1[4];
+};
+
+/* hwrm_vnic_update_output (size:128b/16B) */
+struct hwrm_vnic_update_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_free_input (size:192b/24B) */
+struct hwrm_vnic_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	vnic_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_vnic_free_output (size:128b/16B) */
+struct hwrm_vnic_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_cfg_input (size:384b/48B) */
+struct hwrm_vnic_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define VNIC_CFG_REQ_FLAGS_DEFAULT                              0x1UL
+	#define VNIC_CFG_REQ_FLAGS_VLAN_STRIP_MODE                      0x2UL
+	#define VNIC_CFG_REQ_FLAGS_BD_STALL_MODE                        0x4UL
+	#define VNIC_CFG_REQ_FLAGS_ROCE_DUAL_VNIC_MODE                  0x8UL
+	#define VNIC_CFG_REQ_FLAGS_ROCE_ONLY_VNIC_MODE                  0x10UL
+	#define VNIC_CFG_REQ_FLAGS_RSS_DFLT_CR_MODE                     0x20UL
+	#define VNIC_CFG_REQ_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_MODE     0x40UL
+	#define VNIC_CFG_REQ_FLAGS_PORTCOS_MAPPING_MODE                 0x80UL
+	__le32	enables;
+	#define VNIC_CFG_REQ_ENABLES_DFLT_RING_GRP            0x1UL
+	#define VNIC_CFG_REQ_ENABLES_RSS_RULE                 0x2UL
+	#define VNIC_CFG_REQ_ENABLES_COS_RULE                 0x4UL
+	#define VNIC_CFG_REQ_ENABLES_LB_RULE                  0x8UL
+	#define VNIC_CFG_REQ_ENABLES_MRU                      0x10UL
+	#define VNIC_CFG_REQ_ENABLES_DEFAULT_RX_RING_ID       0x20UL
+	#define VNIC_CFG_REQ_ENABLES_DEFAULT_CMPL_RING_ID     0x40UL
+	#define VNIC_CFG_REQ_ENABLES_QUEUE_ID                 0x80UL
+	#define VNIC_CFG_REQ_ENABLES_RX_CSUM_V2_MODE          0x100UL
+	#define VNIC_CFG_REQ_ENABLES_L2_CQE_MODE              0x200UL
+	#define VNIC_CFG_REQ_ENABLES_RAW_QP_ID                0x400UL
+	__le16	vnic_id;
+	__le16	dflt_ring_grp;
+	__le16	rss_rule;
+	__le16	cos_rule;
+	__le16	lb_rule;
+	__le16	mru;
+	__le16	default_rx_ring_id;
+	__le16	default_cmpl_ring_id;
+	__le16	queue_id;
+	u8	rx_csum_v2_mode;
+	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_DEFAULT 0x0UL
+	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_ALL_OK  0x1UL
+	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX     0x2UL
+	#define VNIC_CFG_REQ_RX_CSUM_V2_MODE_LAST   VNIC_CFG_REQ_RX_CSUM_V2_MODE_MAX
+	u8	l2_cqe_mode;
+	#define VNIC_CFG_REQ_L2_CQE_MODE_DEFAULT    0x0UL
+	#define VNIC_CFG_REQ_L2_CQE_MODE_COMPRESSED 0x1UL
+	#define VNIC_CFG_REQ_L2_CQE_MODE_MIXED      0x2UL
+	#define VNIC_CFG_REQ_L2_CQE_MODE_LAST      VNIC_CFG_REQ_L2_CQE_MODE_MIXED
+	__le32	raw_qp_id;
+};
+
+/* hwrm_vnic_cfg_output (size:128b/16B) */
+struct hwrm_vnic_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_qcaps_input (size:192b/24B) */
+struct hwrm_vnic_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	u8	unused_0[4];
+};
+
+/* hwrm_vnic_qcaps_output (size:192b/24B) */
+struct hwrm_vnic_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	mru;
+	u8	unused_0[2];
+	__le32	flags;
+	#define VNIC_QCAPS_RESP_FLAGS_UNUSED                                  0x1UL
+	#define VNIC_QCAPS_RESP_FLAGS_VLAN_STRIP_CAP                          0x2UL
+	#define VNIC_QCAPS_RESP_FLAGS_BD_STALL_CAP                            0x4UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_DUAL_VNIC_CAP                      0x8UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_ONLY_VNIC_CAP                      0x10UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_DFLT_CR_CAP                         0x20UL
+	#define VNIC_QCAPS_RESP_FLAGS_ROCE_MIRRORING_CAPABLE_VNIC_CAP         0x40UL
+	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_CAP                       0x80UL
+	#define VNIC_QCAPS_RESP_FLAGS_COS_ASSIGNMENT_CAP                      0x100UL
+	#define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V2_CAP                          0x200UL
+	#define VNIC_QCAPS_RESP_FLAGS_VNIC_STATE_CAP                          0x400UL
+	#define VNIC_QCAPS_RESP_FLAGS_VIRTIO_NET_VNIC_ALLOC_CAP               0x800UL
+	#define VNIC_QCAPS_RESP_FLAGS_METADATA_FORMAT_CAP                     0x1000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_STRICT_HASH_TYPE_CAP                0x2000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_HASH_TYPE_DELTA_CAP                 0x4000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_TOEPLITZ_CAP           0x8000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_XOR_CAP                0x10000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RING_SELECT_MODE_TOEPLITZ_CHKSM_CAP     0x20000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPV6_FLOW_LABEL_CAP                 0x40000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RX_CMPL_V3_CAP                          0x80000UL
+	#define VNIC_QCAPS_RESP_FLAGS_L2_CQE_MODE_CAP                         0x100000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV4_CAP               0x200000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV4_CAP              0x400000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_AH_SPI_IPV6_CAP               0x800000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_IPSEC_ESP_SPI_IPV6_CAP              0x1000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_OUTERMOST_RSS_TRUSTED_VF_CAP            0x2000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_PORTCOS_MAPPING_MODE                    0x4000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RSS_PROF_TCAM_MODE_ENABLED              0x8000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_VNIC_RSS_HASH_MODE_CAP                  0x10000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_HW_TUNNEL_TPA_CAP                       0x20000000UL
+	#define VNIC_QCAPS_RESP_FLAGS_RE_FLUSH_CAP                            0x40000000UL
+	__le16	max_aggs_supported;
+	u8	unused_1[5];
+	u8	valid;
+};
+
+/* hwrm_vnic_tpa_cfg_input (size:384b/48B) */
+struct hwrm_vnic_tpa_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define VNIC_TPA_CFG_REQ_FLAGS_TPA                       0x1UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_ENCAP_TPA                 0x2UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_RSC_WND_UPDATE            0x4UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_GRO                       0x8UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_ECN              0x10UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_IPID_CHECK            0x40UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_GRO_TTL_CHECK             0x80UL
+	#define VNIC_TPA_CFG_REQ_FLAGS_AGG_PACK_AS_GRO           0x100UL
+	__le32	enables;
+	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_SEGS      0x1UL
+	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGGS          0x2UL
+	#define VNIC_TPA_CFG_REQ_ENABLES_MAX_AGG_TIMER     0x4UL
+	#define VNIC_TPA_CFG_REQ_ENABLES_MIN_AGG_LEN       0x8UL
+	#define VNIC_TPA_CFG_REQ_ENABLES_TNL_TPA_EN        0x10UL
+	__le16	vnic_id;
+	__le16	max_agg_segs;
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_1   0x0UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_2   0x1UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_4   0x2UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_8   0x3UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_MAX 0x1fUL
+	#define VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_LAST VNIC_TPA_CFG_REQ_MAX_AGG_SEGS_MAX
+	__le16	max_aggs;
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_1   0x0UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_2   0x1UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_4   0x2UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_8   0x3UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_16  0x4UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_MAX 0x7UL
+	#define VNIC_TPA_CFG_REQ_MAX_AGGS_LAST VNIC_TPA_CFG_REQ_MAX_AGGS_MAX
+	u8	unused_0[2];
+	__le32	max_agg_timer;
+	__le32	min_agg_len;
+	__le32	tnl_tpa_en_bitmap;
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN           0x1UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GENEVE          0x2UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_NVGRE           0x4UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE             0x8UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV4            0x10UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_IPV6            0x20UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_GPE       0x40UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_VXLAN_CUST1     0x80UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_GRE_CUST1       0x100UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR1           0x200UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR2           0x400UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR3           0x800UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR4           0x1000UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR5           0x2000UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR6           0x4000UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR7           0x8000UL
+	#define VNIC_TPA_CFG_REQ_TNL_TPA_EN_BITMAP_UPAR8           0x10000UL
+	u8	unused_1[4];
+};
+
+/* hwrm_vnic_tpa_cfg_output (size:128b/16B) */
+struct hwrm_vnic_tpa_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_tpa_qcfg_input (size:192b/24B) */
+struct hwrm_vnic_tpa_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	vnic_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_vnic_tpa_qcfg_output (size:256b/32B) */
+struct hwrm_vnic_tpa_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define VNIC_TPA_QCFG_RESP_FLAGS_TPA                       0x1UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_ENCAP_TPA                 0x2UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_RSC_WND_UPDATE            0x4UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO                       0x8UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_AGG_WITH_ECN              0x10UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_AGG_WITH_SAME_GRE_SEQ     0x20UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO_IPID_CHECK            0x40UL
+	#define VNIC_TPA_QCFG_RESP_FLAGS_GRO_TTL_CHECK             0x80UL
+	__le16	max_agg_segs;
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_1   0x0UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_2   0x1UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_4   0x2UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_8   0x3UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_MAX 0x1fUL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_LAST VNIC_TPA_QCFG_RESP_MAX_AGG_SEGS_MAX
+	__le16	max_aggs;
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_1   0x0UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_2   0x1UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_4   0x2UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_8   0x3UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_16  0x4UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_MAX 0x7UL
+	#define VNIC_TPA_QCFG_RESP_MAX_AGGS_LAST VNIC_TPA_QCFG_RESP_MAX_AGGS_MAX
+	__le32	max_agg_timer;
+	__le32	min_agg_len;
+	__le32	tnl_tpa_en_bitmap;
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN           0x1UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GENEVE          0x2UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_NVGRE           0x4UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GRE             0x8UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_IPV4            0x10UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_IPV6            0x20UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN_GPE       0x40UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_VXLAN_CUST1     0x80UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_GRE_CUST1       0x100UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR1           0x200UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR2           0x400UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR3           0x800UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR4           0x1000UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR5           0x2000UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR6           0x4000UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR7           0x8000UL
+	#define VNIC_TPA_QCFG_RESP_TNL_TPA_EN_BITMAP_UPAR8           0x10000UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_vnic_rss_cfg_input (size:384b/48B) */
+struct hwrm_vnic_rss_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	hash_type;
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV4                0x1UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV4            0x2UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV4            0x4UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6                0x8UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_TCP_IPV6            0x10UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_UDP_IPV6            0x20UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_IPV6_FLOW_LABEL     0x40UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV4         0x80UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV4        0x100UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_AH_SPI_IPV6         0x200UL
+	#define VNIC_RSS_CFG_REQ_HASH_TYPE_ESP_SPI_IPV6        0x400UL
+	__le16	vnic_id;
+	u8	ring_table_pair_index;
+	u8	hash_mode_flags;
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_DEFAULT         0x1UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
+	#define VNIC_RSS_CFG_REQ_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
+	__le64	ring_grp_tbl_addr;
+	__le64	hash_key_tbl_addr;
+	__le16	rss_ctx_idx;
+	u8	flags;
+	#define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_INCLUDE               0x1UL
+	#define VNIC_RSS_CFG_REQ_FLAGS_HASH_TYPE_EXCLUDE               0x2UL
+	#define VNIC_RSS_CFG_REQ_FLAGS_IPSEC_HASH_TYPE_CFG_SUPPORT     0x4UL
+	u8	ring_select_mode;
+	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ          0x0UL
+	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_XOR               0x1UL
+	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL
+	#define VNIC_RSS_CFG_REQ_RING_SELECT_MODE_LAST             VNIC_RSS_CFG_REQ_RING_SELECT_MODE_TOEPLITZ_CHECKSUM
+	u8	unused_1[4];
+};
+
+/* hwrm_vnic_rss_cfg_output (size:128b/16B) */
+struct hwrm_vnic_rss_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_rss_cfg_cmd_err (size:64b/8B) */
+struct hwrm_vnic_rss_cfg_cmd_err {
+	u8	code;
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_UNKNOWN             0x0UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY 0x1UL
+	#define VNIC_RSS_CFG_CMD_ERR_CODE_LAST               VNIC_RSS_CFG_CMD_ERR_CODE_INTERFACE_NOT_READY
+	u8	unused_0[7];
+};
+
+/* hwrm_vnic_rss_qcfg_input (size:192b/24B) */
+struct hwrm_vnic_rss_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	rss_ctx_idx;
+	__le16	vnic_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_vnic_rss_qcfg_output (size:512b/64B) */
+struct hwrm_vnic_rss_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	hash_type;
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV4                0x1UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV4            0x2UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV4            0x4UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6                0x8UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_TCP_IPV6            0x10UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_UDP_IPV6            0x20UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_IPV6_FLOW_LABEL     0x40UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV4         0x80UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV4        0x100UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_AH_SPI_IPV6         0x200UL
+	#define VNIC_RSS_QCFG_RESP_HASH_TYPE_ESP_SPI_IPV6        0x400UL
+	u8	unused_0[4];
+	__le32	hash_key[10];
+	u8	hash_mode_flags;
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_DEFAULT         0x1UL
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_4     0x2UL
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_INNERMOST_2     0x4UL
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_4     0x8UL
+	#define VNIC_RSS_QCFG_RESP_HASH_MODE_FLAGS_OUTERMOST_2     0x10UL
+	u8	ring_select_mode;
+	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ          0x0UL
+	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_XOR               0x1UL
+	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM 0x2UL
+	#define VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_LAST             VNIC_RSS_QCFG_RESP_RING_SELECT_MODE_TOEPLITZ_CHECKSUM
+	u8	unused_1[5];
+	u8	valid;
+};
+
+/* hwrm_vnic_plcmodes_cfg_input (size:320b/40B) */
+struct hwrm_vnic_plcmodes_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_REGULAR_PLACEMENT     0x1UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_JUMBO_PLACEMENT       0x2UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV4              0x4UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_IPV6              0x8UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_FCOE              0x10UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_HDS_ROCE              0x20UL
+	#define VNIC_PLCMODES_CFG_REQ_FLAGS_VIRTIO_PLACEMENT      0x40UL
+	__le32	enables;
+	#define VNIC_PLCMODES_CFG_REQ_ENABLES_JUMBO_THRESH_VALID      0x1UL
+	#define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_OFFSET_VALID        0x2UL
+	#define VNIC_PLCMODES_CFG_REQ_ENABLES_HDS_THRESHOLD_VALID     0x4UL
+	#define VNIC_PLCMODES_CFG_REQ_ENABLES_MAX_BDS_VALID           0x8UL
+	__le32	vnic_id;
+	__le16	jumbo_thresh;
+	__le16	hds_offset;
+	__le16	hds_threshold;
+	__le16	max_bds;
+	u8	unused_0[4];
+};
+
+/* hwrm_vnic_plcmodes_cfg_output (size:128b/16B) */
+struct hwrm_vnic_plcmodes_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vnic_plcmodes_cfg_cmd_err (size:64b/8B) */
+struct hwrm_vnic_plcmodes_cfg_cmd_err {
+	u8	code;
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_UNKNOWN               0x0UL
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD 0x1UL
+	#define VNIC_PLCMODES_CFG_CMD_ERR_CODE_LAST                 VNIC_PLCMODES_CFG_CMD_ERR_CODE_INVALID_HDS_THRESHOLD
+	u8	unused_0[7];
+};
+
+/* hwrm_vnic_rss_cos_lb_ctx_alloc_input (size:128b/16B) */
+struct hwrm_vnic_rss_cos_lb_ctx_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_vnic_rss_cos_lb_ctx_alloc_output (size:128b/16B) */
+struct hwrm_vnic_rss_cos_lb_ctx_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	rss_cos_lb_ctx_id;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_vnic_rss_cos_lb_ctx_free_input (size:192b/24B) */
+struct hwrm_vnic_rss_cos_lb_ctx_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	rss_cos_lb_ctx_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_vnic_rss_cos_lb_ctx_free_output (size:128b/16B) */
+struct hwrm_vnic_rss_cos_lb_ctx_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_ring_alloc_input (size:704b/88B) */
+struct hwrm_ring_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define RING_ALLOC_REQ_ENABLES_RING_ARB_CFG              0x2UL
+	#define RING_ALLOC_REQ_ENABLES_STAT_CTX_ID_VALID         0x8UL
+	#define RING_ALLOC_REQ_ENABLES_MAX_BW_VALID              0x20UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RING_ID_VALID          0x40UL
+	#define RING_ALLOC_REQ_ENABLES_NQ_RING_ID_VALID          0x80UL
+	#define RING_ALLOC_REQ_ENABLES_RX_BUF_SIZE_VALID         0x100UL
+	#define RING_ALLOC_REQ_ENABLES_SCHQ_ID                   0x200UL
+	#define RING_ALLOC_REQ_ENABLES_MPC_CHNLS_TYPE            0x400UL
+	#define RING_ALLOC_REQ_ENABLES_STEERING_TAG_VALID        0x800UL
+	#define RING_ALLOC_REQ_ENABLES_RX_RATE_PROFILE_VALID     0x1000UL
+	u8	ring_type;
+	#define RING_ALLOC_REQ_RING_TYPE_L2_CMPL   0x0UL
+	#define RING_ALLOC_REQ_RING_TYPE_TX        0x1UL
+	#define RING_ALLOC_REQ_RING_TYPE_RX        0x2UL
+	#define RING_ALLOC_REQ_RING_TYPE_ROCE_CMPL 0x3UL
+	#define RING_ALLOC_REQ_RING_TYPE_RX_AGG    0x4UL
+	#define RING_ALLOC_REQ_RING_TYPE_NQ        0x5UL
+	#define RING_ALLOC_REQ_RING_TYPE_LAST     RING_ALLOC_REQ_RING_TYPE_NQ
+	u8	cmpl_coal_cnt;
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_OFF 0x0UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_4   0x1UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_8   0x2UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_12  0x3UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_16  0x4UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_24  0x5UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_32  0x6UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_48  0x7UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_64  0x8UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_96  0x9UL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_128 0xaUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_192 0xbUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_256 0xcUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_320 0xdUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_384 0xeUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX 0xfUL
+	#define RING_ALLOC_REQ_CMPL_COAL_CNT_LAST    RING_ALLOC_REQ_CMPL_COAL_CNT_COAL_MAX
+	__le16	flags;
+	#define RING_ALLOC_REQ_FLAGS_RX_SOP_PAD                        0x1UL
+	#define RING_ALLOC_REQ_FLAGS_DISABLE_CQ_OVERFLOW_DETECTION     0x2UL
+	#define RING_ALLOC_REQ_FLAGS_NQ_DBR_PACING                     0x4UL
+	#define RING_ALLOC_REQ_FLAGS_TX_PKT_TS_CMPL_ENABLE             0x8UL
+	__le64	page_tbl_addr;
+	__le32	fbo;
+	u8	page_size;
+	u8	page_tbl_depth;
+	__le16	schq_id;
+	__le32	length;
+	__le16	logical_id;
+	__le16	cmpl_ring_id;
+	__le16	queue_id;
+	__le16	rx_buf_size;
+	__le16	rx_ring_id;
+	__le16	nq_ring_id;
+	__le16	ring_arb_cfg;
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_MASK      0xfUL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SFT       0
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_SP          0x1UL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_WFQ         0x2UL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_LAST       RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_WFQ
+	#define RING_ALLOC_REQ_RING_ARB_CFG_RSVD_MASK            0xf0UL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_RSVD_SFT             4
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_PARAM_MASK 0xff00UL
+	#define RING_ALLOC_REQ_RING_ARB_CFG_ARB_POLICY_PARAM_SFT 8
+	__le16	steering_tag;
+	__le32	reserved3;
+	__le32	stat_ctx_id;
+	__le32	reserved4;
+	__le32	max_bw;
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_MASK             0xfffffffUL
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_SFT              0
+	#define RING_ALLOC_REQ_MAX_BW_SCALE                     0x10000000UL
+	#define RING_ALLOC_REQ_MAX_BW_SCALE_BITS                  (0x0UL << 28)
+	#define RING_ALLOC_REQ_MAX_BW_SCALE_BYTES                 (0x1UL << 28)
+	#define RING_ALLOC_REQ_MAX_BW_SCALE_LAST                 RING_ALLOC_REQ_MAX_BW_SCALE_BYTES
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_MASK        0xe0000000UL
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_SFT         29
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_MEGA          (0x0UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_KILO          (0x2UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_BASE          (0x4UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_GIGA          (0x6UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_PERCENT1_100  (0x1UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_INVALID       (0x7UL << 29)
+	#define RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_LAST         RING_ALLOC_REQ_MAX_BW_BW_VALUE_UNIT_INVALID
+	u8	int_mode;
+	#define RING_ALLOC_REQ_INT_MODE_LEGACY 0x0UL
+	#define RING_ALLOC_REQ_INT_MODE_RSVD   0x1UL
+	#define RING_ALLOC_REQ_INT_MODE_MSIX   0x2UL
+	#define RING_ALLOC_REQ_INT_MODE_POLL   0x3UL
+	#define RING_ALLOC_REQ_INT_MODE_LAST  RING_ALLOC_REQ_INT_MODE_POLL
+	u8	mpc_chnls_type;
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TCE     0x0UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RCE     0x1UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_TE_CFA  0x2UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_RE_CFA  0x3UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE 0x4UL
+	#define RING_ALLOC_REQ_MPC_CHNLS_TYPE_LAST   RING_ALLOC_REQ_MPC_CHNLS_TYPE_PRIMATE
+	u8	rx_rate_profile_sel;
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_DEFAULT   0x0UL
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE 0x1UL
+	#define RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_LAST     RING_ALLOC_REQ_RX_RATE_PROFILE_SEL_POLL_MODE
+	u8	unused_4;
+	__le64	cq_handle;
+};
+
+/* hwrm_ring_alloc_output (size:128b/16B) */
+struct hwrm_ring_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	ring_id;
+	__le16	logical_ring_id;
+	u8	push_buffer_index;
+	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL
+	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL
+	#define RING_ALLOC_RESP_PUSH_BUFFER_INDEX_LAST       RING_ALLOC_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER
+	u8	unused_0[2];
+	u8	valid;
+};
+
+/* hwrm_ring_free_input (size:256b/32B) */
+struct hwrm_ring_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	ring_type;
+	#define RING_FREE_REQ_RING_TYPE_L2_CMPL   0x0UL
+	#define RING_FREE_REQ_RING_TYPE_TX        0x1UL
+	#define RING_FREE_REQ_RING_TYPE_RX        0x2UL
+	#define RING_FREE_REQ_RING_TYPE_ROCE_CMPL 0x3UL
+	#define RING_FREE_REQ_RING_TYPE_RX_AGG    0x4UL
+	#define RING_FREE_REQ_RING_TYPE_NQ        0x5UL
+	#define RING_FREE_REQ_RING_TYPE_LAST     RING_FREE_REQ_RING_TYPE_NQ
+	u8	flags;
+	#define RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID 0x1UL
+	#define RING_FREE_REQ_FLAGS_LAST             RING_FREE_REQ_FLAGS_VIRTIO_RING_VALID
+	__le16	ring_id;
+	__le32	prod_idx;
+	__le32	opaque;
+	__le32	unused_1;
+};
+
+/* hwrm_ring_free_output (size:128b/16B) */
+struct hwrm_ring_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_ring_reset_input (size:192b/24B) */
+struct hwrm_ring_reset_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	ring_type;
+	#define RING_RESET_REQ_RING_TYPE_L2_CMPL     0x0UL
+	#define RING_RESET_REQ_RING_TYPE_TX          0x1UL
+	#define RING_RESET_REQ_RING_TYPE_RX          0x2UL
+	#define RING_RESET_REQ_RING_TYPE_ROCE_CMPL   0x3UL
+	#define RING_RESET_REQ_RING_TYPE_RX_RING_GRP 0x6UL
+	#define RING_RESET_REQ_RING_TYPE_LAST       RING_RESET_REQ_RING_TYPE_RX_RING_GRP
+	u8	unused_0;
+	__le16	ring_id;
+	u8	unused_1[4];
+};
+
+/* hwrm_ring_reset_output (size:128b/16B) */
+struct hwrm_ring_reset_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	push_buffer_index;
+	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_PING_BUFFER 0x0UL
+	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER 0x1UL
+	#define RING_RESET_RESP_PUSH_BUFFER_INDEX_LAST       RING_RESET_RESP_PUSH_BUFFER_INDEX_PONG_BUFFER
+	u8	unused_0[3];
+	u8	consumer_idx[3];
+	u8	valid;
+};
+
+/* hwrm_ring_aggint_qcaps_input (size:128b/16B) */
+struct hwrm_ring_aggint_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_ring_aggint_qcaps_output (size:384b/48B) */
+struct hwrm_ring_aggint_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	cmpl_params;
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MIN                  0x1UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_INT_LAT_TMR_MAX                  0x2UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_TIMER_RESET                      0x4UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_RING_IDLE                        0x8UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR                0x10UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_DMA_AGGR_DURING_INT     0x20UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR                0x40UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_CMPL_AGGR_DMA_TMR_DURING_INT     0x80UL
+	#define RING_AGGINT_QCAPS_RESP_CMPL_PARAMS_NUM_CMPL_AGGR_INT                0x100UL
+	__le32	nq_params;
+	#define RING_AGGINT_QCAPS_RESP_NQ_PARAMS_INT_LAT_TMR_MIN     0x1UL
+	__le16	num_cmpl_dma_aggr_min;
+	__le16	num_cmpl_dma_aggr_max;
+	__le16	num_cmpl_dma_aggr_during_int_min;
+	__le16	num_cmpl_dma_aggr_during_int_max;
+	__le16	cmpl_aggr_dma_tmr_min;
+	__le16	cmpl_aggr_dma_tmr_max;
+	__le16	cmpl_aggr_dma_tmr_during_int_min;
+	__le16	cmpl_aggr_dma_tmr_during_int_max;
+	__le16	int_lat_tmr_min_min;
+	__le16	int_lat_tmr_min_max;
+	__le16	int_lat_tmr_max_min;
+	__le16	int_lat_tmr_max_max;
+	__le16	num_cmpl_aggr_int_min;
+	__le16	num_cmpl_aggr_int_max;
+	__le16	timer_units;
+	u8	unused_0[1];
+	u8	valid;
+};
+
+/* hwrm_ring_cmpl_ring_qaggint_params_input (size:192b/24B) */
+struct hwrm_ring_cmpl_ring_qaggint_params_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	ring_id;
+	__le16	flags;
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_MASK 0x3UL
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_UNUSED_0_SFT 0
+	#define RING_CMPL_RING_QAGGINT_PARAMS_REQ_FLAGS_IS_NQ        0x4UL
+	u8	unused_0[4];
+};
+
+/* hwrm_ring_cmpl_ring_qaggint_params_output (size:256b/32B) */
+struct hwrm_ring_cmpl_ring_qaggint_params_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	flags;
+	#define RING_CMPL_RING_QAGGINT_PARAMS_RESP_FLAGS_TIMER_RESET     0x1UL
+	#define RING_CMPL_RING_QAGGINT_PARAMS_RESP_FLAGS_RING_IDLE       0x2UL
+	__le16	num_cmpl_dma_aggr;
+	__le16	num_cmpl_dma_aggr_during_int;
+	__le16	cmpl_aggr_dma_tmr;
+	__le16	cmpl_aggr_dma_tmr_during_int;
+	__le16	int_lat_tmr_min;
+	__le16	int_lat_tmr_max;
+	__le16	num_cmpl_aggr_int;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_ring_cmpl_ring_cfg_aggint_params_input (size:320b/40B) */
+struct hwrm_ring_cmpl_ring_cfg_aggint_params_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	ring_id;
+	__le16	flags;
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_TIMER_RESET     0x1UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_RING_IDLE       0x2UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_FLAGS_IS_NQ           0x4UL
+	__le16	num_cmpl_dma_aggr;
+	__le16	num_cmpl_dma_aggr_during_int;
+	__le16	cmpl_aggr_dma_tmr;
+	__le16	cmpl_aggr_dma_tmr_during_int;
+	__le16	int_lat_tmr_min;
+	__le16	int_lat_tmr_max;
+	__le16	num_cmpl_aggr_int;
+	__le16	enables;
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR                0x1UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_DMA_AGGR_DURING_INT     0x2UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_CMPL_AGGR_DMA_TMR                0x4UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MIN                  0x8UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_INT_LAT_TMR_MAX                  0x10UL
+	#define RING_CMPL_RING_CFG_AGGINT_PARAMS_REQ_ENABLES_NUM_CMPL_AGGR_INT                0x20UL
+	u8	unused_0[4];
+};
+
+/* hwrm_ring_cmpl_ring_cfg_aggint_params_output (size:128b/16B) */
+struct hwrm_ring_cmpl_ring_cfg_aggint_params_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_ring_grp_alloc_input (size:192b/24B) */
+struct hwrm_ring_grp_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	cr;
+	__le16	rr;
+	__le16	ar;
+	__le16	sc;
+};
+
+/* hwrm_ring_grp_alloc_output (size:128b/16B) */
+struct hwrm_ring_grp_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	ring_group_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_ring_grp_free_input (size:192b/24B) */
+struct hwrm_ring_grp_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	ring_group_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_ring_grp_free_output (size:128b/16B) */
+struct hwrm_ring_grp_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+#define DEFAULT_FLOW_ID 0xFFFFFFFFUL
+#define ROCEV1_FLOW_ID 0xFFFFFFFEUL
+#define ROCEV2_FLOW_ID 0xFFFFFFFDUL
+#define ROCEV2_CNP_FLOW_ID 0xFFFFFFFCUL
+
+/* hwrm_cfa_l2_filter_alloc_input (size:768b/96B) */
+struct hwrm_cfa_l2_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH              0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_TX             0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX             0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_LAST          CFA_L2_FILTER_ALLOC_REQ_FLAGS_PATH_RX
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_LOOPBACK          0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_DROP              0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_OUTERMOST         0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_MASK      0x30UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_SFT       4
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_NO_ROCE_L2  (0x0UL << 4)
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_L2          (0x1UL << 4)
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE        (0x2UL << 4)
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_LAST       CFA_L2_FILTER_ALLOC_REQ_FLAGS_TRAFFIC_ROCE
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_XDP_DISABLE       0x40UL
+	#define CFA_L2_FILTER_ALLOC_REQ_FLAGS_SOURCE_VALID      0x80UL
+	__le32	enables;
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR             0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_ADDR_MASK        0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_OVLAN            0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_OVLAN_MASK       0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN            0x10UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN_MASK       0x20UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_ADDR           0x40UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_ADDR_MASK      0x80UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_OVLAN          0x100UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_OVLAN_MASK     0x200UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_IVLAN          0x400UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_L2_IVLAN_MASK     0x800UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_TYPE            0x1000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_SRC_ID              0x2000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE         0x4000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_DST_ID              0x8000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID      0x10000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_NUM_VLANS           0x20000UL
+	#define CFA_L2_FILTER_ALLOC_REQ_ENABLES_T_NUM_VLANS         0x40000UL
+	u8	l2_addr[6];
+	u8	num_vlans;
+	u8	t_num_vlans;
+	u8	l2_addr_mask[6];
+	__le16	l2_ovlan;
+	__le16	l2_ovlan_mask;
+	__le16	l2_ivlan;
+	__le16	l2_ivlan_mask;
+	u8	unused_1[2];
+	u8	t_l2_addr[6];
+	u8	unused_2[2];
+	u8	t_l2_addr_mask[6];
+	__le16	t_l2_ovlan;
+	__le16	t_l2_ovlan_mask;
+	__le16	t_l2_ivlan;
+	__le16	t_l2_ivlan_mask;
+	u8	src_type;
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_NPORT 0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_PF    0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_VF    0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_VNIC  0x3UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_KONG  0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_APE   0x5UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_BONO  0x6UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_TANG  0x7UL
+	#define CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_LAST CFA_L2_FILTER_ALLOC_REQ_SRC_TYPE_TANG
+	u8	unused_3;
+	__le32	src_id;
+	u8	tunnel_type;
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_L2_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	u8	unused_4;
+	__le16	dst_id;
+	__le16	mirror_vnic_id;
+	u8	pri_hint;
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER    0x0UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_ABOVE_FILTER 0x1UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_BELOW_FILTER 0x2UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MAX          0x3UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MIN          0x4UL
+	#define CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_LAST        CFA_L2_FILTER_ALLOC_REQ_PRI_HINT_MIN
+	u8	unused_5;
+	__le32	unused_6;
+	__le64	l2_filter_id_hint;
+};
+
+/* hwrm_cfa_l2_filter_alloc_output (size:192b/24B) */
+struct hwrm_cfa_l2_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	l2_filter_id;
+	__le32	flow_id;
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_L2_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_l2_filter_free_input (size:192b/24B) */
+struct hwrm_cfa_l2_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	l2_filter_id;
+};
+
+/* hwrm_cfa_l2_filter_free_output (size:128b/16B) */
+struct hwrm_cfa_l2_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_l2_filter_cfg_input (size:384b/48B) */
+struct hwrm_cfa_l2_filter_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH                  0x1UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_TX                 0x0UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX                 0x1UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_LAST              CFA_L2_FILTER_CFG_REQ_FLAGS_PATH_RX
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_DROP                  0x2UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_MASK          0xcUL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_SFT           2
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_NO_ROCE_L2      (0x0UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_L2              (0x1UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE            (0x2UL << 2)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_LAST           CFA_L2_FILTER_CFG_REQ_FLAGS_TRAFFIC_ROCE
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_MASK         0x30UL
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_SFT          4
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_NO_UPDATE      (0x0UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_BYPASS_LKUP    (0x1UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_ENABLE_LKUP    (0x2UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP  (0x3UL << 4)
+	#define CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_LAST          CFA_L2_FILTER_CFG_REQ_FLAGS_REMAP_OP_RESTORE_FW_OP
+	__le32	enables;
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_DST_ID                 0x1UL
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID     0x2UL
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_PROF_FUNC              0x4UL
+	#define CFA_L2_FILTER_CFG_REQ_ENABLES_L2_CONTEXT_ID          0x8UL
+	__le64	l2_filter_id;
+	__le32	dst_id;
+	__le32	new_mirror_vnic_id;
+	__le32	prof_func;
+	__le32	l2_context_id;
+};
+
+/* hwrm_cfa_l2_filter_cfg_output (size:128b/16B) */
+struct hwrm_cfa_l2_filter_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_l2_set_rx_mask_input (size:448b/56B) */
+struct hwrm_cfa_l2_set_rx_mask_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	vnic_id;
+	__le32	mask;
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_MCAST               0x2UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_ALL_MCAST           0x4UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_BCAST               0x8UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_PROMISCUOUS         0x10UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_OUTERMOST           0x20UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLANONLY            0x40UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_VLAN_NONVLAN        0x80UL
+	#define CFA_L2_SET_RX_MASK_REQ_MASK_ANYVLAN_NONVLAN     0x100UL
+	__le64	mc_tbl_addr;
+	__le32	num_mc_entries;
+	u8	unused_0[4];
+	__le64	vlan_tag_tbl_addr;
+	__le32	num_vlan_tags;
+	u8	unused_1[4];
+};
+
+/* hwrm_cfa_l2_set_rx_mask_output (size:128b/16B) */
+struct hwrm_cfa_l2_set_rx_mask_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_l2_set_rx_mask_cmd_err (size:64b/8B) */
+struct hwrm_cfa_l2_set_rx_mask_cmd_err {
+	u8	code;
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_UNKNOWN                    0x0UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR 0x1UL
+	#define CFA_L2_SET_RX_MASK_CMD_ERR_CODE_LAST                      CFA_L2_SET_RX_MASK_CMD_ERR_CODE_NTUPLE_FILTER_CONFLICT_ERR
+	u8	unused_0[7];
+};
+
+/* hwrm_cfa_tunnel_filter_alloc_input (size:704b/88B) */
+struct hwrm_cfa_tunnel_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
+	__le32	enables;
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID       0x1UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_ADDR            0x2UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L2_IVLAN           0x4UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L3_ADDR            0x8UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_L3_ADDR_TYPE       0x10UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_T_L3_ADDR_TYPE     0x20UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_T_L3_ADDR          0x40UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE        0x80UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_VNI                0x100UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_DST_VNIC_ID        0x200UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x400UL
+	__le64	l2_filter_id;
+	u8	l2_addr[6];
+	__le16	l2_ivlan;
+	__le32	l3_addr[4];
+	__le32	t_l3_addr[4];
+	u8	l3_addr_type;
+	u8	t_l3_addr_type;
+	u8	tunnel_type;
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	u8	tunnel_flags;
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_OAM_CHECKSUM_EXPLHDR     0x1UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_CRITICAL_OPT_S1          0x2UL
+	#define CFA_TUNNEL_FILTER_ALLOC_REQ_TUNNEL_FLAGS_TUN_FLAGS_EXTHDR_SEQNUM_S0         0x4UL
+	__le32	vni;
+	__le32	dst_vnic_id;
+	__le32	mirror_vnic_id;
+};
+
+/* hwrm_cfa_tunnel_filter_alloc_output (size:192b/24B) */
+struct hwrm_cfa_tunnel_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	tunnel_filter_id;
+	__le32	flow_id;
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_TUNNEL_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_tunnel_filter_free_input (size:192b/24B) */
+struct hwrm_cfa_tunnel_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	tunnel_filter_id;
+};
+
+/* hwrm_cfa_tunnel_filter_free_output (size:128b/16B) */
+struct hwrm_cfa_tunnel_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_vxlan_ipv4_hdr (size:128b/16B) */
+struct hwrm_vxlan_ipv4_hdr {
+	u8	ver_hlen;
+	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_MASK 0xfUL
+	#define VXLAN_IPV4_HDR_VER_HLEN_HEADER_LENGTH_SFT 0
+	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_MASK      0xf0UL
+	#define VXLAN_IPV4_HDR_VER_HLEN_VERSION_SFT       4
+	u8	tos;
+	__be16	ip_id;
+	__be16	flags_frag_offset;
+	u8	ttl;
+	u8	protocol;
+	__be32	src_ip_addr;
+	__be32	dest_ip_addr;
+};
+
+/* hwrm_vxlan_ipv6_hdr (size:320b/40B) */
+struct hwrm_vxlan_ipv6_hdr {
+	__be32	ver_tc_flow_label;
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_SFT         0x1cUL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_VER_MASK        0xf0000000UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_SFT          0x14UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_TC_MASK         0xff00000UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_SFT  0x0UL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK 0xfffffUL
+	#define VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_LAST           VXLAN_IPV6_HDR_VER_TC_FLOW_LABEL_FLOW_LABEL_MASK
+	__be16	payload_len;
+	u8	next_hdr;
+	u8	ttl;
+	__be32	src_ip_addr[4];
+	__be32	dest_ip_addr[4];
+};
+
+/* hwrm_cfa_encap_data_vxlan (size:640b/80B) */
+struct hwrm_cfa_encap_data_vxlan {
+	u8	src_mac_addr[6];
+	__le16	unused_0;
+	u8	dst_mac_addr[6];
+	u8	num_vlan_tags;
+	u8	unused_1;
+	__be16	ovlan_tpid;
+	__be16	ovlan_tci;
+	__be16	ivlan_tpid;
+	__be16	ivlan_tci;
+	__le32	l3[10];
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_MASK 0xfUL
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV4 0x4UL
+	#define CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6 0x6UL
+	#define CFA_ENCAP_DATA_VXLAN_L3_LAST    CFA_ENCAP_DATA_VXLAN_L3_VER_IPV6
+	__be16	src_port;
+	__be16	dst_port;
+	__be32	vni;
+	u8	hdr_rsvd0[3];
+	u8	hdr_rsvd1;
+	u8	hdr_flags;
+	u8	unused[3];
+};
+
+/* hwrm_cfa_encap_record_alloc_input (size:832b/104B) */
+struct hwrm_cfa_encap_record_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_LOOPBACK     0x1UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_FLAGS_EXTERNAL     0x2UL
+	u8	encap_type;
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN        0x1UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_NVGRE        0x2UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2GRE        0x3UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPIP         0x4UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_GENEVE       0x5UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_MPLS         0x6UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VLAN         0x7UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE        0x8UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_V4     0x9UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_IPGRE_V1     0xaUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_L2_ETYPE     0xbUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_LAST        CFA_ENCAP_RECORD_ALLOC_REQ_ENCAP_TYPE_VXLAN_GPE
+	u8	unused_0[3];
+	__le32	encap_data[20];
+};
+
+/* hwrm_cfa_encap_record_alloc_output (size:128b/16B) */
+struct hwrm_cfa_encap_record_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	encap_record_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_encap_record_free_input (size:192b/24B) */
+struct hwrm_cfa_encap_record_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	encap_record_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_cfa_encap_record_free_output (size:128b/16B) */
+struct hwrm_cfa_encap_record_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_ntuple_filter_alloc_input (size:1024b/128B) */
+struct hwrm_cfa_ntuple_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_LOOPBACK              0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DROP                  0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_METER                 0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_FID              0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_ARP_REPLY             0x10UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_DEST_RFS_RING_IDX     0x20UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_FLAGS_NO_L2_CONTEXT         0x40UL
+	__le32	enables;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_L2_FILTER_ID         0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE            0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE          0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR          0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE          0x10UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR           0x20UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR_MASK      0x40UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR           0x80UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR_MASK      0x100UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL          0x200UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT             0x400UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_SRC_PORT_MASK        0x800UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT             0x1000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_PORT_MASK        0x2000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_PRI_HINT             0x4000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_NTUPLE_FILTER_ID     0x8000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_ID               0x10000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID       0x20000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR          0x40000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_ENABLES_RFS_RING_TBL_IDX     0x80000UL
+	__le64	l2_filter_id;
+	u8	src_macaddr[6];
+	__be16	ethertype;
+	u8	ip_addr_type;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN 0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4    0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6    0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6
+	u8	ip_protocol;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP     0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP     0x11UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMP    0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_ICMPV6  0x3aUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD    0xffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_NTUPLE_FILTER_ALLOC_REQ_IP_PROTOCOL_RSVD
+	__le16	dst_id;
+	__le16	rfs_ring_tbl_idx;
+	u8	tunnel_type;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_NTUPLE_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	u8	pri_hint;
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_NO_PREFER 0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_ABOVE     0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_BELOW     0x2UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_HIGHEST   0x3UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST    0x4UL
+	#define CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LAST     CFA_NTUPLE_FILTER_ALLOC_REQ_PRI_HINT_LOWEST
+	__be32	src_ipaddr[4];
+	__be32	src_ipaddr_mask[4];
+	__be32	dst_ipaddr[4];
+	__be32	dst_ipaddr_mask[4];
+	__be16	src_port;
+	__be16	src_port_mask;
+	__be16	dst_port;
+	__be16	dst_port_mask;
+	__le64	ntuple_filter_id_hint;
+};
+
+/* hwrm_cfa_ntuple_filter_alloc_output (size:192b/24B) */
+struct hwrm_cfa_ntuple_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	ntuple_filter_id;
+	__le32	flow_id;
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_NTUPLE_FILTER_ALLOC_RESP_FLOW_ID_DIR_TX
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_ntuple_filter_alloc_cmd_err (size:64b/8B) */
+struct hwrm_cfa_ntuple_filter_alloc_cmd_err {
+	u8	code;
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_UNKNOWN                   0x0UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR 0x1UL
+	#define CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_LAST                     CFA_NTUPLE_FILTER_ALLOC_CMD_ERR_CODE_RX_MASK_VLAN_CONFLICT_ERR
+	u8	unused_0[7];
+};
+
+/* hwrm_cfa_ntuple_filter_free_input (size:192b/24B) */
+struct hwrm_cfa_ntuple_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	ntuple_filter_id;
+};
+
+/* hwrm_cfa_ntuple_filter_free_output (size:128b/16B) */
+struct hwrm_cfa_ntuple_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_ntuple_filter_cfg_input (size:384b/48B) */
+struct hwrm_cfa_ntuple_filter_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_DST_ID                0x1UL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_MIRROR_VNIC_ID        0x2UL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_ENABLES_NEW_METER_INSTANCE_ID     0x4UL
+	__le32	flags;
+	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_FID              0x1UL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_DEST_RFS_RING_IDX     0x2UL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_FLAGS_NO_L2_CONTEXT         0x4UL
+	__le64	ntuple_filter_id;
+	__le32	new_dst_id;
+	__le32	new_mirror_vnic_id;
+	__le16	new_meter_instance_id;
+	#define CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_INVALID 0xffffUL
+	#define CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_LAST   CFA_NTUPLE_FILTER_CFG_REQ_NEW_METER_INSTANCE_ID_INVALID
+	u8	unused_1[6];
+};
+
+/* hwrm_cfa_ntuple_filter_cfg_output (size:128b/16B) */
+struct hwrm_cfa_ntuple_filter_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_decap_filter_alloc_input (size:832b/104B) */
+struct hwrm_cfa_decap_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_FLAGS_OVS_TUNNEL     0x1UL
+	__le32	enables;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_TYPE        0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_TUNNEL_ID          0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_MACADDR        0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_MACADDR        0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_OVLAN_VID          0x10UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IVLAN_VID          0x20UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_OVLAN_VID        0x40UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_T_IVLAN_VID        0x80UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_ETHERTYPE          0x100UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_IPADDR         0x200UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_IPADDR         0x400UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IPADDR_TYPE        0x800UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_IP_PROTOCOL        0x1000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_SRC_PORT           0x2000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_PORT           0x4000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_DST_ID             0x8000UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_ENABLES_MIRROR_VNIC_ID     0x10000UL
+	__be32	tunnel_id;
+	u8	tunnel_type;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_DECAP_FILTER_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+	u8	unused_0;
+	__le16	unused_1;
+	u8	src_macaddr[6];
+	u8	unused_2[2];
+	u8	dst_macaddr[6];
+	__be16	ovlan_vid;
+	__be16	ivlan_vid;
+	__be16	t_ovlan_vid;
+	__be16	t_ivlan_vid;
+	__be16	ethertype;
+	u8	ip_addr_type;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_UNKNOWN 0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV4    0x4UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6    0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_LAST   CFA_DECAP_FILTER_ALLOC_REQ_IP_ADDR_TYPE_IPV6
+	u8	ip_protocol;
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UNKNOWN 0x0UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_TCP     0x6UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP     0x11UL
+	#define CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_LAST   CFA_DECAP_FILTER_ALLOC_REQ_IP_PROTOCOL_UDP
+	__le16	unused_3;
+	__le32	unused_4;
+	__be32	src_ipaddr[4];
+	__be32	dst_ipaddr[4];
+	__be16	src_port;
+	__be16	dst_port;
+	__le16	dst_id;
+	__le16	l2_ctxt_ref_id;
+};
+
+/* hwrm_cfa_decap_filter_alloc_output (size:128b/16B) */
+struct hwrm_cfa_decap_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	decap_filter_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_decap_filter_free_input (size:192b/24B) */
+struct hwrm_cfa_decap_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	decap_filter_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_cfa_decap_filter_free_output (size:128b/16B) */
+struct hwrm_cfa_decap_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_flow_alloc_input (size:1024b/128B) */
+struct hwrm_cfa_flow_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	flags;
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_TUNNEL                 0x1UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_MASK          0x6UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_SFT           1
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_NONE            (0x0UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_ONE             (0x1UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO             (0x2UL << 1)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_LAST           CFA_FLOW_ALLOC_REQ_FLAGS_NUM_VLAN_TWO
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_MASK          0x38UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_SFT           3
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_L2              (0x0UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV4            (0x1UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6            (0x2UL << 3)
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_LAST           CFA_FLOW_ALLOC_REQ_FLAGS_FLOWTYPE_IPV6
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_TX                0x40UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_PATH_RX                0x80UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_MATCH_VXLAN_IP_VNI     0x100UL
+	#define CFA_FLOW_ALLOC_REQ_FLAGS_VHOST_ID_USE_VLAN      0x200UL
+	__le16	src_fid;
+	__le32	tunnel_handle;
+	__le16	action_flags;
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FWD                       0x1UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_RECYCLE                   0x2UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_DROP                      0x4UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_METER                     0x8UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL                    0x10UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_SRC                   0x20UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_DEST                  0x40UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NAT_IPV4_ADDRESS          0x80UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_L2_HEADER_REWRITE         0x100UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TTL_DECREMENT             0x200UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_TUNNEL_IP                 0x400UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_FLOW_AGING_ENABLED        0x800UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_PRI_HINT                  0x1000UL
+	#define CFA_FLOW_ALLOC_REQ_ACTION_FLAGS_NO_FLOW_COUNTER_ALLOC     0x2000UL
+	__le16	dst_fid;
+	__be16	l2_rewrite_vlan_tpid;
+	__be16	l2_rewrite_vlan_tci;
+	__le16	act_meter_id;
+	__le16	ref_flow_handle;
+	__be16	ethertype;
+	__be16	outer_vlan_tci;
+	__be16	dmac[3];
+	__be16	inner_vlan_tci;
+	__be16	smac[3];
+	u8	ip_dst_mask_len;
+	u8	ip_src_mask_len;
+	__be32	ip_dst[4];
+	__be32	ip_src[4];
+	__be16	l4_src_port;
+	__be16	l4_src_port_mask;
+	__be16	l4_dst_port;
+	__be16	l4_dst_port_mask;
+	__be32	nat_ip_address[4];
+	__be16	l2_rewrite_dmac[3];
+	__be16	nat_port;
+	__be16	l2_rewrite_smac[3];
+	u8	ip_proto;
+	u8	tunnel_type;
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NONTUNNEL    0x0UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN        0x1UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_NVGRE        0x2UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2GRE        0x3UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPIP         0x4UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_GENEVE       0x5UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_MPLS         0x6UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_STT          0x7UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE        0x8UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4     0x9UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1     0xaUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE     0xbUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6 0xcUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE    0x10UL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL    0xffUL
+	#define CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_LAST        CFA_FLOW_ALLOC_REQ_TUNNEL_TYPE_ANYTUNNEL
+};
+
+/* hwrm_cfa_flow_alloc_output (size:256b/32B) */
+struct hwrm_cfa_flow_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	flow_handle;
+	u8	unused_0[2];
+	__le32	flow_id;
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_MASK 0x3fffffffUL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_VALUE_SFT 0
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE      0x40000000UL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_INT    (0x0UL << 30)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT    (0x1UL << 30)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_LAST  CFA_FLOW_ALLOC_RESP_FLOW_ID_TYPE_EXT
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR       0x80000000UL
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_RX      (0x0UL << 31)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX      (0x1UL << 31)
+	#define CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_LAST   CFA_FLOW_ALLOC_RESP_FLOW_ID_DIR_TX
+	__le64	ext_flow_handle;
+	__le32	flow_counter_id;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_flow_alloc_cmd_err (size:64b/8B) */
+struct hwrm_cfa_flow_alloc_cmd_err {
+	u8	code;
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_UNKNOWN         0x0UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_L2_CONTEXT_TCAM 0x1UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_ACTION_RECORD   0x2UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_COUNTER    0x3UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_WILD_CARD_TCAM  0x4UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_HASH_COLLISION  0x5UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_KEY_EXISTS      0x6UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB    0x7UL
+	#define CFA_FLOW_ALLOC_CMD_ERR_CODE_LAST           CFA_FLOW_ALLOC_CMD_ERR_CODE_FLOW_CTXT_DB
+	u8	unused_0[7];
+};
+
+/* hwrm_cfa_flow_free_input (size:256b/32B) */
+struct hwrm_cfa_flow_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	flow_handle;
+	__le16	unused_0;
+	__le32	flow_counter_id;
+	__le64	ext_flow_handle;
+};
+
+/* hwrm_cfa_flow_free_output (size:256b/32B) */
+struct hwrm_cfa_flow_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	packet;
+	__le64	byte;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_flow_info_input (size:256b/32B) */
+struct hwrm_cfa_flow_info_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	flow_handle;
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_MAX_MASK      0xfffUL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT       0x1000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT    0x2000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_NIC_TX        0x3000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT    0x4000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_DIR_RX        0x8000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_CNP_CNT_RX    0x9000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV1_CNT_RX 0xa000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_NIC_RX        0xb000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT_RX 0xc000UL
+	#define CFA_FLOW_INFO_REQ_FLOW_HANDLE_LAST         CFA_FLOW_INFO_REQ_FLOW_HANDLE_ROCEV2_CNT_RX
+	u8	unused_0[6];
+	__le64	ext_flow_handle;
+};
+
+/* hwrm_cfa_flow_info_output (size:5632b/704B) */
+struct hwrm_cfa_flow_info_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_TX     0x1UL
+	#define CFA_FLOW_INFO_RESP_FLAGS_PATH_RX     0x2UL
+	u8	profile;
+	__le16	src_fid;
+	__le16	dst_fid;
+	__le16	l2_ctxt_id;
+	__le64	em_info;
+	__le64	tcam_info;
+	__le64	vfp_tcam_info;
+	__le16	ar_id;
+	__le16	flow_handle;
+	__le32	tunnel_handle;
+	__le16	flow_timer;
+	u8	unused_0[6];
+	__le32	flow_key_data[130];
+	__le32	flow_action_info[30];
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_flow_stats_input (size:640b/80B) */
+struct hwrm_cfa_flow_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	num_flows;
+	__le16	flow_handle_0;
+	__le16	flow_handle_1;
+	__le16	flow_handle_2;
+	__le16	flow_handle_3;
+	__le16	flow_handle_4;
+	__le16	flow_handle_5;
+	__le16	flow_handle_6;
+	__le16	flow_handle_7;
+	__le16	flow_handle_8;
+	__le16	flow_handle_9;
+	u8	unused_0[2];
+	__le32	flow_id_0;
+	__le32	flow_id_1;
+	__le32	flow_id_2;
+	__le32	flow_id_3;
+	__le32	flow_id_4;
+	__le32	flow_id_5;
+	__le32	flow_id_6;
+	__le32	flow_id_7;
+	__le32	flow_id_8;
+	__le32	flow_id_9;
+};
+
+/* hwrm_cfa_flow_stats_output (size:1408b/176B) */
+struct hwrm_cfa_flow_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	packet_0;
+	__le64	packet_1;
+	__le64	packet_2;
+	__le64	packet_3;
+	__le64	packet_4;
+	__le64	packet_5;
+	__le64	packet_6;
+	__le64	packet_7;
+	__le64	packet_8;
+	__le64	packet_9;
+	__le64	byte_0;
+	__le64	byte_1;
+	__le64	byte_2;
+	__le64	byte_3;
+	__le64	byte_4;
+	__le64	byte_5;
+	__le64	byte_6;
+	__le64	byte_7;
+	__le64	byte_8;
+	__le64	byte_9;
+	__le16	flow_hits;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_cfa_vfr_alloc_input (size:448b/56B) */
+struct hwrm_cfa_vfr_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	vf_id;
+	__le16	reserved;
+	u8	unused_0[4];
+	char	vfr_name[32];
+};
+
+/* hwrm_cfa_vfr_alloc_output (size:128b/16B) */
+struct hwrm_cfa_vfr_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	rx_cfa_code;
+	__le16	tx_cfa_action;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_cfa_vfr_free_input (size:448b/56B) */
+struct hwrm_cfa_vfr_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	char	vfr_name[32];
+	__le16	vf_id;
+	__le16	reserved;
+	u8	unused_0[4];
+};
+
+/* hwrm_cfa_vfr_free_output (size:128b/16B) */
+struct hwrm_cfa_vfr_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_qcaps_input (size:192b/24B) */
+struct hwrm_cfa_eem_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_QCAPS_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	unused_0;
+};
+
+/* hwrm_cfa_eem_qcaps_output (size:320b/40B) */
+struct hwrm_cfa_eem_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_TX                                         0x1UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_PATH_RX                                         0x2UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_CENTRALIZED_MEMORY_MODEL_SUPPORTED              0x4UL
+	#define CFA_EEM_QCAPS_RESP_FLAGS_DETACHED_CENTRALIZED_MEMORY_MODEL_SUPPORTED     0x8UL
+	__le32	unused_0;
+	__le32	supported;
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY0_TABLE                       0x1UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_KEY1_TABLE                       0x2UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_RECORD_TABLE            0x4UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_EXTERNAL_FLOW_COUNTERS_TABLE     0x8UL
+	#define CFA_EEM_QCAPS_RESP_SUPPORTED_FID_TABLE                        0x10UL
+	__le32	max_entries_supported;
+	__le16	key_entry_size;
+	__le16	record_entry_size;
+	__le16	efc_entry_size;
+	__le16	fid_entry_size;
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_cfg_input (size:384b/48B) */
+struct hwrm_cfa_eem_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_CFG_REQ_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_CFG_REQ_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_CFG_REQ_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	#define CFA_EEM_CFG_REQ_FLAGS_SECONDARY_PF          0x8UL
+	__le16	group_id;
+	__le16	unused_0;
+	__le32	num_entries;
+	__le32	unused_1;
+	__le16	key0_ctx_id;
+	__le16	key1_ctx_id;
+	__le16	record_ctx_id;
+	__le16	efc_ctx_id;
+	__le16	fid_ctx_id;
+	__le16	unused_2;
+	__le32	unused_3;
+};
+
+/* hwrm_cfa_eem_cfg_output (size:128b/16B) */
+struct hwrm_cfa_eem_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_qcfg_input (size:192b/24B) */
+struct hwrm_cfa_eem_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_QCFG_REQ_FLAGS_PATH_RX     0x2UL
+	__le32	unused_0;
+};
+
+/* hwrm_cfa_eem_qcfg_output (size:256b/32B) */
+struct hwrm_cfa_eem_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_TX               0x1UL
+	#define CFA_EEM_QCFG_RESP_FLAGS_PATH_RX               0x2UL
+	#define CFA_EEM_QCFG_RESP_FLAGS_PREFERRED_OFFLOAD     0x4UL
+	__le32	num_entries;
+	__le16	key0_ctx_id;
+	__le16	key1_ctx_id;
+	__le16	record_ctx_id;
+	__le16	efc_ctx_id;
+	__le16	fid_ctx_id;
+	u8	unused_2[5];
+	u8	valid;
+};
+
+/* hwrm_cfa_eem_op_input (size:192b/24B) */
+struct hwrm_cfa_eem_op_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define CFA_EEM_OP_REQ_FLAGS_PATH_TX     0x1UL
+	#define CFA_EEM_OP_REQ_FLAGS_PATH_RX     0x2UL
+	__le16	unused_0;
+	__le16	op;
+	#define CFA_EEM_OP_REQ_OP_RESERVED    0x0UL
+	#define CFA_EEM_OP_REQ_OP_EEM_DISABLE 0x1UL
+	#define CFA_EEM_OP_REQ_OP_EEM_ENABLE  0x2UL
+	#define CFA_EEM_OP_REQ_OP_EEM_CLEANUP 0x3UL
+	#define CFA_EEM_OP_REQ_OP_LAST       CFA_EEM_OP_REQ_OP_EEM_CLEANUP
+};
+
+/* hwrm_cfa_eem_op_output (size:128b/16B) */
+struct hwrm_cfa_eem_op_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_cfa_adv_flow_mgnt_qcaps_input (size:256b/32B) */
+struct hwrm_cfa_adv_flow_mgnt_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	unused_0[4];
+};
+
+/* hwrm_cfa_adv_flow_mgnt_qcaps_output (size:128b/16B) */
+struct hwrm_cfa_adv_flow_mgnt_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	flags;
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_16BIT_SUPPORTED                     0x1UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_HND_64BIT_SUPPORTED                     0x2UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_BATCH_DELETE_SUPPORTED                  0x4UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_RESET_ALL_SUPPORTED                     0x8UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_DEST_FUNC_SUPPORTED              0x10UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TX_EEM_FLOW_SUPPORTED                        0x20UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RX_EEM_FLOW_SUPPORTED                        0x40UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_FLOW_COUNTER_ALLOC_SUPPORTED                 0x80UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_SUPPORTED                   0x100UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_UNTAGGED_VLAN_SUPPORTED                      0x200UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_XDP_SUPPORTED                                0x400UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_HEADER_SOURCE_FIELDS_SUPPORTED            0x800UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ARP_SUPPORTED                 0x1000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V2_SUPPORTED                0x2000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_ETHERTYPE_IP_SUPPORTED        0x4000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_TRUFLOW_CAPABLE                              0x8000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_L2_FILTER_TRAFFIC_TYPE_L2_ROCE_SUPPORTED     0x10000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_LAG_SUPPORTED                                0x20000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_NO_L2CTX_SUPPORTED               0x40000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NIC_FLOW_STATS_SUPPORTED                     0x80000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_NTUPLE_FLOW_RX_EXT_IP_PROTO_SUPPORTED        0x100000UL
+	#define CFA_ADV_FLOW_MGNT_QCAPS_RESP_FLAGS_RFS_RING_TBL_IDX_V3_SUPPORTED                0x200000UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_tunnel_dst_port_query_input (size:192b/24B) */
+struct hwrm_tunnel_dst_port_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	tunnel_type;
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN              0x1UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GENEVE             0x5UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ECPRI              0xeUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_SRV6               0xfUL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_GRE                0x11UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_QUERY_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
+	u8	tunnel_next_proto;
+	u8	unused_0[6];
+};
+
+/* hwrm_tunnel_dst_port_query_output (size:128b/16B) */
+struct hwrm_tunnel_dst_port_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	tunnel_dst_port_id;
+	__be16	tunnel_dst_port_val;
+	u8	upar_in_use;
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR0     0x1UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR1     0x2UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR2     0x4UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR3     0x8UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR4     0x10UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR5     0x20UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR6     0x40UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_UPAR_IN_USE_UPAR7     0x80UL
+	u8	status;
+	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_CHIP_LEVEL     0x1UL
+	#define TUNNEL_DST_PORT_QUERY_RESP_STATUS_FUNC_LEVEL     0x2UL
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_tunnel_dst_port_alloc_input (size:192b/24B) */
+struct hwrm_tunnel_dst_port_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	tunnel_type;
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN              0x1UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GENEVE             0x5UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ECPRI              0xeUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_SRV6               0xfUL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_GRE                0x11UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_ALLOC_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
+	u8	tunnel_next_proto;
+	__be16	tunnel_dst_port_val;
+	u8	unused_0[4];
+};
+
+/* hwrm_tunnel_dst_port_alloc_output (size:128b/16B) */
+struct hwrm_tunnel_dst_port_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	tunnel_dst_port_id;
+	u8	error_info;
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_SUCCESS         0x0UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ALLOCATED   0x1UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_NO_RESOURCE 0x2UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED     0x3UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_LAST           TUNNEL_DST_PORT_ALLOC_RESP_ERROR_INFO_ERR_ENABLED
+	u8	upar_in_use;
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR0     0x1UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR1     0x2UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR2     0x4UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR3     0x8UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR4     0x10UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR5     0x20UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR6     0x40UL
+	#define TUNNEL_DST_PORT_ALLOC_RESP_UPAR_IN_USE_UPAR7     0x80UL
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_tunnel_dst_port_free_input (size:192b/24B) */
+struct hwrm_tunnel_dst_port_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	tunnel_type;
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN              0x1UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GENEVE             0x5UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_V4           0x9UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_IPGRE_V1           0xaUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_L2_ETYPE           0xbUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE_V6       0xcUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_CUSTOM_GRE         0xdUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ECPRI              0xeUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_SRV6               0xfUL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_VXLAN_GPE          0x10UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_GRE                0x11UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR       0x12UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES01 0x13UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES02 0x14UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES03 0x15UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES04 0x16UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES05 0x17UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES06 0x18UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07 0x19UL
+	#define TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_LAST              TUNNEL_DST_PORT_FREE_REQ_TUNNEL_TYPE_ULP_DYN_UPAR_RES07
+	u8	tunnel_next_proto;
+	__le16	tunnel_dst_port_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_tunnel_dst_port_free_output (size:128b/16B) */
+struct hwrm_tunnel_dst_port_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	error_info;
+	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_SUCCESS           0x0UL
+	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_OWNER     0x1UL
+	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED 0x2UL
+	#define TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_LAST             TUNNEL_DST_PORT_FREE_RESP_ERROR_INFO_ERR_NOT_ALLOCATED
+	u8	unused_1[6];
+	u8	valid;
+};
+
+/* ctx_hw_stats (size:1280b/160B) */
+struct ctx_hw_stats {
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	tpa_pkts;
+	__le64	tpa_bytes;
+	__le64	tpa_events;
+	__le64	tpa_aborts;
+};
+
+/* ctx_hw_stats_ext (size:1408b/176B) */
+struct ctx_hw_stats_ext {
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_tpa_eligible_pkt;
+	__le64	rx_tpa_eligible_bytes;
+	__le64	rx_tpa_pkt;
+	__le64	rx_tpa_bytes;
+	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
+};
+
+/* hwrm_stat_ctx_alloc_input (size:384b/48B) */
+struct hwrm_stat_ctx_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	stats_dma_addr;
+	__le32	update_period_ms;
+	u8	stat_ctx_flags;
+	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_ROCE             0x1UL
+	#define STAT_CTX_ALLOC_REQ_STAT_CTX_FLAGS_DUP_HOST_BUF     0x2UL
+	u8	unused_0;
+	__le16	stats_dma_length;
+	__le16	flags;
+	#define STAT_CTX_ALLOC_REQ_FLAGS_STEERING_TAG_VALID     0x1UL
+	__le16	steering_tag;
+	__le32	stat_ctx_id;
+	__le16	alloc_seq_id;
+	u8	unused_1[6];
+};
+
+/* hwrm_stat_ctx_alloc_output (size:128b/16B) */
+struct hwrm_stat_ctx_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	stat_ctx_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_stat_ctx_free_input (size:192b/24B) */
+struct hwrm_stat_ctx_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	stat_ctx_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_stat_ctx_free_output (size:128b/16B) */
+struct hwrm_stat_ctx_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	stat_ctx_id;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_stat_ctx_query_input (size:192b/24B) */
+struct hwrm_stat_ctx_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	stat_ctx_id;
+	u8	flags;
+	#define STAT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[3];
+};
+
+/* hwrm_stat_ctx_query_output (size:1408b/176B) */
+struct hwrm_stat_ctx_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	rx_agg_pkts;
+	__le64	rx_agg_bytes;
+	__le64	rx_agg_events;
+	__le64	rx_agg_aborts;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_stat_ext_ctx_query_input (size:192b/24B) */
+struct hwrm_stat_ext_ctx_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	stat_ctx_id;
+	u8	flags;
+	#define STAT_EXT_CTX_QUERY_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[3];
+};
+
+/* hwrm_stat_ext_ctx_query_output (size:1536b/192B) */
+struct hwrm_stat_ext_ctx_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	rx_ucast_pkts;
+	__le64	rx_mcast_pkts;
+	__le64	rx_bcast_pkts;
+	__le64	rx_discard_pkts;
+	__le64	rx_error_pkts;
+	__le64	rx_ucast_bytes;
+	__le64	rx_mcast_bytes;
+	__le64	rx_bcast_bytes;
+	__le64	tx_ucast_pkts;
+	__le64	tx_mcast_pkts;
+	__le64	tx_bcast_pkts;
+	__le64	tx_error_pkts;
+	__le64	tx_discard_pkts;
+	__le64	tx_ucast_bytes;
+	__le64	tx_mcast_bytes;
+	__le64	tx_bcast_bytes;
+	__le64	rx_tpa_eligible_pkt;
+	__le64	rx_tpa_eligible_bytes;
+	__le64	rx_tpa_pkt;
+	__le64	rx_tpa_bytes;
+	__le64	rx_tpa_errors;
+	__le64	rx_tpa_events;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_stat_ctx_clr_stats_input (size:192b/24B) */
+struct hwrm_stat_ctx_clr_stats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	stat_ctx_id;
+	u8	unused_0[4];
+};
+
+/* hwrm_stat_ctx_clr_stats_output (size:128b/16B) */
+struct hwrm_stat_ctx_clr_stats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_pcie_qstats_input (size:256b/32B) */
+struct hwrm_pcie_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	pcie_stat_size;
+	u8	unused_0[6];
+	__le64	pcie_stat_host_addr;
+};
+
+/* hwrm_pcie_qstats_output (size:128b/16B) */
+struct hwrm_pcie_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	pcie_stat_size;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* pcie_ctx_hw_stats (size:768b/96B) */
+struct pcie_ctx_hw_stats {
+	__le64	pcie_pl_signal_integrity;
+	__le64	pcie_dl_signal_integrity;
+	__le64	pcie_tl_signal_integrity;
+	__le64	pcie_link_integrity;
+	__le64	pcie_tx_traffic_rate;
+	__le64	pcie_rx_traffic_rate;
+	__le64	pcie_tx_dllp_statistics;
+	__le64	pcie_rx_dllp_statistics;
+	__le64	pcie_equalization_time;
+	__le32	pcie_ltssm_histogram[4];
+	__le64	pcie_recovery_histogram;
+};
+
+/* pcie_ctx_hw_stats_v2 (size:4096b/512B) */
+struct pcie_ctx_hw_stats_v2 {
+	__le64	pcie_pl_signal_integrity;
+	__le64	pcie_dl_signal_integrity;
+	__le64	pcie_tl_signal_integrity;
+	__le64	pcie_link_integrity;
+	__le64	pcie_tx_traffic_rate;
+	__le64	pcie_rx_traffic_rate;
+	__le64	pcie_tx_dllp_statistics;
+	__le64	pcie_rx_dllp_statistics;
+	__le64	pcie_equalization_time;
+	__le32	pcie_ltssm_histogram[4];
+	__le64	pcie_recovery_histogram;
+	__le32	pcie_tl_credit_nph_histogram[8];
+	__le32	pcie_tl_credit_ph_histogram[8];
+	__le32	pcie_tl_credit_pd_histogram[8];
+	__le32	pcie_cmpl_latest_times[4];
+	__le32	pcie_cmpl_longest_time;
+	__le32	pcie_cmpl_shortest_time;
+	__le32	unused_0[2];
+	__le32	pcie_cmpl_latest_headers[4][4];
+	__le32	pcie_cmpl_longest_headers[4][4];
+	__le32	pcie_cmpl_shortest_headers[4][4];
+	__le32	pcie_wr_latency_histogram[12];
+	__le32	pcie_wr_latency_all_normal_count;
+	__le32	unused_1;
+	__le64	pcie_posted_packet_count;
+	__le64	pcie_non_posted_packet_count;
+	__le64	pcie_other_packet_count;
+	__le64	pcie_blocked_packet_count;
+	__le64	pcie_cmpl_packet_count;
+};
+
+/* hwrm_stat_generic_qstats_input (size:256b/32B) */
+struct hwrm_stat_generic_qstats_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	generic_stat_size;
+	u8	flags;
+	#define STAT_GENERIC_QSTATS_REQ_FLAGS_COUNTER_MASK     0x1UL
+	u8	unused_0[5];
+	__le64	generic_stat_host_addr;
+};
+
+/* hwrm_stat_generic_qstats_output (size:128b/16B) */
+struct hwrm_stat_generic_qstats_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	generic_stat_size;
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* generic_sw_hw_stats (size:1472b/184B) */
+struct generic_sw_hw_stats {
+	__le64	pcie_statistics_tx_tlp;
+	__le64	pcie_statistics_rx_tlp;
+	__le64	pcie_credit_fc_hdr_posted;
+	__le64	pcie_credit_fc_hdr_nonposted;
+	__le64	pcie_credit_fc_hdr_cmpl;
+	__le64	pcie_credit_fc_data_posted;
+	__le64	pcie_credit_fc_data_nonposted;
+	__le64	pcie_credit_fc_data_cmpl;
+	__le64	pcie_credit_fc_tgt_nonposted;
+	__le64	pcie_credit_fc_tgt_data_posted;
+	__le64	pcie_credit_fc_tgt_hdr_posted;
+	__le64	pcie_credit_fc_cmpl_hdr_posted;
+	__le64	pcie_credit_fc_cmpl_data_posted;
+	__le64	pcie_cmpl_longest;
+	__le64	pcie_cmpl_shortest;
+	__le64	cache_miss_count_cfcq;
+	__le64	cache_miss_count_cfcs;
+	__le64	cache_miss_count_cfcc;
+	__le64	cache_miss_count_cfcm;
+	__le64	hw_db_recov_dbs_dropped;
+	__le64	hw_db_recov_drops_serviced;
+	__le64	hw_db_recov_dbs_recovered;
+	__le64	hw_db_recov_oo_drop_count;
+};
+
+/* hwrm_fw_reset_input (size:192b/24B) */
+struct hwrm_fw_reset_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	embedded_proc_type;
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_BOOT                  0x0UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_MGMT                  0x1UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_NETCTRL               0x2UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_ROCE                  0x3UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST                  0x4UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_AP                    0x5UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_CHIP                  0x6UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_HOST_RESOURCE_REINIT  0x7UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION 0x8UL
+	#define FW_RESET_REQ_EMBEDDED_PROC_TYPE_LAST                 FW_RESET_REQ_EMBEDDED_PROC_TYPE_IMPACTLESS_ACTIVATION
+	u8	selfrst_status;
+	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTNONE      0x0UL
+	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTASAP      0x1UL
+	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTPCIERST   0x2UL
+	#define FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
+	#define FW_RESET_REQ_SELFRST_STATUS_LAST            FW_RESET_REQ_SELFRST_STATUS_SELFRSTIMMEDIATE
+	u8	host_idx;
+	u8	flags;
+	#define FW_RESET_REQ_FLAGS_RESET_GRACEFUL     0x1UL
+	#define FW_RESET_REQ_FLAGS_FW_ACTIVATION      0x2UL
+	u8	unused_0[4];
+};
+
+/* hwrm_fw_reset_output (size:128b/16B) */
+struct hwrm_fw_reset_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	selfrst_status;
+	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTNONE      0x0UL
+	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTASAP      0x1UL
+	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTPCIERST   0x2UL
+	#define FW_RESET_RESP_SELFRST_STATUS_SELFRSTIMMEDIATE 0x3UL
+	#define FW_RESET_RESP_SELFRST_STATUS_LAST            FW_RESET_RESP_SELFRST_STATUS_SELFRSTIMMEDIATE
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_fw_qstatus_input (size:192b/24B) */
+struct hwrm_fw_qstatus_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	embedded_proc_type;
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_BOOT    0x0UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_MGMT    0x1UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_NETCTRL 0x2UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_ROCE    0x3UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_HOST    0x4UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_AP      0x5UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP    0x6UL
+	#define FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_LAST   FW_QSTATUS_REQ_EMBEDDED_PROC_TYPE_CHIP
+	u8	unused_0[7];
+};
+
+/* hwrm_fw_qstatus_output (size:128b/16B) */
+struct hwrm_fw_qstatus_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	selfrst_status;
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTNONE    0x0UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTASAP    0x1UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPCIERST 0x2UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER   0x3UL
+	#define FW_QSTATUS_RESP_SELFRST_STATUS_LAST          FW_QSTATUS_RESP_SELFRST_STATUS_SELFRSTPOWER
+	u8	nvm_option_action_status;
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_NONE     0x0UL
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_HOTRESET 0x1UL
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_WARMBOOT 0x2UL
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_COLDBOOT 0x3UL
+	#define FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_LAST                  FW_QSTATUS_RESP_NVM_OPTION_ACTION_STATUS_NVMOPT_ACTION_COLDBOOT
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_fw_set_time_input (size:256b/32B) */
+struct hwrm_fw_set_time_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	year;
+	#define FW_SET_TIME_REQ_YEAR_UNKNOWN 0x0UL
+	#define FW_SET_TIME_REQ_YEAR_LAST   FW_SET_TIME_REQ_YEAR_UNKNOWN
+	u8	month;
+	u8	day;
+	u8	hour;
+	u8	minute;
+	u8	second;
+	u8	unused_0;
+	__le16	millisecond;
+	__le16	zone;
+	#define FW_SET_TIME_REQ_ZONE_UTC     0
+	#define FW_SET_TIME_REQ_ZONE_UNKNOWN 65535
+	#define FW_SET_TIME_REQ_ZONE_LAST   FW_SET_TIME_REQ_ZONE_UNKNOWN
+	u8	unused_1[4];
+};
+
+/* hwrm_fw_set_time_output (size:128b/16B) */
+struct hwrm_fw_set_time_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_struct_hdr (size:128b/16B) */
+struct hwrm_struct_hdr {
+	__le16	struct_id;
+	#define STRUCT_HDR_STRUCT_ID_LLDP_CFG              0x41bUL
+	#define STRUCT_HDR_STRUCT_ID_DCBX_ETS              0x41dUL
+	#define STRUCT_HDR_STRUCT_ID_DCBX_PFC              0x41fUL
+	#define STRUCT_HDR_STRUCT_ID_DCBX_APP              0x421UL
+	#define STRUCT_HDR_STRUCT_ID_DCBX_FEATURE_STATE    0x422UL
+	#define STRUCT_HDR_STRUCT_ID_LLDP_GENERIC          0x424UL
+	#define STRUCT_HDR_STRUCT_ID_LLDP_DEVICE           0x426UL
+	#define STRUCT_HDR_STRUCT_ID_POWER_BKUP            0x427UL
+	#define STRUCT_HDR_STRUCT_ID_PEER_MMAP             0x429UL
+	#define STRUCT_HDR_STRUCT_ID_AFM_OPAQUE            0x1UL
+	#define STRUCT_HDR_STRUCT_ID_PORT_DESCRIPTION      0xaUL
+	#define STRUCT_HDR_STRUCT_ID_RSS_V2                0x64UL
+	#define STRUCT_HDR_STRUCT_ID_MSIX_PER_VF           0xc8UL
+	#define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_COUNT 0x12cUL
+	#define STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND 0x12dUL
+	#define STRUCT_HDR_STRUCT_ID_LAST                 STRUCT_HDR_STRUCT_ID_UDCC_RTT_BUCKET_BOUND
+	__le16	len;
+	u8	version;
+	#define STRUCT_HDR_VERSION_0 0x0UL
+	#define STRUCT_HDR_VERSION_1 0x1UL
+	#define STRUCT_HDR_VERSION_LAST STRUCT_HDR_VERSION_1
+	u8	count;
+	__le16	subtype;
+	__le16	next_offset;
+	#define STRUCT_HDR_NEXT_OFFSET_LAST 0x0UL
+	u8	unused_0[6];
+};
+
+/* hwrm_struct_data_dcbx_app (size:64b/8B) */
+struct hwrm_struct_data_dcbx_app {
+	__be16	protocol_id;
+	u8	protocol_selector;
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_ETHER_TYPE   0x1UL
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_PORT     0x2UL
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_UDP_PORT     0x3UL
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_UDP_PORT 0x4UL
+	#define STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_LAST        STRUCT_DATA_DCBX_APP_PROTOCOL_SELECTOR_TCP_UDP_PORT
+	u8	priority;
+	u8	valid;
+	u8	unused_0[3];
+};
+
+/* hwrm_fw_set_structured_data_input (size:256b/32B) */
+struct hwrm_fw_set_structured_data_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	src_data_addr;
+	__le16	data_len;
+	u8	hdr_cnt;
+	u8	unused_0[5];
+};
+
+/* hwrm_fw_set_structured_data_output (size:128b/16B) */
+struct hwrm_fw_set_structured_data_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_fw_set_structured_data_cmd_err (size:64b/8B) */
+struct hwrm_fw_set_structured_data_cmd_err {
+	u8	code;
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN     0x0UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_HDR_CNT 0x1UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_FMT     0x2UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID      0x3UL
+	#define FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_LAST       FW_SET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID
+	u8	unused_0[7];
+};
+
+/* hwrm_fw_get_structured_data_input (size:256b/32B) */
+struct hwrm_fw_get_structured_data_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	dest_data_addr;
+	__le16	data_len;
+	__le16	structure_id;
+	__le16	subtype;
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_UNUSED                  0x0UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_ALL                     0xffffUL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_ADMIN       0x100UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_PEER        0x101UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NEAR_BRIDGE_OPERATIONAL 0x102UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_ADMIN          0x200UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_PEER           0x201UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_NON_TPMR_OPERATIONAL    0x202UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL        0x300UL
+	#define FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_LAST                   FW_GET_STRUCTURED_DATA_REQ_SUBTYPE_HOST_OPERATIONAL
+	u8	count;
+	u8	unused_0;
+};
+
+/* hwrm_fw_get_structured_data_output (size:128b/16B) */
+struct hwrm_fw_get_structured_data_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	hdr_cnt;
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_fw_get_structured_data_cmd_err (size:64b/8B) */
+struct hwrm_fw_get_structured_data_cmd_err {
+	u8	code;
+	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_UNKNOWN 0x0UL
+	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID  0x3UL
+	#define FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_LAST   FW_GET_STRUCTURED_DATA_CMD_ERR_CODE_BAD_ID
+	u8	unused_0[7];
+};
+
+/* hwrm_fw_livepatch_query_input (size:192b/24B) */
+struct hwrm_fw_livepatch_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	fw_target;
+	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_COMMON_FW 0x1UL
+	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW 0x2UL
+	#define FW_LIVEPATCH_QUERY_REQ_FW_TARGET_LAST     FW_LIVEPATCH_QUERY_REQ_FW_TARGET_SECURE_FW
+	u8	unused_0[7];
+};
+
+/* hwrm_fw_livepatch_query_output (size:640b/80B) */
+struct hwrm_fw_livepatch_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	char	install_ver[32];
+	char	active_ver[32];
+	__le16	status_flags;
+	#define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_INSTALL     0x1UL
+	#define FW_LIVEPATCH_QUERY_RESP_STATUS_FLAGS_ACTIVE      0x2UL
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_fw_livepatch_input (size:256b/32B) */
+struct hwrm_fw_livepatch_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	opcode;
+	#define FW_LIVEPATCH_REQ_OPCODE_ACTIVATE   0x1UL
+	#define FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE 0x2UL
+	#define FW_LIVEPATCH_REQ_OPCODE_LAST      FW_LIVEPATCH_REQ_OPCODE_DEACTIVATE
+	u8	fw_target;
+	#define FW_LIVEPATCH_REQ_FW_TARGET_COMMON_FW 0x1UL
+	#define FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW 0x2UL
+	#define FW_LIVEPATCH_REQ_FW_TARGET_LAST     FW_LIVEPATCH_REQ_FW_TARGET_SECURE_FW
+	u8	loadtype;
+	#define FW_LIVEPATCH_REQ_LOADTYPE_NVM_INSTALL   0x1UL
+	#define FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT 0x2UL
+	#define FW_LIVEPATCH_REQ_LOADTYPE_LAST         FW_LIVEPATCH_REQ_LOADTYPE_MEMORY_DIRECT
+	u8	flags;
+	__le32	patch_len;
+	__le64	host_addr;
+};
+
+/* hwrm_fw_livepatch_output (size:128b/16B) */
+struct hwrm_fw_livepatch_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_fw_livepatch_cmd_err (size:64b/8B) */
+struct hwrm_fw_livepatch_cmd_err {
+	u8	code;
+	#define FW_LIVEPATCH_CMD_ERR_CODE_UNKNOWN         0x0UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_OPCODE  0x1UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_TARGET  0x2UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_SUPPORTED   0x3UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_INSTALLED   0x4UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_NOT_PATCHED     0x5UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_AUTH_FAIL       0x6UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_HEADER  0x7UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_INVALID_SIZE    0x8UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED 0x9UL
+	#define FW_LIVEPATCH_CMD_ERR_CODE_LAST           FW_LIVEPATCH_CMD_ERR_CODE_ALREADY_PATCHED
+	u8	unused_0[7];
+};
+
+/* hwrm_exec_fwd_resp_input (size:1024b/128B) */
+struct hwrm_exec_fwd_resp_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	encap_request[26];
+	__le16	encap_resp_target_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_exec_fwd_resp_output (size:128b/16B) */
+struct hwrm_exec_fwd_resp_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_reject_fwd_resp_input (size:1024b/128B) */
+struct hwrm_reject_fwd_resp_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	encap_request[26];
+	__le16	encap_resp_target_id;
+	u8	unused_0[6];
+};
+
+/* hwrm_reject_fwd_resp_output (size:128b/16B) */
+struct hwrm_reject_fwd_resp_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_fwd_resp_input (size:1024b/128B) */
+struct hwrm_fwd_resp_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	encap_resp_target_id;
+	__le16	encap_resp_cmpl_ring;
+	__le16	encap_resp_len;
+	u8	unused_0;
+	u8	unused_1;
+	__le64	encap_resp_addr;
+	__le32	encap_resp[24];
+};
+
+/* hwrm_fwd_resp_output (size:128b/16B) */
+struct hwrm_fwd_resp_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_fwd_async_event_cmpl_input (size:320b/40B) */
+struct hwrm_fwd_async_event_cmpl_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	encap_async_event_target_id;
+	u8	unused_0[6];
+	__le32	encap_async_event_cmpl[4];
+};
+
+/* hwrm_fwd_async_event_cmpl_output (size:128b/16B) */
+struct hwrm_fwd_async_event_cmpl_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_temp_monitor_query_input (size:128b/16B) */
+struct hwrm_temp_monitor_query_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_temp_monitor_query_output (size:192b/24B) */
+struct hwrm_temp_monitor_query_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	temp;
+	u8	phy_temp;
+	u8	om_temp;
+	u8	flags;
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_TEMP_NOT_AVAILABLE             0x1UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_PHY_TEMP_NOT_AVAILABLE         0x2UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_NOT_PRESENT                 0x4UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_OM_TEMP_NOT_AVAILABLE          0x8UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_EXT_TEMP_FIELDS_AVAILABLE      0x10UL
+	#define TEMP_MONITOR_QUERY_RESP_FLAGS_THRESHOLD_VALUES_AVAILABLE     0x20UL
+	u8	temp2;
+	u8	phy_temp2;
+	u8	om_temp2;
+	u8	warn_threshold;
+	u8	critical_threshold;
+	u8	fatal_threshold;
+	u8	shutdown_threshold;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* hwrm_wol_filter_alloc_input (size:512b/64B) */
+struct hwrm_wol_filter_alloc_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	__le32	enables;
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_MAC_ADDRESS           0x1UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_OFFSET        0x2UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_SIZE      0x4UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_BUF_ADDR      0x8UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_ADDR     0x10UL
+	#define WOL_FILTER_ALLOC_REQ_ENABLES_PATTERN_MASK_SIZE     0x20UL
+	__le16	port_id;
+	u8	wol_type;
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_MAGICPKT 0x0UL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_BMP      0x1UL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID  0xffUL
+	#define WOL_FILTER_ALLOC_REQ_WOL_TYPE_LAST    WOL_FILTER_ALLOC_REQ_WOL_TYPE_INVALID
+	u8	unused_0[5];
+	u8	mac_address[6];
+	__le16	pattern_offset;
+	__le16	pattern_buf_size;
+	__le16	pattern_mask_size;
+	u8	unused_1[4];
+	__le64	pattern_buf_addr;
+	__le64	pattern_mask_addr;
+};
+
+/* hwrm_wol_filter_alloc_output (size:128b/16B) */
+struct hwrm_wol_filter_alloc_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	wol_filter_id;
+	u8	unused_0[6];
+	u8	valid;
+};
+
+/* hwrm_wol_filter_free_input (size:256b/32B) */
+struct hwrm_wol_filter_free_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	flags;
+	#define WOL_FILTER_FREE_REQ_FLAGS_FREE_ALL_WOL_FILTERS     0x1UL
+	__le32	enables;
+	#define WOL_FILTER_FREE_REQ_ENABLES_WOL_FILTER_ID     0x1UL
+	__le16	port_id;
+	u8	wol_filter_id;
+	u8	unused_0[5];
+};
+
+/* hwrm_wol_filter_free_output (size:128b/16B) */
+struct hwrm_wol_filter_free_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_wol_filter_qcfg_input (size:448b/56B) */
+struct hwrm_wol_filter_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	__le16	handle;
+	u8	unused_0[4];
+	__le64	pattern_buf_addr;
+	__le16	pattern_buf_size;
+	u8	unused_1[6];
+	__le64	pattern_mask_addr;
+	__le16	pattern_mask_size;
+	u8	unused_2[6];
+};
+
+/* hwrm_wol_filter_qcfg_output (size:256b/32B) */
+struct hwrm_wol_filter_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	next_handle;
+	u8	wol_filter_id;
+	u8	wol_type;
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_MAGICPKT 0x0UL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_BMP      0x1UL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID  0xffUL
+	#define WOL_FILTER_QCFG_RESP_WOL_TYPE_LAST    WOL_FILTER_QCFG_RESP_WOL_TYPE_INVALID
+	__le32	unused_0;
+	u8	mac_address[6];
+	__le16	pattern_offset;
+	__le16	pattern_size;
+	__le16	pattern_mask_size;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_wol_reason_qcfg_input (size:320b/40B) */
+struct hwrm_wol_reason_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	port_id;
+	u8	unused_0[6];
+	__le64	wol_pkt_buf_addr;
+	__le16	wol_pkt_buf_size;
+	u8	unused_1[6];
+};
+
+/* hwrm_wol_reason_qcfg_output (size:128b/16B) */
+struct hwrm_wol_reason_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	wol_filter_id;
+	u8	wol_reason;
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_MAGICPKT 0x0UL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_BMP      0x1UL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_INVALID  0xffUL
+	#define WOL_REASON_QCFG_RESP_WOL_REASON_LAST    WOL_REASON_QCFG_RESP_WOL_REASON_INVALID
+	u8	wol_pkt_len;
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* hwrm_dbg_read_direct_input (size:256b/32B) */
+struct hwrm_dbg_read_direct_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	read_addr;
+	__le32	read_len32;
+};
+
+/* hwrm_dbg_read_direct_output (size:128b/16B) */
+struct hwrm_dbg_read_direct_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	crc32;
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_qcaps_input (size:192b/24B) */
+struct hwrm_dbg_qcaps_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	u8	unused_0[6];
+};
+
+/* hwrm_dbg_qcaps_output (size:192b/24B) */
+struct hwrm_dbg_qcaps_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	u8	unused_0[2];
+	__le32	coredump_component_disable_caps;
+	#define DBG_QCAPS_RESP_COREDUMP_COMPONENT_DISABLE_CAPS_NVRAM     0x1UL
+	__le32	flags;
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_NVM             0x1UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_HOST_DDR        0x2UL
+	#define DBG_QCAPS_RESP_FLAGS_CRASHDUMP_SOC_DDR         0x4UL
+	#define DBG_QCAPS_RESP_FLAGS_USEQ                      0x8UL
+	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_DDR         0x10UL
+	#define DBG_QCAPS_RESP_FLAGS_COREDUMP_HOST_CAPTURE     0x20UL
+	#define DBG_QCAPS_RESP_FLAGS_PTRACE                    0x40UL
+	#define DBG_QCAPS_RESP_FLAGS_REG_ACCESS_RESTRICTED     0x80UL
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_qcfg_input (size:192b/24B) */
+struct hwrm_dbg_qcfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	fid;
+	__le16	flags;
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_MASK         0x3UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_SFT          0
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_NVM       0x0UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_HOST_DDR  0x1UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR   0x2UL
+	#define DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_LAST          DBG_QCFG_REQ_FLAGS_CRASHDUMP_SIZE_FOR_DEST_DEST_SOC_DDR
+	__le32	coredump_component_disable_flags;
+	#define DBG_QCFG_REQ_COREDUMP_COMPONENT_DISABLE_FLAGS_NVRAM     0x1UL
+};
+
+/* hwrm_dbg_qcfg_output (size:256b/32B) */
+struct hwrm_dbg_qcfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	fid;
+	u8	unused_0[2];
+	__le32	coredump_size;
+	__le32	flags;
+	#define DBG_QCFG_RESP_FLAGS_UART_LOG               0x1UL
+	#define DBG_QCFG_RESP_FLAGS_UART_LOG_SECONDARY     0x2UL
+	#define DBG_QCFG_RESP_FLAGS_FW_TRACE               0x4UL
+	#define DBG_QCFG_RESP_FLAGS_FW_TRACE_SECONDARY     0x8UL
+	#define DBG_QCFG_RESP_FLAGS_DEBUG_NOTIFY           0x10UL
+	#define DBG_QCFG_RESP_FLAGS_JTAG_DEBUG             0x20UL
+	__le16	async_cmpl_ring;
+	u8	unused_2[2];
+	__le32	crashdump_size;
+	u8	unused_3[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_crashdump_medium_cfg_input (size:320b/40B) */
+struct hwrm_dbg_crashdump_medium_cfg_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	output_dest_flags;
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_TYPE_DDR     0x1UL
+	__le16	pg_size_lvl;
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_MASK      0x3UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_SFT       0
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_0       0x0UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_1       0x1UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2       0x2UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LAST       DBG_CRASHDUMP_MEDIUM_CFG_REQ_LVL_LVL_2
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_MASK  0x1cUL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_SFT   2
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_4K   (0x0UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8K   (0x1UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_64K  (0x2UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_2M   (0x3UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_8M   (0x4UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G   (0x5UL << 2)
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_LAST   DBG_CRASHDUMP_MEDIUM_CFG_REQ_PG_SIZE_PG_1G
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_MASK 0xffe0UL
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_UNUSED11_SFT  5
+	__le32	size;
+	__le32	coredump_component_disable_flags;
+	#define DBG_CRASHDUMP_MEDIUM_CFG_REQ_NVRAM     0x1UL
+	__le32	unused_0;
+	__le64	pbl;
+};
+
+/* hwrm_dbg_crashdump_medium_cfg_output (size:128b/16B) */
+struct hwrm_dbg_crashdump_medium_cfg_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_1[7];
+	u8	valid;
+};
+
+/* coredump_segment_record (size:128b/16B) */
+struct coredump_segment_record {
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	max_instances;
+	u8	version_hi;
+	u8	version_low;
+	u8	seg_flags;
+	u8	compress_flags;
+	#define SFLAG_COMPRESSED_ZLIB     0x1UL
+	u8	unused_0[2];
+	__le32	segment_len;
+};
+
+/* hwrm_dbg_coredump_list_input (size:256b/32B) */
+struct hwrm_dbg_coredump_list_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	host_buf_len;
+	__le16	seq_no;
+	u8	flags;
+	#define DBG_COREDUMP_LIST_REQ_FLAGS_CRASHDUMP     0x1UL
+	u8	unused_0[1];
+};
+
+/* hwrm_dbg_coredump_list_output (size:128b/16B) */
+struct hwrm_dbg_coredump_list_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define DBG_COREDUMP_LIST_RESP_FLAGS_MORE     0x1UL
+	u8	unused_0;
+	__le16	total_segments;
+	__le16	data_len;
+	u8	unused_1;
+	u8	valid;
+};
+
+/* hwrm_dbg_coredump_initiate_input (size:256b/32B) */
+struct hwrm_dbg_coredump_initiate_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	instance;
+	__le16	unused_0;
+	u8	seg_flags;
+	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_LIVE_DATA                0x1UL
+	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_CRASH_DATA               0x2UL
+	#define DBG_COREDUMP_INITIATE_REQ_SEG_FLAGS_COLLECT_CTX_L1_CACHE     0x4UL
+	u8	unused_1[7];
+};
+
+/* hwrm_dbg_coredump_initiate_output (size:128b/16B) */
+struct hwrm_dbg_coredump_initiate_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* coredump_data_hdr (size:128b/16B) */
+struct coredump_data_hdr {
+	__le32	address;
+	__le32	flags_length;
+	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_ACTUAL_LEN_MASK     0xffffffUL
+	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_ACTUAL_LEN_SFT      0
+	#define COREDUMP_DATA_HDR_FLAGS_LENGTH_INDIRECT_ACCESS     0x1000000UL
+	__le32	instance;
+	__le32	next_offset;
+};
+
+/* hwrm_dbg_coredump_retrieve_input (size:448b/56B) */
+struct hwrm_dbg_coredump_retrieve_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le32	host_buf_len;
+	__le32	unused_0;
+	__le16	component_id;
+	__le16	segment_id;
+	__le16	instance;
+	__le16	unused_1;
+	u8	seg_flags;
+	u8	unused_2;
+	__le16	unused_3;
+	__le32	unused_4;
+	__le32	seq_no;
+	__le32	unused_5;
+};
+
+/* hwrm_dbg_coredump_retrieve_output (size:128b/16B) */
+struct hwrm_dbg_coredump_retrieve_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	flags;
+	#define DBG_COREDUMP_RETRIEVE_RESP_FLAGS_MORE     0x1UL
+	u8	unused_0;
+	__le16	data_len;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_dbg_ring_info_get_input (size:192b/24B) */
+struct hwrm_dbg_ring_info_get_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	ring_type;
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_L2_CMPL 0x0UL
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_TX      0x1UL
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_RX      0x2UL
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_NQ      0x3UL
+	#define DBG_RING_INFO_GET_REQ_RING_TYPE_LAST   DBG_RING_INFO_GET_REQ_RING_TYPE_NQ
+	u8	unused_0[3];
+	__le32	fw_ring_id;
+};
+
+/* hwrm_dbg_ring_info_get_output (size:192b/24B) */
+struct hwrm_dbg_ring_info_get_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	producer_index;
+	__le32	consumer_index;
+	__le32	cag_vector_ctrl;
+	__le16	st_tag;
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_dbg_log_buffer_flush_input (size:192b/24B) */
+struct hwrm_dbg_log_buffer_flush_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	type;
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT_TRACE           0x0UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_SRT2_TRACE          0x1UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT_TRACE           0x2UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CRT2_TRACE          0x3UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP0_TRACE         0x4UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_L2_HWRM_TRACE       0x5UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_ROCE_HWRM_TRACE     0x6UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA0_TRACE           0x7UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA1_TRACE           0x8UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_CA2_TRACE           0x9UL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_RIGP1_TRACE         0xaUL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE 0xbUL
+	#define DBG_LOG_BUFFER_FLUSH_REQ_TYPE_LAST               DBG_LOG_BUFFER_FLUSH_REQ_TYPE_AFM_KONG_HWRM_TRACE
+	u8	unused_1[2];
+	__le32	flags;
+	#define DBG_LOG_BUFFER_FLUSH_REQ_FLAGS_FLUSH_ALL_BUFFERS     0x1UL
+};
+
+/* hwrm_dbg_log_buffer_flush_output (size:128b/16B) */
+struct hwrm_dbg_log_buffer_flush_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	current_buffer_offset;
+	u8	unused_1[3];
+	u8	valid;
+};
+
+/* hwrm_nvm_read_input (size:320b/40B) */
+struct hwrm_nvm_read_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+	__le16	dir_idx;
+	u8	unused_0[2];
+	__le32	offset;
+	__le32	len;
+	u8	unused_1[4];
+};
+
+/* hwrm_nvm_read_output (size:128b/16B) */
+struct hwrm_nvm_read_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_get_dir_entries_input (size:192b/24B) */
+struct hwrm_nvm_get_dir_entries_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_dest_addr;
+};
+
+/* hwrm_nvm_get_dir_entries_output (size:128b/16B) */
+struct hwrm_nvm_get_dir_entries_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_get_dir_info_input (size:128b/16B) */
+struct hwrm_nvm_get_dir_info_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_nvm_get_dir_info_output (size:192b/24B) */
+struct hwrm_nvm_get_dir_info_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	entries;
+	__le32	entry_length;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_write_input (size:448b/56B) */
+struct hwrm_nvm_write_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_src_addr;
+	__le16	dir_type;
+	__le16	dir_ordinal;
+	__le16	dir_ext;
+	__le16	dir_attr;
+	__le32	dir_data_length;
+	__le16	option;
+	__le16	flags;
+	#define NVM_WRITE_REQ_FLAGS_KEEP_ORIG_ACTIVE_IMG     0x1UL
+	#define NVM_WRITE_REQ_FLAGS_BATCH_MODE               0x2UL
+	#define NVM_WRITE_REQ_FLAGS_BATCH_LAST               0x4UL
+	#define NVM_WRITE_REQ_FLAGS_SKIP_CRID_CHECK          0x8UL
+	__le32	dir_item_length;
+	__le32	offset;
+	__le32	len;
+	__le32	unused_0;
+};
+
+/* hwrm_nvm_write_output (size:128b/16B) */
+struct hwrm_nvm_write_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	dir_item_length;
+	__le16	dir_idx;
+	u8	unused_0;
+	u8	valid;
+};
+
+/* hwrm_nvm_write_cmd_err (size:64b/8B) */
+struct hwrm_nvm_write_cmd_err {
+	u8	code;
+	#define NVM_WRITE_CMD_ERR_CODE_UNKNOWN  0x0UL
+	#define NVM_WRITE_CMD_ERR_CODE_FRAG_ERR 0x1UL
+	#define NVM_WRITE_CMD_ERR_CODE_NO_SPACE 0x2UL
+	#define NVM_WRITE_CMD_ERR_CODE_LAST    NVM_WRITE_CMD_ERR_CODE_NO_SPACE
+	u8	unused_0[7];
+};
+
+/* hwrm_nvm_modify_input (size:320b/40B) */
+struct hwrm_nvm_modify_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	host_src_addr;
+	__le16	dir_idx;
+	__le16	flags;
+	#define NVM_MODIFY_REQ_FLAGS_BATCH_MODE     0x1UL
+	#define NVM_MODIFY_REQ_FLAGS_BATCH_LAST     0x2UL
+	__le32	offset;
+	__le32	len;
+	u8	unused_1[4];
+};
+
+/* hwrm_nvm_modify_output (size:128b/16B) */
+struct hwrm_nvm_modify_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_find_dir_entry_input (size:256b/32B) */
+struct hwrm_nvm_find_dir_entry_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define NVM_FIND_DIR_ENTRY_REQ_ENABLES_DIR_IDX_VALID     0x1UL
+	__le16	dir_idx;
+	__le16	dir_type;
+	__le16	dir_ordinal;
+	__le16	dir_ext;
+	u8	opt_ordinal;
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_MASK 0x3UL
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_SFT 0
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_EQ    0x0UL
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GE    0x1UL
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GT    0x2UL
+	#define NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_LAST NVM_FIND_DIR_ENTRY_REQ_OPT_ORDINAL_GT
+	u8	unused_0[3];
+};
+
+/* hwrm_nvm_find_dir_entry_output (size:256b/32B) */
+struct hwrm_nvm_find_dir_entry_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le32	dir_item_length;
+	__le32	dir_data_length;
+	__le32	fw_ver;
+	__le16	dir_ordinal;
+	__le16	dir_idx;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_erase_dir_entry_input (size:192b/24B) */
+struct hwrm_nvm_erase_dir_entry_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	dir_idx;
+	u8	unused_0[6];
+};
+
+/* hwrm_nvm_erase_dir_entry_output (size:128b/16B) */
+struct hwrm_nvm_erase_dir_entry_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_get_dev_info_input (size:192b/24B) */
+struct hwrm_nvm_get_dev_info_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	flags;
+	#define NVM_GET_DEV_INFO_REQ_FLAGS_SECURITY_SOC_NVM     0x1UL
+	u8	unused_0[7];
+};
+
+/* hwrm_nvm_get_dev_info_output (size:768b/96B) */
+struct hwrm_nvm_get_dev_info_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	manufacturer_id;
+	__le16	device_id;
+	__le32	sector_size;
+	__le32	nvram_size;
+	__le32	reserved_size;
+	__le32	available_size;
+	u8	nvm_cfg_ver_maj;
+	u8	nvm_cfg_ver_min;
+	u8	nvm_cfg_ver_upd;
+	u8	flags;
+	#define NVM_GET_DEV_INFO_RESP_FLAGS_FW_VER_VALID     0x1UL
+	char	pkg_name[16];
+	__le16	hwrm_fw_major;
+	__le16	hwrm_fw_minor;
+	__le16	hwrm_fw_build;
+	__le16	hwrm_fw_patch;
+	__le16	mgmt_fw_major;
+	__le16	mgmt_fw_minor;
+	__le16	mgmt_fw_build;
+	__le16	mgmt_fw_patch;
+	__le16	roce_fw_major;
+	__le16	roce_fw_minor;
+	__le16	roce_fw_build;
+	__le16	roce_fw_patch;
+	__le16	netctrl_fw_major;
+	__le16	netctrl_fw_minor;
+	__le16	netctrl_fw_build;
+	__le16	netctrl_fw_patch;
+	__le16	srt2_fw_major;
+	__le16	srt2_fw_minor;
+	__le16	srt2_fw_build;
+	__le16	srt2_fw_patch;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_mod_dir_entry_input (size:256b/32B) */
+struct hwrm_nvm_mod_dir_entry_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	enables;
+	#define NVM_MOD_DIR_ENTRY_REQ_ENABLES_CHECKSUM     0x1UL
+	__le16	dir_idx;
+	__le16	dir_ordinal;
+	__le16	dir_ext;
+	__le16	dir_attr;
+	__le32	checksum;
+};
+
+/* hwrm_nvm_mod_dir_entry_output (size:128b/16B) */
+struct hwrm_nvm_mod_dir_entry_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_verify_update_input (size:192b/24B) */
+struct hwrm_nvm_verify_update_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le16	dir_type;
+	__le16	dir_ordinal;
+	__le16	dir_ext;
+	u8	unused_0[2];
+};
+
+/* hwrm_nvm_verify_update_output (size:128b/16B) */
+struct hwrm_nvm_verify_update_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_install_update_input (size:192b/24B) */
+struct hwrm_nvm_install_update_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le32	install_type;
+	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_NORMAL 0x0UL
+	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_ALL    0xffffffffUL
+	#define NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_LAST  NVM_INSTALL_UPDATE_REQ_INSTALL_TYPE_ALL
+	__le16	flags;
+	#define NVM_INSTALL_UPDATE_REQ_FLAGS_ERASE_UNUSED_SPACE     0x1UL
+	#define NVM_INSTALL_UPDATE_REQ_FLAGS_REMOVE_UNUSED_PKG      0x2UL
+	#define NVM_INSTALL_UPDATE_REQ_FLAGS_ALLOWED_TO_DEFRAG      0x4UL
+	#define NVM_INSTALL_UPDATE_REQ_FLAGS_VERIFY_ONLY            0x8UL
+	u8	unused_0[2];
+};
+
+/* hwrm_nvm_install_update_output (size:192b/24B) */
+struct hwrm_nvm_install_update_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le64	installed_items;
+	u8	result;
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_SUCCESS                      0x0UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_FAILURE                      0xffUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_MALLOC_FAILURE               0xfdUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_INDEX_PARAMETER      0xfbUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TYPE_PARAMETER       0xf3UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PREREQUISITE         0xf2UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_FILE_HEADER          0xecUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_SIGNATURE            0xebUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_STREAM          0xeaUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_PROP_LENGTH          0xe9UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_MANIFEST             0xe8UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_TRAILER              0xe7UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_CHECKSUM             0xe6UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_ITEM_CHECKSUM        0xe5UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DATA_LENGTH          0xe4UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INVALID_DIRECTIVE            0xe1UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_CHIP_REV         0xceUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_DEVICE_ID        0xcdUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_VENDOR    0xccUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_SUBSYS_ID        0xcbUL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_UNSUPPORTED_PLATFORM         0xc5UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_DUPLICATE_ITEM               0xc4UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_ZERO_LENGTH_ITEM             0xc3UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_CHECKSUM_ERROR       0xb9UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_DATA_ERROR           0xb8UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_INSTALL_AUTHENTICATION_ERROR 0xb7UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_NOT_FOUND               0xb0UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED                  0xa7UL
+	#define NVM_INSTALL_UPDATE_RESP_RESULT_LAST                        NVM_INSTALL_UPDATE_RESP_RESULT_ITEM_LOCKED
+	u8	problem_item;
+	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_NONE    0x0UL
+	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE 0xffUL
+	#define NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_LAST   NVM_INSTALL_UPDATE_RESP_PROBLEM_ITEM_PACKAGE
+	u8	reset_required;
+	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_NONE  0x0UL
+	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_PCI   0x1UL
+	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_POWER 0x2UL
+	#define NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_LAST NVM_INSTALL_UPDATE_RESP_RESET_REQUIRED_POWER
+	u8	unused_0[4];
+	u8	valid;
+};
+
+/* hwrm_nvm_install_update_cmd_err (size:64b/8B) */
+struct hwrm_nvm_install_update_cmd_err {
+	u8	code;
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_UNKNOWN            0x0UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_FRAG_ERR           0x1UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_SPACE           0x2UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_ANTI_ROLLBACK      0x3UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT 0x4UL
+	#define NVM_INSTALL_UPDATE_CMD_ERR_CODE_LAST              NVM_INSTALL_UPDATE_CMD_ERR_CODE_NO_VOLTREG_SUPPORT
+	u8	unused_0[7];
+};
+
+/* hwrm_nvm_get_variable_input (size:320b/40B) */
+struct hwrm_nvm_get_variable_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	dest_data_addr;
+	__le16	data_len;
+	__le16	option_num;
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_0    0x0UL
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
+	#define NVM_GET_VARIABLE_REQ_OPTION_NUM_LAST     NVM_GET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF
+	__le16	dimensions;
+	__le16	index_0;
+	__le16	index_1;
+	__le16	index_2;
+	__le16	index_3;
+	u8	flags;
+	#define NVM_GET_VARIABLE_REQ_FLAGS_FACTORY_DFLT     0x1UL
+	u8	unused_0;
+};
+
+/* hwrm_nvm_get_variable_output (size:128b/16B) */
+struct hwrm_nvm_get_variable_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	__le16	data_len;
+	__le16	option_num;
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_0    0x0UL
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF 0xffffUL
+	#define NVM_GET_VARIABLE_RESP_OPTION_NUM_LAST     NVM_GET_VARIABLE_RESP_OPTION_NUM_RSVD_FFFF
+	u8	unused_0[3];
+	u8	valid;
+};
+
+/* hwrm_nvm_get_variable_cmd_err (size:64b/8B) */
+struct hwrm_nvm_get_variable_cmd_err {
+	u8	code;
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_UNKNOWN       0x0UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR   0x2UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT 0x3UL
+	#define NVM_GET_VARIABLE_CMD_ERR_CODE_LAST         NVM_GET_VARIABLE_CMD_ERR_CODE_LEN_TOO_SHORT
+	u8	unused_0[7];
+};
+
+/* hwrm_nvm_set_variable_input (size:320b/40B) */
+struct hwrm_nvm_set_variable_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	__le64	src_data_addr;
+	__le16	data_len;
+	__le16	option_num;
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_0    0x0UL
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF 0xffffUL
+	#define NVM_SET_VARIABLE_REQ_OPTION_NUM_LAST     NVM_SET_VARIABLE_REQ_OPTION_NUM_RSVD_FFFF
+	__le16	dimensions;
+	__le16	index_0;
+	__le16	index_1;
+	__le16	index_2;
+	__le16	index_3;
+	u8	flags;
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FORCE_FLUSH                0x1UL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_MASK          0xeUL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_SFT           1
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_NONE            (0x0UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1       (0x1UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_AES256          (0x2UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH  (0x3UL << 1)
+	#define NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_LAST           NVM_SET_VARIABLE_REQ_FLAGS_ENCRYPT_MODE_HMAC_SHA1_AUTH
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_MASK        0x70UL
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FLAGS_UNUSED_0_SFT         4
+	#define NVM_SET_VARIABLE_REQ_FLAGS_FACTORY_DEFAULT            0x80UL
+	u8	unused_0;
+};
+
+/* hwrm_nvm_set_variable_output (size:128b/16B) */
+struct hwrm_nvm_set_variable_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* hwrm_nvm_set_variable_cmd_err (size:64b/8B) */
+struct hwrm_nvm_set_variable_cmd_err {
+	u8	code;
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_UNKNOWN       0x0UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_VAR_NOT_EXIST 0x1UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR   0x2UL
+	#define NVM_SET_VARIABLE_CMD_ERR_CODE_LAST         NVM_SET_VARIABLE_CMD_ERR_CODE_CORRUPT_VAR
+	u8	unused_0[7];
+};
+
+/* hwrm_selftest_qlist_input (size:128b/16B) */
+struct hwrm_selftest_qlist_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_selftest_qlist_output (size:2240b/280B) */
+struct hwrm_selftest_qlist_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	num_tests;
+	u8	available_tests;
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_NVM_TEST                 0x1UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_LINK_TEST                0x2UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_REGISTER_TEST            0x4UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_MEMORY_TEST              0x8UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_QLIST_RESP_AVAILABLE_TESTS_ETHERNET_SERDES_TEST     0x20UL
+	u8	offline_tests;
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_NVM_TEST                 0x1UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_LINK_TEST                0x2UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_REGISTER_TEST            0x4UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_MEMORY_TEST              0x8UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_QLIST_RESP_OFFLINE_TESTS_ETHERNET_SERDES_TEST     0x20UL
+	u8	unused_0;
+	__le16	test_timeout;
+	u8	unused_1[2];
+	char	test_name[8][32];
+	u8	eyescope_target_BER_support;
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E8_SUPPORTED  0x0UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E9_SUPPORTED  0x1UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E10_SUPPORTED 0x2UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E11_SUPPORTED 0x3UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED 0x4UL
+	#define SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_LAST              SELFTEST_QLIST_RESP_EYESCOPE_TARGET_BER_SUPPORT_BER_1E12_SUPPORTED
+	u8	unused_2[6];
+	u8	valid;
+};
+
+/* hwrm_selftest_exec_input (size:192b/24B) */
+struct hwrm_selftest_exec_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+	u8	flags;
+	#define SELFTEST_EXEC_REQ_FLAGS_NVM_TEST                 0x1UL
+	#define SELFTEST_EXEC_REQ_FLAGS_LINK_TEST                0x2UL
+	#define SELFTEST_EXEC_REQ_FLAGS_REGISTER_TEST            0x4UL
+	#define SELFTEST_EXEC_REQ_FLAGS_MEMORY_TEST              0x8UL
+	#define SELFTEST_EXEC_REQ_FLAGS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_EXEC_REQ_FLAGS_ETHERNET_SERDES_TEST     0x20UL
+	u8	unused_0[7];
+};
+
+/* hwrm_selftest_exec_output (size:128b/16B) */
+struct hwrm_selftest_exec_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	requested_tests;
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_NVM_TEST                 0x1UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_LINK_TEST                0x2UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_REGISTER_TEST            0x4UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_MEMORY_TEST              0x8UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_EXEC_RESP_REQUESTED_TESTS_ETHERNET_SERDES_TEST     0x20UL
+	u8	test_success;
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_NVM_TEST                 0x1UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_LINK_TEST                0x2UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_REGISTER_TEST            0x4UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_MEMORY_TEST              0x8UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_PCIE_SERDES_TEST         0x10UL
+	#define SELFTEST_EXEC_RESP_TEST_SUCCESS_ETHERNET_SERDES_TEST     0x20UL
+	u8	unused_0[5];
+	u8	valid;
+};
+
+/* hwrm_selftest_irq_input (size:128b/16B) */
+struct hwrm_selftest_irq_input {
+	__le16	req_type;
+	__le16	cmpl_ring;
+	__le16	seq_id;
+	__le16	target_id;
+	__le64	resp_addr;
+};
+
+/* hwrm_selftest_irq_output (size:128b/16B) */
+struct hwrm_selftest_irq_output {
+	__le16	error_code;
+	__le16	req_type;
+	__le16	seq_id;
+	__le16	resp_len;
+	u8	unused_0[7];
+	u8	valid;
+};
+
+/* dbc_dbc (size:64b/8B) */
+struct dbc_dbc {
+	__le32	index;
+	#define DBC_DBC_INDEX_MASK 0xffffffUL
+	#define DBC_DBC_INDEX_SFT  0
+	#define DBC_DBC_EPOCH      0x1000000UL
+	#define DBC_DBC_TOGGLE_MASK 0x6000000UL
+	#define DBC_DBC_TOGGLE_SFT 25
+	__le32	type_path_xid;
+	#define DBC_DBC_XID_MASK          0xfffffUL
+	#define DBC_DBC_XID_SFT           0
+	#define DBC_DBC_PATH_MASK         0x3000000UL
+	#define DBC_DBC_PATH_SFT          24
+	#define DBC_DBC_PATH_ROCE           (0x0UL << 24)
+	#define DBC_DBC_PATH_L2             (0x1UL << 24)
+	#define DBC_DBC_PATH_ENGINE         (0x2UL << 24)
+	#define DBC_DBC_PATH_LAST          DBC_DBC_PATH_ENGINE
+	#define DBC_DBC_VALID             0x4000000UL
+	#define DBC_DBC_DEBUG_TRACE       0x8000000UL
+	#define DBC_DBC_TYPE_MASK         0xf0000000UL
+	#define DBC_DBC_TYPE_SFT          28
+	#define DBC_DBC_TYPE_SQ             (0x0UL << 28)
+	#define DBC_DBC_TYPE_RQ             (0x1UL << 28)
+	#define DBC_DBC_TYPE_SRQ            (0x2UL << 28)
+	#define DBC_DBC_TYPE_SRQ_ARM        (0x3UL << 28)
+	#define DBC_DBC_TYPE_CQ             (0x4UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMSE       (0x5UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMALL      (0x6UL << 28)
+	#define DBC_DBC_TYPE_CQ_ARMENA      (0x7UL << 28)
+	#define DBC_DBC_TYPE_SRQ_ARMENA     (0x8UL << 28)
+	#define DBC_DBC_TYPE_CQ_CUTOFF_ACK  (0x9UL << 28)
+	#define DBC_DBC_TYPE_NQ             (0xaUL << 28)
+	#define DBC_DBC_TYPE_NQ_ARM         (0xbUL << 28)
+	#define DBC_DBC_TYPE_NQ_MASK        (0xeUL << 28)
+	#define DBC_DBC_TYPE_NULL           (0xfUL << 28)
+	#define DBC_DBC_TYPE_LAST          DBC_DBC_TYPE_NULL
+};
+
+/* db_push_start (size:64b/8B) */
+struct db_push_start {
+	u64	db;
+	#define DB_PUSH_START_DB_INDEX_MASK     0xffffffUL
+	#define DB_PUSH_START_DB_INDEX_SFT      0
+	#define DB_PUSH_START_DB_PI_LO_MASK     0xff000000UL
+	#define DB_PUSH_START_DB_PI_LO_SFT      24
+	#define DB_PUSH_START_DB_XID_MASK       0xfffff00000000ULL
+	#define DB_PUSH_START_DB_XID_SFT        32
+	#define DB_PUSH_START_DB_PI_HI_MASK     0xf0000000000000ULL
+	#define DB_PUSH_START_DB_PI_HI_SFT      52
+	#define DB_PUSH_START_DB_TYPE_MASK      0xf000000000000000ULL
+	#define DB_PUSH_START_DB_TYPE_SFT       60
+	#define DB_PUSH_START_DB_TYPE_PUSH_START  (0xcULL << 60)
+	#define DB_PUSH_START_DB_TYPE_PUSH_END    (0xdULL << 60)
+	#define DB_PUSH_START_DB_TYPE_LAST       DB_PUSH_START_DB_TYPE_PUSH_END
+};
+
+/* db_push_end (size:64b/8B) */
+struct db_push_end {
+	u64	db;
+	#define DB_PUSH_END_DB_INDEX_MASK      0xffffffUL
+	#define DB_PUSH_END_DB_INDEX_SFT       0
+	#define DB_PUSH_END_DB_PI_LO_MASK      0xff000000UL
+	#define DB_PUSH_END_DB_PI_LO_SFT       24
+	#define DB_PUSH_END_DB_XID_MASK        0xfffff00000000ULL
+	#define DB_PUSH_END_DB_XID_SFT         32
+	#define DB_PUSH_END_DB_PI_HI_MASK      0xf0000000000000ULL
+	#define DB_PUSH_END_DB_PI_HI_SFT       52
+	#define DB_PUSH_END_DB_PATH_MASK       0x300000000000000ULL
+	#define DB_PUSH_END_DB_PATH_SFT        56
+	#define DB_PUSH_END_DB_PATH_ROCE         (0x0ULL << 56)
+	#define DB_PUSH_END_DB_PATH_L2           (0x1ULL << 56)
+	#define DB_PUSH_END_DB_PATH_ENGINE       (0x2ULL << 56)
+	#define DB_PUSH_END_DB_PATH_LAST        DB_PUSH_END_DB_PATH_ENGINE
+	#define DB_PUSH_END_DB_DEBUG_TRACE     0x800000000000000ULL
+	#define DB_PUSH_END_DB_TYPE_MASK       0xf000000000000000ULL
+	#define DB_PUSH_END_DB_TYPE_SFT        60
+	#define DB_PUSH_END_DB_TYPE_PUSH_START   (0xcULL << 60)
+	#define DB_PUSH_END_DB_TYPE_PUSH_END     (0xdULL << 60)
+	#define DB_PUSH_END_DB_TYPE_LAST        DB_PUSH_END_DB_TYPE_PUSH_END
+};
+
+/* db_push_info (size:64b/8B) */
+struct db_push_info {
+	u32	push_size_push_index;
+	#define DB_PUSH_INFO_PUSH_INDEX_MASK 0xffffffUL
+	#define DB_PUSH_INFO_PUSH_INDEX_SFT 0
+	#define DB_PUSH_INFO_PUSH_SIZE_MASK 0x1f000000UL
+	#define DB_PUSH_INFO_PUSH_SIZE_SFT  24
+	u32	reserved32;
+};
+
+/* fw_status_reg (size:32b/4B) */
+struct fw_status_reg {
+	u32	fw_status;
+	#define FW_STATUS_REG_CODE_MASK              0xffffUL
+	#define FW_STATUS_REG_CODE_SFT               0
+	#define FW_STATUS_REG_CODE_READY               0x8000UL
+	#define FW_STATUS_REG_CODE_LAST               FW_STATUS_REG_CODE_READY
+	#define FW_STATUS_REG_IMAGE_DEGRADED         0x10000UL
+	#define FW_STATUS_REG_RECOVERABLE            0x20000UL
+	#define FW_STATUS_REG_CRASHDUMP_ONGOING      0x40000UL
+	#define FW_STATUS_REG_CRASHDUMP_COMPLETE     0x80000UL
+	#define FW_STATUS_REG_SHUTDOWN               0x100000UL
+	#define FW_STATUS_REG_CRASHED_NO_MASTER      0x200000UL
+	#define FW_STATUS_REG_RECOVERING             0x400000UL
+	#define FW_STATUS_REG_MANU_DEBUG_STATUS      0x800000UL
+};
+
+/* hcomm_status (size:64b/8B) */
+struct hcomm_status {
+	u32	sig_ver;
+	#define HCOMM_STATUS_VER_MASK      0xffUL
+	#define HCOMM_STATUS_VER_SFT       0
+	#define HCOMM_STATUS_VER_LATEST      0x1UL
+	#define HCOMM_STATUS_VER_LAST       HCOMM_STATUS_VER_LATEST
+	#define HCOMM_STATUS_SIGNATURE_MASK 0xffffff00UL
+	#define HCOMM_STATUS_SIGNATURE_SFT 8
+	#define HCOMM_STATUS_SIGNATURE_VAL   (0x484353UL << 8)
+	#define HCOMM_STATUS_SIGNATURE_LAST HCOMM_STATUS_SIGNATURE_VAL
+	u32	fw_status_loc;
+	#define HCOMM_STATUS_TRUE_ADDR_SPACE_MASK    0x3UL
+	#define HCOMM_STATUS_TRUE_ADDR_SPACE_SFT     0
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_PCIE_CFG  0x0UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_GRC       0x1UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR0      0x2UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1      0x3UL
+	#define HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_LAST     HCOMM_STATUS_FW_STATUS_LOC_ADDR_SPACE_BAR1
+	#define HCOMM_STATUS_TRUE_OFFSET_MASK        0xfffffffcUL
+	#define HCOMM_STATUS_TRUE_OFFSET_SFT         2
+};
+#define HCOMM_STATUS_STRUCT_LOC 0x31001F0UL
+
+#endif /* _BNXT_HSI_H_ */
-- 
cgit v1.2.3


From 941ab0b369c983f7867de54c8579fd7f1676ee3c Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 1 Jul 2025 17:23:28 -0700
Subject: rcutorture: Remove support for SRCU-lite

Because SRCU-lite is being replaced by SRCU-fast, this commit removes
support for SRCU-lite from rcutorture.c

Both SRCU-lite and SRCU-fast provide faster readers by dropping the
smp_mb() call from their lock and unlock primitives, but incur a pair
of added RCU grace periods during the SRCU grace period.  There is a
trivial mapping from the SRCU-lite API to that of SRCU-fast, so there
should be no transition issues.

[ paulmck: Apply Christoph Hellwig feedback. ]

Signed-off-by: "Paul E. McKenney" <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.upadhyay@kernel.org>
---
 include/linux/srcu.h    | 2 +-
 kernel/rcu/rcutorture.c | 7 -------
 2 files changed, 1 insertion(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 900b0d5c05f5..c20dacb563e5 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -49,7 +49,7 @@ int init_srcu_struct(struct srcu_struct *ssp);
 #define SRCU_READ_FLAVOR_LITE	0x4		// srcu_read_lock_lite().
 #define SRCU_READ_FLAVOR_FAST	0x8		// srcu_read_lock_fast().
 #define SRCU_READ_FLAVOR_ALL   (SRCU_READ_FLAVOR_NORMAL | SRCU_READ_FLAVOR_NMI | \
-				SRCU_READ_FLAVOR_LITE | SRCU_READ_FLAVOR_FAST) // All of the above.
+				SRCU_READ_FLAVOR_FAST) // All of the above.
 #define SRCU_READ_FLAVOR_SLOWGP	(SRCU_READ_FLAVOR_LITE | SRCU_READ_FLAVOR_FAST)
 						// Flavors requiring synchronize_rcu()
 						// instead of smp_mb().
diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
index 213f23f20a64..7a893d51d02b 100644
--- a/kernel/rcu/rcutorture.c
+++ b/kernel/rcu/rcutorture.c
@@ -718,11 +718,6 @@ static int srcu_torture_read_lock(void)
 		WARN_ON_ONCE(idx & ~0x1);
 		ret += idx << 1;
 	}
-	if (reader_flavor & SRCU_READ_FLAVOR_LITE) {
-		idx = srcu_read_lock_lite(srcu_ctlp);
-		WARN_ON_ONCE(idx & ~0x1);
-		ret += idx << 2;
-	}
 	if (reader_flavor & SRCU_READ_FLAVOR_FAST) {
 		scp = srcu_read_lock_fast(srcu_ctlp);
 		idx = __srcu_ptr_to_ctr(srcu_ctlp, scp);
@@ -756,8 +751,6 @@ static void srcu_torture_read_unlock(int idx)
 	WARN_ON_ONCE((reader_flavor && (idx & ~reader_flavor)) || (!reader_flavor && (idx & ~0x1)));
 	if (reader_flavor & SRCU_READ_FLAVOR_FAST)
 		srcu_read_unlock_fast(srcu_ctlp, __srcu_ctr_to_ptr(srcu_ctlp, (idx & 0x8) >> 3));
-	if (reader_flavor & SRCU_READ_FLAVOR_LITE)
-		srcu_read_unlock_lite(srcu_ctlp, (idx & 0x4) >> 2);
 	if (reader_flavor & SRCU_READ_FLAVOR_NMI)
 		srcu_read_unlock_nmisafe(srcu_ctlp, (idx & 0x2) >> 1);
 	if ((reader_flavor & SRCU_READ_FLAVOR_NORMAL) || !(reader_flavor & SRCU_READ_FLAVOR_ALL))
-- 
cgit v1.2.3


From 623baa01d5b43ca06ba337751d9a4f62199d1715 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 1 Jul 2025 17:23:29 -0700
Subject: srcu: Remove SRCU-lite implementation

This commit removes the SRCU-lite implementation, which has been replaced
by SRCU-fast.

Both SRCU-lite and SRCU-fast provide faster readers by dropping the
smp_mb() call from their lock and unlock primitives, but incur a pair
of added RCU grace periods during the SRCU grace period.  There is a
trivial mapping from the SRCU-lite API to that of SRCU-fast, so there
should be no transition issues.

[ paulmck: Apply Christoph Hellwig feedback. ]

Signed-off-by: "Paul E. McKenney" <paulmck@kernel.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.upadhyay@kernel.org>
---
 include/linux/srcu.h     | 47 ++---------------------------------------------
 include/linux/srcutiny.h |  3 ---
 include/linux/srcutree.h | 38 --------------------------------------
 3 files changed, 2 insertions(+), 86 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index c20dacb563e5..cf711a0f440b 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -46,11 +46,11 @@ int init_srcu_struct(struct srcu_struct *ssp);
 /* Values for SRCU Tree srcu_data ->srcu_reader_flavor, but also used by rcutorture. */
 #define SRCU_READ_FLAVOR_NORMAL	0x1		// srcu_read_lock().
 #define SRCU_READ_FLAVOR_NMI	0x2		// srcu_read_lock_nmisafe().
-#define SRCU_READ_FLAVOR_LITE	0x4		// srcu_read_lock_lite().
+//				0x4		// SRCU-lite is no longer with us.
 #define SRCU_READ_FLAVOR_FAST	0x8		// srcu_read_lock_fast().
 #define SRCU_READ_FLAVOR_ALL   (SRCU_READ_FLAVOR_NORMAL | SRCU_READ_FLAVOR_NMI | \
 				SRCU_READ_FLAVOR_FAST) // All of the above.
-#define SRCU_READ_FLAVOR_SLOWGP	(SRCU_READ_FLAVOR_LITE | SRCU_READ_FLAVOR_FAST)
+#define SRCU_READ_FLAVOR_SLOWGP	SRCU_READ_FLAVOR_FAST
 						// Flavors requiring synchronize_rcu()
 						// instead of smp_mb().
 void __srcu_read_unlock(struct srcu_struct *ssp, int idx) __releases(ssp);
@@ -299,33 +299,6 @@ static inline struct srcu_ctr __percpu *srcu_down_read_fast(struct srcu_struct *
 	return __srcu_read_lock_fast(ssp);
 }
 
-/**
- * srcu_read_lock_lite - register a new reader for an SRCU-protected structure.
- * @ssp: srcu_struct in which to register the new reader.
- *
- * Enter an SRCU read-side critical section, but for a light-weight
- * smp_mb()-free reader.  See srcu_read_lock() for more information.
- *
- * If srcu_read_lock_lite() is ever used on an srcu_struct structure,
- * then none of the other flavors may be used, whether before, during,
- * or after.  Note that grace-period auto-expediting is disabled for _lite
- * srcu_struct structures because auto-expedited grace periods invoke
- * synchronize_rcu_expedited(), IPIs and all.
- *
- * Note that srcu_read_lock_lite() can be invoked only from those contexts
- * where RCU is watching, that is, from contexts where it would be legal
- * to invoke rcu_read_lock().  Otherwise, lockdep will complain.
- */
-static inline int srcu_read_lock_lite(struct srcu_struct *ssp) __acquires(ssp)
-{
-	int retval;
-
-	srcu_check_read_flavor_force(ssp, SRCU_READ_FLAVOR_LITE);
-	retval = __srcu_read_lock_lite(ssp);
-	rcu_try_lock_acquire(&ssp->dep_map);
-	return retval;
-}
-
 /**
  * srcu_read_lock_nmisafe - register a new reader for an SRCU-protected structure.
  * @ssp: srcu_struct in which to register the new reader.
@@ -434,22 +407,6 @@ static inline void srcu_up_read_fast(struct srcu_struct *ssp, struct srcu_ctr __
 	__srcu_read_unlock_fast(ssp, scp);
 }
 
-/**
- * srcu_read_unlock_lite - unregister a old reader from an SRCU-protected structure.
- * @ssp: srcu_struct in which to unregister the old reader.
- * @idx: return value from corresponding srcu_read_lock_lite().
- *
- * Exit a light-weight SRCU read-side critical section.
- */
-static inline void srcu_read_unlock_lite(struct srcu_struct *ssp, int idx)
-	__releases(ssp)
-{
-	WARN_ON_ONCE(idx & ~0x1);
-	srcu_check_read_flavor(ssp, SRCU_READ_FLAVOR_LITE);
-	srcu_lock_release(&ssp->dep_map);
-	__srcu_read_unlock_lite(ssp, idx);
-}
-
 /**
  * srcu_read_unlock_nmisafe - unregister a old reader from an SRCU-protected structure.
  * @ssp: srcu_struct in which to unregister the old reader.
diff --git a/include/linux/srcutiny.h b/include/linux/srcutiny.h
index 380260317d98..51ce25f07930 100644
--- a/include/linux/srcutiny.h
+++ b/include/linux/srcutiny.h
@@ -93,9 +93,6 @@ static inline void __srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_
 	__srcu_read_unlock(ssp, __srcu_ptr_to_ctr(ssp, scp));
 }
 
-#define __srcu_read_lock_lite __srcu_read_lock
-#define __srcu_read_unlock_lite __srcu_read_unlock
-
 static inline void synchronize_srcu_expedited(struct srcu_struct *ssp)
 {
 	synchronize_srcu(ssp);
diff --git a/include/linux/srcutree.h b/include/linux/srcutree.h
index 8bed7e6cc4c1..bf44d8d1e69e 100644
--- a/include/linux/srcutree.h
+++ b/include/linux/srcutree.h
@@ -278,44 +278,6 @@ static inline void __srcu_read_unlock_fast(struct srcu_struct *ssp, struct srcu_
 	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_fast().");
 }
 
-/*
- * Counts the new reader in the appropriate per-CPU element of the
- * srcu_struct.  Returns an index that must be passed to the matching
- * srcu_read_unlock_lite().
- *
- * Note that this_cpu_inc() is an RCU read-side critical section either
- * because it disables interrupts, because it is a single instruction,
- * or because it is a read-modify-write atomic operation, depending on
- * the whims of the architecture.
- */
-static inline int __srcu_read_lock_lite(struct srcu_struct *ssp)
-{
-	struct srcu_ctr __percpu *scp = READ_ONCE(ssp->srcu_ctrp);
-
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_lock_lite().");
-	this_cpu_inc(scp->srcu_locks.counter); /* Y */
-	barrier(); /* Avoid leaking the critical section. */
-	return __srcu_ptr_to_ctr(ssp, scp);
-}
-
-/*
- * Removes the count for the old reader from the appropriate
- * per-CPU element of the srcu_struct.  Note that this may well be a
- * different CPU than that which was incremented by the corresponding
- * srcu_read_lock_lite(), but it must be within the same task.
- *
- * Note that this_cpu_inc() is an RCU read-side critical section either
- * because it disables interrupts, because it is a single instruction,
- * or because it is a read-modify-write atomic operation, depending on
- * the whims of the architecture.
- */
-static inline void __srcu_read_unlock_lite(struct srcu_struct *ssp, int idx)
-{
-	barrier();  /* Avoid leaking the critical section. */
-	this_cpu_inc(__srcu_ctr_to_ptr(ssp, idx)->srcu_unlocks.counter);  /* Z */
-	RCU_LOCKDEP_WARN(!rcu_is_watching(), "RCU must be watching srcu_read_unlock_lite().");
-}
-
 void __srcu_check_read_flavor(struct srcu_struct *ssp, int read_flavor);
 
 // Record reader usage even for CONFIG_PROVE_RCU=n kernels.  This is
-- 
cgit v1.2.3


From df6f9a918ea856fc288b9001b0414c5be136d7d0 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 16 Jul 2025 11:03:13 +0900
Subject: ata: libata-eh: Remove ata_do_eh()

The only reason for ata_do_eh() to exist is that the two caller sites,
ata_std_error_handler() and ata_sff_error_handler() may pass it a
NULL hardreset operation so that the built-in (generic) hardreset
operation for a driver is ignored if the adapter SCR access is not
available.

However, ata_std_error_handler() and ata_sff_error_handler()
modifications of the hardreset port operation can easily be combined as
they are mutually exclusive. That is, a driver using sata_std_hardreset()
as its hardreset operation cannot use sata_sff_hardreset() and
vice-versa.

With this observation, ata_do_eh() can be removed and its code moved to
ata_std_error_handler(). The condition used to ignore the built-in
hardreset port operation is modified to be the one that was used in
ata_sff_error_handler(). This requires defining a stub for the function
sata_sff_hardreset() to avoid compilation errors when CONFIG_ATA_SFF is
not enabled. Furthermore, instead of modifying the local hardreset
operation definition, set the ATA_LFLAG_NO_HRST link flag to prevent
the use of built-in hardreset methods for ports without a valid scr_read
function. This flag is checked in ata_eh_reset() and if set, the
hardreset method is ignored.

This change simplifies ata_sff_error_handler() as this function now only
needs to call ata_std_error_handler().

No functional changes.

Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20250716020315.235457-2-dlemoal@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/libata-eh.c  | 48 ++++++++++++++----------------------------------
 drivers/ata/libata-sff.c | 10 +---------
 include/linux/libata.h   |  9 ++++++---
 3 files changed, 21 insertions(+), 46 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 436536112043..30c831e56a7f 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -4067,59 +4067,39 @@ void ata_eh_finish(struct ata_port *ap)
 }
 
 /**
- *	ata_do_eh - do standard error handling
+ *	ata_std_error_handler - standard error handler
  *	@ap: host port to handle error for
  *
- *	@prereset: prereset method (can be NULL)
- *	@softreset: softreset method (can be NULL)
- *	@hardreset: hardreset method (can be NULL)
- *	@postreset: postreset method (can be NULL)
- *
  *	Perform standard error handling sequence.
  *
  *	LOCKING:
  *	Kernel thread context (may sleep).
  */
-void ata_do_eh(struct ata_port *ap, ata_prereset_fn_t prereset,
-	       ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
-	       ata_postreset_fn_t postreset)
+void ata_std_error_handler(struct ata_port *ap)
 {
-	struct ata_device *dev;
+	struct ata_port_operations *ops = ap->ops;
+	struct ata_link *link = &ap->link;
 	int rc;
 
+	/* Ignore built-in hardresets if SCR access is not available */
+	if ((ops->hardreset == sata_std_hardreset ||
+	     ops->hardreset == sata_sff_hardreset) && !sata_scr_valid(link))
+		link->flags |= ATA_LFLAG_NO_HRST;
+
 	ata_eh_autopsy(ap);
 	ata_eh_report(ap);
 
-	rc = ata_eh_recover(ap, prereset, softreset, hardreset, postreset,
-			    NULL);
+	rc = ata_eh_recover(ap, ops->prereset, ops->softreset,
+			    ops->hardreset, ops->postreset, NULL);
 	if (rc) {
-		ata_for_each_dev(dev, &ap->link, ALL)
+		struct ata_device *dev;
+
+		ata_for_each_dev(dev, link, ALL)
 			ata_dev_disable(dev);
 	}
 
 	ata_eh_finish(ap);
 }
-
-/**
- *	ata_std_error_handler - standard error handler
- *	@ap: host port to handle error for
- *
- *	Standard error handler
- *
- *	LOCKING:
- *	Kernel thread context (may sleep).
- */
-void ata_std_error_handler(struct ata_port *ap)
-{
-	struct ata_port_operations *ops = ap->ops;
-	ata_reset_fn_t hardreset = ops->hardreset;
-
-	/* ignore built-in hardreset if SCR access is not available */
-	if (hardreset == sata_std_hardreset && !sata_scr_valid(&ap->link))
-		hardreset = NULL;
-
-	ata_do_eh(ap, ops->prereset, ops->softreset, hardreset, ops->postreset);
-}
 EXPORT_SYMBOL_GPL(ata_std_error_handler);
 
 #ifdef CONFIG_PM
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index 5a46c066abc3..e61f00779e40 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -2054,8 +2054,6 @@ EXPORT_SYMBOL_GPL(ata_sff_drain_fifo);
  */
 void ata_sff_error_handler(struct ata_port *ap)
 {
-	ata_reset_fn_t softreset = ap->ops->softreset;
-	ata_reset_fn_t hardreset = ap->ops->hardreset;
 	struct ata_queued_cmd *qc;
 	unsigned long flags;
 
@@ -2077,13 +2075,7 @@ void ata_sff_error_handler(struct ata_port *ap)
 
 	spin_unlock_irqrestore(ap->lock, flags);
 
-	/* ignore built-in hardresets if SCR access is not available */
-	if ((hardreset == sata_std_hardreset ||
-	     hardreset == sata_sff_hardreset) && !sata_scr_valid(&ap->link))
-		hardreset = NULL;
-
-	ata_do_eh(ap, ap->ops->prereset, softreset, hardreset,
-		  ap->ops->postreset);
+	ata_std_error_handler(ap);
 }
 EXPORT_SYMBOL_GPL(ata_sff_error_handler);
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index d092747be588..cf0b3fff3198 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -1412,9 +1412,6 @@ extern void ata_eh_thaw_port(struct ata_port *ap);
 extern void ata_eh_qc_complete(struct ata_queued_cmd *qc);
 extern void ata_eh_qc_retry(struct ata_queued_cmd *qc);
 
-extern void ata_do_eh(struct ata_port *ap, ata_prereset_fn_t prereset,
-		      ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
-		      ata_postreset_fn_t postreset);
 extern void ata_std_error_handler(struct ata_port *ap);
 extern void ata_std_sched_eh(struct ata_port *ap);
 extern void ata_std_end_eh(struct ata_port *ap);
@@ -2152,6 +2149,12 @@ static inline u8 ata_wait_idle(struct ata_port *ap)
 
 	return status;
 }
+#else /* CONFIG_ATA_SFF */
+static inline int sata_sff_hardreset(struct ata_link *link, unsigned int *class,
+				     unsigned long deadline)
+{
+	return -EOPNOTSUPP;
+}
 #endif /* CONFIG_ATA_SFF */
 
 #endif /* __LINUX_LIBATA_H__ */
-- 
cgit v1.2.3


From a4daf088a77323154514eb1f8626bbdf9329cfd4 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Wed, 16 Jul 2025 11:03:14 +0900
Subject: ata: libata-eh: Simplify reset operation management

Introduce struct ata_reset_operations to aggregate in a single structure
the definitions of the 4 reset methods (prereset, softreset, hardreset
and postreset) for a port. This new structure is used in struct ata_port
to define the reset methods for a regular port (reset field) and for a
port-multiplier port (pmp_reset field). A pointer to either of these
fields replaces the 4 reset method arguments passed to ata_eh_recover()
and ata_eh_reset().

The definition of the reset methods for all drivers is changed to use
the reset and pmp_reset fields in struct ata_port_operations.

A large number of files is modifed, but no functional changes are
introduced.

Suggested-by: Niklas Cassel <cassel@kernel.org>
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Niklas Cassel <cassel@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Reviewed-by: Hannes Reinecke <hare@suse.de>
Link: https://lore.kernel.org/r/20250716020315.235457-3-dlemoal@kernel.org
Signed-off-by: Niklas Cassel <cassel@kernel.org>
---
 drivers/ata/ahci.c                      |  6 +++---
 drivers/ata/ahci_da850.c                |  6 +++---
 drivers/ata/ahci_dm816.c                |  2 +-
 drivers/ata/ahci_imx.c                  | 13 +++++++------
 drivers/ata/ahci_qoriq.c                |  4 ++--
 drivers/ata/ahci_xgene.c                |  8 ++++----
 drivers/ata/ata_piix.c                  |  4 ++--
 drivers/ata/libahci.c                   | 10 +++++-----
 drivers/ata/libata-core.c               |  4 ++--
 drivers/ata/libata-eh.c                 | 29 +++++++++++++----------------
 drivers/ata/libata-pmp.c                | 26 +++++++++-----------------
 drivers/ata/libata-sata.c               |  2 +-
 drivers/ata/libata-sff.c                |  8 ++++----
 drivers/ata/libata.h                    |  8 +++-----
 drivers/ata/pata_acpi.c                 |  2 +-
 drivers/ata/pata_ali.c                  | 10 +++++-----
 drivers/ata/pata_amd.c                  |  4 ++--
 drivers/ata/pata_artop.c                |  4 ++--
 drivers/ata/pata_atiixp.c               |  2 +-
 drivers/ata/pata_efar.c                 |  2 +-
 drivers/ata/pata_ep93xx.c               |  4 ++--
 drivers/ata/pata_hpt366.c               |  2 +-
 drivers/ata/pata_hpt37x.c               |  4 ++--
 drivers/ata/pata_hpt3x2n.c              |  2 +-
 drivers/ata/pata_icside.c               |  2 +-
 drivers/ata/pata_it8213.c               |  2 +-
 drivers/ata/pata_jmicron.c              |  2 +-
 drivers/ata/pata_marvell.c              |  2 +-
 drivers/ata/pata_mpiix.c                |  2 +-
 drivers/ata/pata_ns87410.c              |  2 +-
 drivers/ata/pata_octeon_cf.c            |  2 +-
 drivers/ata/pata_oldpiix.c              |  2 +-
 drivers/ata/pata_opti.c                 |  2 +-
 drivers/ata/pata_optidma.c              |  2 +-
 drivers/ata/pata_parport/pata_parport.c |  4 ++--
 drivers/ata/pata_pdc2027x.c             |  2 +-
 drivers/ata/pata_rdc.c                  |  2 +-
 drivers/ata/pata_sis.c                  |  2 +-
 drivers/ata/pata_sl82c105.c             |  2 +-
 drivers/ata/pata_triflex.c              |  2 +-
 drivers/ata/pata_via.c                  |  2 +-
 drivers/ata/pdc_adma.c                  |  2 +-
 drivers/ata/sata_dwc_460ex.c            |  2 +-
 drivers/ata/sata_fsl.c                  |  6 +++---
 drivers/ata/sata_highbank.c             |  2 +-
 drivers/ata/sata_inic162x.c             |  2 +-
 drivers/ata/sata_mv.c                   | 10 +++++-----
 drivers/ata/sata_nv.c                   |  2 +-
 drivers/ata/sata_promise.c              |  4 ++--
 drivers/ata/sata_qstor.c                |  4 ++--
 drivers/ata/sata_rcar.c                 |  2 +-
 drivers/ata/sata_sil24.c                |  8 ++++----
 drivers/ata/sata_svw.c                  |  4 ++--
 drivers/ata/sata_sx4.c                  |  2 +-
 drivers/ata/sata_uli.c                  |  2 +-
 drivers/ata/sata_via.c                  |  4 ++--
 drivers/scsi/libsas/sas_ata.c           |  4 ++--
 include/linux/libata.h                  | 17 +++++++++--------
 58 files changed, 134 insertions(+), 145 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/ahci.c b/drivers/ata/ahci.c
index 5558e9f7b85d..e1c24bbacf64 100644
--- a/drivers/ata/ahci.c
+++ b/drivers/ata/ahci.c
@@ -110,17 +110,17 @@ static const struct scsi_host_template ahci_sht = {
 
 static struct ata_port_operations ahci_vt8251_ops = {
 	.inherits		= &ahci_ops,
-	.hardreset		= ahci_vt8251_hardreset,
+	.reset.hardreset	= ahci_vt8251_hardreset,
 };
 
 static struct ata_port_operations ahci_p5wdh_ops = {
 	.inherits		= &ahci_ops,
-	.hardreset		= ahci_p5wdh_hardreset,
+	.reset.hardreset	= ahci_p5wdh_hardreset,
 };
 
 static struct ata_port_operations ahci_avn_ops = {
 	.inherits		= &ahci_ops,
-	.hardreset		= ahci_avn_hardreset,
+	.reset.hardreset	= ahci_avn_hardreset,
 };
 
 static const struct ata_port_info ahci_port_info[] = {
diff --git a/drivers/ata/ahci_da850.c b/drivers/ata/ahci_da850.c
index ca0924dc5bd2..f97566c420f8 100644
--- a/drivers/ata/ahci_da850.c
+++ b/drivers/ata/ahci_da850.c
@@ -137,13 +137,13 @@ static int ahci_da850_hardreset(struct ata_link *link,
 
 static struct ata_port_operations ahci_da850_port_ops = {
 	.inherits = &ahci_platform_ops,
-	.softreset = ahci_da850_softreset,
+	.reset.softreset = ahci_da850_softreset,
 	/*
 	 * No need to override .pmp_softreset - it's only used for actual
 	 * PMP-enabled ports.
 	 */
-	.hardreset = ahci_da850_hardreset,
-	.pmp_hardreset = ahci_da850_hardreset,
+	.reset.hardreset = ahci_da850_hardreset,
+	.pmp_reset.hardreset = ahci_da850_hardreset,
 };
 
 static const struct ata_port_info ahci_da850_port_info = {
diff --git a/drivers/ata/ahci_dm816.c b/drivers/ata/ahci_dm816.c
index b08547b877a1..93faed2cfeb6 100644
--- a/drivers/ata/ahci_dm816.c
+++ b/drivers/ata/ahci_dm816.c
@@ -124,7 +124,7 @@ static int ahci_dm816_softreset(struct ata_link *link,
 
 static struct ata_port_operations ahci_dm816_port_ops = {
 	.inherits = &ahci_platform_ops,
-	.softreset = ahci_dm816_softreset,
+	.reset.softreset = ahci_dm816_softreset,
 };
 
 static const struct ata_port_info ahci_dm816_port_info = {
diff --git a/drivers/ata/ahci_imx.c b/drivers/ata/ahci_imx.c
index f01f08048f97..86aedd5923ac 100644
--- a/drivers/ata/ahci_imx.c
+++ b/drivers/ata/ahci_imx.c
@@ -642,18 +642,19 @@ static int ahci_imx_softreset(struct ata_link *link, unsigned int *class,
 	int ret;
 
 	if (imxpriv->type == AHCI_IMX53)
-		ret = ahci_pmp_retry_srst_ops.softreset(link, class, deadline);
+		ret = ahci_pmp_retry_srst_ops.reset.softreset(link, class,
+							      deadline);
 	else
-		ret = ahci_ops.softreset(link, class, deadline);
+		ret = ahci_ops.reset.softreset(link, class, deadline);
 
 	return ret;
 }
 
 static struct ata_port_operations ahci_imx_ops = {
-	.inherits	= &ahci_ops,
-	.host_stop	= ahci_imx_host_stop,
-	.error_handler	= ahci_imx_error_handler,
-	.softreset	= ahci_imx_softreset,
+	.inherits		= &ahci_ops,
+	.host_stop		= ahci_imx_host_stop,
+	.error_handler		= ahci_imx_error_handler,
+	.reset.softreset	= ahci_imx_softreset,
 };
 
 static const struct ata_port_info ahci_imx_port_info = {
diff --git a/drivers/ata/ahci_qoriq.c b/drivers/ata/ahci_qoriq.c
index 30e39885b64e..0dec1a17e5b1 100644
--- a/drivers/ata/ahci_qoriq.c
+++ b/drivers/ata/ahci_qoriq.c
@@ -146,8 +146,8 @@ static int ahci_qoriq_hardreset(struct ata_link *link, unsigned int *class,
 }
 
 static struct ata_port_operations ahci_qoriq_ops = {
-	.inherits	= &ahci_ops,
-	.hardreset	= ahci_qoriq_hardreset,
+	.inherits		= &ahci_ops,
+	.reset.hardreset	= ahci_qoriq_hardreset,
 };
 
 static const struct ata_port_info ahci_qoriq_port_info = {
diff --git a/drivers/ata/ahci_xgene.c b/drivers/ata/ahci_xgene.c
index dfbd8c53abcb..5d5a51a77f5d 100644
--- a/drivers/ata/ahci_xgene.c
+++ b/drivers/ata/ahci_xgene.c
@@ -613,11 +613,11 @@ static irqreturn_t xgene_ahci_irq_intr(int irq, void *dev_instance)
 static struct ata_port_operations xgene_ahci_v1_ops = {
 	.inherits = &ahci_ops,
 	.host_stop = xgene_ahci_host_stop,
-	.hardreset = xgene_ahci_hardreset,
+	.reset.hardreset = xgene_ahci_hardreset,
+	.reset.softreset = xgene_ahci_softreset,
+	.pmp_reset.softreset = xgene_ahci_pmp_softreset,
 	.read_id = xgene_ahci_read_id,
 	.qc_issue = xgene_ahci_qc_issue,
-	.softreset = xgene_ahci_softreset,
-	.pmp_softreset = xgene_ahci_pmp_softreset
 };
 
 static const struct ata_port_info xgene_ahci_v1_port_info = {
@@ -630,7 +630,7 @@ static const struct ata_port_info xgene_ahci_v1_port_info = {
 static struct ata_port_operations xgene_ahci_v2_ops = {
 	.inherits = &ahci_ops,
 	.host_stop = xgene_ahci_host_stop,
-	.hardreset = xgene_ahci_hardreset,
+	.reset.hardreset = xgene_ahci_hardreset,
 	.read_id = xgene_ahci_read_id,
 };
 
diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index d441246fa357..229429ba5027 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -1074,7 +1074,7 @@ static struct ata_port_operations piix_pata_ops = {
 	.cable_detect		= ata_cable_40wire,
 	.set_piomode		= piix_set_piomode,
 	.set_dmamode		= piix_set_dmamode,
-	.prereset		= piix_pata_prereset,
+	.reset.prereset		= piix_pata_prereset,
 };
 
 static struct ata_port_operations piix_vmw_ops = {
@@ -1102,7 +1102,7 @@ static const struct scsi_host_template piix_sidpr_sht = {
 
 static struct ata_port_operations piix_sidpr_sata_ops = {
 	.inherits		= &piix_sata_ops,
-	.hardreset		= sata_std_hardreset,
+	.reset.hardreset	= sata_std_hardreset,
 	.scr_read		= piix_sidpr_scr_read,
 	.scr_write		= piix_sidpr_scr_write,
 	.set_lpm		= piix_sidpr_set_lpm,
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index 4e9c82f36df1..b335fb7e5cb4 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -162,10 +162,10 @@ struct ata_port_operations ahci_ops = {
 
 	.freeze			= ahci_freeze,
 	.thaw			= ahci_thaw,
-	.softreset		= ahci_softreset,
-	.hardreset		= ahci_hardreset,
-	.postreset		= ahci_postreset,
-	.pmp_softreset		= ahci_softreset,
+	.reset.softreset	= ahci_softreset,
+	.reset.hardreset	= ahci_hardreset,
+	.reset.postreset	= ahci_postreset,
+	.pmp_reset.softreset	= ahci_softreset,
 	.error_handler		= ahci_error_handler,
 	.post_internal_cmd	= ahci_post_internal_cmd,
 	.dev_config		= ahci_dev_config,
@@ -192,7 +192,7 @@ EXPORT_SYMBOL_GPL(ahci_ops);
 
 struct ata_port_operations ahci_pmp_retry_srst_ops = {
 	.inherits		= &ahci_ops,
-	.softreset		= ahci_pmp_retry_softreset,
+	.reset.softreset	= ahci_pmp_retry_softreset,
 };
 EXPORT_SYMBOL_GPL(ahci_pmp_retry_srst_ops);
 
diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
index bbf1318a2b9a..97d9f0488cc1 100644
--- a/drivers/ata/libata-core.c
+++ b/drivers/ata/libata-core.c
@@ -65,8 +65,8 @@
 #include "libata-transport.h"
 
 const struct ata_port_operations ata_base_port_ops = {
-	.prereset		= ata_std_prereset,
-	.postreset		= ata_std_postreset,
+	.reset.prereset		= ata_std_prereset,
+	.reset.postreset	= ata_std_postreset,
 	.error_handler		= ata_std_error_handler,
 	.sched_eh		= ata_std_sched_eh,
 	.end_eh			= ata_std_end_eh,
diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
index 30c831e56a7f..2946ae6d4b2c 100644
--- a/drivers/ata/libata-eh.c
+++ b/drivers/ata/libata-eh.c
@@ -2793,13 +2793,16 @@ static bool ata_eh_followup_srst_needed(struct ata_link *link, int rc)
 }
 
 int ata_eh_reset(struct ata_link *link, int classify,
-		 ata_prereset_fn_t prereset, ata_reset_fn_t softreset,
-		 ata_reset_fn_t hardreset, ata_postreset_fn_t postreset)
+		 struct ata_reset_operations *reset_ops)
 {
 	struct ata_port *ap = link->ap;
 	struct ata_link *slave = ap->slave_link;
 	struct ata_eh_context *ehc = &link->eh_context;
 	struct ata_eh_context *sehc = slave ? &slave->eh_context : NULL;
+	ata_reset_fn_t hardreset = reset_ops->hardreset;
+	ata_reset_fn_t softreset = reset_ops->softreset;
+	ata_prereset_fn_t prereset = reset_ops->prereset;
+	ata_postreset_fn_t postreset = reset_ops->postreset;
 	unsigned int *classes = ehc->classes;
 	unsigned int lflags = link->flags;
 	int verbose = !(ehc->i.flags & ATA_EHI_QUIET);
@@ -3756,10 +3759,7 @@ static int ata_eh_handle_dev_fail(struct ata_device *dev, int err)
 /**
  *	ata_eh_recover - recover host port after error
  *	@ap: host port to recover
- *	@prereset: prereset method (can be NULL)
- *	@softreset: softreset method (can be NULL)
- *	@hardreset: hardreset method (can be NULL)
- *	@postreset: postreset method (can be NULL)
+ *	@reset_ops: The set of reset operations to use
  *	@r_failed_link: out parameter for failed link
  *
  *	This is the alpha and omega, eum and yang, heart and soul of
@@ -3775,9 +3775,7 @@ static int ata_eh_handle_dev_fail(struct ata_device *dev, int err)
  *	RETURNS:
  *	0 on success, -errno on failure.
  */
-int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
-		   ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
-		   ata_postreset_fn_t postreset,
+int ata_eh_recover(struct ata_port *ap, struct ata_reset_operations *reset_ops,
 		   struct ata_link **r_failed_link)
 {
 	struct ata_link *link;
@@ -3845,8 +3843,7 @@ int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
 		if (!(ehc->i.action & ATA_EH_RESET))
 			continue;
 
-		rc = ata_eh_reset(link, ata_link_nr_vacant(link),
-				  prereset, softreset, hardreset, postreset);
+		rc = ata_eh_reset(link, ata_link_nr_vacant(link), reset_ops);
 		if (rc) {
 			ata_link_err(link, "reset failed, giving up\n");
 			goto out;
@@ -4077,20 +4074,20 @@ void ata_eh_finish(struct ata_port *ap)
  */
 void ata_std_error_handler(struct ata_port *ap)
 {
-	struct ata_port_operations *ops = ap->ops;
+	struct ata_reset_operations *reset_ops = &ap->ops->reset;
 	struct ata_link *link = &ap->link;
 	int rc;
 
 	/* Ignore built-in hardresets if SCR access is not available */
-	if ((ops->hardreset == sata_std_hardreset ||
-	     ops->hardreset == sata_sff_hardreset) && !sata_scr_valid(link))
+	if ((reset_ops->hardreset == sata_std_hardreset ||
+	     reset_ops->hardreset == sata_sff_hardreset) &&
+	    !sata_scr_valid(link))
 		link->flags |= ATA_LFLAG_NO_HRST;
 
 	ata_eh_autopsy(ap);
 	ata_eh_report(ap);
 
-	rc = ata_eh_recover(ap, ops->prereset, ops->softreset,
-			    ops->hardreset, ops->postreset, NULL);
+	rc = ata_eh_recover(ap, reset_ops, NULL);
 	if (rc) {
 		struct ata_device *dev;
 
diff --git a/drivers/ata/libata-pmp.c b/drivers/ata/libata-pmp.c
index d5d189328ae6..57023324a56f 100644
--- a/drivers/ata/libata-pmp.c
+++ b/drivers/ata/libata-pmp.c
@@ -15,9 +15,9 @@
 
 const struct ata_port_operations sata_pmp_port_ops = {
 	.inherits		= &sata_port_ops,
-	.pmp_prereset		= ata_std_prereset,
-	.pmp_hardreset		= sata_std_hardreset,
-	.pmp_postreset		= ata_std_postreset,
+	.pmp_reset.prereset	= ata_std_prereset,
+	.pmp_reset.hardreset	= sata_std_hardreset,
+	.pmp_reset.postreset	= ata_std_postreset,
 	.error_handler		= sata_pmp_error_handler,
 };
 
@@ -727,10 +727,7 @@ static int sata_pmp_revalidate_quick(struct ata_device *dev)
 /**
  *	sata_pmp_eh_recover_pmp - recover PMP
  *	@ap: ATA port PMP is attached to
- *	@prereset: prereset method (can be NULL)
- *	@softreset: softreset method
- *	@hardreset: hardreset method
- *	@postreset: postreset method (can be NULL)
+ *	@reset_ops: The set of reset operations to use
  *
  *	Recover PMP attached to @ap.  Recovery procedure is somewhat
  *	similar to that of ata_eh_recover() except that reset should
@@ -744,8 +741,7 @@ static int sata_pmp_revalidate_quick(struct ata_device *dev)
  *	0 on success, -errno on failure.
  */
 static int sata_pmp_eh_recover_pmp(struct ata_port *ap,
-		ata_prereset_fn_t prereset, ata_reset_fn_t softreset,
-		ata_reset_fn_t hardreset, ata_postreset_fn_t postreset)
+				   struct ata_reset_operations *reset_ops)
 {
 	struct ata_link *link = &ap->link;
 	struct ata_eh_context *ehc = &link->eh_context;
@@ -767,8 +763,7 @@ static int sata_pmp_eh_recover_pmp(struct ata_port *ap,
 		struct ata_link *tlink;
 
 		/* reset */
-		rc = ata_eh_reset(link, 0, prereset, softreset, hardreset,
-				  postreset);
+		rc = ata_eh_reset(link, 0, reset_ops);
 		if (rc) {
 			ata_link_err(link, "failed to reset PMP, giving up\n");
 			goto fail;
@@ -932,8 +927,7 @@ static int sata_pmp_eh_recover(struct ata_port *ap)
  retry:
 	/* PMP attached? */
 	if (!sata_pmp_attached(ap)) {
-		rc = ata_eh_recover(ap, ops->prereset, ops->softreset,
-				    ops->hardreset, ops->postreset, NULL);
+		rc = ata_eh_recover(ap, &ops->reset, NULL);
 		if (rc) {
 			ata_for_each_dev(dev, &ap->link, ALL)
 				ata_dev_disable(dev);
@@ -951,8 +945,7 @@ static int sata_pmp_eh_recover(struct ata_port *ap)
 	}
 
 	/* recover pmp */
-	rc = sata_pmp_eh_recover_pmp(ap, ops->prereset, ops->softreset,
-				     ops->hardreset, ops->postreset);
+	rc = sata_pmp_eh_recover_pmp(ap, &ops->reset);
 	if (rc)
 		goto pmp_fail;
 
@@ -978,8 +971,7 @@ static int sata_pmp_eh_recover(struct ata_port *ap)
 		goto pmp_fail;
 
 	/* recover links */
-	rc = ata_eh_recover(ap, ops->pmp_prereset, ops->pmp_softreset,
-			    ops->pmp_hardreset, ops->pmp_postreset, &link);
+	rc = ata_eh_recover(ap, &ops->pmp_reset, &link);
 	if (rc)
 		goto link_fail;
 
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 47169c469f43..4734465d3b1e 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -1704,6 +1704,6 @@ const struct ata_port_operations sata_port_ops = {
 	.inherits		= &ata_base_port_ops,
 
 	.qc_defer		= ata_std_qc_defer,
-	.hardreset		= sata_std_hardreset,
+	.reset.hardreset	= sata_std_hardreset,
 };
 EXPORT_SYMBOL_GPL(sata_port_ops);
diff --git a/drivers/ata/libata-sff.c b/drivers/ata/libata-sff.c
index e61f00779e40..7fc407255eb4 100644
--- a/drivers/ata/libata-sff.c
+++ b/drivers/ata/libata-sff.c
@@ -31,10 +31,10 @@ const struct ata_port_operations ata_sff_port_ops = {
 
 	.freeze			= ata_sff_freeze,
 	.thaw			= ata_sff_thaw,
-	.prereset		= ata_sff_prereset,
-	.softreset		= ata_sff_softreset,
-	.hardreset		= sata_sff_hardreset,
-	.postreset		= ata_sff_postreset,
+	.reset.prereset		= ata_sff_prereset,
+	.reset.softreset	= ata_sff_softreset,
+	.reset.hardreset	= sata_sff_hardreset,
+	.reset.postreset	= ata_sff_postreset,
 	.error_handler		= ata_sff_error_handler,
 
 	.sff_dev_select		= ata_sff_dev_select,
diff --git a/drivers/ata/libata.h b/drivers/ata/libata.h
index ca44fb792aeb..e5b977a8d3e1 100644
--- a/drivers/ata/libata.h
+++ b/drivers/ata/libata.h
@@ -180,11 +180,9 @@ extern void ata_eh_autopsy(struct ata_port *ap);
 const char *ata_get_cmd_name(u8 command);
 extern void ata_eh_report(struct ata_port *ap);
 extern int ata_eh_reset(struct ata_link *link, int classify,
-			ata_prereset_fn_t prereset, ata_reset_fn_t softreset,
-			ata_reset_fn_t hardreset, ata_postreset_fn_t postreset);
-extern int ata_eh_recover(struct ata_port *ap, ata_prereset_fn_t prereset,
-			  ata_reset_fn_t softreset, ata_reset_fn_t hardreset,
-			  ata_postreset_fn_t postreset,
+			struct ata_reset_operations *reset_ops);
+extern int ata_eh_recover(struct ata_port *ap,
+			  struct ata_reset_operations *reset_ops,
 			  struct ata_link **r_failed_disk);
 extern void ata_eh_finish(struct ata_port *ap);
 extern int ata_ering_map(struct ata_ering *ering,
diff --git a/drivers/ata/pata_acpi.c b/drivers/ata/pata_acpi.c
index ab38871b5e00..23fff10af2ac 100644
--- a/drivers/ata/pata_acpi.c
+++ b/drivers/ata/pata_acpi.c
@@ -216,7 +216,7 @@ static struct ata_port_operations pacpi_ops = {
 	.mode_filter		= pacpi_mode_filter,
 	.set_piomode		= pacpi_set_piomode,
 	.set_dmamode		= pacpi_set_dmamode,
-	.prereset		= pacpi_pre_reset,
+	.reset.prereset		= pacpi_pre_reset,
 	.port_start		= pacpi_port_start,
 };
 
diff --git a/drivers/ata/pata_ali.c b/drivers/ata/pata_ali.c
index bb790edd6036..9d5cb9c34c52 100644
--- a/drivers/ata/pata_ali.c
+++ b/drivers/ata/pata_ali.c
@@ -392,11 +392,11 @@ static struct ata_port_operations ali_20_port_ops = {
  *	Port operations for DMA capable ALi with cable detect
  */
 static struct ata_port_operations ali_c2_port_ops = {
-	.inherits	= &ali_dma_base_ops,
-	.check_atapi_dma = ali_check_atapi_dma,
-	.cable_detect	= ali_c2_cable_detect,
-	.dev_config	= ali_lock_sectors,
-	.postreset	= ali_c2_c3_postreset,
+	.inherits		= &ali_dma_base_ops,
+	.check_atapi_dma	= ali_check_atapi_dma,
+	.cable_detect		= ali_c2_cable_detect,
+	.dev_config		= ali_lock_sectors,
+	.reset.postreset	= ali_c2_c3_postreset,
 };
 
 /*
diff --git a/drivers/ata/pata_amd.c b/drivers/ata/pata_amd.c
index 5b02b89748b7..a2fecadc927d 100644
--- a/drivers/ata/pata_amd.c
+++ b/drivers/ata/pata_amd.c
@@ -394,7 +394,7 @@ static const struct scsi_host_template amd_sht = {
 
 static const struct ata_port_operations amd_base_port_ops = {
 	.inherits	= &ata_bmdma32_port_ops,
-	.prereset	= amd_pre_reset,
+	.reset.prereset	= amd_pre_reset,
 };
 
 static struct ata_port_operations amd33_port_ops = {
@@ -429,7 +429,7 @@ static const struct ata_port_operations nv_base_port_ops = {
 	.inherits	= &ata_bmdma_port_ops,
 	.cable_detect	= ata_cable_ignore,
 	.mode_filter	= nv_mode_filter,
-	.prereset	= nv_pre_reset,
+	.reset.prereset	= nv_pre_reset,
 	.host_stop	= nv_host_stop,
 };
 
diff --git a/drivers/ata/pata_artop.c b/drivers/ata/pata_artop.c
index 40544282f455..6160414172a3 100644
--- a/drivers/ata/pata_artop.c
+++ b/drivers/ata/pata_artop.c
@@ -301,7 +301,7 @@ static struct ata_port_operations artop6210_ops = {
 	.cable_detect		= ata_cable_40wire,
 	.set_piomode		= artop6210_set_piomode,
 	.set_dmamode		= artop6210_set_dmamode,
-	.prereset		= artop62x0_pre_reset,
+	.reset.prereset		= artop62x0_pre_reset,
 	.qc_defer		= artop6210_qc_defer,
 };
 
@@ -310,7 +310,7 @@ static struct ata_port_operations artop6260_ops = {
 	.cable_detect		= artop6260_cable_detect,
 	.set_piomode		= artop6260_set_piomode,
 	.set_dmamode		= artop6260_set_dmamode,
-	.prereset		= artop62x0_pre_reset,
+	.reset.prereset		= artop62x0_pre_reset,
 };
 
 static void atp8xx_fixup(struct pci_dev *pdev)
diff --git a/drivers/ata/pata_atiixp.c b/drivers/ata/pata_atiixp.c
index 8c5cc803aab3..4c612f9543f6 100644
--- a/drivers/ata/pata_atiixp.c
+++ b/drivers/ata/pata_atiixp.c
@@ -264,7 +264,7 @@ static struct ata_port_operations atiixp_port_ops = {
 	.bmdma_start 	= atiixp_bmdma_start,
 	.bmdma_stop	= atiixp_bmdma_stop,
 
-	.prereset	= atiixp_prereset,
+	.reset.prereset	= atiixp_prereset,
 	.cable_detect	= atiixp_cable_detect,
 	.set_piomode	= atiixp_set_piomode,
 	.set_dmamode	= atiixp_set_dmamode,
diff --git a/drivers/ata/pata_efar.c b/drivers/ata/pata_efar.c
index 2e6eccf2902f..6fe49b303fee 100644
--- a/drivers/ata/pata_efar.c
+++ b/drivers/ata/pata_efar.c
@@ -243,7 +243,7 @@ static struct ata_port_operations efar_ops = {
 	.cable_detect		= efar_cable_detect,
 	.set_piomode		= efar_set_piomode,
 	.set_dmamode		= efar_set_dmamode,
-	.prereset		= efar_pre_reset,
+	.reset.prereset		= efar_pre_reset,
 };
 
 
diff --git a/drivers/ata/pata_ep93xx.c b/drivers/ata/pata_ep93xx.c
index e8cda988feb5..b2b9e0058333 100644
--- a/drivers/ata/pata_ep93xx.c
+++ b/drivers/ata/pata_ep93xx.c
@@ -879,8 +879,8 @@ static const struct scsi_host_template ep93xx_pata_sht = {
 static struct ata_port_operations ep93xx_pata_port_ops = {
 	.inherits		= &ata_bmdma_port_ops,
 
-	.softreset		= ep93xx_pata_softreset,
-	.hardreset		= ATA_OP_NULL,
+	.reset.softreset	= ep93xx_pata_softreset,
+	.reset.hardreset	= ATA_OP_NULL,
 
 	.sff_dev_select		= ep93xx_pata_dev_select,
 	.sff_set_devctl		= ep93xx_pata_set_devctl,
diff --git a/drivers/ata/pata_hpt366.c b/drivers/ata/pata_hpt366.c
index 5280e9960025..b96e8bd2a3f8 100644
--- a/drivers/ata/pata_hpt366.c
+++ b/drivers/ata/pata_hpt366.c
@@ -322,7 +322,7 @@ static const struct scsi_host_template hpt36x_sht = {
 
 static struct ata_port_operations hpt366_port_ops = {
 	.inherits	= &ata_bmdma_port_ops,
-	.prereset	= hpt366_prereset,
+	.reset.prereset	= hpt366_prereset,
 	.cable_detect	= hpt36x_cable_detect,
 	.mode_filter	= hpt366_filter,
 	.set_piomode	= hpt366_set_piomode,
diff --git a/drivers/ata/pata_hpt37x.c b/drivers/ata/pata_hpt37x.c
index 4af22b819416..07e3a984cbb1 100644
--- a/drivers/ata/pata_hpt37x.c
+++ b/drivers/ata/pata_hpt37x.c
@@ -543,7 +543,7 @@ static struct ata_port_operations hpt370_port_ops = {
 	.cable_detect	= hpt37x_cable_detect,
 	.set_piomode	= hpt37x_set_piomode,
 	.set_dmamode	= hpt37x_set_dmamode,
-	.prereset	= hpt37x_pre_reset,
+	.reset.prereset	= hpt37x_pre_reset,
 };
 
 /*
@@ -567,7 +567,7 @@ static struct ata_port_operations hpt302_port_ops = {
 	.cable_detect	= hpt37x_cable_detect,
 	.set_piomode	= hpt37x_set_piomode,
 	.set_dmamode	= hpt37x_set_dmamode,
-	.prereset	= hpt37x_pre_reset,
+	.reset.prereset	= hpt37x_pre_reset,
 };
 
 /*
diff --git a/drivers/ata/pata_hpt3x2n.c b/drivers/ata/pata_hpt3x2n.c
index 5b1ecccf3c83..2cc57fcf2c46 100644
--- a/drivers/ata/pata_hpt3x2n.c
+++ b/drivers/ata/pata_hpt3x2n.c
@@ -356,7 +356,7 @@ static struct ata_port_operations hpt3xxn_port_ops = {
 	.cable_detect	= hpt3x2n_cable_detect,
 	.set_piomode	= hpt3x2n_set_piomode,
 	.set_dmamode	= hpt3x2n_set_dmamode,
-	.prereset	= hpt3x2n_pre_reset,
+	.reset.prereset	= hpt3x2n_pre_reset,
 };
 
 /*
diff --git a/drivers/ata/pata_icside.c b/drivers/ata/pata_icside.c
index 61d8760f09d9..70f056e47e6b 100644
--- a/drivers/ata/pata_icside.c
+++ b/drivers/ata/pata_icside.c
@@ -336,7 +336,7 @@ static struct ata_port_operations pata_icside_port_ops = {
 
 	.cable_detect		= ata_cable_40wire,
 	.set_dmamode		= pata_icside_set_dmamode,
-	.postreset		= pata_icside_postreset,
+	.reset.postreset	= pata_icside_postreset,
 
 	.port_start		= ATA_OP_NULL,	/* don't need PRD table */
 };
diff --git a/drivers/ata/pata_it8213.c b/drivers/ata/pata_it8213.c
index 9cbe2132ce59..a6f2cfc1602e 100644
--- a/drivers/ata/pata_it8213.c
+++ b/drivers/ata/pata_it8213.c
@@ -238,7 +238,7 @@ static struct ata_port_operations it8213_ops = {
 	.cable_detect		= it8213_cable_detect,
 	.set_piomode		= it8213_set_piomode,
 	.set_dmamode		= it8213_set_dmamode,
-	.prereset		= it8213_pre_reset,
+	.reset.prereset		= it8213_pre_reset,
 };
 
 
diff --git a/drivers/ata/pata_jmicron.c b/drivers/ata/pata_jmicron.c
index f51fb8219762..b885f33e8980 100644
--- a/drivers/ata/pata_jmicron.c
+++ b/drivers/ata/pata_jmicron.c
@@ -113,7 +113,7 @@ static const struct scsi_host_template jmicron_sht = {
 
 static struct ata_port_operations jmicron_ops = {
 	.inherits		= &ata_bmdma_port_ops,
-	.prereset		= jmicron_pre_reset,
+	.reset.prereset		= jmicron_pre_reset,
 };
 
 
diff --git a/drivers/ata/pata_marvell.c b/drivers/ata/pata_marvell.c
index 8119caaad605..deab67328388 100644
--- a/drivers/ata/pata_marvell.c
+++ b/drivers/ata/pata_marvell.c
@@ -99,7 +99,7 @@ static const struct scsi_host_template marvell_sht = {
 static struct ata_port_operations marvell_ops = {
 	.inherits		= &ata_bmdma_port_ops,
 	.cable_detect		= marvell_cable_detect,
-	.prereset		= marvell_pre_reset,
+	.reset.prereset		= marvell_pre_reset,
 };
 
 
diff --git a/drivers/ata/pata_mpiix.c b/drivers/ata/pata_mpiix.c
index 69e4baf27d72..ce310ae7c93a 100644
--- a/drivers/ata/pata_mpiix.c
+++ b/drivers/ata/pata_mpiix.c
@@ -145,7 +145,7 @@ static struct ata_port_operations mpiix_port_ops = {
 	.qc_issue	= mpiix_qc_issue,
 	.cable_detect	= ata_cable_40wire,
 	.set_piomode	= mpiix_set_piomode,
-	.prereset	= mpiix_pre_reset,
+	.reset.prereset	= mpiix_pre_reset,
 	.sff_data_xfer	= ata_sff_data_xfer32,
 };
 
diff --git a/drivers/ata/pata_ns87410.c b/drivers/ata/pata_ns87410.c
index 44cc24d21d5f..bdb55c1a3280 100644
--- a/drivers/ata/pata_ns87410.c
+++ b/drivers/ata/pata_ns87410.c
@@ -123,7 +123,7 @@ static struct ata_port_operations ns87410_port_ops = {
 	.qc_issue	= ns87410_qc_issue,
 	.cable_detect	= ata_cable_40wire,
 	.set_piomode	= ns87410_set_piomode,
-	.prereset	= ns87410_pre_reset,
+	.reset.prereset	= ns87410_pre_reset,
 };
 
 static int ns87410_init_one(struct pci_dev *dev, const struct pci_device_id *id)
diff --git a/drivers/ata/pata_octeon_cf.c b/drivers/ata/pata_octeon_cf.c
index 2d32125c16fd..df42ebe98db7 100644
--- a/drivers/ata/pata_octeon_cf.c
+++ b/drivers/ata/pata_octeon_cf.c
@@ -941,7 +941,7 @@ static int octeon_cf_probe(struct platform_device *pdev)
 		/* 16 bit but not True IDE */
 		base = cs0 + 0x800;
 		octeon_cf_ops.sff_data_xfer	= octeon_cf_data_xfer16;
-		octeon_cf_ops.softreset		= octeon_cf_softreset16;
+		octeon_cf_ops.reset.softreset	= octeon_cf_softreset16;
 		octeon_cf_ops.sff_check_status	= octeon_cf_check_status16;
 		octeon_cf_ops.sff_tf_read	= octeon_cf_tf_read16;
 		octeon_cf_ops.sff_tf_load	= octeon_cf_tf_load16;
diff --git a/drivers/ata/pata_oldpiix.c b/drivers/ata/pata_oldpiix.c
index 3d01b7000e41..81a7f3eb5654 100644
--- a/drivers/ata/pata_oldpiix.c
+++ b/drivers/ata/pata_oldpiix.c
@@ -214,7 +214,7 @@ static struct ata_port_operations oldpiix_pata_ops = {
 	.cable_detect		= ata_cable_40wire,
 	.set_piomode		= oldpiix_set_piomode,
 	.set_dmamode		= oldpiix_set_dmamode,
-	.prereset		= oldpiix_pre_reset,
+	.reset.prereset		= oldpiix_pre_reset,
 };
 
 
diff --git a/drivers/ata/pata_opti.c b/drivers/ata/pata_opti.c
index 3d23f57eb128..3db1b95d1404 100644
--- a/drivers/ata/pata_opti.c
+++ b/drivers/ata/pata_opti.c
@@ -156,7 +156,7 @@ static struct ata_port_operations opti_port_ops = {
 	.inherits	= &ata_sff_port_ops,
 	.cable_detect	= ata_cable_40wire,
 	.set_piomode	= opti_set_piomode,
-	.prereset	= opti_pre_reset,
+	.reset.prereset	= opti_pre_reset,
 };
 
 static int opti_init_one(struct pci_dev *dev, const struct pci_device_id *id)
diff --git a/drivers/ata/pata_optidma.c b/drivers/ata/pata_optidma.c
index cc876dc7a9d8..b42dba5f4e05 100644
--- a/drivers/ata/pata_optidma.c
+++ b/drivers/ata/pata_optidma.c
@@ -346,7 +346,7 @@ static struct ata_port_operations optidma_port_ops = {
 	.set_piomode	= optidma_set_pio_mode,
 	.set_dmamode	= optidma_set_dma_mode,
 	.set_mode	= optidma_set_mode,
-	.prereset	= optidma_pre_reset,
+	.reset.prereset	= optidma_pre_reset,
 };
 
 static struct ata_port_operations optiplus_port_ops = {
diff --git a/drivers/ata/pata_parport/pata_parport.c b/drivers/ata/pata_parport/pata_parport.c
index 93ebf566b54e..22bd3ff6b7ae 100644
--- a/drivers/ata/pata_parport/pata_parport.c
+++ b/drivers/ata/pata_parport/pata_parport.c
@@ -321,8 +321,8 @@ static void pata_parport_drain_fifo(struct ata_queued_cmd *qc)
 static struct ata_port_operations pata_parport_port_ops = {
 	.inherits		= &ata_sff_port_ops,
 
-	.softreset		= pata_parport_softreset,
-	.hardreset		= NULL,
+	.reset.softreset	= pata_parport_softreset,
+	.reset.hardreset	= NULL,
 
 	.sff_dev_select		= pata_parport_dev_select,
 	.sff_set_devctl		= pata_parport_set_devctl,
diff --git a/drivers/ata/pata_pdc2027x.c b/drivers/ata/pata_pdc2027x.c
index a4ee3b92c9aa..d792ce6d97bf 100644
--- a/drivers/ata/pata_pdc2027x.c
+++ b/drivers/ata/pata_pdc2027x.c
@@ -130,7 +130,7 @@ static struct ata_port_operations pdc2027x_pata100_ops = {
 	.inherits		= &ata_bmdma_port_ops,
 	.check_atapi_dma	= pdc2027x_check_atapi_dma,
 	.cable_detect		= pdc2027x_cable_detect,
-	.prereset		= pdc2027x_prereset,
+	.reset.prereset		= pdc2027x_prereset,
 };
 
 static struct ata_port_operations pdc2027x_pata133_ops = {
diff --git a/drivers/ata/pata_rdc.c b/drivers/ata/pata_rdc.c
index 19cbb5c94b42..6ff4c11e937d 100644
--- a/drivers/ata/pata_rdc.c
+++ b/drivers/ata/pata_rdc.c
@@ -276,7 +276,7 @@ static struct ata_port_operations rdc_pata_ops = {
 	.cable_detect		= rdc_pata_cable_detect,
 	.set_piomode		= rdc_set_piomode,
 	.set_dmamode		= rdc_set_dmamode,
-	.prereset		= rdc_pata_prereset,
+	.reset.prereset		= rdc_pata_prereset,
 };
 
 static const struct ata_port_info rdc_port_info = {
diff --git a/drivers/ata/pata_sis.c b/drivers/ata/pata_sis.c
index 31de06b66221..2b751e393771 100644
--- a/drivers/ata/pata_sis.c
+++ b/drivers/ata/pata_sis.c
@@ -552,7 +552,7 @@ static struct ata_port_operations sis_133_for_sata_ops = {
 
 static struct ata_port_operations sis_base_ops = {
 	.inherits		= &ata_bmdma_port_ops,
-	.prereset		= sis_pre_reset,
+	.reset.prereset		= sis_pre_reset,
 };
 
 static struct ata_port_operations sis_133_ops = {
diff --git a/drivers/ata/pata_sl82c105.c b/drivers/ata/pata_sl82c105.c
index 93882e976ede..2d24c6b3e9d9 100644
--- a/drivers/ata/pata_sl82c105.c
+++ b/drivers/ata/pata_sl82c105.c
@@ -248,7 +248,7 @@ static struct ata_port_operations sl82c105_port_ops = {
 	.bmdma_stop	= sl82c105_bmdma_stop,
 	.cable_detect	= ata_cable_40wire,
 	.set_piomode	= sl82c105_set_piomode,
-	.prereset	= sl82c105_pre_reset,
+	.reset.prereset	= sl82c105_pre_reset,
 	.sff_irq_check	= sl82c105_sff_irq_check,
 };
 
diff --git a/drivers/ata/pata_triflex.c b/drivers/ata/pata_triflex.c
index 26d448a869e2..596e86a031b3 100644
--- a/drivers/ata/pata_triflex.c
+++ b/drivers/ata/pata_triflex.c
@@ -170,7 +170,7 @@ static struct ata_port_operations triflex_port_ops = {
 	.bmdma_stop	= triflex_bmdma_stop,
 	.cable_detect	= ata_cable_40wire,
 	.set_piomode	= triflex_set_piomode,
-	.prereset	= triflex_prereset,
+	.reset.prereset	= triflex_prereset,
 };
 
 static int triflex_init_one(struct pci_dev *dev, const struct pci_device_id *id)
diff --git a/drivers/ata/pata_via.c b/drivers/ata/pata_via.c
index bb80e7800dcb..a8c9cf685b4b 100644
--- a/drivers/ata/pata_via.c
+++ b/drivers/ata/pata_via.c
@@ -451,7 +451,7 @@ static struct ata_port_operations via_port_ops = {
 	.cable_detect	= via_cable_detect,
 	.set_piomode	= via_set_piomode,
 	.set_dmamode	= via_set_dmamode,
-	.prereset	= via_pre_reset,
+	.reset.prereset	= via_pre_reset,
 	.sff_tf_load	= via_tf_load,
 	.port_start	= via_port_start,
 	.mode_filter	= via_mode_filter,
diff --git a/drivers/ata/pdc_adma.c b/drivers/ata/pdc_adma.c
index 8e6b2599f0d5..17a5a59861c3 100644
--- a/drivers/ata/pdc_adma.c
+++ b/drivers/ata/pdc_adma.c
@@ -140,7 +140,7 @@ static struct ata_port_operations adma_ata_ops = {
 
 	.freeze			= adma_freeze,
 	.thaw			= adma_thaw,
-	.prereset		= adma_prereset,
+	.reset.prereset		= adma_prereset,
 
 	.port_start		= adma_port_start,
 	.port_stop		= adma_port_stop,
diff --git a/drivers/ata/sata_dwc_460ex.c b/drivers/ata/sata_dwc_460ex.c
index 6e1dd0d9c035..7a4f59202156 100644
--- a/drivers/ata/sata_dwc_460ex.c
+++ b/drivers/ata/sata_dwc_460ex.c
@@ -1097,7 +1097,7 @@ static struct ata_port_operations sata_dwc_ops = {
 	.inherits		= &ata_sff_port_ops,
 
 	.error_handler		= sata_dwc_error_handler,
-	.hardreset		= sata_dwc_hardreset,
+	.reset.hardreset	= sata_dwc_hardreset,
 
 	.qc_issue		= sata_dwc_qc_issue,
 
diff --git a/drivers/ata/sata_fsl.c b/drivers/ata/sata_fsl.c
index 87e91a937a44..84da8d6ef28e 100644
--- a/drivers/ata/sata_fsl.c
+++ b/drivers/ata/sata_fsl.c
@@ -1395,9 +1395,9 @@ static struct ata_port_operations sata_fsl_ops = {
 
 	.freeze = sata_fsl_freeze,
 	.thaw = sata_fsl_thaw,
-	.softreset = sata_fsl_softreset,
-	.hardreset = sata_fsl_hardreset,
-	.pmp_softreset = sata_fsl_softreset,
+	.reset.softreset = sata_fsl_softreset,
+	.reset.hardreset = sata_fsl_hardreset,
+	.pmp_reset.softreset = sata_fsl_softreset,
 	.error_handler = sata_fsl_error_handler,
 	.post_internal_cmd = sata_fsl_post_internal_cmd,
 
diff --git a/drivers/ata/sata_highbank.c b/drivers/ata/sata_highbank.c
index c8c817c51230..3421039f4bae 100644
--- a/drivers/ata/sata_highbank.c
+++ b/drivers/ata/sata_highbank.c
@@ -428,7 +428,7 @@ static int ahci_highbank_hardreset(struct ata_link *link, unsigned int *class,
 
 static struct ata_port_operations ahci_highbank_ops = {
 	.inherits		= &ahci_ops,
-	.hardreset		= ahci_highbank_hardreset,
+	.reset.hardreset	= ahci_highbank_hardreset,
 	.transmit_led_message   = ecx_transmit_led_message,
 };
 
diff --git a/drivers/ata/sata_inic162x.c b/drivers/ata/sata_inic162x.c
index db9c255dc9f2..46a8c20daf18 100644
--- a/drivers/ata/sata_inic162x.c
+++ b/drivers/ata/sata_inic162x.c
@@ -730,7 +730,7 @@ static struct ata_port_operations inic_port_ops = {
 
 	.freeze			= inic_freeze,
 	.thaw			= inic_thaw,
-	.hardreset		= inic_hardreset,
+	.reset.hardreset	= inic_hardreset,
 	.error_handler		= inic_error_handler,
 	.post_internal_cmd	= inic_post_internal_cmd,
 
diff --git a/drivers/ata/sata_mv.c b/drivers/ata/sata_mv.c
index bcbf96867f89..ffb396f61731 100644
--- a/drivers/ata/sata_mv.c
+++ b/drivers/ata/sata_mv.c
@@ -687,7 +687,7 @@ static struct ata_port_operations mv5_ops = {
 
 	.freeze			= mv_eh_freeze,
 	.thaw			= mv_eh_thaw,
-	.hardreset		= mv_hardreset,
+	.reset.hardreset	= mv_hardreset,
 
 	.scr_read		= mv5_scr_read,
 	.scr_write		= mv5_scr_write,
@@ -709,10 +709,10 @@ static struct ata_port_operations mv6_ops = {
 
 	.freeze			= mv_eh_freeze,
 	.thaw			= mv_eh_thaw,
-	.hardreset		= mv_hardreset,
-	.softreset		= mv_softreset,
-	.pmp_hardreset		= mv_pmp_hardreset,
-	.pmp_softreset		= mv_softreset,
+	.reset.hardreset	= mv_hardreset,
+	.reset.softreset	= mv_softreset,
+	.pmp_reset.hardreset	= mv_pmp_hardreset,
+	.pmp_reset.softreset	= mv_softreset,
 	.error_handler		= mv_pmp_error_handler,
 
 	.scr_read		= mv_scr_read,
diff --git a/drivers/ata/sata_nv.c b/drivers/ata/sata_nv.c
index f36e2915ccf1..841e7de2bba6 100644
--- a/drivers/ata/sata_nv.c
+++ b/drivers/ata/sata_nv.c
@@ -462,7 +462,7 @@ static struct ata_port_operations nv_generic_ops = {
 	.lost_interrupt		= ATA_OP_NULL,
 	.scr_read		= nv_scr_read,
 	.scr_write		= nv_scr_write,
-	.hardreset		= nv_hardreset,
+	.reset.hardreset	= nv_hardreset,
 };
 
 static struct ata_port_operations nv_nf2_ops = {
diff --git a/drivers/ata/sata_promise.c b/drivers/ata/sata_promise.c
index 2df1a070b25a..2a005aede123 100644
--- a/drivers/ata/sata_promise.c
+++ b/drivers/ata/sata_promise.c
@@ -188,7 +188,7 @@ static struct ata_port_operations pdc_sata_ops = {
 	.scr_read		= pdc_sata_scr_read,
 	.scr_write		= pdc_sata_scr_write,
 	.port_start		= pdc_sata_port_start,
-	.hardreset		= pdc_sata_hardreset,
+	.reset.hardreset	= pdc_sata_hardreset,
 };
 
 /* First-generation chips need a more restrictive ->check_atapi_dma op,
@@ -206,7 +206,7 @@ static struct ata_port_operations pdc_pata_ops = {
 	.freeze			= pdc_freeze,
 	.thaw			= pdc_thaw,
 	.port_start		= pdc_common_port_start,
-	.softreset		= pdc_pata_softreset,
+	.reset.softreset	= pdc_pata_softreset,
 };
 
 static const struct ata_port_info pdc_port_info[] = {
diff --git a/drivers/ata/sata_qstor.c b/drivers/ata/sata_qstor.c
index 8a6286159044..cfb9b5b61cd7 100644
--- a/drivers/ata/sata_qstor.c
+++ b/drivers/ata/sata_qstor.c
@@ -123,8 +123,8 @@ static struct ata_port_operations qs_ata_ops = {
 
 	.freeze			= qs_freeze,
 	.thaw			= qs_thaw,
-	.prereset		= qs_prereset,
-	.softreset		= ATA_OP_NULL,
+	.reset.prereset		= qs_prereset,
+	.reset.softreset	= ATA_OP_NULL,
 	.error_handler		= qs_error_handler,
 	.lost_interrupt		= ATA_OP_NULL,
 
diff --git a/drivers/ata/sata_rcar.c b/drivers/ata/sata_rcar.c
index 22820a02d740..487eadd4073f 100644
--- a/drivers/ata/sata_rcar.c
+++ b/drivers/ata/sata_rcar.c
@@ -624,7 +624,7 @@ static struct ata_port_operations sata_rcar_port_ops = {
 
 	.freeze			= sata_rcar_freeze,
 	.thaw			= sata_rcar_thaw,
-	.softreset		= sata_rcar_softreset,
+	.reset.softreset	= sata_rcar_softreset,
 
 	.scr_read		= sata_rcar_scr_read,
 	.scr_write		= sata_rcar_scr_write,
diff --git a/drivers/ata/sata_sil24.c b/drivers/ata/sata_sil24.c
index 87f4cde6a686..d642ece9f07a 100644
--- a/drivers/ata/sata_sil24.c
+++ b/drivers/ata/sata_sil24.c
@@ -393,10 +393,10 @@ static struct ata_port_operations sil24_ops = {
 
 	.freeze			= sil24_freeze,
 	.thaw			= sil24_thaw,
-	.softreset		= sil24_softreset,
-	.hardreset		= sil24_hardreset,
-	.pmp_softreset		= sil24_softreset,
-	.pmp_hardreset		= sil24_pmp_hardreset,
+	.reset.softreset	= sil24_softreset,
+	.reset.hardreset	= sil24_hardreset,
+	.pmp_reset.softreset	= sil24_softreset,
+	.pmp_reset.hardreset	= sil24_pmp_hardreset,
 	.error_handler		= sil24_error_handler,
 	.post_internal_cmd	= sil24_post_internal_cmd,
 	.dev_config		= sil24_dev_config,
diff --git a/drivers/ata/sata_svw.c b/drivers/ata/sata_svw.c
index 598a872f6a08..c5d6aa36c9c3 100644
--- a/drivers/ata/sata_svw.c
+++ b/drivers/ata/sata_svw.c
@@ -340,8 +340,8 @@ static const struct scsi_host_template k2_sata_sht = {
 
 static struct ata_port_operations k2_sata_ops = {
 	.inherits		= &ata_bmdma_port_ops,
-	.softreset              = k2_sata_softreset,
-	.hardreset              = k2_sata_hardreset,
+	.reset.softreset	= k2_sata_softreset,
+	.reset.hardreset	= k2_sata_hardreset,
 	.sff_tf_load		= k2_sata_tf_load,
 	.sff_tf_read		= k2_sata_tf_read,
 	.sff_check_status	= k2_stat_check_status,
diff --git a/drivers/ata/sata_sx4.c b/drivers/ata/sata_sx4.c
index f7f5131af937..0986ebd1eb4e 100644
--- a/drivers/ata/sata_sx4.c
+++ b/drivers/ata/sata_sx4.c
@@ -241,7 +241,7 @@ static struct ata_port_operations pdc_20621_ops = {
 
 	.freeze			= pdc_freeze,
 	.thaw			= pdc_thaw,
-	.softreset		= pdc_softreset,
+	.reset.softreset	= pdc_softreset,
 	.error_handler		= pdc_error_handler,
 	.lost_interrupt		= ATA_OP_NULL,
 	.post_internal_cmd	= pdc_post_internal_cmd,
diff --git a/drivers/ata/sata_uli.c b/drivers/ata/sata_uli.c
index 52894ff49dcb..44985796cc47 100644
--- a/drivers/ata/sata_uli.c
+++ b/drivers/ata/sata_uli.c
@@ -67,7 +67,7 @@ static struct ata_port_operations uli_ops = {
 	.inherits		= &ata_bmdma_port_ops,
 	.scr_read		= uli_scr_read,
 	.scr_write		= uli_scr_write,
-	.hardreset		= ATA_OP_NULL,
+	.reset.hardreset	= ATA_OP_NULL,
 };
 
 static const struct ata_port_info uli_port_info = {
diff --git a/drivers/ata/sata_via.c b/drivers/ata/sata_via.c
index 4ecd8f33b082..68e9003ec2d4 100644
--- a/drivers/ata/sata_via.c
+++ b/drivers/ata/sata_via.c
@@ -120,7 +120,7 @@ static struct ata_port_operations svia_base_ops = {
 static struct ata_port_operations vt6420_sata_ops = {
 	.inherits		= &svia_base_ops,
 	.freeze			= svia_noop_freeze,
-	.prereset		= vt6420_prereset,
+	.reset.prereset		= vt6420_prereset,
 	.bmdma_start		= vt6420_bmdma_start,
 };
 
@@ -140,7 +140,7 @@ static struct ata_port_operations vt6421_sata_ops = {
 
 static struct ata_port_operations vt8251_ops = {
 	.inherits		= &svia_base_ops,
-	.hardreset		= sata_std_hardreset,
+	.reset.hardreset	= sata_std_hardreset,
 	.scr_read		= vt8251_scr_read,
 	.scr_write		= vt8251_scr_write,
 };
diff --git a/drivers/scsi/libsas/sas_ata.c b/drivers/scsi/libsas/sas_ata.c
index 7b4e7a61965a..adb9e7a94785 100644
--- a/drivers/scsi/libsas/sas_ata.c
+++ b/drivers/scsi/libsas/sas_ata.c
@@ -559,8 +559,8 @@ static int sas_ata_prereset(struct ata_link *link, unsigned long deadline)
 }
 
 static struct ata_port_operations sas_sata_ops = {
-	.prereset		= sas_ata_prereset,
-	.hardreset		= sas_ata_hard_reset,
+	.reset.prereset		= sas_ata_prereset,
+	.reset.hardreset	= sas_ata_hard_reset,
 	.error_handler		= ata_std_error_handler,
 	.post_internal_cmd	= sas_ata_post_internal,
 	.qc_defer               = ata_std_qc_defer,
diff --git a/include/linux/libata.h b/include/linux/libata.h
index cf0b3fff3198..912ace523880 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -944,6 +944,13 @@ struct ata_port {
  */
 #define ATA_OP_NULL		(void *)(unsigned long)(-ENOENT)
 
+struct ata_reset_operations {
+	ata_prereset_fn_t	prereset;
+	ata_reset_fn_t		softreset;
+	ata_reset_fn_t		hardreset;
+	ata_postreset_fn_t	postreset;
+};
+
 struct ata_port_operations {
 	/*
 	 * Command execution
@@ -970,14 +977,8 @@ struct ata_port_operations {
 
 	void (*freeze)(struct ata_port *ap);
 	void (*thaw)(struct ata_port *ap);
-	ata_prereset_fn_t	prereset;
-	ata_reset_fn_t		softreset;
-	ata_reset_fn_t		hardreset;
-	ata_postreset_fn_t	postreset;
-	ata_prereset_fn_t	pmp_prereset;
-	ata_reset_fn_t		pmp_softreset;
-	ata_reset_fn_t		pmp_hardreset;
-	ata_postreset_fn_t	pmp_postreset;
+	struct ata_reset_operations reset;
+	struct ata_reset_operations pmp_reset;
 	void (*error_handler)(struct ata_port *ap);
 	void (*lost_interrupt)(struct ata_port *ap);
 	void (*post_internal_cmd)(struct ata_queued_cmd *qc);
-- 
cgit v1.2.3


From 35cff7af7598b9eb143cc0556e5532e2ded3b61a Mon Sep 17 00:00:00 2001
From: Sakari Ailus <sakari.ailus@linux.intel.com>
Date: Tue, 20 May 2025 13:34:37 +0300
Subject: container_of: Document container_of() is not to be used in new code

There is a warning in the kerneldoc documentation of container_of() that
constness of its ptr argument is lost. While this is a valid suggestion
container_of_const() should be used instead, the vast majority of new
code still uses container_of():

$ git diff v6.13 v6.14|grep container_of\(|wc -l
646
$ git diff v6.13 v6.14|grep container_of_const|wc -l
9

Make an explicit recommendation to use container_of_const().

Signed-off-by: Sakari Ailus <sakari.ailus@linux.intel.com>
Link: https://lore.kernel.org/r/20250520103437.468691-1-sakari.ailus@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/container_of.h | 3 +++
 1 file changed, 3 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/container_of.h b/include/linux/container_of.h
index 713890c867be..1f6ebf27d962 100644
--- a/include/linux/container_of.h
+++ b/include/linux/container_of.h
@@ -14,6 +14,7 @@
  * @member:	the name of the member within the struct.
  *
  * WARNING: any const qualifier of @ptr is lost.
+ * Do not use container_of() in new code.
  */
 #define container_of(ptr, type, member) ({				\
 	void *__mptr = (void *)(ptr);					\
@@ -28,6 +29,8 @@
  * @ptr:		the pointer to the member
  * @type:		the type of the container struct this is embedded in.
  * @member:		the name of the member within the struct.
+ *
+ * Always prefer container_of_const() instead of container_of() in new code.
  */
 #define container_of_const(ptr, type, member)				\
 	_Generic(ptr,							\
-- 
cgit v1.2.3


From 5eac636917486f3f072328d7f5bcdc22bbc9a1d1 Mon Sep 17 00:00:00 2001
From: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Date: Tue, 1 Jul 2025 14:07:01 +0200
Subject: fsi: make fsi_bus_type constant

Now that the driver core can properly handle constant struct bus_type,
move the fsi_bus_type variable to be a constant structure as well,
placing it into read-only memory which can not be modified at runtime.

Cc: Ninad Palsule <ninad@linux.ibm.com>
Cc: linux-fsi@lists.ozlabs.org
Reviewed-by: Eddie James <eajames@linux.ibm.com>
Link: https://lore.kernel.org/r/2025070100-overblown-busily-a04b@gregkh
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 drivers/fsi/fsi-core.c | 2 +-
 include/linux/fsi.h    | 2 +-
 2 files changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/fsi/fsi-core.c b/drivers/fsi/fsi-core.c
index 50e8736039fe..ee39d1699387 100644
--- a/drivers/fsi/fsi-core.c
+++ b/drivers/fsi/fsi-core.c
@@ -1404,7 +1404,7 @@ void fsi_driver_unregister(struct fsi_driver *fsi_drv)
 }
 EXPORT_SYMBOL_GPL(fsi_driver_unregister);
 
-struct bus_type fsi_bus_type = {
+const struct bus_type fsi_bus_type = {
 	.name		= "fsi",
 	.match		= fsi_bus_match,
 };
diff --git a/include/linux/fsi.h b/include/linux/fsi.h
index 8c5eef808788..adea1b432f2d 100644
--- a/include/linux/fsi.h
+++ b/include/linux/fsi.h
@@ -68,7 +68,7 @@ extern int fsi_slave_read(struct fsi_slave *slave, uint32_t addr,
 extern int fsi_slave_write(struct fsi_slave *slave, uint32_t addr,
 		const void *val, size_t size);
 
-extern struct bus_type fsi_bus_type;
+extern const struct bus_type fsi_bus_type;
 extern const struct device_type fsi_cdev_type;
 
 enum fsi_dev_type {
-- 
cgit v1.2.3


From e9d8e2bf23206825ca9b4d3caf587945ba807939 Mon Sep 17 00:00:00 2001
From: Taotao Chen <chentaotao@didiglobal.com>
Date: Wed, 16 Jul 2025 09:36:06 +0000
Subject: fs: change write_begin/write_end interface to take struct kiocb *

Change the address_space_operations callbacks write_begin() and
write_end() to take struct kiocb * as the first argument instead of
struct file *.

Update all affected function prototypes, implementations, call sites,
and related documentation across VFS, filesystems, and block layer.

Part of a series refactoring address_space_operations write_begin and
write_end callbacks to use struct kiocb for passing write context and
flags.

Signed-off-by: Taotao Chen <chentaotao@didiglobal.com>
Link: https://lore.kernel.org/20250716093559.217344-4-chentaotao@didiglobal.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 Documentation/filesystems/locking.rst |  4 ++--
 Documentation/filesystems/vfs.rst     |  6 +++---
 block/fops.c                          | 13 ++++++++-----
 fs/adfs/inode.c                       |  9 +++++----
 fs/affs/file.c                        | 26 +++++++++++++++-----------
 fs/bcachefs/fs-io-buffered.c          |  4 ++--
 fs/bcachefs/fs-io-buffered.h          |  4 ++--
 fs/bfs/file.c                         |  7 ++++---
 fs/buffer.c                           | 26 +++++++++++++-------------
 fs/ceph/addr.c                        | 10 +++++++---
 fs/ecryptfs/mmap.c                    | 10 +++++-----
 fs/exfat/file.c                       | 11 +++++------
 fs/exfat/inode.c                      | 16 +++++++++-------
 fs/ext2/inode.c                       | 11 ++++++-----
 fs/ext4/inode.c                       | 18 ++++++++++--------
 fs/f2fs/data.c                        |  8 +++++---
 fs/fat/inode.c                        | 18 ++++++++++--------
 fs/fuse/file.c                        | 14 +++++++++-----
 fs/hfs/hfs_fs.h                       |  2 +-
 fs/hfs/inode.c                        |  4 ++--
 fs/hfsplus/hfsplus_fs.h               |  6 ++++--
 fs/hfsplus/inode.c                    |  8 +++++---
 fs/hostfs/hostfs_kern.c               |  8 +++++---
 fs/hpfs/file.c                        | 18 ++++++++++--------
 fs/hugetlbfs/inode.c                  |  9 +++++----
 fs/jffs2/file.c                       | 28 ++++++++++++++++------------
 fs/jfs/inode.c                        | 16 +++++++++-------
 fs/libfs.c                            | 11 ++++++-----
 fs/minix/inode.c                      |  7 ++++---
 fs/nfs/file.c                         |  8 ++++++--
 fs/nilfs2/inode.c                     |  8 +++++---
 fs/ntfs3/file.c                       |  4 ++--
 fs/ntfs3/inode.c                      |  7 ++++---
 fs/ntfs3/ntfs_fs.h                    | 10 ++++++----
 fs/ocfs2/aops.c                       |  6 ++++--
 fs/omfs/file.c                        |  7 ++++---
 fs/orangefs/inode.c                   | 16 +++++++++-------
 fs/ubifs/file.c                       |  8 +++++---
 fs/udf/inode.c                        | 11 +++++++----
 fs/ufs/inode.c                        | 16 +++++++++-------
 fs/vboxsf/file.c                      |  5 +++--
 include/linux/buffer_head.h           |  4 ++--
 include/linux/fs.h                    | 11 ++++++-----
 mm/filemap.c                          |  4 ++--
 mm/shmem.c                            | 12 ++++++------
 45 files changed, 267 insertions(+), 202 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/locking.rst b/Documentation/filesystems/locking.rst
index 2e567e341c3b..580581281ed7 100644
--- a/Documentation/filesystems/locking.rst
+++ b/Documentation/filesystems/locking.rst
@@ -253,10 +253,10 @@ prototypes::
 	int (*writepages)(struct address_space *, struct writeback_control *);
 	bool (*dirty_folio)(struct address_space *, struct folio *folio);
 	void (*readahead)(struct readahead_control *);
-	int (*write_begin)(struct file *, struct address_space *mapping,
+	int (*write_begin)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len,
 				struct folio **foliop, void **fsdata);
-	int (*write_end)(struct file *, struct address_space *mapping,
+	int (*write_end)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct folio *folio, void *fsdata);
 	sector_t (*bmap)(struct address_space *, sector_t);
diff --git a/Documentation/filesystems/vfs.rst b/Documentation/filesystems/vfs.rst
index dd9da7e04a99..57604b07bdc9 100644
--- a/Documentation/filesystems/vfs.rst
+++ b/Documentation/filesystems/vfs.rst
@@ -823,10 +823,10 @@ cache in your filesystem.  The following members are defined:
 		int (*writepages)(struct address_space *, struct writeback_control *);
 		bool (*dirty_folio)(struct address_space *, struct folio *);
 		void (*readahead)(struct readahead_control *);
-		int (*write_begin)(struct file *, struct address_space *mapping,
+		int (*write_begin)(const struct kiocb *, struct address_space *mapping,
 				   loff_t pos, unsigned len,
-				struct page **pagep, void **fsdata);
-		int (*write_end)(struct file *, struct address_space *mapping,
+				   struct page **pagep, void **fsdata);
+		int (*write_end)(const struct kiocb *, struct address_space *mapping,
 				 loff_t pos, unsigned len, unsigned copied,
 				 struct folio *folio, void *fsdata);
 		sector_t (*bmap)(struct address_space *, sector_t);
diff --git a/block/fops.c b/block/fops.c
index 35cea0cb304d..f34e7315c83c 100644
--- a/block/fops.c
+++ b/block/fops.c
@@ -496,15 +496,18 @@ static void blkdev_readahead(struct readahead_control *rac)
 	mpage_readahead(rac, blkdev_get_block);
 }
 
-static int blkdev_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+static int blkdev_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping, loff_t pos,
+			      unsigned len, struct folio **foliop,
+			      void **fsdata)
 {
 	return block_write_begin(mapping, pos, len, foliop, blkdev_get_block);
 }
 
-static int blkdev_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
-		void *fsdata)
+static int blkdev_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned copied,
+			    struct folio *folio, void *fsdata)
 {
 	int ret;
 	ret = block_write_end(pos, len, copied, folio);
diff --git a/fs/adfs/inode.c b/fs/adfs/inode.c
index 21527189e430..6830f8bc8d4e 100644
--- a/fs/adfs/inode.c
+++ b/fs/adfs/inode.c
@@ -53,13 +53,14 @@ static void adfs_write_failed(struct address_space *mapping, loff_t to)
 		truncate_pagecache(inode, inode->i_size);
 }
 
-static int adfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int adfs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len,
+			    struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				adfs_get_block,
 				&ADFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 7a71018e3f67..219ea0353906 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -415,13 +415,14 @@ affs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	return ret;
 }
 
-static int affs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int affs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len,
+			    struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				affs_get_block,
 				&AFFS_I(mapping->host)->mmu_private);
 	if (unlikely(ret))
@@ -430,14 +431,15 @@ static int affs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int affs_write_end(struct file *file, struct address_space *mapping,
-			  loff_t pos, unsigned int len, unsigned int copied,
+static int affs_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping, loff_t pos,
+			  unsigned int len, unsigned int copied,
 			  struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 
 	/* Clear Archived bit on file writes, as AmigaOS would do */
 	if (AFFS_I(inode)->i_protect & FIBF_ARCHIVED) {
@@ -645,7 +647,8 @@ static int affs_read_folio_ofs(struct file *file, struct folio *folio)
 	return err;
 }
 
-static int affs_write_begin_ofs(struct file *file, struct address_space *mapping,
+static int affs_write_begin_ofs(const struct kiocb *iocb,
+				struct address_space *mapping,
 				loff_t pos, unsigned len,
 				struct folio **foliop, void **fsdata)
 {
@@ -684,9 +687,10 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 	return err;
 }
 
-static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct folio *folio, void *fsdata)
+static int affs_write_end_ofs(const struct kiocb *iocb,
+			      struct address_space *mapping,
+			      loff_t pos, unsigned len, unsigned copied,
+			      struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct super_block *sb = inode->i_sb;
diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
index 66bacdd49f78..1c54b9b5bd69 100644
--- a/fs/bcachefs/fs-io-buffered.c
+++ b/fs/bcachefs/fs-io-buffered.c
@@ -674,7 +674,7 @@ int bch2_writepages(struct address_space *mapping, struct writeback_control *wbc
 
 /* buffered writes: */
 
-int bch2_write_begin(struct file *file, struct address_space *mapping,
+int bch2_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		     loff_t pos, unsigned len,
 		     struct folio **foliop, void **fsdata)
 {
@@ -757,7 +757,7 @@ err_unlock:
 	return bch2_err_class(ret);
 }
 
-int bch2_write_end(struct file *file, struct address_space *mapping,
+int bch2_write_end(const struct kiocb *iocb, struct address_space *mapping,
 		   loff_t pos, unsigned len, unsigned copied,
 		   struct folio *folio, void *fsdata)
 {
diff --git a/fs/bcachefs/fs-io-buffered.h b/fs/bcachefs/fs-io-buffered.h
index 3207ebbb4ab4..14de91c27656 100644
--- a/fs/bcachefs/fs-io-buffered.h
+++ b/fs/bcachefs/fs-io-buffered.h
@@ -10,9 +10,9 @@ int bch2_read_folio(struct file *, struct folio *);
 int bch2_writepages(struct address_space *, struct writeback_control *);
 void bch2_readahead(struct readahead_control *);
 
-int bch2_write_begin(struct file *, struct address_space *, loff_t pos,
+int bch2_write_begin(const struct kiocb *, struct address_space *, loff_t pos,
 		     unsigned len, struct folio **, void **);
-int bch2_write_end(struct file *, struct address_space *, loff_t,
+int bch2_write_end(const struct kiocb *, struct address_space *, loff_t,
 		   unsigned len, unsigned copied, struct folio *, void *);
 
 ssize_t bch2_write_iter(struct kiocb *, struct iov_iter *);
diff --git a/fs/bfs/file.c b/fs/bfs/file.c
index fa66a09e496a..10dc0151ea55 100644
--- a/fs/bfs/file.c
+++ b/fs/bfs/file.c
@@ -170,9 +170,10 @@ static void bfs_write_failed(struct address_space *mapping, loff_t to)
 		truncate_pagecache(inode, inode->i_size);
 }
 
-static int bfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int bfs_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len,
+			   struct folio **foliop, void **fsdata)
 {
 	int ret;
 
diff --git a/fs/buffer.c b/fs/buffer.c
index 565fe88773c2..ead4dc85debd 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -2297,9 +2297,9 @@ int block_write_end(loff_t pos, unsigned len, unsigned copied,
 }
 EXPORT_SYMBOL(block_write_end);
 
-int generic_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+int generic_write_end(const struct kiocb *iocb, struct address_space *mapping,
+		      loff_t pos, unsigned len, unsigned copied,
+		      struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	loff_t old_size = inode->i_size;
@@ -2494,7 +2494,8 @@ out:
 }
 EXPORT_SYMBOL(generic_cont_expand_simple);
 
-static int cont_expand_zero(struct file *file, struct address_space *mapping,
+static int cont_expand_zero(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
@@ -2518,12 +2519,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		}
 		len = PAGE_SIZE - zerofrom;
 
-		err = aops->write_begin(file, mapping, curpos, len,
+		err = aops->write_begin(iocb, mapping, curpos, len,
 					    &folio, &fsdata);
 		if (err)
 			goto out;
 		folio_zero_range(folio, offset_in_folio(folio, curpos), len);
-		err = aops->write_end(file, mapping, curpos, len, len,
+		err = aops->write_end(iocb, mapping, curpos, len, len,
 						folio, fsdata);
 		if (err < 0)
 			goto out;
@@ -2551,12 +2552,12 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		}
 		len = offset - zerofrom;
 
-		err = aops->write_begin(file, mapping, curpos, len,
+		err = aops->write_begin(iocb, mapping, curpos, len,
 					    &folio, &fsdata);
 		if (err)
 			goto out;
 		folio_zero_range(folio, offset_in_folio(folio, curpos), len);
-		err = aops->write_end(file, mapping, curpos, len, len,
+		err = aops->write_end(iocb, mapping, curpos, len, len,
 						folio, fsdata);
 		if (err < 0)
 			goto out;
@@ -2571,17 +2572,16 @@ out:
  * For moronic filesystems that do not allow holes in file.
  * We may have to extend the file.
  */
-int cont_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata,
-			get_block_t *get_block, loff_t *bytes)
+int cont_write_begin(const struct kiocb *iocb, struct address_space *mapping,
+		     loff_t pos, unsigned len, struct folio **foliop,
+		     void **fsdata, get_block_t *get_block, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
 	unsigned int blocksize = i_blocksize(inode);
 	unsigned int zerofrom;
 	int err;
 
-	err = cont_expand_zero(file, mapping, pos, bytes);
+	err = cont_expand_zero(iocb, mapping, pos, bytes);
 	if (err)
 		return err;
 
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index 60a621b00c65..02468c848cce 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -1864,10 +1864,12 @@ static int ceph_netfs_check_write_begin(struct file *file, loff_t pos, unsigned
  * We are only allowed to write into/dirty the page if the page is
  * clean, or already dirty within the same snap context.
  */
-static int ceph_write_begin(struct file *file, struct address_space *mapping,
+static int ceph_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned len,
 			    struct folio **foliop, void **fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int r;
@@ -1885,10 +1887,12 @@ static int ceph_write_begin(struct file *file, struct address_space *mapping,
  * we don't do anything in here that simple_write_end doesn't do
  * except adjust dirty page accounting
  */
-static int ceph_write_end(struct file *file, struct address_space *mapping,
-			  loff_t pos, unsigned len, unsigned copied,
+static int ceph_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping, loff_t pos,
+			  unsigned len, unsigned copied,
 			  struct folio *folio, void *fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct inode *inode = file_inode(file);
 	struct ceph_client *cl = ceph_inode_to_client(inode);
 	bool check_cap = false;
diff --git a/fs/ecryptfs/mmap.c b/fs/ecryptfs/mmap.c
index 60f0ac8744b5..2c2b12fedeae 100644
--- a/fs/ecryptfs/mmap.c
+++ b/fs/ecryptfs/mmap.c
@@ -228,7 +228,7 @@ out:
 
 /**
  * ecryptfs_write_begin
- * @file: The eCryptfs file
+ * @iocb: I/O control block for the eCryptfs file
  * @mapping: The eCryptfs object
  * @pos: The file offset at which to start writing
  * @len: Length of the write
@@ -239,7 +239,7 @@ out:
  *
  * Returns zero on success; non-zero otherwise
  */
-static int ecryptfs_write_begin(struct file *file,
+static int ecryptfs_write_begin(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct folio **foliop, void **fsdata)
@@ -322,7 +322,7 @@ static int ecryptfs_write_begin(struct file *file,
 	 * Note, this will increase i_size. */
 	if (index != 0) {
 		if (prev_page_end_size > i_size_read(mapping->host)) {
-			rc = ecryptfs_truncate(file->f_path.dentry,
+			rc = ecryptfs_truncate(iocb->ki_filp->f_path.dentry,
 					       prev_page_end_size);
 			if (rc) {
 				printk(KERN_ERR "%s: Error on attempt to "
@@ -429,7 +429,7 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode)
 
 /**
  * ecryptfs_write_end
- * @file: The eCryptfs file object
+ * @iocb: I/O control block for the eCryptfs file
  * @mapping: The eCryptfs object
  * @pos: The file position
  * @len: The length of the data (unused)
@@ -437,7 +437,7 @@ int ecryptfs_write_inode_size_to_metadata(struct inode *ecryptfs_inode)
  * @folio: The eCryptfs folio
  * @fsdata: The fsdata (unused)
  */
-static int ecryptfs_write_end(struct file *file,
+static int ecryptfs_write_end(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct folio *folio, void *fsdata)
diff --git a/fs/exfat/file.c b/fs/exfat/file.c
index 841a5b18e3df..70f53edd0a10 100644
--- a/fs/exfat/file.c
+++ b/fs/exfat/file.c
@@ -532,11 +532,10 @@ int exfat_file_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	return blkdev_issue_flush(inode->i_sb->s_bdev);
 }
 
-static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size)
+static int exfat_extend_valid_size(struct inode *inode, loff_t new_valid_size)
 {
 	int err;
 	loff_t pos;
-	struct inode *inode = file_inode(file);
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	struct address_space *mapping = inode->i_mapping;
 	const struct address_space_operations *ops = mapping->a_ops;
@@ -551,14 +550,14 @@ static int exfat_extend_valid_size(struct file *file, loff_t new_valid_size)
 		if (pos + len > new_valid_size)
 			len = new_valid_size - pos;
 
-		err = ops->write_begin(file, mapping, pos, len, &folio, NULL);
+		err = ops->write_begin(NULL, mapping, pos, len, &folio, NULL);
 		if (err)
 			goto out;
 
 		off = offset_in_folio(folio, pos);
 		folio_zero_new_buffers(folio, off, off + len);
 
-		err = ops->write_end(file, mapping, pos, len, len, folio, NULL);
+		err = ops->write_end(NULL, mapping, pos, len, len, folio, NULL);
 		if (err < 0)
 			goto out;
 		pos += len;
@@ -604,7 +603,7 @@ static ssize_t exfat_file_write_iter(struct kiocb *iocb, struct iov_iter *iter)
 	}
 
 	if (pos > valid_size) {
-		ret = exfat_extend_valid_size(file, pos);
+		ret = exfat_extend_valid_size(inode, pos);
 		if (ret < 0 && ret != -ENOSPC) {
 			exfat_err(inode->i_sb,
 				"write: fail to zero from %llu to %llu(%zd)",
@@ -665,7 +664,7 @@ static vm_fault_t exfat_page_mkwrite(struct vm_fault *vmf)
 			start + vma->vm_end - vma->vm_start);
 
 	if (ei->valid_size < end) {
-		err = exfat_extend_valid_size(file, end);
+		err = exfat_extend_valid_size(inode, end);
 		if (err < 0) {
 			inode_unlock(inode);
 			return vmf_fs_error(err);
diff --git a/fs/exfat/inode.c b/fs/exfat/inode.c
index b22c02d6000f..c10844e1e16c 100644
--- a/fs/exfat/inode.c
+++ b/fs/exfat/inode.c
@@ -446,9 +446,10 @@ static void exfat_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int exfat_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned int len,
-		struct folio **foliop, void **fsdata)
+static int exfat_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned int len,
+			     struct folio **foliop, void **fsdata)
 {
 	int ret;
 
@@ -463,15 +464,16 @@ static int exfat_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int exfat_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned int len, unsigned int copied,
-		struct folio *folio, void *fsdata)
+static int exfat_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned int len, unsigned int copied,
+			   struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct exfat_inode_info *ei = EXFAT_I(inode);
 	int err;
 
-	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (err < len)
 		exfat_write_failed(mapping, pos+len);
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index 30f8201c155f..d35ca26eee3c 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -915,7 +915,7 @@ static void ext2_readahead(struct readahead_control *rac)
 }
 
 static int
-ext2_write_begin(struct file *file, struct address_space *mapping,
+ext2_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	int ret;
@@ -926,13 +926,14 @@ ext2_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int ext2_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int ext2_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct folio *folio, void *fsdata)
 {
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (ret < len)
 		ext2_write_failed(mapping, pos + len);
 	return ret;
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index e6aa7ca6d842..9a16efd072bb 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -1252,7 +1252,8 @@ int ext4_block_write_begin(handle_t *handle, struct folio *folio,
  * and the ext4_write_end().  So doing the jbd2_journal_start at the start of
  * ext4_write_begin() is the right place.
  */
-static int ext4_write_begin(struct file *file, struct address_space *mapping,
+static int ext4_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned len,
 			    struct folio **foliop, void **fsdata)
 {
@@ -1400,12 +1401,12 @@ static int write_end_fn(handle_t *handle, struct inode *inode,
 
 /*
  * We need to pick up the new inode size which generic_commit_write gave us
- * `file' can be NULL - eg, when called from page_symlink().
+ * `iocb` can be NULL - eg, when called from page_symlink().
  *
  * ext4 never places buffers on inode->i_mapping->i_private_list.  metadata
  * buffers are managed internally.
  */
-static int ext4_write_end(struct file *file,
+static int ext4_write_end(const struct kiocb *iocb,
 			  struct address_space *mapping,
 			  loff_t pos, unsigned len, unsigned copied,
 			  struct folio *folio, void *fsdata)
@@ -1510,7 +1511,7 @@ static void ext4_journalled_zero_new_buffers(handle_t *handle,
 	} while (bh != head);
 }
 
-static int ext4_journalled_write_end(struct file *file,
+static int ext4_journalled_write_end(const struct kiocb *iocb,
 				     struct address_space *mapping,
 				     loff_t pos, unsigned len, unsigned copied,
 				     struct folio *folio, void *fsdata)
@@ -3036,7 +3037,8 @@ static int ext4_nonda_switch(struct super_block *sb)
 	return 0;
 }
 
-static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
+static int ext4_da_write_begin(const struct kiocb *iocb,
+			       struct address_space *mapping,
 			       loff_t pos, unsigned len,
 			       struct folio **foliop, void **fsdata)
 {
@@ -3054,7 +3056,7 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 
 	if (ext4_nonda_switch(inode->i_sb) || ext4_verity_in_progress(inode)) {
 		*fsdata = (void *)FALL_BACK_TO_NONDELALLOC;
-		return ext4_write_begin(file, mapping, pos,
+		return ext4_write_begin(iocb, mapping, pos,
 					len, foliop, fsdata);
 	}
 	*fsdata = (void *)0;
@@ -3195,7 +3197,7 @@ static int ext4_da_do_write_end(struct address_space *mapping,
 	return copied;
 }
 
-static int ext4_da_write_end(struct file *file,
+static int ext4_da_write_end(const struct kiocb *iocb,
 			     struct address_space *mapping,
 			     loff_t pos, unsigned len, unsigned copied,
 			     struct folio *folio, void *fsdata)
@@ -3204,7 +3206,7 @@ static int ext4_da_write_end(struct file *file,
 	int write_mode = (int)(unsigned long)fsdata;
 
 	if (write_mode == FALL_BACK_TO_NONDELALLOC)
-		return ext4_write_end(file, mapping, pos,
+		return ext4_write_end(iocb, mapping, pos,
 				      len, copied, folio, fsdata);
 
 	trace_ext4_da_write_end(inode, pos, len, copied);
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 31e892842625..711ad80b38d0 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -3519,8 +3519,10 @@ reserve_block:
 	return 0;
 }
 
-static int f2fs_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+static int f2fs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, struct folio **foliop,
+			    void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -3656,7 +3658,7 @@ fail:
 	return err;
 }
 
-static int f2fs_write_end(struct file *file,
+static int f2fs_write_end(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len, unsigned copied,
 			struct folio *folio, void *fsdata)
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 3852bb66358c..9648ed097816 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -219,13 +219,14 @@ static void fat_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int fat_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int fat_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len,
+			   struct folio **foliop, void **fsdata)
 {
 	int err;
 
-	err = cont_write_begin(file, mapping, pos, len,
+	err = cont_write_begin(iocb, mapping, pos, len,
 				foliop, fsdata, fat_get_block,
 				&MSDOS_I(mapping->host)->mmu_private);
 	if (err < 0)
@@ -233,13 +234,14 @@ static int fat_write_begin(struct file *file, struct address_space *mapping,
 	return err;
 }
 
-static int fat_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int fat_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
+			 loff_t pos, unsigned len, unsigned copied,
+			 struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int err;
-	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (err < len)
 		fat_write_failed(mapping, pos + len);
 	if (!(err < 0) && !(MSDOS_I(inode)->i_attrs & ATTR_ARCH)) {
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index f102afc03359..21c6f8654bfe 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -2213,10 +2213,13 @@ out:
  * It's worthy to make sure that space is reserved on disk for the write,
  * but how to implement it without killing performance need more thinking.
  */
-static int fuse_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+static int fuse_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, struct folio **foliop,
+			    void **fsdata)
 {
 	pgoff_t index = pos >> PAGE_SHIFT;
+	struct file *file = iocb->ki_filp;
 	struct fuse_conn *fc = get_fuse_conn(file_inode(file));
 	struct folio *folio;
 	loff_t fsize;
@@ -2256,9 +2259,10 @@ error:
 	return err;
 }
 
-static int fuse_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied,
-		struct folio *folio, void *fsdata)
+static int fuse_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct folio *folio, void *fsdata)
 {
 	struct inode *inode = folio->mapping->host;
 
diff --git a/fs/hfs/hfs_fs.h b/fs/hfs/hfs_fs.h
index a0c7cb0f79fc..c3fd3172fdd6 100644
--- a/fs/hfs/hfs_fs.h
+++ b/fs/hfs/hfs_fs.h
@@ -201,7 +201,7 @@ extern int hfs_get_block(struct inode *, sector_t, struct buffer_head *, int);
 extern const struct address_space_operations hfs_aops;
 extern const struct address_space_operations hfs_btree_aops;
 
-int hfs_write_begin(struct file *file, struct address_space *mapping,
+int hfs_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		loff_t pos, unsigned len, struct folio **foliop, void **fsdata);
 extern struct inode *hfs_new_inode(struct inode *, const struct qstr *, umode_t);
 extern void hfs_inode_write_fork(struct inode *, struct hfs_extent *, __be32 *, __be32 *);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index a81ce7a740b9..096f338134f9 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -44,12 +44,12 @@ static void hfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-int hfs_write_begin(struct file *file, struct address_space *mapping,
+int hfs_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				hfs_get_block,
 				&HFS_I(mapping->host)->phys_size);
 	if (unlikely(ret))
diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
index 2f089bff0095..3d5c65aef3b2 100644
--- a/fs/hfsplus/hfsplus_fs.h
+++ b/fs/hfsplus/hfsplus_fs.h
@@ -473,8 +473,10 @@ extern const struct address_space_operations hfsplus_aops;
 extern const struct address_space_operations hfsplus_btree_aops;
 extern const struct dentry_operations hfsplus_dentry_operations;
 
-int hfsplus_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata);
+int hfsplus_write_begin(const struct kiocb *iocb,
+			struct address_space *mapping,
+			loff_t pos, unsigned len, struct folio **foliop,
+			void **fsdata);
 struct inode *hfsplus_new_inode(struct super_block *sb, struct inode *dir,
 				umode_t mode);
 void hfsplus_delete_inode(struct inode *inode);
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index f331e9574217..97d75bb2c388 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -38,12 +38,14 @@ static void hfsplus_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-int hfsplus_write_begin(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, struct folio **foliop, void **fsdata)
+int hfsplus_write_begin(const struct kiocb *iocb,
+			struct address_space *mapping, loff_t pos,
+			unsigned len, struct folio **foliop,
+			void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				hfsplus_get_block,
 				&HFSPLUS_I(mapping->host)->phys_size);
 	if (unlikely(ret))
diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
index 702c41317589..6c2cf0cdf3d6 100644
--- a/fs/hostfs/hostfs_kern.c
+++ b/fs/hostfs/hostfs_kern.c
@@ -445,7 +445,8 @@ static int hostfs_read_folio(struct file *file, struct folio *folio)
 	return ret;
 }
 
-static int hostfs_write_begin(struct file *file, struct address_space *mapping,
+static int hostfs_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping,
 			      loff_t pos, unsigned len,
 			      struct folio **foliop, void **fsdata)
 {
@@ -458,7 +459,8 @@ static int hostfs_write_begin(struct file *file, struct address_space *mapping,
 	return 0;
 }
 
-static int hostfs_write_end(struct file *file, struct address_space *mapping,
+static int hostfs_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned len, unsigned copied,
 			    struct folio *folio, void *fsdata)
 {
@@ -468,7 +470,7 @@ static int hostfs_write_end(struct file *file, struct address_space *mapping,
 	int err;
 
 	buffer = kmap_local_folio(folio, from);
-	err = write_file(FILE_HOSTFS_I(file)->fd, &pos, buffer, copied);
+	err = write_file(FILE_HOSTFS_I(iocb->ki_filp)->fd, &pos, buffer, copied);
 	kunmap_local(buffer);
 
 	if (!folio_test_uptodate(folio) && err == folio_size(folio))
diff --git a/fs/hpfs/file.c b/fs/hpfs/file.c
index 449a3fc1b8d9..7b95a3d2e2a6 100644
--- a/fs/hpfs/file.c
+++ b/fs/hpfs/file.c
@@ -188,13 +188,14 @@ static void hpfs_write_failed(struct address_space *mapping, loff_t to)
 	hpfs_unlock(inode->i_sb);
 }
 
-static int hpfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int hpfs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len,
+			    struct folio **foliop, void **fsdata)
 {
 	int ret;
 
-	ret = cont_write_begin(file, mapping, pos, len, foliop, fsdata,
+	ret = cont_write_begin(iocb, mapping, pos, len, foliop, fsdata,
 				hpfs_get_block,
 				&hpfs_i(mapping->host)->mmu_private);
 	if (unlikely(ret))
@@ -203,13 +204,14 @@ static int hpfs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int hpfs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int hpfs_write_end(const struct kiocb *iocb,
+			  struct address_space *mapping,
+			  loff_t pos, unsigned len, unsigned copied,
+			  struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 	int err;
-	err = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	err = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (err < len)
 		hpfs_write_failed(mapping, pos + len);
 	if (!(err < 0)) {
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index e4de5425838d..541aae502d4d 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -311,7 +311,7 @@ static ssize_t hugetlbfs_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	return retval;
 }
 
-static int hugetlbfs_write_begin(struct file *file,
+static int hugetlbfs_write_begin(const struct kiocb *iocb,
 			struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct folio **foliop, void **fsdata)
@@ -319,9 +319,10 @@ static int hugetlbfs_write_begin(struct file *file,
 	return -EINVAL;
 }
 
-static int hugetlbfs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int hugetlbfs_write_end(const struct kiocb *iocb,
+			       struct address_space *mapping,
+			       loff_t pos, unsigned len, unsigned copied,
+			       struct folio *folio, void *fsdata)
 {
 	BUG();
 	return -EINVAL;
diff --git a/fs/jffs2/file.c b/fs/jffs2/file.c
index 13c18ccc13b0..adec3af9bf8d 100644
--- a/fs/jffs2/file.c
+++ b/fs/jffs2/file.c
@@ -21,12 +21,14 @@
 #include <linux/jffs2.h>
 #include "nodelist.h"
 
-static int jffs2_write_end(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata);
-static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata);
+static int jffs2_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len, unsigned copied,
+			   struct folio *folio, void *fsdata);
+static int jffs2_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len,
+			     struct folio **foliop, void **fsdata);
 static int jffs2_read_folio(struct file *filp, struct folio *folio);
 
 int jffs2_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
@@ -121,9 +123,10 @@ static int jffs2_read_folio(struct file *file, struct folio *folio)
 	return ret;
 }
 
-static int jffs2_write_begin(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int jffs2_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len,
+			     struct folio **foliop, void **fsdata)
 {
 	struct folio *folio;
 	struct inode *inode = mapping->host;
@@ -235,9 +238,10 @@ out_err:
 	return ret;
 }
 
-static int jffs2_write_end(struct file *filp, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int jffs2_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len, unsigned copied,
+			   struct folio *folio, void *fsdata)
 {
 	/* Actually commit the write from the page cache page we're looking at.
 	 * For now, we write the full page out each time. It sucks, but it's simple
diff --git a/fs/jfs/inode.c b/fs/jfs/inode.c
index 60fc92dee24d..083e7fa54709 100644
--- a/fs/jfs/inode.c
+++ b/fs/jfs/inode.c
@@ -290,9 +290,10 @@ static void jfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int jfs_write_begin(struct file *file, struct address_space *mapping,
-				loff_t pos, unsigned len,
-				struct folio **foliop, void **fsdata)
+static int jfs_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len,
+			   struct folio **foliop, void **fsdata)
 {
 	int ret;
 
@@ -303,13 +304,14 @@ static int jfs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int jfs_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
-		void *fsdata)
+static int jfs_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
+			 loff_t pos, unsigned len, unsigned copied,
+			 struct folio *folio, void *fsdata)
 {
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (ret < len)
 		jfs_write_failed(mapping, pos + len);
 	return ret;
diff --git a/fs/libfs.c b/fs/libfs.c
index f99ecc300647..52196566ccbc 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -910,7 +910,7 @@ static int simple_read_folio(struct file *file, struct folio *folio)
 	return 0;
 }
 
-int simple_write_begin(struct file *file, struct address_space *mapping,
+int simple_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 			loff_t pos, unsigned len,
 			struct folio **foliop, void **fsdata)
 {
@@ -935,7 +935,7 @@ EXPORT_SYMBOL(simple_write_begin);
 
 /**
  * simple_write_end - .write_end helper for non-block-device FSes
- * @file: See .write_end of address_space_operations
+ * @iocb: kernel I/O control block
  * @mapping: 		"
  * @pos: 		"
  * @len: 		"
@@ -956,9 +956,10 @@ EXPORT_SYMBOL(simple_write_begin);
  *
  * Use *ONLY* with simple_read_folio()
  */
-static int simple_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int simple_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len, unsigned copied,
+			    struct folio *folio, void *fsdata)
 {
 	struct inode *inode = folio->mapping->host;
 	loff_t last_pos = pos + copied;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index f007e389d5d2..df9d11479caf 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -442,9 +442,10 @@ static void minix_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int minix_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int minix_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
+			     loff_t pos, unsigned len,
+			     struct folio **foliop, void **fsdata)
 {
 	int ret;
 
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 033feeab8c34..2bd557ca1af9 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -342,12 +342,14 @@ static bool nfs_want_read_modify_write(struct file *file, struct folio *folio,
  * If the writer ends up delaying the write, the writer needs to
  * increment the page use counts until he is done with the page.
  */
-static int nfs_write_begin(struct file *file, struct address_space *mapping,
+static int nfs_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len, struct folio **foliop,
 			   void **fsdata)
 {
 	fgf_t fgp = FGP_WRITEBEGIN;
 	struct folio *folio;
+	struct file *file = iocb->ki_filp;
 	int once_thru = 0;
 	int ret;
 
@@ -377,10 +379,12 @@ start:
 	return ret;
 }
 
-static int nfs_write_end(struct file *file, struct address_space *mapping,
+static int nfs_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
 			 loff_t pos, unsigned len, unsigned copied,
 			 struct folio *folio, void *fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct nfs_open_context *ctx = nfs_file_open_context(file);
 	unsigned offset = offset_in_folio(folio, pos);
 	int status;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index 6613b8fcceb0..c2ccafdf4a19 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -218,7 +218,8 @@ void nilfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int nilfs_write_begin(struct file *file, struct address_space *mapping,
+static int nilfs_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len,
 			     struct folio **foliop, void **fsdata)
 
@@ -237,7 +238,8 @@ static int nilfs_write_begin(struct file *file, struct address_space *mapping,
 	return err;
 }
 
-static int nilfs_write_end(struct file *file, struct address_space *mapping,
+static int nilfs_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct folio *folio, void *fsdata)
 {
@@ -248,7 +250,7 @@ static int nilfs_write_end(struct file *file, struct address_space *mapping,
 
 	nr_dirty = nilfs_page_count_clean_buffers(folio, start,
 						  start + copied);
-	copied = generic_write_end(file, mapping, pos, len, copied, folio,
+	copied = generic_write_end(iocb, mapping, pos, len, copied, folio,
 				   fsdata);
 	nilfs_set_file_dirty(inode, nr_dirty);
 	err = nilfs_transaction_commit(inode->i_sb);
diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
index 1e99a35691cd..1590c2a3c48f 100644
--- a/fs/ntfs3/file.c
+++ b/fs/ntfs3/file.c
@@ -154,13 +154,13 @@ static int ntfs_extend_initialized_size(struct file *file,
 		if (pos + len > new_valid)
 			len = new_valid - pos;
 
-		err = ntfs_write_begin(file, mapping, pos, len, &folio, NULL);
+		err = ntfs_write_begin(NULL, mapping, pos, len, &folio, NULL);
 		if (err)
 			goto out;
 
 		folio_zero_range(folio, zerofrom, folio_size(folio) - zerofrom);
 
-		err = ntfs_write_end(file, mapping, pos, len, len, folio, NULL);
+		err = ntfs_write_end(NULL, mapping, pos, len, len, folio, NULL);
 		if (err < 0)
 			goto out;
 		pos += len;
diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
index 0f0d27d4644a..dad088e64b3c 100644
--- a/fs/ntfs3/inode.c
+++ b/fs/ntfs3/inode.c
@@ -912,7 +912,7 @@ static int ntfs_get_block_write_begin(struct inode *inode, sector_t vbn,
 				  bh_result, create, GET_BLOCK_WRITE_BEGIN);
 }
 
-int ntfs_write_begin(struct file *file, struct address_space *mapping,
+int ntfs_write_begin(const struct kiocb *iocb, struct address_space *mapping,
 		     loff_t pos, u32 len, struct folio **foliop, void **fsdata)
 {
 	int err;
@@ -957,7 +957,8 @@ out:
 /*
  * ntfs_write_end - Address_space_operations::write_end.
  */
-int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
+int ntfs_write_end(const struct kiocb *iocb,
+		   struct address_space *mapping, loff_t pos,
 		   u32 len, u32 copied, struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
@@ -989,7 +990,7 @@ int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
 		folio_unlock(folio);
 		folio_put(folio);
 	} else {
-		err = generic_write_end(file, mapping, pos, len, copied, folio,
+		err = generic_write_end(iocb, mapping, pos, len, copied, folio,
 					fsdata);
 	}
 
diff --git a/fs/ntfs3/ntfs_fs.h b/fs/ntfs3/ntfs_fs.h
index 36b8052660d5..921257773eec 100644
--- a/fs/ntfs3/ntfs_fs.h
+++ b/fs/ntfs3/ntfs_fs.h
@@ -702,10 +702,12 @@ struct inode *ntfs_iget5(struct super_block *sb, const struct MFT_REF *ref,
 int ntfs_set_size(struct inode *inode, u64 new_size);
 int ntfs_get_block(struct inode *inode, sector_t vbn,
 		   struct buffer_head *bh_result, int create);
-int ntfs_write_begin(struct file *file, struct address_space *mapping,
-		     loff_t pos, u32 len, struct folio **foliop, void **fsdata);
-int ntfs_write_end(struct file *file, struct address_space *mapping, loff_t pos,
-		   u32 len, u32 copied, struct folio *folio, void *fsdata);
+int ntfs_write_begin(const struct kiocb *iocb, struct address_space *mapping,
+		     loff_t pos, u32 len, struct folio **foliop,
+		     void **fsdata);
+int ntfs_write_end(const struct kiocb *iocb, struct address_space *mapping,
+		   loff_t pos, u32 len, u32 copied, struct folio *folio,
+		   void *fsdata);
 int ntfs3_write_inode(struct inode *inode, struct writeback_control *wbc);
 int ntfs_sync_inode(struct inode *inode);
 int inode_read_data(struct inode *inode, void *data, size_t bytes);
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 40b6bce12951..2203438738f6 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1856,7 +1856,8 @@ out:
 	return ret;
 }
 
-static int ocfs2_write_begin(struct file *file, struct address_space *mapping,
+static int ocfs2_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len,
 			     struct folio **foliop, void **fsdata)
 {
@@ -2047,7 +2048,8 @@ out:
 	return copied;
 }
 
-static int ocfs2_write_end(struct file *file, struct address_space *mapping,
+static int ocfs2_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len, unsigned copied,
 			   struct folio *folio, void *fsdata)
 {
diff --git a/fs/omfs/file.c b/fs/omfs/file.c
index 98358d405b6a..8d70f816b0c9 100644
--- a/fs/omfs/file.c
+++ b/fs/omfs/file.c
@@ -310,9 +310,10 @@ static void omfs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int omfs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int omfs_write_begin(const struct kiocb *iocb,
+			    struct address_space *mapping,
+			    loff_t pos, unsigned len,
+			    struct folio **foliop, void **fsdata)
 {
 	int ret;
 
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 08a6f372a352..a7ab63776735 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -285,9 +285,10 @@ static int orangefs_read_folio(struct file *file, struct folio *folio)
 	return ret;
 }
 
-static int orangefs_write_begin(struct file *file,
-		struct address_space *mapping, loff_t pos, unsigned len,
-		struct folio **foliop, void **fsdata)
+static int orangefs_write_begin(const struct kiocb *iocb,
+				struct address_space *mapping, loff_t pos,
+				unsigned len, struct folio **foliop,
+				void **fsdata)
 {
 	struct orangefs_write_range *wr;
 	struct folio *folio;
@@ -340,9 +341,10 @@ okay:
 	return 0;
 }
 
-static int orangefs_write_end(struct file *file, struct address_space *mapping,
-		loff_t pos, unsigned len, unsigned copied, struct folio *folio,
-		void *fsdata)
+static int orangefs_write_end(const struct kiocb *iocb,
+			      struct address_space *mapping,
+			      loff_t pos, unsigned len, unsigned copied,
+			      struct folio *folio, void *fsdata)
 {
 	struct inode *inode = folio->mapping->host;
 	loff_t last_pos = pos + copied;
@@ -372,7 +374,7 @@ static int orangefs_write_end(struct file *file, struct address_space *mapping,
 	folio_unlock(folio);
 	folio_put(folio);
 
-	mark_inode_dirty_sync(file_inode(file));
+	mark_inode_dirty_sync(file_inode(iocb->ki_filp));
 	return copied;
 }
 
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index bf311c38d9a8..cee8bec1ea26 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -404,7 +404,8 @@ static int allocate_budget(struct ubifs_info *c, struct folio *folio,
  * there is a plenty of flash space and the budget will be acquired quickly,
  * without forcing write-back. The slow path does not make this assumption.
  */
-static int ubifs_write_begin(struct file *file, struct address_space *mapping,
+static int ubifs_write_begin(const struct kiocb *iocb,
+			     struct address_space *mapping,
 			     loff_t pos, unsigned len,
 			     struct folio **foliop, void **fsdata)
 {
@@ -514,8 +515,9 @@ static void cancel_budget(struct ubifs_info *c, struct folio *folio,
 	}
 }
 
-static int ubifs_write_end(struct file *file, struct address_space *mapping,
-			   loff_t pos, unsigned len, unsigned copied,
+static int ubifs_write_end(const struct kiocb *iocb,
+			   struct address_space *mapping, loff_t pos,
+			   unsigned len, unsigned copied,
 			   struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 4386dd845e40..356b75676fa9 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -244,10 +244,12 @@ static void udf_readahead(struct readahead_control *rac)
 	mpage_readahead(rac, udf_get_block);
 }
 
-static int udf_write_begin(struct file *file, struct address_space *mapping,
+static int udf_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
 			   loff_t pos, unsigned len,
 			   struct folio **foliop, void **fsdata)
 {
+	struct file *file = iocb->ki_filp;
 	struct udf_inode_info *iinfo = UDF_I(file_inode(file));
 	struct folio *folio;
 	int ret;
@@ -271,15 +273,16 @@ static int udf_write_begin(struct file *file, struct address_space *mapping,
 	return 0;
 }
 
-static int udf_write_end(struct file *file, struct address_space *mapping,
+static int udf_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
 			 loff_t pos, unsigned len, unsigned copied,
 			 struct folio *folio, void *fsdata)
 {
-	struct inode *inode = file_inode(file);
+	struct inode *inode = file_inode(iocb->ki_filp);
 	loff_t last_pos;
 
 	if (UDF_I(inode)->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB)
-		return generic_write_end(file, mapping, pos, len, copied, folio,
+		return generic_write_end(iocb, mapping, pos, len, copied, folio,
 					 fsdata);
 	last_pos = pos + copied;
 	if (last_pos > inode->i_size)
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 7dc38fdef2ea..8361c00e8fa6 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -474,9 +474,10 @@ static void ufs_write_failed(struct address_space *mapping, loff_t to)
 	}
 }
 
-static int ufs_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+static int ufs_write_begin(const struct kiocb *iocb,
+			   struct address_space *mapping,
+			   loff_t pos, unsigned len,
+			   struct folio **foliop, void **fsdata)
 {
 	int ret;
 
@@ -487,13 +488,14 @@ static int ufs_write_begin(struct file *file, struct address_space *mapping,
 	return ret;
 }
 
-static int ufs_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+static int ufs_write_end(const struct kiocb *iocb,
+			 struct address_space *mapping,
+			 loff_t pos, unsigned len, unsigned copied,
+			 struct folio *folio, void *fsdata)
 {
 	int ret;
 
-	ret = generic_write_end(file, mapping, pos, len, copied, folio, fsdata);
+	ret = generic_write_end(iocb, mapping, pos, len, copied, folio, fsdata);
 	if (ret < len)
 		ufs_write_failed(mapping, pos + len);
 	return ret;
diff --git a/fs/vboxsf/file.c b/fs/vboxsf/file.c
index b492794f8e9a..af01e3beaa42 100644
--- a/fs/vboxsf/file.c
+++ b/fs/vboxsf/file.c
@@ -300,12 +300,13 @@ static int vboxsf_writepages(struct address_space *mapping,
 	return error;
 }
 
-static int vboxsf_write_end(struct file *file, struct address_space *mapping,
+static int vboxsf_write_end(const struct kiocb *iocb,
+			    struct address_space *mapping,
 			    loff_t pos, unsigned int len, unsigned int copied,
 			    struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
-	struct vboxsf_handle *sf_handle = file->private_data;
+	struct vboxsf_handle *sf_handle = iocb->ki_filp->private_data;
 	size_t from = offset_in_folio(folio, pos);
 	u32 nwritten = len;
 	u8 *buf;
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 178eb90e9cf3..b16b88bfbc3e 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -263,11 +263,11 @@ int block_write_begin(struct address_space *mapping, loff_t pos, unsigned len,
 int __block_write_begin(struct folio *folio, loff_t pos, unsigned len,
 		get_block_t *get_block);
 int block_write_end(loff_t pos, unsigned len, unsigned copied, struct folio *);
-int generic_write_end(struct file *, struct address_space *,
+int generic_write_end(const struct kiocb *, struct address_space *,
 				loff_t, unsigned len, unsigned copied,
 				struct folio *, void *);
 void folio_zero_new_buffers(struct folio *folio, size_t from, size_t to);
-int cont_write_begin(struct file *, struct address_space *, loff_t,
+int cont_write_begin(const struct kiocb *, struct address_space *, loff_t,
 			unsigned, struct folio **, void **,
 			get_block_t *, loff_t *);
 int generic_cont_expand_simple(struct inode *inode, loff_t size);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 09e3e80b0528..df8c503100c4 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -444,10 +444,10 @@ struct address_space_operations {
 
 	void (*readahead)(struct readahead_control *);
 
-	int (*write_begin)(struct file *, struct address_space *mapping,
+	int (*write_begin)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len,
 				struct folio **foliop, void **fsdata);
-	int (*write_end)(struct file *, struct address_space *mapping,
+	int (*write_end)(const struct kiocb *, struct address_space *mapping,
 				loff_t pos, unsigned len, unsigned copied,
 				struct folio *folio, void *fsdata);
 
@@ -3598,9 +3598,10 @@ extern void simple_recursive_removal(struct dentry *,
 extern int noop_fsync(struct file *, loff_t, loff_t, int);
 extern ssize_t noop_direct_IO(struct kiocb *iocb, struct iov_iter *iter);
 extern int simple_empty(struct dentry *);
-extern int simple_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata);
+extern int simple_write_begin(const struct kiocb *iocb,
+			      struct address_space *mapping,
+			      loff_t pos, unsigned len,
+			      struct folio **foliop, void **fsdata);
 extern const struct address_space_operations ram_aops;
 extern int always_delete_dentry(const struct dentry *);
 extern struct inode *alloc_anon_inode(struct super_block *);
diff --git a/mm/filemap.c b/mm/filemap.c
index bada249b9fb7..ba089d75fc86 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -4109,7 +4109,7 @@ retry:
 			break;
 		}
 
-		status = a_ops->write_begin(file, mapping, pos, bytes,
+		status = a_ops->write_begin(iocb, mapping, pos, bytes,
 						&folio, &fsdata);
 		if (unlikely(status < 0))
 			break;
@@ -4130,7 +4130,7 @@ retry:
 		copied = copy_folio_from_iter_atomic(folio, offset, bytes, i);
 		flush_dcache_folio(folio);
 
-		status = a_ops->write_end(file, mapping, pos, bytes, copied,
+		status = a_ops->write_end(iocb, mapping, pos, bytes, copied,
 						folio, fsdata);
 		if (unlikely(status != copied)) {
 			iov_iter_revert(i, copied - max(status, 0L));
diff --git a/mm/shmem.c b/mm/shmem.c
index 0c5fb4ffa03a..2229425e1b29 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3266,9 +3266,9 @@ static const struct inode_operations shmem_symlink_inode_operations;
 static const struct inode_operations shmem_short_symlink_operations;
 
 static int
-shmem_write_begin(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len,
-			struct folio **foliop, void **fsdata)
+shmem_write_begin(const struct kiocb *iocb, struct address_space *mapping,
+		  loff_t pos, unsigned len,
+		  struct folio **foliop, void **fsdata)
 {
 	struct inode *inode = mapping->host;
 	struct shmem_inode_info *info = SHMEM_I(inode);
@@ -3300,9 +3300,9 @@ shmem_write_begin(struct file *file, struct address_space *mapping,
 }
 
 static int
-shmem_write_end(struct file *file, struct address_space *mapping,
-			loff_t pos, unsigned len, unsigned copied,
-			struct folio *folio, void *fsdata)
+shmem_write_end(const struct kiocb *iocb, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned copied,
+		struct folio *folio, void *fsdata)
 {
 	struct inode *inode = mapping->host;
 
-- 
cgit v1.2.3


From b799474b9aeb46ec698874d4de1a799de8b5f64f Mon Sep 17 00:00:00 2001
From: Taotao Chen <chentaotao@didiglobal.com>
Date: Wed, 16 Jul 2025 09:36:08 +0000
Subject: mm/pagemap: add write_begin_get_folio() helper function

Add write_begin_get_folio() to simplify the common folio lookup logic
used by filesystem ->write_begin() implementations.

This helper wraps __filemap_get_folio() with common flags such as
FGP_WRITEBEGIN, conditional FGP_DONTCACHE, and set folio order based
on the write length.

Part of a series refactoring address_space_operations write_begin and
write_end callbacks to use struct kiocb for passing write context and
flags.

Signed-off-by: Taotao Chen <chentaotao@didiglobal.com>
Link: https://lore.kernel.org/20250716093559.217344-5-chentaotao@didiglobal.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/pagemap.h | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index e63fbfbd5b0f..ce2bcdcadb73 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -750,6 +750,33 @@ struct folio *__filemap_get_folio(struct address_space *mapping, pgoff_t index,
 struct page *pagecache_get_page(struct address_space *mapping, pgoff_t index,
 		fgf_t fgp_flags, gfp_t gfp);
 
+/**
+ * write_begin_get_folio - Get folio for write_begin with flags.
+ * @iocb: The kiocb passed from write_begin (may be NULL).
+ * @mapping: The address space to search.
+ * @index: The page cache index.
+ * @len: Length of data being written.
+ *
+ * This is a helper for filesystem write_begin() implementations.
+ * It wraps __filemap_get_folio(), setting appropriate flags in
+ * the write begin context.
+ *
+ * Return: A folio or an ERR_PTR.
+ */
+static inline struct folio *write_begin_get_folio(const struct kiocb *iocb,
+		  struct address_space *mapping, pgoff_t index, size_t len)
+{
+        fgf_t fgp_flags = FGP_WRITEBEGIN;
+
+        fgp_flags |= fgf_set_order(len);
+
+        if (iocb && iocb->ki_flags & IOCB_DONTCACHE)
+                fgp_flags |= FGP_DONTCACHE;
+
+        return __filemap_get_folio(mapping, index, fgp_flags,
+                                   mapping_gfp_mask(mapping));
+}
+
 /**
  * filemap_get_folio - Find and get a folio.
  * @mapping: The address_space to search.
-- 
cgit v1.2.3


From 857d18f23ab17284d1b6de6f61f4e74958596376 Mon Sep 17 00:00:00 2001
From: Peter Zijlstra <peterz@infradead.org>
Date: Fri, 11 Jul 2025 16:49:25 -0700
Subject: cleanup: Introduce ACQUIRE() and ACQUIRE_ERR() for conditional locks

scoped_cond_guard(), automatic cleanup for conditional locks, has a couple
pain points:

* It causes existing straight-line code to be re-indented into a new
  bracketed scope. While this can be mitigated by a new helper function
  to contain the scope, that is not always a comfortable conversion.

* The return code from the conditional lock is tossed in favor of a scheme
  to pass a 'return err;' statement to the macro.

Other attempts to clean this up, to behave more like guard() [1], got hung
up trying to both establish and evaluate the conditional lock in one
statement.

ACQUIRE() solves this by reflecting the result of the condition in the
automatic variable established by the lock CLASS(). The result is
separately retrieved with the ACQUIRE_ERR() helper, effectively a PTR_ERR()
operation.

Link: http://lore.kernel.org/all/Z1LBnX9TpZLR5Dkf@gmail.com [1]
Link: http://patch.msgid.link/20250512105026.GP4439@noisy.programming.kicks-ass.net
Link: http://patch.msgid.link/20250512185817.GA1808@noisy.programming.kicks-ass.net
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: David Lechner <dlechner@baylibre.com>
Cc: Fabio M. De Francesco <fabio.m.de.francesco@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
[djbw: wrap Peter's proposal with changelog and comments]
Co-developed-by: Dan Williams <dan.j.williams@intel.com>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Link: https://patch.msgid.link/20250711234932.671292-2-dan.j.williams@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 include/linux/cleanup.h | 95 +++++++++++++++++++++++++++++++++++++++++--------
 include/linux/mutex.h   |  2 +-
 include/linux/rwsem.h   |  2 +-
 3 files changed, 83 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 7093e1d08af0..4eb83dd71cfe 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -3,6 +3,8 @@
 #define _LINUX_CLEANUP_H
 
 #include <linux/compiler.h>
+#include <linux/err.h>
+#include <linux/args.h>
 
 /**
  * DOC: scope-based cleanup helpers
@@ -61,9 +63,21 @@
  * Observe the lock is held for the remainder of the "if ()" block not
  * the remainder of "func()".
  *
- * Now, when a function uses both __free() and guard(), or multiple
- * instances of __free(), the LIFO order of variable definition order
- * matters. GCC documentation says:
+ * The ACQUIRE() macro can be used in all places that guard() can be
+ * used and additionally support conditional locks
+ *
+ *
+ *	DEFINE_GUARD_COND(pci_dev, _try, pci_dev_trylock(_T))
+ *	...
+ *	ACQUIRE(pci_dev_try, lock)(dev);
+ *	rc = ACQUIRE_ERR(pci_dev_try, &lock);
+ *	if (rc)
+ *		return rc;
+ *	// @lock is held
+ *
+ * Now, when a function uses both __free() and guard()/ACQUIRE(), or
+ * multiple instances of __free(), the LIFO order of variable definition
+ * order matters. GCC documentation says:
  *
  * "When multiple variables in the same scope have cleanup attributes,
  * at exit from the scope their associated cleanup functions are run in
@@ -305,14 +319,46 @@ static inline class_##_name##_t class_##_name##ext##_constructor(_init_args) \
  *      acquire fails.
  *
  *      Only for conditional locks.
+ *
+ * ACQUIRE(name, var):
+ *	a named instance of the (guard) class, suitable for conditional
+ *	locks when paired with ACQUIRE_ERR().
+ *
+ * ACQUIRE_ERR(name, &var):
+ *	a helper that is effectively a PTR_ERR() conversion of the guard
+ *	pointer. Returns 0 when the lock was acquired and a negative
+ *	error code otherwise.
  */
 
 #define __DEFINE_CLASS_IS_CONDITIONAL(_name, _is_cond)	\
 static __maybe_unused const bool class_##_name##_is_conditional = _is_cond
 
-#define __DEFINE_GUARD_LOCK_PTR(_name, _exp) \
-	static inline void * class_##_name##_lock_ptr(class_##_name##_t *_T) \
-	{ return (void *)(__force unsigned long)*(_exp); }
+#define __GUARD_IS_ERR(_ptr)                                       \
+	({                                                         \
+		unsigned long _rc = (__force unsigned long)(_ptr); \
+		unlikely((_rc - 1) >= -MAX_ERRNO - 1);             \
+	})
+
+#define __DEFINE_GUARD_LOCK_PTR(_name, _exp)                                \
+	static inline void *class_##_name##_lock_ptr(class_##_name##_t *_T) \
+	{                                                                   \
+		void *_ptr = (void *)(__force unsigned long)*(_exp);        \
+		if (IS_ERR(_ptr)) {                                         \
+			_ptr = NULL;                                        \
+		}                                                           \
+		return _ptr;                                                \
+	}                                                                   \
+	static inline int class_##_name##_lock_err(class_##_name##_t *_T)   \
+	{                                                                   \
+		long _rc = (__force unsigned long)*(_exp);                  \
+		if (!_rc) {                                                 \
+			_rc = -EBUSY;                                       \
+		}                                                           \
+		if (!IS_ERR_VALUE(_rc)) {                                   \
+			_rc = 0;                                            \
+		}                                                           \
+		return _rc;                                                 \
+	}
 
 #define DEFINE_CLASS_IS_GUARD(_name) \
 	__DEFINE_CLASS_IS_CONDITIONAL(_name, false); \
@@ -323,23 +369,37 @@ static __maybe_unused const bool class_##_name##_is_conditional = _is_cond
 	__DEFINE_GUARD_LOCK_PTR(_name, _T)
 
 #define DEFINE_GUARD(_name, _type, _lock, _unlock) \
-	DEFINE_CLASS(_name, _type, if (_T) { _unlock; }, ({ _lock; _T; }), _type _T); \
+	DEFINE_CLASS(_name, _type, if (!__GUARD_IS_ERR(_T)) { _unlock; }, ({ _lock; _T; }), _type _T); \
 	DEFINE_CLASS_IS_GUARD(_name)
 
-#define DEFINE_GUARD_COND(_name, _ext, _condlock) \
+#define DEFINE_GUARD_COND_4(_name, _ext, _lock, _cond) \
 	__DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true); \
 	EXTEND_CLASS(_name, _ext, \
-		     ({ void *_t = _T; if (_T && !(_condlock)) _t = NULL; _t; }), \
+		     ({ void *_t = _T; int _RET = (_lock); if (_T && !(_cond)) _t = ERR_PTR(_RET); _t; }), \
 		     class_##_name##_t _T) \
 	static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
-	{ return class_##_name##_lock_ptr(_T); }
+	{ return class_##_name##_lock_ptr(_T); } \
+	static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_err(_T); }
+
+/*
+ * Default binary condition; success on 'true'.
+ */
+#define DEFINE_GUARD_COND_3(_name, _ext, _lock) \
+	DEFINE_GUARD_COND_4(_name, _ext, _lock, _RET)
+
+#define DEFINE_GUARD_COND(X...) CONCATENATE(DEFINE_GUARD_COND_, COUNT_ARGS(X))(X)
 
 #define guard(_name) \
 	CLASS(_name, __UNIQUE_ID(guard))
 
 #define __guard_ptr(_name) class_##_name##_lock_ptr
+#define __guard_err(_name) class_##_name##_lock_err
 #define __is_cond_ptr(_name) class_##_name##_is_conditional
 
+#define ACQUIRE(_name, _var)     CLASS(_name, _var)
+#define ACQUIRE_ERR(_name, _var) __guard_err(_name)(_var)
+
 /*
  * Helper macro for scoped_guard().
  *
@@ -401,7 +461,7 @@ typedef struct {							\
 									\
 static inline void class_##_name##_destructor(class_##_name##_t *_T)	\
 {									\
-	if (_T->lock) { _unlock; }					\
+	if (!__GUARD_IS_ERR(_T->lock)) { _unlock; }			\
 }									\
 									\
 __DEFINE_GUARD_LOCK_PTR(_name, &_T->lock)
@@ -433,15 +493,22 @@ __DEFINE_CLASS_IS_CONDITIONAL(_name, false);				\
 __DEFINE_UNLOCK_GUARD(_name, void, _unlock, __VA_ARGS__)		\
 __DEFINE_LOCK_GUARD_0(_name, _lock)
 
-#define DEFINE_LOCK_GUARD_1_COND(_name, _ext, _condlock)		\
+#define DEFINE_LOCK_GUARD_1_COND_4(_name, _ext, _lock, _cond)		\
 	__DEFINE_CLASS_IS_CONDITIONAL(_name##_ext, true);		\
 	EXTEND_CLASS(_name, _ext,					\
 		     ({ class_##_name##_t _t = { .lock = l }, *_T = &_t;\
-		        if (_T->lock && !(_condlock)) _T->lock = NULL;	\
+		        int _RET = (_lock);                             \
+		        if (_T->lock && !(_cond)) _T->lock = ERR_PTR(_RET);\
 			_t; }),						\
 		     typeof_member(class_##_name##_t, lock) l)		\
 	static inline void * class_##_name##_ext##_lock_ptr(class_##_name##_t *_T) \
-	{ return class_##_name##_lock_ptr(_T); }
+	{ return class_##_name##_lock_ptr(_T); } \
+	static inline int class_##_name##_ext##_lock_err(class_##_name##_t *_T) \
+	{ return class_##_name##_lock_err(_T); }
+
+#define DEFINE_LOCK_GUARD_1_COND_3(_name, _ext, _lock) \
+	DEFINE_LOCK_GUARD_1_COND_4(_name, _ext, _lock, _RET)
 
+#define DEFINE_LOCK_GUARD_1_COND(X...) CONCATENATE(DEFINE_LOCK_GUARD_1_COND_, COUNT_ARGS(X))(X)
 
 #endif /* _LINUX_CLEANUP_H */
diff --git a/include/linux/mutex.h b/include/linux/mutex.h
index a039fa8c1780..9d5d7ed5c101 100644
--- a/include/linux/mutex.h
+++ b/include/linux/mutex.h
@@ -224,7 +224,7 @@ extern int atomic_dec_and_mutex_lock(atomic_t *cnt, struct mutex *lock);
 
 DEFINE_GUARD(mutex, struct mutex *, mutex_lock(_T), mutex_unlock(_T))
 DEFINE_GUARD_COND(mutex, _try, mutex_trylock(_T))
-DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T) == 0)
+DEFINE_GUARD_COND(mutex, _intr, mutex_lock_interruptible(_T), _RET == 0)
 
 extern unsigned long mutex_get_owner(struct mutex *lock);
 
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index c8b543d428b0..c810deb88d13 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -240,7 +240,7 @@ extern void up_write(struct rw_semaphore *sem);
 
 DEFINE_GUARD(rwsem_read, struct rw_semaphore *, down_read(_T), up_read(_T))
 DEFINE_GUARD_COND(rwsem_read, _try, down_read_trylock(_T))
-DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T) == 0)
+DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T), _RET == 0)
 
 DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
 DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T))
-- 
cgit v1.2.3


From d03fcf50ba56f4479685b951506422eeca230853 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Fri, 11 Jul 2025 16:49:32 -0700
Subject: cxl: Convert to ACQUIRE() for conditional rwsem locking

Use ACQUIRE() to cleanup conditional locking paths in the CXL driver
The ACQUIRE() macro and its associated ACQUIRE_ERR() helpers, like
scoped_cond_guard(), arrange for scoped-based conditional locking. Unlike
scoped_cond_guard(), these macros arrange for an ERR_PTR() to be retrieved
representing the state of the conditional lock.

The goal of this conversion is to complete the removal of all explicit
unlock calls in the subsystem. I.e. the methods to acquire a lock are
solely via guard(), scoped_guard() (for limited cases), or ACQUIRE(). All
unlock is implicit / scope-based. In order to make sure all lock sites are
converted, the existing rwsem's are consolidated and renamed in 'struct
cxl_rwsem'. While that makes the patch noisier it gives a clean cut-off
between old-world (explicit unlock allowed), and new world (explicit unlock
deleted).

Cc: David Lechner <dlechner@baylibre.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Fabio M. De Francesco <fabio.m.de.francesco@linux.intel.com>
Cc: Davidlohr Bueso <dave@stgolabs.net>
Cc: Jonathan Cameron <jonathan.cameron@huawei.com>
Cc: Dave Jiang <dave.jiang@intel.com>
Cc: Alison Schofield <alison.schofield@intel.com>
Cc: Vishal Verma <vishal.l.verma@intel.com>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Shiju Jose <shiju.jose@huawei.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Reviewed-by: Jonathan Cameron <jonathan.cameron@huawei.com>
Reviewed-by: Fabio M. De Francesco <fabio.m.de.francesco@linux.intel.com>
Reviewed-by: Dave Jiang <dave.jiang@intel.com>
Tested-by: Shiju Jose <shiju.jose@huawei.com>
Link: https://patch.msgid.link/20250711234932.671292-9-dan.j.williams@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 drivers/cxl/core/cdat.c   |   6 +-
 drivers/cxl/core/core.h   |  17 ++-
 drivers/cxl/core/edac.c   |  44 ++++---
 drivers/cxl/core/hdm.c    |  41 +++----
 drivers/cxl/core/mbox.c   |   6 +-
 drivers/cxl/core/memdev.c |  50 +++-----
 drivers/cxl/core/port.c   |  18 +--
 drivers/cxl/core/region.c | 295 +++++++++++++++++++---------------------------
 drivers/cxl/cxl.h         |  13 +-
 include/linux/rwsem.h     |   1 +
 10 files changed, 212 insertions(+), 279 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/cxl/core/cdat.c b/drivers/cxl/core/cdat.c
index 0ccef2f2a26a..c0af645425f4 100644
--- a/drivers/cxl/core/cdat.c
+++ b/drivers/cxl/core/cdat.c
@@ -336,7 +336,7 @@ static int match_cxlrd_hb(struct device *dev, void *data)
 	cxlrd = to_cxl_root_decoder(dev);
 	cxlsd = &cxlrd->cxlsd;
 
-	guard(rwsem_read)(&cxl_region_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.region);
 	for (int i = 0; i < cxlsd->nr_targets; i++) {
 		if (host_bridge == cxlsd->target[i]->dport_dev)
 			return 1;
@@ -987,7 +987,7 @@ void cxl_region_shared_upstream_bandwidth_update(struct cxl_region *cxlr)
 	bool is_root;
 	int rc;
 
-	lockdep_assert_held(&cxl_dpa_rwsem);
+	lockdep_assert_held(&cxl_rwsem.dpa);
 
 	struct xarray *usp_xa __free(free_perf_xa) =
 		kzalloc(sizeof(*usp_xa), GFP_KERNEL);
@@ -1057,7 +1057,7 @@ void cxl_region_perf_data_calculate(struct cxl_region *cxlr,
 {
 	struct cxl_dpa_perf *perf;
 
-	lockdep_assert_held(&cxl_dpa_rwsem);
+	lockdep_assert_held(&cxl_rwsem.dpa);
 
 	perf = cxled_get_dpa_perf(cxled);
 	if (IS_ERR(perf))
diff --git a/drivers/cxl/core/core.h b/drivers/cxl/core/core.h
index 2be37084409f..f796731deedf 100644
--- a/drivers/cxl/core/core.h
+++ b/drivers/cxl/core/core.h
@@ -5,6 +5,7 @@
 #define __CXL_CORE_H__
 
 #include <cxl/mailbox.h>
+#include <linux/rwsem.h>
 
 extern const struct device_type cxl_nvdimm_bridge_type;
 extern const struct device_type cxl_nvdimm_type;
@@ -107,8 +108,20 @@ u16 cxl_rcrb_to_aer(struct device *dev, resource_size_t rcrb);
 #define PCI_RCRB_CAP_HDR_NEXT_MASK	GENMASK(15, 8)
 #define PCI_CAP_EXP_SIZEOF		0x3c
 
-extern struct rw_semaphore cxl_dpa_rwsem;
-extern struct rw_semaphore cxl_region_rwsem;
+struct cxl_rwsem {
+	/*
+	 * All changes to HPA (interleave configuration) occur with this
+	 * lock held for write.
+	 */
+	struct rw_semaphore region;
+	/*
+	 * All changes to a device DPA space occur with this lock held
+	 * for write.
+	 */
+	struct rw_semaphore dpa;
+};
+
+extern struct cxl_rwsem cxl_rwsem;
 
 int cxl_memdev_init(void);
 void cxl_memdev_exit(void);
diff --git a/drivers/cxl/core/edac.c b/drivers/cxl/core/edac.c
index 623aaa4439c4..9ed1b670efb8 100644
--- a/drivers/cxl/core/edac.c
+++ b/drivers/cxl/core/edac.c
@@ -115,10 +115,9 @@ static int cxl_scrub_get_attrbs(struct cxl_patrol_scrub_context *cxl_ps_ctx,
 						flags, min_cycle);
 	}
 
-	struct rw_semaphore *region_lock __free(rwsem_read_release) =
-		rwsem_read_intr_acquire(&cxl_region_rwsem);
-	if (!region_lock)
-		return -EINTR;
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((ret = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
+		return ret;
 
 	cxlr = cxl_ps_ctx->cxlr;
 	p = &cxlr->params;
@@ -158,10 +157,9 @@ static int cxl_scrub_set_attrbs_region(struct device *dev,
 	struct cxl_region *cxlr;
 	int ret, i;
 
-	struct rw_semaphore *region_lock __free(rwsem_read_release) =
-		rwsem_read_intr_acquire(&cxl_region_rwsem);
-	if (!region_lock)
-		return -EINTR;
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((ret = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
+		return ret;
 
 	cxlr = cxl_ps_ctx->cxlr;
 	p = &cxlr->params;
@@ -1340,16 +1338,15 @@ cxl_mem_perform_sparing(struct device *dev,
 	struct cxl_memdev_sparing_in_payload sparing_pi;
 	struct cxl_event_dram *rec = NULL;
 	u16 validity_flags = 0;
+	int ret;
 
-	struct rw_semaphore *region_lock __free(rwsem_read_release) =
-		rwsem_read_intr_acquire(&cxl_region_rwsem);
-	if (!region_lock)
-		return -EINTR;
+	ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region);
+	if ((ret = ACQUIRE_ERR(rwsem_read_intr, &region_rwsem)))
+		return ret;
 
-	struct rw_semaphore *dpa_lock __free(rwsem_read_release) =
-		rwsem_read_intr_acquire(&cxl_dpa_rwsem);
-	if (!dpa_lock)
-		return -EINTR;
+	ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa);
+	if ((ret = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem)))
+		return ret;
 
 	if (!cxl_sparing_ctx->cap_safe_when_in_use) {
 		/* Memory to repair must be offline */
@@ -1787,16 +1784,15 @@ static int cxl_mem_perform_ppr(struct cxl_ppr_context *cxl_ppr_ctx)
 	struct cxl_memdev_ppr_maintenance_attrbs maintenance_attrbs;
 	struct cxl_memdev *cxlmd = cxl_ppr_ctx->cxlmd;
 	struct cxl_mem_repair_attrbs attrbs = { 0 };
+	int ret;
 
-	struct rw_semaphore *region_lock __free(rwsem_read_release) =
-		rwsem_read_intr_acquire(&cxl_region_rwsem);
-	if (!region_lock)
-		return -EINTR;
+	ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region);
+	if ((ret = ACQUIRE_ERR(rwsem_read_intr, &region_rwsem)))
+		return ret;
 
-	struct rw_semaphore *dpa_lock __free(rwsem_read_release) =
-		rwsem_read_intr_acquire(&cxl_dpa_rwsem);
-	if (!dpa_lock)
-		return -EINTR;
+	ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa);
+	if ((ret = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem)))
+		return ret;
 
 	if (!cxl_ppr_ctx->media_accessible || !cxl_ppr_ctx->data_retained) {
 		/* Memory to repair must be offline */
diff --git a/drivers/cxl/core/hdm.c b/drivers/cxl/core/hdm.c
index e9cb34e30248..865a71bce251 100644
--- a/drivers/cxl/core/hdm.c
+++ b/drivers/cxl/core/hdm.c
@@ -16,7 +16,10 @@
  * for enumerating these registers and capabilities.
  */
 
-DECLARE_RWSEM(cxl_dpa_rwsem);
+struct cxl_rwsem cxl_rwsem = {
+	.region = __RWSEM_INITIALIZER(cxl_rwsem.region),
+	.dpa = __RWSEM_INITIALIZER(cxl_rwsem.dpa),
+};
 
 static int add_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 			   int *target_map)
@@ -214,7 +217,7 @@ void cxl_dpa_debug(struct seq_file *file, struct cxl_dev_state *cxlds)
 {
 	struct resource *p1, *p2;
 
-	guard(rwsem_read)(&cxl_dpa_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.dpa);
 	for (p1 = cxlds->dpa_res.child; p1; p1 = p1->sibling) {
 		__cxl_dpa_debug(file, p1, 0);
 		for (p2 = p1->child; p2; p2 = p2->sibling)
@@ -266,7 +269,7 @@ static void __cxl_dpa_release(struct cxl_endpoint_decoder *cxled)
 	struct resource *res = cxled->dpa_res;
 	resource_size_t skip_start;
 
-	lockdep_assert_held_write(&cxl_dpa_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.dpa);
 
 	/* save @skip_start, before @res is released */
 	skip_start = res->start - cxled->skip;
@@ -281,7 +284,7 @@ static void __cxl_dpa_release(struct cxl_endpoint_decoder *cxled)
 
 static void cxl_dpa_release(void *cxled)
 {
-	guard(rwsem_write)(&cxl_dpa_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.dpa);
 	__cxl_dpa_release(cxled);
 }
 
@@ -293,7 +296,7 @@ static void devm_cxl_dpa_release(struct cxl_endpoint_decoder *cxled)
 {
 	struct cxl_port *port = cxled_to_port(cxled);
 
-	lockdep_assert_held_write(&cxl_dpa_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.dpa);
 	devm_remove_action(&port->dev, cxl_dpa_release, cxled);
 	__cxl_dpa_release(cxled);
 }
@@ -361,7 +364,7 @@ static int __cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 	struct resource *res;
 	int rc;
 
-	lockdep_assert_held_write(&cxl_dpa_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.dpa);
 
 	if (!len) {
 		dev_warn(dev, "decoder%d.%d: empty reservation attempted\n",
@@ -470,7 +473,7 @@ int cxl_dpa_setup(struct cxl_dev_state *cxlds, const struct cxl_dpa_info *info)
 {
 	struct device *dev = cxlds->dev;
 
-	guard(rwsem_write)(&cxl_dpa_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.dpa);
 
 	if (cxlds->nr_partitions)
 		return -EBUSY;
@@ -516,9 +519,8 @@ int devm_cxl_dpa_reserve(struct cxl_endpoint_decoder *cxled,
 	struct cxl_port *port = cxled_to_port(cxled);
 	int rc;
 
-	down_write(&cxl_dpa_rwsem);
-	rc = __cxl_dpa_reserve(cxled, base, len, skipped);
-	up_write(&cxl_dpa_rwsem);
+	scoped_guard(rwsem_write, &cxl_rwsem.dpa)
+		rc = __cxl_dpa_reserve(cxled, base, len, skipped);
 
 	if (rc)
 		return rc;
@@ -529,7 +531,7 @@ EXPORT_SYMBOL_NS_GPL(devm_cxl_dpa_reserve, "CXL");
 
 resource_size_t cxl_dpa_size(struct cxl_endpoint_decoder *cxled)
 {
-	guard(rwsem_read)(&cxl_dpa_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.dpa);
 	if (cxled->dpa_res)
 		return resource_size(cxled->dpa_res);
 
@@ -540,7 +542,7 @@ resource_size_t cxl_dpa_resource_start(struct cxl_endpoint_decoder *cxled)
 {
 	resource_size_t base = -1;
 
-	lockdep_assert_held(&cxl_dpa_rwsem);
+	lockdep_assert_held(&cxl_rwsem.dpa);
 	if (cxled->dpa_res)
 		base = cxled->dpa_res->start;
 
@@ -552,7 +554,7 @@ int cxl_dpa_free(struct cxl_endpoint_decoder *cxled)
 	struct cxl_port *port = cxled_to_port(cxled);
 	struct device *dev = &cxled->cxld.dev;
 
-	guard(rwsem_write)(&cxl_dpa_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.dpa);
 	if (!cxled->dpa_res)
 		return 0;
 	if (cxled->cxld.region) {
@@ -582,7 +584,7 @@ int cxl_dpa_set_part(struct cxl_endpoint_decoder *cxled,
 	struct device *dev = &cxled->cxld.dev;
 	int part;
 
-	guard(rwsem_write)(&cxl_dpa_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.dpa);
 	if (cxled->cxld.flags & CXL_DECODER_F_ENABLE)
 		return -EBUSY;
 
@@ -614,7 +616,7 @@ static int __cxl_dpa_alloc(struct cxl_endpoint_decoder *cxled, u64 size)
 	struct resource *p, *last;
 	int part;
 
-	guard(rwsem_write)(&cxl_dpa_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.dpa);
 	if (cxled->cxld.region) {
 		dev_dbg(dev, "decoder attached to %s\n",
 			dev_name(&cxled->cxld.region->dev));
@@ -842,9 +844,8 @@ static int cxl_decoder_commit(struct cxl_decoder *cxld)
 		}
 	}
 
-	down_read(&cxl_dpa_rwsem);
-	setup_hw_decoder(cxld, hdm);
-	up_read(&cxl_dpa_rwsem);
+	scoped_guard(rwsem_read, &cxl_rwsem.dpa)
+		setup_hw_decoder(cxld, hdm);
 
 	port->commit_end++;
 	rc = cxld_await_commit(hdm, cxld->id);
@@ -882,7 +883,7 @@ void cxl_port_commit_reap(struct cxl_decoder *cxld)
 {
 	struct cxl_port *port = to_cxl_port(cxld->dev.parent);
 
-	lockdep_assert_held_write(&cxl_region_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.region);
 
 	/*
 	 * Once the highest committed decoder is disabled, free any other
@@ -1030,7 +1031,7 @@ static int init_hdm_decoder(struct cxl_port *port, struct cxl_decoder *cxld,
 		else
 			cxld->target_type = CXL_DECODER_DEVMEM;
 
-		guard(rwsem_write)(&cxl_region_rwsem);
+		guard(rwsem_write)(&cxl_rwsem.region);
 		if (cxld->id != cxl_num_decoders_committed(port)) {
 			dev_warn(&port->dev,
 				 "decoder%d.%d: Committed out of order\n",
diff --git a/drivers/cxl/core/mbox.c b/drivers/cxl/core/mbox.c
index 81b21effe8cf..92cd3cbdd8ec 100644
--- a/drivers/cxl/core/mbox.c
+++ b/drivers/cxl/core/mbox.c
@@ -909,8 +909,8 @@ void cxl_event_trace_record(const struct cxl_memdev *cxlmd,
 		 * translations. Take topology mutation locks and lookup
 		 * { HPA, REGION } from { DPA, MEMDEV } in the event record.
 		 */
-		guard(rwsem_read)(&cxl_region_rwsem);
-		guard(rwsem_read)(&cxl_dpa_rwsem);
+		guard(rwsem_read)(&cxl_rwsem.region);
+		guard(rwsem_read)(&cxl_rwsem.dpa);
 
 		dpa = le64_to_cpu(evt->media_hdr.phys_addr) & CXL_DPA_MASK;
 		cxlr = cxl_dpa_to_region(cxlmd, dpa);
@@ -1265,7 +1265,7 @@ int cxl_mem_sanitize(struct cxl_memdev *cxlmd, u16 cmd)
 	/* synchronize with cxl_mem_probe() and decoder write operations */
 	guard(device)(&cxlmd->dev);
 	endpoint = cxlmd->endpoint;
-	guard(rwsem_read)(&cxl_region_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.region);
 	/*
 	 * Require an endpoint to be safe otherwise the driver can not
 	 * be sure that the device is unmapped.
diff --git a/drivers/cxl/core/memdev.c b/drivers/cxl/core/memdev.c
index f88a13adf7fa..f5fbd34310fd 100644
--- a/drivers/cxl/core/memdev.c
+++ b/drivers/cxl/core/memdev.c
@@ -232,15 +232,13 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 	if (!port || !is_cxl_endpoint(port))
 		return -EINVAL;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &region_rwsem)))
 		return rc;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
-	if (rc) {
-		up_read(&cxl_region_rwsem);
+	ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem)))
 		return rc;
-	}
 
 	if (cxl_num_decoders_committed(port) == 0) {
 		/* No regions mapped to this memdev */
@@ -249,8 +247,6 @@ int cxl_trigger_poison_list(struct cxl_memdev *cxlmd)
 		/* Regions mapped, collect poison by endpoint */
 		rc =  cxl_get_poison_by_endpoint(port);
 	}
-	up_read(&cxl_dpa_rwsem);
-	up_read(&cxl_region_rwsem);
 
 	return rc;
 }
@@ -292,19 +288,17 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &region_rwsem)))
 		return rc;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
-	if (rc) {
-		up_read(&cxl_region_rwsem);
+	ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem)))
 		return rc;
-	}
 
 	rc = cxl_validate_poison_dpa(cxlmd, dpa);
 	if (rc)
-		goto out;
+		return rc;
 
 	inject.address = cpu_to_le64(dpa);
 	mbox_cmd = (struct cxl_mbox_cmd) {
@@ -314,7 +308,7 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	};
 	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc)
-		goto out;
+		return rc;
 
 	cxlr = cxl_dpa_to_region(cxlmd, dpa);
 	if (cxlr)
@@ -327,11 +321,8 @@ int cxl_inject_poison(struct cxl_memdev *cxlmd, u64 dpa)
 		.length = cpu_to_le32(1),
 	};
 	trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_INJECT);
-out:
-	up_read(&cxl_dpa_rwsem);
-	up_read(&cxl_region_rwsem);
 
-	return rc;
+	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_inject_poison, "CXL");
 
@@ -347,19 +338,17 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 	if (!IS_ENABLED(CONFIG_DEBUG_FS))
 		return 0;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &region_rwsem)))
 		return rc;
 
-	rc = down_read_interruptible(&cxl_dpa_rwsem);
-	if (rc) {
-		up_read(&cxl_region_rwsem);
+	ACQUIRE(rwsem_read_intr, dpa_rwsem)(&cxl_rwsem.dpa);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &dpa_rwsem)))
 		return rc;
-	}
 
 	rc = cxl_validate_poison_dpa(cxlmd, dpa);
 	if (rc)
-		goto out;
+		return rc;
 
 	/*
 	 * In CXL 3.0 Spec 8.2.9.8.4.3, the Clear Poison mailbox command
@@ -378,7 +367,7 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 
 	rc = cxl_internal_send_cmd(cxl_mbox, &mbox_cmd);
 	if (rc)
-		goto out;
+		return rc;
 
 	cxlr = cxl_dpa_to_region(cxlmd, dpa);
 	if (cxlr)
@@ -391,11 +380,8 @@ int cxl_clear_poison(struct cxl_memdev *cxlmd, u64 dpa)
 		.length = cpu_to_le32(1),
 	};
 	trace_cxl_poison(cxlmd, cxlr, &record, 0, 0, CXL_POISON_TRACE_CLEAR);
-out:
-	up_read(&cxl_dpa_rwsem);
-	up_read(&cxl_region_rwsem);
 
-	return rc;
+	return 0;
 }
 EXPORT_SYMBOL_NS_GPL(cxl_clear_poison, "CXL");
 
diff --git a/drivers/cxl/core/port.c b/drivers/cxl/core/port.c
index 087a20a9ee1c..bacf1380dc4d 100644
--- a/drivers/cxl/core/port.c
+++ b/drivers/cxl/core/port.c
@@ -30,18 +30,12 @@
  * instantiated by the core.
  */
 
-/*
- * All changes to the interleave configuration occur with this lock held
- * for write.
- */
-DECLARE_RWSEM(cxl_region_rwsem);
-
 static DEFINE_IDA(cxl_port_ida);
 static DEFINE_XARRAY(cxl_root_buses);
 
 int cxl_num_decoders_committed(struct cxl_port *port)
 {
-	lockdep_assert_held(&cxl_region_rwsem);
+	lockdep_assert_held(&cxl_rwsem.region);
 
 	return port->commit_end + 1;
 }
@@ -176,7 +170,7 @@ static ssize_t target_list_show(struct device *dev,
 	ssize_t offset;
 	int rc;
 
-	guard(rwsem_read)(&cxl_region_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.region);
 	rc = emit_target_list(cxlsd, buf);
 	if (rc < 0)
 		return rc;
@@ -196,7 +190,7 @@ static ssize_t mode_show(struct device *dev, struct device_attribute *attr,
 	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
 	struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
 	struct cxl_dev_state *cxlds = cxlmd->cxlds;
-	/* without @cxl_dpa_rwsem, make sure @part is not reloaded */
+	/* without @cxl_rwsem.dpa, make sure @part is not reloaded */
 	int part = READ_ONCE(cxled->part);
 	const char *desc;
 
@@ -235,7 +229,7 @@ static ssize_t dpa_resource_show(struct device *dev, struct device_attribute *at
 {
 	struct cxl_endpoint_decoder *cxled = to_cxl_endpoint_decoder(dev);
 
-	guard(rwsem_read)(&cxl_dpa_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.dpa);
 	return sysfs_emit(buf, "%#llx\n", (u64)cxl_dpa_resource_start(cxled));
 }
 static DEVICE_ATTR_RO(dpa_resource);
@@ -560,7 +554,7 @@ static ssize_t decoders_committed_show(struct device *dev,
 {
 	struct cxl_port *port = to_cxl_port(dev);
 
-	guard(rwsem_read)(&cxl_region_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.region);
 	return sysfs_emit(buf, "%d\n", cxl_num_decoders_committed(port));
 }
 
@@ -1722,7 +1716,7 @@ static int decoder_populate_targets(struct cxl_switch_decoder *cxlsd,
 	if (xa_empty(&port->dports))
 		return -EINVAL;
 
-	guard(rwsem_write)(&cxl_region_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.region);
 	for (i = 0; i < cxlsd->cxld.interleave_ways; i++) {
 		struct cxl_dport *dport = find_dport(port, target_map[i]);
 
diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
index 4314aaed8ad8..ad60c93be803 100644
--- a/drivers/cxl/core/region.c
+++ b/drivers/cxl/core/region.c
@@ -141,16 +141,12 @@ static ssize_t uuid_show(struct device *dev, struct device_attribute *attr,
 	struct cxl_region_params *p = &cxlr->params;
 	ssize_t rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, region_rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &region_rwsem)))
 		return rc;
 	if (cxlr->mode != CXL_PARTMODE_PMEM)
-		rc = sysfs_emit(buf, "\n");
-	else
-		rc = sysfs_emit(buf, "%pUb\n", &p->uuid);
-	up_read(&cxl_region_rwsem);
-
-	return rc;
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%pUb\n", &p->uuid);
 }
 
 static int is_dup(struct device *match, void *data)
@@ -162,7 +158,7 @@ static int is_dup(struct device *match, void *data)
 	if (!is_cxl_region(match))
 		return 0;
 
-	lockdep_assert_held(&cxl_region_rwsem);
+	lockdep_assert_held(&cxl_rwsem.region);
 	cxlr = to_cxl_region(match);
 	p = &cxlr->params;
 
@@ -192,27 +188,22 @@ static ssize_t uuid_store(struct device *dev, struct device_attribute *attr,
 	if (uuid_is_null(&temp))
 		return -EINVAL;
 
-	rc = down_write_killable(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_write_kill, region_rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_write_kill, &region_rwsem)))
 		return rc;
 
 	if (uuid_equal(&p->uuid, &temp))
-		goto out;
+		return len;
 
-	rc = -EBUSY;
 	if (p->state >= CXL_CONFIG_ACTIVE)
-		goto out;
+		return -EBUSY;
 
 	rc = bus_for_each_dev(&cxl_bus_type, NULL, &temp, is_dup);
 	if (rc < 0)
-		goto out;
+		return rc;
 
 	uuid_copy(&p->uuid, &temp);
-out:
-	up_write(&cxl_region_rwsem);
 
-	if (rc)
-		return rc;
 	return len;
 }
 static DEVICE_ATTR_RW(uuid);
@@ -354,20 +345,17 @@ static int queue_reset(struct cxl_region *cxlr)
 	struct cxl_region_params *p = &cxlr->params;
 	int rc;
 
-	rc = down_write_killable(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem)))
 		return rc;
 
 	/* Already in the requested state? */
 	if (p->state < CXL_CONFIG_COMMIT)
-		goto out;
+		return 0;
 
 	p->state = CXL_CONFIG_RESET_PENDING;
 
-out:
-	up_write(&cxl_region_rwsem);
-
-	return rc;
+	return 0;
 }
 
 static int __commit(struct cxl_region *cxlr)
@@ -375,19 +363,17 @@ static int __commit(struct cxl_region *cxlr)
 	struct cxl_region_params *p = &cxlr->params;
 	int rc;
 
-	rc = down_write_killable(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem)))
 		return rc;
 
 	/* Already in the requested state? */
 	if (p->state >= CXL_CONFIG_COMMIT)
-		goto out;
+		return 0;
 
 	/* Not ready to commit? */
-	if (p->state < CXL_CONFIG_ACTIVE) {
-		rc = -ENXIO;
-		goto out;
-	}
+	if (p->state < CXL_CONFIG_ACTIVE)
+		return -ENXIO;
 
 	/*
 	 * Invalidate caches before region setup to drop any speculative
@@ -395,16 +381,15 @@ static int __commit(struct cxl_region *cxlr)
 	 */
 	rc = cxl_region_invalidate_memregion(cxlr);
 	if (rc)
-		goto out;
+		return rc;
 
 	rc = cxl_region_decode_commit(cxlr);
-	if (rc == 0)
-		p->state = CXL_CONFIG_COMMIT;
+	if (rc)
+		return rc;
 
-out:
-	up_write(&cxl_region_rwsem);
+	p->state = CXL_CONFIG_COMMIT;
 
-	return rc;
+	return 0;
 }
 
 static ssize_t commit_store(struct device *dev, struct device_attribute *attr,
@@ -437,10 +422,10 @@ static ssize_t commit_store(struct device *dev, struct device_attribute *attr,
 	device_release_driver(&cxlr->dev);
 
 	/*
-	 * With the reset pending take cxl_region_rwsem unconditionally
+	 * With the reset pending take cxl_rwsem.region unconditionally
 	 * to ensure the reset gets handled before returning.
 	 */
-	guard(rwsem_write)(&cxl_region_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.region);
 
 	/*
 	 * Revalidate that the reset is still pending in case another
@@ -461,13 +446,10 @@ static ssize_t commit_show(struct device *dev, struct device_attribute *attr,
 	struct cxl_region_params *p = &cxlr->params;
 	ssize_t rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
 		return rc;
-	rc = sysfs_emit(buf, "%d\n", p->state >= CXL_CONFIG_COMMIT);
-	up_read(&cxl_region_rwsem);
-
-	return rc;
+	return sysfs_emit(buf, "%d\n", p->state >= CXL_CONFIG_COMMIT);
 }
 static DEVICE_ATTR_RW(commit);
 
@@ -491,15 +473,12 @@ static ssize_t interleave_ways_show(struct device *dev,
 {
 	struct cxl_region *cxlr = to_cxl_region(dev);
 	struct cxl_region_params *p = &cxlr->params;
-	ssize_t rc;
+	int rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
 		return rc;
-	rc = sysfs_emit(buf, "%d\n", p->interleave_ways);
-	up_read(&cxl_region_rwsem);
-
-	return rc;
+	return sysfs_emit(buf, "%d\n", p->interleave_ways);
 }
 
 static const struct attribute_group *get_cxl_region_target_group(void);
@@ -534,23 +513,21 @@ static ssize_t interleave_ways_store(struct device *dev,
 		return -EINVAL;
 	}
 
-	rc = down_write_killable(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem)))
 		return rc;
-	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) {
-		rc = -EBUSY;
-		goto out;
-	}
+
+	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE)
+		return -EBUSY;
 
 	save = p->interleave_ways;
 	p->interleave_ways = val;
 	rc = sysfs_update_group(&cxlr->dev.kobj, get_cxl_region_target_group());
-	if (rc)
+	if (rc) {
 		p->interleave_ways = save;
-out:
-	up_write(&cxl_region_rwsem);
-	if (rc)
 		return rc;
+	}
+
 	return len;
 }
 static DEVICE_ATTR_RW(interleave_ways);
@@ -561,15 +538,12 @@ static ssize_t interleave_granularity_show(struct device *dev,
 {
 	struct cxl_region *cxlr = to_cxl_region(dev);
 	struct cxl_region_params *p = &cxlr->params;
-	ssize_t rc;
+	int rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
 		return rc;
-	rc = sysfs_emit(buf, "%d\n", p->interleave_granularity);
-	up_read(&cxl_region_rwsem);
-
-	return rc;
+	return sysfs_emit(buf, "%d\n", p->interleave_granularity);
 }
 
 static ssize_t interleave_granularity_store(struct device *dev,
@@ -602,19 +576,15 @@ static ssize_t interleave_granularity_store(struct device *dev,
 	if (cxld->interleave_ways > 1 && val != cxld->interleave_granularity)
 		return -EINVAL;
 
-	rc = down_write_killable(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem)))
 		return rc;
-	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) {
-		rc = -EBUSY;
-		goto out;
-	}
+
+	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE)
+		return -EBUSY;
 
 	p->interleave_granularity = val;
-out:
-	up_write(&cxl_region_rwsem);
-	if (rc)
-		return rc;
+
 	return len;
 }
 static DEVICE_ATTR_RW(interleave_granularity);
@@ -625,17 +595,15 @@ static ssize_t resource_show(struct device *dev, struct device_attribute *attr,
 	struct cxl_region *cxlr = to_cxl_region(dev);
 	struct cxl_region_params *p = &cxlr->params;
 	u64 resource = -1ULL;
-	ssize_t rc;
+	int rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
 		return rc;
+
 	if (p->res)
 		resource = p->res->start;
-	rc = sysfs_emit(buf, "%#llx\n", resource);
-	up_read(&cxl_region_rwsem);
-
-	return rc;
+	return sysfs_emit(buf, "%#llx\n", resource);
 }
 static DEVICE_ATTR_RO(resource);
 
@@ -663,7 +631,7 @@ static int alloc_hpa(struct cxl_region *cxlr, resource_size_t size)
 	struct resource *res;
 	u64 remainder = 0;
 
-	lockdep_assert_held_write(&cxl_region_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.region);
 
 	/* Nothing to do... */
 	if (p->res && resource_size(p->res) == size)
@@ -705,7 +673,7 @@ static void cxl_region_iomem_release(struct cxl_region *cxlr)
 	struct cxl_region_params *p = &cxlr->params;
 
 	if (device_is_registered(&cxlr->dev))
-		lockdep_assert_held_write(&cxl_region_rwsem);
+		lockdep_assert_held_write(&cxl_rwsem.region);
 	if (p->res) {
 		/*
 		 * Autodiscovered regions may not have been able to insert their
@@ -722,7 +690,7 @@ static int free_hpa(struct cxl_region *cxlr)
 {
 	struct cxl_region_params *p = &cxlr->params;
 
-	lockdep_assert_held_write(&cxl_region_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.region);
 
 	if (!p->res)
 		return 0;
@@ -746,15 +714,14 @@ static ssize_t size_store(struct device *dev, struct device_attribute *attr,
 	if (rc)
 		return rc;
 
-	rc = down_write_killable(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem)))
 		return rc;
 
 	if (val)
 		rc = alloc_hpa(cxlr, val);
 	else
 		rc = free_hpa(cxlr);
-	up_write(&cxl_region_rwsem);
 
 	if (rc)
 		return rc;
@@ -770,15 +737,12 @@ static ssize_t size_show(struct device *dev, struct device_attribute *attr,
 	u64 size = 0;
 	ssize_t rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
 		return rc;
 	if (p->res)
 		size = resource_size(p->res);
-	rc = sysfs_emit(buf, "%#llx\n", size);
-	up_read(&cxl_region_rwsem);
-
-	return rc;
+	return sysfs_emit(buf, "%#llx\n", size);
 }
 static DEVICE_ATTR_RW(size);
 
@@ -804,26 +768,20 @@ static size_t show_targetN(struct cxl_region *cxlr, char *buf, int pos)
 	struct cxl_endpoint_decoder *cxled;
 	int rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
 		return rc;
 
 	if (pos >= p->interleave_ways) {
 		dev_dbg(&cxlr->dev, "position %d out of range %d\n", pos,
 			p->interleave_ways);
-		rc = -ENXIO;
-		goto out;
+		return -ENXIO;
 	}
 
 	cxled = p->targets[pos];
 	if (!cxled)
-		rc = sysfs_emit(buf, "\n");
-	else
-		rc = sysfs_emit(buf, "%s\n", dev_name(&cxled->cxld.dev));
-out:
-	up_read(&cxl_region_rwsem);
-
-	return rc;
+		return sysfs_emit(buf, "\n");
+	return sysfs_emit(buf, "%s\n", dev_name(&cxled->cxld.dev));
 }
 
 static int check_commit_order(struct device *dev, void *data)
@@ -938,7 +896,7 @@ cxl_port_pick_region_decoder(struct cxl_port *port,
 	/*
 	 * This decoder is pinned registered as long as the endpoint decoder is
 	 * registered, and endpoint decoder unregistration holds the
-	 * cxl_region_rwsem over unregister events, so no need to hold on to
+	 * cxl_rwsem.region over unregister events, so no need to hold on to
 	 * this extra reference.
 	 */
 	put_device(dev);
@@ -1129,7 +1087,7 @@ static int cxl_port_attach_region(struct cxl_port *port,
 	unsigned long index;
 	int rc = -EBUSY;
 
-	lockdep_assert_held_write(&cxl_region_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.region);
 
 	cxl_rr = cxl_rr_load(port, cxlr);
 	if (cxl_rr) {
@@ -1239,7 +1197,7 @@ static void cxl_port_detach_region(struct cxl_port *port,
 	struct cxl_region_ref *cxl_rr;
 	struct cxl_ep *ep = NULL;
 
-	lockdep_assert_held_write(&cxl_region_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.region);
 
 	cxl_rr = cxl_rr_load(port, cxlr);
 	if (!cxl_rr)
@@ -2142,7 +2100,7 @@ __cxl_decoder_detach(struct cxl_region *cxlr,
 {
 	struct cxl_region_params *p;
 
-	lockdep_assert_held_write(&cxl_region_rwsem);
+	lockdep_assert_held_write(&cxl_rwsem.region);
 
 	if (!cxled) {
 		p = &cxlr->params;
@@ -2215,18 +2173,18 @@ int cxl_decoder_detach(struct cxl_region *cxlr,
 	struct cxl_region *detach;
 
 	/* when the decoder is being destroyed lock unconditionally */
-	if (mode == DETACH_INVALIDATE)
-		down_write(&cxl_region_rwsem);
-	else {
-		int rc = down_write_killable(&cxl_region_rwsem);
+	if (mode == DETACH_INVALIDATE) {
+		guard(rwsem_write)(&cxl_rwsem.region);
+		detach = __cxl_decoder_detach(cxlr, cxled, pos, mode);
+	} else {
+		int rc;
 
-		if (rc)
+		ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region);
+		if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem)))
 			return rc;
+		detach = __cxl_decoder_detach(cxlr, cxled, pos, mode);
 	}
 
-	detach = __cxl_decoder_detach(cxlr, cxled, pos, mode);
-	up_write(&cxl_region_rwsem);
-
 	if (detach) {
 		device_release_driver(&detach->dev);
 		put_device(&detach->dev);
@@ -2234,29 +2192,35 @@ int cxl_decoder_detach(struct cxl_region *cxlr,
 	return 0;
 }
 
+static int __attach_target(struct cxl_region *cxlr,
+			   struct cxl_endpoint_decoder *cxled, int pos,
+			   unsigned int state)
+{
+	int rc;
+
+	if (state == TASK_INTERRUPTIBLE) {
+		ACQUIRE(rwsem_write_kill, rwsem)(&cxl_rwsem.region);
+		if ((rc = ACQUIRE_ERR(rwsem_write_kill, &rwsem)))
+			return rc;
+		guard(rwsem_read)(&cxl_rwsem.dpa);
+		return cxl_region_attach(cxlr, cxled, pos);
+	}
+	guard(rwsem_write)(&cxl_rwsem.region);
+	guard(rwsem_read)(&cxl_rwsem.dpa);
+	return cxl_region_attach(cxlr, cxled, pos);
+}
+
 static int attach_target(struct cxl_region *cxlr,
 			 struct cxl_endpoint_decoder *cxled, int pos,
 			 unsigned int state)
 {
-	int rc = 0;
-
-	if (state == TASK_INTERRUPTIBLE)
-		rc = down_write_killable(&cxl_region_rwsem);
-	else
-		down_write(&cxl_region_rwsem);
-	if (rc)
-		return rc;
-
-	down_read(&cxl_dpa_rwsem);
-	rc = cxl_region_attach(cxlr, cxled, pos);
-	up_read(&cxl_dpa_rwsem);
-	up_write(&cxl_region_rwsem);
+	int rc = __attach_target(cxlr, cxled, pos, state);
 
-	if (rc)
-		dev_warn(cxled->cxld.dev.parent,
-			"failed to attach %s to %s: %d\n",
-			dev_name(&cxled->cxld.dev), dev_name(&cxlr->dev), rc);
+	if (rc == 0)
+		return 0;
 
+	dev_warn(cxled->cxld.dev.parent, "failed to attach %s to %s: %d\n",
+		 dev_name(&cxled->cxld.dev), dev_name(&cxlr->dev), rc);
 	return rc;
 }
 
@@ -2516,7 +2480,7 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
 		return NOTIFY_DONE;
 
 	/*
-	 * No need to hold cxl_region_rwsem; region parameters are stable
+	 * No need to hold cxl_rwsem.region; region parameters are stable
 	 * within the cxl_region driver.
 	 */
 	region_nid = phys_to_target_node(cxlr->params.res->start);
@@ -2539,7 +2503,7 @@ static int cxl_region_calculate_adistance(struct notifier_block *nb,
 	int region_nid;
 
 	/*
-	 * No need to hold cxl_region_rwsem; region parameters are stable
+	 * No need to hold cxl_rwsem.region; region parameters are stable
 	 * within the cxl_region driver.
 	 */
 	region_nid = phys_to_target_node(cxlr->params.res->start);
@@ -2688,17 +2652,13 @@ static ssize_t region_show(struct device *dev, struct device_attribute *attr,
 	struct cxl_decoder *cxld = to_cxl_decoder(dev);
 	ssize_t rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc)
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem)))
 		return rc;
 
 	if (cxld->region)
-		rc = sysfs_emit(buf, "%s\n", dev_name(&cxld->region->dev));
-	else
-		rc = sysfs_emit(buf, "\n");
-	up_read(&cxl_region_rwsem);
-
-	return rc;
+		return sysfs_emit(buf, "%s\n", dev_name(&cxld->region->dev));
+	return sysfs_emit(buf, "\n");
 }
 DEVICE_ATTR_RO(region);
 
@@ -3037,7 +2997,7 @@ static int cxl_pmem_region_alloc(struct cxl_region *cxlr)
 	struct device *dev;
 	int i;
 
-	guard(rwsem_read)(&cxl_region_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.region);
 	if (p->state != CXL_CONFIG_COMMIT)
 		return -ENXIO;
 
@@ -3049,7 +3009,7 @@ static int cxl_pmem_region_alloc(struct cxl_region *cxlr)
 	cxlr_pmem->hpa_range.start = p->res->start;
 	cxlr_pmem->hpa_range.end = p->res->end;
 
-	/* Snapshot the region configuration underneath the cxl_region_rwsem */
+	/* Snapshot the region configuration underneath the cxl_rwsem.region */
 	cxlr_pmem->nr_mappings = p->nr_targets;
 	for (i = 0; i < p->nr_targets; i++) {
 		struct cxl_endpoint_decoder *cxled = p->targets[i];
@@ -3126,7 +3086,7 @@ static struct cxl_dax_region *cxl_dax_region_alloc(struct cxl_region *cxlr)
 	struct cxl_dax_region *cxlr_dax;
 	struct device *dev;
 
-	guard(rwsem_read)(&cxl_region_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.region);
 	if (p->state != CXL_CONFIG_COMMIT)
 		return ERR_PTR(-ENXIO);
 
@@ -3326,7 +3286,7 @@ static int match_region_by_range(struct device *dev, const void *data)
 	cxlr = to_cxl_region(dev);
 	p = &cxlr->params;
 
-	guard(rwsem_read)(&cxl_region_rwsem);
+	guard(rwsem_read)(&cxl_rwsem.region);
 	if (p->res && p->res->start == r->start && p->res->end == r->end)
 		return 1;
 
@@ -3386,7 +3346,7 @@ static int __construct_region(struct cxl_region *cxlr,
 	struct resource *res;
 	int rc;
 
-	guard(rwsem_write)(&cxl_region_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.region);
 	p = &cxlr->params;
 	if (p->state >= CXL_CONFIG_INTERLEAVE_ACTIVE) {
 		dev_err(cxlmd->dev.parent,
@@ -3522,10 +3482,10 @@ int cxl_add_to_region(struct cxl_endpoint_decoder *cxled)
 
 	attach_target(cxlr, cxled, -1, TASK_UNINTERRUPTIBLE);
 
-	down_read(&cxl_region_rwsem);
-	p = &cxlr->params;
-	attach = p->state == CXL_CONFIG_COMMIT;
-	up_read(&cxl_region_rwsem);
+	scoped_guard(rwsem_read, &cxl_rwsem.region) {
+		p = &cxlr->params;
+		attach = p->state == CXL_CONFIG_COMMIT;
+	}
 
 	if (attach) {
 		/*
@@ -3550,7 +3510,7 @@ u64 cxl_port_get_spa_cache_alias(struct cxl_port *endpoint, u64 spa)
 	if (!endpoint)
 		return ~0ULL;
 
-	guard(rwsem_write)(&cxl_region_rwsem);
+	guard(rwsem_write)(&cxl_rwsem.region);
 
 	xa_for_each(&endpoint->regions, index, iter) {
 		struct cxl_region_params *p = &iter->region->params;
@@ -3592,30 +3552,23 @@ static int cxl_region_can_probe(struct cxl_region *cxlr)
 	struct cxl_region_params *p = &cxlr->params;
 	int rc;
 
-	rc = down_read_interruptible(&cxl_region_rwsem);
-	if (rc) {
+	ACQUIRE(rwsem_read_intr, rwsem)(&cxl_rwsem.region);
+	if ((rc = ACQUIRE_ERR(rwsem_read_intr, &rwsem))) {
 		dev_dbg(&cxlr->dev, "probe interrupted\n");
 		return rc;
 	}
 
 	if (p->state < CXL_CONFIG_COMMIT) {
 		dev_dbg(&cxlr->dev, "config state: %d\n", p->state);
-		rc = -ENXIO;
-		goto out;
+		return -ENXIO;
 	}
 
 	if (test_bit(CXL_REGION_F_NEEDS_RESET, &cxlr->flags)) {
 		dev_err(&cxlr->dev,
 			"failed to activate, re-commit region and retry\n");
-		rc = -ENXIO;
-		goto out;
+		return -ENXIO;
 	}
 
-out:
-	up_read(&cxl_region_rwsem);
-
-	if (rc)
-		return rc;
 	return 0;
 }
 
diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
index 3f1695c96abc..50799a681231 100644
--- a/drivers/cxl/cxl.h
+++ b/drivers/cxl/cxl.h
@@ -469,7 +469,7 @@ enum cxl_config_state {
  * @nr_targets: number of targets
  * @cache_size: extended linear cache size if exists, otherwise zero.
  *
- * State transitions are protected by the cxl_region_rwsem
+ * State transitions are protected by cxl_rwsem.region
  */
 struct cxl_region_params {
 	enum cxl_config_state state;
@@ -912,15 +912,4 @@ bool cxl_endpoint_decoder_reset_detected(struct cxl_port *port);
 #endif
 
 u16 cxl_gpf_get_dvsec(struct device *dev);
-
-static inline struct rw_semaphore *rwsem_read_intr_acquire(struct rw_semaphore *rwsem)
-{
-	if (down_read_interruptible(rwsem))
-		return NULL;
-
-	return rwsem;
-}
-
-DEFINE_FREE(rwsem_read_release, struct rw_semaphore *, if (_T) up_read(_T))
-
 #endif /* __CXL_H__ */
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index c810deb88d13..cbafdc12e743 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -244,6 +244,7 @@ DEFINE_GUARD_COND(rwsem_read, _intr, down_read_interruptible(_T), _RET == 0)
 
 DEFINE_GUARD(rwsem_write, struct rw_semaphore *, down_write(_T), up_write(_T))
 DEFINE_GUARD_COND(rwsem_write, _try, down_write_trylock(_T))
+DEFINE_GUARD_COND(rwsem_write, _kill, down_write_killable(_T), _RET == 0)
 
 /*
  * downgrade write lock to read lock
-- 
cgit v1.2.3


From 09813cde376d9d8f30eaf761534532101a0a7755 Mon Sep 17 00:00:00 2001
From: Hiago De Franco <hiago.franco@toradex.com>
Date: Sun, 29 Jun 2025 14:25:10 -0300
Subject: pmdomain: core: introduce dev_pm_genpd_is_on()

This helper function returns the current power status of a given generic
power domain.

As example, remoteproc/imx_rproc.c can now use this function to check
the power status of the remote core to properly set "attached" or
"offline" modes.

Suggested-by: Ulf Hansson <ulf.hansson@linaro.org>
Reviewed-by: Bjorn Andersson <andersson@kernel.org>
Reviewed-by: Peng Fan <peng.fan@nxp.com>
Signed-off-by: Hiago De Franco <hiago.franco@toradex.com>
Link: https://lore.kernel.org/r/20250629172512.14857-2-hiagofranco@gmail.com
Signed-off-by: Ulf Hansson <ulf.hansson@linaro.org>
---
 drivers/pmdomain/core.c   | 33 +++++++++++++++++++++++++++++++++
 include/linux/pm_domain.h |  6 ++++++
 2 files changed, 39 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
index a86aeda1c955..0006ab3d0789 100644
--- a/drivers/pmdomain/core.c
+++ b/drivers/pmdomain/core.c
@@ -769,6 +769,39 @@ int dev_pm_genpd_rpm_always_on(struct device *dev, bool on)
 }
 EXPORT_SYMBOL_GPL(dev_pm_genpd_rpm_always_on);
 
+/**
+ * dev_pm_genpd_is_on() - Get device's current power domain status
+ *
+ * @dev: Device to get the current power status
+ *
+ * This function checks whether the generic power domain associated with the
+ * given device is on or not by verifying if genpd_status_on equals
+ * GENPD_STATE_ON.
+ *
+ * Note: this function returns the power status of the genpd at the time of the
+ * call. The power status may change after due to activity from other devices
+ * sharing the same genpd. Therefore, this information should not be relied for
+ * long-term decisions about the device power state.
+ *
+ * Return: 'true' if the device's power domain is on, 'false' otherwise.
+ */
+bool dev_pm_genpd_is_on(struct device *dev)
+{
+	struct generic_pm_domain *genpd;
+	bool is_on;
+
+	genpd = dev_to_genpd_safe(dev);
+	if (!genpd)
+		return false;
+
+	genpd_lock(genpd);
+	is_on = genpd_status_on(genpd);
+	genpd_unlock(genpd);
+
+	return is_on;
+}
+EXPORT_SYMBOL_GPL(dev_pm_genpd_is_on);
+
 /**
  * pm_genpd_inc_rejected() - Adjust the rejected/usage counts for an idle-state.
  *
diff --git a/include/linux/pm_domain.h b/include/linux/pm_domain.h
index 99556589f45e..b9d3c7d5c4f8 100644
--- a/include/linux/pm_domain.h
+++ b/include/linux/pm_domain.h
@@ -315,6 +315,7 @@ void dev_pm_genpd_synced_poweroff(struct device *dev);
 int dev_pm_genpd_set_hwmode(struct device *dev, bool enable);
 bool dev_pm_genpd_get_hwmode(struct device *dev);
 int dev_pm_genpd_rpm_always_on(struct device *dev, bool on);
+bool dev_pm_genpd_is_on(struct device *dev);
 
 extern struct dev_power_governor simple_qos_governor;
 extern struct dev_power_governor pm_domain_always_on_gov;
@@ -407,6 +408,11 @@ static inline int dev_pm_genpd_rpm_always_on(struct device *dev, bool on)
 	return -EOPNOTSUPP;
 }
 
+static inline bool dev_pm_genpd_is_on(struct device *dev)
+{
+	return false;
+}
+
 #define simple_qos_governor		(*(struct dev_power_governor *)(NULL))
 #define pm_domain_always_on_gov		(*(struct dev_power_governor *)(NULL))
 #endif
-- 
cgit v1.2.3


From c1f1fda141373d7253b4c1497043b0ef85f534ce Mon Sep 17 00:00:00 2001
From: Shuai Xue <xueshuai@linux.alibaba.com>
Date: Mon, 14 Jul 2025 19:42:12 +0800
Subject: ACPI: APEI: handle synchronous exceptions in task work

The memory uncorrected error could be signaled by asynchronous interrupt
(specifically, SPI in arm64 platform), e.g. when an error is detected by
a background scrubber, or signaled by synchronous exception
(specifically, data abort exception in arm64 platform), e.g. when a CPU
tries to access a poisoned cache line. Currently, both synchronous and
asynchronous errors use memory_failure_queue() to schedule
memory_failure() to exectute in a kworker context.

As a result, when a user-space process is accessing a poisoned data, a
data abort is taken and the memory_failure() is executed in the kworker
context, which:

  - will send wrong si_code by SIGBUS signal in early_kill mode, and
  - can not kill the user-space in some cases resulting a synchronous
    error infinite loop

Issue 1: send wrong si_code in early_kill mode

Since commit a70297d22132 ("ACPI: APEI: set memory failure flags as
MF_ACTION_REQUIRED on synchronous events")', the flag MF_ACTION_REQUIRED
could be used to determine whether a synchronous exception occurs on
ARM64 platform.  When a synchronous exception is detected, the kernel is
expected to terminate the current process which has accessed a poisoned
page. This is done by sending a SIGBUS signal with error code
BUS_MCEERR_AR, indicating an action-required machine check error on
read.

However, when kill_proc() is called to terminate the processes who has
the poisoned page mapped, it sends the incorrect SIGBUS error code
BUS_MCEERR_AO because the context in which it operates is not the one
where the error was triggered.

To reproduce this problem:

  #sysctl -w vm.memory_failure_early_kill=1
  vm.memory_failure_early_kill = 1

  # STEP2: inject an UCE error and consume it to trigger a synchronous error
  #einj_mem_uc single
  0: single   vaddr = 0xffffb0d75400 paddr = 4092d55b400
  injecting ...
  triggering ...
  signal 7 code 5 addr 0xffffb0d75000
  page not present
  Test passed

The si_code (code 5) from einj_mem_uc indicates that it is BUS_MCEERR_AO
error and it is not factually correct.

After this change:

  # STEP1: enable early kill mode
  #sysctl -w vm.memory_failure_early_kill=1
  vm.memory_failure_early_kill = 1
  # STEP2: inject an UCE error and consume it to trigger a synchronous error
  #einj_mem_uc single
  0: single   vaddr = 0xffffb0d75400 paddr = 4092d55b400
  injecting ...
  triggering ...
  signal 7 code 4 addr 0xffffb0d75000
  page not present
  Test passed

The si_code (code 4) from einj_mem_uc indicates that it is a BUS_MCEERR_AR
error as expected.

Issue 2: a synchronous error infinite loop

If a user-space process, e.g. devmem, accesses a poisoned page for which
the HWPoison flag is set, kill_accessing_process() is called to send
SIGBUS to current processs with error info. Since the memory_failure()
is executed in the kworker context, it will just do nothing but return
EFAULT. So, devmem will access the posioned page and trigger an
exception again, resulting in a synchronous error infinite loop. Such
exception loop may cause platform firmware to exceed some threshold and
reboot when Linux could have recovered from this error.

To reproduce this problem:

  # STEP 1: inject an UCE error, and kernel will set HWPosion flag for related page
  #einj_mem_uc single
  0: single   vaddr = 0xffffb0d75400 paddr = 4092d55b400
  injecting ...
  triggering ...
  signal 7 code 4 addr 0xffffb0d75000
  page not present
  Test passed

  # STEP 2: access the same page and it will trigger a synchronous error infinite loop
  devmem 0x4092d55b400

To fix above two issues, queue memory_failure() as a task_work so that
it runs in the context of the process that is actually consuming the
poisoned data.

Signed-off-by: Shuai Xue <xueshuai@linux.alibaba.com>
Tested-by: Ma Wupeng <mawupeng1@huawei.com>
Reviewed-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Reviewed-by: Xiaofei Tan <tanxiaofei@huawei.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Reviewed-by: Jane Chu <jane.chu@oracle.com>
Reviewed-by: Yazen Ghannam <yazen.ghannam@amd.com>
Reviewed-by: Hanjun Guo <guohanjun@huawei.com>
Link: https://patch.msgid.link/20250714114212.31660-3-xueshuai@linux.alibaba.com
[ rjw: Changelog edits ]
Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
---
 drivers/acpi/apei/ghes.c | 79 +++++++++++++++++++++++++++---------------------
 include/acpi/ghes.h      |  3 --
 include/linux/mm.h       |  1 -
 mm/memory-failure.c      | 13 --------
 4 files changed, 45 insertions(+), 51 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/acpi/apei/ghes.c b/drivers/acpi/apei/ghes.c
index bda33a0f0a01..a0d54993edb3 100644
--- a/drivers/acpi/apei/ghes.c
+++ b/drivers/acpi/apei/ghes.c
@@ -464,28 +464,41 @@ static void ghes_clear_estatus(struct ghes *ghes,
 		ghes_ack_error(ghes->generic_v2);
 }
 
-/*
- * Called as task_work before returning to user-space.
- * Ensure any queued work has been done before we return to the context that
- * triggered the notification.
+/**
+ * struct ghes_task_work - for synchronous RAS event
+ *
+ * @twork:                callback_head for task work
+ * @pfn:                  page frame number of corrupted page
+ * @flags:                work control flags
+ *
+ * Structure to pass task work to be handled before
+ * returning to user-space via task_work_add().
  */
-static void ghes_kick_task_work(struct callback_head *head)
+struct ghes_task_work {
+	struct callback_head twork;
+	u64 pfn;
+	int flags;
+};
+
+static void memory_failure_cb(struct callback_head *twork)
 {
-	struct acpi_hest_generic_status *estatus;
-	struct ghes_estatus_node *estatus_node;
-	u32 node_len;
+	struct ghes_task_work *twcb = container_of(twork, struct ghes_task_work, twork);
+	int ret;
 
-	estatus_node = container_of(head, struct ghes_estatus_node, task_work);
-	if (IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
-		memory_failure_queue_kick(estatus_node->task_work_cpu);
+	ret = memory_failure(twcb->pfn, twcb->flags);
+	gen_pool_free(ghes_estatus_pool, (unsigned long)twcb, sizeof(*twcb));
 
-	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
-	node_len = GHES_ESTATUS_NODE_LEN(cper_estatus_len(estatus));
-	gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node, node_len);
+	if (!ret || ret == -EHWPOISON || ret == -EOPNOTSUPP)
+		return;
+
+	pr_err("%#llx: Sending SIGBUS to %s:%d due to hardware memory corruption\n",
+			twcb->pfn, current->comm, task_pid_nr(current));
+	force_sig(SIGBUS);
 }
 
 static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 {
+	struct ghes_task_work *twcb;
 	unsigned long pfn;
 
 	if (!IS_ENABLED(CONFIG_ACPI_APEI_MEMORY_FAILURE))
@@ -499,6 +512,18 @@ static bool ghes_do_memory_failure(u64 physical_addr, int flags)
 		return false;
 	}
 
+	if (flags == MF_ACTION_REQUIRED && current->mm) {
+		twcb = (void *)gen_pool_alloc(ghes_estatus_pool, sizeof(*twcb));
+		if (!twcb)
+			return false;
+
+		twcb->pfn = pfn;
+		twcb->flags = flags;
+		init_task_work(&twcb->twork, memory_failure_cb);
+		task_work_add(current, &twcb->twork, TWA_RESUME);
+		return true;
+	}
+
 	memory_failure_queue(pfn, flags);
 	return true;
 }
@@ -842,7 +867,7 @@ int cxl_cper_kfifo_get(struct cxl_cper_work_data *wd)
 }
 EXPORT_SYMBOL_NS_GPL(cxl_cper_kfifo_get, "CXL");
 
-static bool ghes_do_proc(struct ghes *ghes,
+static void ghes_do_proc(struct ghes *ghes,
 			 const struct acpi_hest_generic_status *estatus)
 {
 	int sev, sec_sev;
@@ -912,8 +937,6 @@ static bool ghes_do_proc(struct ghes *ghes,
 			current->comm, task_pid_nr(current));
 		force_sig(SIGBUS);
 	}
-
-	return queued;
 }
 
 static void __ghes_print_estatus(const char *pfx,
@@ -1219,9 +1242,7 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 	struct ghes_estatus_node *estatus_node;
 	struct acpi_hest_generic *generic;
 	struct acpi_hest_generic_status *estatus;
-	bool task_work_pending;
 	u32 len, node_len;
-	int ret;
 
 	llnode = llist_del_all(&ghes_estatus_llist);
 	/*
@@ -1236,25 +1257,16 @@ static void ghes_proc_in_irq(struct irq_work *irq_work)
 		estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 		len = cper_estatus_len(estatus);
 		node_len = GHES_ESTATUS_NODE_LEN(len);
-		task_work_pending = ghes_do_proc(estatus_node->ghes, estatus);
+
+		ghes_do_proc(estatus_node->ghes, estatus);
+
 		if (!ghes_estatus_cached(estatus)) {
 			generic = estatus_node->generic;
 			if (ghes_print_estatus(NULL, generic, estatus))
 				ghes_estatus_cache_add(generic, estatus);
 		}
-
-		if (task_work_pending && current->mm) {
-			estatus_node->task_work.func = ghes_kick_task_work;
-			estatus_node->task_work_cpu = smp_processor_id();
-			ret = task_work_add(current, &estatus_node->task_work,
-					    TWA_RESUME);
-			if (ret)
-				estatus_node->task_work.func = NULL;
-		}
-
-		if (!estatus_node->task_work.func)
-			gen_pool_free(ghes_estatus_pool,
-				      (unsigned long)estatus_node, node_len);
+		gen_pool_free(ghes_estatus_pool, (unsigned long)estatus_node,
+			      node_len);
 
 		llnode = next;
 	}
@@ -1315,7 +1327,6 @@ static int ghes_in_nmi_queue_one_entry(struct ghes *ghes,
 
 	estatus_node->ghes = ghes;
 	estatus_node->generic = ghes->generic;
-	estatus_node->task_work.func = NULL;
 	estatus = GHES_ESTATUS_FROM_NODE(estatus_node);
 
 	if (__ghes_read_estatus(estatus, buf_paddr, fixmap_idx, len)) {
diff --git a/include/acpi/ghes.h b/include/acpi/ghes.h
index be1dd4c1a917..ebd21b05fe6e 100644
--- a/include/acpi/ghes.h
+++ b/include/acpi/ghes.h
@@ -35,9 +35,6 @@ struct ghes_estatus_node {
 	struct llist_node llnode;
 	struct acpi_hest_generic *generic;
 	struct ghes *ghes;
-
-	int task_work_cpu;
-	struct callback_head task_work;
 };
 
 struct ghes_estatus_cache {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 0ef2ba0c667a..02dffff2508b 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3896,7 +3896,6 @@ enum mf_flags {
 int mf_dax_kill_procs(struct address_space *mapping, pgoff_t index,
 		      unsigned long count, int mf_flags);
 extern int memory_failure(unsigned long pfn, int flags);
-extern void memory_failure_queue_kick(int cpu);
 extern int unpoison_memory(unsigned long pfn);
 extern atomic_long_t num_poisoned_pages __read_mostly;
 extern int soft_offline_page(unsigned long pfn, int flags);
diff --git a/mm/memory-failure.c b/mm/memory-failure.c
index b91a33fb6c69..5278132a2b6d 100644
--- a/mm/memory-failure.c
+++ b/mm/memory-failure.c
@@ -2503,19 +2503,6 @@ static void memory_failure_work_func(struct work_struct *work)
 	}
 }
 
-/*
- * Process memory_failure work queued on the specified CPU.
- * Used to avoid return-to-userspace racing with the memory_failure workqueue.
- */
-void memory_failure_queue_kick(int cpu)
-{
-	struct memory_failure_cpu *mf_cpu;
-
-	mf_cpu = &per_cpu(memory_failure_cpu, cpu);
-	cancel_work_sync(&mf_cpu->work);
-	memory_failure_work_func(&mf_cpu->work);
-}
-
 static int __init memory_failure_init(void)
 {
 	struct memory_failure_cpu *mf_cpu;
-- 
cgit v1.2.3


From 19d18fdfc79217c86802271c9ce5b4ed174628cc Mon Sep 17 00:00:00 2001
From: Tao Chen <chen.dylane@linux.dev>
Date: Wed, 16 Jul 2025 21:46:53 +0800
Subject: bpf: Add struct bpf_token_info

The 'commit 35f96de04127 ("bpf: Introduce BPF token object")' added
BPF token as a new kind of BPF kernel object. And BPF_OBJ_GET_INFO_BY_FD
already used to get BPF object info, so we can also get token info with
this cmd.
One usage scenario, when program runs failed with token, because of
the permission failure, we can report what BPF token is allowing with
this API for debugging.

Acked-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Tao Chen <chen.dylane@linux.dev>
Link: https://lore.kernel.org/r/20250716134654.1162635-1-chen.dylane@linux.dev
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h            | 11 +++++++++++
 include/uapi/linux/bpf.h       |  8 ++++++++
 kernel/bpf/syscall.c           | 18 ++++++++++++++++++
 kernel/bpf/token.c             | 25 ++++++++++++++++++++++++-
 tools/include/uapi/linux/bpf.h |  8 ++++++++
 5 files changed, 69 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index bc887831eaa5..f9cd2164ed23 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -2354,6 +2354,7 @@ extern const struct super_operations bpf_super_ops;
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 extern const struct file_operations bpf_iter_fops;
+extern const struct file_operations bpf_token_fops;
 
 #define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	extern const struct bpf_prog_ops _name ## _prog_ops; \
@@ -2551,6 +2552,9 @@ void bpf_token_inc(struct bpf_token *token);
 void bpf_token_put(struct bpf_token *token);
 int bpf_token_create(union bpf_attr *attr);
 struct bpf_token *bpf_token_get_from_fd(u32 ufd);
+int bpf_token_get_info_by_fd(struct bpf_token *token,
+			     const union bpf_attr *attr,
+			     union bpf_attr __user *uattr);
 
 bool bpf_token_allow_cmd(const struct bpf_token *token, enum bpf_cmd cmd);
 bool bpf_token_allow_map_type(const struct bpf_token *token, enum bpf_map_type type);
@@ -2949,6 +2953,13 @@ static inline struct bpf_token *bpf_token_get_from_fd(u32 ufd)
 	return ERR_PTR(-EOPNOTSUPP);
 }
 
+static inline int bpf_token_get_info_by_fd(struct bpf_token *token,
+					   const union bpf_attr *attr,
+					   union bpf_attr __user *uattr)
+{
+	return -EOPNOTSUPP;
+}
+
 static inline void __dev_flush(struct list_head *flush_list)
 {
 }
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0670e15a6100..233de8677382 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -450,6 +450,7 @@ union bpf_iter_link_info {
  *		* **struct bpf_map_info**
  *		* **struct bpf_btf_info**
  *		* **struct bpf_link_info**
+ *		* **struct bpf_token_info**
  *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
@@ -6803,6 +6804,13 @@ struct bpf_link_info {
 	};
 } __attribute__((aligned(8)));
 
+struct bpf_token_info {
+	__u64 allowed_cmds;
+	__u64 allowed_maps;
+	__u64 allowed_progs;
+	__u64 allowed_attachs;
+} __attribute__((aligned(8)));
+
 /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
  * by user and intended to be used by socket (e.g. to bind to, depends on
  * attach type).
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 1a26d17536be..e63039817af3 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -5239,6 +5239,21 @@ static int bpf_link_get_info_by_fd(struct file *file,
 }
 
 
+static int token_get_info_by_fd(struct file *file,
+				struct bpf_token *token,
+				const union bpf_attr *attr,
+				union bpf_attr __user *uattr)
+{
+	struct bpf_token_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+	u32 info_len = attr->info.info_len;
+	int err;
+
+	err = bpf_check_uarg_tail_zero(USER_BPFPTR(uinfo), sizeof(*uinfo), info_len);
+	if (err)
+		return err;
+	return bpf_token_get_info_by_fd(token, attr, uattr);
+}
+
 #define BPF_OBJ_GET_INFO_BY_FD_LAST_FIELD info.info
 
 static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
@@ -5262,6 +5277,9 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	else if (fd_file(f)->f_op == &bpf_link_fops || fd_file(f)->f_op == &bpf_link_fops_poll)
 		return bpf_link_get_info_by_fd(fd_file(f), fd_file(f)->private_data,
 					      attr, uattr);
+	else if (fd_file(f)->f_op == &bpf_token_fops)
+		return token_get_info_by_fd(fd_file(f), fd_file(f)->private_data,
+					    attr, uattr);
 	return -EINVAL;
 }
 
diff --git a/kernel/bpf/token.c b/kernel/bpf/token.c
index 26057aa13503..0bbe412f854e 100644
--- a/kernel/bpf/token.c
+++ b/kernel/bpf/token.c
@@ -103,7 +103,7 @@ static void bpf_token_show_fdinfo(struct seq_file *m, struct file *filp)
 
 static const struct inode_operations bpf_token_iops = { };
 
-static const struct file_operations bpf_token_fops = {
+const struct file_operations bpf_token_fops = {
 	.release	= bpf_token_release,
 	.show_fdinfo	= bpf_token_show_fdinfo,
 };
@@ -210,6 +210,29 @@ out_file:
 	return err;
 }
 
+int bpf_token_get_info_by_fd(struct bpf_token *token,
+			     const union bpf_attr *attr,
+			     union bpf_attr __user *uattr)
+{
+	struct bpf_token_info __user *uinfo = u64_to_user_ptr(attr->info.info);
+	struct bpf_token_info info;
+	u32 info_len = attr->info.info_len;
+
+	info_len = min_t(u32, info_len, sizeof(info));
+	memset(&info, 0, sizeof(info));
+
+	info.allowed_cmds = token->allowed_cmds;
+	info.allowed_maps = token->allowed_maps;
+	info.allowed_progs = token->allowed_progs;
+	info.allowed_attachs = token->allowed_attachs;
+
+	if (copy_to_user(uinfo, &info, info_len) ||
+	    put_user(info_len, &uattr->info.info_len))
+		return -EFAULT;
+
+	return 0;
+}
+
 struct bpf_token *bpf_token_get_from_fd(u32 ufd)
 {
 	CLASS(fd, f)(ufd);
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 0670e15a6100..233de8677382 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -450,6 +450,7 @@ union bpf_iter_link_info {
  *		* **struct bpf_map_info**
  *		* **struct bpf_btf_info**
  *		* **struct bpf_link_info**
+ *		* **struct bpf_token_info**
  *
  *	Return
  *		Returns zero on success. On error, -1 is returned and *errno*
@@ -6803,6 +6804,13 @@ struct bpf_link_info {
 	};
 } __attribute__((aligned(8)));
 
+struct bpf_token_info {
+	__u64 allowed_cmds;
+	__u64 allowed_maps;
+	__u64 allowed_progs;
+	__u64 allowed_attachs;
+} __attribute__((aligned(8)));
+
 /* User bpf_sock_addr struct to access socket fields and sockaddr struct passed
  * by user and intended to be used by socket (e.g. to bind to, depends on
  * attach type).
-- 
cgit v1.2.3


From 23972da96e1eee7f10c8ef641d56202ab9af8ba7 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 30 Jun 2025 14:12:02 +0200
Subject: firmware: qcom: scm: remove unused arguments from SHM bridge routines

qcom_scm_shm_bridge_create() and qcom_scm_shm_bridge_delete() take
struct device as argument but don't use it. Remove it from these
functions' prototypes.

Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Link: https://lore.kernel.org/r/20250630-qcom-scm-race-v2-1-fa3851c98611@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/firmware/qcom/qcom_scm.c       | 4 ++--
 drivers/firmware/qcom/qcom_tzmem.c     | 8 ++++----
 include/linux/firmware/qcom/qcom_scm.h | 4 ++--
 3 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c
index f63b716be5b0..d830511a0082 100644
--- a/drivers/firmware/qcom/qcom_scm.c
+++ b/drivers/firmware/qcom/qcom_scm.c
@@ -1631,7 +1631,7 @@ int qcom_scm_shm_bridge_enable(void)
 }
 EXPORT_SYMBOL_GPL(qcom_scm_shm_bridge_enable);
 
-int qcom_scm_shm_bridge_create(struct device *dev, u64 pfn_and_ns_perm_flags,
+int qcom_scm_shm_bridge_create(u64 pfn_and_ns_perm_flags,
 			       u64 ipfn_and_s_perm_flags, u64 size_and_flags,
 			       u64 ns_vmids, u64 *handle)
 {
@@ -1659,7 +1659,7 @@ int qcom_scm_shm_bridge_create(struct device *dev, u64 pfn_and_ns_perm_flags,
 }
 EXPORT_SYMBOL_GPL(qcom_scm_shm_bridge_create);
 
-int qcom_scm_shm_bridge_delete(struct device *dev, u64 handle)
+int qcom_scm_shm_bridge_delete(u64 handle)
 {
 	struct qcom_scm_desc desc = {
 		.svc = QCOM_SCM_SVC_MP,
diff --git a/drivers/firmware/qcom/qcom_tzmem.c b/drivers/firmware/qcom/qcom_tzmem.c
index 94196ad87105..4fe333fd2f07 100644
--- a/drivers/firmware/qcom/qcom_tzmem.c
+++ b/drivers/firmware/qcom/qcom_tzmem.c
@@ -124,9 +124,9 @@ static int qcom_tzmem_init_area(struct qcom_tzmem_area *area)
 	if (!handle)
 		return -ENOMEM;
 
-	ret = qcom_scm_shm_bridge_create(qcom_tzmem_dev, pfn_and_ns_perm,
-					 ipfn_and_s_perm, size_and_flags,
-					 QCOM_SCM_VMID_HLOS, handle);
+	ret = qcom_scm_shm_bridge_create(pfn_and_ns_perm, ipfn_and_s_perm,
+					 size_and_flags, QCOM_SCM_VMID_HLOS,
+					 handle);
 	if (ret)
 		return ret;
 
@@ -142,7 +142,7 @@ static void qcom_tzmem_cleanup_area(struct qcom_tzmem_area *area)
 	if (!qcom_tzmem_using_shm_bridge)
 		return;
 
-	qcom_scm_shm_bridge_delete(qcom_tzmem_dev, *handle);
+	qcom_scm_shm_bridge_delete(*handle);
 	kfree(handle);
 }
 
diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h
index 983e1591bbba..82b1b8c50ca3 100644
--- a/include/linux/firmware/qcom/qcom_scm.h
+++ b/include/linux/firmware/qcom/qcom_scm.h
@@ -149,10 +149,10 @@ bool qcom_scm_lmh_dcvsh_available(void);
 int qcom_scm_gpu_init_regs(u32 gpu_req);
 
 int qcom_scm_shm_bridge_enable(void);
-int qcom_scm_shm_bridge_create(struct device *dev, u64 pfn_and_ns_perm_flags,
+int qcom_scm_shm_bridge_create(u64 pfn_and_ns_perm_flags,
 			       u64 ipfn_and_s_perm_flags, u64 size_and_flags,
 			       u64 ns_vmids, u64 *handle);
-int qcom_scm_shm_bridge_delete(struct device *dev, u64 handle);
+int qcom_scm_shm_bridge_delete(u64 handle);
 
 #ifdef CONFIG_QCOM_QSEECOM
 
-- 
cgit v1.2.3


From dc3f4e75c54c19bad9a70419afae00ce6baf3ebf Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Mon, 30 Jun 2025 14:12:03 +0200
Subject: firmware: qcom: scm: take struct device as argument in SHM bridge
 enable

qcom_scm_shm_bridge_enable() is used early in the SCM initialization
routine. It makes an SCM call and so expects the internal __scm pointer
in the SCM driver to be assigned. For this reason the tzmem memory pool
is allocated *after* this pointer is assigned. However, this can lead to
a crash if another consumer of the SCM API makes a call using the memory
pool between the assignment of the __scm pointer and the initialization
of the tzmem memory pool.

As qcom_scm_shm_bridge_enable() is a special case, not meant to be
called by ordinary users, pull it into the local SCM header. Make it
take struct device as argument. This is the device that will be used to
make the SCM call as opposed to the global __scm pointer. This will
allow us to move the tzmem initialization *before* the __scm assignment
in the core SCM driver.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Konrad Dybcio <konrad.dybcio@oss.qualcomm.com>
Link: https://lore.kernel.org/r/20250630-qcom-scm-race-v2-2-fa3851c98611@linaro.org
Signed-off-by: Bjorn Andersson <andersson@kernel.org>
---
 drivers/firmware/qcom/qcom_scm.c       | 12 +++++++++---
 drivers/firmware/qcom/qcom_scm.h       |  1 +
 drivers/firmware/qcom/qcom_tzmem.c     |  3 ++-
 include/linux/firmware/qcom/qcom_scm.h |  1 -
 4 files changed, 12 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c
index d830511a0082..09b698b90216 100644
--- a/drivers/firmware/qcom/qcom_scm.c
+++ b/drivers/firmware/qcom/qcom_scm.c
@@ -1603,7 +1603,13 @@ bool qcom_scm_lmh_dcvsh_available(void)
 }
 EXPORT_SYMBOL_GPL(qcom_scm_lmh_dcvsh_available);
 
-int qcom_scm_shm_bridge_enable(void)
+/*
+ * This is only supposed to be called once by the TZMem module. It takes the
+ * SCM struct device as argument and uses it to pass the call as at the time
+ * the SHM Bridge is enabled, the SCM is not yet fully set up and doesn't
+ * accept global user calls. Don't try to use the __scm pointer here.
+ */
+int qcom_scm_shm_bridge_enable(struct device *scm_dev)
 {
 	int ret;
 
@@ -1615,11 +1621,11 @@ int qcom_scm_shm_bridge_enable(void)
 
 	struct qcom_scm_res res;
 
-	if (!__qcom_scm_is_call_available(__scm->dev, QCOM_SCM_SVC_MP,
+	if (!__qcom_scm_is_call_available(scm_dev, QCOM_SCM_SVC_MP,
 					  QCOM_SCM_MP_SHM_BRIDGE_ENABLE))
 		return -EOPNOTSUPP;
 
-	ret = qcom_scm_call(__scm->dev, &desc, &res);
+	ret = qcom_scm_call(scm_dev, &desc, &res);
 
 	if (ret)
 		return ret;
diff --git a/drivers/firmware/qcom/qcom_scm.h b/drivers/firmware/qcom/qcom_scm.h
index 3133d826f5fa..0e8dd838099e 100644
--- a/drivers/firmware/qcom/qcom_scm.h
+++ b/drivers/firmware/qcom/qcom_scm.h
@@ -83,6 +83,7 @@ int scm_legacy_call(struct device *dev, const struct qcom_scm_desc *desc,
 		    struct qcom_scm_res *res);
 
 struct qcom_tzmem_pool *qcom_scm_get_tzmem_pool(void);
+int qcom_scm_shm_bridge_enable(struct device *scm_dev);
 
 #define QCOM_SCM_SVC_BOOT		0x01
 #define QCOM_SCM_BOOT_SET_ADDR		0x01
diff --git a/drivers/firmware/qcom/qcom_tzmem.c b/drivers/firmware/qcom/qcom_tzmem.c
index 4fe333fd2f07..ea0a35355657 100644
--- a/drivers/firmware/qcom/qcom_tzmem.c
+++ b/drivers/firmware/qcom/qcom_tzmem.c
@@ -20,6 +20,7 @@
 #include <linux/spinlock.h>
 #include <linux/types.h>
 
+#include "qcom_scm.h"
 #include "qcom_tzmem.h"
 
 struct qcom_tzmem_area {
@@ -94,7 +95,7 @@ static int qcom_tzmem_init(void)
 			goto notsupp;
 	}
 
-	ret = qcom_scm_shm_bridge_enable();
+	ret = qcom_scm_shm_bridge_enable(qcom_tzmem_dev);
 	if (ret == -EOPNOTSUPP)
 		goto notsupp;
 
diff --git a/include/linux/firmware/qcom/qcom_scm.h b/include/linux/firmware/qcom/qcom_scm.h
index 82b1b8c50ca3..0f667bf1d4d9 100644
--- a/include/linux/firmware/qcom/qcom_scm.h
+++ b/include/linux/firmware/qcom/qcom_scm.h
@@ -148,7 +148,6 @@ bool qcom_scm_lmh_dcvsh_available(void);
 
 int qcom_scm_gpu_init_regs(u32 gpu_req);
 
-int qcom_scm_shm_bridge_enable(void);
 int qcom_scm_shm_bridge_create(u64 pfn_and_ns_perm_flags,
 			       u64 ipfn_and_s_perm_flags, u64 size_and_flags,
 			       u64 ns_vmids, u64 *handle);
-- 
cgit v1.2.3


From ddb8172cdf8854a215ce23ad0f20b2578fa512db Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Tue, 8 Jul 2025 16:33:44 +0300
Subject: watchdog: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Link: https://lore.kernel.org/r/20250708133646.70384-3-andriy.shevchenko@linux.intel.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Signed-off-by: Wim Van Sebroeck <wim@linux-watchdog.org>
---
 drivers/watchdog/watchdog_core.h       |  8 +++++++-
 drivers/watchdog/watchdog_pretimeout.c |  2 ++
 include/linux/watchdog.h               | 12 ++++++++----
 3 files changed, 17 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/watchdog/watchdog_core.h b/drivers/watchdog/watchdog_core.h
index 5b35a8439e26..ab825d9f9248 100644
--- a/drivers/watchdog/watchdog_core.h
+++ b/drivers/watchdog/watchdog_core.h
@@ -24,8 +24,14 @@
  *	This material is provided "AS-IS" and at no charge.
  */
 
-#include <linux/hrtimer.h>
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/hrtimer_types.h>
+#include <linux/init.h>
 #include <linux/kthread.h>
+#include <linux/mutex_types.h>
+#include <linux/types.h>
+#include <linux/watchdog.h>
 
 #define MAX_DOGS	32	/* Maximum number of watchdog devices */
 
diff --git a/drivers/watchdog/watchdog_pretimeout.c b/drivers/watchdog/watchdog_pretimeout.c
index e5295c990fa1..2526436dc74d 100644
--- a/drivers/watchdog/watchdog_pretimeout.c
+++ b/drivers/watchdog/watchdog_pretimeout.c
@@ -7,6 +7,8 @@
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/sysfs.h>
+#include <linux/types.h>
 #include <linux/watchdog.h>
 
 #include "watchdog_core.h"
diff --git a/include/linux/watchdog.h b/include/linux/watchdog.h
index 99660197a36c..8c60687a3e55 100644
--- a/include/linux/watchdog.h
+++ b/include/linux/watchdog.h
@@ -9,14 +9,18 @@
 #ifndef _LINUX_WATCHDOG_H
 #define _LINUX_WATCHDOG_H
 
-
 #include <linux/bitops.h>
-#include <linux/cdev.h>
-#include <linux/device.h>
-#include <linux/kernel.h>
+#include <linux/limits.h>
 #include <linux/notifier.h>
+#include <linux/printk.h>
+#include <linux/types.h>
+
 #include <uapi/linux/watchdog.h>
 
+struct attribute_group;
+struct device;
+struct module;
+
 struct watchdog_ops;
 struct watchdog_device;
 struct watchdog_core_data;
-- 
cgit v1.2.3


From b5cd5f1e50205831cb078f5c52359004eb1cbe74 Mon Sep 17 00:00:00 2001
From: Alok Tiwari <alok.a.tiwari@oracle.com>
Date: Tue, 24 Jun 2025 21:16:33 -0700
Subject: nvme: fix typo in status code constant for self-test in progress

Correct a typo error in the NVMe status code constant from
NVME_SC_SELT_TEST_IN_PROGRESS to NVME_SC_SELF_TEST_IN_PROGRESS to
accurately reflect its meaning.

Signed-off-by: Alok Tiwari <alok.a.tiwari@oracle.com>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Chaitanya Kulkarni <kch@nvidia.com>
Signed-off-by: Christoph Hellwig <hch@lst.de>
---
 drivers/nvme/host/constants.c | 4 ++--
 include/linux/nvme.h          | 2 +-
 2 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
index 1a0058be5821..dc90df9e13a2 100644
--- a/drivers/nvme/host/constants.c
+++ b/drivers/nvme/host/constants.c
@@ -133,7 +133,7 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_NS_NOT_ATTACHED] = "Namespace Not Attached",
 	[NVME_SC_THIN_PROV_NOT_SUPP] = "Thin Provisioning Not Supported",
 	[NVME_SC_CTRL_LIST_INVALID] = "Controller List Invalid",
-	[NVME_SC_SELT_TEST_IN_PROGRESS] = "Device Self-test In Progress",
+	[NVME_SC_SELF_TEST_IN_PROGRESS] = "Device Self-test In Progress",
 	[NVME_SC_BP_WRITE_PROHIBITED] = "Boot Partition Write Prohibited",
 	[NVME_SC_CTRL_ID_INVALID] = "Invalid Controller Identifier",
 	[NVME_SC_SEC_CTRL_STATE_INVALID] = "Invalid Secondary Controller State",
@@ -145,7 +145,7 @@ static const char * const nvme_statuses[] = {
 	[NVME_SC_BAD_ATTRIBUTES] = "Conflicting Attributes",
 	[NVME_SC_INVALID_PI] = "Invalid Protection Information",
 	[NVME_SC_READ_ONLY] = "Attempted Write to Read Only Range",
-	[NVME_SC_CMD_SIZE_LIM_EXCEEDED	] = "Command Size Limits Exceeded",
+	[NVME_SC_CMD_SIZE_LIM_EXCEEDED] = "Command Size Limits Exceeded",
 	[NVME_SC_ZONE_BOUNDARY_ERROR] = "Zoned Boundary Error",
 	[NVME_SC_ZONE_FULL] = "Zone Is Full",
 	[NVME_SC_ZONE_READ_ONLY] = "Zone Is Read Only",
diff --git a/include/linux/nvme.h b/include/linux/nvme.h
index b65a1b9f2116..655d194f8e72 100644
--- a/include/linux/nvme.h
+++ b/include/linux/nvme.h
@@ -2155,7 +2155,7 @@ enum {
 	NVME_SC_NS_NOT_ATTACHED		= 0x11a,
 	NVME_SC_THIN_PROV_NOT_SUPP	= 0x11b,
 	NVME_SC_CTRL_LIST_INVALID	= 0x11c,
-	NVME_SC_SELT_TEST_IN_PROGRESS	= 0x11d,
+	NVME_SC_SELF_TEST_IN_PROGRESS	= 0x11d,
 	NVME_SC_BP_WRITE_PROHIBITED	= 0x11e,
 	NVME_SC_CTRL_ID_INVALID		= 0x11f,
 	NVME_SC_SEC_CTRL_STATE_INVALID	= 0x120,
-- 
cgit v1.2.3


From 6381061d82141909c382811978ccdd7566698bca Mon Sep 17 00:00:00 2001
From: John Garry <john.g.garry@oracle.com>
Date: Fri, 11 Jul 2025 10:52:53 +0000
Subject: ilog2: add max_pow_of_two_factor()

Relocate the function max_pow_of_two_factor() to common ilog2.h from the
xfs code, as it will be used elsewhere.

Also simplify the function, as advised by Mikulas Patocka.

Signed-off-by: John Garry <john.g.garry@oracle.com>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
Link: https://lore.kernel.org/r/20250711105258.3135198-2-john.g.garry@oracle.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 fs/xfs/xfs_mount.c   |  5 -----
 include/linux/log2.h | 14 ++++++++++++++
 2 files changed, 14 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 29276fe60df9..6c669ae082d4 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -672,11 +672,6 @@ static inline xfs_extlen_t xfs_calc_atomic_write_max(struct xfs_mount *mp)
 	return rounddown_pow_of_two(XFS_B_TO_FSB(mp, MAX_RW_COUNT));
 }
 
-static inline unsigned int max_pow_of_two_factor(const unsigned int nr)
-{
-	return 1 << (ffs(nr) - 1);
-}
-
 /*
  * If the data device advertises atomic write support, limit the size of data
  * device atomic writes to the greatest power-of-two factor of the AG size so
diff --git a/include/linux/log2.h b/include/linux/log2.h
index 1366cb688a6d..2eac3fc9303d 100644
--- a/include/linux/log2.h
+++ b/include/linux/log2.h
@@ -255,4 +255,18 @@ int __bits_per(unsigned long n)
 	) :					\
 	__bits_per(n)				\
 )
+
+/**
+ * max_pow_of_two_factor - return highest power-of-2 factor
+ * @n: parameter
+ *
+ * find highest power-of-2 which is evenly divisible into n.
+ * 0 is returned for n == 0 or 1.
+ */
+static inline __attribute__((const))
+unsigned int max_pow_of_two_factor(unsigned int n)
+{
+	return n & -n;
+}
+
 #endif /* _LINUX_LOG2_H */
-- 
cgit v1.2.3


From dfe25fbaedfc2a07281ed5ff0442270217d25b31 Mon Sep 17 00:00:00 2001
From: Shakeel Butt <shakeel.butt@linux.dev>
Date: Fri, 4 Jul 2025 11:08:04 -0700
Subject: cgroup: llist: avoid memory tears for llist_node

Before the commit 36df6e3dbd7e ("cgroup: make css_rstat_updated nmi
safe"), the struct llist_node is expected to be private to the one
inserting the node to the lockless list or the one removing the node
from the lockless list. After the mentioned commit, the llist_node in
the rstat code is per-cpu shared between the stacked contexts i.e.
process, softirq, hardirq & nmi. It is possible the compiler may tear
the loads or stores of llist_node. Let's avoid that.

KCSAN reported the following race:

 Reported by Kernel Concurrency Sanitizer on:
 CPU: 60 UID: 0 PID: 5425 ... 6.16.0-rc3-next-20250626 #1 NONE
 Tainted: [E]=UNSIGNED_MODULE
 Hardware name: ...
 ==================================================================
 ==================================================================
 BUG: KCSAN: data-race in css_rstat_flush / css_rstat_updated
 write to 0xffffe8fffe1c85f0 of 8 bytes by task 1061 on cpu 1:
  css_rstat_flush+0x1b8/0xeb0
  __mem_cgroup_flush_stats+0x184/0x190
  flush_memcg_stats_dwork+0x22/0x50
  process_one_work+0x335/0x630
  worker_thread+0x5f1/0x8a0
  kthread+0x197/0x340
  ret_from_fork+0xd3/0x110
  ret_from_fork_asm+0x11/0x20
 read to 0xffffe8fffe1c85f0 of 8 bytes by task 3551 on cpu 15:
  css_rstat_updated+0x81/0x180
  mod_memcg_lruvec_state+0x113/0x2d0
  __mod_lruvec_state+0x3d/0x50
  lru_add+0x21e/0x3f0
  folio_batch_move_lru+0x80/0x1b0
  __folio_batch_add_and_move+0xd7/0x160
  folio_add_lru_vma+0x42/0x50
  do_anonymous_page+0x892/0xe90
  __handle_mm_fault+0xfaa/0x1520
  handle_mm_fault+0xdc/0x350
  do_user_addr_fault+0x1dc/0x650
  exc_page_fault+0x5c/0x110
  asm_exc_page_fault+0x22/0x30
 value changed: 0xffffe8fffe18e0d0 -> 0xffffe8fffe1c85f0

$ ./scripts/faddr2line vmlinux css_rstat_flush+0x1b8/0xeb0
css_rstat_flush+0x1b8/0xeb0:
init_llist_node at include/linux/llist.h:86
(inlined by) llist_del_first_init at include/linux/llist.h:308
(inlined by) css_process_update_tree at kernel/cgroup/rstat.c:148
(inlined by) css_rstat_updated_list at kernel/cgroup/rstat.c:258
(inlined by) css_rstat_flush at kernel/cgroup/rstat.c:389

$ ./scripts/faddr2line vmlinux css_rstat_updated+0x81/0x180
css_rstat_updated+0x81/0x180:
css_rstat_updated at kernel/cgroup/rstat.c:90 (discriminator 1)

These are expected race and a simple READ_ONCE/WRITE_ONCE resolves these
reports. However let's add comments to explain the race and the need for
memory barriers if stronger guarantees are needed.

More specifically the rstat updater and the flusher can race and cause a
scenario where the stats updater skips adding the css to the lockless
list but the flusher might not see those updates done by the skipped
updater. This is benign race and the subsequent flusher will flush those
stats and at the moment there aren't any rstat users which are not fine
with this kind of race. However some future user might want more
stricter guarantee, so let's add appropriate comments to ease the job of
future users.

Signed-off-by: Shakeel Butt <shakeel.butt@linux.dev>
Reviewed-by: Paul E. McKenney <paulmck@kernel.org>
Fixes: 36df6e3dbd7e ("cgroup: make css_rstat_updated nmi safe")
Signed-off-by: Tejun Heo <tj@kernel.org>
---
 include/linux/llist.h |  6 +++---
 kernel/cgroup/rstat.c | 28 +++++++++++++++++++++++++++-
 2 files changed, 30 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/llist.h b/include/linux/llist.h
index 27b17f64bcee..607b2360c938 100644
--- a/include/linux/llist.h
+++ b/include/linux/llist.h
@@ -83,7 +83,7 @@ static inline void init_llist_head(struct llist_head *list)
  */
 static inline void init_llist_node(struct llist_node *node)
 {
-	node->next = node;
+	WRITE_ONCE(node->next, node);
 }
 
 /**
@@ -97,7 +97,7 @@ static inline void init_llist_node(struct llist_node *node)
  */
 static inline bool llist_on_list(const struct llist_node *node)
 {
-	return node->next != node;
+	return READ_ONCE(node->next) != node;
 }
 
 /**
@@ -220,7 +220,7 @@ static inline bool llist_empty(const struct llist_head *head)
 
 static inline struct llist_node *llist_next(struct llist_node *node)
 {
-	return node->next;
+	return READ_ONCE(node->next);
 }
 
 /**
diff --git a/kernel/cgroup/rstat.c b/kernel/cgroup/rstat.c
index c8a48cf83878..981e2f77ad4e 100644
--- a/kernel/cgroup/rstat.c
+++ b/kernel/cgroup/rstat.c
@@ -60,6 +60,12 @@ static inline struct llist_head *ss_lhead_cpu(struct cgroup_subsys *ss, int cpu)
  * Atomically inserts the css in the ss's llist for the given cpu. This is
  * reentrant safe i.e. safe against softirq, hardirq and nmi. The ss's llist
  * will be processed at the flush time to create the update tree.
+ *
+ * NOTE: if the user needs the guarantee that the updater either add itself in
+ * the lockless list or the concurrent flusher flushes its updated stats, a
+ * memory barrier is needed before the call to css_rstat_updated() i.e. a
+ * barrier after updating the per-cpu stats and before calling
+ * css_rstat_updated().
  */
 __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 {
@@ -86,7 +92,12 @@ __bpf_kfunc void css_rstat_updated(struct cgroup_subsys_state *css, int cpu)
 		return;
 
 	rstatc = css_rstat_cpu(css, cpu);
-	/* If already on list return. */
+	/*
+	 * If already on list return. This check is racy and smp_mb() is needed
+	 * to pair it with the smp_mb() in css_process_update_tree() if the
+	 * guarantee that the updated stats are visible to concurrent flusher is
+	 * needed.
+	 */
 	if (llist_on_list(&rstatc->lnode))
 		return;
 
@@ -148,6 +159,21 @@ static void css_process_update_tree(struct cgroup_subsys *ss, int cpu)
 	while ((lnode = llist_del_first_init(lhead))) {
 		struct css_rstat_cpu *rstatc;
 
+		/*
+		 * smp_mb() is needed here (more specifically in between
+		 * init_llist_node() and per-cpu stats flushing) if the
+		 * guarantee is required by a rstat user where etiher the
+		 * updater should add itself on the lockless list or the
+		 * flusher flush the stats updated by the updater who have
+		 * observed that they are already on the list. The
+		 * corresponding barrier pair for this one should be before
+		 * css_rstat_updated() by the user.
+		 *
+		 * For now, there aren't any such user, so not adding the
+		 * barrier here but if such a use-case arise, please add
+		 * smp_mb() here.
+		 */
+
 		rstatc = container_of(lnode, struct css_rstat_cpu, lnode);
 		__css_process_update_tree(rstatc->owner, cpu);
 	}
-- 
cgit v1.2.3


From fc6f89dc707838564abbb8e22dad8e4d75c7fa26 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Tue, 8 Jul 2025 15:47:29 -0700
Subject: stop_machine: Improve kernel-doc function-header comments

Add more detail to the kernel-doc function-header comments for
stop_machine(), stop_machine_cpuslocked(), and stop_core_cpuslocked().

Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
---
 include/linux/stop_machine.h | 64 ++++++++++++++++++++++++++++----------------
 1 file changed, 41 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/stop_machine.h b/include/linux/stop_machine.h
index 3132262a404d..72820503514c 100644
--- a/include/linux/stop_machine.h
+++ b/include/linux/stop_machine.h
@@ -88,55 +88,73 @@ static inline void print_stop_info(const char *log_lvl, struct task_struct *task
 #endif	/* CONFIG_SMP */
 
 /*
- * stop_machine "Bogolock": stop the entire machine, disable
- * interrupts.  This is a very heavy lock, which is equivalent to
- * grabbing every spinlock (and more).  So the "read" side to such a
- * lock is anything which disables preemption.
+ * stop_machine "Bogolock": stop the entire machine, disable interrupts.
+ * This is a very heavy lock, which is equivalent to grabbing every raw
+ * spinlock (and more).  So the "read" side to such a lock is anything
+ * which disables preemption.
  */
 #if defined(CONFIG_SMP) || defined(CONFIG_HOTPLUG_CPU)
 
 /**
  * stop_machine: freeze the machine on all CPUs and run this function
  * @fn: the function to run
- * @data: the data ptr for the @fn()
- * @cpus: the cpus to run the @fn() on (NULL = any online cpu)
+ * @data: the data ptr to pass to @fn()
+ * @cpus: the cpus to run @fn() on (NULL = run on each online CPU)
  *
- * Description: This causes a thread to be scheduled on every cpu,
- * each of which disables interrupts.  The result is that no one is
- * holding a spinlock or inside any other preempt-disabled region when
- * @fn() runs.
+ * Description: This causes a thread to be scheduled on every CPU, which
+ * will run with interrupts disabled.  Each CPU specified by @cpus will
+ * run @fn.  While @fn is executing, there will no other CPUs holding
+ * a raw spinlock or running within any other type of preempt-disabled
+ * region of code.
  *
- * This can be thought of as a very heavy write lock, equivalent to
- * grabbing every spinlock in the kernel.
+ * When @cpus specifies only a single CPU, this can be thought of as
+ * a reader-writer lock where readers disable preemption (for example,
+ * by holding a raw spinlock) and where the insanely heavy writers run
+ * @fn while also preventing any other CPU from doing any useful work.
+ * These writers can also be thought of as having implicitly grabbed every
+ * raw spinlock in the kernel.
  *
- * Protects against CPU hotplug.
+ * When @fn is a no-op, this can be thought of as an RCU implementation
+ * where readers again disable preemption and writers use stop_machine()
+ * in place of synchronize_rcu(), albeit with orders of magnitude more
+ * disruption than even that of synchronize_rcu_expedited().
+ *
+ * Although only one stop_machine() operation can proceed at a time,
+ * the possibility of blocking in cpus_read_lock() means that the caller
+ * cannot usefully rely on this serialization.
+ *
+ * Return: 0 if all invocations of @fn return zero.  Otherwise, the
+ * value returned by an arbitrarily chosen member of the set of calls to
+ * @fn that returned non-zero.
  */
 int stop_machine(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
 /**
  * stop_machine_cpuslocked: freeze the machine on all CPUs and run this function
  * @fn: the function to run
- * @data: the data ptr for the @fn()
- * @cpus: the cpus to run the @fn() on (NULL = any online cpu)
+ * @data: the data ptr to pass to @fn()
+ * @cpus: the cpus to run @fn() on (NULL = run on each online CPU)
+ *
+ * Same as above.  Avoids nested calls to cpus_read_lock().
  *
- * Same as above. Must be called from with in a cpus_read_lock() protected
- * region. Avoids nested calls to cpus_read_lock().
+ * Context: Must be called from within a cpus_read_lock() protected region.
  */
 int stop_machine_cpuslocked(cpu_stop_fn_t fn, void *data, const struct cpumask *cpus);
 
 /**
  * stop_core_cpuslocked: - stop all threads on just one core
  * @cpu: any cpu in the targeted core
- * @fn: the function to run
- * @data: the data ptr for @fn()
+ * @fn: the function to run on each CPU in the core containing @cpu
+ * @data: the data ptr to pass to @fn()
  *
- * Same as above, but instead of every CPU, only the logical CPUs of a
- * single core are affected.
+ * Same as above, but instead of every CPU, only the logical CPUs of the
+ * single core containing @cpu are affected.
  *
  * Context: Must be called from within a cpus_read_lock() protected region.
  *
- * Return: 0 if all executions of @fn returned 0, any non zero return
- * value if any returned non zero.
+ * Return: 0 if all invocations of @fn return zero.  Otherwise, the
+ * value returned by an arbitrarily chosen member of the set of calls to
+ * @fn that returned non-zero.
  */
 int stop_core_cpuslocked(unsigned int cpu, cpu_stop_fn_t fn, void *data);
 
-- 
cgit v1.2.3


From 76720eed7d18baf51c0f31fe8a3784702f50e3fc Mon Sep 17 00:00:00 2001
From: Mario Limonciello <mario.limonciello@amd.com>
Date: Thu, 17 Jul 2025 12:38:04 -0500
Subject: PCI: Add pci_is_display() to check if device is a display controller

Several places in the kernel do class shifting to match whether a PCI
device is display class.  Add pci_is_display() for those places to use.

Signed-off-by: Mario Limonciello <mario.limonciello@amd.com>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Reviewed-by: Daniel Dadap <ddadap@nvidia.com>
Reviewed-by: Simona Vetter <simona.vetter@ffwll.ch>
Link: https://patch.msgid.link/20250717173812.3633478-2-superm1@kernel.org
---
 include/linux/pci.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/pci.h b/include/linux/pci.h
index 05e68f35f392..4fff6405a830 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -744,6 +744,21 @@ static inline bool pci_is_vga(struct pci_dev *pdev)
 	return false;
 }
 
+/**
+ * pci_is_display - check if the PCI device is a display controller
+ * @pdev: PCI device
+ *
+ * Determine whether the given PCI device corresponds to a display
+ * controller. Display controllers are typically used for graphical output
+ * and are identified based on their class code.
+ *
+ * Return: true if the PCI device is a display controller, false otherwise.
+ */
+static inline bool pci_is_display(struct pci_dev *pdev)
+{
+	return (pdev->class >> 16) == PCI_BASE_CLASS_DISPLAY;
+}
+
 #define for_each_pci_bridge(dev, bus)				\
 	list_for_each_entry(dev, &bus->devices, bus_list)	\
 		if (!pci_is_bridge(dev)) {} else
-- 
cgit v1.2.3


From 2d8ae9a4f1bc04a118e3d438ac50dd49281b34fd Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 11 Jul 2025 11:55:14 +0300
Subject: string: Group str_has_prefix() and strstarts()

The two str_has_prefix() and strstarts() are about the same
with a slight difference on what they return. Group them in
the header.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250711085514.1294428-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/string.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/string.h b/include/linux/string.h
index 01621ad0f598..fdd3442c6bcb 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -345,16 +345,6 @@ extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
 
 int ptr_to_hashval(const void *ptr, unsigned long *hashval_out);
 
-/**
- * strstarts - does @str start with @prefix?
- * @str: string to examine
- * @prefix: prefix to look for.
- */
-static inline bool strstarts(const char *str, const char *prefix)
-{
-	return strncmp(str, prefix, strlen(prefix)) == 0;
-}
-
 size_t memweight(const void *ptr, size_t bytes);
 
 /**
@@ -562,4 +552,14 @@ static __always_inline size_t str_has_prefix(const char *str, const char *prefix
 	return strncmp(str, prefix, len) == 0 ? len : 0;
 }
 
+/**
+ * strstarts - does @str start with @prefix?
+ * @str: string to examine
+ * @prefix: prefix to look for.
+ */
+static inline bool strstarts(const char *str, const char *prefix)
+{
+	return strncmp(str, prefix, strlen(prefix)) == 0;
+}
+
 #endif /* _LINUX_STRING_H_ */
-- 
cgit v1.2.3


From b2df55a98672f4be076ff69d0f0d0b1fc81f2044 Mon Sep 17 00:00:00 2001
From: Dan Williams <dan.j.williams@intel.com>
Date: Thu, 17 Jul 2025 09:30:36 -0700
Subject: cleanup: Fix documentation build error for ACQUIRE updates

Stephen reports:

Documentation/core-api/cleanup:7: include/linux/cleanup.h:73: ERROR: Unexpected indentation. [docutils]
Documentation/core-api/cleanup:7: include/linux/cleanup.h:74: WARNING: Block quote ends without a blank line; unexpected unindent. [docutils]

Which points out that the ACQUIRE() example in cleanup.h missed the "::"
suffix to mark the following text as a code-block.

Fixes: 857d18f23ab1 ("cleanup: Introduce ACQUIRE() and ACQUIRE_ERR() for conditional locks")
Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: http://lore.kernel.org/20250717173354.34375751@canb.auug.org.au
Signed-off-by: Dan Williams <dan.j.williams@intel.com>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Link: https://patch.msgid.link/20250717163036.1275791-1-dan.j.williams@intel.com
Signed-off-by: Dave Jiang <dave.jiang@intel.com>
---
 include/linux/cleanup.h | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cleanup.h b/include/linux/cleanup.h
index 4eb83dd71cfe..0fb796db4811 100644
--- a/include/linux/cleanup.h
+++ b/include/linux/cleanup.h
@@ -64,8 +64,7 @@
  * the remainder of "func()".
  *
  * The ACQUIRE() macro can be used in all places that guard() can be
- * used and additionally support conditional locks
- *
+ * used and additionally support conditional locks::
  *
  *	DEFINE_GUARD_COND(pci_dev, _try, pci_dev_trylock(_T))
  *	...
-- 
cgit v1.2.3


From 4e301d858af17ae2ce56886296e5458c5a08219a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Sat, 7 Jun 2025 13:53:03 +0200
Subject: fs: constify file ptr in backing_file accessor helpers

Add internal helper backing_file_set_user_path() for the only
two cases that need to modify backing_file fields.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Link: https://lore.kernel.org/20250607115304.2521155-2-amir73il@gmail.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 fs/backing-file.c  |  4 ++--
 fs/file_table.c    | 13 ++++++++-----
 fs/internal.h      |  1 +
 include/linux/fs.h |  6 +++---
 4 files changed, 14 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/backing-file.c b/fs/backing-file.c
index 763fbe9b72b2..8c7396bff121 100644
--- a/fs/backing-file.c
+++ b/fs/backing-file.c
@@ -41,7 +41,7 @@ struct file *backing_file_open(const struct path *user_path, int flags,
 		return f;
 
 	path_get(user_path);
-	*backing_file_user_path(f) = *user_path;
+	backing_file_set_user_path(f, user_path);
 	error = vfs_open(real_path, f);
 	if (error) {
 		fput(f);
@@ -65,7 +65,7 @@ struct file *backing_tmpfile_open(const struct path *user_path, int flags,
 		return f;
 
 	path_get(user_path);
-	*backing_file_user_path(f) = *user_path;
+	backing_file_set_user_path(f, user_path);
 	error = vfs_tmpfile(real_idmap, real_parentpath, f, mode);
 	if (error) {
 		fput(f);
diff --git a/fs/file_table.c b/fs/file_table.c
index 138114d64307..f09d79a98111 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -52,17 +52,20 @@ struct backing_file {
 	};
 };
 
-static inline struct backing_file *backing_file(struct file *f)
-{
-	return container_of(f, struct backing_file, file);
-}
+#define backing_file(f) container_of(f, struct backing_file, file)
 
-struct path *backing_file_user_path(struct file *f)
+struct path *backing_file_user_path(const struct file *f)
 {
 	return &backing_file(f)->user_path;
 }
 EXPORT_SYMBOL_GPL(backing_file_user_path);
 
+void backing_file_set_user_path(struct file *f, const struct path *path)
+{
+	backing_file(f)->user_path = *path;
+}
+EXPORT_SYMBOL_GPL(backing_file_set_user_path);
+
 static inline void file_free(struct file *f)
 {
 	security_file_free(f);
diff --git a/fs/internal.h b/fs/internal.h
index 393f6c5c24f6..d733d8bb3d1f 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -101,6 +101,7 @@ extern void chroot_fs_refs(const struct path *, const struct path *);
 struct file *alloc_empty_file(int flags, const struct cred *cred);
 struct file *alloc_empty_file_noaccount(int flags, const struct cred *cred);
 struct file *alloc_empty_backing_file(int flags, const struct cred *cred);
+void backing_file_set_user_path(struct file *f, const struct path *path);
 
 static inline void file_put_write_access(struct file *file)
 {
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 1d9586a78041..8116b1080457 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -2864,7 +2864,7 @@ struct file *dentry_open_nonotify(const struct path *path, int flags,
 				  const struct cred *cred);
 struct file *dentry_create(const struct path *path, int flags, umode_t mode,
 			   const struct cred *cred);
-struct path *backing_file_user_path(struct file *f);
+struct path *backing_file_user_path(const struct file *f);
 
 /*
  * When mmapping a file on a stackable filesystem (e.g., overlayfs), the file
@@ -2876,14 +2876,14 @@ struct path *backing_file_user_path(struct file *f);
  * by fstat() on that same fd.
  */
 /* Get the path to display in /proc/<pid>/maps */
-static inline const struct path *file_user_path(struct file *f)
+static inline const struct path *file_user_path(const struct file *f)
 {
 	if (unlikely(f->f_mode & FMODE_BACKING))
 		return backing_file_user_path(f);
 	return &f->f_path;
 }
 /* Get the inode whose inode number to display in /proc/<pid>/maps */
-static inline const struct inode *file_user_inode(struct file *f)
+static inline const struct inode *file_user_inode(const struct file *f)
 {
 	if (unlikely(f->f_mode & FMODE_BACKING))
 		return d_inode(backing_file_user_path(f)->dentry);
-- 
cgit v1.2.3


From 380b84e168e57c54d0a9e053a5558fddc43f0c1a Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Date: Tue, 1 Jul 2025 10:58:05 +0200
Subject: vdso/vsyscall: Update auxiliary clock data in the datapage
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Expose the auxiliary clock data so it can be read from the vDSO.

Architectures not using the generic vDSO time framework,
namely SPARC64, are not supported.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/20250701-vdso-auxclock-v1-11-df7d9f87b9b8@linutronix.de
---
 include/linux/timekeeper_internal.h |  6 ++++++
 include/vdso/datapage.h             |  3 +++
 kernel/time/namespace.c             |  5 +++++
 kernel/time/timekeeping.c           | 12 +++++++++++
 kernel/time/vsyscall.c              | 40 +++++++++++++++++++++++++++++++++++++
 5 files changed, 66 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/timekeeper_internal.h b/include/linux/timekeeper_internal.h
index ca79938b62f3..c27aac67cb3f 100644
--- a/include/linux/timekeeper_internal.h
+++ b/include/linux/timekeeper_internal.h
@@ -190,4 +190,10 @@ static inline void update_vsyscall_tz(void)
 }
 #endif
 
+#if defined(CONFIG_GENERIC_GETTIMEOFDAY) && defined(CONFIG_POSIX_AUX_CLOCKS)
+extern void vdso_time_update_aux(struct timekeeper *tk);
+#else
+static inline void vdso_time_update_aux(struct timekeeper *tk) { }
+#endif
+
 #endif /* _LINUX_TIMEKEEPER_INTERNAL_H */
diff --git a/include/vdso/datapage.h b/include/vdso/datapage.h
index 1864e76e8f69..f4c96d9ce674 100644
--- a/include/vdso/datapage.h
+++ b/include/vdso/datapage.h
@@ -38,6 +38,7 @@ struct vdso_arch_data {
 #endif
 
 #define VDSO_BASES	(CLOCK_TAI + 1)
+#define VDSO_BASE_AUX	0
 #define VDSO_HRES	(BIT(CLOCK_REALTIME)		| \
 			 BIT(CLOCK_MONOTONIC)		| \
 			 BIT(CLOCK_BOOTTIME)		| \
@@ -117,6 +118,7 @@ struct vdso_clock {
  * @arch_data:		architecture specific data (optional, defaults
  *			to an empty struct)
  * @clock_data:		clocksource related data (array)
+ * @aux_clock_data:	auxiliary clocksource related data (array)
  * @tz_minuteswest:	minutes west of Greenwich
  * @tz_dsttime:		type of DST correction
  * @hrtimer_res:	hrtimer resolution
@@ -133,6 +135,7 @@ struct vdso_time_data {
 	struct arch_vdso_time_data	arch_data;
 
 	struct vdso_clock		clock_data[CS_BASES];
+	struct vdso_clock		aux_clock_data[MAX_AUX_CLOCKS];
 
 	s32				tz_minuteswest;
 	s32				tz_dsttime;
diff --git a/kernel/time/namespace.c b/kernel/time/namespace.c
index e3642278df43..667452768ed3 100644
--- a/kernel/time/namespace.c
+++ b/kernel/time/namespace.c
@@ -242,6 +242,11 @@ static void timens_set_vvar_page(struct task_struct *task,
 	for (i = 0; i < CS_BASES; i++)
 		timens_setup_vdso_clock_data(&vc[i], ns);
 
+	if (IS_ENABLED(CONFIG_POSIX_AUX_CLOCKS)) {
+		for (i = 0; i < ARRAY_SIZE(vdata->aux_clock_data); i++)
+			timens_setup_vdso_clock_data(&vdata->aux_clock_data[i], ns);
+	}
+
 out:
 	mutex_unlock(&offset_lock);
 }
diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
index cbcf090bb4be..243fe25e680a 100644
--- a/kernel/time/timekeeping.c
+++ b/kernel/time/timekeeping.c
@@ -66,11 +66,21 @@ static inline bool tk_get_aux_ts64(unsigned int tkid, struct timespec64 *ts)
 {
 	return ktime_get_aux_ts64(CLOCK_AUX + tkid - TIMEKEEPER_AUX_FIRST, ts);
 }
+
+static inline bool tk_is_aux(const struct timekeeper *tk)
+{
+	return tk->id >= TIMEKEEPER_AUX_FIRST && tk->id <= TIMEKEEPER_AUX_LAST;
+}
 #else
 static inline bool tk_get_aux_ts64(unsigned int tkid, struct timespec64 *ts)
 {
 	return false;
 }
+
+static inline bool tk_is_aux(const struct timekeeper *tk)
+{
+	return false;
+}
 #endif
 
 /* flag for if timekeeping is suspended */
@@ -719,6 +729,8 @@ static void timekeeping_update_from_shadow(struct tk_data *tkd, unsigned int act
 
 		update_fast_timekeeper(&tk->tkr_mono, &tk_fast_mono);
 		update_fast_timekeeper(&tk->tkr_raw,  &tk_fast_raw);
+	} else if (tk_is_aux(tk)) {
+		vdso_time_update_aux(tk);
 	}
 
 	if (action & TK_CLOCK_WAS_SET)
diff --git a/kernel/time/vsyscall.c b/kernel/time/vsyscall.c
index df6bada2d58e..8ba8b0d8a387 100644
--- a/kernel/time/vsyscall.c
+++ b/kernel/time/vsyscall.c
@@ -136,6 +136,46 @@ void update_vsyscall_tz(void)
 	__arch_sync_vdso_time_data(vdata);
 }
 
+#ifdef CONFIG_POSIX_AUX_CLOCKS
+void vdso_time_update_aux(struct timekeeper *tk)
+{
+	struct vdso_time_data *vdata = vdso_k_time_data;
+	struct vdso_timestamp *vdso_ts;
+	struct vdso_clock *vc;
+	s32 clock_mode;
+	u64 nsec;
+
+	vc = &vdata->aux_clock_data[tk->id - TIMEKEEPER_AUX_FIRST];
+	vdso_ts = &vc->basetime[VDSO_BASE_AUX];
+	clock_mode = tk->tkr_mono.clock->vdso_clock_mode;
+	if (!tk->clock_valid)
+		clock_mode = VDSO_CLOCKMODE_NONE;
+
+	/* copy vsyscall data */
+	vdso_write_begin_clock(vc);
+
+	vc->clock_mode = clock_mode;
+
+	if (clock_mode != VDSO_CLOCKMODE_NONE) {
+		fill_clock_configuration(vc, &tk->tkr_mono);
+
+		vdso_ts->sec	= tk->xtime_sec;
+
+		nsec = tk->tkr_mono.xtime_nsec >> tk->tkr_mono.shift;
+		nsec += tk->offs_aux;
+		vdso_ts->sec += __iter_div_u64_rem(nsec, NSEC_PER_SEC, &nsec);
+		nsec = nsec << tk->tkr_mono.shift;
+		vdso_ts->nsec = nsec;
+	}
+
+	__arch_update_vdso_clock(vc);
+
+	vdso_write_end_clock(vc);
+
+	__arch_sync_vdso_time_data(vdata);
+}
+#endif
+
 /**
  * vdso_update_begin - Start of a VDSO update section
  *
-- 
cgit v1.2.3


From 78e50d88998a4a634eeda3e0d136cb8b9c9bc9d8 Mon Sep 17 00:00:00 2001
From: Fabio Estevam <festevam@gmail.com>
Date: Sat, 12 Jul 2025 18:53:07 -0300
Subject: wifi: brcmfmac: Add support for the SDIO 43751 device

Add the SDIO ID and firmware matching for the 43751 device.

Based on the previous work from Marc Gonzalez <mgonzalez@freebox.fr>.

Tested on an i.MX6DL board connected to an AP6398SV chip with the
brcmfmac43752-sdio.bin firmware taken from:

https://source.puri.sm/Librem5/firmware-brcm43752-nonfree

Signed-off-by: Fabio Estevam <festevam@gmail.com>
Acked-by: Arend van Spriel <arend.vanspriel@broadcom.com>>
Link: https://patch.msgid.link/20250712215307.1310802-1-festevam@gmail.com
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
---
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c     | 1 +
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c       | 2 ++
 drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c       | 5 ++++-
 drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h | 1 +
 include/linux/mmc/sdio_ids.h                                  | 1 +
 5 files changed, 9 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
index 6bc107476a2a..8ab7d1e34a6e 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/bcmsdh.c
@@ -996,6 +996,7 @@ static const struct sdio_device_id brcmf_sdmmc_ids[] = {
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4354, WCC),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4356, WCC),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_4359, WCC),
+	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_43751, WCC),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373, CYW),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_43012, CYW),
 	BRCMF_SDIO_DEVICE(SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752, CYW),
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
index 2ef92ef25517..9074ab49e806 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/chip.c
@@ -739,6 +739,7 @@ static u32 brcmf_chip_tcm_rambase(struct brcmf_chip_priv *ci)
 	case CY_CC_4373_CHIP_ID:
 		return 0x160000;
 	case CY_CC_43752_CHIP_ID:
+	case BRCM_CC_43751_CHIP_ID:
 	case BRCM_CC_4377_CHIP_ID:
 		return 0x170000;
 	case BRCM_CC_4378_CHIP_ID:
@@ -1450,6 +1451,7 @@ bool brcmf_chip_sr_capable(struct brcmf_chip *pub)
 		reg = chip->ops->read32(chip->ctx, addr);
 		return (reg & CC_SR_CTL0_ENABLE_MASK) != 0;
 	case BRCM_CC_4359_CHIP_ID:
+	case BRCM_CC_43751_CHIP_ID:
 	case CY_CC_43752_CHIP_ID:
 	case CY_CC_43012_CHIP_ID:
 		addr = CORE_CC_REG(pmu->base, retention_ctl);
diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
index cf26ab15ee0c..8a0bad5119a0 100644
--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
+++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/sdio.c
@@ -654,6 +654,7 @@ static const struct brcmf_firmware_mapping brcmf_sdio_fwnames[] = {
 	BRCMF_FW_ENTRY(BRCM_CC_4354_CHIP_ID, 0xFFFFFFFF, 4354),
 	BRCMF_FW_ENTRY(BRCM_CC_4356_CHIP_ID, 0xFFFFFFFF, 4356),
 	BRCMF_FW_ENTRY(BRCM_CC_4359_CHIP_ID, 0xFFFFFFFF, 4359),
+	BRCMF_FW_ENTRY(BRCM_CC_43751_CHIP_ID, 0xFFFFFFFF, 43752),
 	BRCMF_FW_ENTRY(CY_CC_4373_CHIP_ID, 0xFFFFFFFF, 4373),
 	BRCMF_FW_ENTRY(CY_CC_43012_CHIP_ID, 0xFFFFFFFF, 43012),
 	BRCMF_FW_ENTRY(CY_CC_43439_CHIP_ID, 0xFFFFFFFF, 43439),
@@ -3424,7 +3425,8 @@ err:
 
 static bool brcmf_sdio_aos_no_decode(struct brcmf_sdio *bus)
 {
-	if (bus->ci->chip == CY_CC_43012_CHIP_ID ||
+	if (bus->ci->chip == BRCM_CC_43751_CHIP_ID ||
+	    bus->ci->chip == CY_CC_43012_CHIP_ID ||
 	    bus->ci->chip == CY_CC_43752_CHIP_ID)
 		return true;
 	else
@@ -4275,6 +4277,7 @@ static void brcmf_sdio_firmware_callback(struct device *dev, int err,
 				   bus->hostintmask, NULL);
 
 		switch (sdiod->func1->device) {
+		case SDIO_DEVICE_ID_BROADCOM_43751:
 		case SDIO_DEVICE_ID_BROADCOM_CYPRESS_4373:
 		case SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752:
 			brcmf_dbg(INFO, "set F2 watermark to 0x%x*4 bytes\n",
diff --git a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
index c1e22c589d85..6564616a57df 100644
--- a/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
+++ b/drivers/net/wireless/broadcom/brcm80211/include/brcm_hw_ids.h
@@ -52,6 +52,7 @@
 #define BRCM_CC_43664_CHIP_ID		43664
 #define BRCM_CC_43666_CHIP_ID		43666
 #define BRCM_CC_4371_CHIP_ID		0x4371
+#define BRCM_CC_43751_CHIP_ID		43751
 #define BRCM_CC_43752_CHIP_ID		43752
 #define BRCM_CC_4377_CHIP_ID		0x4377
 #define BRCM_CC_4378_CHIP_ID		0x4378
diff --git a/include/linux/mmc/sdio_ids.h b/include/linux/mmc/sdio_ids.h
index 7cddfdac2f57..fe3d6d98f8da 100644
--- a/include/linux/mmc/sdio_ids.h
+++ b/include/linux/mmc/sdio_ids.h
@@ -76,6 +76,7 @@
 #define SDIO_DEVICE_ID_BROADCOM_43430		0xa9a6
 #define SDIO_DEVICE_ID_BROADCOM_43439		0xa9af
 #define SDIO_DEVICE_ID_BROADCOM_43455		0xa9bf
+#define SDIO_DEVICE_ID_BROADCOM_43751		0xaae7
 #define SDIO_DEVICE_ID_BROADCOM_CYPRESS_43752	0xaae8
 
 #define SDIO_VENDOR_ID_CYPRESS			0x04b4
-- 
cgit v1.2.3


From 733c43f1df34f9185b945e6f12ac00c8556c6dfe Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Tue, 8 Jul 2025 14:22:10 -0600
Subject: io_uring/cmd: introduce IORING_URING_CMD_REISSUE flag

Add a flag IORING_URING_CMD_REISSUE that ->uring_cmd() implementations
can use to tell whether this is the first or subsequent issue of the
uring_cmd. This will allow ->uring_cmd() implementations to store
information in the io_uring_cmd's pdu across issues.

Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Acked-by: David Sterba <dsterba@suse.com>
Link: https://lore.kernel.org/r/20250708202212.2851548-3-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring/cmd.h | 2 ++
 io_uring/uring_cmd.c         | 6 +++++-
 2 files changed, 7 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 53408124c1e5..29892f54e0ac 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -8,6 +8,8 @@
 
 /* only top 8 bits of sqe->uring_cmd_flags for kernel internal use */
 #define IORING_URING_CMD_CANCELABLE	(1U << 30)
+/* io_uring_cmd is being issued again */
+#define IORING_URING_CMD_REISSUE	(1U << 31)
 
 struct io_uring_cmd {
 	struct file	*file;
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index b228b84a510f..58964a2f8582 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -261,7 +261,11 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
 	}
 
 	ret = file->f_op->uring_cmd(ioucmd, issue_flags);
-	if (ret == -EAGAIN || ret == -EIOCBQUEUED)
+	if (ret == -EAGAIN) {
+		ioucmd->flags |= IORING_URING_CMD_REISSUE;
+		return ret;
+	}
+	if (ret == -EIOCBQUEUED)
 		return ret;
 	if (ret < 0)
 		req_set_fail(req);
-- 
cgit v1.2.3


From 2e6dbb25ea15844c8b617260d635731c37c85ac9 Mon Sep 17 00:00:00 2001
From: Caleb Sander Mateos <csander@purestorage.com>
Date: Tue, 8 Jul 2025 14:22:12 -0600
Subject: io_uring/cmd: remove struct io_uring_cmd_data

There are no more users of struct io_uring_cmd_data and its op_data
field. Remove it to shave 8 bytes from struct io_async_cmd and eliminate
a store and load for every uring_cmd.

Signed-off-by: Caleb Sander Mateos <csander@purestorage.com>
Acked-by: David Sterba <dsterba@suse.com>
Link: https://lore.kernel.org/r/20250708202212.2851548-5-csander@purestorage.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/io_uring/cmd.h |  9 ---------
 io_uring/uring_cmd.c         | 12 +-----------
 io_uring/uring_cmd.h         |  1 -
 3 files changed, 1 insertion(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/io_uring/cmd.h b/include/linux/io_uring/cmd.h
index 29892f54e0ac..cfa6d0c0c322 100644
--- a/include/linux/io_uring/cmd.h
+++ b/include/linux/io_uring/cmd.h
@@ -21,10 +21,6 @@ struct io_uring_cmd {
 	u8		pdu[32]; /* available inline for free use */
 };
 
-struct io_uring_cmd_data {
-	void			*op_data;
-};
-
 static inline const void *io_uring_sqe_cmd(const struct io_uring_sqe *sqe)
 {
 	return sqe->cmd;
@@ -137,11 +133,6 @@ static inline struct task_struct *io_uring_cmd_get_task(struct io_uring_cmd *cmd
 	return cmd_to_io_kiocb(cmd)->tctx->task;
 }
 
-static inline struct io_uring_cmd_data *io_uring_cmd_get_async_data(struct io_uring_cmd *cmd)
-{
-	return cmd_to_io_kiocb(cmd)->async_data;
-}
-
 /*
  * Return uring_cmd's context reference as its context handle for driver to
  * track per-context resource, such as registered kernel IO buffer
diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
index 58964a2f8582..053bac89b6c0 100644
--- a/io_uring/uring_cmd.c
+++ b/io_uring/uring_cmd.c
@@ -26,12 +26,6 @@ static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
 {
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
 	struct io_async_cmd *ac = req->async_data;
-	struct io_uring_cmd_data *cache = &ac->data;
-
-	if (cache->op_data) {
-		kfree(cache->op_data);
-		cache->op_data = NULL;
-	}
 
 	if (issue_flags & IO_URING_F_UNLOCKED)
 		return;
@@ -40,7 +34,7 @@ static void io_req_uring_cleanup(struct io_kiocb *req, unsigned int issue_flags)
 	if (ac->vec.nr > IO_VEC_CACHE_SOFT_CAP)
 		io_vec_free(&ac->vec);
 
-	if (io_alloc_cache_put(&req->ctx->cmd_cache, cache)) {
+	if (io_alloc_cache_put(&req->ctx->cmd_cache, ac)) {
 		ioucmd->sqe = NULL;
 		req->async_data = NULL;
 		req->flags &= ~(REQ_F_ASYNC_DATA|REQ_F_NEED_CLEANUP);
@@ -193,9 +187,6 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	struct io_uring_cmd *ioucmd = io_kiocb_to_cmd(req, struct io_uring_cmd);
 	struct io_async_cmd *ac;
 
-	/* see io_uring_cmd_get_async_data() */
-	BUILD_BUG_ON(offsetof(struct io_async_cmd, data) != 0);
-
 	if (sqe->__pad1)
 		return -EINVAL;
 
@@ -211,7 +202,6 @@ int io_uring_cmd_prep(struct io_kiocb *req, const struct io_uring_sqe *sqe)
 	ac = io_uring_alloc_async_data(&req->ctx->cmd_cache, req);
 	if (!ac)
 		return -ENOMEM;
-	ac->data.op_data = NULL;
 	ioucmd->sqe = sqe;
 	return 0;
 }
diff --git a/io_uring/uring_cmd.h b/io_uring/uring_cmd.h
index 9e11da10ecab..041aef8a8aa3 100644
--- a/io_uring/uring_cmd.h
+++ b/io_uring/uring_cmd.h
@@ -4,7 +4,6 @@
 #include <linux/io_uring_types.h>
 
 struct io_async_cmd {
-	struct io_uring_cmd_data	data;
 	struct iou_vec			vec;
 	struct io_uring_sqe		sqes[2];
 };
-- 
cgit v1.2.3


From 850f14f5b91986e586b66565c9c75bdd4c834571 Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@linux.intel.com>
Date: Wed, 16 Jul 2025 15:03:45 +0800
Subject: iommufd: Destroy vdevice on idevice destroy

Destroy iommufd_vdevice (vdev) on iommufd_idevice (idev) destruction so
that vdev can't outlive idev.

idev represents the physical device bound to iommufd, while the vdev
represents the virtual instance of the physical device in the VM. The
lifecycle of the vdev should not be longer than idev. This doesn't
cause real problem on existing use cases cause vdev doesn't impact the
physical device, only provides virtualization information. But to
extend vdev for Confidential Computing (CC), there are needs to do
secure configuration for the vdev, e.g. TSM Bind/Unbind. These
configurations should be rolled back on idev destroy, or the external
driver (VFIO) functionality may be impact.

The idev is created by external driver so its destruction can't fail.
The idev implements pre_destroy() op to actively remove its associated
vdev before destroying itself. There are 3 cases on idev pre_destroy():

  1. vdev is already destroyed by userspace. No extra handling needed.
  2. vdev is still alive. Use iommufd_object_tombstone_user() to
     destroy vdev and tombstone the vdev ID.
  3. vdev is being destroyed by userspace. The vdev ID is already
     freed, but vdev destroy handler is not completed. This requires
     multi-threads syncing - vdev holds idev's short term users
     reference until vdev destruction completes, idev leverages
     existing wait_shortterm mechanism for syncing.

idev should also block any new reference to it after pre_destroy(),
or the following wait shortterm would timeout. Introduce a 'destroying'
flag, set it to true on idev pre_destroy(). Any attempt to reference
idev should honor this flag under the protection of
idev->igroup->lock.

Link: https://patch.msgid.link/r/20250716070349.1807226-5-yilun.xu@linux.intel.com
Originally-by: Nicolin Chen <nicolinc@nvidia.com>
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Co-developed-by: "Aneesh Kumar K.V (Arm)" <aneesh.kumar@kernel.org>
Signed-off-by: "Aneesh Kumar K.V (Arm)" <aneesh.kumar@kernel.org>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/device.c          | 51 ++++++++++++++++++++++++++++++++
 drivers/iommu/iommufd/iommufd_private.h | 12 ++++++++
 drivers/iommu/iommufd/main.c            |  2 ++
 drivers/iommu/iommufd/viommu.c          | 52 ++++++++++++++++++++++++++++++---
 include/linux/iommufd.h                 |  1 +
 include/uapi/linux/iommufd.h            |  5 ++++
 6 files changed, 119 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index e2ba21c43ad2..ee6ff4caf398 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -137,6 +137,57 @@ static struct iommufd_group *iommufd_get_group(struct iommufd_ctx *ictx,
 	}
 }
 
+static void iommufd_device_remove_vdev(struct iommufd_device *idev)
+{
+	struct iommufd_vdevice *vdev;
+
+	mutex_lock(&idev->igroup->lock);
+	/* prevent new references from vdev */
+	idev->destroying = true;
+	/* vdev has been completely destroyed by userspace */
+	if (!idev->vdev)
+		goto out_unlock;
+
+	vdev = iommufd_get_vdevice(idev->ictx, idev->vdev->obj.id);
+	/*
+	 * An ongoing vdev destroy ioctl has removed the vdev from the object
+	 * xarray, but has not finished iommufd_vdevice_destroy() yet as it
+	 * needs the same mutex. We exit the locking then wait on short term
+	 * users for the vdev destruction.
+	 */
+	if (IS_ERR(vdev))
+		goto out_unlock;
+
+	/* Should never happen */
+	if (WARN_ON(vdev != idev->vdev)) {
+		iommufd_put_object(idev->ictx, &vdev->obj);
+		goto out_unlock;
+	}
+
+	/*
+	 * vdev is still alive. Hold a users refcount to prevent racing with
+	 * userspace destruction, then use iommufd_object_tombstone_user() to
+	 * destroy it and leave a tombstone.
+	 */
+	refcount_inc(&vdev->obj.users);
+	iommufd_put_object(idev->ictx, &vdev->obj);
+	mutex_unlock(&idev->igroup->lock);
+	iommufd_object_tombstone_user(idev->ictx, &vdev->obj);
+	return;
+
+out_unlock:
+	mutex_unlock(&idev->igroup->lock);
+}
+
+void iommufd_device_pre_destroy(struct iommufd_object *obj)
+{
+	struct iommufd_device *idev =
+		container_of(obj, struct iommufd_device, obj);
+
+	/* Release the short term users on this */
+	iommufd_device_remove_vdev(idev);
+}
+
 void iommufd_device_destroy(struct iommufd_object *obj)
 {
 	struct iommufd_device *idev =
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 149545060029..5d6ea5395cfe 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -489,6 +489,8 @@ struct iommufd_device {
 	/* always the physical device */
 	struct device *dev;
 	bool enforce_cache_coherency;
+	struct iommufd_vdevice *vdev;
+	bool destroying;
 };
 
 static inline struct iommufd_device *
@@ -499,6 +501,7 @@ iommufd_get_device(struct iommufd_ucmd *ucmd, u32 id)
 			    struct iommufd_device, obj);
 }
 
+void iommufd_device_pre_destroy(struct iommufd_object *obj);
 void iommufd_device_destroy(struct iommufd_object *obj);
 int iommufd_get_hw_info(struct iommufd_ucmd *ucmd);
 
@@ -687,9 +690,18 @@ int iommufd_viommu_alloc_ioctl(struct iommufd_ucmd *ucmd);
 void iommufd_viommu_destroy(struct iommufd_object *obj);
 int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd);
 void iommufd_vdevice_destroy(struct iommufd_object *obj);
+void iommufd_vdevice_abort(struct iommufd_object *obj);
 int iommufd_hw_queue_alloc_ioctl(struct iommufd_ucmd *ucmd);
 void iommufd_hw_queue_destroy(struct iommufd_object *obj);
 
+static inline struct iommufd_vdevice *
+iommufd_get_vdevice(struct iommufd_ctx *ictx, u32 id)
+{
+	return container_of(iommufd_get_object(ictx, id,
+					       IOMMUFD_OBJ_VDEVICE),
+			    struct iommufd_vdevice, obj);
+}
+
 #ifdef CONFIG_IOMMUFD_TEST
 int iommufd_test(struct iommufd_ucmd *ucmd);
 void iommufd_selftest_destroy(struct iommufd_object *obj);
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 53085d24ce4a..99c1aab3d396 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -655,6 +655,7 @@ static const struct iommufd_object_ops iommufd_object_ops[] = {
 		.destroy = iommufd_access_destroy_object,
 	},
 	[IOMMUFD_OBJ_DEVICE] = {
+		.pre_destroy = iommufd_device_pre_destroy,
 		.destroy = iommufd_device_destroy,
 	},
 	[IOMMUFD_OBJ_FAULT] = {
@@ -676,6 +677,7 @@ static const struct iommufd_object_ops iommufd_object_ops[] = {
 	},
 	[IOMMUFD_OBJ_VDEVICE] = {
 		.destroy = iommufd_vdevice_destroy,
+		.abort = iommufd_vdevice_abort,
 	},
 	[IOMMUFD_OBJ_VEVENTQ] = {
 		.destroy = iommufd_veventq_destroy,
diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index dcf8a85b9f6e..ecbae5091ffe 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -110,20 +110,37 @@ out_put_idev:
 	return rc;
 }
 
-void iommufd_vdevice_destroy(struct iommufd_object *obj)
+void iommufd_vdevice_abort(struct iommufd_object *obj)
 {
 	struct iommufd_vdevice *vdev =
 		container_of(obj, struct iommufd_vdevice, obj);
 	struct iommufd_viommu *viommu = vdev->viommu;
+	struct iommufd_device *idev = vdev->idev;
+
+	lockdep_assert_held(&idev->igroup->lock);
 
 	if (vdev->destroy)
 		vdev->destroy(vdev);
 	/* xa_cmpxchg is okay to fail if alloc failed xa_cmpxchg previously */
 	xa_cmpxchg(&viommu->vdevs, vdev->virt_id, vdev, NULL, GFP_KERNEL);
 	refcount_dec(&viommu->obj.users);
+	idev->vdev = NULL;
 	put_device(vdev->dev);
 }
 
+void iommufd_vdevice_destroy(struct iommufd_object *obj)
+{
+	struct iommufd_vdevice *vdev =
+		container_of(obj, struct iommufd_vdevice, obj);
+	struct iommufd_device *idev = vdev->idev;
+	struct iommufd_ctx *ictx = idev->ictx;
+
+	mutex_lock(&idev->igroup->lock);
+	iommufd_vdevice_abort(obj);
+	mutex_unlock(&idev->igroup->lock);
+	iommufd_put_object(ictx, &idev->obj);
+}
+
 int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 {
 	struct iommu_vdevice_alloc *cmd = ucmd->cmd;
@@ -153,6 +170,17 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 		goto out_put_idev;
 	}
 
+	mutex_lock(&idev->igroup->lock);
+	if (idev->destroying) {
+		rc = -ENOENT;
+		goto out_unlock_igroup;
+	}
+
+	if (idev->vdev) {
+		rc = -EEXIST;
+		goto out_unlock_igroup;
+	}
+
 	if (viommu->ops && viommu->ops->vdevice_size) {
 		/*
 		 * It is a driver bug for:
@@ -171,7 +199,7 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 		ucmd->ictx, vdev_size, IOMMUFD_OBJ_VDEVICE);
 	if (IS_ERR(vdev)) {
 		rc = PTR_ERR(vdev);
-		goto out_put_idev;
+		goto out_unlock_igroup;
 	}
 
 	vdev->virt_id = virt_id;
@@ -179,6 +207,19 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 	get_device(idev->dev);
 	vdev->viommu = viommu;
 	refcount_inc(&viommu->obj.users);
+	/*
+	 * A short term users reference is held on the idev so long as we have
+	 * the pointer. iommufd_device_pre_destroy() will revoke it before the
+	 * idev real destruction.
+	 */
+	vdev->idev = idev;
+
+	/*
+	 * iommufd_device_destroy() delays until idev->vdev is NULL before
+	 * freeing the idev, which only happens once the vdev is finished
+	 * destruction.
+	 */
+	idev->vdev = vdev;
 
 	curr = xa_cmpxchg(&viommu->vdevs, virt_id, NULL, vdev, GFP_KERNEL);
 	if (curr) {
@@ -197,12 +238,15 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 	if (rc)
 		goto out_abort;
 	iommufd_object_finalize(ucmd->ictx, &vdev->obj);
-	goto out_put_idev;
+	goto out_unlock_igroup;
 
 out_abort:
 	iommufd_object_abort_and_destroy(ucmd->ictx, &vdev->obj);
+out_unlock_igroup:
+	mutex_unlock(&idev->igroup->lock);
 out_put_idev:
-	iommufd_put_object(ucmd->ictx, &idev->obj);
+	if (rc)
+		iommufd_put_object(ucmd->ictx, &idev->obj);
 out_put_viommu:
 	iommufd_put_object(ucmd->ictx, &viommu->obj);
 	return rc;
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index e3a0cd47384d..b88911026bc4 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -108,6 +108,7 @@ struct iommufd_viommu {
 struct iommufd_vdevice {
 	struct iommufd_object obj;
 	struct iommufd_viommu *viommu;
+	struct iommufd_device *idev;
 	struct device *dev;
 
 	/*
diff --git a/include/uapi/linux/iommufd.h b/include/uapi/linux/iommufd.h
index 554aacf89ea7..c218c89e0e2e 100644
--- a/include/uapi/linux/iommufd.h
+++ b/include/uapi/linux/iommufd.h
@@ -1070,6 +1070,11 @@ struct iommu_viommu_alloc {
  *
  * Allocate a virtual device instance (for a physical device) against a vIOMMU.
  * This instance holds the device's information (related to its vIOMMU) in a VM.
+ * User should use IOMMU_DESTROY to destroy the virtual device before
+ * destroying the physical device (by closing vfio_cdev fd). Otherwise the
+ * virtual device would be forcibly destroyed on physical device destruction,
+ * its vdevice_id would be permanently leaked (unremovable & unreusable) until
+ * iommu fd closed.
  */
 struct iommu_vdevice_alloc {
 	__u32 size;
-- 
cgit v1.2.3


From 651f733675c4a26e59dd34522917eace20c557c0 Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@linux.intel.com>
Date: Wed, 16 Jul 2025 15:03:46 +0800
Subject: iommufd/vdevice: Remove struct device reference from struct vdevice

Remove struct device *dev from struct vdevice.

The dev pointer is the Plan B for vdevice to reference the physical
device. As now vdev->idev is added without refcounting concern, just
use vdev->idev->dev when needed. To avoid exposing
struct iommufd_device in the public header, export a
iommufd_vdevice_to_device() helper.

Link: https://patch.msgid.link/r/20250716070349.1807226-6-yilun.xu@linux.intel.com
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Co-developed-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c |  3 ++-
 drivers/iommu/iommufd/driver.c                 | 10 ++++++++--
 drivers/iommu/iommufd/viommu.c                 |  3 ---
 include/linux/iommufd.h                        |  8 +++++++-
 4 files changed, 17 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
index eb90af5093d8..4c86eacd36b1 100644
--- a/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
+++ b/drivers/iommu/arm/arm-smmu-v3/tegra241-cmdqv.c
@@ -1218,7 +1218,8 @@ static void tegra241_vintf_destroy_vsid(struct iommufd_vdevice *vdev)
 
 static int tegra241_vintf_init_vsid(struct iommufd_vdevice *vdev)
 {
-	struct arm_smmu_master *master = dev_iommu_priv_get(vdev->dev);
+	struct device *dev = iommufd_vdevice_to_device(vdev);
+	struct arm_smmu_master *master = dev_iommu_priv_get(dev);
 	struct tegra241_vintf *vintf = viommu_to_vintf(vdev->viommu);
 	struct tegra241_vintf_sid *vsid = vdev_to_vsid(vdev);
 	struct arm_smmu_stream *stream = &master->streams[0];
diff --git a/drivers/iommu/iommufd/driver.c b/drivers/iommu/iommufd/driver.c
index e4eae20bcd4e..6f1010da221c 100644
--- a/drivers/iommu/iommufd/driver.c
+++ b/drivers/iommu/iommufd/driver.c
@@ -83,6 +83,12 @@ void _iommufd_destroy_mmap(struct iommufd_ctx *ictx,
 }
 EXPORT_SYMBOL_NS_GPL(_iommufd_destroy_mmap, "IOMMUFD");
 
+struct device *iommufd_vdevice_to_device(struct iommufd_vdevice *vdev)
+{
+	return vdev->idev->dev;
+}
+EXPORT_SYMBOL_NS_GPL(iommufd_vdevice_to_device, "IOMMUFD");
+
 /* Caller should xa_lock(&viommu->vdevs) to protect the return value */
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id)
@@ -92,7 +98,7 @@ struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 	lockdep_assert_held(&viommu->vdevs.xa_lock);
 
 	vdev = xa_load(&viommu->vdevs, vdev_id);
-	return vdev ? vdev->dev : NULL;
+	return vdev ? iommufd_vdevice_to_device(vdev) : NULL;
 }
 EXPORT_SYMBOL_NS_GPL(iommufd_viommu_find_dev, "IOMMUFD");
 
@@ -109,7 +115,7 @@ int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
 
 	xa_lock(&viommu->vdevs);
 	xa_for_each(&viommu->vdevs, index, vdev) {
-		if (vdev->dev == dev) {
+		if (iommufd_vdevice_to_device(vdev) == dev) {
 			*vdev_id = vdev->virt_id;
 			rc = 0;
 			break;
diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index ecbae5091ffe..6cf0bd5d8f08 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -125,7 +125,6 @@ void iommufd_vdevice_abort(struct iommufd_object *obj)
 	xa_cmpxchg(&viommu->vdevs, vdev->virt_id, vdev, NULL, GFP_KERNEL);
 	refcount_dec(&viommu->obj.users);
 	idev->vdev = NULL;
-	put_device(vdev->dev);
 }
 
 void iommufd_vdevice_destroy(struct iommufd_object *obj)
@@ -203,8 +202,6 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 	}
 
 	vdev->virt_id = virt_id;
-	vdev->dev = idev->dev;
-	get_device(idev->dev);
 	vdev->viommu = viommu;
 	refcount_inc(&viommu->obj.users);
 	/*
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index b88911026bc4..810e4d8ac912 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -109,7 +109,6 @@ struct iommufd_vdevice {
 	struct iommufd_object obj;
 	struct iommufd_viommu *viommu;
 	struct iommufd_device *idev;
-	struct device *dev;
 
 	/*
 	 * Virtual device ID per vIOMMU, e.g. vSID of ARM SMMUv3, vDeviceID of
@@ -261,6 +260,7 @@ int _iommufd_alloc_mmap(struct iommufd_ctx *ictx, struct iommufd_object *owner,
 			unsigned long *offset);
 void _iommufd_destroy_mmap(struct iommufd_ctx *ictx,
 			   struct iommufd_object *owner, unsigned long offset);
+struct device *iommufd_vdevice_to_device(struct iommufd_vdevice *vdev);
 struct device *iommufd_viommu_find_dev(struct iommufd_viommu *viommu,
 				       unsigned long vdev_id);
 int iommufd_viommu_get_vdev_id(struct iommufd_viommu *viommu,
@@ -295,6 +295,12 @@ static inline void _iommufd_destroy_mmap(struct iommufd_ctx *ictx,
 {
 }
 
+static inline struct device *
+iommufd_vdevice_to_device(struct iommufd_vdevice *vdev)
+{
+	return NULL;
+}
+
 static inline struct device *
 iommufd_viommu_find_dev(struct iommufd_viommu *viommu, unsigned long vdev_id)
 {
-- 
cgit v1.2.3


From ab6bc44159d8f0c4ee757e0ce041fa9033e0ead8 Mon Sep 17 00:00:00 2001
From: Xu Yilun <yilun.xu@linux.intel.com>
Date: Wed, 16 Jul 2025 15:03:49 +0800
Subject: iommufd: Rename some shortterm-related identifiers

Rename the shortterm-related identifiers to wait-related.

The usage of shortterm_users refcount is now beyond its name.  It is
also used for references which live longer than an ioctl execution.
E.g. vdev holds idev's shortterm_users refcount on vdev allocation,
releases it during idev's pre_destroy(). Rename the refcount as
wait_cnt, since it is always used to sync the referencing & the
destruction of the object by waiting for it to go to zero.

List all changed identifiers:

  iommufd_object::shortterm_users -> iommufd_object::wait_cnt
  REMOVE_WAIT_SHORTTERM -> REMOVE_WAIT
  iommufd_object_dec_wait_shortterm() -> iommufd_object_dec_wait()
  zerod_shortterm -> zerod_wait_cnt

No functional change intended.

Link: https://patch.msgid.link/r/20250716070349.1807226-9-yilun.xu@linux.intel.com
Suggested-by: Kevin Tian <kevin.tian@intel.com>
Suggested-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Nicolin Chen <nicolinc@nvidia.com>
Tested-by: Nicolin Chen <nicolinc@nvidia.com>
Signed-off-by: Xu Yilun <yilun.xu@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/iommu/iommufd/device.c          |  6 ++---
 drivers/iommu/iommufd/iommufd_private.h | 18 +++++++--------
 drivers/iommu/iommufd/main.c            | 39 +++++++++++++++++----------------
 drivers/iommu/iommufd/viommu.c          |  4 ++--
 include/linux/iommufd.h                 |  8 ++++++-
 5 files changed, 41 insertions(+), 34 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
index ee6ff4caf398..65fbd098f9e9 100644
--- a/drivers/iommu/iommufd/device.c
+++ b/drivers/iommu/iommufd/device.c
@@ -152,8 +152,8 @@ static void iommufd_device_remove_vdev(struct iommufd_device *idev)
 	/*
 	 * An ongoing vdev destroy ioctl has removed the vdev from the object
 	 * xarray, but has not finished iommufd_vdevice_destroy() yet as it
-	 * needs the same mutex. We exit the locking then wait on short term
-	 * users for the vdev destruction.
+	 * needs the same mutex. We exit the locking then wait on wait_cnt
+	 * reference for the vdev destruction.
 	 */
 	if (IS_ERR(vdev))
 		goto out_unlock;
@@ -184,7 +184,7 @@ void iommufd_device_pre_destroy(struct iommufd_object *obj)
 	struct iommufd_device *idev =
 		container_of(obj, struct iommufd_device, obj);
 
-	/* Release the short term users on this */
+	/* Release the wait_cnt reference on this */
 	iommufd_device_remove_vdev(idev);
 }
 
diff --git a/drivers/iommu/iommufd/iommufd_private.h b/drivers/iommu/iommufd/iommufd_private.h
index 5d6ea5395cfe..0da2a81eedfa 100644
--- a/drivers/iommu/iommufd/iommufd_private.h
+++ b/drivers/iommu/iommufd/iommufd_private.h
@@ -169,7 +169,7 @@ static inline bool iommufd_lock_obj(struct iommufd_object *obj)
 {
 	if (!refcount_inc_not_zero(&obj->users))
 		return false;
-	if (!refcount_inc_not_zero(&obj->shortterm_users)) {
+	if (!refcount_inc_not_zero(&obj->wait_cnt)) {
 		/*
 		 * If the caller doesn't already have a ref on obj this must be
 		 * called under the xa_lock. Otherwise the caller is holding a
@@ -187,11 +187,11 @@ static inline void iommufd_put_object(struct iommufd_ctx *ictx,
 				      struct iommufd_object *obj)
 {
 	/*
-	 * Users first, then shortterm so that REMOVE_WAIT_SHORTTERM never sees
-	 * a spurious !0 users with a 0 shortterm_users.
+	 * Users first, then wait_cnt so that REMOVE_WAIT never sees a spurious
+	 * !0 users with a 0 wait_cnt.
 	 */
 	refcount_dec(&obj->users);
-	if (refcount_dec_and_test(&obj->shortterm_users))
+	if (refcount_dec_and_test(&obj->wait_cnt))
 		wake_up_interruptible_all(&ictx->destroy_wait);
 }
 
@@ -202,7 +202,7 @@ void iommufd_object_finalize(struct iommufd_ctx *ictx,
 			     struct iommufd_object *obj);
 
 enum {
-	REMOVE_WAIT_SHORTTERM	= BIT(0),
+	REMOVE_WAIT		= BIT(0),
 	REMOVE_OBJ_TOMBSTONE	= BIT(1),
 };
 int iommufd_object_remove(struct iommufd_ctx *ictx,
@@ -211,15 +211,15 @@ int iommufd_object_remove(struct iommufd_ctx *ictx,
 
 /*
  * The caller holds a users refcount and wants to destroy the object. At this
- * point the caller has no shortterm_users reference and at least the xarray
- * will be holding one.
+ * point the caller has no wait_cnt reference and at least the xarray will be
+ * holding one.
  */
 static inline void iommufd_object_destroy_user(struct iommufd_ctx *ictx,
 					       struct iommufd_object *obj)
 {
 	int ret;
 
-	ret = iommufd_object_remove(ictx, obj, obj->id, REMOVE_WAIT_SHORTTERM);
+	ret = iommufd_object_remove(ictx, obj, obj->id, REMOVE_WAIT);
 
 	/*
 	 * If there is a bug and we couldn't destroy the object then we did put
@@ -239,7 +239,7 @@ static inline void iommufd_object_tombstone_user(struct iommufd_ctx *ictx,
 	int ret;
 
 	ret = iommufd_object_remove(ictx, obj, obj->id,
-				    REMOVE_WAIT_SHORTTERM | REMOVE_OBJ_TOMBSTONE);
+				    REMOVE_WAIT | REMOVE_OBJ_TOMBSTONE);
 
 	/*
 	 * If there is a bug and we couldn't destroy the object then we did put
diff --git a/drivers/iommu/iommufd/main.c b/drivers/iommu/iommufd/main.c
index 99c1aab3d396..15af7ced0501 100644
--- a/drivers/iommu/iommufd/main.c
+++ b/drivers/iommu/iommufd/main.c
@@ -42,7 +42,7 @@ struct iommufd_object *_iommufd_object_alloc(struct iommufd_ctx *ictx,
 		return ERR_PTR(-ENOMEM);
 	obj->type = type;
 	/* Starts out bias'd by 1 until it is removed from the xarray */
-	refcount_set(&obj->shortterm_users, 1);
+	refcount_set(&obj->wait_cnt, 1);
 	refcount_set(&obj->users, 1);
 
 	/*
@@ -155,22 +155,22 @@ struct iommufd_object *iommufd_get_object(struct iommufd_ctx *ictx, u32 id,
 	return obj;
 }
 
-static int iommufd_object_dec_wait_shortterm(struct iommufd_ctx *ictx,
-					     struct iommufd_object *to_destroy)
+static int iommufd_object_dec_wait(struct iommufd_ctx *ictx,
+				   struct iommufd_object *to_destroy)
 {
-	if (refcount_dec_and_test(&to_destroy->shortterm_users))
+	if (refcount_dec_and_test(&to_destroy->wait_cnt))
 		return 0;
 
 	if (iommufd_object_ops[to_destroy->type].pre_destroy)
 		iommufd_object_ops[to_destroy->type].pre_destroy(to_destroy);
 
 	if (wait_event_timeout(ictx->destroy_wait,
-			       refcount_read(&to_destroy->shortterm_users) == 0,
+			       refcount_read(&to_destroy->wait_cnt) == 0,
 			       msecs_to_jiffies(60000)))
 		return 0;
 
 	pr_crit("Time out waiting for iommufd object to become free\n");
-	refcount_inc(&to_destroy->shortterm_users);
+	refcount_inc(&to_destroy->wait_cnt);
 	return -EBUSY;
 }
 
@@ -184,17 +184,18 @@ int iommufd_object_remove(struct iommufd_ctx *ictx,
 {
 	struct iommufd_object *obj;
 	XA_STATE(xas, &ictx->objects, id);
-	bool zerod_shortterm = false;
+	bool zerod_wait_cnt = false;
 	int ret;
 
 	/*
-	 * The purpose of the shortterm_users is to ensure deterministic
-	 * destruction of objects used by external drivers and destroyed by this
-	 * function. Any temporary increment of the refcount must increment
-	 * shortterm_users, such as during ioctl execution.
+	 * The purpose of the wait_cnt is to ensure deterministic destruction
+	 * of objects used by external drivers and destroyed by this function.
+	 * Incrementing this wait_cnt should either be short lived, such as
+	 * during ioctl execution, or be revoked and blocked during
+	 * pre_destroy(), such as vdev holding the idev's refcount.
 	 */
-	if (flags & REMOVE_WAIT_SHORTTERM) {
-		ret = iommufd_object_dec_wait_shortterm(ictx, to_destroy);
+	if (flags & REMOVE_WAIT) {
+		ret = iommufd_object_dec_wait(ictx, to_destroy);
 		if (ret) {
 			/*
 			 * We have a bug. Put back the callers reference and
@@ -203,7 +204,7 @@ int iommufd_object_remove(struct iommufd_ctx *ictx,
 			refcount_dec(&to_destroy->users);
 			return ret;
 		}
-		zerod_shortterm = true;
+		zerod_wait_cnt = true;
 	}
 
 	xa_lock(&ictx->objects);
@@ -235,11 +236,11 @@ int iommufd_object_remove(struct iommufd_ctx *ictx,
 	xa_unlock(&ictx->objects);
 
 	/*
-	 * Since users is zero any positive users_shortterm must be racing
+	 * Since users is zero any positive wait_cnt must be racing
 	 * iommufd_put_object(), or we have a bug.
 	 */
-	if (!zerod_shortterm) {
-		ret = iommufd_object_dec_wait_shortterm(ictx, obj);
+	if (!zerod_wait_cnt) {
+		ret = iommufd_object_dec_wait(ictx, obj);
 		if (WARN_ON(ret))
 			return ret;
 	}
@@ -249,9 +250,9 @@ int iommufd_object_remove(struct iommufd_ctx *ictx,
 	return 0;
 
 err_xa:
-	if (zerod_shortterm) {
+	if (zerod_wait_cnt) {
 		/* Restore the xarray owned reference */
-		refcount_set(&obj->shortterm_users, 1);
+		refcount_set(&obj->wait_cnt, 1);
 	}
 	xa_unlock(&ictx->objects);
 
diff --git a/drivers/iommu/iommufd/viommu.c b/drivers/iommu/iommufd/viommu.c
index 6cf0bd5d8f08..2ca5809b238b 100644
--- a/drivers/iommu/iommufd/viommu.c
+++ b/drivers/iommu/iommufd/viommu.c
@@ -205,8 +205,8 @@ int iommufd_vdevice_alloc_ioctl(struct iommufd_ucmd *ucmd)
 	vdev->viommu = viommu;
 	refcount_inc(&viommu->obj.users);
 	/*
-	 * A short term users reference is held on the idev so long as we have
-	 * the pointer. iommufd_device_pre_destroy() will revoke it before the
+	 * A wait_cnt reference is held on the idev so long as we have the
+	 * pointer. iommufd_device_pre_destroy() will revoke it before the
 	 * idev real destruction.
 	 */
 	vdev->idev = idev;
diff --git a/include/linux/iommufd.h b/include/linux/iommufd.h
index 810e4d8ac912..6e7efe83bc5d 100644
--- a/include/linux/iommufd.h
+++ b/include/linux/iommufd.h
@@ -46,7 +46,13 @@ enum iommufd_object_type {
 
 /* Base struct for all objects with a userspace ID handle. */
 struct iommufd_object {
-	refcount_t shortterm_users;
+	/*
+	 * Destroy will sleep and wait for wait_cnt to go to zero. This allows
+	 * concurrent users of the ID to reliably avoid causing a spurious
+	 * destroy failure. Incrementing this count should either be short
+	 * lived or be revoked and blocked during pre_destroy().
+	 */
+	refcount_t wait_cnt;
 	refcount_t users;
 	enum iommufd_object_type type;
 	unsigned int id;
-- 
cgit v1.2.3


From a6f190630d070173897a7e98a30188b7638ba0a1 Mon Sep 17 00:00:00 2001
From: Jesper Dangaard Brouer <hawk@kernel.org>
Date: Wed, 16 Jul 2025 18:26:53 +0200
Subject: net: track pfmemalloc drops via SKB_DROP_REASON_PFMEMALLOC

Add a new SKB drop reason (SKB_DROP_REASON_PFMEMALLOC) to track packets
dropped due to memory pressure. In production environments, we've observed
memory exhaustion reported by memory layer stack traces, but these drops
were not properly tracked in the SKB drop reason infrastructure.

While most network code paths now properly report pfmemalloc drops, some
protocol-specific socket implementations still use sk_filter() without
drop reason tracking:
- Bluetooth L2CAP sockets
- CAIF sockets
- IUCV sockets
- Netlink sockets
- SCTP sockets
- Unix domain sockets

These remaining cases represent less common paths and could be converted
in a follow-up patch if needed. The current implementation provides
significantly improved observability into memory pressure events in the
network stack, especially for key protocols like TCP and UDP, helping to
diagnose problems in production environments.

Reported-by: Matt Fleming <mfleming@cloudflare.com>
Signed-off-by: Jesper Dangaard Brouer <hawk@kernel.org>
Link: https://patch.msgid.link/175268316579.2407873.11634752355644843509.stgit@firesoul
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tun.c             |  6 ++----
 include/linux/filter.h        | 14 ++++++++++++--
 include/net/dropreason-core.h |  6 ++++++
 include/net/tcp.h             |  2 +-
 net/core/dev.c                |  8 ++++++--
 net/core/filter.c             | 15 ++++++++++++---
 net/core/sock.c               | 20 +++++++++++++-------
 net/ipv4/tcp_ipv4.c           | 26 +++++++++++++++-----------
 net/ipv4/udp.c                |  6 ++----
 net/ipv6/tcp_ipv6.c           |  9 +++------
 net/ipv6/udp.c                |  4 +---
 net/rose/rose_in.c            |  3 ++-
 12 files changed, 75 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 49bcd12a4ac8..e65228ba3fae 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -1002,8 +1002,8 @@ static unsigned int run_ebpf_filter(struct tun_struct *tun,
 /* Net device start xmit */
 static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 {
+	enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct tun_struct *tun = netdev_priv(dev);
-	enum skb_drop_reason drop_reason;
 	int txq = skb->queue_mapping;
 	struct netdev_queue *queue;
 	struct tun_file *tfile;
@@ -1032,10 +1032,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
 	}
 
 	if (tfile->socket.sk->sk_filter &&
-	    sk_filter(tfile->socket.sk, skb)) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	    sk_filter_reason(tfile->socket.sk, skb, &drop_reason))
 		goto drop;
-	}
 
 	len = run_ebpf_filter(tun, skb, len);
 	if (len == 0) {
diff --git a/include/linux/filter.h b/include/linux/filter.h
index f5cf4d35d83e..4e82332afe03 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1073,10 +1073,20 @@ bpf_jit_binary_lock_ro(struct bpf_binary_header *hdr)
 	return set_memory_rox((unsigned long)hdr, hdr->size >> PAGE_SHIFT);
 }
 
-int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap);
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap,
+		       enum skb_drop_reason *reason);
+
 static inline int sk_filter(struct sock *sk, struct sk_buff *skb)
 {
-	return sk_filter_trim_cap(sk, skb, 1);
+	enum skb_drop_reason ignore_reason;
+
+	return sk_filter_trim_cap(sk, skb, 1, &ignore_reason);
+}
+
+static inline int sk_filter_reason(struct sock *sk, struct sk_buff *skb,
+				   enum skb_drop_reason *reason)
+{
+	return sk_filter_trim_cap(sk, skb, 1, reason);
 }
 
 struct bpf_prog *bpf_prog_select_runtime(struct bpf_prog *fp, int *err);
diff --git a/include/net/dropreason-core.h b/include/net/dropreason-core.h
index 229bb1826f2a..e19184dd1b0f 100644
--- a/include/net/dropreason-core.h
+++ b/include/net/dropreason-core.h
@@ -125,6 +125,7 @@
 	FN(CAN_RX_INVALID_FRAME)	\
 	FN(CANFD_RX_INVALID_FRAME)	\
 	FN(CANXL_RX_INVALID_FRAME)	\
+	FN(PFMEMALLOC)	\
 	FNe(MAX)
 
 /**
@@ -598,6 +599,11 @@ enum skb_drop_reason {
 	 * non conform CAN-XL frame (or device is unable to receive CAN frames)
 	 */
 	SKB_DROP_REASON_CANXL_RX_INVALID_FRAME,
+	/**
+	 * @SKB_DROP_REASON_PFMEMALLOC: packet allocated from memory reserve
+	 * reached a path or socket not eligible for use of memory reserves
+	 */
+	SKB_DROP_REASON_PFMEMALLOC,
 	/**
 	 * @SKB_DROP_REASON_MAX: the maximum of core drop reasons, which
 	 * shouldn't be used as a real 'reason' - only for tracing code gen
diff --git a/include/net/tcp.h b/include/net/tcp.h
index bc08de49805c..b3815d104340 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1559,7 +1559,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 		     enum skb_drop_reason *reason);
 
 
-int tcp_filter(struct sock *sk, struct sk_buff *skb);
+int tcp_filter(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason);
 void tcp_set_state(struct sock *sk, int state);
 void tcp_done(struct sock *sk);
 int tcp_abort(struct sock *sk, int err);
diff --git a/net/core/dev.c b/net/core/dev.c
index 621a639aeba1..59a9089117de 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -5749,6 +5749,7 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev,
 static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc,
 				    struct packet_type **ppt_prev)
 {
+	enum skb_drop_reason drop_reason = SKB_DROP_REASON_UNHANDLED_PROTO;
 	struct packet_type *ptype, *pt_prev;
 	rx_handler_func_t *rx_handler;
 	struct sk_buff *skb = *pskb;
@@ -5840,8 +5841,10 @@ skip_taps:
 #endif
 	skb_reset_redirect(skb);
 skip_classify:
-	if (pfmemalloc && !skb_pfmemalloc_protocol(skb))
+	if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) {
+		drop_reason = SKB_DROP_REASON_PFMEMALLOC;
 		goto drop;
+	}
 
 	if (skb_vlan_tag_present(skb)) {
 		if (pt_prev) {
@@ -5946,7 +5949,8 @@ drop:
 			dev_core_stats_rx_dropped_inc(skb->dev);
 		else
 			dev_core_stats_rx_nohandler_inc(skb->dev);
-		kfree_skb_reason(skb, SKB_DROP_REASON_UNHANDLED_PROTO);
+
+		kfree_skb_reason(skb, drop_reason);
 		/* Jamal, now you will not able to escape explaining
 		 * me how you were going to use this. :-)
 		 */
diff --git a/net/core/filter.c b/net/core/filter.c
index 7a72f766aacf..2eb8947d8097 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -122,6 +122,7 @@ EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user);
  *	@sk: sock associated with &sk_buff
  *	@skb: buffer to filter
  *	@cap: limit on how short the eBPF program may trim the packet
+ *	@reason: record drop reason on errors (negative return value)
  *
  * Run the eBPF program and then cut skb->data to correct size returned by
  * the program. If pkt_len is 0 we toss packet. If skb->len is smaller
@@ -130,7 +131,8 @@ EXPORT_SYMBOL_GPL(copy_bpf_fprog_from_user);
  * be accepted or -EPERM if the packet should be tossed.
  *
  */
-int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
+int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb,
+		       unsigned int cap, enum skb_drop_reason *reason)
 {
 	int err;
 	struct sk_filter *filter;
@@ -142,15 +144,20 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 	 */
 	if (skb_pfmemalloc(skb) && !sock_flag(sk, SOCK_MEMALLOC)) {
 		NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP);
+		*reason = SKB_DROP_REASON_PFMEMALLOC;
 		return -ENOMEM;
 	}
 	err = BPF_CGROUP_RUN_PROG_INET_INGRESS(sk, skb);
-	if (err)
+	if (err) {
+		*reason = SKB_DROP_REASON_SOCKET_FILTER;
 		return err;
+	}
 
 	err = security_sock_rcv_skb(sk, skb);
-	if (err)
+	if (err) {
+		*reason = SKB_DROP_REASON_SECURITY_HOOK;
 		return err;
+	}
 
 	rcu_read_lock();
 	filter = rcu_dereference(sk->sk_filter);
@@ -162,6 +169,8 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap)
 		pkt_len = bpf_prog_run_save_cb(filter->prog, skb);
 		skb->sk = save_sk;
 		err = pkt_len ? pskb_trim(skb, max(cap, pkt_len)) : -EPERM;
+		if (err)
+			*reason = SKB_DROP_REASON_SOCKET_FILTER;
 	}
 	rcu_read_unlock();
 
diff --git a/net/core/sock.c b/net/core/sock.c
index 8b7623c7d547..7c26ec8dce63 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -526,11 +526,10 @@ int sock_queue_rcv_skb_reason(struct sock *sk, struct sk_buff *skb,
 	enum skb_drop_reason drop_reason;
 	int err;
 
-	err = sk_filter(sk, skb);
-	if (err) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	err = sk_filter_reason(sk, skb, &drop_reason);
+	if (err)
 		goto out;
-	}
+
 	err = __sock_queue_rcv_skb(sk, skb);
 	switch (err) {
 	case -ENOMEM:
@@ -553,15 +552,18 @@ EXPORT_SYMBOL(sock_queue_rcv_skb_reason);
 int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 		     const int nested, unsigned int trim_cap, bool refcounted)
 {
+	enum skb_drop_reason reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	int rc = NET_RX_SUCCESS;
+	int err;
 
-	if (sk_filter_trim_cap(sk, skb, trim_cap))
+	if (sk_filter_trim_cap(sk, skb, trim_cap, &reason))
 		goto discard_and_relse;
 
 	skb->dev = NULL;
 
 	if (sk_rcvqueues_full(sk, READ_ONCE(sk->sk_rcvbuf))) {
 		atomic_inc(&sk->sk_drops);
+		reason = SKB_DROP_REASON_SOCKET_RCVBUFF;
 		goto discard_and_relse;
 	}
 	if (nested)
@@ -577,8 +579,12 @@ int __sk_receive_skb(struct sock *sk, struct sk_buff *skb,
 		rc = sk_backlog_rcv(sk, skb);
 
 		mutex_release(&sk->sk_lock.dep_map, _RET_IP_);
-	} else if (sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf))) {
+	} else if ((err = sk_add_backlog(sk, skb, READ_ONCE(sk->sk_rcvbuf)))) {
 		bh_unlock_sock(sk);
+		if (err == -ENOMEM)
+			reason = SKB_DROP_REASON_PFMEMALLOC;
+		if (err == -ENOBUFS)
+			reason = SKB_DROP_REASON_SOCKET_BACKLOG;
 		atomic_inc(&sk->sk_drops);
 		goto discard_and_relse;
 	}
@@ -589,7 +595,7 @@ out:
 		sock_put(sk);
 	return rc;
 discard_and_relse:
-	kfree_skb(skb);
+	sk_skb_reason_drop(sk, skb, reason);
 	goto out;
 }
 EXPORT_SYMBOL(__sk_receive_skb);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 16bf6fdff96b..84d3d556ed80 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -2026,6 +2026,7 @@ bool tcp_add_backlog(struct sock *sk, struct sk_buff *skb,
 	u32 gso_size;
 	u64 limit;
 	int delta;
+	int err;
 
 	/* In case all data was pulled from skb frags (in __pskb_pull_tail()),
 	 * we can fix skb->truesize to its real value to avoid future drops.
@@ -2136,21 +2137,27 @@ no_coalesce:
 
 	limit = min_t(u64, limit, UINT_MAX);
 
-	if (unlikely(sk_add_backlog(sk, skb, limit))) {
+	err = sk_add_backlog(sk, skb, limit);
+	if (unlikely(err)) {
 		bh_unlock_sock(sk);
-		*reason = SKB_DROP_REASON_SOCKET_BACKLOG;
-		__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP);
+		if (err == -ENOMEM) {
+			*reason = SKB_DROP_REASON_PFMEMALLOC;
+			__NET_INC_STATS(sock_net(sk), LINUX_MIB_PFMEMALLOCDROP);
+		} else {
+			*reason = SKB_DROP_REASON_SOCKET_BACKLOG;
+			__NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPBACKLOGDROP);
+		}
 		return true;
 	}
 	return false;
 }
 EXPORT_IPV6_MOD(tcp_add_backlog);
 
-int tcp_filter(struct sock *sk, struct sk_buff *skb)
+int tcp_filter(struct sock *sk, struct sk_buff *skb, enum skb_drop_reason *reason)
 {
 	struct tcphdr *th = (struct tcphdr *)skb->data;
 
-	return sk_filter_trim_cap(sk, skb, th->doff * 4);
+	return sk_filter_trim_cap(sk, skb, th->doff * 4, reason);
 }
 EXPORT_IPV6_MOD(tcp_filter);
 
@@ -2277,14 +2284,12 @@ lookup:
 		}
 		refcounted = true;
 		nsk = NULL;
-		if (!tcp_filter(sk, skb)) {
+		if (!tcp_filter(sk, skb, &drop_reason)) {
 			th = (const struct tcphdr *)skb->data;
 			iph = ip_hdr(skb);
 			tcp_v4_fill_cb(skb, iph, th);
 			nsk = tcp_check_req(sk, skb, req, false, &req_stolen,
 					    &drop_reason);
-		} else {
-			drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		}
 		if (!nsk) {
 			reqsk_put(req);
@@ -2340,10 +2345,9 @@ process:
 
 	nf_reset_ct(skb);
 
-	if (tcp_filter(sk, skb)) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	if (tcp_filter(sk, skb, &drop_reason))
 		goto discard_and_relse;
-	}
+
 	th = (const struct tcphdr *)skb->data;
 	iph = ip_hdr(skb);
 	tcp_v4_fill_cb(skb, iph, th);
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 49f43c54cfb0..cc3ce0f762ec 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -2347,7 +2347,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb)
  */
 static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 {
-	int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
+	enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED;
 	struct udp_sock *up = udp_sk(sk);
 	int is_udplite = IS_UDPLITE(sk);
 
@@ -2436,10 +2436,8 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	    udp_lib_checksum_complete(skb))
 			goto csum_error;
 
-	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason))
 		goto drop;
-	}
 
 	udp_csum_pull_header(skb);
 
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 8f2c3cba1f1f..7577e7eb2c97 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1834,14 +1834,12 @@ lookup:
 		}
 		refcounted = true;
 		nsk = NULL;
-		if (!tcp_filter(sk, skb)) {
+		if (!tcp_filter(sk, skb, &drop_reason)) {
 			th = (const struct tcphdr *)skb->data;
 			hdr = ipv6_hdr(skb);
 			tcp_v6_fill_cb(skb, hdr, th);
 			nsk = tcp_check_req(sk, skb, req, false, &req_stolen,
 					    &drop_reason);
-		} else {
-			drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
 		}
 		if (!nsk) {
 			reqsk_put(req);
@@ -1897,10 +1895,9 @@ process:
 
 	nf_reset_ct(skb);
 
-	if (tcp_filter(sk, skb)) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	if (tcp_filter(sk, skb, &drop_reason))
 		goto discard_and_relse;
-	}
+
 	th = (const struct tcphdr *)skb->data;
 	hdr = ipv6_hdr(skb);
 	tcp_v6_fill_cb(skb, hdr, th);
diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c
index 6bbdadbd5fec..6a68f77da44b 100644
--- a/net/ipv6/udp.c
+++ b/net/ipv6/udp.c
@@ -894,10 +894,8 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 	    udp_lib_checksum_complete(skb))
 		goto csum_error;
 
-	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) {
-		drop_reason = SKB_DROP_REASON_SOCKET_FILTER;
+	if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason))
 		goto drop;
-	}
 
 	udp_csum_pull_header(skb);
 
diff --git a/net/rose/rose_in.c b/net/rose/rose_in.c
index 4d67f36dce1b..3e99181e759f 100644
--- a/net/rose/rose_in.c
+++ b/net/rose/rose_in.c
@@ -101,6 +101,7 @@ static int rose_state2_machine(struct sock *sk, struct sk_buff *skb, int framety
  */
 static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype, int ns, int nr, int q, int d, int m)
 {
+	enum skb_drop_reason dr; /* ignored */
 	struct rose_sock *rose = rose_sk(sk);
 	int queued = 0;
 
@@ -162,7 +163,7 @@ static int rose_state3_machine(struct sock *sk, struct sk_buff *skb, int framety
 		rose_frames_acked(sk, nr);
 		if (ns == rose->vr) {
 			rose_start_idletimer(sk);
-			if (sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN) == 0 &&
+			if (!sk_filter_trim_cap(sk, skb, ROSE_MIN_LEN, &dr) &&
 			    __sock_queue_rcv_skb(sk, skb) == 0) {
 				rose->vr = (rose->vr + 1) % ROSE_MODULUS;
 				queued = 1;
-- 
cgit v1.2.3


From ffea1168346120df9417fcafd8f3a1c93033ae34 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 17 Jul 2025 10:23:27 -0700
Subject: net: s/dev_get_port_parent_id/netif_get_port_parent_id/

Commit cc34acd577f1 ("docs: net: document new locking reality")
introduced netif_ vs dev_ function semantics: the former expects locked
netdev, the latter takes care of the locking. We don't strictly
follow this semantics on either side, but there are more dev_xxx handlers
now that don't fit. Rename them to netif_xxx where appropriate.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250717172333.1288349-2-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_tc.c |  2 +-
 include/linux/netdevice.h                       |  4 ++--
 net/bridge/br_switchdev.c                       |  2 +-
 net/core/dev.c                                  | 25 +++++++++++++------------
 net/core/net-sysfs.c                            |  2 +-
 net/core/rtnetlink.c                            |  2 +-
 net/ipv4/ipmr.c                                 |  2 +-
 7 files changed, 20 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
index fef418e1ed1a..32c07a8b03d1 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c
@@ -5446,7 +5446,7 @@ int mlx5e_tc_esw_init(struct mlx5_rep_uplink_priv *uplink_priv)
 		goto err_action_counter;
 	}
 
-	err = dev_get_port_parent_id(priv->netdev, &ppid, false);
+	err = netif_get_port_parent_id(priv->netdev, &ppid, false);
 	if (!err) {
 		memcpy(&key, &ppid.id, sizeof(key));
 		mlx5_esw_offloads_devcom_init(esw, key);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index e49d8c98d284..c6ba4ea66039 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4223,8 +4223,8 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 int dev_set_mac_address_user(struct net_device *dev, struct sockaddr_storage *ss,
 			     struct netlink_ext_ack *extack);
 int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
-int dev_get_port_parent_id(struct net_device *dev,
-			   struct netdev_phys_item_id *ppid, bool recurse);
+int netif_get_port_parent_id(struct net_device *dev,
+			     struct netdev_phys_item_id *ppid, bool recurse);
 bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
 
 struct sk_buff *validate_xmit_skb_list(struct sk_buff *skb, struct net_device *dev, bool *again);
diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c
index 9a910cf0256e..fe3f7bbe86ee 100644
--- a/net/bridge/br_switchdev.c
+++ b/net/bridge/br_switchdev.c
@@ -837,7 +837,7 @@ int br_switchdev_port_offload(struct net_bridge_port *p,
 	struct netdev_phys_item_id ppid;
 	int err;
 
-	err = dev_get_port_parent_id(dev, &ppid, false);
+	err = netif_get_port_parent_id(dev, &ppid, false);
 	if (err)
 		return err;
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 59a9089117de..4979a9197b18 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9844,16 +9844,17 @@ int dev_get_phys_port_name(struct net_device *dev,
 }
 
 /**
- *	dev_get_port_parent_id - Get the device's port parent identifier
- *	@dev: network device
- *	@ppid: pointer to a storage for the port's parent identifier
- *	@recurse: allow/disallow recursion to lower devices
+ * netif_get_port_parent_id() - Get the device's port parent identifier
+ * @dev: network device
+ * @ppid: pointer to a storage for the port's parent identifier
+ * @recurse: allow/disallow recursion to lower devices
+ *
+ * Get the devices's port parent identifier.
  *
- *	Get the devices's port parent identifier
+ * Return: 0 on success, -errno on failure.
  */
-int dev_get_port_parent_id(struct net_device *dev,
-			   struct netdev_phys_item_id *ppid,
-			   bool recurse)
+int netif_get_port_parent_id(struct net_device *dev,
+			     struct netdev_phys_item_id *ppid, bool recurse)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 	struct netdev_phys_item_id first = { };
@@ -9872,7 +9873,7 @@ int dev_get_port_parent_id(struct net_device *dev,
 		return err;
 
 	netdev_for_each_lower_dev(dev, lower_dev, iter) {
-		err = dev_get_port_parent_id(lower_dev, ppid, true);
+		err = netif_get_port_parent_id(lower_dev, ppid, true);
 		if (err)
 			break;
 		if (!first.id_len)
@@ -9883,7 +9884,7 @@ int dev_get_port_parent_id(struct net_device *dev,
 
 	return err;
 }
-EXPORT_SYMBOL(dev_get_port_parent_id);
+EXPORT_SYMBOL(netif_get_port_parent_id);
 
 /**
  *	netdev_port_same_parent_id - Indicate if two network devices have
@@ -9896,8 +9897,8 @@ bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b)
 	struct netdev_phys_item_id a_id = { };
 	struct netdev_phys_item_id b_id = { };
 
-	if (dev_get_port_parent_id(a, &a_id, true) ||
-	    dev_get_port_parent_id(b, &b_id, true))
+	if (netif_get_port_parent_id(a, &a_id, true) ||
+	    netif_get_port_parent_id(b, &b_id, true))
 		return false;
 
 	return netdev_phys_item_id_same(&a_id, &b_id);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index 8f897e2c8b4f..f7a6cc7aea79 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -687,7 +687,7 @@ static ssize_t phys_switch_id_show(struct device *dev,
 	if (ret)
 		return ret;
 
-	ret = dev_get_port_parent_id(netdev, &ppid, false);
+	ret = netif_get_port_parent_id(netdev, &ppid, false);
 	if (!ret)
 		ret = sysfs_emit(buf, "%*phN\n", ppid.id_len, ppid.id);
 
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index a9555bfc372f..108995b6eced 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -1448,7 +1448,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev)
 	struct netdev_phys_item_id ppid = { };
 	int err;
 
-	err = dev_get_port_parent_id(dev, &ppid, false);
+	err = netif_get_port_parent_id(dev, &ppid, false);
 	if (err) {
 		if (err == -EOPNOTSUPP)
 			return 0;
diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c
index 3a2044e6033d..e86a8a862c41 100644
--- a/net/ipv4/ipmr.c
+++ b/net/ipv4/ipmr.c
@@ -901,7 +901,7 @@ static int vif_add(struct net *net, struct mr_table *mrt,
 			vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0),
 			(VIFF_TUNNEL | VIFF_REGISTER));
 
-	err = dev_get_port_parent_id(dev, &ppid, true);
+	err = netif_get_port_parent_id(dev, &ppid, true);
 	if (err == 0) {
 		memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len);
 		v->dev_parent_id.id_len = ppid.id_len;
-- 
cgit v1.2.3


From af1d017377c1c1931bfb898e719ab712cf79f944 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 17 Jul 2025 10:23:28 -0700
Subject: net: s/dev_get_mac_address/netif_get_mac_address/

Commit cc34acd577f1 ("docs: net: document new locking reality")
introduced netif_ vs dev_ function semantics: the former expects locked
netdev, the latter takes care of the locking. We don't strictly
follow this semantics on either side, but there are more dev_xxx handlers
now that don't fit. Rename them to netif_xxx where appropriate.

netif_get_mac_address is used only by tun/tap, so move it into
NETDEV_INTERNAL namespace.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250717172333.1288349-3-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/tap.c         | 5 +++--
 drivers/net/tun.c         | 3 ++-
 include/linux/netdevice.h | 2 +-
 net/core/dev.c            | 4 ++--
 net/core/dev_ioctl.c      | 3 ++-
 net/core/net-sysfs.c      | 2 +-
 6 files changed, 11 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/tap.c b/drivers/net/tap.c
index d82eb7276a8b..1197f245e873 100644
--- a/drivers/net/tap.c
+++ b/drivers/net/tap.c
@@ -1000,8 +1000,8 @@ static long tap_ioctl(struct file *file, unsigned int cmd,
 			return -ENOLINK;
 		}
 		ret = 0;
-		dev_get_mac_address((struct sockaddr *)&ss, dev_net(tap->dev),
-				    tap->dev->name);
+		netif_get_mac_address((struct sockaddr *)&ss, dev_net(tap->dev),
+				      tap->dev->name);
 		if (copy_to_user(&ifr->ifr_name, tap->dev->name, IFNAMSIZ) ||
 		    copy_to_user(&ifr->ifr_hwaddr, &ss, sizeof(ifr->ifr_hwaddr)))
 			ret = -EFAULT;
@@ -1282,3 +1282,4 @@ MODULE_DESCRIPTION("Common library for drivers implementing the TAP interface");
 MODULE_AUTHOR("Arnd Bergmann <arnd@arndb.de>");
 MODULE_AUTHOR("Sainath Grandhi <sainath.grandhi@intel.com>");
 MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index e65228ba3fae..cc6c50180663 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -3223,7 +3223,7 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd,
 
 	case SIOCGIFHWADDR:
 		/* Get hw address */
-		dev_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name);
+		netif_get_mac_address(&ifr.ifr_hwaddr, net, tun->dev->name);
 		if (copy_to_user(argp, &ifr, ifreq_len))
 			ret = -EFAULT;
 		break;
@@ -3732,3 +3732,4 @@ MODULE_AUTHOR(DRV_COPYRIGHT);
 MODULE_LICENSE("GPL");
 MODULE_ALIAS_MISCDEV(TUN_MINOR);
 MODULE_ALIAS("devname:net/tun");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c6ba4ea66039..b3a48934b4cb 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4222,7 +4222,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 			struct netlink_ext_ack *extack);
 int dev_set_mac_address_user(struct net_device *dev, struct sockaddr_storage *ss,
 			     struct netlink_ext_ack *extack);
-int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
+int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name);
 int netif_get_port_parent_id(struct net_device *dev,
 			     struct netdev_phys_item_id *ppid, bool recurse);
 bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b);
diff --git a/net/core/dev.c b/net/core/dev.c
index 4979a9197b18..d71f03874057 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9765,7 +9765,7 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 DECLARE_RWSEM(dev_addr_sem);
 
 /* "sa" is a true struct sockaddr with limited "sa_data" member. */
-int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
+int netif_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name)
 {
 	size_t size = sizeof(sa->sa_data_min);
 	struct net_device *dev;
@@ -9791,7 +9791,7 @@ unlock:
 	up_read(&dev_addr_sem);
 	return ret;
 }
-EXPORT_SYMBOL(dev_get_mac_address);
+EXPORT_SYMBOL_NS_GPL(netif_get_mac_address, "NETDEV_INTERNAL");
 
 int netif_change_carrier(struct net_device *dev, bool new_carrier)
 {
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index 616479e71466..ceb2d63a818a 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -728,7 +728,8 @@ int dev_ioctl(struct net *net, unsigned int cmd, struct ifreq *ifr,
 	switch (cmd) {
 	case SIOCGIFHWADDR:
 		dev_load(net, ifr->ifr_name);
-		ret = dev_get_mac_address(&ifr->ifr_hwaddr, net, ifr->ifr_name);
+		ret = netif_get_mac_address(&ifr->ifr_hwaddr, net,
+					    ifr->ifr_name);
 		if (colon)
 			*colon = ':';
 		return ret;
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index f7a6cc7aea79..e41ad1890e49 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -256,7 +256,7 @@ static ssize_t name_assign_type_show(struct device *dev,
 }
 static DEVICE_ATTR_RO(name_assign_type);
 
-/* use same locking rules as GIFHWADDR ioctl's (dev_get_mac_address()) */
+/* use same locking rules as GIFHWADDR ioctl's (netif_get_mac_address()) */
 static ssize_t address_show(struct device *dev, struct device_attribute *attr,
 			    char *buf)
 {
-- 
cgit v1.2.3


From 0413a34ef678c3e2f0fafb4e113e810a05197030 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 17 Jul 2025 10:23:29 -0700
Subject: net: s/dev_pre_changeaddr_notify/netif_pre_changeaddr_notify/

Commit cc34acd577f1 ("docs: net: document new locking reality")
introduced netif_ vs dev_ function semantics: the former expects locked
netdev, the latter takes care of the locking. We don't strictly
follow this semantics on either side, but there are more dev_xxx handlers
now that don't fit. Rename them to netif_xxx where appropriate.

netif_pre_changeaddr_notify is used only by ipvlan/bond, so move it into
NETDEV_INTERNAL namespace.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250717172333.1288349-4-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c  |  3 ++-
 drivers/net/ipvlan/ipvlan_main.c |  7 ++++---
 include/linux/netdevice.h        |  4 ++--
 net/bridge/br.c                  |  7 ++++---
 net/bridge/br_if.c               |  3 ++-
 net/core/dev.c                   | 18 ++++++++++--------
 net/core/dev_addr_lists.c        |  2 +-
 7 files changed, 25 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 17c7542be6a5..d8281c486a44 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -1040,7 +1040,7 @@ static int bond_set_dev_addr(struct net_device *bond_dev,
 
 	slave_dbg(bond_dev, slave_dev, "bond_dev=%p slave_dev=%p slave_dev->addr_len=%d\n",
 		  bond_dev, slave_dev, slave_dev->addr_len);
-	err = dev_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL);
+	err = netif_pre_changeaddr_notify(bond_dev, slave_dev->dev_addr, NULL);
 	if (err)
 		return err;
 
@@ -6743,3 +6743,4 @@ module_exit(bonding_exit);
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION(DRV_DESCRIPTION);
 MODULE_AUTHOR("Thomas Davis, tadavis@lbl.gov and many others");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/drivers/net/ipvlan/ipvlan_main.c b/drivers/net/ipvlan/ipvlan_main.c
index 0ed2fd833a5d..660f3db11766 100644
--- a/drivers/net/ipvlan/ipvlan_main.c
+++ b/drivers/net/ipvlan/ipvlan_main.c
@@ -784,9 +784,9 @@ static int ipvlan_device_event(struct notifier_block *unused,
 	case NETDEV_PRE_CHANGEADDR:
 		prechaddr_info = ptr;
 		list_for_each_entry(ipvlan, &port->ipvlans, pnode) {
-			err = dev_pre_changeaddr_notify(ipvlan->dev,
-						    prechaddr_info->dev_addr,
-						    extack);
+			err = netif_pre_changeaddr_notify(ipvlan->dev,
+							  prechaddr_info->dev_addr,
+							  extack);
 			if (err)
 				return notifier_from_errno(err);
 		}
@@ -1094,3 +1094,4 @@ MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Mahesh Bandewar <maheshb@google.com>");
 MODULE_DESCRIPTION("Driver for L3 (IPv6/IPv4) based VLANs");
 MODULE_ALIAS_RTNL_LINK("ipvlan");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b3a48934b4cb..55c5cd9d1929 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4214,8 +4214,8 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net,
 int __dev_set_mtu(struct net_device *, int);
 int netif_set_mtu(struct net_device *dev, int new_mtu);
 int dev_set_mtu(struct net_device *, int);
-int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
-			      struct netlink_ext_ack *extack);
+int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr,
+				struct netlink_ext_ack *extack);
 int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 			  struct netlink_ext_ack *extack);
 int dev_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
diff --git a/net/bridge/br.c b/net/bridge/br.c
index 0adeafe11a36..1885d0c315f0 100644
--- a/net/bridge/br.c
+++ b/net/bridge/br.c
@@ -74,9 +74,9 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v
 		if (br->dev->addr_assign_type == NET_ADDR_SET)
 			break;
 		prechaddr_info = ptr;
-		err = dev_pre_changeaddr_notify(br->dev,
-						prechaddr_info->dev_addr,
-						extack);
+		err = netif_pre_changeaddr_notify(br->dev,
+						  prechaddr_info->dev_addr,
+						  extack);
 		if (err)
 			return notifier_from_errno(err);
 		break;
@@ -484,3 +484,4 @@ MODULE_LICENSE("GPL");
 MODULE_VERSION(BR_VERSION);
 MODULE_ALIAS_RTNL_LINK("bridge");
 MODULE_DESCRIPTION("Ethernet bridge driver");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c
index 2450690f98cf..98c5b9c3145f 100644
--- a/net/bridge/br_if.c
+++ b/net/bridge/br_if.c
@@ -668,7 +668,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev,
 		/* Ask for permission to use this MAC address now, even if we
 		 * don't end up choosing it below.
 		 */
-		err = dev_pre_changeaddr_notify(br->dev, dev->dev_addr, extack);
+		err = netif_pre_changeaddr_notify(br->dev, dev->dev_addr,
+						  extack);
 		if (err)
 			goto err6;
 	}
diff --git a/net/core/dev.c b/net/core/dev.c
index d71f03874057..a47754fa7b15 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9716,13 +9716,15 @@ void netif_set_group(struct net_device *dev, int new_group)
 }
 
 /**
- *	dev_pre_changeaddr_notify - Call NETDEV_PRE_CHANGEADDR.
- *	@dev: device
- *	@addr: new address
- *	@extack: netlink extended ack
+ * netif_pre_changeaddr_notify() - Call NETDEV_PRE_CHANGEADDR.
+ * @dev: device
+ * @addr: new address
+ * @extack: netlink extended ack
+ *
+ * Return: 0 on success, -errno on failure.
  */
-int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
-			      struct netlink_ext_ack *extack)
+int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr,
+				struct netlink_ext_ack *extack)
 {
 	struct netdev_notifier_pre_changeaddr_info info = {
 		.info.dev = dev,
@@ -9734,7 +9736,7 @@ int dev_pre_changeaddr_notify(struct net_device *dev, const char *addr,
 	rc = call_netdevice_notifiers_info(NETDEV_PRE_CHANGEADDR, &info.info);
 	return notifier_to_errno(rc);
 }
-EXPORT_SYMBOL(dev_pre_changeaddr_notify);
+EXPORT_SYMBOL_NS_GPL(netif_pre_changeaddr_notify, "NETDEV_INTERNAL");
 
 int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 			  struct netlink_ext_ack *extack)
@@ -9748,7 +9750,7 @@ int netif_set_mac_address(struct net_device *dev, struct sockaddr_storage *ss,
 		return -EINVAL;
 	if (!netif_device_present(dev))
 		return -ENODEV;
-	err = dev_pre_changeaddr_notify(dev, ss->__data, extack);
+	err = netif_pre_changeaddr_notify(dev, ss->__data, extack);
 	if (err)
 		return err;
 	if (memcmp(dev->dev_addr, ss->__data, dev->addr_len)) {
diff --git a/net/core/dev_addr_lists.c b/net/core/dev_addr_lists.c
index 90716bd736f3..76c91f224886 100644
--- a/net/core/dev_addr_lists.c
+++ b/net/core/dev_addr_lists.c
@@ -603,7 +603,7 @@ int dev_addr_add(struct net_device *dev, const unsigned char *addr,
 
 	ASSERT_RTNL();
 
-	err = dev_pre_changeaddr_notify(dev, addr, NULL);
+	err = netif_pre_changeaddr_notify(dev, addr, NULL);
 	if (err)
 		return err;
 	err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type);
-- 
cgit v1.2.3


From 303a8487a657c357ca6abc06a4045f72cdae90d5 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 17 Jul 2025 10:23:30 -0700
Subject: net: s/__dev_set_mtu/__netif_set_mtu/

Commit cc34acd577f1 ("docs: net: document new locking reality")
introduced netif_ vs dev_ function semantics: the former expects locked
netdev, the latter takes care of the locking. We don't strictly
follow this semantics on either side, but there are more dev_xxx handlers
now that don't fit. Rename them to netif_xxx where appropriate.

__netif_set_mtu is used only by bond, so move it into
NETDEV_INTERNAL namespace.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250717172333.1288349-5-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/bonding/bond_main.c |  2 +-
 include/linux/netdevice.h       |  2 +-
 net/core/dev.c                  | 22 +++++++++++++---------
 3 files changed, 15 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index d8281c486a44..257333c88710 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -2669,7 +2669,7 @@ static int __bond_release_one(struct net_device *bond_dev,
 
 	if (unregister) {
 		netdev_lock_ops(slave_dev);
-		__dev_set_mtu(slave_dev, slave->original_mtu);
+		__netif_set_mtu(slave_dev, slave->original_mtu);
 		netdev_unlock_ops(slave_dev);
 	} else {
 		dev_set_mtu(slave_dev, slave->original_mtu);
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 55c5cd9d1929..8978fbfbd644 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4211,7 +4211,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net,
 			       struct netlink_ext_ack *extack);
 int dev_change_net_namespace(struct net_device *dev, struct net *net,
 			     const char *pat);
-int __dev_set_mtu(struct net_device *, int);
+int __netif_set_mtu(struct net_device *dev, int new_mtu);
 int netif_set_mtu(struct net_device *dev, int new_mtu);
 int dev_set_mtu(struct net_device *, int);
 int netif_pre_changeaddr_notify(struct net_device *dev, const char *addr,
diff --git a/net/core/dev.c b/net/core/dev.c
index a47754fa7b15..a056f0dfc516 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9594,7 +9594,7 @@ int netif_change_flags(struct net_device *dev, unsigned int flags,
 	return ret;
 }
 
-int __dev_set_mtu(struct net_device *dev, int new_mtu)
+int __netif_set_mtu(struct net_device *dev, int new_mtu)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
 
@@ -9605,7 +9605,7 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu)
 	WRITE_ONCE(dev->mtu, new_mtu);
 	return 0;
 }
-EXPORT_SYMBOL(__dev_set_mtu);
+EXPORT_SYMBOL_NS_GPL(__netif_set_mtu, "NETDEV_INTERNAL");
 
 int dev_validate_mtu(struct net_device *dev, int new_mtu,
 		     struct netlink_ext_ack *extack)
@@ -9624,18 +9624,22 @@ int dev_validate_mtu(struct net_device *dev, int new_mtu,
 }
 
 /**
- *	netif_set_mtu_ext - Change maximum transfer unit
- *	@dev: device
- *	@new_mtu: new transfer unit
- *	@extack: netlink extended ack
+ * netif_set_mtu_ext() - Change maximum transfer unit
+ * @dev: device
+ * @new_mtu: new transfer unit
+ * @extack: netlink extended ack
  *
- *	Change the maximum transfer size of the network device.
+ * Change the maximum transfer size of the network device.
+ *
+ * Return: 0 on success, -errno on failure.
  */
 int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
 		      struct netlink_ext_ack *extack)
 {
 	int err, orig_mtu;
 
+	netdev_ops_assert_locked(dev);
+
 	if (new_mtu == dev->mtu)
 		return 0;
 
@@ -9652,7 +9656,7 @@ int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
 		return err;
 
 	orig_mtu = dev->mtu;
-	err = __dev_set_mtu(dev, new_mtu);
+	err = __netif_set_mtu(dev, new_mtu);
 
 	if (!err) {
 		err = call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
@@ -9662,7 +9666,7 @@ int netif_set_mtu_ext(struct net_device *dev, int new_mtu,
 			/* setting mtu back and notifying everyone again,
 			 * so that they have a chance to revert changes.
 			 */
-			__dev_set_mtu(dev, orig_mtu);
+			__netif_set_mtu(dev, orig_mtu);
 			call_netdevice_notifiers_mtu(NETDEV_CHANGEMTU, dev,
 						     new_mtu);
 		}
-- 
cgit v1.2.3


From 93893a57efd431b9b4e72359bc8a8428681ca688 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 17 Jul 2025 10:23:31 -0700
Subject: net: s/dev_get_flags/netif_get_flags/

Commit cc34acd577f1 ("docs: net: document new locking reality")
introduced netif_ vs dev_ function semantics: the former expects locked
netdev, the latter takes care of the locking. We don't strictly
follow this semantics on either side, but there are more dev_xxx handlers
now that don't fit. Rename them to netif_xxx where appropriate.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250717172333.1288349-6-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/infiniband/sw/rxe/rxe_verbs.c |  2 +-
 fs/smb/server/smb2pdu.c               |  2 +-
 include/linux/netdevice.h             |  2 +-
 net/8021q/vlan.c                      |  2 +-
 net/bridge/br_netlink.c               |  2 +-
 net/core/dev.c                        | 10 +++++-----
 net/core/dev_ioctl.c                  |  2 +-
 net/core/rtnetlink.c                  |  4 ++--
 net/ipv4/fib_frontend.c               |  2 +-
 net/ipv4/fib_semantics.c              |  2 +-
 net/ipv4/nexthop.c                    |  2 +-
 net/ipv6/addrconf.c                   |  2 +-
 net/mpls/af_mpls.c                    |  6 +++---
 net/wireless/wext-core.c              |  2 +-
 14 files changed, 21 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/infiniband/sw/rxe/rxe_verbs.c b/drivers/infiniband/sw/rxe/rxe_verbs.c
index 2331e698a65b..4f86b56fee26 100644
--- a/drivers/infiniband/sw/rxe/rxe_verbs.c
+++ b/drivers/infiniband/sw/rxe/rxe_verbs.c
@@ -65,7 +65,7 @@ static int rxe_query_port(struct ib_device *ibdev,
 	attr->state = ib_get_curr_port_state(ndev);
 	if (attr->state == IB_PORT_ACTIVE)
 		attr->phys_state = IB_PORT_PHYS_STATE_LINK_UP;
-	else if (dev_get_flags(ndev) & IFF_UP)
+	else if (netif_get_flags(ndev) & IFF_UP)
 		attr->phys_state = IB_PORT_PHYS_STATE_POLLING;
 	else
 		attr->phys_state = IB_PORT_PHYS_STATE_DISABLED;
diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
index 63d17cea2e95..fca92d1fea22 100644
--- a/fs/smb/server/smb2pdu.c
+++ b/fs/smb/server/smb2pdu.c
@@ -7847,7 +7847,7 @@ static int fsctl_query_iface_info_ioctl(struct ksmbd_conn *conn,
 		if (!ksmbd_find_netdev_name_iface_list(netdev->name))
 			continue;
 
-		flags = dev_get_flags(netdev);
+		flags = netif_get_flags(netdev);
 		if (!(flags & IFF_RUNNING))
 			continue;
 ipv6_retry:
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8978fbfbd644..8370cd0f8f6b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -4196,7 +4196,7 @@ int generic_hwtstamp_set_lower(struct net_device *dev,
 			       struct kernel_hwtstamp_config *kernel_cfg,
 			       struct netlink_ext_ack *extack);
 int dev_ethtool(struct net *net, struct ifreq *ifr, void __user *userdata);
-unsigned int dev_get_flags(const struct net_device *);
+unsigned int netif_get_flags(const struct net_device *dev);
 int __dev_change_flags(struct net_device *dev, unsigned int flags,
 		       struct netlink_ext_ack *extack);
 int netif_change_flags(struct net_device *dev, unsigned int flags,
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 9a6df8c1daf9..7ffd3386a842 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -483,7 +483,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 	case NETDEV_UP:
 		/* Put all VLANs for this dev in the up state too.  */
 		vlan_group_for_each_dev(grp, i, vlandev) {
-			flgs = dev_get_flags(vlandev);
+			flgs = netif_get_flags(vlandev);
 			if (flgs & IFF_UP)
 				continue;
 
diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c
index 6e337937d0d7..4e2d53b27221 100644
--- a/net/bridge/br_netlink.c
+++ b/net/bridge/br_netlink.c
@@ -479,7 +479,7 @@ static int br_fill_ifinfo(struct sk_buff *skb,
 	hdr->__ifi_pad = 0;
 	hdr->ifi_type = dev->type;
 	hdr->ifi_index = dev->ifindex;
-	hdr->ifi_flags = dev_get_flags(dev);
+	hdr->ifi_flags = netif_get_flags(dev);
 	hdr->ifi_change = 0;
 
 	if (nla_put_string(skb, IFLA_IFNAME, dev->name) ||
diff --git a/net/core/dev.c b/net/core/dev.c
index a056f0dfc516..25905bbf1972 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -9454,12 +9454,12 @@ void dev_set_rx_mode(struct net_device *dev)
 }
 
 /**
- *	dev_get_flags - get flags reported to userspace
- *	@dev: device
+ * netif_get_flags() - get flags reported to userspace
+ * @dev: device
  *
- *	Get the combination of flag bits exported through APIs to userspace.
+ * Get the combination of flag bits exported through APIs to userspace.
  */
-unsigned int dev_get_flags(const struct net_device *dev)
+unsigned int netif_get_flags(const struct net_device *dev)
 {
 	unsigned int flags;
 
@@ -9482,7 +9482,7 @@ unsigned int dev_get_flags(const struct net_device *dev)
 
 	return flags;
 }
-EXPORT_SYMBOL(dev_get_flags);
+EXPORT_SYMBOL(netif_get_flags);
 
 int __dev_change_flags(struct net_device *dev, unsigned int flags,
 		       struct netlink_ext_ack *extack)
diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c
index ceb2d63a818a..9c0ad7f4b5d8 100644
--- a/net/core/dev_ioctl.c
+++ b/net/core/dev_ioctl.c
@@ -147,7 +147,7 @@ static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cm
 
 	switch (cmd) {
 	case SIOCGIFFLAGS:	/* Get interface flags */
-		ifr->ifr_flags = (short) dev_get_flags(dev);
+		ifr->ifr_flags = (short)netif_get_flags(dev);
 		return 0;
 
 	case SIOCGIFMETRIC:	/* Get the metric on the interface
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index 108995b6eced..094b085cff20 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -2038,7 +2038,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb,
 	ifm->__ifi_pad = 0;
 	ifm->ifi_type = READ_ONCE(dev->type);
 	ifm->ifi_index = READ_ONCE(dev->ifindex);
-	ifm->ifi_flags = dev_get_flags(dev);
+	ifm->ifi_flags = netif_get_flags(dev);
 	ifm->ifi_change = change;
 
 	if (tgt_netnsid >= 0 && nla_put_s32(skb, IFLA_TARGET_NETNSID, tgt_netnsid))
@@ -5227,7 +5227,7 @@ int ndo_dflt_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq,
 	ifm->__ifi_pad = 0;
 	ifm->ifi_type = dev->type;
 	ifm->ifi_index = dev->ifindex;
-	ifm->ifi_flags = dev_get_flags(dev);
+	ifm->ifi_flags = netif_get_flags(dev);
 	ifm->ifi_change = 0;
 
 
diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c
index fd1e1507a224..6e1b94796f67 100644
--- a/net/ipv4/fib_frontend.c
+++ b/net/ipv4/fib_frontend.c
@@ -1524,7 +1524,7 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo
 		fib_disable_ip(dev, event, false);
 		break;
 	case NETDEV_CHANGE:
-		flags = dev_get_flags(dev);
+		flags = netif_get_flags(dev);
 		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
 			fib_sync_up(dev, RTNH_F_LINKDOWN);
 		else
diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
index a2f04992f579..a5f3c8459758 100644
--- a/net/ipv4/fib_semantics.c
+++ b/net/ipv4/fib_semantics.c
@@ -2087,7 +2087,7 @@ int fib_sync_up(struct net_device *dev, unsigned char nh_flags)
 		return 0;
 
 	if (nh_flags & RTNH_F_DEAD) {
-		unsigned int flags = dev_get_flags(dev);
+		unsigned int flags = netif_get_flags(dev);
 
 		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
 			nh_flags |= RTNH_F_LINKDOWN;
diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
index e808801ab9b8..29118c43ebf5 100644
--- a/net/ipv4/nexthop.c
+++ b/net/ipv4/nexthop.c
@@ -3884,7 +3884,7 @@ static int nh_netdev_event(struct notifier_block *this,
 		nexthop_flush_dev(dev, event);
 		break;
 	case NETDEV_CHANGE:
-		if (!(dev_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP)))
+		if (!(netif_get_flags(dev) & (IFF_RUNNING | IFF_LOWER_UP)))
 			nexthop_flush_dev(dev, event);
 		break;
 	case NETDEV_CHANGEMTU:
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index c85b1db74b1a..4f1d7d110302 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -6072,7 +6072,7 @@ static int inet6_fill_ifinfo(struct sk_buff *skb, struct inet6_dev *idev,
 	hdr->ifi_type = dev->type;
 	ifindex = READ_ONCE(dev->ifindex);
 	hdr->ifi_index = ifindex;
-	hdr->ifi_flags = dev_get_flags(dev);
+	hdr->ifi_flags = netif_get_flags(dev);
 	hdr->ifi_change = 0;
 
 	iflink = dev_get_iflink(dev);
diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c
index 47d7dfd9ad09..25c88cba5c48 100644
--- a/net/mpls/af_mpls.c
+++ b/net/mpls/af_mpls.c
@@ -706,7 +706,7 @@ static int mpls_nh_assign_dev(struct net *net, struct mpls_route *rt,
 	} else {
 		unsigned int flags;
 
-		flags = dev_get_flags(dev);
+		flags = netif_get_flags(dev);
 		if (!(flags & (IFF_RUNNING | IFF_LOWER_UP)))
 			nh->nh_flags |= RTNH_F_LINKDOWN;
 	}
@@ -1616,14 +1616,14 @@ static int mpls_dev_notify(struct notifier_block *this, unsigned long event,
 			return notifier_from_errno(err);
 		break;
 	case NETDEV_UP:
-		flags = dev_get_flags(dev);
+		flags = netif_get_flags(dev);
 		if (flags & (IFF_RUNNING | IFF_LOWER_UP))
 			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
 		else
 			mpls_ifup(dev, RTNH_F_DEAD);
 		break;
 	case NETDEV_CHANGE:
-		flags = dev_get_flags(dev);
+		flags = netif_get_flags(dev);
 		if (flags & (IFF_RUNNING | IFF_LOWER_UP)) {
 			mpls_ifup(dev, RTNH_F_DEAD | RTNH_F_LINKDOWN);
 		} else {
diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c
index bea70eb6f034..c32a7c6903d5 100644
--- a/net/wireless/wext-core.c
+++ b/net/wireless/wext-core.c
@@ -431,7 +431,7 @@ static struct nlmsghdr *rtnetlink_ifinfo_prep(struct net_device *dev,
 	r->__ifi_pad = 0;
 	r->ifi_type = dev->type;
 	r->ifi_index = dev->ifindex;
-	r->ifi_flags = dev_get_flags(dev);
+	r->ifi_flags = netif_get_flags(dev);
 	r->ifi_change = 0;	/* Wireless changes don't affect those flags */
 
 	if (nla_put_string(skb, IFLA_IFNAME, dev->name))
-- 
cgit v1.2.3


From 5d4d84618e1aa2c9531afa3a6323f56e1db4dcf7 Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 17 Jul 2025 10:23:32 -0700
Subject: net: s/dev_set_threaded/netif_set_threaded/

Commit cc34acd577f1 ("docs: net: document new locking reality")
introduced netif_ vs dev_ function semantics: the former expects locked
netdev, the latter takes care of the locking. We don't strictly
follow this semantics on either side, but there are more dev_xxx handlers
now that don't fit. Rename them to netif_xxx where appropriate.

Note that one dev_set_threaded call still remains in mt76 for debugfs file.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250717172333.1288349-7-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/net_cachelines/net_device.rst |  2 +-
 drivers/net/ethernet/atheros/atl1c/atl1c_main.c        |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/pci.c              |  2 +-
 drivers/net/ethernet/renesas/ravb_main.c               |  2 +-
 drivers/net/wireguard/device.c                         |  2 +-
 drivers/net/wireless/ath/ath10k/snoc.c                 |  2 +-
 include/linux/netdevice.h                              |  1 +
 net/core/dev.c                                         |  6 +++---
 net/core/dev_api.c                                     | 12 ++++++++++++
 net/core/net-sysfs.c                                   |  2 +-
 10 files changed, 23 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index c69cc89c958e..2d3dc4692d20 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -165,7 +165,7 @@ struct sfp_bus*                     sfp_bus
 struct lock_class_key*              qdisc_tx_busylock
 bool                                proto_down
 unsigned:1                          wol_enabled
-unsigned:1                          threaded                                                            napi_poll(napi_enable,dev_set_threaded)
+unsigned:1                          threaded                                                            napi_poll(napi_enable,netif_set_threaded)
 unsigned_long:1                     see_all_hwtstamp_requests
 unsigned_long:1                     change_proto_down
 unsigned_long:1                     netns_immutable
diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index ef1a51347351..3a9ad4a9c1cb 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2688,7 +2688,7 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->mii.mdio_write = atl1c_mdio_write;
 	adapter->mii.phy_id_mask = 0x1f;
 	adapter->mii.reg_num_mask = MDIO_CTRL_REG_MASK;
-	dev_set_threaded(netdev, true);
+	netif_set_threaded(netdev, true);
 	for (i = 0; i < adapter->rx_queue_count; ++i)
 		netif_napi_add(netdev, &adapter->rrd_ring[i].napi,
 			       atl1c_clean_rx);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index 058dcabfaa2e..a2e97b712a3d 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -156,7 +156,7 @@ static int mlxsw_pci_napi_devs_init(struct mlxsw_pci *mlxsw_pci)
 	}
 	strscpy(mlxsw_pci->napi_dev_rx->name, "mlxsw_rx",
 		sizeof(mlxsw_pci->napi_dev_rx->name));
-	dev_set_threaded(mlxsw_pci->napi_dev_rx, true);
+	netif_set_threaded(mlxsw_pci->napi_dev_rx, true);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index c9f4976a3527..4e79bf88688a 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -3075,7 +3075,7 @@ static int ravb_probe(struct platform_device *pdev)
 	if (info->coalesce_irqs) {
 		netdev_sw_irq_coalesce_default_on(ndev);
 		if (num_present_cpus() == 1)
-			dev_set_threaded(ndev, true);
+			netif_set_threaded(ndev, true);
 	}
 
 	/* Network device register */
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 4a529f1f9bea..5afec5a865f4 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -366,7 +366,7 @@ static int wg_newlink(struct net_device *dev,
 	if (ret < 0)
 		goto err_free_handshake_queue;
 
-	dev_set_threaded(dev, true);
+	netif_set_threaded(dev, true);
 	ret = register_netdevice(dev);
 	if (ret < 0)
 		goto err_uninit_ratelimiter;
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index d51f2e5a79a4..0ee68d3dad12 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -936,7 +936,7 @@ static int ath10k_snoc_hif_start(struct ath10k *ar)
 
 	bitmap_clear(ar_snoc->pending_ce_irqs, 0, CE_COUNT_MAX);
 
-	dev_set_threaded(ar->napi_dev, true);
+	netif_set_threaded(ar->napi_dev, true);
 	ath10k_core_napi_enable(ar);
 	/* IRQs are left enabled when we restart due to a firmware crash */
 	if (!test_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags))
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 8370cd0f8f6b..7929ddfd4433 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -589,6 +589,7 @@ static inline bool napi_complete(struct napi_struct *n)
 	return napi_complete_done(n, 0);
 }
 
+int netif_set_threaded(struct net_device *dev, bool threaded);
 int dev_set_threaded(struct net_device *dev, bool threaded);
 
 void napi_disable(struct napi_struct *n);
diff --git a/net/core/dev.c b/net/core/dev.c
index 25905bbf1972..a22f26997b94 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -4798,7 +4798,7 @@ static inline void ____napi_schedule(struct softnet_data *sd,
 
 	if (test_bit(NAPI_STATE_THREADED, &napi->state)) {
 		/* Paired with smp_mb__before_atomic() in
-		 * napi_enable()/dev_set_threaded().
+		 * napi_enable()/netif_set_threaded().
 		 * Use READ_ONCE() to guarantee a complete
 		 * read on napi->thread. Only call
 		 * wake_up_process() when it's not NULL.
@@ -6990,7 +6990,7 @@ int napi_set_threaded(struct napi_struct *napi, bool threaded)
 	return 0;
 }
 
-int dev_set_threaded(struct net_device *dev, bool threaded)
+int netif_set_threaded(struct net_device *dev, bool threaded)
 {
 	struct napi_struct *napi;
 	int err = 0;
@@ -7031,7 +7031,7 @@ int dev_set_threaded(struct net_device *dev, bool threaded)
 
 	return err;
 }
-EXPORT_SYMBOL(dev_set_threaded);
+EXPORT_SYMBOL(netif_set_threaded);
 
 /**
  * netif_queue_set_napi - Associate queue with the napi
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index 1bf0153195f2..dd7f57013ce5 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -367,3 +367,15 @@ void netdev_state_change(struct net_device *dev)
 	netdev_unlock_ops(dev);
 }
 EXPORT_SYMBOL(netdev_state_change);
+
+int dev_set_threaded(struct net_device *dev, bool threaded)
+{
+	int ret;
+
+	netdev_lock(dev);
+	ret = netif_set_threaded(dev, threaded);
+	netdev_unlock(dev);
+
+	return ret;
+}
+EXPORT_SYMBOL(dev_set_threaded);
diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
index e41ad1890e49..c28cd6665444 100644
--- a/net/core/net-sysfs.c
+++ b/net/core/net-sysfs.c
@@ -757,7 +757,7 @@ static int modify_napi_threaded(struct net_device *dev, unsigned long val)
 	if (val != 0 && val != 1)
 		return -EOPNOTSUPP;
 
-	ret = dev_set_threaded(dev, val);
+	ret = netif_set_threaded(dev, val);
 
 	return ret;
 }
-- 
cgit v1.2.3


From 88d3cec28274f9c15355835466c0c694e313680e Mon Sep 17 00:00:00 2001
From: Stanislav Fomichev <sdf@fomichev.me>
Date: Thu, 17 Jul 2025 10:23:33 -0700
Subject: net: s/dev_close_many/netif_close_many/

Commit cc34acd577f1 ("docs: net: document new locking reality")
introduced netif_ vs dev_ function semantics: the former expects locked
netdev, the latter takes care of the locking. We don't strictly
follow this semantics on either side, but there are more dev_xxx handlers
now that don't fit. Rename them to netif_xxx where appropriate.

netif_close_many is used only by vlan/dsa and one mtk driver, so move it into
NETDEV_INTERNAL namespace.

Signed-off-by: Stanislav Fomichev <sdf@fomichev.me>
Link: https://patch.msgid.link/20250717172333.1288349-8-sdf@fomichev.me
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mediatek/mtk_eth_soc.c |  3 ++-
 include/linux/netdevice.h                   |  2 +-
 net/8021q/vlan.c                            |  3 ++-
 net/core/dev.c                              | 10 +++++-----
 net/dsa/dsa.c                               |  3 ++-
 net/dsa/user.c                              |  2 +-
 6 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
index 11ee7e1829bf..5a5fcde76dc0 100644
--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
@@ -4967,7 +4967,7 @@ void mtk_eth_set_dma_device(struct mtk_eth *eth, struct device *dma_dev)
 		list_add_tail(&dev->close_list, &dev_list);
 	}
 
-	dev_close_many(&dev_list, false);
+	netif_close_many(&dev_list, false);
 
 	eth->dma_dev = dma_dev;
 
@@ -5610,3 +5610,4 @@ module_platform_driver(mtk_driver);
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("John Crispin <blogic@openwrt.org>");
 MODULE_DESCRIPTION("Ethernet driver for MediaTek SoC");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 7929ddfd4433..5aee8d3895f4 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -3343,7 +3343,7 @@ int netif_open(struct net_device *dev, struct netlink_ext_ack *extack);
 int dev_open(struct net_device *dev, struct netlink_ext_ack *extack);
 void netif_close(struct net_device *dev);
 void dev_close(struct net_device *dev);
-void dev_close_many(struct list_head *head, bool unlink);
+void netif_close_many(struct list_head *head, bool unlink);
 void netif_disable_lro(struct net_device *dev);
 void dev_disable_lro(struct net_device *dev);
 int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb);
diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c
index 7ffd3386a842..fda3a80e9340 100644
--- a/net/8021q/vlan.c
+++ b/net/8021q/vlan.c
@@ -470,7 +470,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event,
 				list_add(&vlandev->close_list, &close_list);
 		}
 
-		dev_close_many(&close_list, false);
+		netif_close_many(&close_list, false);
 
 		list_for_each_entry_safe(vlandev, tmp, &close_list, close_list) {
 			vlan_stacked_transfer_operstate(dev, vlandev,
@@ -765,3 +765,4 @@ module_exit(vlan_cleanup_module);
 MODULE_DESCRIPTION("802.1Q/802.1ad VLAN Protocol");
 MODULE_LICENSE("GPL");
 MODULE_VERSION(DRV_VERSION);
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/net/core/dev.c b/net/core/dev.c
index a22f26997b94..354d3453b407 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1768,7 +1768,7 @@ static void __dev_close(struct net_device *dev)
 	list_del(&single);
 }
 
-void dev_close_many(struct list_head *head, bool unlink)
+void netif_close_many(struct list_head *head, bool unlink)
 {
 	struct net_device *dev, *tmp;
 
@@ -1786,7 +1786,7 @@ void dev_close_many(struct list_head *head, bool unlink)
 			list_del_init(&dev->close_list);
 	}
 }
-EXPORT_SYMBOL(dev_close_many);
+EXPORT_SYMBOL_NS_GPL(netif_close_many, "NETDEV_INTERNAL");
 
 void netif_close(struct net_device *dev)
 {
@@ -1794,7 +1794,7 @@ void netif_close(struct net_device *dev)
 		LIST_HEAD(single);
 
 		list_add(&dev->close_list, &single);
-		dev_close_many(&single, true);
+		netif_close_many(&single, true);
 		list_del(&single);
 	}
 }
@@ -12099,7 +12099,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 			netdev_lock(dev);
 		}
 	}
-	dev_close_many(&close_head, true);
+	netif_close_many(&close_head, true);
 	/* ... now unlock them and go over the rest. */
 	list_for_each_entry(dev, head, unreg_list) {
 		if (netdev_need_ops_lock(dev))
@@ -12107,7 +12107,7 @@ void unregister_netdevice_many_notify(struct list_head *head,
 		else
 			list_add_tail(&dev->close_list, &close_head);
 	}
-	dev_close_many(&close_head, true);
+	netif_close_many(&close_head, true);
 
 	list_for_each_entry(dev, head, unreg_list) {
 		/* And unlink it from device chain. */
diff --git a/net/dsa/dsa.c b/net/dsa/dsa.c
index 436a7e1b412a..5b01a0e43ebe 100644
--- a/net/dsa/dsa.c
+++ b/net/dsa/dsa.c
@@ -1621,7 +1621,7 @@ void dsa_switch_shutdown(struct dsa_switch *ds)
 	dsa_switch_for_each_cpu_port(dp, ds)
 		list_add(&dp->conduit->close_list, &close_list);
 
-	dev_close_many(&close_list, true);
+	netif_close_many(&close_list, true);
 
 	dsa_switch_for_each_user_port(dp, ds) {
 		conduit = dsa_port_to_conduit(dp);
@@ -1829,3 +1829,4 @@ MODULE_AUTHOR("Lennert Buytenhek <buytenh@wantstofly.org>");
 MODULE_DESCRIPTION("Driver for Distributed Switch Architecture switch chips");
 MODULE_LICENSE("GPL");
 MODULE_ALIAS("platform:dsa");
+MODULE_IMPORT_NS("NETDEV_INTERNAL");
diff --git a/net/dsa/user.c b/net/dsa/user.c
index e9334520c54a..f59d66f0975d 100644
--- a/net/dsa/user.c
+++ b/net/dsa/user.c
@@ -3604,7 +3604,7 @@ static int dsa_user_netdevice_event(struct notifier_block *nb,
 			list_add(&dp->user->close_list, &close_list);
 		}
 
-		dev_close_many(&close_list, true);
+		netif_close_many(&close_list, true);
 
 		return NOTIFY_OK;
 	}
-- 
cgit v1.2.3


From 954c0d74129948eed5c8f4a6898d3d5b344c8b18 Mon Sep 17 00:00:00 2001
From: "Paul E. McKenney" <paulmck@kernel.org>
Date: Thu, 17 Jul 2025 11:55:41 -0700
Subject: srcu: Add guards for SRCU-fast readers

This adds the usual scoped_guard(srcu_fast, &my_srcu) and
guard(srcu_fast)(&my_srcu).

Suggested-by: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Paul E. McKenney <paulmck@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Neeraj Upadhyay (AMD) <neeraj.upadhyay@kernel.org>
---
 include/linux/srcu.h | 5 +++++
 1 file changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index cf711a0f440b..f179700fecaf 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -481,4 +481,9 @@ DEFINE_LOCK_GUARD_1(srcu, struct srcu_struct,
 		    srcu_read_unlock(_T->lock, _T->idx),
 		    int idx)
 
+DEFINE_LOCK_GUARD_1(srcu_fast, struct srcu_struct,
+		    _T->scp = srcu_read_lock_fast(_T->lock),
+		    srcu_read_unlock_fast(_T->lock, _T->scp),
+		    struct srcu_ctr __percpu *scp)
+
 #endif
-- 
cgit v1.2.3


From d2b5be741a5045272b9d711908eab017632ac022 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sat, 5 Jul 2025 10:49:58 -0700
Subject: mm/damon/sysfs: use DAMON core API damon_is_running()

DAMON core implements a static function to see if a given DAMON context is
running.  DAMON sysfs interface is implementing the same one on its own.
Make the core function non-static and reuse it from the DAMON sysfs
interface.

Link: https://lkml.kernel.org/r/20250705175000.56259-5-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h |  1 +
 mm/damon/core.c       |  8 +++++++-
 mm/damon/sysfs.c      | 14 ++------------
 3 files changed, 10 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index bb58e36f019e..e1fea3119538 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -934,6 +934,7 @@ static inline unsigned int damon_max_nr_accesses(const struct damon_attrs *attrs
 
 int damon_start(struct damon_ctx **ctxs, int nr_ctxs, bool exclusive);
 int damon_stop(struct damon_ctx **ctxs, int nr_ctxs);
+bool damon_is_running(struct damon_ctx *ctx);
 
 int damon_call(struct damon_ctx *ctx, struct damon_call_control *control);
 int damos_walk(struct damon_ctx *ctx, struct damos_walk_control *control);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index e8036254cc98..c66583869e95 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1311,7 +1311,13 @@ int damon_stop(struct damon_ctx **ctxs, int nr_ctxs)
 	return err;
 }
 
-static bool damon_is_running(struct damon_ctx *ctx)
+/**
+ * damon_is_running() - Returns if a given DAMON context is running.
+ * @ctx:	The DAMON context to see if running.
+ *
+ * Return: true if @ctx is running, false otherwise.
+ */
+bool damon_is_running(struct damon_ctx *ctx)
 {
 	bool running;
 
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index 1b1476b79cdb..79d65dcc9dd0 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1189,16 +1189,6 @@ static void damon_sysfs_kdamond_rm_dirs(struct damon_sysfs_kdamond *kdamond)
 	kobject_put(&kdamond->contexts->kobj);
 }
 
-static bool damon_sysfs_ctx_running(struct damon_ctx *ctx)
-{
-	bool running;
-
-	mutex_lock(&ctx->kdamond_lock);
-	running = ctx->kdamond != NULL;
-	mutex_unlock(&ctx->kdamond_lock);
-	return running;
-}
-
 /*
  * enum damon_sysfs_cmd - Commands for a specific kdamond.
  */
@@ -1275,7 +1265,7 @@ static ssize_t state_show(struct kobject *kobj, struct kobj_attribute *attr,
 	if (!ctx)
 		running = false;
 	else
-		running = damon_sysfs_ctx_running(ctx);
+		running = damon_is_running(ctx);
 
 	return sysfs_emit(buf, "%s\n", running ?
 			damon_sysfs_cmd_strs[DAMON_SYSFS_CMD_ON] :
@@ -1429,7 +1419,7 @@ static inline bool damon_sysfs_kdamond_running(
 		struct damon_sysfs_kdamond *kdamond)
 {
 	return kdamond->damon_ctx &&
-		damon_sysfs_ctx_running(kdamond->damon_ctx);
+		damon_is_running(kdamond->damon_ctx);
 }
 
 static int damon_sysfs_apply_inputs(struct damon_ctx *ctx,
-- 
cgit v1.2.3


From fdc5001b002eaca9989b5f3563245662fd1e4d40 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 4 Jun 2025 12:51:11 +0300
Subject: mm/vmstat: make MEMCG select VM_EVENT_COUNTERS

The vmstat_text array contains labels for counters displayed in
/proc/vmstat.  It is important to keep the labels in sync with the
counters.

There is a BUILD_BUG_ON() check in vmstat_start() that ensures the size of
the vmstat_text is not smaller than VM_EVENT_COUNTERS.  This helps to
catch cases where a new counter is added but the label is not.  However,
it does not help if a counter is removed but the label remains.

It would be nice to make the BUILD_BUG_ON() check more strict to catch
such cases.  However, when compiling with MEMCG enabled but
VM_EVENT_COUNTERS disabled, the vmstat_text array is larger than
NR_VMSTAT_ITEMS.

This issue arises because some elements of the vmstat_text array are
present when either MEMCG or VM_EVENT_COUNTERS is enabled, but
NR_VMSTAT_ITEMS only accounts for these elements if VM_EVENT_COUNTERS is
enabled.

Instead of adjusting the NR_VMSTAT_ITEMS definition to account for MEMCG,
make MEMCG select VM_EVENT_COUNTERS.  VM_EVENT_COUNTERS is enabled in most
configurations anyway.

Link: https://lkml.kernel.org/r/20250604095111.533783-1-kirill.shutemov@linux.intel.com
Fixes: ebc5d83d0443 ("mm/memcontrol: use vmstat names for printing statistics")
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Reported-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Randy Dunlap <rdunlap@infradead.org>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/vmstat.h | 4 ++--
 init/Kconfig           | 1 +
 mm/vmstat.c            | 4 ++--
 3 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/vmstat.h b/include/linux/vmstat.h
index b2ccb6845595..c287998908bf 100644
--- a/include/linux/vmstat.h
+++ b/include/linux/vmstat.h
@@ -507,7 +507,7 @@ static inline const char *lru_list_name(enum lru_list lru)
 	return node_stat_name(NR_LRU_BASE + lru) + 3; // skip "nr_"
 }
 
-#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
+#if defined(CONFIG_VM_EVENT_COUNTERS)
 static inline const char *vm_event_name(enum vm_event_item item)
 {
 	return vmstat_text[NR_VM_ZONE_STAT_ITEMS +
@@ -516,7 +516,7 @@ static inline const char *vm_event_name(enum vm_event_item item)
 			   NR_VM_STAT_ITEMS +
 			   item];
 }
-#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
+#endif /* CONFIG_VM_EVENT_COUNTERS */
 
 #ifdef CONFIG_MEMCG
 
diff --git a/init/Kconfig b/init/Kconfig
index 666783eb50ab..e9b88d527aeb 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -992,6 +992,7 @@ config MEMCG
 	select PAGE_COUNTER
 	select EVENTFD
 	select SLAB_OBJ_EXT
+	select VM_EVENT_COUNTERS
 	help
 	  Provides control over the memory footprint of tasks in a cgroup.
 
diff --git a/mm/vmstat.c b/mm/vmstat.c
index a78d70ddeacd..01d76216d65a 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1287,7 +1287,7 @@ const char * const vmstat_text[] = {
 	"nr_memmap_pages",
 	"nr_memmap_boot_pages",
 
-#if defined(CONFIG_VM_EVENT_COUNTERS) || defined(CONFIG_MEMCG)
+#if defined(CONFIG_VM_EVENT_COUNTERS)
 	/* enum vm_event_item counters */
 	"pgpgin",
 	"pgpgout",
@@ -1475,7 +1475,7 @@ const char * const vmstat_text[] = {
 	"kstack_rest",
 #endif
 #endif
-#endif /* CONFIG_VM_EVENT_COUNTERS || CONFIG_MEMCG */
+#endif /* CONFIG_VM_EVENT_COUNTERS */
 };
 #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA || CONFIG_MEMCG */
 
-- 
cgit v1.2.3


From 8356a5a3b078ca89c526dd6d71e9a76fec571c37 Mon Sep 17 00:00:00 2001
From: Vlastimil Babka <vbabka@suse.cz>
Date: Wed, 25 Jun 2025 17:51:52 +0200
Subject: mm, vmstat: remove the NR_WRITEBACK_TEMP node_stat_item counter

The only user of the counter (FUSE) was removed in commit 0c58a97f919c
("fuse: remove tmp folio for writebacks and internal rb tree") so follow
the established pattern of removing the counter and hardcoding 0 in
meminfo output, as done recently with NR_BOUNCE.  Update documentation for
procfs, including for the value for Bounce that was missed when removing
its counter.

Also remove the mention of NR_WRITEBACK_TEMP implications from a comment
in wb_position_ratio(). The rest of the comment there about fuse setting
bdi->max_ratio to 1% is still correct.

[vbabka@suse.cz: v2]
  Link: https://lkml.kernel.org/r/5a848e15-6a57-4ecb-a015-d4f358b8a5d3@suse.cz
Link: https://lkml.kernel.org/r/20250625-nr_writeback_removal-v1-1-7f2a0df70faa@suse.cz
Signed-off-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Brendan Jackman <jackmanb@google.com>
Cc: Danilo Krummrich <dakr@kernel.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jeff Layton <jlayton@kernel.org>
Cc: Jeffle Xu <jefflexu@linux.alibaba.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Joanne Koong <joannelkoong@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kirill A. Shuemov <kirill.shutemov@linux.intel.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Maxim Patlasov <mpatlasov@parallels.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Miklos Szeredi <mszeredi@redhat.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zach O'Keefe <zokeefe@google.com>
Cc: Zi Yan <ziy@nvidia.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/filesystems/proc.rst | 8 +++++---
 drivers/base/node.c                | 2 +-
 fs/proc/meminfo.c                  | 3 +--
 include/linux/mmzone.h             | 1 -
 mm/page-writeback.c                | 4 +---
 mm/show_mem.c                      | 2 --
 mm/vmstat.c                        | 1 -
 7 files changed, 8 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/filesystems/proc.rst b/Documentation/filesystems/proc.rst
index 5236cb52e357..2971551b7235 100644
--- a/Documentation/filesystems/proc.rst
+++ b/Documentation/filesystems/proc.rst
@@ -1196,12 +1196,14 @@ SecPageTables
               Memory consumed by secondary page tables, this currently includes
               KVM mmu and IOMMU allocations on x86 and arm64.
 NFS_Unstable
-              Always zero. Previous counted pages which had been written to
+              Always zero. Previously counted pages which had been written to
               the server, but has not been committed to stable storage.
 Bounce
-              Memory used for block device "bounce buffers"
+              Always zero. Previously memory used for block device
+              "bounce buffers".
 WritebackTmp
-              Memory used by FUSE for temporary writeback buffers
+              Always zero. Previously memory used by FUSE for temporary
+              writeback buffers.
 CommitLimit
               Based on the overcommit ratio ('vm.overcommit_ratio'),
               this is the total amount of  memory currently available to
diff --git a/drivers/base/node.c b/drivers/base/node.c
index 6d66382dae65..e434cb260e61 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -500,7 +500,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 			     nid, K(node_page_state(pgdat, NR_SECONDARY_PAGETABLE)),
 			     nid, 0UL,
 			     nid, 0UL,
-			     nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
+			     nid, 0UL,
 			     nid, K(sreclaimable +
 				    node_page_state(pgdat, NR_KERNEL_MISC_RECLAIMABLE)),
 			     nid, K(sreclaimable + sunreclaimable),
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index bc2bc60c36cc..a458f1e112fd 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -121,8 +121,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 
 	show_val_kb(m, "NFS_Unstable:   ", 0);
 	show_val_kb(m, "Bounce:         ", 0);
-	show_val_kb(m, "WritebackTmp:   ",
-		    global_node_page_state(NR_WRITEBACK_TEMP));
+	show_val_kb(m, "WritebackTmp:   ", 0);
 	show_val_kb(m, "CommitLimit:    ", vm_commit_limit());
 	show_val_kb(m, "Committed_AS:   ", committed);
 	seq_printf(m, "VmallocTotal:   %8lu kB\n",
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 1d1bb2b7f40d..0c5da9141983 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -206,7 +206,6 @@ enum node_stat_item {
 	NR_FILE_PAGES,
 	NR_FILE_DIRTY,
 	NR_WRITEBACK,
-	NR_WRITEBACK_TEMP,	/* Writeback using temporary buffers */
 	NR_SHMEM,		/* shmem pages (included tmpfs/GEM pages) */
 	NR_SHMEM_THPS,
 	NR_SHMEM_PMDMAPPED,
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index 72b0ff0d4bae..3e248d1c3969 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -1101,9 +1101,7 @@ static void wb_position_ratio(struct dirty_throttle_control *dtc)
 	 * such filesystems balance_dirty_pages always checks wb counters
 	 * against wb limits. Even if global "nr_dirty" is under "freerun".
 	 * This is especially important for fuse which sets bdi->max_ratio to
-	 * 1% by default. Without strictlimit feature, fuse writeback may
-	 * consume arbitrary amount of RAM because it is accounted in
-	 * NR_WRITEBACK_TEMP which is not involved in calculating "nr_dirty".
+	 * 1% by default.
 	 *
 	 * Here, in wb_position_ratio(), we calculate pos_ratio based on
 	 * two values: wb_dirty and wb_thresh. Let's consider an example:
diff --git a/mm/show_mem.c b/mm/show_mem.c
index 0cf8bf5d832d..41999e94a56d 100644
--- a/mm/show_mem.c
+++ b/mm/show_mem.c
@@ -246,7 +246,6 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 			" shmem_pmdmapped:%lukB"
 			" anon_thp:%lukB"
 #endif
-			" writeback_tmp:%lukB"
 			" kernel_stack:%lukB"
 #ifdef CONFIG_SHADOW_CALL_STACK
 			" shadow_call_stack:%lukB"
@@ -273,7 +272,6 @@ static void show_free_areas(unsigned int filter, nodemask_t *nodemask, int max_z
 			K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED)),
 			K(node_page_state(pgdat, NR_ANON_THPS)),
 #endif
-			K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
 			node_page_state(pgdat, NR_KERNEL_STACK_KB),
 #ifdef CONFIG_SHADOW_CALL_STACK
 			node_page_state(pgdat, NR_KERNEL_SCS_KB),
diff --git a/mm/vmstat.c b/mm/vmstat.c
index c250eeba0f16..71cd1ceba191 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1251,7 +1251,6 @@ const char * const vmstat_text[] = {
 	[I(NR_FILE_PAGES)]			= "nr_file_pages",
 	[I(NR_FILE_DIRTY)]			= "nr_dirty",
 	[I(NR_WRITEBACK)]			= "nr_writeback",
-	[I(NR_WRITEBACK_TEMP)]			= "nr_writeback_temp",
 	[I(NR_SHMEM)]				= "nr_shmem",
 	[I(NR_SHMEM_THPS)]			= "nr_shmem_hugepages",
 	[I(NR_SHMEM_PMDMAPPED)]			= "nr_shmem_pmdmapped",
-- 
cgit v1.2.3


From a2c24eae5a15f79673eba2913d87d658a04830cf Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Tue, 8 Jul 2025 19:59:31 -0500
Subject: mm/damon: add struct damos_migrate_dests

Patch series "mm/damon/vaddr: Allow interleaving in migrate_{hot,cold}
actions", v4.

A recent patchset automatically sets the interleave weight for each node
according to the node's maximum bandwidth [1].  In another thread, the
patch set's author, Joshua Hahn, wondered if/how thes weights should be
changed if the bandwidth utilization of the system changes [2].

This patch set adds the mechanism for dynamically changing how application
data is interleaved across nodes while leaving the policy of what the
interleave weights should be to userspace.  It does this by having the
migrate_{hot,cold} operating schemes interleave application data according
to the list of migration nodes and weights passed in via the DAMON sysfs
interface.  This functionality can be used to dynamically adjust how
folios are interleaved by having a userspace process adjust those weights.
If no specific destination nodes or weights are provided, the
migrate_{hot,cold} actions will only migrate folios to damos->target_nid
as before.

The algorithm used to interleave the folios is similar to the one used for
the weighted interleave mempolicy [3].  It uses the offset from which a
folio is mapped into a VMA to determine the node the folio should be
placed in.  This method is convenient because for a given set of
interleave weights, a folio has only one valid node it can be placed in,
limitng the amount of unnecessary data movement.  However, finding out how
a folio is mapped inside of a VMA requires a costly rmap walk when using a
paddr scheme.  As such, we have decided that this functionality makes more
sense as a vaddr scheme [4].  To this end, this patch set also adds vaddr
versions of the migrate_{hot,cold}.

Motivation
==========
There have been prior discussions about how changing the interleave
weights in response to the system's bandwidth utilization can be
beneficial [2].  However, currently the interleave weights only are
applied when data is allocated.  Migrating already allocated pages
according to the dynamically changing weights will better help balance the
bandwidth utilization across nodes.

As a toy example, imagine some application that uses 75% of the local
bandwidth.  Assuming sufficient capacity, when running alone, we want to
keep that application's data in local memory.  However, if a second
instance of that application begins, using the same amount of bandwidth,
it would be best to interleave the data of both processes to alleviate the
bandwidth pressure from the local node.  Likewise, when one of the
processes ends, the data should be moves back to local memory.

We imagine there would be a userspace application that would monitor
system performance characteristics, such as bandwidth utilization or
memory access latency, and uses that information to tune the interleave
weights.  Others seem to have come to a similar conclusion in previous
discussions [5].  We are currently working on a userspace program that
does this, but it is not quite ready to be published yet.

After the userspace application tunes the interleave weights, there must
be some mechanism that actually migrates pages to be consistent with those
weights.  This patchset is what provides this mechanism.

We believe DAMON is the correct venue for the interleaving mechanism for a
few reasons.  First, we noticed that we don't have to migrate all of the
application's pages to improve performance.  we just need to migrate the
frequently accessed pages.  DAMON's existing hotness traching is very
useful for this.  Second, DAMON's quota system can be used to ensure we
are not using too much bandwidth for migrations.  Finally, as Ying pointed
out [6], a complete solution must also handle when a memory node is at
capacity.  The existing migrate_cold action can be used in conjunction
with the functionality added in this patch set to provide that complete
solution.

Functionality Test
==================
Below is an example of this new functionality in use to confirm that these
patches behave as intended.

In this example, the user starts an application, alloc_data, which
allocates 1GB using the default memory policy (i.e.  allocate to local
memory) then sleeps.  Afterwards, we start DAMON to interleave the data at
a 1:1 ratio.  Using numastat, we show that DAMON has migrated the
application's data to match the new interleave ratio.

For this example, I modified the userspace damo tool [8] to write to the
migration_dest sysfs files.  I plan to upstream these changes when these
patches are merged.

  $ # Allocate the data initially
  $ ./alloc_data 1G &
  [1] 6587
  $ numastat -c -p alloc_data

  Per-node process memory usage (in MBs) for PID 6587 (alloc_data)
           Node 0 Node 1 Total
           ------ ------ -----
  Huge          0      0     0
  Heap          0      0     0
  Stack         0      0     0
  Private    1027      0  1027
  -------  ------ ------ -----
  Total      1027      0  1027
  $ # Start DAMON to interleave data at a 1:1 ratio
  $ cat ./interleave_vaddr.yaml
  kdamonds:
  - contexts:
    - ops: vaddr
      addr_unit: null
      targets:
      - pid: 6587
        regions: []
      intervals:
        sample_us: 500 ms
        aggr_us: 5 s
        ops_update_us: 20 s
        intervals_goal:
          access_bp: 0 %
          aggrs: '0'
          min_sample_us: 0 ns
          max_sample_us: 0 ns
      nr_regions:
        min: '20'
        max: '50'
      schemes:
      - action: migrate_hot
        dests:
        - nid: 0
          weight: 1
        - nid: 1
          weight: 1
        access_pattern:
          sz_bytes:
            min: 0 B
            max: max
          nr_accesses:
            min: 0 %
            max: 100 %
          age:
            min: 0 ns
            max: max
  $ sudo ./damo/damo interleave_vaddr.yaml
  $ # Verify that DAMON has migrated data to match the 1:1 ratio
  $ numastat -c -p alloc_data

  Per-node process memory usage (in MBs) for PID 6587 (alloc_data)
           Node 0 Node 1 Total
           ------ ------ -----
  Huge          0      0     0
  Heap          0      0     0
  Stack         0      0     0
  Private     514    514  1027
  -------  ------ ------ -----
  Total       514    514  1027

Performance Test
================
Below is a simple example showing that interleaving application data using
these patches can improve application performance.  To do this, we run a
bandwidth intensive embedding reduction application [7].  This workload is
useful for this test because it reports the time it takes each iteration
to run and each iteration reuses the same allocation, allowing us to see
the benefits of the migration.

We evaluate this on a 128 core/256 thread AMD CPU with 72GB/s of local DDR
bandwidth and 26 GB/s of CXL bandwidth.

Before we start the workload, the system bandwidth utilization is low, so
we start with the interleave weights of 1:0, i.e.  allocating all data to
local memory.  When the workload beings, it saturates the local bandwidth,
making the page placement suboptimal.  To alleviate this, we modify the
interleave weights, triggering DAMON to migrate the workload's data.

We use the same interleave_vaddr.yaml file to setup DAMON, except we
configure it to begin with a 1:0 interleave ratio, and attach it to the
shell and its children processes.

  $ sudo ./damo/damo start interleave_vaddr.yaml --include_child_tasks &
  $ <path>/eval_baseline -d amazon_All -c 255 -r 100
  <clip startup output>
  Eval Phase 3: Running Baseline...

  REPEAT # 0 Baseline Total time : 7323.54 ms
  REPEAT # 1 Baseline Total time : 7624.56 ms
  REPEAT # 2 Baseline Total time : 7619.61 ms
  REPEAT # 3 Baseline Total time : 7617.12 ms
  REPEAT # 4 Baseline Total time : 7638.64 ms
  REPEAT # 5 Baseline Total time : 7611.27 ms
  REPEAT # 6 Baseline Total time : 7629.32 ms
  REPEAT # 7 Baseline Total time : 7695.63 ms
  # Interleave weights set to 3:1
  REPEAT # 8 Baseline Total time : 7077.5 ms
  REPEAT # 9 Baseline Total time : 5633.23 ms
  REPEAT # 10 Baseline Total time : 5644.6 ms
  REPEAT # 11 Baseline Total time : 5627.66 ms
  REPEAT # 12 Baseline Total time : 5629.76 ms
  REPEAT # 13 Baseline Total time : 5633.05 ms
  REPEAT # 14 Baseline Total time : 5641.24 ms
  REPEAT # 15 Baseline Total time : 5631.18 ms
  REPEAT # 16 Baseline Total time : 5631.33 ms

Updating the interleave weights and having DAMON migrate the workload data
according to the weights resulted in an approximarely 25% speedup.

Patches Sequence
================
Patches 1-7 extend the DAMON API to specify multiple destination nodes and
weights for the migrate_{hot,cold} actions.  These patches are from SJ'S
RFC [8].

Patches 8-10 add a vaddr implementation of the migrate_{hot,cold} schemes.

Patch 11 modifies the vaddr migrate_{hot,cold} schemes to interleave data
according to the weights provided by damos->migrate_dest.

Patches 12-13 allow the vaddr migrate_{hot,cold} implementation to filter
out folios like the paddr version.


This patch (of 13):

Introduce a new struct, namely damos_migrate_dests, for specifying
multiple DAMOS' migration destination nodes and their weights.

Link: https://lkml.kernel.org/r/20250709005952.17776-1-bijan311@gmail.com
Link: https://lkml.kernel.org/r/20250709005952.17776-2-bijan311@gmail.com
Link: https://lore.kernel.org/linux-mm/20250520141236.2987309-1-joshua.hahnjy@gmail.com/ [1]
Link: https://lore.kernel.org/linux-mm/20250313155705.1943522-1-joshua.hahnjy@gmail.com/ [2]
Link: https://elixir.bootlin.com/linux/v6.15.4/source/mm/mempolicy.c#L2015 [3]
Link: https://lore.kernel.org/damon/20250624223310.55786-1-sj@kernel.org/ [4]
Link: https://lore.kernel.org/linux-mm/20250314151137.892379-1-joshua.hahnjy@gmail.com/ [5]
Link: https://lore.kernel.org/linux-mm/87frjfx6u4.fsf@DESKTOP-5N7EMDA/ [6]
Link: https://github.com/SNU-ARC/MERCI [7]
Link: https://lore.kernel.org/damon/20250702051558.54138-1-sj@kernel.org/ [8]
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Bijan Tabatabai <bijantabatab@micron.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Ravi Shankar Jonnalagadda <ravis.opensrc@micron.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 16 ++++++++++++++++
 1 file changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index e1fea3119538..07cee590ff09 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -447,6 +447,22 @@ struct damos_access_pattern {
 	unsigned int max_age_region;
 };
 
+/**
+ * struct damos_migrate_dests - Migration destination nodes and their weights.
+ * @node_id_arr:	Array of migration destination node ids.
+ * @weight_arr:		Array of migration weights for @node_id_arr.
+ * @nr_dests:		Length of the @node_id_arr and @weight_arr arrays.
+ *
+ * @node_id_arr is an array of the ids of migration destination nodes.
+ * @weight_arr is an array of the weights for those.  The weights in
+ * @weight_arr are for nodes in @node_id_arr of same array index.
+ */
+struct damos_migrate_dests {
+	unsigned int *node_id_arr;
+	unsigned int *weight_arr;
+	size_t nr_dests;
+};
+
 /**
  * struct damos - Represents a Data Access Monitoring-based Operation Scheme.
  * @pattern:		Access pattern of target regions.
-- 
cgit v1.2.3


From aabc85ee33c883243f2c506a5d88963f2456faa6 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Tue, 8 Jul 2025 19:59:32 -0500
Subject: mm/damon/core: add damos->migrate_dests field

Add a new field to 'struct damos', namely migrate_dests, to allow DAMON
API callers specify multiple migration destination nodes and their
weights.  Also update 'struct damos' creation and destruction functions
accordingly to initialize the new field and free up the API
caller-allocated buffers on those, respectively.

Link: https://lkml.kernel.org/r/20250709005952.17776-3-bijan311@gmail.com
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Bijan Tabatabai <bijantabatab@micron.com>
Reviewed-by: SeongJae Park <sj@kernel.org>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Ravi Shankar Jonnalagadda <ravis.opensrc@micron.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 13 ++++++++++---
 mm/damon/core.c       |  4 ++++
 2 files changed, 14 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 07cee590ff09..1f425d830bb9 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -470,6 +470,7 @@ struct damos_migrate_dests {
  * @apply_interval_us:	The time between applying the @action.
  * @quota:		Control the aggressiveness of this scheme.
  * @wmarks:		Watermarks for automated (in)activation of this scheme.
+ * @migrate_dests:	Destination nodes if @action is "migrate_{hot,cold}".
  * @target_nid:		Destination node if @action is "migrate_{hot,cold}".
  * @filters:		Additional set of &struct damos_filter for &action.
  * @ops_filters:	ops layer handling &struct damos_filter objects list.
@@ -488,9 +489,12 @@ struct damos_migrate_dests {
  * monitoring context are inactive, DAMON stops monitoring either, and just
  * repeatedly checks the watermarks.
  *
+ * @migrate_dests specifies multiple migration target nodes with different
+ * weights for migrate_hot or migrate_cold actions.  @target_nid is ignored if
+ * this is set.
+ *
  * @target_nid is used to set the migration target node for migrate_hot or
- * migrate_cold actions, which means it's only meaningful when @action is either
- * "migrate_hot" or "migrate_cold".
+ * migrate_cold actions, and @migrate_dests is unset.
  *
  * Before applying the &action to a memory region, &struct damon_operations
  * implementation could check pages of the region and skip &action to respect
@@ -533,7 +537,10 @@ struct damos {
 	struct damos_quota quota;
 	struct damos_watermarks wmarks;
 	union {
-		int target_nid;
+		struct {
+			int target_nid;
+			struct damos_migrate_dests migrate_dests;
+		};
 	};
 	struct list_head filters;
 	struct list_head ops_filters;
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 04e01e08253a..6c8170d4f695 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -407,6 +407,7 @@ struct damos *damon_new_scheme(struct damos_access_pattern *pattern,
 	scheme->wmarks = *wmarks;
 	scheme->wmarks.activated = true;
 
+	scheme->migrate_dests = (struct damos_migrate_dests){};
 	scheme->target_nid = target_nid;
 
 	return scheme;
@@ -449,6 +450,9 @@ void damon_destroy_scheme(struct damos *s)
 
 	damos_for_each_filter_safe(f, next, s)
 		damos_destroy_filter(f);
+
+	kfree(s->migrate_dests.node_id_arr);
+	kfree(s->migrate_dests.weight_arr);
 	damon_del_scheme(s);
 	damon_free_scheme(s);
 }
-- 
cgit v1.2.3


From e05d3a6014fd4ae224b44b89fbeacfaa4ace0a8e Mon Sep 17 00:00:00 2001
From: "Vishal Moola (Oracle)" <vishal.moola@gmail.com>
Date: Wed, 9 Jul 2025 12:40:18 -0700
Subject: mm: remove unmap_and_put_page()

There are no callers of unmap_and_put_page() left. Remove it.

Link: https://lkml.kernel.org/r/20250709194017.927978-6-vishal.moola@gmail.com
Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jordan Rome <linux@jordanrome.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/highmem.h | 6 ------
 1 file changed, 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index a30526cc53a7..6234f316468c 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -682,10 +682,4 @@ static inline void folio_release_kmap(struct folio *folio, void *addr)
 	kunmap_local(addr);
 	folio_put(folio);
 }
-
-static inline void unmap_and_put_page(struct page *page, void *addr)
-{
-	folio_release_kmap(page_folio(page), addr);
-}
-
 #endif /* _LINUX_HIGHMEM_H */
-- 
cgit v1.2.3


From b980077899ea49cc747afe003e01ca303b00d463 Mon Sep 17 00:00:00 2001
From: Davidlohr Bueso <dave@stgolabs.net>
Date: Mon, 23 Jun 2025 11:58:51 -0700
Subject: mm: introduce per-node proactive reclaim interface

This adds support for allowing proactive reclaim in general on a NUMA
system.  A per-node interface extends support for beyond a memcg-specific
interface, respecting the current semantics of memory.reclaim: respecting
aging LRU and not supporting artificially triggering eviction on nodes
belonging to non-bottom tiers.

This patch allows userspace to do:

     echo "512M swappiness=10" > /sys/devices/system/node/nodeX/reclaim

One of the premises for this is to semantically align as best as possible
with memory.reclaim.  During a brief time memcg did support nodemask until
55ab834a86a9 (Revert "mm: add nodes= arg to memory.reclaim"), for which
semantics around reclaim (eviction) vs demotion were not clear, rendering
charging expectations to be broken.

With this approach:

1. Users who do not use memcg can benefit from proactive reclaim.  The
   memcg interface is not NUMA aware and there are usecases that are
   focusing on NUMA balancing rather than workload memory footprint.

2. Proactive reclaim on top tiers will trigger demotion, for which
   memory is still byte-addressable.  Reclaiming on the bottom nodes will
   trigger evicting to swap (the traditional sense of reclaim).  This
   follows the semantics of what is today part of the aging process on
   tiered memory, mirroring what every other form of reclaim does
   (reactive and memcg proactive reclaim).  Furthermore per-node proactive
   reclaim is not as susceptible to the memcg charging problem mentioned
   above.

3. Unlike the nodes= arg, this interface avoids confusing semantics,
   such as what exactly the user wants when mixing top-tier and low-tier
   nodes in the nodemask.  Further per-node interface is less exposed to
   "free up memory in my container" usecases, where eviction is intended.

4. Users that *really* want to free up memory can use proactive
   reclaim on nodes knowingly to be on the bottom tiers to force eviction
   in a natural way - higher access latencies are still better than swap.
   If compelled, while no guarantees and perhaps not worth the effort,
   users could also also potentially follow a ladder-like approach to
   eventually free up the memory.  Alternatively, perhaps an 'evict'
   option could be added to the parameters for both memory.reclaim and
   per-node interfaces to force this action unconditionally.

[akpm@linux-foundation.org: user_proactive_reclaim(): return -EBUSY on PGDAT_RECLAIM_LOCKED contention, per Roman]
[dave@stgolabs.net: memcg && node is also a bogus case, per Shakeel]
  Link: https://lkml.kernel.org/r/20250717235604.2atyx2aobwowpge3@offworld
Link: https://lkml.kernel.org/r/20250623185851.830632-5-dave@stgolabs.net
Signed-off-by: Davidlohr Bueso <dave@stgolabs.net>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Roman Gushchin <roman.gushchin@linux.dev>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Yosry Ahmed <yosryahmed@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/ABI/stable/sysfs-devices-node |  9 +++++
 drivers/base/node.c                         |  2 ++
 include/linux/swap.h                        | 16 +++++++++
 mm/vmscan.c                                 | 55 +++++++++++++++++++++++++----
 4 files changed, 75 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
index a02707cb7cbc..2d0e023f22a7 100644
--- a/Documentation/ABI/stable/sysfs-devices-node
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -227,3 +227,12 @@ Contact:	Jiaqi Yan <jiaqiyan@google.com>
 Description:
 		Of the raw poisoned pages on a NUMA node, how many pages are
 		recovered by memory error recovery attempt.
+
+What:		/sys/devices/system/node/nodeX/reclaim
+Date:		June 2025
+Contact:	Linux Memory Management list <linux-mm@kvack.org>
+Description:
+		Perform user-triggered proactive reclaim on a NUMA node.
+		This interface is equivalent to the memcg variant.
+
+		See Documentation/admin-guide/cgroup-v2.rst
diff --git a/drivers/base/node.c b/drivers/base/node.c
index e434cb260e61..bef84f01712f 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -659,6 +659,7 @@ static int register_node(struct node *node, int num)
 	} else {
 		hugetlb_register_node(node);
 		compaction_register_node(node);
+		reclaim_register_node(node);
 	}
 
 	return error;
@@ -675,6 +676,7 @@ void unregister_node(struct node *node)
 {
 	hugetlb_unregister_node(node);
 	compaction_unregister_node(node);
+	reclaim_unregister_node(node);
 	node_remove_accesses(node);
 	node_remove_caches(node);
 	device_unregister(&node->dev);
diff --git a/include/linux/swap.h b/include/linux/swap.h
index a49be950c485..95c6061fa1dc 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -431,6 +431,22 @@ extern unsigned long shrink_all_memory(unsigned long nr_pages);
 extern int vm_swappiness;
 long remove_mapping(struct address_space *mapping, struct folio *folio);
 
+#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
+extern int reclaim_register_node(struct node *node);
+extern void reclaim_unregister_node(struct node *node);
+
+#else
+
+static inline int reclaim_register_node(struct node *node)
+{
+	return 0;
+}
+
+static inline void reclaim_unregister_node(struct node *node)
+{
+}
+#endif /* CONFIG_SYSFS && CONFIG_NUMA */
+
 #ifdef CONFIG_NUMA
 extern int sysctl_min_unmapped_ratio;
 extern int sysctl_min_slab_ratio;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index d165b66da796..19bfce93b373 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -94,10 +94,8 @@ struct scan_control {
 	unsigned long	anon_cost;
 	unsigned long	file_cost;
 
-#ifdef CONFIG_MEMCG
 	/* Swappiness value for proactive reclaim. Always use sc_swappiness()! */
 	int *proactive_swappiness;
-#endif
 
 	/* Can active folios be deactivated as part of reclaim? */
 #define DEACTIVATE_ANON 1
@@ -121,7 +119,7 @@ struct scan_control {
 	/* Has cache_trim_mode failed at least once? */
 	unsigned int cache_trim_mode_failed:1;
 
-	/* Proactive reclaim invoked by userspace through memory.reclaim */
+	/* Proactive reclaim invoked by userspace */
 	unsigned int proactive:1;
 
 	/*
@@ -7732,15 +7730,17 @@ static const match_table_t tokens = {
 	{ MEMORY_RECLAIM_NULL, NULL },
 };
 
-int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat)
+int user_proactive_reclaim(char *buf,
+			   struct mem_cgroup *memcg, pg_data_t *pgdat)
 {
 	unsigned int nr_retries = MAX_RECLAIM_RETRIES;
 	unsigned long nr_to_reclaim, nr_reclaimed = 0;
 	int swappiness = -1;
 	char *old_buf, *start;
 	substring_t args[MAX_OPT_ARGS];
+	gfp_t gfp_mask = GFP_KERNEL;
 
-	if (!buf || (!memcg && !pgdat))
+	if (!buf || (!memcg && !pgdat) || (memcg && pgdat))
 		return -EINVAL;
 
 	buf = strstrip(buf);
@@ -7792,11 +7792,29 @@ int user_proactive_reclaim(char *buf, struct mem_cgroup *memcg, pg_data_t *pgdat
 			reclaim_options = MEMCG_RECLAIM_MAY_SWAP |
 					  MEMCG_RECLAIM_PROACTIVE;
 			reclaimed = try_to_free_mem_cgroup_pages(memcg,
-						 batch_size, GFP_KERNEL,
+						 batch_size, gfp_mask,
 						 reclaim_options,
 						 swappiness == -1 ? NULL : &swappiness);
 		} else {
-			return -EINVAL;
+			struct scan_control sc = {
+				.gfp_mask = current_gfp_context(gfp_mask),
+				.reclaim_idx = gfp_zone(gfp_mask),
+				.proactive_swappiness = swappiness == -1 ? NULL : &swappiness,
+				.priority = DEF_PRIORITY,
+				.may_writepage = !laptop_mode,
+				.nr_to_reclaim = max(batch_size, SWAP_CLUSTER_MAX),
+				.may_unmap = 1,
+				.may_swap = 1,
+				.proactive = 1,
+			};
+
+			if (test_and_set_bit_lock(PGDAT_RECLAIM_LOCKED,
+						  &pgdat->flags))
+				return -EBUSY;
+
+			reclaimed = __node_reclaim(pgdat, gfp_mask,
+						   batch_size, &sc);
+			clear_bit_unlock(PGDAT_RECLAIM_LOCKED, &pgdat->flags);
 		}
 
 		if (!reclaimed && !nr_retries--)
@@ -7855,3 +7873,26 @@ void check_move_unevictable_folios(struct folio_batch *fbatch)
 	}
 }
 EXPORT_SYMBOL_GPL(check_move_unevictable_folios);
+
+#if defined(CONFIG_SYSFS) && defined(CONFIG_NUMA)
+static ssize_t reclaim_store(struct device *dev,
+			     struct device_attribute *attr,
+			     const char *buf, size_t count)
+{
+	int ret, nid = dev->id;
+
+	ret = user_proactive_reclaim((char *)buf, NULL, NODE_DATA(nid));
+	return ret ? -EAGAIN : count;
+}
+
+static DEVICE_ATTR_WO(reclaim);
+int reclaim_register_node(struct node *node)
+{
+	return device_create_file(&node->dev, &dev_attr_reclaim);
+}
+
+void reclaim_unregister_node(struct node *node)
+{
+	return device_remove_file(&node->dev, &dev_attr_reclaim);
+}
+#endif
-- 
cgit v1.2.3


From 004ded6bee11b8ed463cdc54b89a4390f4b64f6d Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sat, 12 Jul 2025 12:50:03 -0700
Subject: mm/damon: accept parallel damon_call() requests

Patch series "mm/damon: remove damon_callback".

damon_callback was the only way for communicating with DAMON for contexts
running on its worker thread.  The interface is flexible and simple.  But
as DAMON evolves with more features, damon_callback has become somewhat
too old.  With runtime parameters update, for example, its lack of
synchronization support was found to be inconvenient.  Arguably it is also
not easy to use correctly since the callers should understand when each
callback is called, and implication of the return values from the
callbacks.

To replace it, damon_call() and damos_walk() are introduced.  And those
replaced a few damon_callback use cases.  Some use cases of damon_callback
such as parallel or repetitive DAMON internal data reading and additional
cleanups cannot simply be replaced by damon_call() and damos_walk(),
though.

To allow those replaceable, extend damon_call() for parallel and/or
repeated callbacks and modify the core/ops layers for additional resources
cleanup.  With the updates, replace the remaining damon_callback usages
and finally say goodbye to damon_callback.


This patch (of 14):

Calling damon_call() while it is serving for another parallel thread
immediately fails with -EBUSY.  The caller should call it again, later.
Each caller implementing such retry logic would be redundant.  Accept
parallel damon_call() requests and do the wait instead of the caller.

Link: https://lkml.kernel.org/r/20250712195016.151108-1-sj@kernel.org
Link: https://lkml.kernel.org/r/20250712195016.151108-2-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h |  7 +++++--
 mm/damon/core.c       | 49 +++++++++++++++++++++++++------------------------
 2 files changed, 30 insertions(+), 26 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 1f425d830bb9..562c7876ba88 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -673,6 +673,8 @@ struct damon_call_control {
 	struct completion completion;
 	/* informs if the kdamond canceled @fn infocation */
 	bool canceled;
+	/* List head for siblings. */
+	struct list_head list;
 };
 
 /**
@@ -798,8 +800,9 @@ struct damon_ctx {
 	/* for scheme quotas prioritization */
 	unsigned long *regions_score_histogram;
 
-	struct damon_call_control *call_control;
-	struct mutex call_control_lock;
+	/* lists of &struct damon_call_control */
+	struct list_head call_controls;
+	struct mutex call_controls_lock;
 
 	struct damos_walk_control *walk_control;
 	struct mutex walk_control_lock;
diff --git a/mm/damon/core.c b/mm/damon/core.c
index 2714a7a023db..b0a0b98f6889 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -533,7 +533,8 @@ struct damon_ctx *damon_new_ctx(void)
 	ctx->next_ops_update_sis = 0;
 
 	mutex_init(&ctx->kdamond_lock);
-	mutex_init(&ctx->call_control_lock);
+	INIT_LIST_HEAD(&ctx->call_controls);
+	mutex_init(&ctx->call_controls_lock);
 	mutex_init(&ctx->walk_control_lock);
 
 	ctx->attrs.min_nr_regions = 10;
@@ -1393,14 +1394,11 @@ int damon_call(struct damon_ctx *ctx, struct damon_call_control *control)
 {
 	init_completion(&control->completion);
 	control->canceled = false;
+	INIT_LIST_HEAD(&control->list);
 
-	mutex_lock(&ctx->call_control_lock);
-	if (ctx->call_control) {
-		mutex_unlock(&ctx->call_control_lock);
-		return -EBUSY;
-	}
-	ctx->call_control = control;
-	mutex_unlock(&ctx->call_control_lock);
+	mutex_lock(&ctx->call_controls_lock);
+	list_add_tail(&ctx->call_controls, &control->list);
+	mutex_unlock(&ctx->call_controls_lock);
 	if (!damon_is_running(ctx))
 		return -EINVAL;
 	wait_for_completion(&control->completion);
@@ -2419,11 +2417,11 @@ static void kdamond_usleep(unsigned long usecs)
 }
 
 /*
- * kdamond_call() - handle damon_call_control.
+ * kdamond_call() - handle damon_call_control objects.
  * @ctx:	The &struct damon_ctx of the kdamond.
  * @cancel:	Whether to cancel the invocation of the function.
  *
- * If there is a &struct damon_call_control request that registered via
+ * If there are &struct damon_call_control requests that registered via
  * &damon_call() on @ctx, do or cancel the invocation of the function depending
  * on @cancel.  @cancel is set when the kdamond is already out of the main loop
  * and therefore will be terminated.
@@ -2433,21 +2431,24 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel)
 	struct damon_call_control *control;
 	int ret = 0;
 
-	mutex_lock(&ctx->call_control_lock);
-	control = ctx->call_control;
-	mutex_unlock(&ctx->call_control_lock);
-	if (!control)
-		return;
-	if (cancel) {
-		control->canceled = true;
-	} else {
-		ret = control->fn(control->data);
-		control->return_code = ret;
+	while (true) {
+		mutex_lock(&ctx->call_controls_lock);
+		control = list_first_entry_or_null(&ctx->call_controls,
+				struct damon_call_control, list);
+		mutex_unlock(&ctx->call_controls_lock);
+		if (!control)
+			return;
+		if (cancel) {
+			control->canceled = true;
+		} else {
+			ret = control->fn(control->data);
+			control->return_code = ret;
+		}
+		mutex_lock(&ctx->call_controls_lock);
+		list_del(&control->list);
+		mutex_unlock(&ctx->call_controls_lock);
+		complete(&control->completion);
 	}
-	complete(&control->completion);
-	mutex_lock(&ctx->call_control_lock);
-	ctx->call_control = NULL;
-	mutex_unlock(&ctx->call_control_lock);
 }
 
 /* Returns negative error code if it's not activated but should return */
-- 
cgit v1.2.3


From 43df7676e5508895c33b846d37cff9cf3b52674c Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sat, 12 Jul 2025 12:50:04 -0700
Subject: mm/damon/core: introduce repeat mode damon_call()

damon_call() can be useful for reading or writing DAMON internal data for
one time.  A common pattern of DAMON core usage from DAMON modules is
doing such reads and writes repeatedly, for example, to periodically
update the DAMOS stats.  To do that with damon_call(), callers should call
damon_call() repeatedly, with their own delay loop.  Each caller doing
that is repetitive.  Introduce a repeat mode damon_call().  Callers can
use the mode by setting a new field in damon_call_control.  If the mode is
turned on, damon_call() returns success immediately, and DAMON repeats
invoking the callback function inside the kdamond main loop.

Link: https://lkml.kernel.org/r/20250712195016.151108-3-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h |  2 ++
 mm/damon/core.c       | 25 ++++++++++++++++++++-----
 2 files changed, 22 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 562c7876ba88..b83987275ff9 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -659,6 +659,7 @@ struct damon_callback {
  *
  * @fn:			Function to be called back.
  * @data:		Data that will be passed to @fn.
+ * @repeat:		Repeat invocations.
  * @return_code:	Return code from @fn invocation.
  *
  * Control damon_call(), which requests specific kdamond to invoke a given
@@ -667,6 +668,7 @@ struct damon_callback {
 struct damon_call_control {
 	int (*fn)(void *data);
 	void *data;
+	bool repeat;
 	int return_code;
 /* private: internal use only */
 	/* informs if the kdamond finished handling of the request */
diff --git a/mm/damon/core.c b/mm/damon/core.c
index b0a0b98f6889..ffb87497dbb5 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -1379,8 +1379,9 @@ bool damon_is_running(struct damon_ctx *ctx)
  *
  * Ask DAMON worker thread (kdamond) of @ctx to call a function with an
  * argument data that respectively passed via &damon_call_control->fn and
- * &damon_call_control->data of @control, and wait until the kdamond finishes
- * handling of the request.
+ * &damon_call_control->data of @control.  If &damon_call_control->repeat of
+ * @control is set, further wait until the kdamond finishes handling of the
+ * request.  Otherwise, return as soon as the request is made.
  *
  * The kdamond executes the function with the argument in the main loop, just
  * after a sampling of the iteration is finished.  The function can hence
@@ -1392,7 +1393,8 @@ bool damon_is_running(struct damon_ctx *ctx)
  */
 int damon_call(struct damon_ctx *ctx, struct damon_call_control *control)
 {
-	init_completion(&control->completion);
+	if (!control->repeat)
+		init_completion(&control->completion);
 	control->canceled = false;
 	INIT_LIST_HEAD(&control->list);
 
@@ -1401,6 +1403,8 @@ int damon_call(struct damon_ctx *ctx, struct damon_call_control *control)
 	mutex_unlock(&ctx->call_controls_lock);
 	if (!damon_is_running(ctx))
 		return -EINVAL;
+	if (control->repeat)
+		return 0;
 	wait_for_completion(&control->completion);
 	if (control->canceled)
 		return -ECANCELED;
@@ -2429,6 +2433,7 @@ static void kdamond_usleep(unsigned long usecs)
 static void kdamond_call(struct damon_ctx *ctx, bool cancel)
 {
 	struct damon_call_control *control;
+	LIST_HEAD(repeat_controls);
 	int ret = 0;
 
 	while (true) {
@@ -2437,7 +2442,7 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel)
 				struct damon_call_control, list);
 		mutex_unlock(&ctx->call_controls_lock);
 		if (!control)
-			return;
+			break;
 		if (cancel) {
 			control->canceled = true;
 		} else {
@@ -2447,8 +2452,18 @@ static void kdamond_call(struct damon_ctx *ctx, bool cancel)
 		mutex_lock(&ctx->call_controls_lock);
 		list_del(&control->list);
 		mutex_unlock(&ctx->call_controls_lock);
-		complete(&control->completion);
+		if (!control->repeat)
+			complete(&control->completion);
+		else
+			list_add(&control->list, &repeat_controls);
 	}
+	control = list_first_entry_or_null(&repeat_controls,
+			struct damon_call_control, list);
+	if (!control || cancel)
+		return;
+	mutex_lock(&ctx->call_controls_lock);
+	list_add_tail(&control->list, &ctx->call_controls);
+	mutex_unlock(&ctx->call_controls_lock);
 }
 
 /* Returns negative error code if it's not activated but should return */
-- 
cgit v1.2.3


From 7114bc5e01cf393e1fdc97e10399eb9451b6af45 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sat, 12 Jul 2025 12:50:11 -0700
Subject: mm/damon/core: add cleanup_target() ops callback

Some DAMON operation sets may need additional cleanup per target.  For
example, [f]vaddr need to put pids of each target.  Each user and core
logic is doing that redundantly.  Add another DAMON ops callback that will
be used for doing such cleanups in operations set layer.

[sj@kernel.org: add kernel-doc comment for damon_operations->cleanup_target]
  Link: https://lkml.kernel.org/r/20250715185239.89152-2-sj@kernel.org
[sj@kernel.org: remove damon_ctx->callback kernel-doc comment]
  Link: https://lkml.kernel.org/r/20250715185239.89152-3-sj@kernel.org
Link: https://lkml.kernel.org/r/20250712195016.151108-10-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h        |  6 ++++--
 mm/damon/core.c              | 12 ++++++++----
 mm/damon/sysfs.c             |  4 ++--
 mm/damon/tests/core-kunit.h  |  4 ++--
 mm/damon/tests/vaddr-kunit.h |  2 +-
 5 files changed, 17 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index b83987275ff9..8c765e36623a 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -576,6 +576,7 @@ enum damon_ops_id {
  * @get_scheme_score:		Get the score of a region for a scheme.
  * @apply_scheme:		Apply a DAMON-based operation scheme.
  * @target_valid:		Determine if the target is valid.
+ * @cleanup_target:		Clean up each target before deallocation.
  * @cleanup:			Clean up the context.
  *
  * DAMON can be extended for various address spaces and usages.  For this,
@@ -608,6 +609,7 @@ enum damon_ops_id {
  * filters (&struct damos_filter) that handled by itself.
  * @target_valid should check whether the target is still valid for the
  * monitoring.
+ * @cleanup_target is called before the target will be deallocated.
  * @cleanup is called from @kdamond just before its termination.
  */
 struct damon_operations {
@@ -623,6 +625,7 @@ struct damon_operations {
 			struct damon_target *t, struct damon_region *r,
 			struct damos *scheme, unsigned long *sz_filter_passed);
 	bool (*target_valid)(struct damon_target *t);
+	void (*cleanup_target)(struct damon_target *t);
 	void (*cleanup)(struct damon_ctx *context);
 };
 
@@ -771,7 +774,6 @@ struct damon_attrs {
  * Accesses to other fields must be protected by themselves.
  *
  * @ops:	Set of monitoring operations for given use cases.
- * @callback:	Set of callbacks for monitoring events notifications.
  *
  * @adaptive_targets:	Head of monitoring targets (&damon_target) list.
  * @schemes:		Head of schemes (&damos) list.
@@ -933,7 +935,7 @@ struct damon_target *damon_new_target(void);
 void damon_add_target(struct damon_ctx *ctx, struct damon_target *t);
 bool damon_targets_empty(struct damon_ctx *ctx);
 void damon_free_target(struct damon_target *t);
-void damon_destroy_target(struct damon_target *t);
+void damon_destroy_target(struct damon_target *t, struct damon_ctx *ctx);
 unsigned int damon_nr_regions(struct damon_target *t);
 
 struct damon_ctx *damon_new_ctx(void);
diff --git a/mm/damon/core.c b/mm/damon/core.c
index b82a838b5a0e..678c9b4e038c 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -502,8 +502,12 @@ void damon_free_target(struct damon_target *t)
 	kfree(t);
 }
 
-void damon_destroy_target(struct damon_target *t)
+void damon_destroy_target(struct damon_target *t, struct damon_ctx *ctx)
 {
+
+	if (ctx && ctx->ops.cleanup_target)
+		ctx->ops.cleanup_target(t);
+
 	damon_del_target(t);
 	damon_free_target(t);
 }
@@ -551,7 +555,7 @@ static void damon_destroy_targets(struct damon_ctx *ctx)
 	struct damon_target *t, *next_t;
 
 	damon_for_each_target_safe(t, next_t, ctx)
-		damon_destroy_target(t);
+		damon_destroy_target(t, ctx);
 }
 
 void damon_destroy_ctx(struct damon_ctx *ctx)
@@ -1137,7 +1141,7 @@ static int damon_commit_targets(
 
 			if (damon_target_has_pid(dst))
 				put_pid(dst_target->pid);
-			damon_destroy_target(dst_target);
+			damon_destroy_target(dst_target, dst);
 			damon_for_each_scheme(s, dst) {
 				if (s->quota.charge_target_from == dst_target) {
 					s->quota.charge_target_from = NULL;
@@ -1156,7 +1160,7 @@ static int damon_commit_targets(
 		err = damon_commit_target(new_target, false,
 				src_target, damon_target_has_pid(src));
 		if (err) {
-			damon_destroy_target(new_target);
+			damon_destroy_target(new_target, NULL);
 			return err;
 		}
 		damon_add_target(dst, new_target);
diff --git a/mm/damon/sysfs.c b/mm/damon/sysfs.c
index c0193de6fb9a..f2f9f756f5a2 100644
--- a/mm/damon/sysfs.c
+++ b/mm/damon/sysfs.c
@@ -1303,7 +1303,7 @@ static void damon_sysfs_destroy_targets(struct damon_ctx *ctx)
 	damon_for_each_target_safe(t, next, ctx) {
 		if (has_pid)
 			put_pid(t->pid);
-		damon_destroy_target(t);
+		damon_destroy_target(t, ctx);
 	}
 }
 
@@ -1389,7 +1389,7 @@ static void damon_sysfs_before_terminate(struct damon_ctx *ctx)
 
 	damon_for_each_target_safe(t, next, ctx) {
 		put_pid(t->pid);
-		damon_destroy_target(t);
+		damon_destroy_target(t, ctx);
 	}
 }
 
diff --git a/mm/damon/tests/core-kunit.h b/mm/damon/tests/core-kunit.h
index 298c67557fae..dfedfff19940 100644
--- a/mm/damon/tests/core-kunit.h
+++ b/mm/damon/tests/core-kunit.h
@@ -58,7 +58,7 @@ static void damon_test_target(struct kunit *test)
 	damon_add_target(c, t);
 	KUNIT_EXPECT_EQ(test, 1u, nr_damon_targets(c));
 
-	damon_destroy_target(t);
+	damon_destroy_target(t, c);
 	KUNIT_EXPECT_EQ(test, 0u, nr_damon_targets(c));
 
 	damon_destroy_ctx(c);
@@ -310,7 +310,7 @@ static void damon_test_set_regions(struct kunit *test)
 		KUNIT_EXPECT_EQ(test, r->ar.start, expects[expect_idx++]);
 		KUNIT_EXPECT_EQ(test, r->ar.end, expects[expect_idx++]);
 	}
-	damon_destroy_target(t);
+	damon_destroy_target(t, NULL);
 }
 
 static void damon_test_nr_accesses_to_accesses_bp(struct kunit *test)
diff --git a/mm/damon/tests/vaddr-kunit.h b/mm/damon/tests/vaddr-kunit.h
index 7cd944266a92..d2b37ccf2cc0 100644
--- a/mm/damon/tests/vaddr-kunit.h
+++ b/mm/damon/tests/vaddr-kunit.h
@@ -149,7 +149,7 @@ static void damon_do_test_apply_three_regions(struct kunit *test,
 		KUNIT_EXPECT_EQ(test, r->ar.end, expected[i * 2 + 1]);
 	}
 
-	damon_destroy_target(t);
+	damon_destroy_target(t, NULL);
 }
 
 /*
-- 
cgit v1.2.3


From 5add26c0a18636e8e9fe409d4591c8a36e1bf695 Mon Sep 17 00:00:00 2001
From: SeongJae Park <sj@kernel.org>
Date: Sat, 12 Jul 2025 12:50:16 -0700
Subject: mm/damon/core: remove damon_callback

All damon_callback usages are replicated by damon_call() and damos_walk().
Time to say goodbye.  Remove damon_callback.

Link: https://lkml.kernel.org/r/20250712195016.151108-15-sj@kernel.org
Signed-off-by: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/damon.h | 31 +------------------------------
 mm/damon/core.c       | 26 +++++++-------------------
 2 files changed, 8 insertions(+), 49 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/damon.h b/include/linux/damon.h
index 8c765e36623a..f13664c62ddd 100644
--- a/include/linux/damon.h
+++ b/include/linux/damon.h
@@ -629,34 +629,6 @@ struct damon_operations {
 	void (*cleanup)(struct damon_ctx *context);
 };
 
-/**
- * struct damon_callback - Monitoring events notification callbacks.
- *
- * @after_wmarks_check:	Called after each schemes' watermarks check.
- * @after_aggregation:	Called after each aggregation.
- * @before_terminate:	Called before terminating the monitoring.
- *
- * The monitoring thread (&damon_ctx.kdamond) calls @before_terminate just
- * before finishing the monitoring.
- *
- * The monitoring thread calls @after_wmarks_check after each DAMON-based
- * operation schemes' watermarks check.  If users need to make changes to the
- * attributes of the monitoring context while it's deactivated due to the
- * watermarks, this is the good place to do.
- *
- * The monitoring thread calls @after_aggregation for each of the aggregation
- * intervals.  Therefore, users can safely access the monitoring results
- * without additional protection.  For the reason, users are recommended to use
- * these callback for the accesses to the results.
- *
- * If any callback returns non-zero, monitoring stops.
- */
-struct damon_callback {
-	int (*after_wmarks_check)(struct damon_ctx *context);
-	int (*after_aggregation)(struct damon_ctx *context);
-	void (*before_terminate)(struct damon_ctx *context);
-};
-
 /*
  * struct damon_call_control - Control damon_call().
  *
@@ -727,7 +699,7 @@ struct damon_intervals_goal {
  * ``mmap()`` calls from the application, in case of virtual memory monitoring)
  * and applies the changes for each @ops_update_interval.  All time intervals
  * are in micro-seconds.  Please refer to &struct damon_operations and &struct
- * damon_callback for more detail.
+ * damon_call_control for more detail.
  */
 struct damon_attrs {
 	unsigned long sample_interval;
@@ -816,7 +788,6 @@ struct damon_ctx {
 	struct mutex kdamond_lock;
 
 	struct damon_operations ops;
-	struct damon_callback callback;
 
 	struct list_head adaptive_targets;
 	struct list_head schemes;
diff --git a/mm/damon/core.c b/mm/damon/core.c
index ffd1a061c2cb..f3ec3bd736ec 100644
--- a/mm/damon/core.c
+++ b/mm/damon/core.c
@@ -680,9 +680,7 @@ static bool damon_valid_intervals_goal(struct damon_attrs *attrs)
  * @attrs:		monitoring attributes
  *
  * This function should be called while the kdamond is not running, an access
- * check results aggregation is not ongoing (e.g., from &struct
- * damon_callback->after_aggregation or &struct
- * damon_callback->after_wmarks_check callbacks), or from damon_call().
+ * check results aggregation is not ongoing (e.g., from damon_call().
  *
  * Every time interval is in micro-seconds.
  *
@@ -778,7 +776,7 @@ static void damos_commit_quota_goal(
  * DAMON contexts, instead of manual in-place updates.
  *
  * This function should be called from parameters-update safe context, like
- * DAMON callbacks.
+ * damon_call().
  */
 int damos_commit_quota_goals(struct damos_quota *dst, struct damos_quota *src)
 {
@@ -1177,7 +1175,7 @@ static int damon_commit_targets(
  * in-place updates.
  *
  * This function should be called from parameters-update safe context, like
- * DAMON callbacks.
+ * damon_call().
  */
 int damon_commit_ctx(struct damon_ctx *dst, struct damon_ctx *src)
 {
@@ -2484,9 +2482,6 @@ static int kdamond_wait_activation(struct damon_ctx *ctx)
 
 		kdamond_usleep(min_wait_time);
 
-		if (ctx->callback.after_wmarks_check &&
-				ctx->callback.after_wmarks_check(ctx))
-			break;
 		kdamond_call(ctx, false);
 		damos_walk_cancel(ctx);
 	}
@@ -2543,10 +2538,9 @@ static int kdamond_fn(void *data)
 	while (!kdamond_need_stop(ctx)) {
 		/*
 		 * ctx->attrs and ctx->next_{aggregation,ops_update}_sis could
-		 * be changed from after_wmarks_check() or after_aggregation()
-		 * callbacks.  Read the values here, and use those for this
-		 * iteration.  That is, damon_set_attrs() updated new values
-		 * are respected from next iteration.
+		 * be changed from kdamond_call().  Read the values here, and
+		 * use those for this iteration.  That is, damon_set_attrs()
+		 * updated new values are respected from next iteration.
 		 */
 		unsigned long next_aggregation_sis = ctx->next_aggregation_sis;
 		unsigned long next_ops_update_sis = ctx->next_ops_update_sis;
@@ -2564,14 +2558,10 @@ static int kdamond_fn(void *data)
 		if (ctx->ops.check_accesses)
 			max_nr_accesses = ctx->ops.check_accesses(ctx);
 
-		if (ctx->passed_sample_intervals >= next_aggregation_sis) {
+		if (ctx->passed_sample_intervals >= next_aggregation_sis)
 			kdamond_merge_regions(ctx,
 					max_nr_accesses / 10,
 					sz_limit);
-			if (ctx->callback.after_aggregation &&
-					ctx->callback.after_aggregation(ctx))
-				break;
-		}
 
 		/*
 		 * do kdamond_call() and kdamond_apply_schemes() after
@@ -2637,8 +2627,6 @@ done:
 			damon_destroy_region(r, t);
 	}
 
-	if (ctx->callback.before_terminate)
-		ctx->callback.before_terminate(ctx);
 	if (ctx->ops.cleanup)
 		ctx->ops.cleanup(ctx);
 	kfree(ctx->regions_score_histogram);
-- 
cgit v1.2.3


From 9989db9f230542cfc097be3291b9457173371eb1 Mon Sep 17 00:00:00 2001
From: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Date: Fri, 11 Jul 2025 10:59:10 -0400
Subject: mm/page_owner: convert set_page_owner_migrate_reason() to folios

Both callers of set_page_owner_migrate_reason() use folios.  Convert the
function to take a folio directly and move the &folio->page conversion
inside __set_page_owner_migrate_reason().

Link: https://lkml.kernel.org/r/20250711145910.90135-1-sidhartha.kumar@oracle.com
Signed-off-by: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Reviewed-by: Vishal Moola (Oracle) <vishal.moola@gmail.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page_owner.h | 8 ++++----
 mm/hugetlb.c               | 2 +-
 mm/migrate.c               | 2 +-
 mm/page_owner.c            | 4 ++--
 4 files changed, 8 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page_owner.h b/include/linux/page_owner.h
index debdc25f08b9..3328357f6dba 100644
--- a/include/linux/page_owner.h
+++ b/include/linux/page_owner.h
@@ -14,7 +14,7 @@ extern void __set_page_owner(struct page *page,
 extern void __split_page_owner(struct page *page, int old_order,
 			int new_order);
 extern void __folio_copy_owner(struct folio *newfolio, struct folio *old);
-extern void __set_page_owner_migrate_reason(struct page *page, int reason);
+extern void __folio_set_owner_migrate_reason(struct folio *folio, int reason);
 extern void __dump_page_owner(const struct page *page);
 extern void pagetypeinfo_showmixedcount_print(struct seq_file *m,
 					pg_data_t *pgdat, struct zone *zone);
@@ -43,10 +43,10 @@ static inline void folio_copy_owner(struct folio *newfolio, struct folio *old)
 	if (static_branch_unlikely(&page_owner_inited))
 		__folio_copy_owner(newfolio, old);
 }
-static inline void set_page_owner_migrate_reason(struct page *page, int reason)
+static inline void folio_set_owner_migrate_reason(struct folio *folio, int reason)
 {
 	if (static_branch_unlikely(&page_owner_inited))
-		__set_page_owner_migrate_reason(page, reason);
+		__folio_set_owner_migrate_reason(folio, reason);
 }
 static inline void dump_page_owner(const struct page *page)
 {
@@ -68,7 +68,7 @@ static inline void split_page_owner(struct page *page, int old_order,
 static inline void folio_copy_owner(struct folio *newfolio, struct folio *folio)
 {
 }
-static inline void set_page_owner_migrate_reason(struct page *page, int reason)
+static inline void folio_set_owner_migrate_reason(struct folio *folio, int reason)
 {
 }
 static inline void dump_page_owner(const struct page *page)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f13fa5aa6624..753f99b4c718 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7835,7 +7835,7 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re
 	struct hstate *h = folio_hstate(old_folio);
 
 	hugetlb_cgroup_migrate(old_folio, new_folio);
-	set_page_owner_migrate_reason(&new_folio->page, reason);
+	folio_set_owner_migrate_reason(new_folio, reason);
 
 	/*
 	 * transfer temporary state of the new hugetlb folio. This is
diff --git a/mm/migrate.c b/mm/migrate.c
index 36b2764204b6..425401b2d4e1 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -1367,7 +1367,7 @@ static int migrate_folio_move(free_folio_t put_new_folio, unsigned long private,
 
 out_unlock_both:
 	folio_unlock(dst);
-	set_page_owner_migrate_reason(&dst->page, reason);
+	folio_set_owner_migrate_reason(dst, reason);
 	/*
 	 * If migration is successful, decrease refcount of dst,
 	 * which will not free the page because new page owner increased
diff --git a/mm/page_owner.c b/mm/page_owner.c
index 9928c9ac8c31..c3ca21132c2c 100644
--- a/mm/page_owner.c
+++ b/mm/page_owner.c
@@ -333,9 +333,9 @@ noinline void __set_page_owner(struct page *page, unsigned short order,
 	inc_stack_record_count(handle, gfp_mask, 1 << order);
 }
 
-void __set_page_owner_migrate_reason(struct page *page, int reason)
+void __folio_set_owner_migrate_reason(struct folio *folio, int reason)
 {
-	struct page_ext *page_ext = page_ext_get(page);
+	struct page_ext *page_ext = page_ext_get(&folio->page);
 	struct page_owner *page_owner;
 
 	if (unlikely(!page_ext))
-- 
cgit v1.2.3


From 35c18f2933c596b4fd6a98baee36f3137d133a5f Mon Sep 17 00:00:00 2001
From: Jiri Bohac <jbohac@suse.cz>
Date: Thu, 12 Jun 2025 12:13:21 +0200
Subject: Add a new optional ",cma" suffix to the crashkernel= command line
 option

Patch series "kdump: crashkernel reservation from CMA", v5.

This series implements a way to reserve additional crash kernel memory
using CMA.

Currently, all the memory for the crash kernel is not usable by the 1st
(production) kernel.  It is also unmapped so that it can't be corrupted by
the fault that will eventually trigger the crash.  This makes sense for
the memory actually used by the kexec-loaded crash kernel image and initrd
and the data prepared during the load (vmcoreinfo, ...).  However, the
reserved space needs to be much larger than that to provide enough
run-time memory for the crash kernel and the kdump userspace.  Estimating
the amount of memory to reserve is difficult.  Being too careful makes
kdump likely to end in OOM, being too generous takes even more memory from
the production system.  Also, the reservation only allows reserving a
single contiguous block (or two with the "low" suffix).  I've seen systems
where this fails because the physical memory is fragmented.

By reserving additional crashkernel memory from CMA, the main crashkernel
reservation can be just large enough to fit the kernel and initrd image,
minimizing the memory taken away from the production system.  Most of the
run-time memory for the crash kernel will be memory previously available
to userspace in the production system.  As this memory is no longer
wasted, the reservation can be done with a generous margin, making kdump
more reliable.  Kernel memory that we need to preserve for dumping is
normally not allocated from CMA, unless it is explicitly allocated as
movable.  Currently this is only the case for memory ballooning and zswap.
Such movable memory will be missing from the vmcore.  User data is
typically not dumped by makedumpfile.  When dumping of user data is
intended this new CMA reservation cannot be used.

There are five patches in this series:

The first adds a new ",cma" suffix to the recenly introduced generic
crashkernel parsing code.  parse_crashkernel() takes one more argument to
store the cma reservation size.

The second patch implements reserve_crashkernel_cma() which performs the
reservation.  If the requested size is not available in a single range,
multiple smaller ranges will be reserved.

The third patch updates Documentation/, explicitly mentioning the
potential DMA corruption of the CMA-reserved memory.

The fourth patch adds a short delay before booting the kdump kernel,
allowing pending DMA transfers to finish.

The fifth patch enables the functionality for x86 as a proof of
concept. There are just three things every arch needs to do:
- call reserve_crashkernel_cma()
- include the CMA-reserved ranges in the physical memory map
- exclude the CMA-reserved ranges from the memory available
  through /proc/vmcore by excluding them from the vmcoreinfo
  PT_LOAD ranges.

Adding other architectures is easy and I can do that as soon as this
series is merged.

With this series applied, specifying
	crashkernel=100M craskhernel=1G,cma
on the command line will make a standard crashkernel reservation
of 100M, where kexec will load the kernel and initrd.

An additional 1G will be reserved from CMA, still usable by the production
system.  The crash kernel will have 1.1G memory available.  The 100M can
be reliably predicted based on the size of the kernel and initrd.

The new cma suffix is completely optional. When no
crashkernel=size,cma is specified, everything works as before.


This patch (of 5):

Add a new cma_size parameter to parse_crashkernel().  When not NULL, call
__parse_crashkernel to parse the CMA reservation size from
"crashkernel=size,cma" and store it in cma_size.

Set cma_size to NULL in all calls to parse_crashkernel().

Link: https://lkml.kernel.org/r/aEqnxxfLZMllMC8I@dwarf.suse.cz
Link: https://lkml.kernel.org/r/aEqoQckgoTQNULnh@dwarf.suse.cz
Signed-off-by: Jiri Bohac <jbohac@suse.cz>
Cc: Baoquan He <bhe@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: Donald Dutile <ddutile@redhat.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Philipp Rudo <prudo@redhat.com>
Cc: Pingfan Liu <piliu@redhat.com>
Cc: Tao Liu <ltao@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm/kernel/setup.c              |  2 +-
 arch/arm64/mm/init.c                 |  2 +-
 arch/loongarch/kernel/setup.c        |  2 +-
 arch/mips/kernel/setup.c             |  2 +-
 arch/powerpc/kernel/fadump.c         |  2 +-
 arch/powerpc/kexec/core.c            |  2 +-
 arch/powerpc/mm/nohash/kaslr_booke.c |  2 +-
 arch/riscv/mm/init.c                 |  2 +-
 arch/s390/kernel/setup.c             |  2 +-
 arch/sh/kernel/machine_kexec.c       |  2 +-
 arch/x86/kernel/setup.c              |  2 +-
 include/linux/crash_reserve.h        |  3 ++-
 kernel/crash_reserve.c               | 16 ++++++++++++++--
 13 files changed, 27 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index a41c93988d2c..0bfd66c7ada0 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -1004,7 +1004,7 @@ static void __init reserve_crashkernel(void)
 	total_mem = get_total_mem();
 	ret = parse_crashkernel(boot_command_line, total_mem,
 				&crash_size, &crash_base,
-				NULL, NULL);
+				NULL, NULL, NULL);
 	/* invalid value specified or crashkernel=0 */
 	if (ret || !crash_size)
 		return;
diff --git a/arch/arm64/mm/init.c b/arch/arm64/mm/init.c
index 0c8c35dd645e..ea84a61ed508 100644
--- a/arch/arm64/mm/init.c
+++ b/arch/arm64/mm/init.c
@@ -106,7 +106,7 @@ static void __init arch_reserve_crashkernel(void)
 
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
-				&low_size, &high);
+				&low_size, NULL, &high);
 	if (ret)
 		return;
 
diff --git a/arch/loongarch/kernel/setup.c b/arch/loongarch/kernel/setup.c
index b99fbb388fe0..22b27cd447a1 100644
--- a/arch/loongarch/kernel/setup.c
+++ b/arch/loongarch/kernel/setup.c
@@ -265,7 +265,7 @@ static void __init arch_reserve_crashkernel(void)
 		return;
 
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
-				&crash_size, &crash_base, &low_size, &high);
+				&crash_size, &crash_base, &low_size, NULL, &high);
 	if (ret)
 		return;
 
diff --git a/arch/mips/kernel/setup.c b/arch/mips/kernel/setup.c
index fbfe0771317e..11b9b6b63e19 100644
--- a/arch/mips/kernel/setup.c
+++ b/arch/mips/kernel/setup.c
@@ -458,7 +458,7 @@ static void __init mips_parse_crashkernel(void)
 	total_mem = memblock_phys_mem_size();
 	ret = parse_crashkernel(boot_command_line, total_mem,
 				&crash_size, &crash_base,
-				NULL, NULL);
+				NULL, NULL, NULL);
 	if (ret != 0 || crash_size <= 0)
 		return;
 
diff --git a/arch/powerpc/kernel/fadump.c b/arch/powerpc/kernel/fadump.c
index 8ca49e40c473..28cab25d5b33 100644
--- a/arch/powerpc/kernel/fadump.c
+++ b/arch/powerpc/kernel/fadump.c
@@ -333,7 +333,7 @@ static __init u64 fadump_calculate_reserve_size(void)
 	 * memory at a predefined offset.
 	 */
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
-				&size, &base, NULL, NULL);
+				&size, &base, NULL, NULL, NULL);
 	if (ret == 0 && size > 0) {
 		unsigned long max_size;
 
diff --git a/arch/powerpc/kexec/core.c b/arch/powerpc/kexec/core.c
index 00e9c267b912..d1a2d755381c 100644
--- a/arch/powerpc/kexec/core.c
+++ b/arch/powerpc/kexec/core.c
@@ -110,7 +110,7 @@ void __init arch_reserve_crashkernel(void)
 
 	/* use common parsing */
 	ret = parse_crashkernel(boot_command_line, total_mem_sz, &crash_size,
-				&crash_base, NULL, NULL);
+				&crash_base, NULL, NULL, NULL);
 
 	if (ret)
 		return;
diff --git a/arch/powerpc/mm/nohash/kaslr_booke.c b/arch/powerpc/mm/nohash/kaslr_booke.c
index 5c8d1bb98b3e..5e4897daaaea 100644
--- a/arch/powerpc/mm/nohash/kaslr_booke.c
+++ b/arch/powerpc/mm/nohash/kaslr_booke.c
@@ -178,7 +178,7 @@ static void __init get_crash_kernel(void *fdt, unsigned long size)
 	int ret;
 
 	ret = parse_crashkernel(boot_command_line, size, &crash_size,
-				&crash_base, NULL, NULL);
+				&crash_base, NULL, NULL, NULL);
 	if (ret != 0 || crash_size == 0)
 		return;
 	if (crash_base == 0)
diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
index 8d0374d7ce8e..15683ae13fa5 100644
--- a/arch/riscv/mm/init.c
+++ b/arch/riscv/mm/init.c
@@ -1408,7 +1408,7 @@ static void __init arch_reserve_crashkernel(void)
 
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
-				&low_size, &high);
+				&low_size, NULL, &high);
 	if (ret)
 		return;
 
diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
index f244c5560e7f..b99aeb0db2ee 100644
--- a/arch/s390/kernel/setup.c
+++ b/arch/s390/kernel/setup.c
@@ -605,7 +605,7 @@ static void __init reserve_crashkernel(void)
 	int rc;
 
 	rc = parse_crashkernel(boot_command_line, ident_map_size,
-			       &crash_size, &crash_base, NULL, NULL);
+			       &crash_size, &crash_base, NULL, NULL, NULL);
 
 	crash_base = ALIGN(crash_base, KEXEC_CRASH_MEM_ALIGN);
 	crash_size = ALIGN(crash_size, KEXEC_CRASH_MEM_ALIGN);
diff --git a/arch/sh/kernel/machine_kexec.c b/arch/sh/kernel/machine_kexec.c
index 8321b31d2e19..37073ca1e0ad 100644
--- a/arch/sh/kernel/machine_kexec.c
+++ b/arch/sh/kernel/machine_kexec.c
@@ -146,7 +146,7 @@ void __init reserve_crashkernel(void)
 		return;
 
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
-			&crash_size, &crash_base, NULL, NULL);
+			&crash_size, &crash_base, NULL, NULL, NULL);
 	if (ret == 0 && crash_size > 0) {
 		crashk_res.start = crash_base;
 		crashk_res.end = crash_base + crash_size - 1;
diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index fb27be697128..c22dc630c297 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -608,7 +608,7 @@ static void __init arch_reserve_crashkernel(void)
 
 	ret = parse_crashkernel(boot_command_line, memblock_phys_mem_size(),
 				&crash_size, &crash_base,
-				&low_size, &high);
+				&low_size, NULL, &high);
 	if (ret)
 		return;
 
diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h
index 1fe7e7d1b214..e784aaff2f5a 100644
--- a/include/linux/crash_reserve.h
+++ b/include/linux/crash_reserve.h
@@ -16,7 +16,8 @@ extern struct resource crashk_low_res;
 
 int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base,
-		unsigned long long *low_size, bool *high);
+		unsigned long long *low_size, unsigned long long *cma_size,
+		bool *high);
 
 #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
 #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index acb6bf42e30d..86ae1365d04e 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -172,17 +172,19 @@ static int __init parse_crashkernel_simple(char *cmdline,
 
 #define SUFFIX_HIGH 0
 #define SUFFIX_LOW  1
-#define SUFFIX_NULL 2
+#define SUFFIX_CMA  2
+#define SUFFIX_NULL 3
 static __initdata char *suffix_tbl[] = {
 	[SUFFIX_HIGH] = ",high",
 	[SUFFIX_LOW]  = ",low",
+	[SUFFIX_CMA]  = ",cma",
 	[SUFFIX_NULL] = NULL,
 };
 
 /*
  * That function parses "suffix"  crashkernel command lines like
  *
- *	crashkernel=size,[high|low]
+ *	crashkernel=size,[high|low|cma]
  *
  * It returns 0 on success and -EINVAL on failure.
  */
@@ -298,9 +300,11 @@ int __init parse_crashkernel(char *cmdline,
 			     unsigned long long *crash_size,
 			     unsigned long long *crash_base,
 			     unsigned long long *low_size,
+			     unsigned long long *cma_size,
 			     bool *high)
 {
 	int ret;
+	unsigned long long __always_unused cma_base;
 
 	/* crashkernel=X[@offset] */
 	ret = __parse_crashkernel(cmdline, system_ram, crash_size,
@@ -331,6 +335,14 @@ int __init parse_crashkernel(char *cmdline,
 
 		*high = true;
 	}
+
+	/*
+	 * optional CMA reservation
+	 * cma_base is ignored
+	 */
+	if (cma_size)
+		__parse_crashkernel(cmdline, 0, cma_size,
+			&cma_base, suffix_tbl[SUFFIX_CMA]);
 #endif
 	if (!*crash_size)
 		ret = -EINVAL;
-- 
cgit v1.2.3


From ab475510e0422bb5672d465f9d0f523d72fdb7f1 Mon Sep 17 00:00:00 2001
From: Jiri Bohac <jbohac@suse.cz>
Date: Thu, 12 Jun 2025 12:16:39 +0200
Subject: kdump: implement reserve_crashkernel_cma

reserve_crashkernel_cma() reserves CMA ranges for the crash kernel.  If
allocating the requested size fails, try to reserve in smaller blocks.

Store the reserved ranges in the crashk_cma_ranges array and the number of
ranges in crashk_cma_cnt.

Link: https://lkml.kernel.org/r/aEqpBwOy_ekm0gw9@dwarf.suse.cz
Signed-off-by: Jiri Bohac <jbohac@suse.cz>
Cc: Baoquan He <bhe@redhat.com>
Cc: Dave Young <dyoung@redhat.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Donald Dutile <ddutile@redhat.com>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Philipp Rudo <prudo@redhat.com>
Cc: Pingfan Liu <piliu@redhat.com>
Cc: Tao Liu <ltao@redhat.com>
Cc: Vivek Goyal <vgoyal@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/crash_reserve.h | 12 ++++++++++
 kernel/crash_reserve.c        | 52 +++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/crash_reserve.h b/include/linux/crash_reserve.h
index e784aaff2f5a..7b44b41d0a20 100644
--- a/include/linux/crash_reserve.h
+++ b/include/linux/crash_reserve.h
@@ -13,12 +13,24 @@
  */
 extern struct resource crashk_res;
 extern struct resource crashk_low_res;
+extern struct range crashk_cma_ranges[];
+#if defined(CONFIG_CMA) && defined(CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION)
+#define CRASHKERNEL_CMA
+#define CRASHKERNEL_CMA_RANGES_MAX 4
+extern int crashk_cma_cnt;
+#else
+#define crashk_cma_cnt 0
+#define CRASHKERNEL_CMA_RANGES_MAX 0
+#endif
+
 
 int __init parse_crashkernel(char *cmdline, unsigned long long system_ram,
 		unsigned long long *crash_size, unsigned long long *crash_base,
 		unsigned long long *low_size, unsigned long long *cma_size,
 		bool *high);
 
+void __init reserve_crashkernel_cma(unsigned long long cma_size);
+
 #ifdef CONFIG_ARCH_HAS_GENERIC_CRASHKERNEL_RESERVATION
 #ifndef DEFAULT_CRASH_KERNEL_LOW_SIZE
 #define DEFAULT_CRASH_KERNEL_LOW_SIZE	(128UL << 20)
diff --git a/kernel/crash_reserve.c b/kernel/crash_reserve.c
index 86ae1365d04e..87bf4d41eabb 100644
--- a/kernel/crash_reserve.c
+++ b/kernel/crash_reserve.c
@@ -14,6 +14,8 @@
 #include <linux/cpuhotplug.h>
 #include <linux/memblock.h>
 #include <linux/kmemleak.h>
+#include <linux/cma.h>
+#include <linux/crash_reserve.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -469,6 +471,56 @@ retry:
 #endif
 }
 
+struct range crashk_cma_ranges[CRASHKERNEL_CMA_RANGES_MAX];
+#ifdef CRASHKERNEL_CMA
+int crashk_cma_cnt;
+void __init reserve_crashkernel_cma(unsigned long long cma_size)
+{
+	unsigned long long request_size = roundup(cma_size, PAGE_SIZE);
+	unsigned long long reserved_size = 0;
+
+	if (!cma_size)
+		return;
+
+	while (cma_size > reserved_size &&
+	       crashk_cma_cnt < CRASHKERNEL_CMA_RANGES_MAX) {
+
+		struct cma *res;
+
+		if (cma_declare_contiguous(0, request_size, 0, 0, 0, false,
+				       "crashkernel", &res)) {
+			/* reservation failed, try half-sized blocks */
+			if (request_size <= PAGE_SIZE)
+				break;
+
+			request_size = roundup(request_size / 2, PAGE_SIZE);
+			continue;
+		}
+
+		crashk_cma_ranges[crashk_cma_cnt].start = cma_get_base(res);
+		crashk_cma_ranges[crashk_cma_cnt].end =
+			crashk_cma_ranges[crashk_cma_cnt].start +
+			cma_get_size(res) - 1;
+		++crashk_cma_cnt;
+		reserved_size += request_size;
+	}
+
+	if (cma_size > reserved_size)
+		pr_warn("crashkernel CMA reservation failed: %lld MB requested, %lld MB reserved in %d ranges\n",
+			cma_size >> 20, reserved_size >> 20, crashk_cma_cnt);
+	else
+		pr_info("crashkernel CMA reserved: %lld MB in %d ranges\n",
+			reserved_size >> 20, crashk_cma_cnt);
+}
+
+#else /* CRASHKERNEL_CMA */
+void __init reserve_crashkernel_cma(unsigned long long cma_size)
+{
+	if (cma_size)
+		pr_warn("crashkernel CMA reservation not supported\n");
+}
+#endif
+
 #ifndef HAVE_ARCH_ADD_CRASH_RES_TO_IOMEM_EARLY
 static __init int insert_crashkernel_resources(void)
 {
-- 
cgit v1.2.3


From b76e89e50fc3693b7b8a443ed906320d8ccb93fd Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@linux.alibaba.com>
Date: Thu, 3 Jul 2025 10:10:01 +0800
Subject: panic: generalize panic_print's function to show sys info

'panic_print' was introduced to help debugging kernel panic by dumping
different kinds of system information like tasks' call stack, memory,
ftrace buffer, etc.  Actually this function could also be used to help
debugging other cases like task-hung, soft/hard lockup, etc.  where user
may need the snapshot of system info at that time.

Extract system info dump function related code from panic.c to separate
file sys_info.[ch], for wider usage by other kernel parts for debugging.

Also modify the macro names about singulars/plurals.

Link: https://lkml.kernel.org/r/20250703021004.42328-3-feng.tang@linux.alibaba.com
Signed-off-by: Feng Tang <feng.tang@linux.alibaba.com>
Suggested-by: Petr Mladek <pmladek@suse.com>
Cc: John Ogness <john.ogness@linutronix.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/sys_info.h | 20 ++++++++++++++++++++
 kernel/panic.c           | 36 ++++--------------------------------
 lib/Makefile             |  2 +-
 lib/sys_info.c           | 32 ++++++++++++++++++++++++++++++++
 4 files changed, 57 insertions(+), 33 deletions(-)
 create mode 100644 include/linux/sys_info.h
 create mode 100644 lib/sys_info.c

(limited to 'include/linux')

diff --git a/include/linux/sys_info.h b/include/linux/sys_info.h
new file mode 100644
index 000000000000..53b7e27dbf2a
--- /dev/null
+++ b/include/linux/sys_info.h
@@ -0,0 +1,20 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_SYS_INFO_H
+#define _LINUX_SYS_INFO_H
+
+/*
+ * SYS_INFO_PANIC_CONSOLE_REPLAY is for panic case only, as it needs special
+ * handling which only fits panic case.
+ */
+#define SYS_INFO_TASKS			0x00000001
+#define SYS_INFO_MEM			0x00000002
+#define SYS_INFO_TIMERS			0x00000004
+#define SYS_INFO_LOCKS			0x00000008
+#define SYS_INFO_FTRACE			0x00000010
+#define SYS_INFO_PANIC_CONSOLE_REPLAY	0x00000020
+#define SYS_INFO_ALL_CPU_BT		0x00000040
+#define SYS_INFO_BLOCKED_TASKS		0x00000080
+
+void sys_info(unsigned long si_mask);
+
+#endif	/* _LINUX_SYS_INFO_H */
diff --git a/kernel/panic.c b/kernel/panic.c
index 9b6c5dc28a65..cbb0681177b3 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -36,6 +36,7 @@
 #include <linux/sysfs.h>
 #include <linux/context_tracking.h>
 #include <linux/seq_buf.h>
+#include <linux/sys_info.h>
 #include <trace/events/error_report.h>
 #include <asm/sections.h>
 
@@ -69,14 +70,6 @@ bool panic_triggering_all_cpu_backtrace;
 int panic_timeout = CONFIG_PANIC_TIMEOUT;
 EXPORT_SYMBOL_GPL(panic_timeout);
 
-#define PANIC_PRINT_TASK_INFO		0x00000001
-#define PANIC_PRINT_MEM_INFO		0x00000002
-#define PANIC_PRINT_TIMER_INFO		0x00000004
-#define PANIC_PRINT_LOCK_INFO		0x00000008
-#define PANIC_PRINT_FTRACE_INFO		0x00000010
-#define PANIC_CONSOLE_REPLAY		0x00000020
-#define PANIC_PRINT_ALL_CPU_BT		0x00000040
-#define PANIC_PRINT_BLOCKED_TASKS	0x00000080
 unsigned long panic_print;
 
 ATOMIC_NOTIFIER_HEAD(panic_notifier_list);
@@ -240,31 +233,10 @@ EXPORT_SYMBOL(nmi_panic);
 
 static void panic_console_replay(void)
 {
-	if (panic_print & PANIC_CONSOLE_REPLAY)
+	if (panic_print & SYS_INFO_PANIC_CONSOLE_REPLAY)
 		console_flush_on_panic(CONSOLE_REPLAY_ALL);
 }
 
-static void panic_print_sys_info(void)
-{
-	if (panic_print & PANIC_PRINT_TASK_INFO)
-		show_state();
-
-	if (panic_print & PANIC_PRINT_MEM_INFO)
-		show_mem();
-
-	if (panic_print & PANIC_PRINT_TIMER_INFO)
-		sysrq_timer_list_show();
-
-	if (panic_print & PANIC_PRINT_LOCK_INFO)
-		debug_show_all_locks();
-
-	if (panic_print & PANIC_PRINT_FTRACE_INFO)
-		ftrace_dump(DUMP_ALL);
-
-	if (panic_print & PANIC_PRINT_BLOCKED_TASKS)
-		show_state_filter(TASK_UNINTERRUPTIBLE);
-}
-
 void check_panic_on_warn(const char *origin)
 {
 	unsigned int limit;
@@ -285,7 +257,7 @@ void check_panic_on_warn(const char *origin)
  */
 static void panic_other_cpus_shutdown(bool crash_kexec)
 {
-	if (panic_print & PANIC_PRINT_ALL_CPU_BT) {
+	if (panic_print & SYS_INFO_ALL_CPU_BT) {
 		/* Temporary allow non-panic CPUs to write their backtraces. */
 		panic_triggering_all_cpu_backtrace = true;
 		trigger_all_cpu_backtrace();
@@ -410,7 +382,7 @@ void panic(const char *fmt, ...)
 	 */
 	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
-	panic_print_sys_info();
+	sys_info(panic_print);
 
 	kmsg_dump_desc(KMSG_DUMP_PANIC, buf);
 
diff --git a/lib/Makefile b/lib/Makefile
index c38582f187dd..88d6228089a8 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -40,7 +40,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 is_single_threaded.o plist.o decompress.o kobject_uevent.o \
 	 earlycpio.o seq_buf.o siphash.o dec_and_lock.o \
 	 nmi_backtrace.o win_minmax.o memcat_p.o \
-	 buildid.o objpool.o iomem_copy.o
+	 buildid.o objpool.o iomem_copy.o sys_info.o
 
 lib-$(CONFIG_UNION_FIND) += union_find.o
 lib-$(CONFIG_PRINTK) += dump_stack.o
diff --git a/lib/sys_info.c b/lib/sys_info.c
new file mode 100644
index 000000000000..53031e5cb98e
--- /dev/null
+++ b/lib/sys_info.c
@@ -0,0 +1,32 @@
+// SPDX-License-Identifier: GPL-2.0-only
+#include <linux/sched/debug.h>
+#include <linux/console.h>
+#include <linux/kernel.h>
+#include <linux/ftrace.h>
+#include <linux/nmi.h>
+
+#include <linux/sys_info.h>
+
+void sys_info(unsigned long si_mask)
+{
+	if (si_mask & SYS_INFO_TASKS)
+		show_state();
+
+	if (si_mask & SYS_INFO_MEM)
+		show_mem();
+
+	if (si_mask & SYS_INFO_TIMERS)
+		sysrq_timer_list_show();
+
+	if (si_mask & SYS_INFO_LOCKS)
+		debug_show_all_locks();
+
+	if (si_mask & SYS_INFO_FTRACE)
+		ftrace_dump(DUMP_ALL);
+
+	if (si_mask & SYS_INFO_ALL_CPU_BT)
+		trigger_all_cpu_backtrace();
+
+	if (si_mask & SYS_INFO_BLOCKED_TASKS)
+		show_state_filter(TASK_UNINTERRUPTIBLE);
+}
-- 
cgit v1.2.3


From d747755917bf8ae08f490c3fe7d8e321afab8127 Mon Sep 17 00:00:00 2001
From: Feng Tang <feng.tang@linux.alibaba.com>
Date: Thu, 3 Jul 2025 10:10:02 +0800
Subject: panic: add 'panic_sys_info' sysctl to take human readable string
 parameter

Bitmap definition for 'panic_print' is hard to remember and decode.  Add
'panic_sys_info='sysctl to take human readable string like
"tasks,mem,timers,locks,ftrace,..." and translate it into bitmap.

The detailed mapping is:
	SYS_INFO_TASKS		"tasks"
	SYS_INFO_MEM		"mem"
	SYS_INFO_TIMERS		"timers"
	SYS_INFO_LOCKS		"locks"
	SYS_INFO_FTRACE		"ftrace"
	SYS_INFO_ALL_CPU_BT	"all_bt"
	SYS_INFO_BLOCKED_TASKS	"blocked_tasks"

[nathan@kernel.org: add __maybe_unused to sys_info_avail]
  Link: https://lkml.kernel.org/r/20250708-fix-clang-sys_info_avail-warning-v1-1-60d239eacd64@kernel.org
Link: https://lkml.kernel.org/r/20250703021004.42328-4-feng.tang@linux.alibaba.com
Signed-off-by: Feng Tang <feng.tang@linux.alibaba.com>
Suggested-by: Petr Mladek <pmladek@suse.com>
Cc: John Ogness <john.ogness@linutronix.de>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Lance Yang <lance.yang@linux.dev>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Nathan Chancellor <nathan@kernel.org>
Cc: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/admin-guide/sysctl/kernel.rst | 18 ++++++
 include/linux/sys_info.h                    |  8 +++
 kernel/panic.c                              |  7 +++
 lib/sys_info.c                              | 90 +++++++++++++++++++++++++++++
 4 files changed, 123 insertions(+)

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index 0d08b7a2db2d..cccb06d1a6bf 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -899,6 +899,24 @@ So for example to print tasks and memory info on panic, user can::
   echo 3 > /proc/sys/kernel/panic_print
 
 
+panic_sys_info
+==============
+
+A comma separated list of extra information to be dumped on panic,
+for example, "tasks,mem,timers,...".  It is a human readable alternative
+to 'panic_print'. Possible values are:
+
+=============   ===================================================
+tasks           print all tasks info
+mem             print system memory info
+timer           print timers info
+lock            print locks info if CONFIG_LOCKDEP is on
+ftrace          print ftrace buffer
+all_bt          print all CPUs backtrace (if available in the arch)
+blocked_tasks   print only tasks in uninterruptible (blocked) state
+=============   ===================================================
+
+
 panic_on_rcu_stall
 ==================
 
diff --git a/include/linux/sys_info.h b/include/linux/sys_info.h
index 53b7e27dbf2a..89d77dc4f2ed 100644
--- a/include/linux/sys_info.h
+++ b/include/linux/sys_info.h
@@ -2,6 +2,8 @@
 #ifndef _LINUX_SYS_INFO_H
 #define _LINUX_SYS_INFO_H
 
+#include <linux/sysctl.h>
+
 /*
  * SYS_INFO_PANIC_CONSOLE_REPLAY is for panic case only, as it needs special
  * handling which only fits panic case.
@@ -16,5 +18,11 @@
 #define SYS_INFO_BLOCKED_TASKS		0x00000080
 
 void sys_info(unsigned long si_mask);
+unsigned long sys_info_parse_param(char *str);
 
+#ifdef CONFIG_SYSCTL
+int sysctl_sys_info_handler(const struct ctl_table *ro_table, int write,
+					  void *buffer, size_t *lenp,
+					  loff_t *ppos);
+#endif
 #endif	/* _LINUX_SYS_INFO_H */
diff --git a/kernel/panic.c b/kernel/panic.c
index cbb0681177b3..d7aa427dc23c 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -126,6 +126,13 @@ static const struct ctl_table kern_panic_table[] = {
 		.mode           = 0644,
 		.proc_handler   = proc_douintvec,
 	},
+	{
+		.procname	= "panic_sys_info",
+		.data		= &panic_print,
+		.maxlen         = sizeof(panic_print),
+		.mode		= 0644,
+		.proc_handler	= sysctl_sys_info_handler,
+	},
 };
 
 static __init int kernel_panic_sysctls_init(void)
diff --git a/lib/sys_info.c b/lib/sys_info.c
index 53031e5cb98e..5bf503fd7ec1 100644
--- a/lib/sys_info.c
+++ b/lib/sys_info.c
@@ -3,10 +3,100 @@
 #include <linux/console.h>
 #include <linux/kernel.h>
 #include <linux/ftrace.h>
+#include <linux/sysctl.h>
 #include <linux/nmi.h>
 
 #include <linux/sys_info.h>
 
+struct sys_info_name {
+	unsigned long bit;
+	const char *name;
+};
+
+/*
+ * When 'si_names' gets updated,  please make sure the 'sys_info_avail'
+ * below is updated accordingly.
+ */
+static const struct sys_info_name  si_names[] = {
+	{ SYS_INFO_TASKS,		"tasks" },
+	{ SYS_INFO_MEM,			"mem" },
+	{ SYS_INFO_TIMERS,		"timers" },
+	{ SYS_INFO_LOCKS,		"locks" },
+	{ SYS_INFO_FTRACE,		"ftrace" },
+	{ SYS_INFO_ALL_CPU_BT,		"all_bt" },
+	{ SYS_INFO_BLOCKED_TASKS,	"blocked_tasks" },
+};
+
+/* Expecting string like "xxx_sys_info=tasks,mem,timers,locks,ftrace,..." */
+unsigned long sys_info_parse_param(char *str)
+{
+	unsigned long si_bits = 0;
+	char *s, *name;
+	int i;
+
+	s = str;
+	while ((name = strsep(&s, ",")) && *name) {
+		for (i = 0; i < ARRAY_SIZE(si_names); i++) {
+			if (!strcmp(name, si_names[i].name)) {
+				si_bits |= si_names[i].bit;
+				break;
+			}
+		}
+	}
+
+	return si_bits;
+}
+
+#ifdef CONFIG_SYSCTL
+
+static const char sys_info_avail[] __maybe_unused = "tasks,mem,timers,locks,ftrace,all_bt,blocked_tasks";
+
+int sysctl_sys_info_handler(const struct ctl_table *ro_table, int write,
+					  void *buffer, size_t *lenp,
+					  loff_t *ppos)
+{
+	char names[sizeof(sys_info_avail) + 1];
+	struct ctl_table table;
+	unsigned long *si_bits_global;
+
+	si_bits_global = ro_table->data;
+
+	if (write) {
+		unsigned long si_bits;
+		int ret;
+
+		table = *ro_table;
+		table.data = names;
+		table.maxlen = sizeof(names);
+		ret = proc_dostring(&table, write, buffer, lenp, ppos);
+		if (ret)
+			return ret;
+
+		si_bits = sys_info_parse_param(names);
+		/* The access to the global value is not synchronized. */
+		WRITE_ONCE(*si_bits_global, si_bits);
+		return 0;
+	} else {
+		/* for 'read' operation */
+		char *delim = "";
+		int i, len = 0;
+
+		for (i = 0; i < ARRAY_SIZE(si_names); i++) {
+			if (*si_bits_global & si_names[i].bit) {
+				len += scnprintf(names + len, sizeof(names) - len,
+					"%s%s", delim, si_names[i].name);
+				delim = ",";
+			}
+		}
+
+		table = *ro_table;
+		table.data = names;
+		table.maxlen = sizeof(names);
+		return proc_dostring(&table, write, buffer, lenp, ppos);
+	}
+}
+#endif
+
 void sys_info(unsigned long si_mask)
 {
 	if (si_mask & SYS_INFO_TASKS)
-- 
cgit v1.2.3


From ae2da51def76020fa16f53cd3446c00cafe41008 Mon Sep 17 00:00:00 2001
From: Lance Yang <lance.yang@linux.dev>
Date: Fri, 27 Jun 2025 15:29:22 +0800
Subject: locking/rwsem: make owner helpers globally available

Patch series "extend hung task blocker tracking to rwsems".

Inspired by mutex blocker tracking[1], and having already extended it to
semaphores, let's now add support for reader-writer semaphores (rwsems).

The approach is simple: when a task enters TASK_UNINTERRUPTIBLE while
waiting for an rwsem, we just call hung_task_set_blocker().  The hung task
detector can then query the rwsem's owner to identify the lock holder.

Tracking works reliably for writers, as there can only be a single writer
holding the lock, and its task struct is stored in the owner field.

The main challenge lies with readers.  The owner field points to only one
of many concurrent readers, so we might lose track of the blocker if that
specific reader unlocks, even while others remain.  This is not a
significant issue, however.  In practice, long-lasting lock contention is
almost always caused by a writer.  Therefore, reliably tracking the writer
is the primary goal of this patch series ;)

With this change, the hung task detector can now show blocker task's info
like below:

[Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked for more than 122 seconds.
[Fri Jun 27 15:21:34 2025]       Tainted: G S                  6.16.0-rc3 #8
[Fri Jun 27 15:21:34 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[Fri Jun 27 15:21:34 2025] task:cat             state:D stack:0     pid:28631 tgid:28631 ppid:28501  task_flags:0x400000 flags:0x00004000
[Fri Jun 27 15:21:34 2025] Call Trace:
[Fri Jun 27 15:21:34 2025]  <TASK>
[Fri Jun 27 15:21:34 2025]  __schedule+0x7c7/0x1930
[Fri Jun 27 15:21:34 2025]  ? __pfx___schedule+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? policy_nodemask+0x215/0x340
[Fri Jun 27 15:21:34 2025]  ? _raw_spin_lock_irq+0x8a/0xe0
[Fri Jun 27 15:21:34 2025]  ? __pfx__raw_spin_lock_irq+0x10/0x10
[Fri Jun 27 15:21:34 2025]  schedule+0x6a/0x180
[Fri Jun 27 15:21:34 2025]  schedule_preempt_disabled+0x15/0x30
[Fri Jun 27 15:21:34 2025]  rwsem_down_read_slowpath+0x55e/0xe10
[Fri Jun 27 15:21:34 2025]  ? __pfx_rwsem_down_read_slowpath+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? __pfx___might_resched+0x10/0x10
[Fri Jun 27 15:21:34 2025]  down_read+0xc9/0x230
[Fri Jun 27 15:21:34 2025]  ? __pfx_down_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? __debugfs_file_get+0x14d/0x700
[Fri Jun 27 15:21:34 2025]  ? __pfx___debugfs_file_get+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? handle_pte_fault+0x52a/0x710
[Fri Jun 27 15:21:34 2025]  ? selinux_file_permission+0x3a9/0x590
[Fri Jun 27 15:21:34 2025]  read_dummy_rwsem_read+0x4a/0x90
[Fri Jun 27 15:21:34 2025]  full_proxy_read+0xff/0x1c0
[Fri Jun 27 15:21:34 2025]  ? rw_verify_area+0x6d/0x410
[Fri Jun 27 15:21:34 2025]  vfs_read+0x177/0xa50
[Fri Jun 27 15:21:34 2025]  ? __pfx_vfs_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? fdget_pos+0x1cf/0x4c0
[Fri Jun 27 15:21:34 2025]  ksys_read+0xfc/0x1d0
[Fri Jun 27 15:21:34 2025]  ? __pfx_ksys_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  do_syscall_64+0x66/0x2d0
[Fri Jun 27 15:21:34 2025]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f3f8faefb40
[Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffdeda5ab98 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f3f8faefb40
[Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 00000000010fa000 RDI: 0000000000000003
[Fri Jun 27 15:21:34 2025] RBP: 00000000010fa000 R08: 0000000000000000 R09: 0000000000010fff
[Fri Jun 27 15:21:34 2025] R10: 00007ffdeda59fe0 R11: 0000000000000246 R12: 00000000010fa000
[Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff
[Fri Jun 27 15:21:34 2025]  </TASK>
[Fri Jun 27 15:21:34 2025] INFO: task cat:28631 <reader> blocked on an rw-semaphore likely owned by task cat:28630 <writer>
[Fri Jun 27 15:21:34 2025] task:cat             state:S stack:0     pid:28630 tgid:28630 ppid:28501  task_flags:0x400000 flags:0x00004000
[Fri Jun 27 15:21:34 2025] Call Trace:
[Fri Jun 27 15:21:34 2025]  <TASK>
[Fri Jun 27 15:21:34 2025]  __schedule+0x7c7/0x1930
[Fri Jun 27 15:21:34 2025]  ? __pfx___schedule+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? __mod_timer+0x304/0xa80
[Fri Jun 27 15:21:34 2025]  schedule+0x6a/0x180
[Fri Jun 27 15:21:34 2025]  schedule_timeout+0xfb/0x230
[Fri Jun 27 15:21:34 2025]  ? __pfx_schedule_timeout+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? __pfx_process_timeout+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? down_write+0xc4/0x140
[Fri Jun 27 15:21:34 2025]  msleep_interruptible+0xbe/0x150
[Fri Jun 27 15:21:34 2025]  read_dummy_rwsem_write+0x54/0x90
[Fri Jun 27 15:21:34 2025]  full_proxy_read+0xff/0x1c0
[Fri Jun 27 15:21:34 2025]  ? rw_verify_area+0x6d/0x410
[Fri Jun 27 15:21:34 2025]  vfs_read+0x177/0xa50
[Fri Jun 27 15:21:34 2025]  ? __pfx_vfs_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? fdget_pos+0x1cf/0x4c0
[Fri Jun 27 15:21:34 2025]  ksys_read+0xfc/0x1d0
[Fri Jun 27 15:21:34 2025]  ? __pfx_ksys_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  do_syscall_64+0x66/0x2d0
[Fri Jun 27 15:21:34 2025]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f8f288efb40
[Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffffb631038 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f8f288efb40
[Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 000000002a4b5000 RDI: 0000000000000003
[Fri Jun 27 15:21:34 2025] RBP: 000000002a4b5000 R08: 0000000000000000 R09: 0000000000010fff
[Fri Jun 27 15:21:34 2025] R10: 00007ffffb630460 R11: 0000000000000246 R12: 000000002a4b5000
[Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff
[Fri Jun 27 15:21:34 2025]  </TASK>


This patch (of 3):

In preparation for extending blocker tracking to support rwsems, make the
rwsem_owner() and is_rwsem_reader_owned() helpers globally available for
determining if the blocker is a writer or one of the readers.

Additionally, a stale owner pointer in a reader-owned rwsem can lead to
false positives in blocker tracking when CONFIG_DETECT_HUNG_TASK_BLOCKER
is enabled.  To mitigate this, clear the owner field on the reader unlock
path, similar to what CONFIG_DEBUG_RWSEMS does.  A NULL owner is better
than a stale one for diagnostics.

Link: https://lkml.kernel.org/r/20250627072924.36567-1-lance.yang@linux.dev
Link: https://lkml.kernel.org/r/20250627072924.36567-2-lance.yang@linux.dev
Link: https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com/ [1]
Signed-off-by: Lance Yang <lance.yang@linux.dev>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Anna Schumaker <anna.schumaker@oracle.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joel Granados <joel.granados@kernel.org>
Cc: John Stultz <jstultz@google.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Mingzhe Yang <mingzhe.yang@ly.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tomasz Figa <tfiga@chromium.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yongliang Gao <leonylgao@tencent.com>
Cc: Zi Li <zi.li@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rwsem.h  | 12 ++++++++++++
 kernel/locking/rwsem.c | 14 +++++++-------
 2 files changed, 19 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index c8b543d428b0..544853bed5b9 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -132,6 +132,18 @@ static inline int rwsem_is_contended(struct rw_semaphore *sem)
 	return !list_empty(&sem->wait_list);
 }
 
+#if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER)
+/*
+ * Return just the real task structure pointer of the owner
+ */
+extern struct task_struct *rwsem_owner(struct rw_semaphore *sem);
+
+/*
+ * Return true if the rwsem is owned by a reader.
+ */
+extern bool is_rwsem_reader_owned(struct rw_semaphore *sem);
+#endif
+
 #else /* !CONFIG_PREEMPT_RT */
 
 #include <linux/rwbase_rt.h>
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index 2ddb827e3bea..a310eb9896de 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -181,11 +181,11 @@ static inline void rwsem_set_reader_owned(struct rw_semaphore *sem)
 	__rwsem_set_reader_owned(sem, current);
 }
 
-#ifdef CONFIG_DEBUG_RWSEMS
+#if defined(CONFIG_DEBUG_RWSEMS) || defined(CONFIG_DETECT_HUNG_TASK_BLOCKER)
 /*
  * Return just the real task structure pointer of the owner
  */
-static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
+struct task_struct *rwsem_owner(struct rw_semaphore *sem)
 {
 	return (struct task_struct *)
 		(atomic_long_read(&sem->owner) & ~RWSEM_OWNER_FLAGS_MASK);
@@ -194,7 +194,7 @@ static inline struct task_struct *rwsem_owner(struct rw_semaphore *sem)
 /*
  * Return true if the rwsem is owned by a reader.
  */
-static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
+bool is_rwsem_reader_owned(struct rw_semaphore *sem)
 {
 	/*
 	 * Check the count to see if it is write-locked.
@@ -207,10 +207,10 @@ static inline bool is_rwsem_reader_owned(struct rw_semaphore *sem)
 }
 
 /*
- * With CONFIG_DEBUG_RWSEMS configured, it will make sure that if there
- * is a task pointer in owner of a reader-owned rwsem, it will be the
- * real owner or one of the real owners. The only exception is when the
- * unlock is done by up_read_non_owner().
+ * With CONFIG_DEBUG_RWSEMS or CONFIG_DETECT_HUNG_TASK_BLOCKER configured,
+ * it will make sure that the owner field of a reader-owned rwsem either
+ * points to a real reader-owner(s) or gets cleared. The only exception is
+ * when the unlock is done by up_read_non_owner().
  */
 static inline void rwsem_clear_reader_owned(struct rw_semaphore *sem)
 {
-- 
cgit v1.2.3


From 77da18de55ac6417e48905bec8b3c66f023b15a9 Mon Sep 17 00:00:00 2001
From: Lance Yang <lance.yang@linux.dev>
Date: Fri, 27 Jun 2025 15:29:23 +0800
Subject: hung_task: extend hung task blocker tracking to rwsems

Inspired by mutex blocker tracking[1], and having already extended it to
semaphores, let's now add support for reader-writer semaphores (rwsems).

The approach is simple: when a task enters TASK_UNINTERRUPTIBLE while
waiting for an rwsem, we just call hung_task_set_blocker().  The hung task
detector can then query the rwsem's owner to identify the lock holder.

Tracking works reliably for writers, as there can only be a single writer
holding the lock, and its task struct is stored in the owner field.

The main challenge lies with readers.  The owner field points to only one
of many concurrent readers, so we might lose track of the blocker if that
specific reader unlocks, even while others remain.  This is not a
significant issue, however.  In practice, long-lasting lock contention is
almost always caused by a writer.  Therefore, reliably tracking the writer
is the primary goal of this patch series ;)

With this change, the hung task detector can now show blocker task's info
like below:

[Fri Jun 27 15:21:34 2025] INFO: task cat:28631 blocked for more than 122 seconds.
[Fri Jun 27 15:21:34 2025]       Tainted: G S                  6.16.0-rc3 #8
[Fri Jun 27 15:21:34 2025] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message.
[Fri Jun 27 15:21:34 2025] task:cat             state:D stack:0     pid:28631 tgid:28631 ppid:28501  task_flags:0x400000 flags:0x00004000
[Fri Jun 27 15:21:34 2025] Call Trace:
[Fri Jun 27 15:21:34 2025]  <TASK>
[Fri Jun 27 15:21:34 2025]  __schedule+0x7c7/0x1930
[Fri Jun 27 15:21:34 2025]  ? __pfx___schedule+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? policy_nodemask+0x215/0x340
[Fri Jun 27 15:21:34 2025]  ? _raw_spin_lock_irq+0x8a/0xe0
[Fri Jun 27 15:21:34 2025]  ? __pfx__raw_spin_lock_irq+0x10/0x10
[Fri Jun 27 15:21:34 2025]  schedule+0x6a/0x180
[Fri Jun 27 15:21:34 2025]  schedule_preempt_disabled+0x15/0x30
[Fri Jun 27 15:21:34 2025]  rwsem_down_read_slowpath+0x55e/0xe10
[Fri Jun 27 15:21:34 2025]  ? __pfx_rwsem_down_read_slowpath+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? __pfx___might_resched+0x10/0x10
[Fri Jun 27 15:21:34 2025]  down_read+0xc9/0x230
[Fri Jun 27 15:21:34 2025]  ? __pfx_down_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? __debugfs_file_get+0x14d/0x700
[Fri Jun 27 15:21:34 2025]  ? __pfx___debugfs_file_get+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? handle_pte_fault+0x52a/0x710
[Fri Jun 27 15:21:34 2025]  ? selinux_file_permission+0x3a9/0x590
[Fri Jun 27 15:21:34 2025]  read_dummy_rwsem_read+0x4a/0x90
[Fri Jun 27 15:21:34 2025]  full_proxy_read+0xff/0x1c0
[Fri Jun 27 15:21:34 2025]  ? rw_verify_area+0x6d/0x410
[Fri Jun 27 15:21:34 2025]  vfs_read+0x177/0xa50
[Fri Jun 27 15:21:34 2025]  ? __pfx_vfs_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? fdget_pos+0x1cf/0x4c0
[Fri Jun 27 15:21:34 2025]  ksys_read+0xfc/0x1d0
[Fri Jun 27 15:21:34 2025]  ? __pfx_ksys_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  do_syscall_64+0x66/0x2d0
[Fri Jun 27 15:21:34 2025]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f3f8faefb40
[Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffdeda5ab98 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f3f8faefb40
[Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 00000000010fa000 RDI: 0000000000000003
[Fri Jun 27 15:21:34 2025] RBP: 00000000010fa000 R08: 0000000000000000 R09: 0000000000010fff
[Fri Jun 27 15:21:34 2025] R10: 00007ffdeda59fe0 R11: 0000000000000246 R12: 00000000010fa000
[Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff
[Fri Jun 27 15:21:34 2025]  </TASK>
[Fri Jun 27 15:21:34 2025] INFO: task cat:28631 <reader> blocked on an rw-semaphore likely owned by task cat:28630 <writer>
[Fri Jun 27 15:21:34 2025] task:cat             state:S stack:0     pid:28630 tgid:28630 ppid:28501  task_flags:0x400000 flags:0x00004000
[Fri Jun 27 15:21:34 2025] Call Trace:
[Fri Jun 27 15:21:34 2025]  <TASK>
[Fri Jun 27 15:21:34 2025]  __schedule+0x7c7/0x1930
[Fri Jun 27 15:21:34 2025]  ? __pfx___schedule+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? __mod_timer+0x304/0xa80
[Fri Jun 27 15:21:34 2025]  schedule+0x6a/0x180
[Fri Jun 27 15:21:34 2025]  schedule_timeout+0xfb/0x230
[Fri Jun 27 15:21:34 2025]  ? __pfx_schedule_timeout+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? __pfx_process_timeout+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? down_write+0xc4/0x140
[Fri Jun 27 15:21:34 2025]  msleep_interruptible+0xbe/0x150
[Fri Jun 27 15:21:34 2025]  read_dummy_rwsem_write+0x54/0x90
[Fri Jun 27 15:21:34 2025]  full_proxy_read+0xff/0x1c0
[Fri Jun 27 15:21:34 2025]  ? rw_verify_area+0x6d/0x410
[Fri Jun 27 15:21:34 2025]  vfs_read+0x177/0xa50
[Fri Jun 27 15:21:34 2025]  ? __pfx_vfs_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  ? fdget_pos+0x1cf/0x4c0
[Fri Jun 27 15:21:34 2025]  ksys_read+0xfc/0x1d0
[Fri Jun 27 15:21:34 2025]  ? __pfx_ksys_read+0x10/0x10
[Fri Jun 27 15:21:34 2025]  do_syscall_64+0x66/0x2d0
[Fri Jun 27 15:21:34 2025]  entry_SYSCALL_64_after_hwframe+0x76/0x7e
[Fri Jun 27 15:21:34 2025] RIP: 0033:0x7f8f288efb40
[Fri Jun 27 15:21:34 2025] RSP: 002b:00007ffffb631038 EFLAGS: 00000246 ORIG_RAX: 0000000000000000
[Fri Jun 27 15:21:34 2025] RAX: ffffffffffffffda RBX: 0000000000010000 RCX: 00007f8f288efb40
[Fri Jun 27 15:21:34 2025] RDX: 0000000000010000 RSI: 000000002a4b5000 RDI: 0000000000000003
[Fri Jun 27 15:21:34 2025] RBP: 000000002a4b5000 R08: 0000000000000000 R09: 0000000000010fff
[Fri Jun 27 15:21:34 2025] R10: 00007ffffb630460 R11: 0000000000000246 R12: 000000002a4b5000
[Fri Jun 27 15:21:34 2025] R13: 0000000000000003 R14: 0000000000000000 R15: 0000000000000fff
[Fri Jun 27 15:21:34 2025]  </TASK>

[1] https://lore.kernel.org/all/174046694331.2194069.15472952050240807469.stgit@mhiramat.tok.corp.google.com/

Link: https://lkml.kernel.org/r/20250627072924.36567-3-lance.yang@linux.dev
Signed-off-by: Lance Yang <lance.yang@linux.dev>
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Anna Schumaker <anna.schumaker@oracle.com>
Cc: Boqun Feng <boqun.feng@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Joel Granados <joel.granados@kernel.org>
Cc: John Stultz <jstultz@google.com>
Cc: Kent Overstreet <kent.overstreet@linux.dev>
Cc: Mingzhe Yang <mingzhe.yang@ly.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Tomasz Figa <tfiga@chromium.org>
Cc: Waiman Long <longman@redhat.com>
Cc: Will Deacon <will@kernel.org>
Cc: Yongliang Gao <leonylgao@tencent.com>
Cc: Zi Li <zi.li@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/hung_task.h | 18 +++++++++---------
 kernel/hung_task.c        | 29 +++++++++++++++++++++++++----
 kernel/locking/rwsem.c    | 17 ++++++++++++++++-
 3 files changed, 50 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/hung_task.h b/include/linux/hung_task.h
index 1bc2b3244613..34e615c76ca5 100644
--- a/include/linux/hung_task.h
+++ b/include/linux/hung_task.h
@@ -21,17 +21,17 @@
  * type.
  *
  * Type encoding:
- * 00 - Blocked on mutex        (BLOCKER_TYPE_MUTEX)
- * 01 - Blocked on semaphore    (BLOCKER_TYPE_SEM)
- * 10 - Blocked on rt-mutex     (BLOCKER_TYPE_RTMUTEX)
- * 11 - Blocked on rw-semaphore (BLOCKER_TYPE_RWSEM)
+ * 00 - Blocked on mutex			(BLOCKER_TYPE_MUTEX)
+ * 01 - Blocked on semaphore			(BLOCKER_TYPE_SEM)
+ * 10 - Blocked on rw-semaphore as READER	(BLOCKER_TYPE_RWSEM_READER)
+ * 11 - Blocked on rw-semaphore as WRITER	(BLOCKER_TYPE_RWSEM_WRITER)
  */
-#define BLOCKER_TYPE_MUTEX      0x00UL
-#define BLOCKER_TYPE_SEM        0x01UL
-#define BLOCKER_TYPE_RTMUTEX    0x02UL
-#define BLOCKER_TYPE_RWSEM      0x03UL
+#define BLOCKER_TYPE_MUTEX		0x00UL
+#define BLOCKER_TYPE_SEM		0x01UL
+#define BLOCKER_TYPE_RWSEM_READER	0x02UL
+#define BLOCKER_TYPE_RWSEM_WRITER	0x03UL
 
-#define BLOCKER_TYPE_MASK       0x03UL
+#define BLOCKER_TYPE_MASK		0x03UL
 
 #ifdef CONFIG_DETECT_HUNG_TASK_BLOCKER
 static inline void hung_task_set_blocker(void *lock, unsigned long type)
diff --git a/kernel/hung_task.c b/kernel/hung_task.c
index d2432df2b905..8708a1205f82 100644
--- a/kernel/hung_task.c
+++ b/kernel/hung_task.c
@@ -23,6 +23,7 @@
 #include <linux/sched/debug.h>
 #include <linux/sched/sysctl.h>
 #include <linux/hung_task.h>
+#include <linux/rwsem.h>
 
 #include <trace/events/sched.h>
 
@@ -100,6 +101,7 @@ static void debug_show_blocker(struct task_struct *task)
 {
 	struct task_struct *g, *t;
 	unsigned long owner, blocker, blocker_type;
+	const char *rwsem_blocked_by, *rwsem_blocked_as;
 
 	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "No rcu lock held");
 
@@ -111,12 +113,20 @@ static void debug_show_blocker(struct task_struct *task)
 
 	switch (blocker_type) {
 	case BLOCKER_TYPE_MUTEX:
-		owner = mutex_get_owner(
-			(struct mutex *)hung_task_blocker_to_lock(blocker));
+		owner = mutex_get_owner(hung_task_blocker_to_lock(blocker));
 		break;
 	case BLOCKER_TYPE_SEM:
-		owner = sem_last_holder(
-			(struct semaphore *)hung_task_blocker_to_lock(blocker));
+		owner = sem_last_holder(hung_task_blocker_to_lock(blocker));
+		break;
+	case BLOCKER_TYPE_RWSEM_READER:
+	case BLOCKER_TYPE_RWSEM_WRITER:
+		owner = (unsigned long)rwsem_owner(
+					hung_task_blocker_to_lock(blocker));
+		rwsem_blocked_as = (blocker_type == BLOCKER_TYPE_RWSEM_READER) ?
+					"reader" : "writer";
+		rwsem_blocked_by = is_rwsem_reader_owned(
+					hung_task_blocker_to_lock(blocker)) ?
+					"reader" : "writer";
 		break;
 	default:
 		WARN_ON_ONCE(1);
@@ -134,6 +144,11 @@ static void debug_show_blocker(struct task_struct *task)
 			pr_err("INFO: task %s:%d is blocked on a semaphore, but the last holder is not found.\n",
 			       task->comm, task->pid);
 			break;
+		case BLOCKER_TYPE_RWSEM_READER:
+		case BLOCKER_TYPE_RWSEM_WRITER:
+			pr_err("INFO: task %s:%d is blocked on an rw-semaphore, but the owner is not found.\n",
+			       task->comm, task->pid);
+			break;
 		}
 		return;
 	}
@@ -152,6 +167,12 @@ static void debug_show_blocker(struct task_struct *task)
 			pr_err("INFO: task %s:%d blocked on a semaphore likely last held by task %s:%d\n",
 			       task->comm, task->pid, t->comm, t->pid);
 			break;
+		case BLOCKER_TYPE_RWSEM_READER:
+		case BLOCKER_TYPE_RWSEM_WRITER:
+			pr_err("INFO: task %s:%d <%s> blocked on an rw-semaphore likely owned by task %s:%d <%s>\n",
+			       task->comm, task->pid, rwsem_blocked_as, t->comm,
+			       t->pid, rwsem_blocked_by);
+			break;
 		}
 		sched_show_task(t);
 		return;
diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
index a310eb9896de..92c6332da401 100644
--- a/kernel/locking/rwsem.c
+++ b/kernel/locking/rwsem.c
@@ -27,6 +27,7 @@
 #include <linux/export.h>
 #include <linux/rwsem.h>
 #include <linux/atomic.h>
+#include <linux/hung_task.h>
 #include <trace/events/lock.h>
 
 #ifndef CONFIG_PREEMPT_RT
@@ -1065,10 +1066,13 @@ queue:
 		wake_up_q(&wake_q);
 
 	trace_contention_begin(sem, LCB_F_READ);
+	set_current_state(state);
+
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_READER);
 
 	/* wait to be given the lock */
 	for (;;) {
-		set_current_state(state);
 		if (!smp_load_acquire(&waiter.task)) {
 			/* Matches rwsem_mark_wake()'s smp_store_release(). */
 			break;
@@ -1083,8 +1087,12 @@ queue:
 		}
 		schedule_preempt_disabled();
 		lockevent_inc(rwsem_sleep_reader);
+		set_current_state(state);
 	}
 
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_clear_blocker();
+
 	__set_current_state(TASK_RUNNING);
 	lockevent_inc(rwsem_rlock);
 	trace_contention_end(sem, 0);
@@ -1146,6 +1154,9 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 	set_current_state(state);
 	trace_contention_begin(sem, LCB_F_WRITE);
 
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_set_blocker(sem, BLOCKER_TYPE_RWSEM_WRITER);
+
 	for (;;) {
 		if (rwsem_try_write_lock(sem, &waiter)) {
 			/* rwsem_try_write_lock() implies ACQUIRE on success */
@@ -1179,6 +1190,10 @@ rwsem_down_write_slowpath(struct rw_semaphore *sem, int state)
 trylock_again:
 		raw_spin_lock_irq(&sem->wait_lock);
 	}
+
+	if (state == TASK_UNINTERRUPTIBLE)
+		hung_task_clear_blocker();
+
 	__set_current_state(TASK_RUNNING);
 	raw_spin_unlock_irq(&sem->wait_lock);
 	lockevent_inc(rwsem_wlock);
-- 
cgit v1.2.3


From b3d5fd6f82dde8c906dc2a587003a44252ae5eae Mon Sep 17 00:00:00 2001
From: Kuan-Wei Chiu <visitorckw@gmail.com>
Date: Fri, 6 Jun 2025 21:47:56 +0800
Subject: lib/math/gcd: use static key to select implementation at runtime

Patch series "Optimize GCD performance on RISC-V by selecting
implementation at runtime", v3.

The current implementation of gcd() selects between the binary GCD and the
odd-even GCD algorithm at compile time, depending on whether
CONFIG_CPU_NO_EFFICIENT_FFS is set.  On platforms like RISC-V, however,
this compile-time decision can be misleading: even when the compiler emits
ctz instructions based on the assumption that they are efficient (as is
the case when CONFIG_RISCV_ISA_ZBB is enabled), the actual hardware may
lack support for the Zbb extension.  In such cases, ffs() falls back to a
software implementation at runtime, making the binary GCD algorithm
significantly slower than the odd-even variant.

To address this, we introduce a static key to allow runtime selection
between the binary and odd-even GCD implementations.  On RISC-V, the
kernel now checks for Zbb support during boot.  If Zbb is unavailable, the
static key is disabled so that gcd() consistently uses the more efficient
odd-even algorithm in that scenario.  Additionally, to further reduce code
size, we select CONFIG_CPU_NO_EFFICIENT_FFS automatically when
CONFIG_RISCV_ISA_ZBB is not enabled, avoiding compilation of the unused
binary GCD implementation entirely on systems where it would never be
executed.

This series ensures that the most efficient GCD algorithm is used in
practice and avoids compiling unnecessary code based on hardware
capabilities and kernel configuration.


This patch (of 3):

On platforms like RISC-V, the compiler may generate hardware FFS
instructions even if the underlying CPU does not actually support them.
Currently, the GCD implementation is chosen at compile time based on
CONFIG_CPU_NO_EFFICIENT_FFS, which can result in suboptimal behavior on
such systems.

Introduce a static key, efficient_ffs_key, to enable runtime selection
between the binary GCD (using ffs) and the odd-even GCD implementation.
This allows the kernel to default to the faster binary GCD when FFS is
efficient, while retaining the ability to fall back when needed.

Link: https://lkml.kernel.org/r/20250606134758.1308400-1-visitorckw@gmail.com
Link: https://lkml.kernel.org/r/20250606134758.1308400-2-visitorckw@gmail.com
Co-developed-by: Yu-Chun Lin <eleanor15x@gmail.com>
Signed-off-by: Yu-Chun Lin <eleanor15x@gmail.com>
Signed-off-by: Kuan-Wei Chiu <visitorckw@gmail.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Ching-Chun (Jim) Huang <jserv@ccns.ncku.edu.tw>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/gcd.h |  3 +++
 lib/math/gcd.c      | 27 +++++++++++++++------------
 2 files changed, 18 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/gcd.h b/include/linux/gcd.h
index cb572677fd7f..616e81a7f7e3 100644
--- a/include/linux/gcd.h
+++ b/include/linux/gcd.h
@@ -3,6 +3,9 @@
 #define _GCD_H
 
 #include <linux/compiler.h>
+#include <linux/jump_label.h>
+
+DECLARE_STATIC_KEY_TRUE(efficient_ffs_key);
 
 unsigned long gcd(unsigned long a, unsigned long b) __attribute_const__;
 
diff --git a/lib/math/gcd.c b/lib/math/gcd.c
index e3b042214d1b..62efca6787ae 100644
--- a/lib/math/gcd.c
+++ b/lib/math/gcd.c
@@ -11,22 +11,16 @@
  * has decent hardware division.
  */
 
+DEFINE_STATIC_KEY_TRUE(efficient_ffs_key);
+
 #if !defined(CONFIG_CPU_NO_EFFICIENT_FFS)
 
 /* If __ffs is available, the even/odd algorithm benchmarks slower. */
 
-/**
- * gcd - calculate and return the greatest common divisor of 2 unsigned longs
- * @a: first value
- * @b: second value
- */
-unsigned long gcd(unsigned long a, unsigned long b)
+static unsigned long binary_gcd(unsigned long a, unsigned long b)
 {
 	unsigned long r = a | b;
 
-	if (!a || !b)
-		return r;
-
 	b >>= __ffs(b);
 	if (b == 1)
 		return r & -r;
@@ -44,9 +38,15 @@ unsigned long gcd(unsigned long a, unsigned long b)
 	}
 }
 
-#else
+#endif
 
 /* If normalization is done by loops, the even/odd algorithm is a win. */
+
+/**
+ * gcd - calculate and return the greatest common divisor of 2 unsigned longs
+ * @a: first value
+ * @b: second value
+ */
 unsigned long gcd(unsigned long a, unsigned long b)
 {
 	unsigned long r = a | b;
@@ -54,6 +54,11 @@ unsigned long gcd(unsigned long a, unsigned long b)
 	if (!a || !b)
 		return r;
 
+#if !defined(CONFIG_CPU_NO_EFFICIENT_FFS)
+	if (static_branch_likely(&efficient_ffs_key))
+		return binary_gcd(a, b);
+#endif
+
 	/* Isolate lsbit of r */
 	r &= -r;
 
@@ -80,6 +85,4 @@ unsigned long gcd(unsigned long a, unsigned long b)
 	}
 }
 
-#endif
-
 EXPORT_SYMBOL_GPL(gcd);
-- 
cgit v1.2.3


From 438794e93f6271af93f0d16a1851725115b5fd51 Mon Sep 17 00:00:00 2001
From: Jianbo Liu <jianbol@nvidia.com>
Date: Thu, 17 Jul 2025 09:48:13 +0300
Subject: net/mlx5: Add IFC bits to support RSS for IPSec offload

This adds the capabilities, ipsec_next_header and inner/outer
l4_type_ext fields to support RSS for the decrypted packets.

These fields are specifically for firmware steering. HWS validation
logic is updated to correctly handle the changes, ensuring the
unsupported fields are not set.

Besides, reserved_at_c4 is fixed to reserved_at_d4 to reflect the
accurate offset within the structure.

Signed-off-by: Jianbo Liu <jianbol@nvidia.com>
Reviewed-by: Carolina Jubran <cjubran@nvidia.com>
Reviewed-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1752734895-257735-2-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 .../mellanox/mlx5/core/steering/hws/definer.c      | 13 ++++++-----
 include/linux/mlx5/mlx5_ifc.h                      | 25 ++++++++++++++++------
 2 files changed, 26 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
index d45e1145d197..c6436c3a7a83 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/hws/definer.c
@@ -727,8 +727,9 @@ hws_definer_conv_outer(struct mlx5hws_definer_conv_data *cd,
 	u32 *s_ipv6, *d_ipv6;
 
 	if (HWS_IS_FLD_SET_SZ(match_param, outer_headers.l4_type, 0x2) ||
-	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c2, 0xe) ||
-	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c4, 0x4)) {
+	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.l4_type_ext, 0x4) ||
+	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_c6, 0xa) ||
+	    HWS_IS_FLD_SET_SZ(match_param, outer_headers.reserved_at_d4, 0x4)) {
 		mlx5hws_err(cd->ctx, "Unsupported outer parameters set\n");
 		return -EINVAL;
 	}
@@ -903,8 +904,9 @@ hws_definer_conv_inner(struct mlx5hws_definer_conv_data *cd,
 	u32 *s_ipv6, *d_ipv6;
 
 	if (HWS_IS_FLD_SET_SZ(match_param, inner_headers.l4_type, 0x2) ||
-	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c2, 0xe) ||
-	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c4, 0x4)) {
+	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.l4_type_ext, 0x4) ||
+	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_c6, 0xa) ||
+	    HWS_IS_FLD_SET_SZ(match_param, inner_headers.reserved_at_d4, 0x4)) {
 		mlx5hws_err(cd->ctx, "Unsupported inner parameters set\n");
 		return -EINVAL;
 	}
@@ -1279,7 +1281,8 @@ hws_definer_conv_misc2(struct mlx5hws_definer_conv_data *cd,
 	struct mlx5hws_definer_fc *curr_fc;
 
 	if (HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1a0, 0x8) ||
-	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1b8, 0x8) ||
+	    HWS_IS_FLD_SET_SZ(match_param,
+			      misc_parameters_2.ipsec_next_header, 0x8) ||
 	    HWS_IS_FLD_SET_SZ(match_param, misc_parameters_2.reserved_at_1c0, 0x40) ||
 	    HWS_IS_FLD_SET(match_param, misc_parameters_2.macsec_syndrome) ||
 	    HWS_IS_FLD_SET(match_param, misc_parameters_2.ipsec_syndrome)) {
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 639dd0b56655..c9a7773ac8ec 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -420,7 +420,8 @@ struct mlx5_ifc_flow_table_fields_supported_bits {
 
 /* Table 2170 - Flow Table Fields Supported 2 Format */
 struct mlx5_ifc_flow_table_fields_supported_2_bits {
-	u8         reserved_at_0[0x2];
+	u8         inner_l4_type_ext[0x1];
+	u8         outer_l4_type_ext[0x1];
 	u8         inner_l4_type[0x1];
 	u8         outer_l4_type[0x1];
 	u8         reserved_at_4[0xa];
@@ -429,7 +430,11 @@ struct mlx5_ifc_flow_table_fields_supported_2_bits {
 	u8         tunnel_header_0_1[0x1];
 	u8         reserved_at_11[0xf];
 
-	u8         reserved_at_20[0x60];
+	u8         reserved_at_20[0xf];
+	u8         ipsec_next_header[0x1];
+	u8         reserved_at_30[0x10];
+
+	u8         reserved_at_40[0x40];
 };
 
 struct mlx5_ifc_flow_table_prop_layout_bits {
@@ -552,6 +557,13 @@ enum {
 	MLX5_PACKET_L4_TYPE_UDP,
 };
 
+enum {
+	MLX5_PACKET_L4_TYPE_EXT_NONE,
+	MLX5_PACKET_L4_TYPE_EXT_TCP,
+	MLX5_PACKET_L4_TYPE_EXT_UDP,
+	MLX5_PACKET_L4_TYPE_EXT_ICMP,
+};
+
 struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 	u8         smac_47_16[0x20];
 
@@ -578,10 +590,10 @@ struct mlx5_ifc_fte_match_set_lyr_2_4_bits {
 	u8         tcp_dport[0x10];
 
 	u8         l4_type[0x2];
-	u8         reserved_at_c2[0xe];
+	u8         l4_type_ext[0x4];
+	u8         reserved_at_c6[0xa];
 	u8         ipv4_ihl[0x4];
-	u8         reserved_at_c4[0x4];
-
+	u8         reserved_at_d4[0x4];
 	u8         ttl_hoplimit[0x8];
 
 	u8         udp_sport[0x10];
@@ -689,10 +701,9 @@ struct mlx5_ifc_fte_match_set_misc2_bits {
 	u8         metadata_reg_a[0x20];
 
 	u8         reserved_at_1a0[0x8];
-
 	u8         macsec_syndrome[0x8];
 	u8         ipsec_syndrome[0x8];
-	u8         reserved_at_1b8[0x8];
+	u8         ipsec_next_header[0x8];
 
 	u8         reserved_at_1c0[0x40];
 };
-- 
cgit v1.2.3


From 6f09ee0b583cad4f2b6a82842c26235bee3d5c2e Mon Sep 17 00:00:00 2001
From: Oren Sidi <osidi@nvidia.com>
Date: Thu, 17 Jul 2025 09:48:14 +0300
Subject: net/mlx5: Add IFC bits and enums for buf_ownership

Extend structure layouts and defines buf_ownership.
buf_ownership indicates whether the buffer is managed by SW or FW.

Signed-off-by: Oren Sidi <osidi@nvidia.com>
Reviewed-by: Alex Lazar <alazar@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1752734895-257735-3-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index c9a7773ac8ec..e1220aa1e7dc 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -10474,8 +10474,16 @@ struct mlx5_ifc_pifr_reg_bits {
 	u8         port_filter_update_en[8][0x20];
 };
 
+enum {
+	MLX5_BUF_OWNERSHIP_UNKNOWN	= 0x0,
+	MLX5_BUF_OWNERSHIP_FW_OWNED	= 0x1,
+	MLX5_BUF_OWNERSHIP_SW_OWNED	= 0x2,
+};
+
 struct mlx5_ifc_pfcc_reg_bits {
-	u8         reserved_at_0[0x8];
+	u8         reserved_at_0[0x4];
+	u8	   buf_ownership[0x2];
+	u8	   reserved_at_6[0x2];
 	u8         local_port[0x8];
 	u8         reserved_at_10[0xb];
 	u8         ppan_mask_n[0x1];
@@ -10611,7 +10619,9 @@ struct mlx5_ifc_pcam_enhanced_features_bits {
 	u8         fec_200G_per_lane_in_pplm[0x1];
 	u8         reserved_at_1e[0x2a];
 	u8         fec_100G_per_lane_in_pplm[0x1];
-	u8         reserved_at_49[0x1f];
+	u8         reserved_at_49[0xa];
+	u8	   buffer_ownership[0x1];
+	u8	   resereved_at_54[0x14];
 	u8         fec_50G_per_lane_in_pplm[0x1];
 	u8         reserved_at_69[0x4];
 	u8         rx_icrc_encapsulated_counter[0x1];
-- 
cgit v1.2.3


From 9a0048e0ae14cb7babfd459ec920234e8a2ab86e Mon Sep 17 00:00:00 2001
From: Oren Sidi <osidi@nvidia.com>
Date: Thu, 17 Jul 2025 09:48:15 +0300
Subject: net/mlx5: Expose cable_length field in PFCC register

Introduce new "cable_length" field in PFCC register and related fields
to enhance rx buffer configuration management:
1. cable_length: Shifts cable length handling to fw by storing a
   manually entered length from user in PFCC.cable_length
2. lane_rate_oper: In a case where PFCC.cable_length is not supported,
   helps compute a default cable length

Signed-off-by: Oren Sidi <osidi@nvidia.com>
Reviewed-by: Alex Lazar <alazar@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/1752734895-257735-4-git-send-email-tariqt@nvidia.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 19 +++++++++++++++----
 1 file changed, 15 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index e1220aa1e7dc..ed4130e49c27 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -9994,6 +9994,10 @@ struct mlx5_ifc_pude_reg_bits {
 	u8         reserved_at_20[0x60];
 };
 
+enum {
+	MLX5_PTYS_CONNECTOR_TYPE_PORT_DA = 0x7,
+};
+
 struct mlx5_ifc_ptys_reg_bits {
 	u8         reserved_at_0[0x1];
 	u8         an_disable_admin[0x1];
@@ -10030,7 +10034,8 @@ struct mlx5_ifc_ptys_reg_bits {
 	u8         ib_link_width_oper[0x10];
 	u8         ib_proto_oper[0x10];
 
-	u8         reserved_at_160[0x1c];
+	u8         reserved_at_160[0x8];
+	u8         lane_rate_oper[0x14];
 	u8         connector_type[0x4];
 
 	u8         eth_proto_lp_advertise[0x20];
@@ -10485,7 +10490,8 @@ struct mlx5_ifc_pfcc_reg_bits {
 	u8	   buf_ownership[0x2];
 	u8	   reserved_at_6[0x2];
 	u8         local_port[0x8];
-	u8         reserved_at_10[0xb];
+	u8         reserved_at_10[0xa];
+	u8	   cable_length_mask[0x1];
 	u8         ppan_mask_n[0x1];
 	u8         minor_stall_mask[0x1];
 	u8         critical_stall_mask[0x1];
@@ -10514,7 +10520,10 @@ struct mlx5_ifc_pfcc_reg_bits {
 	u8         device_stall_minor_watermark[0x10];
 	u8         device_stall_critical_watermark[0x10];
 
-	u8         reserved_at_a0[0x60];
+	u8	   reserved_at_a0[0x18];
+	u8	   cable_length[0x8];
+
+	u8         reserved_at_c0[0x40];
 };
 
 struct mlx5_ifc_pelc_reg_bits {
@@ -10615,7 +10624,9 @@ struct mlx5_ifc_mtutc_reg_bits {
 struct mlx5_ifc_pcam_enhanced_features_bits {
 	u8         reserved_at_0[0x10];
 	u8         ppcnt_recovery_counters[0x1];
-	u8         reserved_at_11[0xc];
+	u8         reserved_at_11[0x7];
+	u8	   cable_length[0x1];
+	u8	   reserved_at_19[0x4];
 	u8         fec_200G_per_lane_in_pplm[0x1];
 	u8         reserved_at_1e[0x2a];
 	u8         fec_100G_per_lane_in_pplm[0x1];
-- 
cgit v1.2.3


From 7114b74d99a3cd588da4ecb6011858c06f8408a1 Mon Sep 17 00:00:00 2001
From: Florin Leotescu <florin.leotescu@nxp.com>
Date: Tue, 3 Jun 2025 14:31:22 +0300
Subject: hwmon: (emc2305) Add support for PWM frequency, polarity and output

Add three new attributes to the driver data structures to support
configuration of PWM frequency, PWM polarity and PWM output config.

Signed-off-by: Florin Leotescu <florin.leotescu@nxp.com>
Link: https://lore.kernel.org/r/20250603113125.3175103-2-florin.leotescu@oss.nxp.com
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
---
 drivers/hwmon/emc2305.c               | 6 ++++++
 include/linux/platform_data/emc2305.h | 6 ++++++
 2 files changed, 12 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/hwmon/emc2305.c b/drivers/hwmon/emc2305.c
index 234c54956a4b..8fc4fcf8a063 100644
--- a/drivers/hwmon/emc2305.c
+++ b/drivers/hwmon/emc2305.c
@@ -89,8 +89,11 @@ struct emc2305_cdev_data {
  * @hwmon_dev: hwmon device
  * @max_state: maximum cooling state of the cooling device
  * @pwm_num: number of PWM channels
+ * @pwm_output_mask: PWM output mask
+ * @pwm_polarity_mask: PWM polarity mask
  * @pwm_separate: separate PWM settings for every channel
  * @pwm_min: array of minimum PWM per channel
+ * @pwm_freq: array of PWM frequency per channel
  * @cdev_data: array of cooling devices data
  */
 struct emc2305_data {
@@ -98,8 +101,11 @@ struct emc2305_data {
 	struct device *hwmon_dev;
 	u8 max_state;
 	u8 pwm_num;
+	u8 pwm_output_mask;
+	u8 pwm_polarity_mask;
 	bool pwm_separate;
 	u8 pwm_min[EMC2305_PWM_MAX];
+	u16 pwm_freq[EMC2305_PWM_MAX];
 	struct emc2305_cdev_data cdev_data[EMC2305_PWM_MAX];
 };
 
diff --git a/include/linux/platform_data/emc2305.h b/include/linux/platform_data/emc2305.h
index 54d672dd6f7d..76043a97f975 100644
--- a/include/linux/platform_data/emc2305.h
+++ b/include/linux/platform_data/emc2305.h
@@ -9,14 +9,20 @@
  * struct emc2305_platform_data - EMC2305 driver platform data
  * @max_state: maximum cooling state of the cooling device;
  * @pwm_num: number of active channels;
+ * @pwm_output_mask: PWM output mask
+ * @pwm_polarity_mask: PWM polarity mask
  * @pwm_separate: separate PWM settings for every channel;
  * @pwm_min: array of minimum PWM per channel;
+ * @pwm_freq: array of PWM frequency per channel
  */
 struct emc2305_platform_data {
 	u8 max_state;
 	u8 pwm_num;
+	u8 pwm_output_mask;
+	u8 pwm_polarity_mask;
 	bool pwm_separate;
 	u8 pwm_min[EMC2305_PWM_MAX];
+	u16 pwm_freq[EMC2305_PWM_MAX];
 };
 
 #endif
-- 
cgit v1.2.3


From 34b1cb4ec286603127aa8c4191ea527eb8dd3567 Mon Sep 17 00:00:00 2001
From: Venkata Prasad Potturu <venkataprasad.potturu@amd.com>
Date: Tue, 15 Jul 2025 17:40:41 +0530
Subject: soundwire: amd: Add support for acp7.2 platform

Add soundwire support for acp7.2 platform.

Signed-off-by: Venkata Prasad Potturu <venkataprasad.potturu@amd.com>
Link: https://lore.kernel.org/r/20250715121048.1795607-1-venkataprasad.potturu@amd.com
Signed-off-by: Vinod Koul <vkoul@kernel.org>
---
 drivers/soundwire/amd_manager.c   | 4 ++++
 include/linux/soundwire/sdw_amd.h | 1 +
 2 files changed, 5 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/soundwire/amd_manager.c b/drivers/soundwire/amd_manager.c
index d4e62c383b12..3632838f3ed9 100644
--- a/drivers/soundwire/amd_manager.c
+++ b/drivers/soundwire/amd_manager.c
@@ -499,6 +499,7 @@ static int amd_sdw_port_params(struct sdw_bus *bus, struct sdw_port_params *p_pa
 		break;
 	case ACP70_PCI_REV_ID:
 	case ACP71_PCI_REV_ID:
+	case ACP72_PCI_REV_ID:
 		frame_fmt_reg = acp70_sdw_dp_reg[p_params->num].frame_fmt_reg;
 		break;
 	default:
@@ -551,6 +552,7 @@ static int amd_sdw_transport_params(struct sdw_bus *bus,
 		break;
 	case ACP70_PCI_REV_ID:
 	case ACP71_PCI_REV_ID:
+	case ACP72_PCI_REV_ID:
 		frame_fmt_reg = acp70_sdw_dp_reg[params->port_num].frame_fmt_reg;
 		sample_int_reg = acp70_sdw_dp_reg[params->port_num].sample_int_reg;
 		hctrl_dp0_reg = acp70_sdw_dp_reg[params->port_num].hctrl_dp0_reg;
@@ -614,6 +616,7 @@ static int amd_sdw_port_enable(struct sdw_bus *bus,
 		break;
 	case ACP70_PCI_REV_ID:
 	case ACP71_PCI_REV_ID:
+	case ACP72_PCI_REV_ID:
 		lane_ctrl_ch_en_reg = acp70_sdw_dp_reg[enable_ch->port_num].lane_ctrl_ch_en_reg;
 		break;
 	default:
@@ -1038,6 +1041,7 @@ static int amd_sdw_manager_probe(struct platform_device *pdev)
 		break;
 	case ACP70_PCI_REV_ID:
 	case ACP71_PCI_REV_ID:
+	case ACP72_PCI_REV_ID:
 		amd_manager->num_dout_ports = AMD_ACP70_SDW_MAX_TX_PORTS;
 		amd_manager->num_din_ports = AMD_ACP70_SDW_MAX_RX_PORTS;
 		break;
diff --git a/include/linux/soundwire/sdw_amd.h b/include/linux/soundwire/sdw_amd.h
index 6b839987f14c..fe31773d5210 100644
--- a/include/linux/soundwire/sdw_amd.h
+++ b/include/linux/soundwire/sdw_amd.h
@@ -30,6 +30,7 @@
 #define ACP63_PCI_REV_ID		0x63
 #define ACP70_PCI_REV_ID		0x70
 #define ACP71_PCI_REV_ID		0x71
+#define ACP72_PCI_REV_ID		0x72
 
 struct acp_sdw_pdata {
 	u16 instance;
-- 
cgit v1.2.3


From ee4a2e08c10188f02fe3fb36b6beddc3c2fdb287 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Tue, 8 Jul 2025 19:27:41 +1000
Subject: entry: Add arch_in_rcu_eqs()

All architectures have an interruptible RCU extended quiescent state
(EQS) as part of their idle sequences, where interrupts can occur
without RCU watching. Entry code must account for this and wake RCU as
necessary; the common entry code deals with this in irqentry_enter() by
treating any interrupt from an idle thread as potentially having
occurred within an EQS and waking RCU for the duration of the interrupt
via rcu_irq_enter() .. rcu_irq_exit().

Some architectures may have other interruptible EQSs which require
similar treatment. For example, on s390 it is necessary to enable
interrupts around guest entry in the middle of a period where core KVM
code has entered an EQS.

So that architectures can wake RCU in these cases, this patch adds a
new arch_in_rcu_eqs() hook to the common entry code which is checked in
addition to the existing is_idle_thread() check, with RCU woken if
either returns true. A default implementation is provided which always
returns false, which suffices for most architectures.

As no architectures currently implement arch_in_rcu_eqs(), there should
be no functional change as a result of this patch alone. A subsequent
patch will add an s390 implementation to fix a latent bug with missing
RCU wakeups.

[ajd@linux.ibm.com: rebase, fix commit message]

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Christian Borntraeger <borntraeger@linux.ibm.com>
Cc: Heiko Carstens <hca@linux.ibm.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Sven Schnelle <svens@linux.ibm.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Claudio Imbrenda <imbrenda@linux.ibm.com>
Cc: Vasily Gorbik <gor@linux.ibm.com>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Janosch Frank <frankja@linux.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@linux.ibm.com>
Signed-off-by: Andrew Donnellan <ajd@linux.ibm.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Janosch Frank <frankja@linux.ibm.com>
Link: https://lore.kernel.org/r/20250708092742.104309-2-ajd@linux.ibm.com
Signed-off-by: Janosch Frank <frankja@linux.ibm.com>
Message-ID: <20250708092742.104309-2-ajd@linux.ibm.com>
---
 include/linux/entry-common.h | 16 ++++++++++++++++
 kernel/entry/common.c        |  3 ++-
 2 files changed, 18 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index f94f3fdf15fc..3bf99cbad8a3 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -86,6 +86,22 @@ static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs);
 static __always_inline void arch_enter_from_user_mode(struct pt_regs *regs) {}
 #endif
 
+/**
+ * arch_in_rcu_eqs - Architecture specific check for RCU extended quiescent
+ * states.
+ *
+ * Returns: true if the CPU is potentially in an RCU EQS, false otherwise.
+ *
+ * Architectures only need to define this if threads other than the idle thread
+ * may have an interruptible EQS. This does not need to handle idle threads. It
+ * is safe to over-estimate at the cost of redundant RCU management work.
+ *
+ * Invoked from irqentry_enter()
+ */
+#ifndef arch_in_rcu_eqs
+static __always_inline bool arch_in_rcu_eqs(void) { return false; }
+#endif
+
 /**
  * enter_from_user_mode - Establish state when coming from user mode
  *
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index a8dd1f27417c..eb52d38e8099 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -220,7 +220,8 @@ noinstr irqentry_state_t irqentry_enter(struct pt_regs *regs)
 	 * TINY_RCU does not support EQS, so let the compiler eliminate
 	 * this part when enabled.
 	 */
-	if (!IS_ENABLED(CONFIG_TINY_RCU) && is_idle_task(current)) {
+	if (!IS_ENABLED(CONFIG_TINY_RCU) &&
+	    (is_idle_task(current) || arch_in_rcu_eqs())) {
 		/*
 		 * If RCU is not watching then the same careful
 		 * sequence vs. lockdep and tracing is required
-- 
cgit v1.2.3


From fcb476990beb55c958db0b5aa2e9ca772d0fc982 Mon Sep 17 00:00:00 2001
From: Xu Yang <xu.yang_2@nxp.com>
Date: Mon, 21 Jul 2025 18:44:17 +0800
Subject: usb: core: add urb->sgt parameter description

The parameter description of urb->sgt is lost, this will add it for
completeness.

Reported-by: Stephen Rothwell <sfr@canb.auug.org.au>
Closes: https://lore.kernel.org/all/20250711182803.1d548467@canb.auug.org.au/
Signed-off-by: Xu Yang <xu.yang_2@nxp.com>
Fixes: 488e6eaab88c ("usb: core: add dma-noncoherent buffer alloc and free API")
Link: https://lore.kernel.org/r/20250721104417.3442530-1-xu.yang_2@nxp.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
---
 include/linux/usb.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/usb.h b/include/linux/usb.h
index 535ac37198a1..9d662c6abb4d 100644
--- a/include/linux/usb.h
+++ b/include/linux/usb.h
@@ -1455,6 +1455,10 @@ typedef void (*usb_complete_t)(struct urb *);
  * @sg: scatter gather buffer list, the buffer size of each element in
  * 	the list (except the last) must be divisible by the endpoint's
  * 	max packet size if no_sg_constraint isn't set in 'struct usb_bus'
+ * @sgt: used to hold a scatter gather table returned by usb_alloc_noncoherent(),
+ *      which describes the allocated non-coherent and possibly non-contiguous
+ *      memory and is guaranteed to have 1 single DMA mapped segment. The
+ *      allocated memory needs to be freed by usb_free_noncoherent().
  * @num_mapped_sgs: (internal) number of mapped sg entries
  * @num_sgs: number of entries in the sg list
  * @transfer_buffer_length: How big is transfer_buffer.  The transfer may
-- 
cgit v1.2.3


From ab16122115327b2a602595f539cae7e39a331d0e Mon Sep 17 00:00:00 2001
From: Jack Thomson <jackabt@amazon.com>
Date: Mon, 21 Jul 2025 14:05:58 +0100
Subject: arm64: kvm, smccc: Fix vendor uuid

Commit 13423063c7cb ("arm64: kvm, smccc: Introduce and use API for
getting hypervisor UUID") replaced the explicit register constants
with the UUID_INIT macro. However, there is an endian issue, meaning
the UUID generated and used in the handshake didn't match UUID prior to
the commit.

The change in UUID causes the SMCCC vendor handshake to fail with older
guest kernels, meaning devices such as PTP were not available in the
guest.

This patch updates the parameters to the macro to generate a UUID which
matches the previous value, and re-establish backwards compatibility
with older guest kernels.

Fixes: 13423063c7cb ("arm64: kvm, smccc: Introduce and use API for getting hypervisor UUID")
Signed-off-by: Jack Thomson <jackabt@amazon.com>
Reviewed-by: Marc Zyngier <maz@kernel.org>
Tested-by: Marc Zyngier <maz@kernel.org>
Reviewed-by: Sudeep Holla <sudeep.holla@arm.com>
Link: https://lore.kernel.org/r/20250721130558.50823-1-jackabt.amazon@gmail.com
Signed-off-by: Will Deacon <will@kernel.org>
---
 include/linux/arm-smccc.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/arm-smccc.h b/include/linux/arm-smccc.h
index 784ebe4607a4..50b47eba7d01 100644
--- a/include/linux/arm-smccc.h
+++ b/include/linux/arm-smccc.h
@@ -113,7 +113,7 @@
 
 /* KVM UID value: 28b46fb6-2ec5-11e9-a9ca-4b564d003a74 */
 #define ARM_SMCCC_VENDOR_HYP_UID_KVM UUID_INIT(\
-	0xb66fb428, 0xc52e, 0xe911, \
+	0x28b46fb6, 0x2ec5, 0x11e9, \
 	0xa9, 0xca, 0x4b, 0x56, \
 	0x4d, 0x00, 0x3a, 0x74)
 
-- 
cgit v1.2.3


From 61c3e8940f2d8b5bfeaeec4bedc2f3e7d873abb3 Mon Sep 17 00:00:00 2001
From: Oliver Neukum <oneukum@suse.com>
Date: Thu, 17 Jul 2025 14:06:17 +0200
Subject: net: usb: cdc-ncm: check for filtering capability

If the decice does not support filtering, filtering
must not be used and all packets delivered for the
upper layers to sort.

Signed-off-by: Oliver Neukum <oneukum@suse.com>
Link: https://patch.msgid.link/20250717120649.2090929-1-oneukum@suse.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/cdc_ncm.c   | 20 ++++++++++++++++----
 include/linux/usb/cdc_ncm.h |  1 +
 2 files changed, 17 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c
index 34e82f1e37d9..ea0e5e276cd6 100644
--- a/drivers/net/usb/cdc_ncm.c
+++ b/drivers/net/usb/cdc_ncm.c
@@ -892,6 +892,10 @@ int cdc_ncm_bind_common(struct usbnet *dev, struct usb_interface *intf, u8 data_
 		}
 	}
 
+	if (ctx->func_desc)
+		ctx->filtering_supported = !!(ctx->func_desc->bmNetworkCapabilities
+			& USB_CDC_NCM_NCAP_ETH_FILTER);
+
 	iface_no = ctx->data->cur_altsetting->desc.bInterfaceNumber;
 
 	/* Device-specific flags */
@@ -1898,6 +1902,14 @@ static void cdc_ncm_status(struct usbnet *dev, struct urb *urb)
 	}
 }
 
+static void cdc_ncm_update_filter(struct usbnet *dev)
+{
+	struct cdc_ncm_ctx *ctx = (struct cdc_ncm_ctx *)dev->data[0];
+
+	if (ctx->filtering_supported)
+		usbnet_cdc_update_filter(dev);
+}
+
 static const struct driver_info cdc_ncm_info = {
 	.description = "CDC NCM (NO ZLP)",
 	.flags = FLAG_POINTTOPOINT | FLAG_NO_SETINT | FLAG_MULTI_PACKET
@@ -1908,7 +1920,7 @@ static const struct driver_info cdc_ncm_info = {
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
-	.set_rx_mode = usbnet_cdc_update_filter,
+	.set_rx_mode = cdc_ncm_update_filter,
 };
 
 /* Same as cdc_ncm_info, but with FLAG_SEND_ZLP  */
@@ -1922,7 +1934,7 @@ static const struct driver_info cdc_ncm_zlp_info = {
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
-	.set_rx_mode = usbnet_cdc_update_filter,
+	.set_rx_mode = cdc_ncm_update_filter,
 };
 
 /* Same as cdc_ncm_info, but with FLAG_SEND_ZLP */
@@ -1964,7 +1976,7 @@ static const struct driver_info wwan_info = {
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
-	.set_rx_mode = usbnet_cdc_update_filter,
+	.set_rx_mode = cdc_ncm_update_filter,
 };
 
 /* Same as wwan_info, but with FLAG_NOARP  */
@@ -1978,7 +1990,7 @@ static const struct driver_info wwan_noarp_info = {
 	.status = cdc_ncm_status,
 	.rx_fixup = cdc_ncm_rx_fixup,
 	.tx_fixup = cdc_ncm_tx_fixup,
-	.set_rx_mode = usbnet_cdc_update_filter,
+	.set_rx_mode = cdc_ncm_update_filter,
 };
 
 static const struct usb_device_id cdc_devs[] = {
diff --git a/include/linux/usb/cdc_ncm.h b/include/linux/usb/cdc_ncm.h
index 2d207cb4837d..4ac082a63173 100644
--- a/include/linux/usb/cdc_ncm.h
+++ b/include/linux/usb/cdc_ncm.h
@@ -119,6 +119,7 @@ struct cdc_ncm_ctx {
 	u32 timer_interval;
 	u32 max_ndp_size;
 	u8 is_ndp16;
+	u8 filtering_supported;
 	union {
 		struct usb_cdc_ncm_ndp16 *delayed_ndp16;
 		struct usb_cdc_ncm_ndp32 *delayed_ndp32;
-- 
cgit v1.2.3


From 51a62199a8aaac0d1645b1dd8e670a6f35aead81 Mon Sep 17 00:00:00 2001
From: Geliang Tang <tanggeliang@kylinos.cn>
Date: Sat, 19 Jul 2025 00:06:57 +0200
Subject: tcp: add tcp_sock_set_maxseg

Add a helper tcp_sock_set_maxseg() to directly set the TCP_MAXSEG
sockopt from kernel space.

This new helper will be used in the following patch from MPTCP.

Signed-off-by: Geliang Tang <tanggeliang@kylinos.cn>
Acked-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20250719-net-next-mptcp-tcp_maxseg-v2-2-8c910fbc5307@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/tcp.h |  1 +
 net/ipv4/tcp.c      | 23 ++++++++++++++---------
 2 files changed, 15 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 1a5737b3753d..57e478bfaef2 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -621,6 +621,7 @@ void tcp_sock_set_nodelay(struct sock *sk);
 void tcp_sock_set_quickack(struct sock *sk, int val);
 int tcp_sock_set_syncnt(struct sock *sk, int val);
 int tcp_sock_set_user_timeout(struct sock *sk, int val);
+int tcp_sock_set_maxseg(struct sock *sk, int val);
 
 static inline bool dst_tcp_usec_ts(const struct dst_entry *dst)
 {
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 31149a0ac849..71a956fbfc55 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -3751,6 +3751,19 @@ int tcp_set_window_clamp(struct sock *sk, int val)
 	return 0;
 }
 
+int tcp_sock_set_maxseg(struct sock *sk, int val)
+{
+	/* Values greater than interface MTU won't take effect. However
+	 * at the point when this call is done we typically don't yet
+	 * know which interface is going to be used
+	 */
+	if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW))
+		return -EINVAL;
+
+	tcp_sk(sk)->rx_opt.user_mss = val;
+	return 0;
+}
+
 /*
  *	Socket option code for TCP.
  */
@@ -3883,15 +3896,7 @@ int do_tcp_setsockopt(struct sock *sk, int level, int optname,
 
 	switch (optname) {
 	case TCP_MAXSEG:
-		/* Values greater than interface MTU won't take effect. However
-		 * at the point when this call is done we typically don't yet
-		 * know which interface is going to be used
-		 */
-		if (val && (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW)) {
-			err = -EINVAL;
-			break;
-		}
-		tp->rx_opt.user_mss = val;
+		err = tcp_sock_set_maxseg(sk, val);
 		break;
 
 	case TCP_NODELAY:
-- 
cgit v1.2.3


From 57fbad15c2eee77276a541c616589b32976d2b8e Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Thu, 17 Jul 2025 16:25:06 -0700
Subject: stackleak: Rename STACKLEAK to KSTACK_ERASE

In preparation for adding Clang sanitizer coverage stack depth tracking
that can support stack depth callbacks:

- Add the new top-level CONFIG_KSTACK_ERASE option which will be
  implemented either with the stackleak GCC plugin, or with the Clang
  stack depth callback support.
- Rename CONFIG_GCC_PLUGIN_STACKLEAK as needed to CONFIG_KSTACK_ERASE,
  but keep it for anything specific to the GCC plugin itself.
- Rename all exposed "STACKLEAK" names and files to "KSTACK_ERASE" (named
  for what it does rather than what it protects against), but leave as
  many of the internals alone as possible to avoid even more churn.

While here, also split "prev_lowest_stack" into CONFIG_KSTACK_ERASE_METRICS,
since that's the only place it is referenced from.

Suggested-by: Ingo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20250717232519.2984886-1-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 Documentation/admin-guide/sysctl/kernel.rst        |   4 +-
 Documentation/arch/x86/x86_64/mm.rst               |   2 +-
 Documentation/security/self-protection.rst         |   2 +-
 .../zh_CN/security/self-protection.rst             |   2 +-
 MAINTAINERS                                        |   4 +-
 arch/Kconfig                                       |   4 +-
 arch/arm/Kconfig                                   |   2 +-
 arch/arm/boot/compressed/Makefile                  |   2 +-
 arch/arm/kernel/entry-common.S                     |   2 +-
 arch/arm64/Kconfig                                 |   2 +-
 arch/arm64/kernel/entry.S                          |   2 +-
 arch/arm64/kernel/pi/Makefile                      |   2 +-
 arch/arm64/kvm/hyp/nvhe/Makefile                   |   2 +-
 arch/loongarch/Kconfig                             |   2 +-
 arch/riscv/Kconfig                                 |   2 +-
 arch/riscv/kernel/entry.S                          |   2 +-
 arch/riscv/kernel/pi/Makefile                      |   2 +-
 arch/riscv/purgatory/Makefile                      |   2 +-
 arch/s390/Kconfig                                  |   2 +-
 arch/s390/kernel/entry.S                           |   2 +-
 arch/x86/Kconfig                                   |   2 +-
 arch/x86/entry/calling.h                           |   4 +-
 arch/x86/purgatory/Makefile                        |   2 +-
 drivers/firmware/efi/libstub/Makefile              |   8 +-
 drivers/misc/lkdtm/Makefile                        |   2 +-
 drivers/misc/lkdtm/kstack_erase.c                  | 150 +++++++++++++++++
 drivers/misc/lkdtm/stackleak.c                     | 150 -----------------
 fs/proc/base.c                                     |   6 +-
 include/linux/kstack_erase.h                       |  89 +++++++++++
 include/linux/sched.h                              |   4 +-
 include/linux/stackleak.h                          |  89 -----------
 kernel/Makefile                                    |  10 +-
 kernel/fork.c                                      |   2 +-
 kernel/kstack_erase.c                              | 177 +++++++++++++++++++++
 kernel/stackleak.c                                 | 177 ---------------------
 lib/Makefile                                       |   2 +-
 scripts/Makefile.gcc-plugins                       |   6 +-
 security/Kconfig.hardening                         |  36 +++--
 tools/objtool/check.c                              |   2 +-
 tools/testing/selftests/lkdtm/config               |   2 +-
 40 files changed, 486 insertions(+), 480 deletions(-)
 create mode 100644 drivers/misc/lkdtm/kstack_erase.c
 delete mode 100644 drivers/misc/lkdtm/stackleak.c
 create mode 100644 include/linux/kstack_erase.h
 delete mode 100644 include/linux/stackleak.h
 create mode 100644 kernel/kstack_erase.c
 delete mode 100644 kernel/stackleak.c

(limited to 'include/linux')

diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
index dd49a89a62d3..19224eeac1c2 100644
--- a/Documentation/admin-guide/sysctl/kernel.rst
+++ b/Documentation/admin-guide/sysctl/kernel.rst
@@ -1465,7 +1465,7 @@ stack_erasing
 =============
 
 This parameter can be used to control kernel stack erasing at the end
-of syscalls for kernels built with ``CONFIG_GCC_PLUGIN_STACKLEAK``.
+of syscalls for kernels built with ``CONFIG_KSTACK_ERASE``.
 
 That erasing reduces the information which kernel stack leak bugs
 can reveal and blocks some uninitialized stack variable attacks.
@@ -1473,7 +1473,7 @@ The tradeoff is the performance impact: on a single CPU system kernel
 compilation sees a 1% slowdown, other systems and workloads may vary.
 
 = ====================================================================
-0 Kernel stack erasing is disabled, STACKLEAK_METRICS are not updated.
+0 Kernel stack erasing is disabled, KSTACK_ERASE_METRICS are not updated.
 1 Kernel stack erasing is enabled (default), it is performed before
   returning to the userspace at the end of syscalls.
 = ====================================================================
diff --git a/Documentation/arch/x86/x86_64/mm.rst b/Documentation/arch/x86/x86_64/mm.rst
index f2db178b353f..a6cf05d51bd8 100644
--- a/Documentation/arch/x86/x86_64/mm.rst
+++ b/Documentation/arch/x86/x86_64/mm.rst
@@ -176,5 +176,5 @@ Be very careful vs. KASLR when changing anything here. The KASLR address
 range must not overlap with anything except the KASAN shadow area, which is
 correct as KASAN disables KASLR.
 
-For both 4- and 5-level layouts, the STACKLEAK_POISON value in the last 2MB
+For both 4- and 5-level layouts, the KSTACK_ERASE_POISON value in the last 2MB
 hole: ffffffffffff4111
diff --git a/Documentation/security/self-protection.rst b/Documentation/security/self-protection.rst
index 910668e665cb..a32ca23c21b0 100644
--- a/Documentation/security/self-protection.rst
+++ b/Documentation/security/self-protection.rst
@@ -303,7 +303,7 @@ Memory poisoning
 
 When releasing memory, it is best to poison the contents, to avoid reuse
 attacks that rely on the old contents of memory. E.g., clear stack on a
-syscall return (``CONFIG_GCC_PLUGIN_STACKLEAK``), wipe heap memory on a
+syscall return (``CONFIG_KSTACK_ERASE``), wipe heap memory on a
 free. This frustrates many uninitialized variable attacks, stack content
 exposures, heap content exposures, and use-after-free attacks.
 
diff --git a/Documentation/translations/zh_CN/security/self-protection.rst b/Documentation/translations/zh_CN/security/self-protection.rst
index 3c8a68b1e1be..93de9cee5c1a 100644
--- a/Documentation/translations/zh_CN/security/self-protection.rst
+++ b/Documentation/translations/zh_CN/security/self-protection.rst
@@ -259,7 +259,7 @@ KALLSYSM，则会直接打印原始地址。
 --------
 
 在释放内存时，最好对内存内容进行清除处理，以防止攻击者重用内存中以前
-的内容。例如，在系统调用返回时清除堆栈（CONFIG_GCC_PLUGIN_STACKLEAK）,
+的内容。例如，在系统调用返回时清除堆栈（CONFIG_KSTACK_ERASE）,
 在释放堆内容是清除其内容。这有助于防止许多未初始化变量攻击、堆栈内容
 泄露、堆内容泄露以及使用后释放攻击（user-after-free）。
 
diff --git a/MAINTAINERS b/MAINTAINERS
index 0c1d245bf7b8..470d159d8fea 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -9992,8 +9992,6 @@ L:	linux-hardening@vger.kernel.org
 S:	Maintained
 T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/hardening
 F:	Documentation/kbuild/gcc-plugins.rst
-F:	include/linux/stackleak.h
-F:	kernel/stackleak.c
 F:	scripts/Makefile.gcc-plugins
 F:	scripts/gcc-plugins/
 
@@ -13087,10 +13085,12 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/kees/linux.git for-next/har
 F:	Documentation/ABI/testing/sysfs-kernel-oops_count
 F:	Documentation/ABI/testing/sysfs-kernel-warn_count
 F:	arch/*/configs/hardening.config
+F:	include/linux/kstack_erase.h
 F:	include/linux/overflow.h
 F:	include/linux/randomize_kstack.h
 F:	include/linux/ucopysize.h
 F:	kernel/configs/hardening.config
+F:	kernel/kstack_erase.c
 F:	lib/tests/randstruct_kunit.c
 F:	lib/tests/usercopy_kunit.c
 F:	mm/usercopy.c
diff --git a/arch/Kconfig b/arch/Kconfig
index a3308a220f86..4d1908f6f084 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -630,11 +630,11 @@ config SECCOMP_CACHE_DEBUG
 
 	  If unsure, say N.
 
-config HAVE_ARCH_STACKLEAK
+config HAVE_ARCH_KSTACK_ERASE
 	bool
 	help
 	  An architecture should select this if it has the code which
-	  fills the used part of the kernel stack with the STACKLEAK_POISON
+	  fills the used part of the kernel stack with the KSTACK_ERASE_POISON
 	  value before returning from system calls.
 
 config HAVE_STACKPROTECTOR
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3072731fe09c..cb0b2e2211ca 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -87,11 +87,11 @@ config ARM
 	select HAVE_ARCH_KGDB if !CPU_ENDIAN_BE32 && MMU
 	select HAVE_ARCH_KASAN if MMU && !XIP_KERNEL
 	select HAVE_ARCH_KASAN_VMALLOC if HAVE_ARCH_KASAN
+	select HAVE_ARCH_KSTACK_ERASE
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_PFN_VALID
 	select HAVE_ARCH_SECCOMP
 	select HAVE_ARCH_SECCOMP_FILTER if AEABI && !OABI_COMPAT
-	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if ARM_LPAE
diff --git a/arch/arm/boot/compressed/Makefile b/arch/arm/boot/compressed/Makefile
index d61369b1eabe..f9075edfd773 100644
--- a/arch/arm/boot/compressed/Makefile
+++ b/arch/arm/boot/compressed/Makefile
@@ -9,7 +9,7 @@ OBJS		=
 
 HEAD	= head.o
 OBJS	+= misc.o decompress.o
-CFLAGS_decompress.o += $(DISABLE_STACKLEAK_PLUGIN)
+CFLAGS_decompress.o += $(DISABLE_KSTACK_ERASE)
 ifeq ($(CONFIG_DEBUG_UNCOMPRESS),y)
 OBJS	+= debug.o
 AFLAGS_head.o += -DDEBUG
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index f379c852dcb7..88336a1292bb 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -119,7 +119,7 @@ no_work_pending:
 
 	ct_user_enter save = 0
 
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	bl	stackleak_erase_on_task_stack
 #endif
 	restore_user_regs fast = 0, offset = 0
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 55fc331af337..e2a9e013b6a9 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -187,12 +187,12 @@ config ARM64
 	select HAVE_ARCH_KCSAN if EXPERT
 	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_KSTACK_ERASE
 	select HAVE_ARCH_MMAP_RND_BITS
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_PREL32_RELOCATIONS
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
-	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S
index 5ae2a34b50bd..67331437b2aa 100644
--- a/arch/arm64/kernel/entry.S
+++ b/arch/arm64/kernel/entry.S
@@ -614,7 +614,7 @@ SYM_CODE_END(ret_to_kernel)
 SYM_CODE_START_LOCAL(ret_to_user)
 	ldr	x19, [tsk, #TSK_TI_FLAGS]	// re-check for single-step
 	enable_step_tsk x19, x2
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	bl	stackleak_erase_on_task_stack
 #endif
 	kernel_exit 0
diff --git a/arch/arm64/kernel/pi/Makefile b/arch/arm64/kernel/pi/Makefile
index 4d11a8c29181..f440bf57b1a5 100644
--- a/arch/arm64/kernel/pi/Makefile
+++ b/arch/arm64/kernel/pi/Makefile
@@ -2,7 +2,7 @@
 # Copyright 2022 Google LLC
 
 KBUILD_CFLAGS	:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \
-		   -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_STACKLEAK_PLUGIN) \
+		   -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_KSTACK_ERASE) \
 		   $(DISABLE_LATENT_ENTROPY_PLUGIN) \
 		   $(call cc-option,-mbranch-protection=none) \
 		   -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \
diff --git a/arch/arm64/kvm/hyp/nvhe/Makefile b/arch/arm64/kvm/hyp/nvhe/Makefile
index a76522d63c3e..0b0a68b663d4 100644
--- a/arch/arm64/kvm/hyp/nvhe/Makefile
+++ b/arch/arm64/kvm/hyp/nvhe/Makefile
@@ -12,7 +12,7 @@ asflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS
 ccflags-y := -D__KVM_NVHE_HYPERVISOR__ -D__DISABLE_EXPORTS -D__DISABLE_TRACE_MMIO__
 ccflags-y += -fno-stack-protector	\
 	     -DDISABLE_BRANCH_PROFILING	\
-	     $(DISABLE_STACKLEAK_PLUGIN)
+	     $(DISABLE_KSTACK_ERASE)
 
 hostprogs := gen-hyprel
 HOST_EXTRACFLAGS += -I$(objtree)/include
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 4b19f93379a1..1514789bea4a 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -120,11 +120,11 @@ config LOONGARCH
 	select HAVE_ARCH_KASAN
 	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KGDB if PERF_EVENTS
+	select HAVE_ARCH_KSTACK_ERASE
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP
 	select HAVE_ARCH_SECCOMP_FILTER
-	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_USERFAULTFD_MINOR if USERFAULTFD
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 36061f4732b7..cfc084fc9e6f 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -135,13 +135,13 @@ config RISCV
 	select HAVE_ARCH_KASAN if MMU && 64BIT
 	select HAVE_ARCH_KASAN_VMALLOC if MMU && 64BIT
 	select HAVE_ARCH_KFENCE if MMU && 64BIT
+	select HAVE_ARCH_KSTACK_ERASE
 	select HAVE_ARCH_KGDB if !XIP_KERNEL
 	select HAVE_ARCH_KGDB_QXFER_PKT
 	select HAVE_ARCH_MMAP_RND_BITS if MMU
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS if COMPAT
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
-	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE if 64BIT && MMU
diff --git a/arch/riscv/kernel/entry.S b/arch/riscv/kernel/entry.S
index 75656afa2d6b..3a0ec6fd5956 100644
--- a/arch/riscv/kernel/entry.S
+++ b/arch/riscv/kernel/entry.S
@@ -220,7 +220,7 @@ SYM_CODE_START_NOALIGN(ret_from_exception)
 #endif
 	bnez s0, 1f
 
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	call	stackleak_erase_on_task_stack
 #endif
 
diff --git a/arch/riscv/kernel/pi/Makefile b/arch/riscv/kernel/pi/Makefile
index 81d69d45c06c..7dd15be69c90 100644
--- a/arch/riscv/kernel/pi/Makefile
+++ b/arch/riscv/kernel/pi/Makefile
@@ -2,7 +2,7 @@
 # This file was copied from arm64/kernel/pi/Makefile.
 
 KBUILD_CFLAGS	:= $(subst $(CC_FLAGS_FTRACE),,$(KBUILD_CFLAGS)) -fpie \
-		   -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_STACKLEAK_PLUGIN) \
+		   -Os -DDISABLE_BRANCH_PROFILING $(DISABLE_KSTACK_ERASE) \
 		   $(call cc-option,-mbranch-protection=none) \
 		   -I$(srctree)/scripts/dtc/libfdt -fno-stack-protector \
 		   -include $(srctree)/include/linux/hidden.h \
diff --git a/arch/riscv/purgatory/Makefile b/arch/riscv/purgatory/Makefile
index fb9c917c9b45..240592e3f5c2 100644
--- a/arch/riscv/purgatory/Makefile
+++ b/arch/riscv/purgatory/Makefile
@@ -53,7 +53,7 @@ targets += purgatory.ro purgatory.chk
 
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
 PURGATORY_CFLAGS := -mcmodel=medany -ffreestanding -fno-zero-initialized-in-bss
-PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
+PURGATORY_CFLAGS += $(DISABLE_KSTACK_ERASE) -DDISABLE_BRANCH_PROFILING
 PURGATORY_CFLAGS += -fno-stack-protector -g0
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 0c16dc443e2f..a8e74ed8e3cc 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -176,10 +176,10 @@ config S390
 	select HAVE_ARCH_KCSAN
 	select HAVE_ARCH_KMSAN
 	select HAVE_ARCH_KFENCE
+	select HAVE_ARCH_KSTACK_ERASE
 	select HAVE_ARCH_RANDOMIZE_KSTACK_OFFSET
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_SOFT_DIRTY
-	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_VMAP_STACK
diff --git a/arch/s390/kernel/entry.S b/arch/s390/kernel/entry.S
index 0f00f4b06d51..75b0fbb236d0 100644
--- a/arch/s390/kernel/entry.S
+++ b/arch/s390/kernel/entry.S
@@ -124,7 +124,7 @@ _LPP_OFFSET	= __LC_LPP
 #endif
 
 	.macro STACKLEAK_ERASE
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	brasl	%r14,stackleak_erase_on_task_stack
 #endif
 	.endm
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 340e5468980e..bc3708cad46b 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -204,13 +204,13 @@ config X86
 	select HAVE_ARCH_KFENCE
 	select HAVE_ARCH_KMSAN			if X86_64
 	select HAVE_ARCH_KGDB
+	select HAVE_ARCH_KSTACK_ERASE
 	select HAVE_ARCH_MMAP_RND_BITS		if MMU
 	select HAVE_ARCH_MMAP_RND_COMPAT_BITS	if MMU && COMPAT
 	select HAVE_ARCH_COMPAT_MMAP_BASES	if MMU && COMPAT
 	select HAVE_ARCH_PREL32_RELOCATIONS
 	select HAVE_ARCH_SECCOMP_FILTER
 	select HAVE_ARCH_THREAD_STRUCT_WHITELIST
-	select HAVE_ARCH_STACKLEAK
 	select HAVE_ARCH_TRACEHOOK
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD if X86_64
diff --git a/arch/x86/entry/calling.h b/arch/x86/entry/calling.h
index d83236b96f22..94519688b007 100644
--- a/arch/x86/entry/calling.h
+++ b/arch/x86/entry/calling.h
@@ -369,7 +369,7 @@ For 32-bit we have the following conventions - kernel is built with
 .endm
 
 .macro STACKLEAK_ERASE_NOCLOBBER
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	PUSH_AND_CLEAR_REGS
 	call stackleak_erase
 	POP_REGS
@@ -388,7 +388,7 @@ For 32-bit we have the following conventions - kernel is built with
 #endif /* !CONFIG_X86_64 */
 
 .macro STACKLEAK_ERASE
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	call stackleak_erase
 #endif
 .endm
diff --git a/arch/x86/purgatory/Makefile b/arch/x86/purgatory/Makefile
index ebdfd7b84feb..e0a607a14e7e 100644
--- a/arch/x86/purgatory/Makefile
+++ b/arch/x86/purgatory/Makefile
@@ -35,7 +35,7 @@ targets += purgatory.ro purgatory.chk
 PURGATORY_CFLAGS_REMOVE := -mcmodel=kernel
 PURGATORY_CFLAGS := -mcmodel=small -ffreestanding -fno-zero-initialized-in-bss -g0
 PURGATORY_CFLAGS += -fpic -fvisibility=hidden
-PURGATORY_CFLAGS += $(DISABLE_STACKLEAK_PLUGIN) -DDISABLE_BRANCH_PROFILING
+PURGATORY_CFLAGS += $(DISABLE_KSTACK_ERASE) -DDISABLE_BRANCH_PROFILING
 PURGATORY_CFLAGS += -fno-stack-protector
 
 # Default KBUILD_CFLAGS can have -pg option set when FTRACE is enabled. That
diff --git a/drivers/firmware/efi/libstub/Makefile b/drivers/firmware/efi/libstub/Makefile
index 939a4955e00b..94b05e4451dd 100644
--- a/drivers/firmware/efi/libstub/Makefile
+++ b/drivers/firmware/efi/libstub/Makefile
@@ -22,16 +22,16 @@ cflags-$(CONFIG_X86)		+= -m$(BITS) -D__KERNEL__ -std=gnu11 \
 
 # arm64 uses the full KBUILD_CFLAGS so it's necessary to explicitly
 # disable the stackleak plugin
-cflags-$(CONFIG_ARM64)		+= -fpie $(DISABLE_STACKLEAK_PLUGIN) \
+cflags-$(CONFIG_ARM64)		+= -fpie $(DISABLE_KSTACK_ERASE) \
 				   -fno-unwind-tables -fno-asynchronous-unwind-tables
 cflags-$(CONFIG_ARM)		+= -DEFI_HAVE_STRLEN -DEFI_HAVE_STRNLEN \
 				   -DEFI_HAVE_MEMCHR -DEFI_HAVE_STRRCHR \
 				   -DEFI_HAVE_STRCMP -fno-builtin -fpic \
 				   $(call cc-option,-mno-single-pic-base) \
-				   $(DISABLE_STACKLEAK_PLUGIN)
+				   $(DISABLE_KSTACK_ERASE)
 cflags-$(CONFIG_RISCV)		+= -fpic -DNO_ALTERNATIVE -mno-relax \
-				   $(DISABLE_STACKLEAK_PLUGIN)
-cflags-$(CONFIG_LOONGARCH)	+= -fpie $(DISABLE_STACKLEAK_PLUGIN)
+				   $(DISABLE_KSTACK_ERASE)
+cflags-$(CONFIG_LOONGARCH)	+= -fpie $(DISABLE_KSTACK_ERASE)
 
 cflags-$(CONFIG_EFI_PARAMS_FROM_FDT)	+= -I$(srctree)/scripts/dtc/libfdt
 
diff --git a/drivers/misc/lkdtm/Makefile b/drivers/misc/lkdtm/Makefile
index 39468bd27b85..03ebe33185f9 100644
--- a/drivers/misc/lkdtm/Makefile
+++ b/drivers/misc/lkdtm/Makefile
@@ -8,7 +8,7 @@ lkdtm-$(CONFIG_LKDTM)		+= perms.o
 lkdtm-$(CONFIG_LKDTM)		+= refcount.o
 lkdtm-$(CONFIG_LKDTM)		+= rodata_objcopy.o
 lkdtm-$(CONFIG_LKDTM)		+= usercopy.o
-lkdtm-$(CONFIG_LKDTM)		+= stackleak.o
+lkdtm-$(CONFIG_LKDTM)		+= kstack_erase.o
 lkdtm-$(CONFIG_LKDTM)		+= cfi.o
 lkdtm-$(CONFIG_LKDTM)		+= fortify.o
 lkdtm-$(CONFIG_PPC_64S_HASH_MMU)	+= powerpc.o
diff --git a/drivers/misc/lkdtm/kstack_erase.c b/drivers/misc/lkdtm/kstack_erase.c
new file mode 100644
index 000000000000..4fd9b0bfb874
--- /dev/null
+++ b/drivers/misc/lkdtm/kstack_erase.c
@@ -0,0 +1,150 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This code tests that the current task stack is properly erased (filled
+ * with KSTACK_ERASE_POISON).
+ *
+ * Authors:
+ *   Alexander Popov <alex.popov@linux.com>
+ *   Tycho Andersen <tycho@tycho.ws>
+ */
+
+#include "lkdtm.h"
+#include <linux/kstack_erase.h>
+
+#if defined(CONFIG_KSTACK_ERASE)
+/*
+ * Check that stackleak tracks the lowest stack pointer and erases the stack
+ * below this as expected.
+ *
+ * To prevent the lowest stack pointer changing during the test, IRQs are
+ * masked and instrumentation of this function is disabled. We assume that the
+ * compiler will create a fixed-size stack frame for this function.
+ *
+ * Any non-inlined function may make further use of the stack, altering the
+ * lowest stack pointer and/or clobbering poison values. To avoid spurious
+ * failures we must avoid printing until the end of the test or have already
+ * encountered a failure condition.
+ */
+static void noinstr check_stackleak_irqoff(void)
+{
+	const unsigned long task_stack_base = (unsigned long)task_stack_page(current);
+	const unsigned long task_stack_low = stackleak_task_low_bound(current);
+	const unsigned long task_stack_high = stackleak_task_high_bound(current);
+	const unsigned long current_sp = current_stack_pointer;
+	const unsigned long lowest_sp = current->lowest_stack;
+	unsigned long untracked_high;
+	unsigned long poison_high, poison_low;
+	bool test_failed = false;
+
+	/*
+	 * Check that the current and lowest recorded stack pointer values fall
+	 * within the expected task stack boundaries. These tests should never
+	 * fail unless the boundaries are incorrect or we're clobbering the
+	 * STACK_END_MAGIC, and in either casee something is seriously wrong.
+	 */
+	if (current_sp < task_stack_low || current_sp >= task_stack_high) {
+		instrumentation_begin();
+		pr_err("FAIL: current_stack_pointer (0x%lx) outside of task stack bounds [0x%lx..0x%lx]\n",
+		       current_sp, task_stack_low, task_stack_high - 1);
+		test_failed = true;
+		goto out;
+	}
+	if (lowest_sp < task_stack_low || lowest_sp >= task_stack_high) {
+		instrumentation_begin();
+		pr_err("FAIL: current->lowest_stack (0x%lx) outside of task stack bounds [0x%lx..0x%lx]\n",
+		       lowest_sp, task_stack_low, task_stack_high - 1);
+		test_failed = true;
+		goto out;
+	}
+
+	/*
+	 * Depending on what has run prior to this test, the lowest recorded
+	 * stack pointer could be above or below the current stack pointer.
+	 * Start from the lowest of the two.
+	 *
+	 * Poison values are naturally-aligned unsigned longs. As the current
+	 * stack pointer might not be sufficiently aligned, we must align
+	 * downwards to find the lowest known stack pointer value. This is the
+	 * high boundary for a portion of the stack which may have been used
+	 * without being tracked, and has to be scanned for poison.
+	 */
+	untracked_high = min(current_sp, lowest_sp);
+	untracked_high = ALIGN_DOWN(untracked_high, sizeof(unsigned long));
+
+	/*
+	 * Find the top of the poison in the same way as the erasing code.
+	 */
+	poison_high = stackleak_find_top_of_poison(task_stack_low, untracked_high);
+
+	/*
+	 * Check whether the poisoned portion of the stack (if any) consists
+	 * entirely of poison. This verifies the entries that
+	 * stackleak_find_top_of_poison() should have checked.
+	 */
+	poison_low = poison_high;
+	while (poison_low > task_stack_low) {
+		poison_low -= sizeof(unsigned long);
+
+		if (*(unsigned long *)poison_low == KSTACK_ERASE_POISON)
+			continue;
+
+		instrumentation_begin();
+		pr_err("FAIL: non-poison value %lu bytes below poison boundary: 0x%lx\n",
+		       poison_high - poison_low, *(unsigned long *)poison_low);
+		test_failed = true;
+		goto out;
+	}
+
+	instrumentation_begin();
+	pr_info("kstack erase stack usage:\n"
+		"  high offset: %lu bytes\n"
+		"  current:     %lu bytes\n"
+		"  lowest:      %lu bytes\n"
+		"  tracked:     %lu bytes\n"
+		"  untracked:   %lu bytes\n"
+		"  poisoned:    %lu bytes\n"
+		"  low offset:  %lu bytes\n",
+		task_stack_base + THREAD_SIZE - task_stack_high,
+		task_stack_high - current_sp,
+		task_stack_high - lowest_sp,
+		task_stack_high - untracked_high,
+		untracked_high - poison_high,
+		poison_high - task_stack_low,
+		task_stack_low - task_stack_base);
+
+out:
+	if (test_failed) {
+		pr_err("FAIL: the thread stack is NOT properly erased!\n");
+	} else {
+		pr_info("OK: the rest of the thread stack is properly erased\n");
+	}
+	instrumentation_end();
+}
+
+static void lkdtm_KSTACK_ERASE(void)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	check_stackleak_irqoff();
+	local_irq_restore(flags);
+}
+#else /* defined(CONFIG_KSTACK_ERASE) */
+static void lkdtm_KSTACK_ERASE(void)
+{
+	if (IS_ENABLED(CONFIG_HAVE_ARCH_KSTACK_ERASE)) {
+		pr_err("XFAIL: stackleak is not enabled (CONFIG_KSTACK_ERASE=n)\n");
+	} else {
+		pr_err("XFAIL: stackleak is not supported on this arch (HAVE_ARCH_KSTACK_ERASE=n)\n");
+	}
+}
+#endif /* defined(CONFIG_KSTACK_ERASE) */
+
+static struct crashtype crashtypes[] = {
+	CRASHTYPE(KSTACK_ERASE),
+};
+
+struct crashtype_category stackleak_crashtypes = {
+	.crashtypes = crashtypes,
+	.len	    = ARRAY_SIZE(crashtypes),
+};
diff --git a/drivers/misc/lkdtm/stackleak.c b/drivers/misc/lkdtm/stackleak.c
deleted file mode 100644
index f1d022160913..000000000000
--- a/drivers/misc/lkdtm/stackleak.c
+++ /dev/null
@@ -1,150 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This code tests that the current task stack is properly erased (filled
- * with STACKLEAK_POISON).
- *
- * Authors:
- *   Alexander Popov <alex.popov@linux.com>
- *   Tycho Andersen <tycho@tycho.ws>
- */
-
-#include "lkdtm.h"
-#include <linux/stackleak.h>
-
-#if defined(CONFIG_GCC_PLUGIN_STACKLEAK)
-/*
- * Check that stackleak tracks the lowest stack pointer and erases the stack
- * below this as expected.
- *
- * To prevent the lowest stack pointer changing during the test, IRQs are
- * masked and instrumentation of this function is disabled. We assume that the
- * compiler will create a fixed-size stack frame for this function.
- *
- * Any non-inlined function may make further use of the stack, altering the
- * lowest stack pointer and/or clobbering poison values. To avoid spurious
- * failures we must avoid printing until the end of the test or have already
- * encountered a failure condition.
- */
-static void noinstr check_stackleak_irqoff(void)
-{
-	const unsigned long task_stack_base = (unsigned long)task_stack_page(current);
-	const unsigned long task_stack_low = stackleak_task_low_bound(current);
-	const unsigned long task_stack_high = stackleak_task_high_bound(current);
-	const unsigned long current_sp = current_stack_pointer;
-	const unsigned long lowest_sp = current->lowest_stack;
-	unsigned long untracked_high;
-	unsigned long poison_high, poison_low;
-	bool test_failed = false;
-
-	/*
-	 * Check that the current and lowest recorded stack pointer values fall
-	 * within the expected task stack boundaries. These tests should never
-	 * fail unless the boundaries are incorrect or we're clobbering the
-	 * STACK_END_MAGIC, and in either casee something is seriously wrong.
-	 */
-	if (current_sp < task_stack_low || current_sp >= task_stack_high) {
-		instrumentation_begin();
-		pr_err("FAIL: current_stack_pointer (0x%lx) outside of task stack bounds [0x%lx..0x%lx]\n",
-		       current_sp, task_stack_low, task_stack_high - 1);
-		test_failed = true;
-		goto out;
-	}
-	if (lowest_sp < task_stack_low || lowest_sp >= task_stack_high) {
-		instrumentation_begin();
-		pr_err("FAIL: current->lowest_stack (0x%lx) outside of task stack bounds [0x%lx..0x%lx]\n",
-		       lowest_sp, task_stack_low, task_stack_high - 1);
-		test_failed = true;
-		goto out;
-	}
-
-	/*
-	 * Depending on what has run prior to this test, the lowest recorded
-	 * stack pointer could be above or below the current stack pointer.
-	 * Start from the lowest of the two.
-	 *
-	 * Poison values are naturally-aligned unsigned longs. As the current
-	 * stack pointer might not be sufficiently aligned, we must align
-	 * downwards to find the lowest known stack pointer value. This is the
-	 * high boundary for a portion of the stack which may have been used
-	 * without being tracked, and has to be scanned for poison.
-	 */
-	untracked_high = min(current_sp, lowest_sp);
-	untracked_high = ALIGN_DOWN(untracked_high, sizeof(unsigned long));
-
-	/*
-	 * Find the top of the poison in the same way as the erasing code.
-	 */
-	poison_high = stackleak_find_top_of_poison(task_stack_low, untracked_high);
-
-	/*
-	 * Check whether the poisoned portion of the stack (if any) consists
-	 * entirely of poison. This verifies the entries that
-	 * stackleak_find_top_of_poison() should have checked.
-	 */
-	poison_low = poison_high;
-	while (poison_low > task_stack_low) {
-		poison_low -= sizeof(unsigned long);
-
-		if (*(unsigned long *)poison_low == STACKLEAK_POISON)
-			continue;
-
-		instrumentation_begin();
-		pr_err("FAIL: non-poison value %lu bytes below poison boundary: 0x%lx\n",
-		       poison_high - poison_low, *(unsigned long *)poison_low);
-		test_failed = true;
-		goto out;
-	}
-
-	instrumentation_begin();
-	pr_info("stackleak stack usage:\n"
-		"  high offset: %lu bytes\n"
-		"  current:     %lu bytes\n"
-		"  lowest:      %lu bytes\n"
-		"  tracked:     %lu bytes\n"
-		"  untracked:   %lu bytes\n"
-		"  poisoned:    %lu bytes\n"
-		"  low offset:  %lu bytes\n",
-		task_stack_base + THREAD_SIZE - task_stack_high,
-		task_stack_high - current_sp,
-		task_stack_high - lowest_sp,
-		task_stack_high - untracked_high,
-		untracked_high - poison_high,
-		poison_high - task_stack_low,
-		task_stack_low - task_stack_base);
-
-out:
-	if (test_failed) {
-		pr_err("FAIL: the thread stack is NOT properly erased!\n");
-	} else {
-		pr_info("OK: the rest of the thread stack is properly erased\n");
-	}
-	instrumentation_end();
-}
-
-static void lkdtm_STACKLEAK_ERASING(void)
-{
-	unsigned long flags;
-
-	local_irq_save(flags);
-	check_stackleak_irqoff();
-	local_irq_restore(flags);
-}
-#else /* defined(CONFIG_GCC_PLUGIN_STACKLEAK) */
-static void lkdtm_STACKLEAK_ERASING(void)
-{
-	if (IS_ENABLED(CONFIG_HAVE_ARCH_STACKLEAK)) {
-		pr_err("XFAIL: stackleak is not enabled (CONFIG_GCC_PLUGIN_STACKLEAK=n)\n");
-	} else {
-		pr_err("XFAIL: stackleak is not supported on this arch (HAVE_ARCH_STACKLEAK=n)\n");
-	}
-}
-#endif /* defined(CONFIG_GCC_PLUGIN_STACKLEAK) */
-
-static struct crashtype crashtypes[] = {
-	CRASHTYPE(STACKLEAK_ERASING),
-};
-
-struct crashtype_category stackleak_crashtypes = {
-	.crashtypes = crashtypes,
-	.len	    = ARRAY_SIZE(crashtypes),
-};
diff --git a/fs/proc/base.c b/fs/proc/base.c
index c667702dc69b..be34612af8b6 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -3291,7 +3291,7 @@ static int proc_pid_ksm_stat(struct seq_file *m, struct pid_namespace *ns,
 }
 #endif /* CONFIG_KSM */
 
-#ifdef CONFIG_STACKLEAK_METRICS
+#ifdef CONFIG_KSTACK_ERASE_METRICS
 static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns,
 				struct pid *pid, struct task_struct *task)
 {
@@ -3304,7 +3304,7 @@ static int proc_stack_depth(struct seq_file *m, struct pid_namespace *ns,
 							prev_depth, depth);
 	return 0;
 }
-#endif /* CONFIG_STACKLEAK_METRICS */
+#endif /* CONFIG_KSTACK_ERASE_METRICS */
 
 /*
  * Thread groups
@@ -3411,7 +3411,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #ifdef CONFIG_LIVEPATCH
 	ONE("patch_state",  S_IRUSR, proc_pid_patch_state),
 #endif
-#ifdef CONFIG_STACKLEAK_METRICS
+#ifdef CONFIG_KSTACK_ERASE_METRICS
 	ONE("stack_depth", S_IRUGO, proc_stack_depth),
 #endif
 #ifdef CONFIG_PROC_PID_ARCH_STATUS
diff --git a/include/linux/kstack_erase.h b/include/linux/kstack_erase.h
new file mode 100644
index 000000000000..4e432eefa4d0
--- /dev/null
+++ b/include/linux/kstack_erase.h
@@ -0,0 +1,89 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_KSTACK_ERASE_H
+#define _LINUX_KSTACK_ERASE_H
+
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+
+/*
+ * Check that the poison value points to the unused hole in the
+ * virtual memory map for your platform.
+ */
+#define KSTACK_ERASE_POISON -0xBEEF
+#define KSTACK_ERASE_SEARCH_DEPTH 128
+
+#ifdef CONFIG_KSTACK_ERASE
+#include <asm/stacktrace.h>
+#include <linux/linkage.h>
+
+/*
+ * The lowest address on tsk's stack which we can plausibly erase.
+ */
+static __always_inline unsigned long
+stackleak_task_low_bound(const struct task_struct *tsk)
+{
+	/*
+	 * The lowest unsigned long on the task stack contains STACK_END_MAGIC,
+	 * which we must not corrupt.
+	 */
+	return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long);
+}
+
+/*
+ * The address immediately after the highest address on tsk's stack which we
+ * can plausibly erase.
+ */
+static __always_inline unsigned long
+stackleak_task_high_bound(const struct task_struct *tsk)
+{
+	/*
+	 * The task's pt_regs lives at the top of the task stack and will be
+	 * overwritten by exception entry, so there's no need to erase them.
+	 */
+	return (unsigned long)task_pt_regs(tsk);
+}
+
+/*
+ * Find the address immediately above the poisoned region of the stack, where
+ * that region falls between 'low' (inclusive) and 'high' (exclusive).
+ */
+static __always_inline unsigned long
+stackleak_find_top_of_poison(const unsigned long low, const unsigned long high)
+{
+	const unsigned int depth = KSTACK_ERASE_SEARCH_DEPTH / sizeof(unsigned long);
+	unsigned int poison_count = 0;
+	unsigned long poison_high = high;
+	unsigned long sp = high;
+
+	while (sp > low && poison_count < depth) {
+		sp -= sizeof(unsigned long);
+
+		if (*(unsigned long *)sp == KSTACK_ERASE_POISON) {
+			poison_count++;
+		} else {
+			poison_count = 0;
+			poison_high = sp;
+		}
+	}
+
+	return poison_high;
+}
+
+static inline void stackleak_task_init(struct task_struct *t)
+{
+	t->lowest_stack = stackleak_task_low_bound(t);
+# ifdef CONFIG_KSTACK_ERASE_METRICS
+	t->prev_lowest_stack = t->lowest_stack;
+# endif
+}
+
+asmlinkage void noinstr stackleak_erase(void);
+asmlinkage void noinstr stackleak_erase_on_task_stack(void);
+asmlinkage void noinstr stackleak_erase_off_task_stack(void);
+void __no_caller_saved_registers noinstr stackleak_track_stack(void);
+
+#else /* !CONFIG_KSTACK_ERASE */
+static inline void stackleak_task_init(struct task_struct *t) { }
+#endif
+
+#endif
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52..b7d2f2fd4cd4 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -1607,8 +1607,10 @@ struct task_struct {
 	/* Used by BPF for per-TASK xdp storage */
 	struct bpf_net_context		*bpf_net_context;
 
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
+#ifdef CONFIG_KSTACK_ERASE
 	unsigned long			lowest_stack;
+#endif
+#ifdef CONFIG_KSTACK_ERASE_METRICS
 	unsigned long			prev_lowest_stack;
 #endif
 
diff --git a/include/linux/stackleak.h b/include/linux/stackleak.h
deleted file mode 100644
index 3be2cb564710..000000000000
--- a/include/linux/stackleak.h
+++ /dev/null
@@ -1,89 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_STACKLEAK_H
-#define _LINUX_STACKLEAK_H
-
-#include <linux/sched.h>
-#include <linux/sched/task_stack.h>
-
-/*
- * Check that the poison value points to the unused hole in the
- * virtual memory map for your platform.
- */
-#define STACKLEAK_POISON -0xBEEF
-#define STACKLEAK_SEARCH_DEPTH 128
-
-#ifdef CONFIG_GCC_PLUGIN_STACKLEAK
-#include <asm/stacktrace.h>
-#include <linux/linkage.h>
-
-/*
- * The lowest address on tsk's stack which we can plausibly erase.
- */
-static __always_inline unsigned long
-stackleak_task_low_bound(const struct task_struct *tsk)
-{
-	/*
-	 * The lowest unsigned long on the task stack contains STACK_END_MAGIC,
-	 * which we must not corrupt.
-	 */
-	return (unsigned long)end_of_stack(tsk) + sizeof(unsigned long);
-}
-
-/*
- * The address immediately after the highest address on tsk's stack which we
- * can plausibly erase.
- */
-static __always_inline unsigned long
-stackleak_task_high_bound(const struct task_struct *tsk)
-{
-	/*
-	 * The task's pt_regs lives at the top of the task stack and will be
-	 * overwritten by exception entry, so there's no need to erase them.
-	 */
-	return (unsigned long)task_pt_regs(tsk);
-}
-
-/*
- * Find the address immediately above the poisoned region of the stack, where
- * that region falls between 'low' (inclusive) and 'high' (exclusive).
- */
-static __always_inline unsigned long
-stackleak_find_top_of_poison(const unsigned long low, const unsigned long high)
-{
-	const unsigned int depth = STACKLEAK_SEARCH_DEPTH / sizeof(unsigned long);
-	unsigned int poison_count = 0;
-	unsigned long poison_high = high;
-	unsigned long sp = high;
-
-	while (sp > low && poison_count < depth) {
-		sp -= sizeof(unsigned long);
-
-		if (*(unsigned long *)sp == STACKLEAK_POISON) {
-			poison_count++;
-		} else {
-			poison_count = 0;
-			poison_high = sp;
-		}
-	}
-
-	return poison_high;
-}
-
-static inline void stackleak_task_init(struct task_struct *t)
-{
-	t->lowest_stack = stackleak_task_low_bound(t);
-# ifdef CONFIG_STACKLEAK_METRICS
-	t->prev_lowest_stack = t->lowest_stack;
-# endif
-}
-
-asmlinkage void noinstr stackleak_erase(void);
-asmlinkage void noinstr stackleak_erase_on_task_stack(void);
-asmlinkage void noinstr stackleak_erase_off_task_stack(void);
-void __no_caller_saved_registers noinstr stackleak_track_stack(void);
-
-#else /* !CONFIG_GCC_PLUGIN_STACKLEAK */
-static inline void stackleak_task_init(struct task_struct *t) { }
-#endif
-
-#endif
diff --git a/kernel/Makefile b/kernel/Makefile
index 32e80dd626af..e4f01f1d4d0c 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -139,11 +139,11 @@ obj-$(CONFIG_WATCH_QUEUE) += watch_queue.o
 obj-$(CONFIG_RESOURCE_KUNIT_TEST) += resource_kunit.o
 obj-$(CONFIG_SYSCTL_KUNIT_TEST) += sysctl-test.o
 
-CFLAGS_stackleak.o += $(DISABLE_STACKLEAK_PLUGIN)
-obj-$(CONFIG_GCC_PLUGIN_STACKLEAK) += stackleak.o
-KASAN_SANITIZE_stackleak.o := n
-KCSAN_SANITIZE_stackleak.o := n
-KCOV_INSTRUMENT_stackleak.o := n
+CFLAGS_kstack_erase.o += $(DISABLE_KSTACK_ERASE)
+obj-$(CONFIG_KSTACK_ERASE) += kstack_erase.o
+KASAN_SANITIZE_kstack_erase.o := n
+KCSAN_SANITIZE_kstack_erase.o := n
+KCOV_INSTRUMENT_kstack_erase.o := n
 
 obj-$(CONFIG_SCF_TORTURE_TEST) += scftorture.o
 
diff --git a/kernel/fork.c b/kernel/fork.c
index 1ee8eb11f38b..1ec66911f6f6 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -93,7 +93,7 @@
 #include <linux/kcov.h>
 #include <linux/livepatch.h>
 #include <linux/thread_info.h>
-#include <linux/stackleak.h>
+#include <linux/kstack_erase.h>
 #include <linux/kasan.h>
 #include <linux/scs.h>
 #include <linux/io_uring.h>
diff --git a/kernel/kstack_erase.c b/kernel/kstack_erase.c
new file mode 100644
index 000000000000..201b846f8345
--- /dev/null
+++ b/kernel/kstack_erase.c
@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * This code fills the used part of the kernel stack with a poison value
+ * before returning to userspace. It's part of the STACKLEAK feature
+ * ported from grsecurity/PaX.
+ *
+ * Author: Alexander Popov <alex.popov@linux.com>
+ *
+ * KSTACK_ERASE reduces the information which kernel stack leak bugs can
+ * reveal and blocks some uninitialized stack variable attacks.
+ */
+
+#include <linux/kstack_erase.h>
+#include <linux/kprobes.h>
+
+#ifdef CONFIG_KSTACK_ERASE_RUNTIME_DISABLE
+#include <linux/jump_label.h>
+#include <linux/string_choices.h>
+#include <linux/sysctl.h>
+#include <linux/init.h>
+
+static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
+
+#ifdef CONFIG_SYSCTL
+static int stack_erasing_sysctl(const struct ctl_table *table, int write,
+			void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	int ret = 0;
+	int state = !static_branch_unlikely(&stack_erasing_bypass);
+	int prev_state = state;
+	struct ctl_table table_copy = *table;
+
+	table_copy.data = &state;
+	ret = proc_dointvec_minmax(&table_copy, write, buffer, lenp, ppos);
+	state = !!state;
+	if (ret || !write || state == prev_state)
+		return ret;
+
+	if (state)
+		static_branch_disable(&stack_erasing_bypass);
+	else
+		static_branch_enable(&stack_erasing_bypass);
+
+	pr_warn("stackleak: kernel stack erasing is %s\n",
+					str_enabled_disabled(state));
+	return ret;
+}
+static const struct ctl_table stackleak_sysctls[] = {
+	{
+		.procname	= "stack_erasing",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0600,
+		.proc_handler	= stack_erasing_sysctl,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
+static int __init stackleak_sysctls_init(void)
+{
+	register_sysctl_init("kernel", stackleak_sysctls);
+	return 0;
+}
+late_initcall(stackleak_sysctls_init);
+#endif /* CONFIG_SYSCTL */
+
+#define skip_erasing()	static_branch_unlikely(&stack_erasing_bypass)
+#else
+#define skip_erasing()	false
+#endif /* CONFIG_KSTACK_ERASE_RUNTIME_DISABLE */
+
+#ifndef __stackleak_poison
+static __always_inline void __stackleak_poison(unsigned long erase_low,
+					       unsigned long erase_high,
+					       unsigned long poison)
+{
+	while (erase_low < erase_high) {
+		*(unsigned long *)erase_low = poison;
+		erase_low += sizeof(unsigned long);
+	}
+}
+#endif
+
+static __always_inline void __stackleak_erase(bool on_task_stack)
+{
+	const unsigned long task_stack_low = stackleak_task_low_bound(current);
+	const unsigned long task_stack_high = stackleak_task_high_bound(current);
+	unsigned long erase_low, erase_high;
+
+	erase_low = stackleak_find_top_of_poison(task_stack_low,
+						 current->lowest_stack);
+
+#ifdef CONFIG_KSTACK_ERASE_METRICS
+	current->prev_lowest_stack = erase_low;
+#endif
+
+	/*
+	 * Write poison to the task's stack between 'erase_low' and
+	 * 'erase_high'.
+	 *
+	 * If we're running on a different stack (e.g. an entry trampoline
+	 * stack) we can erase everything below the pt_regs at the top of the
+	 * task stack.
+	 *
+	 * If we're running on the task stack itself, we must not clobber any
+	 * stack used by this function and its caller. We assume that this
+	 * function has a fixed-size stack frame, and the current stack pointer
+	 * doesn't change while we write poison.
+	 */
+	if (on_task_stack)
+		erase_high = current_stack_pointer;
+	else
+		erase_high = task_stack_high;
+
+	__stackleak_poison(erase_low, erase_high, KSTACK_ERASE_POISON);
+
+	/* Reset the 'lowest_stack' value for the next syscall */
+	current->lowest_stack = task_stack_high;
+}
+
+/*
+ * Erase and poison the portion of the task stack used since the last erase.
+ * Can be called from the task stack or an entry stack when the task stack is
+ * no longer in use.
+ */
+asmlinkage void noinstr stackleak_erase(void)
+{
+	if (skip_erasing())
+		return;
+
+	__stackleak_erase(on_thread_stack());
+}
+
+/*
+ * Erase and poison the portion of the task stack used since the last erase.
+ * Can only be called from the task stack.
+ */
+asmlinkage void noinstr stackleak_erase_on_task_stack(void)
+{
+	if (skip_erasing())
+		return;
+
+	__stackleak_erase(true);
+}
+
+/*
+ * Erase and poison the portion of the task stack used since the last erase.
+ * Can only be called from a stack other than the task stack.
+ */
+asmlinkage void noinstr stackleak_erase_off_task_stack(void)
+{
+	if (skip_erasing())
+		return;
+
+	__stackleak_erase(false);
+}
+
+void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
+{
+	unsigned long sp = current_stack_pointer;
+
+	/*
+	 * Having CONFIG_KSTACK_ERASE_TRACK_MIN_SIZE larger than
+	 * KSTACK_ERASE_SEARCH_DEPTH makes the poison search in
+	 * stackleak_erase() unreliable. Let's prevent that.
+	 */
+	BUILD_BUG_ON(CONFIG_KSTACK_ERASE_TRACK_MIN_SIZE > KSTACK_ERASE_SEARCH_DEPTH);
+
+	/* 'lowest_stack' should be aligned on the register width boundary */
+	sp = ALIGN(sp, sizeof(unsigned long));
+	if (sp < current->lowest_stack &&
+	    sp >= stackleak_task_low_bound(current)) {
+		current->lowest_stack = sp;
+	}
+}
+EXPORT_SYMBOL(stackleak_track_stack);
diff --git a/kernel/stackleak.c b/kernel/stackleak.c
deleted file mode 100644
index bb65321761b4..000000000000
--- a/kernel/stackleak.c
+++ /dev/null
@@ -1,177 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * This code fills the used part of the kernel stack with a poison value
- * before returning to userspace. It's part of the STACKLEAK feature
- * ported from grsecurity/PaX.
- *
- * Author: Alexander Popov <alex.popov@linux.com>
- *
- * STACKLEAK reduces the information which kernel stack leak bugs can
- * reveal and blocks some uninitialized stack variable attacks.
- */
-
-#include <linux/stackleak.h>
-#include <linux/kprobes.h>
-
-#ifdef CONFIG_STACKLEAK_RUNTIME_DISABLE
-#include <linux/jump_label.h>
-#include <linux/string_choices.h>
-#include <linux/sysctl.h>
-#include <linux/init.h>
-
-static DEFINE_STATIC_KEY_FALSE(stack_erasing_bypass);
-
-#ifdef CONFIG_SYSCTL
-static int stack_erasing_sysctl(const struct ctl_table *table, int write,
-			void __user *buffer, size_t *lenp, loff_t *ppos)
-{
-	int ret = 0;
-	int state = !static_branch_unlikely(&stack_erasing_bypass);
-	int prev_state = state;
-	struct ctl_table table_copy = *table;
-
-	table_copy.data = &state;
-	ret = proc_dointvec_minmax(&table_copy, write, buffer, lenp, ppos);
-	state = !!state;
-	if (ret || !write || state == prev_state)
-		return ret;
-
-	if (state)
-		static_branch_disable(&stack_erasing_bypass);
-	else
-		static_branch_enable(&stack_erasing_bypass);
-
-	pr_warn("stackleak: kernel stack erasing is %s\n",
-					str_enabled_disabled(state));
-	return ret;
-}
-static const struct ctl_table stackleak_sysctls[] = {
-	{
-		.procname	= "stack_erasing",
-		.data		= NULL,
-		.maxlen		= sizeof(int),
-		.mode		= 0600,
-		.proc_handler	= stack_erasing_sysctl,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-};
-
-static int __init stackleak_sysctls_init(void)
-{
-	register_sysctl_init("kernel", stackleak_sysctls);
-	return 0;
-}
-late_initcall(stackleak_sysctls_init);
-#endif /* CONFIG_SYSCTL */
-
-#define skip_erasing()	static_branch_unlikely(&stack_erasing_bypass)
-#else
-#define skip_erasing()	false
-#endif /* CONFIG_STACKLEAK_RUNTIME_DISABLE */
-
-#ifndef __stackleak_poison
-static __always_inline void __stackleak_poison(unsigned long erase_low,
-					       unsigned long erase_high,
-					       unsigned long poison)
-{
-	while (erase_low < erase_high) {
-		*(unsigned long *)erase_low = poison;
-		erase_low += sizeof(unsigned long);
-	}
-}
-#endif
-
-static __always_inline void __stackleak_erase(bool on_task_stack)
-{
-	const unsigned long task_stack_low = stackleak_task_low_bound(current);
-	const unsigned long task_stack_high = stackleak_task_high_bound(current);
-	unsigned long erase_low, erase_high;
-
-	erase_low = stackleak_find_top_of_poison(task_stack_low,
-						 current->lowest_stack);
-
-#ifdef CONFIG_STACKLEAK_METRICS
-	current->prev_lowest_stack = erase_low;
-#endif
-
-	/*
-	 * Write poison to the task's stack between 'erase_low' and
-	 * 'erase_high'.
-	 *
-	 * If we're running on a different stack (e.g. an entry trampoline
-	 * stack) we can erase everything below the pt_regs at the top of the
-	 * task stack.
-	 *
-	 * If we're running on the task stack itself, we must not clobber any
-	 * stack used by this function and its caller. We assume that this
-	 * function has a fixed-size stack frame, and the current stack pointer
-	 * doesn't change while we write poison.
-	 */
-	if (on_task_stack)
-		erase_high = current_stack_pointer;
-	else
-		erase_high = task_stack_high;
-
-	__stackleak_poison(erase_low, erase_high, STACKLEAK_POISON);
-
-	/* Reset the 'lowest_stack' value for the next syscall */
-	current->lowest_stack = task_stack_high;
-}
-
-/*
- * Erase and poison the portion of the task stack used since the last erase.
- * Can be called from the task stack or an entry stack when the task stack is
- * no longer in use.
- */
-asmlinkage void noinstr stackleak_erase(void)
-{
-	if (skip_erasing())
-		return;
-
-	__stackleak_erase(on_thread_stack());
-}
-
-/*
- * Erase and poison the portion of the task stack used since the last erase.
- * Can only be called from the task stack.
- */
-asmlinkage void noinstr stackleak_erase_on_task_stack(void)
-{
-	if (skip_erasing())
-		return;
-
-	__stackleak_erase(true);
-}
-
-/*
- * Erase and poison the portion of the task stack used since the last erase.
- * Can only be called from a stack other than the task stack.
- */
-asmlinkage void noinstr stackleak_erase_off_task_stack(void)
-{
-	if (skip_erasing())
-		return;
-
-	__stackleak_erase(false);
-}
-
-void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
-{
-	unsigned long sp = current_stack_pointer;
-
-	/*
-	 * Having CONFIG_STACKLEAK_TRACK_MIN_SIZE larger than
-	 * STACKLEAK_SEARCH_DEPTH makes the poison search in
-	 * stackleak_erase() unreliable. Let's prevent that.
-	 */
-	BUILD_BUG_ON(CONFIG_STACKLEAK_TRACK_MIN_SIZE > STACKLEAK_SEARCH_DEPTH);
-
-	/* 'lowest_stack' should be aligned on the register width boundary */
-	sp = ALIGN(sp, sizeof(unsigned long));
-	if (sp < current->lowest_stack &&
-	    sp >= stackleak_task_low_bound(current)) {
-		current->lowest_stack = sp;
-	}
-}
-EXPORT_SYMBOL(stackleak_track_stack);
diff --git a/lib/Makefile b/lib/Makefile
index c38582f187dd..632e69d25feb 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -337,7 +337,7 @@ obj-$(CONFIG_UBSAN) += ubsan.o
 UBSAN_SANITIZE_ubsan.o := n
 KASAN_SANITIZE_ubsan.o := n
 KCSAN_SANITIZE_ubsan.o := n
-CFLAGS_ubsan.o := -fno-stack-protector $(DISABLE_STACKLEAK_PLUGIN)
+CFLAGS_ubsan.o := -fno-stack-protector $(DISABLE_KSTACK_ERASE)
 
 obj-$(CONFIG_SBITMAP) += sbitmap.o
 
diff --git a/scripts/Makefile.gcc-plugins b/scripts/Makefile.gcc-plugins
index 435ab3f0ec44..28b8867c4e84 100644
--- a/scripts/Makefile.gcc-plugins
+++ b/scripts/Makefile.gcc-plugins
@@ -12,15 +12,15 @@ gcc-plugin-$(CONFIG_GCC_PLUGIN_STACKLEAK)	+= stackleak_plugin.so
 gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK)		\
 		+= -DSTACKLEAK_PLUGIN
 gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK)		\
-		+= -fplugin-arg-stackleak_plugin-track-min-size=$(CONFIG_STACKLEAK_TRACK_MIN_SIZE)
+		+= -fplugin-arg-stackleak_plugin-track-min-size=$(CONFIG_KSTACK_ERASE_TRACK_MIN_SIZE)
 gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK)		\
 		+= -fplugin-arg-stackleak_plugin-arch=$(SRCARCH)
 gcc-plugin-cflags-$(CONFIG_GCC_PLUGIN_STACKLEAK_VERBOSE)	\
 		+= -fplugin-arg-stackleak_plugin-verbose
 ifdef CONFIG_GCC_PLUGIN_STACKLEAK
-    DISABLE_STACKLEAK_PLUGIN += -fplugin-arg-stackleak_plugin-disable
+    DISABLE_KSTACK_ERASE += -fplugin-arg-stackleak_plugin-disable
 endif
-export DISABLE_STACKLEAK_PLUGIN
+export DISABLE_KSTACK_ERASE
 
 # All the plugin CFLAGS are collected here in case a build target needs to
 # filter them out of the KBUILD_CFLAGS.
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index fd1238753cad..125b35e2ef0f 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -82,10 +82,10 @@ choice
 
 endchoice
 
-config GCC_PLUGIN_STACKLEAK
+config KSTACK_ERASE
 	bool "Poison kernel stack before returning from syscalls"
+	depends on HAVE_ARCH_KSTACK_ERASE
 	depends on GCC_PLUGINS
-	depends on HAVE_ARCH_STACKLEAK
 	help
 	  This option makes the kernel erase the kernel stack before
 	  returning from system calls. This has the effect of leaving
@@ -103,6 +103,10 @@ config GCC_PLUGIN_STACKLEAK
 	  are advised to test this feature on your expected workload before
 	  deploying it.
 
+config GCC_PLUGIN_STACKLEAK
+	def_bool KSTACK_ERASE
+	depends on GCC_PLUGINS
+	help
 	  This plugin was ported from grsecurity/PaX. More information at:
 	   * https://grsecurity.net/
 	   * https://pax.grsecurity.net/
@@ -117,37 +121,37 @@ config GCC_PLUGIN_STACKLEAK_VERBOSE
 	  instrumented. This is useful for comparing coverage between
 	  builds.
 
-config STACKLEAK_TRACK_MIN_SIZE
-	int "Minimum stack frame size of functions tracked by STACKLEAK"
+config KSTACK_ERASE_TRACK_MIN_SIZE
+	int "Minimum stack frame size of functions tracked by KSTACK_ERASE"
 	default 100
 	range 0 4096
-	depends on GCC_PLUGIN_STACKLEAK
+	depends on KSTACK_ERASE
 	help
-	  The STACKLEAK gcc plugin instruments the kernel code for tracking
+	  The KSTACK_ERASE option instruments the kernel code for tracking
 	  the lowest border of the kernel stack (and for some other purposes).
 	  It inserts the stackleak_track_stack() call for the functions with
 	  a stack frame size greater than or equal to this parameter.
 	  If unsure, leave the default value 100.
 
-config STACKLEAK_METRICS
-	bool "Show STACKLEAK metrics in the /proc file system"
-	depends on GCC_PLUGIN_STACKLEAK
+config KSTACK_ERASE_METRICS
+	bool "Show KSTACK_ERASE metrics in the /proc file system"
+	depends on KSTACK_ERASE
 	depends on PROC_FS
 	help
-	  If this is set, STACKLEAK metrics for every task are available in
-	  the /proc file system. In particular, /proc/<pid>/stack_depth
+	  If this is set, KSTACK_ERASE metrics for every task are available
+	  in the /proc file system. In particular, /proc/<pid>/stack_depth
 	  shows the maximum kernel stack consumption for the current and
 	  previous syscalls. Although this information is not precise, it
-	  can be useful for estimating the STACKLEAK performance impact for
-	  your workloads.
+	  can be useful for estimating the KSTACK_ERASE performance impact
+	  for your workloads.
 
-config STACKLEAK_RUNTIME_DISABLE
+config KSTACK_ERASE_RUNTIME_DISABLE
 	bool "Allow runtime disabling of kernel stack erasing"
-	depends on GCC_PLUGIN_STACKLEAK
+	depends on KSTACK_ERASE
 	help
 	  This option provides 'stack_erasing' sysctl, which can be used in
 	  runtime to control kernel stack erasing for kernels built with
-	  CONFIG_GCC_PLUGIN_STACKLEAK.
+	  CONFIG_KSTACK_ERASE.
 
 config INIT_ON_ALLOC_DEFAULT_ON
 	bool "Enable heap memory zeroing on allocation by default"
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index f23bdda737aa..5451bdbcf84a 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1192,7 +1192,7 @@ static const char *uaccess_safe_builtin[] = {
 	"__ubsan_handle_type_mismatch_v1",
 	"__ubsan_handle_shift_out_of_bounds",
 	"__ubsan_handle_load_invalid_value",
-	/* STACKLEAK */
+	/* KSTACK_ERASE */
 	"stackleak_track_stack",
 	/* TRACE_BRANCH_PROFILING */
 	"ftrace_likely_update",
diff --git a/tools/testing/selftests/lkdtm/config b/tools/testing/selftests/lkdtm/config
index 7afe05e8c4d7..bd09fdaf53e0 100644
--- a/tools/testing/selftests/lkdtm/config
+++ b/tools/testing/selftests/lkdtm/config
@@ -2,7 +2,7 @@ CONFIG_LKDTM=y
 CONFIG_DEBUG_LIST=y
 CONFIG_SLAB_FREELIST_HARDENED=y
 CONFIG_FORTIFY_SOURCE=y
-CONFIG_GCC_PLUGIN_STACKLEAK=y
+CONFIG_KSTACK_ERASE=y
 CONFIG_HARDENED_USERCOPY=y
 CONFIG_RANDOMIZE_KSTACK_OFFSET_DEFAULT=y
 CONFIG_INIT_ON_FREE_DEFAULT_ON=y
-- 
cgit v1.2.3


From 9ea1e8d28add49ab3c1ecfa43f08d92ee23f3e33 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Thu, 17 Jul 2025 16:25:07 -0700
Subject: stackleak: Rename stackleak_track_stack to
 __sanitizer_cov_stack_depth

The Clang stack depth tracking implementation has a fixed name for
the stack depth tracking callback, "__sanitizer_cov_stack_depth", so
rename the GCC plugin function to match since the plugin has no external
dependencies on naming.

Link: https://lore.kernel.org/r/20250717232519.2984886-2-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/kstack_erase.h           |  2 +-
 kernel/kstack_erase.c                  |  4 +--
 scripts/gcc-plugins/stackleak_plugin.c | 52 +++++++++++++++++-----------------
 security/Kconfig.hardening             |  4 +--
 tools/objtool/check.c                  |  2 +-
 5 files changed, 32 insertions(+), 32 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kstack_erase.h b/include/linux/kstack_erase.h
index 4e432eefa4d0..bf3bf1905557 100644
--- a/include/linux/kstack_erase.h
+++ b/include/linux/kstack_erase.h
@@ -80,7 +80,7 @@ static inline void stackleak_task_init(struct task_struct *t)
 asmlinkage void noinstr stackleak_erase(void);
 asmlinkage void noinstr stackleak_erase_on_task_stack(void);
 asmlinkage void noinstr stackleak_erase_off_task_stack(void);
-void __no_caller_saved_registers noinstr stackleak_track_stack(void);
+void __no_caller_saved_registers noinstr __sanitizer_cov_stack_depth(void);
 
 #else /* !CONFIG_KSTACK_ERASE */
 static inline void stackleak_task_init(struct task_struct *t) { }
diff --git a/kernel/kstack_erase.c b/kernel/kstack_erase.c
index 201b846f8345..e49bb88b4f0a 100644
--- a/kernel/kstack_erase.c
+++ b/kernel/kstack_erase.c
@@ -156,7 +156,7 @@ asmlinkage void noinstr stackleak_erase_off_task_stack(void)
 	__stackleak_erase(false);
 }
 
-void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
+void __used __no_caller_saved_registers noinstr __sanitizer_cov_stack_depth(void)
 {
 	unsigned long sp = current_stack_pointer;
 
@@ -174,4 +174,4 @@ void __used __no_caller_saved_registers noinstr stackleak_track_stack(void)
 		current->lowest_stack = sp;
 	}
 }
-EXPORT_SYMBOL(stackleak_track_stack);
+EXPORT_SYMBOL(__sanitizer_cov_stack_depth);
diff --git a/scripts/gcc-plugins/stackleak_plugin.c b/scripts/gcc-plugins/stackleak_plugin.c
index d20c47d21ad8..e486488c867d 100644
--- a/scripts/gcc-plugins/stackleak_plugin.c
+++ b/scripts/gcc-plugins/stackleak_plugin.c
@@ -9,7 +9,7 @@
  * any of the gcc libraries
  *
  * This gcc plugin is needed for tracking the lowest border of the kernel stack.
- * It instruments the kernel code inserting stackleak_track_stack() calls:
+ * It instruments the kernel code inserting __sanitizer_cov_stack_depth() calls:
  *  - after alloca();
  *  - for the functions with a stack frame size greater than or equal
  *     to the "track-min-size" plugin parameter.
@@ -33,7 +33,7 @@ __visible int plugin_is_GPL_compatible;
 
 static int track_frame_size = -1;
 static bool build_for_x86 = false;
-static const char track_function[] = "stackleak_track_stack";
+static const char track_function[] = "__sanitizer_cov_stack_depth";
 static bool disable = false;
 static bool verbose = false;
 
@@ -58,7 +58,7 @@ static void add_stack_tracking_gcall(gimple_stmt_iterator *gsi, bool after)
 	cgraph_node_ptr node;
 	basic_block bb;
 
-	/* Insert calling stackleak_track_stack() */
+	/* Insert calling __sanitizer_cov_stack_depth() */
 	stmt = gimple_build_call(track_function_decl, 0);
 	gimple_call = as_a_gcall(stmt);
 	if (after)
@@ -120,12 +120,12 @@ static void add_stack_tracking_gasm(gimple_stmt_iterator *gsi, bool after)
 	gcc_assert(build_for_x86);
 
 	/*
-	 * Insert calling stackleak_track_stack() in asm:
-	 *   asm volatile("call stackleak_track_stack"
+	 * Insert calling __sanitizer_cov_stack_depth() in asm:
+	 *   asm volatile("call __sanitizer_cov_stack_depth"
 	 *		  :: "r" (current_stack_pointer))
 	 * Use ASM_CALL_CONSTRAINT trick from arch/x86/include/asm/asm.h.
 	 * This constraint is taken into account during gcc shrink-wrapping
-	 * optimization. It is needed to be sure that stackleak_track_stack()
+	 * optimization. It is needed to be sure that __sanitizer_cov_stack_depth()
 	 * call is inserted after the prologue of the containing function,
 	 * when the stack frame is prepared.
 	 */
@@ -137,7 +137,7 @@ static void add_stack_tracking_gasm(gimple_stmt_iterator *gsi, bool after)
 	input = build_tree_list(NULL_TREE, build_const_char_string(2, "r"));
 	input = chainon(NULL_TREE, build_tree_list(input, sp_decl));
 	vec_safe_push(inputs, input);
-	asm_call = gimple_build_asm_vec("call stackleak_track_stack",
+	asm_call = gimple_build_asm_vec("call __sanitizer_cov_stack_depth",
 					inputs, NULL, NULL, NULL);
 	gimple_asm_set_volatile(asm_call, true);
 	if (after)
@@ -151,11 +151,11 @@ static void add_stack_tracking(gimple_stmt_iterator *gsi, bool after)
 {
 	/*
 	 * The 'no_caller_saved_registers' attribute is used for
-	 * stackleak_track_stack(). If the compiler supports this attribute for
-	 * the target arch, we can add calling stackleak_track_stack() in asm.
+	 * __sanitizer_cov_stack_depth(). If the compiler supports this attribute for
+	 * the target arch, we can add calling __sanitizer_cov_stack_depth() in asm.
 	 * That improves performance: we avoid useless operations with the
 	 * caller-saved registers in the functions from which we will remove
-	 * stackleak_track_stack() call during the stackleak_cleanup pass.
+	 * __sanitizer_cov_stack_depth() call during the stackleak_cleanup pass.
 	 */
 	if (lookup_attribute_spec(get_identifier("no_caller_saved_registers")))
 		add_stack_tracking_gasm(gsi, after);
@@ -165,7 +165,7 @@ static void add_stack_tracking(gimple_stmt_iterator *gsi, bool after)
 
 /*
  * Work with the GIMPLE representation of the code. Insert the
- * stackleak_track_stack() call after alloca() and into the beginning
+ * __sanitizer_cov_stack_depth() call after alloca() and into the beginning
  * of the function if it is not instrumented.
  */
 static unsigned int stackleak_instrument_execute(void)
@@ -205,7 +205,7 @@ static unsigned int stackleak_instrument_execute(void)
 					DECL_NAME_POINTER(current_function_decl));
 			}
 
-			/* Insert stackleak_track_stack() call after alloca() */
+			/* Insert __sanitizer_cov_stack_depth() call after alloca() */
 			add_stack_tracking(&gsi, true);
 			if (bb == entry_bb)
 				prologue_instrumented = true;
@@ -241,7 +241,7 @@ static unsigned int stackleak_instrument_execute(void)
 		return 0;
 	}
 
-	/* Insert stackleak_track_stack() call at the function beginning */
+	/* Insert __sanitizer_cov_stack_depth() call at the function beginning */
 	bb = entry_bb;
 	if (!single_pred_p(bb)) {
 		/* gcc_assert(bb_loop_depth(bb) ||
@@ -270,15 +270,15 @@ static void remove_stack_tracking_gcall(void)
 	rtx_insn *insn, *next;
 
 	/*
-	 * Find stackleak_track_stack() calls. Loop through the chain of insns,
+	 * Find __sanitizer_cov_stack_depth() calls. Loop through the chain of insns,
 	 * which is an RTL representation of the code for a function.
 	 *
 	 * The example of a matching insn:
-	 *  (call_insn 8 4 10 2 (call (mem (symbol_ref ("stackleak_track_stack")
-	 *  [flags 0x41] <function_decl 0x7f7cd3302a80 stackleak_track_stack>)
-	 *  [0 stackleak_track_stack S1 A8]) (0)) 675 {*call} (expr_list
-	 *  (symbol_ref ("stackleak_track_stack") [flags 0x41] <function_decl
-	 *  0x7f7cd3302a80 stackleak_track_stack>) (expr_list (0) (nil))) (nil))
+	 *  (call_insn 8 4 10 2 (call (mem (symbol_ref ("__sanitizer_cov_stack_depth")
+	 *  [flags 0x41] <function_decl 0x7f7cd3302a80 __sanitizer_cov_stack_depth>)
+	 *  [0 __sanitizer_cov_stack_depth S1 A8]) (0)) 675 {*call} (expr_list
+	 *  (symbol_ref ("__sanitizer_cov_stack_depth") [flags 0x41] <function_decl
+	 *  0x7f7cd3302a80 __sanitizer_cov_stack_depth>) (expr_list (0) (nil))) (nil))
 	 */
 	for (insn = get_insns(); insn; insn = next) {
 		rtx body;
@@ -318,7 +318,7 @@ static void remove_stack_tracking_gcall(void)
 		if (SYMBOL_REF_DECL(body) != track_function_decl)
 			continue;
 
-		/* Delete the stackleak_track_stack() call */
+		/* Delete the __sanitizer_cov_stack_depth() call */
 		delete_insn_and_edges(insn);
 #if BUILDING_GCC_VERSION < 8000
 		if (GET_CODE(next) == NOTE &&
@@ -340,12 +340,12 @@ static bool remove_stack_tracking_gasm(void)
 	gcc_assert(build_for_x86);
 
 	/*
-	 * Find stackleak_track_stack() asm calls. Loop through the chain of
+	 * Find __sanitizer_cov_stack_depth() asm calls. Loop through the chain of
 	 * insns, which is an RTL representation of the code for a function.
 	 *
 	 * The example of a matching insn:
 	 *  (insn 11 5 12 2 (parallel [ (asm_operands/v
-	 *  ("call stackleak_track_stack") ("") 0
+	 *  ("call __sanitizer_cov_stack_depth") ("") 0
 	 *  [ (reg/v:DI 7 sp [ current_stack_pointer ]) ]
 	 *  [ (asm_input:DI ("r")) ] [])
 	 *  (clobber (reg:CC 17 flags)) ]) -1 (nil))
@@ -375,7 +375,7 @@ static bool remove_stack_tracking_gasm(void)
 			continue;
 
 		if (strcmp(ASM_OPERANDS_TEMPLATE(body),
-						"call stackleak_track_stack")) {
+						"call __sanitizer_cov_stack_depth")) {
 			continue;
 		}
 
@@ -389,7 +389,7 @@ static bool remove_stack_tracking_gasm(void)
 
 /*
  * Work with the RTL representation of the code.
- * Remove the unneeded stackleak_track_stack() calls from the functions
+ * Remove the unneeded __sanitizer_cov_stack_depth() calls from the functions
  * which don't call alloca() and don't have a large enough stack frame size.
  */
 static unsigned int stackleak_cleanup_execute(void)
@@ -474,13 +474,13 @@ static bool stackleak_gate(void)
 	return track_frame_size >= 0;
 }
 
-/* Build the function declaration for stackleak_track_stack() */
+/* Build the function declaration for __sanitizer_cov_stack_depth() */
 static void stackleak_start_unit(void *gcc_data __unused,
 				 void *user_data __unused)
 {
 	tree fntype;
 
-	/* void stackleak_track_stack(void) */
+	/* void __sanitizer_cov_stack_depth(void) */
 	fntype = build_function_type_list(void_type_node, NULL_TREE);
 	track_function_decl = build_fn_decl(track_function, fntype);
 	DECL_ASSEMBLER_NAME(track_function_decl); /* for LTO */
diff --git a/security/Kconfig.hardening b/security/Kconfig.hardening
index 125b35e2ef0f..f7aa2024ab25 100644
--- a/security/Kconfig.hardening
+++ b/security/Kconfig.hardening
@@ -129,8 +129,8 @@ config KSTACK_ERASE_TRACK_MIN_SIZE
 	help
 	  The KSTACK_ERASE option instruments the kernel code for tracking
 	  the lowest border of the kernel stack (and for some other purposes).
-	  It inserts the stackleak_track_stack() call for the functions with
-	  a stack frame size greater than or equal to this parameter.
+	  It inserts the __sanitizer_cov_stack_depth() call for the functions
+	  with a stack frame size greater than or equal to this parameter.
 	  If unsure, leave the default value 100.
 
 config KSTACK_ERASE_METRICS
diff --git a/tools/objtool/check.c b/tools/objtool/check.c
index 5451bdbcf84a..b7e24684f592 100644
--- a/tools/objtool/check.c
+++ b/tools/objtool/check.c
@@ -1193,7 +1193,7 @@ static const char *uaccess_safe_builtin[] = {
 	"__ubsan_handle_shift_out_of_bounds",
 	"__ubsan_handle_load_invalid_value",
 	/* KSTACK_ERASE */
-	"stackleak_track_stack",
+	"__sanitizer_cov_stack_depth",
 	/* TRACE_BRANCH_PROFILING */
 	"ftrace_likely_update",
 	/* STACKPROTECTOR */
-- 
cgit v1.2.3


From 2424fe1cac4fc8ea0520ba22ede7544c3ddc8dd1 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Thu, 17 Jul 2025 16:25:10 -0700
Subject: arm: Handle KCOV __init vs inline mismatches

When KCOV is enabled all functions get instrumented, unless
the __no_sanitize_coverage attribute is used. To prepare for
__no_sanitize_coverage being applied to __init functions, we have to
handle differences in how GCC's inline optimizations get resolved. For
arm this exposed several places where __init annotations were missing
but ended up being "accidentally correct". Fix these cases and force
several functions to be inline with __always_inline.

Acked-by: Nishanth Menon <nm@ti.com>
Acked-by: Lee Jones <lee@kernel.org>
Reviewed-by: Nishanth Menon <nm@ti.com>
Link: https://lore.kernel.org/r/20250717232519.2984886-5-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 arch/arm/mm/cache-feroceon-l2.c   | 2 +-
 arch/arm/mm/cache-tauros2.c       | 2 +-
 drivers/clocksource/timer-orion.c | 2 +-
 drivers/soc/ti/pm33xx.c           | 2 +-
 include/linux/mfd/dbx500-prcmu.h  | 2 +-
 5 files changed, 5 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index 25dbd84a1aaf..2bfefb252ffd 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -295,7 +295,7 @@ static inline u32 read_extra_features(void)
 	return u;
 }
 
-static inline void write_extra_features(u32 u)
+static inline void __init write_extra_features(u32 u)
 {
 	__asm__("mcr p15, 1, %0, c15, c1, 0" : : "r" (u));
 }
diff --git a/arch/arm/mm/cache-tauros2.c b/arch/arm/mm/cache-tauros2.c
index b1e1aba602f7..bfe166ccace0 100644
--- a/arch/arm/mm/cache-tauros2.c
+++ b/arch/arm/mm/cache-tauros2.c
@@ -177,7 +177,7 @@ static inline void __init write_actlr(u32 actlr)
 	__asm__("mcr p15, 0, %0, c1, c0, 1\n" : : "r" (actlr));
 }
 
-static void enable_extra_feature(unsigned int features)
+static void __init enable_extra_feature(unsigned int features)
 {
 	u32 u;
 
diff --git a/drivers/clocksource/timer-orion.c b/drivers/clocksource/timer-orion.c
index 49e86cb70a7a..61f1e27fc41e 100644
--- a/drivers/clocksource/timer-orion.c
+++ b/drivers/clocksource/timer-orion.c
@@ -43,7 +43,7 @@ static struct delay_timer orion_delay_timer = {
 	.read_current_timer = orion_read_timer,
 };
 
-static void orion_delay_timer_init(unsigned long rate)
+static void __init orion_delay_timer_init(unsigned long rate)
 {
 	orion_delay_timer.freq = rate;
 	register_current_timer_delay(&orion_delay_timer);
diff --git a/drivers/soc/ti/pm33xx.c b/drivers/soc/ti/pm33xx.c
index dfdff186c805..dc52a2197d24 100644
--- a/drivers/soc/ti/pm33xx.c
+++ b/drivers/soc/ti/pm33xx.c
@@ -145,7 +145,7 @@ static int am33xx_do_sram_idle(u32 wfi_flags)
 	return pm_ops->cpu_suspend(am33xx_do_wfi_sram, wfi_flags);
 }
 
-static int __init am43xx_map_gic(void)
+static int am43xx_map_gic(void)
 {
 	gic_dist_base = ioremap(AM43XX_GIC_DIST_BASE, SZ_4K);
 
diff --git a/include/linux/mfd/dbx500-prcmu.h b/include/linux/mfd/dbx500-prcmu.h
index 98567623c9df..828362b7860c 100644
--- a/include/linux/mfd/dbx500-prcmu.h
+++ b/include/linux/mfd/dbx500-prcmu.h
@@ -213,7 +213,7 @@ struct prcmu_fw_version {
 
 #if defined(CONFIG_UX500_SOC_DB8500)
 
-static inline void prcmu_early_init(void)
+static inline void __init prcmu_early_init(void)
 {
 	db8500_prcmu_early_init();
 }
-- 
cgit v1.2.3


From 1b5f1454091e9e9fb5c944b3161acf4ec0894d0d Mon Sep 17 00:00:00 2001
From: Feng Lee <379943137@qq.com>
Date: Mon, 21 Jul 2025 16:04:35 +0800
Subject: sched/idle: Remove play_idle()

play_idle() is no longer in use, so delete it.

Signed-off-by: Feng Lee <379943137@qq.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/all/tencent_C3E0BD9B812C27A30FC49F1EA6A4B1352707@qq.com
---
 include/linux/cpu.h | 5 -----
 1 file changed, 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index 6378370a952f..8b1abbf5b6d2 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -187,11 +187,6 @@ static inline void arch_cpu_finalize_init(void) { }
 
 void play_idle_precise(u64 duration_ns, u64 latency_ns);
 
-static inline void play_idle(unsigned long duration_us)
-{
-	play_idle_precise(duration_us * NSEC_PER_USEC, U64_MAX);
-}
-
 #ifdef CONFIG_HOTPLUG_CPU
 void cpuhp_report_idle_dead(void);
 #else
-- 
cgit v1.2.3


From 2fb4af5ea3c735a205d97de10f044f809b20af51 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 18 Jul 2025 10:14:49 +0200
Subject: NFS: track active delegations per-server

The active delegation watermark was added to avoid overloading servers.
Track the active delegation per-server instead of globally so that clients
talking to multiple servers aren't limited by the global limit.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jeff Layton <jlayton@kernel.org>
Link: https://lore.kernel.org/r/20250718081509.2607553-5-hch@lst.de
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/client.c           |  1 +
 fs/nfs/delegation.c       | 35 +++++++++++++++++++----------------
 include/linux/nfs_fs_sb.h |  1 +
 3 files changed, 21 insertions(+), 16 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 47258dc3af70..e13eb429b8b5 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -1005,6 +1005,7 @@ struct nfs_server *nfs_alloc_server(void)
 	INIT_LIST_HEAD(&server->ss_src_copies);
 
 	atomic_set(&server->active, 0);
+	atomic_long_set(&server->nr_active_delegations, 0);
 
 	server->io_stats = nfs_alloc_iostats();
 	if (!server->io_stats) {
diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index 5f85966d7709..ea96f77e38c2 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -27,7 +27,6 @@
 
 #define NFS_DEFAULT_DELEGATION_WATERMARK (5000U)
 
-static atomic_long_t nfs_active_delegations;
 static unsigned nfs_delegation_watermark = NFS_DEFAULT_DELEGATION_WATERMARK;
 module_param_named(delegation_watermark, nfs_delegation_watermark, uint, 0644);
 
@@ -38,11 +37,12 @@ static void __nfs_free_delegation(struct nfs_delegation *delegation)
 	kfree_rcu(delegation, rcu);
 }
 
-static void nfs_mark_delegation_revoked(struct nfs_delegation *delegation)
+static void nfs_mark_delegation_revoked(struct nfs_server *server,
+		struct nfs_delegation *delegation)
 {
 	if (!test_and_set_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
 		delegation->stateid.type = NFS4_INVALID_STATEID_TYPE;
-		atomic_long_dec(&nfs_active_delegations);
+		atomic_long_dec(&server->nr_active_delegations);
 		if (!test_bit(NFS_DELEGATION_RETURNING, &delegation->flags))
 			nfs_clear_verifier_delegated(delegation->inode);
 	}
@@ -60,9 +60,10 @@ static void nfs_put_delegation(struct nfs_delegation *delegation)
 		__nfs_free_delegation(delegation);
 }
 
-static void nfs_free_delegation(struct nfs_delegation *delegation)
+static void nfs_free_delegation(struct nfs_server *server,
+		struct nfs_delegation *delegation)
 {
-	nfs_mark_delegation_revoked(delegation);
+	nfs_mark_delegation_revoked(server, delegation);
 	nfs_put_delegation(delegation);
 }
 
@@ -261,7 +262,7 @@ void nfs_inode_reclaim_delegation(struct inode *inode, const struct cred *cred,
 	}
 	clear_bit(NFS_DELEGATION_NEED_RECLAIM, &delegation->flags);
 	if (test_and_clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags))
-		atomic_long_inc(&nfs_active_delegations);
+		atomic_long_inc(&NFS_SERVER(inode)->nr_active_delegations);
 	spin_unlock(&delegation->lock);
 	rcu_read_unlock();
 	put_cred(oldcred);
@@ -413,7 +414,8 @@ nfs_update_delegation_cred(struct nfs_delegation *delegation,
 }
 
 static void
-nfs_update_inplace_delegation(struct nfs_delegation *delegation,
+nfs_update_inplace_delegation(struct nfs_server *server,
+		struct nfs_delegation *delegation,
 		const struct nfs_delegation *update)
 {
 	if (nfs4_stateid_is_newer(&update->stateid, &delegation->stateid)) {
@@ -426,7 +428,7 @@ nfs_update_inplace_delegation(struct nfs_delegation *delegation,
 			nfs_update_delegation_cred(delegation, update->cred);
 			/* smp_mb__before_atomic() is implicit due to xchg() */
 			clear_bit(NFS_DELEGATION_REVOKED, &delegation->flags);
-			atomic_long_inc(&nfs_active_delegations);
+			atomic_long_inc(&server->nr_active_delegations);
 		}
 	}
 }
@@ -481,7 +483,7 @@ int nfs_inode_set_delegation(struct inode *inode, const struct cred *cred,
 	if (nfs4_stateid_match_other(&old_delegation->stateid,
 				&delegation->stateid)) {
 		spin_lock(&old_delegation->lock);
-		nfs_update_inplace_delegation(old_delegation,
+		nfs_update_inplace_delegation(server, old_delegation,
 				delegation);
 		spin_unlock(&old_delegation->lock);
 		goto out;
@@ -530,7 +532,7 @@ add_new:
 	rcu_assign_pointer(nfsi->delegation, delegation);
 	delegation = NULL;
 
-	atomic_long_inc(&nfs_active_delegations);
+	atomic_long_inc(&server->nr_active_delegations);
 
 	trace_nfs4_set_delegation(inode, type);
 
@@ -544,7 +546,7 @@ out:
 		__nfs_free_delegation(delegation);
 	if (freeme != NULL) {
 		nfs_do_return_delegation(inode, freeme, 0);
-		nfs_free_delegation(freeme);
+		nfs_free_delegation(server, freeme);
 	}
 	return status;
 }
@@ -756,7 +758,7 @@ void nfs_inode_evict_delegation(struct inode *inode)
 		set_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
 		set_bit(NFS_DELEGATION_INODE_FREEING, &delegation->flags);
 		nfs_do_return_delegation(inode, delegation, 1);
-		nfs_free_delegation(delegation);
+		nfs_free_delegation(NFS_SERVER(inode), delegation);
 	}
 }
 
@@ -842,7 +844,8 @@ void nfs4_inode_return_delegation_on_close(struct inode *inode)
 	if (!delegation)
 		goto out;
 	if (test_bit(NFS_DELEGATION_RETURN_IF_CLOSED, &delegation->flags) ||
-	    atomic_long_read(&nfs_active_delegations) >= nfs_delegation_watermark) {
+	    atomic_long_read(&NFS_SERVER(inode)->nr_active_delegations) >=
+	    nfs_delegation_watermark) {
 		spin_lock(&delegation->lock);
 		if (delegation->inode &&
 		    list_empty(&NFS_I(inode)->open_files) &&
@@ -1018,7 +1021,7 @@ static void nfs_revoke_delegation(struct inode *inode,
 		}
 		spin_unlock(&delegation->lock);
 	}
-	nfs_mark_delegation_revoked(delegation);
+	nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation);
 	ret = true;
 out:
 	rcu_read_unlock();
@@ -1050,7 +1053,7 @@ void nfs_delegation_mark_returned(struct inode *inode,
 			delegation->stateid.seqid = stateid->seqid;
 	}
 
-	nfs_mark_delegation_revoked(delegation);
+	nfs_mark_delegation_revoked(NFS_SERVER(inode), delegation);
 	clear_bit(NFS_DELEGATION_RETURNING, &delegation->flags);
 	spin_unlock(&delegation->lock);
 	if (nfs_detach_delegation(NFS_I(inode), delegation, NFS_SERVER(inode)))
@@ -1270,7 +1273,7 @@ restart:
 		if (delegation != NULL) {
 			if (nfs_detach_delegation(NFS_I(inode), delegation,
 						server) != NULL)
-				nfs_free_delegation(delegation);
+				nfs_free_delegation(server, delegation);
 			/* Match nfs_start_delegation_return_locked */
 			nfs_put_delegation(delegation);
 		}
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index d2d36711a119..a9b44f12623f 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -254,6 +254,7 @@ struct nfs_server {
 	struct list_head	state_owners_lru;
 	struct list_head	layouts;
 	struct list_head	delegations;
+	atomic_long_t		nr_active_delegations;
 	struct list_head	ss_copies;
 	struct list_head	ss_src_copies;
 
-- 
cgit v1.2.3


From f5b3108e6a14418b120a3c38ca589b8d6cf87627 Mon Sep 17 00:00:00 2001
From: Christoph Hellwig <hch@lst.de>
Date: Fri, 18 Jul 2025 10:14:50 +0200
Subject: NFS: use a hash table for delegation lookup

nfs_delegation_find_inode currently has to walk the entire list of
delegations per inode, which can become pretty large, and can become even
larger when increasing the delegation watermark.

Add a hash table to speed up the delegation lookup, sized as a fraction
of the delegation watermark.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Link: https://lore.kernel.org/r/20250718081509.2607553-6-hch@lst.de
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
---
 fs/nfs/delegation.c       | 28 +++++++++++++++++++++++++++-
 fs/nfs/delegation.h       |  3 +++
 fs/nfs/nfs4client.c       |  5 +++++
 fs/nfs/nfs4proc.c         | 22 +++++++++++++++++++++-
 include/linux/nfs_fs_sb.h |  2 ++
 5 files changed, 58 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
index ea96f77e38c2..9d3a5f29f17f 100644
--- a/fs/nfs/delegation.c
+++ b/fs/nfs/delegation.c
@@ -30,6 +30,13 @@
 static unsigned nfs_delegation_watermark = NFS_DEFAULT_DELEGATION_WATERMARK;
 module_param_named(delegation_watermark, nfs_delegation_watermark, uint, 0644);
 
+static struct hlist_head *nfs_delegation_hash(struct nfs_server *server,
+		const struct nfs_fh *fhandle)
+{
+	return server->delegation_hash_table +
+		(nfs_fhandle_hash(fhandle) & server->delegation_hash_mask);
+}
+
 static void __nfs_free_delegation(struct nfs_delegation *delegation)
 {
 	put_cred(delegation->cred);
@@ -367,6 +374,7 @@ nfs_detach_delegation_locked(struct nfs_inode *nfsi,
 		spin_unlock(&delegation->lock);
 		return NULL;
 	}
+	hlist_del_init_rcu(&delegation->hash);
 	list_del_rcu(&delegation->super_list);
 	delegation->inode = NULL;
 	rcu_assign_pointer(nfsi->delegation, NULL);
@@ -529,6 +537,8 @@ add_new:
 	spin_unlock(&inode->i_lock);
 
 	list_add_tail_rcu(&delegation->super_list, &server->delegations);
+	hlist_add_head_rcu(&delegation->hash,
+			nfs_delegation_hash(server, &NFS_I(inode)->fh));
 	rcu_assign_pointer(nfsi->delegation, delegation);
 	delegation = NULL;
 
@@ -1166,11 +1176,12 @@ static struct inode *
 nfs_delegation_find_inode_server(struct nfs_server *server,
 				 const struct nfs_fh *fhandle)
 {
+	struct hlist_head *head = nfs_delegation_hash(server, fhandle);
 	struct nfs_delegation *delegation;
 	struct super_block *freeme = NULL;
 	struct inode *res = NULL;
 
-	list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
+	hlist_for_each_entry_rcu(delegation, head, hash) {
 		spin_lock(&delegation->lock);
 		if (delegation->inode != NULL &&
 		    !test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) &&
@@ -1577,3 +1588,18 @@ out:
 	rcu_read_unlock();
 	return ret;
 }
+
+int nfs4_delegation_hash_alloc(struct nfs_server *server)
+{
+	int delegation_buckets, i;
+
+	delegation_buckets = roundup_pow_of_two(nfs_delegation_watermark / 16);
+	server->delegation_hash_mask = delegation_buckets - 1;
+	server->delegation_hash_table = kmalloc_array(delegation_buckets,
+			sizeof(*server->delegation_hash_table), GFP_KERNEL);
+	if (!server->delegation_hash_table)
+		return -ENOMEM;
+	for (i = 0; i < delegation_buckets; i++)
+		INIT_HLIST_HEAD(&server->delegation_hash_table[i]);
+	return 0;
+}
diff --git a/fs/nfs/delegation.h b/fs/nfs/delegation.h
index 8ff5ab9c5c25..08ec2e9c68a4 100644
--- a/fs/nfs/delegation.h
+++ b/fs/nfs/delegation.h
@@ -14,6 +14,7 @@
  * NFSv4 delegation
  */
 struct nfs_delegation {
+	struct hlist_node hash;
 	struct list_head super_list;
 	const struct cred *cred;
 	struct inode *inode;
@@ -123,4 +124,6 @@ static inline int nfs_have_delegated_mtime(struct inode *inode)
 						 NFS_DELEGATION_FLAG_TIME);
 }
 
+int nfs4_delegation_hash_alloc(struct nfs_server *server);
+
 #endif
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 5943a192f36b..2ea98f1f116f 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -802,6 +802,7 @@ static void nfs4_destroy_server(struct nfs_server *server)
 	unset_pnfs_layoutdriver(server);
 	nfs4_purge_state_owners(server, &freeme);
 	nfs4_free_state_owners(&freeme);
+	kfree(server->delegation_hash_table);
 }
 
 /*
@@ -1096,6 +1097,10 @@ static int nfs4_server_common_setup(struct nfs_server *server,
 {
 	int error;
 
+	error = nfs4_delegation_hash_alloc(server);
+	if (error)
+		return error;
+
 	/* data servers support only a subset of NFSv4.1 */
 	if (is_ds_only_client(server->nfs_client))
 		return -EPROTONOSUPPORT;
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index ef2077e185b6..d8bebd757af3 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -10967,6 +10967,26 @@ static const struct inode_operations nfs4_file_inode_operations = {
 	.listxattr	= nfs4_listxattr,
 };
 
+static struct nfs_server *nfs4_clone_server(struct nfs_server *source,
+		struct nfs_fh *fh, struct nfs_fattr *fattr,
+		rpc_authflavor_t flavor)
+{
+	struct nfs_server *server;
+	int error;
+
+	server = nfs_clone_server(source, fh, fattr, flavor);
+	if (IS_ERR(server))
+		return server;
+
+	error = nfs4_delegation_hash_alloc(server);
+	if (error) {
+		nfs_free_server(server);
+		return ERR_PTR(error);
+	}
+
+	return server;
+}
+
 const struct nfs_rpc_ops nfs_v4_clientops = {
 	.version	= 4,			/* protocol version */
 	.dentry_ops	= &nfs4_dentry_operations,
@@ -11019,7 +11039,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.init_client	= nfs4_init_client,
 	.free_client	= nfs4_free_client,
 	.create_server	= nfs4_create_server,
-	.clone_server	= nfs_clone_server,
+	.clone_server	= nfs4_clone_server,
 	.discover_trunking = nfs4_discover_trunking,
 	.enable_swap	= nfs4_enable_swap,
 	.disable_swap	= nfs4_disable_swap,
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index a9b44f12623f..d30c0245031c 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -255,6 +255,8 @@ struct nfs_server {
 	struct list_head	layouts;
 	struct list_head	delegations;
 	atomic_long_t		nr_active_delegations;
+	unsigned int		delegation_hash_mask;
+	struct hlist_head	*delegation_hash_table;
 	struct list_head	ss_copies;
 	struct list_head	ss_src_copies;
 
-- 
cgit v1.2.3


From ad38574a8e8223361e265973fbd87013ea058c5d Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 8 Jul 2025 18:03:33 +0100
Subject: f2fs: Pass a folio to ADDRS_PER_PAGE()

All callers now have a folio so pass it in.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c          |  2 +-
 fs/f2fs/file.c          | 18 +++++++++---------
 fs/f2fs/recovery.c      |  4 ++--
 fs/f2fs/segment.c       |  2 +-
 include/linux/f2fs_fs.h |  2 +-
 5 files changed, 14 insertions(+), 14 deletions(-)

(limited to 'include/linux')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 0e261caf2f91..8a2414ce39ff 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -1588,7 +1588,7 @@ next_dnode:
 	start_pgofs = pgofs;
 	prealloc = 0;
 	last_ofs_in_node = ofs_in_node = dn.ofs_in_node;
-	end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+	end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 
 next_block:
 	blkaddr = f2fs_data_blkaddr(&dn);
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 04a5a1089320..60618c52ba50 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -489,7 +489,7 @@ static loff_t f2fs_seek_block(struct file *file, loff_t offset, int whence)
 			}
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 
 		/* find data/hole in dnode block */
 		for (; dn.ofs_in_node < end_offset;
@@ -814,7 +814,7 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 		goto out;
 	}
 
-	count = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+	count = ADDRS_PER_PAGE(dn.node_folio, inode);
 
 	count -= dn.ofs_in_node;
 	f2fs_bug_on(sbi, count < 0);
@@ -1233,7 +1233,7 @@ int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end)
 			return err;
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 		count = min(end_offset - dn.ofs_in_node, pg_end - pg_start);
 
 		f2fs_bug_on(F2FS_I_SB(inode), count == 0 || count > end_offset);
@@ -1332,7 +1332,7 @@ next_dnode:
 		goto next;
 	}
 
-	done = min((pgoff_t)ADDRS_PER_PAGE(&dn.node_folio->page, inode) -
+	done = min((pgoff_t)ADDRS_PER_PAGE(dn.node_folio, inode) -
 							dn.ofs_in_node, len);
 	for (i = 0; i < done; i++, blkaddr++, do_replace++, dn.ofs_in_node++) {
 		*blkaddr = f2fs_data_blkaddr(&dn);
@@ -1421,7 +1421,7 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 			}
 
 			ilen = min((pgoff_t)
-				ADDRS_PER_PAGE(&dn.node_folio->page, dst_inode) -
+				ADDRS_PER_PAGE(dn.node_folio, dst_inode) -
 						dn.ofs_in_node, len - i);
 			do {
 				dn.data_blkaddr = f2fs_data_blkaddr(&dn);
@@ -1717,7 +1717,7 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 				goto out;
 			}
 
-			end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+			end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 			end = min(pg_end, end_offset - dn.ofs_in_node + index);
 
 			ret = f2fs_do_zero_range(&dn, index, end);
@@ -3885,7 +3885,7 @@ static int f2fs_release_compress_blocks(struct file *filp, unsigned long arg)
 			break;
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
 		count = round_up(count, fi->i_cluster_size);
 
@@ -4063,7 +4063,7 @@ static int f2fs_reserve_compress_blocks(struct file *filp, unsigned long arg)
 			break;
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 		count = min(end_offset - dn.ofs_in_node, last_idx - page_idx);
 		count = round_up(count, fi->i_cluster_size);
 
@@ -4227,7 +4227,7 @@ static int f2fs_sec_trim_file(struct file *filp, unsigned long arg)
 			goto out;
 		}
 
-		end_offset = ADDRS_PER_PAGE(&dn.node_folio->page, inode);
+		end_offset = ADDRS_PER_PAGE(dn.node_folio, inode);
 		count = min(end_offset - dn.ofs_in_node, pg_end - index);
 		for (i = 0; i < count; i++, index++, dn.ofs_in_node++) {
 			struct block_device *cur_bdev;
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 5a45d0d1f05c..894b27b0329d 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -527,7 +527,7 @@ got_it:
 	nid = le32_to_cpu(sum.nid);
 	ofs_in_node = le16_to_cpu(sum.ofs_in_node);
 
-	max_addrs = ADDRS_PER_PAGE(&dn->node_folio->page, dn->inode);
+	max_addrs = ADDRS_PER_PAGE(dn->node_folio, dn->inode);
 	if (ofs_in_node >= max_addrs) {
 		f2fs_err(sbi, "Inconsistent ofs_in_node:%u in summary, ino:%lu, nid:%u, max:%u",
 			ofs_in_node, dn->inode->i_ino, nid, max_addrs);
@@ -649,7 +649,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 
 	/* step 3: recover data indices */
 	start = f2fs_start_bidx_of_node(ofs_of_node(folio), inode);
-	end = start + ADDRS_PER_PAGE(&folio->page, inode);
+	end = start + ADDRS_PER_PAGE(folio, inode);
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 retry_dn:
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 2a6dcfba911f..909637873ff7 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -334,7 +334,7 @@ static int __f2fs_commit_atomic_write(struct inode *inode)
 			goto next;
 		}
 
-		blen = min((pgoff_t)ADDRS_PER_PAGE(&dn.node_folio->page, cow_inode),
+		blen = min((pgoff_t)ADDRS_PER_PAGE(dn.node_folio, cow_inode),
 				len);
 		index = off;
 		for (i = 0; i < blen; i++, dn.ofs_in_node++, index++) {
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 5206d63b3386..25857877eaec 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -268,7 +268,7 @@ struct node_footer {
 /* Node IDs in an Indirect Block */
 #define NIDS_PER_BLOCK		((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32))
 
-#define ADDRS_PER_PAGE(page, inode)	(addrs_per_page(inode, IS_INODE(page)))
+#define ADDRS_PER_PAGE(folio, inode)	(addrs_per_page(inode, IS_INODE(&folio->page)))
 
 #define	NODE_DIR1_BLOCK		(DEF_ADDRS_PER_INODE + 1)
 #define	NODE_DIR2_BLOCK		(DEF_ADDRS_PER_INODE + 2)
-- 
cgit v1.2.3


From a5f3be6e652a7beaaf6c482bc013b64129a5d239 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 8 Jul 2025 18:03:34 +0100
Subject: f2fs: Pass a folio to IS_INODE()

All callers now have a folio so pass it in.  Also make it const to help
the compiler.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/f2fs.h          |  6 +++---
 fs/f2fs/file.c          |  2 +-
 fs/f2fs/gc.c            |  2 +-
 fs/f2fs/inline.c        |  2 +-
 fs/f2fs/inode.c         |  2 +-
 fs/f2fs/node.c          | 14 ++++++--------
 fs/f2fs/recovery.c      |  8 ++++----
 include/linux/f2fs_fs.h |  2 +-
 8 files changed, 18 insertions(+), 20 deletions(-)

(limited to 'include/linux')

diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 3933327d8cc3..09ddc0626dfe 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3019,9 +3019,9 @@ static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
 
 #define RAW_IS_INODE(p)	((p)->footer.nid == (p)->footer.ino)
 
-static inline bool IS_INODE(struct page *page)
+static inline bool IS_INODE(const struct folio *folio)
 {
-	struct f2fs_node *p = F2FS_NODE(page);
+	struct f2fs_node *p = F2FS_NODE(&folio->page);
 
 	return RAW_IS_INODE(p);
 }
@@ -3041,7 +3041,7 @@ static inline int f2fs_has_extra_attr(struct inode *inode);
 static inline unsigned int get_dnode_base(struct inode *inode,
 					struct folio *node_folio)
 {
-	if (!IS_INODE(&node_folio->page))
+	if (!IS_INODE(node_folio))
 		return 0;
 
 	return inode ? get_extra_isize(inode) :
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 60618c52ba50..36b32757d5b9 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -819,7 +819,7 @@ int f2fs_do_truncate_blocks(struct inode *inode, u64 from, bool lock)
 	count -= dn.ofs_in_node;
 	f2fs_bug_on(sbi, count < 0);
 
-	if (dn.ofs_in_node || IS_INODE(&dn.node_folio->page)) {
+	if (dn.ofs_in_node || IS_INODE(dn.node_folio)) {
 		f2fs_truncate_data_blocks_range(&dn, count);
 		free_from += count;
 	}
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 781b955cbb77..c1d4ecbd2505 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -1162,7 +1162,7 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 		return false;
 	}
 
-	if (IS_INODE(&node_folio->page)) {
+	if (IS_INODE(node_folio)) {
 		base = offset_in_addr(F2FS_INODE(node_folio));
 		max_addrs = DEF_ADDRS_PER_INODE;
 	} else {
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index 9851310cdb87..51adc43d5a5c 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -305,7 +305,7 @@ int f2fs_recover_inline_data(struct inode *inode, struct folio *nfolio)
 	 *    x       o  -> remove data blocks, and then recover inline_data
 	 *    x       x  -> recover data blocks
 	 */
-	if (IS_INODE(&nfolio->page))
+	if (IS_INODE(nfolio))
 		ri = F2FS_INODE(nfolio);
 
 	if (f2fs_has_inline_data(inode) &&
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index a8f64d206d19..dd3b43c24831 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -124,7 +124,7 @@ bool f2fs_enable_inode_chksum(struct f2fs_sb_info *sbi, struct folio *folio)
 	if (!f2fs_sb_has_inode_chksum(sbi))
 		return false;
 
-	if (!IS_INODE(&folio->page) || !(ri->i_inline & F2FS_EXTRA_ATTR))
+	if (!IS_INODE(folio) || !(ri->i_inline & F2FS_EXTRA_ATTR))
 		return false;
 
 	if (!F2FS_FITS_IN_INODE(ri, le16_to_cpu(ri->i_extra_isize),
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index b56e627e0b56..908a1eb9c415 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -973,7 +973,7 @@ static int truncate_dnode(struct dnode_of_data *dn)
 	else if (IS_ERR(folio))
 		return PTR_ERR(folio);
 
-	if (IS_INODE(&folio->page) || ino_of_node(folio) != dn->inode->i_ino) {
+	if (IS_INODE(folio) || ino_of_node(folio) != dn->inode->i_ino) {
 		f2fs_err(sbi, "incorrect node reference, ino: %lu, nid: %u, ino_of_node: %u",
 				dn->inode->i_ino, dn->nid, ino_of_node(folio));
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
@@ -1474,10 +1474,8 @@ static int sanity_check_node_footer(struct f2fs_sb_info *sbi,
 					struct folio *folio, pgoff_t nid,
 					enum node_type ntype)
 {
-	struct page *page = &folio->page;
-
 	if (unlikely(nid != nid_of_node(folio) ||
-		(ntype == NODE_TYPE_INODE && !IS_INODE(page)) ||
+		(ntype == NODE_TYPE_INODE && !IS_INODE(folio)) ||
 		(ntype == NODE_TYPE_XATTR &&
 		!f2fs_has_xattr_block(ofs_of_node(folio))) ||
 		time_to_inject(sbi, FAULT_INCONSISTENT_FOOTER))) {
@@ -1867,7 +1865,7 @@ continue_unlock:
 			if (!atomic || folio == last_folio) {
 				set_fsync_mark(folio, 1);
 				percpu_counter_inc(&sbi->rf_node_block_count);
-				if (IS_INODE(&folio->page)) {
+				if (IS_INODE(folio)) {
 					if (is_inode_flag_set(inode,
 								FI_DIRTY_INODE))
 						f2fs_update_inode(inode, folio);
@@ -1976,7 +1974,7 @@ void f2fs_flush_inline_data(struct f2fs_sb_info *sbi)
 		for (i = 0; i < nr_folios; i++) {
 			struct folio *folio = fbatch.folios[i];
 
-			if (!IS_INODE(&folio->page))
+			if (!IS_INODE(folio))
 				continue;
 
 			folio_lock(folio);
@@ -2077,7 +2075,7 @@ continue_unlock:
 			}
 
 			/* flush dirty inode */
-			if (IS_INODE(&folio->page) && flush_dirty_inode(folio))
+			if (IS_INODE(folio) && flush_dirty_inode(folio))
 				goto lock_node;
 write_node:
 			f2fs_folio_wait_writeback(folio, NODE, true, true);
@@ -2213,7 +2211,7 @@ static bool f2fs_dirty_node_folio(struct address_space *mapping,
 	if (!folio_test_uptodate(folio))
 		folio_mark_uptodate(folio);
 #ifdef CONFIG_F2FS_CHECK_FS
-	if (IS_INODE(&folio->page))
+	if (IS_INODE(folio))
 		f2fs_inode_chksum_set(F2FS_M_SB(mapping), folio);
 #endif
 	if (filemap_dirty_folio(mapping, folio)) {
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 894b27b0329d..4cb3a91801b4 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -437,7 +437,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
 			bool quota_inode = false;
 
 			if (!check_only &&
-					IS_INODE(&folio->page) &&
+					IS_INODE(folio) &&
 					is_dent_dnode(folio)) {
 				err = f2fs_recover_inode_page(sbi, folio);
 				if (err) {
@@ -463,7 +463,7 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
 		}
 		entry->blkaddr = blkaddr;
 
-		if (IS_INODE(&folio->page) && is_dent_dnode(folio))
+		if (IS_INODE(folio) && is_dent_dnode(folio))
 			entry->last_dentry = blkaddr;
 next:
 		/* check next segment */
@@ -628,7 +628,7 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	int err = 0, recovered = 0;
 
 	/* step 1: recover xattr */
-	if (IS_INODE(&folio->page)) {
+	if (IS_INODE(folio)) {
 		err = f2fs_recover_inline_xattr(inode, folio);
 		if (err)
 			goto out;
@@ -821,7 +821,7 @@ static int recover_data(struct f2fs_sb_info *sbi, struct list_head *inode_list,
 		 * In this case, we can lose the latest inode(x).
 		 * So, call recover_inode for the inode update.
 		 */
-		if (IS_INODE(&folio->page)) {
+		if (IS_INODE(folio)) {
 			err = recover_inode(entry->inode, folio);
 			if (err) {
 				f2fs_folio_put(folio, true);
diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
index 25857877eaec..2f8b8bfc0e73 100644
--- a/include/linux/f2fs_fs.h
+++ b/include/linux/f2fs_fs.h
@@ -268,7 +268,7 @@ struct node_footer {
 /* Node IDs in an Indirect Block */
 #define NIDS_PER_BLOCK		((F2FS_BLKSIZE - sizeof(struct node_footer)) / sizeof(__le32))
 
-#define ADDRS_PER_PAGE(folio, inode)	(addrs_per_page(inode, IS_INODE(&folio->page)))
+#define ADDRS_PER_PAGE(folio, inode)	(addrs_per_page(inode, IS_INODE(folio)))
 
 #define	NODE_DIR1_BLOCK		(DEF_ADDRS_PER_INODE + 1)
 #define	NODE_DIR2_BLOCK		(DEF_ADDRS_PER_INODE + 2)
-- 
cgit v1.2.3


From a824388d911927b2a82bf7dcfd7cef6ee45c8b43 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Tue, 8 Jul 2025 18:03:36 +0100
Subject: f2fs: Use a folio in f2fs_is_cp_guaranteed()

Convert the passed page to a folio and use it throughout.  Removes
a use of fscrypt_is_bounce_page(), which we're trying to remove.

Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: Chao Yu <chao@kernel.org>
Signed-off-by: Jaegeuk Kim <jaegeuk@kernel.org>
---
 fs/f2fs/data.c          | 11 ++++++-----
 fs/f2fs/f2fs.h          |  2 +-
 include/linux/fscrypt.h | 10 ++++++----
 3 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index f3e11f5672ec..c1fc8c7b1256 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -47,14 +47,15 @@ void f2fs_destroy_bioset(void)
 	bioset_exit(&f2fs_bioset);
 }
 
-bool f2fs_is_cp_guaranteed(struct page *page)
+bool f2fs_is_cp_guaranteed(const struct page *page)
 {
-	struct address_space *mapping = page_folio(page)->mapping;
+	const struct folio *folio = page_folio(page);
+	struct address_space *mapping = folio->mapping;
 	struct inode *inode;
 	struct f2fs_sb_info *sbi;
 
-	if (fscrypt_is_bounce_page(page))
-		return page_private_gcing(fscrypt_pagecache_page(page));
+	if (fscrypt_is_bounce_folio(folio))
+		return folio_test_f2fs_gcing(fscrypt_pagecache_folio(folio));
 
 	inode = mapping->host;
 	sbi = F2FS_I_SB(inode);
@@ -65,7 +66,7 @@ bool f2fs_is_cp_guaranteed(struct page *page)
 		return true;
 
 	if ((S_ISREG(inode->i_mode) && IS_NOQUOTA(inode)) ||
-			page_private_gcing(page))
+			folio_test_f2fs_gcing(folio))
 		return true;
 	return false;
 }
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 0e607305e308..be9b7a0120a9 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -3990,7 +3990,7 @@ void f2fs_init_ckpt_req_control(struct f2fs_sb_info *sbi);
  */
 int __init f2fs_init_bioset(void);
 void f2fs_destroy_bioset(void);
-bool f2fs_is_cp_guaranteed(struct page *page);
+bool f2fs_is_cp_guaranteed(const struct page *page);
 int f2fs_init_bio_entry_cache(void);
 void f2fs_destroy_bio_entry_cache(void);
 void f2fs_submit_read_bio(struct f2fs_sb_info *sbi, struct bio *bio,
diff --git a/include/linux/fscrypt.h b/include/linux/fscrypt.h
index 56fad33043d5..8d9127a0fdb3 100644
--- a/include/linux/fscrypt.h
+++ b/include/linux/fscrypt.h
@@ -332,12 +332,13 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
 	return (struct page *)page_private(bounce_page);
 }
 
-static inline bool fscrypt_is_bounce_folio(struct folio *folio)
+static inline bool fscrypt_is_bounce_folio(const struct folio *folio)
 {
 	return folio->mapping == NULL;
 }
 
-static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio)
+static inline
+struct folio *fscrypt_pagecache_folio(const struct folio *bounce_folio)
 {
 	return bounce_folio->private;
 }
@@ -518,12 +519,13 @@ static inline struct page *fscrypt_pagecache_page(struct page *bounce_page)
 	return ERR_PTR(-EINVAL);
 }
 
-static inline bool fscrypt_is_bounce_folio(struct folio *folio)
+static inline bool fscrypt_is_bounce_folio(const struct folio *folio)
 {
 	return false;
 }
 
-static inline struct folio *fscrypt_pagecache_folio(struct folio *bounce_folio)
+static inline
+struct folio *fscrypt_pagecache_folio(const struct folio *bounce_folio)
 {
 	WARN_ON_ONCE(1);
 	return ERR_PTR(-EINVAL);
-- 
cgit v1.2.3


From e612423be33465d2b9822bf09e03d4e6c165e384 Mon Sep 17 00:00:00 2001
From: Marc Zyngier <maz@kernel.org>
Date: Tue, 8 Jul 2025 18:34:04 +0100
Subject: cpu/hotplug: Remove unused cpuhp_state CPUHP_PCI_XGENE_DEAD

Now that the XGene MSI driver has been mostly rewritten and doesn't
use the CPU hotplug infrastructure, CPUHP_PCI_XGENE_DEAD is unused.

Remove it to reduce the size of cpuhp_hp_states[].

Signed-off-by: Marc Zyngier <maz@kernel.org>
Signed-off-by: Lorenzo Pieralisi <lpieralisi@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://lore.kernel.org/r/20250708173404.1278635-14-maz@kernel.org
---
 include/linux/cpuhotplug.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index df366ee15456..eaca70eb6136 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -90,7 +90,6 @@ enum cpuhp_state {
 	CPUHP_RADIX_DEAD,
 	CPUHP_PAGE_ALLOC,
 	CPUHP_NET_DEV_DEAD,
-	CPUHP_PCI_XGENE_DEAD,
 	CPUHP_IOMMU_IOVA_DEAD,
 	CPUHP_AP_ARM_CACHE_B15_RAC_DEAD,
 	CPUHP_PADATA_DEAD,
-- 
cgit v1.2.3


From 07d8004d6fb95cbe48918e56012f16454cfdfe89 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 20 Jun 2025 15:08:07 +0200
Subject: tpm: add bufsiz parameter in the .send callback

Add a new `bufsiz` parameter to the `.send` callback in `tpm_class_ops`.
This parameter will allow drivers to differentiate between the actual
command length to send and the total buffer size. Currently `bufsiz` is
not used, but it will be used to implement devices with synchronous send()
to send the command and receive the response on the same buffer.

Also rename the previous parameter `len` to `cmd_len` in the declaration
to make it clear that it contains the length in bytes of the command
stored in the buffer. The semantics don't change and it can be used as
before by drivers. This is an optimization since the drivers could get it
from the header, but let's avoid duplicating code.

While we are here, resolve a checkpatch warning:
  WARNING: Unnecessary space before function pointer arguments
  #66: FILE: include/linux/tpm.h:90:
  +	int (*send) (struct tpm_chip *chip, u8 *buf, size_t bufsiz,

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Suggested-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/st33zp24/st33zp24.c | 2 +-
 drivers/char/tpm/tpm-interface.c     | 2 +-
 drivers/char/tpm/tpm_atmel.c         | 3 ++-
 drivers/char/tpm/tpm_crb.c           | 2 +-
 drivers/char/tpm/tpm_ftpm_tee.c      | 4 +++-
 drivers/char/tpm/tpm_i2c_atmel.c     | 3 ++-
 drivers/char/tpm/tpm_i2c_infineon.c  | 3 ++-
 drivers/char/tpm/tpm_i2c_nuvoton.c   | 3 ++-
 drivers/char/tpm/tpm_ibmvtpm.c       | 6 ++++--
 drivers/char/tpm/tpm_infineon.c      | 3 ++-
 drivers/char/tpm/tpm_nsc.c           | 3 ++-
 drivers/char/tpm/tpm_svsm.c          | 3 ++-
 drivers/char/tpm/tpm_tis_core.c      | 3 ++-
 drivers/char/tpm/tpm_tis_i2c_cr50.c  | 6 ++++--
 drivers/char/tpm/tpm_vtpm_proxy.c    | 4 +++-
 drivers/char/tpm/xen-tpmfront.c      | 3 ++-
 include/linux/tpm.h                  | 3 ++-
 17 files changed, 37 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/tpm/st33zp24/st33zp24.c b/drivers/char/tpm/st33zp24/st33zp24.c
index c0771980bc2f..2ed7815e4899 100644
--- a/drivers/char/tpm/st33zp24/st33zp24.c
+++ b/drivers/char/tpm/st33zp24/st33zp24.c
@@ -300,7 +300,7 @@ static irqreturn_t tpm_ioserirq_handler(int irq, void *dev_id)
  * send TPM commands through the I2C bus.
  */
 static int st33zp24_send(struct tpm_chip *chip, unsigned char *buf,
-			 size_t len)
+			 size_t bufsiz, size_t len)
 {
 	struct st33zp24_dev *tpm_dev = dev_get_drvdata(&chip->dev);
 	u32 status, i, size, ordinal;
diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 8d7e4da6ed53..816b7c690bc9 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -106,7 +106,7 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip, void *buf, size_t bufsiz)
 		return -E2BIG;
 	}
 
-	rc = chip->ops->send(chip, buf, count);
+	rc = chip->ops->send(chip, buf, bufsiz, count);
 	if (rc < 0) {
 		if (rc != -EPIPE)
 			dev_err(&chip->dev,
diff --git a/drivers/char/tpm/tpm_atmel.c b/drivers/char/tpm/tpm_atmel.c
index 54a0360a3c95..f25faf468bba 100644
--- a/drivers/char/tpm/tpm_atmel.c
+++ b/drivers/char/tpm/tpm_atmel.c
@@ -148,7 +148,8 @@ static int tpm_atml_recv(struct tpm_chip *chip, u8 *buf, size_t count)
 	return size;
 }
 
-static int tpm_atml_send(struct tpm_chip *chip, u8 *buf, size_t count)
+static int tpm_atml_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			 size_t count)
 {
 	struct tpm_atmel_priv *priv = dev_get_drvdata(&chip->dev);
 	int i;
diff --git a/drivers/char/tpm/tpm_crb.c b/drivers/char/tpm/tpm_crb.c
index 876edf2705ab..ed97344f2324 100644
--- a/drivers/char/tpm/tpm_crb.c
+++ b/drivers/char/tpm/tpm_crb.c
@@ -426,7 +426,7 @@ static int tpm_crb_smc_start(struct device *dev, unsigned long func_id)
 }
 #endif
 
-static int crb_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int crb_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz, size_t len)
 {
 	struct crb_priv *priv = dev_get_drvdata(&chip->dev);
 	int rc = 0;
diff --git a/drivers/char/tpm/tpm_ftpm_tee.c b/drivers/char/tpm/tpm_ftpm_tee.c
index 53ba28ccd5d3..dbad83bf798e 100644
--- a/drivers/char/tpm/tpm_ftpm_tee.c
+++ b/drivers/char/tpm/tpm_ftpm_tee.c
@@ -63,13 +63,15 @@ static int ftpm_tee_tpm_op_recv(struct tpm_chip *chip, u8 *buf, size_t count)
  * ftpm_tee_tpm_op_send() - send TPM commands through the TEE shared memory.
  * @chip:	the tpm_chip description as specified in driver/char/tpm/tpm.h
  * @buf:	the buffer to send.
+ * @bufsiz:	the size of the buffer.
  * @len:	the number of bytes to send.
  *
  * Return:
  *	In case of success, returns 0.
  *	On failure, -errno
  */
-static int ftpm_tee_tpm_op_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int ftpm_tee_tpm_op_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+				size_t len)
 {
 	struct ftpm_tee_private *pvt_data = dev_get_drvdata(chip->dev.parent);
 	size_t resp_len;
diff --git a/drivers/char/tpm/tpm_i2c_atmel.c b/drivers/char/tpm/tpm_i2c_atmel.c
index d1d27fdfe523..4f229656a8e2 100644
--- a/drivers/char/tpm/tpm_i2c_atmel.c
+++ b/drivers/char/tpm/tpm_i2c_atmel.c
@@ -37,7 +37,8 @@ struct priv_data {
 	u8 buffer[sizeof(struct tpm_header) + 25];
 };
 
-static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int i2c_atmel_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			  size_t len)
 {
 	struct priv_data *priv = dev_get_drvdata(&chip->dev);
 	struct i2c_client *client = to_i2c_client(chip->dev.parent);
diff --git a/drivers/char/tpm/tpm_i2c_infineon.c b/drivers/char/tpm/tpm_i2c_infineon.c
index 81d8a78dc655..bdf1f329a679 100644
--- a/drivers/char/tpm/tpm_i2c_infineon.c
+++ b/drivers/char/tpm/tpm_i2c_infineon.c
@@ -514,7 +514,8 @@ out:
 	return size;
 }
 
-static int tpm_tis_i2c_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_tis_i2c_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			    size_t len)
 {
 	int rc, status;
 	ssize_t burstcnt;
diff --git a/drivers/char/tpm/tpm_i2c_nuvoton.c b/drivers/char/tpm/tpm_i2c_nuvoton.c
index 3c3ee5f551db..d44903b29929 100644
--- a/drivers/char/tpm/tpm_i2c_nuvoton.c
+++ b/drivers/char/tpm/tpm_i2c_nuvoton.c
@@ -350,7 +350,8 @@ static int i2c_nuvoton_recv(struct tpm_chip *chip, u8 *buf, size_t count)
  * tpm.c can skip polling for the data to be available as the interrupt is
  * waited for here
  */
-static int i2c_nuvoton_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int i2c_nuvoton_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			    size_t len)
 {
 	struct priv_data *priv = dev_get_drvdata(&chip->dev);
 	struct device *dev = chip->dev.parent;
diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
index 76d048f63d55..4734a69406ce 100644
--- a/drivers/char/tpm/tpm_ibmvtpm.c
+++ b/drivers/char/tpm/tpm_ibmvtpm.c
@@ -191,13 +191,15 @@ static int tpm_ibmvtpm_resume(struct device *dev)
  * tpm_ibmvtpm_send() - Send a TPM command
  * @chip:	tpm chip struct
  * @buf:	buffer contains data to send
- * @count:	size of buffer
+ * @bufsiz:	size of the buffer
+ * @count:	length of the command
  *
  * Return:
  *   0 on success,
  *   -errno on error
  */
-static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
+static int tpm_ibmvtpm_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			    size_t count)
 {
 	struct ibmvtpm_dev *ibmvtpm = dev_get_drvdata(&chip->dev);
 	bool retry = true;
diff --git a/drivers/char/tpm/tpm_infineon.c b/drivers/char/tpm/tpm_infineon.c
index 2d2ae37153ba..7638b65b851b 100644
--- a/drivers/char/tpm/tpm_infineon.c
+++ b/drivers/char/tpm/tpm_infineon.c
@@ -312,7 +312,8 @@ recv_begin:
 	return -EIO;
 }
 
-static int tpm_inf_send(struct tpm_chip *chip, u8 * buf, size_t count)
+static int tpm_inf_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			size_t count)
 {
 	int i;
 	int ret;
diff --git a/drivers/char/tpm/tpm_nsc.c b/drivers/char/tpm/tpm_nsc.c
index 0f62bbc940da..879ac88f5783 100644
--- a/drivers/char/tpm/tpm_nsc.c
+++ b/drivers/char/tpm/tpm_nsc.c
@@ -178,7 +178,8 @@ static int tpm_nsc_recv(struct tpm_chip *chip, u8 * buf, size_t count)
 	return size;
 }
 
-static int tpm_nsc_send(struct tpm_chip *chip, u8 * buf, size_t count)
+static int tpm_nsc_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			size_t count)
 {
 	struct tpm_nsc_priv *priv = dev_get_drvdata(&chip->dev);
 	u8 data;
diff --git a/drivers/char/tpm/tpm_svsm.c b/drivers/char/tpm/tpm_svsm.c
index 4280edf427d6..0847cbf450b4 100644
--- a/drivers/char/tpm/tpm_svsm.c
+++ b/drivers/char/tpm/tpm_svsm.c
@@ -25,7 +25,8 @@ struct tpm_svsm_priv {
 	void *buffer;
 };
 
-static int tpm_svsm_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_svsm_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			 size_t len)
 {
 	struct tpm_svsm_priv *priv = dev_get_drvdata(&chip->dev);
 	int ret;
diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index ed0d3d8449b3..4b12c4b9da8b 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -580,7 +580,8 @@ out_err:
 	return rc;
 }
 
-static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_tis_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+			size_t len)
 {
 	int rc, irq;
 	struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
diff --git a/drivers/char/tpm/tpm_tis_i2c_cr50.c b/drivers/char/tpm/tpm_tis_i2c_cr50.c
index 3b55a7b05c46..fc6891a0b693 100644
--- a/drivers/char/tpm/tpm_tis_i2c_cr50.c
+++ b/drivers/char/tpm/tpm_tis_i2c_cr50.c
@@ -546,13 +546,15 @@ out_err:
  * tpm_cr50_i2c_tis_send() - TPM transmission callback.
  * @chip:	A TPM chip.
  * @buf:	Buffer to send.
- * @len:	Buffer length.
+ * @bufsiz:	Buffer size.
+ * @len:	Command length.
  *
  * Return:
  * - 0:		Success.
  * - -errno:	A POSIX error code.
  */
-static int tpm_cr50_i2c_tis_send(struct tpm_chip *chip, u8 *buf, size_t len)
+static int tpm_cr50_i2c_tis_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+				 size_t len)
 {
 	size_t burstcnt, limit, sent = 0;
 	u8 tpm_go[4] = { TPM_STS_GO };
diff --git a/drivers/char/tpm/tpm_vtpm_proxy.c b/drivers/char/tpm/tpm_vtpm_proxy.c
index 8fe4a01eea12..0818bb517805 100644
--- a/drivers/char/tpm/tpm_vtpm_proxy.c
+++ b/drivers/char/tpm/tpm_vtpm_proxy.c
@@ -321,12 +321,14 @@ static int vtpm_proxy_is_driver_command(struct tpm_chip *chip,
  *
  * @chip: tpm chip to use
  * @buf: send buffer
+ * @bufsiz: size of the buffer
  * @count: bytes to send
  *
  * Return:
  *      0 in case of success, negative error value otherwise.
  */
-static int vtpm_proxy_tpm_op_send(struct tpm_chip *chip, u8 *buf, size_t count)
+static int vtpm_proxy_tpm_op_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+				  size_t count)
 {
 	struct proxy_dev *proxy_dev = dev_get_drvdata(&chip->dev);
 
diff --git a/drivers/char/tpm/xen-tpmfront.c b/drivers/char/tpm/xen-tpmfront.c
index 80cca3b83b22..556bf2256716 100644
--- a/drivers/char/tpm/xen-tpmfront.c
+++ b/drivers/char/tpm/xen-tpmfront.c
@@ -131,7 +131,8 @@ static size_t shr_data_offset(struct vtpm_shared_page *shr)
 	return struct_size(shr, extra_pages, shr->nr_extra_pages);
 }
 
-static int vtpm_send(struct tpm_chip *chip, u8 *buf, size_t count)
+static int vtpm_send(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+		     size_t count)
 {
 	struct tpm_private *priv = dev_get_drvdata(&chip->dev);
 	struct vtpm_shared_page *shr = priv->shr;
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index a3d8305e88a5..cafe8c283e88 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -87,7 +87,8 @@ struct tpm_class_ops {
 	const u8 req_complete_val;
 	bool (*req_canceled)(struct tpm_chip *chip, u8 status);
 	int (*recv) (struct tpm_chip *chip, u8 *buf, size_t len);
-	int (*send) (struct tpm_chip *chip, u8 *buf, size_t len);
+	int (*send)(struct tpm_chip *chip, u8 *buf, size_t bufsiz,
+		    size_t cmd_len);
 	void (*cancel) (struct tpm_chip *chip);
 	u8 (*status) (struct tpm_chip *chip);
 	void (*update_timeouts)(struct tpm_chip *chip,
-- 
cgit v1.2.3


From 04fe47015d7726b42c34615c124697c7a3537bf0 Mon Sep 17 00:00:00 2001
From: Stefano Garzarella <sgarzare@redhat.com>
Date: Fri, 20 Jun 2025 15:08:08 +0200
Subject: tpm: support devices with synchronous send()

Some devices do not support interrupts and provide a single synchronous
operation to send the command and receive the response on the same buffer.

Currently, these types of drivers must use an internal buffer where they
temporarily store the response between .send() and .recv() calls.

Introduce a new flag (TPM_CHIP_FLAG_SYNC) to support synchronous send().
If that flag is set by the driver, tpm_try_transmit() will use the send()
callback to send the command and receive the response on the same buffer
synchronously. In that case send() return the number of bytes of the
response on success, or -errno on failure.

Signed-off-by: Stefano Garzarella <sgarzare@redhat.com>
Suggested-by: Jason Gunthorpe <jgg@ziepe.ca>
Suggested-by: Jarkko Sakkinen <jarkko@kernel.org>
Reviewed-by: Jarkko Sakkinen <jarkko@kernel.org>
Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
 drivers/char/tpm/tpm-interface.c | 20 +++++++++++++++++---
 include/linux/tpm.h              |  1 +
 2 files changed, 18 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/char/tpm/tpm-interface.c b/drivers/char/tpm/tpm-interface.c
index 816b7c690bc9..512882ac0db1 100644
--- a/drivers/char/tpm/tpm-interface.c
+++ b/drivers/char/tpm/tpm-interface.c
@@ -114,8 +114,19 @@ static ssize_t tpm_try_transmit(struct tpm_chip *chip, void *buf, size_t bufsiz)
 		return rc;
 	}
 
-	/* A sanity check. send() should just return zero on success e.g.
-	 * not the command length.
+	/*
+	 * Synchronous devices return the response directly during the send()
+	 * call in the same buffer.
+	 */
+	if (chip->flags & TPM_CHIP_FLAG_SYNC) {
+		len = rc;
+		rc = 0;
+		goto out_sync;
+	}
+
+	/*
+	 * A sanity check. send() of asynchronous devices should just return
+	 * zero on success e.g. not the command length.
 	 */
 	if (rc > 0) {
 		dev_warn(&chip->dev,
@@ -151,7 +162,10 @@ out_recv:
 	if (len < 0) {
 		rc = len;
 		dev_err(&chip->dev, "tpm_transmit: tpm_recv: error %d\n", rc);
-	} else if (len < TPM_HEADER_SIZE || len != be32_to_cpu(header->length))
+		return rc;
+	}
+out_sync:
+	if (len < TPM_HEADER_SIZE || len != be32_to_cpu(header->length))
 		rc = -EFAULT;
 
 	return rc ? rc : len;
diff --git a/include/linux/tpm.h b/include/linux/tpm.h
index cafe8c283e88..804fbbe3873d 100644
--- a/include/linux/tpm.h
+++ b/include/linux/tpm.h
@@ -351,6 +351,7 @@ enum tpm_chip_flags {
 	TPM_CHIP_FLAG_SUSPENDED			= BIT(8),
 	TPM_CHIP_FLAG_HWRNG_DISABLED		= BIT(9),
 	TPM_CHIP_FLAG_DISABLE			= BIT(10),
+	TPM_CHIP_FLAG_SYNC			= BIT(11),
 };
 
 #define to_tpm_chip(d) container_of(d, struct tpm_chip, dev)
-- 
cgit v1.2.3


From 119a5d573622ae90ba730d18acfae9bb75d77b9a Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Mon, 30 Jun 2025 18:04:40 -0400
Subject: ring-buffer: Remove ring_buffer_read_prepare_sync()

When the ring buffer was first introduced, reading the non-consuming
"trace" file required disabling the writing of the ring buffer. To make
sure the writing was fully disabled before iterating the buffer with a
non-consuming read, it would set the disable flag of the buffer and then
call an RCU synchronization to make sure all the buffers were
synchronized.

The function ring_buffer_read_start() originally  would initialize the
iterator and call an RCU synchronization, but this was for each individual
per CPU buffer where this would get called many times on a machine with
many CPUs before the trace file could be read. The commit 72c9ddfd4c5bf
("ring-buffer: Make non-consuming read less expensive with lots of cpus.")
separated ring_buffer_read_start into ring_buffer_read_prepare(),
ring_buffer_read_sync() and then ring_buffer_read_start() to allow each of
the per CPU buffers to be prepared, call the read_buffer_read_sync() once,
and then the ring_buffer_read_start() for each of the CPUs which made
things much faster.

The commit 1039221cc278 ("ring-buffer: Do not disable recording when there
is an iterator") removed the requirement of disabling the recording of the
ring buffer in order to iterate it, but it did not remove the
synchronization that was happening that was required to wait for all the
buffers to have no more writers. It's now OK for the buffers to have
writers and no synchronization is needed.

Remove the synchronization and put back the interface for the ring buffer
iterator back before commit 72c9ddfd4c5bf was applied.

Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/20250630180440.3eabb514@batman.local.home
Reported-by: David Howells <dhowells@redhat.com>
Fixes: 1039221cc278 ("ring-buffer: Do not disable recording when there is an iterator")
Tested-by: David Howells <dhowells@redhat.com>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h |  4 +--
 kernel/trace/ring_buffer.c  | 63 +++++++--------------------------------------
 kernel/trace/trace.c        | 14 +++-------
 kernel/trace/trace_kdb.c    |  8 +++---
 4 files changed, 18 insertions(+), 71 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index cd7f0ae26615..bc90c3c7b5fd 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -152,9 +152,7 @@ ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts,
 		    unsigned long *lost_events);
 
 struct ring_buffer_iter *
-ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags);
-void ring_buffer_read_prepare_sync(void);
-void ring_buffer_read_start(struct ring_buffer_iter *iter);
+ring_buffer_read_start(struct trace_buffer *buffer, int cpu, gfp_t flags);
 void ring_buffer_read_finish(struct ring_buffer_iter *iter);
 
 struct ring_buffer_event *
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index a99ed4716de9..903d9db75e12 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -5943,24 +5943,20 @@ ring_buffer_consume(struct trace_buffer *buffer, int cpu, u64 *ts,
 EXPORT_SYMBOL_GPL(ring_buffer_consume);
 
 /**
- * ring_buffer_read_prepare - Prepare for a non consuming read of the buffer
+ * ring_buffer_read_start - start a non consuming read of the buffer
  * @buffer: The ring buffer to read from
  * @cpu: The cpu buffer to iterate over
  * @flags: gfp flags to use for memory allocation
  *
- * This performs the initial preparations necessary to iterate
- * through the buffer.  Memory is allocated, buffer resizing
- * is disabled, and the iterator pointer is returned to the caller.
- *
- * After a sequence of ring_buffer_read_prepare calls, the user is
- * expected to make at least one call to ring_buffer_read_prepare_sync.
- * Afterwards, ring_buffer_read_start is invoked to get things going
- * for real.
+ * This creates an iterator to allow non-consuming iteration through
+ * the buffer. If the buffer is disabled for writing, it will produce
+ * the same information each time, but if the buffer is still writing
+ * then the first hit of a write will cause the iteration to stop.
  *
- * This overall must be paired with ring_buffer_read_finish.
+ * Must be paired with ring_buffer_read_finish.
  */
 struct ring_buffer_iter *
-ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
+ring_buffer_read_start(struct trace_buffer *buffer, int cpu, gfp_t flags)
 {
 	struct ring_buffer_per_cpu *cpu_buffer;
 	struct ring_buffer_iter *iter;
@@ -5986,51 +5982,12 @@ ring_buffer_read_prepare(struct trace_buffer *buffer, int cpu, gfp_t flags)
 
 	atomic_inc(&cpu_buffer->resize_disabled);
 
-	return iter;
-}
-EXPORT_SYMBOL_GPL(ring_buffer_read_prepare);
-
-/**
- * ring_buffer_read_prepare_sync - Synchronize a set of prepare calls
- *
- * All previously invoked ring_buffer_read_prepare calls to prepare
- * iterators will be synchronized.  Afterwards, read_buffer_read_start
- * calls on those iterators are allowed.
- */
-void
-ring_buffer_read_prepare_sync(void)
-{
-	synchronize_rcu();
-}
-EXPORT_SYMBOL_GPL(ring_buffer_read_prepare_sync);
-
-/**
- * ring_buffer_read_start - start a non consuming read of the buffer
- * @iter: The iterator returned by ring_buffer_read_prepare
- *
- * This finalizes the startup of an iteration through the buffer.
- * The iterator comes from a call to ring_buffer_read_prepare and
- * an intervening ring_buffer_read_prepare_sync must have been
- * performed.
- *
- * Must be paired with ring_buffer_read_finish.
- */
-void
-ring_buffer_read_start(struct ring_buffer_iter *iter)
-{
-	struct ring_buffer_per_cpu *cpu_buffer;
-	unsigned long flags;
-
-	if (!iter)
-		return;
-
-	cpu_buffer = iter->cpu_buffer;
-
-	raw_spin_lock_irqsave(&cpu_buffer->reader_lock, flags);
+	guard(raw_spinlock_irqsave)(&cpu_buffer->reader_lock);
 	arch_spin_lock(&cpu_buffer->lock);
 	rb_iter_reset(iter);
 	arch_spin_unlock(&cpu_buffer->lock);
-	raw_spin_unlock_irqrestore(&cpu_buffer->reader_lock, flags);
+
+	return iter;
 }
 EXPORT_SYMBOL_GPL(ring_buffer_read_start);
 
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 95ae7c4e5835..7996f26c3f46 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -4735,21 +4735,15 @@ __tracing_open(struct inode *inode, struct file *file, bool snapshot)
 	if (iter->cpu_file == RING_BUFFER_ALL_CPUS) {
 		for_each_tracing_cpu(cpu) {
 			iter->buffer_iter[cpu] =
-				ring_buffer_read_prepare(iter->array_buffer->buffer,
-							 cpu, GFP_KERNEL);
-		}
-		ring_buffer_read_prepare_sync();
-		for_each_tracing_cpu(cpu) {
-			ring_buffer_read_start(iter->buffer_iter[cpu]);
+				ring_buffer_read_start(iter->array_buffer->buffer,
+						       cpu, GFP_KERNEL);
 			tracing_iter_reset(iter, cpu);
 		}
 	} else {
 		cpu = iter->cpu_file;
 		iter->buffer_iter[cpu] =
-			ring_buffer_read_prepare(iter->array_buffer->buffer,
-						 cpu, GFP_KERNEL);
-		ring_buffer_read_prepare_sync();
-		ring_buffer_read_start(iter->buffer_iter[cpu]);
+			ring_buffer_read_start(iter->array_buffer->buffer,
+					       cpu, GFP_KERNEL);
 		tracing_iter_reset(iter, cpu);
 	}
 
diff --git a/kernel/trace/trace_kdb.c b/kernel/trace/trace_kdb.c
index d7b135de958a..896ff78b8349 100644
--- a/kernel/trace/trace_kdb.c
+++ b/kernel/trace/trace_kdb.c
@@ -43,17 +43,15 @@ static void ftrace_dump_buf(int skip_entries, long cpu_file)
 	if (cpu_file == RING_BUFFER_ALL_CPUS) {
 		for_each_tracing_cpu(cpu) {
 			iter.buffer_iter[cpu] =
-			ring_buffer_read_prepare(iter.array_buffer->buffer,
-						 cpu, GFP_ATOMIC);
-			ring_buffer_read_start(iter.buffer_iter[cpu]);
+			ring_buffer_read_start(iter.array_buffer->buffer,
+					       cpu, GFP_ATOMIC);
 			tracing_iter_reset(&iter, cpu);
 		}
 	} else {
 		iter.cpu_file = cpu_file;
 		iter.buffer_iter[cpu_file] =
-			ring_buffer_read_prepare(iter.array_buffer->buffer,
+			ring_buffer_read_start(iter.array_buffer->buffer,
 						 cpu_file, GFP_ATOMIC);
-		ring_buffer_read_start(iter.buffer_iter[cpu_file]);
 		tracing_iter_reset(&iter, cpu_file);
 	}
 
-- 
cgit v1.2.3


From 07c3f391bcb217b6949b49785ccb5fee02be21fe Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Wed, 2 Jul 2025 14:36:57 -0400
Subject: tracing: Remove EVENT_FILE_FL_SOFT_MODE flag

When soft disabling of trace events was first created, it needed to have a
way to know if a file had a user that was using it with soft disabled (for
triggers that need to enable or disable events from a context that can not
really enable or disable the event, it would set SOFT_DISABLED to state it
is disabled). The flag SOFT_MODE was used to denote that an event had a
user that would enable or disable it via the SOFT_DISABLED flag.

Commit 1cf4c0732db3c ("tracing: Modify soft-mode only if there's no other
referrer") fixed a bug where if two users were using the SOFT_DISABLED
flag the accounting would get messed up as the SOFT_MODE flag could only
handle one user. That commit added the sm_ref counter which kept track of
how many users were using the event in "soft mode". This made the
SOFT_MODE flag redundant as it should only be set if the sm_ref counter is
non zero.

Remove the SOFT_MODE flag and just use the sm_ref counter to know the
event is in soft mode or not. This makes the code a bit simpler.

Link: https://lore.kernel.org/all/20250702111908.03759998@batman.local.home/

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Gabriele Paoloni <gpaoloni@redhat.com>
Link: https://lore.kernel.org/20250702143657.18dd1882@batman.local.home
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/trace_events.h |  3 ---
 kernel/trace/trace_events.c  | 24 ++++++++++++------------
 2 files changed, 12 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
index fa9cf4292dff..04307a19cde3 100644
--- a/include/linux/trace_events.h
+++ b/include/linux/trace_events.h
@@ -480,7 +480,6 @@ enum {
 	EVENT_FILE_FL_RECORDED_TGID_BIT,
 	EVENT_FILE_FL_FILTERED_BIT,
 	EVENT_FILE_FL_NO_SET_FILTER_BIT,
-	EVENT_FILE_FL_SOFT_MODE_BIT,
 	EVENT_FILE_FL_SOFT_DISABLED_BIT,
 	EVENT_FILE_FL_TRIGGER_MODE_BIT,
 	EVENT_FILE_FL_TRIGGER_COND_BIT,
@@ -618,7 +617,6 @@ extern int __kprobe_event_add_fields(struct dynevent_cmd *cmd, ...);
  *  RECORDED_TGID - The tgids should be recorded at sched_switch
  *  FILTERED	  - The event has a filter attached
  *  NO_SET_FILTER - Set when filter has error and is to be ignored
- *  SOFT_MODE     - The event is enabled/disabled by SOFT_DISABLED
  *  SOFT_DISABLED - When set, do not trace the event (even though its
  *                   tracepoint may be enabled)
  *  TRIGGER_MODE  - When set, invoke the triggers associated with the event
@@ -633,7 +631,6 @@ enum {
 	EVENT_FILE_FL_RECORDED_TGID	= (1 << EVENT_FILE_FL_RECORDED_TGID_BIT),
 	EVENT_FILE_FL_FILTERED		= (1 << EVENT_FILE_FL_FILTERED_BIT),
 	EVENT_FILE_FL_NO_SET_FILTER	= (1 << EVENT_FILE_FL_NO_SET_FILTER_BIT),
-	EVENT_FILE_FL_SOFT_MODE		= (1 << EVENT_FILE_FL_SOFT_MODE_BIT),
 	EVENT_FILE_FL_SOFT_DISABLED	= (1 << EVENT_FILE_FL_SOFT_DISABLED_BIT),
 	EVENT_FILE_FL_TRIGGER_MODE	= (1 << EVENT_FILE_FL_TRIGGER_MODE_BIT),
 	EVENT_FILE_FL_TRIGGER_COND	= (1 << EVENT_FILE_FL_TRIGGER_COND_BIT),
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 120531268abf..0980f4def360 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -768,6 +768,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 {
 	struct trace_event_call *call = file->event_call;
 	struct trace_array *tr = file->tr;
+	bool soft_mode = atomic_read(&file->sm_ref) != 0;
 	int ret = 0;
 	int disable;
 
@@ -782,7 +783,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		 * is set we do not want the event to be enabled before we
 		 * clear the bit.
 		 *
-		 * When soft_disable is not set but the SOFT_MODE flag is,
+		 * When soft_disable is not set but the soft_mode is,
 		 * we do nothing. Do not disable the tracepoint, otherwise
 		 * "soft enable"s (clearing the SOFT_DISABLED bit) wont work.
 		 */
@@ -790,11 +791,11 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 			if (atomic_dec_return(&file->sm_ref) > 0)
 				break;
 			disable = file->flags & EVENT_FILE_FL_SOFT_DISABLED;
-			clear_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+			soft_mode = false;
 			/* Disable use of trace_buffered_event */
 			trace_buffered_event_disable();
 		} else
-			disable = !(file->flags & EVENT_FILE_FL_SOFT_MODE);
+			disable = !soft_mode;
 
 		if (disable && (file->flags & EVENT_FILE_FL_ENABLED)) {
 			clear_bit(EVENT_FILE_FL_ENABLED_BIT, &file->flags);
@@ -812,8 +813,8 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 
 			WARN_ON_ONCE(ret);
 		}
-		/* If in SOFT_MODE, just set the SOFT_DISABLE_BIT, else clear it */
-		if (file->flags & EVENT_FILE_FL_SOFT_MODE)
+		/* If in soft mode, just set the SOFT_DISABLE_BIT, else clear it */
+		if (soft_mode)
 			set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
 		else
 			clear_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
@@ -823,7 +824,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		 * When soft_disable is set and enable is set, we want to
 		 * register the tracepoint for the event, but leave the event
 		 * as is. That means, if the event was already enabled, we do
-		 * nothing (but set SOFT_MODE). If the event is disabled, we
+		 * nothing (but set soft_mode). If the event is disabled, we
 		 * set SOFT_DISABLED before enabling the event tracepoint, so
 		 * it still seems to be disabled.
 		 */
@@ -832,7 +833,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		else {
 			if (atomic_inc_return(&file->sm_ref) > 1)
 				break;
-			set_bit(EVENT_FILE_FL_SOFT_MODE_BIT, &file->flags);
+			soft_mode = true;
 			/* Enable use of trace_buffered_event */
 			trace_buffered_event_enable();
 		}
@@ -840,7 +841,7 @@ static int __ftrace_event_enable_disable(struct trace_event_file *file,
 		if (!(file->flags & EVENT_FILE_FL_ENABLED)) {
 			bool cmd = false, tgid = false;
 
-			/* Keep the event disabled, when going to SOFT_MODE. */
+			/* Keep the event disabled, when going to soft mode. */
 			if (soft_disable)
 				set_bit(EVENT_FILE_FL_SOFT_DISABLED_BIT, &file->flags);
 
@@ -1792,8 +1793,7 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
 	    !(flags & EVENT_FILE_FL_SOFT_DISABLED))
 		strcpy(buf, "1");
 
-	if (flags & EVENT_FILE_FL_SOFT_DISABLED ||
-	    flags & EVENT_FILE_FL_SOFT_MODE)
+	if (atomic_read(&file->sm_ref) != 0)
 		strcat(buf, "*");
 
 	strcat(buf, "\n");
@@ -3584,7 +3584,7 @@ static int probe_remove_event_call(struct trace_event_call *call)
 			continue;
 		/*
 		 * We can't rely on ftrace_event_enable_disable(enable => 0)
-		 * we are going to do, EVENT_FILE_FL_SOFT_MODE can suppress
+		 * we are going to do, soft mode can suppress
 		 * TRACE_REG_UNREGISTER.
 		 */
 		if (file->flags & EVENT_FILE_FL_ENABLED)
@@ -3997,7 +3997,7 @@ static int free_probe_data(void *data)
 
 	edata->ref--;
 	if (!edata->ref) {
-		/* Remove the SOFT_MODE flag */
+		/* Remove soft mode */
 		__ftrace_event_enable_disable(edata->file, 0, 1);
 		trace_event_put_ref(edata->file->event_call);
 		kfree(edata);
-- 
cgit v1.2.3


From 4d6d0a6263babf7c43faa55de4fa3c6637dec624 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 4 Jul 2025 10:48:38 -0400
Subject: tracing: Remove redundant config HAVE_FTRACE_MCOUNT_RECORD

Ftrace is tightly coupled with architecture specific code because it
requires the use of trampolines written in assembly. This means that when
a new feature or optimization is made, it must be done for all
architectures. To simplify the approach, CONFIG_HAVE_FTRACE_* configs are
added to denote which architecture has the new enhancement so that other
architectures can still function until they too have been updated.

The CONFIG_HAVE_FTRACE_MCOUNT was added to help simplify the
DYNAMIC_FTRACE work, but now every architecture that implements
DYNAMIC_FTRACE also has HAVE_FTRACE_MCOUNT set too, making it redundant
with the HAVE_DYNAMIC_FTRACE.

Remove the HAVE_FTRACE_MCOUNT config and use DYNAMIC_FTRACE directly where
applicable.

Link: https://lore.kernel.org/all/20250703154916.48e3ada7@gandalf.local.home/

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: https://lore.kernel.org/20250704104838.27a18690@gandalf.local.home
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 Documentation/trace/ftrace-design.rst | 12 ++++--------
 arch/arm/Kconfig                      |  1 -
 arch/arm64/Kconfig                    |  1 -
 arch/csky/Kconfig                     |  1 -
 arch/loongarch/Kconfig                |  1 -
 arch/microblaze/Kconfig               |  1 -
 arch/mips/Kconfig                     |  1 -
 arch/parisc/Kconfig                   |  1 -
 arch/powerpc/Kconfig                  |  1 -
 arch/riscv/Kconfig                    |  1 -
 arch/s390/Kconfig                     |  1 -
 arch/sh/Kconfig                       |  1 -
 arch/sparc/Kconfig                    |  1 -
 arch/x86/Kconfig                      |  1 -
 include/asm-generic/vmlinux.lds.h     |  2 +-
 include/linux/ftrace.h                |  2 +-
 include/linux/kernel.h                |  6 +++---
 include/linux/module.h                |  2 +-
 kernel/module/main.c                  |  2 +-
 kernel/trace/Kconfig                  | 18 ++++--------------
 kernel/trace/ftrace.c                 |  4 ----
 scripts/recordmcount.pl               |  2 +-
 22 files changed, 16 insertions(+), 47 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/trace/ftrace-design.rst b/Documentation/trace/ftrace-design.rst
index dc82d64b3a44..8f4fab3f9324 100644
--- a/Documentation/trace/ftrace-design.rst
+++ b/Documentation/trace/ftrace-design.rst
@@ -238,19 +238,15 @@ You need very few things to get the syscalls tracing in an arch.
   - Tag this arch as HAVE_SYSCALL_TRACEPOINTS.
 
 
-HAVE_FTRACE_MCOUNT_RECORD
--------------------------
+HAVE_DYNAMIC_FTRACE
+-------------------
 
 See scripts/recordmcount.pl for more info.  Just fill in the arch-specific
 details for how to locate the addresses of mcount call sites via objdump.
 This option doesn't make much sense without also implementing dynamic ftrace.
 
-
-HAVE_DYNAMIC_FTRACE
--------------------
-
-You will first need HAVE_FTRACE_MCOUNT_RECORD and HAVE_FUNCTION_TRACER, so
-scroll your reader back up if you got over eager.
+You will first need HAVE_FUNCTION_TRACER, so scroll your reader back up if you
+got over eager.
 
 Once those are out of the way, you will need to implement:
 	- asm/ftrace.h:
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 3072731fe09c..33cc9dbb7f68 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -107,7 +107,6 @@ config ARM
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS if (CPU_V6 || CPU_V6K || CPU_V7) && MMU
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST if ARM_LPAE
-	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
index 55fc331af337..f943a07db139 100644
--- a/arch/arm64/Kconfig
+++ b/arch/arm64/Kconfig
@@ -223,7 +223,6 @@ config ARM64
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_GUP_FAST
 	select HAVE_FTRACE_GRAPH_FUNC
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_FREGS
diff --git a/arch/csky/Kconfig b/arch/csky/Kconfig
index acc431c331b0..4331313a42ff 100644
--- a/arch/csky/Kconfig
+++ b/arch/csky/Kconfig
@@ -80,7 +80,6 @@ config CSKY
 	select HAVE_FUNCTION_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_ERROR_INJECTION
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_LZO
 	select HAVE_KERNEL_LZMA
diff --git a/arch/loongarch/Kconfig b/arch/loongarch/Kconfig
index 4b19f93379a1..bead8266dc5c 100644
--- a/arch/loongarch/Kconfig
+++ b/arch/loongarch/Kconfig
@@ -144,7 +144,6 @@ config LOONGARCH
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST
 	select HAVE_FTRACE_GRAPH_FUNC
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_FREGS
diff --git a/arch/microblaze/Kconfig b/arch/microblaze/Kconfig
index f18ec02ddeb2..484ebb3baedf 100644
--- a/arch/microblaze/Kconfig
+++ b/arch/microblaze/Kconfig
@@ -28,7 +28,6 @@ config MICROBLAZE
 	select HAVE_DEBUG_KMEMLEAK
 	select HAVE_DMA_CONTIGUOUS
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_PAGE_SIZE_4KB
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index 1e48184ecf1e..268730824f75 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -73,7 +73,6 @@ config MIPS
 	select HAVE_EBPF_JIT if !CPU_MICROMIPS
 	select HAVE_EXIT_THREAD
 	select HAVE_GUP_FAST
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
 	select HAVE_GCC_PLUGINS
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index fcc5973f7519..2efa4b08b7b8 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -81,7 +81,6 @@ config PARISC
 	select HAVE_KPROBES
 	select HAVE_KRETPROBES
 	select HAVE_DYNAMIC_FTRACE if $(cc-option,-fpatchable-function-entry=1,1)
-	select HAVE_FTRACE_MCOUNT_RECORD if HAVE_DYNAMIC_FTRACE
 	select FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY if DYNAMIC_FTRACE
 	select HAVE_KPROBES_ON_FTRACE
 	select HAVE_DYNAMIC_FTRACE_WITH_REGS
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index c3e0cc83f120..cb4fb8d73300 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -246,7 +246,6 @@ config PPC
 	select HAVE_EFFICIENT_UNALIGNED_ACCESS
 	select HAVE_GUP_FAST
 	select HAVE_FTRACE_GRAPH_FUNC
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_DESCRIPTORS	if PPC64_ELF_ABI_V1
 	select HAVE_FUNCTION_ERROR_INJECTION
diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index d71ea0f4466f..62ec265e2962 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -159,7 +159,6 @@ config RISCV
 	select HAVE_DYNAMIC_FTRACE_WITH_CALL_OPS if (DYNAMIC_FTRACE_WITH_ARGS && !CFI_CLANG)
 	select HAVE_DYNAMIC_FTRACE_WITH_ARGS if HAVE_DYNAMIC_FTRACE
 	select HAVE_FTRACE_GRAPH_FUNC
-	select HAVE_FTRACE_MCOUNT_RECORD if !XIP_KERNEL
 	select HAVE_FUNCTION_GRAPH_TRACER if HAVE_DYNAMIC_FTRACE_WITH_ARGS
 	select HAVE_FUNCTION_GRAPH_FREGS
 	select HAVE_FUNCTION_TRACER if !XIP_KERNEL
diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
index 0c16dc443e2f..d956e85f0465 100644
--- a/arch/s390/Kconfig
+++ b/arch/s390/Kconfig
@@ -199,7 +199,6 @@ config S390
 	select HAVE_GUP_FAST
 	select HAVE_FENTRY
 	select HAVE_FTRACE_GRAPH_FUNC
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_ARG_ACCESS_API
 	select HAVE_FUNCTION_ERROR_INJECTION
 	select HAVE_FUNCTION_GRAPH_FREGS
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 89185af7bcc9..d5795067befa 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -40,7 +40,6 @@ config SUPERH
 	select HAVE_GUP_FAST if MMU
 	select HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_TRACER
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_HW_BREAKPOINT
 	select HAVE_IOREMAP_PROT if MMU && !X2TLB
 	select HAVE_KERNEL_BZIP2
diff --git a/arch/sparc/Kconfig b/arch/sparc/Kconfig
index 0f88123925a4..f307e730446c 100644
--- a/arch/sparc/Kconfig
+++ b/arch/sparc/Kconfig
@@ -78,7 +78,6 @@ config SPARC64
 	select MMU_GATHER_NO_FLUSH_CACHE
 	select HAVE_ARCH_TRANSPARENT_HUGEPAGE
 	select HAVE_DYNAMIC_FTRACE
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_PAGE_SIZE_8KB
 	select HAVE_SYSCALL_TRACEPOINTS
 	select HAVE_CONTEXT_TRACKING_USER
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 71019b3b54ea..eb07f236ce53 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -244,7 +244,6 @@ config X86
 	select HAVE_GUP_FAST
 	select HAVE_FENTRY			if X86_64 || DYNAMIC_FTRACE
 	select HAVE_FTRACE_GRAPH_FUNC		if HAVE_FUNCTION_GRAPH_TRACER
-	select HAVE_FTRACE_MCOUNT_RECORD
 	select HAVE_FUNCTION_GRAPH_FREGS	if HAVE_FUNCTION_GRAPH_TRACER
 	select HAVE_FUNCTION_GRAPH_TRACER	if X86_32 || (X86_64 && DYNAMIC_FTRACE)
 	select HAVE_FUNCTION_TRACER
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index fa5f19b8d53a..ae2d2359b79e 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -167,7 +167,7 @@ defined(CONFIG_AUTOFDO_CLANG) || defined(CONFIG_PROPELLER_CLANG)
 #define FTRACE_STUB_HACK
 #endif
 
-#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#ifdef CONFIG_DYNAMIC_FTRACE
 /*
  * The ftrace call sites are logged to a section whose name depends on the
  * compiler option used. A given kernel image will only use one, AKA
diff --git a/include/linux/ftrace.h b/include/linux/ftrace.h
index b672ca15f265..7ded7df6e9b5 100644
--- a/include/linux/ftrace.h
+++ b/include/linux/ftrace.h
@@ -1108,7 +1108,7 @@ static __always_inline unsigned long get_lock_parent_ip(void)
 # define trace_preempt_off(a0, a1) do { } while (0)
 #endif
 
-#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#ifdef CONFIG_DYNAMIC_FTRACE
 extern void ftrace_init(void);
 #ifdef CC_USING_PATCHABLE_FUNCTION_ENTRY
 #define FTRACE_CALLSITE_SECTION	"__patchable_function_entries"
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 1cce1f6410a9..989315dabb86 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -373,9 +373,9 @@ ftrace_vprintk(const char *fmt, va_list ap)
 static inline void ftrace_dump(enum ftrace_dump_mode oops_dump_mode) { }
 #endif /* CONFIG_TRACING */
 
-/* Rebuild everything on CONFIG_FTRACE_MCOUNT_RECORD */
-#ifdef CONFIG_FTRACE_MCOUNT_RECORD
-# define REBUILD_DUE_TO_FTRACE_MCOUNT_RECORD
+/* Rebuild everything on CONFIG_DYNAMIC_FTRACE */
+#ifdef CONFIG_DYNAMIC_FTRACE
+# define REBUILD_DUE_TO_DYNAMIC_FTRACE
 #endif
 
 /* Permissions on a sysfs file: you didn't miss the 0 prefix did you? */
diff --git a/include/linux/module.h b/include/linux/module.h
index 5faa1fb1f4b4..800e6fde9bf7 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -539,7 +539,7 @@ struct module {
 	struct trace_eval_map **trace_evals;
 	unsigned int num_trace_evals;
 #endif
-#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#ifdef CONFIG_DYNAMIC_FTRACE
 	unsigned int num_ftrace_callsites;
 	unsigned long *ftrace_callsites;
 #endif
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 413ac6ea3702..58d36f8cef0d 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -2639,7 +2639,7 @@ static int find_module_sections(struct module *mod, struct load_info *info)
 					 sizeof(*mod->trace_bprintk_fmt_start),
 					 &mod->num_trace_bprintk_fmt);
 #endif
-#ifdef CONFIG_FTRACE_MCOUNT_RECORD
+#ifdef CONFIG_DYNAMIC_FTRACE
 	/* sechdrs[0].sh_size is always zero */
 	mod->ftrace_callsites = section_objs(info, FTRACE_CALLSITE_SECTION,
 					     sizeof(*mod->ftrace_callsites),
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 28afc6941e7a..9f2b1661a8ac 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -74,11 +74,6 @@ config HAVE_DYNAMIC_FTRACE_NO_PATCHABLE
 	  If the architecture generates __patchable_function_entries sections
 	  but does not want them included in the ftrace locations.
 
-config HAVE_FTRACE_MCOUNT_RECORD
-	bool
-	help
-	  See Documentation/trace/ftrace-design.rst
-
 config HAVE_SYSCALL_TRACEPOINTS
 	bool
 	help
@@ -803,27 +798,22 @@ config BPF_KPROBE_OVERRIDE
 	 Allows BPF to override the execution of a probed function and
 	 set a different return value.  This is used for error injection.
 
-config FTRACE_MCOUNT_RECORD
-	def_bool y
-	depends on DYNAMIC_FTRACE
-	depends on HAVE_FTRACE_MCOUNT_RECORD
-
 config FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
 	bool
-	depends on FTRACE_MCOUNT_RECORD
+	depends on DYNAMIC_FTRACE
 
 config FTRACE_MCOUNT_USE_CC
 	def_bool y
 	depends on $(cc-option,-mrecord-mcount)
 	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
-	depends on FTRACE_MCOUNT_RECORD
+	depends on DYNAMIC_FTRACE
 
 config FTRACE_MCOUNT_USE_OBJTOOL
 	def_bool y
 	depends on HAVE_OBJTOOL_MCOUNT
 	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
 	depends on !FTRACE_MCOUNT_USE_CC
-	depends on FTRACE_MCOUNT_RECORD
+	depends on DYNAMIC_FTRACE
 	select OBJTOOL
 
 config FTRACE_MCOUNT_USE_RECORDMCOUNT
@@ -831,7 +821,7 @@ config FTRACE_MCOUNT_USE_RECORDMCOUNT
 	depends on !FTRACE_MCOUNT_USE_PATCHABLE_FUNCTION_ENTRY
 	depends on !FTRACE_MCOUNT_USE_CC
 	depends on !FTRACE_MCOUNT_USE_OBJTOOL
-	depends on FTRACE_MCOUNT_RECORD
+	depends on DYNAMIC_FTRACE
 
 config TRACING_MAP
 	bool
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 4203fad56b6c..00b76d450a89 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1042,10 +1042,6 @@ static struct ftrace_ops *removed_ops;
  */
 static bool update_all_ops;
 
-#ifndef CONFIG_FTRACE_MCOUNT_RECORD
-# error Dynamic ftrace depends on MCOUNT_RECORD
-#endif
-
 struct ftrace_func_probe {
 	struct ftrace_probe_ops	*probe_ops;
 	struct ftrace_ops	ops;
diff --git a/scripts/recordmcount.pl b/scripts/recordmcount.pl
index 0871b2e92584..861b56dda64e 100755
--- a/scripts/recordmcount.pl
+++ b/scripts/recordmcount.pl
@@ -359,7 +359,7 @@ if ($arch eq "x86_64") {
     $mcount_regex = "^\\s*([0-9a-fA-F]+):\\s*R_CKCORE_PCREL_JSR_IMM26BY2\\s+_mcount\$";
     $alignment = 2;
 } else {
-    die "Arch $arch is not supported with CONFIG_FTRACE_MCOUNT_RECORD";
+    die "Arch $arch is not supported with CONFIG_DYNAMIC_FTRACE";
 }
 
 my $text_found = 0;
-- 
cgit v1.2.3


From 5ec9d26b78c4eb7c2fab54dcec6c0eb845302a98 Mon Sep 17 00:00:00 2001
From: Phillip Potter <phil@philpotter.co.uk>
Date: Wed, 23 Jul 2025 00:19:00 +0100
Subject: cdrom: Call cdrom_mrw_exit from cdrom_release function

Remove the cdrom_mrw_exit call from unregister_cdrom, as it invokes
block commands that can fail due to a NULL pointer dereference from the
call happening too late, during the unloading of the driver (e.g.
unplugging of USB optical drives).

Instead perform the call inside cdrom_release, thus also removing the
need for the exit function pointer inside the cdrom_device_info struct.

Reported-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Closes: https://lore.kernel.org/linux-block/uxgzea5ibqxygv3x7i4ojbpvcpv2wziorvb3ns5cdtyvobyn7h@y4g4l5ezv2ec
Suggested-by: Jens Axboe <axboe@kernel.dk>
Link: https://lore.kernel.org/linux-block/6686fe78-a050-4a1d-aa27-b7bf7ca6e912@kernel.dk
Tested-by: Phillip Potter <phil@philpotter.co.uk>
Signed-off-by: Phillip Potter <phil@philpotter.co.uk>
Link: https://lore.kernel.org/r/20250722231900.1164-2-phil@philpotter.co.uk
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 Documentation/cdrom/cdrom-standard.rst | 1 -
 drivers/cdrom/cdrom.c                  | 8 ++------
 include/linux/cdrom.h                  | 1 -
 3 files changed, 2 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/cdrom/cdrom-standard.rst b/Documentation/cdrom/cdrom-standard.rst
index 6c1303cff159..b97a4e9b9bd3 100644
--- a/Documentation/cdrom/cdrom-standard.rst
+++ b/Documentation/cdrom/cdrom-standard.rst
@@ -273,7 +273,6 @@ The drive-specific, minor-like information that is registered with
 	__u8 media_written;			/*  dirty flag, DVD+RW bookkeeping */
 	unsigned short mmc3_profile;		/*  current MMC3 profile */
 	int for_data;				/*  unknown:TBD */
-	int (*exit)(struct cdrom_device_info *);/*  unknown:TBD */
 	int mrw_mode_page;			/*  which MRW mode page is in use */
   };
 
diff --git a/drivers/cdrom/cdrom.c b/drivers/cdrom/cdrom.c
index 21a10552da61..31ba1f8c1f78 100644
--- a/drivers/cdrom/cdrom.c
+++ b/drivers/cdrom/cdrom.c
@@ -624,9 +624,6 @@ int register_cdrom(struct gendisk *disk, struct cdrom_device_info *cdi)
 	if (check_media_type == 1)
 		cdi->options |= (int) CDO_CHECK_TYPE;
 
-	if (CDROM_CAN(CDC_MRW_W))
-		cdi->exit = cdrom_mrw_exit;
-
 	if (cdi->ops->read_cdda_bpc)
 		cdi->cdda_method = CDDA_BPC_FULL;
 	else
@@ -651,9 +648,6 @@ void unregister_cdrom(struct cdrom_device_info *cdi)
 	list_del(&cdi->list);
 	mutex_unlock(&cdrom_mutex);
 
-	if (cdi->exit)
-		cdi->exit(cdi);
-
 	cd_dbg(CD_REG_UNREG, "drive \"/dev/%s\" unregistered\n", cdi->name);
 }
 EXPORT_SYMBOL(unregister_cdrom);
@@ -1264,6 +1258,8 @@ void cdrom_release(struct cdrom_device_info *cdi)
 		cd_dbg(CD_CLOSE, "Use count for \"/dev/%s\" now zero\n",
 		       cdi->name);
 		cdrom_dvd_rw_close_write(cdi);
+		if (CDROM_CAN(CDC_MRW_W))
+			cdrom_mrw_exit(cdi);
 
 		if ((cdo->capability & CDC_LOCK) && !cdi->keeplocked) {
 			cd_dbg(CD_CLOSE, "Unlocking door!\n");
diff --git a/include/linux/cdrom.h b/include/linux/cdrom.h
index fdfb61ccf55a..b907e6c2307d 100644
--- a/include/linux/cdrom.h
+++ b/include/linux/cdrom.h
@@ -62,7 +62,6 @@ struct cdrom_device_info {
 	__u8 last_sense;
 	__u8 media_written;		/* dirty flag, DVD+RW bookkeeping */
 	unsigned short mmc3_profile;	/* current MMC3 profile */
-	int (*exit)(struct cdrom_device_info *);
 	int mrw_mode_page;
 	bool opened_for_data;
 	__s64 last_media_change_ms;
-- 
cgit v1.2.3


From 0a61ec9cc51b0e43981222005444508437e95b33 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Thu, 17 Jul 2025 15:17:25 +0300
Subject: PCI/TPH: Expose pcie_tph_get_st_table_size()

Expose pcie_tph_get_st_table_size() to be used by drivers as will be
done in the next patch from the series.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Acked-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/9ae851e0ee42cc56d2a30276e116b65091030ceb.1752752567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/pci/tph.c       | 11 ++++++-----
 include/linux/pci-tph.h |  1 +
 2 files changed, 7 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/tph.c b/drivers/pci/tph.c
index 77fce5e1b830..cc64f93709a4 100644
--- a/drivers/pci/tph.c
+++ b/drivers/pci/tph.c
@@ -168,7 +168,7 @@ static u32 get_st_table_loc(struct pci_dev *pdev)
  * Return the size of ST table. If ST table is not in TPH Requester Extended
  * Capability space, return 0. Otherwise return the ST Table Size + 1.
  */
-static u16 get_st_table_size(struct pci_dev *pdev)
+u16 pcie_tph_get_st_table_size(struct pci_dev *pdev)
 {
 	u32 reg;
 	u32 loc;
@@ -185,6 +185,7 @@ static u16 get_st_table_size(struct pci_dev *pdev)
 
 	return FIELD_GET(PCI_TPH_CAP_ST_MASK, reg) + 1;
 }
+EXPORT_SYMBOL(pcie_tph_get_st_table_size);
 
 /* Return device's Root Port completer capability */
 static u8 get_rp_completer_type(struct pci_dev *pdev)
@@ -211,7 +212,7 @@ static int write_tag_to_st_table(struct pci_dev *pdev, int index, u16 tag)
 	int offset;
 
 	/* Check if index is out of bound */
-	st_table_size = get_st_table_size(pdev);
+	st_table_size = pcie_tph_get_st_table_size(pdev);
 	if (index >= st_table_size)
 		return -ENXIO;
 
@@ -443,7 +444,7 @@ void pci_restore_tph_state(struct pci_dev *pdev)
 	pci_write_config_dword(pdev, pdev->tph_cap + PCI_TPH_CTRL, *cap++);
 	st_entry = (u16 *)cap;
 	offset = PCI_TPH_BASE_SIZEOF;
-	num_entries = get_st_table_size(pdev);
+	num_entries = pcie_tph_get_st_table_size(pdev);
 	for (i = 0; i < num_entries; i++) {
 		pci_write_config_word(pdev, pdev->tph_cap + offset,
 				      *st_entry++);
@@ -475,7 +476,7 @@ void pci_save_tph_state(struct pci_dev *pdev)
 	/* Save all ST entries in extended capability structure */
 	st_entry = (u16 *)cap;
 	offset = PCI_TPH_BASE_SIZEOF;
-	num_entries = get_st_table_size(pdev);
+	num_entries = pcie_tph_get_st_table_size(pdev);
 	for (i = 0; i < num_entries; i++) {
 		pci_read_config_word(pdev, pdev->tph_cap + offset,
 				     st_entry++);
@@ -499,7 +500,7 @@ void pci_tph_init(struct pci_dev *pdev)
 	if (!pdev->tph_cap)
 		return;
 
-	num_entries = get_st_table_size(pdev);
+	num_entries = pcie_tph_get_st_table_size(pdev);
 	save_size = sizeof(u32) + num_entries * sizeof(u16);
 	pci_add_ext_cap_save_buffer(pdev, PCI_EXT_CAP_ID_TPH, save_size);
 }
diff --git a/include/linux/pci-tph.h b/include/linux/pci-tph.h
index c3e806c13d64..9e4e331b1603 100644
--- a/include/linux/pci-tph.h
+++ b/include/linux/pci-tph.h
@@ -28,6 +28,7 @@ int pcie_tph_get_cpu_st(struct pci_dev *dev,
 			unsigned int cpu_uid, u16 *tag);
 void pcie_disable_tph(struct pci_dev *pdev);
 int pcie_enable_tph(struct pci_dev *pdev, int mode);
+u16 pcie_tph_get_st_table_size(struct pci_dev *pdev);
 #else
 static inline int pcie_tph_set_st_entry(struct pci_dev *pdev,
 					unsigned int index, u16 tag)
-- 
cgit v1.2.3


From 5f9ec7880e6b3c4d0cf242fe28506d0b084328b1 Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Thu, 17 Jul 2025 15:17:26 +0300
Subject: net/mlx5: Expose IFC bits for TPH

Expose IFC bits for the TPH functionality.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Reviewed-by: Edward Srouji <edwards@nvidia.com>
Reviewed-by: Moshe Shemesh <moshe@nvidia.com>
Link: https://patch.msgid.link/38ea3a0d56551364214e8edf359c9c77c9a3b71b.1752752567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 include/linux/mlx5/mlx5_ifc.h | 14 ++++++++++++--
 1 file changed, 12 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index ed4130e49c27..8360d9011d4f 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -1871,7 +1871,9 @@ struct mlx5_ifc_cmd_hca_cap_bits {
 	u8         reserved_at_280[0x10];
 	u8         max_wqe_sz_sq[0x10];
 
-	u8         reserved_at_2a0[0xb];
+	u8         reserved_at_2a0[0x7];
+	u8         mkey_pcie_tph[0x1];
+	u8         reserved_at_2a8[0x3];
 	u8         shampo[0x1];
 	u8         reserved_at_2ac[0x4];
 	u8         max_wqe_sz_rq[0x10];
@@ -4418,6 +4420,10 @@ enum {
 	MLX5_MKC_ACCESS_MODE_CROSSING = 0x6,
 };
 
+enum {
+	MLX5_MKC_PCIE_TPH_NO_STEERING_TAG_INDEX = 0,
+};
+
 struct mlx5_ifc_mkc_bits {
 	u8         reserved_at_0[0x1];
 	u8         free[0x1];
@@ -4469,7 +4475,11 @@ struct mlx5_ifc_mkc_bits {
 	u8         relaxed_ordering_read[0x1];
 	u8         log_page_size[0x6];
 
-	u8         reserved_at_1e0[0x20];
+	u8         reserved_at_1e0[0x5];
+	u8         pcie_tph_en[0x1];
+	u8         pcie_tph_ph[0x2];
+	u8         pcie_tph_steering_tag_index[0x8];
+	u8         reserved_at_1f0[0x10];
 };
 
 struct mlx5_ifc_pkey_bits {
-- 
cgit v1.2.3


From 888a7776f4fb04c19bec70c737c61c2f383c6b1e Mon Sep 17 00:00:00 2001
From: Yishai Hadas <yishaih@nvidia.com>
Date: Thu, 17 Jul 2025 15:17:27 +0300
Subject: net/mlx5: Add support for device steering tag

Background, from PCIe specification 6.2.

TLP Processing Hints (TPH)
--------------------------
TLP Processing Hints is an optional feature that provides hints in
Request TLP headers to facilitate optimized processing of Requests that
target Memory Space. These Processing Hints enable the system hardware
(e.g., the Root Complex and/or Endpoints) to optimize platform
resources such as system and memory interconnect on a per TLP basis.
Steering Tags are system-specific values used to identify a processing
resource that a Requester explicitly targets. System software discovers
and identifies TPH capabilities to determine the Steering Tag allocation
for each Function that supports TPH.

This patch adds steering tag support for mlx5 based NICs by:

- Enabling the TPH functionality over PCI if both FW and OS support it.
- Managing steering tags and their matching steering indexes by
  writing a ST to an ST index over the PCI configuration space.
- Exposing APIs to upper layers (e.g.,mlx5_ib) to allow usage of
  the PCI TPH infrastructure.

Further details:
- Upon probing of a device, the feature will be enabled based
  on both capability detection and OS support.

- It will retrieve the appropriate ST for a given CPU ID and memory
  type using the pcie_tph_get_cpu_st() API.

- It will track available ST indices according to the configuration
  space table size (expected to be 63 entries), reserving index 0 to
  indicate non-TPH use.

- It will assign a free ST index with a ST using the
  pcie_tph_set_st_entry() API.

- It will reuse the same index for identical (CPU ID + memory type)
  combinations by maintaining a reference count per entry.

- It will expose APIs to upper layers (e.g., mlx5_ib) to allow usage of
  the PCI TPH infrastructure.

- SF will use its parent PF stuff.

Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://patch.msgid.link/de1ae7398e9e34eacd8c10845683df44fc9e32f8.1752752567.git.leon@kernel.org
Signed-off-by: Leon Romanovsky <leon@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/Makefile   |   5 +
 drivers/net/ethernet/mellanox/mlx5/core/lib/st.c   | 164 +++++++++++++++++++++
 drivers/net/ethernet/mellanox/mlx5/core/main.c     |   2 +
 .../net/ethernet/mellanox/mlx5/core/mlx5_core.h    |   9 ++
 include/linux/mlx5/driver.h                        |  20 +++
 5 files changed, 200 insertions(+)
 create mode 100644 drivers/net/ethernet/mellanox/mlx5/core/lib/st.c

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
index d292e6a9e22c..bd9d46c6719f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile
+++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile
@@ -167,5 +167,10 @@ mlx5_core-$(CONFIG_MLX5_SF) += sf/vhca_event.o sf/dev/dev.o sf/dev/driver.o irq_
 #
 mlx5_core-$(CONFIG_MLX5_SF_MANAGER) += sf/cmd.o sf/hw_table.o sf/devlink.o
 
+#
+# TPH support
+#
+mlx5_core-$(CONFIG_PCIE_TPH) += lib/st.o
+
 obj-$(CONFIG_MLX5_DPLL) += mlx5_dpll.o
 mlx5_dpll-y :=	dpll.o
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c
new file mode 100644
index 000000000000..47fe215f66bf
--- /dev/null
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/st.c
@@ -0,0 +1,164 @@
+// SPDX-License-Identifier: GPL-2.0 OR Linux-OpenIB
+/*
+ * Copyright (c) 2025, NVIDIA CORPORATION & AFFILIATES. All rights reserved
+ */
+
+#include <linux/mlx5/driver.h>
+#include <linux/mlx5/device.h>
+
+#include "mlx5_core.h"
+#include "lib/mlx5.h"
+
+struct mlx5_st_idx_data {
+	refcount_t usecount;
+	u16 tag;
+};
+
+struct mlx5_st {
+	/* serialize access upon alloc/free flows */
+	struct mutex lock;
+	struct xa_limit index_limit;
+	struct xarray idx_xa; /* key == index, value == struct mlx5_st_idx_data */
+};
+
+struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev)
+{
+	struct pci_dev *pdev = dev->pdev;
+	struct mlx5_st *st;
+	u16 num_entries;
+	int ret;
+
+	if (!MLX5_CAP_GEN(dev, mkey_pcie_tph))
+		return NULL;
+
+#ifdef CONFIG_MLX5_SF
+	if (mlx5_core_is_sf(dev))
+		return dev->priv.parent_mdev->st;
+#endif
+
+	/* Checking whether the device is capable */
+	if (!pdev->tph_cap)
+		return NULL;
+
+	num_entries = pcie_tph_get_st_table_size(pdev);
+	/* We need a reserved entry for non TPH cases */
+	if (num_entries < 2)
+		return NULL;
+
+	/* The OS doesn't support ST */
+	ret = pcie_enable_tph(pdev, PCI_TPH_ST_DS_MODE);
+	if (ret)
+		return NULL;
+
+	st = kzalloc(sizeof(*st), GFP_KERNEL);
+	if (!st)
+		goto end;
+
+	mutex_init(&st->lock);
+	xa_init_flags(&st->idx_xa, XA_FLAGS_ALLOC);
+	/* entry 0 is reserved for non TPH cases */
+	st->index_limit.min = MLX5_MKC_PCIE_TPH_NO_STEERING_TAG_INDEX + 1;
+	st->index_limit.max = num_entries - 1;
+
+	return st;
+
+end:
+	pcie_disable_tph(dev->pdev);
+	return NULL;
+}
+
+void mlx5_st_destroy(struct mlx5_core_dev *dev)
+{
+	struct mlx5_st *st = dev->st;
+
+	if (mlx5_core_is_sf(dev) || !st)
+		return;
+
+	pcie_disable_tph(dev->pdev);
+	WARN_ON_ONCE(!xa_empty(&st->idx_xa));
+	kfree(st);
+}
+
+int mlx5_st_alloc_index(struct mlx5_core_dev *dev, enum tph_mem_type mem_type,
+			unsigned int cpu_uid, u16 *st_index)
+{
+	struct mlx5_st_idx_data *idx_data;
+	struct mlx5_st *st = dev->st;
+	unsigned long index;
+	u32 xa_id;
+	u16 tag;
+	int ret;
+
+	if (!st)
+		return -EOPNOTSUPP;
+
+	ret = pcie_tph_get_cpu_st(dev->pdev, mem_type, cpu_uid, &tag);
+	if (ret)
+		return ret;
+
+	mutex_lock(&st->lock);
+
+	xa_for_each(&st->idx_xa, index, idx_data) {
+		if (tag == idx_data->tag) {
+			refcount_inc(&idx_data->usecount);
+			*st_index = index;
+			goto end;
+		}
+	}
+
+	idx_data = kzalloc(sizeof(*idx_data), GFP_KERNEL);
+	if (!idx_data) {
+		ret = -ENOMEM;
+		goto end;
+	}
+
+	refcount_set(&idx_data->usecount, 1);
+	idx_data->tag = tag;
+
+	ret = xa_alloc(&st->idx_xa, &xa_id, idx_data, st->index_limit, GFP_KERNEL);
+	if (ret)
+		goto clean_idx_data;
+
+	ret = pcie_tph_set_st_entry(dev->pdev, xa_id, tag);
+	if (ret)
+		goto clean_idx_xa;
+
+	*st_index = xa_id;
+	goto end;
+
+clean_idx_xa:
+	xa_erase(&st->idx_xa, xa_id);
+clean_idx_data:
+	kfree(idx_data);
+end:
+	mutex_unlock(&st->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx5_st_alloc_index);
+
+int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index)
+{
+	struct mlx5_st_idx_data *idx_data;
+	struct mlx5_st *st = dev->st;
+	int ret = 0;
+
+	if (!st)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&st->lock);
+	idx_data = xa_load(&st->idx_xa, st_index);
+	if (WARN_ON_ONCE(!idx_data)) {
+		ret = -EINVAL;
+		goto end;
+	}
+
+	if (refcount_dec_and_test(&idx_data->usecount)) {
+		xa_erase(&st->idx_xa, st_index);
+		/* We leave PCI config space as was before, no mkey will refer to it */
+	}
+
+end:
+	mutex_unlock(&st->lock);
+	return ret;
+}
+EXPORT_SYMBOL_GPL(mlx5_st_dealloc_index);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
index b0043cfee29b..be3be043134f 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
@@ -1102,6 +1102,7 @@ static int mlx5_init_once(struct mlx5_core_dev *dev)
 	}
 
 	dev->dm = mlx5_dm_create(dev);
+	dev->st = mlx5_st_create(dev);
 	dev->tracer = mlx5_fw_tracer_create(dev);
 	dev->hv_vhca = mlx5_hv_vhca_create(dev);
 	dev->rsc_dump = mlx5_rsc_dump_create(dev);
@@ -1150,6 +1151,7 @@ static void mlx5_cleanup_once(struct mlx5_core_dev *dev)
 	mlx5_rsc_dump_destroy(dev);
 	mlx5_hv_vhca_destroy(dev->hv_vhca);
 	mlx5_fw_tracer_destroy(dev->tracer);
+	mlx5_st_destroy(dev);
 	mlx5_dm_cleanup(dev);
 	mlx5_fs_core_free(dev);
 	mlx5_sf_table_cleanup(dev);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
index 2e02bdea8361..1cada2f87acf 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/mlx5_core.h
@@ -300,6 +300,15 @@ int mlx5_set_mtppse(struct mlx5_core_dev *mdev, u8 pin, u8 arm, u8 mode);
 struct mlx5_dm *mlx5_dm_create(struct mlx5_core_dev *dev);
 void mlx5_dm_cleanup(struct mlx5_core_dev *dev);
 
+#ifdef CONFIG_PCIE_TPH
+struct mlx5_st *mlx5_st_create(struct mlx5_core_dev *dev);
+void mlx5_st_destroy(struct mlx5_core_dev *dev);
+#else
+static inline struct mlx5_st *
+mlx5_st_create(struct mlx5_core_dev *dev) { return NULL; }
+static inline void mlx5_st_destroy(struct mlx5_core_dev *dev) { return; }
+#endif
+
 void mlx5_toggle_port_link(struct mlx5_core_dev *dev);
 int mlx5_set_port_admin_status(struct mlx5_core_dev *dev,
 			       enum mlx5_port_status status);
diff --git a/include/linux/mlx5/driver.h b/include/linux/mlx5/driver.h
index e6ba8f4f4bd1..104d4921c032 100644
--- a/include/linux/mlx5/driver.h
+++ b/include/linux/mlx5/driver.h
@@ -36,6 +36,7 @@
 #include <linux/kernel.h>
 #include <linux/completion.h>
 #include <linux/pci.h>
+#include <linux/pci-tph.h>
 #include <linux/irq.h>
 #include <linux/spinlock_types.h>
 #include <linux/semaphore.h>
@@ -688,6 +689,7 @@ struct mlx5_fw_tracer;
 struct mlx5_vxlan;
 struct mlx5_geneve;
 struct mlx5_hv_vhca;
+struct mlx5_st;
 
 #define MLX5_LOG_SW_ICM_BLOCK_SIZE(dev) (MLX5_CAP_DEV_MEM(dev, log_sw_icm_alloc_granularity))
 #define MLX5_SW_ICM_BLOCK_SIZE(dev) (1 << MLX5_LOG_SW_ICM_BLOCK_SIZE(dev))
@@ -757,6 +759,7 @@ struct mlx5_core_dev {
 	u32			issi;
 	struct mlx5e_resources  mlx5e_res;
 	struct mlx5_dm          *dm;
+	struct mlx5_st          *st;
 	struct mlx5_vxlan       *vxlan;
 	struct mlx5_geneve      *geneve;
 	struct {
@@ -1160,6 +1163,23 @@ int mlx5_dm_sw_icm_alloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 int mlx5_dm_sw_icm_dealloc(struct mlx5_core_dev *dev, enum mlx5_sw_icm_type type,
 			   u64 length, u16 uid, phys_addr_t addr, u32 obj_id);
 
+#ifdef CONFIG_PCIE_TPH
+int mlx5_st_alloc_index(struct mlx5_core_dev *dev, enum tph_mem_type mem_type,
+			unsigned int cpu_uid, u16 *st_index);
+int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index);
+#else
+static inline int mlx5_st_alloc_index(struct mlx5_core_dev *dev,
+				      enum tph_mem_type mem_type,
+				      unsigned int cpu_uid, u16 *st_index)
+{
+	return -EOPNOTSUPP;
+}
+static inline int mlx5_st_dealloc_index(struct mlx5_core_dev *dev, u16 st_index)
+{
+	return -EOPNOTSUPP;
+}
+#endif
+
 struct mlx5_core_dev *mlx5_vf_get_core_dev(struct pci_dev *pdev);
 void mlx5_vf_put_core_dev(struct mlx5_core_dev *mdev);
 
-- 
cgit v1.2.3


From d0d05f602c1504fb868ed4a560d1465d88a3c5e5 Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Tue, 29 Apr 2025 14:30:00 +0200
Subject: module: Move modprobe_path and modules_disabled ctl_tables into the
 module subsys

Move module sysctl (modprobe_path and modules_disabled) out of sysctl.c
and into the modules subsystem. Make modules_disabled static as it no
longer needs to be exported. Remove module.h from the includes in sysctl
as it no longer uses any module exported variables.

This is part of a greater effort to move ctl tables into their
respective subsystems which will reduce the merge conflicts in
kernel/sysctl.c.

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 include/linux/kmod.h     |  3 ---
 include/linux/module.h   |  1 -
 kernel/module/internal.h |  3 +++
 kernel/module/main.c     | 30 +++++++++++++++++++++++++++++-
 kernel/sysctl.c          | 20 --------------------
 5 files changed, 32 insertions(+), 25 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index 68f69362d427..9a07c3215389 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -14,10 +14,7 @@
 #include <linux/workqueue.h>
 #include <linux/sysctl.h>
 
-#define KMOD_PATH_LEN 256
-
 #ifdef CONFIG_MODULES
-extern char modprobe_path[]; /* for sysctl */
 /* modprobe exit status on success, -ve on error.  Return value
  * usually useless though. */
 extern __printf(2, 3)
diff --git a/include/linux/module.h b/include/linux/module.h
index 92e1420fccdf..e93cdb92ad92 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -304,7 +304,6 @@ struct notifier_block;
 
 #ifdef CONFIG_MODULES
 
-extern int modules_disabled; /* for sysctl */
 /* Get/put a kernel symbol (calls must be symmetric) */
 void *__symbol_get(const char *symbol);
 void *__symbol_get_gpl(const char *symbol);
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index 8d74b0a21c82..51ddd8866ef3 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -58,6 +58,9 @@ extern const struct kernel_symbol __stop___ksymtab_gpl[];
 extern const u32 __start___kcrctab[];
 extern const u32 __start___kcrctab_gpl[];
 
+#define KMOD_PATH_LEN 256
+extern char modprobe_path[];
+
 struct load_info {
 	const char *name;
 	/* pointer to module in temporary copy, freed at end of load_module() */
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 413ac6ea3702..c11d9a125001 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -126,9 +126,37 @@ static void mod_update_bounds(struct module *mod)
 }
 
 /* Block module loading/unloading? */
-int modules_disabled;
+static int modules_disabled;
 core_param(nomodule, modules_disabled, bint, 0);
 
+static const struct ctl_table module_sysctl_table[] = {
+	{
+		.procname	= "modprobe",
+		.data		= &modprobe_path,
+		.maxlen		= KMOD_PATH_LEN,
+		.mode		= 0644,
+		.proc_handler	= proc_dostring,
+	},
+	{
+		.procname	= "modules_disabled",
+		.data		= &modules_disabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		/* only handle a transition from default "0" to "1" */
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_ONE,
+	},
+};
+
+static int __init init_module_sysctl(void)
+{
+	register_sysctl_init("kernel", module_sysctl_table);
+	return 0;
+}
+
+subsys_initcall(init_module_sysctl);
+
 /* Waiting for a module to finish initializing? */
 static DECLARE_WAIT_QUEUE_HEAD(module_wq);
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 9b4f0cff76ea..473133d9651e 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -19,7 +19,6 @@
  *  Removed it and replaced it with older style, 03/23/00, Bill Wendling
  */
 
-#include <linux/module.h>
 #include <linux/sysctl.h>
 #include <linux/bitmap.h>
 #include <linux/printk.h>
@@ -1616,25 +1615,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_MODULES
-	{
-		.procname	= "modprobe",
-		.data		= &modprobe_path,
-		.maxlen		= KMOD_PATH_LEN,
-		.mode		= 0644,
-		.proc_handler	= proc_dostring,
-	},
-	{
-		.procname	= "modules_disabled",
-		.data		= &modules_disabled,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		/* only handle a transition from default "0" to "1" */
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ONE,
-		.extra2		= SYSCTL_ONE,
-	},
-#endif
 #ifdef CONFIG_UEVENT_HELPER
 	{
 		.procname	= "hotplug",
-- 
cgit v1.2.3


From f1b4f23a52c272f6c1e205e8ec243f563323c5aa Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Tue, 29 Apr 2025 15:12:17 +0200
Subject: locking/rtmutex: Move max_lock_depth into rtmutex.c

Move the max_lock_depth sysctl table element into rtmutex_api.c. Removed
the rtmutex.h include from sysctl.c. Chose to move into rtmutex_api.c
to avoid multiple registrations every time rtmutex.c is included in other
files.

This is part of a greater effort to move ctl tables into their
respective subsystems which will reduce the merge conflicts in
kernel/sysctl.c.

Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 include/linux/rtmutex.h      |  2 +-
 kernel/locking/rtmutex_api.c | 18 ++++++++++++++++++
 kernel/sysctl.c              | 12 ------------
 3 files changed, 19 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rtmutex.h b/include/linux/rtmutex.h
index 7d049883a08a..fa9f1021541e 100644
--- a/include/linux/rtmutex.h
+++ b/include/linux/rtmutex.h
@@ -18,7 +18,7 @@
 #include <linux/rbtree_types.h>
 #include <linux/spinlock_types_raw.h>
 
-extern int max_lock_depth; /* for sysctl */
+extern int max_lock_depth;
 
 struct rt_mutex_base {
 	raw_spinlock_t		wait_lock;
diff --git a/kernel/locking/rtmutex_api.c b/kernel/locking/rtmutex_api.c
index 2d933528a0fa..bafd5af98eae 100644
--- a/kernel/locking/rtmutex_api.c
+++ b/kernel/locking/rtmutex_api.c
@@ -13,6 +13,24 @@
  */
 int max_lock_depth = 1024;
 
+static const struct ctl_table rtmutex_sysctl_table[] = {
+	{
+		.procname	= "max_lock_depth",
+		.data		= &max_lock_depth,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+};
+
+static int __init init_rtmutex_sysctl(void)
+{
+	register_sysctl_init("kernel", rtmutex_sysctl_table);
+	return 0;
+}
+
+subsys_initcall(init_rtmutex_sysctl);
+
 /*
  * Debug aware fast / slowpath lock,trylock,unlock
  *
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 473133d9651e..a22f35013da0 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -59,9 +59,6 @@
 #include <asm/nmi.h>
 #include <asm/io.h>
 #endif
-#ifdef CONFIG_RT_MUTEXES
-#include <linux/rtmutex.h>
-#endif
 
 /* shared constants to be used in various sysctls */
 const int sysctl_vals[] = { 0, 1, 2, 3, 4, 100, 200, 1000, 3000, INT_MAX, 65535, -1 };
@@ -1709,15 +1706,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_RT_MUTEXES
-	{
-		.procname	= "max_lock_depth",
-		.data		= &max_lock_depth,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 #ifdef CONFIG_TREE_RCU
 	{
 		.procname	= "panic_on_rcu_stall",
-- 
cgit v1.2.3


From fff6703fc843569d7a2f78ca08e7a69a9be22b0f Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Wed, 30 Apr 2025 14:07:33 +0200
Subject: rcu: Move rcu_stall related sysctls into rcu/tree_stall.h

Move sysctl_panic_on_rcu_stall and sysctl_max_rcu_stall_to_panic into
the kernel/rcu subdirectory. Make these static in tree_stall.h and
removed them as extern from panic.h as their scope is now confined into
one file.

This is part of a greater effort to move ctl tables into their
respective subsystems which will reduce the merge conflicts in
kernel/sysctl.c.

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Joel Fernandes <joelagnelf@nvidia.com>
Reviewed-by: Kees Cook <kees@kernel.org>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 include/linux/panic.h   |  2 --
 kernel/rcu/tree_stall.h | 33 +++++++++++++++++++++++++++++++--
 kernel/sysctl.c         | 20 --------------------
 3 files changed, 31 insertions(+), 24 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/panic.h b/include/linux/panic.h
index 4adc65766935..8f2b5d92ac05 100644
--- a/include/linux/panic.h
+++ b/include/linux/panic.h
@@ -25,8 +25,6 @@ extern int panic_on_warn;
 extern unsigned long panic_on_taint;
 extern bool panic_on_taint_nousertaint;
 
-extern int sysctl_panic_on_rcu_stall;
-extern int sysctl_max_rcu_stall_to_panic;
 extern int sysctl_panic_on_stackoverflow;
 
 extern bool crash_kexec_post_notifiers;
diff --git a/kernel/rcu/tree_stall.h b/kernel/rcu/tree_stall.h
index 486c00536207..69482c2f0771 100644
--- a/kernel/rcu/tree_stall.h
+++ b/kernel/rcu/tree_stall.h
@@ -17,8 +17,37 @@
 // Controlling CPU stall warnings, including delay calculation.
 
 /* panic() on RCU Stall sysctl. */
-int sysctl_panic_on_rcu_stall __read_mostly;
-int sysctl_max_rcu_stall_to_panic __read_mostly;
+static int sysctl_panic_on_rcu_stall __read_mostly;
+static int sysctl_max_rcu_stall_to_panic __read_mostly;
+
+static const struct ctl_table rcu_stall_sysctl_table[] = {
+	{
+		.procname	= "panic_on_rcu_stall",
+		.data		= &sysctl_panic_on_rcu_stall,
+		.maxlen		= sizeof(sysctl_panic_on_rcu_stall),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{
+		.procname	= "max_rcu_stall_to_panic",
+		.data		= &sysctl_max_rcu_stall_to_panic,
+		.maxlen		= sizeof(sysctl_max_rcu_stall_to_panic),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ONE,
+		.extra2		= SYSCTL_INT_MAX,
+	},
+};
+
+static int __init init_rcu_stall_sysctl(void)
+{
+	register_sysctl_init("kernel", rcu_stall_sysctl_table);
+	return 0;
+}
+
+subsys_initcall(init_rcu_stall_sysctl);
 
 #ifdef CONFIG_SYSFS
 
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index a22f35013da0..fd76f0e1d490 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1706,26 +1706,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_dointvec,
 	},
 #endif
-#ifdef CONFIG_TREE_RCU
-	{
-		.procname	= "panic_on_rcu_stall",
-		.data		= &sysctl_panic_on_rcu_stall,
-		.maxlen		= sizeof(sysctl_panic_on_rcu_stall),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ZERO,
-		.extra2		= SYSCTL_ONE,
-	},
-	{
-		.procname	= "max_rcu_stall_to_panic",
-		.data		= &sysctl_max_rcu_stall_to_panic,
-		.maxlen		= sizeof(sysctl_max_rcu_stall_to_panic),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec_minmax,
-		.extra1		= SYSCTL_ONE,
-		.extra2		= SYSCTL_INT_MAX,
-	},
-#endif
 };
 
 int __init sysctl_init_bases(void)
-- 
cgit v1.2.3


From 9e2f403dd8c2b07aff012e72c1fe5455538d72d2 Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Fri, 2 May 2025 15:32:17 +0200
Subject: parisc/power: Move soft-power into power.c

Move the soft-power ctl table into parisc/power.c. As a consequence the
pwrsw_enabled var is made static.

This is part of a greater effort to move ctl tables into their
respective subsystems which will reduce the merge conflicts in
kernel/sysctl.c.

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 drivers/parisc/power.c | 20 +++++++++++++++++++-
 include/linux/sysctl.h |  1 -
 kernel/sysctl.c        |  9 ---------
 3 files changed, 19 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/parisc/power.c b/drivers/parisc/power.c
index 7a6a3e7f2825..9d6c7bf72e29 100644
--- a/drivers/parisc/power.c
+++ b/drivers/parisc/power.c
@@ -83,7 +83,25 @@ static struct task_struct *power_task;
 #define SYSCTL_FILENAME	"sys/kernel/power"
 
 /* soft power switch enabled/disabled */
-int pwrsw_enabled __read_mostly = 1;
+static int pwrsw_enabled __read_mostly = 1;
+
+static const struct ctl_table power_sysctl_table[] = {
+	{
+		.procname	= "soft-power",
+		.data		= &pwrsw_enabled,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+};
+
+static int __init init_power_sysctl(void)
+{
+	register_sysctl_init("kernel", power_sysctl_table);
+	return 0;
+}
+
+arch_initcall(init_power_sysctl);
 
 /* main kernel thread worker. It polls the button state */
 static int kpowerswd(void *param)
diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 40a6ac6c9713..ae762eabb7c9 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -242,7 +242,6 @@ int do_proc_douintvec(const struct ctl_table *table, int write,
 				  int write, void *data),
 		      void *data);
 
-extern int pwrsw_enabled;
 extern int unaligned_enabled;
 extern int unaligned_dump_stack;
 extern int no_unaligned_warning;
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index adc2d3ea1278..718140251972 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1594,15 +1594,6 @@ static const struct ctl_table kern_table[] = {
 		.extra2		= SYSCTL_ONE,
 	},
 #endif
-#ifdef CONFIG_PARISC
-	{
-		.procname	= "soft-power",
-		.data		= &pwrsw_enabled,
-		.maxlen		= sizeof (int),
-		.mode		= 0644,
-		.proc_handler	= proc_dointvec,
-	},
-#endif
 #ifdef CONFIG_SYSCTL_ARCH_UNALIGN_ALLOW
 	{
 		.procname	= "unaligned-trap",
-- 
cgit v1.2.3


From 8e5f04b0d58c734c69a0b6e26317561919299638 Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Fri, 2 May 2025 22:27:38 +0200
Subject: fork: mv threads-max into kernel/fork.c

make sysctl_max_threads static as it no longer needs to be exported into
sysctl.c.

This is part of a greater effort to move ctl tables into their
respective subsystems which will reduce the merge conflicts in
kernel/sysctl.c.

Reviewed-by: Luis Chamberlain <mcgrof@kernel.org>
Reviewed-by: Kees Cook <kees@kernel.org>
Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 include/linux/sysctl.h |  3 ---
 kernel/fork.c          | 20 +++++++++++++++++++-
 kernel/sysctl.c        |  7 -------
 3 files changed, 19 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index ae762eabb7c9..30bcbc59d12d 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -284,7 +284,4 @@ static inline bool sysctl_is_alias(char *param)
 }
 #endif /* CONFIG_SYSCTL */
 
-int sysctl_max_threads(const struct ctl_table *table, int write, void *buffer,
-		size_t *lenp, loff_t *ppos);
-
 #endif /* _LINUX_SYSCTL_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 1ee8eb11f38b..dea8e7740ad2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -3216,7 +3216,7 @@ int unshare_files(void)
 	return 0;
 }
 
-int sysctl_max_threads(const struct ctl_table *table, int write,
+static int sysctl_max_threads(const struct ctl_table *table, int write,
 		       void *buffer, size_t *lenp, loff_t *ppos)
 {
 	struct ctl_table t;
@@ -3238,3 +3238,21 @@ int sysctl_max_threads(const struct ctl_table *table, int write,
 
 	return 0;
 }
+
+static const struct ctl_table fork_sysctl_table[] = {
+	{
+		.procname	= "threads-max",
+		.data		= NULL,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= sysctl_max_threads,
+	},
+};
+
+static int __init init_fork_sysctl(void)
+{
+	register_sysctl_init("kernel", fork_sysctl_table);
+	return 0;
+}
+
+subsys_initcall(init_fork_sysctl);
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 718140251972..febf328054aa 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1630,13 +1630,6 @@ static const struct ctl_table kern_table[] = {
 		.proc_handler	= proc_do_cad_pid,
 	},
 #endif
-	{
-		.procname	= "threads-max",
-		.data		= NULL,
-		.maxlen		= sizeof(int),
-		.mode		= 0644,
-		.proc_handler	= sysctl_max_threads,
-	},
 	{
 		.procname	= "overflowuid",
 		.data		= &overflowuid,
-- 
cgit v1.2.3


From 39dac316f09ae5a0930878d2cae8aea113648b5a Mon Sep 17 00:00:00 2001
From: Joel Granados <joel.granados@kernel.org>
Date: Fri, 27 Jun 2025 09:00:05 +0200
Subject: sysctl: Removed unused variable

Remove unaligned_dump_stack from sysctl.h; it is no longer used or
defined.

Signed-off-by: Joel Granados <joel.granados@kernel.org>
---
 include/linux/sysctl.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sysctl.h b/include/linux/sysctl.h
index 30bcbc59d12d..92e9146b1104 100644
--- a/include/linux/sysctl.h
+++ b/include/linux/sysctl.h
@@ -243,7 +243,6 @@ int do_proc_douintvec(const struct ctl_table *table, int write,
 		      void *data);
 
 extern int unaligned_enabled;
-extern int unaligned_dump_stack;
 extern int no_unaligned_warning;
 
 #else /* CONFIG_SYSCTL */
-- 
cgit v1.2.3


From 4e8fc4f7208b032674ef8a4977b96484c328515c Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Wed, 23 Jul 2025 20:23:29 +0800
Subject: netfs: Remove unused declaration netfs_queue_write_request()

Commit c245868524cc ("netfs: Remove the old writeback code") removed
the implementation but leave declaration.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Link: https://lore.kernel.org/20250723122329.923223-1-yuehaibing@huawei.com
Signed-off-by: Christian Brauner <brauner@kernel.org>
---
 include/linux/netfs.h | 1 -
 1 file changed, 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/netfs.h b/include/linux/netfs.h
index 065c17385e53..486d5766fe77 100644
--- a/include/linux/netfs.h
+++ b/include/linux/netfs.h
@@ -443,7 +443,6 @@ size_t netfs_limit_iter(const struct iov_iter *iter, size_t start_offset,
 			size_t max_size, size_t max_segs);
 void netfs_prepare_write_failed(struct netfs_io_subrequest *subreq);
 void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error);
-void netfs_queue_write_request(struct netfs_io_subrequest *subreq);
 
 int netfs_start_io_read(struct inode *inode);
 void netfs_end_io_read(struct inode *inode);
-- 
cgit v1.2.3


From 89ade7c7306508f46b811cd43960eaed88e0e1dd Mon Sep 17 00:00:00 2001
From: Byungchul Park <byungchul@sk.com>
Date: Mon, 21 Jul 2025 11:18:26 +0900
Subject: netmem, mlx4: access ->pp_ref_count through netmem_desc instead of
 page

To eliminate the use of struct page in page pool, the page pool users
should use netmem descriptor and APIs instead.

Make mlx4 access ->pp_ref_count through netmem_desc instead of page.

While at it, add a helper, pp_page_to_nmdesc() and __pp_page_to_nmdesc(),
that can be used to get netmem_desc from page only if it's a pp page.
For now that netmem_desc overlays on page, it can be achieved by just
casting, and use macro and _Generic to cover const casting as well.

Plus, change page_pool_page_is_pp() to check for 'const struct page *'
instead of 'struct page *' since it doesn't modify data and additionally
covers const type.

Signed-off-by: Byungchul Park <byungchul@sk.com>
Link: https://patch.msgid.link/20250721021835.63939-4-byungchul@sk.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx4/en_rx.c |  4 +++-
 include/linux/mm.h                         |  4 ++--
 include/net/netmem.h                       | 17 +++++++++++++++++
 3 files changed, 22 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
index b33285d755b9..92a16ddb7d86 100644
--- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c
@@ -460,9 +460,11 @@ static int mlx4_en_complete_rx_desc(struct mlx4_en_priv *priv,
 
 		truesize += frag_info->frag_stride;
 		if (frag_info->frag_stride == PAGE_SIZE / 2) {
+			struct netmem_desc *desc = pp_page_to_nmdesc(page);
+
 			frags->page_offset ^= PAGE_SIZE / 2;
 			release = page_count(page) != 1 ||
-				  atomic_long_read(&page->pp_ref_count) != 1 ||
+				  atomic_long_read(&desc->pp_ref_count) != 1 ||
 				  page_is_pfmemalloc(page) ||
 				  page_to_nid(page) != numa_mem_id();
 		} else if (!priv->rx_headroom) {
diff --git a/include/linux/mm.h b/include/linux/mm.h
index fa538feaa8d9..ae50c1641bed 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4178,12 +4178,12 @@ int arch_lock_shadow_stack_status(struct task_struct *t, unsigned long status);
 #define PP_MAGIC_MASK ~(PP_DMA_INDEX_MASK | 0x3UL)
 
 #ifdef CONFIG_PAGE_POOL
-static inline bool page_pool_page_is_pp(struct page *page)
+static inline bool page_pool_page_is_pp(const struct page *page)
 {
 	return (page->pp_magic & PP_MAGIC_MASK) == PP_SIGNATURE;
 }
 #else
-static inline bool page_pool_page_is_pp(struct page *page)
+static inline bool page_pool_page_is_pp(const struct page *page)
 {
 	return false;
 }
diff --git a/include/net/netmem.h b/include/net/netmem.h
index 097bc74d9555..f7dacc9e75fd 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -285,6 +285,23 @@ static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem)
 	return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV);
 }
 
+/* XXX: How to extract netmem_desc from page must be changed, once
+ * netmem_desc no longer overlays on page and will be allocated through
+ * slab.
+ */
+#define __pp_page_to_nmdesc(p)	(_Generic((p),				\
+	const struct page * :	(const struct netmem_desc *)(p),	\
+	struct page * :		(struct netmem_desc *)(p)))
+
+/* CAUTION: Check if the page is a pp page before calling this helper or
+ * know it's a pp page.
+ */
+#define pp_page_to_nmdesc(p)						\
+({									\
+	DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p));		\
+	__pp_page_to_nmdesc(p);						\
+})
+
 /**
  * __netmem_get_pp - unsafely get pointer to the &page_pool backing @netmem
  * @netmem: netmem reference to get the pointer from
-- 
cgit v1.2.3


From 28517c8b6275a9cd25a4974d0e4d58eaba465a67 Mon Sep 17 00:00:00 2001
From: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Date: Wed, 23 Jul 2025 19:34:56 +0200
Subject: pwm: mc33xs2410: add hwmon support
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

Support for hwmon is provided by a separate driver residing in hwmon
subsystem which is implemented as auxiliary device. Add handling of this
device.

Signed-off-by: Dimitri Fedrau <dimitri.fedrau@liebherr.com>
Link: https://lore.kernel.org/r/20250723-mc33xs2410-hwmon-v5-1-f62aab71cd59@liebherr.com
Signed-off-by: Uwe Kleine-König <ukleinek@kernel.org>
---
 drivers/pwm/Kconfig          |  1 +
 drivers/pwm/pwm-mc33xs2410.c | 20 ++++++++++++++++++--
 include/linux/mc33xs2410.h   | 16 ++++++++++++++++
 3 files changed, 35 insertions(+), 2 deletions(-)
 create mode 100644 include/linux/mc33xs2410.h

(limited to 'include/linux')

diff --git a/drivers/pwm/Kconfig b/drivers/pwm/Kconfig
index 3ef1757502eb..64f1c86340fd 100644
--- a/drivers/pwm/Kconfig
+++ b/drivers/pwm/Kconfig
@@ -436,6 +436,7 @@ config PWM_MC33XS2410
 	tristate "MC33XS2410 PWM support"
 	depends on OF
 	depends on SPI
+	select AUXILIARY_BUS
 	help
 	  NXP MC33XS2410 high-side switch driver. The MC33XS2410 is a four
 	  channel high-side switch. The device is operational from 3.0 V
diff --git a/drivers/pwm/pwm-mc33xs2410.c b/drivers/pwm/pwm-mc33xs2410.c
index a1ac3445ccdb..6d99e3ff7239 100644
--- a/drivers/pwm/pwm-mc33xs2410.c
+++ b/drivers/pwm/pwm-mc33xs2410.c
@@ -17,11 +17,14 @@
  *   behavior of the output pin that is neither the old nor the new state,
  *   rather something in between.
  */
+#define DEFAULT_SYMBOL_NAMESPACE		"PWM_MC33XS2410"
 
+#include <linux/auxiliary_bus.h>
 #include <linux/bitfield.h>
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/math64.h>
+#include <linux/mc33xs2410.h>
 #include <linux/minmax.h>
 #include <linux/module.h>
 #include <linux/of.h>
@@ -120,12 +123,19 @@ static int mc33xs2410_read_reg(struct spi_device *spi, u8 reg, u16 *val, u8 flag
 	return mc33xs2410_read_regs(spi, &reg, flag, val, 1);
 }
 
-static int mc33xs2410_read_reg_ctrl(struct spi_device *spi, u8 reg, u16 *val)
+int mc33xs2410_read_reg_ctrl(struct spi_device *spi, u8 reg, u16 *val)
 {
 	return mc33xs2410_read_reg(spi, reg, val, MC33XS2410_FRAME_IN_DATA_RD);
 }
+EXPORT_SYMBOL_GPL(mc33xs2410_read_reg_ctrl);
 
-static int mc33xs2410_modify_reg(struct spi_device *spi, u8 reg, u8 mask, u8 val)
+int mc33xs2410_read_reg_diag(struct spi_device *spi, u8 reg, u16 *val)
+{
+	return mc33xs2410_read_reg(spi, reg, val, 0);
+}
+EXPORT_SYMBOL_GPL(mc33xs2410_read_reg_diag);
+
+int mc33xs2410_modify_reg(struct spi_device *spi, u8 reg, u8 mask, u8 val)
 {
 	u16 tmp;
 	int ret;
@@ -139,6 +149,7 @@ static int mc33xs2410_modify_reg(struct spi_device *spi, u8 reg, u8 mask, u8 val
 
 	return mc33xs2410_write_reg(spi, reg, tmp);
 }
+EXPORT_SYMBOL_GPL(mc33xs2410_modify_reg);
 
 static u8 mc33xs2410_pwm_get_freq(u64 period)
 {
@@ -314,6 +325,7 @@ static int mc33xs2410_reset(struct device *dev)
 static int mc33xs2410_probe(struct spi_device *spi)
 {
 	struct device *dev = &spi->dev;
+	struct auxiliary_device *adev;
 	struct pwm_chip *chip;
 	int ret;
 
@@ -361,6 +373,10 @@ static int mc33xs2410_probe(struct spi_device *spi)
 	if (ret < 0)
 		return dev_err_probe(dev, ret, "Failed to add pwm chip\n");
 
+	adev = devm_auxiliary_device_create(dev, "hwmon", NULL);
+	if (!adev)
+		return dev_err_probe(dev, -ENODEV, "Failed to register hwmon device\n");
+
 	return 0;
 }
 
diff --git a/include/linux/mc33xs2410.h b/include/linux/mc33xs2410.h
new file mode 100644
index 000000000000..31c0edf10dd7
--- /dev/null
+++ b/include/linux/mc33xs2410.h
@@ -0,0 +1,16 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2024 Liebherr-Electronics and Drives GmbH
+ */
+#ifndef _MC33XS2410_H
+#define _MC33XS2410_H
+
+#include <linux/spi/spi.h>
+
+MODULE_IMPORT_NS("PWM_MC33XS2410");
+
+int mc33xs2410_read_reg_ctrl(struct spi_device *spi, u8 reg, u16 *val);
+int mc33xs2410_read_reg_diag(struct spi_device *spi, u8 reg, u16 *val);
+int mc33xs2410_modify_reg(struct spi_device *spi, u8 reg, u8 mask, u8 val);
+
+#endif /* _MC33XS2410_H */
-- 
cgit v1.2.3


From e038d985c9823a12cd64fa077d0c5aca2c644b67 Mon Sep 17 00:00:00 2001
From: Sven Peter <sven@kernel.org>
Date: Tue, 10 Jun 2025 15:29:46 +0000
Subject: mfd: Add Apple Silicon System Management Controller

The System Management Controller (SMC) on Apple Silicon machines is a
piece of hardware that exposes various functionalities such as
temperature sensors, voltage/power meters, shutdown/reboot handling,
GPIOs and more.

Communication happens via a shared mailbox using the RTKit protocol
which is also used for other co-processors. The SMC protocol then allows
reading and writing many different keys which implement the various
features. The MFD core device handles this protocol and exposes it
to the sub-devices.

Some of the sub-devices are potentially also useful on pre-M1 Apple
machines and support for SMCs on these machines can be added at a later
time.

Co-developed-by: Hector Martin <marcan@marcan.st>
Signed-off-by: Hector Martin <marcan@marcan.st>
Reviewed-by: Alyssa Rosenzweig <alyssa@rosenzweig.io>
Reviewed-by: Neal Gompa <neal@gompa.dev>
Signed-off-by: Sven Peter <sven@kernel.org>
Link: https://lore.kernel.org/r/20250610-smc-6-15-v7-5-556cafd771d3@kernel.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 MAINTAINERS                |   2 +
 drivers/mfd/Kconfig        |  18 ++
 drivers/mfd/Makefile       |   1 +
 drivers/mfd/macsmc.c       | 498 +++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mfd/macsmc.h | 279 +++++++++++++++++++++++++
 5 files changed, 798 insertions(+)
 create mode 100644 drivers/mfd/macsmc.c
 create mode 100644 include/linux/mfd/macsmc.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index 329b2df08d4b..f6bf4643c20b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -2364,6 +2364,7 @@ F:	drivers/input/touchscreen/apple_z2.c
 F:	drivers/iommu/apple-dart.c
 F:	drivers/iommu/io-pgtable-dart.c
 F:	drivers/irqchip/irq-apple-aic.c
+F:	drivers/mfd/macsmc.c
 F:	drivers/nvme/host/apple.c
 F:	drivers/nvmem/apple-efuses.c
 F:	drivers/nvmem/apple-spmi-nvmem.c
@@ -2376,6 +2377,7 @@ F:	drivers/video/backlight/apple_dwi_bl.c
 F:	drivers/watchdog/apple_wdt.c
 F:	include/dt-bindings/interrupt-controller/apple-aic.h
 F:	include/dt-bindings/pinctrl/apple.h
+F:	include/linux/mfd/macsmc.h
 F:	include/linux/soc/apple/*
 F:	include/uapi/drm/asahi_drm.h
 
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 6fb3768e3d71..c6cc42360887 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -285,6 +285,24 @@ config MFD_CS42L43_SDW
 	  Select this to support the Cirrus Logic CS42L43 PC CODEC with
 	  headphone and class D speaker drivers over SoundWire.
 
+config MFD_MACSMC
+	tristate "Apple Silicon System Management Controller (SMC)"
+	depends on ARCH_APPLE || COMPILE_TEST
+	depends on OF
+	depends on APPLE_RTKIT
+	select MFD_CORE
+	help
+	  The System Management Controller (SMC) on Apple Silicon machines is a
+	  piece of hardware that exposes various functionalities such as
+	  temperature sensors, voltage/power meters, shutdown/reboot handling,
+	  GPIOs and more.
+
+	  Communication happens via a shared mailbox using the RTKit protocol
+	  which is also used for other co-processors. The SMC protocol then
+	  allows reading and writing many different keys which implement the
+	  various features. The MFD core device handles this protocol and
+	  exposes it to the sub-devices.
+
 config MFD_MADERA
 	tristate "Cirrus Logic Madera codecs"
 	select MFD_CORE
diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
index 79495f9f3457..f7bdedd5a66d 100644
--- a/drivers/mfd/Makefile
+++ b/drivers/mfd/Makefile
@@ -21,6 +21,7 @@ obj-$(CONFIG_MFD_CS42L43_SDW)	+= cs42l43-sdw.o
 obj-$(CONFIG_MFD_ENE_KB3930)	+= ene-kb3930.o
 obj-$(CONFIG_MFD_EXYNOS_LPASS)	+= exynos-lpass.o
 obj-$(CONFIG_MFD_GATEWORKS_GSC)	+= gateworks-gsc.o
+obj-$(CONFIG_MFD_MACSMC)	+= macsmc.o
 
 obj-$(CONFIG_MFD_TI_LP873X)	+= lp873x.o
 obj-$(CONFIG_MFD_TI_LP87565)	+= lp87565.o
diff --git a/drivers/mfd/macsmc.c b/drivers/mfd/macsmc.c
new file mode 100644
index 000000000000..870c8b2028a8
--- /dev/null
+++ b/drivers/mfd/macsmc.c
@@ -0,0 +1,498 @@
+// SPDX-License-Identifier: GPL-2.0-only OR MIT
+/*
+ * Apple SMC (System Management Controller) MFD driver
+ *
+ * Copyright The Asahi Linux Contributors
+ */
+
+#include <linux/bitfield.h>
+#include <linux/delay.h>
+#include <linux/device.h>
+#include <linux/io.h>
+#include <linux/ioport.h>
+#include <linux/math.h>
+#include <linux/mfd/core.h>
+#include <linux/mfd/macsmc.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/overflow.h>
+#include <linux/platform_device.h>
+#include <linux/soc/apple/rtkit.h>
+#include <linux/unaligned.h>
+
+#define SMC_ENDPOINT			0x20
+
+/* We don't actually know the true size here but this seem reasonable */
+#define SMC_SHMEM_SIZE			0x1000
+#define SMC_MAX_SIZE			255
+
+#define SMC_MSG_READ_KEY		0x10
+#define SMC_MSG_WRITE_KEY		0x11
+#define SMC_MSG_GET_KEY_BY_INDEX	0x12
+#define SMC_MSG_GET_KEY_INFO		0x13
+#define SMC_MSG_INITIALIZE		0x17
+#define SMC_MSG_NOTIFICATION		0x18
+#define SMC_MSG_RW_KEY			0x20
+
+#define SMC_DATA			GENMASK_ULL(63, 32)
+#define SMC_WSIZE			GENMASK_ULL(31, 24)
+#define SMC_SIZE			GENMASK_ULL(23, 16)
+#define SMC_ID				GENMASK_ULL(15, 12)
+#define SMC_MSG				GENMASK_ULL(7, 0)
+#define SMC_RESULT			SMC_MSG
+
+#define SMC_TIMEOUT_MS		500
+
+static const struct mfd_cell apple_smc_devs[] = {
+	MFD_CELL_OF("macsmc-gpio", NULL, NULL, 0, 0, "apple,smc-gpio"),
+	MFD_CELL_OF("macsmc-reboot", NULL, NULL, 0, 0, "apple,smc-reboot"),
+};
+
+static int apple_smc_cmd_locked(struct apple_smc *smc, u64 cmd, u64 arg,
+				  u64 size, u64 wsize, u32 *ret_data)
+{
+	u8 result;
+	int ret;
+	u64 msg;
+
+	lockdep_assert_held(&smc->mutex);
+
+	if (smc->boot_stage != APPLE_SMC_INITIALIZED)
+		return -EIO;
+	if (smc->atomic_mode)
+		return -EIO;
+
+	reinit_completion(&smc->cmd_done);
+
+	smc->msg_id = (smc->msg_id + 1) & 0xf;
+	msg = (FIELD_PREP(SMC_MSG, cmd) |
+	       FIELD_PREP(SMC_SIZE, size) |
+	       FIELD_PREP(SMC_WSIZE, wsize) |
+	       FIELD_PREP(SMC_ID, smc->msg_id) |
+	       FIELD_PREP(SMC_DATA, arg));
+
+	ret = apple_rtkit_send_message(smc->rtk, SMC_ENDPOINT, msg, NULL, false);
+	if (ret) {
+		dev_err(smc->dev, "Failed to send command\n");
+		return ret;
+	}
+
+	if (wait_for_completion_timeout(&smc->cmd_done, msecs_to_jiffies(SMC_TIMEOUT_MS)) <= 0) {
+		dev_err(smc->dev, "Command timed out (%llx)", msg);
+		return -ETIMEDOUT;
+	}
+
+	if (FIELD_GET(SMC_ID, smc->cmd_ret) != smc->msg_id) {
+		dev_err(smc->dev, "Command sequence mismatch (expected %d, got %d)\n",
+			smc->msg_id, (unsigned int)FIELD_GET(SMC_ID, smc->cmd_ret));
+		return -EIO;
+	}
+
+	result = FIELD_GET(SMC_RESULT, smc->cmd_ret);
+	if (result)
+		return -EIO;
+
+	if (ret_data)
+		*ret_data = FIELD_GET(SMC_DATA, smc->cmd_ret);
+
+	return FIELD_GET(SMC_SIZE, smc->cmd_ret);
+}
+
+static int apple_smc_cmd(struct apple_smc *smc, u64 cmd, u64 arg,
+			 u64 size, u64 wsize, u32 *ret_data)
+{
+	guard(mutex)(&smc->mutex);
+
+	return apple_smc_cmd_locked(smc, cmd, arg, size, wsize, ret_data);
+}
+
+static int apple_smc_rw_locked(struct apple_smc *smc, smc_key key,
+				const void *wbuf, size_t wsize,
+				void *rbuf, size_t rsize)
+{
+	u64 smc_size, smc_wsize;
+	u32 rdata;
+	int ret;
+	u64 cmd;
+
+	lockdep_assert_held(&smc->mutex);
+
+	if (rsize > SMC_MAX_SIZE)
+		return -EINVAL;
+	if (wsize > SMC_MAX_SIZE)
+		return -EINVAL;
+
+	if (rsize && wsize) {
+		cmd = SMC_MSG_RW_KEY;
+		memcpy_toio(smc->shmem.iomem, wbuf, wsize);
+		smc_size = rsize;
+		smc_wsize = wsize;
+	} else if (wsize && !rsize) {
+		cmd = SMC_MSG_WRITE_KEY;
+		memcpy_toio(smc->shmem.iomem, wbuf, wsize);
+		/*
+		 * Setting size to the length we want to write and wsize to 0
+		 * looks silly but that's how the SMC protocol works ¯\_(ツ)_/¯
+		 */
+		smc_size = wsize;
+		smc_wsize = 0;
+	} else if (!wsize && rsize) {
+		cmd = SMC_MSG_READ_KEY;
+		smc_size = rsize;
+		smc_wsize = 0;
+	} else {
+		return -EINVAL;
+	}
+
+	ret = apple_smc_cmd_locked(smc, cmd, key, smc_size, smc_wsize, &rdata);
+	if (ret < 0)
+		return ret;
+
+	if (rsize) {
+		/*
+		 * Small data <= 4 bytes is returned as part of the reply
+		 * message which is sent over the mailbox FIFO. Everything
+		 * bigger has to be copied from SRAM which is mapped as
+		 * Device memory.
+		 */
+		if (rsize <= 4)
+			memcpy(rbuf, &rdata, rsize);
+		else
+			memcpy_fromio(rbuf, smc->shmem.iomem, rsize);
+	}
+
+	return ret;
+}
+
+int apple_smc_read(struct apple_smc *smc, smc_key key, void *buf, size_t size)
+{
+	guard(mutex)(&smc->mutex);
+
+	return apple_smc_rw_locked(smc, key, NULL, 0, buf, size);
+}
+EXPORT_SYMBOL(apple_smc_read);
+
+int apple_smc_write(struct apple_smc *smc, smc_key key, void *buf, size_t size)
+{
+	guard(mutex)(&smc->mutex);
+
+	return apple_smc_rw_locked(smc, key, buf, size, NULL, 0);
+}
+EXPORT_SYMBOL(apple_smc_write);
+
+int apple_smc_rw(struct apple_smc *smc, smc_key key, void *wbuf, size_t wsize,
+		 void *rbuf, size_t rsize)
+{
+	guard(mutex)(&smc->mutex);
+
+	return apple_smc_rw_locked(smc, key, wbuf, wsize, rbuf, rsize);
+}
+EXPORT_SYMBOL(apple_smc_rw);
+
+int apple_smc_get_key_by_index(struct apple_smc *smc, int index, smc_key *key)
+{
+	int ret;
+
+	ret = apple_smc_cmd(smc, SMC_MSG_GET_KEY_BY_INDEX, index, 0, 0, key);
+
+	*key = swab32(*key);
+	return ret;
+}
+EXPORT_SYMBOL(apple_smc_get_key_by_index);
+
+int apple_smc_get_key_info(struct apple_smc *smc, smc_key key, struct apple_smc_key_info *info)
+{
+	u8 key_info[6];
+	int ret;
+
+	ret = apple_smc_cmd(smc, SMC_MSG_GET_KEY_INFO, key, 0, 0, NULL);
+	if (ret >= 0 && info) {
+		memcpy_fromio(key_info, smc->shmem.iomem, sizeof(key_info));
+		info->size = key_info[0];
+		info->type_code = get_unaligned_be32(&key_info[1]);
+		info->flags = key_info[5];
+	}
+	return ret;
+}
+EXPORT_SYMBOL(apple_smc_get_key_info);
+
+int apple_smc_enter_atomic(struct apple_smc *smc)
+{
+	guard(mutex)(&smc->mutex);
+
+	/*
+	 * Disable notifications since this is called before shutdown and no
+	 * notification handler will be able to handle the notification
+	 * using atomic operations only. Also ignore any failure here
+	 * because we're about to shut down or reboot anyway.
+	 * We can't use apple_smc_write_flag here since that would try to lock
+	 * smc->mutex again.
+	 */
+	const u8 flag = 0;
+
+	apple_smc_rw_locked(smc, SMC_KEY(NTAP), &flag, sizeof(flag), NULL, 0);
+
+	smc->atomic_mode = true;
+
+	return 0;
+}
+EXPORT_SYMBOL(apple_smc_enter_atomic);
+
+int apple_smc_write_atomic(struct apple_smc *smc, smc_key key, void *buf, size_t size)
+{
+	guard(spinlock_irqsave)(&smc->lock);
+	u8 result;
+	int ret;
+	u64 msg;
+
+	if (size > SMC_MAX_SIZE || size == 0)
+		return -EINVAL;
+
+	if (smc->boot_stage != APPLE_SMC_INITIALIZED)
+		return -EIO;
+	if (!smc->atomic_mode)
+		return -EIO;
+
+	memcpy_toio(smc->shmem.iomem, buf, size);
+	smc->msg_id = (smc->msg_id + 1) & 0xf;
+	msg = (FIELD_PREP(SMC_MSG, SMC_MSG_WRITE_KEY) |
+	       FIELD_PREP(SMC_SIZE, size) |
+	       FIELD_PREP(SMC_ID, smc->msg_id) |
+	       FIELD_PREP(SMC_DATA, key));
+	smc->atomic_pending = true;
+
+	ret = apple_rtkit_send_message(smc->rtk, SMC_ENDPOINT, msg, NULL, true);
+	if (ret < 0) {
+		dev_err(smc->dev, "Failed to send command (%d)\n", ret);
+		return ret;
+	}
+
+	while (smc->atomic_pending) {
+		ret = apple_rtkit_poll(smc->rtk);
+		if (ret < 0) {
+			dev_err(smc->dev, "RTKit poll failed (%llx)", msg);
+			return ret;
+		}
+		udelay(100);
+	}
+
+	if (FIELD_GET(SMC_ID, smc->cmd_ret) != smc->msg_id) {
+		dev_err(smc->dev, "Command sequence mismatch (expected %d, got %d)\n",
+			smc->msg_id, (unsigned int)FIELD_GET(SMC_ID, smc->cmd_ret));
+		return -EIO;
+	}
+
+	result = FIELD_GET(SMC_RESULT, smc->cmd_ret);
+	if (result)
+		return -EIO;
+
+	return FIELD_GET(SMC_SIZE, smc->cmd_ret);
+}
+EXPORT_SYMBOL(apple_smc_write_atomic);
+
+static void apple_smc_rtkit_crashed(void *cookie, const void *bfr, size_t bfr_len)
+{
+	struct apple_smc *smc = cookie;
+
+	smc->boot_stage = APPLE_SMC_ERROR_CRASHED;
+	dev_err(smc->dev, "SMC crashed! Your system will reboot in a few seconds...\n");
+}
+
+static int apple_smc_rtkit_shmem_setup(void *cookie, struct apple_rtkit_shmem *bfr)
+{
+	struct apple_smc *smc = cookie;
+	size_t bfr_end;
+
+	if (!bfr->iova) {
+		dev_err(smc->dev, "RTKit wants a RAM buffer\n");
+		return -EIO;
+	}
+
+	if (check_add_overflow(bfr->iova, bfr->size - 1, &bfr_end))
+		return -EFAULT;
+
+	if (bfr->iova < smc->sram->start || bfr->iova > smc->sram->end ||
+	    bfr_end > smc->sram->end) {
+		dev_err(smc->dev, "RTKit buffer request outside SRAM region: [0x%llx, 0x%llx]\n",
+			(unsigned long long)bfr->iova,
+			(unsigned long long)bfr_end);
+		return -EFAULT;
+	}
+
+	bfr->iomem = smc->sram_base + (bfr->iova - smc->sram->start);
+	bfr->is_mapped = true;
+
+	return 0;
+}
+
+static bool apple_smc_rtkit_recv_early(void *cookie, u8 endpoint, u64 message)
+{
+	struct apple_smc *smc = cookie;
+
+	if (endpoint != SMC_ENDPOINT) {
+		dev_warn(smc->dev, "Received message for unknown endpoint 0x%x\n", endpoint);
+		return false;
+	}
+
+	if (smc->boot_stage == APPLE_SMC_BOOTING) {
+		int ret;
+
+		smc->shmem.iova = message;
+		smc->shmem.size = SMC_SHMEM_SIZE;
+		ret = apple_smc_rtkit_shmem_setup(smc, &smc->shmem);
+		if (ret < 0) {
+			smc->boot_stage = APPLE_SMC_ERROR_NO_SHMEM;
+			dev_err(smc->dev, "Failed to initialize shared memory (%d)\n", ret);
+		} else {
+			smc->boot_stage = APPLE_SMC_INITIALIZED;
+		}
+		complete(&smc->init_done);
+	} else if (FIELD_GET(SMC_MSG, message) == SMC_MSG_NOTIFICATION) {
+		/* Handle these in the RTKit worker thread */
+		return false;
+	} else {
+		smc->cmd_ret = message;
+		if (smc->atomic_pending)
+			smc->atomic_pending = false;
+		else
+			complete(&smc->cmd_done);
+	}
+
+	return true;
+}
+
+static void apple_smc_rtkit_recv(void *cookie, u8 endpoint, u64 message)
+{
+	struct apple_smc *smc = cookie;
+
+	if (endpoint != SMC_ENDPOINT) {
+		dev_warn(smc->dev, "Received message for unknown endpoint 0x%x\n", endpoint);
+		return;
+	}
+
+	if (FIELD_GET(SMC_MSG, message) != SMC_MSG_NOTIFICATION) {
+		dev_warn(smc->dev, "Received unknown message from worker: 0x%llx\n", message);
+		return;
+	}
+
+	blocking_notifier_call_chain(&smc->event_handlers, FIELD_GET(SMC_DATA, message), NULL);
+}
+
+static const struct apple_rtkit_ops apple_smc_rtkit_ops = {
+	.crashed = apple_smc_rtkit_crashed,
+	.recv_message = apple_smc_rtkit_recv,
+	.recv_message_early = apple_smc_rtkit_recv_early,
+	.shmem_setup = apple_smc_rtkit_shmem_setup,
+};
+
+static void apple_smc_rtkit_shutdown(void *data)
+{
+	struct apple_smc *smc = data;
+
+	/* Shut down SMC firmware, if it's not completely wedged */
+	if (apple_rtkit_is_running(smc->rtk))
+		apple_rtkit_quiesce(smc->rtk);
+}
+
+static void apple_smc_disable_notifications(void *data)
+{
+	struct apple_smc *smc = data;
+
+	apple_smc_write_flag(smc, SMC_KEY(NTAP), false);
+}
+
+static int apple_smc_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct apple_smc *smc;
+	u32 count;
+	int ret;
+
+	smc = devm_kzalloc(dev, sizeof(*smc), GFP_KERNEL);
+	if (!smc)
+		return -ENOMEM;
+
+	smc->dev = &pdev->dev;
+	smc->sram_base = devm_platform_get_and_ioremap_resource(pdev, 1, &smc->sram);
+	if (IS_ERR(smc->sram_base))
+		return dev_err_probe(dev, PTR_ERR(smc->sram_base), "Failed to map SRAM region");
+
+	smc->rtk = devm_apple_rtkit_init(dev, smc, NULL, 0, &apple_smc_rtkit_ops);
+	if (IS_ERR(smc->rtk))
+		return dev_err_probe(dev, PTR_ERR(smc->rtk), "Failed to initialize RTKit");
+
+	smc->boot_stage = APPLE_SMC_BOOTING;
+	ret = apple_rtkit_wake(smc->rtk);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to wake up SMC");
+
+	ret = devm_add_action_or_reset(dev, apple_smc_rtkit_shutdown, smc);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to register rtkit shutdown action");
+
+	ret = apple_rtkit_start_ep(smc->rtk, SMC_ENDPOINT);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to start SMC endpoint");
+
+	init_completion(&smc->init_done);
+	init_completion(&smc->cmd_done);
+
+	ret = apple_rtkit_send_message(smc->rtk, SMC_ENDPOINT,
+				       FIELD_PREP(SMC_MSG, SMC_MSG_INITIALIZE), NULL, false);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to send init message");
+
+	if (wait_for_completion_timeout(&smc->init_done, msecs_to_jiffies(SMC_TIMEOUT_MS)) == 0) {
+		dev_err(dev, "Timed out initializing SMC");
+		return -ETIMEDOUT;
+	}
+
+	if (smc->boot_stage != APPLE_SMC_INITIALIZED) {
+		dev_err(dev, "SMC failed to boot successfully, boot stage=%d\n", smc->boot_stage);
+		return -EIO;
+	}
+
+	dev_set_drvdata(&pdev->dev, smc);
+	BLOCKING_INIT_NOTIFIER_HEAD(&smc->event_handlers);
+
+	ret = apple_smc_read_u32(smc, SMC_KEY(#KEY), &count);
+	if (ret)
+		return dev_err_probe(smc->dev, ret, "Failed to get key count");
+	smc->key_count = be32_to_cpu(count);
+
+	/* Enable notifications */
+	apple_smc_write_flag(smc, SMC_KEY(NTAP), true);
+	ret = devm_add_action_or_reset(dev, apple_smc_disable_notifications, smc);
+	if (ret)
+		return dev_err_probe(dev, ret, "Failed to register notification disable action");
+
+	ret = devm_mfd_add_devices(smc->dev, PLATFORM_DEVID_NONE,
+				   apple_smc_devs, ARRAY_SIZE(apple_smc_devs),
+				   NULL, 0, NULL);
+	if (ret)
+		return dev_err_probe(smc->dev, ret, "Failed to register sub-devices");
+
+
+	return 0;
+}
+
+static const struct of_device_id apple_smc_of_match[] = {
+	{ .compatible = "apple,smc" },
+	{},
+};
+MODULE_DEVICE_TABLE(of, apple_smc_of_match);
+
+static struct platform_driver apple_smc_driver = {
+	.driver = {
+		.name = "macsmc",
+		.of_match_table = apple_smc_of_match,
+	},
+	.probe = apple_smc_probe,
+};
+module_platform_driver(apple_smc_driver);
+
+MODULE_AUTHOR("Hector Martin <marcan@marcan.st>");
+MODULE_AUTHOR("Sven Peter <sven@kernel.org>");
+MODULE_LICENSE("Dual MIT/GPL");
+MODULE_DESCRIPTION("Apple SMC driver");
diff --git a/include/linux/mfd/macsmc.h b/include/linux/mfd/macsmc.h
new file mode 100644
index 000000000000..6b13f01a8592
--- /dev/null
+++ b/include/linux/mfd/macsmc.h
@@ -0,0 +1,279 @@
+/* SPDX-License-Identifier: GPL-2.0-only OR MIT */
+/*
+ * Apple SMC (System Management Controller) core definitions
+ *
+ * Copyright (C) The Asahi Linux Contributors
+ */
+
+#ifndef _LINUX_MFD_MACSMC_H
+#define _LINUX_MFD_MACSMC_H
+
+#include <linux/soc/apple/rtkit.h>
+
+/**
+ * typedef smc_key - Alias for u32 to be used for SMC keys
+ *
+ * SMC keys are 32bit integers containing packed ASCII characters in natural
+ * integer order, i.e. 0xAABBCCDD, which represent the FourCC ABCD.
+ * The SMC driver is designed with this assumption and ensures the right
+ * endianness is used when these are stored to memory and sent to or received
+ * from the actual SMC firmware (which can be done in either shared memory or
+ * as 64bit mailbox message on Apple Silicon).
+ * Internally, SMC stores these keys in a table sorted lexicographically and
+ * allows resolving an index into this table to the corresponding SMC key.
+ * Thus, storing keys as u32 is very convenient as it allows to e.g. use
+ * normal comparison operators which directly map to the natural order used
+ * by SMC firmware.
+ *
+ * This simple type alias is introduced to allow easy recognition of SMC key
+ * variables and arguments.
+ */
+typedef u32 smc_key;
+
+/**
+ * SMC_KEY - Convert FourCC SMC keys in source code to smc_key
+ *
+ * This macro can be used to easily define FourCC SMC keys in source code
+ * and convert these to u32 / smc_key, e.g. SMC_KEY(NTAP) will expand to
+ * 0x4e544150.
+ *
+ * @s: FourCC SMC key to be converted
+ */
+#define SMC_KEY(s) (smc_key)(_SMC_KEY(#s))
+#define _SMC_KEY(s) (((s)[0] << 24) | ((s)[1] << 16) | ((s)[2] << 8) | (s)[3])
+
+#define APPLE_SMC_READABLE BIT(7)
+#define APPLE_SMC_WRITABLE BIT(6)
+#define APPLE_SMC_FUNCTION BIT(4)
+
+/**
+ * struct apple_smc_key_info - Information for a SMC key as returned by SMC
+ * @type_code: FourCC code indicating the type for this key.
+ *             Known types:
+ *              ch8*: ASCII string
+ *              flag: Boolean, 1 or 0
+ *              flt: 32-bit single-precision IEEE 754 float
+ *              hex: Binary data
+ *              ioft: 64bit Unsigned fixed-point intger (48.16)
+ *              {si,ui}{8,16,32,64}: Signed/Unsigned 8-/16-/32-/64-bit integer
+ * @size: Size of the buffer associated with this key
+ * @flags: Bitfield encoding flags (APPLE_SMC_{READABLE,WRITABLE,FUNCTION})
+ */
+struct apple_smc_key_info {
+	u32 type_code;
+	u8 size;
+	u8 flags;
+};
+
+/**
+ * enum apple_smc_boot_stage - SMC boot stage
+ * @APPLE_SMC_BOOTING: SMC is booting
+ * @APPLE_SMC_INITIALIZED: SMC is initialized and ready to use
+ * @APPLE_SMC_ERROR_NO_SHMEM: Shared memory could not be initialized during boot
+ * @APPLE_SMC_ERROR_CRASHED: SMC has crashed
+ */
+enum apple_smc_boot_stage {
+	APPLE_SMC_BOOTING,
+	APPLE_SMC_INITIALIZED,
+	APPLE_SMC_ERROR_NO_SHMEM,
+	APPLE_SMC_ERROR_CRASHED
+};
+
+/**
+ * struct apple_smc
+ * @dev: Underlying device struct for the physical backend device
+ * @key_count: Number of available SMC keys
+ * @first_key: First valid SMC key
+ * @last_key: Last valid SMC key
+ * @event_handlers: Notifier call chain for events received from SMC
+ * @rtk: Pointer to Apple RTKit instance
+ * @init_done: Completion for initialization
+ * @boot_stage: Current boot stage of SMC
+ * @sram: Pointer to SRAM resource
+ * @sram_base: SRAM base address
+ * @shmem: RTKit shared memory structure for SRAM
+ * @msg_id: Current message id for commands, will be incremented for each command
+ * @atomic_mode: Flag set when atomic mode is entered
+ * @atomic_pending: Flag indicating pending atomic command
+ * @cmd_done: Completion for command execution in non-atomic mode
+ * @cmd_ret: Return value from SMC for last command
+ * @mutex: Mutex for non-atomic mode
+ * @lock: Spinlock for atomic mode
+ */
+struct apple_smc {
+	struct device *dev;
+
+	u32 key_count;
+	smc_key first_key;
+	smc_key last_key;
+
+	struct blocking_notifier_head event_handlers;
+
+	struct apple_rtkit *rtk;
+
+	struct completion init_done;
+	enum apple_smc_boot_stage boot_stage;
+
+	struct resource *sram;
+	void __iomem *sram_base;
+	struct apple_rtkit_shmem shmem;
+
+	unsigned int msg_id;
+
+	bool atomic_mode;
+	bool atomic_pending;
+	struct completion cmd_done;
+	u64 cmd_ret;
+
+	struct mutex mutex;
+	spinlock_t lock;
+};
+
+/**
+ * apple_smc_read - Read size bytes from given SMC key into buf
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key to be read
+ * @buf: Buffer into which size bytes of data will be read from SMC
+ * @size: Number of bytes to be read into buf
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_read(struct apple_smc *smc, smc_key key, void *buf, size_t size);
+
+/**
+ * apple_smc_write - Write size bytes into given SMC key from buf
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key data will be written to
+ * @buf: Buffer from which size bytes of data will be written to SMC
+ * @size: Number of bytes to be written
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_write(struct apple_smc *smc, smc_key key, void *buf, size_t size);
+
+/**
+ * apple_smc_enter_atomic - Enter atomic mode to be able to use apple_smc_write_atomic
+ * @smc: Pointer to apple_smc struct
+ *
+ * This function switches the SMC backend to atomic mode which allows the
+ * use of apple_smc_write_atomic while disabling *all* other functions.
+ * This is only used for shutdown/reboot which requires writing to a SMC
+ * key from atomic context.
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_enter_atomic(struct apple_smc *smc);
+
+/**
+ * apple_smc_write_atomic - Write size bytes into given SMC key from buf without sleeping
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key data will be written to
+ * @buf: Buffer from which size bytes of data will be written to SMC
+ * @size: Number of bytes to be written
+ *
+ * Note that this function will fail if apple_smc_enter_atomic hasn't been
+ * called before.
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_write_atomic(struct apple_smc *smc, smc_key key, void *buf, size_t size);
+
+/**
+ * apple_smc_rw - Write and then read using the given SMC key
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key data will be written to
+ * @wbuf: Buffer from which size bytes of data will be written to SMC
+ * @wsize: Number of bytes to be written
+ * @rbuf: Buffer to which size bytes of data will be read from SMC
+ * @rsize: Number of bytes to be read
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_rw(struct apple_smc *smc, smc_key key, void *wbuf, size_t wsize,
+		 void *rbuf, size_t rsize);
+
+/**
+ * apple_smc_get_key_by_index - Given an index return the corresponding SMC key
+ * @smc: Pointer to apple_smc struct
+ * @index: Index to be resolved
+ * @key: Buffer for SMC key to be returned
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_get_key_by_index(struct apple_smc *smc, int index, smc_key *key);
+
+/**
+ * apple_smc_get_key_info - Get key information from SMC
+ * @smc: Pointer to apple_smc struct
+ * @key: Key to acquire information for
+ * @info: Pointer to struct apple_smc_key_info which will be filled
+ *
+ * Return: Zero on success, negative errno on error
+ */
+int apple_smc_get_key_info(struct apple_smc *smc, smc_key key, struct apple_smc_key_info *info);
+
+/**
+ * apple_smc_key_exists - Check if the given SMC key exists
+ * @smc: Pointer to apple_smc struct
+ * @key: smc_key to be checked
+ *
+ * Return: True if the key exists, false otherwise
+ */
+static inline bool apple_smc_key_exists(struct apple_smc *smc, smc_key key)
+{
+	return apple_smc_get_key_info(smc, key, NULL) >= 0;
+}
+
+#define APPLE_SMC_TYPE_OPS(type) \
+	static inline int apple_smc_read_##type(struct apple_smc *smc, smc_key key, type *p) \
+	{ \
+		int ret = apple_smc_read(smc, key, p, sizeof(*p)); \
+		return (ret < 0) ? ret : ((ret != sizeof(*p)) ? -EINVAL : 0); \
+	} \
+	static inline int apple_smc_write_##type(struct apple_smc *smc, smc_key key, type p) \
+	{ \
+		return apple_smc_write(smc, key, &p, sizeof(p)); \
+	} \
+	static inline int apple_smc_write_##type##_atomic(struct apple_smc *smc, smc_key key, type p) \
+	{ \
+		return apple_smc_write_atomic(smc, key, &p, sizeof(p)); \
+	} \
+	static inline int apple_smc_rw_##type(struct apple_smc *smc, smc_key key, \
+					      type w, type *r) \
+	{ \
+		int ret = apple_smc_rw(smc, key, &w, sizeof(w), r, sizeof(*r)); \
+		return (ret < 0) ? ret : ((ret != sizeof(*r)) ? -EINVAL : 0); \
+	}
+
+APPLE_SMC_TYPE_OPS(u64)
+APPLE_SMC_TYPE_OPS(u32)
+APPLE_SMC_TYPE_OPS(u16)
+APPLE_SMC_TYPE_OPS(u8)
+APPLE_SMC_TYPE_OPS(s64)
+APPLE_SMC_TYPE_OPS(s32)
+APPLE_SMC_TYPE_OPS(s16)
+APPLE_SMC_TYPE_OPS(s8)
+
+static inline int apple_smc_read_flag(struct apple_smc *smc, smc_key key, bool *flag)
+{
+	u8 val;
+	int ret = apple_smc_read_u8(smc, key, &val);
+
+	if (ret < 0)
+		return ret;
+
+	*flag = val ? true : false;
+	return ret;
+}
+
+static inline int apple_smc_write_flag(struct apple_smc *smc, smc_key key, bool state)
+{
+	return apple_smc_write_u8(smc, key, state ? 1 : 0);
+}
+
+static inline int apple_smc_write_flag_atomic(struct apple_smc *smc, smc_key key, bool state)
+{
+	return apple_smc_write_u8_atomic(smc, key, state ? 1 : 0);
+}
+
+#endif
-- 
cgit v1.2.3


From 897e8601b9cff1d054cdd53047f568b0e1995726 Mon Sep 17 00:00:00 2001
From: Halil Pasic <pasic@linux.ibm.com>
Date: Tue, 22 Jul 2025 18:18:17 +0200
Subject: s390/ism: fix concurrency management in ism_cmd()

The s390x ISM device data sheet clearly states that only one
request-response sequence is allowable per ISM function at any point in
time.  Unfortunately as of today the s390/ism driver in Linux does not
honor that requirement. This patch aims to rectify that.

This problem was discovered based on Aliaksei's bug report which states
that for certain workloads the ISM functions end up entering error state
(with PEC 2 as seen from the logs) after a while and as a consequence
connections handled by the respective function break, and for future
connection requests the ISM device is not considered -- given it is in a
dysfunctional state. During further debugging PEC 3A was observed as
well.

A kernel message like
[ 1211.244319] zpci: 061a:00:00.0: Event 0x2 reports an error for PCI function 0x61a
is a reliable indicator of the stated function entering error state
with PEC 2. Let me also point out that a kernel message like
[ 1211.244325] zpci: 061a:00:00.0: The ism driver bound to the device does not support error recovery
is a reliable indicator that the ISM function won't be auto-recovered
because the ISM driver currently lacks support for it.

On a technical level, without this synchronization, commands (inputs to
the FW) may be partially or fully overwritten (corrupted) by another CPU
trying to issue commands on the same function. There is hard evidence that
this can lead to DMB token values being used as DMB IOVAs, leading to
PEC 2 PCI events indicating invalid DMA. But this is only one of the
failure modes imaginable. In theory even completely losing one command
and executing another one twice and then trying to interpret the outputs
as if the command we intended to execute was actually executed and not
the other one is also possible.  Frankly, I don't feel confident about
providing an exhaustive list of possible consequences.

Fixes: 684b89bc39ce ("s390/ism: add device driver for internal shared memory")
Reported-by: Aliaksei Makarau <Aliaksei.Makarau@ibm.com>
Tested-by: Mahanta Jambigi <mjambigi@linux.ibm.com>
Tested-by: Aliaksei Makarau <Aliaksei.Makarau@ibm.com>
Signed-off-by: Halil Pasic <pasic@linux.ibm.com>
Reviewed-by: Alexandra Winter <wintera@linux.ibm.com>
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250722161817.1298473-1-wintera@linux.ibm.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/s390/net/ism_drv.c | 3 +++
 include/linux/ism.h        | 1 +
 2 files changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/s390/net/ism_drv.c b/drivers/s390/net/ism_drv.c
index b7f15f303ea2..967dc4f9eea8 100644
--- a/drivers/s390/net/ism_drv.c
+++ b/drivers/s390/net/ism_drv.c
@@ -130,6 +130,7 @@ static int ism_cmd(struct ism_dev *ism, void *cmd)
 	struct ism_req_hdr *req = cmd;
 	struct ism_resp_hdr *resp = cmd;
 
+	spin_lock(&ism->cmd_lock);
 	__ism_write_cmd(ism, req + 1, sizeof(*req), req->len - sizeof(*req));
 	__ism_write_cmd(ism, req, 0, sizeof(*req));
 
@@ -143,6 +144,7 @@ static int ism_cmd(struct ism_dev *ism, void *cmd)
 	}
 	__ism_read_cmd(ism, resp + 1, sizeof(*resp), resp->len - sizeof(*resp));
 out:
+	spin_unlock(&ism->cmd_lock);
 	return resp->ret;
 }
 
@@ -606,6 +608,7 @@ static int ism_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 		return -ENOMEM;
 
 	spin_lock_init(&ism->lock);
+	spin_lock_init(&ism->cmd_lock);
 	dev_set_drvdata(&pdev->dev, ism);
 	ism->pdev = pdev;
 	ism->dev.parent = &pdev->dev;
diff --git a/include/linux/ism.h b/include/linux/ism.h
index 5428edd90982..8358b4cd7ba6 100644
--- a/include/linux/ism.h
+++ b/include/linux/ism.h
@@ -28,6 +28,7 @@ struct ism_dmb {
 
 struct ism_dev {
 	spinlock_t lock; /* protects the ism device */
+	spinlock_t cmd_lock; /* serializes cmds */
 	struct list_head list;
 	struct pci_dev *pdev;
 
-- 
cgit v1.2.3


From fe473fba6435f631a4c7459c02057bf57457e128 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sat, 7 Jun 2025 21:22:32 +0100
Subject: mfd: twl6030-irq: Remove unused twl6030_mmc_card_detect*

twl6030_mmc_card_detect() and twl6030_mmc_card_detect_config() have been
unused since 2013's commit b2ff4790612b ("ARM: OMAP2+: Remove legacy
omap4_twl6030_hsmmc_init")

Remove them.

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Link: https://lore.kernel.org/r/20250607202232.265344-1-linux@treblig.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/twl6030-irq.c | 74 -----------------------------------------------
 include/linux/mfd/twl.h   | 21 --------------
 2 files changed, 95 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/twl6030-irq.c b/drivers/mfd/twl6030-irq.c
index 00b14cef1dfb..ffb4b98639c7 100644
--- a/drivers/mfd/twl6030-irq.c
+++ b/drivers/mfd/twl6030-irq.c
@@ -256,80 +256,6 @@ int twl6030_interrupt_mask(u8 bit_mask, u8 offset)
 }
 EXPORT_SYMBOL(twl6030_interrupt_mask);
 
-int twl6030_mmc_card_detect_config(void)
-{
-	int ret;
-	u8 reg_val = 0;
-
-	/* Unmasking the Card detect Interrupt line for MMC1 from Phoenix */
-	twl6030_interrupt_unmask(TWL6030_MMCDETECT_INT_MASK,
-						REG_INT_MSK_LINE_B);
-	twl6030_interrupt_unmask(TWL6030_MMCDETECT_INT_MASK,
-						REG_INT_MSK_STS_B);
-	/*
-	 * Initially Configuring MMC_CTRL for receiving interrupts &
-	 * Card status on TWL6030 for MMC1
-	 */
-	ret = twl_i2c_read_u8(TWL6030_MODULE_ID0, &reg_val, TWL6030_MMCCTRL);
-	if (ret < 0) {
-		pr_err("twl6030: Failed to read MMCCTRL, error %d\n", ret);
-		return ret;
-	}
-	reg_val &= ~VMMC_AUTO_OFF;
-	reg_val |= SW_FC;
-	ret = twl_i2c_write_u8(TWL6030_MODULE_ID0, reg_val, TWL6030_MMCCTRL);
-	if (ret < 0) {
-		pr_err("twl6030: Failed to write MMCCTRL, error %d\n", ret);
-		return ret;
-	}
-
-	/* Configuring PullUp-PullDown register */
-	ret = twl_i2c_read_u8(TWL6030_MODULE_ID0, &reg_val,
-						TWL6030_CFG_INPUT_PUPD3);
-	if (ret < 0) {
-		pr_err("twl6030: Failed to read CFG_INPUT_PUPD3, error %d\n",
-									ret);
-		return ret;
-	}
-	reg_val &= ~(MMC_PU | MMC_PD);
-	ret = twl_i2c_write_u8(TWL6030_MODULE_ID0, reg_val,
-						TWL6030_CFG_INPUT_PUPD3);
-	if (ret < 0) {
-		pr_err("twl6030: Failed to write CFG_INPUT_PUPD3, error %d\n",
-									ret);
-		return ret;
-	}
-
-	return irq_find_mapping(twl6030_irq->irq_domain,
-				 MMCDETECT_INTR_OFFSET);
-}
-EXPORT_SYMBOL(twl6030_mmc_card_detect_config);
-
-int twl6030_mmc_card_detect(struct device *dev, int slot)
-{
-	int ret = -EIO;
-	u8 read_reg = 0;
-	struct platform_device *pdev = to_platform_device(dev);
-
-	if (pdev->id) {
-		/* TWL6030 provide's Card detect support for
-		 * only MMC1 controller.
-		 */
-		pr_err("Unknown MMC controller %d in %s\n", pdev->id, __func__);
-		return ret;
-	}
-	/*
-	 * BIT0 of MMC_CTRL on TWL6030 provides card status for MMC1
-	 * 0 - Card not present ,1 - Card present
-	 */
-	ret = twl_i2c_read_u8(TWL6030_MODULE_ID0, &read_reg,
-						TWL6030_MMCCTRL);
-	if (ret >= 0)
-		ret = read_reg & STS_MMC;
-	return ret;
-}
-EXPORT_SYMBOL(twl6030_mmc_card_detect);
-
 static int twl6030_irq_map(struct irq_domain *d, unsigned int virq,
 			      irq_hw_number_t hwirq)
 {
diff --git a/include/linux/mfd/twl.h b/include/linux/mfd/twl.h
index 85dc406173db..b31e07fa4d51 100644
--- a/include/linux/mfd/twl.h
+++ b/include/linux/mfd/twl.h
@@ -205,27 +205,6 @@ int twl_get_hfclk_rate(void);
 int twl6030_interrupt_unmask(u8 bit_mask, u8 offset);
 int twl6030_interrupt_mask(u8 bit_mask, u8 offset);
 
-/* Card detect Configuration for MMC1 Controller on OMAP4 */
-#ifdef CONFIG_TWL4030_CORE
-int twl6030_mmc_card_detect_config(void);
-#else
-static inline int twl6030_mmc_card_detect_config(void)
-{
-	pr_debug("twl6030_mmc_card_detect_config not supported\n");
-	return 0;
-}
-#endif
-
-/* MMC1 Controller on OMAP4 uses Phoenix irq for Card detect */
-#ifdef CONFIG_TWL4030_CORE
-int twl6030_mmc_card_detect(struct device *dev, int slot);
-#else
-static inline int twl6030_mmc_card_detect(struct device *dev, int slot)
-{
-	pr_debug("Call back twl6030_mmc_card_detect not supported\n");
-	return -EIO;
-}
-#endif
 /*----------------------------------------------------------------------*/
 
 /*
-- 
cgit v1.2.3


From ea39dd2638ff6920c342313db98dbc152e815ecd Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 21 Jun 2025 20:30:51 +0200
Subject: mfd: tps65219: Remove an unused field from 'struct tps65219'

Since commit 3df4c6367520 ("mfd: tps65219: Add support for soft shutdown
via sys-off API"), the 'nb' field from 'struct tps65219' is unused.
Remove it.

Also remove the now useless #include <linux/notifier.h> for the same
reason.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/8a264c3a92b8e62c1dadd374f2685030e042eb08.1750530460.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Lee Jones <lee@kernel.org>
---
 include/linux/mfd/tps65219.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/tps65219.h b/include/linux/mfd/tps65219.h
index 3e8d29189267..690002932377 100644
--- a/include/linux/mfd/tps65219.h
+++ b/include/linux/mfd/tps65219.h
@@ -10,7 +10,6 @@
 #define MFD_TPS65219_H
 
 #include <linux/bitops.h>
-#include <linux/notifier.h>
 #include <linux/regmap.h>
 #include <linux/regulator/driver.h>
 
@@ -440,7 +439,6 @@ enum tps65219_irqs {
  * @regmap: Regmap for accessing the device registers
  * @chip_id: Chip ID
  * @irq_data: Regmap irq data used for the irq chip
- * @nb: notifier block for the restart handler
  */
 struct tps65219 {
 	struct device *dev;
@@ -448,7 +446,6 @@ struct tps65219 {
 
 	unsigned int chip_id;
 	struct regmap_irq_chip_data *irq_data;
-	struct notifier_block nb;
 };
 
 #endif /* MFD_TPS65219_H */
-- 
cgit v1.2.3


From 83f9afe4689d96279d9ade6c1cce36fa86e8ac63 Mon Sep 17 00:00:00 2001
From: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Date: Sat, 21 Jun 2025 20:30:52 +0200
Subject: mfd: tps65219: Remove another unused field from 'struct tps65219'

The 'chip_id' field from 'struct tps65219' is unused.
Remove it.

Signed-off-by: Christophe JAILLET <christophe.jaillet@wanadoo.fr>
Link: https://lore.kernel.org/r/f20443e6e13b0b101648a41010a19ee56589fa0b.1750530460.git.christophe.jaillet@wanadoo.fr
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/tps65219.c       | 5 +++--
 include/linux/mfd/tps65219.h | 2 --
 2 files changed, 3 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/tps65219.c b/drivers/mfd/tps65219.c
index 83b8ab4707c2..65a952555218 100644
--- a/drivers/mfd/tps65219.c
+++ b/drivers/mfd/tps65219.c
@@ -477,6 +477,7 @@ static int tps65219_probe(struct i2c_client *client)
 {
 	struct tps65219 *tps;
 	const struct tps65219_chip_data *pmic;
+	unsigned int chip_id;
 	bool pwr_button;
 	int ret;
 
@@ -487,8 +488,8 @@ static int tps65219_probe(struct i2c_client *client)
 	i2c_set_clientdata(client, tps);
 
 	tps->dev = &client->dev;
-	tps->chip_id = (uintptr_t)i2c_get_match_data(client);
-	pmic = &chip_info_table[tps->chip_id];
+	chip_id = (uintptr_t)i2c_get_match_data(client);
+	pmic = &chip_info_table[chip_id];
 
 	tps->regmap = devm_regmap_init_i2c(client, &tps65219_regmap_config);
 	if (IS_ERR(tps->regmap)) {
diff --git a/include/linux/mfd/tps65219.h b/include/linux/mfd/tps65219.h
index 690002932377..55234e771ba7 100644
--- a/include/linux/mfd/tps65219.h
+++ b/include/linux/mfd/tps65219.h
@@ -437,14 +437,12 @@ enum tps65219_irqs {
  *
  * @dev: MFD device
  * @regmap: Regmap for accessing the device registers
- * @chip_id: Chip ID
  * @irq_data: Regmap irq data used for the irq chip
  */
 struct tps65219 {
 	struct device *dev;
 	struct regmap *regmap;
 
-	unsigned int chip_id;
 	struct regmap_irq_chip_data *irq_data;
 };
 
-- 
cgit v1.2.3


From e403cdf0704b7b1fedaf4ed5f05cc814dffbd6d5 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 1 Jul 2025 15:56:25 +0100
Subject: mfd: pcf50633: Remove the header file core.h

The patches to remove all of the pieces of the pcf50633
have gone in and we're left with the header.

Remove it.

The pcf50633 was used as part of the OpenMoko devices but
the support for its main chip was recently removed in:
commit 61b7f8920b17 ("ARM: s3c: remove all s3c24xx support")

See https://lore.kernel.org/all/Z8z236h4B5A6Ki3D@gallifrey/

Signed-off-by: "Dr. David Alan Gilbert" <linux@treblig.org>
Link: https://lore.kernel.org/r/20250701145625.204048-1-linux@treblig.org
Signed-off-by: Lee Jones <lee@kernel.org>
---
 include/linux/mfd/pcf50633/core.h | 229 --------------------------------------
 1 file changed, 229 deletions(-)
 delete mode 100644 include/linux/mfd/pcf50633/core.h

(limited to 'include/linux')

diff --git a/include/linux/mfd/pcf50633/core.h b/include/linux/mfd/pcf50633/core.h
deleted file mode 100644
index 42d2b0e4884e..000000000000
--- a/include/linux/mfd/pcf50633/core.h
+++ /dev/null
@@ -1,229 +0,0 @@
-/* SPDX-License-Identifier: GPL-2.0-or-later */
-/*
- * core.h  -- Core driver for NXP PCF50633
- *
- * (C) 2006-2008 by Openmoko, Inc.
- * All rights reserved.
- */
-
-#ifndef __LINUX_MFD_PCF50633_CORE_H
-#define __LINUX_MFD_PCF50633_CORE_H
-
-#include <linux/i2c.h>
-#include <linux/workqueue.h>
-#include <linux/regulator/driver.h>
-#include <linux/regulator/machine.h>
-#include <linux/pm.h>
-#include <linux/power_supply.h>
-
-struct pcf50633;
-struct regmap;
-
-#define PCF50633_NUM_REGULATORS	11
-
-struct pcf50633_platform_data {
-	struct regulator_init_data reg_init_data[PCF50633_NUM_REGULATORS];
-
-	char **batteries;
-	int num_batteries;
-
-	/*
-	 * Should be set accordingly to the reference resistor used, see
-	 * I_{ch(ref)} charger reference current in the pcf50633 User
-	 * Manual.
-	 */
-	int charger_reference_current_ma;
-
-	/* Callbacks */
-	void (*probe_done)(struct pcf50633 *);
-	void (*mbc_event_callback)(struct pcf50633 *, int);
-	void (*regulator_registered)(struct pcf50633 *, int);
-	void (*force_shutdown)(struct pcf50633 *);
-
-	u8 resumers[5];
-};
-
-struct pcf50633_irq {
-	void (*handler) (int, void *);
-	void *data;
-};
-
-int pcf50633_register_irq(struct pcf50633 *pcf, int irq,
-			void (*handler) (int, void *), void *data);
-int pcf50633_free_irq(struct pcf50633 *pcf, int irq);
-
-int pcf50633_irq_mask(struct pcf50633 *pcf, int irq);
-int pcf50633_irq_unmask(struct pcf50633 *pcf, int irq);
-int pcf50633_irq_mask_get(struct pcf50633 *pcf, int irq);
-
-int pcf50633_read_block(struct pcf50633 *, u8 reg,
-					int nr_regs, u8 *data);
-int pcf50633_write_block(struct pcf50633 *pcf, u8 reg,
-					int nr_regs, u8 *data);
-u8 pcf50633_reg_read(struct pcf50633 *, u8 reg);
-int pcf50633_reg_write(struct pcf50633 *pcf, u8 reg, u8 val);
-
-int pcf50633_reg_set_bit_mask(struct pcf50633 *pcf, u8 reg, u8 mask, u8 val);
-int pcf50633_reg_clear_bits(struct pcf50633 *pcf, u8 reg, u8 bits);
-
-/* Interrupt registers */
-
-#define PCF50633_REG_INT1	0x02
-#define PCF50633_REG_INT2	0x03
-#define PCF50633_REG_INT3	0x04
-#define PCF50633_REG_INT4	0x05
-#define PCF50633_REG_INT5	0x06
-
-#define PCF50633_REG_INT1M	0x07
-#define PCF50633_REG_INT2M	0x08
-#define PCF50633_REG_INT3M	0x09
-#define PCF50633_REG_INT4M	0x0a
-#define PCF50633_REG_INT5M	0x0b
-
-enum {
-	/* Chip IRQs */
-	PCF50633_IRQ_ADPINS,
-	PCF50633_IRQ_ADPREM,
-	PCF50633_IRQ_USBINS,
-	PCF50633_IRQ_USBREM,
-	PCF50633_IRQ_RESERVED1,
-	PCF50633_IRQ_RESERVED2,
-	PCF50633_IRQ_ALARM,
-	PCF50633_IRQ_SECOND,
-	PCF50633_IRQ_ONKEYR,
-	PCF50633_IRQ_ONKEYF,
-	PCF50633_IRQ_EXTON1R,
-	PCF50633_IRQ_EXTON1F,
-	PCF50633_IRQ_EXTON2R,
-	PCF50633_IRQ_EXTON2F,
-	PCF50633_IRQ_EXTON3R,
-	PCF50633_IRQ_EXTON3F,
-	PCF50633_IRQ_BATFULL,
-	PCF50633_IRQ_CHGHALT,
-	PCF50633_IRQ_THLIMON,
-	PCF50633_IRQ_THLIMOFF,
-	PCF50633_IRQ_USBLIMON,
-	PCF50633_IRQ_USBLIMOFF,
-	PCF50633_IRQ_ADCRDY,
-	PCF50633_IRQ_ONKEY1S,
-	PCF50633_IRQ_LOWSYS,
-	PCF50633_IRQ_LOWBAT,
-	PCF50633_IRQ_HIGHTMP,
-	PCF50633_IRQ_AUTOPWRFAIL,
-	PCF50633_IRQ_DWN1PWRFAIL,
-	PCF50633_IRQ_DWN2PWRFAIL,
-	PCF50633_IRQ_LEDPWRFAIL,
-	PCF50633_IRQ_LEDOVP,
-	PCF50633_IRQ_LDO1PWRFAIL,
-	PCF50633_IRQ_LDO2PWRFAIL,
-	PCF50633_IRQ_LDO3PWRFAIL,
-	PCF50633_IRQ_LDO4PWRFAIL,
-	PCF50633_IRQ_LDO5PWRFAIL,
-	PCF50633_IRQ_LDO6PWRFAIL,
-	PCF50633_IRQ_HCLDOPWRFAIL,
-	PCF50633_IRQ_HCLDOOVL,
-
-	/* Always last */
-	PCF50633_NUM_IRQ,
-};
-
-struct pcf50633 {
-	struct device *dev;
-	struct regmap *regmap;
-
-	struct pcf50633_platform_data *pdata;
-	int irq;
-	struct pcf50633_irq irq_handler[PCF50633_NUM_IRQ];
-	struct work_struct irq_work;
-	struct workqueue_struct *work_queue;
-	struct mutex lock;
-
-	u8 mask_regs[5];
-
-	u8 suspend_irq_masks[5];
-	u8 resume_reason[5];
-	int is_suspended;
-
-	int onkey1s_held;
-
-	struct platform_device *rtc_pdev;
-	struct platform_device *mbc_pdev;
-	struct platform_device *adc_pdev;
-	struct platform_device *input_pdev;
-	struct platform_device *bl_pdev;
-	struct platform_device *regulator_pdev[PCF50633_NUM_REGULATORS];
-};
-
-enum pcf50633_reg_int1 {
-	PCF50633_INT1_ADPINS	= 0x01,	/* Adapter inserted */
-	PCF50633_INT1_ADPREM	= 0x02,	/* Adapter removed */
-	PCF50633_INT1_USBINS	= 0x04,	/* USB inserted */
-	PCF50633_INT1_USBREM	= 0x08,	/* USB removed */
-	/* reserved */
-	PCF50633_INT1_ALARM	= 0x40, /* RTC alarm time is reached */
-	PCF50633_INT1_SECOND	= 0x80,	/* RTC periodic second interrupt */
-};
-
-enum pcf50633_reg_int2 {
-	PCF50633_INT2_ONKEYR	= 0x01, /* ONKEY rising edge */
-	PCF50633_INT2_ONKEYF	= 0x02, /* ONKEY falling edge */
-	PCF50633_INT2_EXTON1R	= 0x04, /* EXTON1 rising edge */
-	PCF50633_INT2_EXTON1F	= 0x08, /* EXTON1 falling edge */
-	PCF50633_INT2_EXTON2R	= 0x10, /* EXTON2 rising edge */
-	PCF50633_INT2_EXTON2F	= 0x20, /* EXTON2 falling edge */
-	PCF50633_INT2_EXTON3R	= 0x40, /* EXTON3 rising edge */
-	PCF50633_INT2_EXTON3F	= 0x80, /* EXTON3 falling edge */
-};
-
-enum pcf50633_reg_int3 {
-	PCF50633_INT3_BATFULL	= 0x01, /* Battery full */
-	PCF50633_INT3_CHGHALT	= 0x02,	/* Charger halt */
-	PCF50633_INT3_THLIMON	= 0x04,
-	PCF50633_INT3_THLIMOFF	= 0x08,
-	PCF50633_INT3_USBLIMON	= 0x10,
-	PCF50633_INT3_USBLIMOFF	= 0x20,
-	PCF50633_INT3_ADCRDY	= 0x40, /* ADC result ready */
-	PCF50633_INT3_ONKEY1S	= 0x80,	/* ONKEY pressed 1 second */
-};
-
-enum pcf50633_reg_int4 {
-	PCF50633_INT4_LOWSYS		= 0x01,
-	PCF50633_INT4_LOWBAT		= 0x02,
-	PCF50633_INT4_HIGHTMP		= 0x04,
-	PCF50633_INT4_AUTOPWRFAIL	= 0x08,
-	PCF50633_INT4_DWN1PWRFAIL	= 0x10,
-	PCF50633_INT4_DWN2PWRFAIL	= 0x20,
-	PCF50633_INT4_LEDPWRFAIL	= 0x40,
-	PCF50633_INT4_LEDOVP		= 0x80,
-};
-
-enum pcf50633_reg_int5 {
-	PCF50633_INT5_LDO1PWRFAIL	= 0x01,
-	PCF50633_INT5_LDO2PWRFAIL	= 0x02,
-	PCF50633_INT5_LDO3PWRFAIL	= 0x04,
-	PCF50633_INT5_LDO4PWRFAIL	= 0x08,
-	PCF50633_INT5_LDO5PWRFAIL	= 0x10,
-	PCF50633_INT5_LDO6PWRFAIL	= 0x20,
-	PCF50633_INT5_HCLDOPWRFAIL	= 0x40,
-	PCF50633_INT5_HCLDOOVL		= 0x80,
-};
-
-/* misc. registers */
-#define PCF50633_REG_OOCSHDWN	0x0c
-
-/* LED registers */
-#define PCF50633_REG_LEDOUT 0x28
-#define PCF50633_REG_LEDENA 0x29
-#define PCF50633_REG_LEDCTL 0x2a
-#define PCF50633_REG_LEDDIM 0x2b
-
-static inline struct pcf50633 *dev_to_pcf50633(struct device *dev)
-{
-	return dev_get_drvdata(dev);
-}
-
-int pcf50633_irq_init(struct pcf50633 *pcf, int irq);
-void pcf50633_irq_free(struct pcf50633 *pcf);
-extern const struct dev_pm_ops pcf50633_pm;
-
-#endif
-- 
cgit v1.2.3


From c371040f31ab63de992c7d811ffc4c7d450b46a5 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 26 Jun 2025 18:43:54 +0300
Subject: mfd: davinci_voicecodec: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250626154354.324439-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 include/linux/mfd/davinci_voicecodec.h | 8 +++++---
 1 file changed, 5 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/davinci_voicecodec.h b/include/linux/mfd/davinci_voicecodec.h
index 556375b91316..9acd703dd5ca 100644
--- a/include/linux/mfd/davinci_voicecodec.h
+++ b/include/linux/mfd/davinci_voicecodec.h
@@ -10,11 +10,13 @@
 #ifndef __LINUX_MFD_DAVINCI_VOICECODEC_H_
 #define __LINUX_MFD_DAVINCI_VOICECODEC_H_
 
-#include <linux/kernel.h>
-#include <linux/platform_device.h>
+#include <linux/bits.h>
 #include <linux/mfd/core.h>
-#include <linux/platform_data/edma.h>
+#include <linux/types.h>
 
+struct clk;
+struct device;
+struct platform_device;
 struct regmap;
 
 /*
-- 
cgit v1.2.3


From dd1902b6e90508b4243af930db933ea3d26d2981 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 26 Jun 2025 18:59:51 +0300
Subject: mfd: wm8350-core: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20250626155951.325683-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 include/linux/mfd/wm8350/core.h | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/wm8350/core.h b/include/linux/mfd/wm8350/core.h
index a3241e4d7548..5f70d3b5d1b1 100644
--- a/include/linux/mfd/wm8350/core.h
+++ b/include/linux/mfd/wm8350/core.h
@@ -8,11 +8,12 @@
 #ifndef __LINUX_MFD_WM8350_CORE_H_
 #define __LINUX_MFD_WM8350_CORE_H_
 
-#include <linux/kernel.h>
-#include <linux/mutex.h>
-#include <linux/interrupt.h>
 #include <linux/completion.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/mutex.h>
 #include <linux/regmap.h>
+#include <linux/types.h>
 
 #include <linux/mfd/wm8350/audio.h>
 #include <linux/mfd/wm8350/gpio.h>
@@ -21,6 +22,9 @@
 #include <linux/mfd/wm8350/supply.h>
 #include <linux/mfd/wm8350/wdt.h>
 
+struct device;
+struct platform_device;
+
 /*
  * Register values.
  */
-- 
cgit v1.2.3


From dd394515d18aedd379e8dc886cb8286e1714f735 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 26 Jun 2025 18:45:44 +0300
Subject: mfd: madera: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Reviewed-by: Charles Keepax <ckeepax@opensource.cirrus.com>
Link: https://lore.kernel.org/r/20250626154544.324724-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 include/linux/mfd/madera/pdata.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/mfd/madera/pdata.h b/include/linux/mfd/madera/pdata.h
index 32e3470708ed..7e84738cbb20 100644
--- a/include/linux/mfd/madera/pdata.h
+++ b/include/linux/mfd/madera/pdata.h
@@ -8,10 +8,11 @@
 #ifndef MADERA_PDATA_H
 #define MADERA_PDATA_H
 
-#include <linux/kernel.h>
 #include <linux/regulator/arizona-ldo1.h>
 #include <linux/regulator/arizona-micsupp.h>
 #include <linux/regulator/machine.h>
+#include <linux/types.h>
+
 #include <sound/madera-pdata.h>
 
 #define MADERA_MAX_MICBIAS		4
-- 
cgit v1.2.3


From b9ec71fbd572042770df16c9b65bbf91cbd556cf Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Fri, 27 Jun 2025 19:43:58 +0300
Subject: mfd: syscon: atmel-smc: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Link: https://lore.kernel.org/r/20250627164414.1043434-1-andriy.shevchenko@linux.intel.com
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/atmel-smc.c              | 9 ++++++++-
 include/linux/mfd/syscon/atmel-smc.h | 8 +++++---
 2 files changed, 13 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mfd/atmel-smc.c b/drivers/mfd/atmel-smc.c
index 4628ca14e766..0a5b42c83f17 100644
--- a/drivers/mfd/atmel-smc.c
+++ b/drivers/mfd/atmel-smc.c
@@ -8,9 +8,16 @@
  * Author: Boris Brezillon <boris.brezillon@free-electrons.com>
  */
 
-#include <linux/mfd/syscon/atmel-smc.h>
+#include <linux/bits.h>
+#include <linux/err.h>
+#include <linux/export.h>
+#include <linux/mod_devicetable.h>
+#include <linux/of.h>
+#include <linux/regmap.h>
 #include <linux/string.h>
 
+#include <linux/mfd/syscon/atmel-smc.h>
+
 /**
  * atmel_smc_cs_conf_init - initialize a SMC CS conf
  * @conf: the SMC CS conf to initialize
diff --git a/include/linux/mfd/syscon/atmel-smc.h b/include/linux/mfd/syscon/atmel-smc.h
index e9e24f4c4578..9b9119c742a2 100644
--- a/include/linux/mfd/syscon/atmel-smc.h
+++ b/include/linux/mfd/syscon/atmel-smc.h
@@ -11,9 +11,11 @@
 #ifndef _LINUX_MFD_SYSCON_ATMEL_SMC_H_
 #define _LINUX_MFD_SYSCON_ATMEL_SMC_H_
 
-#include <linux/kernel.h>
-#include <linux/of.h>
-#include <linux/regmap.h>
+#include <linux/bits.h>
+#include <linux/types.h>
+
+struct device_node;
+struct regmap;
 
 #define ATMEL_SMC_SETUP(cs)			(((cs) * 0x10))
 #define ATMEL_HSMC_SETUP(layout, cs)		\
-- 
cgit v1.2.3


From db8db85cff331eb5a520a18a606692ff85405c3d Mon Sep 17 00:00:00 2001
From: Quentin Schulz <quentin.schulz@cherry.de>
Date: Fri, 27 Jun 2025 12:53:54 +0200
Subject: mfd: rk8xx-core: Allow to customize RK806 reset mode

The RK806 PMIC has a bitfield for configuring the restart/reset behavior
(which I assume Rockchip calls "function") whenever the PMIC is reset
either programmatically (c.f. DEV_RST in the datasheet) or via PWRCTRL
or RESETB pins.

For RK806, the following values are possible for RST_FUN:

0b00 means "Restart PMU"
0b01 means "Reset all the power off reset registers, forcing
	the state to switch to ACTIVE mode"
0b10 means "Reset all the power off reset registers, forcing
	the state to switch to ACTIVE mode, and simultaneously
	pull down the RESETB PIN for 5mS before releasing"
0b11 means the same as for 0b10 just above.

This adds the appropriate logic in the driver to parse the new
rockchip,reset-mode DT property to pass this information. It just
happens that the values in the binding match the values to write in the
bitfield so no mapping is necessary.

If it is missing, the register is left untouched and relies either on
the silicon default or on whatever was set earlier in the boot stages
(e.g. the bootloader).

Signed-off-by: Quentin Schulz <quentin.schulz@cherry.de>
Link: https://lore.kernel.org/r/20250627-rk8xx-rst-fun-v4-2-ce05d041b45f@cherry.de
Signed-off-by: Lee Jones <lee@kernel.org>
---
 drivers/mfd/rk8xx-core.c  | 12 ++++++++++++
 include/linux/mfd/rk808.h |  2 ++
 2 files changed, 14 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/mfd/rk8xx-core.c b/drivers/mfd/rk8xx-core.c
index 71c2b80a4678..def4587fdfb8 100644
--- a/drivers/mfd/rk8xx-core.c
+++ b/drivers/mfd/rk8xx-core.c
@@ -10,6 +10,7 @@
  * Author: Wadim Egorov <w.egorov@phytec.de>
  */
 
+#include <linux/bitfield.h>
 #include <linux/interrupt.h>
 #include <linux/mfd/rk808.h>
 #include <linux/mfd/core.h>
@@ -699,6 +700,7 @@ int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap
 	const struct mfd_cell *cells;
 	int dual_support = 0;
 	int nr_pre_init_regs;
+	u32 rst_fun = 0;
 	int nr_cells;
 	int ret;
 	int i;
@@ -726,6 +728,16 @@ int rk8xx_probe(struct device *dev, int variant, unsigned int irq, struct regmap
 		cells = rk806s;
 		nr_cells = ARRAY_SIZE(rk806s);
 		dual_support = IRQF_SHARED;
+
+		ret = device_property_read_u32(dev, "rockchip,reset-mode", &rst_fun);
+		if (ret)
+			break;
+
+		ret = regmap_update_bits(rk808->regmap, RK806_SYS_CFG3, RK806_RST_FUN_MSK,
+					 FIELD_PREP(RK806_RST_FUN_MSK, rst_fun));
+		if (ret)
+			return dev_err_probe(dev, ret,
+					     "Failed to configure requested restart/reset behavior\n");
 		break;
 	case RK808_ID:
 		rk808->regmap_irq_chip = &rk808_irq_chip;
diff --git a/include/linux/mfd/rk808.h b/include/linux/mfd/rk808.h
index 69cbea78b430..28170ee08898 100644
--- a/include/linux/mfd/rk808.h
+++ b/include/linux/mfd/rk808.h
@@ -812,6 +812,8 @@ enum rk806_pin_dr_sel {
 #define RK806_INT_POL_H			BIT(1)
 #define RK806_INT_POL_L			0
 
+/* SYS_CFG3 */
+#define RK806_RST_FUN_MSK		GENMASK(7, 6)
 #define RK806_SLAVE_RESTART_FUN_MSK	BIT(1)
 #define RK806_SLAVE_RESTART_FUN_EN	BIT(1)
 #define RK806_SLAVE_RESTART_FUN_OFF	0
-- 
cgit v1.2.3


From 678bae2eaa812662929a83b3de399645e9de93ad Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Tue, 22 Jul 2025 17:35:43 +0200
Subject: gpiolib: make legacy interfaces optional

The traditional interfaces are only used on a small number of ancient
boards. Make these optional now so they can be disabled by default.

Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Alexander Sverdlin <alexander.sverdlin@gmail.com>
Link: https://lore.kernel.org/r/20250722153634.3683927-1-arnd@kernel.org
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/Kconfig  |  3 +++
 drivers/gpio/Makefile |  2 +-
 include/linux/gpio.h  | 10 ++++++----
 3 files changed, 10 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 6e3c3f0e3dcf..500d839f65ee 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -14,6 +14,9 @@ menuconfig GPIOLIB
 
 if GPIOLIB
 
+config GPIOLIB_LEGACY
+	def_bool y
+
 config GPIOLIB_FASTPATH_LIMIT
 	int "Maximum number of GPIOs for fast path"
 	range 32 512
diff --git a/drivers/gpio/Makefile b/drivers/gpio/Makefile
index 3e5bc90ba59e..379f55e9ed1e 100644
--- a/drivers/gpio/Makefile
+++ b/drivers/gpio/Makefile
@@ -5,7 +5,7 @@ ccflags-$(CONFIG_DEBUG_GPIO)	+= -DDEBUG
 
 obj-$(CONFIG_GPIOLIB)		+= gpiolib.o
 obj-$(CONFIG_GPIOLIB)		+= gpiolib-devres.o
-obj-$(CONFIG_GPIOLIB)		+= gpiolib-legacy.o
+obj-$(CONFIG_GPIOLIB_LEGACY)	+= gpiolib-legacy.o
 obj-$(CONFIG_OF_GPIO)		+= gpiolib-of.o
 obj-$(CONFIG_GPIO_CDEV)		+= gpiolib-cdev.o
 obj-$(CONFIG_GPIO_SYSFS)	+= gpiolib-sysfs.o
diff --git a/include/linux/gpio.h b/include/linux/gpio.h
index ff99ed76fdc3..8f85ddb26429 100644
--- a/include/linux/gpio.h
+++ b/include/linux/gpio.h
@@ -13,6 +13,11 @@
 #define __LINUX_GPIO_H
 
 #include <linux/types.h>
+#ifdef CONFIG_GPIOLIB
+#include <linux/gpio/consumer.h>
+#endif
+
+#ifdef CONFIG_GPIOLIB_LEGACY
 
 struct device;
 
@@ -22,9 +27,6 @@ struct device;
 #define GPIOF_OUT_INIT_HIGH	((0 << 0) | (1 << 1))
 
 #ifdef CONFIG_GPIOLIB
-
-#include <linux/gpio/consumer.h>
-
 /*
  * "valid" GPIO numbers are nonnegative and may be passed to
  * setup routines like gpio_request().  Only some valid numbers
@@ -170,5 +172,5 @@ static inline int devm_gpio_request_one(struct device *dev, unsigned gpio,
 }
 
 #endif /* ! CONFIG_GPIOLIB */
-
+#endif /* CONFIG_GPIOLIB_LEGACY */
 #endif /* __LINUX_GPIO_H */
-- 
cgit v1.2.3


From fdb7f139864aa332ea8f161beb636dc0599c64f2 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Mon, 16 Jun 2025 13:29:56 -0700
Subject: ice, libie: move generic adminq descriptors to lib

The descriptor structure is the same in ice, ixgbe and i40e. Move it to
common libie header to use it across different driver.

Leave device specific adminq commands in separate folders. This lead to
a change that need to be done in filling/getting descriptor:
- previous: struct specific_desc *cmd;
	    cmd = &desc.params.specific_desc;
- now: struct specific_desc *cmd;
       cmd = libie_aq_raw(&desc);

Do this changes across the driver to allow clean build. The casting only
have to be done in case of specific descriptors, for generic one union
can still be used.

Changes beside code moving:
- change ICE_ prefix to LIBIE_ prefix (ice_ and libie_ too)
- remove shift variables not otherwise needed (in libie_aq_flags)
- fill/get descriptor data based on desc.params.raw whenever the
  descriptor isn't defined in libie
- move defines from the libie_aq_sth structure outside
- add libie_aq_raw helper and use it instead of explicit casting

Reviewed by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/health.c |   4 +-
 drivers/net/ethernet/intel/ice/ice.h            |   2 +-
 drivers/net/ethernet/intel/ice/ice_adminq_cmd.h | 270 +----------------
 drivers/net/ethernet/intel/ice/ice_common.c     | 384 ++++++++++++------------
 drivers/net/ethernet/intel/ice/ice_common.h     |   6 +-
 drivers/net/ethernet/intel/ice/ice_controlq.c   |  53 ++--
 drivers/net/ethernet/intel/ice/ice_controlq.h   |   8 +-
 drivers/net/ethernet/intel/ice/ice_dcb.c        |  36 +--
 drivers/net/ethernet/intel/ice/ice_dcb_lib.c    |   2 +-
 drivers/net/ethernet/intel/ice/ice_ddp.c        |  47 +--
 drivers/net/ethernet/intel/ice/ice_dpll.c       |   4 +-
 drivers/net/ethernet/intel/ice/ice_fw_update.c  |  24 +-
 drivers/net/ethernet/intel/ice/ice_fwlog.c      |  16 +-
 drivers/net/ethernet/intel/ice/ice_lag.c        |   4 +-
 drivers/net/ethernet/intel/ice/ice_lib.c        |   6 +-
 drivers/net/ethernet/intel/ice/ice_main.c       |  38 +--
 drivers/net/ethernet/intel/ice/ice_nvm.c        |  38 +--
 drivers/net/ethernet/intel/ice/ice_ptp_hw.c     |  16 +-
 drivers/net/ethernet/intel/ice/ice_sched.c      |  18 +-
 drivers/net/ethernet/intel/ice/ice_sriov.c      |   4 +-
 drivers/net/ethernet/intel/ice/ice_switch.c     |  55 ++--
 drivers/net/ethernet/intel/ice/ice_vf_mbx.c     |   6 +-
 drivers/net/ethernet/intel/ice/ice_virtchnl.c   |   2 +-
 drivers/net/ethernet/intel/ice/ice_vlan_mode.c  |   6 +-
 include/linux/net/intel/libie/adminq.h          | 273 +++++++++++++++++
 25 files changed, 673 insertions(+), 649 deletions(-)
 create mode 100644 include/linux/net/intel/libie/adminq.h

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/ice/devlink/health.c b/drivers/net/ethernet/intel/ice/devlink/health.c
index 19c3d37aa768..b149b8185449 100644
--- a/drivers/net/ethernet/intel/ice/devlink/health.c
+++ b/drivers/net/ethernet/intel/ice/devlink/health.c
@@ -217,10 +217,12 @@ static void ice_config_health_events(struct ice_pf *pf, bool enable)
 void ice_process_health_status_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 {
 	const struct ice_aqc_health_status_elem *health_info;
+	const struct ice_aqc_get_health_status *cmd;
 	u16 count;
 
 	health_info = (struct ice_aqc_health_status_elem *)event->msg_buf;
-	count = le16_to_cpu(event->desc.params.get_health_status.health_status_count);
+	cmd = libie_aq_raw(&event->desc);
+	count = le16_to_cpu(cmd->health_status_count);
 
 	if (count > (event->buf_len / sizeof(*health_info))) {
 		dev_err(ice_pf_to_dev(pf), "Received a health status event with invalid element count\n");
diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
index 657e1f608f1a..2c35782c7800 100644
--- a/drivers/net/ethernet/intel/ice/ice.h
+++ b/drivers/net/ethernet/intel/ice/ice.h
@@ -960,7 +960,7 @@ int ice_plug_aux_dev(struct ice_pf *pf);
 void ice_unplug_aux_dev(struct ice_pf *pf);
 int ice_init_rdma(struct ice_pf *pf);
 void ice_deinit_rdma(struct ice_pf *pf);
-const char *ice_aq_str(enum ice_aq_err aq_err);
+const char *ice_aq_str(enum libie_aq_err aq_err);
 bool ice_is_wol_supported(struct ice_hw *hw);
 void ice_fdir_del_all_fltrs(struct ice_vsi *vsi);
 int
diff --git a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
index 39d99c2f7976..3bd3ea3af888 100644
--- a/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/ice/ice_adminq_cmd.h
@@ -4,6 +4,8 @@
 #ifndef _ICE_ADMINQ_CMD_H_
 #define _ICE_ADMINQ_CMD_H_
 
+#include <linux/net/intel/libie/adminq.h>
+
 /* This header file defines the Admin Queue commands, error codes and
  * descriptor format. It is shared between Firmware and Software.
  */
@@ -31,38 +33,6 @@ typedef struct __packed { u8 buf[ICE_TXQ_CTX_SZ]; } ice_txq_ctx_buf_t;
 
 typedef struct __packed { u8 buf[ICE_TXQ_CTX_FULL_SZ]; } ice_txq_ctx_buf_full_t;
 
-struct ice_aqc_generic {
-	__le32 param0;
-	__le32 param1;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
-/* Get version (direct 0x0001) */
-struct ice_aqc_get_ver {
-	__le32 rom_ver;
-	__le32 fw_build;
-	u8 fw_branch;
-	u8 fw_major;
-	u8 fw_minor;
-	u8 fw_patch;
-	u8 api_branch;
-	u8 api_major;
-	u8 api_minor;
-	u8 api_patch;
-};
-
-/* Send driver version (indirect 0x0002) */
-struct ice_aqc_driver_ver {
-	u8 major_ver;
-	u8 minor_ver;
-	u8 build_ver;
-	u8 subbuild_ver;
-	u8 reserved[4];
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
 /* Queue Shutdown (direct 0x0003) */
 struct ice_aqc_q_shutdown {
 	u8 driver_unloading;
@@ -70,94 +40,6 @@ struct ice_aqc_q_shutdown {
 	u8 reserved[15];
 };
 
-/* Request resource ownership (direct 0x0008)
- * Release resource ownership (direct 0x0009)
- */
-struct ice_aqc_req_res {
-	__le16 res_id;
-#define ICE_AQC_RES_ID_NVM		1
-#define ICE_AQC_RES_ID_SDP		2
-#define ICE_AQC_RES_ID_CHNG_LOCK	3
-#define ICE_AQC_RES_ID_GLBL_LOCK	4
-	__le16 access_type;
-#define ICE_AQC_RES_ACCESS_READ		1
-#define ICE_AQC_RES_ACCESS_WRITE	2
-
-	/* Upon successful completion, FW writes this value and driver is
-	 * expected to release resource before timeout. This value is provided
-	 * in milliseconds.
-	 */
-	__le32 timeout;
-#define ICE_AQ_RES_NVM_READ_DFLT_TIMEOUT_MS	3000
-#define ICE_AQ_RES_NVM_WRITE_DFLT_TIMEOUT_MS	180000
-#define ICE_AQ_RES_CHNG_LOCK_DFLT_TIMEOUT_MS	1000
-#define ICE_AQ_RES_GLBL_LOCK_DFLT_TIMEOUT_MS	3000
-	/* For SDP: pin ID of the SDP */
-	__le32 res_number;
-	/* Status is only used for ICE_AQC_RES_ID_GLBL_LOCK */
-	__le16 status;
-#define ICE_AQ_RES_GLBL_SUCCESS		0
-#define ICE_AQ_RES_GLBL_IN_PROG		1
-#define ICE_AQ_RES_GLBL_DONE		2
-	u8 reserved[2];
-};
-
-/* Get function capabilities (indirect 0x000A)
- * Get device capabilities (indirect 0x000B)
- */
-struct ice_aqc_list_caps {
-	u8 cmd_flags;
-	u8 pf_index;
-	u8 reserved[2];
-	__le32 count;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
-/* Device/Function buffer entry, repeated per reported capability */
-struct ice_aqc_list_caps_elem {
-	__le16 cap;
-#define ICE_AQC_CAPS_VALID_FUNCTIONS			0x0005
-#define ICE_AQC_CAPS_SRIOV				0x0012
-#define ICE_AQC_CAPS_VF					0x0013
-#define ICE_AQC_CAPS_VSI				0x0017
-#define ICE_AQC_CAPS_DCB				0x0018
-#define ICE_AQC_CAPS_RSS				0x0040
-#define ICE_AQC_CAPS_RXQS				0x0041
-#define ICE_AQC_CAPS_TXQS				0x0042
-#define ICE_AQC_CAPS_MSIX				0x0043
-#define ICE_AQC_CAPS_FD					0x0045
-#define ICE_AQC_CAPS_1588				0x0046
-#define ICE_AQC_CAPS_MAX_MTU				0x0047
-#define ICE_AQC_CAPS_NVM_VER				0x0048
-#define ICE_AQC_CAPS_PENDING_NVM_VER			0x0049
-#define ICE_AQC_CAPS_OROM_VER				0x004A
-#define ICE_AQC_CAPS_PENDING_OROM_VER			0x004B
-#define ICE_AQC_CAPS_NET_VER				0x004C
-#define ICE_AQC_CAPS_PENDING_NET_VER			0x004D
-#define ICE_AQC_CAPS_RDMA				0x0051
-#define ICE_AQC_CAPS_SENSOR_READING			0x0067
-#define ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
-#define ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT		0x0077
-#define ICE_AQC_CAPS_NVM_MGMT				0x0080
-#define ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE		0x0085
-#define ICE_AQC_CAPS_NAC_TOPOLOGY			0x0087
-#define ICE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
-#define ICE_AQC_BIT_ROCEV2_LAG				0x01
-#define ICE_AQC_BIT_SRIOV_LAG				0x02
-
-	u8 major_ver;
-	u8 minor_ver;
-	/* Number of resources described by this capability */
-	__le32 number;
-	/* Only meaningful for some types of resources */
-	__le32 logical_id;
-	/* Only meaningful for some types of resources */
-	__le32 phys_id;
-	__le64 rsvd1;
-	__le64 rsvd2;
-};
-
 /* Manage MAC address, read command - indirect (0x0107)
  * This struct is also used for the response
  */
@@ -2672,154 +2554,6 @@ struct ice_aqc_fw_log_cfg_resp {
 	u8 rsvd0;
 };
 
-/**
- * struct ice_aq_desc - Admin Queue (AQ) descriptor
- * @flags: ICE_AQ_FLAG_* flags
- * @opcode: AQ command opcode
- * @datalen: length in bytes of indirect/external data buffer
- * @retval: return value from firmware
- * @cookie_high: opaque data high-half
- * @cookie_low: opaque data low-half
- * @params: command-specific parameters
- *
- * Descriptor format for commands the driver posts on the Admin Transmit Queue
- * (ATQ). The firmware writes back onto the command descriptor and returns
- * the result of the command. Asynchronous events that are not an immediate
- * result of the command are written to the Admin Receive Queue (ARQ) using
- * the same descriptor format. Descriptors are in little-endian notation with
- * 32-bit words.
- */
-struct ice_aq_desc {
-	__le16 flags;
-	__le16 opcode;
-	__le16 datalen;
-	__le16 retval;
-	__le32 cookie_high;
-	__le32 cookie_low;
-	union {
-		u8 raw[16];
-		struct ice_aqc_generic generic;
-		struct ice_aqc_get_ver get_ver;
-		struct ice_aqc_driver_ver driver_ver;
-		struct ice_aqc_q_shutdown q_shutdown;
-		struct ice_aqc_req_res res_owner;
-		struct ice_aqc_manage_mac_read mac_read;
-		struct ice_aqc_manage_mac_write mac_write;
-		struct ice_aqc_clear_pxe clear_pxe;
-		struct ice_aqc_list_caps get_cap;
-		struct ice_aqc_get_phy_caps get_phy;
-		struct ice_aqc_set_phy_cfg set_phy;
-		struct ice_aqc_restart_an restart_an;
-		struct ice_aqc_set_phy_rec_clk_out set_phy_rec_clk_out;
-		struct ice_aqc_get_phy_rec_clk_out get_phy_rec_clk_out;
-		struct ice_aqc_get_sensor_reading get_sensor_reading;
-		struct ice_aqc_get_sensor_reading_resp get_sensor_reading_resp;
-		struct ice_aqc_gpio read_write_gpio;
-		struct ice_aqc_sff_eeprom read_write_sff_param;
-		struct ice_aqc_set_port_id_led set_port_id_led;
-		struct ice_aqc_get_port_options get_port_options;
-		struct ice_aqc_set_port_option set_port_option;
-		struct ice_aqc_get_sw_cfg get_sw_conf;
-		struct ice_aqc_set_port_params set_port_params;
-		struct ice_aqc_sw_rules sw_rules;
-		struct ice_aqc_add_get_recipe add_get_recipe;
-		struct ice_aqc_recipe_to_profile recipe_to_profile;
-		struct ice_aqc_get_topo get_topo;
-		struct ice_aqc_sched_elem_cmd sched_elem_cmd;
-		struct ice_aqc_query_txsched_res query_sched_res;
-		struct ice_aqc_query_port_ets port_ets;
-		struct ice_aqc_rl_profile rl_profile;
-		struct ice_aqc_nvm nvm;
-		struct ice_aqc_nvm_checksum nvm_checksum;
-		struct ice_aqc_nvm_pkg_data pkg_data;
-		struct ice_aqc_nvm_pass_comp_tbl pass_comp_tbl;
-		struct ice_aqc_pf_vf_msg virt;
-		struct ice_aqc_set_query_pfc_mode set_query_pfc_mode;
-		struct ice_aqc_lldp_get_mib lldp_get_mib;
-		struct ice_aqc_lldp_set_mib_change lldp_set_event;
-		struct ice_aqc_lldp_stop lldp_stop;
-		struct ice_aqc_lldp_start lldp_start;
-		struct ice_aqc_lldp_set_local_mib lldp_set_mib;
-		struct ice_aqc_lldp_stop_start_specific_agent lldp_agent_ctrl;
-		struct ice_aqc_lldp_filter_ctrl lldp_filter_ctrl;
-		struct ice_aqc_get_set_rss_lut get_set_rss_lut;
-		struct ice_aqc_get_set_rss_key get_set_rss_key;
-		struct ice_aqc_neigh_dev_req neigh_dev;
-		struct ice_aqc_add_txqs add_txqs;
-		struct ice_aqc_dis_txqs dis_txqs;
-		struct ice_aqc_cfg_txqs cfg_txqs;
-		struct ice_aqc_add_rdma_qset add_rdma_qset;
-		struct ice_aqc_add_get_update_free_vsi vsi_cmd;
-		struct ice_aqc_add_update_free_vsi_resp add_update_free_vsi_res;
-		struct ice_aqc_download_pkg download_pkg;
-		struct ice_aqc_get_cgu_input_measure get_cgu_input_measure;
-		struct ice_aqc_set_cgu_input_config set_cgu_input_config;
-		struct ice_aqc_get_cgu_input_config get_cgu_input_config;
-		struct ice_aqc_set_cgu_output_config set_cgu_output_config;
-		struct ice_aqc_get_cgu_output_config get_cgu_output_config;
-		struct ice_aqc_get_cgu_dpll_status get_cgu_dpll_status;
-		struct ice_aqc_set_cgu_dpll_config set_cgu_dpll_config;
-		struct ice_aqc_set_cgu_ref_prio set_cgu_ref_prio;
-		struct ice_aqc_get_cgu_ref_prio get_cgu_ref_prio;
-		struct ice_aqc_get_cgu_info get_cgu_info;
-		struct ice_aqc_driver_shared_params drv_shared_params;
-		struct ice_aqc_fw_log fw_log;
-		struct ice_aqc_set_mac_lb set_mac_lb;
-		struct ice_aqc_alloc_free_res_cmd sw_res_ctrl;
-		struct ice_aqc_set_mac_cfg set_mac_cfg;
-		struct ice_aqc_set_event_mask set_event_mask;
-		struct ice_aqc_get_link_status get_link_status;
-		struct ice_aqc_event_lan_overflow lan_overflow;
-		struct ice_aqc_get_link_topo get_link_topo;
-		struct ice_aqc_set_health_status_cfg set_health_status_cfg;
-		struct ice_aqc_get_health_status get_health_status;
-		struct ice_aqc_dnl_call_command dnl_call;
-		struct ice_aqc_i2c read_write_i2c;
-		struct ice_aqc_read_i2c_resp read_i2c_resp;
-		struct ice_aqc_get_set_tx_topo get_set_tx_topo;
-	} params;
-};
-
-/* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
-#define ICE_AQ_LG_BUF	512
-
-#define ICE_AQ_FLAG_DD_S	0
-#define ICE_AQ_FLAG_CMP_S	1
-#define ICE_AQ_FLAG_ERR_S	2
-#define ICE_AQ_FLAG_LB_S	9
-#define ICE_AQ_FLAG_RD_S	10
-#define ICE_AQ_FLAG_BUF_S	12
-#define ICE_AQ_FLAG_SI_S	13
-
-#define ICE_AQ_FLAG_DD		BIT(ICE_AQ_FLAG_DD_S)  /* 0x1    */
-#define ICE_AQ_FLAG_CMP		BIT(ICE_AQ_FLAG_CMP_S) /* 0x2    */
-#define ICE_AQ_FLAG_ERR		BIT(ICE_AQ_FLAG_ERR_S) /* 0x4    */
-#define ICE_AQ_FLAG_LB		BIT(ICE_AQ_FLAG_LB_S)  /* 0x200  */
-#define ICE_AQ_FLAG_RD		BIT(ICE_AQ_FLAG_RD_S)  /* 0x400  */
-#define ICE_AQ_FLAG_BUF		BIT(ICE_AQ_FLAG_BUF_S) /* 0x1000 */
-#define ICE_AQ_FLAG_SI		BIT(ICE_AQ_FLAG_SI_S)  /* 0x2000 */
-
-/* error codes */
-enum ice_aq_err {
-	ICE_AQ_RC_OK		= 0,  /* Success */
-	ICE_AQ_RC_EPERM		= 1,  /* Operation not permitted */
-	ICE_AQ_RC_ENOENT	= 2,  /* No such element */
-	ICE_AQ_RC_ESRCH		= 3,  /* Bad opcode */
-	ICE_AQ_RC_EAGAIN	= 8,  /* Try again */
-	ICE_AQ_RC_ENOMEM	= 9,  /* Out of memory */
-	ICE_AQ_RC_EBUSY		= 12, /* Device or resource busy */
-	ICE_AQ_RC_EEXIST	= 13, /* Object already exists */
-	ICE_AQ_RC_EINVAL	= 14, /* Invalid argument */
-	ICE_AQ_RC_ENOSPC	= 16, /* No space left or allocation failure */
-	ICE_AQ_RC_ENOSYS	= 17, /* Function not implemented */
-	ICE_AQ_RC_EMODE		= 21, /* Op not allowed in current dev mode */
-	ICE_AQ_RC_ENOSEC	= 24, /* Missing security manifest */
-	ICE_AQ_RC_EBADSIG	= 25, /* Bad RSA signature */
-	ICE_AQ_RC_ESVN		= 26, /* SVN number prohibits this package */
-	ICE_AQ_RC_EBADMAN	= 27, /* Manifest hash mismatch */
-	ICE_AQ_RC_EBADBUF	= 28, /* Buffer hash mismatches manifest */
-};
-
 /* Admin Queue command opcodes */
 enum ice_adminq_opc {
 	/* AQ commands */
diff --git a/drivers/net/ethernet/intel/ice/ice_common.c b/drivers/net/ethernet/intel/ice/ice_common.c
index b542e1e0f0c9..003d60a4db21 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.c
+++ b/drivers/net/ethernet/intel/ice/ice_common.c
@@ -248,7 +248,7 @@ static bool ice_is_pf_c827(struct ice_hw *hw)
  */
 int ice_clear_pf_cfg(struct ice_hw *hw)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_clear_pf_cfg);
 
@@ -276,12 +276,12 @@ ice_aq_manage_mac_read(struct ice_hw *hw, void *buf, u16 buf_size,
 {
 	struct ice_aqc_manage_mac_read_resp *resp;
 	struct ice_aqc_manage_mac_read *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 	u16 flags;
 	u8 i;
 
-	cmd = &desc.params.mac_read;
+	cmd = libie_aq_raw(&desc);
 
 	if (buf_size < sizeof(*resp))
 		return -EINVAL;
@@ -330,12 +330,12 @@ ice_aq_get_phy_caps(struct ice_port_info *pi, bool qual_mods, u8 report_mode,
 {
 	struct ice_aqc_get_phy_caps *cmd;
 	u16 pcaps_size = sizeof(*pcaps);
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	const char *prefix;
 	struct ice_hw *hw;
 	int status;
 
-	cmd = &desc.params.get_phy;
+	cmd = libie_aq_raw(&desc);
 
 	if (!pcaps || (report_mode & ~ICE_AQC_REPORT_MODE_M) || !pi)
 		return -EINVAL;
@@ -424,9 +424,9 @@ ice_aq_get_link_topo_handle(struct ice_port_info *pi, u8 node_type,
 			    struct ice_sq_cd *cd)
 {
 	struct ice_aqc_get_link_topo *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.get_link_topo;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
 
@@ -454,19 +454,20 @@ int
 ice_aq_get_netlist_node(struct ice_hw *hw, struct ice_aqc_get_link_topo *cmd,
 			u8 *node_part_number, u16 *node_handle)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_get_link_topo *resp;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
-	desc.params.get_link_topo = *cmd;
+	resp = libie_aq_raw(&desc);
+	*resp = *cmd;
 
 	if (ice_aq_send_cmd(hw, &desc, NULL, 0, NULL))
 		return -EINTR;
 
 	if (node_handle)
-		*node_handle =
-			le16_to_cpu(desc.params.get_link_topo.addr.handle);
+		*node_handle = le16_to_cpu(resp->addr.handle);
 	if (node_part_number)
-		*node_part_number = desc.params.get_link_topo.node_part_num;
+		*node_part_number = resp->node_part_num;
 
 	return 0;
 }
@@ -689,8 +690,8 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 	struct ice_link_status *li_old, *li;
 	enum ice_media_type *hw_media_type;
 	struct ice_fc_info *hw_fc_info;
+	struct libie_aq_desc desc;
 	bool tx_pause, rx_pause;
-	struct ice_aq_desc desc;
 	struct ice_hw *hw;
 	u16 cmd_flags;
 	int status;
@@ -705,7 +706,7 @@ ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_status);
 	cmd_flags = (ena_lse) ? ICE_AQ_LSE_ENA : ICE_AQ_LSE_DIS;
-	resp = &desc.params.get_link_status;
+	resp = libie_aq_raw(&desc);
 	resp->cmd_flags = cpu_to_le16(cmd_flags);
 	resp->lport_num = pi->lport;
 
@@ -834,9 +835,9 @@ int
 ice_aq_set_mac_cfg(struct ice_hw *hw, u16 max_frame_size, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_set_mac_cfg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_mac_cfg;
+	cmd = libie_aq_raw(&desc);
 
 	if (max_frame_size == 0)
 		return -EINVAL;
@@ -1707,7 +1708,7 @@ ice_sbq_send_cmd(struct ice_hw *hw, struct ice_sbq_cmd_desc *desc,
 		 void *buf, u16 buf_size, struct ice_sq_cd *cd)
 {
 	return ice_sq_send_cmd(hw, ice_get_sbq(hw),
-			       (struct ice_aq_desc *)desc, buf, buf_size, cd);
+			       (struct libie_aq_desc *)desc, buf, buf_size, cd);
 }
 
 /**
@@ -1792,10 +1793,10 @@ static bool ice_should_retry_sq_send_cmd(u16 opcode)
  */
 static int
 ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
-		      struct ice_aq_desc *desc, void *buf, u16 buf_size,
+		      struct libie_aq_desc *desc, void *buf, u16 buf_size,
 		      struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc_cpy;
+	struct libie_aq_desc desc_cpy;
 	bool is_cmd_for_retry;
 	u8 idx = 0;
 	u16 opcode;
@@ -1816,7 +1817,7 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		status = ice_sq_send_cmd(hw, cq, desc, buf, buf_size, cd);
 
 		if (!is_cmd_for_retry || !status ||
-		    hw->adminq.sq_last_status != ICE_AQ_RC_EBUSY)
+		    hw->adminq.sq_last_status != LIBIE_AQ_RC_EBUSY)
 			break;
 
 		memcpy(desc, &desc_cpy, sizeof(desc_cpy));
@@ -1839,10 +1840,10 @@ ice_sq_send_cmd_retry(struct ice_hw *hw, struct ice_ctl_q_info *cq,
  * Helper function to send FW Admin Queue commands to the FW Admin Queue.
  */
 int
-ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
+ice_aq_send_cmd(struct ice_hw *hw, struct libie_aq_desc *desc, void *buf,
 		u16 buf_size, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_req_res *cmd = &desc->params.res_owner;
+	struct libie_aqc_req_res *cmd = libie_aq_raw(desc);
 	bool lock_acquired = false;
 	int status;
 
@@ -1873,7 +1874,7 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
 	case ice_aqc_opc_get_recipe_to_profile:
 		break;
 	case ice_aqc_opc_release_res:
-		if (le16_to_cpu(cmd->res_id) == ICE_AQC_RES_ID_GLBL_LOCK)
+		if (le16_to_cpu(cmd->res_id) == LIBIE_AQC_RES_ID_GLBL_LOCK)
 			break;
 		fallthrough;
 	default:
@@ -1898,8 +1899,8 @@ ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc, void *buf,
  */
 int ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_get_ver *resp;
-	struct ice_aq_desc desc;
+	struct libie_aqc_get_ver *resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	resp = &desc.params.get_ver;
@@ -1935,8 +1936,8 @@ int
 ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv,
 		       struct ice_sq_cd *cd)
 {
-	struct ice_aqc_driver_ver *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aqc_driver_ver *cmd;
+	struct libie_aq_desc desc;
 	u16 len;
 
 	cmd = &desc.params.driver_ver;
@@ -1946,7 +1947,7 @@ ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv,
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_driver_ver);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	cmd->major_ver = dv->major_ver;
 	cmd->minor_ver = dv->minor_ver;
 	cmd->build_ver = dv->build_ver;
@@ -1971,9 +1972,9 @@ ice_aq_send_driver_ver(struct ice_hw *hw, struct ice_driver_ver *dv,
 int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading)
 {
 	struct ice_aqc_q_shutdown *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.q_shutdown;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_q_shutdown);
 
@@ -2014,8 +2015,8 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 	       enum ice_aq_res_access_type access, u8 sdp_number, u32 *timeout,
 	       struct ice_sq_cd *cd)
 {
-	struct ice_aqc_req_res *cmd_resp;
-	struct ice_aq_desc desc;
+	struct libie_aqc_req_res *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	cmd_resp = &desc.params.res_owner;
@@ -2037,20 +2038,20 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 	/* Global config lock response utilizes an additional status field.
 	 *
 	 * If the Global config lock resource is held by some other driver, the
-	 * command completes with ICE_AQ_RES_GLBL_IN_PROG in the status field
+	 * command completes with LIBIE_AQ_RES_GLBL_IN_PROG in the status field
 	 * and the timeout field indicates the maximum time the current owner
 	 * of the resource has to free it.
 	 */
 	if (res == ICE_GLOBAL_CFG_LOCK_RES_ID) {
-		if (le16_to_cpu(cmd_resp->status) == ICE_AQ_RES_GLBL_SUCCESS) {
+		if (le16_to_cpu(cmd_resp->status) == LIBIE_AQ_RES_GLBL_SUCCESS) {
 			*timeout = le32_to_cpu(cmd_resp->timeout);
 			return 0;
 		} else if (le16_to_cpu(cmd_resp->status) ==
-			   ICE_AQ_RES_GLBL_IN_PROG) {
+			   LIBIE_AQ_RES_GLBL_IN_PROG) {
 			*timeout = le32_to_cpu(cmd_resp->timeout);
 			return -EIO;
 		} else if (le16_to_cpu(cmd_resp->status) ==
-			   ICE_AQ_RES_GLBL_DONE) {
+			   LIBIE_AQ_RES_GLBL_DONE) {
 			return -EALREADY;
 		}
 
@@ -2063,7 +2064,7 @@ ice_aq_req_res(struct ice_hw *hw, enum ice_aq_res_ids res,
 	 * with a busy return value and the timeout field indicates the maximum
 	 * time the current owner of the resource has to free it.
 	 */
-	if (!status || hw->adminq.sq_last_status == ICE_AQ_RC_EBUSY)
+	if (!status || hw->adminq.sq_last_status == LIBIE_AQ_RC_EBUSY)
 		*timeout = le32_to_cpu(cmd_resp->timeout);
 
 	return status;
@@ -2082,8 +2083,8 @@ static int
 ice_aq_release_res(struct ice_hw *hw, enum ice_aq_res_ids res, u8 sdp_number,
 		   struct ice_sq_cd *cd)
 {
-	struct ice_aqc_req_res *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aqc_req_res *cmd;
+	struct libie_aq_desc desc;
 
 	cmd = &desc.params.res_owner;
 
@@ -2192,16 +2193,16 @@ int ice_aq_alloc_free_res(struct ice_hw *hw,
 			  enum ice_adminq_opc opc)
 {
 	struct ice_aqc_alloc_free_res_cmd *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.sw_res_ctrl;
+	cmd = libie_aq_raw(&desc);
 
 	if (!buf || buf_size < flex_array_size(buf, elem, 1))
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, opc);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->num_entries = cpu_to_le16(1);
 
@@ -2315,7 +2316,7 @@ static u32 ice_get_num_per_func(struct ice_hw *hw, u32 max)
  */
 static bool
 ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
-		      struct ice_aqc_list_caps_elem *elem, const char *prefix)
+		      struct libie_aqc_list_caps_elem *elem, const char *prefix)
 {
 	u32 logical_id = le32_to_cpu(elem->logical_id);
 	u32 phys_id = le32_to_cpu(elem->phys_id);
@@ -2324,17 +2325,17 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 	bool found = true;
 
 	switch (cap) {
-	case ICE_AQC_CAPS_VALID_FUNCTIONS:
+	case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
 		caps->valid_functions = number;
 		ice_debug(hw, ICE_DBG_INIT, "%s: valid_functions (bitmap) = %d\n", prefix,
 			  caps->valid_functions);
 		break;
-	case ICE_AQC_CAPS_SRIOV:
+	case LIBIE_AQC_CAPS_SRIOV:
 		caps->sr_iov_1_1 = (number == 1);
 		ice_debug(hw, ICE_DBG_INIT, "%s: sr_iov_1_1 = %d\n", prefix,
 			  caps->sr_iov_1_1);
 		break;
-	case ICE_AQC_CAPS_DCB:
+	case LIBIE_AQC_CAPS_DCB:
 		caps->dcb = (number == 1);
 		caps->active_tc_bitmap = logical_id;
 		caps->maxtc = phys_id;
@@ -2343,7 +2344,7 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 			  caps->active_tc_bitmap);
 		ice_debug(hw, ICE_DBG_INIT, "%s: maxtc = %d\n", prefix, caps->maxtc);
 		break;
-	case ICE_AQC_CAPS_RSS:
+	case LIBIE_AQC_CAPS_RSS:
 		caps->rss_table_size = number;
 		caps->rss_table_entry_width = logical_id;
 		ice_debug(hw, ICE_DBG_INIT, "%s: rss_table_size = %d\n", prefix,
@@ -2351,7 +2352,7 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: rss_table_entry_width = %d\n", prefix,
 			  caps->rss_table_entry_width);
 		break;
-	case ICE_AQC_CAPS_RXQS:
+	case LIBIE_AQC_CAPS_RXQS:
 		caps->num_rxq = number;
 		caps->rxq_first_id = phys_id;
 		ice_debug(hw, ICE_DBG_INIT, "%s: num_rxq = %d\n", prefix,
@@ -2359,7 +2360,7 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: rxq_first_id = %d\n", prefix,
 			  caps->rxq_first_id);
 		break;
-	case ICE_AQC_CAPS_TXQS:
+	case LIBIE_AQC_CAPS_TXQS:
 		caps->num_txq = number;
 		caps->txq_first_id = phys_id;
 		ice_debug(hw, ICE_DBG_INIT, "%s: num_txq = %d\n", prefix,
@@ -2367,7 +2368,7 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: txq_first_id = %d\n", prefix,
 			  caps->txq_first_id);
 		break;
-	case ICE_AQC_CAPS_MSIX:
+	case LIBIE_AQC_CAPS_MSIX:
 		caps->num_msix_vectors = number;
 		caps->msix_vector_first_id = phys_id;
 		ice_debug(hw, ICE_DBG_INIT, "%s: num_msix_vectors = %d\n", prefix,
@@ -2375,56 +2376,56 @@ ice_parse_common_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps,
 		ice_debug(hw, ICE_DBG_INIT, "%s: msix_vector_first_id = %d\n", prefix,
 			  caps->msix_vector_first_id);
 		break;
-	case ICE_AQC_CAPS_PENDING_NVM_VER:
+	case LIBIE_AQC_CAPS_PENDING_NVM_VER:
 		caps->nvm_update_pending_nvm = true;
 		ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_nvm\n", prefix);
 		break;
-	case ICE_AQC_CAPS_PENDING_OROM_VER:
+	case LIBIE_AQC_CAPS_PENDING_OROM_VER:
 		caps->nvm_update_pending_orom = true;
 		ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_orom\n", prefix);
 		break;
-	case ICE_AQC_CAPS_PENDING_NET_VER:
+	case LIBIE_AQC_CAPS_PENDING_NET_VER:
 		caps->nvm_update_pending_netlist = true;
 		ice_debug(hw, ICE_DBG_INIT, "%s: update_pending_netlist\n", prefix);
 		break;
-	case ICE_AQC_CAPS_NVM_MGMT:
+	case LIBIE_AQC_CAPS_NVM_MGMT:
 		caps->nvm_unified_update =
 			(number & ICE_NVM_MGMT_UNIFIED_UPD_SUPPORT) ?
 			true : false;
 		ice_debug(hw, ICE_DBG_INIT, "%s: nvm_unified_update = %d\n", prefix,
 			  caps->nvm_unified_update);
 		break;
-	case ICE_AQC_CAPS_RDMA:
+	case LIBIE_AQC_CAPS_RDMA:
 		if (IS_ENABLED(CONFIG_INFINIBAND_IRDMA))
 			caps->rdma = (number == 1);
 		ice_debug(hw, ICE_DBG_INIT, "%s: rdma = %d\n", prefix, caps->rdma);
 		break;
-	case ICE_AQC_CAPS_MAX_MTU:
+	case LIBIE_AQC_CAPS_MAX_MTU:
 		caps->max_mtu = number;
 		ice_debug(hw, ICE_DBG_INIT, "%s: max_mtu = %d\n",
 			  prefix, caps->max_mtu);
 		break;
-	case ICE_AQC_CAPS_PCIE_RESET_AVOIDANCE:
+	case LIBIE_AQC_CAPS_PCIE_RESET_AVOIDANCE:
 		caps->pcie_reset_avoidance = (number > 0);
 		ice_debug(hw, ICE_DBG_INIT,
 			  "%s: pcie_reset_avoidance = %d\n", prefix,
 			  caps->pcie_reset_avoidance);
 		break;
-	case ICE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT:
+	case LIBIE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT:
 		caps->reset_restrict_support = (number == 1);
 		ice_debug(hw, ICE_DBG_INIT,
 			  "%s: reset_restrict_support = %d\n", prefix,
 			  caps->reset_restrict_support);
 		break;
-	case ICE_AQC_CAPS_FW_LAG_SUPPORT:
-		caps->roce_lag = !!(number & ICE_AQC_BIT_ROCEV2_LAG);
+	case LIBIE_AQC_CAPS_FW_LAG_SUPPORT:
+		caps->roce_lag = !!(number & LIBIE_AQC_BIT_ROCEV2_LAG);
 		ice_debug(hw, ICE_DBG_INIT, "%s: roce_lag = %u\n",
 			  prefix, caps->roce_lag);
-		caps->sriov_lag = !!(number & ICE_AQC_BIT_SRIOV_LAG);
+		caps->sriov_lag = !!(number & LIBIE_AQC_BIT_SRIOV_LAG);
 		ice_debug(hw, ICE_DBG_INIT, "%s: sriov_lag = %u\n",
 			  prefix, caps->sriov_lag);
 		break;
-	case ICE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE:
+	case LIBIE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE:
 		caps->tx_sched_topo_comp_mode_en = (number == 1);
 		break;
 	default:
@@ -2478,7 +2479,7 @@ ice_recalc_port_limited_caps(struct ice_hw *hw, struct ice_hw_common_caps *caps)
  */
 static void
 ice_parse_vf_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
-		       struct ice_aqc_list_caps_elem *cap)
+		       struct libie_aqc_list_caps_elem *cap)
 {
 	u32 logical_id = le32_to_cpu(cap->logical_id);
 	u32 number = le32_to_cpu(cap->number);
@@ -2501,7 +2502,7 @@ ice_parse_vf_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
  */
 static void
 ice_parse_vsi_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
-			struct ice_aqc_list_caps_elem *cap)
+			struct libie_aqc_list_caps_elem *cap)
 {
 	func_p->guar_num_vsi = ice_get_num_per_func(hw, ICE_MAX_VSI);
 	ice_debug(hw, ICE_DBG_INIT, "func caps: guar_num_vsi (fw) = %d\n",
@@ -2520,7 +2521,7 @@ ice_parse_vsi_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
  */
 static void
 ice_parse_1588_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
-			 struct ice_aqc_list_caps_elem *cap)
+			 struct libie_aqc_list_caps_elem *cap)
 {
 	struct ice_ts_func_info *info = &func_p->ts_func_info;
 	u32 number = le32_to_cpu(cap->number);
@@ -2619,7 +2620,7 @@ static void
 ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 		    void *buf, u32 cap_count)
 {
-	struct ice_aqc_list_caps_elem *cap_resp;
+	struct libie_aqc_list_caps_elem *cap_resp;
 	u32 i;
 
 	cap_resp = buf;
@@ -2634,16 +2635,16 @@ ice_parse_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_p,
 					      &cap_resp[i], "func caps");
 
 		switch (cap) {
-		case ICE_AQC_CAPS_VF:
+		case LIBIE_AQC_CAPS_VF:
 			ice_parse_vf_func_caps(hw, func_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_VSI:
+		case LIBIE_AQC_CAPS_VSI:
 			ice_parse_vsi_func_caps(hw, func_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_1588:
+		case LIBIE_AQC_CAPS_1588:
 			ice_parse_1588_func_caps(hw, func_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_FD:
+		case LIBIE_AQC_CAPS_FD:
 			ice_parse_fdir_func_caps(hw, func_p);
 			break;
 		default:
@@ -2687,7 +2688,7 @@ static int ice_func_id_to_logical_id(u32 active_function_bitmap, u8 pf_id)
  */
 static void
 ice_parse_valid_functions_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-			      struct ice_aqc_list_caps_elem *cap)
+			      struct libie_aqc_list_caps_elem *cap)
 {
 	u32 number = le32_to_cpu(cap->number);
 
@@ -2708,7 +2709,7 @@ ice_parse_valid_functions_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_vf_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-		      struct ice_aqc_list_caps_elem *cap)
+		      struct libie_aqc_list_caps_elem *cap)
 {
 	u32 number = le32_to_cpu(cap->number);
 
@@ -2727,7 +2728,7 @@ ice_parse_vf_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_vsi_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-		       struct ice_aqc_list_caps_elem *cap)
+		       struct libie_aqc_list_caps_elem *cap)
 {
 	u32 number = le32_to_cpu(cap->number);
 
@@ -2746,7 +2747,7 @@ ice_parse_vsi_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-			struct ice_aqc_list_caps_elem *cap)
+			struct libie_aqc_list_caps_elem *cap)
 {
 	struct ice_ts_dev_info *info = &dev_p->ts_dev_info;
 	u32 logical_id = le32_to_cpu(cap->logical_id);
@@ -2807,7 +2808,7 @@ ice_parse_1588_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_fdir_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-			struct ice_aqc_list_caps_elem *cap)
+			struct libie_aqc_list_caps_elem *cap)
 {
 	u32 number = le32_to_cpu(cap->number);
 
@@ -2827,7 +2828,7 @@ ice_parse_fdir_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void
 ice_parse_sensor_reading_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
-			     struct ice_aqc_list_caps_elem *cap)
+			     struct libie_aqc_list_caps_elem *cap)
 {
 	dev_p->supported_sensors = le32_to_cpu(cap->number);
 
@@ -2846,7 +2847,7 @@ ice_parse_sensor_reading_cap(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
  */
 static void ice_parse_nac_topo_dev_caps(struct ice_hw *hw,
 					struct ice_hw_dev_caps *dev_p,
-					struct ice_aqc_list_caps_elem *cap)
+					struct libie_aqc_list_caps_elem *cap)
 {
 	dev_p->nac_topo.mode = le32_to_cpu(cap->number);
 	dev_p->nac_topo.id = le32_to_cpu(cap->phys_id) & ICE_NAC_TOPO_ID_M;
@@ -2882,7 +2883,7 @@ static void
 ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 		   void *buf, u32 cap_count)
 {
-	struct ice_aqc_list_caps_elem *cap_resp;
+	struct libie_aqc_list_caps_elem *cap_resp;
 	u32 i;
 
 	cap_resp = buf;
@@ -2897,25 +2898,25 @@ ice_parse_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_p,
 					      &cap_resp[i], "dev caps");
 
 		switch (cap) {
-		case ICE_AQC_CAPS_VALID_FUNCTIONS:
+		case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
 			ice_parse_valid_functions_cap(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_VF:
+		case LIBIE_AQC_CAPS_VF:
 			ice_parse_vf_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_VSI:
+		case LIBIE_AQC_CAPS_VSI:
 			ice_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_1588:
+		case LIBIE_AQC_CAPS_1588:
 			ice_parse_1588_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_FD:
+		case LIBIE_AQC_CAPS_FD:
 			ice_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_SENSOR_READING:
+		case LIBIE_AQC_CAPS_SENSOR_READING:
 			ice_parse_sensor_reading_cap(hw, dev_p, &cap_resp[i]);
 			break;
-		case ICE_AQC_CAPS_NAC_TOPOLOGY:
+		case LIBIE_AQC_CAPS_NAC_TOPOLOGY:
 			ice_parse_nac_topo_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
 		default:
@@ -3035,8 +3036,8 @@ int
 ice_aq_list_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count,
 		 enum ice_adminq_opc opc, struct ice_sq_cd *cd)
 {
-	struct ice_aqc_list_caps *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aqc_list_caps *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	cmd = &desc.params.get_cap;
@@ -3077,7 +3078,7 @@ ice_discover_dev_caps(struct ice_hw *hw, struct ice_hw_dev_caps *dev_caps)
 	 * device will return, we can simply send a 4KB buffer, the maximum
 	 * possible size that firmware can return.
 	 */
-	cap_count = ICE_AQ_MAX_BUF_LEN / sizeof(struct ice_aqc_list_caps_elem);
+	cap_count = ICE_AQ_MAX_BUF_LEN / sizeof(struct libie_aqc_list_caps_elem);
 
 	status = ice_aq_list_caps(hw, cbuf, ICE_AQ_MAX_BUF_LEN, &cap_count,
 				  ice_aqc_opc_list_dev_caps, NULL);
@@ -3111,7 +3112,7 @@ ice_discover_func_caps(struct ice_hw *hw, struct ice_hw_func_caps *func_caps)
 	 * device will return, we can simply send a 4KB buffer, the maximum
 	 * possible size that firmware can return.
 	 */
-	cap_count = ICE_AQ_MAX_BUF_LEN / sizeof(struct ice_aqc_list_caps_elem);
+	cap_count = ICE_AQ_MAX_BUF_LEN / sizeof(struct libie_aqc_list_caps_elem);
 
 	status = ice_aq_list_caps(hw, cbuf, ICE_AQ_MAX_BUF_LEN, &cap_count,
 				  ice_aqc_opc_list_func_caps, NULL);
@@ -3220,9 +3221,9 @@ ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
 			struct ice_sq_cd *cd)
 {
 	struct ice_aqc_manage_mac_write *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.mac_write;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_manage_mac_write);
 
 	cmd->flags = flags;
@@ -3239,10 +3240,12 @@ ice_aq_manage_mac_write(struct ice_hw *hw, const u8 *mac_addr, u8 flags,
  */
 static int ice_aq_clear_pxe_mode(struct ice_hw *hw)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_clear_pxe *cmd;
+	struct libie_aq_desc desc;
 
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_clear_pxe_mode);
-	desc.params.clear_pxe.rx_cnt = ICE_AQC_CLEAR_PXE_RX_CNT;
+	cmd->rx_cnt = ICE_AQC_CLEAR_PXE_RX_CNT;
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
@@ -3275,10 +3278,10 @@ ice_aq_set_port_params(struct ice_port_info *pi, bool double_vlan,
 {
 	struct ice_aqc_set_port_params *cmd;
 	struct ice_hw *hw = pi->hw;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 cmd_flags = 0;
 
-	cmd = &desc.params.set_port_params;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params);
 	if (double_vlan)
@@ -3515,7 +3518,8 @@ int
 ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
 		   struct ice_aqc_set_phy_cfg_data *cfg, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_set_phy_cfg *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!cfg)
@@ -3530,8 +3534,9 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
 	}
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_cfg);
-	desc.params.set_phy.lport_num = pi->lport;
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	cmd = libie_aq_raw(&desc);
+	cmd->lport_num = pi->lport;
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	ice_debug(hw, ICE_DBG_LINK, "set phy cfg\n");
 	ice_debug(hw, ICE_DBG_LINK, "	phy_type_low = 0x%llx\n",
@@ -3547,7 +3552,7 @@ ice_aq_set_phy_cfg(struct ice_hw *hw, struct ice_port_info *pi,
 		  cfg->link_fec_opt);
 
 	status = ice_aq_send_cmd(hw, &desc, cfg, sizeof(*cfg), cd);
-	if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE)
+	if (hw->adminq.sq_last_status == LIBIE_AQ_RC_EMODE)
 		status = 0;
 
 	if (!status)
@@ -3604,17 +3609,17 @@ int ice_aq_get_phy_equalization(struct ice_hw *hw, u16 data_in, u16 op_code,
 {
 	struct ice_aqc_dnl_call_command *cmd;
 	struct ice_aqc_dnl_call buf = {};
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int err;
 
 	buf.sto.txrx_equa_reqs.data_in = cpu_to_le16(data_in);
 	buf.sto.txrx_equa_reqs.op_code_serdes_sel =
 		cpu_to_le16(op_code | (serdes_num & 0xF));
-	cmd = &desc.params.dnl_call;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dnl_call);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_BUF |
-				  ICE_AQ_FLAG_RD |
-				  ICE_AQ_FLAG_SI);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF |
+				  LIBIE_AQ_FLAG_RD |
+				  LIBIE_AQ_FLAG_SI);
 	desc.datalen = cpu_to_le16(sizeof(struct ice_aqc_dnl_call));
 	cmd->activity_id = cpu_to_le16(ICE_AQC_ACT_ID_DNL);
 
@@ -3652,7 +3657,7 @@ static const u32 fec_reg[][ICE_FEC_MAX] = {
 int ice_aq_get_fec_stats(struct ice_hw *hw, u16 pcs_quad, u16 pcs_port,
 			 enum ice_fec_stats_types fec_type, u32 *output)
 {
-	u16 flag = (ICE_AQ_FLAG_RD | ICE_AQ_FLAG_BUF | ICE_AQ_FLAG_SI);
+	u16 flag = (LIBIE_AQ_FLAG_RD | LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_SI);
 	struct ice_sbq_msg_input msg = {};
 	u32 receiver_id, reg_offset;
 	int err;
@@ -4075,9 +4080,9 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 			   struct ice_sq_cd *cd)
 {
 	struct ice_aqc_restart_an *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.restart_an;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_restart_an);
 
@@ -4105,9 +4110,9 @@ ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
 		      struct ice_sq_cd *cd)
 {
 	struct ice_aqc_set_event_mask *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_event_mask;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_event_mask);
 
@@ -4129,9 +4134,9 @@ int
 ice_aq_set_mac_loopback(struct ice_hw *hw, bool ena_lpbk, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_set_mac_lb *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_mac_lb;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_mac_lb);
 	if (ena_lpbk)
@@ -4154,9 +4159,9 @@ ice_aq_set_port_id_led(struct ice_port_info *pi, bool is_orig_mode,
 {
 	struct ice_aqc_set_port_id_led *cmd;
 	struct ice_hw *hw = pi->hw;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_port_id_led;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_id_led);
 
@@ -4192,7 +4197,7 @@ ice_aq_get_port_options(struct ice_hw *hw,
 			u8 *pending_option_idx, bool *pending_option_valid)
 {
 	struct ice_aqc_get_port_options *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 	u8 i;
 
@@ -4200,7 +4205,7 @@ ice_aq_get_port_options(struct ice_hw *hw,
 	if (*option_count < ICE_AQC_PORT_OPT_COUNT_M)
 		return -EINVAL;
 
-	cmd = &desc.params.get_port_options;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_port_options);
 
 	if (lport_valid)
@@ -4266,12 +4271,12 @@ ice_aq_set_port_option(struct ice_hw *hw, u8 lport, u8 lport_valid,
 		       u8 new_option)
 {
 	struct ice_aqc_set_port_option *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (new_option > ICE_AQC_PORT_OPT_COUNT_M)
 		return -EINVAL;
 
-	cmd = &desc.params.set_port_option;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_option);
 
 	if (lport_valid)
@@ -4357,7 +4362,7 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		  bool write, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_sff_eeprom *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 i2c_bus_addr;
 	int status;
 
@@ -4365,8 +4370,8 @@ ice_aq_sff_eeprom(struct ice_hw *hw, u16 lport, u8 bus_addr,
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_sff_eeprom);
-	cmd = &desc.params.read_write_sff_param;
-	desc.flags = cpu_to_le16(ICE_AQ_FLAG_RD);
+	cmd = libie_aq_raw(&desc);
+	desc.flags = cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	cmd->lport_num = (u8)(lport & 0xff);
 	cmd->lport_num_valid = (u8)((lport >> 8) & 0x01);
 	i2c_bus_addr = FIELD_PREP(ICE_AQC_SFF_I2CBUS_7BIT_M, bus_addr >> 1) |
@@ -4426,7 +4431,7 @@ __ice_aq_get_set_rss_lut(struct ice_hw *hw,
 	struct ice_aqc_get_set_rss_lut *desc_params;
 	enum ice_aqc_lut_flags flags;
 	enum ice_lut_size lut_size;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u8 *lut = params->lut;
 
 
@@ -4442,9 +4447,9 @@ __ice_aq_get_set_rss_lut(struct ice_hw *hw,
 	opcode = set ? ice_aqc_opc_set_rss_lut : ice_aqc_opc_get_rss_lut;
 	ice_fill_dflt_direct_cmd_desc(&desc, opcode);
 	if (set)
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
-	desc_params = &desc.params.get_set_rss_lut;
+	desc_params = libie_aq_raw(&desc);
 	vsi_id = ice_get_hw_vsi_num(hw, vsi_handle);
 	desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID);
 
@@ -4499,16 +4504,16 @@ __ice_aq_get_set_rss_key(struct ice_hw *hw, u16 vsi_id,
 {
 	struct ice_aqc_get_set_rss_key *desc_params;
 	u16 key_size = sizeof(*key);
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (set) {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_rss_key);
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	} else {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_rss_key);
 	}
 
-	desc_params = &desc.params.get_set_rss_key;
+	desc_params = libie_aq_raw(&desc);
 	desc_params->vsi_id = cpu_to_le16(vsi_id | ICE_AQC_RSS_VSI_VALID);
 
 	return ice_aq_send_cmd(hw, &desc, key, key_size, NULL);
@@ -4580,10 +4585,10 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 {
 	struct ice_aqc_add_tx_qgrp *list;
 	struct ice_aqc_add_txqs *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 i, sum_size = 0;
 
-	cmd = &desc.params.add_txqs;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_txqs);
 
@@ -4602,7 +4607,7 @@ ice_aq_add_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 	if (buf_size != sum_size)
 		return -EINVAL;
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->num_qgrps = num_qgrps;
 
@@ -4629,12 +4634,12 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 {
 	struct ice_aqc_dis_txq_item *item;
 	struct ice_aqc_dis_txqs *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 vmvf_and_timeout;
 	u16 i, sz = 0;
 	int status;
 
-	cmd = &desc.params.dis_txqs;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_dis_txqs);
 
 	/* qg_list can be NULL only in VM/VF reset flow */
@@ -4675,7 +4680,7 @@ ice_aq_dis_lan_txq(struct ice_hw *hw, u8 num_qgrps,
 	/* set RD bit to indicate that command buffer is provided by the driver
 	 * and it needs to be read by the firmware
 	 */
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	for (i = 0, item = qg_list; i < num_qgrps; i++) {
 		u16 item_size = struct_size(item, q_id, item->num_qs);
@@ -4727,12 +4732,12 @@ ice_aq_cfg_lan_txq(struct ice_hw *hw, struct ice_aqc_cfg_txqs_buf *buf,
 		   struct ice_sq_cd *cd)
 {
 	struct ice_aqc_cfg_txqs *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.cfg_txqs;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_cfg_txqs);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (!buf)
 		return -EINVAL;
@@ -4768,10 +4773,10 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps,
 {
 	struct ice_aqc_add_rdma_qset_data *list;
 	struct ice_aqc_add_rdma_qset *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 i, sum_size = 0;
 
-	cmd = &desc.params.add_rdma_qset;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_rdma_qset);
 
@@ -4789,7 +4794,7 @@ ice_aq_add_rdma_qsets(struct ice_hw *hw, u8 num_qset_grps,
 	if (buf_size != sum_size)
 		return -EINVAL;
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->num_qset_grps = num_qset_grps;
 
@@ -5223,10 +5228,10 @@ int ice_aq_get_cgu_input_pin_measure(struct ice_hw *hw, u8 dpll_idx,
 				     u16 meas_num)
 {
 	struct ice_aqc_get_cgu_input_measure *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_input_measure);
-	cmd = &desc.params.get_cgu_input_measure;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_idx_opt = dpll_idx & ICE_AQC_GET_CGU_IN_MEAS_DPLL_IDX_M;
 
 	return ice_aq_send_cmd(hw, &desc, meas, meas_num * sizeof(*meas), NULL);
@@ -5244,7 +5249,7 @@ int
 ice_aq_get_cgu_abilities(struct ice_hw *hw,
 			 struct ice_aqc_get_cgu_abilities *abilities)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_abilities);
 	return ice_aq_send_cmd(hw, &desc, abilities, sizeof(*abilities), NULL);
@@ -5267,10 +5272,10 @@ ice_aq_set_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 flags1, u8 flags2,
 			 u32 freq, s32 phase_delay)
 {
 	struct ice_aqc_set_cgu_input_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_input_config);
-	cmd = &desc.params.set_cgu_input_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->input_idx = input_idx;
 	cmd->flags1 = flags1;
 	cmd->flags2 = flags2;
@@ -5299,11 +5304,11 @@ ice_aq_get_input_pin_cfg(struct ice_hw *hw, u8 input_idx, u8 *status, u8 *type,
 			 u8 *flags1, u8 *flags2, u32 *freq, s32 *phase_delay)
 {
 	struct ice_aqc_get_cgu_input_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int ret;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_input_config);
-	cmd = &desc.params.get_cgu_input_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->input_idx = input_idx;
 
 	ret = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
@@ -5342,10 +5347,10 @@ ice_aq_set_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 flags,
 			  u8 src_sel, u32 freq, s32 phase_delay)
 {
 	struct ice_aqc_set_cgu_output_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_output_config);
-	cmd = &desc.params.set_cgu_output_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->output_idx = output_idx;
 	cmd->flags = flags;
 	cmd->src_sel = src_sel;
@@ -5372,11 +5377,11 @@ ice_aq_get_output_pin_cfg(struct ice_hw *hw, u8 output_idx, u8 *flags,
 			  u8 *src_sel, u32 *freq, u32 *src_freq)
 {
 	struct ice_aqc_get_cgu_output_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int ret;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_output_config);
-	cmd = &desc.params.get_cgu_output_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->output_idx = output_idx;
 
 	ret = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
@@ -5413,11 +5418,11 @@ ice_aq_get_cgu_dpll_status(struct ice_hw *hw, u8 dpll_num, u8 *ref_state,
 			   u8 *eec_mode)
 {
 	struct ice_aqc_get_cgu_dpll_status *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_dpll_status);
-	cmd = &desc.params.get_cgu_dpll_status;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_num = dpll_num;
 
 	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
@@ -5451,10 +5456,10 @@ ice_aq_set_cgu_dpll_config(struct ice_hw *hw, u8 dpll_num, u8 ref_state,
 			   u8 config, u8 eec_mode)
 {
 	struct ice_aqc_set_cgu_dpll_config *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_dpll_config);
-	cmd = &desc.params.set_cgu_dpll_config;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_num = dpll_num;
 	cmd->ref_state = ref_state;
 	cmd->config = config;
@@ -5478,10 +5483,10 @@ ice_aq_set_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx,
 			u8 ref_priority)
 {
 	struct ice_aqc_set_cgu_ref_prio *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_cgu_ref_prio);
-	cmd = &desc.params.set_cgu_ref_prio;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_num = dpll_num;
 	cmd->ref_idx = ref_idx;
 	cmd->ref_priority = ref_priority;
@@ -5504,11 +5509,11 @@ ice_aq_get_cgu_ref_prio(struct ice_hw *hw, u8 dpll_num, u8 ref_idx,
 			u8 *ref_prio)
 {
 	struct ice_aqc_get_cgu_ref_prio *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_ref_prio);
-	cmd = &desc.params.get_cgu_ref_prio;
+	cmd = libie_aq_raw(&desc);
 	cmd->dpll_num = dpll_num;
 	cmd->ref_idx = ref_idx;
 
@@ -5534,11 +5539,11 @@ ice_aq_get_cgu_info(struct ice_hw *hw, u32 *cgu_id, u32 *cgu_cfg_ver,
 		    u32 *cgu_fw_ver)
 {
 	struct ice_aqc_get_cgu_info *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cgu_info);
-	cmd = &desc.params.get_cgu_info;
+	cmd = libie_aq_raw(&desc);
 
 	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 	if (!status) {
@@ -5565,11 +5570,11 @@ ice_aq_set_phy_rec_clk_out(struct ice_hw *hw, u8 phy_output, bool enable,
 			   u32 *freq)
 {
 	struct ice_aqc_set_phy_rec_clk_out *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_phy_rec_clk_out);
-	cmd = &desc.params.set_phy_rec_clk_out;
+	cmd = libie_aq_raw(&desc);
 	cmd->phy_output = phy_output;
 	cmd->port_num = ICE_AQC_SET_PHY_REC_CLK_OUT_CURR_PORT;
 	cmd->flags = enable & ICE_AQC_SET_PHY_REC_CLK_OUT_OUT_EN;
@@ -5598,11 +5603,11 @@ ice_aq_get_phy_rec_clk_out(struct ice_hw *hw, u8 *phy_output, u8 *port_num,
 			   u8 *flags, u16 *node_handle)
 {
 	struct ice_aqc_get_phy_rec_clk_out *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_phy_rec_clk_out);
-	cmd = &desc.params.get_phy_rec_clk_out;
+	cmd = libie_aq_raw(&desc);
 	cmd->phy_output = *phy_output;
 
 	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
@@ -5630,11 +5635,11 @@ int ice_aq_get_sensor_reading(struct ice_hw *hw,
 			      struct ice_aqc_get_sensor_reading_resp *data)
 {
 	struct ice_aqc_get_sensor_reading *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sensor_reading);
-	cmd = &desc.params.get_sensor_reading;
+	cmd = libie_aq_raw(&desc);
 #define ICE_INTERNAL_TEMP_SENSOR_FORMAT	0
 #define ICE_INTERNAL_TEMP_SENSOR	0
 	cmd->sensor = ICE_INTERNAL_TEMP_SENSOR;
@@ -5642,7 +5647,7 @@ int ice_aq_get_sensor_reading(struct ice_hw *hw,
 
 	status = ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 	if (!status)
-		memcpy(data, &desc.params.get_sensor_reading_resp,
+		memcpy(data, &desc.params.raw,
 		       sizeof(*data));
 
 	return status;
@@ -5839,13 +5844,13 @@ ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		u16 bus_addr, __le16 addr, u8 params, u8 *data,
 		struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc = { 0 };
+	struct libie_aq_desc desc = { 0 };
 	struct ice_aqc_i2c *cmd;
 	u8 data_size;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_read_i2c);
-	cmd = &desc.params.read_write_i2c;
+	cmd = libie_aq_raw(&desc);
 
 	if (!data)
 		return -EINVAL;
@@ -5862,7 +5867,7 @@ ice_aq_read_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		struct ice_aqc_read_i2c_resp *resp;
 		u8 i;
 
-		resp = &desc.params.read_i2c_resp;
+		resp = libie_aq_raw(&desc);
 		for (i = 0; i < data_size; i++) {
 			*data = resp->i2c_data[i];
 			data++;
@@ -5894,12 +5899,12 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 		 u16 bus_addr, __le16 addr, u8 params, const u8 *data,
 		 struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc = { 0 };
+	struct libie_aq_desc desc = { 0 };
 	struct ice_aqc_i2c *cmd;
 	u8 data_size;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_write_i2c);
-	cmd = &desc.params.read_write_i2c;
+	cmd = libie_aq_raw(&desc);
 
 	data_size = FIELD_GET(ICE_AQC_I2C_DATA_SIZE_M, params);
 
@@ -5931,7 +5936,7 @@ ice_aq_write_i2c(struct ice_hw *hw, struct ice_aqc_link_topo_addr topo_addr,
 int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
 {
 	struct ice_aqc_get_link_topo *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int err;
 	u8 idx;
 
@@ -5954,7 +5959,7 @@ int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
 
 	/* If handle was not detected read it from the netlist */
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_link_topo);
-	cmd = &desc.params.get_link_topo;
+	cmd = libie_aq_raw(&desc);
 	cmd->addr.topo_params.node_type_ctx =
 		ICE_AQC_LINK_TOPO_NODE_TYPE_GPIO_CTRL;
 	cmd->addr.topo_params.index = idx;
@@ -5964,13 +5969,12 @@ int ice_get_pca9575_handle(struct ice_hw *hw, u16 *pca9575_handle)
 		return -ENXIO;
 
 	/* Verify if we found the right IO expander type */
-	if (desc.params.get_link_topo.node_part_num !=
-	    ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
+	if (cmd->node_part_num != ICE_AQC_GET_LINK_TOPO_NODE_NR_PCA9575)
 		return -ENXIO;
 
 	/* If present save the handle and return it */
 	hw->io_expander_handle =
-		le16_to_cpu(desc.params.get_link_topo.addr.handle);
+		le16_to_cpu(cmd->addr.handle);
 	*pca9575_handle = hw->io_expander_handle;
 
 	return 0;
@@ -6021,11 +6025,11 @@ int
 ice_aq_set_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx, bool value,
 		struct ice_sq_cd *cd)
 {
+	struct libie_aq_desc desc;
 	struct ice_aqc_gpio *cmd;
-	struct ice_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_gpio);
-	cmd = &desc.params.read_write_gpio;
+	cmd = libie_aq_raw(&desc);
 	cmd->gpio_ctrl_handle = cpu_to_le16(gpio_ctrl_handle);
 	cmd->gpio_num = pin_idx;
 	cmd->gpio_val = value ? 1 : 0;
@@ -6048,12 +6052,12 @@ int
 ice_aq_get_gpio(struct ice_hw *hw, u16 gpio_ctrl_handle, u8 pin_idx,
 		bool *value, struct ice_sq_cd *cd)
 {
+	struct libie_aq_desc desc;
 	struct ice_aqc_gpio *cmd;
-	struct ice_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_gpio);
-	cmd = &desc.params.read_write_gpio;
+	cmd = libie_aq_raw(&desc);
 	cmd->gpio_ctrl_handle = cpu_to_le16(gpio_ctrl_handle);
 	cmd->gpio_num = pin_idx;
 
@@ -6216,9 +6220,9 @@ bool ice_is_fw_health_report_supported(struct ice_hw *hw)
 int ice_aq_set_health_status_cfg(struct ice_hw *hw, u8 event_source)
 {
 	struct ice_aqc_set_health_status_cfg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_health_status_cfg;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_health_status_cfg);
 
@@ -6242,16 +6246,16 @@ ice_aq_set_lldp_mib(struct ice_hw *hw, u8 mib_type, void *buf, u16 buf_size,
 		    struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_set_local_mib *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.lldp_set_mib;
+	cmd = libie_aq_raw(&desc);
 
 	if (buf_size == 0 || !buf)
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_local_mib);
 
-	desc.flags |= cpu_to_le16((u16)ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 	desc.datalen = cpu_to_le16(buf_size);
 
 	cmd->type = mib_type;
@@ -6287,12 +6291,12 @@ bool ice_fw_supports_lldp_fltr_ctrl(struct ice_hw *hw)
 int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add)
 {
 	struct ice_aqc_lldp_filter_ctrl *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (vsi->type != ICE_VSI_PF || !ice_fw_supports_lldp_fltr_ctrl(hw))
 		return -EOPNOTSUPP;
 
-	cmd = &desc.params.lldp_filter_ctrl;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_filter_ctrl);
 
@@ -6312,7 +6316,7 @@ int ice_lldp_fltr_add_remove(struct ice_hw *hw, struct ice_vsi *vsi, bool add)
  */
 int ice_lldp_execute_pending_mib(struct ice_hw *hw)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_execute_pending_mib);
 
@@ -6389,7 +6393,7 @@ int ice_read_cgu_reg(struct ice_hw *hw, u32 addr, u32 *val)
 	};
 	int err;
 
-	err = ice_sbq_rw_reg(hw, &cgu_msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &cgu_msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to read CGU register 0x%04x, err %d\n",
 			  addr, err);
@@ -6422,7 +6426,7 @@ int ice_write_cgu_reg(struct ice_hw *hw, u32 addr, u32 val)
 	};
 	int err;
 
-	err = ice_sbq_rw_reg(hw, &cgu_msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &cgu_msg, LIBIE_AQ_FLAG_RD);
 	if (err)
 		ice_debug(hw, ICE_DBG_PTP, "Failed to write CGU register 0x%04x, err %d\n",
 			  addr, err);
diff --git a/drivers/net/ethernet/intel/ice/ice_common.h b/drivers/net/ethernet/intel/ice/ice_common.h
index 25d9785f32cc..60320cdf7804 100644
--- a/drivers/net/ethernet/intel/ice/ice_common.h
+++ b/drivers/net/ethernet/intel/ice/ice_common.h
@@ -109,7 +109,7 @@ bool ice_is_sbq_supported(struct ice_hw *hw);
 struct ice_ctl_q_info *ice_get_sbq(struct ice_hw *hw);
 int
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
-		struct ice_aq_desc *desc, void *buf, u16 buf_size,
+		struct libie_aq_desc *desc, void *buf, u16 buf_size,
 		struct ice_sq_cd *cd);
 void ice_clear_pxe_mode(struct ice_hw *hw);
 int ice_get_caps(struct ice_hw *hw);
@@ -138,14 +138,14 @@ ice_aq_set_rss_key(struct ice_hw *hw, u16 vsi_handle,
 
 bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq);
 int ice_aq_q_shutdown(struct ice_hw *hw, bool unloading);
-void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode);
+void ice_fill_dflt_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode);
 
 void ice_pack_txq_ctx(const struct ice_tlan_ctx *ctx, ice_txq_ctx_buf_t *buf);
 
 extern struct mutex ice_global_cfg_lock_sw;
 
 int
-ice_aq_send_cmd(struct ice_hw *hw, struct ice_aq_desc *desc,
+ice_aq_send_cmd(struct ice_hw *hw, struct libie_aq_desc *desc,
 		void *buf, u16 buf_size, struct ice_sq_cd *cd);
 int ice_aq_get_fw_ver(struct ice_hw *hw, struct ice_sq_cd *cd);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.c b/drivers/net/ethernet/intel/ice/ice_controlq.c
index e3959ad442a2..dcb837cadd18 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.c
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.c
@@ -90,7 +90,7 @@ bool ice_check_sq_alive(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 static int
 ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	size_t size = cq->num_sq_entries * sizeof(struct ice_aq_desc);
+	size_t size = cq->num_sq_entries * sizeof(struct libie_aq_desc);
 
 	cq->sq.desc_buf.va = dmam_alloc_coherent(ice_hw_to_dev(hw), size,
 						 &cq->sq.desc_buf.pa,
@@ -110,7 +110,7 @@ ice_alloc_ctrlq_sq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 static int
 ice_alloc_ctrlq_rq_ring(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
-	size_t size = cq->num_rq_entries * sizeof(struct ice_aq_desc);
+	size_t size = cq->num_rq_entries * sizeof(struct libie_aq_desc);
 
 	cq->rq.desc_buf.va = dmam_alloc_coherent(ice_hw_to_dev(hw), size,
 						 &cq->rq.desc_buf.pa,
@@ -159,7 +159,7 @@ ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 
 	/* allocate the mapped buffers */
 	for (i = 0; i < cq->num_rq_entries; i++) {
-		struct ice_aq_desc *desc;
+		struct libie_aq_desc *desc;
 		struct ice_dma_mem *bi;
 
 		bi = &cq->rq.r.rq_bi[i];
@@ -173,9 +173,9 @@ ice_alloc_rq_bufs(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 		/* now configure the descriptors for use */
 		desc = ICE_CTL_Q_DESC(cq->rq, i);
 
-		desc->flags = cpu_to_le16(ICE_AQ_FLAG_BUF);
-		if (cq->rq_buf_size > ICE_AQ_LG_BUF)
-			desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB);
+		desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
+		if (cq->rq_buf_size > LIBIE_AQ_LG_BUF)
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 		desc->opcode = 0;
 		/* This is in accordance with control queue design, there is no
 		 * register for buffer size configuration
@@ -858,7 +858,7 @@ static u16 ice_clean_sq(struct ice_hw *hw, struct ice_ctl_q_info *cq)
 {
 	struct ice_ctl_q_ring *sq = &cq->sq;
 	u16 ntc = sq->next_to_clean;
-	struct ice_aq_desc *desc;
+	struct libie_aq_desc *desc;
 
 	desc = ICE_CTL_Q_DESC(*sq, ntc);
 
@@ -912,7 +912,7 @@ static const char *ice_ctl_q_str(enum ice_ctl_q qtype)
 static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 			 void *desc, void *buf, u16 buf_len, bool response)
 {
-	struct ice_aq_desc *cq_desc = desc;
+	struct libie_aq_desc *cq_desc = desc;
 	u16 datalen, flags;
 
 	if (!IS_ENABLED(CONFIG_DYNAMIC_DEBUG) &&
@@ -939,7 +939,8 @@ static void ice_debug_cq(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	 * by the DD and/or CMP flag set or a command with the RD flag set.
 	 */
 	if (buf && cq_desc->datalen &&
-	    (flags & (ICE_AQ_FLAG_DD | ICE_AQ_FLAG_CMP | ICE_AQ_FLAG_RD))) {
+	    (flags & (LIBIE_AQ_FLAG_DD | LIBIE_AQ_FLAG_CMP |
+		      LIBIE_AQ_FLAG_RD))) {
 		char prefix[] = KBUILD_MODNAME " 0x12341234 0x12341234 ";
 
 		sprintf(prefix, KBUILD_MODNAME " 0x%08X 0x%08X ",
@@ -992,11 +993,11 @@ static bool ice_sq_done(struct ice_hw *hw, struct ice_ctl_q_info *cq)
  */
 int
 ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
-		struct ice_aq_desc *desc, void *buf, u16 buf_size,
+		struct libie_aq_desc *desc, void *buf, u16 buf_size,
 		struct ice_sq_cd *cd)
 {
 	struct ice_dma_mem *dma_buf = NULL;
-	struct ice_aq_desc *desc_on_ring;
+	struct libie_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
 	int status = 0;
 	u16 retval = 0;
@@ -1007,7 +1008,7 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		return -EBUSY;
 	mutex_lock(&cq->sq_lock);
 
-	cq->sq_last_status = ICE_AQ_RC_OK;
+	cq->sq_last_status = LIBIE_AQ_RC_OK;
 
 	if (!cq->sq.count) {
 		ice_debug(hw, ICE_DBG_AQ_MSG, "Control Send queue not initialized.\n");
@@ -1028,9 +1029,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 			goto sq_send_command_error;
 		}
 
-		desc->flags |= cpu_to_le16(ICE_AQ_FLAG_BUF);
-		if (buf_size > ICE_AQ_LG_BUF)
-			desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB);
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF);
+		if (buf_size > LIBIE_AQ_LG_BUF)
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 	}
 
 	val = rd32(hw, cq->sq.head);
@@ -1112,9 +1113,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 			retval &= 0xff;
 		}
 		cmd_completed = true;
-		if (!status && retval != ICE_AQ_RC_OK)
+		if (!status && retval != LIBIE_AQ_RC_OK)
 			status = -EIO;
-		cq->sq_last_status = (enum ice_aq_err)retval;
+		cq->sq_last_status = (enum libie_aq_err)retval;
 	}
 
 	ice_debug(hw, ICE_DBG_AQ_MSG, "ATQ: desc and buffer writeback:\n");
@@ -1149,12 +1150,12 @@ sq_send_command_error:
  *
  * Fill the desc with default values
  */
-void ice_fill_dflt_direct_cmd_desc(struct ice_aq_desc *desc, u16 opcode)
+void ice_fill_dflt_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode)
 {
 	/* zero out the desc */
 	memset(desc, 0, sizeof(*desc));
 	desc->opcode = cpu_to_le16(opcode);
-	desc->flags = cpu_to_le16(ICE_AQ_FLAG_SI);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
 }
 
 /**
@@ -1172,9 +1173,9 @@ int
 ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		  struct ice_rq_event_info *e, u16 *pending)
 {
+	enum libie_aq_err rq_last_status;
 	u16 ntc = cq->rq.next_to_clean;
-	enum ice_aq_err rq_last_status;
-	struct ice_aq_desc *desc;
+	struct libie_aq_desc *desc;
 	struct ice_dma_mem *bi;
 	int ret_code = 0;
 	u16 desc_idx;
@@ -1207,9 +1208,9 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	desc = ICE_CTL_Q_DESC(cq->rq, ntc);
 	desc_idx = ntc;
 
-	rq_last_status = (enum ice_aq_err)le16_to_cpu(desc->retval);
+	rq_last_status = (enum libie_aq_err)le16_to_cpu(desc->retval);
 	flags = le16_to_cpu(desc->flags);
-	if (flags & ICE_AQ_FLAG_ERR) {
+	if (flags & LIBIE_AQ_FLAG_ERR) {
 		ret_code = -EIO;
 		ice_debug(hw, ICE_DBG_AQ_MSG, "Control Receive Queue Event 0x%04X received with error 0x%X\n",
 			  le16_to_cpu(desc->opcode), rq_last_status);
@@ -1230,9 +1231,9 @@ ice_clean_rq_elem(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 	bi = &cq->rq.r.rq_bi[ntc];
 	memset(desc, 0, sizeof(*desc));
 
-	desc->flags = cpu_to_le16(ICE_AQ_FLAG_BUF);
-	if (cq->rq_buf_size > ICE_AQ_LG_BUF)
-		desc->flags |= cpu_to_le16(ICE_AQ_FLAG_LB);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
+	if (cq->rq_buf_size > LIBIE_AQ_LG_BUF)
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 	desc->datalen = cpu_to_le16(bi->size);
 	desc->params.generic.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
 	desc->params.generic.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
diff --git a/drivers/net/ethernet/intel/ice/ice_controlq.h b/drivers/net/ethernet/intel/ice/ice_controlq.h
index ca97b7365a1b..788040dd662e 100644
--- a/drivers/net/ethernet/intel/ice/ice_controlq.h
+++ b/drivers/net/ethernet/intel/ice/ice_controlq.h
@@ -12,7 +12,7 @@
 #define ICE_SBQ_MAX_BUF_LEN 512
 
 #define ICE_CTL_Q_DESC(R, i) \
-	(&(((struct ice_aq_desc *)((R).desc_buf.va))[i]))
+	(&(((struct libie_aq_desc *)((R).desc_buf.va))[i]))
 
 #define ICE_CTL_Q_DESC_UNUSED(R) \
 	((u16)((((R)->next_to_clean > (R)->next_to_use) ? 0 : (R)->count) + \
@@ -76,12 +76,12 @@ struct ice_ctl_q_ring {
 
 /* sq transaction details */
 struct ice_sq_cd {
-	struct ice_aq_desc *wb_desc;
+	struct libie_aq_desc *wb_desc;
 };
 
 /* rq event information */
 struct ice_rq_event_info {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 msg_len;
 	u16 buf_len;
 	u8 *msg_buf;
@@ -96,7 +96,7 @@ struct ice_ctl_q_info {
 	u16 num_sq_entries;		/* send queue depth */
 	u16 rq_buf_size;		/* receive queue buffer size */
 	u16 sq_buf_size;		/* send queue buffer size */
-	enum ice_aq_err sq_last_status;	/* last status on send queue */
+	enum libie_aq_err sq_last_status;	/* last status on send queue */
 	struct mutex sq_lock;		/* Send queue lock */
 	struct mutex rq_lock;		/* Receive queue lock */
 };
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb.c b/drivers/net/ethernet/intel/ice/ice_dcb.c
index 64737fc62306..abea84f14658 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb.c
@@ -24,10 +24,10 @@ ice_aq_get_lldp_mib(struct ice_hw *hw, u8 bridge_type, u8 mib_type, void *buf,
 		    struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_get_mib *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.lldp_get_mib;
+	cmd = libie_aq_raw(&desc);
 
 	if (buf_size == 0 || !buf)
 		return -EINVAL;
@@ -64,9 +64,9 @@ ice_aq_cfg_lldp_mib_change(struct ice_hw *hw, bool ena_update,
 			   struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_set_mib_change *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.lldp_set_event;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_set_mib_change);
 
@@ -95,9 +95,9 @@ ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist,
 		 struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_stop *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.lldp_stop;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_stop);
 
@@ -121,9 +121,9 @@ ice_aq_stop_lldp(struct ice_hw *hw, bool shutdown_lldp_agent, bool persist,
 int ice_aq_start_lldp(struct ice_hw *hw, bool persist, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_start *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.lldp_start;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_lldp_start);
 
@@ -677,11 +677,11 @@ ice_aq_start_stop_dcbx(struct ice_hw *hw, bool start_dcbx_agent,
 		       bool *dcbx_agent_status, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_lldp_stop_start_specific_agent *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 opcode;
 	int status;
 
-	cmd = &desc.params.lldp_agent_ctrl;
+	cmd = libie_aq_raw(&desc);
 
 	opcode = ice_aqc_opc_lldp_stop_start_specific_agent;
 
@@ -714,7 +714,7 @@ ice_aq_get_cee_dcb_cfg(struct ice_hw *hw,
 		       struct ice_aqc_get_cee_dcb_cfg_resp *buff,
 		       struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_cee_dcb_cfg);
 
@@ -733,13 +733,13 @@ ice_aq_get_cee_dcb_cfg(struct ice_hw *hw,
 int ice_aq_set_pfc_mode(struct ice_hw *hw, u8 pfc_mode, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_set_query_pfc_mode *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (pfc_mode > ICE_AQC_PFC_DSCP_BASED_PFC)
 		return -EINVAL;
 
-	cmd = &desc.params.set_query_pfc_mode;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_pfc_mode);
 
@@ -914,7 +914,7 @@ static int ice_get_ieee_or_cee_dcb_cfg(struct ice_port_info *pi, u8 dcbx_mode)
 	ret = ice_aq_get_dcb_cfg(pi->hw, ICE_AQ_LLDP_MIB_REMOTE,
 				 ICE_AQ_LLDP_BRID_TYPE_NEAREST_BRID, dcbx_cfg);
 	/* Don't treat ENOENT as an error for Remote MIBs */
-	if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT)
+	if (pi->hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOENT)
 		ret = 0;
 
 out:
@@ -941,7 +941,7 @@ int ice_get_dcb_cfg(struct ice_port_info *pi)
 		/* CEE mode */
 		ret = ice_get_ieee_or_cee_dcb_cfg(pi, ICE_DCBX_MODE_CEE);
 		ice_cee_to_dcb_cfg(&cee_cfg, pi);
-	} else if (pi->hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT) {
+	} else if (pi->hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOENT) {
 		/* CEE mode not enabled try querying IEEE data */
 		dcbx_cfg = &pi->qos_cfg.local_dcbx_cfg;
 		dcbx_cfg->dcbx_mode = ICE_DCBX_MODE_IEEE;
@@ -965,7 +965,7 @@ void ice_get_dcb_cfg_from_mib_change(struct ice_port_info *pi,
 	struct ice_aqc_lldp_get_mib *mib;
 	u8 change_type, dcbx_mode;
 
-	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+	mib = libie_aq_raw(&event->desc);
 
 	change_type = FIELD_GET(ICE_AQ_LLDP_MIB_TYPE_M, mib->type);
 	if (change_type == ICE_AQ_LLDP_MIB_REMOTE)
@@ -1537,12 +1537,12 @@ ice_aq_query_port_ets(struct ice_port_info *pi,
 		      struct ice_sq_cd *cd)
 {
 	struct ice_aqc_query_port_ets *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!pi)
 		return -EINVAL;
-	cmd = &desc.params.port_ets;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_query_port_ets);
 	cmd->port_teid = pi->root->info.node_teid;
 
diff --git a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
index 533eb8930aa8..9fc8681cc58e 100644
--- a/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_dcb_lib.c
@@ -1020,7 +1020,7 @@ ice_dcb_process_lldp_set_mib_change(struct ice_pf *pf,
 	}
 
 	pi = pf->hw.port_info;
-	mib = (struct ice_aqc_lldp_get_mib *)&event->desc.params.raw;
+	mib = libie_aq_raw(&event->desc);
 
 	/* Ignore if event is not for Nearest Bridge */
 	mib_type = FIELD_GET(ICE_AQ_LLDP_BRID_TYPE_M, mib->type);
diff --git a/drivers/net/ethernet/intel/ice/ice_ddp.c b/drivers/net/ethernet/intel/ice/ice_ddp.c
index 59323c019544..e7ae220158b5 100644
--- a/drivers/net/ethernet/intel/ice/ice_ddp.c
+++ b/drivers/net/ethernet/intel/ice/ice_ddp.c
@@ -1101,16 +1101,16 @@ struct ice_buf *ice_pkg_buf(struct ice_buf_build *bld)
 	return &bld->buf;
 }
 
-static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum ice_aq_err aq_err)
+static enum ice_ddp_state ice_map_aq_err_to_ddp_state(enum libie_aq_err aq_err)
 {
 	switch (aq_err) {
-	case ICE_AQ_RC_ENOSEC:
-	case ICE_AQ_RC_EBADSIG:
+	case LIBIE_AQ_RC_ENOSEC:
+	case LIBIE_AQ_RC_EBADSIG:
 		return ICE_DDP_PKG_FILE_SIGNATURE_INVALID;
-	case ICE_AQ_RC_ESVN:
+	case LIBIE_AQ_RC_ESVN:
 		return ICE_DDP_PKG_FILE_REVISION_TOO_LOW;
-	case ICE_AQ_RC_EBADMAN:
-	case ICE_AQ_RC_EBADBUF:
+	case LIBIE_AQ_RC_EBADMAN:
+	case LIBIE_AQ_RC_EBADBUF:
 		return ICE_DDP_PKG_LOAD_ERROR;
 	default:
 		return ICE_DDP_PKG_ERR;
@@ -1180,7 +1180,7 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 		    u32 *error_info, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_download_pkg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (error_offset)
@@ -1188,9 +1188,9 @@ ice_aq_download_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 	if (error_info)
 		*error_info = 0;
 
-	cmd = &desc.params.download_pkg;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_download_pkg);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (last_buf)
 		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
@@ -1259,7 +1259,7 @@ static enum ice_ddp_state ice_ddp_send_hunk(struct ice_ddp_send_ctx *ctx,
 	struct ice_buf_hdr *prev_hunk = ctx->hdr;
 	struct ice_hw *hw = ctx->hw;
 	bool prev_was_last = !hunk;
-	enum ice_aq_err aq_err;
+	enum libie_aq_err aq_err;
 	u32 offset, info;
 	int attempt, err;
 
@@ -1278,7 +1278,8 @@ static enum ice_ddp_state ice_ddp_send_hunk(struct ice_ddp_send_ctx *ctx,
 					  prev_was_last, &offset, &info, NULL);
 
 		aq_err = hw->adminq.sq_last_status;
-		if (aq_err != ICE_AQ_RC_ENOSEC && aq_err != ICE_AQ_RC_EBADSIG)
+		if (aq_err != LIBIE_AQ_RC_ENOSEC &&
+		    aq_err != LIBIE_AQ_RC_EBADSIG)
 			break;
 	}
 
@@ -1537,7 +1538,7 @@ ice_post_dwnld_pkg_actions(struct ice_hw *hw)
 static enum ice_ddp_state
 ice_download_pkg_with_sig_seg(struct ice_hw *hw, struct ice_pkg_hdr *pkg_hdr)
 {
-	enum ice_aq_err aq_err = hw->adminq.sq_last_status;
+	enum libie_aq_err aq_err = hw->adminq.sq_last_status;
 	enum ice_ddp_state state = ICE_DDP_PKG_ERR;
 	struct ice_ddp_send_ctx ctx = { .hw = hw };
 	int status;
@@ -1687,7 +1688,7 @@ static int ice_aq_get_pkg_info_list(struct ice_hw *hw,
 				    struct ice_aqc_get_pkg_info_resp *pkg_info,
 				    u16 buf_size, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_pkg_info_list);
 
@@ -1711,7 +1712,7 @@ static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 			     u32 *error_info, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_download_pkg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (error_offset)
@@ -1719,9 +1720,9 @@ static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 	if (error_info)
 		*error_info = 0;
 
-	cmd = &desc.params.download_pkg;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_pkg);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (last_buf)
 		cmd->flags |= ICE_AQC_DOWNLOAD_PKG_LAST_BUF;
@@ -1753,10 +1754,10 @@ static int ice_aq_update_pkg(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 int ice_aq_upload_section(struct ice_hw *hw, struct ice_buf_hdr *pkg_buf,
 			  u16 buf_size, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_upload_section);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ice_aq_send_cmd(hw, &desc, pkg_buf, buf_size, cd);
 }
@@ -2333,10 +2334,10 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
 		    struct ice_sq_cd *cd, u8 *flags, bool set)
 {
 	struct ice_aqc_get_set_tx_topo *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.get_set_tx_topo;
+	cmd = libie_aq_raw(&desc);
 	if (set) {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_tx_topo);
 		cmd->set_flags = ICE_AQC_TX_TOPO_FLAGS_ISSUED;
@@ -2345,14 +2346,14 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
 			cmd->set_flags |= ICE_AQC_TX_TOPO_FLAGS_SRC_RAM |
 					  ICE_AQC_TX_TOPO_FLAGS_LOAD_NEW;
 
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	} else {
 		ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_tx_topo);
 		cmd->get_flags = ICE_AQC_TX_TOPO_GET_RAM;
 
 		if (hw->mac_type == ICE_MAC_E810 ||
 		    hw->mac_type == ICE_MAC_GENERIC)
-			desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+			desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	}
 
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
@@ -2360,7 +2361,7 @@ ice_get_set_tx_topo(struct ice_hw *hw, u8 *buf, u16 buf_size,
 		return status;
 	/* read the return flag values (first byte) for get operation */
 	if (!set && flags)
-		*flags = desc.params.get_set_tx_topo.set_flags;
+		*flags = cmd->set_flags;
 
 	return 0;
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_dpll.c b/drivers/net/ethernet/intel/ice/ice_dpll.c
index 39743cdba986..093835d2c822 100644
--- a/drivers/net/ethernet/intel/ice/ice_dpll.c
+++ b/drivers/net/ethernet/intel/ice/ice_dpll.c
@@ -2509,7 +2509,7 @@ static bool ice_dpll_is_pps_phase_monitor(struct ice_pf *pf)
 	int ret = ice_aq_get_cgu_input_pin_measure(&pf->hw, DPLL_TYPE_PPS, meas,
 						   ARRAY_SIZE(meas));
 
-	if (ret && pf->hw.adminq.sq_last_status == ICE_AQ_RC_ESRCH)
+	if (ret && pf->hw.adminq.sq_last_status == LIBIE_AQ_RC_ESRCH)
 		return false;
 
 	return true;
@@ -2562,7 +2562,7 @@ static int ice_dpll_pps_update_phase_offsets(struct ice_pf *pf,
 	*phase_offset_pins_updated = 0;
 	ret = ice_aq_get_cgu_input_pin_measure(&pf->hw, DPLL_TYPE_PPS, meas,
 					       ARRAY_SIZE(meas));
-	if (ret && pf->hw.adminq.sq_last_status == ICE_AQ_RC_EAGAIN) {
+	if (ret && pf->hw.adminq.sq_last_status == LIBIE_AQ_RC_EAGAIN) {
 		return 0;
 	} else if (ret) {
 		dev_err(ice_pf_to_dev(pf),
diff --git a/drivers/net/ethernet/intel/ice/ice_fw_update.c b/drivers/net/ethernet/intel/ice/ice_fw_update.c
index 70c201f569ce..4d9ad92a44fe 100644
--- a/drivers/net/ethernet/intel/ice/ice_fw_update.c
+++ b/drivers/net/ethernet/intel/ice/ice_fw_update.c
@@ -299,7 +299,8 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_aq_task task = {};
 	struct ice_hw *hw = &pf->hw;
-	struct ice_aq_desc *desc;
+	struct libie_aq_desc *desc;
+	struct ice_aqc_nvm *cmd;
 	u32 completion_offset;
 	int err;
 
@@ -333,11 +334,12 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	}
 
 	desc = &task.event.desc;
-	completion_module = le16_to_cpu(desc->params.nvm.module_typeid);
+	cmd = libie_aq_raw(desc);
+	completion_module = le16_to_cpu(cmd->module_typeid);
 	completion_retval = le16_to_cpu(desc->retval);
 
-	completion_offset = le16_to_cpu(desc->params.nvm.offset_low);
-	completion_offset |= desc->params.nvm.offset_high << 16;
+	completion_offset = le16_to_cpu(cmd->offset_low);
+	completion_offset |= cmd->offset_high << 16;
 
 	if (completion_module != module) {
 		dev_err(dev, "Unexpected module_typeid in write completion: got 0x%x, expected 0x%x\n",
@@ -356,7 +358,7 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	if (completion_retval) {
 		dev_err(dev, "Firmware failed to flash module 0x%02x with block of size %u at offset %u, err %s\n",
 			module, block_size, offset,
-			ice_aq_str((enum ice_aq_err)completion_retval));
+			ice_aq_str((enum libie_aq_err)completion_retval));
 		NL_SET_ERR_MSG_MOD(extack, "Firmware failed to program flash module");
 		return -EIO;
 	}
@@ -369,7 +371,7 @@ int ice_write_one_nvm_block(struct ice_pf *pf, u16 module, u32 offset,
 	 */
 	if (reset_level && last_cmd && module == ICE_SR_1ST_NVM_BANK_PTR) {
 		if (hw->dev_caps.common_cap.pcie_reset_avoidance) {
-			*reset_level = desc->params.nvm.cmd_flags &
+			*reset_level = cmd->cmd_flags &
 				       ICE_AQC_NVM_RESET_LVL_M;
 			dev_dbg(dev, "Firmware reported required reset level as %u\n",
 				*reset_level);
@@ -487,7 +489,8 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 	struct device *dev = ice_pf_to_dev(pf);
 	struct ice_aq_task task = {};
 	struct ice_hw *hw = &pf->hw;
-	struct ice_aq_desc *desc;
+	struct libie_aq_desc *desc;
+	struct ice_aqc_nvm *cmd;
 	struct devlink *devlink;
 	int err;
 
@@ -518,7 +521,8 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 	}
 
 	desc = &task.event.desc;
-	completion_module = le16_to_cpu(desc->params.nvm.module_typeid);
+	cmd = libie_aq_raw(desc);
+	completion_module = le16_to_cpu(cmd->module_typeid);
 	completion_retval = le16_to_cpu(desc->retval);
 
 	if (completion_module != module) {
@@ -532,7 +536,7 @@ ice_erase_nvm_module(struct ice_pf *pf, u16 module, const char *component,
 	if (completion_retval) {
 		dev_err(dev, "Firmware failed to erase %s (module 0x02%x), aq_err %s\n",
 			component, module,
-			ice_aq_str((enum ice_aq_err)completion_retval));
+			ice_aq_str((enum libie_aq_err)completion_retval));
 		NL_SET_ERR_MSG_MOD(extack, "Firmware failed to erase flash");
 		err = -EIO;
 		goto out_notify_devlink;
@@ -611,7 +615,7 @@ ice_switch_flash_banks(struct ice_pf *pf, u8 activate_flags,
 	completion_retval = le16_to_cpu(task.event.desc.retval);
 	if (completion_retval) {
 		dev_err(dev, "Firmware failed to switch active flash banks aq_err %s\n",
-			ice_aq_str((enum ice_aq_err)completion_retval));
+			ice_aq_str((enum libie_aq_err)completion_retval));
 		NL_SET_ERR_MSG_MOD(extack, "Firmware failed to switch active flash banks");
 		return -EIO;
 	}
diff --git a/drivers/net/ethernet/intel/ice/ice_fwlog.c b/drivers/net/ethernet/intel/ice/ice_fwlog.c
index 4fd15387a7e5..a31bb026ad34 100644
--- a/drivers/net/ethernet/intel/ice/ice_fwlog.c
+++ b/drivers/net/ethernet/intel/ice/ice_fwlog.c
@@ -240,7 +240,7 @@ ice_aq_fwlog_set(struct ice_hw *hw, struct ice_fwlog_module_entry *entries,
 {
 	struct ice_aqc_fw_log_cfg_resp *fw_modules;
 	struct ice_aqc_fw_log *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 	int i;
 
@@ -255,9 +255,9 @@ ice_aq_fwlog_set(struct ice_hw *hw, struct ice_fwlog_module_entry *entries,
 	}
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_config);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
-	cmd = &desc.params.fw_log;
+	cmd = libie_aq_raw(&desc);
 
 	cmd->cmd_flags = ICE_AQC_FW_LOG_CONF_SET_VALID;
 	cmd->ops.cfg.log_resolution = cpu_to_le16(log_resolution);
@@ -309,7 +309,7 @@ static int ice_aq_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
 {
 	struct ice_aqc_fw_log_cfg_resp *fw_modules;
 	struct ice_aqc_fw_log *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 module_id_cnt;
 	int status;
 	void *buf;
@@ -322,7 +322,7 @@ static int ice_aq_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
 		return -ENOMEM;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_query);
-	cmd = &desc.params.fw_log;
+	cmd = libie_aq_raw(&desc);
 
 	cmd->cmd_flags = ICE_AQC_FW_LOG_AQ_QUERY;
 
@@ -384,12 +384,14 @@ int ice_fwlog_get(struct ice_hw *hw, struct ice_fwlog_cfg *cfg)
  */
 static int ice_aq_fwlog_register(struct ice_hw *hw, bool reg)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_fw_log *cmd;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_fw_logs_register);
+	cmd = libie_aq_raw(&desc);
 
 	if (reg)
-		desc.params.fw_log.cmd_flags = ICE_AQC_FW_LOG_AQ_REGISTER;
+		cmd->cmd_flags = ICE_AQC_FW_LOG_AQ_REGISTER;
 
 	return ice_aq_send_cmd(hw, &desc, NULL, 0, NULL);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_lag.c b/drivers/net/ethernet/intel/ice/ice_lag.c
index c8b4fa3efbd4..b1129da72139 100644
--- a/drivers/net/ethernet/intel/ice/ice_lag.c
+++ b/drivers/net/ethernet/intel/ice/ice_lag.c
@@ -1144,7 +1144,7 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 {
 	struct ice_aqc_alloc_free_res_elem *buf;
 	struct ice_aqc_set_port_params *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_len, swid;
 	int status, i;
 
@@ -1192,7 +1192,7 @@ ice_lag_set_swid(u16 primary_swid, struct ice_lag *local_lag,
 	else
 		swid = local_lag->pf->hw.port_info->sw_id;
 
-	cmd = &desc.params.set_port_params;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_port_params);
 
 	cmd->swid = cpu_to_le16(ICE_AQC_PORT_SWID_VALID | swid);
diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
index 1be1e429a7c8..e563700d4ba1 100644
--- a/drivers/net/ethernet/intel/ice/ice_lib.c
+++ b/drivers/net/ethernet/intel/ice/ice_lib.c
@@ -3736,13 +3736,13 @@ int ice_set_link(struct ice_vsi *vsi, bool ena)
 
 	status = ice_aq_set_link_restart_an(pi, ena, NULL);
 
-	/* if link is owned by manageability, FW will return ICE_AQ_RC_EMODE.
+	/* if link is owned by manageability, FW will return LIBIE_AQ_RC_EMODE.
 	 * this is not a fatal error, so print a warning message and return
 	 * a success code. Return an error if FW returns an error code other
-	 * than ICE_AQ_RC_EMODE
+	 * than LIBIE_AQ_RC_EMODE
 	 */
 	if (status == -EIO) {
-		if (hw->adminq.sq_last_status == ICE_AQ_RC_EMODE)
+		if (hw->adminq.sq_last_status == LIBIE_AQ_RC_EMODE)
 			dev_dbg(dev, "can't set link to %s, err %d aq_err %s. not fatal, continuing\n",
 				(ena ? "ON" : "OFF"), status,
 				ice_aq_str(hw->adminq.sq_last_status));
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 204e906af591..3024f5dde384 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -379,7 +379,7 @@ static int ice_vsi_sync_fltr(struct ice_vsi *vsi)
 		 * should go into promiscuous mode. There should be some
 		 * space reserved for promiscuous filters.
 		 */
-		if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOSPC &&
+		if (hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOSPC &&
 		    !test_and_set_bit(ICE_FLTR_OVERFLOW_PROMISC,
 				      vsi->state)) {
 			promisc_forced_on = true;
@@ -7914,42 +7914,42 @@ int ice_change_mtu(struct net_device *netdev, int new_mtu)
  * ice_aq_str - convert AQ err code to a string
  * @aq_err: the AQ error code to convert
  */
-const char *ice_aq_str(enum ice_aq_err aq_err)
+const char *ice_aq_str(enum libie_aq_err aq_err)
 {
 	switch (aq_err) {
-	case ICE_AQ_RC_OK:
+	case LIBIE_AQ_RC_OK:
 		return "OK";
-	case ICE_AQ_RC_EPERM:
+	case LIBIE_AQ_RC_EPERM:
 		return "ICE_AQ_RC_EPERM";
-	case ICE_AQ_RC_ENOENT:
+	case LIBIE_AQ_RC_ENOENT:
 		return "ICE_AQ_RC_ENOENT";
-	case ICE_AQ_RC_ESRCH:
+	case LIBIE_AQ_RC_ESRCH:
 		return "ICE_AQ_RC_ESRCH";
-	case ICE_AQ_RC_EAGAIN:
+	case LIBIE_AQ_RC_EAGAIN:
 		return "ICE_AQ_RC_EAGAIN";
-	case ICE_AQ_RC_ENOMEM:
+	case LIBIE_AQ_RC_ENOMEM:
 		return "ICE_AQ_RC_ENOMEM";
-	case ICE_AQ_RC_EBUSY:
+	case LIBIE_AQ_RC_EBUSY:
 		return "ICE_AQ_RC_EBUSY";
-	case ICE_AQ_RC_EEXIST:
+	case LIBIE_AQ_RC_EEXIST:
 		return "ICE_AQ_RC_EEXIST";
-	case ICE_AQ_RC_EINVAL:
+	case LIBIE_AQ_RC_EINVAL:
 		return "ICE_AQ_RC_EINVAL";
-	case ICE_AQ_RC_ENOSPC:
+	case LIBIE_AQ_RC_ENOSPC:
 		return "ICE_AQ_RC_ENOSPC";
-	case ICE_AQ_RC_ENOSYS:
+	case LIBIE_AQ_RC_ENOSYS:
 		return "ICE_AQ_RC_ENOSYS";
-	case ICE_AQ_RC_EMODE:
+	case LIBIE_AQ_RC_EMODE:
 		return "ICE_AQ_RC_EMODE";
-	case ICE_AQ_RC_ENOSEC:
+	case LIBIE_AQ_RC_ENOSEC:
 		return "ICE_AQ_RC_ENOSEC";
-	case ICE_AQ_RC_EBADSIG:
+	case LIBIE_AQ_RC_EBADSIG:
 		return "ICE_AQ_RC_EBADSIG";
-	case ICE_AQ_RC_ESVN:
+	case LIBIE_AQ_RC_ESVN:
 		return "ICE_AQ_RC_ESVN";
-	case ICE_AQ_RC_EBADMAN:
+	case LIBIE_AQ_RC_EBADMAN:
 		return "ICE_AQ_RC_EBADMAN";
-	case ICE_AQ_RC_EBADBUF:
+	case LIBIE_AQ_RC_EBADBUF:
 		return "ICE_AQ_RC_EBADBUF";
 	}
 
diff --git a/drivers/net/ethernet/intel/ice/ice_nvm.c b/drivers/net/ethernet/intel/ice/ice_nvm.c
index 59e8879ac059..7e187a804dfa 100644
--- a/drivers/net/ethernet/intel/ice/ice_nvm.c
+++ b/drivers/net/ethernet/intel/ice/ice_nvm.c
@@ -22,10 +22,10 @@ int ice_aq_read_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
 		    u16 length, void *data, bool last_command,
 		    bool read_shadow_ram, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	if (offset > ICE_AQC_NVM_MAX_OFFSET)
 		return -EINVAL;
@@ -125,10 +125,10 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
 		  u16 length, void *data, bool last_command, u8 command_flags,
 		  struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	/* In offset the highest byte must be zeroed. */
 	if (offset & 0xFF000000)
@@ -146,7 +146,7 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
 	cmd->offset_high = (offset >> 16) & 0xFF;
 	cmd->length = cpu_to_le16(length);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ice_aq_send_cmd(hw, &desc, data, length, cd);
 }
@@ -161,10 +161,10 @@ ice_aq_update_nvm(struct ice_hw *hw, u16 module_typeid, u32 offset,
  */
 int ice_aq_erase_nvm(struct ice_hw *hw, u16 module_typeid, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_erase);
 
@@ -869,7 +869,7 @@ static int ice_discover_flash_size(struct ice_hw *hw)
 
 		status = ice_read_flat_nvm(hw, offset, &len, &data, false);
 		if (status == -EIO &&
-		    hw->adminq.sq_last_status == ICE_AQ_RC_EINVAL) {
+		    hw->adminq.sq_last_status == LIBIE_AQ_RC_EINVAL) {
 			ice_debug(hw, ICE_DBG_NVM, "%s: New upper bound of %u bytes\n",
 				  __func__, offset);
 			status = 0;
@@ -1182,14 +1182,14 @@ int ice_init_nvm(struct ice_hw *hw)
 int ice_nvm_validate_checksum(struct ice_hw *hw)
 {
 	struct ice_aqc_nvm_checksum *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	status = ice_acquire_nvm(hw, ICE_RES_READ);
 	if (status)
 		return status;
 
-	cmd = &desc.params.nvm_checksum;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_checksum);
 	cmd->flags = ICE_AQC_NVM_CHECKSUM_VERIFY;
@@ -1226,11 +1226,11 @@ int ice_nvm_validate_checksum(struct ice_hw *hw)
  */
 int ice_nvm_write_activate(struct ice_hw *hw, u16 cmd_flags, u8 *response_flags)
 {
+	struct libie_aq_desc desc;
 	struct ice_aqc_nvm *cmd;
-	struct ice_aq_desc desc;
 	int err;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_write_activate);
 
 	cmd->cmd_flags = (u8)(cmd_flags & 0xFF);
@@ -1252,7 +1252,7 @@ int ice_nvm_write_activate(struct ice_hw *hw, u16 cmd_flags, u8 *response_flags)
  */
 int ice_aq_nvm_update_empr(struct ice_hw *hw)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_update_empr);
 
@@ -1278,15 +1278,15 @@ ice_nvm_set_pkg_data(struct ice_hw *hw, bool del_pkg_data_flag, u8 *data,
 		     u16 length, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_nvm_pkg_data *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (length != 0 && !data)
 		return -EINVAL;
 
-	cmd = &desc.params.pkg_data;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_nvm_pkg_data);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (del_pkg_data_flag)
 		cmd->cmd_flags |= ICE_AQC_NVM_PKG_DELETE;
@@ -1316,17 +1316,17 @@ ice_nvm_pass_component_tbl(struct ice_hw *hw, u8 *data, u16 length,
 			   u8 *comp_response_code, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_nvm_pass_comp_tbl *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!data || !comp_response || !comp_response_code)
 		return -EINVAL;
 
-	cmd = &desc.params.pass_comp_tbl;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc,
 				      ice_aqc_opc_nvm_pass_component_tbl);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->transfer_flag = transfer_flag;
 	status = ice_aq_send_cmd(hw, &desc, data, length, cd);
diff --git a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
index e8e439fd64a4..523f95271f35 100644
--- a/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
+++ b/drivers/net/ethernet/intel/ice/ice_ptp_hw.c
@@ -424,7 +424,7 @@ static int ice_write_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 val)
 	};
 	int err;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err)
 		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
 			  err);
@@ -451,7 +451,7 @@ static int ice_read_phy_eth56g(struct ice_hw *hw, u8 port, u32 addr, u32 *val)
 	};
 	int err;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err)
 		ice_debug(hw, ICE_DBG_PTP, "PTP failed to send msg to phy %d\n",
 			  err);
@@ -2348,7 +2348,7 @@ ice_read_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 *val)
 	ice_fill_phy_msg_e82x(hw, &msg, port, offset);
 	msg.opcode = ice_sbq_msg_rd;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -2426,7 +2426,7 @@ ice_write_phy_reg_e82x(struct ice_hw *hw, u8 port, u16 offset, u32 val)
 	msg.opcode = ice_sbq_msg_wr;
 	msg.data = val;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -2587,7 +2587,7 @@ ice_read_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 *val)
 
 	msg.opcode = ice_sbq_msg_rd;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -2622,7 +2622,7 @@ ice_write_quad_reg_e82x(struct ice_hw *hw, u8 quad, u16 offset, u32 val)
 	msg.opcode = ice_sbq_msg_wr;
 	msg.data = val;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -4267,7 +4267,7 @@ static int ice_read_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 *val)
 	msg.opcode = ice_sbq_msg_rd;
 	msg.dest_dev = ice_sbq_dev_phy_0;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
@@ -4298,7 +4298,7 @@ static int ice_write_phy_reg_e810(struct ice_hw *hw, u32 addr, u32 val)
 	msg.dest_dev = ice_sbq_dev_phy_0;
 	msg.data = val;
 
-	err = ice_sbq_rw_reg(hw, &msg, ICE_AQ_FLAG_RD);
+	err = ice_sbq_rw_reg(hw, &msg, LIBIE_AQ_FLAG_RD);
 	if (err) {
 		ice_debug(hw, ICE_DBG_PTP, "Failed to send message to PHY, err %d\n",
 			  err);
diff --git a/drivers/net/ethernet/intel/ice/ice_sched.c b/drivers/net/ethernet/intel/ice/ice_sched.c
index d9d09296d1d4..fff0c1afdb41 100644
--- a/drivers/net/ethernet/intel/ice/ice_sched.c
+++ b/drivers/net/ethernet/intel/ice/ice_sched.c
@@ -123,13 +123,13 @@ ice_aqc_send_sched_elem_cmd(struct ice_hw *hw, enum ice_adminq_opc cmd_opc,
 			    u16 *elems_resp, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_sched_elem_cmd *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.sched_elem_cmd;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, cmd_opc);
 	cmd->num_elem_req = cpu_to_le16(elems_req);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
 	if (!status && elems_resp)
 		*elems_resp = le16_to_cpu(cmd->num_elem_resp);
@@ -392,10 +392,10 @@ ice_aq_get_dflt_topo(struct ice_hw *hw, u8 lport,
 		     u8 *num_branches, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_get_topo *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.get_topo;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_dflt_topo);
 	cmd->port_num = lport;
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
@@ -518,7 +518,7 @@ ice_aq_query_sched_res(struct ice_hw *hw, u16 buf_size,
 		       struct ice_aqc_query_txsched_res_resp *buf,
 		       struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_query_sched_res);
 	return ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
@@ -683,13 +683,13 @@ ice_aq_rl_profile(struct ice_hw *hw, enum ice_adminq_opc opcode,
 		  u16 buf_size, u16 *num_processed, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_rl_profile *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.rl_profile;
+	cmd = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, opcode);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 	cmd->num_profiles = cpu_to_le16(num_profiles);
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
 	if (!status && num_processed)
diff --git a/drivers/net/ethernet/intel/ice/ice_sriov.c b/drivers/net/ethernet/intel/ice/ice_sriov.c
index c434326a4694..9ce4c4db400e 100644
--- a/drivers/net/ethernet/intel/ice/ice_sriov.c
+++ b/drivers/net/ethernet/intel/ice/ice_sriov.c
@@ -1161,10 +1161,12 @@ static u32 ice_globalq_to_pfq(struct ice_pf *pf, u32 globalq)
 void
 ice_vf_lan_overflow_event(struct ice_pf *pf, struct ice_rq_event_info *event)
 {
+	struct ice_aqc_event_lan_overflow *cmd;
 	u32 gldcb_rtctq, queue;
 	struct ice_vf *vf;
 
-	gldcb_rtctq = le32_to_cpu(event->desc.params.lan_overflow.prtdcb_ruptq);
+	cmd = libie_aq_raw(&event->desc);
+	gldcb_rtctq = le32_to_cpu(cmd->prtdcb_ruptq);
 	dev_dbg(ice_pf_to_dev(pf), "GLDCB_RTCTQ: 0x%08x\n", gldcb_rtctq);
 
 	/* event returns device global Rx queue number */
diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
index 9d9a7edd3618..84848f0123e7 100644
--- a/drivers/net/ethernet/intel/ice/ice_switch.c
+++ b/drivers/net/ethernet/intel/ice/ice_switch.c
@@ -1511,11 +1511,11 @@ ice_aq_get_sw_cfg(struct ice_hw *hw, struct ice_aqc_get_sw_cfg_resp_elem *buf,
 		  struct ice_sq_cd *cd)
 {
 	struct ice_aqc_get_sw_cfg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_sw_cfg);
-	cmd = &desc.params.get_sw_conf;
+	cmd = libie_aq_raw(&desc);
 	cmd->element = cpu_to_le16(*req_desc);
 
 	status = ice_aq_send_cmd(hw, &desc, buf, buf_size, cd);
@@ -1541,11 +1541,11 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 {
 	struct ice_aqc_add_update_free_vsi_resp *res;
 	struct ice_aqc_add_get_update_free_vsi *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.vsi_cmd;
-	res = &desc.params.add_update_free_vsi_res;
+	cmd = libie_aq_raw(&desc);
+	res = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_vsi);
 
@@ -1556,7 +1556,7 @@ ice_aq_add_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 
 	cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	status = ice_aq_send_cmd(hw, &desc, &vsi_ctx->info,
 				 sizeof(vsi_ctx->info), cd);
@@ -1585,11 +1585,11 @@ ice_aq_free_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 {
 	struct ice_aqc_add_update_free_vsi_resp *resp;
 	struct ice_aqc_add_get_update_free_vsi *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.vsi_cmd;
-	resp = &desc.params.add_update_free_vsi_res;
+	cmd = libie_aq_raw(&desc);
+	resp = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_free_vsi);
 
@@ -1620,17 +1620,17 @@ ice_aq_update_vsi(struct ice_hw *hw, struct ice_vsi_ctx *vsi_ctx,
 {
 	struct ice_aqc_add_update_free_vsi_resp *resp;
 	struct ice_aqc_add_get_update_free_vsi *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.vsi_cmd;
-	resp = &desc.params.add_update_free_vsi_res;
+	cmd = libie_aq_raw(&desc);
+	resp = libie_aq_raw(&desc);
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_update_vsi);
 
 	cmd->vsi_num = cpu_to_le16(vsi_ctx->vsi_num | ICE_AQ_VSI_IS_VALID);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	status = ice_aq_send_cmd(hw, &desc, &vsi_ctx->info,
 				 sizeof(vsi_ctx->info), cd);
@@ -1944,7 +1944,8 @@ int
 ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz,
 		u8 num_rules, enum ice_adminq_opc opc, struct ice_sq_cd *cd)
 {
-	struct ice_aq_desc desc;
+	struct ice_aqc_sw_rules *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (opc != ice_aqc_opc_add_sw_rules &&
@@ -1953,13 +1954,13 @@ ice_aq_sw_rules(struct ice_hw *hw, void *rule_list, u16 rule_list_sz,
 		return -EINVAL;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, opc);
+	cmd = libie_aq_raw(&desc);
 
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
-	desc.params.sw_rules.num_rules_fltr_entry_index =
-		cpu_to_le16(num_rules);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
+	cmd->num_rules_fltr_entry_index = cpu_to_le16(num_rules);
 	status = ice_aq_send_cmd(hw, &desc, rule_list, rule_list_sz, cd);
 	if (opc != ice_aqc_opc_add_sw_rules &&
-	    hw->adminq.sq_last_status == ICE_AQ_RC_ENOENT)
+	    hw->adminq.sq_last_status == LIBIE_AQ_RC_ENOENT)
 		status = -ENOENT;
 
 	if (!status) {
@@ -1989,14 +1990,14 @@ ice_aq_add_recipe(struct ice_hw *hw,
 		  u16 num_recipes, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_add_get_recipe *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 
-	cmd = &desc.params.add_get_recipe;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_add_recipe);
 
 	cmd->num_sub_recipes = cpu_to_le16(num_recipes);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	buf_size = num_recipes * sizeof(*s_recipe_list);
 
@@ -2026,14 +2027,14 @@ ice_aq_get_recipe(struct ice_hw *hw,
 		  u16 *num_recipes, u16 recipe_root, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_add_get_recipe *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 	int status;
 
 	if (*num_recipes != ICE_MAX_NUM_RECIPES)
 		return -EINVAL;
 
-	cmd = &desc.params.add_get_recipe;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe);
 
 	cmd->return_index = cpu_to_le16(recipe_root);
@@ -2118,9 +2119,9 @@ ice_aq_map_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 r_assoc,
 			     struct ice_sq_cd *cd)
 {
 	struct ice_aqc_recipe_to_profile *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.recipe_to_profile;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_recipe_to_profile);
 	cmd->profile_id = cpu_to_le16(profile_id);
 	/* Set the recipe ID bit in the bitmask to let the device know which
@@ -2144,10 +2145,10 @@ ice_aq_get_recipe_to_profile(struct ice_hw *hw, u32 profile_id, u64 *r_assoc,
 			     struct ice_sq_cd *cd)
 {
 	struct ice_aqc_recipe_to_profile *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = &desc.params.recipe_to_profile;
+	cmd = libie_aq_raw(&desc);
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_get_recipe_to_profile);
 	cmd->profile_id = cpu_to_le16(profile_id);
 
diff --git a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
index 75c8113e58ee..7798a5d4bc9d 100644
--- a/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
+++ b/drivers/net/ethernet/intel/ice/ice_vf_mbx.c
@@ -23,18 +23,18 @@ ice_aq_send_msg_to_vf(struct ice_hw *hw, u16 vfid, u32 v_opcode, u32 v_retval,
 		      u8 *msg, u16 msglen, struct ice_sq_cd *cd)
 {
 	struct ice_aqc_pf_vf_msg *cmd;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	ice_fill_dflt_direct_cmd_desc(&desc, ice_mbx_opc_send_msg_to_vf);
 
-	cmd = &desc.params.virt;
+	cmd = libie_aq_raw(&desc);
 	cmd->id = cpu_to_le32(vfid);
 
 	desc.cookie_high = cpu_to_le32(v_opcode);
 	desc.cookie_low = cpu_to_le32(v_retval);
 
 	if (msglen)
-		desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ice_sq_send_cmd(hw, &hw->mailboxq, &desc, msg, msglen, cd);
 }
diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl.c b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
index 05511157c571..faec052cf469 100644
--- a/drivers/net/ethernet/intel/ice/ice_virtchnl.c
+++ b/drivers/net/ethernet/intel/ice/ice_virtchnl.c
@@ -304,7 +304,7 @@ ice_vc_send_msg_to_vf(struct ice_vf *vf, u32 v_opcode,
 
 	aq_ret = ice_aq_send_msg_to_vf(&pf->hw, vf->vf_id, v_opcode, v_retval,
 				       msg, msglen, NULL);
-	if (aq_ret && pf->hw.mailboxq.sq_last_status != ICE_AQ_RC_ENOSYS) {
+	if (aq_ret && pf->hw.mailboxq.sq_last_status != LIBIE_AQ_RC_ENOSYS) {
 		dev_info(dev, "Unable to send the message to VF %d ret %d aq_err %s\n",
 			 vf->vf_id, aq_ret,
 			 ice_aq_str(pf->hw.mailboxq.sq_last_status));
diff --git a/drivers/net/ethernet/intel/ice/ice_vlan_mode.c b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c
index 1279c1ffe31c..fb526cb84776 100644
--- a/drivers/net/ethernet/intel/ice/ice_vlan_mode.c
+++ b/drivers/net/ethernet/intel/ice/ice_vlan_mode.c
@@ -63,7 +63,7 @@ static int
 ice_aq_get_vlan_mode(struct ice_hw *hw,
 		     struct ice_aqc_get_vlan_mode *get_params)
 {
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (!get_params)
 		return -EINVAL;
@@ -275,7 +275,7 @@ ice_aq_set_vlan_mode(struct ice_hw *hw,
 		     struct ice_aqc_set_vlan_mode *set_params)
 {
 	u8 rdma_packet, mng_vlan_prot_id;
-	struct ice_aq_desc desc;
+	struct libie_aq_desc desc;
 
 	if (!set_params)
 		return -EINVAL;
@@ -295,7 +295,7 @@ ice_aq_set_vlan_mode(struct ice_hw *hw,
 
 	ice_fill_dflt_direct_cmd_desc(&desc,
 				      ice_aqc_opc_set_vlan_mode_parameters);
-	desc.flags |= cpu_to_le16(ICE_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ice_aq_send_cmd(hw, &desc, set_params, sizeof(*set_params),
 			       NULL);
diff --git a/include/linux/net/intel/libie/adminq.h b/include/linux/net/intel/libie/adminq.h
new file mode 100644
index 000000000000..3676adc33d3e
--- /dev/null
+++ b/include/linux/net/intel/libie/adminq.h
@@ -0,0 +1,273 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (C) 2025 Intel Corporation */
+
+#ifndef __LIBIE_ADMINQ_H
+#define __LIBIE_ADMINQ_H
+
+#include <linux/build_bug.h>
+#include <linux/types.h>
+
+#define LIBIE_CHECK_STRUCT_LEN(n, X)	\
+	static_assert((n) == sizeof(struct X))
+
+/**
+ * struct libie_aqc_generic - Generic structure used in adminq communication
+ * @param0: generic parameter high 32bit
+ * @param1: generic parameter lower 32bit
+ * @addr_high: generic address high 32bit
+ * @addr_low: generic address lower 32bit
+ */
+struct libie_aqc_generic {
+	__le32 param0;
+	__le32 param1;
+	__le32 addr_high;
+	__le32 addr_low;
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_generic);
+
+/**
+ * struct libie_aqc_get_ver -  Used in command get version (direct 0x0001)
+ * @rom_ver: rom version
+ * @fw_build: number coressponding to firmware build
+ * @fw_branch: branch identifier of firmware version
+ * @fw_major: major number of firmware version
+ * @fw_minor: minor number of firmware version
+ * @fw_patch: patch of firmware version
+ * @api_branch: brancch identifier of API version
+ * @api_major: major number of API version
+ * @api_minor: minor number of API version
+ * @api_patch: patch of API version
+ */
+struct libie_aqc_get_ver {
+	__le32	rom_ver;
+	__le32	fw_build;
+	u8	fw_branch;
+	u8	fw_major;
+	u8	fw_minor;
+	u8	fw_patch;
+	u8	api_branch;
+	u8	api_major;
+	u8	api_minor;
+	u8	api_patch;
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_get_ver);
+
+/**
+ * struct libie_aqc_driver_ver - Used in command send driver version
+ *				 (indirect 0x0002)
+ * @major_ver: driver major version
+ * @minor_ver: driver minor version
+ * @build_ver: driver build version
+ * @subbuild_ver: driver subbuild version
+ * @reserved: for feature use
+ * @addr_high: high part of response address buff
+ * @addr_low: low part of response address buff
+ */
+struct libie_aqc_driver_ver {
+	u8	major_ver;
+	u8	minor_ver;
+	u8	build_ver;
+	u8	subbuild_ver;
+	u8	reserved[4];
+	__le32	addr_high;
+	__le32	addr_low;
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_driver_ver);
+
+enum libie_aq_res_id {
+	LIBIE_AQC_RES_ID_NVM				= 1,
+	LIBIE_AQC_RES_ID_SDP				= 2,
+	LIBIE_AQC_RES_ID_CHNG_LOCK			= 3,
+	LIBIE_AQC_RES_ID_GLBL_LOCK			= 4,
+};
+
+enum libie_aq_res_access_type {
+	LIBIE_AQC_RES_ACCESS_READ			= 1,
+	LIBIE_AQC_RES_ACCESS_WRITE			= 2,
+};
+
+#define LIBIE_AQ_RES_NVM_READ_DFLT_TIMEOUT_MS		3000
+#define LIBIE_AQ_RES_NVM_WRITE_DFLT_TIMEOUT_MS		180000
+#define LIBIE_AQ_RES_CHNG_LOCK_DFLT_TIMEOUT_MS		1000
+#define LIBIE_AQ_RES_GLBL_LOCK_DFLT_TIMEOUT_MS		3000
+
+#define LIBIE_AQ_RES_GLBL_SUCCESS			0
+#define LIBIE_AQ_RES_GLBL_IN_PROG			1
+#define LIBIE_AQ_RES_GLBL_DONE				2
+
+/**
+ * struct libie_aqc_req_res - Request resource ownership
+ * @res_id: resource ID (look at enum definition above)
+ * @access_type: read or write (enum definition above)
+ * @timeout: Upon successful completion, FW writes this value and driver is
+ * expected to release resource before timeout. This value is provided in
+ * milliseconds.
+ * @res_number: for SDP, this is the pin ID of the SDP
+ * @status: status only used for LIBIE_AQC_RES_ID_GLBL_LOCK, for others reserved
+ * @reserved: reserved for future use
+ *
+ * Used in commands:
+ * request resource ownership (direct 0x0008)
+ * request resource ownership (direct 0x0009)
+ */
+struct libie_aqc_req_res {
+	__le16	res_id;
+	__le16	access_type;
+
+	__le32	timeout;
+	__le32	res_number;
+	__le16	status;
+	u8	reserved[2];
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_req_res);
+
+/**
+ * struct libie_aqc_list_caps - Getting capabilities
+ * @cmd_flags: command flags
+ * @pf_index: index of PF to get caps from
+ * @reserved: reserved for future use
+ * @count: number of capabilities records
+ * @addr_high: high part of response address buff
+ * @addr_low: low part of response address buff
+ *
+ * Used in commands:
+ * get function capabilities (indirect 0x000A)
+ * get device capabilities (indirect 0x000B)
+ */
+struct libie_aqc_list_caps {
+	u8	cmd_flags;
+	u8	pf_index;
+	u8	reserved[2];
+	__le32	count;
+	__le32	addr_high;
+	__le32	addr_low;
+};
+LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps);
+
+/* Device/Function buffer entry, repeated per reported capability */
+#define LIBIE_AQC_CAPS_VALID_FUNCTIONS			0x0005
+#define LIBIE_AQC_CAPS_SRIOV				0x0012
+#define LIBIE_AQC_CAPS_VF				0x0013
+#define LIBIE_AQC_CAPS_VSI				0x0017
+#define LIBIE_AQC_CAPS_DCB				0x0018
+#define LIBIE_AQC_CAPS_RSS				0x0040
+#define LIBIE_AQC_CAPS_RXQS				0x0041
+#define LIBIE_AQC_CAPS_TXQS				0x0042
+#define LIBIE_AQC_CAPS_MSIX				0x0043
+#define LIBIE_AQC_CAPS_FD				0x0045
+#define LIBIE_AQC_CAPS_1588				0x0046
+#define LIBIE_AQC_CAPS_MAX_MTU				0x0047
+#define LIBIE_AQC_CAPS_NVM_VER				0x0048
+#define LIBIE_AQC_CAPS_PENDING_NVM_VER			0x0049
+#define LIBIE_AQC_CAPS_OROM_VER				0x004A
+#define LIBIE_AQC_CAPS_PENDING_OROM_VER			0x004B
+#define LIBIE_AQC_CAPS_NET_VER				0x004C
+#define LIBIE_AQC_CAPS_PENDING_NET_VER			0x004D
+#define LIBIE_AQC_CAPS_RDMA				0x0051
+#define LIBIE_AQC_CAPS_SENSOR_READING			0x0067
+#define LIBIE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
+#define LIBIE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT	0x0077
+#define LIBIE_AQC_CAPS_NVM_MGMT				0x0080
+#define LIBIE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE		0x0085
+#define LIBIE_AQC_CAPS_NAC_TOPOLOGY			0x0087
+#define LIBIE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
+#define LIBIE_AQC_BIT_ROCEV2_LAG			0x01
+#define LIBIE_AQC_BIT_SRIOV_LAG				0x02
+
+/**
+ * struct libie_aqc_list_caps_elem - Getting list of caps elements
+ * @cap: one from the defines list above
+ * @major_ver: major version
+ * @minor_ver: minor version
+ * @number: number of resources described by this capability
+ * @logical_id: logical ID, only meaningful for some types of resources
+ * @phys_id: physical ID, only meaningful for some types of resources
+ * @rsvd1: reserved for future use
+ * @rsvd2: reserved for future use
+ */
+struct libie_aqc_list_caps_elem {
+	__le16	cap;
+
+	u8	major_ver;
+	u8	minor_ver;
+	__le32	number;
+	__le32	logical_id;
+	__le32	phys_id;
+	__le64	rsvd1;
+	__le64	rsvd2;
+};
+LIBIE_CHECK_STRUCT_LEN(32, libie_aqc_list_caps_elem);
+
+/**
+ * struct libie_aq_desc - Admin Queue (AQ) descriptor
+ * @flags: LIBIE_AQ_FLAG_* flags
+ * @opcode: AQ command opcode
+ * @datalen: length in bytes of indirect/external data buffer
+ * @retval: return value from firmware
+ * @cookie_high: opaque data high-half
+ * @cookie_low: opaque data low-half
+ * @params: command-specific parameters
+ *
+ * Descriptor format for commands the driver posts on the Admin Transmit Queue
+ * (ATQ). The firmware writes back onto the command descriptor and returns
+ * the result of the command. Asynchronous events that are not an immediate
+ * result of the command are written to the Admin Receive Queue (ARQ) using
+ * the same descriptor format. Descriptors are in little-endian notation with
+ * 32-bit words.
+ */
+struct libie_aq_desc {
+	__le16	flags;
+	__le16	opcode;
+	__le16	datalen;
+	__le16	retval;
+	__le32	cookie_high;
+	__le32	cookie_low;
+	union {
+		u8	raw[16];
+		struct	libie_aqc_generic generic;
+		struct	libie_aqc_get_ver get_ver;
+		struct	libie_aqc_driver_ver driver_ver;
+		struct	libie_aqc_req_res res_owner;
+		struct	libie_aqc_list_caps get_cap;
+	} params;
+};
+LIBIE_CHECK_STRUCT_LEN(32, libie_aq_desc);
+
+/* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
+#define LIBIE_AQ_LG_BUF				512
+
+#define LIBIE_AQ_FLAG_DD			BIT(0)	/* 0x1    */
+#define LIBIE_AQ_FLAG_CMP			BIT(1)	/* 0x2    */
+#define LIBIE_AQ_FLAG_ERR			BIT(2)	/* 0x4    */
+#define LIBIE_AQ_FLAG_LB			BIT(9)	/* 0x200  */
+#define LIBIE_AQ_FLAG_RD			BIT(10)	/* 0x400  */
+#define LIBIE_AQ_FLAG_BUF			BIT(12)	/* 0x1000 */
+#define LIBIE_AQ_FLAG_SI			BIT(13)	/* 0x2000 */
+
+/* error codes */
+enum libie_aq_err {
+	LIBIE_AQ_RC_OK		= 0,  /* Success */
+	LIBIE_AQ_RC_EPERM	= 1,  /* Operation not permitted */
+	LIBIE_AQ_RC_ENOENT	= 2,  /* No such element */
+	LIBIE_AQ_RC_ESRCH	= 3,  /* Bad opcode */
+	LIBIE_AQ_RC_EAGAIN	= 8,  /* Try again */
+	LIBIE_AQ_RC_ENOMEM	= 9,  /* Out of memory */
+	LIBIE_AQ_RC_EBUSY	= 12, /* Device or resource busy */
+	LIBIE_AQ_RC_EEXIST	= 13, /* Object already exists */
+	LIBIE_AQ_RC_EINVAL	= 14, /* Invalid argument */
+	LIBIE_AQ_RC_ENOSPC	= 16, /* No space left or allocation failure */
+	LIBIE_AQ_RC_ENOSYS	= 17, /* Function not implemented */
+	LIBIE_AQ_RC_EMODE	= 21, /* Op not allowed in current dev mode */
+	LIBIE_AQ_RC_ENOSEC	= 24, /* Missing security manifest */
+	LIBIE_AQ_RC_EBADSIG	= 25, /* Bad RSA signature */
+	LIBIE_AQ_RC_ESVN	= 26, /* SVN number prohibits this package */
+	LIBIE_AQ_RC_EBADMAN	= 27, /* Manifest hash mismatch */
+	LIBIE_AQ_RC_EBADBUF	= 28, /* Buffer hash mismatches manifest */
+};
+
+static inline void *libie_aq_raw(struct libie_aq_desc *desc)
+{
+	return &desc->params.raw;
+}
+
+#endif /* __LIBIE_ADMINQ_H */
-- 
cgit v1.2.3


From 5b36bef444432b75e7285e33338eb8bad53fe152 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Fri, 25 Apr 2025 08:08:03 +0200
Subject: ixgbe: use libie adminq descriptors

Use libie_aq_desc instead of ixgbe_aci_desc. Do needed changes to allow
clean build.

Move additional caps used in ixgbe to libie.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Reviewed-by: Aleksandr Loktionov <aleksandr.loktionov@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ixgbe/devlink/region.c  |   4 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c      | 272 +++++++++++----------
 drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h      |  12 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c |   4 +-
 drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h | 226 +----------------
 include/linux/net/intel/libie/adminq.h             |  16 ++
 6 files changed, 167 insertions(+), 367 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/ixgbe/devlink/region.c b/drivers/net/ethernet/intel/ixgbe/devlink/region.c
index 76f6571c3c34..478b4f435120 100644
--- a/drivers/net/ethernet/intel/ixgbe/devlink/region.c
+++ b/drivers/net/ethernet/intel/ixgbe/devlink/region.c
@@ -74,7 +74,7 @@ static int ixgbe_devlink_nvm_snapshot(struct devlink *devlink,
 		 * total period of reading whole NVM is longer than the maximum
 		 * period the lock can be taken defined by the IXGBE_NVM_TIMEOUT.
 		 */
-		err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+		err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
 		if (err) {
 			NL_SET_ERR_MSG_MOD(extack,
 					   "Failed to acquire NVM semaphore");
@@ -184,7 +184,7 @@ static int ixgbe_devlink_nvm_read(struct devlink *devlink,
 		return -ERANGE;
 	}
 
-	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack, "Failed to acquire NVM semaphore");
 		return -EBUSY;
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
index 87b03c1992a8..d74116441d1c 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.c
@@ -56,7 +56,7 @@ static bool ixgbe_should_retry_aci_send_cmd_execute(u16 opcode)
  * Admin Command failed with error Y.
  */
 static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
-				      struct ixgbe_aci_desc *desc,
+				      struct libie_aq_desc *desc,
 				      void *buf, u16 buf_size)
 {
 	u16 opcode, buf_tail_size = buf_size % 4;
@@ -64,7 +64,7 @@ static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
 	u32 hicr, i, buf_tail = 0;
 	bool valid_buf = false;
 
-	hw->aci.last_status = IXGBE_ACI_RC_OK;
+	hw->aci.last_status = LIBIE_AQ_RC_OK;
 
 	/* It's necessary to check if mechanism is enabled */
 	hicr = IXGBE_READ_REG(hw, IXGBE_PF_HICR);
@@ -73,7 +73,7 @@ static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
 		return -EIO;
 
 	if (hicr & IXGBE_PF_HICR_C) {
-		hw->aci.last_status = IXGBE_ACI_RC_EBUSY;
+		hw->aci.last_status = LIBIE_AQ_RC_EBUSY;
 		return -EBUSY;
 	}
 
@@ -83,9 +83,9 @@ static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
 		return -EINVAL;
 
 	if (buf)
-		desc->flags |= cpu_to_le16(IXGBE_ACI_FLAG_BUF);
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 
-	if (desc->flags & cpu_to_le16(IXGBE_ACI_FLAG_BUF)) {
+	if (desc->flags & cpu_to_le16(LIBIE_AQ_FLAG_BUF)) {
 		if ((buf && !buf_size) ||
 		    (!buf && buf_size))
 			return -EINVAL;
@@ -98,12 +98,12 @@ static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
 			memcpy(&buf_tail, buf + buf_size - buf_tail_size,
 			       buf_tail_size);
 
-		if (((buf_size + 3) & ~0x3) > IXGBE_ACI_LG_BUF)
-			desc->flags |= cpu_to_le16(IXGBE_ACI_FLAG_LB);
+		if (((buf_size + 3) & ~0x3) > LIBIE_AQ_LG_BUF)
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 
 		desc->datalen = cpu_to_le16(buf_size);
 
-		if (desc->flags & cpu_to_le16(IXGBE_ACI_FLAG_RD)) {
+		if (desc->flags & cpu_to_le16(LIBIE_AQ_FLAG_RD)) {
 			for (i = 0; i < buf_size / 4; i++)
 				IXGBE_WRITE_REG(hw, IXGBE_PF_HIBA(i), ((u32 *)buf)[i]);
 			if (buf_tail_size)
@@ -174,7 +174,7 @@ static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
 		return -EIO;
 
 	if (desc->retval) {
-		hw->aci.last_status = (enum ixgbe_aci_err)
+		hw->aci.last_status = (enum libie_aq_err)
 			le16_to_cpu(desc->retval);
 		return -EIO;
 	}
@@ -207,12 +207,12 @@ static int ixgbe_aci_send_cmd_execute(struct ixgbe_hw *hw,
  *
  * Return: the exit code of the operation.
  */
-int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc,
+int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct libie_aq_desc *desc,
 		       void *buf, u16 buf_size)
 {
 	u16 opcode = le16_to_cpu(desc->opcode);
-	struct ixgbe_aci_desc desc_cpy;
-	enum ixgbe_aci_err last_status;
+	struct libie_aq_desc desc_cpy;
+	enum libie_aq_err last_status;
 	u8 idx = 0, *buf_cpy = NULL;
 	bool is_cmd_for_retry;
 	unsigned long timeout;
@@ -237,7 +237,7 @@ int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc,
 		mutex_unlock(&hw->aci.lock);
 
 		if (!is_cmd_for_retry || !err ||
-		    last_status != IXGBE_ACI_RC_EBUSY)
+		    last_status != LIBIE_AQ_RC_EBUSY)
 			break;
 
 		if (buf)
@@ -286,7 +286,7 @@ bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw)
 int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e,
 			bool *pending)
 {
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 	int err;
 
 	if (!e || (!e->msg_buf && e->buf_len))
@@ -335,12 +335,12 @@ aci_get_event_exit:
  * Helper function to fill the descriptor desc with default values
  * and the provided opcode.
  */
-void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode)
+void ixgbe_fill_dflt_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode)
 {
 	/* Zero out the desc. */
 	memset(desc, 0, sizeof(*desc));
 	desc->opcode = cpu_to_le16(opcode);
-	desc->flags = cpu_to_le16(IXGBE_ACI_FLAG_SI);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
 }
 
 /**
@@ -353,8 +353,8 @@ void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode)
  */
 static int ixgbe_aci_get_fw_ver(struct ixgbe_hw *hw)
 {
-	struct ixgbe_aci_cmd_get_ver *resp;
-	struct ixgbe_aci_desc desc;
+	struct libie_aqc_get_ver *resp;
+	struct libie_aq_desc desc;
 	int err;
 
 	resp = &desc.params.get_ver;
@@ -393,12 +393,12 @@ static int ixgbe_aci_get_fw_ver(struct ixgbe_hw *hw)
  *
  * Return: the exit code of the operation.
  */
-static int ixgbe_aci_req_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
-			     enum ixgbe_aci_res_access_type access,
+static int ixgbe_aci_req_res(struct ixgbe_hw *hw, enum libie_aq_res_id res,
+			     enum libie_aq_res_access_type access,
 			     u8 sdp_number, u32 *timeout)
 {
-	struct ixgbe_aci_cmd_req_res *cmd_resp;
-	struct ixgbe_aci_desc desc;
+	struct libie_aqc_req_res *cmd_resp;
+	struct libie_aq_desc desc;
 	int err;
 
 	cmd_resp = &desc.params.res_owner;
@@ -417,7 +417,7 @@ static int ixgbe_aci_req_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
 	 * with a busy return value and the timeout field indicates the maximum
 	 * time the current owner of the resource has to free it.
 	 */
-	if (!err || hw->aci.last_status == IXGBE_ACI_RC_EBUSY)
+	if (!err || hw->aci.last_status == LIBIE_AQ_RC_EBUSY)
 		*timeout = le32_to_cpu(cmd_resp->timeout);
 
 	return err;
@@ -433,11 +433,11 @@ static int ixgbe_aci_req_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
  *
  * Return: the exit code of the operation.
  */
-static int ixgbe_aci_release_res(struct ixgbe_hw *hw,
-				 enum ixgbe_aci_res_ids res, u8 sdp_number)
+static int ixgbe_aci_release_res(struct ixgbe_hw *hw, enum libie_aq_res_id res,
+				 u8 sdp_number)
 {
-	struct ixgbe_aci_cmd_req_res *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aqc_req_res *cmd;
+	struct libie_aq_desc desc;
 
 	cmd = &desc.params.res_owner;
 
@@ -465,8 +465,8 @@ static int ixgbe_aci_release_res(struct ixgbe_hw *hw,
  *
  * Return: the exit code of the operation.
  */
-int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
-		      enum ixgbe_aci_res_access_type access, u32 timeout)
+int ixgbe_acquire_res(struct ixgbe_hw *hw, enum libie_aq_res_id res,
+		      enum libie_aq_res_access_type access, u32 timeout)
 {
 #define IXGBE_RES_POLLING_DELAY_MS	10
 	u32 delay = IXGBE_RES_POLLING_DELAY_MS;
@@ -514,7 +514,7 @@ int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
  *
  * Release a common resource using ixgbe_aci_release_res.
  */
-void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res)
+void ixgbe_release_res(struct ixgbe_hw *hw, enum libie_aq_res_id res)
 {
 	u32 total_delay = 0;
 	int err;
@@ -547,7 +547,7 @@ void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res)
  */
 static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw,
 				  struct ixgbe_hw_caps *caps,
-				  struct ixgbe_aci_cmd_list_caps_elem *elem,
+				  struct libie_aqc_list_caps_elem *elem,
 				  const char *prefix)
 {
 	u32 logical_id = le32_to_cpu(elem->logical_id);
@@ -556,67 +556,67 @@ static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw,
 	u16 cap = le16_to_cpu(elem->cap);
 
 	switch (cap) {
-	case IXGBE_ACI_CAPS_VALID_FUNCTIONS:
+	case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
 		caps->valid_functions = number;
 		break;
-	case IXGBE_ACI_CAPS_SRIOV:
+	case LIBIE_AQC_CAPS_SRIOV:
 		caps->sr_iov_1_1 = (number == 1);
 		break;
-	case IXGBE_ACI_CAPS_VMDQ:
+	case LIBIE_AQC_CAPS_VMDQ:
 		caps->vmdq = (number == 1);
 		break;
-	case IXGBE_ACI_CAPS_DCB:
+	case LIBIE_AQC_CAPS_DCB:
 		caps->dcb = (number == 1);
 		caps->active_tc_bitmap = logical_id;
 		caps->maxtc = phys_id;
 		break;
-	case IXGBE_ACI_CAPS_RSS:
+	case LIBIE_AQC_CAPS_RSS:
 		caps->rss_table_size = number;
 		caps->rss_table_entry_width = logical_id;
 		break;
-	case IXGBE_ACI_CAPS_RXQS:
+	case LIBIE_AQC_CAPS_RXQS:
 		caps->num_rxq = number;
 		caps->rxq_first_id = phys_id;
 		break;
-	case IXGBE_ACI_CAPS_TXQS:
+	case LIBIE_AQC_CAPS_TXQS:
 		caps->num_txq = number;
 		caps->txq_first_id = phys_id;
 		break;
-	case IXGBE_ACI_CAPS_MSIX:
+	case LIBIE_AQC_CAPS_MSIX:
 		caps->num_msix_vectors = number;
 		caps->msix_vector_first_id = phys_id;
 		break;
-	case IXGBE_ACI_CAPS_NVM_VER:
+	case LIBIE_AQC_CAPS_NVM_VER:
 		break;
-	case IXGBE_ACI_CAPS_PENDING_NVM_VER:
+	case LIBIE_AQC_CAPS_PENDING_NVM_VER:
 		caps->nvm_update_pending_nvm = true;
 		break;
-	case IXGBE_ACI_CAPS_PENDING_OROM_VER:
+	case LIBIE_AQC_CAPS_PENDING_OROM_VER:
 		caps->nvm_update_pending_orom = true;
 		break;
-	case IXGBE_ACI_CAPS_PENDING_NET_VER:
+	case LIBIE_AQC_CAPS_PENDING_NET_VER:
 		caps->nvm_update_pending_netlist = true;
 		break;
-	case IXGBE_ACI_CAPS_NVM_MGMT:
+	case LIBIE_AQC_CAPS_NVM_MGMT:
 		caps->nvm_unified_update =
 			(number & IXGBE_NVM_MGMT_UNIFIED_UPD_SUPPORT) ?
 			true : false;
 		break;
-	case IXGBE_ACI_CAPS_MAX_MTU:
+	case LIBIE_AQC_CAPS_MAX_MTU:
 		caps->max_mtu = number;
 		break;
-	case IXGBE_ACI_CAPS_PCIE_RESET_AVOIDANCE:
+	case LIBIE_AQC_CAPS_PCIE_RESET_AVOIDANCE:
 		caps->pcie_reset_avoidance = (number > 0);
 		break;
-	case IXGBE_ACI_CAPS_POST_UPDATE_RESET_RESTRICT:
+	case LIBIE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT:
 		caps->reset_restrict_support = (number == 1);
 		break;
-	case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0:
-	case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG1:
-	case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG2:
-	case IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG3:
+	case LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG0:
+	case LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG1:
+	case LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG2:
+	case LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG3:
 	{
-		u8 index = cap - IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0;
+		u8 index = cap - LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG0;
 
 		caps->ext_topo_dev_img_ver_high[index] = number;
 		caps->ext_topo_dev_img_ver_low[index] = logical_id;
@@ -637,62 +637,62 @@ static bool ixgbe_parse_e610_caps(struct ixgbe_hw *hw,
 }
 
 /**
- * ixgbe_parse_valid_functions_cap - Parse IXGBE_ACI_CAPS_VALID_FUNCTIONS caps
+ * ixgbe_parse_valid_functions_cap - Parse LIBIE_AQC_CAPS_VALID_FUNCTIONS caps
  * @hw: pointer to the HW struct
  * @dev_p: pointer to device capabilities structure
  * @cap: capability element to parse
  *
- * Parse IXGBE_ACI_CAPS_VALID_FUNCTIONS for device capabilities.
+ * Parse LIBIE_AQC_CAPS_VALID_FUNCTIONS for device capabilities.
  */
 static void
 ixgbe_parse_valid_functions_cap(struct ixgbe_hw *hw,
 				struct ixgbe_hw_dev_caps *dev_p,
-				struct ixgbe_aci_cmd_list_caps_elem *cap)
+				struct libie_aqc_list_caps_elem *cap)
 {
 	dev_p->num_funcs = hweight32(le32_to_cpu(cap->number));
 }
 
 /**
- * ixgbe_parse_vf_dev_caps - Parse IXGBE_ACI_CAPS_VF device caps
+ * ixgbe_parse_vf_dev_caps - Parse LIBIE_AQC_CAPS_VF device caps
  * @hw: pointer to the HW struct
  * @dev_p: pointer to device capabilities structure
  * @cap: capability element to parse
  *
- * Parse IXGBE_ACI_CAPS_VF for device capabilities.
+ * Parse LIBIE_AQC_CAPS_VF for device capabilities.
  */
 static void ixgbe_parse_vf_dev_caps(struct ixgbe_hw *hw,
 				    struct ixgbe_hw_dev_caps *dev_p,
-				    struct ixgbe_aci_cmd_list_caps_elem *cap)
+				    struct libie_aqc_list_caps_elem *cap)
 {
 	dev_p->num_vfs_exposed = le32_to_cpu(cap->number);
 }
 
 /**
- * ixgbe_parse_vsi_dev_caps - Parse IXGBE_ACI_CAPS_VSI device caps
+ * ixgbe_parse_vsi_dev_caps - Parse LIBIE_AQC_CAPS_VSI device caps
  * @hw: pointer to the HW struct
  * @dev_p: pointer to device capabilities structure
  * @cap: capability element to parse
  *
- * Parse IXGBE_ACI_CAPS_VSI for device capabilities.
+ * Parse LIBIE_AQC_CAPS_VSI for device capabilities.
  */
 static void ixgbe_parse_vsi_dev_caps(struct ixgbe_hw *hw,
 				     struct ixgbe_hw_dev_caps *dev_p,
-				     struct ixgbe_aci_cmd_list_caps_elem *cap)
+				     struct libie_aqc_list_caps_elem *cap)
 {
 	dev_p->num_vsi_allocd_to_host = le32_to_cpu(cap->number);
 }
 
 /**
- * ixgbe_parse_fdir_dev_caps - Parse IXGBE_ACI_CAPS_FD device caps
+ * ixgbe_parse_fdir_dev_caps - Parse LIBIE_AQC_CAPS_FD device caps
  * @hw: pointer to the HW struct
  * @dev_p: pointer to device capabilities structure
  * @cap: capability element to parse
  *
- * Parse IXGBE_ACI_CAPS_FD for device capabilities.
+ * Parse LIBIE_AQC_CAPS_FD for device capabilities.
  */
 static void ixgbe_parse_fdir_dev_caps(struct ixgbe_hw *hw,
 				      struct ixgbe_hw_dev_caps *dev_p,
-				      struct ixgbe_aci_cmd_list_caps_elem *cap)
+				      struct libie_aqc_list_caps_elem *cap)
 {
 	dev_p->num_flow_director_fltr = le32_to_cpu(cap->number);
 }
@@ -715,10 +715,10 @@ static void ixgbe_parse_dev_caps(struct ixgbe_hw *hw,
 				 struct ixgbe_hw_dev_caps *dev_p,
 				 void *buf, u32 cap_count)
 {
-	struct ixgbe_aci_cmd_list_caps_elem *cap_resp;
+	struct libie_aqc_list_caps_elem *cap_resp;
 	u32 i;
 
-	cap_resp = (struct ixgbe_aci_cmd_list_caps_elem *)buf;
+	cap_resp = (struct libie_aqc_list_caps_elem *)buf;
 
 	memset(dev_p, 0, sizeof(*dev_p));
 
@@ -729,17 +729,17 @@ static void ixgbe_parse_dev_caps(struct ixgbe_hw *hw,
 				      "dev caps");
 
 		switch (cap) {
-		case IXGBE_ACI_CAPS_VALID_FUNCTIONS:
+		case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
 			ixgbe_parse_valid_functions_cap(hw, dev_p,
 							&cap_resp[i]);
 			break;
-		case IXGBE_ACI_CAPS_VF:
+		case LIBIE_AQC_CAPS_VF:
 			ixgbe_parse_vf_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case IXGBE_ACI_CAPS_VSI:
+		case LIBIE_AQC_CAPS_VSI:
 			ixgbe_parse_vsi_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
-		case  IXGBE_ACI_CAPS_FD:
+		case  LIBIE_AQC_CAPS_FD:
 			ixgbe_parse_fdir_dev_caps(hw, dev_p, &cap_resp[i]);
 			break;
 		default:
@@ -750,16 +750,16 @@ static void ixgbe_parse_dev_caps(struct ixgbe_hw *hw,
 }
 
 /**
- * ixgbe_parse_vf_func_caps - Parse IXGBE_ACI_CAPS_VF function caps
+ * ixgbe_parse_vf_func_caps - Parse LIBIE_AQC_CAPS_VF function caps
  * @hw: pointer to the HW struct
  * @func_p: pointer to function capabilities structure
  * @cap: pointer to the capability element to parse
  *
- * Extract function capabilities for IXGBE_ACI_CAPS_VF.
+ * Extract function capabilities for LIBIE_AQC_CAPS_VF.
  */
 static void ixgbe_parse_vf_func_caps(struct ixgbe_hw *hw,
 				     struct ixgbe_hw_func_caps *func_p,
-				     struct ixgbe_aci_cmd_list_caps_elem *cap)
+				     struct libie_aqc_list_caps_elem *cap)
 {
 	func_p->num_allocd_vfs = le32_to_cpu(cap->number);
 	func_p->vf_base_id = le32_to_cpu(cap->logical_id);
@@ -786,16 +786,16 @@ static u32 ixgbe_get_num_per_func(struct ixgbe_hw *hw, u32 max)
 }
 
 /**
- * ixgbe_parse_vsi_func_caps - Parse IXGBE_ACI_CAPS_VSI function caps
+ * ixgbe_parse_vsi_func_caps - Parse LIBIE_AQC_CAPS_VSI function caps
  * @hw: pointer to the HW struct
  * @func_p: pointer to function capabilities structure
  * @cap: pointer to the capability element to parse
  *
- * Extract function capabilities for IXGBE_ACI_CAPS_VSI.
+ * Extract function capabilities for LIBIE_AQC_CAPS_VSI.
  */
 static void ixgbe_parse_vsi_func_caps(struct ixgbe_hw *hw,
 				      struct ixgbe_hw_func_caps *func_p,
-				      struct ixgbe_aci_cmd_list_caps_elem *cap)
+				      struct libie_aqc_list_caps_elem *cap)
 {
 	func_p->guar_num_vsi = ixgbe_get_num_per_func(hw, IXGBE_MAX_VSI);
 }
@@ -818,10 +818,10 @@ static void ixgbe_parse_func_caps(struct ixgbe_hw *hw,
 				  struct ixgbe_hw_func_caps *func_p,
 				  void *buf, u32 cap_count)
 {
-	struct ixgbe_aci_cmd_list_caps_elem *cap_resp;
+	struct libie_aqc_list_caps_elem *cap_resp;
 	u32 i;
 
-	cap_resp = (struct ixgbe_aci_cmd_list_caps_elem *)buf;
+	cap_resp = (struct libie_aqc_list_caps_elem *)buf;
 
 	memset(func_p, 0, sizeof(*func_p));
 
@@ -832,10 +832,10 @@ static void ixgbe_parse_func_caps(struct ixgbe_hw *hw,
 				      &cap_resp[i], "func caps");
 
 		switch (cap) {
-		case IXGBE_ACI_CAPS_VF:
+		case LIBIE_AQC_CAPS_VF:
 			ixgbe_parse_vf_func_caps(hw, func_p, &cap_resp[i]);
 			break;
-		case IXGBE_ACI_CAPS_VSI:
+		case LIBIE_AQC_CAPS_VSI:
 			ixgbe_parse_vsi_func_caps(hw, func_p, &cap_resp[i]);
 			break;
 		default:
@@ -869,8 +869,8 @@ static void ixgbe_parse_func_caps(struct ixgbe_hw *hw,
 int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size,
 			u32 *cap_count, enum ixgbe_aci_opc opc)
 {
-	struct ixgbe_aci_cmd_list_caps *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aqc_list_caps *cmd;
+	struct libie_aq_desc desc;
 	int err;
 
 	cmd = &desc.params.get_cap;
@@ -914,7 +914,7 @@ int ixgbe_discover_dev_caps(struct ixgbe_hw *hw,
 	 * possible size that firmware can return.
 	 */
 	cap_count = IXGBE_ACI_MAX_BUFFER_SIZE /
-		    sizeof(struct ixgbe_aci_cmd_list_caps_elem);
+		    sizeof(struct libie_aqc_list_caps_elem);
 
 	err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE,
 				  &cap_count,
@@ -953,7 +953,7 @@ int ixgbe_discover_func_caps(struct ixgbe_hw *hw,
 	 * possible size that firmware can return.
 	 */
 	cap_count = IXGBE_ACI_MAX_BUFFER_SIZE /
-		    sizeof(struct ixgbe_aci_cmd_list_caps_elem);
+		    sizeof(struct libie_aqc_list_caps_elem);
 
 	err = ixgbe_aci_list_caps(hw, cbuf, IXGBE_ACI_MAX_BUFFER_SIZE,
 				  &cap_count,
@@ -996,9 +996,9 @@ int ixgbe_get_caps(struct ixgbe_hw *hw)
 int ixgbe_aci_disable_rxen(struct ixgbe_hw *hw)
 {
 	struct ixgbe_aci_cmd_disable_rxen *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.disable_rxen;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_disable_rxen);
 
@@ -1024,10 +1024,10 @@ int ixgbe_aci_get_phy_caps(struct ixgbe_hw *hw, bool qual_mods, u8 report_mode,
 {
 	struct ixgbe_aci_cmd_get_phy_caps *cmd;
 	u16 pcaps_size = sizeof(*pcaps);
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 	int err;
 
-	cmd = &desc.params.get_phy;
+	cmd = libie_aq_raw(&desc);
 
 	if (!pcaps || (report_mode & ~IXGBE_ACI_REPORT_MODE_M))
 		return -EINVAL;
@@ -1091,18 +1091,20 @@ void ixgbe_copy_phy_caps_to_cfg(struct ixgbe_aci_cmd_get_phy_caps_data *caps,
 int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw,
 			  struct ixgbe_aci_cmd_set_phy_cfg_data *cfg)
 {
-	struct ixgbe_aci_desc desc;
+	struct ixgbe_aci_cmd_set_phy_cfg *cmd;
+	struct libie_aq_desc desc;
 	int err;
 
 	if (!cfg)
 		return -EINVAL;
 
+	cmd = libie_aq_raw(&desc);
 	/* Ensure that only valid bits of cfg->caps can be turned on. */
 	cfg->caps &= IXGBE_ACI_PHY_ENA_VALID_MASK;
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_phy_cfg);
-	desc.params.set_phy.lport_num = hw->bus.func;
-	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+	cmd->lport_num = hw->bus.func;
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	err = ixgbe_aci_send_cmd(hw, &desc, cfg, sizeof(*cfg));
 	if (!err)
@@ -1123,9 +1125,9 @@ int ixgbe_aci_set_phy_cfg(struct ixgbe_hw *hw,
 int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link)
 {
 	struct ixgbe_aci_cmd_restart_an *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.restart_an;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_restart_an);
 
@@ -1151,9 +1153,9 @@ int ixgbe_aci_set_link_restart_an(struct ixgbe_hw *hw, bool ena_link)
 static bool ixgbe_is_media_cage_present(struct ixgbe_hw *hw)
 {
 	struct ixgbe_aci_cmd_get_link_topo *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.get_link_topo;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo);
 
@@ -1346,7 +1348,7 @@ int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse,
 	struct ixgbe_aci_cmd_get_link_status *resp;
 	struct ixgbe_link_status *li_old, *li;
 	struct ixgbe_fc_info *hw_fc_info;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 	bool tx_pause, rx_pause;
 	u8 cmd_flags;
 	int err;
@@ -1360,7 +1362,7 @@ int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse,
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_status);
 	cmd_flags = (ena_lse) ? IXGBE_ACI_LSE_ENA : IXGBE_ACI_LSE_DIS;
-	resp = &desc.params.get_link_status;
+	resp = libie_aq_raw(&desc);
 	resp->cmd_flags = cpu_to_le16(cmd_flags);
 	resp->lport_num = hw->bus.func;
 
@@ -1423,9 +1425,9 @@ int ixgbe_aci_get_link_info(struct ixgbe_hw *hw, bool ena_lse,
 int ixgbe_aci_set_event_mask(struct ixgbe_hw *hw, u8 port_num, u16 mask)
 {
 	struct ixgbe_aci_cmd_set_event_mask *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_event_mask;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_event_mask);
 
@@ -1496,9 +1498,9 @@ static int ixgbe_start_hw_e610(struct ixgbe_hw *hw)
 int ixgbe_aci_set_port_id_led(struct ixgbe_hw *hw, bool orig_mode)
 {
 	struct ixgbe_aci_cmd_set_port_id_led *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.set_port_id_led;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_set_port_id_led);
 
@@ -2260,19 +2262,20 @@ int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw,
 			       struct ixgbe_aci_cmd_get_link_topo *cmd,
 			       u8 *node_part_number, u16 *node_handle)
 {
-	struct ixgbe_aci_desc desc;
+	struct ixgbe_aci_cmd_get_link_topo *resp;
+	struct libie_aq_desc desc;
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_get_link_topo);
-	desc.params.get_link_topo = *cmd;
+	resp = libie_aq_raw(&desc);
+	*resp = *cmd;
 
 	if (ixgbe_aci_send_cmd(hw, &desc, NULL, 0))
 		return -EOPNOTSUPP;
 
 	if (node_handle)
-		*node_handle =
-			le16_to_cpu(desc.params.get_link_topo.addr.handle);
+		*node_handle = le16_to_cpu(resp->addr.handle);
 	if (node_part_number)
-		*node_part_number = desc.params.get_link_topo.node_part_num;
+		*node_part_number = resp->node_part_num;
 
 	return 0;
 }
@@ -2286,8 +2289,7 @@ int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw,
  *
  * Return: the exit code of the operation.
  */
-int ixgbe_acquire_nvm(struct ixgbe_hw *hw,
-		      enum ixgbe_aci_res_access_type access)
+int ixgbe_acquire_nvm(struct ixgbe_hw *hw, enum libie_aq_res_access_type access)
 {
 	u32 fla;
 
@@ -2296,7 +2298,7 @@ int ixgbe_acquire_nvm(struct ixgbe_hw *hw,
 	if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0)
 		return 0;
 
-	return ixgbe_acquire_res(hw, IXGBE_NVM_RES_ID, access,
+	return ixgbe_acquire_res(hw, LIBIE_AQC_RES_ID_NVM, access,
 				 IXGBE_NVM_TIMEOUT);
 }
 
@@ -2315,7 +2317,7 @@ void ixgbe_release_nvm(struct ixgbe_hw *hw)
 	if ((fla & IXGBE_GLNVM_FLA_LOCKED_M) == 0)
 		return;
 
-	ixgbe_release_res(hw, IXGBE_NVM_RES_ID);
+	ixgbe_release_res(hw, LIBIE_AQC_RES_ID_NVM);
 }
 
 /**
@@ -2337,12 +2339,12 @@ int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
 		       bool read_shadow_ram)
 {
 	struct ixgbe_aci_cmd_nvm *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
 	if (offset > IXGBE_ACI_NVM_MAX_OFFSET)
 		return -EINVAL;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_read);
 
@@ -2372,7 +2374,7 @@ int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
 int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid)
 {
 	struct ixgbe_aci_cmd_nvm *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 	__le16 len;
 	int err;
 
@@ -2385,7 +2387,7 @@ int ixgbe_aci_erase_nvm(struct ixgbe_hw *hw, u16 module_typeid)
 	if (err)
 		return err;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_erase);
 
@@ -2416,9 +2418,9 @@ int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid,
 			 bool last_command, u8 command_flags)
 {
 	struct ixgbe_aci_cmd_nvm *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 
 	/* In offset the highest byte must be zeroed. */
 	if (offset & 0xFF000000)
@@ -2436,7 +2438,7 @@ int ixgbe_aci_update_nvm(struct ixgbe_hw *hw, u16 module_typeid,
 	cmd->offset_high = FIELD_GET(IXGBE_ACI_NVM_OFFSET_HI_U_MASK, offset);
 	cmd->length = cpu_to_le16(length);
 
-	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	return ixgbe_aci_send_cmd(hw, &desc, data, length);
 }
@@ -2467,10 +2469,10 @@ int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags,
 			     u8 *response_flags)
 {
 	struct ixgbe_aci_cmd_nvm *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 	s32 err;
 
-	cmd = &desc.params.nvm;
+	cmd = libie_aq_raw(&desc);
 	ixgbe_fill_dflt_direct_cmd_desc(&desc,
 					ixgbe_aci_opc_nvm_write_activate);
 
@@ -2498,14 +2500,14 @@ int ixgbe_nvm_write_activate(struct ixgbe_hw *hw, u16 cmd_flags,
 int ixgbe_nvm_validate_checksum(struct ixgbe_hw *hw)
 {
 	struct ixgbe_aci_cmd_nvm_checksum *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 	int err;
 
-	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
 	if (err)
 		return err;
 
-	cmd = &desc.params.nvm_checksum;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_checksum);
 	cmd->flags = IXGBE_ACI_NVM_CHECKSUM_VERIFY;
@@ -2541,7 +2543,7 @@ static int ixgbe_discover_flash_size(struct ixgbe_hw *hw)
 	u32 min_size = 0, max_size = IXGBE_ACI_NVM_MAX_OFFSET + 1;
 	int err;
 
-	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
 	if (err)
 		return err;
 
@@ -2552,7 +2554,7 @@ static int ixgbe_discover_flash_size(struct ixgbe_hw *hw)
 
 		err = ixgbe_read_flat_nvm(hw, offset, &len, &data, false);
 		if (err == -EIO &&
-		    hw->aci.last_status == IXGBE_ACI_RC_EINVAL) {
+		    hw->aci.last_status == LIBIE_AQ_RC_EINVAL) {
 			err = 0;
 			max_size = offset;
 		} else if (!err) {
@@ -2805,7 +2807,7 @@ static int ixgbe_read_flash_module(struct ixgbe_hw *hw,
 	if (!start)
 		return -EINVAL;
 
-	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
 	if (err)
 		return err;
 
@@ -3389,7 +3391,7 @@ int ixgbe_get_flash_data(struct ixgbe_hw *hw)
  */
 int ixgbe_aci_nvm_update_empr(struct ixgbe_hw *hw)
 {
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_update_empr);
 
@@ -3415,15 +3417,15 @@ int ixgbe_nvm_set_pkg_data(struct ixgbe_hw *hw, bool del_pkg_data_flag,
 			   u8 *data, u16 length)
 {
 	struct ixgbe_aci_cmd_nvm_pkg_data *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 
 	if (length != 0 && !data)
 		return -EINVAL;
 
-	cmd = &desc.params.pkg_data;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc, ixgbe_aci_opc_nvm_pkg_data);
-	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	if (del_pkg_data_flag)
 		cmd->cmd_flags |= IXGBE_ACI_NVM_PKG_DELETE;
@@ -3453,17 +3455,17 @@ int ixgbe_nvm_pass_component_tbl(struct ixgbe_hw *hw, u8 *data, u16 length,
 				 u8 *comp_response_code)
 {
 	struct ixgbe_aci_cmd_nvm_pass_comp_tbl *cmd;
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 	int err;
 
 	if (!data || !comp_response || !comp_response_code)
 		return -EINVAL;
 
-	cmd = &desc.params.pass_comp_tbl;
+	cmd = libie_aq_raw(&desc);
 
 	ixgbe_fill_dflt_direct_cmd_desc(&desc,
 					ixgbe_aci_opc_nvm_pass_component_tbl);
-	desc.flags |= cpu_to_le16(IXGBE_ACI_FLAG_RD);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_RD);
 
 	cmd->transfer_flag = transfer_flag;
 	err = ixgbe_aci_send_cmd(hw, &desc, data, length);
@@ -3617,7 +3619,7 @@ int ixgbe_read_ee_aci_e610(struct ixgbe_hw *hw, u16 offset, u16 *data)
 			return err;
 	}
 
-	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
 	if (err)
 		return err;
 
@@ -3650,7 +3652,7 @@ int ixgbe_read_ee_aci_buffer_e610(struct ixgbe_hw *hw, u16 offset,
 			return err;
 	}
 
-	err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
 	if (err)
 		return err;
 
@@ -3690,7 +3692,7 @@ int ixgbe_validate_eeprom_checksum_e610(struct ixgbe_hw *hw, u16 *checksum_val)
 	if (checksum_val) {
 		u16 tmp_checksum;
 
-		err = ixgbe_acquire_nvm(hw, IXGBE_RES_READ);
+		err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_READ);
 		if (err)
 			return err;
 
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
index bb31d65bd1c8..782c489b0fa7 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_e610.h
@@ -6,15 +6,15 @@
 
 #include "ixgbe_type.h"
 
-int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct ixgbe_aci_desc *desc,
+int ixgbe_aci_send_cmd(struct ixgbe_hw *hw, struct libie_aq_desc *desc,
 		       void *buf, u16 buf_size);
 bool ixgbe_aci_check_event_pending(struct ixgbe_hw *hw);
 int ixgbe_aci_get_event(struct ixgbe_hw *hw, struct ixgbe_aci_event *e,
 			bool *pending);
-void ixgbe_fill_dflt_direct_cmd_desc(struct ixgbe_aci_desc *desc, u16 opcode);
-int ixgbe_acquire_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res,
-		      enum ixgbe_aci_res_access_type access, u32 timeout);
-void ixgbe_release_res(struct ixgbe_hw *hw, enum ixgbe_aci_res_ids res);
+void ixgbe_fill_dflt_direct_cmd_desc(struct libie_aq_desc *desc, u16 opcode);
+int ixgbe_acquire_res(struct ixgbe_hw *hw, enum libie_aq_res_id res,
+		      enum libie_aq_res_access_type access, u32 timeout);
+void ixgbe_release_res(struct ixgbe_hw *hw, enum libie_aq_res_id res);
 int ixgbe_aci_list_caps(struct ixgbe_hw *hw, void *buf, u16 buf_size,
 			u32 *cap_count, enum ixgbe_aci_opc opc);
 int ixgbe_discover_dev_caps(struct ixgbe_hw *hw,
@@ -62,7 +62,7 @@ int ixgbe_aci_get_netlist_node(struct ixgbe_hw *hw,
 			       struct ixgbe_aci_cmd_get_link_topo *cmd,
 			       u8 *node_part_number, u16 *node_handle);
 int ixgbe_acquire_nvm(struct ixgbe_hw *hw,
-		      enum ixgbe_aci_res_access_type access);
+		      enum libie_aq_res_access_type access);
 void ixgbe_release_nvm(struct ixgbe_hw *hw);
 int ixgbe_aci_read_nvm(struct ixgbe_hw *hw, u16 module_typeid, u32 offset,
 		       u16 length, void *data, bool last_command,
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
index 49d3b66add7e..e5479fc07a07 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fw_update.c
@@ -593,7 +593,7 @@ static int ixgbe_cancel_pending_update(struct ixgbe_adapter *adapter,
 					   "Canceling previous pending update",
 					   component, 0, 0);
 
-	err = ixgbe_acquire_nvm(hw, IXGBE_RES_WRITE);
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_WRITE);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Failed to acquire device flash lock");
@@ -686,7 +686,7 @@ int ixgbe_flash_pldm_image(struct devlink *devlink,
 	if (err)
 		return err;
 
-	err = ixgbe_acquire_nvm(hw, IXGBE_RES_WRITE);
+	err = ixgbe_acquire_nvm(hw, LIBIE_AQC_RES_ACCESS_WRITE);
 	if (err) {
 		NL_SET_ERR_MSG_MOD(extack,
 				   "Failed to acquire device flash lock");
diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
index 09df67f03cf4..d2f22d8558f8 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type_e610.h
@@ -4,6 +4,8 @@
 #ifndef _IXGBE_TYPE_E610_H_
 #define _IXGBE_TYPE_E610_H_
 
+#include <linux/net/intel/libie/adminq.h>
+
 #define BYTES_PER_DWORD	4
 
 /* General E610 defines */
@@ -135,60 +137,6 @@
 /* [ms] timeout of waiting for resource release */
 #define IXGBE_ACI_RELEASE_RES_TIMEOUT		10000
 
-/* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
-#define IXGBE_ACI_LG_BUF		512
-
-/* Flags sub-structure
- * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
- * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
- */
-
-#define IXGBE_ACI_FLAG_DD	BIT(0) /* 0x1 */
-#define IXGBE_ACI_FLAG_CMP	BIT(1) /* 0x2 */
-#define IXGBE_ACI_FLAG_ERR	BIT(2) /* 0x4 */
-#define IXGBE_ACI_FLAG_VFE	BIT(3) /* 0x8 */
-#define IXGBE_ACI_FLAG_LB	BIT(9) /* 0x200 */
-#define IXGBE_ACI_FLAG_RD	BIT(10) /* 0x400 */
-#define IXGBE_ACI_FLAG_VFC	BIT(11) /* 0x800 */
-#define IXGBE_ACI_FLAG_BUF	BIT(12) /* 0x1000 */
-#define IXGBE_ACI_FLAG_SI	BIT(13) /* 0x2000 */
-#define IXGBE_ACI_FLAG_EI	BIT(14) /* 0x4000 */
-#define IXGBE_ACI_FLAG_FE	BIT(15) /* 0x8000 */
-
-/* Admin Command Interface (ACI) error codes */
-enum ixgbe_aci_err {
-	IXGBE_ACI_RC_OK		= 0,  /* Success */
-	IXGBE_ACI_RC_EPERM	= 1,  /* Operation not permitted */
-	IXGBE_ACI_RC_ENOENT	= 2,  /* No such element */
-	IXGBE_ACI_RC_ESRCH	= 3,  /* Bad opcode */
-	IXGBE_ACI_RC_EINTR	= 4,  /* Operation interrupted */
-	IXGBE_ACI_RC_EIO	= 5,  /* I/O error */
-	IXGBE_ACI_RC_ENXIO	= 6,  /* No such resource */
-	IXGBE_ACI_RC_E2BIG	= 7,  /* Arg too long */
-	IXGBE_ACI_RC_EAGAIN	= 8,  /* Try again */
-	IXGBE_ACI_RC_ENOMEM	= 9,  /* Out of memory */
-	IXGBE_ACI_RC_EACCES	= 10, /* Permission denied */
-	IXGBE_ACI_RC_EFAULT	= 11, /* Bad address */
-	IXGBE_ACI_RC_EBUSY	= 12, /* Device or resource busy */
-	IXGBE_ACI_RC_EEXIST	= 13, /* Object already exists */
-	IXGBE_ACI_RC_EINVAL	= 14, /* Invalid argument */
-	IXGBE_ACI_RC_ENOTTY	= 15, /* Not a typewriter */
-	IXGBE_ACI_RC_ENOSPC	= 16, /* No space left or alloc failure */
-	IXGBE_ACI_RC_ENOSYS	= 17, /* Function not implemented */
-	IXGBE_ACI_RC_ERANGE	= 18, /* Parameter out of range */
-	IXGBE_ACI_RC_EFLUSHED	= 19, /* Cmd flushed due to prev cmd error */
-	IXGBE_ACI_RC_BAD_ADDR	= 20, /* Descriptor contains a bad pointer */
-	IXGBE_ACI_RC_EMODE	= 21, /* Op not allowed in current dev mode */
-	IXGBE_ACI_RC_EFBIG	= 22, /* File too big */
-	IXGBE_ACI_RC_ESBCOMP	= 23, /* SB-IOSF completion unsuccessful */
-	IXGBE_ACI_RC_ENOSEC	= 24, /* Missing security manifest */
-	IXGBE_ACI_RC_EBADSIG	= 25, /* Bad RSA signature */
-	IXGBE_ACI_RC_ESVN	= 26, /* SVN number prohibits this package */
-	IXGBE_ACI_RC_EBADMAN	= 27, /* Manifest hash mismatch */
-	IXGBE_ACI_RC_EBADBUF	= 28, /* Buffer hash mismatches manifest */
-	IXGBE_ACI_RC_EACCES_BMCU	= 29, /* BMC Update in progress */
-};
-
 /* Admin Command Interface (ACI) opcodes */
 enum ixgbe_aci_opc {
 	ixgbe_aci_opc_get_ver				= 0x0001,
@@ -265,33 +213,8 @@ enum ixgbe_aci_opc {
 	ixgbe_aci_opc_clear_health_status		= 0xFF23,
 };
 
-/* Get version (direct 0x0001) */
-struct ixgbe_aci_cmd_get_ver {
-	__le32 rom_ver;
-	__le32 fw_build;
-	u8 fw_branch;
-	u8 fw_major;
-	u8 fw_minor;
-	u8 fw_patch;
-	u8 api_branch;
-	u8 api_major;
-	u8 api_minor;
-	u8 api_patch;
-};
-
 #define IXGBE_DRV_VER_STR_LEN_E610	32
 
-/* Send driver version (indirect 0x0002) */
-struct ixgbe_aci_cmd_driver_ver {
-	u8 major_ver;
-	u8 minor_ver;
-	u8 build_ver;
-	u8 subbuild_ver;
-	u8 reserved[4];
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
 /* Get Expanded Error Code (0x0005, direct) */
 struct ixgbe_aci_cmd_get_exp_err {
 	__le32 reason;
@@ -303,98 +226,6 @@ struct ixgbe_aci_cmd_get_exp_err {
 /* FW update timeout definitions are in milliseconds */
 #define IXGBE_NVM_TIMEOUT		180000
 
-enum ixgbe_aci_res_access_type {
-	IXGBE_RES_READ = 1,
-	IXGBE_RES_WRITE
-};
-
-enum ixgbe_aci_res_ids {
-	IXGBE_NVM_RES_ID = 1,
-	IXGBE_SPD_RES_ID,
-	IXGBE_CHANGE_LOCK_RES_ID,
-	IXGBE_GLOBAL_CFG_LOCK_RES_ID
-};
-
-/* Request resource ownership (direct 0x0008)
- * Release resource ownership (direct 0x0009)
- */
-struct ixgbe_aci_cmd_req_res {
-	__le16 res_id;
-	__le16 access_type;
-
-	/* Upon successful completion, FW writes this value and driver is
-	 * expected to release resource before timeout. This value is provided
-	 * in milliseconds.
-	 */
-	__le32 timeout;
-#define IXGBE_ACI_RES_NVM_READ_DFLT_TIMEOUT_MS	3000
-#define IXGBE_ACI_RES_NVM_WRITE_DFLT_TIMEOUT_MS	180000
-#define IXGBE_ACI_RES_CHNG_LOCK_DFLT_TIMEOUT_MS	1000
-#define IXGBE_ACI_RES_GLBL_LOCK_DFLT_TIMEOUT_MS	3000
-	/* For SDP: pin ID of the SDP */
-	__le32 res_number;
-	__le16 status;
-#define IXGBE_ACI_RES_GLBL_SUCCESS		0
-#define IXGBE_ACI_RES_GLBL_IN_PROG		1
-#define IXGBE_ACI_RES_GLBL_DONE			2
-	u8 reserved[2];
-};
-
-/* Get function capabilities (indirect 0x000A)
- * Get device capabilities (indirect 0x000B)
- */
-struct ixgbe_aci_cmd_list_caps {
-	u8 cmd_flags;
-	u8 pf_index;
-	u8 reserved[2];
-	__le32 count;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
-/* Device/Function buffer entry, repeated per reported capability */
-struct ixgbe_aci_cmd_list_caps_elem {
-	__le16 cap;
-#define IXGBE_ACI_CAPS_VALID_FUNCTIONS			0x0005
-#define IXGBE_ACI_MAX_VALID_FUNCTIONS			0x8
-#define IXGBE_ACI_CAPS_SRIOV				0x0012
-#define IXGBE_ACI_CAPS_VF				0x0013
-#define IXGBE_ACI_CAPS_VMDQ				0x0014
-#define IXGBE_ACI_CAPS_VSI				0x0017
-#define IXGBE_ACI_CAPS_DCB				0x0018
-#define IXGBE_ACI_CAPS_RSS				0x0040
-#define IXGBE_ACI_CAPS_RXQS				0x0041
-#define IXGBE_ACI_CAPS_TXQS				0x0042
-#define IXGBE_ACI_CAPS_MSIX				0x0043
-#define IXGBE_ACI_CAPS_FD				0x0045
-#define IXGBE_ACI_CAPS_1588				0x0046
-#define IXGBE_ACI_CAPS_MAX_MTU				0x0047
-#define IXGBE_ACI_CAPS_NVM_VER				0x0048
-#define IXGBE_ACI_CAPS_PENDING_NVM_VER			0x0049
-#define IXGBE_ACI_CAPS_OROM_VER				0x004A
-#define IXGBE_ACI_CAPS_PENDING_OROM_VER			0x004B
-#define IXGBE_ACI_CAPS_PENDING_NET_VER			0x004D
-#define IXGBE_ACI_CAPS_INLINE_IPSEC			0x0070
-#define IXGBE_ACI_CAPS_NUM_ENABLED_PORTS		0x0072
-#define IXGBE_ACI_CAPS_PCIE_RESET_AVOIDANCE		0x0076
-#define IXGBE_ACI_CAPS_POST_UPDATE_RESET_RESTRICT	0x0077
-#define IXGBE_ACI_CAPS_NVM_MGMT				0x0080
-#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG0		0x0081
-#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG1		0x0082
-#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG2		0x0083
-#define IXGBE_ACI_CAPS_EXT_TOPO_DEV_IMG3		0x0084
-	u8 major_ver;
-	u8 minor_ver;
-	/* Number of resources described by this capability */
-	__le32 number;
-	/* Only meaningful for some types of resources */
-	__le32 logical_id;
-	/* Only meaningful for some types of resources */
-	__le32 phys_id;
-	__le64 rsvd1;
-	__le64 rsvd2;
-};
-
 /* Disable RXEN (direct 0x000C) */
 struct ixgbe_aci_cmd_disable_rxen {
 	u8 lport_num;
@@ -960,55 +791,6 @@ struct ixgbe_aci_cmd_nvm_comp_tbl {
 	u8 cvs[]; /* Component Version String */
 } __packed;
 
-/**
- * struct ixgbe_aci_desc - Admin Command (AC) descriptor
- * @flags: IXGBE_ACI_FLAG_* flags
- * @opcode: Admin command opcode
- * @datalen: length in bytes of indirect/external data buffer
- * @retval: return value from firmware
- * @cookie_high: opaque data high-half
- * @cookie_low: opaque data low-half
- * @params: command-specific parameters
- *
- * Descriptor format for commands the driver posts via the
- * Admin Command Interface (ACI).
- * The firmware writes back onto the command descriptor and returns
- * the result of the command. Asynchronous events that are not an immediate
- * result of the command are written to the Admin Command Interface (ACI) using
- * the same descriptor format. Descriptors are in little-endian notation with
- * 32-bit words.
- */
-struct ixgbe_aci_desc {
-	__le16 flags;
-	__le16 opcode;
-	__le16 datalen;
-	__le16 retval;
-	__le32 cookie_high;
-	__le32 cookie_low;
-	union {
-		u8 raw[16];
-		struct ixgbe_aci_cmd_get_ver get_ver;
-		struct ixgbe_aci_cmd_driver_ver driver_ver;
-		struct ixgbe_aci_cmd_get_exp_err exp_err;
-		struct ixgbe_aci_cmd_req_res res_owner;
-		struct ixgbe_aci_cmd_list_caps get_cap;
-		struct ixgbe_aci_cmd_disable_rxen disable_rxen;
-		struct ixgbe_aci_cmd_get_phy_caps get_phy;
-		struct ixgbe_aci_cmd_set_phy_cfg set_phy;
-		struct ixgbe_aci_cmd_restart_an restart_an;
-		struct ixgbe_aci_cmd_get_link_status get_link_status;
-		struct ixgbe_aci_cmd_set_event_mask set_event_mask;
-		struct ixgbe_aci_cmd_set_port_id_led set_port_id_led;
-		struct ixgbe_aci_cmd_get_link_topo get_link_topo;
-		struct ixgbe_aci_cmd_get_link_topo_pin get_link_topo_pin;
-		struct ixgbe_aci_cmd_sff_eeprom read_write_sff_param;
-		struct ixgbe_aci_cmd_nvm nvm;
-		struct ixgbe_aci_cmd_nvm_checksum nvm_checksum;
-		struct ixgbe_aci_cmd_nvm_pkg_data pkg_data;
-		struct ixgbe_aci_cmd_nvm_pass_comp_tbl pass_comp_tbl;
-	} params;
-};
-
 /* E610-specific adapter context structures */
 
 struct ixgbe_link_status {
@@ -1172,7 +954,7 @@ struct ixgbe_hw_dev_caps {
 
 /* ACI event information */
 struct ixgbe_aci_event {
-	struct ixgbe_aci_desc desc;
+	struct libie_aq_desc desc;
 	u8 *msg_buf;
 	u16 msg_len;
 	u16 buf_len;
@@ -1180,7 +962,7 @@ struct ixgbe_aci_event {
 
 struct ixgbe_aci_info {
 	struct mutex lock;		/* admin command interface lock */
-	enum ixgbe_aci_err last_status;	/* last status of sent admin command */
+	enum libie_aq_err last_status;	/* last status of sent admin command */
 };
 
 enum ixgbe_bank_select {
diff --git a/include/linux/net/intel/libie/adminq.h b/include/linux/net/intel/libie/adminq.h
index 3676adc33d3e..b8079e7d842a 100644
--- a/include/linux/net/intel/libie/adminq.h
+++ b/include/linux/net/intel/libie/adminq.h
@@ -146,8 +146,10 @@ LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps);
 
 /* Device/Function buffer entry, repeated per reported capability */
 #define LIBIE_AQC_CAPS_VALID_FUNCTIONS			0x0005
+#define LIBIE_AQC_MAX_VALID_FUNCTIONS			0x8
 #define LIBIE_AQC_CAPS_SRIOV				0x0012
 #define LIBIE_AQC_CAPS_VF				0x0013
+#define LIBIE_AQC_CAPS_VMDQ				0x0014
 #define LIBIE_AQC_CAPS_VSI				0x0017
 #define LIBIE_AQC_CAPS_DCB				0x0018
 #define LIBIE_AQC_CAPS_RSS				0x0040
@@ -165,9 +167,15 @@ LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps);
 #define LIBIE_AQC_CAPS_PENDING_NET_VER			0x004D
 #define LIBIE_AQC_CAPS_RDMA				0x0051
 #define LIBIE_AQC_CAPS_SENSOR_READING			0x0067
+#define LIBIE_AQC_INLINE_IPSEC				0x0070
+#define LIBIE_AQC_CAPS_NUM_ENABLED_PORTS		0x0072
 #define LIBIE_AQC_CAPS_PCIE_RESET_AVOIDANCE		0x0076
 #define LIBIE_AQC_CAPS_POST_UPDATE_RESET_RESTRICT	0x0077
 #define LIBIE_AQC_CAPS_NVM_MGMT				0x0080
+#define LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG0		0x0081
+#define LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG1		0x0082
+#define LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG2		0x0083
+#define LIBIE_AQC_CAPS_EXT_TOPO_DEV_IMG3		0x0084
 #define LIBIE_AQC_CAPS_TX_SCHED_TOPO_COMP_MODE		0x0085
 #define LIBIE_AQC_CAPS_NAC_TOPOLOGY			0x0087
 #define LIBIE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
@@ -236,13 +244,21 @@ LIBIE_CHECK_STRUCT_LEN(32, libie_aq_desc);
 /* FW defined boundary for a large buffer, 4k >= Large buffer > 512 bytes */
 #define LIBIE_AQ_LG_BUF				512
 
+/* Flags sub-structure
+ * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
+ * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
+ */
 #define LIBIE_AQ_FLAG_DD			BIT(0)	/* 0x1    */
 #define LIBIE_AQ_FLAG_CMP			BIT(1)	/* 0x2    */
 #define LIBIE_AQ_FLAG_ERR			BIT(2)	/* 0x4    */
+#define LIBIE_AQ_FLAG_VFE			BIT(3)	/* 0x8    */
 #define LIBIE_AQ_FLAG_LB			BIT(9)	/* 0x200  */
 #define LIBIE_AQ_FLAG_RD			BIT(10)	/* 0x400  */
+#define LIBIE_AQ_FLAG_VFC			BIT(11) /* 0x800  */
 #define LIBIE_AQ_FLAG_BUF			BIT(12)	/* 0x1000 */
 #define LIBIE_AQ_FLAG_SI			BIT(13)	/* 0x2000 */
+#define LIBIE_AQ_FLAG_EI			BIT(14)	/* 0x4000 */
+#define LIBIE_AQ_FLAG_FE			BIT(15)	/* 0x8000 */
 
 /* error codes */
 enum libie_aq_err {
-- 
cgit v1.2.3


From b46012a20006a689529b6b51e05a8ad5320f7e7c Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Fri, 25 Apr 2025 08:08:04 +0200
Subject: i40e: use libie adminq descriptors

Use libie_aq_desc instead of i40e_aq_desc. Do needed changes to allow
clean build.

Get version descriptor is a little less detailed on i40e. To not mess up
with shifting or union inside libie desc use get version descriptor from
i40e.

Move additional caps for i40e to libie.

Fix RCT in declaration that is using libie_aq_desc;

Use libie_aq_raw() wherever it can be used.

The libie aq error is extended, cover it in ice driver just to clean
build. In next patches the libie code for that will be used in each
of intel driver.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Tested-by: Rinitha S <sx.rinitha@intel.com> (A Contingent worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/i40e/i40e_adminq.c     |  68 +-
 drivers/net/ethernet/intel/i40e/i40e_adminq.h     |  12 +-
 drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h | 155 +----
 drivers/net/ethernet/intel/i40e/i40e_common.c     | 754 +++++++++++-----------
 drivers/net/ethernet/intel/i40e/i40e_dcb.c        |  10 +-
 drivers/net/ethernet/intel/i40e/i40e_debugfs.c    |  46 +-
 drivers/net/ethernet/intel/i40e/i40e_ethtool.c    |  14 +-
 drivers/net/ethernet/intel/i40e/i40e_main.c       |  31 +-
 drivers/net/ethernet/intel/i40e/i40e_nvm.c        |  16 +-
 drivers/net/ethernet/intel/i40e/i40e_prototype.h  |  16 +-
 drivers/net/ethernet/intel/i40e/i40e_type.h       |   6 +-
 drivers/net/ethernet/intel/ice/ice_main.c         |   4 +
 include/linux/net/intel/libie/adminq.h            |  17 +
 13 files changed, 499 insertions(+), 650 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
index 175c1320c143..096ec46bb619 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c
@@ -18,7 +18,7 @@ static int i40e_alloc_adminq_asq_ring(struct i40e_hw *hw)
 
 	ret_code = i40e_allocate_dma_mem(hw, &hw->aq.asq.desc_buf,
 					 (hw->aq.num_asq_entries *
-					 sizeof(struct i40e_aq_desc)),
+					 sizeof(struct libie_aq_desc)),
 					 I40E_ADMINQ_DESC_ALIGNMENT);
 	if (ret_code)
 		return ret_code;
@@ -44,7 +44,7 @@ static int i40e_alloc_adminq_arq_ring(struct i40e_hw *hw)
 
 	ret_code = i40e_allocate_dma_mem(hw, &hw->aq.arq.desc_buf,
 					 (hw->aq.num_arq_entries *
-					 sizeof(struct i40e_aq_desc)),
+					 sizeof(struct libie_aq_desc)),
 					 I40E_ADMINQ_DESC_ALIGNMENT);
 
 	return ret_code;
@@ -80,7 +80,7 @@ static void i40e_free_adminq_arq(struct i40e_hw *hw)
  **/
 static int i40e_alloc_arq_bufs(struct i40e_hw *hw)
 {
-	struct i40e_aq_desc *desc;
+	struct libie_aq_desc *desc;
 	struct i40e_dma_mem *bi;
 	int ret_code;
 	int i;
@@ -108,9 +108,9 @@ static int i40e_alloc_arq_bufs(struct i40e_hw *hw)
 		/* now configure the descriptors for use */
 		desc = I40E_ADMINQ_DESC(hw->aq.arq, i);
 
-		desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
+		desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 		if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
-			desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+			desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 		desc->opcode = 0;
 		/* This is in accordance with Admin queue design, there is no
 		 * register for buffer size configuration
@@ -119,12 +119,12 @@ static int i40e_alloc_arq_bufs(struct i40e_hw *hw)
 		desc->retval = 0;
 		desc->cookie_high = 0;
 		desc->cookie_low = 0;
-		desc->params.external.addr_high =
+		desc->params.generic.addr_high =
 			cpu_to_le32(upper_32_bits(bi->pa));
-		desc->params.external.addr_low =
+		desc->params.generic.addr_low =
 			cpu_to_le32(lower_32_bits(bi->pa));
-		desc->params.external.param0 = 0;
-		desc->params.external.param1 = 0;
+		desc->params.generic.param0 = 0;
+		desc->params.generic.param1 = 0;
 	}
 
 alloc_arq_bufs:
@@ -691,8 +691,8 @@ static u16 i40e_clean_asq(struct i40e_hw *hw)
 	struct i40e_adminq_ring *asq = &(hw->aq.asq);
 	struct i40e_asq_cmd_details *details;
 	u16 ntc = asq->next_to_clean;
-	struct i40e_aq_desc desc_cb;
-	struct i40e_aq_desc *desc;
+	struct libie_aq_desc desc_cb;
+	struct libie_aq_desc *desc;
 
 	desc = I40E_ADMINQ_DESC(*asq, ntc);
 	details = I40E_ADMINQ_DETAILS(*asq, ntc);
@@ -750,7 +750,7 @@ static bool i40e_asq_done(struct i40e_hw *hw)
  **/
 static int
 i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
-				  struct i40e_aq_desc *desc,
+				  struct libie_aq_desc *desc,
 				  void *buff, /* can be NULL */
 				  u16  buff_size,
 				  struct i40e_asq_cmd_details *cmd_details,
@@ -758,7 +758,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 {
 	struct i40e_dma_mem *dma_buff = NULL;
 	struct i40e_asq_cmd_details *details;
-	struct i40e_aq_desc *desc_on_ring;
+	struct libie_aq_desc *desc_on_ring;
 	bool cmd_completed = false;
 	u16  retval = 0;
 	int status = 0;
@@ -771,7 +771,7 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 		goto asq_send_command_error;
 	}
 
-	hw->aq.asq_last_status = I40E_AQ_RC_OK;
+	hw->aq.asq_last_status = LIBIE_AQ_RC_OK;
 
 	val = rd32(hw, I40E_PF_ATQH);
 	if (val >= hw->aq.num_asq_entries) {
@@ -851,9 +851,9 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 		/* Update the address values in the desc with the pa value
 		 * for respective buffer
 		 */
-		desc_on_ring->params.external.addr_high =
+		desc_on_ring->params.generic.addr_high =
 				cpu_to_le32(upper_32_bits(dma_buff->pa));
-		desc_on_ring->params.external.addr_low =
+		desc_on_ring->params.generic.addr_low =
 				cpu_to_le32(lower_32_bits(dma_buff->pa));
 	}
 
@@ -905,13 +905,13 @@ i40e_asq_send_command_atomic_exec(struct i40e_hw *hw,
 			retval &= 0xff;
 		}
 		cmd_completed = true;
-		if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_OK)
+		if ((enum libie_aq_err)retval == LIBIE_AQ_RC_OK)
 			status = 0;
-		else if ((enum i40e_admin_queue_err)retval == I40E_AQ_RC_EBUSY)
+		else if ((enum libie_aq_err)retval == LIBIE_AQ_RC_EBUSY)
 			status = -EBUSY;
 		else
 			status = -EIO;
-		hw->aq.asq_last_status = (enum i40e_admin_queue_err)retval;
+		hw->aq.asq_last_status = (enum libie_aq_err)retval;
 	}
 
 	i40e_debug(hw, I40E_DEBUG_AQ_COMMAND,
@@ -954,7 +954,7 @@ asq_send_command_error:
  **/
 int
 i40e_asq_send_command_atomic(struct i40e_hw *hw,
-			     struct i40e_aq_desc *desc,
+			     struct libie_aq_desc *desc,
 			     void *buff, /* can be NULL */
 			     u16  buff_size,
 			     struct i40e_asq_cmd_details *cmd_details,
@@ -972,7 +972,7 @@ i40e_asq_send_command_atomic(struct i40e_hw *hw,
 }
 
 int
-i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc,
+i40e_asq_send_command(struct i40e_hw *hw, struct libie_aq_desc *desc,
 		      void *buff, /* can be NULL */ u16  buff_size,
 		      struct i40e_asq_cmd_details *cmd_details)
 {
@@ -996,12 +996,12 @@ i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc,
  **/
 int
 i40e_asq_send_command_atomic_v2(struct i40e_hw *hw,
-				struct i40e_aq_desc *desc,
+				struct libie_aq_desc *desc,
 				void *buff, /* can be NULL */
 				u16  buff_size,
 				struct i40e_asq_cmd_details *cmd_details,
 				bool is_atomic_context,
-				enum i40e_admin_queue_err *aq_status)
+				enum libie_aq_err *aq_status)
 {
 	int status;
 
@@ -1023,13 +1023,13 @@ i40e_asq_send_command_atomic_v2(struct i40e_hw *hw,
  *
  *  Fill the desc with default values
  **/
-void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
+void i40e_fill_default_direct_cmd_desc(struct libie_aq_desc *desc,
 				       u16 opcode)
 {
 	/* zero out the desc */
-	memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+	memset((void *)desc, 0, sizeof(struct libie_aq_desc));
 	desc->opcode = cpu_to_le16(opcode);
-	desc->flags = cpu_to_le16(I40E_AQ_FLAG_SI);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_SI);
 }
 
 /**
@@ -1047,7 +1047,7 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 			   u16 *pending)
 {
 	u16 ntc = hw->aq.arq.next_to_clean;
-	struct i40e_aq_desc *desc;
+	struct libie_aq_desc *desc;
 	struct i40e_dma_mem *bi;
 	int ret_code = 0;
 	u16 desc_idx;
@@ -1081,9 +1081,9 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 	desc_idx = ntc;
 
 	hw->aq.arq_last_status =
-		(enum i40e_admin_queue_err)le16_to_cpu(desc->retval);
+		(enum libie_aq_err)le16_to_cpu(desc->retval);
 	flags = le16_to_cpu(desc->flags);
-	if (flags & I40E_AQ_FLAG_ERR) {
+	if (flags & LIBIE_AQ_FLAG_ERR) {
 		ret_code = -EIO;
 		i40e_debug(hw,
 			   I40E_DEBUG_AQ_MESSAGE,
@@ -1107,14 +1107,14 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 	 * size
 	 */
 	bi = &hw->aq.arq.r.arq_bi[ntc];
-	memset((void *)desc, 0, sizeof(struct i40e_aq_desc));
+	memset((void *)desc, 0, sizeof(struct libie_aq_desc));
 
-	desc->flags = cpu_to_le16(I40E_AQ_FLAG_BUF);
+	desc->flags = cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 	if (hw->aq.arq_buf_size > I40E_AQ_LARGE_BUF)
-		desc->flags |= cpu_to_le16(I40E_AQ_FLAG_LB);
+		desc->flags |= cpu_to_le16(LIBIE_AQ_FLAG_LB);
 	desc->datalen = cpu_to_le16((u16)bi->size);
-	desc->params.external.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
-	desc->params.external.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
+	desc->params.generic.addr_high = cpu_to_le32(upper_32_bits(bi->pa));
+	desc->params.generic.addr_low = cpu_to_le32(lower_32_bits(bi->pa));
 
 	/* set tail = the last cleaned desc index. */
 	wr32(hw, I40E_PF_ARQT, ntc);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
index 55b5bb884d73..1be97a3a86ce 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h
@@ -9,7 +9,7 @@
 #include "i40e_adminq_cmd.h"
 
 #define I40E_ADMINQ_DESC(R, i)   \
-	(&(((struct i40e_aq_desc *)((R).desc_buf.va))[i]))
+	(&(((struct libie_aq_desc *)((R).desc_buf.va))[i]))
 
 #define I40E_ADMINQ_DESC_ALIGNMENT 4096
 
@@ -39,7 +39,7 @@ struct i40e_asq_cmd_details {
 	u16 flags_dis;
 	bool async;
 	bool postpone;
-	struct i40e_aq_desc *wb_desc;
+	struct libie_aq_desc *wb_desc;
 };
 
 #define I40E_ADMINQ_DETAILS(R, i)   \
@@ -47,7 +47,7 @@ struct i40e_asq_cmd_details {
 
 /* ARQ event information */
 struct i40e_arq_event_info {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 msg_len;
 	u16 buf_len;
 	u8 *msg_buf;
@@ -72,8 +72,8 @@ struct i40e_adminq_info {
 	struct mutex arq_mutex; /* Receive queue lock */
 
 	/* last status values on send and receive queues */
-	enum i40e_admin_queue_err asq_last_status;
-	enum i40e_admin_queue_err arq_last_status;
+	enum libie_aq_err asq_last_status;
+	enum libie_aq_err arq_last_status;
 };
 
 /**
@@ -119,7 +119,7 @@ static inline int i40e_aq_rc_to_posix(int aq_ret, int aq_rc)
 #define I40E_AQ_LARGE_BUF	512
 #define I40E_ASQ_CMD_TIMEOUT	250000  /* usecs */
 
-void i40e_fill_default_direct_cmd_desc(struct i40e_aq_desc *desc,
+void i40e_fill_default_direct_cmd_desc(struct libie_aq_desc *desc,
 				       u16 opcode);
 
 #endif /* _I40E_ADMINQ_H_ */
diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
index c8f35d4de271..76d872b91a38 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h
@@ -4,6 +4,8 @@
 #ifndef _I40E_ADMINQ_CMD_H_
 #define _I40E_ADMINQ_CMD_H_
 
+#include <linux/net/intel/libie/adminq.h>
+
 #include <linux/bits.h>
 #include <linux/types.h>
 
@@ -30,75 +32,6 @@
 /* API version 1.10 for X722 devices adds ability to request FEC encoding */
 #define I40E_MINOR_VER_FW_REQUEST_FEC_X722 0x000A
 
-struct i40e_aq_desc {
-	__le16 flags;
-	__le16 opcode;
-	__le16 datalen;
-	__le16 retval;
-	__le32 cookie_high;
-	__le32 cookie_low;
-	union {
-		struct {
-			__le32 param0;
-			__le32 param1;
-			__le32 param2;
-			__le32 param3;
-		} internal;
-		struct {
-			__le32 param0;
-			__le32 param1;
-			__le32 addr_high;
-			__le32 addr_low;
-		} external;
-		u8 raw[16];
-	} params;
-};
-
-/* Flags sub-structure
- * |0  |1  |2  |3  |4  |5  |6  |7  |8  |9  |10 |11 |12 |13 |14 |15 |
- * |DD |CMP|ERR|VFE| * *  RESERVED * * |LB |RD |VFC|BUF|SI |EI |FE |
- */
-
-/* command flags and offsets*/
-#define I40E_AQ_FLAG_ERR_SHIFT	2
-#define I40E_AQ_FLAG_LB_SHIFT	9
-#define I40E_AQ_FLAG_RD_SHIFT	10
-#define I40E_AQ_FLAG_BUF_SHIFT	12
-#define I40E_AQ_FLAG_SI_SHIFT	13
-
-#define I40E_AQ_FLAG_ERR	BIT(I40E_AQ_FLAG_ERR_SHIFT) /* 0x4    */
-#define I40E_AQ_FLAG_LB		BIT(I40E_AQ_FLAG_LB_SHIFT)  /* 0x200  */
-#define I40E_AQ_FLAG_RD		BIT(I40E_AQ_FLAG_RD_SHIFT)  /* 0x400  */
-#define I40E_AQ_FLAG_BUF	BIT(I40E_AQ_FLAG_BUF_SHIFT) /* 0x1000 */
-#define I40E_AQ_FLAG_SI		BIT(I40E_AQ_FLAG_SI_SHIFT)  /* 0x2000 */
-
-/* error codes */
-enum i40e_admin_queue_err {
-	I40E_AQ_RC_OK		= 0,  /* success */
-	I40E_AQ_RC_EPERM	= 1,  /* Operation not permitted */
-	I40E_AQ_RC_ENOENT	= 2,  /* No such element */
-	I40E_AQ_RC_ESRCH	= 3,  /* Bad opcode */
-	I40E_AQ_RC_EINTR	= 4,  /* operation interrupted */
-	I40E_AQ_RC_EIO		= 5,  /* I/O error */
-	I40E_AQ_RC_ENXIO	= 6,  /* No such resource */
-	I40E_AQ_RC_E2BIG	= 7,  /* Arg too long */
-	I40E_AQ_RC_EAGAIN	= 8,  /* Try again */
-	I40E_AQ_RC_ENOMEM	= 9,  /* Out of memory */
-	I40E_AQ_RC_EACCES	= 10, /* Permission denied */
-	I40E_AQ_RC_EFAULT	= 11, /* Bad address */
-	I40E_AQ_RC_EBUSY	= 12, /* Device or resource busy */
-	I40E_AQ_RC_EEXIST	= 13, /* object already exists */
-	I40E_AQ_RC_EINVAL	= 14, /* Invalid argument */
-	I40E_AQ_RC_ENOTTY	= 15, /* Not a typewriter */
-	I40E_AQ_RC_ENOSPC	= 16, /* No space left or alloc failure */
-	I40E_AQ_RC_ENOSYS	= 17, /* Function not implemented */
-	I40E_AQ_RC_ERANGE	= 18, /* Parameter out of range */
-	I40E_AQ_RC_EFLUSHED	= 19, /* Cmd flushed due to prev cmd error */
-	I40E_AQ_RC_BAD_ADDR	= 20, /* Descriptor contains a bad pointer */
-	I40E_AQ_RC_EMODE	= 21, /* Op not allowed in current dev mode */
-	I40E_AQ_RC_EFBIG	= 22, /* File too large */
-};
-
 /* Admin Queue command opcodes */
 enum i40e_admin_queue_opc {
 	/* aq commands */
@@ -320,21 +253,6 @@ struct i40e_aqc_get_version {
 	__le16 api_minor;
 };
 
-I40E_CHECK_CMD_LENGTH(i40e_aqc_get_version);
-
-/* Send driver version (indirect 0x0002) */
-struct i40e_aqc_driver_version {
-	u8	driver_major_ver;
-	u8	driver_minor_ver;
-	u8	driver_build_ver;
-	u8	driver_subbuild_ver;
-	u8	reserved[4];
-	__le32	address_high;
-	__le32	address_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_driver_version);
-
 /* Queue Shutdown (direct 0x0003) */
 struct i40e_aqc_queue_shutdown {
 	__le32	driver_unloading;
@@ -352,75 +270,6 @@ struct i40e_aqc_set_pf_context {
 
 I40E_CHECK_CMD_LENGTH(i40e_aqc_set_pf_context);
 
-/* Request resource ownership (direct 0x0008)
- * Release resource ownership (direct 0x0009)
- */
-struct i40e_aqc_request_resource {
-	__le16	resource_id;
-	__le16	access_type;
-	__le32	timeout;
-	__le32	resource_number;
-	u8	reserved[4];
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_request_resource);
-
-/* Get function capabilities (indirect 0x000A)
- * Get device capabilities (indirect 0x000B)
- */
-struct i40e_aqc_list_capabilites {
-	u8 command_flags;
-	u8 pf_index;
-	u8 reserved[2];
-	__le32 count;
-	__le32 addr_high;
-	__le32 addr_low;
-};
-
-I40E_CHECK_CMD_LENGTH(i40e_aqc_list_capabilites);
-
-struct i40e_aqc_list_capabilities_element_resp {
-	__le16	id;
-	u8	major_rev;
-	u8	minor_rev;
-	__le32	number;
-	__le32	logical_id;
-	__le32	phys_id;
-	u8	reserved[16];
-};
-
-/* list of caps */
-
-#define I40E_AQ_CAP_ID_SWITCH_MODE	0x0001
-#define I40E_AQ_CAP_ID_MNG_MODE		0x0002
-#define I40E_AQ_CAP_ID_NPAR_ACTIVE	0x0003
-#define I40E_AQ_CAP_ID_OS2BMC_CAP	0x0004
-#define I40E_AQ_CAP_ID_FUNCTIONS_VALID	0x0005
-#define I40E_AQ_CAP_ID_SRIOV		0x0012
-#define I40E_AQ_CAP_ID_VF		0x0013
-#define I40E_AQ_CAP_ID_VMDQ		0x0014
-#define I40E_AQ_CAP_ID_8021QBG		0x0015
-#define I40E_AQ_CAP_ID_8021QBR		0x0016
-#define I40E_AQ_CAP_ID_VSI		0x0017
-#define I40E_AQ_CAP_ID_DCB		0x0018
-#define I40E_AQ_CAP_ID_FCOE		0x0021
-#define I40E_AQ_CAP_ID_ISCSI		0x0022
-#define I40E_AQ_CAP_ID_RSS		0x0040
-#define I40E_AQ_CAP_ID_RXQ		0x0041
-#define I40E_AQ_CAP_ID_TXQ		0x0042
-#define I40E_AQ_CAP_ID_MSIX		0x0043
-#define I40E_AQ_CAP_ID_VF_MSIX		0x0044
-#define I40E_AQ_CAP_ID_FLOW_DIRECTOR	0x0045
-#define I40E_AQ_CAP_ID_1588		0x0046
-#define I40E_AQ_CAP_ID_IWARP		0x0051
-#define I40E_AQ_CAP_ID_LED		0x0061
-#define I40E_AQ_CAP_ID_SDP		0x0062
-#define I40E_AQ_CAP_ID_MDIO		0x0063
-#define I40E_AQ_CAP_ID_WSR_PROT		0x0064
-#define I40E_AQ_CAP_ID_NVM_MGMT		0x0080
-#define I40E_AQ_CAP_ID_FLEX10		0x00F1
-#define I40E_AQ_CAP_ID_CEM		0x00F2
-
 /* Set CPPM Configuration (direct 0x0103) */
 struct i40e_aqc_cppm_configuration {
 	__le16	command_flags;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c
index b11c35e307ca..75074611285a 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_common.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_common.c
@@ -73,55 +73,47 @@ int i40e_set_mac_type(struct i40e_hw *hw)
  * @hw: pointer to the HW structure
  * @aq_err: the AQ error code to convert
  **/
-const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
+const char *i40e_aq_str(struct i40e_hw *hw, enum libie_aq_err aq_err)
 {
 	switch (aq_err) {
-	case I40E_AQ_RC_OK:
+	case LIBIE_AQ_RC_OK:
 		return "OK";
-	case I40E_AQ_RC_EPERM:
-		return "I40E_AQ_RC_EPERM";
-	case I40E_AQ_RC_ENOENT:
-		return "I40E_AQ_RC_ENOENT";
-	case I40E_AQ_RC_ESRCH:
-		return "I40E_AQ_RC_ESRCH";
-	case I40E_AQ_RC_EINTR:
-		return "I40E_AQ_RC_EINTR";
-	case I40E_AQ_RC_EIO:
-		return "I40E_AQ_RC_EIO";
-	case I40E_AQ_RC_ENXIO:
-		return "I40E_AQ_RC_ENXIO";
-	case I40E_AQ_RC_E2BIG:
-		return "I40E_AQ_RC_E2BIG";
-	case I40E_AQ_RC_EAGAIN:
-		return "I40E_AQ_RC_EAGAIN";
-	case I40E_AQ_RC_ENOMEM:
-		return "I40E_AQ_RC_ENOMEM";
-	case I40E_AQ_RC_EACCES:
-		return "I40E_AQ_RC_EACCES";
-	case I40E_AQ_RC_EFAULT:
-		return "I40E_AQ_RC_EFAULT";
-	case I40E_AQ_RC_EBUSY:
-		return "I40E_AQ_RC_EBUSY";
-	case I40E_AQ_RC_EEXIST:
-		return "I40E_AQ_RC_EEXIST";
-	case I40E_AQ_RC_EINVAL:
-		return "I40E_AQ_RC_EINVAL";
-	case I40E_AQ_RC_ENOTTY:
-		return "I40E_AQ_RC_ENOTTY";
-	case I40E_AQ_RC_ENOSPC:
-		return "I40E_AQ_RC_ENOSPC";
-	case I40E_AQ_RC_ENOSYS:
-		return "I40E_AQ_RC_ENOSYS";
-	case I40E_AQ_RC_ERANGE:
-		return "I40E_AQ_RC_ERANGE";
-	case I40E_AQ_RC_EFLUSHED:
-		return "I40E_AQ_RC_EFLUSHED";
-	case I40E_AQ_RC_BAD_ADDR:
-		return "I40E_AQ_RC_BAD_ADDR";
-	case I40E_AQ_RC_EMODE:
-		return "I40E_AQ_RC_EMODE";
-	case I40E_AQ_RC_EFBIG:
-		return "I40E_AQ_RC_EFBIG";
+	case LIBIE_AQ_RC_EPERM:
+		return "LIBIE_AQ_RC_EPERM";
+	case LIBIE_AQ_RC_ENOENT:
+		return "LIBIE_AQ_RC_ENOENT";
+	case LIBIE_AQ_RC_ESRCH:
+		return "LIBIE_AQ_RC_ESRCH";
+	case LIBIE_AQ_RC_EIO:
+		return "LIBIE_AQ_RC_EIO";
+	case LIBIE_AQ_RC_EAGAIN:
+		return "LIBIE_AQ_RC_EAGAIN";
+	case LIBIE_AQ_RC_ENOMEM:
+		return "LIBIE_AQ_RC_ENOMEM";
+	case LIBIE_AQ_RC_EACCES:
+		return "LIBIE_AQ_RC_EACCES";
+	case LIBIE_AQ_RC_EBUSY:
+		return "LIBIE_AQ_RC_EBUSY";
+	case LIBIE_AQ_RC_EEXIST:
+		return "LIBIE_AQ_RC_EEXIST";
+	case LIBIE_AQ_RC_EINVAL:
+		return "LIBIE_AQ_RC_EINVAL";
+	case LIBIE_AQ_RC_ENOSPC:
+		return "LIBIE_AQ_RC_ENOSPC";
+	case LIBIE_AQ_RC_ENOSYS:
+		return "LIBIE_AQ_RC_ENOSYS";
+	case LIBIE_AQ_RC_EMODE:
+		return "LIBIE_AQ_RC_EMODE";
+	case LIBIE_AQ_RC_ENOSEC:
+		return "LIBIE_AQ_RC_ENOSEC";
+	case LIBIE_AQ_RC_EBADSIG:
+		return "LIBIE_AQ_RC_EBADSIG";
+	case LIBIE_AQ_RC_ESVN:
+		return "LIBIE_AQ_RC_ESVN";
+	case LIBIE_AQ_RC_EBADMAN:
+		return "LIBIE_AQ_RC_EBADMAN";
+	case LIBIE_AQ_RC_EBADBUF:
+		return "LIBIE_AQ_RC_EBADBUF";
 	}
 
 	snprintf(hw->err_str, sizeof(hw->err_str), "%d", aq_err);
@@ -141,7 +133,7 @@ const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err)
 void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 		   void *buffer, u16 buf_len)
 {
-	struct i40e_aq_desc *aq_desc = (struct i40e_aq_desc *)desc;
+	struct libie_aq_desc *aq_desc = (struct libie_aq_desc *)desc;
 	u32 effective_mask = hw->debug_mask & mask;
 	char prefix[27];
 	u16 len;
@@ -164,12 +156,12 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask, void *desc,
 		   le32_to_cpu(aq_desc->cookie_low));
 	i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
 		   "\tparam (0,1)  0x%08X 0x%08X\n",
-		   le32_to_cpu(aq_desc->params.internal.param0),
-		   le32_to_cpu(aq_desc->params.internal.param1));
+		   le32_to_cpu(aq_desc->params.generic.param0),
+		   le32_to_cpu(aq_desc->params.generic.param1));
 	i40e_debug(hw, mask & I40E_DEBUG_AQ_DESCRIPTOR,
 		   "\taddr (h,l)   0x%08X 0x%08X\n",
-		   le32_to_cpu(aq_desc->params.external.addr_high),
-		   le32_to_cpu(aq_desc->params.external.addr_low));
+		   le32_to_cpu(aq_desc->params.generic.addr_high),
+		   le32_to_cpu(aq_desc->params.generic.addr_low));
 
 	if (buffer && buf_len != 0 && len != 0 &&
 	    (effective_mask & I40E_DEBUG_AQ_DESC_BUFFER)) {
@@ -214,14 +206,14 @@ bool i40e_check_asq_alive(struct i40e_hw *hw)
 int i40e_aq_queue_shutdown(struct i40e_hw *hw,
 			   bool unloading)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_queue_shutdown *cmd =
-		(struct i40e_aqc_queue_shutdown *)&desc.params.raw;
+	struct i40e_aqc_queue_shutdown *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_queue_shutdown);
 
+	cmd = libie_aq_raw(&desc);
 	if (unloading)
 		cmd->driver_unloading = cpu_to_le32(I40E_AQ_DRIVER_UNLOADING);
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, NULL);
@@ -245,9 +237,8 @@ static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
 				   u8 *lut, u16 lut_size,
 				   bool set)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_set_rss_lut *cmd_resp =
-		   (struct i40e_aqc_get_set_rss_lut *)&desc.params.raw;
+	struct i40e_aqc_get_set_rss_lut *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 	u16 flags;
 
@@ -258,9 +249,10 @@ static int i40e_aq_get_set_rss_lut(struct i40e_hw *hw,
 		i40e_fill_default_direct_cmd_desc(&desc,
 						  i40e_aqc_opc_get_rss_lut);
 
+	cmd_resp = libie_aq_raw(&desc);
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 
 	vsi_id = FIELD_PREP(I40E_AQC_SET_RSS_LUT_VSI_ID_MASK, vsi_id) |
 		 FIELD_PREP(I40E_AQC_SET_RSS_LUT_VSI_VALID, 1);
@@ -326,10 +318,9 @@ static int i40e_aq_get_set_rss_key(struct i40e_hw *hw,
 				   struct i40e_aqc_get_set_rss_key_data *key,
 				   bool set)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_set_rss_key *cmd_resp =
-			(struct i40e_aqc_get_set_rss_key *)&desc.params.raw;
 	u16 key_size = sizeof(struct i40e_aqc_get_set_rss_key_data);
+	struct i40e_aqc_get_set_rss_key *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (set)
@@ -339,9 +330,10 @@ static int i40e_aq_get_set_rss_key(struct i40e_hw *hw,
 		i40e_fill_default_direct_cmd_desc(&desc,
 						  i40e_aqc_opc_get_rss_key);
 
+	cmd_resp = libie_aq_raw(&desc);
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 
 	vsi_id = FIELD_PREP(I40E_AQC_SET_RSS_KEY_VSI_ID_MASK, vsi_id) |
 		 FIELD_PREP(I40E_AQC_SET_RSS_KEY_VSI_VALID, 1);
@@ -439,13 +431,13 @@ i40e_aq_mac_address_read(struct i40e_hw *hw,
 			 struct i40e_aqc_mac_address_read_data *addrs,
 			 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_mac_address_read *cmd_data =
-		(struct i40e_aqc_mac_address_read *)&desc.params.raw;
+	struct i40e_aqc_mac_address_read *cmd_data;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_mac_address_read);
-	desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF);
+	cmd_data = libie_aq_raw(&desc);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF);
 
 	status = i40e_asq_send_command(hw, &desc, addrs,
 				       sizeof(*addrs), cmd_details);
@@ -465,13 +457,13 @@ int i40e_aq_mac_address_write(struct i40e_hw *hw,
 			      u16 flags, u8 *mac_addr,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_mac_address_write *cmd_data =
-		(struct i40e_aqc_mac_address_write *)&desc.params.raw;
+	struct i40e_aqc_mac_address_write *cmd_data;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_mac_address_write);
+	cmd_data = libie_aq_raw(&desc);
 	cmd_data->command_flags = cpu_to_le16(flags);
 	cmd_data->mac_sah = cpu_to_le16((u16)mac_addr[0] << 8 | mac_addr[1]);
 	cmd_data->mac_sal = cpu_to_le32(((u32)mac_addr[2] << 24) |
@@ -1061,7 +1053,7 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 {
 	u16 abilities_size = sizeof(struct i40e_aq_get_phy_abilities_resp);
 	u16 max_delay = I40E_MAX_PHY_TIMEOUT, total_delay = 0;
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!abilities)
@@ -1071,36 +1063,36 @@ i40e_aq_get_phy_capabilities(struct i40e_hw *hw,
 		i40e_fill_default_direct_cmd_desc(&desc,
 					       i40e_aqc_opc_get_phy_abilities);
 
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 		if (abilities_size > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+			desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 		if (qualified_modules)
-			desc.params.external.param0 |=
+			desc.params.generic.param0 |=
 			cpu_to_le32(I40E_AQ_PHY_REPORT_QUALIFIED_MODULES);
 
 		if (report_init)
-			desc.params.external.param0 |=
+			desc.params.generic.param0 |=
 			cpu_to_le32(I40E_AQ_PHY_REPORT_INITIAL_VALUES);
 
 		status = i40e_asq_send_command(hw, &desc, abilities,
 					       abilities_size, cmd_details);
 
 		switch (hw->aq.asq_last_status) {
-		case I40E_AQ_RC_EIO:
+		case LIBIE_AQ_RC_EIO:
 			status = -EIO;
 			break;
-		case I40E_AQ_RC_EAGAIN:
+		case LIBIE_AQ_RC_EAGAIN:
 			usleep_range(1000, 2000);
 			total_delay++;
 			status = -EIO;
 			break;
-		/* also covers I40E_AQ_RC_OK */
+		/* also covers LIBIE_AQ_RC_OK */
 		default:
 			break;
 		}
 
-	} while ((hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN) &&
+	} while ((hw->aq.asq_last_status == LIBIE_AQ_RC_EAGAIN) &&
 		(total_delay < max_delay));
 
 	if (status)
@@ -1137,9 +1129,8 @@ int i40e_aq_set_phy_config(struct i40e_hw *hw,
 			   struct i40e_aq_set_phy_config *config,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aq_set_phy_config *cmd =
-			(struct i40e_aq_set_phy_config *)&desc.params.raw;
+	struct i40e_aq_set_phy_config *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!config)
@@ -1148,6 +1139,7 @@ int i40e_aq_set_phy_config(struct i40e_hw *hw,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_config);
 
+	cmd = libie_aq_raw(&desc);
 	*cmd = *config;
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -1259,14 +1251,14 @@ int i40e_set_fc(struct i40e_hw *hw, u8 *aq_failures,
 int i40e_aq_clear_pxe_mode(struct i40e_hw *hw,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_clear_pxe *cmd =
-		(struct i40e_aqc_clear_pxe *)&desc.params.raw;
+	struct i40e_aqc_clear_pxe *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_clear_pxe_mode);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->rx_cnt = 0x2;
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -1288,14 +1280,14 @@ int i40e_aq_set_link_restart_an(struct i40e_hw *hw,
 				bool enable_link,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_link_restart_an *cmd =
-		(struct i40e_aqc_set_link_restart_an *)&desc.params.raw;
+	struct i40e_aqc_set_link_restart_an *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_link_restart_an);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->command = I40E_AQ_PHY_RESTART_AN;
 	if (enable_link)
 		cmd->command |= I40E_AQ_PHY_LINK_ENABLE;
@@ -1320,16 +1312,16 @@ int i40e_aq_get_link_info(struct i40e_hw *hw,
 			  bool enable_lse, struct i40e_link_status *link,
 			  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_link_status *resp =
-		(struct i40e_aqc_get_link_status *)&desc.params.raw;
 	struct i40e_link_status *hw_link_info = &hw->phy.link_info;
+	struct i40e_aqc_get_link_status *resp;
+	struct libie_aq_desc desc;
 	bool tx_pause, rx_pause;
 	u16 command_flags;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_link_status);
 
+	resp = libie_aq_raw(&desc);
 	if (enable_lse)
 		command_flags = I40E_AQ_LSE_ENABLE;
 	else
@@ -1415,14 +1407,14 @@ int i40e_aq_set_phy_int_mask(struct i40e_hw *hw,
 			     u16 mask,
 			     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_phy_int_mask *cmd =
-		(struct i40e_aqc_set_phy_int_mask *)&desc.params.raw;
+	struct i40e_aqc_set_phy_int_mask *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_int_mask);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->event_mask = cpu_to_le16(mask);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -1441,11 +1433,11 @@ int i40e_aq_set_phy_int_mask(struct i40e_hw *hw,
 int i40e_aq_set_mac_loopback(struct i40e_hw *hw, bool ena_lpbk,
 			     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_lb_mode *cmd =
-		(struct i40e_aqc_set_lb_mode *)&desc.params.raw;
+	struct i40e_aqc_set_lb_mode *cmd;
+	struct libie_aq_desc desc;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_set_lb_modes);
+	cmd = libie_aq_raw(&desc);
 	if (ena_lpbk) {
 		if (hw->nvm.version <= I40E_LEGACY_LOOPBACK_NVM_VER)
 			cmd->lb_mode = cpu_to_le16(I40E_AQ_LB_MAC_LOCAL_LEGACY);
@@ -1467,14 +1459,14 @@ int i40e_aq_set_mac_loopback(struct i40e_hw *hw, bool ena_lpbk,
 int i40e_aq_set_phy_debug(struct i40e_hw *hw, u8 cmd_flags,
 			  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_phy_debug *cmd =
-		(struct i40e_aqc_set_phy_debug *)&desc.params.raw;
+	struct i40e_aqc_set_phy_debug *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_debug);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->command_flags = cmd_flags;
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -1494,23 +1486,22 @@ int i40e_aq_add_vsi(struct i40e_hw *hw,
 		    struct i40e_vsi_context *vsi_ctx,
 		    struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_get_update_vsi *cmd =
-		(struct i40e_aqc_add_get_update_vsi *)&desc.params.raw;
-	struct i40e_aqc_add_get_update_vsi_completion *resp =
-		(struct i40e_aqc_add_get_update_vsi_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_add_get_update_vsi_completion *resp;
+	struct i40e_aqc_add_get_update_vsi *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_add_vsi);
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->uplink_seid = cpu_to_le16(vsi_ctx->uplink_seid);
 	cmd->connection_type = vsi_ctx->connection_type;
 	cmd->vf_id = vsi_ctx->vf_num;
 	cmd->vsi_flags = cpu_to_le16(vsi_ctx->flags);
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 
 	status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info,
 					      sizeof(vsi_ctx->info),
@@ -1538,15 +1529,14 @@ int i40e_aq_set_default_vsi(struct i40e_hw *hw,
 			    u16 seid,
 			    struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)
-		&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->promiscuous_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
 	cmd->seid = cpu_to_le16(seid);
@@ -1566,15 +1556,14 @@ int i40e_aq_clear_default_vsi(struct i40e_hw *hw,
 			      u16 seid,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)
-		&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->promiscuous_flags = cpu_to_le16(0);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_DEFAULT);
 	cmd->seid = cpu_to_le16(seid);
@@ -1597,15 +1586,15 @@ int i40e_aq_set_vsi_unicast_promiscuous(struct i40e_hw *hw,
 					struct i40e_asq_cmd_details *cmd_details,
 					bool rx_only_promisc)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (set) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
 		if (rx_only_promisc && i40e_is_aq_api_ver_ge(hw, 1, 5))
@@ -1636,15 +1625,15 @@ int i40e_aq_set_vsi_multicast_promiscuous(struct i40e_hw *hw,
 					  u16 seid, bool set,
 					  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (set)
 		flags |= I40E_AQC_SET_VSI_PROMISC_MULTICAST;
 
@@ -1671,15 +1660,15 @@ int i40e_aq_set_vsi_mc_promisc_on_vlan(struct i40e_hw *hw,
 				       u16 vid,
 				       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (enable)
 		flags |= I40E_AQC_SET_VSI_PROMISC_MULTICAST;
 
@@ -1707,15 +1696,15 @@ int i40e_aq_set_vsi_uc_promisc_on_vlan(struct i40e_hw *hw,
 				       u16 vid,
 				       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (enable) {
 		flags |= I40E_AQC_SET_VSI_PROMISC_UNICAST;
 		if (i40e_is_aq_api_ver_ge(hw, 1, 5))
@@ -1748,9 +1737,8 @@ int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw,
 				       u16 seid, bool enable, u16 vid,
 				       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	u16 flags = 0;
 	int status;
 
@@ -1760,6 +1748,7 @@ int i40e_aq_set_vsi_bc_promisc_on_vlan(struct i40e_hw *hw,
 	if (enable)
 		flags |= I40E_AQC_SET_VSI_PROMISC_BROADCAST;
 
+	cmd = libie_aq_raw(&desc);
 	cmd->promiscuous_flags = cpu_to_le16(flags);
 	cmd->valid_flags = cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_BROADCAST);
 	cmd->seid = cpu_to_le16(seid);
@@ -1783,14 +1772,14 @@ int i40e_aq_set_vsi_broadcast(struct i40e_hw *hw,
 			      u16 seid, bool set_filter,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_vsi_promiscuous_modes *cmd =
-		(struct i40e_aqc_set_vsi_promiscuous_modes *)&desc.params.raw;
+	struct i40e_aqc_set_vsi_promiscuous_modes *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					i40e_aqc_opc_set_vsi_promiscuous_modes);
 
+	cmd = libie_aq_raw(&desc);
 	if (set_filter)
 		cmd->promiscuous_flags
 			    |= cpu_to_le16(I40E_AQC_SET_VSI_PROMISC_BROADCAST);
@@ -1815,20 +1804,19 @@ int i40e_aq_get_vsi_params(struct i40e_hw *hw,
 			   struct i40e_vsi_context *vsi_ctx,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_get_update_vsi *cmd =
-		(struct i40e_aqc_add_get_update_vsi *)&desc.params.raw;
-	struct i40e_aqc_add_get_update_vsi_completion *resp =
-		(struct i40e_aqc_add_get_update_vsi_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_add_get_update_vsi_completion *resp;
+	struct i40e_aqc_add_get_update_vsi *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_vsi_parameters);
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->uplink_seid = cpu_to_le16(vsi_ctx->seid);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 
 	status = i40e_asq_send_command(hw, &desc, &vsi_ctx->info,
 				    sizeof(vsi_ctx->info), NULL);
@@ -1857,19 +1845,18 @@ int i40e_aq_update_vsi_params(struct i40e_hw *hw,
 			      struct i40e_vsi_context *vsi_ctx,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_get_update_vsi *cmd =
-		(struct i40e_aqc_add_get_update_vsi *)&desc.params.raw;
-	struct i40e_aqc_add_get_update_vsi_completion *resp =
-		(struct i40e_aqc_add_get_update_vsi_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_add_get_update_vsi_completion *resp;
+	struct i40e_aqc_add_get_update_vsi *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_update_vsi_parameters);
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->uplink_seid = cpu_to_le16(vsi_ctx->seid);
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 
 	status = i40e_asq_send_command_atomic(hw, &desc, &vsi_ctx->info,
 					      sizeof(vsi_ctx->info),
@@ -1896,16 +1883,16 @@ int i40e_aq_get_switch_config(struct i40e_hw *hw,
 			      u16 buf_size, u16 *start_seid,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_switch_seid *scfg =
-		(struct i40e_aqc_switch_seid *)&desc.params.raw;
+	struct i40e_aqc_switch_seid *scfg;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_switch_config);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	scfg = libie_aq_raw(&desc);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buf_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 	scfg->seid = cpu_to_le16(*start_seid);
 
 	status = i40e_asq_send_command(hw, &desc, buf, buf_size, cmd_details);
@@ -1930,13 +1917,13 @@ int i40e_aq_set_switch_config(struct i40e_hw *hw,
 			      u16 valid_flags, u8 mode,
 			      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_switch_config *scfg =
-		(struct i40e_aqc_set_switch_config *)&desc.params.raw;
+	struct i40e_aqc_set_switch_config *scfg;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_switch_config);
+	scfg = libie_aq_raw(&desc);
 	scfg->flags = cpu_to_le16(flags);
 	scfg->valid_flags = cpu_to_le16(valid_flags);
 	scfg->mode = mode;
@@ -1968,11 +1955,11 @@ int i40e_aq_get_firmware_version(struct i40e_hw *hw,
 				 u16 *api_major_version, u16 *api_minor_version,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_version *resp =
-		(struct i40e_aqc_get_version *)&desc.params.raw;
+	struct i40e_aqc_get_version *resp;
+	struct libie_aq_desc desc;
 	int status;
 
+	resp = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_version);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -2005,22 +1992,22 @@ int i40e_aq_send_driver_version(struct i40e_hw *hw,
 				struct i40e_driver_version *dv,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_driver_version *cmd =
-		(struct i40e_aqc_driver_version *)&desc.params.raw;
+	struct libie_aqc_driver_ver *cmd;
+	struct libie_aq_desc desc;
 	int status;
 	u16 len;
 
 	if (dv == NULL)
 		return -EINVAL;
 
+	cmd = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_driver_version);
 
-	desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD);
-	cmd->driver_major_ver = dv->major_version;
-	cmd->driver_minor_ver = dv->minor_version;
-	cmd->driver_build_ver = dv->build_version;
-	cmd->driver_subbuild_ver = dv->subbuild_version;
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD);
+	cmd->major_ver = dv->major_version;
+	cmd->minor_ver = dv->minor_version;
+	cmd->build_ver = dv->build_version;
+	cmd->subbuild_ver = dv->subbuild_version;
 
 	len = 0;
 	while (len < sizeof(dv->driver_string) &&
@@ -2120,11 +2107,9 @@ int i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
 		    bool enable_stats,
 		    struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_veb *cmd =
-		(struct i40e_aqc_add_veb *)&desc.params.raw;
-	struct i40e_aqc_add_veb_completion *resp =
-		(struct i40e_aqc_add_veb_completion *)&desc.params.raw;
+	struct i40e_aqc_add_veb_completion *resp;
+	struct i40e_aqc_add_veb *cmd;
+	struct libie_aq_desc desc;
 	u16 veb_flags = 0;
 	int status;
 
@@ -2132,6 +2117,8 @@ int i40e_aq_add_veb(struct i40e_hw *hw, u16 uplink_seid,
 	if (!!uplink_seid != !!downlink_seid)
 		return -EINVAL;
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_veb);
 
 	cmd->uplink_seid = cpu_to_le16(uplink_seid);
@@ -2178,15 +2165,14 @@ int i40e_aq_get_veb_parameters(struct i40e_hw *hw,
 			       u16 *vebs_used, u16 *vebs_free,
 			       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_veb_parameters_completion *cmd_resp =
-		(struct i40e_aqc_get_veb_parameters_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_get_veb_parameters_completion *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (veb_seid == 0)
 		return -EINVAL;
 
+	cmd_resp = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_veb_parameters);
 	cmd_resp->seid = cpu_to_le16(veb_seid);
@@ -2228,10 +2214,9 @@ get_veb_exit:
  **/
 static u16
 i40e_prepare_add_macvlan(struct i40e_aqc_add_macvlan_element_data *mv_list,
-			 struct i40e_aq_desc *desc, u16 count, u16 seid)
+			 struct libie_aq_desc *desc, u16 count, u16 seid)
 {
-	struct i40e_aqc_macvlan *cmd =
-		(struct i40e_aqc_macvlan *)&desc->params.raw;
+	struct i40e_aqc_macvlan *cmd = libie_aq_raw(desc);
 	u16 buf_size;
 	int i;
 
@@ -2249,9 +2234,9 @@ i40e_prepare_add_macvlan(struct i40e_aqc_add_macvlan_element_data *mv_list,
 			mv_list[i].flags |=
 			       cpu_to_le16(I40E_AQC_MACVLAN_ADD_USE_SHARED_MAC);
 
-	desc->flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc->flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (buf_size > I40E_AQ_LARGE_BUF)
-		desc->flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc->flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	return buf_size;
 }
@@ -2271,7 +2256,7 @@ i40e_aq_add_macvlan(struct i40e_hw *hw, u16 seid,
 		    struct i40e_aqc_add_macvlan_element_data *mv_list,
 		    u16 count, struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
@@ -2302,9 +2287,9 @@ int
 i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid,
 		       struct i40e_aqc_add_macvlan_element_data *mv_list,
 		       u16 count, struct i40e_asq_cmd_details *cmd_details,
-		       enum i40e_admin_queue_err *aq_status)
+		       enum libie_aq_err *aq_status)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
@@ -2331,9 +2316,8 @@ i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid,
 		       struct i40e_aqc_remove_macvlan_element_data *mv_list,
 		       u16 count, struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_macvlan *cmd =
-		(struct i40e_aqc_macvlan *)&desc.params.raw;
+	struct i40e_aqc_macvlan *cmd;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 	int status;
 
@@ -2344,14 +2328,15 @@ i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid,
 
 	/* prep the rest of the request */
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_macvlan);
+	cmd = libie_aq_raw(&desc);
 	cmd->num_addresses = cpu_to_le16(count);
 	cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid);
 	cmd->seid[1] = 0;
 	cmd->seid[2] = 0;
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (buf_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command_atomic(hw, &desc, mv_list, buf_size,
 					      cmd_details, true);
@@ -2378,10 +2363,10 @@ int
 i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_remove_macvlan_element_data *mv_list,
 			  u16 count, struct i40e_asq_cmd_details *cmd_details,
-			  enum i40e_admin_queue_err *aq_status)
+			  enum libie_aq_err *aq_status)
 {
 	struct i40e_aqc_macvlan *cmd;
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u16 buf_size;
 
 	if (count == 0 || !mv_list || !hw)
@@ -2391,15 +2376,15 @@ i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 
 	/* prep the rest of the request */
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_remove_macvlan);
-	cmd = (struct i40e_aqc_macvlan *)&desc.params.raw;
+	cmd = libie_aq_raw(&desc);
 	cmd->num_addresses = cpu_to_le16(count);
 	cmd->seid[0] = cpu_to_le16(I40E_AQC_MACVLAN_CMD_SEID_VALID | seid);
 	cmd->seid[1] = 0;
 	cmd->seid[2] = 0;
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (buf_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	return i40e_asq_send_command_atomic_v2(hw, &desc, mv_list, buf_size,
 						 cmd_details, true, aq_status);
@@ -2421,21 +2406,21 @@ int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid,
 			   u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_pf_vf_message *cmd =
-		(struct i40e_aqc_pf_vf_message *)&desc.params.raw;
+	struct i40e_aqc_pf_vf_message *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_send_msg_to_vf);
+	cmd = libie_aq_raw(&desc);
 	cmd->id = cpu_to_le32(vfid);
 	desc.cookie_high = cpu_to_le32(v_opcode);
 	desc.cookie_low = cpu_to_le32(v_retval);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_SI);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_SI);
 	if (msglen) {
-		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
-						I40E_AQ_FLAG_RD));
+		desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF |
+						LIBIE_AQ_FLAG_RD));
 		if (msglen > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+			desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 		desc.datalen = cpu_to_le16(msglen);
 	}
 	status = i40e_asq_send_command(hw, &desc, msg, msglen, cmd_details);
@@ -2456,9 +2441,8 @@ int i40e_aq_debug_read_register(struct i40e_hw *hw,
 				u32 reg_addr, u64 *reg_val,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_debug_reg_read_write *cmd_resp =
-		(struct i40e_aqc_debug_reg_read_write *)&desc.params.raw;
+	struct i40e_aqc_debug_reg_read_write *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (reg_val == NULL)
@@ -2466,6 +2450,7 @@ int i40e_aq_debug_read_register(struct i40e_hw *hw,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_debug_read_reg);
 
+	cmd_resp = libie_aq_raw(&desc);
 	cmd_resp->address = cpu_to_le32(reg_addr);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -2491,13 +2476,13 @@ int i40e_aq_debug_write_register(struct i40e_hw *hw,
 				 u32 reg_addr, u64 reg_val,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_debug_reg_read_write *cmd =
-		(struct i40e_aqc_debug_reg_read_write *)&desc.params.raw;
+	struct i40e_aqc_debug_reg_read_write *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_debug_write_reg);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->address = cpu_to_le32(reg_addr);
 	cmd->value_high = cpu_to_le32((u32)(reg_val >> 32));
 	cmd->value_low = cpu_to_le32((u32)(reg_val & 0xFFFFFFFF));
@@ -2524,16 +2509,16 @@ int i40e_aq_request_resource(struct i40e_hw *hw,
 			     u8 sdp_number, u64 *timeout,
 			     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_request_resource *cmd_resp =
-		(struct i40e_aqc_request_resource *)&desc.params.raw;
+	struct libie_aqc_req_res *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_request_resource);
 
-	cmd_resp->resource_id = cpu_to_le16(resource);
+	cmd_resp = libie_aq_raw(&desc);
+	cmd_resp->res_id = cpu_to_le16(resource);
 	cmd_resp->access_type = cpu_to_le16(access);
-	cmd_resp->resource_number = cpu_to_le32(sdp_number);
+	cmd_resp->res_number = cpu_to_le32(sdp_number);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
 	/* The completion specifies the maximum time in ms that the driver
@@ -2542,7 +2527,7 @@ int i40e_aq_request_resource(struct i40e_hw *hw,
 	 * busy return value and the timeout field indicates the maximum time
 	 * the current owner of the resource has to free it.
 	 */
-	if (!status || hw->aq.asq_last_status == I40E_AQ_RC_EBUSY)
+	if (!status || hw->aq.asq_last_status == LIBIE_AQ_RC_EBUSY)
 		*timeout = le32_to_cpu(cmd_resp->timeout);
 
 	return status;
@@ -2562,15 +2547,15 @@ int i40e_aq_release_resource(struct i40e_hw *hw,
 			     u8 sdp_number,
 			     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_request_resource *cmd =
-		(struct i40e_aqc_request_resource *)&desc.params.raw;
+	struct libie_aqc_req_res *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_release_resource);
 
-	cmd->resource_id = cpu_to_le16(resource);
-	cmd->resource_number = cpu_to_le32(sdp_number);
+	cmd = libie_aq_raw(&desc);
+	cmd->res_id = cpu_to_le16(resource);
+	cmd->res_number = cpu_to_le32(sdp_number);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
 
@@ -2594,9 +2579,8 @@ int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
 		     bool last_command,
 		     struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_nvm_update *cmd =
-		(struct i40e_aqc_nvm_update *)&desc.params.raw;
+	struct i40e_aqc_nvm_update *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	/* In offset the highest byte must be zeroed. */
@@ -2607,6 +2591,7 @@ int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_read);
 
+	cmd = libie_aq_raw(&desc);
 	/* If this is the last command in a series, set the proper flag. */
 	if (last_command)
 		cmd->command_flags |= I40E_AQ_NVM_LAST_CMD;
@@ -2614,9 +2599,9 @@ int i40e_aq_read_nvm(struct i40e_hw *hw, u8 module_pointer,
 	cmd->offset = cpu_to_le32(offset);
 	cmd->length = cpu_to_le16(length);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (length > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, data, length, cmd_details);
 
@@ -2639,9 +2624,8 @@ int i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer,
 		      u32 offset, u16 length, bool last_command,
 		      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_nvm_update *cmd =
-		(struct i40e_aqc_nvm_update *)&desc.params.raw;
+	struct i40e_aqc_nvm_update *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	/* In offset the highest byte must be zeroed. */
@@ -2652,6 +2636,7 @@ int i40e_aq_erase_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_erase);
 
+	cmd = libie_aq_raw(&desc);
 	/* If this is the last command in a series, set the proper flag. */
 	if (last_command)
 		cmd->command_flags |= I40E_AQ_NVM_LAST_CMD;
@@ -2678,7 +2663,7 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 				     u32 cap_count,
 				     enum i40e_admin_queue_opc list_type_opc)
 {
-	struct i40e_aqc_list_capabilities_element_resp *cap;
+	struct libie_aqc_list_caps_elem *cap;
 	u32 valid_functions, num_functions;
 	u32 number, logical_id, phys_id;
 	struct i40e_hw_capabilities *p;
@@ -2687,7 +2672,7 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 	int status;
 	u32 i = 0;
 
-	cap = (struct i40e_aqc_list_capabilities_element_resp *) buff;
+	cap = (struct libie_aqc_list_caps_elem *)buff;
 
 	if (list_type_opc == i40e_aqc_opc_list_dev_capabilities)
 		p = &hw->dev_caps;
@@ -2697,17 +2682,17 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 		return;
 
 	for (i = 0; i < cap_count; i++, cap++) {
-		id = le16_to_cpu(cap->id);
+		id = le16_to_cpu(cap->cap);
 		number = le32_to_cpu(cap->number);
 		logical_id = le32_to_cpu(cap->logical_id);
 		phys_id = le32_to_cpu(cap->phys_id);
-		major_rev = cap->major_rev;
+		major_rev = cap->major_ver;
 
 		switch (id) {
-		case I40E_AQ_CAP_ID_SWITCH_MODE:
+		case LIBIE_AQC_CAPS_SWITCH_MODE:
 			p->switch_mode = number;
 			break;
-		case I40E_AQ_CAP_ID_MNG_MODE:
+		case LIBIE_AQC_CAPS_MNG_MODE:
 			p->management_mode = number;
 			if (major_rev > 1) {
 				p->mng_protocols_over_mctp = logical_id;
@@ -2718,76 +2703,76 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 				p->mng_protocols_over_mctp = 0;
 			}
 			break;
-		case I40E_AQ_CAP_ID_NPAR_ACTIVE:
+		case LIBIE_AQC_CAPS_NPAR_ACTIVE:
 			p->npar_enable = number;
 			break;
-		case I40E_AQ_CAP_ID_OS2BMC_CAP:
+		case LIBIE_AQC_CAPS_OS2BMC_CAP:
 			p->os2bmc = number;
 			break;
-		case I40E_AQ_CAP_ID_FUNCTIONS_VALID:
+		case LIBIE_AQC_CAPS_VALID_FUNCTIONS:
 			p->valid_functions = number;
 			break;
-		case I40E_AQ_CAP_ID_SRIOV:
+		case LIBIE_AQC_CAPS_SRIOV:
 			if (number == 1)
 				p->sr_iov_1_1 = true;
 			break;
-		case I40E_AQ_CAP_ID_VF:
+		case LIBIE_AQC_CAPS_VF:
 			p->num_vfs = number;
 			p->vf_base_id = logical_id;
 			break;
-		case I40E_AQ_CAP_ID_VMDQ:
+		case LIBIE_AQC_CAPS_VMDQ:
 			if (number == 1)
 				p->vmdq = true;
 			break;
-		case I40E_AQ_CAP_ID_8021QBG:
+		case LIBIE_AQC_CAPS_8021QBG:
 			if (number == 1)
 				p->evb_802_1_qbg = true;
 			break;
-		case I40E_AQ_CAP_ID_8021QBR:
+		case LIBIE_AQC_CAPS_8021QBR:
 			if (number == 1)
 				p->evb_802_1_qbh = true;
 			break;
-		case I40E_AQ_CAP_ID_VSI:
+		case LIBIE_AQC_CAPS_VSI:
 			p->num_vsis = number;
 			break;
-		case I40E_AQ_CAP_ID_DCB:
+		case LIBIE_AQC_CAPS_DCB:
 			if (number == 1) {
 				p->dcb = true;
 				p->enabled_tcmap = logical_id;
 				p->maxtc = phys_id;
 			}
 			break;
-		case I40E_AQ_CAP_ID_FCOE:
+		case LIBIE_AQC_CAPS_FCOE:
 			if (number == 1)
 				p->fcoe = true;
 			break;
-		case I40E_AQ_CAP_ID_ISCSI:
+		case LIBIE_AQC_CAPS_ISCSI:
 			if (number == 1)
 				p->iscsi = true;
 			break;
-		case I40E_AQ_CAP_ID_RSS:
+		case LIBIE_AQC_CAPS_RSS:
 			p->rss = true;
 			p->rss_table_size = number;
 			p->rss_table_entry_width = logical_id;
 			break;
-		case I40E_AQ_CAP_ID_RXQ:
+		case LIBIE_AQC_CAPS_RXQS:
 			p->num_rx_qp = number;
 			p->base_queue = phys_id;
 			break;
-		case I40E_AQ_CAP_ID_TXQ:
+		case LIBIE_AQC_CAPS_TXQS:
 			p->num_tx_qp = number;
 			p->base_queue = phys_id;
 			break;
-		case I40E_AQ_CAP_ID_MSIX:
+		case LIBIE_AQC_CAPS_MSIX:
 			p->num_msix_vectors = number;
 			i40e_debug(hw, I40E_DEBUG_INIT,
 				   "HW Capability: MSIX vector count = %d\n",
 				   p->num_msix_vectors);
 			break;
-		case I40E_AQ_CAP_ID_VF_MSIX:
+		case LIBIE_AQC_CAPS_VF_MSIX:
 			p->num_msix_vectors_vf = number;
 			break;
-		case I40E_AQ_CAP_ID_FLEX10:
+		case LIBIE_AQC_CAPS_FLEX10:
 			if (major_rev == 1) {
 				if (number == 1) {
 					p->flex10_enable = true;
@@ -2803,42 +2788,42 @@ static void i40e_parse_discover_capabilities(struct i40e_hw *hw, void *buff,
 			p->flex10_mode = logical_id;
 			p->flex10_status = phys_id;
 			break;
-		case I40E_AQ_CAP_ID_CEM:
+		case LIBIE_AQC_CAPS_CEM:
 			if (number == 1)
 				p->mgmt_cem = true;
 			break;
-		case I40E_AQ_CAP_ID_IWARP:
+		case LIBIE_AQC_CAPS_RDMA:
 			if (number == 1)
 				p->iwarp = true;
 			break;
-		case I40E_AQ_CAP_ID_LED:
+		case LIBIE_AQC_CAPS_LED:
 			if (phys_id < I40E_HW_CAP_MAX_GPIO)
 				p->led[phys_id] = true;
 			break;
-		case I40E_AQ_CAP_ID_SDP:
+		case LIBIE_AQC_CAPS_SDP:
 			if (phys_id < I40E_HW_CAP_MAX_GPIO)
 				p->sdp[phys_id] = true;
 			break;
-		case I40E_AQ_CAP_ID_MDIO:
+		case LIBIE_AQC_CAPS_MDIO:
 			if (number == 1) {
 				p->mdio_port_num = phys_id;
 				p->mdio_port_mode = logical_id;
 			}
 			break;
-		case I40E_AQ_CAP_ID_1588:
+		case LIBIE_AQC_CAPS_1588:
 			if (number == 1)
 				p->ieee_1588 = true;
 			break;
-		case I40E_AQ_CAP_ID_FLOW_DIRECTOR:
+		case LIBIE_AQC_CAPS_FD:
 			p->fd = true;
 			p->fd_filters_guaranteed = number;
 			p->fd_filters_best_effort = logical_id;
 			break;
-		case I40E_AQ_CAP_ID_WSR_PROT:
+		case LIBIE_AQC_CAPS_WSR_PROT:
 			p->wr_csr_prot = (u64)number;
 			p->wr_csr_prot |= (u64)logical_id << 32;
 			break;
-		case I40E_AQ_CAP_ID_NVM_MGMT:
+		case LIBIE_AQC_CAPS_NVM_MGMT:
 			if (number & I40E_NVM_MGMT_SEC_REV_DISABLED)
 				p->sec_rev_disabled = true;
 			if (number & I40E_NVM_MGMT_UPDATE_DISABLED)
@@ -2930,11 +2915,11 @@ int i40e_aq_discover_capabilities(struct i40e_hw *hw,
 				  enum i40e_admin_queue_opc list_type_opc,
 				  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aqc_list_capabilites *cmd;
-	struct i40e_aq_desc desc;
+	struct libie_aqc_list_caps *cmd;
+	struct libie_aq_desc desc;
 	int status = 0;
 
-	cmd = (struct i40e_aqc_list_capabilites *)&desc.params.raw;
+	cmd = libie_aq_raw(&desc);
 
 	if (list_type_opc != i40e_aqc_opc_list_func_capabilities &&
 		list_type_opc != i40e_aqc_opc_list_dev_capabilities) {
@@ -2944,9 +2929,9 @@ int i40e_aq_discover_capabilities(struct i40e_hw *hw,
 
 	i40e_fill_default_direct_cmd_desc(&desc, list_type_opc);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
 	*data_size = le16_to_cpu(desc.datalen);
@@ -2979,9 +2964,8 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 		       bool last_command, u8 preservation_flags,
 		       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_nvm_update *cmd =
-		(struct i40e_aqc_nvm_update *)&desc.params.raw;
+	struct i40e_aqc_nvm_update *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	/* In offset the highest byte must be zeroed. */
@@ -2992,6 +2976,7 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_nvm_update);
 
+	cmd = libie_aq_raw(&desc);
 	/* If this is the last command in a series, set the proper flag. */
 	if (last_command)
 		cmd->command_flags |= I40E_AQ_NVM_LAST_CMD;
@@ -3009,9 +2994,9 @@ int i40e_aq_update_nvm(struct i40e_hw *hw, u8 module_pointer,
 	cmd->offset = cpu_to_le32(offset);
 	cmd->length = cpu_to_le16(length);
 
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (length > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, data, length, cmd_details);
 
@@ -3037,11 +3022,9 @@ int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 			 u16 *local_len, u16 *remote_len,
 			 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_get_mib *cmd =
-		(struct i40e_aqc_lldp_get_mib *)&desc.params.raw;
-	struct i40e_aqc_lldp_get_mib *resp =
-		(struct i40e_aqc_lldp_get_mib *)&desc.params.raw;
+	struct i40e_aqc_lldp_get_mib *resp;
+	struct i40e_aqc_lldp_get_mib *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (buff_size == 0 || !buff)
@@ -3049,16 +3032,18 @@ int i40e_aq_get_lldp_mib(struct i40e_hw *hw, u8 bridge_type,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_get_mib);
 	/* Indirect Command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->type = mib_type & I40E_AQ_LLDP_MIB_TYPE_MASK;
 	cmd->type |= FIELD_PREP(I40E_AQ_LLDP_BRIDGE_TYPE_MASK, bridge_type);
 
 	desc.datalen = cpu_to_le16(buff_size);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
 	if (!status) {
@@ -3087,19 +3072,19 @@ i40e_aq_set_lldp_mib(struct i40e_hw *hw,
 		     struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aqc_lldp_set_local_mib *cmd;
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = (struct i40e_aqc_lldp_set_local_mib *)&desc.params.raw;
+	cmd = libie_aq_raw(&desc);
 	if (buff_size == 0 || !buff)
 		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_lldp_set_local_mib);
 	/* Indirect Command */
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 	desc.datalen = cpu_to_le16(buff_size);
 
 	cmd->type = mib_type;
@@ -3124,13 +3109,13 @@ int i40e_aq_cfg_lldp_mib_change_event(struct i40e_hw *hw,
 				      bool enable_update,
 				      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_update_mib *cmd =
-		(struct i40e_aqc_lldp_update_mib *)&desc.params.raw;
+	struct i40e_aqc_lldp_update_mib *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_update_mib);
 
+	cmd = libie_aq_raw(&desc);
 	if (!enable_update)
 		cmd->command |= I40E_AQ_LLDP_MIB_UPDATE_DISABLE;
 
@@ -3152,13 +3137,13 @@ int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 		      bool persist,
 		      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_stop *cmd =
-		(struct i40e_aqc_lldp_stop *)&desc.params.raw;
+	struct i40e_aqc_lldp_stop *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_stop);
 
+	cmd = libie_aq_raw(&desc);
 	if (shutdown_agent)
 		cmd->command |= I40E_AQ_LLDP_AGENT_SHUTDOWN;
 
@@ -3186,13 +3171,13 @@ int i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent,
 int i40e_aq_start_lldp(struct i40e_hw *hw, bool persist,
 		       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_lldp_start *cmd =
-		(struct i40e_aqc_lldp_start *)&desc.params.raw;
+	struct i40e_aqc_lldp_start *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_lldp_start);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->command = I40E_AQ_LLDP_AGENT_START;
 
 	if (persist) {
@@ -3219,9 +3204,8 @@ int
 i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_set_dcb_parameters *cmd =
-		(struct i40e_aqc_set_dcb_parameters *)&desc.params.raw;
+	struct i40e_aqc_set_dcb_parameters *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!test_bit(I40E_HW_CAP_FW_LLDP_STOPPABLE, hw->caps))
@@ -3230,6 +3214,7 @@ i40e_aq_set_dcb_parameters(struct i40e_hw *hw, bool dcb_enable,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_dcb_parameters);
 
+	cmd = libie_aq_raw(&desc);
 	if (dcb_enable) {
 		cmd->valid_flags = I40E_DCB_VALID;
 		cmd->command = I40E_AQ_DCB_SET_AGENT;
@@ -3252,7 +3237,7 @@ int i40e_aq_get_cee_dcb_config(struct i40e_hw *hw,
 			       void *buff, u16 buff_size,
 			       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (buff_size == 0 || !buff)
@@ -3260,7 +3245,7 @@ int i40e_aq_get_cee_dcb_config(struct i40e_hw *hw,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_get_cee_dcb_cfg);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	status = i40e_asq_send_command(hw, &desc, (void *)buff, buff_size,
 				       cmd_details);
 
@@ -3284,15 +3269,15 @@ int i40e_aq_add_udp_tunnel(struct i40e_hw *hw,
 			   u8 *filter_index,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_udp_tunnel *cmd =
-		(struct i40e_aqc_add_udp_tunnel *)&desc.params.raw;
-	struct i40e_aqc_del_udp_tunnel_completion *resp =
-		(struct i40e_aqc_del_udp_tunnel_completion *)&desc.params.raw;
+	struct i40e_aqc_del_udp_tunnel_completion *resp;
+	struct i40e_aqc_add_udp_tunnel *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_add_udp_tunnel);
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	cmd->udp_port = cpu_to_le16(udp_port);
 	cmd->protocol_type = protocol_index;
 
@@ -3313,13 +3298,13 @@ int i40e_aq_add_udp_tunnel(struct i40e_hw *hw,
 int i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_remove_udp_tunnel *cmd =
-		(struct i40e_aqc_remove_udp_tunnel *)&desc.params.raw;
+	struct i40e_aqc_remove_udp_tunnel *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_del_udp_tunnel);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->index = index;
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -3338,9 +3323,8 @@ int i40e_aq_del_udp_tunnel(struct i40e_hw *hw, u8 index,
 int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_switch_seid *cmd =
-		(struct i40e_aqc_switch_seid *)&desc.params.raw;
+	struct i40e_aqc_switch_seid *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (seid == 0)
@@ -3348,6 +3332,7 @@ int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_delete_element);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->seid = cpu_to_le16(seid);
 
 	status = i40e_asq_send_command_atomic(hw, &desc, NULL, 0,
@@ -3368,7 +3353,7 @@ int i40e_aq_delete_element(struct i40e_hw *hw, u16 seid,
 int i40e_aq_dcb_updated(struct i40e_hw *hw,
 			struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_dcb_updated);
@@ -3394,9 +3379,8 @@ static int i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid,
 				enum i40e_admin_queue_opc opcode,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_tx_sched_ind *cmd =
-		(struct i40e_aqc_tx_sched_ind *)&desc.params.raw;
+	struct i40e_aqc_tx_sched_ind *cmd;
+	struct libie_aq_desc desc;
 	int status;
 	bool cmd_param_flag = false;
 
@@ -3423,12 +3407,13 @@ static int i40e_aq_tx_sched_cmd(struct i40e_hw *hw, u16 seid,
 
 	i40e_fill_default_direct_cmd_desc(&desc, opcode);
 
+	cmd = libie_aq_raw(&desc);
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (cmd_param_flag)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	desc.datalen = cpu_to_le16(buff_size);
 
@@ -3451,14 +3436,14 @@ int i40e_aq_config_vsi_bw_limit(struct i40e_hw *hw,
 				u16 seid, u16 credit, u8 max_credit,
 				struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_configure_vsi_bw_limit *cmd =
-		(struct i40e_aqc_configure_vsi_bw_limit *)&desc.params.raw;
+	struct i40e_aqc_configure_vsi_bw_limit *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_configure_vsi_bw_limit);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->vsi_seid = cpu_to_le16(seid);
 	cmd->credit = cpu_to_le16(credit);
 	cmd->max_credit = max_credit;
@@ -3786,18 +3771,16 @@ int i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw,
 					  struct i40e_control_filter_stats *stats,
 					  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_control_packet_filter *cmd =
-		(struct i40e_aqc_add_remove_control_packet_filter *)
-		&desc.params.raw;
-	struct i40e_aqc_add_remove_control_packet_filter_completion *resp =
-		(struct i40e_aqc_add_remove_control_packet_filter_completion *)
-		&desc.params.raw;
+	struct i40e_aqc_add_remove_control_packet_filter_completion *resp;
+	struct i40e_aqc_add_remove_control_packet_filter *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (vsi_seid == 0)
 		return -EINVAL;
 
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	if (is_add) {
 		i40e_fill_default_direct_cmd_desc(&desc,
 				i40e_aqc_opc_add_control_packet_filter);
@@ -3865,15 +3848,15 @@ static int i40e_aq_alternate_read(struct i40e_hw *hw,
 				  u32 reg_addr0, u32 *reg_val0,
 				  u32 reg_addr1, u32 *reg_val1)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_alternate_write *cmd_resp =
-		(struct i40e_aqc_alternate_write *)&desc.params.raw;
+	struct i40e_aqc_alternate_write *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!reg_val0)
 		return -EINVAL;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_alternate_read);
+	cmd_resp = libie_aq_raw(&desc);
 	cmd_resp->address0 = cpu_to_le32(reg_addr0);
 	cmd_resp->address1 = cpu_to_le32(reg_addr1);
 
@@ -3901,10 +3884,10 @@ int i40e_aq_suspend_port_tx(struct i40e_hw *hw, u16 seid,
 			    struct i40e_asq_cmd_details *cmd_details)
 {
 	struct i40e_aqc_tx_sched_ind *cmd;
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
-	cmd = (struct i40e_aqc_tx_sched_ind *)&desc.params.raw;
+	cmd = libie_aq_raw(&desc);
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_suspend_port_tx);
 	cmd->vsi_seid = cpu_to_le16(seid);
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -3922,7 +3905,7 @@ int i40e_aq_suspend_port_tx(struct i40e_hw *hw, u16 seid,
 int i40e_aq_resume_port_tx(struct i40e_hw *hw,
 			   struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_resume_port_tx);
@@ -3999,11 +3982,9 @@ int i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id,
 		       u8 *ret_next_table, u32 *ret_next_index,
 		       struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_debug_dump_internals *cmd =
-		(struct i40e_aqc_debug_dump_internals *)&desc.params.raw;
-	struct i40e_aqc_debug_dump_internals *resp =
-		(struct i40e_aqc_debug_dump_internals *)&desc.params.raw;
+	struct i40e_aqc_debug_dump_internals *resp;
+	struct i40e_aqc_debug_dump_internals *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (buff_size == 0 || !buff)
@@ -4011,10 +3992,12 @@ int i40e_aq_debug_dump(struct i40e_hw *hw, u8 cluster_id,
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_debug_dump_internals);
+	resp = libie_aq_raw(&desc);
+	cmd = libie_aq_raw(&desc);
 	/* Indirect Command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	cmd->cluster_id = cluster_id;
 	cmd->table_id = table_id;
@@ -4091,18 +4074,18 @@ i40e_aq_configure_partition_bw(struct i40e_hw *hw,
 			       struct i40e_asq_cmd_details *cmd_details)
 {
 	u16 bwd_size = sizeof(*bw_data);
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_configure_partition_bw);
 
 	/* Indirect command */
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_RD);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_RD);
 
 	if (bwd_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	desc.datalen = cpu_to_le16(bwd_size);
 
@@ -4534,9 +4517,8 @@ int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw,
 				 u32 reg_addr, u32 *reg_val,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp =
-		(struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw;
+	struct i40e_aqc_rx_ctl_reg_read_write *cmd_resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	if (!reg_val)
@@ -4544,6 +4526,7 @@ int i40e_aq_rx_ctl_read_register(struct i40e_hw *hw,
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_read);
 
+	cmd_resp = libie_aq_raw(&desc);
 	cmd_resp->address = cpu_to_le32(reg_addr);
 
 	status = i40e_asq_send_command(hw, &desc, NULL, 0, cmd_details);
@@ -4572,7 +4555,7 @@ u32 i40e_read_rx_ctl(struct i40e_hw *hw, u32 reg_addr)
 	if (!use_register) {
 do_retry:
 		status = i40e_aq_rx_ctl_read_register(hw, reg_addr, &val, NULL);
-		if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) {
+		if (hw->aq.asq_last_status == LIBIE_AQ_RC_EAGAIN && retry) {
 			usleep_range(1000, 2000);
 			retry--;
 			goto do_retry;
@@ -4600,13 +4583,13 @@ int i40e_aq_rx_ctl_write_register(struct i40e_hw *hw,
 				  u32 reg_addr, u32 reg_val,
 				  struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_rx_ctl_reg_read_write *cmd =
-		(struct i40e_aqc_rx_ctl_reg_read_write *)&desc.params.raw;
+	struct i40e_aqc_rx_ctl_reg_read_write *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc, i40e_aqc_opc_rx_ctl_reg_write);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->address = cpu_to_le32(reg_addr);
 	cmd->value = cpu_to_le32(reg_val);
 
@@ -4634,7 +4617,7 @@ void i40e_write_rx_ctl(struct i40e_hw *hw, u32 reg_addr, u32 reg_val)
 do_retry:
 		status = i40e_aq_rx_ctl_write_register(hw, reg_addr,
 						       reg_val, NULL);
-		if (hw->aq.asq_last_status == I40E_AQ_RC_EAGAIN && retry) {
+		if (hw->aq.asq_last_status == LIBIE_AQ_RC_EAGAIN && retry) {
 			usleep_range(1000, 2000);
 			retry--;
 			goto do_retry;
@@ -4693,14 +4676,14 @@ int i40e_aq_set_phy_register_ext(struct i40e_hw *hw,
 				 u32 reg_addr, u32 reg_val,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_phy_register_access *cmd =
-		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
+	struct i40e_aqc_phy_register_access *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_set_phy_register);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->phy_interface = phy_select;
 	cmd->dev_address = dev_addr;
 	cmd->reg_address = cpu_to_le32(reg_addr);
@@ -4738,14 +4721,14 @@ int i40e_aq_get_phy_register_ext(struct i40e_hw *hw,
 				 u32 reg_addr, u32 *reg_val,
 				 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_phy_register_access *cmd =
-		(struct i40e_aqc_phy_register_access *)&desc.params.raw;
+	struct i40e_aqc_phy_register_access *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_phy_register);
 
+	cmd = libie_aq_raw(&desc);
 	cmd->phy_interface = phy_select;
 	cmd->dev_address = dev_addr;
 	cmd->reg_address = cpu_to_le32(reg_addr);
@@ -4777,19 +4760,18 @@ int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff,
 		      u32 *error_offset, u32 *error_info,
 		      struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_write_personalization_profile *cmd =
-		(struct i40e_aqc_write_personalization_profile *)
-		&desc.params.raw;
+	struct i40e_aqc_write_personalization_profile *cmd;
 	struct i40e_aqc_write_ddp_resp *resp;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_write_personalization_profile);
 
-	desc.flags |= cpu_to_le16(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD);
+	cmd = libie_aq_raw(&desc);
+	desc.flags |= cpu_to_le16(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 
 	desc.datalen = cpu_to_le16(buff_size);
 
@@ -4797,7 +4779,7 @@ int i40e_aq_write_ddp(struct i40e_hw *hw, void *buff,
 
 	status = i40e_asq_send_command(hw, &desc, buff, buff_size, cmd_details);
 	if (!status) {
-		resp = (struct i40e_aqc_write_ddp_resp *)&desc.params.raw;
+		resp = libie_aq_raw(&desc);
 		if (error_offset)
 			*error_offset = le32_to_cpu(resp->error_offset);
 		if (error_info)
@@ -4819,17 +4801,17 @@ int i40e_aq_get_ddp_list(struct i40e_hw *hw, void *buff,
 			 u16 buff_size, u8 flags,
 			 struct i40e_asq_cmd_details *cmd_details)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_get_applied_profiles *cmd =
-		(struct i40e_aqc_get_applied_profiles *)&desc.params.raw;
+	struct i40e_aqc_get_applied_profiles *cmd;
+	struct libie_aq_desc desc;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_get_personalization_profile_list);
 
-	desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+	cmd = libie_aq_raw(&desc);
+	desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 	if (buff_size > I40E_AQ_LARGE_BUF)
-		desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+		desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 	desc.datalen = cpu_to_le16(buff_size);
 
 	cmd->flags = flags;
@@ -4891,7 +4873,7 @@ i40e_find_segment_in_package(u32 segment_type,
 static int i40e_ddp_exec_aq_section(struct i40e_hw *hw,
 				    struct i40e_profile_aq_section *aq)
 {
-	struct i40e_aq_desc desc;
+	struct libie_aq_desc desc;
 	u8 *msg = NULL;
 	u16 msglen;
 	int status;
@@ -4902,10 +4884,10 @@ static int i40e_ddp_exec_aq_section(struct i40e_hw *hw,
 
 	msglen = aq->datalen;
 	if (msglen) {
-		desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF |
-						I40E_AQ_FLAG_RD));
+		desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF |
+						LIBIE_AQ_FLAG_RD));
 		if (msglen > I40E_AQ_LARGE_BUF)
-			desc.flags |= cpu_to_le16((u16)I40E_AQ_FLAG_LB);
+			desc.flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_LB);
 		desc.datalen = cpu_to_le16(msglen);
 		msg = &aq->data[0];
 	}
@@ -5122,18 +5104,18 @@ i40e_aq_add_cloud_filters(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_cloud_filters_element_data *filters,
 			  u8 filter_count)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_cloud_filters *cmd =
-	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	struct i40e_aqc_add_remove_cloud_filters *cmd;
+	struct libie_aq_desc desc;
 	u16 buff_len;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_add_cloud_filters);
 
+	cmd = libie_aq_raw(&desc);
 	buff_len = filter_count * sizeof(*filters);
 	desc.datalen = cpu_to_le16(buff_len);
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	cmd->num_filters = filter_count;
 	cmd->seid = cpu_to_le16(seid);
 
@@ -5159,9 +5141,8 @@ i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 			     struct i40e_aqc_cloud_filters_element_bb *filters,
 			     u8 filter_count)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_cloud_filters *cmd =
-	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	struct i40e_aqc_add_remove_cloud_filters *cmd;
+	struct libie_aq_desc desc;
 	u16 buff_len;
 	int status;
 	int i;
@@ -5169,9 +5150,10 @@ i40e_aq_add_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_add_cloud_filters);
 
+	cmd = libie_aq_raw(&desc);
 	buff_len = filter_count * sizeof(*filters);
 	desc.datalen = cpu_to_le16(buff_len);
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	cmd->num_filters = filter_count;
 	cmd->seid = cpu_to_le16(seid);
 	cmd->big_buffer_flag = I40E_AQC_ADD_CLOUD_CMD_BB;
@@ -5215,18 +5197,18 @@ i40e_aq_rem_cloud_filters(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_cloud_filters_element_data *filters,
 			  u8 filter_count)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_cloud_filters *cmd =
-	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	struct i40e_aqc_add_remove_cloud_filters *cmd;
+	struct libie_aq_desc desc;
 	u16 buff_len;
 	int status;
 
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_remove_cloud_filters);
 
+	cmd = libie_aq_raw(&desc);
 	buff_len = filter_count * sizeof(*filters);
 	desc.datalen = cpu_to_le16(buff_len);
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	cmd->num_filters = filter_count;
 	cmd->seid = cpu_to_le16(seid);
 
@@ -5252,9 +5234,8 @@ i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 			     struct i40e_aqc_cloud_filters_element_bb *filters,
 			     u8 filter_count)
 {
-	struct i40e_aq_desc desc;
-	struct i40e_aqc_add_remove_cloud_filters *cmd =
-	(struct i40e_aqc_add_remove_cloud_filters *)&desc.params.raw;
+	struct i40e_aqc_add_remove_cloud_filters *cmd;
+	struct libie_aq_desc desc;
 	u16 buff_len;
 	int status;
 	int i;
@@ -5262,9 +5243,10 @@ i40e_aq_rem_cloud_filters_bb(struct i40e_hw *hw, u16 seid,
 	i40e_fill_default_direct_cmd_desc(&desc,
 					  i40e_aqc_opc_remove_cloud_filters);
 
+	cmd = libie_aq_raw(&desc);
 	buff_len = filter_count * sizeof(*filters);
 	desc.datalen = cpu_to_le16(buff_len);
-	desc.flags |= cpu_to_le16((u16)(I40E_AQ_FLAG_BUF | I40E_AQ_FLAG_RD));
+	desc.flags |= cpu_to_le16((u16)(LIBIE_AQ_FLAG_BUF | LIBIE_AQ_FLAG_RD));
 	cmd->num_filters = filter_count;
 	cmd->seid = cpu_to_le16(seid);
 	cmd->big_buffer_flag = I40E_AQC_ADD_CLOUD_CMD_BB;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
index 352e957443fd..9e0c9597aeb9 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c
@@ -750,7 +750,7 @@ static int i40e_get_ieee_dcb_config(struct i40e_hw *hw)
 				     I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE,
 				     &hw->remote_dcbx_config);
 	/* Don't treat ENOENT as an error for Remote MIBs */
-	if (hw->aq.asq_last_status == I40E_AQ_RC_ENOENT)
+	if (hw->aq.asq_last_status == LIBIE_AQ_RC_ENOENT)
 		ret = 0;
 
 out:
@@ -799,7 +799,7 @@ int i40e_get_dcb_config(struct i40e_hw *hw)
 	}
 
 	/* CEE mode not enabled try querying IEEE data */
-	if (hw->aq.asq_last_status == I40E_AQ_RC_ENOENT)
+	if (hw->aq.asq_last_status == LIBIE_AQ_RC_ENOENT)
 		return i40e_get_ieee_dcb_config(hw);
 
 	if (ret)
@@ -816,7 +816,7 @@ int i40e_get_dcb_config(struct i40e_hw *hw)
 				     I40E_AQ_LLDP_BRIDGE_TYPE_NEAREST_BRIDGE,
 				     &hw->remote_dcbx_config);
 	/* Don't treat ENOENT as an error for Remote MIBs */
-	if (hw->aq.asq_last_status == I40E_AQ_RC_ENOENT)
+	if (hw->aq.asq_last_status == LIBIE_AQ_RC_ENOENT)
 		ret = 0;
 
 out:
@@ -925,11 +925,11 @@ i40e_get_fw_lldp_status(struct i40e_hw *hw,
 
 	if (!ret) {
 		*lldp_status = I40E_GET_FW_LLDP_STATUS_ENABLED;
-	} else if (hw->aq.asq_last_status == I40E_AQ_RC_ENOENT) {
+	} else if (hw->aq.asq_last_status == LIBIE_AQ_RC_ENOENT) {
 		/* MIB is not available yet but the agent is running */
 		*lldp_status = I40E_GET_FW_LLDP_STATUS_ENABLED;
 		ret = 0;
-	} else if (hw->aq.asq_last_status == I40E_AQ_RC_EPERM) {
+	} else if (hw->aq.asq_last_status == LIBIE_AQ_RC_EPERM) {
 		*lldp_status = I40E_GET_FW_LLDP_STATUS_DISABLED;
 		ret = 0;
 	}
diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
index 6cd9da662ae1..6cd6f23d42a6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c
@@ -489,7 +489,7 @@ static void i40e_dbg_dump_aq_desc(struct i40e_pf *pf)
 	dev_info(&pf->pdev->dev, "AdminQ Tx Ring\n");
 	ring = &(hw->aq.asq);
 	for (i = 0; i < ring->count; i++) {
-		struct i40e_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
+		struct libie_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
 
 		dev_info(&pf->pdev->dev,
 			 "   at[%02d] flags=0x%04x op=0x%04x dlen=0x%04x ret=0x%04x cookie_h=0x%08x cookie_l=0x%08x\n",
@@ -502,7 +502,7 @@ static void i40e_dbg_dump_aq_desc(struct i40e_pf *pf)
 	dev_info(&pf->pdev->dev, "AdminQ Rx Ring\n");
 	ring = &(hw->aq.arq);
 	for (i = 0; i < ring->count; i++) {
-		struct i40e_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
+		struct libie_aq_desc *d = I40E_ADMINQ_DESC(*ring, i);
 
 		dev_info(&pf->pdev->dev,
 			 "   ar[%02d] flags=0x%04x op=0x%04x dlen=0x%04x ret=0x%04x cookie_h=0x%08x cookie_l=0x%08x\n",
@@ -1268,10 +1268,10 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			dev_info(&pf->pdev->dev, "clear_stats vsi [seid] or clear_stats port\n");
 		}
 	} else if (strncmp(cmd_buf, "send aq_cmd", 11) == 0) {
-		struct i40e_aq_desc *desc;
+		struct libie_aq_desc *desc;
 		int ret;
 
-		desc = kzalloc(sizeof(struct i40e_aq_desc), GFP_KERNEL);
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 		if (!desc)
 			goto command_write_done;
 		cnt = sscanf(&cmd_buf[11],
@@ -1279,10 +1279,10 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			     &desc->flags,
 			     &desc->opcode, &desc->datalen, &desc->retval,
 			     &desc->cookie_high, &desc->cookie_low,
-			     &desc->params.internal.param0,
-			     &desc->params.internal.param1,
-			     &desc->params.internal.param2,
-			     &desc->params.internal.param3);
+			     &desc->params.generic.param0,
+			     &desc->params.generic.param1,
+			     &desc->params.generic.addr_high,
+			     &desc->params.generic.addr_low);
 		if (cnt != 10) {
 			dev_info(&pf->pdev->dev,
 				 "send aq_cmd: bad command string, cnt=%d\n",
@@ -1307,19 +1307,19 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			 "AQ desc WB 0x%04x 0x%04x 0x%04x 0x%04x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
 			 desc->flags, desc->opcode, desc->datalen, desc->retval,
 			 desc->cookie_high, desc->cookie_low,
-			 desc->params.internal.param0,
-			 desc->params.internal.param1,
-			 desc->params.internal.param2,
-			 desc->params.internal.param3);
+			 desc->params.generic.param0,
+			 desc->params.generic.param1,
+			 desc->params.generic.addr_high,
+			 desc->params.generic.addr_low);
 		kfree(desc);
 		desc = NULL;
 	} else if (strncmp(cmd_buf, "send indirect aq_cmd", 20) == 0) {
-		struct i40e_aq_desc *desc;
+		struct libie_aq_desc *desc;
 		u16 buffer_len;
 		u8 *buff;
 		int ret;
 
-		desc = kzalloc(sizeof(struct i40e_aq_desc), GFP_KERNEL);
+		desc = kzalloc(sizeof(*desc), GFP_KERNEL);
 		if (!desc)
 			goto command_write_done;
 		cnt = sscanf(&cmd_buf[20],
@@ -1327,10 +1327,10 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			     &desc->flags,
 			     &desc->opcode, &desc->datalen, &desc->retval,
 			     &desc->cookie_high, &desc->cookie_low,
-			     &desc->params.internal.param0,
-			     &desc->params.internal.param1,
-			     &desc->params.internal.param2,
-			     &desc->params.internal.param3,
+			     &desc->params.generic.param0,
+			     &desc->params.generic.param1,
+			     &desc->params.generic.addr_high,
+			     &desc->params.generic.addr_low,
 			     &buffer_len);
 		if (cnt != 11) {
 			dev_info(&pf->pdev->dev,
@@ -1350,7 +1350,7 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			desc = NULL;
 			goto command_write_done;
 		}
-		desc->flags |= cpu_to_le16((u16)I40E_AQ_FLAG_BUF);
+		desc->flags |= cpu_to_le16((u16)LIBIE_AQ_FLAG_BUF);
 		ret = i40e_asq_send_command(&pf->hw, desc, buff,
 					    buffer_len, NULL);
 		if (!ret) {
@@ -1368,10 +1368,10 @@ static ssize_t i40e_dbg_command_write(struct file *filp,
 			 "AQ desc WB 0x%04x 0x%04x 0x%04x 0x%04x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x 0x%08x\n",
 			 desc->flags, desc->opcode, desc->datalen, desc->retval,
 			 desc->cookie_high, desc->cookie_low,
-			 desc->params.internal.param0,
-			 desc->params.internal.param1,
-			 desc->params.internal.param2,
-			 desc->params.internal.param3);
+			 desc->params.generic.param0,
+			 desc->params.generic.param1,
+			 desc->params.generic.addr_high,
+			 desc->params.generic.addr_low);
 		print_hex_dump(KERN_INFO, "AQ buffer WB: ",
 			       DUMP_PREFIX_OFFSET, 16, 1,
 			       buff, buffer_len, true);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
index 2ff17d50135c..2b01eedf3605 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c
@@ -1918,13 +1918,13 @@ static int i40e_get_eeprom(struct net_device *netdev,
 		ret_val = i40e_aq_read_nvm(hw, 0x0, offset, len,
 				(u8 *)eeprom_buff + (I40E_NVM_SECTOR_SIZE * i),
 				last, NULL);
-		if (ret_val && hw->aq.asq_last_status == I40E_AQ_RC_EPERM) {
+		if (ret_val && hw->aq.asq_last_status == LIBIE_AQ_RC_EPERM) {
 			dev_info(&pf->pdev->dev,
 				 "read NVM failed, invalid offset 0x%x\n",
 				 offset);
 			break;
 		} else if (ret_val &&
-			   hw->aq.asq_last_status == I40E_AQ_RC_EACCES) {
+			   hw->aq.asq_last_status == LIBIE_AQ_RC_EACCES) {
 			dev_info(&pf->pdev->dev,
 				 "read NVM failed, access, offset 0x%x\n",
 				 offset);
@@ -5249,9 +5249,9 @@ static int i40e_set_priv_flags(struct net_device *dev, u32 flags)
 	DECLARE_BITMAP(orig_flags, I40E_PF_FLAGS_NBITS);
 	DECLARE_BITMAP(new_flags, I40E_PF_FLAGS_NBITS);
 	struct i40e_netdev_priv *np = netdev_priv(dev);
-	enum i40e_admin_queue_err adq_err;
 	struct i40e_vsi *vsi = np->vsi;
 	struct i40e_pf *pf = vsi->back;
+	enum libie_aq_err adq_err;
 	u32 reset_needed = 0;
 	int status;
 	u32 i, j;
@@ -5371,7 +5371,7 @@ flags_complete:
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		ret = i40e_aq_set_switch_config(&pf->hw, sw_flags, valid_flags,
 						0, NULL);
-		if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) {
+		if (ret && pf->hw.aq.asq_last_status != LIBIE_AQ_RC_ESRCH) {
 			dev_info(&pf->pdev->dev,
 				 "couldn't set switch config bits, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
@@ -5438,16 +5438,16 @@ flags_complete:
 			if (status) {
 				adq_err = pf->hw.aq.asq_last_status;
 				switch (adq_err) {
-				case I40E_AQ_RC_EEXIST:
+				case LIBIE_AQ_RC_EEXIST:
 					dev_warn(&pf->pdev->dev,
 						 "FW LLDP agent is already running\n");
 					reset_needed = 0;
 					break;
-				case I40E_AQ_RC_EPERM:
+				case LIBIE_AQ_RC_EPERM:
 					dev_warn(&pf->pdev->dev,
 						 "Device configuration forbids SW from starting the LLDP agent.\n");
 					return -EINVAL;
-				case I40E_AQ_RC_EAGAIN:
+				case LIBIE_AQ_RC_EAGAIN:
 					dev_warn(&pf->pdev->dev,
 						 "Stop FW LLDP agent command is still being processed, please try again in a second.\n");
 					return -EBUSY;
diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c
index 949b74fbb127..f4d913eeeac6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_main.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_main.c
@@ -2340,14 +2340,14 @@ void i40e_aqc_del_filters(struct i40e_vsi *vsi, const char *vsi_name,
 			  int num_del, int *retval)
 {
 	struct i40e_hw *hw = &vsi->back->hw;
-	enum i40e_admin_queue_err aq_status;
+	enum libie_aq_err aq_status;
 	int aq_ret;
 
 	aq_ret = i40e_aq_remove_macvlan_v2(hw, vsi->seid, list, num_del, NULL,
 					   &aq_status);
 
 	/* Explicitly ignore and do not report when firmware returns ENOENT */
-	if (aq_ret && !(aq_status == I40E_AQ_RC_ENOENT)) {
+	if (aq_ret && !(aq_status == LIBIE_AQ_RC_ENOENT)) {
 		*retval = -EIO;
 		dev_info(&vsi->back->pdev->dev,
 			 "ignoring delete macvlan error on %s, err %pe, aq_err %s\n",
@@ -2375,7 +2375,7 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name,
 			  int num_add)
 {
 	struct i40e_hw *hw = &vsi->back->hw;
-	enum i40e_admin_queue_err aq_status;
+	enum libie_aq_err aq_status;
 	int fcnt;
 
 	i40e_aq_add_macvlan_v2(hw, vsi->seid, list, num_add, NULL, &aq_status);
@@ -5997,8 +5997,8 @@ int i40e_set_bw_limit(struct i40e_vsi *vsi, u16 seid, u64 max_tx_rate)
  **/
 static void i40e_remove_queue_channels(struct i40e_vsi *vsi)
 {
-	enum i40e_admin_queue_err last_aq_status;
 	struct i40e_cloud_filter *cfilter;
+	enum libie_aq_err last_aq_status;
 	struct i40e_channel *ch, *ch_tmp;
 	struct i40e_pf *pf = vsi->back;
 	struct hlist_node *node;
@@ -6539,7 +6539,7 @@ static int i40e_validate_and_set_switch_mode(struct i40e_vsi *vsi)
 	ret = i40e_aq_set_switch_config(hw, pf->last_sw_conf_flags,
 					pf->last_sw_conf_valid_flags,
 					mode, NULL);
-	if (ret && hw->aq.asq_last_status != I40E_AQ_RC_ESRCH)
+	if (ret && hw->aq.asq_last_status != LIBIE_AQ_RC_ESRCH)
 		dev_err(&pf->pdev->dev,
 			"couldn't set switch config bits, err %pe aq_err %s\n",
 			ERR_PTR(ret),
@@ -7214,7 +7214,7 @@ static int i40e_init_pf_dcb(struct i40e_pf *pf)
 			dev_dbg(&pf->pdev->dev,
 				"DCBX offload is supported for this PF.\n");
 		}
-	} else if (pf->hw.aq.asq_last_status == I40E_AQ_RC_EPERM) {
+	} else if (pf->hw.aq.asq_last_status == LIBIE_AQ_RC_EPERM) {
 		dev_info(&pf->pdev->dev, "FW LLDP disabled for this PF.\n");
 		set_bit(I40E_FLAG_FW_LLDP_DIS, pf->flags);
 	} else {
@@ -9419,8 +9419,7 @@ bool i40e_dcb_need_reconfig(struct i40e_pf *pf,
 static int i40e_handle_lldp_event(struct i40e_pf *pf,
 				  struct i40e_arq_event_info *e)
 {
-	struct i40e_aqc_lldp_get_mib *mib =
-		(struct i40e_aqc_lldp_get_mib *)&e->desc.params.raw;
+	struct i40e_aqc_lldp_get_mib *mib = libie_aq_raw(&e->desc);
 	struct i40e_hw *hw = &pf->hw;
 	struct i40e_dcbx_config tmp_dcbx_cfg;
 	bool need_reconfig = false;
@@ -9559,8 +9558,7 @@ void i40e_do_reset_safe(struct i40e_pf *pf, u32 reset_flags)
 static void i40e_handle_lan_overflow_event(struct i40e_pf *pf,
 					   struct i40e_arq_event_info *e)
 {
-	struct i40e_aqc_lan_overflow *data =
-		(struct i40e_aqc_lan_overflow *)&e->desc.params.raw;
+	struct i40e_aqc_lan_overflow *data = libie_aq_raw(&e->desc);
 	u32 queue = le32_to_cpu(data->prtdcb_rupto);
 	u32 qtx_ctl = le32_to_cpu(data->otx_ctl);
 	struct i40e_hw *hw = &pf->hw;
@@ -10080,8 +10078,7 @@ static void i40e_reset_subtask(struct i40e_pf *pf)
 static void i40e_handle_link_event(struct i40e_pf *pf,
 				   struct i40e_arq_event_info *e)
 {
-	struct i40e_aqc_get_link_status *status =
-		(struct i40e_aqc_get_link_status *)&e->desc.params.raw;
+	struct i40e_aqc_get_link_status *status = libie_aq_raw(&e->desc);
 
 	/* Do a new status request to re-enable LSE reporting
 	 * and load new status information into the hw struct
@@ -10453,12 +10450,12 @@ static int i40e_reconstitute_veb(struct i40e_veb *veb)
 static int i40e_get_capabilities(struct i40e_pf *pf,
 				 enum i40e_admin_queue_opc list_type)
 {
-	struct i40e_aqc_list_capabilities_element_resp *cap_buf;
+	struct libie_aqc_list_caps_elem *cap_buf;
 	u16 data_size;
 	int buf_len;
 	int err;
 
-	buf_len = 40 * sizeof(struct i40e_aqc_list_capabilities_element_resp);
+	buf_len = 40 * sizeof(struct libie_aqc_list_caps_elem);
 	do {
 		cap_buf = kzalloc(buf_len, GFP_KERNEL);
 		if (!cap_buf)
@@ -10471,10 +10468,10 @@ static int i40e_get_capabilities(struct i40e_pf *pf,
 		/* data loaded, buffer no longer needed */
 		kfree(cap_buf);
 
-		if (pf->hw.aq.asq_last_status == I40E_AQ_RC_ENOMEM) {
+		if (pf->hw.aq.asq_last_status == LIBIE_AQ_RC_ENOMEM) {
 			/* retry with a larger buffer */
 			buf_len = data_size;
-		} else if (pf->hw.aq.asq_last_status != I40E_AQ_RC_OK || err) {
+		} else if (pf->hw.aq.asq_last_status != LIBIE_AQ_RC_OK || err) {
 			dev_info(&pf->pdev->dev,
 				 "capability discovery failed, err %pe aq_err %s\n",
 				 ERR_PTR(err),
@@ -15029,7 +15026,7 @@ static int i40e_setup_pf_switch(struct i40e_pf *pf, bool reinit, bool lock_acqui
 		valid_flags = I40E_AQ_SET_SWITCH_CFG_PROMISC;
 		ret = i40e_aq_set_switch_config(&pf->hw, flags, valid_flags, 0,
 						NULL);
-		if (ret && pf->hw.aq.asq_last_status != I40E_AQ_RC_ESRCH) {
+		if (ret && pf->hw.aq.asq_last_status != LIBIE_AQ_RC_ESRCH) {
 			dev_info(&pf->pdev->dev,
 				 "couldn't set switch config bits, err %pe aq_err %s\n",
 				 ERR_PTR(ret),
diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
index 7f0936f4e05e..5dfbe71205e6 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c
+++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c
@@ -997,7 +997,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
 			       u8 *bytes, int *perrno)
 {
 	struct i40e_asq_cmd_details cmd_details;
-	struct i40e_aq_desc *aq_desc;
+	struct libie_aq_desc *aq_desc;
 	u32 buff_size = 0;
 	u8 *buff = NULL;
 	u32 aq_desc_len;
@@ -1011,7 +1011,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
 	memset(&cmd_details, 0, sizeof(cmd_details));
 	cmd_details.wb_desc = &hw->nvm_wb_desc;
 
-	aq_desc_len = sizeof(struct i40e_aq_desc);
+	aq_desc_len = sizeof(struct libie_aq_desc);
 	memset(&hw->nvm_wb_desc, 0, aq_desc_len);
 
 	/* get the aq descriptor */
@@ -1022,7 +1022,7 @@ static int i40e_nvmupd_exec_aq(struct i40e_hw *hw,
 		*perrno = -EINVAL;
 		return -EINVAL;
 	}
-	aq_desc = (struct i40e_aq_desc *)bytes;
+	aq_desc = (struct libie_aq_desc *)bytes;
 
 	/* if data buffer needed, make sure it's ready */
 	aq_data_len = cmd->data_size - aq_desc_len;
@@ -1087,7 +1087,7 @@ static int i40e_nvmupd_get_aq_result(struct i40e_hw *hw,
 
 	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
 
-	aq_desc_len = sizeof(struct i40e_aq_desc);
+	aq_desc_len = sizeof(struct libie_aq_desc);
 	aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_wb_desc.datalen);
 
 	/* check offset range */
@@ -1154,7 +1154,7 @@ static int i40e_nvmupd_get_aq_event(struct i40e_hw *hw,
 
 	i40e_debug(hw, I40E_DEBUG_NVM, "NVMUPD: %s\n", __func__);
 
-	aq_desc_len = sizeof(struct i40e_aq_desc);
+	aq_desc_len = sizeof(struct libie_aq_desc);
 	aq_total_len = aq_desc_len + le16_to_cpu(hw->nvm_aq_event_desc.datalen);
 
 	/* check copylength range */
@@ -1442,7 +1442,7 @@ retry:
 	 * so here we try to reacquire the semaphore then retry the write.
 	 * We only do one retry, then give up.
 	 */
-	if (status && hw->aq.asq_last_status == I40E_AQ_RC_EBUSY &&
+	if (status && hw->aq.asq_last_status == LIBIE_AQ_RC_EBUSY &&
 	    !retry_attempt) {
 		u32 old_asq_status = hw->aq.asq_last_status;
 		int old_status = status;
@@ -1628,9 +1628,9 @@ void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw)
  * @desc: AdminQ descriptor
  **/
 void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode,
-				  struct i40e_aq_desc *desc)
+				  struct libie_aq_desc *desc)
 {
-	u32 aq_desc_len = sizeof(struct i40e_aq_desc);
+	u32 aq_desc_len = sizeof(struct libie_aq_desc);
 
 	if (opcode == hw->nvm_wait_opcode) {
 		memcpy(&hw->nvm_aq_event_desc, desc, aq_desc_len);
diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
index 099bb8ab7d70..bd54f06b43cd 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h
@@ -23,22 +23,22 @@ int i40e_clean_arq_element(struct i40e_hw *hw,
 			   struct i40e_arq_event_info *e,
 			   u16 *events_pending);
 int
-i40e_asq_send_command(struct i40e_hw *hw, struct i40e_aq_desc *desc,
+i40e_asq_send_command(struct i40e_hw *hw, struct libie_aq_desc *desc,
 		      void *buff, /* can be NULL */ u16  buff_size,
 		      struct i40e_asq_cmd_details *cmd_details);
 int
-i40e_asq_send_command_atomic(struct i40e_hw *hw, struct i40e_aq_desc *desc,
+i40e_asq_send_command_atomic(struct i40e_hw *hw, struct libie_aq_desc *desc,
 			     void *buff, /* can be NULL */ u16  buff_size,
 			     struct i40e_asq_cmd_details *cmd_details,
 			     bool is_atomic_context);
 int
 i40e_asq_send_command_atomic_v2(struct i40e_hw *hw,
-				struct i40e_aq_desc *desc,
+				struct libie_aq_desc *desc,
 				void *buff, /* can be NULL */
 				u16  buff_size,
 				struct i40e_asq_cmd_details *cmd_details,
 				bool is_atomic_context,
-				enum i40e_admin_queue_err *aq_status);
+				enum libie_aq_err *aq_status);
 
 /* debug function for adminq */
 void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask,
@@ -46,7 +46,7 @@ void i40e_debug_aq(struct i40e_hw *hw, enum i40e_debug_mask mask,
 
 bool i40e_check_asq_alive(struct i40e_hw *hw);
 int i40e_aq_queue_shutdown(struct i40e_hw *hw, bool unloading);
-const char *i40e_aq_str(struct i40e_hw *hw, enum i40e_admin_queue_err aq_err);
+const char *i40e_aq_str(struct i40e_hw *hw, enum libie_aq_err aq_err);
 
 int i40e_aq_get_rss_lut(struct i40e_hw *hw, u16 seid,
 			bool pf_lut, u8 *lut, u16 lut_size);
@@ -155,7 +155,7 @@ int
 i40e_aq_add_macvlan_v2(struct i40e_hw *hw, u16 seid,
 		       struct i40e_aqc_add_macvlan_element_data *mv_list,
 		       u16 count, struct i40e_asq_cmd_details *cmd_details,
-		       enum i40e_admin_queue_err *aq_status);
+		       enum libie_aq_err *aq_status);
 int i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 vsi_id,
 			   struct i40e_aqc_remove_macvlan_element_data *mv_list,
 			   u16 count, struct i40e_asq_cmd_details *cmd_details);
@@ -163,7 +163,7 @@ int
 i40e_aq_remove_macvlan_v2(struct i40e_hw *hw, u16 seid,
 			  struct i40e_aqc_remove_macvlan_element_data *mv_list,
 			  u16 count, struct i40e_asq_cmd_details *cmd_details,
-			  enum i40e_admin_queue_err *aq_status);
+			  enum libie_aq_err *aq_status);
 
 int i40e_aq_send_msg_to_vf(struct i40e_hw *hw, u16 vfid,
 			   u32 v_opcode, u32 v_retval, u8 *msg, u16 msglen,
@@ -339,7 +339,7 @@ int i40e_nvmupd_command(struct i40e_hw *hw,
 			struct i40e_nvm_access *cmd,
 			u8 *bytes, int *errno);
 void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode,
-				  struct i40e_aq_desc *desc);
+				  struct libie_aq_desc *desc);
 void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw);
 void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status);
 
diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h
index a09ed83835ff..ed8bbdb586da 100644
--- a/drivers/net/ethernet/intel/i40e/i40e_type.h
+++ b/drivers/net/ethernet/intel/i40e/i40e_type.h
@@ -24,7 +24,7 @@
 
 /* forward declaration */
 struct i40e_hw;
-typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct i40e_aq_desc *);
+typedef void (*I40E_ADMINQ_CALLBACK)(struct i40e_hw *, struct libie_aq_desc *);
 
 /* Data type manipulation macros. */
 
@@ -555,8 +555,8 @@ struct i40e_hw {
 
 	/* state of nvm update process */
 	enum i40e_nvmupd_state nvmupd_state;
-	struct i40e_aq_desc nvm_wb_desc;
-	struct i40e_aq_desc nvm_aq_event_desc;
+	struct libie_aq_desc nvm_wb_desc;
+	struct libie_aq_desc nvm_aq_event_desc;
 	struct i40e_virt_mem nvm_buff;
 	bool nvm_release_on_done;
 	u16 nvm_wait_opcode;
diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
index 3024f5dde384..143ce7e4aea2 100644
--- a/drivers/net/ethernet/intel/ice/ice_main.c
+++ b/drivers/net/ethernet/intel/ice/ice_main.c
@@ -7951,6 +7951,10 @@ const char *ice_aq_str(enum libie_aq_err aq_err)
 		return "ICE_AQ_RC_EBADMAN";
 	case LIBIE_AQ_RC_EBADBUF:
 		return "ICE_AQ_RC_EBADBUF";
+	case LIBIE_AQ_RC_EIO:
+		return "ICE_AQ_RC_EIO";
+	case LIBIE_AQ_RC_EACCES:
+		return "ICE_AQ_RC_EACCES";
 	}
 
 	return "ICE_AQ_RC_UNKNOWN";
diff --git a/include/linux/net/intel/libie/adminq.h b/include/linux/net/intel/libie/adminq.h
index b8079e7d842a..bab7cecc657f 100644
--- a/include/linux/net/intel/libie/adminq.h
+++ b/include/linux/net/intel/libie/adminq.h
@@ -145,17 +145,26 @@ struct libie_aqc_list_caps {
 LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps);
 
 /* Device/Function buffer entry, repeated per reported capability */
+#define LIBIE_AQC_CAPS_SWITCH_MODE			0x0001
+#define LIBIE_AQC_CAPS_MNG_MODE				0x0002
+#define LIBIE_AQC_CAPS_NPAR_ACTIVE			0x0003
+#define LIBIE_AQC_CAPS_OS2BMC_CAP			0x0004
 #define LIBIE_AQC_CAPS_VALID_FUNCTIONS			0x0005
 #define LIBIE_AQC_MAX_VALID_FUNCTIONS			0x8
 #define LIBIE_AQC_CAPS_SRIOV				0x0012
 #define LIBIE_AQC_CAPS_VF				0x0013
 #define LIBIE_AQC_CAPS_VMDQ				0x0014
+#define LIBIE_AQC_CAPS_8021QBG				0x0015
+#define LIBIE_AQC_CAPS_8021QBR				0x0016
 #define LIBIE_AQC_CAPS_VSI				0x0017
 #define LIBIE_AQC_CAPS_DCB				0x0018
+#define LIBIE_AQC_CAPS_FCOE				0x0021
+#define LIBIE_AQC_CAPS_ISCSI				0x0022
 #define LIBIE_AQC_CAPS_RSS				0x0040
 #define LIBIE_AQC_CAPS_RXQS				0x0041
 #define LIBIE_AQC_CAPS_TXQS				0x0042
 #define LIBIE_AQC_CAPS_MSIX				0x0043
+#define LIBIE_AQC_CAPS_VF_MSIX				0x0044
 #define LIBIE_AQC_CAPS_FD				0x0045
 #define LIBIE_AQC_CAPS_1588				0x0046
 #define LIBIE_AQC_CAPS_MAX_MTU				0x0047
@@ -166,6 +175,10 @@ LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps);
 #define LIBIE_AQC_CAPS_NET_VER				0x004C
 #define LIBIE_AQC_CAPS_PENDING_NET_VER			0x004D
 #define LIBIE_AQC_CAPS_RDMA				0x0051
+#define LIBIE_AQC_CAPS_LED				0x0061
+#define LIBIE_AQC_CAPS_SDP				0x0062
+#define LIBIE_AQC_CAPS_MDIO				0x0063
+#define LIBIE_AQC_CAPS_WSR_PROT				0x0064
 #define LIBIE_AQC_CAPS_SENSOR_READING			0x0067
 #define LIBIE_AQC_INLINE_IPSEC				0x0070
 #define LIBIE_AQC_CAPS_NUM_ENABLED_PORTS		0x0072
@@ -181,6 +194,8 @@ LIBIE_CHECK_STRUCT_LEN(16, libie_aqc_list_caps);
 #define LIBIE_AQC_CAPS_FW_LAG_SUPPORT			0x0092
 #define LIBIE_AQC_BIT_ROCEV2_LAG			0x01
 #define LIBIE_AQC_BIT_SRIOV_LAG				0x02
+#define LIBIE_AQC_CAPS_FLEX10				0x00F1
+#define LIBIE_AQC_CAPS_CEM				0x00F2
 
 /**
  * struct libie_aqc_list_caps_elem - Getting list of caps elements
@@ -266,8 +281,10 @@ enum libie_aq_err {
 	LIBIE_AQ_RC_EPERM	= 1,  /* Operation not permitted */
 	LIBIE_AQ_RC_ENOENT	= 2,  /* No such element */
 	LIBIE_AQ_RC_ESRCH	= 3,  /* Bad opcode */
+	LIBIE_AQ_RC_EIO		= 5,  /* I/O error */
 	LIBIE_AQ_RC_EAGAIN	= 8,  /* Try again */
 	LIBIE_AQ_RC_ENOMEM	= 9,  /* Out of memory */
+	LIBIE_AQ_RC_EACCES	= 10, /* Permission denied */
 	LIBIE_AQ_RC_EBUSY	= 12, /* Device or resource busy */
 	LIBIE_AQ_RC_EEXIST	= 13, /* Object already exists */
 	LIBIE_AQ_RC_EINVAL	= 14, /* Invalid argument */
-- 
cgit v1.2.3


From 5feaa7a07b85ebbef418ba4b80e4e0d23dc379f5 Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Fri, 25 Apr 2025 08:08:06 +0200
Subject: libie: add adminq helper for converting err to str

Add a new module for common handling of Admin Queue related logic.
Start by a helper for error to string conversion. This lives inside
libie/, but is a separate module what follows our logic of splitting
into topical modules, to avoid pulling in not needed stuff, and have
better organization in general.

Olek suggested how to better solve the error to string conversion.

It will be used in follow-up patches in ice, i40e and iavf.

Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Suggested-by: Alexander Lobakin <aleksander.lobakin@intel.com>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/libie/Kconfig  |  6 ++++
 drivers/net/ethernet/intel/libie/Makefile |  4 +++
 drivers/net/ethernet/intel/libie/adminq.c | 52 +++++++++++++++++++++++++++++++
 include/linux/net/intel/libie/adminq.h    |  2 ++
 4 files changed, 64 insertions(+)
 create mode 100644 drivers/net/ethernet/intel/libie/adminq.c

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/intel/libie/Kconfig b/drivers/net/ethernet/intel/libie/Kconfig
index 33aff6bc8f81..e6072758e3d8 100644
--- a/drivers/net/ethernet/intel/libie/Kconfig
+++ b/drivers/net/ethernet/intel/libie/Kconfig
@@ -8,3 +8,9 @@ config LIBIE
 	  libie (Intel Ethernet library) is a common library built on top of
 	  libeth and containing vendor-specific routines shared between several
 	  Intel Ethernet drivers.
+
+config LIBIE_ADMINQ
+	tristate
+	help
+	  Helper functions used by Intel Ethernet drivers for administration
+	  queue command interface (aka adminq).
diff --git a/drivers/net/ethernet/intel/libie/Makefile b/drivers/net/ethernet/intel/libie/Makefile
index ffd27fab916a..e98f00b865d3 100644
--- a/drivers/net/ethernet/intel/libie/Makefile
+++ b/drivers/net/ethernet/intel/libie/Makefile
@@ -4,3 +4,7 @@
 obj-$(CONFIG_LIBIE)	+= libie.o
 
 libie-y			:= rx.o
+
+obj-$(CONFIG_LIBIE_ADMINQ) 	+= libie_adminq.o
+
+libie_adminq-y			:= adminq.o
diff --git a/drivers/net/ethernet/intel/libie/adminq.c b/drivers/net/ethernet/intel/libie/adminq.c
new file mode 100644
index 000000000000..55356548e3f0
--- /dev/null
+++ b/drivers/net/ethernet/intel/libie/adminq.c
@@ -0,0 +1,52 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2025 Intel Corporation */
+
+#include <linux/module.h>
+#include <linux/net/intel/libie/adminq.h>
+
+static const char * const libie_aq_str_arr[] = {
+#define LIBIE_AQ_STR(x)					\
+	[LIBIE_AQ_RC_##x]	= "LIBIE_AQ_RC" #x
+	LIBIE_AQ_STR(OK),
+	LIBIE_AQ_STR(EPERM),
+	LIBIE_AQ_STR(ENOENT),
+	LIBIE_AQ_STR(ESRCH),
+	LIBIE_AQ_STR(EIO),
+	LIBIE_AQ_STR(EAGAIN),
+	LIBIE_AQ_STR(ENOMEM),
+	LIBIE_AQ_STR(EACCES),
+	LIBIE_AQ_STR(EBUSY),
+	LIBIE_AQ_STR(EEXIST),
+	LIBIE_AQ_STR(EINVAL),
+	LIBIE_AQ_STR(ENOSPC),
+	LIBIE_AQ_STR(ENOSYS),
+	LIBIE_AQ_STR(EMODE),
+	LIBIE_AQ_STR(ENOSEC),
+	LIBIE_AQ_STR(EBADSIG),
+	LIBIE_AQ_STR(ESVN),
+	LIBIE_AQ_STR(EBADMAN),
+	LIBIE_AQ_STR(EBADBUF),
+#undef LIBIE_AQ_STR
+	"LIBIE_AQ_RC_UNKNOWN",
+};
+
+#define __LIBIE_AQ_STR_NUM (ARRAY_SIZE(libie_aq_str_arr) - 1)
+
+/**
+ * libie_aq_str - get error string based on aq error
+ * @err: admin queue error type
+ *
+ * Return: error string for passed error code
+ */
+const char *libie_aq_str(enum libie_aq_err err)
+{
+	if (err >= ARRAY_SIZE(libie_aq_str_arr) ||
+	    !libie_aq_str_arr[err])
+		err = __LIBIE_AQ_STR_NUM;
+
+	return libie_aq_str_arr[err];
+}
+EXPORT_SYMBOL_NS_GPL(libie_aq_str, "LIBIE_ADMINQ");
+
+MODULE_DESCRIPTION("Intel(R) Ethernet common library - adminq helpers");
+MODULE_LICENSE("GPL");
diff --git a/include/linux/net/intel/libie/adminq.h b/include/linux/net/intel/libie/adminq.h
index bab7cecc657f..012b5d499c1a 100644
--- a/include/linux/net/intel/libie/adminq.h
+++ b/include/linux/net/intel/libie/adminq.h
@@ -303,4 +303,6 @@ static inline void *libie_aq_raw(struct libie_aq_desc *desc)
 	return &desc->params.raw;
 }
 
+const char *libie_aq_str(enum libie_aq_err err);
+
 #endif /* __LIBIE_ADMINQ_H */
-- 
cgit v1.2.3


From ca7be9c0a148cbfe38df95a0285339c532ca6e17 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Sun, 8 Jun 2025 17:15:35 +0100
Subject: mtd: ubi: Remove unused ubi_flush

ubi_flush() was added in 2012 as part of
commit 62f384552b67 ("UBI: modify ubi_wl_flush function to clear work queue
for a lnum")
but has remained unused.

(It's friend ubi_wl_flush() is still used)

Remove it.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Signed-off-by: Richard Weinberger <richard@nod.at>
---
 drivers/mtd/ubi/kapi.c  | 27 ---------------------------
 include/linux/mtd/ubi.h |  1 -
 2 files changed, 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/ubi/kapi.c b/drivers/mtd/ubi/kapi.c
index f1ea8677467f..df0a5a57b072 100644
--- a/drivers/mtd/ubi/kapi.c
+++ b/drivers/mtd/ubi/kapi.c
@@ -791,33 +791,6 @@ int ubi_sync(int ubi_num)
 }
 EXPORT_SYMBOL_GPL(ubi_sync);
 
-/**
- * ubi_flush - flush UBI work queue.
- * @ubi_num: UBI device to flush work queue
- * @vol_id: volume id to flush for
- * @lnum: logical eraseblock number to flush for
- *
- * This function executes all pending works for a particular volume id / logical
- * eraseblock number pair. If either value is set to %UBI_ALL, then it acts as
- * a wildcard for all of the corresponding volume numbers or logical
- * eraseblock numbers. It returns zero in case of success and a negative error
- * code in case of failure.
- */
-int ubi_flush(int ubi_num, int vol_id, int lnum)
-{
-	struct ubi_device *ubi;
-	int err = 0;
-
-	ubi = ubi_get_device(ubi_num);
-	if (!ubi)
-		return -ENODEV;
-
-	err = ubi_wl_flush(ubi, vol_id, lnum);
-	ubi_put_device(ubi);
-	return err;
-}
-EXPORT_SYMBOL_GPL(ubi_flush);
-
 BLOCKING_NOTIFIER_HEAD(ubi_notifiers);
 
 /**
diff --git a/include/linux/mtd/ubi.h b/include/linux/mtd/ubi.h
index 562f92504f2b..c3f79c4be1cc 100644
--- a/include/linux/mtd/ubi.h
+++ b/include/linux/mtd/ubi.h
@@ -250,7 +250,6 @@ int ubi_leb_unmap(struct ubi_volume_desc *desc, int lnum);
 int ubi_leb_map(struct ubi_volume_desc *desc, int lnum);
 int ubi_is_mapped(struct ubi_volume_desc *desc, int lnum);
 int ubi_sync(int ubi_num);
-int ubi_flush(int ubi_num, int vol_id, int lnum);
 
 /*
  * This function is the same as the 'ubi_leb_read()' function, but it does not
-- 
cgit v1.2.3


From 1c3b002c6bf684b445a7107609979bca5f21bc03 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Thu, 10 Jul 2025 15:13:49 -0400
Subject: PCI: endpoint: Add RC-to-EP doorbell support using platform MSI
 controller

Implement the doorbell feature by mapping the EP's MSI interrupt controller
message address to a dedicated BAR.

The EPF driver should pass the actual message data to be written to the
message address by the host through implementation-specific logic.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
[mani: minor code cleanups and reworded commit message]
Signed-off-by: Manivannan Sadhasivam <mani@kernel.org>
[bhelgaas: fix kernel-doc]
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Niklas Cassel <cassel@kernel.org>
Link: https://patch.msgid.link/20250710-ep-msi-v21-3-57683fc7fb25@nxp.com
---
 drivers/pci/endpoint/Kconfig      |  8 ++++
 drivers/pci/endpoint/Makefile     |  1 +
 drivers/pci/endpoint/pci-ep-msi.c | 92 +++++++++++++++++++++++++++++++++++++++
 include/linux/pci-ep-msi.h        | 28 ++++++++++++
 include/linux/pci-epf.h           | 15 +++++++
 5 files changed, 144 insertions(+)
 create mode 100644 drivers/pci/endpoint/pci-ep-msi.c
 create mode 100644 include/linux/pci-ep-msi.h

(limited to 'include/linux')

diff --git a/drivers/pci/endpoint/Kconfig b/drivers/pci/endpoint/Kconfig
index 1c5d82eb57d4..8dad291be8b8 100644
--- a/drivers/pci/endpoint/Kconfig
+++ b/drivers/pci/endpoint/Kconfig
@@ -28,6 +28,14 @@ config PCI_ENDPOINT_CONFIGFS
 	   configure the endpoint function and used to bind the
 	   function with an endpoint controller.
 
+config PCI_ENDPOINT_MSI_DOORBELL
+	bool "PCI Endpoint MSI Doorbell Support"
+	depends on PCI_ENDPOINT && GENERIC_MSI_IRQ
+	help
+	  This enables the EP's MSI interrupt controller to function as a
+	  doorbell. The RC can trigger doorbell in EP by writing data to a
+	  dedicated BAR, which the EP maps to the controller's message address.
+
 source "drivers/pci/endpoint/functions/Kconfig"
 
 endmenu
diff --git a/drivers/pci/endpoint/Makefile b/drivers/pci/endpoint/Makefile
index 95b2fe47e3b0..b4869d52053a 100644
--- a/drivers/pci/endpoint/Makefile
+++ b/drivers/pci/endpoint/Makefile
@@ -6,3 +6,4 @@
 obj-$(CONFIG_PCI_ENDPOINT_CONFIGFS)	+= pci-ep-cfs.o
 obj-$(CONFIG_PCI_ENDPOINT)		+= pci-epc-core.o pci-epf-core.o\
 					   pci-epc-mem.o functions/
+obj-$(CONFIG_PCI_ENDPOINT_MSI_DOORBELL)	+= pci-ep-msi.o
diff --git a/drivers/pci/endpoint/pci-ep-msi.c b/drivers/pci/endpoint/pci-ep-msi.c
new file mode 100644
index 000000000000..95a47ce155ac
--- /dev/null
+++ b/drivers/pci/endpoint/pci-ep-msi.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * PCI Endpoint *Controller* (EPC) MSI library
+ *
+ * Copyright (C) 2025 NXP
+ * Author: Frank Li <Frank.Li@nxp.com>
+ */
+
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/irqdomain.h>
+#include <linux/module.h>
+#include <linux/msi.h>
+#include <linux/of_irq.h>
+#include <linux/pci-epc.h>
+#include <linux/pci-epf.h>
+#include <linux/pci-ep-cfs.h>
+#include <linux/pci-ep-msi.h>
+#include <linux/slab.h>
+
+static void pci_epf_write_msi_msg(struct msi_desc *desc, struct msi_msg *msg)
+{
+	struct pci_epc *epc;
+	struct pci_epf *epf;
+
+	epc = pci_epc_get(dev_name(msi_desc_to_dev(desc)));
+	if (!epc)
+		return;
+
+	epf = list_first_entry_or_null(&epc->pci_epf, struct pci_epf, list);
+
+	if (epf && epf->db_msg && desc->msi_index < epf->num_db)
+		memcpy(&epf->db_msg[desc->msi_index].msg, msg, sizeof(*msg));
+
+	pci_epc_put(epc);
+}
+
+int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 num_db)
+{
+	struct pci_epc *epc = epf->epc;
+	struct device *dev = &epf->dev;
+	struct irq_domain *domain;
+	void *msg;
+	int ret;
+	int i;
+
+	/* TODO: Multi-EPF support */
+	if (list_first_entry_or_null(&epc->pci_epf, struct pci_epf, list) != epf) {
+		dev_err(dev, "MSI doorbell doesn't support multiple EPF\n");
+		return -EINVAL;
+	}
+
+	domain = of_msi_map_get_device_domain(epc->dev.parent, 0,
+					      DOMAIN_BUS_PLATFORM_MSI);
+	if (!domain) {
+		dev_err(dev, "Can't find MSI domain for EPC\n");
+		return -ENODEV;
+	}
+
+	dev_set_msi_domain(epc->dev.parent, domain);
+
+	msg = kcalloc(num_db, sizeof(struct pci_epf_doorbell_msg), GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	epf->num_db = num_db;
+	epf->db_msg = msg;
+
+	ret = platform_device_msi_init_and_alloc_irqs(epc->dev.parent, num_db,
+						      pci_epf_write_msi_msg);
+	if (ret) {
+		dev_err(dev, "Failed to allocate MSI\n");
+		kfree(msg);
+		return ret;
+	}
+
+	for (i = 0; i < num_db; i++)
+		epf->db_msg[i].virq = msi_get_virq(epc->dev.parent, i);
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(pci_epf_alloc_doorbell);
+
+void pci_epf_free_doorbell(struct pci_epf *epf)
+{
+	platform_device_msi_free_irqs_all(epf->epc->dev.parent);
+
+	kfree(epf->db_msg);
+	epf->db_msg = NULL;
+	epf->num_db = 0;
+}
+EXPORT_SYMBOL_GPL(pci_epf_free_doorbell);
diff --git a/include/linux/pci-ep-msi.h b/include/linux/pci-ep-msi.h
new file mode 100644
index 000000000000..7c5db90f9620
--- /dev/null
+++ b/include/linux/pci-ep-msi.h
@@ -0,0 +1,28 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * PCI Endpoint *Function* side MSI header file
+ *
+ * Copyright (C) 2024 NXP
+ * Author: Frank Li <Frank.Li@nxp.com>
+ */
+
+#ifndef __PCI_EP_MSI__
+#define __PCI_EP_MSI__
+
+struct pci_epf;
+
+#ifdef CONFIG_PCI_ENDPOINT_MSI_DOORBELL
+int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 nums);
+void pci_epf_free_doorbell(struct pci_epf *epf);
+#else
+static inline int pci_epf_alloc_doorbell(struct pci_epf *epf, u16 nums)
+{
+	return -ENODATA;
+}
+
+static inline void pci_epf_free_doorbell(struct pci_epf *epf)
+{
+}
+#endif /* CONFIG_GENERIC_MSI_IRQ */
+
+#endif /* __PCI_EP_MSI__ */
diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 749cee0bcf2c..52e07602f08e 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -12,6 +12,7 @@
 #include <linux/configfs.h>
 #include <linux/device.h>
 #include <linux/mod_devicetable.h>
+#include <linux/msi.h>
 #include <linux/pci.h>
 
 struct pci_epf;
@@ -128,6 +129,16 @@ struct pci_epf_bar {
 	int		flags;
 };
 
+/**
+ * struct pci_epf_doorbell_msg - represents doorbell message
+ * @msg: MSI message
+ * @virq: IRQ number of this doorbell MSI message
+ */
+struct pci_epf_doorbell_msg {
+	struct msi_msg msg;
+	int virq;
+};
+
 /**
  * struct pci_epf - represents the PCI EPF device
  * @dev: the PCI EPF device
@@ -155,6 +166,8 @@ struct pci_epf_bar {
  * @vfunction_num_map: bitmap to manage virtual function number
  * @pci_vepf: list of virtual endpoint functions associated with this function
  * @event_ops: callbacks for capturing the EPC events
+ * @db_msg: data for MSI from RC side
+ * @num_db: number of doorbells
  */
 struct pci_epf {
 	struct device		dev;
@@ -185,6 +198,8 @@ struct pci_epf {
 	unsigned long		vfunction_num_map;
 	struct list_head	pci_vepf;
 	const struct pci_epc_event_ops *event_ops;
+	struct pci_epf_doorbell_msg *db_msg;
+	u16 num_db;
 };
 
 /**
-- 
cgit v1.2.3


From 4ff4252a2355f585c5cad8dc959ff1097300aa47 Mon Sep 17 00:00:00 2001
From: Frank Li <Frank.Li@nxp.com>
Date: Thu, 10 Jul 2025 15:13:51 -0400
Subject: PCI: endpoint: Add pci_epf_align_inbound_addr() helper for inbound
 address alignment

Add pci_epf_align_inbound_addr() to align the inbound addresses according
to PCI BAR alignment requirements. The aligned base address and offset are
returned via 'base' and 'off' parameters.

Signed-off-by: Frank Li <Frank.Li@nxp.com>
[mani: reworded kernel-doc and commit message]
Signed-off-by: Manivannan Sadhasivam <mani@kernel.org>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Tested-by: Niklas Cassel <cassel@kernel.org>
Link: https://patch.msgid.link/20250710-ep-msi-v21-5-57683fc7fb25@nxp.com
---
 drivers/pci/endpoint/pci-epf-core.c | 38 +++++++++++++++++++++++++++++++++++++
 include/linux/pci-epf.h             |  3 +++
 2 files changed, 41 insertions(+)

(limited to 'include/linux')

diff --git a/drivers/pci/endpoint/pci-epf-core.c b/drivers/pci/endpoint/pci-epf-core.c
index 577a9e490115..09b90e1631d5 100644
--- a/drivers/pci/endpoint/pci-epf-core.c
+++ b/drivers/pci/endpoint/pci-epf-core.c
@@ -477,6 +477,44 @@ struct pci_epf *pci_epf_create(const char *name)
 }
 EXPORT_SYMBOL_GPL(pci_epf_create);
 
+/**
+ * pci_epf_align_inbound_addr() - Align the given address based on the BAR
+ *				  alignment requirement
+ * @epf: the EPF device
+ * @addr: inbound address to be aligned
+ * @bar: the BAR number corresponding to the given addr
+ * @base: base address matching the @bar alignment requirement
+ * @off: offset to be added to the @base address
+ *
+ * Helper function to align input @addr based on BAR's alignment requirement.
+ * The aligned base address and offset are returned via @base and @off.
+ *
+ * NOTE: The pci_epf_alloc_space() function already accounts for alignment.
+ * This API is primarily intended for use with other memory regions not
+ * allocated by pci_epf_alloc_space(), such as peripheral register spaces or
+ * the message address of a platform MSI controller.
+ *
+ * Return: 0 on success, errno otherwise.
+ */
+int pci_epf_align_inbound_addr(struct pci_epf *epf, enum pci_barno bar,
+			       u64 addr, dma_addr_t *base, size_t *off)
+{
+	/*
+	 * Most EP controllers require the BAR start address to be aligned to
+	 * the BAR size, because they mask off the lower bits.
+	 *
+	 * Alignment to BAR size also works for controllers that support
+	 * unaligned addresses.
+	 */
+	u64 align = epf->bar[bar].size;
+
+	*base = round_down(addr, align);
+	*off = addr & (align - 1);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(pci_epf_align_inbound_addr);
+
 static void pci_epf_dev_release(struct device *dev)
 {
 	struct pci_epf *epf = to_pci_epf(dev);
diff --git a/include/linux/pci-epf.h b/include/linux/pci-epf.h
index 52e07602f08e..2e85504ba2ba 100644
--- a/include/linux/pci-epf.h
+++ b/include/linux/pci-epf.h
@@ -241,6 +241,9 @@ void *pci_epf_alloc_space(struct pci_epf *epf, size_t size, enum pci_barno bar,
 			  enum pci_epc_interface_type type);
 void pci_epf_free_space(struct pci_epf *epf, void *addr, enum pci_barno bar,
 			enum pci_epc_interface_type type);
+
+int pci_epf_align_inbound_addr(struct pci_epf *epf, enum pci_barno bar,
+			       u64 addr, dma_addr_t *base, size_t *off);
 int pci_epf_bind(struct pci_epf *epf);
 void pci_epf_unbind(struct pci_epf *epf);
 int pci_epf_add_vepf(struct pci_epf *epf_pf, struct pci_epf *epf_vf);
-- 
cgit v1.2.3


From 8245d47cfaba8a38337a447230b4d01f9946f5e1 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 23 Jul 2025 22:50:26 -0700
Subject: x86: Handle KCOV __init vs inline mismatches

GCC appears to have kind of fragile inlining heuristics, in the
sense that it can change whether or not it inlines something based on
optimizations. It looks like the kcov instrumentation being added (or in
this case, removed) from a function changes the optimization results,
and some functions marked "inline" are _not_ inlined. In that case,
we end up with __init code calling a function not marked __init, and we
get the build warnings I'm trying to eliminate in the coming patch that
adds __no_sanitize_coverage to __init functions:

WARNING: modpost: vmlinux: section mismatch in reference: xbc_exit+0x8 (section: .text.unlikely) -> _xbc_exit (section: .init.text)
WARNING: modpost: vmlinux: section mismatch in reference: real_mode_size_needed+0x15 (section: .text.unlikely) -> real_mode_blob_end (section: .init.data)
WARNING: modpost: vmlinux: section mismatch in reference: __set_percpu_decrypted+0x16 (section: .text.unlikely) -> early_set_memory_decrypted (section: .init.text)
WARNING: modpost: vmlinux: section mismatch in reference: memblock_alloc_from+0x26 (section: .text.unlikely) -> memblock_alloc_try_nid (section: .init.text)
WARNING: modpost: vmlinux: section mismatch in reference: acpi_arch_set_root_pointer+0xc (section: .text.unlikely) -> x86_init (section: .init.data)
WARNING: modpost: vmlinux: section mismatch in reference: acpi_arch_get_root_pointer+0x8 (section: .text.unlikely) -> x86_init (section: .init.data)
WARNING: modpost: vmlinux: section mismatch in reference: efi_config_table_is_usable+0x16 (section: .text.unlikely) -> xen_efi_config_table_is_usable (section: .init.text)

This problem is somewhat fragile (though using either __always_inline
or __init will deterministically solve it), but we've tripped over
this before with GCC and the solution has usually been to just use
__always_inline and move on.

For x86 this means forcing several functions to be inline with
__always_inline.

Link: https://lore.kernel.org/r/20250724055029.3623499-2-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 arch/x86/include/asm/acpi.h     | 4 ++--
 arch/x86/include/asm/realmode.h | 2 +-
 arch/x86/kernel/kvm.c           | 2 +-
 arch/x86/mm/init_64.c           | 2 +-
 include/linux/acpi.h            | 4 ++--
 include/linux/bootconfig.h      | 2 +-
 include/linux/efi.h             | 2 +-
 include/linux/memblock.h        | 2 +-
 include/linux/smp.h             | 2 +-
 kernel/kexec_handover.c         | 4 ++--
 10 files changed, 13 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
index 5ab1a4598d00..a03aa6f999d1 100644
--- a/arch/x86/include/asm/acpi.h
+++ b/arch/x86/include/asm/acpi.h
@@ -158,13 +158,13 @@ static inline bool acpi_has_cpu_in_madt(void)
 }
 
 #define ACPI_HAVE_ARCH_SET_ROOT_POINTER
-static inline void acpi_arch_set_root_pointer(u64 addr)
+static __always_inline void acpi_arch_set_root_pointer(u64 addr)
 {
 	x86_init.acpi.set_root_pointer(addr);
 }
 
 #define ACPI_HAVE_ARCH_GET_ROOT_POINTER
-static inline u64 acpi_arch_get_root_pointer(void)
+static __always_inline u64 acpi_arch_get_root_pointer(void)
 {
 	return x86_init.acpi.get_root_pointer();
 }
diff --git a/arch/x86/include/asm/realmode.h b/arch/x86/include/asm/realmode.h
index f607081a022a..e406a1e92c63 100644
--- a/arch/x86/include/asm/realmode.h
+++ b/arch/x86/include/asm/realmode.h
@@ -78,7 +78,7 @@ extern unsigned char secondary_startup_64[];
 extern unsigned char secondary_startup_64_no_verify[];
 #endif
 
-static inline size_t real_mode_size_needed(void)
+static __always_inline size_t real_mode_size_needed(void)
 {
 	if (real_mode_header)
 		return 0;	/* already allocated. */
diff --git a/arch/x86/kernel/kvm.c b/arch/x86/kernel/kvm.c
index 921c1c783bc1..8ae750cde0c6 100644
--- a/arch/x86/kernel/kvm.c
+++ b/arch/x86/kernel/kvm.c
@@ -420,7 +420,7 @@ static u64 kvm_steal_clock(int cpu)
 	return steal;
 }
 
-static inline void __set_percpu_decrypted(void *ptr, unsigned long size)
+static inline __init void __set_percpu_decrypted(void *ptr, unsigned long size)
 {
 	early_set_memory_decrypted((unsigned long) ptr, size);
 }
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index ee66fae9ebcc..c02029cd27e1 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -806,7 +806,7 @@ kernel_physical_mapping_change(unsigned long paddr_start,
 }
 
 #ifndef CONFIG_NUMA
-static inline void x86_numa_init(void)
+static __always_inline void x86_numa_init(void)
 {
 	memblock_set_node(0, PHYS_ADDR_MAX, &memblock.memory, 0);
 }
diff --git a/include/linux/acpi.h b/include/linux/acpi.h
index f102c0fe3431..fc7f5e039074 100644
--- a/include/linux/acpi.h
+++ b/include/linux/acpi.h
@@ -759,13 +759,13 @@ int acpi_arch_timer_mem_init(struct arch_timer_mem *timer_mem, int *timer_count)
 #endif
 
 #ifndef ACPI_HAVE_ARCH_SET_ROOT_POINTER
-static inline void acpi_arch_set_root_pointer(u64 addr)
+static __always_inline void acpi_arch_set_root_pointer(u64 addr)
 {
 }
 #endif
 
 #ifndef ACPI_HAVE_ARCH_GET_ROOT_POINTER
-static inline u64 acpi_arch_get_root_pointer(void)
+static __always_inline u64 acpi_arch_get_root_pointer(void)
 {
 	return 0;
 }
diff --git a/include/linux/bootconfig.h b/include/linux/bootconfig.h
index 3f4b4ac527ca..25df9260d206 100644
--- a/include/linux/bootconfig.h
+++ b/include/linux/bootconfig.h
@@ -290,7 +290,7 @@ int __init xbc_get_info(int *node_size, size_t *data_size);
 /* XBC cleanup data structures */
 void __init _xbc_exit(bool early);
 
-static inline void xbc_exit(void)
+static __always_inline void xbc_exit(void)
 {
 	_xbc_exit(false);
 }
diff --git a/include/linux/efi.h b/include/linux/efi.h
index 7d63d1d75f22..e3776d9cad07 100644
--- a/include/linux/efi.h
+++ b/include/linux/efi.h
@@ -1334,7 +1334,7 @@ struct linux_efi_initrd {
 
 bool xen_efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table);
 
-static inline
+static __always_inline
 bool efi_config_table_is_usable(const efi_guid_t *guid, unsigned long table)
 {
 	if (!IS_ENABLED(CONFIG_XEN_EFI))
diff --git a/include/linux/memblock.h b/include/linux/memblock.h
index bb19a2534224..b96746376e17 100644
--- a/include/linux/memblock.h
+++ b/include/linux/memblock.h
@@ -463,7 +463,7 @@ static inline void *memblock_alloc_raw(phys_addr_t size,
 					  NUMA_NO_NODE);
 }
 
-static inline void *memblock_alloc_from(phys_addr_t size,
+static __always_inline void *memblock_alloc_from(phys_addr_t size,
 						phys_addr_t align,
 						phys_addr_t min_addr)
 {
diff --git a/include/linux/smp.h b/include/linux/smp.h
index f1aa0952e8c3..84e948eb1c20 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -221,7 +221,7 @@ static inline void wake_up_all_idle_cpus(void) {  }
 
 #ifdef CONFIG_UP_LATE_INIT
 extern void __init up_late_init(void);
-static inline void smp_init(void) { up_late_init(); }
+static __always_inline void smp_init(void) { up_late_init(); }
 #else
 static inline void smp_init(void) { }
 #endif
diff --git a/kernel/kexec_handover.c b/kernel/kexec_handover.c
index 69b953551677..f3f6bfe43d47 100644
--- a/kernel/kexec_handover.c
+++ b/kernel/kexec_handover.c
@@ -305,8 +305,8 @@ err_free:
 	return -ENOMEM;
 }
 
-static void deserialize_bitmap(unsigned int order,
-			       struct khoser_mem_bitmap_ptr *elm)
+static void __init deserialize_bitmap(unsigned int order,
+				      struct khoser_mem_bitmap_ptr *elm)
 {
 	struct kho_mem_phys_bits *bitmap = KHOSER_LOAD_PTR(elm->bitmap);
 	unsigned long bit;
-- 
cgit v1.2.3


From 0dec7201788b9152f06321d0dab46eed93834cda Mon Sep 17 00:00:00 2001
From: Stephen Rothwell <sfr@canb.auug.org.au>
Date: Mon, 21 Jul 2025 16:15:57 +1000
Subject: sprintf.h requires stdarg.h

In file included from drivers/crypto/intel/qat/qat_common/adf_pm_dbgfs_utils.c:4:
include/linux/sprintf.h:11:54: error: unknown type name 'va_list'
   11 | __printf(2, 0) int vsprintf(char *buf, const char *, va_list);
      |                                                      ^~~~~~~
include/linux/sprintf.h:1:1: note: 'va_list' is defined in header '<stdarg.h>'; this is probably fixable by adding '#include <stdarg.h>'

Link: https://lkml.kernel.org/r/20250721173754.42865913@canb.auug.org.au
Fixes: 39ced19b9e60 ("lib/vsprintf: split out sprintf() and friends")
Signed-off-by: Stephen Rothwell <sfr@canb.auug.org.au>
Cc: Andriy Shevchenko <andriy.shevchenko@linux.intel.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/sprintf.h | 1 +
 1 file changed, 1 insertion(+)

(limited to 'include/linux')

diff --git a/include/linux/sprintf.h b/include/linux/sprintf.h
index 51cab2def9ec..876130091384 100644
--- a/include/linux/sprintf.h
+++ b/include/linux/sprintf.h
@@ -4,6 +4,7 @@
 
 #include <linux/compiler_attributes.h>
 #include <linux/types.h>
+#include <linux/stdarg.h>
 
 int num_to_str(char *buf, int size, unsigned long long num, unsigned int width);
 
-- 
cgit v1.2.3


From 78afdadafe6fe0c74c08fda156e7be0a0b402b90 Mon Sep 17 00:00:00 2001
From: Samiullah Khawaja <skhawaja@google.com>
Date: Wed, 23 Jul 2025 01:30:30 +0000
Subject: net: Use netif_threaded_enable instead of netif_set_threaded in
 drivers

Prepare for adding an enum type for NAPI threaded states by adding
netif_threaded_enable API. De-export the existing netif_set_threaded API
and only use it internally. Update existing drivers to use
netif_threaded_enable instead of the de-exported netif_set_threaded.

Note that dev_set_threaded used by mt76 debugfs file is unchanged.

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Link: https://patch.msgid.link/20250723013031.2911384-3-skhawaja@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/atheros/atl1c/atl1c_main.c |  2 +-
 drivers/net/ethernet/mellanox/mlxsw/pci.c       |  2 +-
 drivers/net/ethernet/renesas/ravb_main.c        |  2 +-
 drivers/net/wireguard/device.c                  |  2 +-
 drivers/net/wireless/ath/ath10k/snoc.c          |  2 +-
 include/linux/netdevice.h                       |  2 +-
 net/core/dev.c                                  | 18 +++++++++++++++++-
 net/core/dev.h                                  |  2 ++
 8 files changed, 25 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
index 3a9ad4a9c1cb..7efa3fc257b3 100644
--- a/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
+++ b/drivers/net/ethernet/atheros/atl1c/atl1c_main.c
@@ -2688,7 +2688,7 @@ static int atl1c_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	adapter->mii.mdio_write = atl1c_mdio_write;
 	adapter->mii.phy_id_mask = 0x1f;
 	adapter->mii.reg_num_mask = MDIO_CTRL_REG_MASK;
-	netif_set_threaded(netdev, true);
+	netif_threaded_enable(netdev);
 	for (i = 0; i < adapter->rx_queue_count; ++i)
 		netif_napi_add(netdev, &adapter->rrd_ring[i].napi,
 			       atl1c_clean_rx);
diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
index a2e97b712a3d..8769cba2c746 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
@@ -156,7 +156,7 @@ static int mlxsw_pci_napi_devs_init(struct mlxsw_pci *mlxsw_pci)
 	}
 	strscpy(mlxsw_pci->napi_dev_rx->name, "mlxsw_rx",
 		sizeof(mlxsw_pci->napi_dev_rx->name));
-	netif_set_threaded(mlxsw_pci->napi_dev_rx, true);
+	netif_threaded_enable(mlxsw_pci->napi_dev_rx);
 
 	return 0;
 
diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
index 4e79bf88688a..94b6fb94f8f1 100644
--- a/drivers/net/ethernet/renesas/ravb_main.c
+++ b/drivers/net/ethernet/renesas/ravb_main.c
@@ -3075,7 +3075,7 @@ static int ravb_probe(struct platform_device *pdev)
 	if (info->coalesce_irqs) {
 		netdev_sw_irq_coalesce_default_on(ndev);
 		if (num_present_cpus() == 1)
-			netif_set_threaded(ndev, true);
+			netif_threaded_enable(ndev);
 	}
 
 	/* Network device register */
diff --git a/drivers/net/wireguard/device.c b/drivers/net/wireguard/device.c
index 5afec5a865f4..813bd10d3dc7 100644
--- a/drivers/net/wireguard/device.c
+++ b/drivers/net/wireguard/device.c
@@ -366,7 +366,7 @@ static int wg_newlink(struct net_device *dev,
 	if (ret < 0)
 		goto err_free_handshake_queue;
 
-	netif_set_threaded(dev, true);
+	netif_threaded_enable(dev);
 	ret = register_netdevice(dev);
 	if (ret < 0)
 		goto err_uninit_ratelimiter;
diff --git a/drivers/net/wireless/ath/ath10k/snoc.c b/drivers/net/wireless/ath/ath10k/snoc.c
index 0ee68d3dad12..f0713bd36173 100644
--- a/drivers/net/wireless/ath/ath10k/snoc.c
+++ b/drivers/net/wireless/ath/ath10k/snoc.c
@@ -936,7 +936,7 @@ static int ath10k_snoc_hif_start(struct ath10k *ar)
 
 	bitmap_clear(ar_snoc->pending_ce_irqs, 0, CE_COUNT_MAX);
 
-	netif_set_threaded(ar->napi_dev, true);
+	netif_threaded_enable(ar->napi_dev);
 	ath10k_core_napi_enable(ar);
 	/* IRQs are left enabled when we restart due to a firmware crash */
 	if (!test_bit(ATH10K_SNOC_FLAG_RECOVERY, &ar_snoc->flags))
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 5aee8d3895f4..a97c9a337d6b 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -589,7 +589,7 @@ static inline bool napi_complete(struct napi_struct *n)
 	return napi_complete_done(n, 0);
 }
 
-int netif_set_threaded(struct net_device *dev, bool threaded);
+void netif_threaded_enable(struct net_device *dev);
 int dev_set_threaded(struct net_device *dev, bool threaded);
 
 void napi_disable(struct napi_struct *n);
diff --git a/net/core/dev.c b/net/core/dev.c
index 76384b8a7871..f28661d6f5ea 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -7029,7 +7029,23 @@ int netif_set_threaded(struct net_device *dev, bool threaded)
 
 	return err;
 }
-EXPORT_SYMBOL(netif_set_threaded);
+
+/**
+ * netif_threaded_enable() - enable threaded NAPIs
+ * @dev: net_device instance
+ *
+ * Enable threaded mode for the NAPI instances of the device. This may be useful
+ * for devices where multiple NAPI instances get scheduled by a single
+ * interrupt. Threaded NAPI allows moving the NAPI processing to cores other
+ * than the core where IRQ is mapped.
+ *
+ * This function should be called before @dev is registered.
+ */
+void netif_threaded_enable(struct net_device *dev)
+{
+	WARN_ON_ONCE(netif_set_threaded(dev, true));
+}
+EXPORT_SYMBOL(netif_threaded_enable);
 
 /**
  * netif_queue_set_napi - Associate queue with the napi
diff --git a/net/core/dev.h b/net/core/dev.h
index a603387fb566..f5b567310908 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -322,6 +322,8 @@ static inline bool napi_get_threaded(struct napi_struct *n)
 
 int napi_set_threaded(struct napi_struct *n, bool threaded);
 
+int netif_set_threaded(struct net_device *dev, bool threaded);
+
 int rps_cpumask_housekeeping(struct cpumask *mask);
 
 #if defined(CONFIG_DEBUG_NET) && defined(CONFIG_BPF_SYSCALL)
-- 
cgit v1.2.3


From 8e7583a4f65f3dbf3e8deb4e60f3679c276bef62 Mon Sep 17 00:00:00 2001
From: Samiullah Khawaja <skhawaja@google.com>
Date: Wed, 23 Jul 2025 01:30:31 +0000
Subject: net: define an enum for the napi threaded state

Instead of using '0' and '1' for napi threaded state use an enum with
'disabled' and 'enabled' states.

Tested:
 ./tools/testing/selftests/net/nl_netdev.py
 TAP version 13
 1..7
 ok 1 nl_netdev.empty_check
 ok 2 nl_netdev.lo_check
 ok 3 nl_netdev.page_pool_check
 ok 4 nl_netdev.napi_list_check
 ok 5 nl_netdev.dev_set_threaded
 ok 6 nl_netdev.napi_set_threaded
 ok 7 nl_netdev.nsim_rxq_reset_down
 # Totals: pass:7 fail:0 xfail:0 xpass:0 skip:0 error:0

Signed-off-by: Samiullah Khawaja <skhawaja@google.com>
Link: https://patch.msgid.link/20250723013031.2911384-4-skhawaja@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/netlink/specs/netdev.yaml            | 13 +++++---
 .../networking/net_cachelines/net_device.rst       |  2 +-
 include/linux/netdevice.h                          | 10 +++---
 include/uapi/linux/netdev.h                        |  5 +++
 net/core/dev.c                                     | 12 +++++---
 net/core/dev.h                                     | 13 +++++---
 net/core/dev_api.c                                 |  3 +-
 net/core/netdev-genl-gen.c                         |  2 +-
 net/core/netdev-genl.c                             |  2 +-
 tools/include/uapi/linux/netdev.h                  |  5 +++
 tools/testing/selftests/net/nl_netdev.py           | 36 +++++++++++-----------
 11 files changed, 62 insertions(+), 41 deletions(-)

(limited to 'include/linux')

diff --git a/Documentation/netlink/specs/netdev.yaml b/Documentation/netlink/specs/netdev.yaml
index 85d0ea6ac426..c035dc0f64fd 100644
--- a/Documentation/netlink/specs/netdev.yaml
+++ b/Documentation/netlink/specs/netdev.yaml
@@ -85,6 +85,10 @@ definitions:
     name: qstats-scope
     type: flags
     entries: [queue]
+  -
+    name: napi-threaded
+    type: enum
+    entries: [disabled, enabled]
 
 attribute-sets:
   -
@@ -286,11 +290,10 @@ attribute-sets:
       -
         name: threaded
         doc: Whether the NAPI is configured to operate in threaded polling
-             mode. If this is set to 1 then the NAPI context operates in
-             threaded polling mode.
-        type: uint
-        checks:
-          max: 1
+             mode. If this is set to enabled then the NAPI context operates
+             in threaded polling mode.
+        type: u32
+        enum: napi-threaded
   -
     name: xsk-info
     attributes: []
diff --git a/Documentation/networking/net_cachelines/net_device.rst b/Documentation/networking/net_cachelines/net_device.rst
index 2d3dc4692d20..1c19bb7705df 100644
--- a/Documentation/networking/net_cachelines/net_device.rst
+++ b/Documentation/networking/net_cachelines/net_device.rst
@@ -68,6 +68,7 @@ unsigned_char                       addr_assign_type
 unsigned_char                       addr_len
 unsigned_char                       upper_level
 unsigned_char                       lower_level
+u8                                  threaded                                                            napi_poll(napi_enable,netif_set_threaded)
 unsigned_short                      neigh_priv_len
 unsigned_short                      padded
 unsigned_short                      dev_id
@@ -165,7 +166,6 @@ struct sfp_bus*                     sfp_bus
 struct lock_class_key*              qdisc_tx_busylock
 bool                                proto_down
 unsigned:1                          wol_enabled
-unsigned:1                          threaded                                                            napi_poll(napi_enable,netif_set_threaded)
 unsigned_long:1                     see_all_hwtstamp_requests
 unsigned_long:1                     change_proto_down
 unsigned_long:1                     netns_immutable
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a97c9a337d6b..5e5de4b0a433 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -369,7 +369,7 @@ struct napi_config {
 	u64 irq_suspend_timeout;
 	u32 defer_hard_irqs;
 	cpumask_t affinity_mask;
-	bool threaded;
+	u8 threaded;
 	unsigned int napi_id;
 };
 
@@ -590,7 +590,8 @@ static inline bool napi_complete(struct napi_struct *n)
 }
 
 void netif_threaded_enable(struct net_device *dev);
-int dev_set_threaded(struct net_device *dev, bool threaded);
+int dev_set_threaded(struct net_device *dev,
+		     enum netdev_napi_threaded threaded);
 
 void napi_disable(struct napi_struct *n);
 void napi_disable_locked(struct napi_struct *n);
@@ -1872,6 +1873,7 @@ enum netdev_reg_state {
  * 	@addr_len:		Hardware address length
  *	@upper_level:		Maximum depth level of upper devices.
  *	@lower_level:		Maximum depth level of lower devices.
+ *	@threaded:		napi threaded state.
  *	@neigh_priv_len:	Used in neigh_alloc()
  * 	@dev_id:		Used to differentiate devices that share
  * 				the same link layer address
@@ -2011,8 +2013,6 @@ enum netdev_reg_state {
  *			switch driver and used to set the phys state of the
  *			switch port.
  *
- *	@threaded:	napi threaded mode is enabled
- *
  *	@irq_affinity_auto: driver wants the core to store and re-assign the IRQ
  *			    affinity. Set by netif_enable_irq_affinity(), then
  *			    the driver must create a persistent napi by
@@ -2248,6 +2248,7 @@ struct net_device {
 	unsigned char		addr_len;
 	unsigned char		upper_level;
 	unsigned char		lower_level;
+	u8			threaded;
 
 	unsigned short		neigh_priv_len;
 	unsigned short          dev_id;
@@ -2429,7 +2430,6 @@ struct net_device {
 	struct sfp_bus		*sfp_bus;
 	struct lock_class_key	*qdisc_tx_busylock;
 	bool			proto_down;
-	bool			threaded;
 	bool			irq_affinity_auto;
 	bool			rx_cpu_rmap_auto;
 
diff --git a/include/uapi/linux/netdev.h b/include/uapi/linux/netdev.h
index 1f3719a9a0eb..48eb49aa03d4 100644
--- a/include/uapi/linux/netdev.h
+++ b/include/uapi/linux/netdev.h
@@ -77,6 +77,11 @@ enum netdev_qstats_scope {
 	NETDEV_QSTATS_SCOPE_QUEUE = 1,
 };
 
+enum netdev_napi_threaded {
+	NETDEV_NAPI_THREADED_DISABLED,
+	NETDEV_NAPI_THREADED_ENABLED,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
diff --git a/net/core/dev.c b/net/core/dev.c
index f28661d6f5ea..1c6e755841ce 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6963,7 +6963,8 @@ static void napi_stop_kthread(struct napi_struct *napi)
 	napi->thread = NULL;
 }
 
-int napi_set_threaded(struct napi_struct *napi, bool threaded)
+int napi_set_threaded(struct napi_struct *napi,
+		      enum netdev_napi_threaded threaded)
 {
 	if (threaded) {
 		if (!napi->thread) {
@@ -6988,7 +6989,8 @@ int napi_set_threaded(struct napi_struct *napi, bool threaded)
 	return 0;
 }
 
-int netif_set_threaded(struct net_device *dev, bool threaded)
+int netif_set_threaded(struct net_device *dev,
+		       enum netdev_napi_threaded threaded)
 {
 	struct napi_struct *napi;
 	int err = 0;
@@ -7000,7 +7002,7 @@ int netif_set_threaded(struct net_device *dev, bool threaded)
 			if (!napi->thread) {
 				err = napi_kthread_create(napi);
 				if (err) {
-					threaded = false;
+					threaded = NETDEV_NAPI_THREADED_DISABLED;
 					break;
 				}
 			}
@@ -7043,7 +7045,7 @@ int netif_set_threaded(struct net_device *dev, bool threaded)
  */
 void netif_threaded_enable(struct net_device *dev)
 {
-	WARN_ON_ONCE(netif_set_threaded(dev, true));
+	WARN_ON_ONCE(netif_set_threaded(dev, NETDEV_NAPI_THREADED_ENABLED));
 }
 EXPORT_SYMBOL(netif_threaded_enable);
 
@@ -7360,7 +7362,7 @@ void netif_napi_add_weight_locked(struct net_device *dev,
 	 * threaded mode will not be enabled in napi_enable().
 	 */
 	if (dev->threaded && napi_kthread_create(napi))
-		dev->threaded = false;
+		dev->threaded = NETDEV_NAPI_THREADED_DISABLED;
 	netif_napi_set_irq_locked(napi, -1);
 }
 EXPORT_SYMBOL(netif_napi_add_weight_locked);
diff --git a/net/core/dev.h b/net/core/dev.h
index f5b567310908..ab69edc0c3e3 100644
--- a/net/core/dev.h
+++ b/net/core/dev.h
@@ -315,14 +315,19 @@ static inline void napi_set_irq_suspend_timeout(struct napi_struct *n,
 	WRITE_ONCE(n->irq_suspend_timeout, timeout);
 }
 
-static inline bool napi_get_threaded(struct napi_struct *n)
+static inline enum netdev_napi_threaded napi_get_threaded(struct napi_struct *n)
 {
-	return test_bit(NAPI_STATE_THREADED, &n->state);
+	if (test_bit(NAPI_STATE_THREADED, &n->state))
+		return NETDEV_NAPI_THREADED_ENABLED;
+
+	return NETDEV_NAPI_THREADED_DISABLED;
 }
 
-int napi_set_threaded(struct napi_struct *n, bool threaded);
+int napi_set_threaded(struct napi_struct *n,
+		      enum netdev_napi_threaded threaded);
 
-int netif_set_threaded(struct net_device *dev, bool threaded);
+int netif_set_threaded(struct net_device *dev,
+		       enum netdev_napi_threaded threaded);
 
 int rps_cpumask_housekeeping(struct cpumask *mask);
 
diff --git a/net/core/dev_api.c b/net/core/dev_api.c
index dd7f57013ce5..f28852078aa6 100644
--- a/net/core/dev_api.c
+++ b/net/core/dev_api.c
@@ -368,7 +368,8 @@ void netdev_state_change(struct net_device *dev)
 }
 EXPORT_SYMBOL(netdev_state_change);
 
-int dev_set_threaded(struct net_device *dev, bool threaded)
+int dev_set_threaded(struct net_device *dev,
+		     enum netdev_napi_threaded threaded)
 {
 	int ret;
 
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
index 0994bd68a7e6..e9a2a6f26cb7 100644
--- a/net/core/netdev-genl-gen.c
+++ b/net/core/netdev-genl-gen.c
@@ -97,7 +97,7 @@ static const struct nla_policy netdev_napi_set_nl_policy[NETDEV_A_NAPI_THREADED
 	[NETDEV_A_NAPI_DEFER_HARD_IRQS] = NLA_POLICY_FULL_RANGE(NLA_U32, &netdev_a_napi_defer_hard_irqs_range),
 	[NETDEV_A_NAPI_GRO_FLUSH_TIMEOUT] = { .type = NLA_UINT, },
 	[NETDEV_A_NAPI_IRQ_SUSPEND_TIMEOUT] = { .type = NLA_UINT, },
-	[NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_UINT, 1),
+	[NETDEV_A_NAPI_THREADED] = NLA_POLICY_MAX(NLA_U32, 1),
 };
 
 /* NETDEV_CMD_BIND_TX - do */
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index 5875df372415..6314eb7bdf69 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -333,7 +333,7 @@ netdev_nl_napi_set_config(struct napi_struct *napi, struct genl_info *info)
 		int ret;
 
 		threaded = nla_get_uint(info->attrs[NETDEV_A_NAPI_THREADED]);
-		ret = napi_set_threaded(napi, !!threaded);
+		ret = napi_set_threaded(napi, threaded);
 		if (ret)
 			return ret;
 	}
diff --git a/tools/include/uapi/linux/netdev.h b/tools/include/uapi/linux/netdev.h
index 1f3719a9a0eb..48eb49aa03d4 100644
--- a/tools/include/uapi/linux/netdev.h
+++ b/tools/include/uapi/linux/netdev.h
@@ -77,6 +77,11 @@ enum netdev_qstats_scope {
 	NETDEV_QSTATS_SCOPE_QUEUE = 1,
 };
 
+enum netdev_napi_threaded {
+	NETDEV_NAPI_THREADED_DISABLED,
+	NETDEV_NAPI_THREADED_ENABLED,
+};
+
 enum {
 	NETDEV_A_DEV_IFINDEX = 1,
 	NETDEV_A_DEV_PAD,
diff --git a/tools/testing/selftests/net/nl_netdev.py b/tools/testing/selftests/net/nl_netdev.py
index c8ffade79a52..5c66421ab8aa 100755
--- a/tools/testing/selftests/net/nl_netdev.py
+++ b/tools/testing/selftests/net/nl_netdev.py
@@ -52,14 +52,14 @@ def napi_set_threaded(nf) -> None:
         napi1_id = napis[1]['id']
 
         # set napi threaded and verify
-        nf.napi_set({'id': napi0_id, 'threaded': 1})
+        nf.napi_set({'id': napi0_id, 'threaded': "enabled"})
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 1)
+        ksft_eq(napi0['threaded'], "enabled")
         ksft_ne(napi0.get('pid'), None)
 
         # check it is not set for napi1
         napi1 = nf.napi_get({'id': napi1_id})
-        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1['threaded'], "disabled")
         ksft_eq(napi1.get('pid'), None)
 
         ip(f"link set dev {nsim.ifname} down")
@@ -67,18 +67,18 @@ def napi_set_threaded(nf) -> None:
 
         # verify if napi threaded is still set
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 1)
+        ksft_eq(napi0['threaded'], "enabled")
         ksft_ne(napi0.get('pid'), None)
 
         # check it is still not set for napi1
         napi1 = nf.napi_get({'id': napi1_id})
-        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1['threaded'], "disabled")
         ksft_eq(napi1.get('pid'), None)
 
         # unset napi threaded and verify
-        nf.napi_set({'id': napi0_id, 'threaded': 0})
+        nf.napi_set({'id': napi0_id, 'threaded': "disabled"})
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 0)
+        ksft_eq(napi0['threaded'], "disabled")
         ksft_eq(napi0.get('pid'), None)
 
         # set threaded at device level
@@ -86,10 +86,10 @@ def napi_set_threaded(nf) -> None:
 
         # check napi threaded is set for both napis
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 1)
+        ksft_eq(napi0['threaded'], "enabled")
         ksft_ne(napi0.get('pid'), None)
         napi1 = nf.napi_get({'id': napi1_id})
-        ksft_eq(napi1['threaded'], 1)
+        ksft_eq(napi1['threaded'], "enabled")
         ksft_ne(napi1.get('pid'), None)
 
         # unset threaded at device level
@@ -97,16 +97,16 @@ def napi_set_threaded(nf) -> None:
 
         # check napi threaded is unset for both napis
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 0)
+        ksft_eq(napi0['threaded'], "disabled")
         ksft_eq(napi0.get('pid'), None)
         napi1 = nf.napi_get({'id': napi1_id})
-        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1['threaded'], "disabled")
         ksft_eq(napi1.get('pid'), None)
 
         # set napi threaded for napi0
         nf.napi_set({'id': napi0_id, 'threaded': 1})
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 1)
+        ksft_eq(napi0['threaded'], "enabled")
         ksft_ne(napi0.get('pid'), None)
 
         # unset threaded at device level
@@ -114,10 +114,10 @@ def napi_set_threaded(nf) -> None:
 
         # check napi threaded is unset for both napis
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 0)
+        ksft_eq(napi0['threaded'], "disabled")
         ksft_eq(napi0.get('pid'), None)
         napi1 = nf.napi_get({'id': napi1_id})
-        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1['threaded'], "disabled")
         ksft_eq(napi1.get('pid'), None)
 
 def dev_set_threaded(nf) -> None:
@@ -141,10 +141,10 @@ def dev_set_threaded(nf) -> None:
 
         # check napi threaded is set for both napis
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 1)
+        ksft_eq(napi0['threaded'], "enabled")
         ksft_ne(napi0.get('pid'), None)
         napi1 = nf.napi_get({'id': napi1_id})
-        ksft_eq(napi1['threaded'], 1)
+        ksft_eq(napi1['threaded'], "enabled")
         ksft_ne(napi1.get('pid'), None)
 
         # unset threaded
@@ -152,10 +152,10 @@ def dev_set_threaded(nf) -> None:
 
         # check napi threaded is unset for both napis
         napi0 = nf.napi_get({'id': napi0_id})
-        ksft_eq(napi0['threaded'], 0)
+        ksft_eq(napi0['threaded'], "disabled")
         ksft_eq(napi0.get('pid'), None)
         napi1 = nf.napi_get({'id': napi1_id})
-        ksft_eq(napi1['threaded'], 0)
+        ksft_eq(napi1['threaded'], "disabled")
         ksft_eq(napi1.get('pid'), None)
 
 def nsim_rxq_reset_down(nf) -> None:
-- 
cgit v1.2.3


From 3865301dc58aec2ab77651bdbf1e55352f50a608 Mon Sep 17 00:00:00 2001
From: Hugh Dickins <hughd@google.com>
Date: Sun, 13 Jul 2025 12:57:18 -0700
Subject: mm: optimize lru_note_cost() by adding lru_note_cost_unlock_irq()

Dropping a lock, just to demand it again for an afterthought, cannot be
good if contended: convert lru_note_cost() to lru_note_cost_unlock_irq().

[hughd@google.com: delete unneeded comment]
  Link: https://lkml.kernel.org/r/dbf9352a-1ed9-a021-c0c7-9309ac73e174@google.com
Link: https://lkml.kernel.org/r/21100102-51b6-79d5-03db-1bb7f97fa94c@google.com
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Roman Gushchin <roman.gushchin@linux.dev>
Tested-by: Roman Gushchin <roman.gushchin@linux.dev>
Reviewed-by: Shakeel Butt <shakeel.butt@linux.dev>
Cc: David Hildenbrand <david@redhat.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/swap.h |  5 +++--
 mm/swap.c            | 33 +++++++++++++++++++--------------
 mm/vmscan.c          |  8 +++-----
 3 files changed, 25 insertions(+), 21 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/swap.h b/include/linux/swap.h
index 95c6061fa1dc..2fe6ed2cc3fd 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -376,8 +376,9 @@ extern unsigned long totalreserve_pages;
 
 
 /* linux/mm/swap.c */
-void lru_note_cost(struct lruvec *lruvec, bool file,
-		   unsigned int nr_io, unsigned int nr_rotated);
+void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file,
+		unsigned int nr_io, unsigned int nr_rotated)
+		__releases(lruvec->lru_lock);
 void lru_note_cost_refault(struct folio *);
 void folio_add_lru(struct folio *);
 void folio_add_lru_vma(struct folio *, struct vm_area_struct *);
diff --git a/mm/swap.c b/mm/swap.c
index 4fc322f7111a..3632dd061beb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -237,8 +237,9 @@ void folio_rotate_reclaimable(struct folio *folio)
 	folio_batch_add_and_move(folio, lru_move_tail, true);
 }
 
-void lru_note_cost(struct lruvec *lruvec, bool file,
-		   unsigned int nr_io, unsigned int nr_rotated)
+void lru_note_cost_unlock_irq(struct lruvec *lruvec, bool file,
+		unsigned int nr_io, unsigned int nr_rotated)
+		__releases(lruvec->lru_lock)
 {
 	unsigned long cost;
 
@@ -250,18 +251,14 @@ void lru_note_cost(struct lruvec *lruvec, bool file,
 	 * different between them, adjust scan balance for CPU work.
 	 */
 	cost = nr_io * SWAP_CLUSTER_MAX + nr_rotated;
+	if (!cost) {
+		spin_unlock_irq(&lruvec->lru_lock);
+		return;
+	}
 
-	do {
+	for (;;) {
 		unsigned long lrusize;
 
-		/*
-		 * Hold lruvec->lru_lock is safe here, since
-		 * 1) The pinned lruvec in reclaim, or
-		 * 2) From a pre-LRU page during refault (which also holds the
-		 *    rcu lock, so would be safe even if the page was on the LRU
-		 *    and could move simultaneously to a new lruvec).
-		 */
-		spin_lock_irq(&lruvec->lru_lock);
 		/* Record cost event */
 		if (file)
 			lruvec->file_cost += cost;
@@ -285,14 +282,22 @@ void lru_note_cost(struct lruvec *lruvec, bool file,
 			lruvec->file_cost /= 2;
 			lruvec->anon_cost /= 2;
 		}
+
 		spin_unlock_irq(&lruvec->lru_lock);
-	} while ((lruvec = parent_lruvec(lruvec)));
+		lruvec = parent_lruvec(lruvec);
+		if (!lruvec)
+			break;
+		spin_lock_irq(&lruvec->lru_lock);
+	}
 }
 
 void lru_note_cost_refault(struct folio *folio)
 {
-	lru_note_cost(folio_lruvec(folio), folio_is_file_lru(folio),
-		      folio_nr_pages(folio), 0);
+	struct lruvec *lruvec;
+
+	lruvec = folio_lruvec_lock_irq(folio);
+	lru_note_cost_unlock_irq(lruvec, folio_is_file_lru(folio),
+				folio_nr_pages(folio), 0);
 }
 
 static void lru_activate(struct lruvec *lruvec, struct folio *folio)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 0d6b8e1e95e5..d71aeabdc725 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2053,9 +2053,9 @@ static unsigned long shrink_inactive_list(unsigned long nr_to_scan,
 		__count_vm_events(item, nr_reclaimed);
 	count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed);
 	__count_vm_events(PGSTEAL_ANON + file, nr_reclaimed);
-	spin_unlock_irq(&lruvec->lru_lock);
 
-	lru_note_cost(lruvec, file, stat.nr_pageout, nr_scanned - nr_reclaimed);
+	lru_note_cost_unlock_irq(lruvec, file, stat.nr_pageout,
+					nr_scanned - nr_reclaimed);
 
 	/*
 	 * If dirty folios are scanned that are not queued for IO, it
@@ -2201,10 +2201,8 @@ static void shrink_active_list(unsigned long nr_to_scan,
 	count_memcg_events(lruvec_memcg(lruvec), PGDEACTIVATE, nr_deactivate);
 
 	__mod_node_page_state(pgdat, NR_ISOLATED_ANON + file, -nr_taken);
-	spin_unlock_irq(&lruvec->lru_lock);
 
-	if (nr_rotated)
-		lru_note_cost(lruvec, file, 0, nr_rotated);
+	lru_note_cost_unlock_irq(lruvec, file, 0, nr_rotated);
 	trace_mm_vmscan_lru_shrink_active(pgdat->node_id, nr_taken, nr_activate,
 			nr_deactivate, nr_rotated, sc->priority, file);
 }
-- 
cgit v1.2.3


From f9f11398d4dac3c85507f31192e318b20b19af61 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Thu, 17 Jul 2025 17:55:55 +0100
Subject: mm/mremap: use an explicit uffd failure path for mremap

Right now it appears that the code is relying upon the returned
destination address having bits outside PAGE_MASK to indicate whether an
error value is specified, and decrementing the increased refcount on the
uffd ctx if so.

This is not a safe means of determining an error value, so instead, be
specific.  It makes far more sense to do so in a dedicated error path, so
add mremap_userfaultfd_fail() for this purpose and use this when an error
arises.

A vm_userfaultfd_ctx is not established until we are at the point where
mremap_userfaultfd_prep() is invoked in copy_vma_and_data(), so this is a
no-op until this happens.

That is - uffd remap notification only occurs if the VMA is actually moved
- at which point a UFFD_EVENT_REMAP event is raised.

No errors can occur after this point currently, though it's certainly not
guaranteed this will always remain the case, and we mustn't rely on this.

However, the reason for needing to handle this case is that, when an error
arises on a VMA move at the point of adjusting page tables, we revert this
operation, and propagate the error.

At this point, it is not correct to raise a uffd remap event, and we must
handle it.

This refactoring makes it abundantly clear what we are doing.

We assume vrm->new_addr is always valid, which a prior change made the
case even for mremap() invocations which don't move the VMA, however given
no uffd context would be set up in this case it's immaterial to this
change anyway.

No functional change intended.

Link: https://lkml.kernel.org/r/a70e8a1f7bce9f43d1431065b414e0f212297297.1752770784.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Jan Kara <jack@suse.cz>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Peter Xu <peterx@redhat.com>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/userfaultfd.c              | 15 ++++++++++-----
 include/linux/userfaultfd_k.h |  5 +++++
 mm/mremap.c                   | 16 ++++++++++++----
 3 files changed, 27 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 2a644aa1a510..54c6cc7fe9c6 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -750,11 +750,6 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
 	if (!ctx)
 		return;
 
-	if (to & ~PAGE_MASK) {
-		userfaultfd_ctx_put(ctx);
-		return;
-	}
-
 	msg_init(&ewq.msg);
 
 	ewq.msg.event = UFFD_EVENT_REMAP;
@@ -765,6 +760,16 @@ void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
 	userfaultfd_event_wait_completion(ctx, &ewq);
 }
 
+void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *vm_ctx)
+{
+	struct userfaultfd_ctx *ctx = vm_ctx->ctx;
+
+	if (!ctx)
+		return;
+
+	userfaultfd_ctx_put(ctx);
+}
+
 bool userfaultfd_remove(struct vm_area_struct *vma,
 			unsigned long start, unsigned long end)
 {
diff --git a/include/linux/userfaultfd_k.h b/include/linux/userfaultfd_k.h
index df85330bcfa6..c0e716aec26a 100644
--- a/include/linux/userfaultfd_k.h
+++ b/include/linux/userfaultfd_k.h
@@ -259,6 +259,7 @@ extern void mremap_userfaultfd_prep(struct vm_area_struct *,
 extern void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *,
 					unsigned long from, unsigned long to,
 					unsigned long len);
+void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *);
 
 extern bool userfaultfd_remove(struct vm_area_struct *vma,
 			       unsigned long start,
@@ -371,6 +372,10 @@ static inline void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *ctx,
 {
 }
 
+static inline void mremap_userfaultfd_fail(struct vm_userfaultfd_ctx *ctx)
+{
+}
+
 static inline bool userfaultfd_remove(struct vm_area_struct *vma,
 				      unsigned long start,
 				      unsigned long end)
diff --git a/mm/mremap.c b/mm/mremap.c
index 53447761e55d..db7e773d0884 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -1729,12 +1729,17 @@ static int check_prep_vma(struct vma_remap_struct *vrm)
 	return 0;
 }
 
-static void notify_uffd(struct vma_remap_struct *vrm, unsigned long to)
+static void notify_uffd(struct vma_remap_struct *vrm, bool failed)
 {
 	struct mm_struct *mm = current->mm;
 
+	/* Regardless of success/failure, we always notify of any unmaps. */
 	userfaultfd_unmap_complete(mm, vrm->uf_unmap_early);
-	mremap_userfaultfd_complete(vrm->uf, vrm->addr, to, vrm->old_len);
+	if (failed)
+		mremap_userfaultfd_fail(vrm->uf);
+	else
+		mremap_userfaultfd_complete(vrm->uf, vrm->addr,
+			vrm->new_addr, vrm->old_len);
 	userfaultfd_unmap_complete(mm, vrm->uf_unmap);
 }
 
@@ -1742,6 +1747,7 @@ static unsigned long do_mremap(struct vma_remap_struct *vrm)
 {
 	struct mm_struct *mm = current->mm;
 	unsigned long res;
+	bool failed;
 
 	vrm->old_len = PAGE_ALIGN(vrm->old_len);
 	vrm->new_len = PAGE_ALIGN(vrm->new_len);
@@ -1763,13 +1769,15 @@ static unsigned long do_mremap(struct vma_remap_struct *vrm)
 	res = vrm_implies_new_addr(vrm) ? mremap_to(vrm) : mremap_at(vrm);
 
 out:
+	failed = IS_ERR_VALUE(res);
+
 	if (vrm->mmap_locked)
 		mmap_write_unlock(mm);
 
-	if (!IS_ERR_VALUE(res) && vrm->mlocked && vrm->new_len > vrm->old_len)
+	if (!failed && vrm->mlocked && vrm->new_len > vrm->old_len)
 		mm_populate(vrm->new_addr + vrm->old_len, vrm->delta);
 
-	notify_uffd(vrm, res);
+	notify_uffd(vrm, failed);
 	return res;
 }
 
-- 
cgit v1.2.3


From 441413d2a99d1d23bea2df2497493024b00ace57 Mon Sep 17 00:00:00 2001
From: Anthony Yznaga <anthony.yznaga@oracle.com>
Date: Tue, 15 Jul 2025 18:26:11 -0700
Subject: mm: drop hugetlb_free_pgd_range()

There are no longer any callers of hugetlb_free_pgd_range().

Link: https://lkml.kernel.org/r/20250716012611.10369-4-anthony.yznaga@oracle.com
Signed-off-by: Anthony Yznaga <anthony.yznaga@oracle.com>
Acked-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Oscar Salvador <osalvador@suse.de>
Cc: Alexander Gordeev <agordeev@linux.ibm.com>
Cc: Alexandre Ghiti <alexghiti@rivosinc.com>
Cc: Andreas Larsson <andreas@gaisler.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Muchun Song <muchun.song@linux.dev>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/asm-generic/hugetlb.h | 9 ---------
 include/linux/hugetlb.h       | 7 -------
 2 files changed, 16 deletions(-)

(limited to 'include/linux')

diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h
index 4bce4f07f44f..dcb8727f2b82 100644
--- a/include/asm-generic/hugetlb.h
+++ b/include/asm-generic/hugetlb.h
@@ -66,15 +66,6 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 
-#ifndef __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-		unsigned long addr, unsigned long end,
-		unsigned long floor, unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-#endif
-
 #ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		pte_t *ptep, pte_t pte, unsigned long sz)
diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index 474de8e2a8f2..526d27e88b3b 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -390,13 +390,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-				unsigned long addr, unsigned long end,
-				unsigned long floor, unsigned long ceiling)
-{
-	BUG();
-}
-
 #ifdef CONFIG_USERFAULTFD
 static inline int hugetlb_mfill_atomic_pte(pte_t *dst_pte,
 					   struct vm_area_struct *dst_vma,
-- 
cgit v1.2.3


From 378bdb97405a00bf03d8d993435c83add1688e36 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@google.com>
Date: Thu, 17 Jul 2025 19:46:43 +0000
Subject: memcg: convert memcg->socket_pressure to u64

memcg->socket_pressure is initialised with jiffies when the memcg is
created.

Once vmpressure detects that the cgroup is under memory pressure, the
field is updated with jiffies + HZ to signal the fact to the socket layer
and suppress memory allocation for one second.

Otherwise, the field is not updated.

mem_cgroup_under_socket_pressure() uses time_before() to check if jiffies
is less than memcg->socket_pressure, and this has a bug on 32-bit kernel.

  if (time_before(jiffies, memcg->socket_pressure))
          return true;

As time_before() casts the final result to long, the acceptable delta
between two timestamps is 2 ^ (BITS_PER_LONG - 1).

On 32-bit kernel with CONFIG_HZ=1000, this is about 24 days.

  >>> (2 ** 31) / 1000 / 60 / 60 / 24
  24.855134814814818

Once 24 days have passed since the last update of socket_pressure,
mem_cgroup_under_socket_pressure() starts to lie until the next 24 days
pass.

We don't need to worry about this on 64-bit machines unless they serve for
300 million years.

  >>> (2 ** 63) / 1000 / 60 / 60 / 24 / 365
  292471208.6775361

Let's convert memcg->socket_pressure to u64.

Performance teting:

I don't have a real 32-bit machine so this is a result on QEMU, but
with/without the u64 jiffie patch, the time spent in
mem_cgroup_under_socket_pressure() was 1~5us and I didn't see any
measurable delta.

no patch applied:
iperf3   273 [000]   137.296248:
probe:mem_cgroup_under_socket_pressure: (c13660d0)
                c13660d1 mem_cgroup_under_socket_pressure+0x1
([kernel.kallsyms])
iperf3   273 [000]   137.296249:
probe:mem_cgroup_under_socket_pressure__return: (c13660d0 <- c1d8fd7f)
iperf3   273 [000]   137.296251:
probe:mem_cgroup_under_socket_pressure: (c13660d0)
                c13660d1 mem_cgroup_under_socket_pressure+0x1
([kernel.kallsyms])
iperf3   273 [000]   137.296253:
probe:mem_cgroup_under_socket_pressure__return: (c13660d0 <- c1d8fd7f)


u64 jiffies patch applied:
iperf3   308 [001]   330.669370:
probe:mem_cgroup_under_socket_pressure: (c12ddba0)
                c12ddba1 mem_cgroup_under_socket_pressure+0x1
([kernel.kallsyms])
iperf3   308 [001]   330.669371:
probe:mem_cgroup_under_socket_pressure__return: (c12ddba0 <- c1ce98bf)
iperf3   308 [001]   330.669382:
probe:mem_cgroup_under_socket_pressure: (c12ddba0)
                c12ddba1 mem_cgroup_under_socket_pressure+0x1
([kernel.kallsyms])
iperf3   308 [001]   330.669384:
probe:mem_cgroup_under_socket_pressure__return: (c12ddba0 <- c1ce98bf)

So the u64 approach is good enough.

Link: https://lkml.kernel.org/r/20250717194645.1096500-1-kuniyu@google.com
Fixes: 8e8ae645249b ("mm: memcontrol: hook up vmpressure to socket pressure")
Signed-off-by: Kuniyuki Iwashima <kuniyu@google.com>
Reported-by: Neal Cardwell <ncardwell@google.com>
Suggested-by: Andrew Morton <akpm@linux-foundation.org>
Acked-by: Shakeel Butt <shakeel.butt@linux.dev>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: David S. Miller <davem@davemloft.net>
Cc: Eric Dumazet <ncardwell@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/memcontrol.h | 44 +++++++++++++++++++++++++++++++++++++++++---
 mm/memcontrol.c            |  5 ++++-
 mm/vmpressure.c            |  2 +-
 3 files changed, 46 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 87b6688f124a..785173aa0739 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -251,8 +251,10 @@ struct mem_cgroup {
 	 * that this indicator should NOT be used in legacy cgroup mode
 	 * where socket memory is accounted/charged separately.
 	 */
-	unsigned long		socket_pressure;
-
+	u64			socket_pressure;
+#if BITS_PER_LONG < 64
+	seqlock_t		socket_pressure_seqlock;
+#endif
 	int kmemcg_id;
 	/*
 	 * memcg->objcg is wiped out as a part of the objcg repaprenting
@@ -1602,6 +1604,42 @@ extern struct static_key_false memcg_sockets_enabled_key;
 #define mem_cgroup_sockets_enabled static_branch_unlikely(&memcg_sockets_enabled_key)
 void mem_cgroup_sk_alloc(struct sock *sk);
 void mem_cgroup_sk_free(struct sock *sk);
+
+#if BITS_PER_LONG < 64
+static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg)
+{
+	u64 val = get_jiffies_64() + HZ;
+	unsigned long flags;
+
+	write_seqlock_irqsave(&memcg->socket_pressure_seqlock, flags);
+	memcg->socket_pressure = val;
+	write_sequnlock_irqrestore(&memcg->socket_pressure_seqlock, flags);
+}
+
+static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg)
+{
+	unsigned int seq;
+	u64 val;
+
+	do {
+		seq = read_seqbegin(&memcg->socket_pressure_seqlock);
+		val = memcg->socket_pressure;
+	} while (read_seqretry(&memcg->socket_pressure_seqlock, seq));
+
+	return val;
+}
+#else
+static inline void mem_cgroup_set_socket_pressure(struct mem_cgroup *memcg)
+{
+	WRITE_ONCE(memcg->socket_pressure, jiffies + HZ);
+}
+
+static inline u64 mem_cgroup_get_socket_pressure(struct mem_cgroup *memcg)
+{
+	return READ_ONCE(memcg->socket_pressure);
+}
+#endif
+
 static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 {
 #ifdef CONFIG_MEMCG_V1
@@ -1609,7 +1647,7 @@ static inline bool mem_cgroup_under_socket_pressure(struct mem_cgroup *memcg)
 		return !!memcg->tcpmem_pressure;
 #endif /* CONFIG_MEMCG_V1 */
 	do {
-		if (time_before(jiffies, READ_ONCE(memcg->socket_pressure)))
+		if (time_before64(get_jiffies_64(), mem_cgroup_get_socket_pressure(memcg)))
 			return true;
 	} while ((memcg = parent_mem_cgroup(memcg)));
 	return false;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 235c66d2161b..de7d737fe011 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3754,7 +3754,10 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
 	INIT_LIST_HEAD(&memcg->memory_peaks);
 	INIT_LIST_HEAD(&memcg->swap_peaks);
 	spin_lock_init(&memcg->peaks_lock);
-	memcg->socket_pressure = jiffies;
+	memcg->socket_pressure = get_jiffies_64();
+#if BITS_PER_LONG < 64
+	seqlock_init(&memcg->socket_pressure_seqlock);
+#endif
 	memcg1_memcg_init(memcg);
 	memcg->kmemcg_id = -1;
 	INIT_LIST_HEAD(&memcg->objcg_list);
diff --git a/mm/vmpressure.c b/mm/vmpressure.c
index bd5183dfd879..c197ed47bcc4 100644
--- a/mm/vmpressure.c
+++ b/mm/vmpressure.c
@@ -316,7 +316,7 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree,
 			 * asserted for a second in which subsequent
 			 * pressure events can occur.
 			 */
-			WRITE_ONCE(memcg->socket_pressure, jiffies + HZ);
+			mem_cgroup_set_socket_pressure(memcg);
 		}
 	}
 }
-- 
cgit v1.2.3


From 92c99fc614737eaa99125283c306d2ebb13b101a Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Mon, 14 Jul 2025 09:16:51 -0400
Subject: mm/memory: introduce is_huge_zero_pfn() and use it in
 vm_normal_page_pmd()

Patch series "mm: introduce snapshot_page()", v3.

This series introduces snapshot_page(), a helper function that can be used
to create a snapshot of a struct page and its associated struct folio.

This function is intended to help callers with a consistent view of a a
folio while reducing the chance of encountering partially updated or
inconsistent state, such as during folio splitting which could lead to
crashes and BUG_ON()s being triggered.


This patch (of 4):

Let's avoid working with the PMD when not required.  If
vm_normal_page_pmd() would be called on something that is not a present
pmd, it would already be a bug (pfn possibly garbage).

While at it, let's support passing in any pfn covered by the huge zero
folio by masking off PFN bits -- which should be rather cheap.

Link: https://lkml.kernel.org/r/cover.1752499009.git.luizcap@redhat.com
Link: https://lkml.kernel.org/r/4940826e99f0c709a7cf7beb94f53288320aea5a.1752499009.git.luizcap@redhat.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
Signed-off-by: Luiz Capitulino <luizcap@redhat.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Harry Yoo <harry.yoo@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/huge_mm.h | 12 +++++++++++-
 mm/memory.c             |  2 +-
 2 files changed, 12 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
index 4d5bb67dc4ec..7748489fde1b 100644
--- a/include/linux/huge_mm.h
+++ b/include/linux/huge_mm.h
@@ -482,9 +482,14 @@ static inline bool is_huge_zero_folio(const struct folio *folio)
 	return READ_ONCE(huge_zero_folio) == folio;
 }
 
+static inline bool is_huge_zero_pfn(unsigned long pfn)
+{
+	return READ_ONCE(huge_zero_pfn) == (pfn & ~(HPAGE_PMD_NR - 1));
+}
+
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
-	return pmd_present(pmd) && READ_ONCE(huge_zero_pfn) == pmd_pfn(pmd);
+	return pmd_present(pmd) && is_huge_zero_pfn(pmd_pfn(pmd));
 }
 
 struct folio *mm_get_huge_zero_folio(struct mm_struct *mm);
@@ -632,6 +637,11 @@ static inline bool is_huge_zero_folio(const struct folio *folio)
 	return false;
 }
 
+static inline bool is_huge_zero_pfn(unsigned long pfn)
+{
+	return false;
+}
+
 static inline bool is_huge_zero_pmd(pmd_t pmd)
 {
 	return false;
diff --git a/mm/memory.c b/mm/memory.c
index b4fb559dd0c6..92fd18a5d8d1 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -668,7 +668,7 @@ struct page *vm_normal_page_pmd(struct vm_area_struct *vma, unsigned long addr,
 		}
 	}
 
-	if (is_huge_zero_pmd(pmd))
+	if (is_huge_zero_pfn(pfn))
 		return NULL;
 	if (unlikely(pfn > highest_memmap_pfn))
 		return NULL;
-- 
cgit v1.2.3


From d863a12108f24c5f0b49f99f328e33371bd7c69d Mon Sep 17 00:00:00 2001
From: Luiz Capitulino <luizcap@redhat.com>
Date: Mon, 14 Jul 2025 09:16:52 -0400
Subject: mm/util: introduce snapshot_page()

This commit refactors __dump_page() into snapshot_page().

snapshot_page() tries to take a faithful snapshot of a page and its folio
representation.  The snapshot is returned in the struct page_snapshot
parameter along with additional flags that are best retrieved at snapshot
creation time to reduce race windows.

This function is intended to be used by callers that need a stable
representation of a struct page and struct folio so that pointers or page
information doesn't change while working on a page.

The idea and original implementation of snapshot_page() comes from Matthew
Wilcox with suggestions for improvements from David Hildenbrand.  All bugs
and misconceptions are mine.

[luizcap@redhat.com: fix set_ps_flags() commentary]
  Link: https://lkml.kernel.org/r/d5c75701-b353-4536-a306-187fab0655b3@redhat.com
Link: https://lkml.kernel.org/r/637a03a05cb2e3df88f84ff9e9f9642374ef813a.1752499009.git.luizcap@redhat.com
Signed-off-by: Luiz Capitulino <luizcap@redhat.com>
Reviewed-by: Shivank Garg <shivankg@amd.com>
Tested-by: Harry Yoo <harry.yoo@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: SeongJae Park <sj@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h | 19 +++++++++++++
 mm/debug.c         | 42 +++-------------------------
 mm/util.c          | 81 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 104 insertions(+), 38 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 805108d7bbc3..8e3a4c5b78ff 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -4199,4 +4199,23 @@ static inline bool page_pool_page_is_pp(struct page *page)
 }
 #endif
 
+#define PAGE_SNAPSHOT_FAITHFUL (1 << 0)
+#define PAGE_SNAPSHOT_PG_BUDDY (1 << 1)
+#define PAGE_SNAPSHOT_PG_IDLE  (1 << 2)
+
+struct page_snapshot {
+	struct folio folio_snapshot;
+	struct page page_snapshot;
+	unsigned long pfn;
+	unsigned long idx;
+	unsigned long flags;
+};
+
+static inline bool snapshot_page_is_faithful(const struct page_snapshot *ps)
+{
+	return ps->flags & PAGE_SNAPSHOT_FAITHFUL;
+}
+
+void snapshot_page(struct page_snapshot *ps, const struct page *page);
+
 #endif /* _LINUX_MM_H */
diff --git a/mm/debug.c b/mm/debug.c
index e2973e1b3812..b4388f4dcd4d 100644
--- a/mm/debug.c
+++ b/mm/debug.c
@@ -129,47 +129,13 @@ static void __dump_folio(struct folio *folio, struct page *page,
 
 static void __dump_page(const struct page *page)
 {
-	struct folio *foliop, folio;
-	struct page precise;
-	unsigned long head;
-	unsigned long pfn = page_to_pfn(page);
-	unsigned long idx, nr_pages = 1;
-	int loops = 5;
-
-again:
-	memcpy(&precise, page, sizeof(*page));
-	head = precise.compound_head;
-	if ((head & 1) == 0) {
-		foliop = (struct folio *)&precise;
-		idx = 0;
-		if (!folio_test_large(foliop))
-			goto dump;
-		foliop = (struct folio *)page;
-	} else {
-		foliop = (struct folio *)(head - 1);
-		idx = folio_page_idx(foliop, page);
-	}
+	struct page_snapshot ps;
 
-	if (idx < MAX_FOLIO_NR_PAGES) {
-		memcpy(&folio, foliop, 2 * sizeof(struct page));
-		nr_pages = folio_nr_pages(&folio);
-		if (nr_pages > 1)
-			memcpy(&folio.__page_2, &foliop->__page_2,
-			       sizeof(struct page));
-		foliop = &folio;
-	}
-
-	if (idx > nr_pages) {
-		if (loops-- > 0)
-			goto again;
+	snapshot_page(&ps, page);
+	if (!snapshot_page_is_faithful(&ps))
 		pr_warn("page does not match folio\n");
-		precise.compound_head &= ~1UL;
-		foliop = (struct folio *)&precise;
-		idx = 0;
-	}
 
-dump:
-	__dump_folio(foliop, &precise, pfn, idx);
+	__dump_folio(&ps.folio_snapshot, &ps.page_snapshot, ps.pfn, ps.idx);
 }
 
 void dump_page(const struct page *page, const char *reason)
diff --git a/mm/util.c b/mm/util.c
index 68ea833ba25f..f814e6a59ab1 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -25,6 +25,7 @@
 #include <linux/sizes.h>
 #include <linux/compat.h>
 #include <linux/fsnotify.h>
+#include <linux/page_idle.h>
 
 #include <linux/uaccess.h>
 
@@ -1172,6 +1173,86 @@ int compat_vma_mmap_prepare(struct file *file, struct vm_area_struct *vma)
 }
 EXPORT_SYMBOL(compat_vma_mmap_prepare);
 
+static void set_ps_flags(struct page_snapshot *ps, const struct folio *folio,
+			 const struct page *page)
+{
+	/*
+	 * Only the first page of a high-order buddy page has PageBuddy() set.
+	 * So we have to check manually whether this page is part of a high-
+	 * order buddy page.
+	 */
+	if (PageBuddy(page))
+		ps->flags |= PAGE_SNAPSHOT_PG_BUDDY;
+	else if (page_count(page) == 0 && is_free_buddy_page(page))
+		ps->flags |= PAGE_SNAPSHOT_PG_BUDDY;
+
+	if (folio_test_idle(folio))
+		ps->flags |= PAGE_SNAPSHOT_PG_IDLE;
+}
+
+/**
+ * snapshot_page() - Create a snapshot of a struct page
+ * @ps: Pointer to a struct page_snapshot to store the page snapshot
+ * @page: The page to snapshot
+ *
+ * Create a snapshot of the page and store both its struct page and struct
+ * folio representations in @ps.
+ *
+ * A snapshot is marked as "faithful" if the compound state of @page was
+ * stable and allowed safe reconstruction of the folio representation. In
+ * rare cases where this is not possible (e.g. due to folio splitting),
+ * snapshot_page() falls back to treating @page as a single page and the
+ * snapshot is marked as "unfaithful". The snapshot_page_is_faithful()
+ * helper can be used to check for this condition.
+ */
+void snapshot_page(struct page_snapshot *ps, const struct page *page)
+{
+	unsigned long head, nr_pages = 1;
+	struct folio *foliop;
+	int loops = 5;
+
+	ps->pfn = page_to_pfn(page);
+	ps->flags = PAGE_SNAPSHOT_FAITHFUL;
+
+again:
+	memset(&ps->folio_snapshot, 0, sizeof(struct folio));
+	memcpy(&ps->page_snapshot, page, sizeof(*page));
+	head = ps->page_snapshot.compound_head;
+	if ((head & 1) == 0) {
+		ps->idx = 0;
+		foliop = (struct folio *)&ps->page_snapshot;
+		if (!folio_test_large(foliop)) {
+			set_ps_flags(ps, page_folio(page), page);
+			memcpy(&ps->folio_snapshot, foliop,
+			       sizeof(struct page));
+			return;
+		}
+		foliop = (struct folio *)page;
+	} else {
+		foliop = (struct folio *)(head - 1);
+		ps->idx = folio_page_idx(foliop, page);
+	}
+
+	if (ps->idx < MAX_FOLIO_NR_PAGES) {
+		memcpy(&ps->folio_snapshot, foliop, 2 * sizeof(struct page));
+		nr_pages = folio_nr_pages(&ps->folio_snapshot);
+		if (nr_pages > 1)
+			memcpy(&ps->folio_snapshot.__page_2, &foliop->__page_2,
+			       sizeof(struct page));
+		set_ps_flags(ps, foliop, page);
+	}
+
+	if (ps->idx > nr_pages) {
+		if (loops-- > 0)
+			goto again;
+		clear_compound_head(&ps->page_snapshot);
+		foliop = (struct folio *)&ps->page_snapshot;
+		memcpy(&ps->folio_snapshot, foliop, sizeof(struct page));
+		ps->flags = 0;
+		ps->idx = 0;
+	}
+}
+
 #ifdef CONFIG_MMU
 /**
  * folio_pte_batch - detect a PTE batch for a large folio
-- 
cgit v1.2.3


From 5631da56c9a87ea41d69d1bbbc1cee327eb9354b Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Sat, 19 Jul 2025 11:28:54 -0700
Subject: fs/proc/task_mmu: read proc/pid/maps under per-vma lock
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

With maple_tree supporting vma tree traversal under RCU and per-vma locks,
/proc/pid/maps can be read while holding individual vma locks instead of
locking the entire address space.

A completely lockless approach (walking vma tree under RCU) would be quite
complex with the main issue being get_vma_name() using callbacks which
might not work correctly with a stable vma copy, requiring original
(unstable) vma - see special_mapping_name() for example.

When per-vma lock acquisition fails, we take the mmap_lock for reading,
lock the vma, release the mmap_lock and continue.  This fallback to mmap
read lock guarantees the reader to make forward progress even during lock
contention.  This will interfere with the writer but for a very short time
while we are acquiring the per-vma lock and only when there was contention
on the vma reader is interested in.

We shouldn't see a repeated fallback to mmap read locks in practice, as
this require a very unlikely series of lock contentions (for instance due
to repeated vma split operations).  However even if this did somehow
happen, we would still progress.

One case requiring special handling is when a vma changes between the time
it was found and the time it got locked.  A problematic case would be if a
vma got shrunk so that its vm_start moved higher in the address space and
a new vma was installed at the beginning:

reader found:               |--------VMA A--------|
VMA is modified:            |-VMA B-|----VMA A----|
reader locks modified VMA A
reader reports VMA A:       |  gap  |----VMA A----|

This would result in reporting a gap in the address space that does not
exist.  To prevent this we retry the lookup after locking the vma, however
we do that only when we identify a gap and detect that the address space
was changed after we found the vma.

This change is designed to reduce mmap_lock contention and prevent a
process reading /proc/pid/maps files (often a low priority task, such as
monitoring/data collection services) from blocking address space updates.
Note that this change has a userspace visible disadvantage: it allows for
sub-page data tearing as opposed to the previous mechanism where data
tearing could happen only between pages of generated output data.  Since
current userspace considers data tearing between pages to be acceptable,
we assume is will be able to handle sub-page data tearing as well.

Link: https://lkml.kernel.org/r/20250719182854.3166724-7-surenb@google.com
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexey Dobriyan <adobriyan@gmail.com>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jeongjun Park <aha310510@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Josef Bacik <josef@toxicpanda.com>
Cc: Kalesh Singh <kaleshsingh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Oscar Salvador <osalvador@suse.de>
Cc: "Paul E . McKenney" <paulmck@kernel.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Cc: Shuah Khan <shuah@kernel.org>
Cc: Thomas Weißschuh <linux@weissschuh.net>
Cc: T.J. Mercier <tjmercier@google.com>
Cc: Ye Bin <yebin10@huawei.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 fs/proc/internal.h        |   5 ++
 fs/proc/task_mmu.c        | 141 +++++++++++++++++++++++++++++++++++++++++++---
 include/linux/mmap_lock.h |  11 ++++
 mm/madvise.c              |   3 +-
 mm/mmap_lock.c            |  93 ++++++++++++++++++++++++++++++
 5 files changed, 244 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 3d48ffe72583..7c235451c5ea 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -384,6 +384,11 @@ struct proc_maps_private {
 	struct task_struct *task;
 	struct mm_struct *mm;
 	struct vma_iterator iter;
+	loff_t last_pos;
+#ifdef CONFIG_PER_VMA_LOCK
+	bool mmap_locked;
+	struct vm_area_struct *locked_vma;
+#endif
 #ifdef CONFIG_NUMA
 	struct mempolicy *task_mempolicy;
 #endif
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 90237df1ed33..3d6d8a9f13fc 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -130,13 +130,132 @@ static void release_task_mempolicy(struct proc_maps_private *priv)
 }
 #endif
 
-static struct vm_area_struct *proc_get_vma(struct proc_maps_private *priv,
-						loff_t *ppos)
+#ifdef CONFIG_PER_VMA_LOCK
+
+static void unlock_vma(struct proc_maps_private *priv)
+{
+	if (priv->locked_vma) {
+		vma_end_read(priv->locked_vma);
+		priv->locked_vma = NULL;
+	}
+}
+
+static const struct seq_operations proc_pid_maps_op;
+
+static inline bool lock_vma_range(struct seq_file *m,
+				  struct proc_maps_private *priv)
+{
+	/*
+	 * smaps and numa_maps perform page table walk, therefore require
+	 * mmap_lock but maps can be read with locking just the vma and
+	 * walking the vma tree under rcu read protection.
+	 */
+	if (m->op != &proc_pid_maps_op) {
+		if (mmap_read_lock_killable(priv->mm))
+			return false;
+
+		priv->mmap_locked = true;
+	} else {
+		rcu_read_lock();
+		priv->locked_vma = NULL;
+		priv->mmap_locked = false;
+	}
+
+	return true;
+}
+
+static inline void unlock_vma_range(struct proc_maps_private *priv)
+{
+	if (priv->mmap_locked) {
+		mmap_read_unlock(priv->mm);
+	} else {
+		unlock_vma(priv);
+		rcu_read_unlock();
+	}
+}
+
+static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv,
+					   loff_t last_pos)
+{
+	struct vm_area_struct *vma;
+
+	if (priv->mmap_locked)
+		return vma_next(&priv->iter);
+
+	unlock_vma(priv);
+	vma = lock_next_vma(priv->mm, &priv->iter, last_pos);
+	if (!IS_ERR_OR_NULL(vma))
+		priv->locked_vma = vma;
+
+	return vma;
+}
+
+static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv,
+					 loff_t pos)
 {
-	struct vm_area_struct *vma = vma_next(&priv->iter);
+	if (priv->mmap_locked)
+		return false;
+
+	rcu_read_unlock();
+	mmap_read_lock(priv->mm);
+	/* Reinitialize the iterator after taking mmap_lock */
+	vma_iter_set(&priv->iter, pos);
+	priv->mmap_locked = true;
 
+	return true;
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline bool lock_vma_range(struct seq_file *m,
+				  struct proc_maps_private *priv)
+{
+	return mmap_read_lock_killable(priv->mm) == 0;
+}
+
+static inline void unlock_vma_range(struct proc_maps_private *priv)
+{
+	mmap_read_unlock(priv->mm);
+}
+
+static struct vm_area_struct *get_next_vma(struct proc_maps_private *priv,
+					   loff_t last_pos)
+{
+	return vma_next(&priv->iter);
+}
+
+static inline bool fallback_to_mmap_lock(struct proc_maps_private *priv,
+					 loff_t pos)
+{
+	return false;
+}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
+static struct vm_area_struct *proc_get_vma(struct seq_file *m, loff_t *ppos)
+{
+	struct proc_maps_private *priv = m->private;
+	struct vm_area_struct *vma;
+
+retry:
+	vma = get_next_vma(priv, *ppos);
+	/* EINTR of EAGAIN is possible */
+	if (IS_ERR(vma)) {
+		if (PTR_ERR(vma) == -EAGAIN && fallback_to_mmap_lock(priv, *ppos))
+			goto retry;
+
+		return vma;
+	}
+
+	/* Store previous position to be able to restart if needed */
+	priv->last_pos = *ppos;
 	if (vma) {
-		*ppos = vma->vm_start;
+		/*
+		 * Track the end of the reported vma to ensure position changes
+		 * even if previous vma was merged with the next vma and we
+		 * found the extended vma with the same vm_start.
+		 */
+		*ppos = vma->vm_end;
 	} else {
 		*ppos = SENTINEL_VMA_GATE;
 		vma = get_gate_vma(priv->mm);
@@ -166,19 +285,25 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
 		return NULL;
 	}
 
-	if (mmap_read_lock_killable(mm)) {
+	if (!lock_vma_range(m, priv)) {
 		mmput(mm);
 		put_task_struct(priv->task);
 		priv->task = NULL;
 		return ERR_PTR(-EINTR);
 	}
 
+	/*
+	 * Reset current position if last_addr was set before
+	 * and it's not a sentinel.
+	 */
+	if (last_addr > 0)
+		*ppos = last_addr = priv->last_pos;
 	vma_iter_init(&priv->iter, mm, (unsigned long)last_addr);
 	hold_task_mempolicy(priv);
 	if (last_addr == SENTINEL_VMA_GATE)
 		return get_gate_vma(mm);
 
-	return proc_get_vma(priv, ppos);
+	return proc_get_vma(m, ppos);
 }
 
 static void *m_next(struct seq_file *m, void *v, loff_t *ppos)
@@ -187,7 +312,7 @@ static void *m_next(struct seq_file *m, void *v, loff_t *ppos)
 		*ppos = SENTINEL_VMA_END;
 		return NULL;
 	}
-	return proc_get_vma(m->private, ppos);
+	return proc_get_vma(m, ppos);
 }
 
 static void m_stop(struct seq_file *m, void *v)
@@ -199,7 +324,7 @@ static void m_stop(struct seq_file *m, void *v)
 		return;
 
 	release_task_mempolicy(priv);
-	mmap_read_unlock(mm);
+	unlock_vma_range(priv);
 	mmput(mm);
 	put_task_struct(priv->task);
 	priv->task = NULL;
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 5da384bd0a26..1f4f44951abe 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -309,6 +309,17 @@ void vma_mark_detached(struct vm_area_struct *vma);
 struct vm_area_struct *lock_vma_under_rcu(struct mm_struct *mm,
 					  unsigned long address);
 
+/*
+ * Locks next vma pointed by the iterator. Confirms the locked vma has not
+ * been modified and will retry under mmap_lock protection if modification
+ * was detected. Should be called from read RCU section.
+ * Returns either a valid locked VMA, NULL if no more VMAs or -EINTR if the
+ * process was interrupted.
+ */
+struct vm_area_struct *lock_next_vma(struct mm_struct *mm,
+				     struct vma_iterator *iter,
+				     unsigned long address);
+
 #else /* CONFIG_PER_VMA_LOCK */
 
 static inline void mm_lock_seqcount_init(struct mm_struct *mm) {}
diff --git a/mm/madvise.c b/mm/madvise.c
index 2bf80989d5b6..bb80fc5ea08f 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -108,7 +108,8 @@ void anon_vma_name_free(struct kref *kref)
 
 struct anon_vma_name *anon_vma_name(struct vm_area_struct *vma)
 {
-	mmap_assert_locked(vma->vm_mm);
+	if (!rwsem_is_locked(&vma->vm_mm->mmap_lock))
+		vma_assert_locked(vma);
 
 	return vma->anon_name;
 }
diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
index 5f725cc67334..729fb7d0dd59 100644
--- a/mm/mmap_lock.c
+++ b/mm/mmap_lock.c
@@ -178,6 +178,99 @@ inval:
 	count_vm_vma_lock_event(VMA_LOCK_ABORT);
 	return NULL;
 }
+
+static struct vm_area_struct *lock_next_vma_under_mmap_lock(struct mm_struct *mm,
+							    struct vma_iterator *vmi,
+							    unsigned long from_addr)
+{
+	struct vm_area_struct *vma;
+	int ret;
+
+	ret = mmap_read_lock_killable(mm);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/* Lookup the vma at the last position again under mmap_read_lock */
+	vma_iter_set(vmi, from_addr);
+	vma = vma_next(vmi);
+	if (vma) {
+		/* Very unlikely vma->vm_refcnt overflow case */
+		if (unlikely(!vma_start_read_locked(vma)))
+			vma = ERR_PTR(-EAGAIN);
+	}
+
+	mmap_read_unlock(mm);
+
+	return vma;
+}
+
+struct vm_area_struct *lock_next_vma(struct mm_struct *mm,
+				     struct vma_iterator *vmi,
+				     unsigned long from_addr)
+{
+	struct vm_area_struct *vma;
+	unsigned int mm_wr_seq;
+	bool mmap_unlocked;
+
+	RCU_LOCKDEP_WARN(!rcu_read_lock_held(), "no rcu read lock held");
+retry:
+	/* Start mmap_lock speculation in case we need to verify the vma later */
+	mmap_unlocked = mmap_lock_speculate_try_begin(mm, &mm_wr_seq);
+	vma = vma_next(vmi);
+	if (!vma)
+		return NULL;
+
+	vma = vma_start_read(mm, vma);
+	if (IS_ERR_OR_NULL(vma)) {
+		/*
+		 * Retry immediately if the vma gets detached from under us.
+		 * Infinite loop should not happen because the vma we find will
+		 * have to be constantly knocked out from under us.
+		 */
+		if (PTR_ERR(vma) == -EAGAIN) {
+			/* reset to search from the last address */
+			vma_iter_set(vmi, from_addr);
+			goto retry;
+		}
+
+		goto fallback;
+	}
+
+	/*
+	 * Verify the vma we locked belongs to the same address space and it's
+	 * not behind of the last search position.
+	 */
+	if (unlikely(vma->vm_mm != mm || from_addr >= vma->vm_end))
+		goto fallback_unlock;
+
+	/*
+	 * vma can be ahead of the last search position but we need to verify
+	 * it was not shrunk after we found it and another vma has not been
+	 * installed ahead of it. Otherwise we might observe a gap that should
+	 * not be there.
+	 */
+	if (from_addr < vma->vm_start) {
+		/* Verify only if the address space might have changed since vma lookup. */
+		if (!mmap_unlocked || mmap_lock_speculate_retry(mm, mm_wr_seq)) {
+			vma_iter_set(vmi, from_addr);
+			if (vma != vma_next(vmi))
+				goto fallback_unlock;
+		}
+	}
+
+	return vma;
+
+fallback_unlock:
+	vma_end_read(vma);
+fallback:
+	rcu_read_unlock();
+	vma = lock_next_vma_under_mmap_lock(mm, vmi, from_addr);
+	rcu_read_lock();
+	/* Reinitialize the iterator after re-entering rcu read section */
+	vma_iter_set(vmi, IS_ERR_OR_NULL(vma) ? from_addr : vma->vm_end);
+
+	return vma;
+}
 #endif /* CONFIG_PER_VMA_LOCK */
 
 #ifdef CONFIG_LOCK_MM_AND_FIND_VMA
-- 
cgit v1.2.3


From 0aa3657df3ec713fca1f00a57a063b28f2a78147 Mon Sep 17 00:00:00 2001
From: Dev Jain <dev.jain@arm.com>
Date: Fri, 18 Jul 2025 14:32:40 +0530
Subject: mm: add batched versions of ptep_modify_prot_start/commit

Batch ptep_modify_prot_start/commit in preparation for optimizing
mprotect, implementing them as a simple loop over the corresponding single
pte helpers.  Architecture may override these helpers.

Link: https://lkml.kernel.org/r/20250718090244.21092-4-dev.jain@arm.com
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Ryan Roberts <ryan.roberts@arm.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Anshuman Khandual <anshuman.khandual@arm.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Christophe Leroy <christophe.leroy@csgroup.eu>
Cc: David Hildenbrand <david@redhat.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jann Horn <jannh@google.com>
Cc: Joey Gouly <joey.gouly@arm.com>
Cc: Kevin Brodsky <kevin.brodsky@arm.com>
Cc: Lance Yang <ioworker0@gmail.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Matthew Wilcox (Oracle) <willy@infradead.org>
Cc: Peter Xu <peterx@redhat.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Cc: Will Deacon <will@kernel.org>
Cc: Yang Shi <yang@os.amperecomputing.com>
Cc: Yicong Yang <yangyicong@hisilicon.com>
Cc: Zhenhua Huang <quic_zhenhuah@quicinc.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pgtable.h | 84 ++++++++++++++++++++++++++++++++++++++++++++++++-
 mm/mprotect.c           |  4 +--
 2 files changed, 85 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index cf1515c163e2..e3b99920be05 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -1331,7 +1331,9 @@ static inline pte_t ptep_modify_prot_start(struct vm_area_struct *vma,
 
 /*
  * Commit an update to a pte, leaving any hardware-controlled bits in
- * the PTE unmodified.
+ * the PTE unmodified. The pte returned from ptep_modify_prot_start() may
+ * additionally have young and/or dirty bits set where previously they were not,
+ * so the updated pte may have these additional changes.
  */
 static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 					   unsigned long addr,
@@ -1340,6 +1342,86 @@ static inline void ptep_modify_prot_commit(struct vm_area_struct *vma,
 	__ptep_modify_prot_commit(vma, addr, ptep, pte);
 }
 #endif /* __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION */
+
+/**
+ * modify_prot_start_ptes - Start a pte protection read-modify-write transaction
+ * over a batch of ptes, which protects against asynchronous hardware
+ * modifications to the ptes. The intention is not to prevent the hardware from
+ * making pte updates, but to prevent any updates it may make from being lost.
+ * Please see the comment above ptep_modify_prot_start() for full description.
+ *
+ * @vma: The virtual memory area the pages are mapped into.
+ * @addr: Address the first page is mapped at.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over ptep_modify_prot_start(), collecting the a/d bits from each pte
+ * in the batch.
+ *
+ * Note that PTE bits in the PTE batch besides the PFN can differ.
+ *
+ * Context: The caller holds the page table lock.  The PTEs map consecutive
+ * pages that belong to the same folio. All other PTE bits must be identical for
+ * all PTEs in the batch except for young and dirty bits.  The PTEs are all in
+ * the same PMD.
+ */
+#ifndef modify_prot_start_ptes
+static inline pte_t modify_prot_start_ptes(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep, unsigned int nr)
+{
+	pte_t pte, tmp_pte;
+
+	pte = ptep_modify_prot_start(vma, addr, ptep);
+	while (--nr) {
+		ptep++;
+		addr += PAGE_SIZE;
+		tmp_pte = ptep_modify_prot_start(vma, addr, ptep);
+		if (pte_dirty(tmp_pte))
+			pte = pte_mkdirty(pte);
+		if (pte_young(tmp_pte))
+			pte = pte_mkyoung(pte);
+	}
+	return pte;
+}
+#endif
+
+/**
+ * modify_prot_commit_ptes - Commit an update to a batch of ptes, leaving any
+ * hardware-controlled bits in the PTE unmodified.
+ *
+ * @vma: The virtual memory area the pages are mapped into.
+ * @addr: Address the first page is mapped at.
+ * @ptep: Page table pointer for the first entry.
+ * @old_pte: Old page table entry (for the first entry) which is now cleared.
+ * @pte: New page table entry to be set.
+ * @nr: Number of entries.
+ *
+ * May be overridden by the architecture; otherwise, implemented as a simple
+ * loop over ptep_modify_prot_commit().
+ *
+ * Context: The caller holds the page table lock. The PTEs are all in the same
+ * PMD. On exit, the set ptes in the batch map the same folio. The ptes set by
+ * ptep_modify_prot_start() may additionally have young and/or dirty bits set
+ * where previously they were not, so the updated ptes may have these
+ * additional changes.
+ */
+#ifndef modify_prot_commit_ptes
+static inline void modify_prot_commit_ptes(struct vm_area_struct *vma, unsigned long addr,
+		pte_t *ptep, pte_t old_pte, pte_t pte, unsigned int nr)
+{
+	int i;
+
+	for (i = 0; i < nr; ++i, ++ptep, addr += PAGE_SIZE) {
+		ptep_modify_prot_commit(vma, addr, ptep, old_pte, pte);
+
+		/* Advance PFN only, set same prot */
+		old_pte = pte_next_pfn(old_pte);
+		pte = pte_next_pfn(pte);
+	}
+}
+#endif
+
 #endif /* CONFIG_MMU */
 
 /*
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 97adc62c50ab..4977f198168e 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -204,7 +204,7 @@ static long change_pte_range(struct mmu_gather *tlb,
 				}
 			}
 
-			oldpte = ptep_modify_prot_start(vma, addr, pte);
+			oldpte = modify_prot_start_ptes(vma, addr, pte, nr_ptes);
 			ptent = pte_modify(oldpte, newprot);
 
 			if (uffd_wp)
@@ -230,7 +230,7 @@ static long change_pte_range(struct mmu_gather *tlb,
 			    can_change_pte_writable(vma, addr, ptent))
 				ptent = pte_mkwrite(ptent, vma);
 
-			ptep_modify_prot_commit(vma, addr, pte, oldpte, ptent);
+			modify_prot_commit_ptes(vma, addr, pte, oldpte, ptent, nr_ptes);
 			if (pte_needs_flush(oldpte, ptent))
 				tlb_flush_pte_range(tlb, addr, PAGE_SIZE);
 			pages++;
-- 
cgit v1.2.3


From 45cd52c44e85453c9147d41b715cd03c53325cf4 Mon Sep 17 00:00:00 2001
From: "Matthew Wilcox (Oracle)" <willy@infradead.org>
Date: Mon, 21 Jul 2025 21:46:18 +0100
Subject: mm: remove grab_cache_page()

All callers have been converted to use filemap_grab_folio().

Link: https://lkml.kernel.org/r/20250721204619.163883-1-willy@infradead.org
Signed-off-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/pagemap.h | 12 ++----------
 1 file changed, 2 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 10a222e68b85..a5ef64a15f96 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -878,7 +878,8 @@ static inline struct page *find_or_create_page(struct address_space *mapping,
  * @mapping: target address_space
  * @index: the page index
  *
- * Same as grab_cache_page(), but do not wait if the page is unavailable.
+ * Returns locked page at given index in given cache, creating it if
+ * needed, but do not wait if the page is locked or to reclaim memory.
  * This is intended for speculative data generators, where the data can
  * be regenerated if the page couldn't be grabbed.  This routine should
  * be safe to call while holding the lock for another page.
@@ -942,15 +943,6 @@ unsigned filemap_get_folios_contig(struct address_space *mapping,
 unsigned filemap_get_folios_tag(struct address_space *mapping, pgoff_t *start,
 		pgoff_t end, xa_mark_t tag, struct folio_batch *fbatch);
 
-/*
- * Returns locked page at given index in given cache, creating it if needed.
- */
-static inline struct page *grab_cache_page(struct address_space *mapping,
-								pgoff_t index)
-{
-	return find_or_create_page(mapping, index, mapping_gfp_mask(mapping));
-}
-
 struct folio *read_cache_folio(struct address_space *, pgoff_t index,
 		filler_t *filler, struct file *file);
 struct folio *mapping_read_folio_gfp(struct address_space *, pgoff_t index,
-- 
cgit v1.2.3


From ffc72771ff6ec9f5b431a86c4b00d8ef0fea958b Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Fri, 25 Jul 2025 13:03:27 +0200
Subject: regmap: Annotate that MMIO implies fast IO

Document that using the MMIO helpers will automatically enable the
'fast_io' parameter. This makes the used locking scheme more transparent
and avoids superfluous setting of this parameter in drivers.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Link: https://patch.msgid.link/20250725110337.4303-2-wsa+renesas@sang-engineering.com
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 include/linux/regmap.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/regmap.h b/include/linux/regmap.h
index 02b83f5499b8..4e1ac1fbcec4 100644
--- a/include/linux/regmap.h
+++ b/include/linux/regmap.h
@@ -913,7 +913,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
  * @config: Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer to
- * a struct regmap.
+ * a struct regmap. Implies 'fast_io'.
  */
 #define regmap_init_mmio_clk(dev, clk_id, regs, config)			\
 	__regmap_lockdep_wrapper(__regmap_init_mmio_clk, #config,	\
@@ -927,7 +927,7 @@ int regmap_attach_dev(struct device *dev, struct regmap *map,
  * @config: Configuration for register map
  *
  * The return value will be an ERR_PTR() on error or a valid pointer to
- * a struct regmap.
+ * a struct regmap. Implies 'fast_io'.
  */
 #define regmap_init_mmio(dev, regs, config)		\
 	regmap_init_mmio_clk(dev, NULL, regs, config)
@@ -1138,7 +1138,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
  *
  * The return value will be an ERR_PTR() on error or a valid pointer
  * to a struct regmap.  The regmap will be automatically freed by the
- * device management code.
+ * device management code. Implies 'fast_io'.
  */
 #define devm_regmap_init_mmio_clk(dev, clk_id, regs, config)		\
 	__regmap_lockdep_wrapper(__devm_regmap_init_mmio_clk, #config,	\
@@ -1153,7 +1153,7 @@ bool regmap_ac97_default_volatile(struct device *dev, unsigned int reg);
  *
  * The return value will be an ERR_PTR() on error or a valid pointer
  * to a struct regmap.  The regmap will be automatically freed by the
- * device management code.
+ * device management code. Implies 'fast_io'.
  */
 #define devm_regmap_init_mmio(dev, regs, config)		\
 	devm_regmap_init_mmio_clk(dev, NULL, regs, config)
-- 
cgit v1.2.3


From 24cbfe18d55a6866bc2e27fda74306f4a1b5cb01 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Thu, 24 Jul 2025 19:33:27 +0200
Subject: rv: Merge struct rv_monitor_def into struct rv_monitor

Each struct rv_monitor has a unique struct rv_monitor_def associated with
it. struct rv_monitor is statically allocated, while struct rv_monitor_def
is dynamically allocated.

This makes the code more complicated than it should be:

  - Lookup is required to get the associated rv_monitor_def from rv_monitor

  - Dynamic memory allocation is required for rv_monitor_def. This is
    harder to get right compared to static memory. For instance, there is
    an existing mistake: rv_unregister_monitor() does not free the memory
    allocated by rv_register_monitor(). This is fortunately not a real
    memory leak problem, as rv_unregister_monitor() is never called.

Simplify and merge rv_monitor_def into rv_monitor.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/194449c00f87945c207aab4c96920c75796a4f53.1753378331.git.namcao@linutronix.de
Reviewed-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/rv.h            |   8 ++
 kernel/trace/rv/rv.c          | 211 +++++++++++++++++++-----------------------
 kernel/trace/rv/rv.h          |  27 ++----
 kernel/trace/rv/rv_reactors.c |  62 ++++++-------
 4 files changed, 140 insertions(+), 168 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rv.h b/include/linux/rv.h
index 97baf58d88b2..dba53aecdfab 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -7,6 +7,9 @@
 #ifndef _LINUX_RV_H
 #define _LINUX_RV_H
 
+#include <linux/types.h>
+#include <linux/list.h>
+
 #define MAX_DA_NAME_LEN	32
 
 #ifdef CONFIG_RV
@@ -98,8 +101,13 @@ struct rv_monitor {
 	void			(*disable)(void);
 	void			(*reset)(void);
 #ifdef CONFIG_RV_REACTORS
+	struct rv_reactor_def	*rdef;
 	__printf(1, 2) void	(*react)(const char *msg, ...);
+	bool			reacting;
 #endif
+	struct list_head	list;
+	struct rv_monitor	*parent;
+	struct dentry		*root_d;
 };
 
 bool rv_monitoring_on(void);
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 108429d16ec1..6c0be2fdc52d 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -210,9 +210,9 @@ void rv_put_task_monitor_slot(int slot)
  * Monitors with a parent are nested,
  * Monitors without a parent could be standalone or containers.
  */
-bool rv_is_nested_monitor(struct rv_monitor_def *mdef)
+bool rv_is_nested_monitor(struct rv_monitor *mon)
 {
-	return mdef->parent != NULL;
+	return mon->parent != NULL;
 }
 
 /*
@@ -223,16 +223,16 @@ bool rv_is_nested_monitor(struct rv_monitor_def *mdef)
  * for enable()/disable(). Use this condition to find empty containers.
  * Keep both conditions in case we have some non-compliant containers.
  */
-bool rv_is_container_monitor(struct rv_monitor_def *mdef)
+bool rv_is_container_monitor(struct rv_monitor *mon)
 {
-	struct rv_monitor_def *next;
+	struct rv_monitor *next;
 
-	if (list_is_last(&mdef->list, &rv_monitors_list))
+	if (list_is_last(&mon->list, &rv_monitors_list))
 		return false;
 
-	next = list_next_entry(mdef, list);
+	next = list_next_entry(mon, list);
 
-	return next->parent == mdef->monitor || !mdef->monitor->enable;
+	return next->parent == mon || !mon->enable;
 }
 
 /*
@@ -241,10 +241,10 @@ bool rv_is_container_monitor(struct rv_monitor_def *mdef)
 static ssize_t monitor_enable_read_data(struct file *filp, char __user *user_buf, size_t count,
 					loff_t *ppos)
 {
-	struct rv_monitor_def *mdef = filp->private_data;
+	struct rv_monitor *mon = filp->private_data;
 	const char *buff;
 
-	buff = mdef->monitor->enabled ? "1\n" : "0\n";
+	buff = mon->enabled ? "1\n" : "0\n";
 
 	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff)+1);
 }
@@ -252,14 +252,14 @@ static ssize_t monitor_enable_read_data(struct file *filp, char __user *user_buf
 /*
  * __rv_disable_monitor - disabled an enabled monitor
  */
-static int __rv_disable_monitor(struct rv_monitor_def *mdef, bool sync)
+static int __rv_disable_monitor(struct rv_monitor *mon, bool sync)
 {
 	lockdep_assert_held(&rv_interface_lock);
 
-	if (mdef->monitor->enabled) {
-		mdef->monitor->enabled = 0;
-		if (mdef->monitor->disable)
-			mdef->monitor->disable();
+	if (mon->enabled) {
+		mon->enabled = 0;
+		if (mon->disable)
+			mon->disable();
 
 		/*
 		 * Wait for the execution of all events to finish.
@@ -273,90 +273,90 @@ static int __rv_disable_monitor(struct rv_monitor_def *mdef, bool sync)
 	return 0;
 }
 
-static void rv_disable_single(struct rv_monitor_def *mdef)
+static void rv_disable_single(struct rv_monitor *mon)
 {
-	__rv_disable_monitor(mdef, true);
+	__rv_disable_monitor(mon, true);
 }
 
-static int rv_enable_single(struct rv_monitor_def *mdef)
+static int rv_enable_single(struct rv_monitor *mon)
 {
 	int retval;
 
 	lockdep_assert_held(&rv_interface_lock);
 
-	if (mdef->monitor->enabled)
+	if (mon->enabled)
 		return 0;
 
-	retval = mdef->monitor->enable();
+	retval = mon->enable();
 
 	if (!retval)
-		mdef->monitor->enabled = 1;
+		mon->enabled = 1;
 
 	return retval;
 }
 
-static void rv_disable_container(struct rv_monitor_def *mdef)
+static void rv_disable_container(struct rv_monitor *mon)
 {
-	struct rv_monitor_def *p = mdef;
+	struct rv_monitor *p = mon;
 	int enabled = 0;
 
 	list_for_each_entry_continue(p, &rv_monitors_list, list) {
-		if (p->parent != mdef->monitor)
+		if (p->parent != mon)
 			break;
 		enabled += __rv_disable_monitor(p, false);
 	}
 	if (enabled)
 		tracepoint_synchronize_unregister();
-	mdef->monitor->enabled = 0;
+	mon->enabled = 0;
 }
 
-static int rv_enable_container(struct rv_monitor_def *mdef)
+static int rv_enable_container(struct rv_monitor *mon)
 {
-	struct rv_monitor_def *p = mdef;
+	struct rv_monitor *p = mon;
 	int retval = 0;
 
 	list_for_each_entry_continue(p, &rv_monitors_list, list) {
-		if (retval || p->parent != mdef->monitor)
+		if (retval || p->parent != mon)
 			break;
 		retval = rv_enable_single(p);
 	}
 	if (retval)
-		rv_disable_container(mdef);
+		rv_disable_container(mon);
 	else
-		mdef->monitor->enabled = 1;
+		mon->enabled = 1;
 	return retval;
 }
 
 /**
  * rv_disable_monitor - disable a given runtime monitor
- * @mdef: Pointer to the monitor definition structure.
+ * @mon: Pointer to the monitor definition structure.
  *
  * Returns 0 on success.
  */
-int rv_disable_monitor(struct rv_monitor_def *mdef)
+int rv_disable_monitor(struct rv_monitor *mon)
 {
-	if (rv_is_container_monitor(mdef))
-		rv_disable_container(mdef);
+	if (rv_is_container_monitor(mon))
+		rv_disable_container(mon);
 	else
-		rv_disable_single(mdef);
+		rv_disable_single(mon);
 
 	return 0;
 }
 
 /**
  * rv_enable_monitor - enable a given runtime monitor
- * @mdef: Pointer to the monitor definition structure.
+ * @mon: Pointer to the monitor definition structure.
  *
  * Returns 0 on success, error otherwise.
  */
-int rv_enable_monitor(struct rv_monitor_def *mdef)
+int rv_enable_monitor(struct rv_monitor *mon)
 {
 	int retval;
 
-	if (rv_is_container_monitor(mdef))
-		retval = rv_enable_container(mdef);
+	if (rv_is_container_monitor(mon))
+		retval = rv_enable_container(mon);
 	else
-		retval = rv_enable_single(mdef);
+		retval = rv_enable_single(mon);
 
 	return retval;
 }
@@ -367,7 +367,7 @@ int rv_enable_monitor(struct rv_monitor_def *mdef)
 static ssize_t monitor_enable_write_data(struct file *filp, const char __user *user_buf,
 					 size_t count, loff_t *ppos)
 {
-	struct rv_monitor_def *mdef = filp->private_data;
+	struct rv_monitor *mon = filp->private_data;
 	int retval;
 	bool val;
 
@@ -378,9 +378,9 @@ static ssize_t monitor_enable_write_data(struct file *filp, const char __user *u
 	mutex_lock(&rv_interface_lock);
 
 	if (val)
-		retval = rv_enable_monitor(mdef);
+		retval = rv_enable_monitor(mon);
 	else
-		retval = rv_disable_monitor(mdef);
+		retval = rv_disable_monitor(mon);
 
 	mutex_unlock(&rv_interface_lock);
 
@@ -399,12 +399,12 @@ static const struct file_operations interface_enable_fops = {
 static ssize_t monitor_desc_read_data(struct file *filp, char __user *user_buf, size_t count,
 				      loff_t *ppos)
 {
-	struct rv_monitor_def *mdef = filp->private_data;
+	struct rv_monitor *mon = filp->private_data;
 	char buff[256];
 
 	memset(buff, 0, sizeof(buff));
 
-	snprintf(buff, sizeof(buff), "%s\n", mdef->monitor->description);
+	snprintf(buff, sizeof(buff), "%s\n", mon->description);
 
 	return simple_read_from_buffer(user_buf, count, ppos, buff, strlen(buff) + 1);
 }
@@ -419,37 +419,37 @@ static const struct file_operations interface_desc_fops = {
  * the monitor dir, where the specific options of the monitor
  * are exposed.
  */
-static int create_monitor_dir(struct rv_monitor_def *mdef, struct rv_monitor_def *parent)
+static int create_monitor_dir(struct rv_monitor *mon, struct rv_monitor *parent)
 {
 	struct dentry *root = parent ? parent->root_d : get_monitors_root();
-	const char *name = mdef->monitor->name;
+	const char *name = mon->name;
 	struct dentry *tmp;
 	int retval;
 
-	mdef->root_d = rv_create_dir(name, root);
-	if (!mdef->root_d)
+	mon->root_d = rv_create_dir(name, root);
+	if (!mon->root_d)
 		return -ENOMEM;
 
-	tmp = rv_create_file("enable", RV_MODE_WRITE, mdef->root_d, mdef, &interface_enable_fops);
+	tmp = rv_create_file("enable", RV_MODE_WRITE, mon->root_d, mon, &interface_enable_fops);
 	if (!tmp) {
 		retval = -ENOMEM;
 		goto out_remove_root;
 	}
 
-	tmp = rv_create_file("desc", RV_MODE_READ, mdef->root_d, mdef, &interface_desc_fops);
+	tmp = rv_create_file("desc", RV_MODE_READ, mon->root_d, mon, &interface_desc_fops);
 	if (!tmp) {
 		retval = -ENOMEM;
 		goto out_remove_root;
 	}
 
-	retval = reactor_populate_monitor(mdef);
+	retval = reactor_populate_monitor(mon);
 	if (retval)
 		goto out_remove_root;
 
 	return 0;
 
 out_remove_root:
-	rv_remove(mdef->root_d);
+	rv_remove(mon->root_d);
 	return retval;
 }
 
@@ -458,13 +458,12 @@ out_remove_root:
  */
 static int monitors_show(struct seq_file *m, void *p)
 {
-	struct rv_monitor_def *mon_def = p;
+	struct rv_monitor *mon = p;
 
-	if (mon_def->parent)
-		seq_printf(m, "%s:%s\n", mon_def->parent->name,
-			   mon_def->monitor->name);
+	if (mon->parent)
+		seq_printf(m, "%s:%s\n", mon->parent->name, mon->name);
 	else
-		seq_printf(m, "%s\n", mon_def->monitor->name);
+		seq_printf(m, "%s\n", mon->name);
 	return 0;
 }
 
@@ -496,13 +495,13 @@ static void *available_monitors_next(struct seq_file *m, void *p, loff_t *pos)
  */
 static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos)
 {
-	struct rv_monitor_def *m_def = p;
+	struct rv_monitor *mon = p;
 
 	(*pos)++;
 
-	list_for_each_entry_continue(m_def, &rv_monitors_list, list) {
-		if (m_def->monitor->enabled)
-			return m_def;
+	list_for_each_entry_continue(mon, &rv_monitors_list, list) {
+		if (mon->enabled)
+			return mon;
 	}
 
 	return NULL;
@@ -510,7 +509,7 @@ static void *enabled_monitors_next(struct seq_file *m, void *p, loff_t *pos)
 
 static void *enabled_monitors_start(struct seq_file *m, loff_t *pos)
 {
-	struct rv_monitor_def *m_def;
+	struct rv_monitor *mon;
 	loff_t l;
 
 	mutex_lock(&rv_interface_lock);
@@ -518,15 +517,15 @@ static void *enabled_monitors_start(struct seq_file *m, loff_t *pos)
 	if (list_empty(&rv_monitors_list))
 		return NULL;
 
-	m_def = list_entry(&rv_monitors_list, struct rv_monitor_def, list);
+	mon = list_entry(&rv_monitors_list, struct rv_monitor, list);
 
 	for (l = 0; l <= *pos; ) {
-		m_def = enabled_monitors_next(m, m_def, &l);
-		if (!m_def)
+		mon = enabled_monitors_next(m, mon, &l);
+		if (!mon)
 			break;
 	}
 
-	return m_def;
+	return mon;
 }
 
 /*
@@ -566,13 +565,13 @@ static const struct file_operations available_monitors_ops = {
  */
 static void disable_all_monitors(void)
 {
-	struct rv_monitor_def *mdef;
+	struct rv_monitor *mon;
 	int enabled = 0;
 
 	mutex_lock(&rv_interface_lock);
 
-	list_for_each_entry(mdef, &rv_monitors_list, list)
-		enabled += __rv_disable_monitor(mdef, false);
+	list_for_each_entry(mon, &rv_monitors_list, list)
+		enabled += __rv_disable_monitor(mon, false);
 
 	if (enabled) {
 		/*
@@ -598,7 +597,7 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user
 				      size_t count, loff_t *ppos)
 {
 	char buff[MAX_RV_MONITOR_NAME_SIZE + 2];
-	struct rv_monitor_def *mdef;
+	struct rv_monitor *mon;
 	int retval = -EINVAL;
 	bool enable = true;
 	char *ptr, *tmp;
@@ -633,17 +632,17 @@ static ssize_t enabled_monitors_write(struct file *filp, const char __user *user
 	if (tmp)
 		ptr = tmp+1;
 
-	list_for_each_entry(mdef, &rv_monitors_list, list) {
-		if (strcmp(ptr, mdef->monitor->name) != 0)
+	list_for_each_entry(mon, &rv_monitors_list, list) {
+		if (strcmp(ptr, mon->name) != 0)
 			continue;
 
 		/*
 		 * Monitor found!
 		 */
 		if (enable)
-			retval = rv_enable_monitor(mdef);
+			retval = rv_enable_monitor(mon);
 		else
-			retval = rv_disable_monitor(mdef);
+			retval = rv_disable_monitor(mon);
 
 		if (!retval)
 			retval = count;
@@ -702,11 +701,11 @@ static void turn_monitoring_off(void)
 
 static void reset_all_monitors(void)
 {
-	struct rv_monitor_def *mdef;
+	struct rv_monitor *mon;
 
-	list_for_each_entry(mdef, &rv_monitors_list, list) {
-		if (mdef->monitor->enabled && mdef->monitor->reset)
-			mdef->monitor->reset();
+	list_for_each_entry(mon, &rv_monitors_list, list) {
+		if (mon->enabled && mon->reset)
+			mon->reset();
 	}
 }
 
@@ -768,10 +767,10 @@ static const struct file_operations monitoring_on_fops = {
 	.read   = monitoring_on_read_data,
 };
 
-static void destroy_monitor_dir(struct rv_monitor_def *mdef)
+static void destroy_monitor_dir(struct rv_monitor *mon)
 {
-	reactor_cleanup_monitor(mdef);
-	rv_remove(mdef->root_d);
+	reactor_cleanup_monitor(mon);
+	rv_remove(mon->root_d);
 }
 
 /**
@@ -783,7 +782,7 @@ static void destroy_monitor_dir(struct rv_monitor_def *mdef)
  */
 int rv_register_monitor(struct rv_monitor *monitor, struct rv_monitor *parent)
 {
-	struct rv_monitor_def *r, *p = NULL;
+	struct rv_monitor *r;
 	int retval = 0;
 
 	if (strlen(monitor->name) >= MAX_RV_MONITOR_NAME_SIZE) {
@@ -795,49 +794,31 @@ int rv_register_monitor(struct rv_monitor *monitor, struct rv_monitor *parent)
 	mutex_lock(&rv_interface_lock);
 
 	list_for_each_entry(r, &rv_monitors_list, list) {
-		if (strcmp(monitor->name, r->monitor->name) == 0) {
+		if (strcmp(monitor->name, r->name) == 0) {
 			pr_info("Monitor %s is already registered\n", monitor->name);
 			retval = -EEXIST;
 			goto out_unlock;
 		}
 	}
 
-	if (parent) {
-		list_for_each_entry(r, &rv_monitors_list, list) {
-			if (strcmp(parent->name, r->monitor->name) == 0) {
-				p = r;
-				break;
-			}
-		}
-	}
-
-	if (p && rv_is_nested_monitor(p)) {
+	if (parent && rv_is_nested_monitor(parent)) {
 		pr_info("Parent monitor %s is already nested, cannot nest further\n",
 			parent->name);
 		retval = -EINVAL;
 		goto out_unlock;
 	}
 
-	r = kzalloc(sizeof(struct rv_monitor_def), GFP_KERNEL);
-	if (!r) {
-		retval = -ENOMEM;
-		goto out_unlock;
-	}
-
-	r->monitor = monitor;
-	r->parent = parent;
+	monitor->parent = parent;
 
-	retval = create_monitor_dir(r, p);
-	if (retval) {
-		kfree(r);
-		goto out_unlock;
-	}
+	retval = create_monitor_dir(monitor, parent);
+	if (retval)
+		return retval;
 
 	/* keep children close to the parent for easier visualisation */
-	if (p)
-		list_add(&r->list, &p->list);
+	if (parent)
+		list_add(&monitor->list, &parent->list);
 	else
-		list_add_tail(&r->list, &rv_monitors_list);
+		list_add_tail(&monitor->list, &rv_monitors_list);
 
 out_unlock:
 	mutex_unlock(&rv_interface_lock);
@@ -852,17 +833,11 @@ out_unlock:
  */
 int rv_unregister_monitor(struct rv_monitor *monitor)
 {
-	struct rv_monitor_def *ptr, *next;
-
 	mutex_lock(&rv_interface_lock);
 
-	list_for_each_entry_safe(ptr, next, &rv_monitors_list, list) {
-		if (strcmp(monitor->name, ptr->monitor->name) == 0) {
-			rv_disable_monitor(ptr);
-			list_del(&ptr->list);
-			destroy_monitor_dir(ptr);
-		}
-	}
+	rv_disable_monitor(monitor);
+	list_del(&monitor->list);
+	destroy_monitor_dir(monitor);
 
 	mutex_unlock(&rv_interface_lock);
 	return 0;
diff --git a/kernel/trace/rv/rv.h b/kernel/trace/rv/rv.h
index 873364094402..f039ec1c9156 100644
--- a/kernel/trace/rv/rv.h
+++ b/kernel/trace/rv/rv.h
@@ -32,34 +32,23 @@ struct rv_reactor_def {
 };
 #endif
 
-struct rv_monitor_def {
-	struct list_head	list;
-	struct rv_monitor	*monitor;
-	struct rv_monitor	*parent;
-	struct dentry		*root_d;
-#ifdef CONFIG_RV_REACTORS
-	struct rv_reactor_def	*rdef;
-	bool			reacting;
-#endif
-};
-
 struct dentry *get_monitors_root(void);
-int rv_disable_monitor(struct rv_monitor_def *mdef);
-int rv_enable_monitor(struct rv_monitor_def *mdef);
-bool rv_is_container_monitor(struct rv_monitor_def *mdef);
-bool rv_is_nested_monitor(struct rv_monitor_def *mdef);
+int rv_disable_monitor(struct rv_monitor *mon);
+int rv_enable_monitor(struct rv_monitor *mon);
+bool rv_is_container_monitor(struct rv_monitor *mon);
+bool rv_is_nested_monitor(struct rv_monitor *mon);
 
 #ifdef CONFIG_RV_REACTORS
-int reactor_populate_monitor(struct rv_monitor_def *mdef);
-void reactor_cleanup_monitor(struct rv_monitor_def *mdef);
+int reactor_populate_monitor(struct rv_monitor *mon);
+void reactor_cleanup_monitor(struct rv_monitor *mon);
 int init_rv_reactors(struct dentry *root_dir);
 #else
-static inline int reactor_populate_monitor(struct rv_monitor_def *mdef)
+static inline int reactor_populate_monitor(struct rv_monitor *mon)
 {
 	return 0;
 }
 
-static inline void reactor_cleanup_monitor(struct rv_monitor_def *mdef)
+static inline void reactor_cleanup_monitor(struct rv_monitor *mon)
 {
 	return;
 }
diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c
index 740603670dd1..7cc620a1be1a 100644
--- a/kernel/trace/rv/rv_reactors.c
+++ b/kernel/trace/rv/rv_reactors.c
@@ -138,10 +138,10 @@ static const struct file_operations available_reactors_ops = {
  */
 static int monitor_reactor_show(struct seq_file *m, void *p)
 {
-	struct rv_monitor_def *mdef = m->private;
+	struct rv_monitor *mon = m->private;
 	struct rv_reactor_def *rdef = p;
 
-	if (mdef->rdef == rdef)
+	if (mon->rdef == rdef)
 		seq_printf(m, "[%s]\n", rdef->reactor->name);
 	else
 		seq_printf(m, "%s\n", rdef->reactor->name);
@@ -158,41 +158,41 @@ static const struct seq_operations monitor_reactors_seq_ops = {
 	.show	= monitor_reactor_show
 };
 
-static void monitor_swap_reactors_single(struct rv_monitor_def *mdef,
+static void monitor_swap_reactors_single(struct rv_monitor *mon,
 					 struct rv_reactor_def *rdef,
 					 bool reacting, bool nested)
 {
 	bool monitor_enabled;
 
 	/* nothing to do */
-	if (mdef->rdef == rdef)
+	if (mon->rdef == rdef)
 		return;
 
-	monitor_enabled = mdef->monitor->enabled;
+	monitor_enabled = mon->enabled;
 	if (monitor_enabled)
-		rv_disable_monitor(mdef);
+		rv_disable_monitor(mon);
 
 	/* swap reactor's usage */
-	mdef->rdef->counter--;
+	mon->rdef->counter--;
 	rdef->counter++;
 
-	mdef->rdef = rdef;
-	mdef->reacting = reacting;
-	mdef->monitor->react = rdef->reactor->react;
+	mon->rdef = rdef;
+	mon->reacting = reacting;
+	mon->react = rdef->reactor->react;
 
 	/* enable only once if iterating through a container */
 	if (monitor_enabled && !nested)
-		rv_enable_monitor(mdef);
+		rv_enable_monitor(mon);
 }
 
-static void monitor_swap_reactors(struct rv_monitor_def *mdef,
+static void monitor_swap_reactors(struct rv_monitor *mon,
 				  struct rv_reactor_def *rdef, bool reacting)
 {
-	struct rv_monitor_def *p = mdef;
+	struct rv_monitor *p = mon;
 
-	if (rv_is_container_monitor(mdef))
+	if (rv_is_container_monitor(mon))
 		list_for_each_entry_continue(p, &rv_monitors_list, list) {
-			if (p->parent != mdef->monitor)
+			if (p->parent != mon)
 				break;
 			monitor_swap_reactors_single(p, rdef, reacting, true);
 		}
@@ -202,7 +202,7 @@ static void monitor_swap_reactors(struct rv_monitor_def *mdef,
 	 * All nested monitors are enabled also if they were off, we may refine
 	 * this logic in the future.
 	 */
-	monitor_swap_reactors_single(mdef, rdef, reacting, false);
+	monitor_swap_reactors_single(mon, rdef, reacting, false);
 }
 
 static ssize_t
@@ -210,7 +210,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf,
 		      size_t count, loff_t *ppos)
 {
 	char buff[MAX_RV_REACTOR_NAME_SIZE + 2];
-	struct rv_monitor_def *mdef;
+	struct rv_monitor *mon;
 	struct rv_reactor_def *rdef;
 	struct seq_file *seq_f;
 	int retval = -EINVAL;
@@ -237,7 +237,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf,
 	 * See monitor_reactors_open()
 	 */
 	seq_f = file->private_data;
-	mdef = seq_f->private;
+	mon = seq_f->private;
 
 	mutex_lock(&rv_interface_lock);
 
@@ -252,7 +252,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf,
 		else
 			enable = true;
 
-		monitor_swap_reactors(mdef, rdef, enable);
+		monitor_swap_reactors(mon, rdef, enable);
 
 		retval = count;
 		break;
@@ -268,7 +268,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf,
  */
 static int monitor_reactors_open(struct inode *inode, struct file *file)
 {
-	struct rv_monitor_def *mdef = inode->i_private;
+	struct rv_monitor *mon = inode->i_private;
 	struct seq_file *seq_f;
 	int ret;
 
@@ -284,7 +284,7 @@ static int monitor_reactors_open(struct inode *inode, struct file *file)
 	/*
 	 * Copy the create file "private" data to the seq_file private data.
 	 */
-	seq_f->private = mdef;
+	seq_f->private = mon;
 
 	return 0;
 };
@@ -454,37 +454,37 @@ static const struct file_operations reacting_on_fops = {
 
 /**
  * reactor_populate_monitor - creates per monitor reactors file
- * @mdef:	monitor's definition.
+ * @mon:	The monitor.
  *
  * Returns 0 if successful, error otherwise.
  */
-int reactor_populate_monitor(struct rv_monitor_def *mdef)
+int reactor_populate_monitor(struct rv_monitor *mon)
 {
 	struct dentry *tmp;
 
-	tmp = rv_create_file("reactors", RV_MODE_WRITE, mdef->root_d, mdef, &monitor_reactors_ops);
+	tmp = rv_create_file("reactors", RV_MODE_WRITE, mon->root_d, mon, &monitor_reactors_ops);
 	if (!tmp)
 		return -ENOMEM;
 
 	/*
 	 * Configure as the rv_nop reactor.
 	 */
-	mdef->rdef = get_reactor_rdef_by_name("nop");
-	mdef->rdef->counter++;
-	mdef->reacting = false;
+	mon->rdef = get_reactor_rdef_by_name("nop");
+	mon->rdef->counter++;
+	mon->reacting = false;
 
 	return 0;
 }
 
 /**
  * reactor_cleanup_monitor - cleanup a monitor reference
- * @mdef:       monitor's definition.
+ * @mon:       the monitor.
  */
-void reactor_cleanup_monitor(struct rv_monitor_def *mdef)
+void reactor_cleanup_monitor(struct rv_monitor *mon)
 {
 	lockdep_assert_held(&rv_interface_lock);
-	mdef->rdef->counter--;
-	WARN_ON_ONCE(mdef->rdef->counter < 0);
+	mon->rdef->counter--;
+	WARN_ON_ONCE(mon->rdef->counter < 0);
 }
 
 /*
-- 
cgit v1.2.3


From 3d3c376118b5f7ed7723c2b4fd7a0a1c1893d63e Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Thu, 24 Jul 2025 19:33:28 +0200
Subject: rv: Merge struct rv_reactor_def into struct rv_reactor

Each struct rv_reactor has a unique struct rv_reactor_def associated with
it. struct rv_reactor is statically allocated, while struct rv_reactor_def
is dynamically allocated.

This makes the code more complicated than it should be:

  - Lookup is required to get the associated rv_reactor_def from rv_reactor

  - Dynamic memory allocation is required for rv_reactor_def. This is
    harder to get right compared to static memory. For instance, there is
    an existing mistake: rv_unregister_reactor() does not free the memory
    allocated by rv_register_reactor(). This is fortunately not a real
    memory leak problem as rv_unregister_reactor() is never called.

Simplify and merge rv_reactor_def into rv_reactor.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/71cb91c86cd40df5b8c492b788787f2a73c3eaa3.1753378331.git.namcao@linutronix.de
Reviewed-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/rv.h            |  5 ++-
 kernel/trace/rv/rv.h          |  9 -----
 kernel/trace/rv/rv_reactors.c | 92 ++++++++++++++++++-------------------------
 3 files changed, 43 insertions(+), 63 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rv.h b/include/linux/rv.h
index dba53aecdfab..c22c9b8c1567 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -90,6 +90,9 @@ struct rv_reactor {
 	const char		*name;
 	const char		*description;
 	__printf(1, 2) void	(*react)(const char *msg, ...);
+	struct list_head	list;
+	/* protected by the monitor interface lock */
+	int			counter;
 };
 #endif
 
@@ -101,7 +104,7 @@ struct rv_monitor {
 	void			(*disable)(void);
 	void			(*reset)(void);
 #ifdef CONFIG_RV_REACTORS
-	struct rv_reactor_def	*rdef;
+	struct rv_reactor	*reactor;
 	__printf(1, 2) void	(*react)(const char *msg, ...);
 	bool			reacting;
 #endif
diff --git a/kernel/trace/rv/rv.h b/kernel/trace/rv/rv.h
index f039ec1c9156..8c38f9dd41bc 100644
--- a/kernel/trace/rv/rv.h
+++ b/kernel/trace/rv/rv.h
@@ -23,15 +23,6 @@ struct rv_interface {
 extern struct mutex rv_interface_lock;
 extern struct list_head rv_monitors_list;
 
-#ifdef CONFIG_RV_REACTORS
-struct rv_reactor_def {
-	struct list_head	list;
-	struct rv_reactor	*reactor;
-	/* protected by the monitor interface lock */
-	int			counter;
-};
-#endif
-
 struct dentry *get_monitors_root(void);
 int rv_disable_monitor(struct rv_monitor *mon);
 int rv_enable_monitor(struct rv_monitor *mon);
diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c
index 7cc620a1be1a..2c7909e6d0e7 100644
--- a/kernel/trace/rv/rv_reactors.c
+++ b/kernel/trace/rv/rv_reactors.c
@@ -70,12 +70,12 @@
  */
 static LIST_HEAD(rv_reactors_list);
 
-static struct rv_reactor_def *get_reactor_rdef_by_name(char *name)
+static struct rv_reactor *get_reactor_rdef_by_name(char *name)
 {
-	struct rv_reactor_def *r;
+	struct rv_reactor *r;
 
 	list_for_each_entry(r, &rv_reactors_list, list) {
-		if (strcmp(name, r->reactor->name) == 0)
+		if (strcmp(name, r->name) == 0)
 			return r;
 	}
 	return NULL;
@@ -86,9 +86,9 @@ static struct rv_reactor_def *get_reactor_rdef_by_name(char *name)
  */
 static int reactors_show(struct seq_file *m, void *p)
 {
-	struct rv_reactor_def *rea_def = p;
+	struct rv_reactor *reactor = p;
 
-	seq_printf(m, "%s\n", rea_def->reactor->name);
+	seq_printf(m, "%s\n", reactor->name);
 	return 0;
 }
 
@@ -139,12 +139,12 @@ static const struct file_operations available_reactors_ops = {
 static int monitor_reactor_show(struct seq_file *m, void *p)
 {
 	struct rv_monitor *mon = m->private;
-	struct rv_reactor_def *rdef = p;
+	struct rv_reactor *reactor = p;
 
-	if (mon->rdef == rdef)
-		seq_printf(m, "[%s]\n", rdef->reactor->name);
+	if (mon->reactor == reactor)
+		seq_printf(m, "[%s]\n", reactor->name);
 	else
-		seq_printf(m, "%s\n", rdef->reactor->name);
+		seq_printf(m, "%s\n", reactor->name);
 	return 0;
 }
 
@@ -159,13 +159,13 @@ static const struct seq_operations monitor_reactors_seq_ops = {
 };
 
 static void monitor_swap_reactors_single(struct rv_monitor *mon,
-					 struct rv_reactor_def *rdef,
+					 struct rv_reactor *reactor,
 					 bool reacting, bool nested)
 {
 	bool monitor_enabled;
 
 	/* nothing to do */
-	if (mon->rdef == rdef)
+	if (mon->reactor == reactor)
 		return;
 
 	monitor_enabled = mon->enabled;
@@ -173,12 +173,12 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon,
 		rv_disable_monitor(mon);
 
 	/* swap reactor's usage */
-	mon->rdef->counter--;
-	rdef->counter++;
+	mon->reactor->counter--;
+	reactor->counter++;
 
-	mon->rdef = rdef;
+	mon->reactor = reactor;
 	mon->reacting = reacting;
-	mon->react = rdef->reactor->react;
+	mon->react = reactor->react;
 
 	/* enable only once if iterating through a container */
 	if (monitor_enabled && !nested)
@@ -186,7 +186,7 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon,
 }
 
 static void monitor_swap_reactors(struct rv_monitor *mon,
-				  struct rv_reactor_def *rdef, bool reacting)
+				  struct rv_reactor *reactor, bool reacting)
 {
 	struct rv_monitor *p = mon;
 
@@ -194,7 +194,7 @@ static void monitor_swap_reactors(struct rv_monitor *mon,
 		list_for_each_entry_continue(p, &rv_monitors_list, list) {
 			if (p->parent != mon)
 				break;
-			monitor_swap_reactors_single(p, rdef, reacting, true);
+			monitor_swap_reactors_single(p, reactor, reacting, true);
 		}
 	/*
 	 * This call enables and disables the monitor if they were active.
@@ -202,7 +202,7 @@ static void monitor_swap_reactors(struct rv_monitor *mon,
 	 * All nested monitors are enabled also if they were off, we may refine
 	 * this logic in the future.
 	 */
-	monitor_swap_reactors_single(mon, rdef, reacting, false);
+	monitor_swap_reactors_single(mon, reactor, reacting, false);
 }
 
 static ssize_t
@@ -211,7 +211,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf,
 {
 	char buff[MAX_RV_REACTOR_NAME_SIZE + 2];
 	struct rv_monitor *mon;
-	struct rv_reactor_def *rdef;
+	struct rv_reactor *reactor;
 	struct seq_file *seq_f;
 	int retval = -EINVAL;
 	bool enable;
@@ -243,16 +243,16 @@ monitor_reactors_write(struct file *file, const char __user *user_buf,
 
 	retval = -EINVAL;
 
-	list_for_each_entry(rdef, &rv_reactors_list, list) {
-		if (strcmp(ptr, rdef->reactor->name) != 0)
+	list_for_each_entry(reactor, &rv_reactors_list, list) {
+		if (strcmp(ptr, reactor->name) != 0)
 			continue;
 
-		if (rdef == get_reactor_rdef_by_name("nop"))
+		if (strcmp(reactor->name, "nop"))
 			enable = false;
 		else
 			enable = true;
 
-		monitor_swap_reactors(mon, rdef, enable);
+		monitor_swap_reactors(mon, reactor, enable);
 
 		retval = count;
 		break;
@@ -299,23 +299,16 @@ static const struct file_operations monitor_reactors_ops = {
 
 static int __rv_register_reactor(struct rv_reactor *reactor)
 {
-	struct rv_reactor_def *r;
+	struct rv_reactor *r;
 
 	list_for_each_entry(r, &rv_reactors_list, list) {
-		if (strcmp(reactor->name, r->reactor->name) == 0) {
+		if (strcmp(reactor->name, r->name) == 0) {
 			pr_info("Reactor %s is already registered\n", reactor->name);
 			return -EINVAL;
 		}
 	}
 
-	r = kzalloc(sizeof(struct rv_reactor_def), GFP_KERNEL);
-	if (!r)
-		return -ENOMEM;
-
-	r->reactor = reactor;
-	r->counter = 0;
-
-	list_add_tail(&r->list, &rv_reactors_list);
+	list_add_tail(&reactor->list, &rv_reactors_list);
 
 	return 0;
 }
@@ -350,26 +343,19 @@ int rv_register_reactor(struct rv_reactor *reactor)
  */
 int rv_unregister_reactor(struct rv_reactor *reactor)
 {
-	struct rv_reactor_def *ptr, *next;
 	int ret = 0;
 
 	mutex_lock(&rv_interface_lock);
 
-	list_for_each_entry_safe(ptr, next, &rv_reactors_list, list) {
-		if (strcmp(reactor->name, ptr->reactor->name) == 0) {
-
-			if (!ptr->counter) {
-				list_del(&ptr->list);
-			} else {
-				printk(KERN_WARNING
-				       "rv: the rv_reactor %s is in use by %d monitor(s)\n",
-				       ptr->reactor->name, ptr->counter);
-				printk(KERN_WARNING "rv: the rv_reactor %s cannot be removed\n",
-				       ptr->reactor->name);
-				ret = -EBUSY;
-				break;
-			}
-		}
+	if (!reactor->counter) {
+		list_del(&reactor->list);
+	} else {
+		printk(KERN_WARNING
+		       "rv: the rv_reactor %s is in use by %d monitor(s)\n",
+		       reactor->name, reactor->counter);
+		printk(KERN_WARNING "rv: the rv_reactor %s cannot be removed\n",
+		       reactor->name);
+		ret = -EBUSY;
 	}
 
 	mutex_unlock(&rv_interface_lock);
@@ -469,8 +455,8 @@ int reactor_populate_monitor(struct rv_monitor *mon)
 	/*
 	 * Configure as the rv_nop reactor.
 	 */
-	mon->rdef = get_reactor_rdef_by_name("nop");
-	mon->rdef->counter++;
+	mon->reactor = get_reactor_rdef_by_name("nop");
+	mon->reactor->counter++;
 	mon->reacting = false;
 
 	return 0;
@@ -483,8 +469,8 @@ int reactor_populate_monitor(struct rv_monitor *mon)
 void reactor_cleanup_monitor(struct rv_monitor *mon)
 {
 	lockdep_assert_held(&rv_interface_lock);
-	mon->rdef->counter--;
-	WARN_ON_ONCE(mon->rdef->counter < 0);
+	mon->reactor->counter--;
+	WARN_ON_ONCE(mon->reactor->counter < 0);
 }
 
 /*
-- 
cgit v1.2.3


From 3d3800b4f7f4b1472a0ec2cffd535c05603f8f60 Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Thu, 24 Jul 2025 19:33:29 +0200
Subject: rv: Remove rv_reactor's reference counter

rv_reactor has a reference counter to ensure it is not removed while
monitors are still using it.

However, this is futile, as __exit functions are not expected to fail and
will proceed normally despite rv_unregister_reactor() returning an error.

At the moment, reactors do not support being built as modules, therefore
they are never removed and the reference counters are not necessary.

If we support building RV reactors as modules in the future, kernel
module's centralized facilities such as try_module_get(), module_put() or
MODULE_SOFTDEP should be used instead of this custom implementation.

Remove this reference counter.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/bb946398436a5e17fb0f5b842ef3313c02291852.1753378331.git.namcao@linutronix.de
Reviewed-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/rv.h            |  2 --
 kernel/trace/rv/rv.c          |  1 -
 kernel/trace/rv/rv.h          |  6 ------
 kernel/trace/rv/rv_reactors.c | 33 ++-------------------------------
 4 files changed, 2 insertions(+), 40 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rv.h b/include/linux/rv.h
index c22c9b8c1567..2f867d6f72ba 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -91,8 +91,6 @@ struct rv_reactor {
 	const char		*description;
 	__printf(1, 2) void	(*react)(const char *msg, ...);
 	struct list_head	list;
-	/* protected by the monitor interface lock */
-	int			counter;
 };
 #endif
 
diff --git a/kernel/trace/rv/rv.c b/kernel/trace/rv/rv.c
index 6c0be2fdc52d..6c8498743b98 100644
--- a/kernel/trace/rv/rv.c
+++ b/kernel/trace/rv/rv.c
@@ -769,7 +769,6 @@ static const struct file_operations monitoring_on_fops = {
 
 static void destroy_monitor_dir(struct rv_monitor *mon)
 {
-	reactor_cleanup_monitor(mon);
 	rv_remove(mon->root_d);
 }
 
diff --git a/kernel/trace/rv/rv.h b/kernel/trace/rv/rv.h
index 8c38f9dd41bc..1485a70c1bf4 100644
--- a/kernel/trace/rv/rv.h
+++ b/kernel/trace/rv/rv.h
@@ -31,7 +31,6 @@ bool rv_is_nested_monitor(struct rv_monitor *mon);
 
 #ifdef CONFIG_RV_REACTORS
 int reactor_populate_monitor(struct rv_monitor *mon);
-void reactor_cleanup_monitor(struct rv_monitor *mon);
 int init_rv_reactors(struct dentry *root_dir);
 #else
 static inline int reactor_populate_monitor(struct rv_monitor *mon)
@@ -39,11 +38,6 @@ static inline int reactor_populate_monitor(struct rv_monitor *mon)
 	return 0;
 }
 
-static inline void reactor_cleanup_monitor(struct rv_monitor *mon)
-{
-	return;
-}
-
 static inline int init_rv_reactors(struct dentry *root_dir)
 {
 	return 0;
diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c
index 2c7909e6d0e7..a8e849e6cd85 100644
--- a/kernel/trace/rv/rv_reactors.c
+++ b/kernel/trace/rv/rv_reactors.c
@@ -172,10 +172,6 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon,
 	if (monitor_enabled)
 		rv_disable_monitor(mon);
 
-	/* swap reactor's usage */
-	mon->reactor->counter--;
-	reactor->counter++;
-
 	mon->reactor = reactor;
 	mon->reacting = reacting;
 	mon->react = reactor->react;
@@ -343,23 +339,10 @@ int rv_register_reactor(struct rv_reactor *reactor)
  */
 int rv_unregister_reactor(struct rv_reactor *reactor)
 {
-	int ret = 0;
-
 	mutex_lock(&rv_interface_lock);
-
-	if (!reactor->counter) {
-		list_del(&reactor->list);
-	} else {
-		printk(KERN_WARNING
-		       "rv: the rv_reactor %s is in use by %d monitor(s)\n",
-		       reactor->name, reactor->counter);
-		printk(KERN_WARNING "rv: the rv_reactor %s cannot be removed\n",
-		       reactor->name);
-		ret = -EBUSY;
-	}
-
+	list_del(&reactor->list);
 	mutex_unlock(&rv_interface_lock);
-	return ret;
+	return 0;
 }
 
 /*
@@ -456,23 +439,11 @@ int reactor_populate_monitor(struct rv_monitor *mon)
 	 * Configure as the rv_nop reactor.
 	 */
 	mon->reactor = get_reactor_rdef_by_name("nop");
-	mon->reactor->counter++;
 	mon->reacting = false;
 
 	return 0;
 }
 
-/**
- * reactor_cleanup_monitor - cleanup a monitor reference
- * @mon:       the monitor.
- */
-void reactor_cleanup_monitor(struct rv_monitor *mon)
-{
-	lockdep_assert_held(&rv_interface_lock);
-	mon->reactor->counter--;
-	WARN_ON_ONCE(mon->reactor->counter < 0);
-}
-
 /*
  * Nop reactor register
  */
-- 
cgit v1.2.3


From b8a7fba39cd49eab343bfe561d85bb5dc57541af Mon Sep 17 00:00:00 2001
From: Nam Cao <namcao@linutronix.de>
Date: Thu, 24 Jul 2025 19:33:30 +0200
Subject: rv: Remove struct rv_monitor::reacting

The field 'reacting' in struct rv_monitor is set but never used. Delete it.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/a6c16f845d2f1a09c4d0934ab83f3cb14478a71d.1753378331.git.namcao@linutronix.de
Reviewed-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/rv.h            |  1 -
 kernel/trace/rv/rv_reactors.c | 19 +++++--------------
 2 files changed, 5 insertions(+), 15 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rv.h b/include/linux/rv.h
index 2f867d6f72ba..80731242fe60 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -104,7 +104,6 @@ struct rv_monitor {
 #ifdef CONFIG_RV_REACTORS
 	struct rv_reactor	*reactor;
 	__printf(1, 2) void	(*react)(const char *msg, ...);
-	bool			reacting;
 #endif
 	struct list_head	list;
 	struct rv_monitor	*parent;
diff --git a/kernel/trace/rv/rv_reactors.c b/kernel/trace/rv/rv_reactors.c
index a8e849e6cd85..106f2c4740f2 100644
--- a/kernel/trace/rv/rv_reactors.c
+++ b/kernel/trace/rv/rv_reactors.c
@@ -160,7 +160,7 @@ static const struct seq_operations monitor_reactors_seq_ops = {
 
 static void monitor_swap_reactors_single(struct rv_monitor *mon,
 					 struct rv_reactor *reactor,
-					 bool reacting, bool nested)
+					 bool nested)
 {
 	bool monitor_enabled;
 
@@ -173,7 +173,6 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon,
 		rv_disable_monitor(mon);
 
 	mon->reactor = reactor;
-	mon->reacting = reacting;
 	mon->react = reactor->react;
 
 	/* enable only once if iterating through a container */
@@ -181,8 +180,7 @@ static void monitor_swap_reactors_single(struct rv_monitor *mon,
 		rv_enable_monitor(mon);
 }
 
-static void monitor_swap_reactors(struct rv_monitor *mon,
-				  struct rv_reactor *reactor, bool reacting)
+static void monitor_swap_reactors(struct rv_monitor *mon, struct rv_reactor *reactor)
 {
 	struct rv_monitor *p = mon;
 
@@ -190,7 +188,7 @@ static void monitor_swap_reactors(struct rv_monitor *mon,
 		list_for_each_entry_continue(p, &rv_monitors_list, list) {
 			if (p->parent != mon)
 				break;
-			monitor_swap_reactors_single(p, reactor, reacting, true);
+			monitor_swap_reactors_single(p, reactor, true);
 		}
 	/*
 	 * This call enables and disables the monitor if they were active.
@@ -198,7 +196,7 @@ static void monitor_swap_reactors(struct rv_monitor *mon,
 	 * All nested monitors are enabled also if they were off, we may refine
 	 * this logic in the future.
 	 */
-	monitor_swap_reactors_single(mon, reactor, reacting, false);
+	monitor_swap_reactors_single(mon, reactor, false);
 }
 
 static ssize_t
@@ -210,7 +208,6 @@ monitor_reactors_write(struct file *file, const char __user *user_buf,
 	struct rv_reactor *reactor;
 	struct seq_file *seq_f;
 	int retval = -EINVAL;
-	bool enable;
 	char *ptr;
 	int len;
 
@@ -243,12 +240,7 @@ monitor_reactors_write(struct file *file, const char __user *user_buf,
 		if (strcmp(ptr, reactor->name) != 0)
 			continue;
 
-		if (strcmp(reactor->name, "nop"))
-			enable = false;
-		else
-			enable = true;
-
-		monitor_swap_reactors(mon, reactor, enable);
+		monitor_swap_reactors(mon, reactor);
 
 		retval = count;
 		break;
@@ -439,7 +431,6 @@ int reactor_populate_monitor(struct rv_monitor *mon)
 	 * Configure as the rv_nop reactor.
 	 */
 	mon->reactor = get_reactor_rdef_by_name("nop");
-	mon->reacting = false;
 
 	return 0;
 }
-- 
cgit v1.2.3


From 031a712471943ce780a7fc56e35b68cf77243e1e Mon Sep 17 00:00:00 2001
From: Yue Haibing <yuehaibing@huawei.com>
Date: Tue, 24 Jun 2025 09:44:32 +0800
Subject: netfilter: x_tables: Remove unused functions xt_{in|out}name()

Since commit 2173c519d5e9 ("audit: normalize NETFILTER_PKT")
these are unused, so can be removed.

Signed-off-by: Yue Haibing <yuehaibing@huawei.com>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter/x_tables.h | 10 ----------
 1 file changed, 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter/x_tables.h b/include/linux/netfilter/x_tables.h
index f39f688d7285..77c778d84d4c 100644
--- a/include/linux/netfilter/x_tables.h
+++ b/include/linux/netfilter/x_tables.h
@@ -51,21 +51,11 @@ static inline struct net_device *xt_in(const struct xt_action_param *par)
 	return par->state->in;
 }
 
-static inline const char *xt_inname(const struct xt_action_param *par)
-{
-	return par->state->in->name;
-}
-
 static inline struct net_device *xt_out(const struct xt_action_param *par)
 {
 	return par->state->out;
 }
 
-static inline const char *xt_outname(const struct xt_action_param *par)
-{
-	return par->state->out->name;
-}
-
 static inline unsigned int xt_hooknum(const struct xt_action_param *par)
 {
 	return par->state->hook;
-- 
cgit v1.2.3


From bc8c43adfdc57c8253884fc1853cb6679cd5953d Mon Sep 17 00:00:00 2001
From: Phil Sutter <phil@nwl.cc>
Date: Tue, 8 Jul 2025 15:04:02 +0200
Subject: netfilter: nfnetlink_hook: Dump flowtable info

Introduce NFNL_HOOK_TYPE_NFT_FLOWTABLE to distinguish flowtable hooks
from base chain ones. Nested attributes are shared with the old NFTABLES
hook info type since they fit apart from their misleading name.

Old nftables in user space will ignore this new hook type and thus
continue to print flowtable hooks just like before, e.g.:

| family netdev {
| 	hook ingress device test0 {
| 		 0000000000 nf_flow_offload_ip_hook [nf_flow_table]
| 	}
| }

With this patch in place and support for the new hook info type, output
becomes more useful:

| family netdev {
| 	hook ingress device test0 {
| 		 0000000000 flowtable ip mytable myft [nf_flow_table]
| 	}
| }

Suggested-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Phil Sutter <phil@nwl.cc>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 include/linux/netfilter.h                     |  1 +
 include/uapi/linux/netfilter/nfnetlink_hook.h |  2 ++
 net/netfilter/nf_tables_api.c                 | 24 +++++++++---------
 net/netfilter/nfnetlink_hook.c                | 35 +++++++++++++++++++++++++++
 4 files changed, 51 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netfilter.h b/include/linux/netfilter.h
index 5f896fcc074d..efbbfa770d66 100644
--- a/include/linux/netfilter.h
+++ b/include/linux/netfilter.h
@@ -92,6 +92,7 @@ enum nf_hook_ops_type {
 	NF_HOOK_OP_UNDEFINED,
 	NF_HOOK_OP_NF_TABLES,
 	NF_HOOK_OP_BPF,
+	NF_HOOK_OP_NFT_FT,
 };
 
 struct nf_hook_ops {
diff --git a/include/uapi/linux/netfilter/nfnetlink_hook.h b/include/uapi/linux/netfilter/nfnetlink_hook.h
index 84a561a74b98..1a2c4d6424b5 100644
--- a/include/uapi/linux/netfilter/nfnetlink_hook.h
+++ b/include/uapi/linux/netfilter/nfnetlink_hook.h
@@ -61,10 +61,12 @@ enum nfnl_hook_chain_desc_attributes {
  *
  * @NFNL_HOOK_TYPE_NFTABLES: nf_tables base chain
  * @NFNL_HOOK_TYPE_BPF: bpf program
+ * @NFNL_HOOK_TYPE_NFT_FLOWTABLE: nf_tables flowtable
  */
 enum nfnl_hook_chaintype {
 	NFNL_HOOK_TYPE_NFTABLES = 0x1,
 	NFNL_HOOK_TYPE_BPF,
+	NFNL_HOOK_TYPE_NFT_FLOWTABLE,
 };
 
 /**
diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
index 04795af6e586..13d0ed9d1895 100644
--- a/net/netfilter/nf_tables_api.c
+++ b/net/netfilter/nf_tables_api.c
@@ -8895,11 +8895,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx,
 
 	list_for_each_entry(hook, &flowtable_hook->list, list) {
 		list_for_each_entry(ops, &hook->ops_list, list) {
-			ops->pf		= NFPROTO_NETDEV;
-			ops->hooknum	= flowtable_hook->num;
-			ops->priority	= flowtable_hook->priority;
-			ops->priv	= &flowtable->data;
-			ops->hook	= flowtable->data.type->hook;
+			ops->pf			= NFPROTO_NETDEV;
+			ops->hooknum		= flowtable_hook->num;
+			ops->priority		= flowtable_hook->priority;
+			ops->priv		= &flowtable->data;
+			ops->hook		= flowtable->data.type->hook;
+			ops->hook_ops_type	= NF_HOOK_OP_NFT_FT;
 		}
 	}
 
@@ -9727,12 +9728,13 @@ static int nft_flowtable_event(unsigned long event, struct net_device *dev,
 			if (!ops)
 				return 1;
 
-			ops->pf		= NFPROTO_NETDEV;
-			ops->hooknum	= flowtable->hooknum;
-			ops->priority	= flowtable->data.priority;
-			ops->priv	= &flowtable->data;
-			ops->hook	= flowtable->data.type->hook;
-			ops->dev	= dev;
+			ops->pf			= NFPROTO_NETDEV;
+			ops->hooknum		= flowtable->hooknum;
+			ops->priority		= flowtable->data.priority;
+			ops->priv		= &flowtable->data;
+			ops->hook		= flowtable->data.type->hook;
+			ops->hook_ops_type	= NF_HOOK_OP_NFT_FT;
+			ops->dev		= dev;
 			if (nft_register_flowtable_ops(dev_net(dev),
 						       flowtable, ops)) {
 				kfree(ops);
diff --git a/net/netfilter/nfnetlink_hook.c b/net/netfilter/nfnetlink_hook.c
index cd4056527ede..92d869317cba 100644
--- a/net/netfilter/nfnetlink_hook.c
+++ b/net/netfilter/nfnetlink_hook.c
@@ -156,6 +156,38 @@ static int nfnl_hook_put_nft_chain_info(struct sk_buff *nlskb,
 	return 0;
 }
 
+static int nfnl_hook_put_nft_ft_info(struct sk_buff *nlskb,
+				     const struct nfnl_dump_hook_data *ctx,
+				     unsigned int seq,
+				     struct nf_flowtable *nf_ft)
+{
+	struct nft_flowtable *ft =
+		container_of(nf_ft, struct nft_flowtable, data);
+	struct net *net = sock_net(nlskb->sk);
+	struct nlattr *nest;
+	int ret = 0;
+
+	if (WARN_ON_ONCE(!nf_ft))
+		return 0;
+
+	if (!nft_is_active(net, ft))
+		return 0;
+
+	nest = nfnl_start_info_type(nlskb, NFNL_HOOK_TYPE_NFT_FLOWTABLE);
+	if (!nest)
+		return -EMSGSIZE;
+
+	ret = nfnl_hook_put_nft_info_desc(nlskb, ft->table->name,
+					  ft->name, ft->table->family);
+	if (ret) {
+		nla_nest_cancel(nlskb, nest);
+		return ret;
+	}
+
+	nla_nest_end(nlskb, nest);
+	return 0;
+}
+
 static int nfnl_hook_dump_one(struct sk_buff *nlskb,
 			      const struct nfnl_dump_hook_data *ctx,
 			      const struct nf_hook_ops *ops,
@@ -223,6 +255,9 @@ static int nfnl_hook_dump_one(struct sk_buff *nlskb,
 	case NF_HOOK_OP_BPF:
 		ret = nfnl_hook_put_bpf_prog_info(nlskb, ctx, seq, ops->priv);
 		break;
+	case NF_HOOK_OP_NFT_FT:
+		ret = nfnl_hook_put_nft_ft_info(nlskb, ctx, seq, ops->priv);
+		break;
 	case NF_HOOK_OP_UNDEFINED:
 		break;
 	default:
-- 
cgit v1.2.3


From 0d9cfc9b8cb17dbc29a98792d36ec39a1cf1395f Mon Sep 17 00:00:00 2001
From: John Ernberg <john.ernberg@actia.se>
Date: Wed, 23 Jul 2025 10:25:35 +0000
Subject: net: usbnet: Avoid potential RCU stall on LINK_CHANGE event

The Gemalto Cinterion PLS83-W modem (cdc_ether) is emitting confusing link
up and down events when the WWAN interface is activated on the modem-side.

Interrupt URBs will in consecutive polls grab:
* Link Connected
* Link Disconnected
* Link Connected

Where the last Connected is then a stable link state.

When the system is under load this may cause the unlink_urbs() work in
__handle_link_change() to not complete before the next usbnet_link_change()
call turns the carrier on again, allowing rx_submit() to queue new SKBs.

In that event the URB queue is filled faster than it can drain, ending up
in a RCU stall:

    rcu: INFO: rcu_sched detected expedited stalls on CPUs/tasks: { 0-.... } 33108 jiffies s: 201 root: 0x1/.
    rcu: blocking rcu_node structures (internal RCU debug):
    Sending NMI from CPU 1 to CPUs 0:
    NMI backtrace for cpu 0

    Call trace:
     arch_local_irq_enable+0x4/0x8
     local_bh_enable+0x18/0x20
     __netdev_alloc_skb+0x18c/0x1cc
     rx_submit+0x68/0x1f8 [usbnet]
     rx_alloc_submit+0x4c/0x74 [usbnet]
     usbnet_bh+0x1d8/0x218 [usbnet]
     usbnet_bh_tasklet+0x10/0x18 [usbnet]
     tasklet_action_common+0xa8/0x110
     tasklet_action+0x2c/0x34
     handle_softirqs+0x2cc/0x3a0
     __do_softirq+0x10/0x18
     ____do_softirq+0xc/0x14
     call_on_irq_stack+0x24/0x34
     do_softirq_own_stack+0x18/0x20
     __irq_exit_rcu+0xa8/0xb8
     irq_exit_rcu+0xc/0x30
     el1_interrupt+0x34/0x48
     el1h_64_irq_handler+0x14/0x1c
     el1h_64_irq+0x68/0x6c
     _raw_spin_unlock_irqrestore+0x38/0x48
     xhci_urb_dequeue+0x1ac/0x45c [xhci_hcd]
     unlink1+0xd4/0xdc [usbcore]
     usb_hcd_unlink_urb+0x70/0xb0 [usbcore]
     usb_unlink_urb+0x24/0x44 [usbcore]
     unlink_urbs.constprop.0.isra.0+0x64/0xa8 [usbnet]
     __handle_link_change+0x34/0x70 [usbnet]
     usbnet_deferred_kevent+0x1c0/0x320 [usbnet]
     process_scheduled_works+0x2d0/0x48c
     worker_thread+0x150/0x1dc
     kthread+0xd8/0xe8
     ret_from_fork+0x10/0x20

Get around the problem by delaying the carrier on to the scheduled work.

This needs a new flag to keep track of the necessary action.

The carrier ok check cannot be removed as it remains required for the
LINK_RESET event flow.

Fixes: 4b49f58fff00 ("usbnet: handle link change")
Cc: stable@vger.kernel.org
Signed-off-by: John Ernberg <john.ernberg@actia.se>
Link: https://patch.msgid.link/20250723102526.1305339-1-john.ernberg@actia.se
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/usb/usbnet.c   | 11 ++++++++---
 include/linux/usb/usbnet.h |  1 +
 2 files changed, 9 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
index c04e715a4c2a..bc1d8631ffe0 100644
--- a/drivers/net/usb/usbnet.c
+++ b/drivers/net/usb/usbnet.c
@@ -1122,6 +1122,9 @@ static void __handle_link_change(struct usbnet *dev)
 		 * tx queue is stopped by netcore after link becomes off
 		 */
 	} else {
+		if (test_and_clear_bit(EVENT_LINK_CARRIER_ON, &dev->flags))
+			netif_carrier_on(dev->net);
+
 		/* submitting URBs for reading packets */
 		tasklet_schedule(&dev->bh);
 	}
@@ -2009,10 +2012,12 @@ EXPORT_SYMBOL(usbnet_manage_power);
 void usbnet_link_change(struct usbnet *dev, bool link, bool need_reset)
 {
 	/* update link after link is reseted */
-	if (link && !need_reset)
-		netif_carrier_on(dev->net);
-	else
+	if (link && !need_reset) {
+		set_bit(EVENT_LINK_CARRIER_ON, &dev->flags);
+	} else {
+		clear_bit(EVENT_LINK_CARRIER_ON, &dev->flags);
 		netif_carrier_off(dev->net);
+	}
 
 	if (need_reset && link)
 		usbnet_defer_kevent(dev, EVENT_LINK_RESET);
diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
index 0b9f1e598e3a..4bc6bb01a0eb 100644
--- a/include/linux/usb/usbnet.h
+++ b/include/linux/usb/usbnet.h
@@ -76,6 +76,7 @@ struct usbnet {
 #		define EVENT_LINK_CHANGE	11
 #		define EVENT_SET_RX_MODE	12
 #		define EVENT_NO_IP_ALIGN	13
+#		define EVENT_LINK_CARRIER_ON	14
 /* This one is special, as it indicates that the device is going away
  * there are cyclic dependencies between tasklet, timer and bh
  * that must be broken
-- 
cgit v1.2.3


From f24987ef6959a7efaf79bffd265522c3df18d431 Mon Sep 17 00:00:00 2001
From: Gabriel Goller <g.goller@proxmox.com>
Date: Tue, 22 Jul 2025 10:18:45 +0200
Subject: ipv6: add `force_forwarding` sysctl to enable per-interface
 forwarding

It is currently impossible to enable ipv6 forwarding on a per-interface
basis like in ipv4. To enable forwarding on an ipv6 interface we need to
enable it on all interfaces and disable it on the other interfaces using
a netfilter rule. This is especially cumbersome if you have lots of
interfaces and only want to enable forwarding on a few. According to the
sysctl docs [0] the `net.ipv6.conf.all.forwarding` enables forwarding
for all interfaces, while the interface-specific
`net.ipv6.conf.<interface>.forwarding` configures the interface
Host/Router configuration.

Introduce a new sysctl flag `force_forwarding`, which can be set on every
interface. The ip6_forwarding function will then check if the global
forwarding flag OR the force_forwarding flag is active and forward the
packet.

To preserve backwards-compatibility reset the flag (on all interfaces)
to 0 if the net.ipv6.conf.all.forwarding flag is set to 0.

Add a short selftest that checks if a packet gets forwarded with and
without `force_forwarding`.

[0]: https://www.kernel.org/doc/Documentation/networking/ip-sysctl.txt

Acked-by: Nicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: Gabriel Goller <g.goller@proxmox.com>
Link: https://patch.msgid.link/20250722081847.132632-1-g.goller@proxmox.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 Documentation/networking/ip-sysctl.rst             |   8 +-
 include/linux/ipv6.h                               |   1 +
 include/uapi/linux/ipv6.h                          |   1 +
 include/uapi/linux/netconf.h                       |   1 +
 include/uapi/linux/sysctl.h                        |   1 +
 net/ipv6/addrconf.c                                |  82 ++++++++++++++++
 net/ipv6/ip6_output.c                              |   3 +-
 tools/testing/selftests/net/Makefile               |   1 +
 .../testing/selftests/net/ipv6_force_forwarding.sh | 105 +++++++++++++++++++++
 9 files changed, 200 insertions(+), 3 deletions(-)
 create mode 100755 tools/testing/selftests/net/ipv6_force_forwarding.sh

(limited to 'include/linux')

diff --git a/Documentation/networking/ip-sysctl.rst b/Documentation/networking/ip-sysctl.rst
index 14700ea77e75..bb620f554598 100644
--- a/Documentation/networking/ip-sysctl.rst
+++ b/Documentation/networking/ip-sysctl.rst
@@ -2543,8 +2543,8 @@ conf/all/disable_ipv6 - BOOLEAN
 conf/all/forwarding - BOOLEAN
 	Enable global IPv6 forwarding between all interfaces.
 
-	IPv4 and IPv6 work differently here; e.g. netfilter must be used
-	to control which interfaces may forward packets and which not.
+	IPv4 and IPv6 work differently here; the ``force_forwarding`` flag must
+	be used to control which interfaces may forward packets.
 
 	This also sets all interfaces' Host/Router setting
 	'forwarding' to the specified value.  See below for details.
@@ -2561,6 +2561,10 @@ proxy_ndp - BOOLEAN
 
 	Default: 0 (disabled)
 
+force_forwarding - BOOLEAN
+	Enable forwarding on this interface only -- regardless of the setting on
+	``conf/all/forwarding``. When setting ``conf.all.forwarding`` to 0,
+	the ``force_forwarding`` flag will be reset on all interfaces.
 
 fwmark_reflect - BOOLEAN
 	Controls the fwmark of kernel-generated IPv6 reply packets that are not
diff --git a/include/linux/ipv6.h b/include/linux/ipv6.h
index db0eb0d86b64..bc6ec2959173 100644
--- a/include/linux/ipv6.h
+++ b/include/linux/ipv6.h
@@ -17,6 +17,7 @@ struct ipv6_devconf {
 	__s32		hop_limit;
 	__s32		mtu6;
 	__s32		forwarding;
+	__s32		force_forwarding;
 	__s32		disable_policy;
 	__s32		proxy_ndp;
 	__cacheline_group_end(ipv6_devconf_read_txrx);
diff --git a/include/uapi/linux/ipv6.h b/include/uapi/linux/ipv6.h
index cf592d7b630f..d4d3ae774b26 100644
--- a/include/uapi/linux/ipv6.h
+++ b/include/uapi/linux/ipv6.h
@@ -199,6 +199,7 @@ enum {
 	DEVCONF_NDISC_EVICT_NOCARRIER,
 	DEVCONF_ACCEPT_UNTRACKED_NA,
 	DEVCONF_ACCEPT_RA_MIN_LFT,
+	DEVCONF_FORCE_FORWARDING,
 	DEVCONF_MAX
 };
 
diff --git a/include/uapi/linux/netconf.h b/include/uapi/linux/netconf.h
index fac4edd55379..1c8c84d65ae3 100644
--- a/include/uapi/linux/netconf.h
+++ b/include/uapi/linux/netconf.h
@@ -19,6 +19,7 @@ enum {
 	NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN,
 	NETCONFA_INPUT,
 	NETCONFA_BC_FORWARDING,
+	NETCONFA_FORCE_FORWARDING,
 	__NETCONFA_MAX
 };
 #define NETCONFA_MAX	(__NETCONFA_MAX - 1)
diff --git a/include/uapi/linux/sysctl.h b/include/uapi/linux/sysctl.h
index 8981f00204db..63d1464cb71c 100644
--- a/include/uapi/linux/sysctl.h
+++ b/include/uapi/linux/sysctl.h
@@ -573,6 +573,7 @@ enum {
 	NET_IPV6_ACCEPT_RA_FROM_LOCAL=26,
 	NET_IPV6_ACCEPT_RA_RT_INFO_MIN_PLEN=27,
 	NET_IPV6_RA_DEFRTR_METRIC=28,
+	NET_IPV6_FORCE_FORWARDING=29,
 	__NET_IPV6_MAX
 };
 
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 4f1d7d110302..81a067a2e526 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -239,6 +239,7 @@ static struct ipv6_devconf ipv6_devconf __read_mostly = {
 	.ndisc_evict_nocarrier	= 1,
 	.ra_honor_pio_life	= 0,
 	.ra_honor_pio_pflag	= 0,
+	.force_forwarding	= 0,
 };
 
 static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
@@ -303,6 +304,7 @@ static struct ipv6_devconf ipv6_devconf_dflt __read_mostly = {
 	.ndisc_evict_nocarrier	= 1,
 	.ra_honor_pio_life	= 0,
 	.ra_honor_pio_pflag	= 0,
+	.force_forwarding	= 0,
 };
 
 /* Check if link is ready: is it up and is a valid qdisc available */
@@ -857,6 +859,9 @@ static void addrconf_forward_change(struct net *net, __s32 newf)
 		idev = __in6_dev_get_rtnl_net(dev);
 		if (idev) {
 			int changed = (!idev->cnf.forwarding) ^ (!newf);
+			/* Disabling all.forwarding sets 0 to force_forwarding for all interfaces */
+			if (newf == 0)
+				WRITE_ONCE(idev->cnf.force_forwarding, 0);
 
 			WRITE_ONCE(idev->cnf.forwarding, newf);
 			if (changed)
@@ -5710,6 +5715,7 @@ static void ipv6_store_devconf(const struct ipv6_devconf *cnf,
 	array[DEVCONF_ACCEPT_UNTRACKED_NA] =
 		READ_ONCE(cnf->accept_untracked_na);
 	array[DEVCONF_ACCEPT_RA_MIN_LFT] = READ_ONCE(cnf->accept_ra_min_lft);
+	array[DEVCONF_FORCE_FORWARDING] = READ_ONCE(cnf->force_forwarding);
 }
 
 static inline size_t inet6_ifla6_size(void)
@@ -6738,6 +6744,75 @@ static int addrconf_sysctl_disable_policy(const struct ctl_table *ctl, int write
 	return ret;
 }
 
+static void addrconf_force_forward_change(struct net *net, __s32 newf)
+{
+	struct net_device *dev;
+	struct inet6_dev *idev;
+
+	for_each_netdev(net, dev) {
+		idev = __in6_dev_get_rtnl_net(dev);
+		if (idev) {
+			int changed = (!idev->cnf.force_forwarding) ^ (!newf);
+
+			WRITE_ONCE(idev->cnf.force_forwarding, newf);
+			if (changed)
+				inet6_netconf_notify_devconf(dev_net(dev), RTM_NEWNETCONF,
+							     NETCONFA_FORCE_FORWARDING,
+							     dev->ifindex, &idev->cnf);
+		}
+	}
+}
+
+static int addrconf_sysctl_force_forwarding(const struct ctl_table *ctl, int write,
+					    void *buffer, size_t *lenp, loff_t *ppos)
+{
+	struct inet6_dev *idev = ctl->extra1;
+	struct ctl_table tmp_ctl = *ctl;
+	struct net *net = ctl->extra2;
+	int *valp = ctl->data;
+	int new_val = *valp;
+	int old_val = *valp;
+	loff_t pos = *ppos;
+	int ret;
+
+	tmp_ctl.extra1 = SYSCTL_ZERO;
+	tmp_ctl.extra2 = SYSCTL_ONE;
+	tmp_ctl.data = &new_val;
+
+	ret = proc_douintvec_minmax(&tmp_ctl, write, buffer, lenp, ppos);
+
+	if (write && old_val != new_val) {
+		if (!rtnl_net_trylock(net))
+			return restart_syscall();
+
+		WRITE_ONCE(*valp, new_val);
+
+		if (valp == &net->ipv6.devconf_dflt->force_forwarding) {
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORCE_FORWARDING,
+						     NETCONFA_IFINDEX_DEFAULT,
+						     net->ipv6.devconf_dflt);
+		} else if (valp == &net->ipv6.devconf_all->force_forwarding) {
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORCE_FORWARDING,
+						     NETCONFA_IFINDEX_ALL,
+						     net->ipv6.devconf_all);
+
+			addrconf_force_forward_change(net, new_val);
+		} else {
+			inet6_netconf_notify_devconf(net, RTM_NEWNETCONF,
+						     NETCONFA_FORCE_FORWARDING,
+						     idev->dev->ifindex,
+						     &idev->cnf);
+		}
+		rtnl_net_unlock(net);
+	}
+
+	if (ret)
+		*ppos = pos;
+	return ret;
+}
+
 static int minus_one = -1;
 static const int two_five_five = 255;
 static u32 ioam6_if_id_max = U16_MAX;
@@ -7208,6 +7283,13 @@ static const struct ctl_table addrconf_sysctl[] = {
 		.extra1		= SYSCTL_ZERO,
 		.extra2		= SYSCTL_TWO,
 	},
+	{
+		.procname	= "force_forwarding",
+		.data		= &ipv6_devconf.force_forwarding,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= addrconf_sysctl_force_forwarding,
+	},
 };
 
 static int __addrconf_sysctl_register(struct net *net, char *dev_name,
diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 0412f8544695..1e1410237b6e 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -511,7 +511,8 @@ int ip6_forward(struct sk_buff *skb)
 	u32 mtu;
 
 	idev = __in6_dev_get_safely(dev_get_by_index_rcu(net, IP6CB(skb)->iif));
-	if (READ_ONCE(net->ipv6.devconf_all->forwarding) == 0)
+	if (!READ_ONCE(net->ipv6.devconf_all->forwarding) &&
+	    (!idev || !READ_ONCE(idev->cnf.force_forwarding)))
 		goto error;
 
 	if (skb->pkt_type != PACKET_HOST)
diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
index 13e2678d418b..b31a71f2b372 100644
--- a/tools/testing/selftests/net/Makefile
+++ b/tools/testing/selftests/net/Makefile
@@ -116,6 +116,7 @@ TEST_GEN_FILES += skf_net_off
 TEST_GEN_FILES += tfo
 TEST_PROGS += tfo_passive.sh
 TEST_PROGS += broadcast_pmtu.sh
+TEST_PROGS += ipv6_force_forwarding.sh
 
 # YNL files, must be before "include ..lib.mk"
 YNL_GEN_FILES := busy_poller netlink-dumps
diff --git a/tools/testing/selftests/net/ipv6_force_forwarding.sh b/tools/testing/selftests/net/ipv6_force_forwarding.sh
new file mode 100755
index 000000000000..bf0243366caa
--- /dev/null
+++ b/tools/testing/selftests/net/ipv6_force_forwarding.sh
@@ -0,0 +1,105 @@
+#!/bin/bash
+# SPDX-License-Identifier: GPL-2.0
+#
+# Test IPv6 force_forwarding interface property
+#
+# This test verifies that the force_forwarding property works correctly:
+# - When global forwarding is disabled, packets are not forwarded normally
+# - When force_forwarding is enabled on an interface, packets are forwarded
+#   regardless of the global forwarding setting
+
+source lib.sh
+
+cleanup() {
+    cleanup_ns $ns1 $ns2 $ns3
+}
+
+trap cleanup EXIT
+
+setup_test() {
+    # Create three namespaces: sender, router, receiver
+    setup_ns ns1 ns2 ns3
+
+    # Create veth pairs: ns1 <-> ns2 <-> ns3
+    ip link add name veth12 type veth peer name veth21
+    ip link add name veth23 type veth peer name veth32
+
+    # Move interfaces to namespaces
+    ip link set veth12 netns $ns1
+    ip link set veth21 netns $ns2
+    ip link set veth23 netns $ns2
+    ip link set veth32 netns $ns3
+
+    # Configure interfaces
+    ip -n $ns1 addr add 2001:db8:1::1/64 dev veth12 nodad
+    ip -n $ns2 addr add 2001:db8:1::2/64 dev veth21 nodad
+    ip -n $ns2 addr add 2001:db8:2::1/64 dev veth23 nodad
+    ip -n $ns3 addr add 2001:db8:2::2/64 dev veth32 nodad
+
+    # Bring up interfaces
+    ip -n $ns1 link set veth12 up
+    ip -n $ns2 link set veth21 up
+    ip -n $ns2 link set veth23 up
+    ip -n $ns3 link set veth32 up
+
+    # Add routes
+    ip -n $ns1 route add 2001:db8:2::/64 via 2001:db8:1::2
+    ip -n $ns3 route add 2001:db8:1::/64 via 2001:db8:2::1
+
+    # Disable global forwarding
+    ip netns exec $ns2 sysctl -qw net.ipv6.conf.all.forwarding=0
+}
+
+test_force_forwarding() {
+    local ret=0
+
+    echo "TEST: force_forwarding functionality"
+
+    # Check if force_forwarding sysctl exists
+    if ! ip netns exec $ns2 test -f /proc/sys/net/ipv6/conf/veth21/force_forwarding; then
+        echo "SKIP: force_forwarding not available"
+        return $ksft_skip
+    fi
+
+    # Test 1: Without force_forwarding, ping should fail
+    ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=0
+    ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=0
+
+    if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then
+        echo "FAIL: ping succeeded when forwarding disabled"
+        ret=1
+    else
+        echo "PASS: forwarding disabled correctly"
+    fi
+
+    # Test 2: With force_forwarding enabled, ping should succeed
+    ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth21.force_forwarding=1
+    ip netns exec $ns2 sysctl -qw net.ipv6.conf.veth23.force_forwarding=1
+
+    if ip netns exec $ns1 ping -6 -c 1 -W 2 2001:db8:2::2 &>/dev/null; then
+        echo "PASS: force_forwarding enabled forwarding"
+    else
+        echo "FAIL: ping failed with force_forwarding enabled"
+        ret=1
+    fi
+
+    return $ret
+}
+
+echo "IPv6 force_forwarding test"
+echo "=========================="
+
+setup_test
+test_force_forwarding
+ret=$?
+
+if [ $ret -eq 0 ]; then
+    echo "OK"
+    exit 0
+elif [ $ret -eq $ksft_skip ]; then
+    echo "SKIP"
+    exit $ksft_skip
+else
+    echo "FAIL"
+    exit 1
+fi
-- 
cgit v1.2.3


From 33360f2508e07b07bb926ea75f11744dcc1cde07 Mon Sep 17 00:00:00 2001
From: Breno Leitao <leitao@debian.org>
Date: Wed, 23 Jul 2025 10:20:29 -0700
Subject: netpoll: Remove unused fields from inet_addr union

Clean up the inet_addr union by removing unused fields that are
redundant with existing members:

This simplifies the union structure while maintaining all necessary
functionality for both IPv4 and IPv6 address handling.

Signed-off-by: Breno Leitao <leitao@debian.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20250723-netconsole_ref-v3-1-8be9b24e4a99@debian.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/netpoll.h | 3 ---
 1 file changed, 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/netpoll.h b/include/linux/netpoll.h
index 735e65c3cc11..b5ea9882eda8 100644
--- a/include/linux/netpoll.h
+++ b/include/linux/netpoll.h
@@ -15,10 +15,7 @@
 #include <linux/refcount.h>
 
 union inet_addr {
-	__u32		all[4];
 	__be32		ip;
-	__be32		ip6[4];
-	struct in_addr	in;
 	struct in6_addr	in6;
 };
 
-- 
cgit v1.2.3


From 463deed51796fd0995d08d8b6aa793d7ab5a2059 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Tue, 22 Jul 2025 10:18:31 -0700
Subject: ipv6: Add sockaddr_inet unified address structure

There are cases in networking (e.g. wireguard, sctp) where a union is
used to provide coverage for either IPv4 or IPv6 network addresses,
and they include an embedded "struct sockaddr" as well (for "sa_family"
and raw "sa_data" access). The current struct sockaddr contains a
flexible array, which means these unions should not be further embedded
in other structs because they do not technically have a fixed size (and
are generating warnings for the coming -Wflexible-array-not-at-end flag
addition). But the future changes to make struct sockaddr a fixed size
(i.e. with a 14 byte sa_data member) make the "sa_data" uses with an IPv6
address a potential place for the compiler to get upset about object size
mismatches. Therefore, we need a sockaddr that cleanly provides both an
sa_family member and an appropriately fixed-sized sa_data member that does
not bloat member usage via the potential alternative of sockaddr_storage
to cover both IPv4 and IPv6, to avoid unseemly churn in the affected code
bases.

Introduce sockaddr_inet as a unified structure for holding both IPv4 and
IPv6 addresses (i.e. large enough to accommodate sockaddr_in6).

The structure is defined in linux/in6.h since its max size is sized
based on sockaddr_in6 and provides a more specific alternative to the
generic sockaddr_storage for IPv4 with IPv6 address family handling.

The "sa_family" member doesn't use the sa_family_t type to avoid needing
layer violating header inclusions.

Signed-off-by: Kees Cook <kees@kernel.org>
Link: https://patch.msgid.link/20250722171836.1078436-1-kees@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/in6.h | 7 +++++++
 1 file changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/in6.h b/include/linux/in6.h
index 0777a21cbf86..403f926d33d8 100644
--- a/include/linux/in6.h
+++ b/include/linux/in6.h
@@ -18,6 +18,13 @@
 
 #include <uapi/linux/in6.h>
 
+/* Large enough to hold both sockaddr_in and sockaddr_in6. */
+struct sockaddr_inet {
+	unsigned short	sa_family;
+	char		sa_data[sizeof(struct sockaddr_in6) -
+				sizeof(unsigned short)];
+};
+
 /* IPv6 Wildcard Address (::) and Loopback Address (::1) defined in RFC2553
  * NOTE: Be aware the IN6ADDR_* constants and in6addr_* externals are defined
  * in network byte order, not in host byte order as are the IPv4 equivalents
-- 
cgit v1.2.3


From 84c47bfc5b3b40b50b798b6b6c15e8a1442d936d Mon Sep 17 00:00:00 2001
From: Tristram Ha <tristram.ha@microchip.com>
Date: Thu, 24 Jul 2025 17:17:49 -0700
Subject: net: dsa: microchip: Add KSZ8463 switch support to KSZ DSA driver

KSZ8463 switch is a 3-port switch based from KSZ8863.  Its major
difference from other KSZ SPI switches is its register access is not a
simple continual 8-bit transfer with automatic address increase but uses
a byte-enable mechanism specifying 8-bit, 16-bit, or 32-bit access.  Its
registers are also defined in 16-bit format because it shares a design
with a MAC controller using 16-bit access.  As a result some common
register accesses need to be re-arranged.

This patch adds the basic structure for using KSZ8463.  It cannot use the
same regmap table for other KSZ switches as it interprets the 16-bit
value as little-endian and its SPI commands are different.

KSZ8463 uses a byte-enable mechanism to specify 8-bit, 16-bit, and 32-bit
access.  The register is first shifted right by 2 then left by 4.  Extra
4 bits are added.  If the access is 8-bit one of the 4 bits is set.  If
the access is 16-bit two of the 4 bits are set.  If the access is 32-bit
all 4 bits are set.  The SPI command for read or write is then added.

Because of this register transformation separate SPI read and write
functions are provided for KSZ8463.

KSZ8463's internal PHYs use standard PHY register definitions so there is
no need to remap things.  However, the hardware has a bug that the high
word and low word of the PHY id are swapped.  In addition the port
registers are arranged differently so KSZ8463 has its own mapping for
port registers and PHY registers.  Therefore the PORT_CTRL_ADDR macro is
replaced with the get_port_addr helper function.

Signed-off-by: Tristram Ha <tristram.ha@microchip.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20250725001753.6330-3-Tristram.Ha@microchip.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz8.c            |  83 +++++++++++++++++++-
 drivers/net/dsa/microchip/ksz8.h            |   4 +
 drivers/net/dsa/microchip/ksz8_reg.h        |  49 ++++++++++++
 drivers/net/dsa/microchip/ksz_common.c      | 114 ++++++++++++++++++++++++++++
 drivers/net/dsa/microchip/ksz_common.h      |  37 ++++++++-
 drivers/net/dsa/microchip/ksz_spi.c         | 104 +++++++++++++++++++++++++
 include/linux/platform_data/microchip-ksz.h |   1 +
 7 files changed, 389 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/net/dsa/microchip/ksz8.c b/drivers/net/dsa/microchip/ksz8.c
index be433b4e2b1c..3761a81a7320 100644
--- a/drivers/net/dsa/microchip/ksz8.c
+++ b/drivers/net/dsa/microchip/ksz8.c
@@ -3,6 +3,7 @@
  * Microchip KSZ8XXX series switch driver
  *
  * It supports the following switches:
+ * - KSZ8463
  * - KSZ8863, KSZ8873 aka KSZ88X3
  * - KSZ8895, KSZ8864 aka KSZ8895 family
  * - KSZ8794, KSZ8795, KSZ8765 aka KSZ87XX
@@ -41,7 +42,8 @@ static void ksz_cfg(struct ksz_device *dev, u32 addr, u8 bits, bool set)
 static void ksz_port_cfg(struct ksz_device *dev, int port, int offset, u8 bits,
 			 bool set)
 {
-	regmap_update_bits(ksz_regmap_8(dev), PORT_CTRL_ADDR(port, offset),
+	regmap_update_bits(ksz_regmap_8(dev),
+			   dev->dev_ops->get_port_addr(port, offset),
 			   bits, set ? bits : 0);
 }
 
@@ -194,6 +196,7 @@ int ksz8_change_mtu(struct ksz_device *dev, int port, int mtu)
 	case KSZ8794_CHIP_ID:
 	case KSZ8765_CHIP_ID:
 		return ksz8795_change_mtu(dev, frame_size);
+	case KSZ8463_CHIP_ID:
 	case KSZ88X3_CHIP_ID:
 	case KSZ8864_CHIP_ID:
 	case KSZ8895_CHIP_ID:
@@ -1947,6 +1950,84 @@ u32 ksz8_get_port_addr(int port, int offset)
 	return PORT_CTRL_ADDR(port, offset);
 }
 
+u32 ksz8463_get_port_addr(int port, int offset)
+{
+	return offset + 0x18 * port;
+}
+
+static u16 ksz8463_get_phy_addr(u16 phy, u16 reg, u16 offset)
+{
+	return offset + reg * 2 + phy * (P2MBCR - P1MBCR);
+}
+
+int ksz8463_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val)
+{
+	u16 sw_reg = 0;
+	u16 data = 0;
+	int ret;
+
+	if (phy > 1)
+		return -ENOSPC;
+	switch (reg) {
+	case MII_PHYSID1:
+		sw_reg = ksz8463_get_phy_addr(phy, 0, PHY1IHR);
+		break;
+	case MII_PHYSID2:
+		sw_reg = ksz8463_get_phy_addr(phy, 0, PHY1ILR);
+		break;
+	case MII_BMCR:
+	case MII_BMSR:
+	case MII_ADVERTISE:
+	case MII_LPA:
+		sw_reg = ksz8463_get_phy_addr(phy, reg, P1MBCR);
+		break;
+	case MII_TPISTATUS:
+		/* This register holds the PHY interrupt status for simulated
+		 * Micrel KSZ PHY.
+		 */
+		data = 0x0505;
+		break;
+	default:
+		break;
+	}
+	if (sw_reg) {
+		ret = ksz_read16(dev, sw_reg, &data);
+		if (ret)
+			return ret;
+	}
+	*val = data;
+
+	return 0;
+}
+
+int ksz8463_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val)
+{
+	u16 sw_reg = 0;
+	int ret;
+
+	if (phy > 1)
+		return -ENOSPC;
+
+	/* No write to fiber port. */
+	if (dev->ports[phy].fiber)
+		return 0;
+	switch (reg) {
+	case MII_BMCR:
+	case MII_ADVERTISE:
+		sw_reg = ksz8463_get_phy_addr(phy, reg, P1MBCR);
+		break;
+	default:
+		break;
+	}
+	if (sw_reg) {
+		ret = ksz_write16(dev, sw_reg, val);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 int ksz8_switch_init(struct ksz_device *dev)
 {
 	dev->cpu_port = fls(dev->info->cpu_ports) - 1;
diff --git a/drivers/net/dsa/microchip/ksz8.h b/drivers/net/dsa/microchip/ksz8.h
index e1c79ff97123..0f2cd1474b44 100644
--- a/drivers/net/dsa/microchip/ksz8.h
+++ b/drivers/net/dsa/microchip/ksz8.h
@@ -63,4 +63,8 @@ void ksz8_phylink_mac_link_up(struct phylink_config *config,
 			      bool tx_pause, bool rx_pause);
 int ksz8_all_queues_split(struct ksz_device *dev, int queues);
 
+u32 ksz8463_get_port_addr(int port, int offset);
+int ksz8463_r_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 *val);
+int ksz8463_w_phy(struct ksz_device *dev, u16 phy, u16 reg, u16 val);
+
 #endif
diff --git a/drivers/net/dsa/microchip/ksz8_reg.h b/drivers/net/dsa/microchip/ksz8_reg.h
index 329688603a58..491aa1e50175 100644
--- a/drivers/net/dsa/microchip/ksz8_reg.h
+++ b/drivers/net/dsa/microchip/ksz8_reg.h
@@ -729,6 +729,55 @@
 #define PHY_POWER_SAVING_ENABLE		BIT(2)
 #define PHY_REMOTE_LOOPBACK		BIT(1)
 
+/* KSZ8463 specific registers. */
+#define P1MBCR				0x4C
+#define P1MBSR				0x4E
+#define PHY1ILR				0x50
+#define PHY1IHR				0x52
+#define P1ANAR				0x54
+#define P1ANLPR				0x56
+#define P2MBCR				0x58
+#define P2MBSR				0x5A
+#define PHY2ILR				0x5C
+#define PHY2IHR				0x5E
+#define P2ANAR				0x60
+#define P2ANLPR				0x62
+
+#define P1CR1				0x6C
+#define P1CR2				0x6E
+#define P1CR3				0x72
+#define P1CR4				0x7E
+#define P1SR				0x80
+
+#define KSZ8463_FLUSH_TABLE_CTRL	0xAD
+
+#define KSZ8463_FLUSH_DYN_MAC_TABLE	BIT(2)
+#define KSZ8463_FLUSH_STA_MAC_TABLE	BIT(1)
+
+#define KSZ8463_REG_SW_CTRL_9		0xAE
+
+#define KSZ8463_REG_CFG_CTRL		0xD8
+
+#define PORT_2_COPPER_MODE		BIT(7)
+#define PORT_1_COPPER_MODE		BIT(6)
+#define PORT_COPPER_MODE_S		6
+
+#define KSZ8463_REG_SW_RESET		0x126
+
+#define KSZ8463_GLOBAL_SOFTWARE_RESET	BIT(0)
+
+#define KSZ8463_PTP_CLK_CTRL		0x600
+
+#define PTP_CLK_ENABLE			BIT(1)
+
+#define KSZ8463_PTP_MSG_CONF1		0x620
+
+#define PTP_ENABLE			BIT(6)
+
+#define KSZ8463_REG_DSP_CTRL_6		0x734
+
+#define COPPER_RECEIVE_ADJUSTMENT	BIT(13)
+
 /* Chip resource */
 
 #define PRIO_QUEUES			4
diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
index 6e1daf0018bc..095e647b3897 100644
--- a/drivers/net/dsa/microchip/ksz_common.c
+++ b/drivers/net/dsa/microchip/ksz_common.c
@@ -331,6 +331,38 @@ static const struct phylink_mac_ops ksz8_phylink_mac_ops = {
 	.mac_enable_tx_lpi = ksz_phylink_mac_enable_tx_lpi,
 };
 
+static const struct ksz_dev_ops ksz8463_dev_ops = {
+	.setup = ksz8_setup,
+	.get_port_addr = ksz8463_get_port_addr,
+	.cfg_port_member = ksz8_cfg_port_member,
+	.flush_dyn_mac_table = ksz8_flush_dyn_mac_table,
+	.port_setup = ksz8_port_setup,
+	.r_phy = ksz8463_r_phy,
+	.w_phy = ksz8463_w_phy,
+	.r_mib_cnt = ksz8_r_mib_cnt,
+	.r_mib_pkt = ksz8_r_mib_pkt,
+	.r_mib_stat64 = ksz88xx_r_mib_stats64,
+	.freeze_mib = ksz8_freeze_mib,
+	.port_init_cnt = ksz8_port_init_cnt,
+	.fdb_dump = ksz8_fdb_dump,
+	.fdb_add = ksz8_fdb_add,
+	.fdb_del = ksz8_fdb_del,
+	.mdb_add = ksz8_mdb_add,
+	.mdb_del = ksz8_mdb_del,
+	.vlan_filtering = ksz8_port_vlan_filtering,
+	.vlan_add = ksz8_port_vlan_add,
+	.vlan_del = ksz8_port_vlan_del,
+	.mirror_add = ksz8_port_mirror_add,
+	.mirror_del = ksz8_port_mirror_del,
+	.get_caps = ksz8_get_caps,
+	.config_cpu_port = ksz8_config_cpu_port,
+	.enable_stp_addr = ksz8_enable_stp_addr,
+	.reset = ksz8_reset_switch,
+	.init = ksz8_switch_init,
+	.exit = ksz8_switch_exit,
+	.change_mtu = ksz8_change_mtu,
+};
+
 static const struct ksz_dev_ops ksz88xx_dev_ops = {
 	.setup = ksz8_setup,
 	.get_port_addr = ksz8_get_port_addr,
@@ -517,6 +549,60 @@ static const struct ksz_dev_ops lan937x_dev_ops = {
 	.exit = lan937x_switch_exit,
 };
 
+static const u16 ksz8463_regs[] = {
+	[REG_SW_MAC_ADDR]		= 0x10,
+	[REG_IND_CTRL_0]		= 0x30,
+	[REG_IND_DATA_8]		= 0x26,
+	[REG_IND_DATA_CHECK]		= 0x26,
+	[REG_IND_DATA_HI]		= 0x28,
+	[REG_IND_DATA_LO]		= 0x2C,
+	[REG_IND_MIB_CHECK]		= 0x2F,
+	[P_FORCE_CTRL]			= 0x0C,
+	[P_LINK_STATUS]			= 0x0E,
+	[P_LOCAL_CTRL]			= 0x0C,
+	[P_NEG_RESTART_CTRL]		= 0x0D,
+	[P_REMOTE_STATUS]		= 0x0E,
+	[P_SPEED_STATUS]		= 0x0F,
+	[S_TAIL_TAG_CTRL]		= 0xAD,
+	[P_STP_CTRL]			= 0x6F,
+	[S_START_CTRL]			= 0x01,
+	[S_BROADCAST_CTRL]		= 0x06,
+	[S_MULTICAST_CTRL]		= 0x04,
+};
+
+static const u32 ksz8463_masks[] = {
+	[PORT_802_1P_REMAPPING]		= BIT(3),
+	[SW_TAIL_TAG_ENABLE]		= BIT(0),
+	[MIB_COUNTER_OVERFLOW]		= BIT(7),
+	[MIB_COUNTER_VALID]		= BIT(6),
+	[VLAN_TABLE_FID]		= GENMASK(15, 12),
+	[VLAN_TABLE_MEMBERSHIP]		= GENMASK(18, 16),
+	[VLAN_TABLE_VALID]		= BIT(19),
+	[STATIC_MAC_TABLE_VALID]	= BIT(19),
+	[STATIC_MAC_TABLE_USE_FID]	= BIT(21),
+	[STATIC_MAC_TABLE_FID]		= GENMASK(25, 22),
+	[STATIC_MAC_TABLE_OVERRIDE]	= BIT(20),
+	[STATIC_MAC_TABLE_FWD_PORTS]	= GENMASK(18, 16),
+	[DYNAMIC_MAC_TABLE_ENTRIES_H]	= GENMASK(1, 0),
+	[DYNAMIC_MAC_TABLE_MAC_EMPTY]	= BIT(2),
+	[DYNAMIC_MAC_TABLE_NOT_READY]	= BIT(7),
+	[DYNAMIC_MAC_TABLE_ENTRIES]	= GENMASK(31, 24),
+	[DYNAMIC_MAC_TABLE_FID]		= GENMASK(19, 16),
+	[DYNAMIC_MAC_TABLE_SRC_PORT]	= GENMASK(21, 20),
+	[DYNAMIC_MAC_TABLE_TIMESTAMP]	= GENMASK(23, 22),
+};
+
+static u8 ksz8463_shifts[] = {
+	[VLAN_TABLE_MEMBERSHIP_S]	= 16,
+	[STATIC_MAC_FWD_PORTS]		= 16,
+	[STATIC_MAC_FID]		= 22,
+	[DYNAMIC_MAC_ENTRIES_H]		= 8,
+	[DYNAMIC_MAC_ENTRIES]		= 24,
+	[DYNAMIC_MAC_FID]		= 16,
+	[DYNAMIC_MAC_TIMESTAMP]		= 22,
+	[DYNAMIC_MAC_SRC_PORT]		= 20,
+};
+
 static const u16 ksz8795_regs[] = {
 	[REG_SW_MAC_ADDR]		= 0x68,
 	[REG_IND_CTRL_0]		= 0x6E,
@@ -1387,6 +1473,29 @@ static const struct regmap_access_table ksz8873_register_set = {
 };
 
 const struct ksz_chip_data ksz_switch_chips[] = {
+	[KSZ8463] = {
+		.chip_id = KSZ8463_CHIP_ID,
+		.dev_name = "KSZ8463",
+		.num_vlans = 16,
+		.num_alus = 0,
+		.num_statics = 8,
+		.cpu_ports = 0x4,	/* can be configured as cpu port */
+		.port_cnt = 3,
+		.num_tx_queues = 4,
+		.num_ipms = 4,
+		.ops = &ksz8463_dev_ops,
+		.phylink_mac_ops = &ksz88x3_phylink_mac_ops,
+		.mib_names = ksz88xx_mib_names,
+		.mib_cnt = ARRAY_SIZE(ksz88xx_mib_names),
+		.reg_mib_cnt = MIB_COUNTER_NUM,
+		.regs = ksz8463_regs,
+		.masks = ksz8463_masks,
+		.shifts = ksz8463_shifts,
+		.supports_mii = {false, false, true},
+		.supports_rmii = {false, false, true},
+		.internal_phy = {true, true, false},
+	},
+
 	[KSZ8563] = {
 		.chip_id = KSZ8563_CHIP_ID,
 		.dev_name = "KSZ8563",
@@ -3400,6 +3509,7 @@ static enum dsa_tag_protocol ksz_get_tag_protocol(struct dsa_switch *ds,
 		proto = DSA_TAG_PROTO_KSZ8795;
 
 	if (dev->chip_id == KSZ88X3_CHIP_ID ||
+	    dev->chip_id == KSZ8463_CHIP_ID ||
 	    dev->chip_id == KSZ8563_CHIP_ID ||
 	    dev->chip_id == KSZ9893_CHIP_ID ||
 	    dev->chip_id == KSZ9563_CHIP_ID)
@@ -3512,6 +3622,7 @@ static int ksz_max_mtu(struct dsa_switch *ds, int port)
 	case KSZ8794_CHIP_ID:
 	case KSZ8765_CHIP_ID:
 		return KSZ8795_HUGE_PACKET_SIZE - VLAN_ETH_HLEN - ETH_FCS_LEN;
+	case KSZ8463_CHIP_ID:
 	case KSZ88X3_CHIP_ID:
 	case KSZ8864_CHIP_ID:
 	case KSZ8895_CHIP_ID:
@@ -3866,6 +3977,9 @@ static int ksz_switch_detect(struct ksz_device *dev)
 	id2 = FIELD_GET(SW_CHIP_ID_M, id16);
 
 	switch (id1) {
+	case KSZ84_FAMILY_ID:
+		dev->chip_id = KSZ8463_CHIP_ID;
+		break;
 	case KSZ87_FAMILY_ID:
 		if (id2 == KSZ87_CHIP_ID_95) {
 			u8 val;
diff --git a/drivers/net/dsa/microchip/ksz_common.h b/drivers/net/dsa/microchip/ksz_common.h
index a08417df2ca4..a1eb39771bb9 100644
--- a/drivers/net/dsa/microchip/ksz_common.h
+++ b/drivers/net/dsa/microchip/ksz_common.h
@@ -222,6 +222,7 @@ struct ksz_device {
 
 /* List of supported models */
 enum ksz_model {
+	KSZ8463,
 	KSZ8563,
 	KSZ8567,
 	KSZ8795,
@@ -484,6 +485,11 @@ static inline struct regmap *ksz_regmap_32(struct ksz_device *dev)
 	return dev->regmap[KSZ_REGMAP_32];
 }
 
+static inline bool ksz_is_ksz8463(struct ksz_device *dev)
+{
+	return dev->chip_id == KSZ8463_CHIP_ID;
+}
+
 static inline int ksz_read8(struct ksz_device *dev, u32 reg, u8 *val)
 {
 	unsigned int value;
@@ -709,12 +715,13 @@ static inline bool ksz_is_8895_family(struct ksz_device *dev)
 static inline bool is_ksz8(struct ksz_device *dev)
 {
 	return ksz_is_ksz87xx(dev) || ksz_is_ksz88x3(dev) ||
-	       ksz_is_8895_family(dev);
+	       ksz_is_8895_family(dev) || ksz_is_ksz8463(dev);
 }
 
 static inline bool is_ksz88xx(struct ksz_device *dev)
 {
-	return ksz_is_ksz88x3(dev) || ksz_is_8895_family(dev);
+	return ksz_is_ksz88x3(dev) || ksz_is_8895_family(dev) ||
+	       ksz_is_ksz8463(dev);
 }
 
 static inline bool is_ksz9477(struct ksz_device *dev)
@@ -761,6 +768,7 @@ static inline bool ksz_is_sgmii_port(struct ksz_device *dev, int port)
 #define REG_CHIP_ID0			0x00
 
 #define SW_FAMILY_ID_M			GENMASK(15, 8)
+#define KSZ84_FAMILY_ID			0x84
 #define KSZ87_FAMILY_ID			0x87
 #define KSZ88_FAMILY_ID			0x88
 #define KSZ8895_FAMILY_ID		0x95
@@ -939,4 +947,29 @@ static inline bool ksz_is_sgmii_port(struct ksz_device *dev, int port)
 		[KSZ_REGMAP_32] = KSZ_REGMAP_ENTRY(32, swp, (regbits), (regpad), (regalign)), \
 	}
 
+#define KSZ8463_REGMAP_ENTRY(width, regbits, regpad, regalign)		\
+	{								\
+		.name = #width,						\
+		.val_bits = (width),					\
+		.reg_stride = (width / 8),				\
+		.reg_bits = (regbits) + (regalign),			\
+		.pad_bits = (regpad),					\
+		.read = ksz8463_spi_read,				\
+		.write = ksz8463_spi_write,				\
+		.max_register = BIT(regbits) - 1,			\
+		.cache_type = REGCACHE_NONE,				\
+		.zero_flag_mask = 1,					\
+		.use_single_read = 1,					\
+		.use_single_write = 1,					\
+		.lock = ksz_regmap_lock,				\
+		.unlock = ksz_regmap_unlock,				\
+	}
+
+#define KSZ8463_REGMAP_TABLE(ksz, regbits, regpad, regalign)		\
+	static const struct regmap_config ksz##_regmap_config[] = {	\
+		[KSZ_REGMAP_8] = KSZ8463_REGMAP_ENTRY(8, (regbits), (regpad), (regalign)), \
+		[KSZ_REGMAP_16] = KSZ8463_REGMAP_ENTRY(16, (regbits), (regpad), (regalign)), \
+		[KSZ_REGMAP_32] = KSZ8463_REGMAP_ENTRY(32, (regbits), (regpad), (regalign)), \
+	}
+
 #endif
diff --git a/drivers/net/dsa/microchip/ksz_spi.c b/drivers/net/dsa/microchip/ksz_spi.c
index b633d263098c..d8001734b057 100644
--- a/drivers/net/dsa/microchip/ksz_spi.c
+++ b/drivers/net/dsa/microchip/ksz_spi.c
@@ -16,6 +16,10 @@
 
 #include "ksz_common.h"
 
+#define KSZ8463_SPI_ADDR_SHIFT			13
+#define KSZ8463_SPI_ADDR_ALIGN			3
+#define KSZ8463_SPI_TURNAROUND_SHIFT		2
+
 #define KSZ8795_SPI_ADDR_SHIFT			12
 #define KSZ8795_SPI_ADDR_ALIGN			3
 #define KSZ8795_SPI_TURNAROUND_SHIFT		1
@@ -37,6 +41,99 @@ KSZ_REGMAP_TABLE(ksz8863, 16, KSZ8863_SPI_ADDR_SHIFT,
 KSZ_REGMAP_TABLE(ksz9477, 32, KSZ9477_SPI_ADDR_SHIFT,
 		 KSZ9477_SPI_TURNAROUND_SHIFT, KSZ9477_SPI_ADDR_ALIGN);
 
+static u16 ksz8463_reg(u16 reg, size_t size)
+{
+	switch (size) {
+	case 1:
+		reg = ((reg >> 2) << 4) | (1 << (reg & 3));
+		break;
+	case 2:
+		reg = ((reg >> 2) << 4) | (reg & 2 ? 0x0c : 0x03);
+		break;
+	default:
+		reg = ((reg >> 2) << 4) | 0xf;
+		break;
+	}
+	reg <<= KSZ8463_SPI_TURNAROUND_SHIFT;
+	return reg;
+}
+
+static int ksz8463_spi_read(void *context,
+			    const void *reg, size_t reg_size,
+			    void *val, size_t val_size)
+{
+	struct device *dev = context;
+	struct spi_device *spi = to_spi_device(dev);
+	u8 bytes[2];
+	u16 cmd;
+	int rc;
+
+	if (reg_size > 2 || val_size > 4)
+		return -EINVAL;
+	memcpy(&cmd, reg, sizeof(u16));
+	cmd = ksz8463_reg(cmd, val_size);
+	/* SPI command uses big-endian format. */
+	put_unaligned_be16(cmd, bytes);
+	rc = spi_write_then_read(spi, bytes, reg_size, val, val_size);
+#if defined(__BIG_ENDIAN)
+	/* Register value uses little-endian format so need to convert when
+	 * running in big-endian system.
+	 */
+	if (!rc && val_size > 1) {
+		if (val_size == 2) {
+			u16 v = get_unaligned_le16(val);
+
+			memcpy(val, &v, sizeof(v));
+		} else if (val_size == 4) {
+			u32 v = get_unaligned_le32(val);
+
+			memcpy(val, &v, sizeof(v));
+		}
+	}
+#endif
+	return rc;
+}
+
+static int ksz8463_spi_write(void *context, const void *data, size_t count)
+{
+	struct device *dev = context;
+	struct spi_device *spi = to_spi_device(dev);
+	size_t val_size = count - 2;
+	u8 bytes[6];
+	u16 cmd;
+
+	if (count <= 2 || count > 6)
+		return -EINVAL;
+	memcpy(bytes, data, count);
+	memcpy(&cmd, data, sizeof(u16));
+	cmd = ksz8463_reg(cmd, val_size);
+	cmd |= (1 << (KSZ8463_SPI_ADDR_SHIFT + KSZ8463_SPI_TURNAROUND_SHIFT));
+	/* SPI command uses big-endian format. */
+	put_unaligned_be16(cmd, bytes);
+#if defined(__BIG_ENDIAN)
+	/* Register value uses little-endian format so need to convert when
+	 * running in big-endian system.
+	 */
+	if (val_size == 2) {
+		u8 *val = &bytes[2];
+		u16 v;
+
+		memcpy(&v, val, sizeof(v));
+		put_unaligned_le16(v, val);
+	} else if (val_size == 4) {
+		u8 *val = &bytes[2];
+		u32 v;
+
+		memcpy(&v, val, sizeof(v));
+		put_unaligned_le32(v, val);
+	}
+#endif
+	return spi_write(spi, bytes, count);
+}
+
+KSZ8463_REGMAP_TABLE(ksz8463, KSZ8463_SPI_ADDR_SHIFT, 0,
+		     KSZ8463_SPI_ADDR_ALIGN);
+
 static int ksz_spi_probe(struct spi_device *spi)
 {
 	const struct regmap_config *regmap_config;
@@ -58,6 +155,8 @@ static int ksz_spi_probe(struct spi_device *spi)
 	dev->chip_id = chip->chip_id;
 	if (chip->chip_id == KSZ88X3_CHIP_ID)
 		regmap_config = ksz8863_regmap_config;
+	else if (chip->chip_id == KSZ8463_CHIP_ID)
+		regmap_config = ksz8463_regmap_config;
 	else if (chip->chip_id == KSZ8795_CHIP_ID ||
 		 chip->chip_id == KSZ8794_CHIP_ID ||
 		 chip->chip_id == KSZ8765_CHIP_ID)
@@ -125,6 +224,10 @@ static void ksz_spi_shutdown(struct spi_device *spi)
 }
 
 static const struct of_device_id ksz_dt_ids[] = {
+	{
+		.compatible = "microchip,ksz8463",
+		.data = &ksz_switch_chips[KSZ8463]
+	},
 	{
 		.compatible = "microchip,ksz8765",
 		.data = &ksz_switch_chips[KSZ8765]
@@ -214,6 +317,7 @@ static const struct of_device_id ksz_dt_ids[] = {
 MODULE_DEVICE_TABLE(of, ksz_dt_ids);
 
 static const struct spi_device_id ksz_spi_ids[] = {
+	{ "ksz8463" },
 	{ "ksz8765" },
 	{ "ksz8794" },
 	{ "ksz8795" },
diff --git a/include/linux/platform_data/microchip-ksz.h b/include/linux/platform_data/microchip-ksz.h
index 0e0e8fe6975f..028781ad4059 100644
--- a/include/linux/platform_data/microchip-ksz.h
+++ b/include/linux/platform_data/microchip-ksz.h
@@ -23,6 +23,7 @@
 #include <linux/platform_data/dsa.h>
 
 enum ksz_chip_id {
+	KSZ8463_CHIP_ID = 0x8463,
 	KSZ8563_CHIP_ID = 0x8563,
 	KSZ8795_CHIP_ID = 0x8795,
 	KSZ8794_CHIP_ID = 0x8794,
-- 
cgit v1.2.3


From b7b3500bd4eef2c3b5124ed195f26eb048407d9b Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Date: Mon, 21 Jul 2025 11:04:42 +0200
Subject: umd: Remove usermode driver framework
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The code is unused since 98e20e5e13d2 ("bpfilter: remove bpfilter"),
therefore remove it.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Christian Brauner <brauner@kernel.org>
Acked-by: "Eric W. Biederman" <ebiederm@xmission.com>
Link: https://lore.kernel.org/bpf/20250721-remove-usermode-driver-v1-2-0d0083334382@linutronix.de
---
 include/linux/usermode_driver.h |  19 ----
 kernel/Makefile                 |   1 -
 kernel/bpf/preload/Kconfig      |   4 -
 kernel/usermode_driver.c        | 191 ----------------------------------------
 4 files changed, 215 deletions(-)
 delete mode 100644 include/linux/usermode_driver.h
 delete mode 100644 kernel/usermode_driver.c

(limited to 'include/linux')

diff --git a/include/linux/usermode_driver.h b/include/linux/usermode_driver.h
deleted file mode 100644
index ad970416260d..000000000000
--- a/include/linux/usermode_driver.h
+++ /dev/null
@@ -1,19 +0,0 @@
-#ifndef __LINUX_USERMODE_DRIVER_H__
-#define __LINUX_USERMODE_DRIVER_H__
-
-#include <linux/umh.h>
-#include <linux/path.h>
-
-struct umd_info {
-	const char *driver_name;
-	struct file *pipe_to_umh;
-	struct file *pipe_from_umh;
-	struct path wd;
-	struct pid *tgid;
-};
-int umd_load_blob(struct umd_info *info, const void *data, size_t len);
-int umd_unload_blob(struct umd_info *info);
-int fork_usermode_driver(struct umd_info *info);
-void umd_cleanup_helper(struct umd_info *info);
-
-#endif /* __LINUX_USERMODE_DRIVER_H__ */
diff --git a/kernel/Makefile b/kernel/Makefile
index 32e80dd626af..4332de7ffdee 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -12,7 +12,6 @@ obj-y     = fork.o exec_domain.o panic.o \
 	    notifier.o ksysfs.o cred.o reboot.o \
 	    async.o range.o smpboot.o ucount.o regset.o ksyms_common.o
 
-obj-$(CONFIG_USERMODE_DRIVER) += usermode_driver.o
 obj-$(CONFIG_MULTIUSER) += groups.o
 obj-$(CONFIG_VHOST_TASK) += vhost_task.o
 
diff --git a/kernel/bpf/preload/Kconfig b/kernel/bpf/preload/Kconfig
index f9b11d01c3b5..aef7b0bc96d6 100644
--- a/kernel/bpf/preload/Kconfig
+++ b/kernel/bpf/preload/Kconfig
@@ -1,8 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
-config USERMODE_DRIVER
-	bool
-	default n
-
 menuconfig BPF_PRELOAD
 	bool "Preload BPF file system with kernel specific program and map iterators"
 	depends on BPF
diff --git a/kernel/usermode_driver.c b/kernel/usermode_driver.c
deleted file mode 100644
index 8303f4c7ca71..000000000000
--- a/kernel/usermode_driver.c
+++ /dev/null
@@ -1,191 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-/*
- * umd - User mode driver support
- */
-#include <linux/shmem_fs.h>
-#include <linux/pipe_fs_i.h>
-#include <linux/mount.h>
-#include <linux/fs_struct.h>
-#include <linux/task_work.h>
-#include <linux/usermode_driver.h>
-
-static struct vfsmount *blob_to_mnt(const void *data, size_t len, const char *name)
-{
-	struct file_system_type *type;
-	struct vfsmount *mnt;
-	struct file *file;
-	ssize_t written;
-	loff_t pos = 0;
-
-	type = get_fs_type("tmpfs");
-	if (!type)
-		return ERR_PTR(-ENODEV);
-
-	mnt = kern_mount(type);
-	put_filesystem(type);
-	if (IS_ERR(mnt))
-		return mnt;
-
-	file = file_open_root_mnt(mnt, name, O_CREAT | O_WRONLY, 0700);
-	if (IS_ERR(file)) {
-		kern_unmount(mnt);
-		return ERR_CAST(file);
-	}
-
-	written = kernel_write(file, data, len, &pos);
-	if (written != len) {
-		int err = written;
-		if (err >= 0)
-			err = -ENOMEM;
-		filp_close(file, NULL);
-		kern_unmount(mnt);
-		return ERR_PTR(err);
-	}
-
-	fput(file);
-
-	/* Flush delayed fput so exec can open the file read-only */
-	flush_delayed_fput();
-	task_work_run();
-	return mnt;
-}
-
-/**
- * umd_load_blob - Remember a blob of bytes for fork_usermode_driver
- * @info: information about usermode driver
- * @data: a blob of bytes that can be executed as a file
- * @len:  The lentgh of the blob
- *
- */
-int umd_load_blob(struct umd_info *info, const void *data, size_t len)
-{
-	struct vfsmount *mnt;
-
-	if (WARN_ON_ONCE(info->wd.dentry || info->wd.mnt))
-		return -EBUSY;
-
-	mnt = blob_to_mnt(data, len, info->driver_name);
-	if (IS_ERR(mnt))
-		return PTR_ERR(mnt);
-
-	info->wd.mnt = mnt;
-	info->wd.dentry = mnt->mnt_root;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(umd_load_blob);
-
-/**
- * umd_unload_blob - Disassociate @info from a previously loaded blob
- * @info: information about usermode driver
- *
- */
-int umd_unload_blob(struct umd_info *info)
-{
-	if (WARN_ON_ONCE(!info->wd.mnt ||
-			 !info->wd.dentry ||
-			 info->wd.mnt->mnt_root != info->wd.dentry))
-		return -EINVAL;
-
-	kern_unmount(info->wd.mnt);
-	info->wd.mnt = NULL;
-	info->wd.dentry = NULL;
-	return 0;
-}
-EXPORT_SYMBOL_GPL(umd_unload_blob);
-
-static int umd_setup(struct subprocess_info *info, struct cred *new)
-{
-	struct umd_info *umd_info = info->data;
-	struct file *from_umh[2];
-	struct file *to_umh[2];
-	int err;
-
-	/* create pipe to send data to umh */
-	err = create_pipe_files(to_umh, 0);
-	if (err)
-		return err;
-	err = replace_fd(0, to_umh[0], 0);
-	fput(to_umh[0]);
-	if (err < 0) {
-		fput(to_umh[1]);
-		return err;
-	}
-
-	/* create pipe to receive data from umh */
-	err = create_pipe_files(from_umh, 0);
-	if (err) {
-		fput(to_umh[1]);
-		replace_fd(0, NULL, 0);
-		return err;
-	}
-	err = replace_fd(1, from_umh[1], 0);
-	fput(from_umh[1]);
-	if (err < 0) {
-		fput(to_umh[1]);
-		replace_fd(0, NULL, 0);
-		fput(from_umh[0]);
-		return err;
-	}
-
-	set_fs_pwd(current->fs, &umd_info->wd);
-	umd_info->pipe_to_umh = to_umh[1];
-	umd_info->pipe_from_umh = from_umh[0];
-	umd_info->tgid = get_pid(task_tgid(current));
-	return 0;
-}
-
-static void umd_cleanup(struct subprocess_info *info)
-{
-	struct umd_info *umd_info = info->data;
-
-	/* cleanup if umh_setup() was successful but exec failed */
-	if (info->retval)
-		umd_cleanup_helper(umd_info);
-}
-
-/**
- * umd_cleanup_helper - release the resources which were allocated in umd_setup
- * @info: information about usermode driver
- */
-void umd_cleanup_helper(struct umd_info *info)
-{
-	fput(info->pipe_to_umh);
-	fput(info->pipe_from_umh);
-	put_pid(info->tgid);
-	info->tgid = NULL;
-}
-EXPORT_SYMBOL_GPL(umd_cleanup_helper);
-
-/**
- * fork_usermode_driver - fork a usermode driver
- * @info: information about usermode driver (shouldn't be NULL)
- *
- * Returns either negative error or zero which indicates success in
- * executing a usermode driver. In such case 'struct umd_info *info'
- * is populated with two pipes and a tgid of the process. The caller is
- * responsible for health check of the user process, killing it via
- * tgid, and closing the pipes when user process is no longer needed.
- */
-int fork_usermode_driver(struct umd_info *info)
-{
-	struct subprocess_info *sub_info;
-	const char *argv[] = { info->driver_name, NULL };
-	int err;
-
-	if (WARN_ON_ONCE(info->tgid))
-		return -EBUSY;
-
-	err = -ENOMEM;
-	sub_info = call_usermodehelper_setup(info->driver_name,
-					     (char **)argv, NULL, GFP_KERNEL,
-					     umd_setup, umd_cleanup, info);
-	if (!sub_info)
-		goto out;
-
-	err = call_usermodehelper_exec(sub_info, UMH_WAIT_EXEC);
-out:
-	return err;
-}
-EXPORT_SYMBOL_GPL(fork_usermode_driver);
-
-
-- 
cgit v1.2.3


From 3ba58312e65665e5b9097c7969a51fa49914d85d Mon Sep 17 00:00:00 2001
From: Puranjay Mohan <puranjay@kernel.org>
Date: Thu, 24 Jul 2025 12:02:53 +0000
Subject: bpf: Move bpf_jit_get_prog_name() to core.c

bpf_jit_get_prog_name() will be used by all JITs when enabling support
for private stack. This function is currently implemented in the x86
JIT.

Move the function to core.c so that other JITs can easily use it in
their implementation of private stack.

Signed-off-by: Puranjay Mohan <puranjay@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Yonghong Song <yonghong.song@linux.dev>
Link: https://lore.kernel.org/bpf/20250724120257.7299-2-puranjay@kernel.org
---
 arch/x86/net/bpf_jit_comp.c | 9 +--------
 include/linux/filter.h      | 2 ++
 kernel/bpf/core.c           | 7 +++++++
 3 files changed, 10 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
index 40e1b3b9634f..7e3fca164620 100644
--- a/arch/x86/net/bpf_jit_comp.c
+++ b/arch/x86/net/bpf_jit_comp.c
@@ -3501,13 +3501,6 @@ int arch_prepare_bpf_dispatcher(void *image, void *buf, s64 *funcs, int num_func
 	return emit_bpf_dispatcher(&prog, 0, num_funcs - 1, funcs, image, buf);
 }
 
-static const char *bpf_get_prog_name(struct bpf_prog *prog)
-{
-	if (prog->aux->ksym.prog)
-		return prog->aux->ksym.name;
-	return prog->aux->name;
-}
-
 static void priv_stack_init_guard(void __percpu *priv_stack_ptr, int alloc_size)
 {
 	int cpu, underflow_idx = (alloc_size - PRIV_STACK_GUARD_SZ) >> 3;
@@ -3531,7 +3524,7 @@ static void priv_stack_check_guard(void __percpu *priv_stack_ptr, int alloc_size
 		if (stack_ptr[0] != PRIV_STACK_GUARD_VAL ||
 		    stack_ptr[underflow_idx] != PRIV_STACK_GUARD_VAL) {
 			pr_err("BPF private stack overflow/underflow detected for prog %sx\n",
-			       bpf_get_prog_name(prog));
+			       bpf_jit_get_prog_name(prog));
 			break;
 		}
 	}
diff --git a/include/linux/filter.h b/include/linux/filter.h
index eca229752cbe..5cc7a82ec832 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -1278,6 +1278,8 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
 			  const struct bpf_insn *insn, bool extra_pass,
 			  u64 *func_addr, bool *func_addr_fixed);
 
+const char *bpf_jit_get_prog_name(struct bpf_prog *prog);
+
 struct bpf_prog *bpf_jit_blind_constants(struct bpf_prog *fp);
 void bpf_jit_prog_release_other(struct bpf_prog *fp, struct bpf_prog *fp_other);
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 61613785bdd0..29c0225c14aa 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -1297,6 +1297,13 @@ int bpf_jit_get_func_addr(const struct bpf_prog *prog,
 	return 0;
 }
 
+const char *bpf_jit_get_prog_name(struct bpf_prog *prog)
+{
+	if (prog->aux->ksym.prog)
+		return prog->aux->ksym.name;
+	return prog->aux->name;
+}
+
 static int bpf_jit_blind_insn(const struct bpf_insn *from,
 			      const struct bpf_insn *aux,
 			      struct bpf_insn *to_buff,
-- 
cgit v1.2.3


From 381a38ea53d25ed6f93ba007b021db86c2a36bc6 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Wed, 23 Jul 2025 22:50:27 -0700
Subject: init.h: Disable sanitizer coverage for __init and __head

While __noinstr already contained __no_sanitize_coverage, it needs to
be added to __init and __head section markings to support the Clang
implementation of CONFIG_KSTACK_ERASE. This is to make sure the stack
depth tracking callback is not executed in unsupported contexts.

The other sanitizer coverage options (trace-pc and trace-cmp) aren't
needed in __head nor __init either ("We are interested in code coverage
as a function of a syscall inputs"[1]), so this is fine to disable for
them as well.

Link: https://web.git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/tree/kernel/kcov.c?h=v6.14#n179 [1]
Acked-by: Marco Elver <elver@google.com>
Link: https://lore.kernel.org/r/20250724055029.3623499-3-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 arch/x86/include/asm/init.h | 2 +-
 include/linux/init.h        | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 8b1b1abcef15..6bfdaeddbae8 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -5,7 +5,7 @@
 #if defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
 #define __head	__section(".head.text") __no_sanitize_undefined __no_stack_protector
 #else
-#define __head	__section(".head.text") __no_sanitize_undefined
+#define __head	__section(".head.text") __no_sanitize_undefined __no_sanitize_coverage
 #endif
 
 struct x86_mapping_info {
diff --git a/include/linux/init.h b/include/linux/init.h
index ee1309473bc6..c65a050d52a7 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -49,7 +49,9 @@
 
 /* These are for everybody (although not all archs will actually
    discard it in modules) */
-#define __init		__section(".init.text") __cold  __latent_entropy __noinitretpoline
+#define __init		__section(".init.text") __cold __latent_entropy	\
+						__noinitretpoline	\
+						__no_sanitize_coverage
 #define __initdata	__section(".init.data")
 #define __initconst	__section(".init.rodata")
 #define __exitdata	__section(".exit.data")
-- 
cgit v1.2.3


From 32e42ab9fc88a884435c27527a433f61c4d2b61b Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Sat, 26 Jul 2025 00:29:54 -0700
Subject: sched/task_stack: Add missing const qualifier to end_of_stack()

Add missing const qualifier to the non-CONFIG_THREAD_INFO_IN_TASK
version of end_of_stack() to match the CONFIG_THREAD_INFO_IN_TASK
version. Fixes a warning with CONFIG_KSTACK_ERASE=y on archs that don't
select THREAD_INFO_IN_TASK (such as LoongArch):

  error: passing 'const struct task_struct *' to parameter of type 'struct task_struct *' discards qualifiers

The stackleak_task_low_bound() function correctly uses a const task
parameter, but the legacy end_of_stack() prototype didn't like that.

Build tested on loongarch (with CONFIG_KSTACK_ERASE=y) and m68k
(with CONFIG_DEBUG_STACK_USAGE=y).

Fixes: a45728fd4120 ("LoongArch: Enable HAVE_ARCH_STACKLEAK")
Reported-by: Nathan Chancellor <nathan@kernel.org>
Closes: https://lore.kernel.org/all/20250726004313.GA3650901@ax162
Cc: Youling Tang <tangyouling@kylinos.cn>
Cc: Huacai Chen <chenhuacai@loongson.cn>
Tested-by: Nathan Chancellor <nathan@kernel.org>
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/sched/task_stack.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/sched/task_stack.h b/include/linux/sched/task_stack.h
index 85c5a6392e02..1fab7e9043a3 100644
--- a/include/linux/sched/task_stack.h
+++ b/include/linux/sched/task_stack.h
@@ -53,7 +53,7 @@ static inline void setup_thread_stack(struct task_struct *p, struct task_struct
  * When the stack grows up, this is the highest address.
  * Beyond that position, we corrupt data on the next page.
  */
-static inline unsigned long *end_of_stack(struct task_struct *p)
+static inline unsigned long *end_of_stack(const struct task_struct *p)
 {
 #ifdef CONFIG_STACK_GROWSUP
 	return (unsigned long *)((unsigned long)task_thread_info(p) + THREAD_SIZE) - 1;
-- 
cgit v1.2.3


From ea4d331050b4cd43e6a900937db88b01ef75e1f2 Mon Sep 17 00:00:00 2001
From: Javier Carrasco <javier.carrasco@wolfvision.net>
Date: Wed, 16 Oct 2024 06:02:41 +0200
Subject: Input: touch-overlay - add touchscreen overlay handling

Some touch devices provide mechanical overlays with different objects
like buttons or clipped touchscreen surfaces.

In order to support these objects, add a series of helper functions
to the input subsystem to transform them into overlay objects via
device tree nodes.

These overlay objects consume the raw touch events and report the
expected input events depending on the object properties.

Note that the current implementation allows for multiple definitions
of touchscreen areas (regions that report touch events), but only the
first one will be used for the touchscreen device that the consumers
typically provide.
Should the need for multiple touchscreen areas arise, additional
touchscreen devices would be required at the consumer side.
There is no limitation in the number of touch areas defined as buttons.

Reviewed-by: Jeff LaBundy <jeff@labundy.com>
Signed-off-by: Javier Carrasco <javier.carrasco@wolfvision.net>
Link: https://lore.kernel.org/r/20241016-feature-ts_virtobj_patch-v11-2-b292a1bbb0a1@wolfvision.net
Signed-off-by: Dmitry Torokhov <dmitry.torokhov@gmail.com>
---
 MAINTAINERS                         |   7 +
 drivers/input/Makefile              |   2 +-
 drivers/input/touch-overlay.c       | 277 ++++++++++++++++++++++++++++++++++++
 include/linux/input/touch-overlay.h |  25 ++++
 4 files changed, 310 insertions(+), 1 deletion(-)
 create mode 100644 drivers/input/touch-overlay.c
 create mode 100644 include/linux/input/touch-overlay.h

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index adcd58147f97..3466d0d59c5f 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -24609,6 +24609,13 @@ L:	platform-driver-x86@vger.kernel.org
 S:	Maintained
 F:	drivers/platform/x86/toshiba-wmi.c
 
+TOUCH OVERLAY
+M:	Javier Carrasco <javier.carrasco@wolfvision.net>
+L:	linux-input@vger.kernel.org
+S:	Maintained
+F:	drivers/input/touch-overlay.c
+F:	include/linux/input/touch-overlay.h
+
 TPM DEVICE DRIVER
 M:	Peter Huewe <peterhuewe@gmx.de>
 M:	Jarkko Sakkinen <jarkko@kernel.org>
diff --git a/drivers/input/Makefile b/drivers/input/Makefile
index 930b64d2115e..2cd6e1c9a778 100644
--- a/drivers/input/Makefile
+++ b/drivers/input/Makefile
@@ -7,7 +7,7 @@
 
 obj-$(CONFIG_INPUT)		+= input-core.o
 input-core-y := input.o input-compat.o input-mt.o input-poller.o ff-core.o
-input-core-y += touchscreen.o
+input-core-y += touchscreen.o touch-overlay.o
 
 obj-$(CONFIG_INPUT_FF_MEMLESS)	+= ff-memless.o
 obj-$(CONFIG_INPUT_SPARSEKMAP)	+= sparse-keymap.o
diff --git a/drivers/input/touch-overlay.c b/drivers/input/touch-overlay.c
new file mode 100644
index 000000000000..8806373f7a4a
--- /dev/null
+++ b/drivers/input/touch-overlay.c
@@ -0,0 +1,277 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ *  Helper functions for overlay objects on touchscreens
+ *
+ *  Copyright (c) 2023 Javier Carrasco <javier.carrasco@wolfvision.net>
+ */
+
+#include <linux/input.h>
+#include <linux/input/mt.h>
+#include <linux/input/touch-overlay.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/property.h>
+
+struct touch_overlay_segment {
+	struct list_head list;
+	u32 x_origin;
+	u32 y_origin;
+	u32 x_size;
+	u32 y_size;
+	u32 key;
+	bool pressed;
+	int slot;
+};
+
+static int touch_overlay_get_segment(struct fwnode_handle *segment_node,
+				     struct touch_overlay_segment *segment,
+				     struct input_dev *input)
+{
+	int error;
+
+	error = fwnode_property_read_u32(segment_node, "x-origin",
+					 &segment->x_origin);
+	if (error)
+		return error;
+
+	error = fwnode_property_read_u32(segment_node, "y-origin",
+					 &segment->y_origin);
+	if (error)
+		return error;
+
+	error = fwnode_property_read_u32(segment_node, "x-size",
+					 &segment->x_size);
+	if (error)
+		return error;
+
+	error = fwnode_property_read_u32(segment_node, "y-size",
+					 &segment->y_size);
+	if (error)
+		return error;
+
+	error = fwnode_property_read_u32(segment_node, "linux,code",
+					 &segment->key);
+	if (!error)
+		input_set_capability(input, EV_KEY, segment->key);
+	else if (error != -EINVAL)
+		return error;
+
+	return 0;
+}
+
+/**
+ * touch_overlay_map - map overlay objects from the device tree and set
+ * key capabilities if buttons are defined.
+ * @list: pointer to the list that will hold the segments
+ * @input: pointer to the already allocated input_dev
+ *
+ * Returns 0 on success and error number otherwise.
+ *
+ * If buttons are defined, key capabilities are set accordingly.
+ */
+int touch_overlay_map(struct list_head *list, struct input_dev *input)
+{
+	struct fwnode_handle *fw_segment;
+	struct device *dev = input->dev.parent;
+	struct touch_overlay_segment *segment;
+	int error;
+
+	struct fwnode_handle *overlay __free(fwnode_handle) =
+		device_get_named_child_node(dev, "touch-overlay");
+	if (!overlay)
+		return 0;
+
+	fwnode_for_each_available_child_node(overlay, fw_segment) {
+		segment = devm_kzalloc(dev, sizeof(*segment), GFP_KERNEL);
+		if (!segment) {
+			fwnode_handle_put(fw_segment);
+			return -ENOMEM;
+		}
+		error = touch_overlay_get_segment(fw_segment, segment, input);
+		if (error) {
+			fwnode_handle_put(fw_segment);
+			return error;
+		}
+		list_add_tail(&segment->list, list);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(touch_overlay_map);
+
+/**
+ * touch_overlay_get_touchscreen_abs - get abs size from the touchscreen area.
+ * @list: pointer to the list that holds the segments
+ * @x: horizontal abs
+ * @y: vertical abs
+ */
+void touch_overlay_get_touchscreen_abs(struct list_head *list, u16 *x, u16 *y)
+{
+	struct touch_overlay_segment *segment;
+	struct list_head *ptr;
+
+	list_for_each(ptr, list) {
+		segment = list_entry(ptr, struct touch_overlay_segment, list);
+		if (!segment->key) {
+			*x = segment->x_size - 1;
+			*y = segment->y_size - 1;
+			break;
+		}
+	}
+}
+EXPORT_SYMBOL(touch_overlay_get_touchscreen_abs);
+
+static bool touch_overlay_segment_event(struct touch_overlay_segment *seg,
+					struct input_mt_pos *pos)
+{
+	if (pos->x >= seg->x_origin && pos->x < (seg->x_origin + seg->x_size) &&
+	    pos->y >= seg->y_origin && pos->y < (seg->y_origin + seg->y_size))
+		return true;
+
+	return false;
+}
+
+/**
+ * touch_overlay_mapped_touchscreen - check if a touchscreen area is mapped
+ * @list: pointer to the list that holds the segments
+ *
+ * Returns true if a touchscreen area is mapped or false otherwise.
+ */
+bool touch_overlay_mapped_touchscreen(struct list_head *list)
+{
+	struct touch_overlay_segment *segment;
+	struct list_head *ptr;
+
+	list_for_each(ptr, list) {
+		segment = list_entry(ptr, struct touch_overlay_segment, list);
+		if (!segment->key)
+			return true;
+	}
+
+	return false;
+}
+EXPORT_SYMBOL(touch_overlay_mapped_touchscreen);
+
+static bool touch_overlay_event_on_ts(struct list_head *list,
+				      struct input_mt_pos *pos)
+{
+	struct touch_overlay_segment *segment;
+	struct list_head *ptr;
+
+	list_for_each(ptr, list) {
+		segment = list_entry(ptr, struct touch_overlay_segment, list);
+		if (segment->key)
+			continue;
+
+		if (touch_overlay_segment_event(segment, pos)) {
+			pos->x -= segment->x_origin;
+			pos->y -= segment->y_origin;
+			return true;
+		}
+		/* ignore touch events outside the defined area */
+		return false;
+	}
+
+	return true;
+}
+
+static bool touch_overlay_button_event(struct input_dev *input,
+				       struct touch_overlay_segment *segment,
+				       struct input_mt_pos *pos, int slot)
+{
+	struct input_mt *mt = input->mt;
+	struct input_mt_slot *s = &mt->slots[slot];
+	bool button_contact = touch_overlay_segment_event(segment, pos);
+
+	if (segment->slot == slot && segment->pressed) {
+		/* sliding out of the button releases it */
+		if (!button_contact) {
+			input_report_key(input, segment->key, false);
+			segment->pressed = false;
+			/* keep available for a possible touch event */
+			return false;
+		}
+		/* ignore sliding on the button while pressed */
+		s->frame = mt->frame;
+		return true;
+	} else if (button_contact) {
+		input_report_key(input, segment->key, true);
+		s->frame = mt->frame;
+		segment->slot = slot;
+		segment->pressed = true;
+		return true;
+	}
+
+	return false;
+}
+
+/**
+ * touch_overlay_sync_frame - update the status of the segments and report
+ * buttons whose tracked slot is unused.
+ * @list: pointer to the list that holds the segments
+ * @input: pointer to the input device associated to the contact
+ */
+void touch_overlay_sync_frame(struct list_head *list, struct input_dev *input)
+{
+	struct touch_overlay_segment *segment;
+	struct input_mt *mt = input->mt;
+	struct input_mt_slot *s;
+	struct list_head *ptr;
+
+	list_for_each(ptr, list) {
+		segment = list_entry(ptr, struct touch_overlay_segment, list);
+		if (!segment->key)
+			continue;
+
+		s = &mt->slots[segment->slot];
+		if (!input_mt_is_used(mt, s) && segment->pressed) {
+			input_report_key(input, segment->key, false);
+			segment->pressed = false;
+		}
+	}
+}
+EXPORT_SYMBOL(touch_overlay_sync_frame);
+
+/**
+ * touch_overlay_process_contact - process contacts according to the overlay
+ * mapping. This function acts as a filter to release the calling driver
+ * from the contacts that are either related to overlay buttons or out of the
+ * overlay touchscreen area, if defined.
+ * @list: pointer to the list that holds the segments
+ * @input: pointer to the input device associated to the contact
+ * @pos: pointer to the contact position
+ * @slot: slot associated to the contact (0 if multitouch is not supported)
+ *
+ * Returns true if the contact was processed (reported for valid key events
+ * and dropped for contacts outside the overlay touchscreen area) or false
+ * if the contact must be processed by the caller. In that case this function
+ * shifts the (x,y) coordinates to the overlay touchscreen axis if required.
+ */
+bool touch_overlay_process_contact(struct list_head *list,
+				   struct input_dev *input,
+				   struct input_mt_pos *pos, int slot)
+{
+	struct touch_overlay_segment *segment;
+	struct list_head *ptr;
+
+	/*
+	 * buttons must be prioritized over overlay touchscreens to account for
+	 * overlappings e.g. a button inside the touchscreen area.
+	 */
+	list_for_each(ptr, list) {
+		segment = list_entry(ptr, struct touch_overlay_segment, list);
+		if (segment->key &&
+		    touch_overlay_button_event(input, segment, pos, slot))
+			return true;
+	}
+
+	/*
+	 * valid contacts on the overlay touchscreen are left for the client
+	 * to be processed/reported according to its (possibly) unique features.
+	 */
+	return !touch_overlay_event_on_ts(list, pos);
+}
+EXPORT_SYMBOL(touch_overlay_process_contact);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Helper functions for overlay objects on touch devices");
diff --git a/include/linux/input/touch-overlay.h b/include/linux/input/touch-overlay.h
new file mode 100644
index 000000000000..0253e554d3cd
--- /dev/null
+++ b/include/linux/input/touch-overlay.h
@@ -0,0 +1,25 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2023 Javier Carrasco <javier.carrasco@wolfvision.net>
+ */
+
+#ifndef _TOUCH_OVERLAY
+#define _TOUCH_OVERLAY
+
+#include <linux/types.h>
+
+struct input_dev;
+
+int touch_overlay_map(struct list_head *list, struct input_dev *input);
+
+void touch_overlay_get_touchscreen_abs(struct list_head *list, u16 *x, u16 *y);
+
+bool touch_overlay_mapped_touchscreen(struct list_head *list);
+
+bool touch_overlay_process_contact(struct list_head *list,
+				   struct input_dev *input,
+				   struct input_mt_pos *pos, int slot);
+
+void touch_overlay_sync_frame(struct list_head *list, struct input_dev *input);
+
+#endif
-- 
cgit v1.2.3


From 56eb7c13b97c6f9e2fed9e9899b01d1a6a595f28 Mon Sep 17 00:00:00 2001
From: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Date: Thu, 26 Jun 2025 19:08:12 +0300
Subject: mtd: map: Don't use "proxy" headers

Update header inclusions to follow IWYU (Include What You Use)
principle.

Note that kernel.h is discouraged to be included as it's written
at the top of that file.

Signed-off-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com>
Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 include/linux/mtd/map.h | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/map.h b/include/linux/mtd/map.h
index 1b56796f6cb3..288ef765a44e 100644
--- a/include/linux/mtd/map.h
+++ b/include/linux/mtd/map.h
@@ -8,15 +8,15 @@
 #ifndef __LINUX_MTD_MAP_H__
 #define __LINUX_MTD_MAP_H__
 
-#include <linux/types.h>
-#include <linux/list.h>
-#include <linux/string.h>
 #include <linux/bug.h>
-#include <linux/kernel.h>
 #include <linux/io.h>
-
+#include <linux/ioport.h>
+#include <linux/string.h>
+#include <linux/types.h>
 #include <linux/unaligned.h>
-#include <asm/barrier.h>
+
+struct device_node;
+struct module;
 
 #ifdef CONFIG_MTD_MAP_BANK_WIDTH_1
 #define map_bankwidth(map) 1
@@ -188,6 +188,7 @@ typedef union {
    of living.
 */
 
+struct mtd_chip_driver;
 struct map_info {
 	const char *name;
 	unsigned long size;
-- 
cgit v1.2.3


From 08da98e1b2f76cdbacf84b9affaa75960dbce515 Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 8 Jul 2025 16:36:40 +0200
Subject: fsnotify: merge file_set_fsnotify_mode_from_watchers() with open perm
 hook

Create helper fsnotify_open_perm_and_set_mode() that moves the
fsnotify_open_perm() hook into file_set_fsnotify_mode_from_watchers().

This will allow some more optimizations.

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250708143641.418603-2-amir73il@gmail.com
---
 fs/file_table.c          |  2 +-
 fs/notify/fsnotify.c     | 22 +++++++++++++---------
 fs/open.c                |  6 +++---
 include/linux/fsnotify.h |  8 +++-----
 4 files changed, 20 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/fs/file_table.c b/fs/file_table.c
index 138114d64307..14ee3581c768 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -196,7 +196,7 @@ static int init_file(struct file *f, int flags, const struct cred *cred)
 	file_ref_init(&f->f_ref, 1);
 	/*
 	 * Disable permission and pre-content events for all files by default.
-	 * They may be enabled later by file_set_fsnotify_mode_from_watchers().
+	 * They may be enabled later by fsnotify_open_perm_and_set_mode().
 	 */
 	file_set_fsnotify_mode(f, FMODE_NONOTIFY_PERM);
 	return 0;
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index e2b4f17a48bb..de7e7425428b 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -656,12 +656,12 @@ EXPORT_SYMBOL_GPL(fsnotify);
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 /*
- * At open time we check fsnotify_sb_has_priority_watchers() and set the
- * FMODE_NONOTIFY_ mode bits accordignly.
+ * At open time we check fsnotify_sb_has_priority_watchers(), call the open perm
+ * hook and set the FMODE_NONOTIFY_ mode bits accordignly.
  * Later, fsnotify permission hooks do not check if there are permission event
  * watches, but that there were permission event watches at open time.
  */
-void file_set_fsnotify_mode_from_watchers(struct file *file)
+int fsnotify_open_perm_and_set_mode(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry, *parent;
 	struct super_block *sb = dentry->d_sb;
@@ -669,7 +669,7 @@ void file_set_fsnotify_mode_from_watchers(struct file *file)
 
 	/* Is it a file opened by fanotify? */
 	if (FMODE_FSNOTIFY_NONE(file->f_mode))
-		return;
+		return 0;
 
 	/*
 	 * Permission events is a super set of pre-content events, so if there
@@ -679,7 +679,7 @@ void file_set_fsnotify_mode_from_watchers(struct file *file)
 	if (likely(!fsnotify_sb_has_priority_watchers(sb,
 						FSNOTIFY_PRIO_CONTENT))) {
 		file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
-		return;
+		return 0;
 	}
 
 	/*
@@ -689,8 +689,9 @@ void file_set_fsnotify_mode_from_watchers(struct file *file)
 	if ((!d_is_dir(dentry) && !d_is_reg(dentry)) ||
 	    likely(!fsnotify_sb_has_priority_watchers(sb,
 						FSNOTIFY_PRIO_PRE_CONTENT))) {
-		file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
-		return;
+		file_set_fsnotify_mode(file, FMODE_NONOTIFY |
+				       FMODE_NONOTIFY_PERM);
+		goto open_perm;
 	}
 
 	/*
@@ -702,7 +703,7 @@ void file_set_fsnotify_mode_from_watchers(struct file *file)
 				     FSNOTIFY_PRE_CONTENT_EVENTS))) {
 		/* Enable pre-content events */
 		file_set_fsnotify_mode(file, 0);
-		return;
+		goto open_perm;
 	}
 
 	/* Is parent watching for pre-content events on this file? */
@@ -713,11 +714,14 @@ void file_set_fsnotify_mode_from_watchers(struct file *file)
 		if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) {
 			/* Enable pre-content events */
 			file_set_fsnotify_mode(file, 0);
-			return;
+			goto open_perm;
 		}
 	}
 	/* Nobody watching for pre-content events from this file */
 	file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
+
+open_perm:
+	return fsnotify_open_perm(file);
 }
 #endif
 
diff --git a/fs/open.c b/fs/open.c
index 7828234a7caa..f240b96ce586 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -943,12 +943,12 @@ static int do_dentry_open(struct file *f,
 		goto cleanup_all;
 
 	/*
-	 * Set FMODE_NONOTIFY_* bits according to existing permission watches.
+	 * Call fsnotify open permission hook and set FMODE_NONOTIFY_* bits
+	 * according to existing permission watches.
 	 * If FMODE_NONOTIFY mode was already set for an fanotify fd or for a
 	 * pseudo file, this call will not change the mode.
 	 */
-	file_set_fsnotify_mode_from_watchers(f);
-	error = fsnotify_open_perm(f);
+	error = fsnotify_open_perm_and_set_mode(f);
 	if (error)
 		goto cleanup_all;
 
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 454d8e466958..8c1fa617d375 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -129,7 +129,7 @@ static inline int fsnotify_file(struct file *file, __u32 mask)
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 
-void file_set_fsnotify_mode_from_watchers(struct file *file);
+int fsnotify_open_perm_and_set_mode(struct file *file);
 
 /*
  * fsnotify_file_area_perm - permission hook before access to file range
@@ -215,9 +215,6 @@ static inline int fsnotify_open_perm(struct file *file)
 {
 	int ret;
 
-	if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode)))
-		return 0;
-
 	if (file->f_flags & __FMODE_EXEC) {
 		ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM);
 		if (ret)
@@ -228,8 +225,9 @@ static inline int fsnotify_open_perm(struct file *file)
 }
 
 #else
-static inline void file_set_fsnotify_mode_from_watchers(struct file *file)
+static inline int fsnotify_open_perm_and_set_mode(struct file *file)
 {
+	return 0;
 }
 
 static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
-- 
cgit v1.2.3


From 0d4c4d4ea443babab6ec1a79f481260963fc969a Mon Sep 17 00:00:00 2001
From: Amir Goldstein <amir73il@gmail.com>
Date: Tue, 8 Jul 2025 16:36:41 +0200
Subject: fsnotify: optimize FMODE_NONOTIFY_PERM for the common cases

The most unlikely watched permission event is FAN_ACCESS_PERM, because
at the time that it was introduced there were no evictable ignore mark,
so subscribing to FAN_ACCESS_PERM would have incured a very high
overhead.

Yet, when we set the fmode to FMODE_NOTIFY_HSM(), we never skip trying
to send FAN_ACCESS_PERM, which is almost always a waste of cycles.

We got to this logic because of bundling FAN_OPEN*_PERM and
FAN_ACCESS_PERM in the same category and because FAN_OPEN_PERM is a
commonly used event.

By open coding fsnotify_open_perm() in fsnotify_open_perm_and_set_mode(),
we no longer need to regard FAN_OPEN*_PERM when calculating fmode.

This leaves the case of having pre-content events and not having any
other permission event in the object masks a more likely case than the
other way around.

Rework the fmode macros and code so that their meaning now refers only
to hooks on an already open file:

- FMODE_NOTIFY_NONE()		skip all events
- FMODE_NOTIFY_ACCESS_PERM()	send all permission events including
  				FAN_ACCESS_PERM
- FMODE_NOTIFY_HSM()		send pre-content permission events

Signed-off-by: Amir Goldstein <amir73il@gmail.com>
Signed-off-by: Jan Kara <jack@suse.cz>
Link: https://patch.msgid.link/20250708143641.418603-3-amir73il@gmail.com
---
 fs/notify/fsnotify.c     | 75 +++++++++++++++++++++++++++++-------------------
 include/linux/fs.h       | 12 ++++----
 include/linux/fsnotify.h | 27 ++---------------
 3 files changed, 53 insertions(+), 61 deletions(-)

(limited to 'include/linux')

diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index de7e7425428b..079b868552c2 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -199,8 +199,8 @@ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
 }
 
 /* Are there any inode/mount/sb objects that watch for these events? */
-static inline bool fsnotify_object_watched(struct inode *inode, __u32 mnt_mask,
-					   __u32 mask)
+static inline __u32 fsnotify_object_watched(struct inode *inode, __u32 mnt_mask,
+					    __u32 mask)
 {
 	__u32 marks_mask = READ_ONCE(inode->i_fsnotify_mask) | mnt_mask |
 			   READ_ONCE(inode->i_sb->s_fsnotify_mask);
@@ -665,7 +665,7 @@ int fsnotify_open_perm_and_set_mode(struct file *file)
 {
 	struct dentry *dentry = file->f_path.dentry, *parent;
 	struct super_block *sb = dentry->d_sb;
-	__u32 mnt_mask, p_mask;
+	__u32 mnt_mask, p_mask = 0;
 
 	/* Is it a file opened by fanotify? */
 	if (FMODE_FSNOTIFY_NONE(file->f_mode))
@@ -683,45 +683,60 @@ int fsnotify_open_perm_and_set_mode(struct file *file)
 	}
 
 	/*
-	 * If there are permission event watchers but no pre-content event
-	 * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that.
+	 * OK, there are some permission event watchers. Check if anybody is
+	 * watching for permission events on *this* file.
 	 */
-	if ((!d_is_dir(dentry) && !d_is_reg(dentry)) ||
-	    likely(!fsnotify_sb_has_priority_watchers(sb,
-						FSNOTIFY_PRIO_PRE_CONTENT))) {
-		file_set_fsnotify_mode(file, FMODE_NONOTIFY |
-				       FMODE_NONOTIFY_PERM);
-		goto open_perm;
+	mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask);
+	p_mask = fsnotify_object_watched(d_inode(dentry), mnt_mask,
+					 ALL_FSNOTIFY_PERM_EVENTS);
+	if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) {
+		parent = dget_parent(dentry);
+		p_mask |= fsnotify_inode_watches_children(d_inode(parent));
+		dput(parent);
 	}
 
 	/*
-	 * OK, there are some pre-content watchers. Check if anybody is
-	 * watching for pre-content events on *this* file.
+	 * Legacy FAN_ACCESS_PERM events have very high performance overhead,
+	 * so unlikely to be used in the wild. If they are used there will be
+	 * no optimizations at all.
 	 */
-	mnt_mask = READ_ONCE(real_mount(file->f_path.mnt)->mnt_fsnotify_mask);
-	if (unlikely(fsnotify_object_watched(d_inode(dentry), mnt_mask,
-				     FSNOTIFY_PRE_CONTENT_EVENTS))) {
-		/* Enable pre-content events */
+	if (unlikely(p_mask & FS_ACCESS_PERM)) {
+		/* Enable all permission and pre-content events */
 		file_set_fsnotify_mode(file, 0);
 		goto open_perm;
 	}
 
-	/* Is parent watching for pre-content events on this file? */
-	if (dentry->d_flags & DCACHE_FSNOTIFY_PARENT_WATCHED) {
-		parent = dget_parent(dentry);
-		p_mask = fsnotify_inode_watches_children(d_inode(parent));
-		dput(parent);
-		if (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS) {
-			/* Enable pre-content events */
-			file_set_fsnotify_mode(file, 0);
-			goto open_perm;
-		}
+	/*
+	 * Pre-content events are only supported on regular files.
+	 * If there are pre-content event watchers and no permission access
+	 * watchers, set FMODE_NONOTIFY | FMODE_NONOTIFY_PERM to indicate that.
+	 * That is the common case with HSM service.
+	 */
+	if (d_is_reg(dentry) && (p_mask & FSNOTIFY_PRE_CONTENT_EVENTS)) {
+		file_set_fsnotify_mode(file, FMODE_NONOTIFY |
+					     FMODE_NONOTIFY_PERM);
+		goto open_perm;
 	}
-	/* Nobody watching for pre-content events from this file */
-	file_set_fsnotify_mode(file, FMODE_NONOTIFY | FMODE_NONOTIFY_PERM);
+
+	/* Nobody watching permission and pre-content events on this file */
+	file_set_fsnotify_mode(file, FMODE_NONOTIFY_PERM);
 
 open_perm:
-	return fsnotify_open_perm(file);
+	/*
+	 * Send open perm events depending on object masks and regardless of
+	 * FMODE_NONOTIFY_PERM.
+	 */
+	if (file->f_flags & __FMODE_EXEC && p_mask & FS_OPEN_EXEC_PERM) {
+		int ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM);
+
+		if (ret)
+			return ret;
+	}
+
+	if (p_mask & FS_OPEN_PERM)
+		return fsnotify_path(&file->f_path, FS_OPEN_PERM);
+
+	return 0;
 }
 #endif
 
diff --git a/include/linux/fs.h b/include/linux/fs.h
index b085f161ed22..bc92fdb8bfcc 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -200,12 +200,12 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 
 /*
  * The two FMODE_NONOTIFY* define which fsnotify events should not be generated
- * for a file. These are the possible values of (f->f_mode &
- * FMODE_FSNOTIFY_MASK) and their meaning:
+ * for an open file. These are the possible values of
+ * (f->f_mode & FMODE_FSNOTIFY_MASK) and their meaning:
  *
  * FMODE_NONOTIFY - suppress all (incl. non-permission) events.
  * FMODE_NONOTIFY_PERM - suppress permission (incl. pre-content) events.
- * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only pre-content events.
+ * FMODE_NONOTIFY | FMODE_NONOTIFY_PERM - suppress only FAN_ACCESS_PERM.
  */
 #define FMODE_FSNOTIFY_MASK \
 	(FMODE_NONOTIFY | FMODE_NONOTIFY_PERM)
@@ -213,13 +213,13 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
 #define FMODE_FSNOTIFY_NONE(mode) \
 	((mode & FMODE_FSNOTIFY_MASK) == FMODE_NONOTIFY)
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-#define FMODE_FSNOTIFY_PERM(mode) \
+#define FMODE_FSNOTIFY_HSM(mode) \
 	((mode & FMODE_FSNOTIFY_MASK) == 0 || \
 	 (mode & FMODE_FSNOTIFY_MASK) == (FMODE_NONOTIFY | FMODE_NONOTIFY_PERM))
-#define FMODE_FSNOTIFY_HSM(mode) \
+#define FMODE_FSNOTIFY_ACCESS_PERM(mode) \
 	((mode & FMODE_FSNOTIFY_MASK) == 0)
 #else
-#define FMODE_FSNOTIFY_PERM(mode)	0
+#define FMODE_FSNOTIFY_ACCESS_PERM(mode) 0
 #define FMODE_FSNOTIFY_HSM(mode)	0
 #endif
 
diff --git a/include/linux/fsnotify.h b/include/linux/fsnotify.h
index 8c1fa617d375..28a9cb13fbfa 100644
--- a/include/linux/fsnotify.h
+++ b/include/linux/fsnotify.h
@@ -147,9 +147,6 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
 	if (!(perm_mask & (MAY_READ | MAY_WRITE | MAY_ACCESS)))
 		return 0;
 
-	if (likely(!FMODE_FSNOTIFY_PERM(file->f_mode)))
-		return 0;
-
 	/*
 	 * read()/write() and other types of access generate pre-content events.
 	 */
@@ -160,7 +157,8 @@ static inline int fsnotify_file_area_perm(struct file *file, int perm_mask,
 			return ret;
 	}
 
-	if (!(perm_mask & MAY_READ))
+	if (!(perm_mask & MAY_READ) ||
+	    likely(!FMODE_FSNOTIFY_ACCESS_PERM(file->f_mode)))
 		return 0;
 
 	/*
@@ -208,22 +206,6 @@ static inline int fsnotify_file_perm(struct file *file, int perm_mask)
 	return fsnotify_file_area_perm(file, perm_mask, NULL, 0);
 }
 
-/*
- * fsnotify_open_perm - permission hook before file open
- */
-static inline int fsnotify_open_perm(struct file *file)
-{
-	int ret;
-
-	if (file->f_flags & __FMODE_EXEC) {
-		ret = fsnotify_path(&file->f_path, FS_OPEN_EXEC_PERM);
-		if (ret)
-			return ret;
-	}
-
-	return fsnotify_path(&file->f_path, FS_OPEN_PERM);
-}
-
 #else
 static inline int fsnotify_open_perm_and_set_mode(struct file *file)
 {
@@ -251,11 +233,6 @@ static inline int fsnotify_file_perm(struct file *file, int perm_mask)
 {
 	return 0;
 }
-
-static inline int fsnotify_open_perm(struct file *file)
-{
-	return 0;
-}
 #endif
 
 /*
-- 
cgit v1.2.3


From 9d475d80c93735f0f336b34a8e2c22beea6145ab Mon Sep 17 00:00:00 2001
From: Gabriele Monaco <gmonaco@redhat.com>
Date: Mon, 28 Jul 2025 15:50:17 +0200
Subject: rv: Retry when da monitor detects race conditions

DA monitor can be accessed from multiple cores simultaneously, this is
likely, for instance when dealing with per-task monitors reacting on
events that do not always occur on the CPU where the task is running.
This can cause race conditions where two events change the next state
and we see inconsistent values. E.g.:

  [62] event_srs: 27: sleepable x sched_wakeup -> running (final)
  [63] event_srs: 27: sleepable x sched_set_state_sleepable -> sleepable
  [63] error_srs: 27: event sched_switch_suspend not expected in the state running

In this case the monitor fails because the event on CPU 62 wins against
the one on CPU 63, although the correct state should have been
sleepable, since the task get suspended.

Detect if the current state was modified by using try_cmpxchg while
storing the next value. If it was, try again reading the current state.
After a maximum number of failed retries, react by calling a special
tracepoint, print on the console and reset the monitor.

Remove the functions da_monitor_curr_state() and da_monitor_set_state()
as they only hide the underlying implementation in this case.

Monitors where this type of condition can occur must be able to account
for racing events in any possible order, as we cannot know the winner.

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Juri Lelli <jlelli@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://lore.kernel.org/20250728135022.255578-6-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Reviewed-by: Nam Cao <namcao@linutronix.de>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/rv.h         |   3 +-
 include/rv/da_monitor.h    | 107 +++++++++++++++++++++++----------------------
 kernel/trace/rv/Kconfig    |   5 +++
 kernel/trace/rv/rv_trace.h |  24 ++++++++++
 4 files changed, 85 insertions(+), 54 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/rv.h b/include/linux/rv.h
index 80731242fe60..14410a42faef 100644
--- a/include/linux/rv.h
+++ b/include/linux/rv.h
@@ -10,7 +10,8 @@
 #include <linux/types.h>
 #include <linux/list.h>
 
-#define MAX_DA_NAME_LEN	32
+#define MAX_DA_NAME_LEN			32
+#define MAX_DA_RETRY_RACING_EVENTS	3
 
 #ifdef CONFIG_RV
 #include <linux/bitops.h>
diff --git a/include/rv/da_monitor.h b/include/rv/da_monitor.h
index ed3c34fe18d6..17fa4f6e5ea6 100644
--- a/include/rv/da_monitor.h
+++ b/include/rv/da_monitor.h
@@ -54,23 +54,6 @@ static inline void da_monitor_reset_##name(struct da_monitor *da_mon)				\
 	da_mon->curr_state = model_get_initial_state_##name();					\
 }												\
 												\
-/*												\
- * da_monitor_curr_state_##name - return the current state					\
- */												\
-static inline type da_monitor_curr_state_##name(struct da_monitor *da_mon)			\
-{												\
-	return da_mon->curr_state;								\
-}												\
-												\
-/*												\
- * da_monitor_set_state_##name - set the new current state					\
- */												\
-static inline void										\
-da_monitor_set_state_##name(struct da_monitor *da_mon, enum states_##name state)		\
-{												\
-	da_mon->curr_state = state;								\
-}												\
-												\
 /*												\
  * da_monitor_start_##name - start monitoring							\
  *												\
@@ -127,63 +110,81 @@ static inline bool da_monitor_handling_event_##name(struct da_monitor *da_mon)
  * Event handler for implicit monitors. Implicit monitor is the one which the
  * handler does not need to specify which da_monitor to manipulate. Examples
  * of implicit monitor are the per_cpu or the global ones.
+ *
+ * Retry in case there is a race between getting and setting the next state,
+ * warn and reset the monitor if it runs out of retries. The monitor should be
+ * able to handle various orders.
  */
 #define DECLARE_DA_MON_MODEL_HANDLER_IMPLICIT(name, type)					\
 												\
 static inline bool										\
 da_event_##name(struct da_monitor *da_mon, enum events_##name event)				\
 {												\
-	type curr_state = da_monitor_curr_state_##name(da_mon);					\
-	type next_state = model_get_next_state_##name(curr_state, event);			\
-												\
-	if (next_state != INVALID_STATE) {							\
-		da_monitor_set_state_##name(da_mon, next_state);				\
-												\
-		trace_event_##name(model_get_state_name_##name(curr_state),			\
-				   model_get_event_name_##name(event),				\
-				   model_get_state_name_##name(next_state),			\
-				   model_is_final_state_##name(next_state));			\
-												\
-		return true;									\
+	enum states_##name curr_state, next_state;						\
+												\
+	curr_state = READ_ONCE(da_mon->curr_state);						\
+	for (int i = 0; i < MAX_DA_RETRY_RACING_EVENTS; i++) {					\
+		next_state = model_get_next_state_##name(curr_state, event);			\
+		if (next_state == INVALID_STATE) {						\
+			cond_react_##name(curr_state, event);					\
+			trace_error_##name(model_get_state_name_##name(curr_state),		\
+					   model_get_event_name_##name(event));			\
+			return false;								\
+		}										\
+		if (likely(try_cmpxchg(&da_mon->curr_state, &curr_state, next_state))) {	\
+			trace_event_##name(model_get_state_name_##name(curr_state),		\
+					   model_get_event_name_##name(event),			\
+					   model_get_state_name_##name(next_state),		\
+					   model_is_final_state_##name(next_state));		\
+			return true;								\
+		}										\
 	}											\
 												\
-	cond_react_##name(curr_state, event);							\
-												\
-	trace_error_##name(model_get_state_name_##name(curr_state),				\
-			   model_get_event_name_##name(event));					\
-												\
+	trace_rv_retries_error(#name, model_get_event_name_##name(event));			\
+	pr_warn("rv: " __stringify(MAX_DA_RETRY_RACING_EVENTS)					\
+		" retries reached for event %s, resetting monitor %s",				\
+		model_get_event_name_##name(event), #name);					\
 	return false;										\
 }												\
 
 /*
  * Event handler for per_task monitors.
+ *
+ * Retry in case there is a race between getting and setting the next state,
+ * warn and reset the monitor if it runs out of retries. The monitor should be
+ * able to handle various orders.
  */
 #define DECLARE_DA_MON_MODEL_HANDLER_PER_TASK(name, type)					\
 												\
 static inline bool da_event_##name(struct da_monitor *da_mon, struct task_struct *tsk,		\
 				   enum events_##name event)					\
 {												\
-	type curr_state = da_monitor_curr_state_##name(da_mon);					\
-	type next_state = model_get_next_state_##name(curr_state, event);			\
-												\
-	if (next_state != INVALID_STATE) {							\
-		da_monitor_set_state_##name(da_mon, next_state);				\
-												\
-		trace_event_##name(tsk->pid,							\
-				   model_get_state_name_##name(curr_state),			\
-				   model_get_event_name_##name(event),				\
-				   model_get_state_name_##name(next_state),			\
-				   model_is_final_state_##name(next_state));			\
-												\
-		return true;									\
+	enum states_##name curr_state, next_state;						\
+												\
+	curr_state = READ_ONCE(da_mon->curr_state);						\
+	for (int i = 0; i < MAX_DA_RETRY_RACING_EVENTS; i++) {					\
+		next_state = model_get_next_state_##name(curr_state, event);			\
+		if (next_state == INVALID_STATE) {						\
+			cond_react_##name(curr_state, event);					\
+			trace_error_##name(tsk->pid,						\
+					   model_get_state_name_##name(curr_state),		\
+					   model_get_event_name_##name(event));			\
+			return false;								\
+		}										\
+		if (likely(try_cmpxchg(&da_mon->curr_state, &curr_state, next_state))) {	\
+			trace_event_##name(tsk->pid,						\
+					   model_get_state_name_##name(curr_state),		\
+					   model_get_event_name_##name(event),			\
+					   model_get_state_name_##name(next_state),		\
+					   model_is_final_state_##name(next_state));		\
+			return true;								\
+		}										\
 	}											\
 												\
-	cond_react_##name(curr_state, event);							\
-												\
-	trace_error_##name(tsk->pid,								\
-			   model_get_state_name_##name(curr_state),				\
-			   model_get_event_name_##name(event));					\
-												\
+	trace_rv_retries_error(#name, model_get_event_name_##name(event));			\
+	pr_warn("rv: " __stringify(MAX_DA_RETRY_RACING_EVENTS)					\
+		" retries reached for event %s, resetting monitor %s",				\
+		model_get_event_name_##name(event), #name);					\
 	return false;										\
 }
 
diff --git a/kernel/trace/rv/Kconfig b/kernel/trace/rv/Kconfig
index 26017378f79b..34164eb4ec91 100644
--- a/kernel/trace/rv/Kconfig
+++ b/kernel/trace/rv/Kconfig
@@ -3,12 +3,17 @@
 config RV_MON_EVENTS
 	bool
 
+config RV_MON_MAINTENANCE_EVENTS
+	bool
+
 config DA_MON_EVENTS_IMPLICIT
 	select RV_MON_EVENTS
+	select RV_MON_MAINTENANCE_EVENTS
 	bool
 
 config DA_MON_EVENTS_ID
 	select RV_MON_EVENTS
+	select RV_MON_MAINTENANCE_EVENTS
 	bool
 
 config LTL_MON_EVENTS_ID
diff --git a/kernel/trace/rv/rv_trace.h b/kernel/trace/rv/rv_trace.h
index d38e0d3abdfd..3af46cd185b3 100644
--- a/kernel/trace/rv/rv_trace.h
+++ b/kernel/trace/rv/rv_trace.h
@@ -176,6 +176,30 @@ DECLARE_EVENT_CLASS(error_ltl_monitor_id,
 #include <monitors/sleep/sleep_trace.h>
 // Add new monitors based on CONFIG_LTL_MON_EVENTS_ID here
 #endif /* CONFIG_LTL_MON_EVENTS_ID */
+
+#ifdef CONFIG_RV_MON_MAINTENANCE_EVENTS
+/* Tracepoint useful for monitors development, currenly only used in DA */
+TRACE_EVENT(rv_retries_error,
+
+	TP_PROTO(char *name, char *event),
+
+	TP_ARGS(name, event),
+
+	TP_STRUCT__entry(
+		__string(	name,	name	)
+		__string(	event,	event	)
+	),
+
+	TP_fast_assign(
+		__assign_str(name);
+		__assign_str(event);
+	),
+
+	TP_printk(__stringify(MAX_DA_RETRY_RACING_EVENTS)
+		" retries reached for event %s, resetting monitor %s",
+		__get_str(event), __get_str(name))
+);
+#endif /* CONFIG_RV_MON_MAINTENANCE_EVENTS */
 #endif /* _TRACE_RV_H */
 
 /* This part must be outside protection */
-- 
cgit v1.2.3


From adcc3bfa8806761ac21aa271f78454113ec6936e Mon Sep 17 00:00:00 2001
From: Gabriele Monaco <gmonaco@redhat.com>
Date: Mon, 28 Jul 2025 15:50:18 +0200
Subject: sched: Adapt sched tracepoints for RV task model

Add the following tracepoint:
* sched_set_need_resched(tsk, cpu, tif)
    Called when a task is set the need resched [lazy] flag

Remove the unused ip parameter from sched_entry and sched_exit and alter
sched_entry to have a value of preempt consistent with the one used in
sched_switch.

Also adapt all monitors using sched_{entry,exit} to avoid breaking build.

These tracepoints are useful to describe the Linux task model and are
adapted from the patches by Daniel Bristot de Oliveira
(https://bristot.me/linux-task-model/).

Cc: Ingo Molnar <mingo@redhat.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Nam Cao <namcao@linutronix.de>
Cc: Tomas Glozar <tglozar@redhat.com>
Cc: Juri Lelli <jlelli@redhat.com>
Cc: Clark Williams <williams@redhat.com>
Cc: John Kacur <jkacur@redhat.com>
Link: https://lore.kernel.org/20250728135022.255578-7-gmonaco@redhat.com
Signed-off-by: Gabriele Monaco <gmonaco@redhat.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/sched.h                  |  7 ++++++-
 include/trace/events/sched.h           | 12 ++++++++----
 kernel/sched/core.c                    | 13 ++++++++++---
 kernel/trace/rv/monitors/sco/sco.c     |  4 ++--
 kernel/trace/rv/monitors/scpd/scpd.c   |  4 ++--
 kernel/trace/rv/monitors/sncid/sncid.c |  4 ++--
 kernel/trace/rv/monitors/snep/snep.c   |  4 ++--
 kernel/trace/rv/monitors/tss/tss.c     |  4 ++--
 8 files changed, 34 insertions(+), 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index fabd7fe1a07a..91d1fdbc2f56 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -339,9 +339,11 @@ extern void io_schedule_finish(int token);
 extern long io_schedule_timeout(long timeout);
 extern void io_schedule(void);
 
-/* wrapper function to trace from this header file */
+/* wrapper functions to trace from this header file */
 DECLARE_TRACEPOINT(sched_set_state_tp);
 extern void __trace_set_current_state(int state_value);
+DECLARE_TRACEPOINT(sched_set_need_resched_tp);
+extern void __trace_set_need_resched(struct task_struct *curr, int tif);
 
 /**
  * struct prev_cputime - snapshot of system and user cputime
@@ -2063,6 +2065,9 @@ static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
 
 static inline void set_tsk_need_resched(struct task_struct *tsk)
 {
+	if (tracepoint_enabled(sched_set_need_resched_tp) &&
+	    !test_tsk_thread_flag(tsk, TIF_NEED_RESCHED))
+		__trace_set_need_resched(tsk, TIF_NEED_RESCHED);
 	set_tsk_thread_flag(tsk,TIF_NEED_RESCHED);
 }
 
diff --git a/include/trace/events/sched.h b/include/trace/events/sched.h
index 4e6b2910cec3..c08893bde255 100644
--- a/include/trace/events/sched.h
+++ b/include/trace/events/sched.h
@@ -882,18 +882,22 @@ DECLARE_TRACE(sched_compute_energy,
 	TP_ARGS(p, dst_cpu, energy, max_util, busy_time));
 
 DECLARE_TRACE(sched_entry,
-	TP_PROTO(bool preempt, unsigned long ip),
-	TP_ARGS(preempt, ip));
+	TP_PROTO(bool preempt),
+	TP_ARGS(preempt));
 
 DECLARE_TRACE(sched_exit,
-	TP_PROTO(bool is_switch, unsigned long ip),
-	TP_ARGS(is_switch, ip));
+	TP_PROTO(bool is_switch),
+	TP_ARGS(is_switch));
 
 DECLARE_TRACE_CONDITION(sched_set_state,
 	TP_PROTO(struct task_struct *tsk, int state),
 	TP_ARGS(tsk, state),
 	TP_CONDITION(!!(tsk->__state) != !!state));
 
+DECLARE_TRACE(sched_set_need_resched,
+	TP_PROTO(struct task_struct *tsk, int cpu, int tif),
+	TP_ARGS(tsk, cpu, tif));
+
 #endif /* _TRACE_SCHED_H */
 
 /* This part must be outside protection */
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index ec68fc686bd7..b485e0639616 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -1110,6 +1110,7 @@ static void __resched_curr(struct rq *rq, int tif)
 
 	cpu = cpu_of(rq);
 
+	trace_sched_set_need_resched_tp(curr, cpu, tif);
 	if (cpu == smp_processor_id()) {
 		set_ti_thread_flag(cti, tif);
 		if (tif == TIF_NEED_RESCHED)
@@ -1125,6 +1126,11 @@ static void __resched_curr(struct rq *rq, int tif)
 	}
 }
 
+void __trace_set_need_resched(struct task_struct *curr, int tif)
+{
+	trace_sched_set_need_resched_tp(curr, smp_processor_id(), tif);
+}
+
 void resched_curr(struct rq *rq)
 {
 	__resched_curr(rq, TIF_NEED_RESCHED);
@@ -5329,7 +5335,7 @@ asmlinkage __visible void schedule_tail(struct task_struct *prev)
 	 * switched the context for the first time. It is returning from
 	 * schedule for the first time in this path.
 	 */
-	trace_sched_exit_tp(true, CALLER_ADDR0);
+	trace_sched_exit_tp(true);
 	preempt_enable();
 
 	if (current->set_child_tid)
@@ -6678,7 +6684,8 @@ static void __sched notrace __schedule(int sched_mode)
 	struct rq *rq;
 	int cpu;
 
-	trace_sched_entry_tp(preempt, CALLER_ADDR0);
+	/* Trace preemptions consistently with task switches */
+	trace_sched_entry_tp(sched_mode == SM_PREEMPT);
 
 	cpu = smp_processor_id();
 	rq = cpu_rq(cpu);
@@ -6793,7 +6800,7 @@ picked:
 		__balance_callbacks(rq);
 		raw_spin_rq_unlock_irq(rq);
 	}
-	trace_sched_exit_tp(is_switch, CALLER_ADDR0);
+	trace_sched_exit_tp(is_switch);
 }
 
 void __noreturn do_task_dead(void)
diff --git a/kernel/trace/rv/monitors/sco/sco.c b/kernel/trace/rv/monitors/sco/sco.c
index 66f4639d46ac..04c36405e2e3 100644
--- a/kernel/trace/rv/monitors/sco/sco.c
+++ b/kernel/trace/rv/monitors/sco/sco.c
@@ -24,12 +24,12 @@ static void handle_sched_set_state(void *data, struct task_struct *tsk, int stat
 	da_handle_start_event_sco(sched_set_state_sco);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_sco(schedule_entry_sco);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_sco(schedule_exit_sco);
 }
diff --git a/kernel/trace/rv/monitors/scpd/scpd.c b/kernel/trace/rv/monitors/scpd/scpd.c
index 299703cd72b0..1e351ba52fee 100644
--- a/kernel/trace/rv/monitors/scpd/scpd.c
+++ b/kernel/trace/rv/monitors/scpd/scpd.c
@@ -30,12 +30,12 @@ static void handle_preempt_enable(void *data, unsigned long ip, unsigned long pa
 	da_handle_start_event_scpd(preempt_enable_scpd);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_scpd(schedule_entry_scpd);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_event_scpd(schedule_exit_scpd);
 }
diff --git a/kernel/trace/rv/monitors/sncid/sncid.c b/kernel/trace/rv/monitors/sncid/sncid.c
index 3e1ee715a0fb..c8491f426365 100644
--- a/kernel/trace/rv/monitors/sncid/sncid.c
+++ b/kernel/trace/rv/monitors/sncid/sncid.c
@@ -30,12 +30,12 @@ static void handle_irq_enable(void *data, unsigned long ip, unsigned long parent
 	da_handle_start_event_sncid(irq_enable_sncid);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_start_event_sncid(schedule_entry_sncid);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_sncid(schedule_exit_sncid);
 }
diff --git a/kernel/trace/rv/monitors/snep/snep.c b/kernel/trace/rv/monitors/snep/snep.c
index 2adc3108d60c..558950f524a5 100644
--- a/kernel/trace/rv/monitors/snep/snep.c
+++ b/kernel/trace/rv/monitors/snep/snep.c
@@ -30,12 +30,12 @@ static void handle_preempt_enable(void *data, unsigned long ip, unsigned long pa
 	da_handle_start_event_snep(preempt_enable_snep);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_snep(schedule_entry_snep);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_snep(schedule_exit_snep);
 }
diff --git a/kernel/trace/rv/monitors/tss/tss.c b/kernel/trace/rv/monitors/tss/tss.c
index 0452fcd9edcf..95ebd15131f5 100644
--- a/kernel/trace/rv/monitors/tss/tss.c
+++ b/kernel/trace/rv/monitors/tss/tss.c
@@ -27,12 +27,12 @@ static void handle_sched_switch(void *data, bool preempt,
 	da_handle_event_tss(sched_switch_tss);
 }
 
-static void handle_schedule_entry(void *data, bool preempt, unsigned long ip)
+static void handle_schedule_entry(void *data, bool preempt)
 {
 	da_handle_event_tss(schedule_entry_tss);
 }
 
-static void handle_schedule_exit(void *data, bool is_switch, unsigned long ip)
+static void handle_schedule_exit(void *data, bool is_switch)
 {
 	da_handle_start_event_tss(schedule_exit_tss);
 }
-- 
cgit v1.2.3


From 1edaac340f4da813b258a5e3a6c79804612161a4 Mon Sep 17 00:00:00 2001
From: Klara Modin <klarasmodin@gmail.com>
Date: Fri, 25 Jul 2025 18:43:34 +0200
Subject: block: change blk_get_meta_cap() stub return -ENOIOCTLCMD

When introduced in commit 9eb22f7fedfc ("fs: add ioctl to query metadata
and protection info capabilities") the stub of blk_get_meta_cap() for
!BLK_DEV_INTEGRITY always returns -EOPNOTSUPP.  The motivation was that
while the command was unsupported in that configuration it was still
recognized.

A later change instead assumed -ENOIOCTLCMD as is required for unknown
ioctl commands per Documentation/driver-api/ioctl.rst. The result being
that on !BLK_DEV_INTEGRITY configs, any ioctl which reaches
blkdev_common_ioctl() will return -EOPNOTSUPP.

Change the stub to return -ENOIOCTLCMD, fixing the issue and better
matching with expectations.

[ The blkdev_common_ioctl() confusion has been fixed, but -ENOIOCTLCMD
  is the right thing to return for unrecognized ioctls, so the patch
  remains the right thing to do.   - Linus ]

Link: https://lore.kernel.org/lkml/CACzX3AsRd__fXb9=CJPTTJC494SDnYAtYrN2=+bZgMCvM6UQDg@mail.gmail.com
Fixes: 42b0ef01e6b5 ("block: fix FS_IOC_GETLBMD_CAP parsing in blkdev_common_ioctl()")
Signed-off-by: Klara Modin <klarasmodin@gmail.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
 include/linux/blk-integrity.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
index e04c6e5bf1c6..e67a2b6e8f11 100644
--- a/include/linux/blk-integrity.h
+++ b/include/linux/blk-integrity.h
@@ -97,7 +97,7 @@ static inline struct bio_vec rq_integrity_vec(struct request *rq)
 static inline int blk_get_meta_cap(struct block_device *bdev, unsigned int cmd,
 				   struct logical_block_metadata_cap __user *argp)
 {
-	return -EOPNOTSUPP;
+	return -ENOIOCTLCMD;
 }
 static inline int blk_rq_count_integrity_sg(struct request_queue *q,
 					    struct bio *b)
-- 
cgit v1.2.3


From 6cff20ce3b92ffbf2fc5eb9e5a030b3672aa414a Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sun, 13 Jul 2025 16:31:01 +0200
Subject: PCI/ACPI: Fix runtime PM ref imbalance on Hot-Plug Capable ports

pci_bridge_d3_possible() is called from both pcie_portdrv_probe() and
pcie_portdrv_remove() to determine whether runtime power management shall
be enabled (on probe) or disabled (on remove) on a PCIe port.

The underlying assumption is that pci_bridge_d3_possible() always returns
the same value, else a runtime PM reference imbalance would occur.  That
assumption is not given if the PCIe port is inaccessible on remove due to
hot-unplug:  pci_bridge_d3_possible() calls pciehp_is_native(), which
accesses Config Space to determine whether the port is Hot-Plug Capable.
An inaccessible port returns "all ones", which is converted to "all
zeroes" by pcie_capability_read_dword().  Hence the port no longer seems
Hot-Plug Capable on remove even though it was on probe.

The resulting runtime PM ref imbalance causes warning messages such as:

  pcieport 0000:02:04.0: Runtime PM usage count underflow!

Avoid the Config Space access (and thus the runtime PM ref imbalance) by
caching the Hot-Plug Capable bit in struct pci_dev.

The struct already contains an "is_hotplug_bridge" flag, which however is
not only set on Hot-Plug Capable PCIe ports, but also Conventional PCI
Hot-Plug bridges and ACPI slots.  The flag identifies bridges which are
allocated additional MMIO and bus number resources to allow for hierarchy
expansion.

The kernel is somewhat sloppily using "is_hotplug_bridge" in a number of
places to identify Hot-Plug Capable PCIe ports, even though the flag
encompasses other devices.  Subsequent commits replace these occurrences
with the new flag to clearly delineate Hot-Plug Capable PCIe ports from
other kinds of hotplug bridges.

Document the existing "is_hotplug_bridge" and the new "is_pciehp" flag
and document the (non-obvious) requirement that pci_bridge_d3_possible()
always returns the same value across the entire lifetime of a bridge,
including its hot-removal.

Fixes: 5352a44a561d ("PCI: pciehp: Make pciehp_is_native() stricter")
Reported-by: Laurent Bigonville <bigon@bigon.be>
Closes: https://bugzilla.kernel.org/show_bug.cgi?id=220216
Reported-by: Mario Limonciello <mario.limonciello@amd.com>
Closes: https://lore.kernel.org/r/20250609020223.269407-3-superm1@kernel.org/
Link: https://lore.kernel.org/all/20250620025535.3425049-3-superm1@kernel.org/T/#u
Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Acked-by: Rafael J. Wysocki <rafael@kernel.org>
Cc: stable@vger.kernel.org # v4.18+
Link: https://patch.msgid.link/fe5dcc3b2e62ee1df7905d746bde161eb1b3291c.1752390101.git.lukas@wunner.de
---
 drivers/pci/pci-acpi.c | 4 +---
 drivers/pci/pci.c      | 6 +++++-
 drivers/pci/probe.c    | 2 +-
 include/linux/pci.h    | 6 ++++++
 4 files changed, 13 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index b78e0e417324..efe478e5073e 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -816,13 +816,11 @@ int pci_acpi_program_hp_params(struct pci_dev *dev)
 bool pciehp_is_native(struct pci_dev *bridge)
 {
 	const struct pci_host_bridge *host;
-	u32 slot_cap;
 
 	if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE))
 		return false;
 
-	pcie_capability_read_dword(bridge, PCI_EXP_SLTCAP, &slot_cap);
-	if (!(slot_cap & PCI_EXP_SLTCAP_HPC))
+	if (!bridge->is_pciehp)
 		return false;
 
 	if (pcie_ports_native)
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index e9448d55113b..23d8fe98ddf9 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3030,8 +3030,12 @@ static const struct dmi_system_id bridge_d3_blacklist[] = {
  * pci_bridge_d3_possible - Is it possible to put the bridge into D3
  * @bridge: Bridge to check
  *
- * This function checks if it is possible to move the bridge to D3.
  * Currently we only allow D3 for some PCIe ports and for Thunderbolt.
+ *
+ * Return: Whether it is possible to move the bridge to D3.
+ *
+ * The return value is guaranteed to be constant across the entire lifetime
+ * of the bridge, including its hot-removal.
  */
 bool pci_bridge_d3_possible(struct pci_dev *bridge)
 {
diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c
index 4b8693ec9e4c..cf50be63bf5f 100644
--- a/drivers/pci/probe.c
+++ b/drivers/pci/probe.c
@@ -1678,7 +1678,7 @@ void set_pcie_hotplug_bridge(struct pci_dev *pdev)
 
 	pcie_capability_read_dword(pdev, PCI_EXP_SLTCAP, &reg32);
 	if (reg32 & PCI_EXP_SLTCAP_HPC)
-		pdev->is_hotplug_bridge = 1;
+		pdev->is_hotplug_bridge = pdev->is_pciehp = 1;
 }
 
 static void set_pcie_thunderbolt(struct pci_dev *dev)
diff --git a/include/linux/pci.h b/include/linux/pci.h
index 05e68f35f392..d56d0dd80afb 100644
--- a/include/linux/pci.h
+++ b/include/linux/pci.h
@@ -328,6 +328,11 @@ struct rcec_ea;
  *			determined (e.g., for Root Complex Integrated
  *			Endpoints without the relevant Capability
  *			Registers).
+ * @is_hotplug_bridge:	Hotplug bridge of any kind (e.g. PCIe Hot-Plug Capable,
+ *			Conventional PCI Hot-Plug, ACPI slot).
+ *			Such bridges are allocated additional MMIO and bus
+ *			number resources to allow for hierarchy expansion.
+ * @is_pciehp:		PCIe Hot-Plug Capable bridge.
  */
 struct pci_dev {
 	struct list_head bus_list;	/* Node in per-bus list */
@@ -451,6 +456,7 @@ struct pci_dev {
 	unsigned int	is_physfn:1;
 	unsigned int	is_virtfn:1;
 	unsigned int	is_hotplug_bridge:1;
+	unsigned int	is_pciehp:1;
 	unsigned int	shpc_managed:1;		/* SHPC owned by shpchp */
 	unsigned int	is_thunderbolt:1;	/* Thunderbolt controller */
 	/*
-- 
cgit v1.2.3


From c2f9de5e2db29158a8caa86a37aa479488e4ba43 Mon Sep 17 00:00:00 2001
From: Lukas Wunner <lukas@wunner.de>
Date: Sun, 13 Jul 2025 16:31:04 +0200
Subject: PCI: Move is_pciehp check out of pciehp_is_native()

pci_bridge_d3_possible() seeks to forbid runtime power management on:

* Non Hot-Plug Capable PCIe ports which are nevertheless ACPI slots
  (recognizable as: bridge->is_hotplug_bridge && !bridge->is_pciehp)

* Hot-Plug Capable PCIe ports for which platform firmware has not granted
  PCIe Native Hot-Plug control to the operating system
  (recognizable as: bridge->is_pciehp && !pciehp_is_native(bridge))

Somewhat confusingly, the check for is_hotplug_bridge is in
pci_bridge_d3_possible(), whereas the one for is_pciehp is in
pciehp_is_native().

For clarity, check is_pciehp directly in pci_bridge_d3_possible()
(and in the other caller of pciehp_is_native(), hotplug_is_native()).

Rephrase the code comment preceding these checks to no longer mention
"System Management Mode", which is an x86 term inappropriate in generic
PCI code.  Likewise no longer mention "Thunderbolt on non-Macs", because
there is nothing Thunderbolt-specific about these checks.  It used to be
the case that non-Macs relied on the platform for Thunderbolt tunnel
management and hotplug, but they've since moved to OS-native tunnel
management (as Macs always have), hence the code comment is no longer
accurate.

There is a subsequent check for is_hotplug_bridge further down in
pci_bridge_d3_possible().  Change the check to is_pciehp because any
ports matching "bridge->is_hotplug_bridge && !bridge->is_pciehp" are
already filtered out at the top of the function.

Do the same for another check in acpi_pci_bridge_d3(), which is called
from pci_bridge_d3_possible() via platform_pci_bridge_d3().

No functional change intended.

Signed-off-by: Lukas Wunner <lukas@wunner.de>
Signed-off-by: Bjorn Helgaas <bhelgaas@google.com>
Link: https://patch.msgid.link/18b2c2110ad0f27a34b189d793310b9c4f2f24a0.1752390102.git.lukas@wunner.de
---
 drivers/pci/pci-acpi.c      |  5 +----
 drivers/pci/pci.c           | 12 ++++++++----
 include/linux/pci_hotplug.h |  3 ++-
 3 files changed, 11 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/pci/pci-acpi.c b/drivers/pci/pci-acpi.c
index efe478e5073e..ed7ed66a595b 100644
--- a/drivers/pci/pci-acpi.c
+++ b/drivers/pci/pci-acpi.c
@@ -820,9 +820,6 @@ bool pciehp_is_native(struct pci_dev *bridge)
 	if (!IS_ENABLED(CONFIG_HOTPLUG_PCI_PCIE))
 		return false;
 
-	if (!bridge->is_pciehp)
-		return false;
-
 	if (pcie_ports_native)
 		return true;
 
@@ -1000,7 +997,7 @@ bool acpi_pci_bridge_d3(struct pci_dev *dev)
 	struct acpi_device *adev, *rpadev;
 	const union acpi_object *obj;
 
-	if (acpi_pci_disabled || !dev->is_hotplug_bridge)
+	if (acpi_pci_disabled || !dev->is_pciehp)
 		return false;
 
 	adev = ACPI_COMPANION(&dev->dev);
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index 23d8fe98ddf9..749994dad9dc 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -3050,10 +3050,14 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge)
 			return false;
 
 		/*
-		 * Hotplug ports handled by firmware in System Management Mode
-		 * may not be put into D3 by the OS (Thunderbolt on non-Macs).
+		 * Hotplug ports handled by platform firmware may not be put
+		 * into D3 by the OS, e.g. ACPI slots ...
 		 */
-		if (bridge->is_hotplug_bridge && !pciehp_is_native(bridge))
+		if (bridge->is_hotplug_bridge && !bridge->is_pciehp)
+			return false;
+
+		/* ... or PCIe hotplug ports not handled natively by the OS. */
+		if (bridge->is_pciehp && !pciehp_is_native(bridge))
 			return false;
 
 		if (pci_bridge_d3_force)
@@ -3072,7 +3076,7 @@ bool pci_bridge_d3_possible(struct pci_dev *bridge)
 		 * by vendors for runtime D3 at least until 2018 because there
 		 * was no OS support.
 		 */
-		if (bridge->is_hotplug_bridge)
+		if (bridge->is_pciehp)
 			return false;
 
 		if (dmi_check_system(bridge_d3_blacklist))
diff --git a/include/linux/pci_hotplug.h b/include/linux/pci_hotplug.h
index ec77ccf1fc4d..ddf79641917f 100644
--- a/include/linux/pci_hotplug.h
+++ b/include/linux/pci_hotplug.h
@@ -104,6 +104,7 @@ static inline bool shpchp_is_native(struct pci_dev *bridge) { return true; }
 
 static inline bool hotplug_is_native(struct pci_dev *bridge)
 {
-	return pciehp_is_native(bridge) || shpchp_is_native(bridge);
+	return (bridge->is_pciehp && pciehp_is_native(bridge)) ||
+	       shpchp_is_native(bridge);
 }
 #endif
-- 
cgit v1.2.3


From 71753c6ed2bf2aee5be26c1bc06a94c9e3713ade Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 29 Jul 2025 14:23:05 -0400
Subject: unwind_user: Add user space unwinding API with frame pointer support

Introduce a generic API for unwinding user stacks.

In order to expand user space unwinding to be able to handle more complex
scenarios, such as deferred unwinding and reading user space information,
create a generic interface that all architectures can use that support the
various unwinding methods.

This is an alternative method for handling user space stack traces from
the simple stack_trace_save_user() API. This does not replace that
interface, but this interface will be used to expand the functionality of
user space stack walking.

None of the structures introduced will be exposed to user space tooling.

Support for frame pointer unwinding is added. For an architecture to
support frame pointer unwinding it needs to enable
CONFIG_HAVE_UNWIND_USER_FP and define ARCH_INIT_USER_FP_FRAME.

By encoding the frame offsets in struct unwind_user_frame, much of this
code can also be reused for future unwinder implementations like sframe.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182404.975790139@kernel.org
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Co-developed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Link: https://lore.kernel.org/all/20250710164301.3094-2-mathieu.desnoyers@efficios.com/
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Co-developed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 MAINTAINERS                       |   8 +++
 arch/Kconfig                      |   7 +++
 include/asm-generic/Kbuild        |   1 +
 include/asm-generic/unwind_user.h |   5 ++
 include/linux/unwind_user.h       |  14 +++++
 include/linux/unwind_user_types.h |  44 +++++++++++++
 kernel/Makefile                   |   1 +
 kernel/unwind/Makefile            |   1 +
 kernel/unwind/user.c              | 128 ++++++++++++++++++++++++++++++++++++++
 9 files changed, 209 insertions(+)
 create mode 100644 include/asm-generic/unwind_user.h
 create mode 100644 include/linux/unwind_user.h
 create mode 100644 include/linux/unwind_user_types.h
 create mode 100644 kernel/unwind/Makefile
 create mode 100644 kernel/unwind/user.c

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index fad6cb025a19..370d780fd5f8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -25928,6 +25928,14 @@ F:	Documentation/driver-api/uio-howto.rst
 F:	drivers/uio/
 F:	include/linux/uio_driver.h
 
+USERSPACE STACK UNWINDING
+M:	Josh Poimboeuf <jpoimboe@kernel.org>
+M:	Steven Rostedt <rostedt@goodmis.org>
+S:	Maintained
+F:	include/linux/unwind*.h
+F:	kernel/unwind/
+
+
 UTIL-LINUX PACKAGE
 M:	Karel Zak <kzak@redhat.com>
 L:	util-linux@vger.kernel.org
diff --git a/arch/Kconfig b/arch/Kconfig
index a3308a220f86..8e3fd723bd74 100644
--- a/arch/Kconfig
+++ b/arch/Kconfig
@@ -435,6 +435,13 @@ config HAVE_HARDLOCKUP_DETECTOR_ARCH
 	  It uses the same command line parameters, and sysctl interface,
 	  as the generic hardlockup detectors.
 
+config UNWIND_USER
+	bool
+
+config HAVE_UNWIND_USER_FP
+	bool
+	select UNWIND_USER
+
 config HAVE_PERF_REGS
 	bool
 	help
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index 8675b7b4ad23..295c94a3ccc1 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -59,6 +59,7 @@ mandatory-y += tlbflush.h
 mandatory-y += topology.h
 mandatory-y += trace_clock.h
 mandatory-y += uaccess.h
+mandatory-y += unwind_user.h
 mandatory-y += vermagic.h
 mandatory-y += vga.h
 mandatory-y += video.h
diff --git a/include/asm-generic/unwind_user.h b/include/asm-generic/unwind_user.h
new file mode 100644
index 000000000000..b8882b909944
--- /dev/null
+++ b/include/asm-generic/unwind_user.h
@@ -0,0 +1,5 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_GENERIC_UNWIND_USER_H
+#define _ASM_GENERIC_UNWIND_USER_H
+
+#endif /* _ASM_GENERIC_UNWIND_USER_H */
diff --git a/include/linux/unwind_user.h b/include/linux/unwind_user.h
new file mode 100644
index 000000000000..7f7282516bf5
--- /dev/null
+++ b/include/linux/unwind_user.h
@@ -0,0 +1,14 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNWIND_USER_H
+#define _LINUX_UNWIND_USER_H
+
+#include <linux/unwind_user_types.h>
+#include <asm/unwind_user.h>
+
+#ifndef ARCH_INIT_USER_FP_FRAME
+ #define ARCH_INIT_USER_FP_FRAME
+#endif
+
+int unwind_user(struct unwind_stacktrace *trace, unsigned int max_entries);
+
+#endif /* _LINUX_UNWIND_USER_H */
diff --git a/include/linux/unwind_user_types.h b/include/linux/unwind_user_types.h
new file mode 100644
index 000000000000..a449f15be890
--- /dev/null
+++ b/include/linux/unwind_user_types.h
@@ -0,0 +1,44 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNWIND_USER_TYPES_H
+#define _LINUX_UNWIND_USER_TYPES_H
+
+#include <linux/types.h>
+
+/*
+ * Unwind types, listed in priority order: lower numbers are attempted first if
+ * available.
+ */
+enum unwind_user_type_bits {
+	UNWIND_USER_TYPE_FP_BIT =		0,
+
+	NR_UNWIND_USER_TYPE_BITS,
+};
+
+enum unwind_user_type {
+	/* Type "none" for the start of stack walk iteration. */
+	UNWIND_USER_TYPE_NONE =			0,
+	UNWIND_USER_TYPE_FP =			BIT(UNWIND_USER_TYPE_FP_BIT),
+};
+
+struct unwind_stacktrace {
+	unsigned int	nr;
+	unsigned long	*entries;
+};
+
+struct unwind_user_frame {
+	s32 cfa_off;
+	s32 ra_off;
+	s32 fp_off;
+	bool use_fp;
+};
+
+struct unwind_user_state {
+	unsigned long				ip;
+	unsigned long				sp;
+	unsigned long				fp;
+	enum unwind_user_type			current_type;
+	unsigned int				available_types;
+	bool					done;
+};
+
+#endif /* _LINUX_UNWIND_USER_TYPES_H */
diff --git a/kernel/Makefile b/kernel/Makefile
index 32e80dd626af..541186050251 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -55,6 +55,7 @@ obj-y += rcu/
 obj-y += livepatch/
 obj-y += dma/
 obj-y += entry/
+obj-y += unwind/
 obj-$(CONFIG_MODULES) += module/
 
 obj-$(CONFIG_KCMP) += kcmp.o
diff --git a/kernel/unwind/Makefile b/kernel/unwind/Makefile
new file mode 100644
index 000000000000..349ce3677526
--- /dev/null
+++ b/kernel/unwind/Makefile
@@ -0,0 +1 @@
+ obj-$(CONFIG_UNWIND_USER) += user.o
diff --git a/kernel/unwind/user.c b/kernel/unwind/user.c
new file mode 100644
index 000000000000..97a8415e3216
--- /dev/null
+++ b/kernel/unwind/user.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+* Generic interfaces for unwinding user space
+*/
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/sched/task_stack.h>
+#include <linux/unwind_user.h>
+#include <linux/uaccess.h>
+
+static const struct unwind_user_frame fp_frame = {
+	ARCH_INIT_USER_FP_FRAME
+};
+
+#define for_each_user_frame(state) \
+	for (unwind_user_start(state); !(state)->done; unwind_user_next(state))
+
+static int unwind_user_next_fp(struct unwind_user_state *state)
+{
+	const struct unwind_user_frame *frame = &fp_frame;
+	unsigned long cfa, fp, ra;
+	unsigned int shift;
+
+	if (frame->use_fp) {
+		if (state->fp < state->sp)
+			return -EINVAL;
+		cfa = state->fp;
+	} else {
+		cfa = state->sp;
+	}
+
+	/* Get the Canonical Frame Address (CFA) */
+	cfa += frame->cfa_off;
+
+	/* stack going in wrong direction? */
+	if (cfa <= state->sp)
+		return -EINVAL;
+
+	/* Make sure that the address is word aligned */
+	shift = sizeof(long) == 4 ? 2 : 3;
+	if (cfa & ((1 << shift) - 1))
+		return -EINVAL;
+
+	/* Find the Return Address (RA) */
+	if (get_user(ra, (unsigned long *)(cfa + frame->ra_off)))
+		return -EINVAL;
+
+	if (frame->fp_off && get_user(fp, (unsigned long __user *)(cfa + frame->fp_off)))
+		return -EINVAL;
+
+	state->ip = ra;
+	state->sp = cfa;
+	if (frame->fp_off)
+		state->fp = fp;
+	return 0;
+}
+
+static int unwind_user_next(struct unwind_user_state *state)
+{
+	unsigned long iter_mask = state->available_types;
+	unsigned int bit;
+
+	if (state->done)
+		return -EINVAL;
+
+	for_each_set_bit(bit, &iter_mask, NR_UNWIND_USER_TYPE_BITS) {
+		enum unwind_user_type type = BIT(bit);
+
+		state->current_type = type;
+		switch (type) {
+		case UNWIND_USER_TYPE_FP:
+			if (!unwind_user_next_fp(state))
+				return 0;
+			continue;
+		default:
+			WARN_ONCE(1, "Undefined unwind bit %d", bit);
+			break;
+		}
+		break;
+	}
+
+	/* No successful unwind method. */
+	state->current_type = UNWIND_USER_TYPE_NONE;
+	state->done = true;
+	return -EINVAL;
+}
+
+static int unwind_user_start(struct unwind_user_state *state)
+{
+	struct pt_regs *regs = task_pt_regs(current);
+
+	memset(state, 0, sizeof(*state));
+
+	if ((current->flags & PF_KTHREAD) || !user_mode(regs)) {
+		state->done = true;
+		return -EINVAL;
+	}
+
+	if (IS_ENABLED(CONFIG_HAVE_UNWIND_USER_FP))
+		state->available_types |= UNWIND_USER_TYPE_FP;
+
+	state->ip = instruction_pointer(regs);
+	state->sp = user_stack_pointer(regs);
+	state->fp = frame_pointer(regs);
+
+	return 0;
+}
+
+int unwind_user(struct unwind_stacktrace *trace, unsigned int max_entries)
+{
+	struct unwind_user_state state;
+
+	trace->nr = 0;
+
+	if (!max_entries)
+		return -EINVAL;
+
+	if (current->flags & PF_KTHREAD)
+		return 0;
+
+	for_each_user_frame(&state) {
+		trace->entries[trace->nr++] = state.ip;
+		if (trace->nr >= max_entries)
+			break;
+	}
+
+	return 0;
+}
-- 
cgit v1.2.3


From 5e32d0f15cc5c843a4115c4644d984d42524c794 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 29 Jul 2025 14:23:06 -0400
Subject: unwind_user/deferred: Add unwind_user_faultable()

Add a new API to retrieve a user space callstack called
unwind_user_faultable(). The difference between this user space stack
tracer from the current user space stack tracer is that this must be
called from faultable context as it may use routines to access user space
data that needs to be faulted in.

It can be safely called from entering or exiting a system call as the code
can still be faulted in there.

This code is based on work by Josh Poimboeuf's deferred unwinding code:

Link: https://lore.kernel.org/all/6052e8487746603bdb29b65f4033e739092d9925.1737511963.git.jpoimboe@kernel.org/

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182405.147896868@kernel.org
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/sched.h                 |  5 +++
 include/linux/unwind_deferred.h       | 24 ++++++++++++++
 include/linux/unwind_deferred_types.h |  9 ++++++
 kernel/fork.c                         |  4 +++
 kernel/unwind/Makefile                |  2 +-
 kernel/unwind/deferred.c              | 60 +++++++++++++++++++++++++++++++++++
 6 files changed, 103 insertions(+), 1 deletion(-)
 create mode 100644 include/linux/unwind_deferred.h
 create mode 100644 include/linux/unwind_deferred_types.h
 create mode 100644 kernel/unwind/deferred.c

(limited to 'include/linux')

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4f78a64beb52..59fdf7d9bb1e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -46,6 +46,7 @@
 #include <linux/rv.h>
 #include <linux/uidgid_types.h>
 #include <linux/tracepoint-defs.h>
+#include <linux/unwind_deferred_types.h>
 #include <asm/kmap_size.h>
 
 /* task_struct member predeclarations (sorted alphabetically): */
@@ -1654,6 +1655,10 @@ struct task_struct {
 	struct user_event_mm		*user_event_mm;
 #endif
 
+#ifdef CONFIG_UNWIND_USER
+	struct unwind_task_info		unwind_info;
+#endif
+
 	/* CPU-specific state of this task: */
 	struct thread_struct		thread;
 
diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
new file mode 100644
index 000000000000..a5f6e8f8a1a2
--- /dev/null
+++ b/include/linux/unwind_deferred.h
@@ -0,0 +1,24 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNWIND_USER_DEFERRED_H
+#define _LINUX_UNWIND_USER_DEFERRED_H
+
+#include <linux/unwind_user.h>
+#include <linux/unwind_deferred_types.h>
+
+#ifdef CONFIG_UNWIND_USER
+
+void unwind_task_init(struct task_struct *task);
+void unwind_task_free(struct task_struct *task);
+
+int unwind_user_faultable(struct unwind_stacktrace *trace);
+
+#else /* !CONFIG_UNWIND_USER */
+
+static inline void unwind_task_init(struct task_struct *task) {}
+static inline void unwind_task_free(struct task_struct *task) {}
+
+static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; }
+
+#endif /* !CONFIG_UNWIND_USER */
+
+#endif /* _LINUX_UNWIND_USER_DEFERRED_H */
diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h
new file mode 100644
index 000000000000..aa32db574e43
--- /dev/null
+++ b/include/linux/unwind_deferred_types.h
@@ -0,0 +1,9 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H
+#define _LINUX_UNWIND_USER_DEFERRED_TYPES_H
+
+struct unwind_task_info {
+	unsigned long		*entries;
+};
+
+#endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
diff --git a/kernel/fork.c b/kernel/fork.c
index 1ee8eb11f38b..3341d50c61f2 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -105,6 +105,7 @@
 #include <uapi/linux/pidfd.h>
 #include <linux/pidfs.h>
 #include <linux/tick.h>
+#include <linux/unwind_deferred.h>
 
 #include <asm/pgalloc.h>
 #include <linux/uaccess.h>
@@ -732,6 +733,7 @@ void __put_task_struct(struct task_struct *tsk)
 	WARN_ON(refcount_read(&tsk->usage));
 	WARN_ON(tsk == current);
 
+	unwind_task_free(tsk);
 	sched_ext_free(tsk);
 	io_uring_free(tsk);
 	cgroup_free(tsk);
@@ -2135,6 +2137,8 @@ __latent_entropy struct task_struct *copy_process(
 	p->bpf_ctx = NULL;
 #endif
 
+	unwind_task_init(p);
+
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	retval = sched_fork(clone_flags, p);
 	if (retval)
diff --git a/kernel/unwind/Makefile b/kernel/unwind/Makefile
index 349ce3677526..eae37bea54fd 100644
--- a/kernel/unwind/Makefile
+++ b/kernel/unwind/Makefile
@@ -1 +1 @@
- obj-$(CONFIG_UNWIND_USER) += user.o
+ obj-$(CONFIG_UNWIND_USER)	+= user.o deferred.o
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
new file mode 100644
index 000000000000..a0badbeb3cc1
--- /dev/null
+++ b/kernel/unwind/deferred.c
@@ -0,0 +1,60 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Deferred user space unwinding
+ */
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/slab.h>
+#include <linux/unwind_deferred.h>
+
+#define UNWIND_MAX_ENTRIES 512
+
+/**
+ * unwind_user_faultable - Produce a user stacktrace in faultable context
+ * @trace: The descriptor that will store the user stacktrace
+ *
+ * This must be called in a known faultable context (usually when entering
+ * or exiting user space). Depending on the available implementations
+ * the @trace will be loaded with the addresses of the user space stacktrace
+ * if it can be found.
+ *
+ * Return: 0 on success and negative on error
+ *         On success @trace will contain the user space stacktrace
+ */
+int unwind_user_faultable(struct unwind_stacktrace *trace)
+{
+	struct unwind_task_info *info = &current->unwind_info;
+
+	/* Should always be called from faultable context */
+	might_fault();
+
+	if (current->flags & PF_EXITING)
+		return -EINVAL;
+
+	if (!info->entries) {
+		info->entries = kmalloc_array(UNWIND_MAX_ENTRIES, sizeof(long),
+					      GFP_KERNEL);
+		if (!info->entries)
+			return -ENOMEM;
+	}
+
+	trace->nr = 0;
+	trace->entries = info->entries;
+	unwind_user(trace, UNWIND_MAX_ENTRIES);
+
+	return 0;
+}
+
+void unwind_task_init(struct task_struct *task)
+{
+	struct unwind_task_info *info = &task->unwind_info;
+
+	memset(info, 0, sizeof(*info));
+}
+
+void unwind_task_free(struct task_struct *task)
+{
+	struct unwind_task_info *info = &task->unwind_info;
+
+	kfree(info->entries);
+}
-- 
cgit v1.2.3


From 94fd44648dae2a5b6149a41faa0b07928c3e1963 Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Tue, 29 Jul 2025 16:18:25 -0700
Subject: fortify: Fix incorrect reporting of read buffer size

When FORTIFY_SOURCE reports about a run-time buffer overread, the wrong
buffer size was being shown in the error message. (The bounds checking
was correct.)

Fixes: 3d965b33e40d ("fortify: Improve buffer overflow reporting")
Reviewed-by: Gustavo A. R. Silva <gustavoars@kernel.org>
Link: https://lore.kernel.org/r/20250729231817.work.023-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 include/linux/fortify-string.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/fortify-string.h b/include/linux/fortify-string.h
index e4ce1cae03bf..b3b53f8c1b28 100644
--- a/include/linux/fortify-string.h
+++ b/include/linux/fortify-string.h
@@ -596,7 +596,7 @@ __FORTIFY_INLINE bool fortify_memcpy_chk(__kernel_size_t size,
 	if (p_size != SIZE_MAX && p_size < size)
 		fortify_panic(func, FORTIFY_WRITE, p_size, size, true);
 	else if (q_size != SIZE_MAX && q_size < size)
-		fortify_panic(func, FORTIFY_READ, p_size, size, true);
+		fortify_panic(func, FORTIFY_READ, q_size, size, true);
 
 	/*
 	 * Warn when writing beyond destination field size.
-- 
cgit v1.2.3


From f627b51aaa041cba715b59026cf2d9cb1476c7ed Mon Sep 17 00:00:00 2001
From: Kees Cook <kees@kernel.org>
Date: Tue, 29 Jul 2025 16:41:00 -0700
Subject: compiler_types: Provide __no_kstack_erase to disable coverage only on
 Clang

In order to support Clang's stack depth tracking (for Linux's kstack_erase
feature), the coverage sanitizer needed to be disabled for __init (and
__head) section code. Doing this universally (i.e. for GCC too) created
a number of unexpected problems, ranging from changes to inlining logic
to failures to DCE code on earlier GCC versions.

Since this change is only needed for Clang, specialize it so that GCC
doesn't see the change as it isn't needed there (the GCC implementation
of kstack_erase uses a GCC plugin that removes stack depth tracking
instrumentation from __init sections during a late pass in the IR).

Successfully build and boot tested with GCC 12 and Clang 22.

Fixes: 381a38ea53d2 ("init.h: Disable sanitizer coverage for __init and __head")
Reported-by: kernel test robot <lkp@intel.com>
Closes: https://lore.kernel.org/oe-kbuild-all/202507270258.neWuiXLd-lkp@intel.com/
Reported-by: syzbot+5245cb609175fb6e8122@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/all/6888d004.a00a0220.26d0e1.0004.GAE@google.com/
Reviewed-by: Nathan Chancellor <nathan@kernel.org>
Reviewed-by: Marco Elver <elver@google.com>
Link: https://lore.kernel.org/r/20250729234055.it.233-kees@kernel.org
Signed-off-by: Kees Cook <kees@kernel.org>
---
 arch/x86/include/asm/init.h    | 2 +-
 include/linux/compiler-clang.h | 3 +++
 include/linux/compiler_types.h | 4 ++++
 include/linux/init.h           | 2 +-
 4 files changed, 9 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 6bfdaeddbae8..5a68e9db6518 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -5,7 +5,7 @@
 #if defined(CONFIG_CC_IS_CLANG) && CONFIG_CLANG_VERSION < 170000
 #define __head	__section(".head.text") __no_sanitize_undefined __no_stack_protector
 #else
-#define __head	__section(".head.text") __no_sanitize_undefined __no_sanitize_coverage
+#define __head	__section(".head.text") __no_sanitize_undefined __no_kstack_erase
 #endif
 
 struct x86_mapping_info {
diff --git a/include/linux/compiler-clang.h b/include/linux/compiler-clang.h
index 4fc8e26914ad..fa4ffe037bc7 100644
--- a/include/linux/compiler-clang.h
+++ b/include/linux/compiler-clang.h
@@ -89,6 +89,9 @@
 #define __no_sanitize_coverage
 #endif
 
+/* Only Clang needs to disable the coverage sanitizer for kstack_erase. */
+#define __no_kstack_erase	__no_sanitize_coverage
+
 #if __has_feature(shadow_call_stack)
 # define __noscs	__attribute__((__no_sanitize__("shadow-call-stack")))
 #endif
diff --git a/include/linux/compiler_types.h b/include/linux/compiler_types.h
index 2b77d12e07b2..16755431fc11 100644
--- a/include/linux/compiler_types.h
+++ b/include/linux/compiler_types.h
@@ -424,6 +424,10 @@ struct ftrace_likely_data {
 # define randomized_struct_fields_end
 #endif
 
+#ifndef __no_kstack_erase
+# define __no_kstack_erase
+#endif
+
 #ifndef __noscs
 # define __noscs
 #endif
diff --git a/include/linux/init.h b/include/linux/init.h
index c65a050d52a7..a60d32d227ee 100644
--- a/include/linux/init.h
+++ b/include/linux/init.h
@@ -51,7 +51,7 @@
    discard it in modules) */
 #define __init		__section(".init.text") __cold __latent_entropy	\
 						__noinitretpoline	\
-						__no_sanitize_coverage
+						__no_kstack_erase
 #define __initdata	__section(".init.data")
 #define __initconst	__section(".init.rodata")
 #define __exitdata	__section(".exit.data")
-- 
cgit v1.2.3


From a11a51896572273d04a9f6011ad22738c52ba554 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 4 Jun 2025 15:52:19 +0200
Subject: spi: spi-mem: Take into account the actual maximum frequency

In order to pick the best variant, the duration of each typical
operation is derived and then compared. These durations are based on the
maximum capabilities of the chips, which are commonly the limiting
factors. However there are other possible limiting pieces, such as the
hardware layout, EMC considerations and in some cases, the SPI controller
itself.

We need to take this into account to further refine our variant choice,
so let's use the actual frequency that will be used for the operation
instead of the theoretical maximum.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
Reviewed-by: Mark Brown <broonie@kernel.org>
---
 drivers/mtd/nand/spi/core.c |  2 +-
 drivers/spi/spi-mem.c       | 18 ++++++++++++++----
 include/linux/spi/spi-mem.h |  2 +-
 3 files changed, 16 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index b90f15c986a3..39b72947c44c 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -1297,7 +1297,7 @@ spinand_select_op_variant(struct spinand_device *spinand,
 
 			nbytes -= op.data.nbytes;
 
-			op_duration_ns += spi_mem_calc_op_duration(&op);
+			op_duration_ns += spi_mem_calc_op_duration(spinand->spimem, &op);
 		}
 
 		if (!nbytes && op_duration_ns < best_op_duration_ns) {
diff --git a/drivers/spi/spi-mem.c b/drivers/spi/spi-mem.c
index c42c227eb2a2..d3b7e857b377 100644
--- a/drivers/spi/spi-mem.c
+++ b/drivers/spi/spi-mem.c
@@ -586,15 +586,25 @@ EXPORT_SYMBOL_GPL(spi_mem_adjust_op_freq);
  * accurate, all these combinations should be rated (eg. with a time estimate)
  * and the best pick should be taken based on these calculations.
  *
- * Returns a ns estimate for the time this op would take.
+ * Returns a ns estimate for the time this op would take, except if no
+ * frequency limit has been set, in this case we return the number of
+ * cycles nevertheless to allow callers to distinguish which operation
+ * would be the fastest at iso-frequency.
  */
-u64 spi_mem_calc_op_duration(struct spi_mem_op *op)
+u64 spi_mem_calc_op_duration(struct spi_mem *mem, struct spi_mem_op *op)
 {
 	u64 ncycles = 0;
 	u64 ps_per_cycles, duration;
 
-	ps_per_cycles = 1000000000000ULL;
-	do_div(ps_per_cycles, op->max_freq);
+	spi_mem_adjust_op_freq(mem, op);
+
+	if (op->max_freq) {
+		ps_per_cycles = 1000000000000ULL;
+		do_div(ps_per_cycles, op->max_freq);
+	} else {
+		/* In this case, the unit is no longer a time unit */
+		ps_per_cycles = 1;
+	}
 
 	ncycles += ((op->cmd.nbytes * 8) / op->cmd.buswidth) / (op->cmd.dtr ? 2 : 1);
 	ncycles += ((op->addr.nbytes * 8) / op->addr.buswidth) / (op->addr.dtr ? 2 : 1);
diff --git a/include/linux/spi/spi-mem.h b/include/linux/spi/spi-mem.h
index c4830dfaff3d..82390712794c 100644
--- a/include/linux/spi/spi-mem.h
+++ b/include/linux/spi/spi-mem.h
@@ -424,7 +424,7 @@ bool spi_mem_default_supports_op(struct spi_mem *mem,
 
 int spi_mem_adjust_op_size(struct spi_mem *mem, struct spi_mem_op *op);
 void spi_mem_adjust_op_freq(struct spi_mem *mem, struct spi_mem_op *op);
-u64 spi_mem_calc_op_duration(struct spi_mem_op *op);
+u64 spi_mem_calc_op_duration(struct spi_mem *mem, struct spi_mem_op *op);
 
 bool spi_mem_supports_op(struct spi_mem *mem,
 			 const struct spi_mem_op *op);
-- 
cgit v1.2.3


From 5de7ea49653f6b988525b559802da615a61ffbea Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 14:14:20 +0200
Subject: mtd: spinand: Fix macro alignment

No functional change, just a style fix to align with the other
macros all around.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 include/linux/mtd/spinand.h | 6 +++---
 1 file changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 15eaa09da998..28a013f4f4f3 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -71,9 +71,9 @@
 
 #define SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(addr, ndummy, buf, len) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1),				\
-			 SPI_MEM_OP_ADDR(2, addr, 1),			\
-			 SPI_MEM_OP_DUMMY(ndummy, 1),			\
-			 SPI_MEM_OP_DATA_IN(len, buf, 1))
+		   SPI_MEM_OP_ADDR(2, addr, 1),				\
+		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
+		   SPI_MEM_OP_DATA_IN(len, buf, 1))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_1S_OP(addr, ndummy, buf, len) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1),				\
-- 
cgit v1.2.3


From d81ad9d78e2cd5bdefd390a83553203668a96092 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 14:14:21 +0200
Subject: mtd: spinand: Add a frequency field to all READ_FROM_CACHE variants

These macros had initially no frequency field. When I added the "maximum
operation frequency" field, I did it initially on very common macros and
I decided to add an optional field for that (with VA_ARGS) in order to
prevent massively unreadable changes. I then added new variants in the
spinand.h header, and requested a frequency field for them by
default. Some times later, I also added maximum frequencies to other
existing variants, but I did it incorrectly, without noticing I was
wrong because the field was optional.

This mix is error prone, so let's do what I should have done since the
very beginning: add a frequency field to all READ_FROM_CACHE variants.

There is no functional change.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/alliancememory.c | 12 ++++----
 drivers/mtd/nand/spi/ato.c            |  6 ++--
 drivers/mtd/nand/spi/esmt.c           |  8 ++---
 drivers/mtd/nand/spi/foresee.c        |  8 ++---
 drivers/mtd/nand/spi/gigadevice.c     | 48 ++++++++++++++---------------
 drivers/mtd/nand/spi/macronix.c       |  8 ++---
 drivers/mtd/nand/spi/micron.c         | 20 ++++++------
 drivers/mtd/nand/spi/paragon.c        | 12 ++++----
 drivers/mtd/nand/spi/skyhigh.c        | 12 ++++----
 drivers/mtd/nand/spi/toshiba.c        |  8 ++---
 drivers/mtd/nand/spi/winbond.c        | 22 +++++++-------
 drivers/mtd/nand/spi/xtx.c            | 12 ++++----
 include/linux/mtd/spinand.h           | 57 ++++++++++++++++++++---------------
 13 files changed, 121 insertions(+), 112 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/alliancememory.c b/drivers/mtd/nand/spi/alliancememory.c
index 2ee498230ec1..9e97c40955c9 100644
--- a/drivers/mtd/nand/spi/alliancememory.c
+++ b/drivers/mtd/nand/spi/alliancememory.c
@@ -17,12 +17,12 @@
 #define AM_STATUS_ECC_MAX_CORRECTED	(3 << 4)
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 			   SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/ato.c b/drivers/mtd/nand/spi/ato.c
index 2b4df1d917ac..45d38ce0736c 100644
--- a/drivers/mtd/nand/spi/ato.c
+++ b/drivers/mtd/nand/spi/ato.c
@@ -14,9 +14,9 @@
 
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/esmt.c b/drivers/mtd/nand/spi/esmt.c
index 9e286612a296..9a9325c0bc49 100644
--- a/drivers/mtd/nand/spi/esmt.c
+++ b/drivers/mtd/nand/spi/esmt.c
@@ -18,10 +18,10 @@
 	(CFG_OTP_ENABLE | ESMT_F50L1G41LB_CFG_OTP_PROTECT)
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-			   SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+			   SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 			   SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/foresee.c b/drivers/mtd/nand/spi/foresee.c
index 7c61644bfb10..c521dd6abc4b 100644
--- a/drivers/mtd/nand/spi/foresee.c
+++ b/drivers/mtd/nand/spi/foresee.c
@@ -12,10 +12,10 @@
 #define SPINAND_MFR_FORESEE		0xCD
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/gigadevice.c b/drivers/mtd/nand/spi/gigadevice.c
index b4087767fe50..93e40431dbe2 100644
--- a/drivers/mtd/nand/spi/gigadevice.c
+++ b/drivers/mtd/nand/spi/gigadevice.c
@@ -24,36 +24,36 @@
 #define GD5FXGQ4UXFXXG_STATUS_ECC_UNCOR_ERROR	(7 << 4)
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(read_cache_variants_f,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_3A_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_1S_OP(0, 0, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_3A_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_1S_OP(0, 0, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(read_cache_variants_1gq5,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(read_cache_variants_2gq5,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 4, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 2, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 4, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 2, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/macronix.c b/drivers/mtd/nand/spi/macronix.c
index eeaf5bf9f082..edf63b9996cf 100644
--- a/drivers/mtd/nand/spi/macronix.c
+++ b/drivers/mtd/nand/spi/macronix.c
@@ -28,10 +28,10 @@ struct macronix_priv {
 };
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/micron.c b/drivers/mtd/nand/spi/micron.c
index 8281c9d3f4f7..a49d7cb6a96d 100644
--- a/drivers/mtd/nand/spi/micron.c
+++ b/drivers/mtd/nand/spi/micron.c
@@ -35,12 +35,12 @@
 	(CFG_OTP_ENABLE | MICRON_MT29F2G01ABAGD_CFG_OTP_STATE)
 
 static SPINAND_OP_VARIANTS(quadio_read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(x4_write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
@@ -52,10 +52,10 @@ static SPINAND_OP_VARIANTS(x4_update_cache_variants,
 
 /* Micron  MT29F2G01AAAED Device */
 static SPINAND_OP_VARIANTS(x4_read_cache_variants,
-			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-			   SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+			   SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+			   SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(x1_write_cache_variants,
 			   SPINAND_PROG_LOAD_1S_1S_1S_OP(true, 0, NULL, 0));
diff --git a/drivers/mtd/nand/spi/paragon.c b/drivers/mtd/nand/spi/paragon.c
index 4670bac41245..73bd124273a5 100644
--- a/drivers/mtd/nand/spi/paragon.c
+++ b/drivers/mtd/nand/spi/paragon.c
@@ -22,12 +22,12 @@
 
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/skyhigh.c b/drivers/mtd/nand/spi/skyhigh.c
index 51d61785df61..bf9ce163e6a7 100644
--- a/drivers/mtd/nand/spi/skyhigh.c
+++ b/drivers/mtd/nand/spi/skyhigh.c
@@ -17,12 +17,12 @@
 #define SKYHIGH_CONFIG_PROTECT_EN		BIT(1)
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 4, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 2, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 4, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 2, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/toshiba.c b/drivers/mtd/nand/spi/toshiba.c
index 4c6923047aeb..6530257ac0be 100644
--- a/drivers/mtd/nand/spi/toshiba.c
+++ b/drivers/mtd/nand/spi/toshiba.c
@@ -15,10 +15,10 @@
 #define TOSH_STATUS_ECC_HAS_BITFLIPS_T	(3 << 4)
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_x4_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index b7a28f001a38..7a9e22e81dcf 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -27,8 +27,8 @@ static SPINAND_OP_VARIANTS(read_cache_octal_variants,
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_8D_OP(0, 2, NULL, 0, 105 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 16, NULL, 0, 162 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_8S_OP(0, 1, NULL, 0, 133 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_octal_variants,
 		SPINAND_PROG_LOAD_1S_8S_8S_OP(true, 0, NULL, 0),
@@ -43,22 +43,22 @@ static SPINAND_OP_VARIANTS(read_cache_dual_quad_dtr_variants,
 		SPINAND_PAGE_READ_FROM_CACHE_1S_4D_4D_OP(0, 8, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_4D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 104 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_2D_2D_OP(0, 4, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_2D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 104 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_1D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 54 * HZ_PER_MHZ));
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/drivers/mtd/nand/spi/xtx.c b/drivers/mtd/nand/spi/xtx.c
index 37336d5958a9..5915b37b47f5 100644
--- a/drivers/mtd/nand/spi/xtx.c
+++ b/drivers/mtd/nand/spi/xtx.c
@@ -23,12 +23,12 @@
 #define XT26XXXD_STATUS_ECC_UNCOR_ERROR     (2)
 
 static SPINAND_OP_VARIANTS(read_cache_variants,
-		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0),
-		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0));
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
 
 static SPINAND_OP_VARIANTS(write_cache_variants,
 		SPINAND_PROG_LOAD_1S_1S_4S_OP(true, 0, NULL, 0),
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 28a013f4f4f3..61a4571cec7e 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -62,30 +62,33 @@
 		   SPI_MEM_OP_NO_DUMMY,					\
 		   SPI_MEM_OP_NO_DATA)
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(addr, ndummy, buf, len, ...) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
-		   SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_1S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_1S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x03, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_FAST_3A_1S_1S_1S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_FAST_3A_1S_1S_1S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0b, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 1))
+		   SPI_MEM_OP_DATA_IN(len, buf, 1),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_1S_1D_1D_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x0d, 1),				\
@@ -94,17 +97,19 @@
 		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 1),			\
 		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_2S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_2S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3b, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_1S_1D_2D_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x3d, 1),				\
@@ -113,18 +118,19 @@
 		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 2),			\
 		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len, ...) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 2),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
-		   SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_2S_2S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_2S_2S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbb, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 2),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 2),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 2))
+		   SPI_MEM_OP_DATA_IN(len, buf, 2),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_1S_2D_2D_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xbd, 1),				\
@@ -133,17 +139,19 @@
 		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 2),			\
 		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_4S_OP(addr, ndummy, buf, len)	\
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_1S_4S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6b, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 1),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 1),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_1S_1D_4D_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0x6d, 1),				\
@@ -152,18 +160,19 @@
 		   SPI_MEM_DTR_OP_DATA_IN(len, buf, 4),			\
 		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len, ...) \
+#define SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
 		   SPI_MEM_OP_ADDR(2, addr, 4),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
 		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
-		   SPI_MEM_OP_MAX_FREQ(__VA_ARGS__ + 0))
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
-#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_4S_4S_OP(addr, ndummy, buf, len) \
+#define SPINAND_PAGE_READ_FROM_CACHE_3A_1S_4S_4S_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xeb, 1),				\
 		   SPI_MEM_OP_ADDR(3, addr, 4),				\
 		   SPI_MEM_OP_DUMMY(ndummy, 4),				\
-		   SPI_MEM_OP_DATA_IN(len, buf, 4))
+		   SPI_MEM_OP_DATA_IN(len, buf, 4),			\
+		   SPI_MEM_OP_MAX_FREQ(freq))
 
 #define SPINAND_PAGE_READ_FROM_CACHE_1S_4D_4D_OP(addr, ndummy, buf, len, freq) \
 	SPI_MEM_OP(SPI_MEM_OP_CMD(0xed, 1),				\
-- 
cgit v1.2.3


From da55809ebb45d1d80b7a388ffef841ed683e1a6f Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 14:14:22 +0200
Subject: mtd: spinand: Add a ->configure_chip() hook

There is already a manufacturer hook, which is manufacturer specific but
not chip specific. We no longer have access to the actual NAND identity
at this stage so let's add a per-chip configuration hook to align the
chip configuration (if any) with the core's setting.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/core.c | 16 ++++++++++++++--
 include/linux/mtd/spinand.h |  7 +++++++
 2 files changed, 21 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 39b72947c44c..9ed3cf2e5dba 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -1253,8 +1253,19 @@ static int spinand_id_detect(struct spinand_device *spinand)
 
 static int spinand_manufacturer_init(struct spinand_device *spinand)
 {
-	if (spinand->manufacturer->ops->init)
-		return spinand->manufacturer->ops->init(spinand);
+	int ret;
+
+	if (spinand->manufacturer->ops->init) {
+		ret = spinand->manufacturer->ops->init(spinand);
+		if (ret)
+			return ret;
+	}
+
+	if (spinand->configure_chip) {
+		ret = spinand->configure_chip(spinand);
+		if (ret)
+			return ret;
+	}
 
 	return 0;
 }
@@ -1349,6 +1360,7 @@ int spinand_match_and_init(struct spinand_device *spinand,
 		spinand->flags = table[i].flags;
 		spinand->id.len = 1 + table[i].devid.len;
 		spinand->select_target = table[i].select_target;
+		spinand->configure_chip = table[i].configure_chip;
 		spinand->set_cont_read = table[i].set_cont_read;
 		spinand->fact_otp = &table[i].fact_otp;
 		spinand->user_otp = &table[i].user_otp;
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 61a4571cec7e..69674fd191d9 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -493,6 +493,7 @@ struct spinand_user_otp {
  * @op_variants.update_cache: variants of the update-cache operation
  * @select_target: function used to select a target/die. Required only for
  *		   multi-die chips
+ * @configure_chip: Align the chip configuration with the core settings
  * @set_cont_read: enable/disable continuous cached reads
  * @fact_otp: SPI NAND factory OTP info.
  * @user_otp: SPI NAND user OTP info.
@@ -516,6 +517,7 @@ struct spinand_info {
 	} op_variants;
 	int (*select_target)(struct spinand_device *spinand,
 			     unsigned int target);
+	int (*configure_chip)(struct spinand_device *spinand);
 	int (*set_cont_read)(struct spinand_device *spinand,
 			     bool enable);
 	struct spinand_fact_otp fact_otp;
@@ -548,6 +550,9 @@ struct spinand_info {
 #define SPINAND_SELECT_TARGET(__func)					\
 	.select_target = __func
 
+#define SPINAND_CONFIGURE_CHIP(__configure_chip)			\
+	.configure_chip = __configure_chip
+
 #define SPINAND_CONT_READ(__set_cont_read)				\
 	.set_cont_read = __set_cont_read
 
@@ -616,6 +621,7 @@ struct spinand_dirmap {
  *		passed in spi_mem_op be DMA-able, so we can't based the bufs on
  *		the stack
  * @manufacturer: SPI NAND manufacturer information
+ * @configure_chip: Align the chip configuration with the core settings
  * @cont_read_possible: Field filled by the core once the whole system
  *		configuration is known to tell whether continuous reads are
  *		suitable to use or not in general with this chip/configuration.
@@ -656,6 +662,7 @@ struct spinand_device {
 	const struct spinand_manufacturer *manufacturer;
 	void *priv;
 
+	int (*configure_chip)(struct spinand_device *spinand);
 	bool cont_read_possible;
 	int (*set_cont_read)(struct spinand_device *spinand,
 			     bool enable);
-- 
cgit v1.2.3


From f1a91175faaab02a45d1ceb313a315a5bfeb5416 Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 14:14:23 +0200
Subject: mtd: spinand: winbond: Enable high-speed modes on w25n0xjw

w25n0xjw chips have a high-speed capability hidden in a configuration
register. Once enabled, dual/quad SDR reads may be performed at a much
higher frequency.

Implement the new ->configure_chip() hook for this purpose and configure
the SR4 register accordingly.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/core.c    |  2 +-
 drivers/mtd/nand/spi/winbond.c | 45 ++++++++++++++++++++++++++++++++++++++++--
 include/linux/mtd/spinand.h    |  1 +
 3 files changed, 45 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 9ed3cf2e5dba..93d22b412dd3 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -20,7 +20,7 @@
 #include <linux/spi/spi.h>
 #include <linux/spi/spi-mem.h>
 
-static int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val)
+int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val)
 {
 	struct spi_mem_op op = SPINAND_GET_FEATURE_1S_1S_1S_OP(reg,
 						      spinand->scratchbuf);
diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index 7a9e22e81dcf..18ae6f58a546 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -18,6 +18,9 @@
 
 #define W25N04KV_STATUS_ECC_5_8_BITFLIPS	(3 << 4)
 
+#define W25N0XJW_SR4			0xD0
+#define W25N0XJW_SR4_HS			BIT(2)
+
 /*
  * "X2" in the core is equivalent to "dual output" in the datasheets,
  * "X4" in the core is equivalent to "quad output" in the datasheets.
@@ -42,10 +45,12 @@ static SPINAND_OP_VARIANTS(update_cache_octal_variants,
 static SPINAND_OP_VARIANTS(read_cache_dual_quad_dtr_variants,
 		SPINAND_PAGE_READ_FROM_CACHE_1S_4D_4D_OP(0, 8, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_4D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 4, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_4S_4S_OP(0, 2, NULL, 0, 104 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_4S_OP(0, 1, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_2D_2D_OP(0, 4, NULL, 0, 80 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_2D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 2, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_2S_2S_OP(0, 1, NULL, 0, 104 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_2S_OP(0, 1, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_1D_OP(0, 2, NULL, 0, 80 * HZ_PER_MHZ),
@@ -230,6 +235,40 @@ static int w25n02kv_ecc_get_status(struct spinand_device *spinand,
 	return -EINVAL;
 }
 
+static int w25n0xjw_hs_cfg(struct spinand_device *spinand)
+{
+	const struct spi_mem_op *op;
+	bool hs;
+	u8 sr4;
+	int ret;
+
+	op = spinand->op_templates.read_cache;
+	if (op->cmd.dtr || op->addr.dtr || op->dummy.dtr || op->data.dtr)
+		hs = false;
+	else if (op->cmd.buswidth == 1 && op->addr.buswidth == 1 &&
+		 op->dummy.buswidth == 1 && op->data.buswidth == 1)
+		hs = false;
+	else if (!op->max_freq)
+		hs = true;
+	else
+		hs = false;
+
+	ret = spinand_read_reg_op(spinand, W25N0XJW_SR4, &sr4);
+	if (ret)
+		return ret;
+
+	if (hs)
+		sr4 |= W25N0XJW_SR4_HS;
+	else
+		sr4 &= ~W25N0XJW_SR4_HS;
+
+	ret = spinand_write_reg_op(spinand, W25N0XJW_SR4, sr4);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 static const struct spinand_info winbond_spinand_table[] = {
 	/* 512M-bit densities */
 	SPINAND_INFO("W25N512GW", /* 1.8V */
@@ -268,7 +307,8 @@ static const struct spinand_info winbond_spinand_table[] = {
 					      &write_cache_variants,
 					      &update_cache_variants),
 		     0,
-		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL)),
+		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL),
+		     SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg)),
 	SPINAND_INFO("W25N01KV", /* 3.3V */
 		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xae, 0x21),
 		     NAND_MEMORG(1, 2048, 96, 64, 1024, 20, 1, 1, 1),
@@ -324,7 +364,8 @@ static const struct spinand_info winbond_spinand_table[] = {
 					      &write_cache_variants,
 					      &update_cache_variants),
 		     0,
-		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL)),
+		     SPINAND_ECCINFO(&w25m02gv_ooblayout, NULL),
+		     SPINAND_CONFIGURE_CHIP(w25n0xjw_hs_cfg)),
 	SPINAND_INFO("W25N02KV", /* 3.3V */
 		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xaa, 0x22),
 		     NAND_MEMORG(1, 2048, 128, 64, 2048, 40, 1, 1, 1),
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 69674fd191d9..53c881e41fc7 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -739,6 +739,7 @@ int spinand_match_and_init(struct spinand_device *spinand,
 			   enum spinand_readid_method rdid_method);
 
 int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val);
+int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val);
 int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val);
 int spinand_select_target(struct spinand_device *spinand, unsigned int target);
 
-- 
cgit v1.2.3


From 535f30d997baa5e5c6a3a4024d49e1871232c72b Mon Sep 17 00:00:00 2001
From: Miquel Raynal <miquel.raynal@bootlin.com>
Date: Wed, 18 Jun 2025 14:14:24 +0200
Subject: mtd: spinand: winbond: Enable high-speed modes on w35n0xjw

w35n0xjw chips can run at up to 166MHz in octal mode, but this is only
possible after programming various VCR registers.

Implement the new ->configure_chip() hook for this purpose.

Signed-off-by: Miquel Raynal <miquel.raynal@bootlin.com>
---
 drivers/mtd/nand/spi/core.c    |  2 +-
 drivers/mtd/nand/spi/winbond.c | 95 ++++++++++++++++++++++++++++++++++++++++--
 include/linux/mtd/spinand.h    |  1 +
 3 files changed, 94 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/mtd/nand/spi/core.c b/drivers/mtd/nand/spi/core.c
index 93d22b412dd3..b0898990b2a5 100644
--- a/drivers/mtd/nand/spi/core.c
+++ b/drivers/mtd/nand/spi/core.c
@@ -360,7 +360,7 @@ static void spinand_ondie_ecc_save_status(struct nand_device *nand, u8 status)
 		engine_conf->status = status;
 }
 
-static int spinand_write_enable_op(struct spinand_device *spinand)
+int spinand_write_enable_op(struct spinand_device *spinand)
 {
 	struct spi_mem_op op = SPINAND_WR_EN_DIS_1S_0_0_OP(true);
 
diff --git a/drivers/mtd/nand/spi/winbond.c b/drivers/mtd/nand/spi/winbond.c
index 18ae6f58a546..53890b1da65c 100644
--- a/drivers/mtd/nand/spi/winbond.c
+++ b/drivers/mtd/nand/spi/winbond.c
@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/mtd/spinand.h>
 #include <linux/units.h>
+#include <linux/delay.h>
 
 #define SPINAND_MFR_WINBOND		0xEF
 
@@ -21,14 +22,26 @@
 #define W25N0XJW_SR4			0xD0
 #define W25N0XJW_SR4_HS			BIT(2)
 
+#define W35N01JW_VCR_IO_MODE			0x00
+#define W35N01JW_VCR_IO_MODE_SINGLE_SDR		0xFF
+#define W35N01JW_VCR_IO_MODE_OCTAL_SDR		0xDF
+#define W35N01JW_VCR_IO_MODE_OCTAL_DDR_DS	0xE7
+#define W35N01JW_VCR_IO_MODE_OCTAL_DDR		0xC7
+#define W35N01JW_VCR_DUMMY_CLOCK_REG	0x01
+
 /*
  * "X2" in the core is equivalent to "dual output" in the datasheets,
  * "X4" in the core is equivalent to "quad output" in the datasheets.
  */
 
 static SPINAND_OP_VARIANTS(read_cache_octal_variants,
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_8D_OP(0, 3, NULL, 0, 120 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1D_8D_OP(0, 2, NULL, 0, 105 * HZ_PER_MHZ),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 20, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 16, NULL, 0, 162 * HZ_PER_MHZ),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 12, NULL, 0, 124 * HZ_PER_MHZ),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_8S_8S_OP(0, 8, NULL, 0, 86 * HZ_PER_MHZ),
+		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_8S_OP(0, 2, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_8S_OP(0, 1, NULL, 0, 133 * HZ_PER_MHZ),
 		SPINAND_PAGE_READ_FROM_CACHE_FAST_1S_1S_1S_OP(0, 1, NULL, 0, 0),
 		SPINAND_PAGE_READ_FROM_CACHE_1S_1S_1S_OP(0, 1, NULL, 0, 0));
@@ -269,6 +282,79 @@ static int w25n0xjw_hs_cfg(struct spinand_device *spinand)
 	return 0;
 }
 
+static int w35n0xjw_write_vcr(struct spinand_device *spinand, u8 reg, u8 val)
+{
+	struct spi_mem_op op =
+		SPI_MEM_OP(SPI_MEM_OP_CMD(0x81, 1),
+			   SPI_MEM_OP_ADDR(3, reg, 1),
+			   SPI_MEM_OP_NO_DUMMY,
+			   SPI_MEM_OP_DATA_OUT(1, spinand->scratchbuf, 1));
+	int ret;
+
+	*spinand->scratchbuf = val;
+
+	ret = spinand_write_enable_op(spinand);
+	if (ret)
+		return ret;
+
+	ret = spi_mem_exec_op(spinand->spimem, &op);
+	if (ret)
+		return ret;
+
+	/*
+	 * Write VCR operation doesn't set the busy bit in SR, which means we
+	 * cannot perform a status poll. Minimum time of 50ns is needed to
+	 * complete the write.
+	 */
+	ndelay(50);
+
+	return 0;
+}
+
+static int w35n0xjw_vcr_cfg(struct spinand_device *spinand)
+{
+	const struct spi_mem_op *op;
+	unsigned int dummy_cycles;
+	bool dtr, single;
+	u8 io_mode;
+	int ret;
+
+	op = spinand->op_templates.read_cache;
+
+	single = (op->cmd.buswidth == 1 && op->addr.buswidth == 1 && op->data.buswidth == 1);
+	dtr = (op->cmd.dtr || op->addr.dtr || op->data.dtr);
+	if (single && !dtr)
+		io_mode = W35N01JW_VCR_IO_MODE_SINGLE_SDR;
+	else if (!single && !dtr)
+		io_mode = W35N01JW_VCR_IO_MODE_OCTAL_SDR;
+	else if (!single && dtr)
+		io_mode = W35N01JW_VCR_IO_MODE_OCTAL_DDR;
+	else
+		return -EINVAL;
+
+	ret = w35n0xjw_write_vcr(spinand, W35N01JW_VCR_IO_MODE, io_mode);
+	if (ret)
+		return ret;
+
+	dummy_cycles = ((op->dummy.nbytes * 8) / op->dummy.buswidth) / (op->dummy.dtr ? 2 : 1);
+	switch (dummy_cycles) {
+	case 8:
+	case 12:
+	case 16:
+	case 20:
+	case 24:
+	case 28:
+		break;
+	default:
+		return -EINVAL;
+	}
+	ret = w35n0xjw_write_vcr(spinand, W35N01JW_VCR_DUMMY_CLOCK_REG, dummy_cycles);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
 static const struct spinand_info winbond_spinand_table[] = {
 	/* 512M-bit densities */
 	SPINAND_INFO("W25N512GW", /* 1.8V */
@@ -326,7 +412,8 @@ static const struct spinand_info winbond_spinand_table[] = {
 					      &write_cache_octal_variants,
 					      &update_cache_octal_variants),
 		     0,
-		     SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL)),
+		     SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL),
+		     SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg)),
 	SPINAND_INFO("W35N02JW", /* 1.8V */
 		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x22),
 		     NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 2, 1),
@@ -335,7 +422,8 @@ static const struct spinand_info winbond_spinand_table[] = {
 					      &write_cache_octal_variants,
 					      &update_cache_octal_variants),
 		     0,
-		     SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL)),
+		     SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL),
+		     SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg)),
 	SPINAND_INFO("W35N04JW", /* 1.8V */
 		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xdf, 0x23),
 		     NAND_MEMORG(1, 4096, 128, 64, 512, 10, 1, 4, 1),
@@ -344,7 +432,8 @@ static const struct spinand_info winbond_spinand_table[] = {
 					      &write_cache_octal_variants,
 					      &update_cache_octal_variants),
 		     0,
-		     SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL)),
+		     SPINAND_ECCINFO(&w35n01jw_ooblayout, NULL),
+		     SPINAND_CONFIGURE_CHIP(w35n0xjw_vcr_cfg)),
 	/* 2G-bit densities */
 	SPINAND_INFO("W25M02GV", /* 2x1G-bit 3.3V */
 		     SPINAND_ID(SPINAND_READID_METHOD_OPCODE_DUMMY, 0xab, 0x21),
diff --git a/include/linux/mtd/spinand.h b/include/linux/mtd/spinand.h
index 53c881e41fc7..27a45bdab7ec 100644
--- a/include/linux/mtd/spinand.h
+++ b/include/linux/mtd/spinand.h
@@ -741,6 +741,7 @@ int spinand_match_and_init(struct spinand_device *spinand,
 int spinand_upd_cfg(struct spinand_device *spinand, u8 mask, u8 val);
 int spinand_read_reg_op(struct spinand_device *spinand, u8 reg, u8 *val);
 int spinand_write_reg_op(struct spinand_device *spinand, u8 reg, u8 val);
+int spinand_write_enable_op(struct spinand_device *spinand);
 int spinand_select_target(struct spinand_device *spinand, unsigned int target);
 
 int spinand_wait(struct spinand_device *spinand, unsigned long initial_delay_us,
-- 
cgit v1.2.3


From 5523a466e905b6287b94654ddb364536f2f948cf Mon Sep 17 00:00:00 2001
From: Arnd Bergmann <arnd@arndb.de>
Date: Fri, 25 Jul 2025 11:06:03 +0200
Subject: i3c: fix module_i3c_i2c_driver() with I3C=n

When CONFIG_I3C is disabled and the i3c_i2c_driver_register() happens
to not be inlined, any driver calling it still references the i3c_driver
instance, which then causes a link failure:

x86_64-linux-ld: drivers/hwmon/lm75.o: in function `lm75_i3c_reg_read':
lm75.c:(.text+0xc61): undefined reference to `i3cdev_to_dev'
x86_64-linux-ld: lm75.c:(.text+0xd25): undefined reference to `i3c_device_do_priv_xfers'
x86_64-linux-ld: lm75.c:(.text+0xdd8): undefined reference to `i3c_device_do_priv_xfers'

This issue was part of the original i3c code, but only now caused problems
when i3c support got added to lm75.

Change the 'inline' annotations in the header to '__always_inline' to
ensure that the dead-code-elimination pass in the compiler can optimize
it out as intended.

Fixes: 6071d10413ff ("hwmon: (lm75) add I3C support for P3T1755")
Fixes: 3a379bbcea0a ("i3c: Add core I3C infrastructure")
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Randy Dunlap <rdunlap@infradead.org>
Tested-by: Randy Dunlap <rdunlap@infradead.org>
Reviewed-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20250725090609.2456262-1-arnd@kernel.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/device.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/i3c/device.h b/include/linux/i3c/device.h
index b674f64d0822..7f136de4b73e 100644
--- a/include/linux/i3c/device.h
+++ b/include/linux/i3c/device.h
@@ -245,7 +245,7 @@ void i3c_driver_unregister(struct i3c_driver *drv);
  *
  * Return: 0 if both registrations succeeds, a negative error code otherwise.
  */
-static inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv,
+static __always_inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv,
 					  struct i2c_driver *i2cdrv)
 {
 	int ret;
@@ -270,7 +270,7 @@ static inline int i3c_i2c_driver_register(struct i3c_driver *i3cdrv,
  * Note that when CONFIG_I3C is not enabled, this function only unregisters the
  * @i2cdrv.
  */
-static inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv,
+static __always_inline void i3c_i2c_driver_unregister(struct i3c_driver *i3cdrv,
 					     struct i2c_driver *i2cdrv)
 {
 	if (IS_ENABLED(CONFIG_I3C))
-- 
cgit v1.2.3


From 9c0609d685b27a0bb392390680207baa820ed118 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 24 Jul 2025 11:41:40 +0200
Subject: i3c: Standardize defines for specification parameters

Align existing defines to follow the consistent pattern:
I3C_BUS_<PARAM>_<MAX|MIN|TYP>_<UNIT>. Prepare the codebase for adding
new parameters and help avoid duplication.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Tested-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20250724094146.6443-2-wsa+renesas@sang-engineering.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 drivers/i3c/master.c               | 12 ++++++------
 drivers/i3c/master/dw-i3c-master.c |  4 ++--
 include/linux/i3c/master.h         |  9 +++++----
 3 files changed, 13 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/i3c/master.c b/drivers/i3c/master.c
index e00991444f31..2ef898a8fd80 100644
--- a/drivers/i3c/master.c
+++ b/drivers/i3c/master.c
@@ -727,12 +727,12 @@ static int i3c_bus_set_mode(struct i3c_bus *i3cbus, enum i3c_bus_mode mode,
 	switch (i3cbus->mode) {
 	case I3C_BUS_MODE_PURE:
 		if (!i3cbus->scl_rate.i3c)
-			i3cbus->scl_rate.i3c = I3C_BUS_TYP_I3C_SCL_RATE;
+			i3cbus->scl_rate.i3c = I3C_BUS_I3C_SCL_TYP_RATE;
 		break;
 	case I3C_BUS_MODE_MIXED_FAST:
 	case I3C_BUS_MODE_MIXED_LIMITED:
 		if (!i3cbus->scl_rate.i3c)
-			i3cbus->scl_rate.i3c = I3C_BUS_TYP_I3C_SCL_RATE;
+			i3cbus->scl_rate.i3c = I3C_BUS_I3C_SCL_TYP_RATE;
 		if (!i3cbus->scl_rate.i2c)
 			i3cbus->scl_rate.i2c = max_i2c_scl_rate;
 		break;
@@ -754,8 +754,8 @@ static int i3c_bus_set_mode(struct i3c_bus *i3cbus, enum i3c_bus_mode mode,
 	 * I3C/I2C frequency may have been overridden, check that user-provided
 	 * values are not exceeding max possible frequency.
 	 */
-	if (i3cbus->scl_rate.i3c > I3C_BUS_MAX_I3C_SCL_RATE ||
-	    i3cbus->scl_rate.i2c > I3C_BUS_I2C_FM_PLUS_SCL_RATE)
+	if (i3cbus->scl_rate.i3c > I3C_BUS_I3C_SCL_MAX_RATE ||
+	    i3cbus->scl_rate.i2c > I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE)
 		return -EINVAL;
 
 	return 0;
@@ -2787,7 +2787,7 @@ int i3c_master_register(struct i3c_master_controller *master,
 			const struct i3c_master_controller_ops *ops,
 			bool secondary)
 {
-	unsigned long i2c_scl_rate = I3C_BUS_I2C_FM_PLUS_SCL_RATE;
+	unsigned long i2c_scl_rate = I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE;
 	struct i3c_bus *i3cbus = i3c_master_get_bus(master);
 	enum i3c_bus_mode mode = I3C_BUS_MODE_PURE;
 	struct i2c_dev_boardinfo *i2cbi;
@@ -2846,7 +2846,7 @@ int i3c_master_register(struct i3c_master_controller *master,
 		}
 
 		if (i2cbi->lvr & I3C_LVR_I2C_FM_MODE)
-			i2c_scl_rate = I3C_BUS_I2C_FM_SCL_RATE;
+			i2c_scl_rate = I3C_BUS_I2C_FM_SCL_MAX_RATE;
 	}
 
 	ret = i3c_bus_set_mode(i3cbus, mode, i2c_scl_rate);
diff --git a/drivers/i3c/master/dw-i3c-master.c b/drivers/i3c/master/dw-i3c-master.c
index cc872b481691..e61be28cd1e3 100644
--- a/drivers/i3c/master/dw-i3c-master.c
+++ b/drivers/i3c/master/dw-i3c-master.c
@@ -605,14 +605,14 @@ static int dw_i2c_clk_cfg(struct dw_i3c_master *master)
 	core_period = DIV_ROUND_UP(1000000000, core_rate);
 
 	lcnt = DIV_ROUND_UP(I3C_BUS_I2C_FMP_TLOW_MIN_NS, core_period);
-	hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_PLUS_SCL_RATE) - lcnt;
+	hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE) - lcnt;
 	scl_timing = SCL_I2C_FMP_TIMING_HCNT(hcnt) |
 		     SCL_I2C_FMP_TIMING_LCNT(lcnt);
 	writel(scl_timing, master->regs + SCL_I2C_FMP_TIMING);
 	master->i2c_fmp_timing = scl_timing;
 
 	lcnt = DIV_ROUND_UP(I3C_BUS_I2C_FM_TLOW_MIN_NS, core_period);
-	hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_SCL_RATE) - lcnt;
+	hcnt = DIV_ROUND_UP(core_rate, I3C_BUS_I2C_FM_SCL_MAX_RATE) - lcnt;
 	scl_timing = SCL_I2C_FM_TIMING_HCNT(hcnt) |
 		     SCL_I2C_FM_TIMING_LCNT(lcnt);
 	writel(scl_timing, master->regs + SCL_I2C_FM_TIMING);
diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index c67922ece617..7dfcbe530515 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -249,10 +249,11 @@ struct i3c_device {
  */
 #define I3C_BUS_MAX_DEVS		11
 
-#define I3C_BUS_MAX_I3C_SCL_RATE	12900000
-#define I3C_BUS_TYP_I3C_SCL_RATE	12500000
-#define I3C_BUS_I2C_FM_PLUS_SCL_RATE	1000000
-#define I3C_BUS_I2C_FM_SCL_RATE		400000
+/* Taken from the I3C Spec V1.1.1, chapter 6.2. "Timing specification" */
+#define I3C_BUS_I2C_FM_PLUS_SCL_MAX_RATE	1000000
+#define I3C_BUS_I2C_FM_SCL_MAX_RATE		400000
+#define I3C_BUS_I3C_SCL_MAX_RATE	12900000
+#define I3C_BUS_I3C_SCL_TYP_RATE	12500000
 #define I3C_BUS_TLOW_OD_MIN_NS		200
 
 /**
-- 
cgit v1.2.3


From 8acf1f3bae1ea48949458b67d68a72a95c3244a4 Mon Sep 17 00:00:00 2001
From: Wolfram Sang <wsa+renesas@sang-engineering.com>
Date: Thu, 24 Jul 2025 11:41:41 +0200
Subject: i3c: Add more parameters for controllers to the header

Add standard timing value definition from specification.

Signed-off-by: Wolfram Sang <wsa+renesas@sang-engineering.com>
Tested-by: Tommaso Merciai <tommaso.merciai.xr@bp.renesas.com>
Reviewed-by: Frank Li <Frank.Li@nxp.com>
Link: https://lore.kernel.org/r/20250724094146.6443-3-wsa+renesas@sang-engineering.com
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 include/linux/i3c/master.h | 4 ++++
 1 file changed, 4 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/i3c/master.h b/include/linux/i3c/master.h
index 7dfcbe530515..043f5c7ff398 100644
--- a/include/linux/i3c/master.h
+++ b/include/linux/i3c/master.h
@@ -254,6 +254,10 @@ struct i3c_device {
 #define I3C_BUS_I2C_FM_SCL_MAX_RATE		400000
 #define I3C_BUS_I3C_SCL_MAX_RATE	12900000
 #define I3C_BUS_I3C_SCL_TYP_RATE	12500000
+#define I3C_BUS_TAVAL_MIN_NS		1000
+#define I3C_BUS_TBUF_MIXED_FM_MIN_NS	1300
+#define I3C_BUS_THIGH_MIXED_MAX_NS	41
+#define I3C_BUS_TIDLE_MIN_NS		200000
 #define I3C_BUS_TLOW_OD_MIN_NS		200
 
 /**
-- 
cgit v1.2.3


From 0060beec0bfa647c4b510df188b1c4673a197839 Mon Sep 17 00:00:00 2001
From: Damien Le Moal <dlemoal@kernel.org>
Date: Mon, 28 Jul 2025 13:04:29 +0900
Subject: ata: libata-sata: Add link_power_management_supported sysfs attribute

A port link power management (LPM) policy can be controlled using the
link_power_management_policy sysfs host attribute. However, this
attribute exists also for hosts that do not support LPM and in such
case, attempting to change the LPM policy for the host (port) will fail
with -EOPNOTSUPP.

Introduce the new sysfs link_power_management_supported host attribute
to indicate to the user if a the port and the devices connected to the
port for the host support LPM, which implies that the
link_power_management_policy attribute can be used.

Since checking that a port and its devices support LPM is common between
the new ata_scsi_lpm_supported_show() function and the existing
ata_scsi_lpm_store() function, the new helper ata_scsi_lpm_supported()
is introduced.

Fixes: 413e800cadbf ("ata: libata-sata: Disallow changing LPM state if not supported")
Reported-by: Borah, Chaitanya Kumar <chaitanya.kumar.borah@intel.com>
Reported-by: kernel test robot <oliver.sang@intel.com>
Closes: https://lore.kernel.org/oe-lkp/202507251014.a5becc3b-lkp@intel.com
Signed-off-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Martin K. Petersen <martin.petersen@oracle.com>
---
 drivers/ata/ata_piix.c    |  1 +
 drivers/ata/libahci.c     |  1 +
 drivers/ata/libata-sata.c | 53 ++++++++++++++++++++++++++++++++++++-----------
 include/linux/libata.h    |  1 +
 4 files changed, 44 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/ata/ata_piix.c b/drivers/ata/ata_piix.c
index 229429ba5027..495fa096dd65 100644
--- a/drivers/ata/ata_piix.c
+++ b/drivers/ata/ata_piix.c
@@ -1089,6 +1089,7 @@ static struct ata_port_operations ich_pata_ops = {
 };
 
 static struct attribute *piix_sidpr_shost_attrs[] = {
+	&dev_attr_link_power_management_supported.attr,
 	&dev_attr_link_power_management_policy.attr,
 	NULL
 };
diff --git a/drivers/ata/libahci.c b/drivers/ata/libahci.c
index b335fb7e5cb4..c79abdfcd7a9 100644
--- a/drivers/ata/libahci.c
+++ b/drivers/ata/libahci.c
@@ -111,6 +111,7 @@ static DEVICE_ATTR(em_buffer, S_IWUSR | S_IRUGO,
 static DEVICE_ATTR(em_message_supported, S_IRUGO, ahci_show_em_supported, NULL);
 
 static struct attribute *ahci_shost_attrs[] = {
+	&dev_attr_link_power_management_supported.attr,
 	&dev_attr_link_power_management_policy.attr,
 	&dev_attr_em_message_type.attr,
 	&dev_attr_em_message.attr,
diff --git a/drivers/ata/libata-sata.c b/drivers/ata/libata-sata.c
index 4734465d3b1e..b2817a2995d6 100644
--- a/drivers/ata/libata-sata.c
+++ b/drivers/ata/libata-sata.c
@@ -900,14 +900,52 @@ static const char *ata_lpm_policy_names[] = {
 	[ATA_LPM_MIN_POWER]		= "min_power",
 };
 
+/*
+ * Check if a port supports link power management.
+ * Must be called with the port locked.
+ */
+static bool ata_scsi_lpm_supported(struct ata_port *ap)
+{
+	struct ata_link *link;
+	struct ata_device *dev;
+
+	if (ap->flags & ATA_FLAG_NO_LPM)
+		return false;
+
+	ata_for_each_link(link, ap, EDGE) {
+		ata_for_each_dev(dev, &ap->link, ENABLED) {
+			if (dev->quirks & ATA_QUIRK_NOLPM)
+				return false;
+		}
+	}
+
+	return true;
+}
+
+static ssize_t ata_scsi_lpm_supported_show(struct device *dev,
+				 struct device_attribute *attr, char *buf)
+{
+	struct Scsi_Host *shost = class_to_shost(dev);
+	struct ata_port *ap = ata_shost_to_port(shost);
+	unsigned long flags;
+	bool supported;
+
+	spin_lock_irqsave(ap->lock, flags);
+	supported = ata_scsi_lpm_supported(ap);
+	spin_unlock_irqrestore(ap->lock, flags);
+
+	return sysfs_emit(buf, "%d\n", supported);
+}
+DEVICE_ATTR(link_power_management_supported, S_IRUGO,
+	    ata_scsi_lpm_supported_show, NULL);
+EXPORT_SYMBOL_GPL(dev_attr_link_power_management_supported);
+
 static ssize_t ata_scsi_lpm_store(struct device *device,
 				  struct device_attribute *attr,
 				  const char *buf, size_t count)
 {
 	struct Scsi_Host *shost = class_to_shost(device);
 	struct ata_port *ap = ata_shost_to_port(shost);
-	struct ata_link *link;
-	struct ata_device *dev;
 	enum ata_lpm_policy policy;
 	unsigned long flags;
 
@@ -924,20 +962,11 @@ static ssize_t ata_scsi_lpm_store(struct device *device,
 
 	spin_lock_irqsave(ap->lock, flags);
 
-	if (ap->flags & ATA_FLAG_NO_LPM) {
+	if (!ata_scsi_lpm_supported(ap)) {
 		count = -EOPNOTSUPP;
 		goto out_unlock;
 	}
 
-	ata_for_each_link(link, ap, EDGE) {
-		ata_for_each_dev(dev, &ap->link, ENABLED) {
-			if (dev->quirks & ATA_QUIRK_NOLPM) {
-				count = -EOPNOTSUPP;
-				goto out_unlock;
-			}
-		}
-	}
-
 	ap->target_lpm_policy = policy;
 	ata_port_schedule_eh(ap);
 out_unlock:
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 912ace523880..0620dd67369f 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -545,6 +545,7 @@ typedef void (*ata_postreset_fn_t)(struct ata_link *link, unsigned int *classes)
 
 extern struct device_attribute dev_attr_unload_heads;
 #ifdef CONFIG_SATA_HOST
+extern struct device_attribute dev_attr_link_power_management_supported;
 extern struct device_attribute dev_attr_link_power_management_policy;
 extern struct device_attribute dev_attr_ncq_prio_supported;
 extern struct device_attribute dev_attr_ncq_prio_enable;
-- 
cgit v1.2.3


From 199d9ffb31650f948dd342ade1c1b920e157630f Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Date: Fri, 11 Jul 2025 15:31:36 +0200
Subject: module: move 'struct module_use' to internal.h
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The struct was moved to the public header file in commit c8e21ced08b3
("module: fix kdb's illicit use of struct module_use.").
Back then the structure was used outside of the module core.
Nowadays this is not true anymore, so the structure can be made internal.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Link: https://lore.kernel.org/r/20250711-kunit-ifdef-modules-v2-1-39443decb1f8@linutronix.de
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
---
 include/linux/module.h   | 7 -------
 kernel/module/internal.h | 7 +++++++
 2 files changed, 7 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index a7cac01d95e7..97c38e1cd377 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -313,13 +313,6 @@ void *__symbol_get_gpl(const char *symbol);
 		__used __section(".no_trim_symbol") = __stringify(x); \
 	(typeof(&x))(__symbol_get(__stringify(x))); })
 
-/* modules using other modules: kdb wants to see this. */
-struct module_use {
-	struct list_head source_list;
-	struct list_head target_list;
-	struct module *source, *target;
-};
-
 enum module_state {
 	MODULE_STATE_LIVE,	/* Normal state. */
 	MODULE_STATE_COMING,	/* Full formed, running module_init. */
diff --git a/kernel/module/internal.h b/kernel/module/internal.h
index 51ddd8866ef3..618202578b42 100644
--- a/kernel/module/internal.h
+++ b/kernel/module/internal.h
@@ -112,6 +112,13 @@ struct find_symbol_arg {
 	enum mod_license license;
 };
 
+/* modules using other modules */
+struct module_use {
+	struct list_head source_list;
+	struct list_head target_list;
+	struct module *source, *target;
+};
+
 int mod_verify_sig(const void *mod, struct load_info *info);
 int try_to_force_load(struct module *mod, const char *reason);
 bool find_symbol(struct find_symbol_arg *fsa);
-- 
cgit v1.2.3


From 818783c804bc051f7faf0ac226b5597f8259c6f8 Mon Sep 17 00:00:00 2001
From: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Date: Fri, 11 Jul 2025 15:31:37 +0200
Subject: module: make structure definitions always visible
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

To write code that works with both CONFIG_MODULES=y and CONFIG_MODULES=n
it is convenient to use "if (IS_ENABLED(CONFIG_MODULES))" over raw #ifdef.
The code will still fully typechecked but the unreachable parts are
discarded by the compiler. This prevents accidental breakage when a certain
kconfig combination was not specifically tested by the developer.
This pattern is already supported to some extend by module.h defining
empty stub functions if CONFIG_MODULES=n.
However some users of module.h work on the structured defined by module.h.

Therefore these structure definitions need to be visible, too.

Many structure members are still gated by specific configuration settings.
The assumption for those is that the code using them will be gated behind
the same configuration setting anyways.

Signed-off-by: Thomas Weißschuh <thomas.weissschuh@linutronix.de>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Link: https://lore.kernel.org/r/20250711-kunit-ifdef-modules-v2-2-39443decb1f8@linutronix.de
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
---
 include/linux/module.h | 20 ++++++++++----------
 1 file changed, 10 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 97c38e1cd377..5fe812de2d84 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -303,16 +303,6 @@ static typeof(name) __mod_device_table__##type##__##name		\
 
 struct notifier_block;
 
-#ifdef CONFIG_MODULES
-
-/* Get/put a kernel symbol (calls must be symmetric) */
-void *__symbol_get(const char *symbol);
-void *__symbol_get_gpl(const char *symbol);
-#define symbol_get(x)	({ \
-	static const char __notrim[] \
-		__used __section(".no_trim_symbol") = __stringify(x); \
-	(typeof(&x))(__symbol_get(__stringify(x))); })
-
 enum module_state {
 	MODULE_STATE_LIVE,	/* Normal state. */
 	MODULE_STATE_COMING,	/* Full formed, running module_init. */
@@ -597,6 +587,16 @@ struct module {
 #define MODULE_ARCH_INIT {}
 #endif
 
+#ifdef CONFIG_MODULES
+
+/* Get/put a kernel symbol (calls must be symmetric) */
+void *__symbol_get(const char *symbol);
+void *__symbol_get_gpl(const char *symbol);
+#define symbol_get(x)	({ \
+	static const char __notrim[] \
+		__used __section(".no_trim_symbol") = __stringify(x); \
+	(typeof(&x))(__symbol_get(__stringify(x))); })
+
 #ifndef HAVE_ARCH_KALLSYMS_SYMBOL_VALUE
 static inline unsigned long kallsyms_symbol_value(const Elf_Sym *sym)
 {
-- 
cgit v1.2.3


From bdc877ba6b7ff1b6d2ebeff11e63da4a50a54854 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 30 Jun 2025 16:32:34 +0200
Subject: module: Restore the moduleparam prefix length check

The moduleparam code allows modules to provide their own definition of
MODULE_PARAM_PREFIX, instead of using the default KBUILD_MODNAME ".".

Commit 730b69d22525 ("module: check kernel param length at compile time,
not runtime") added a check to ensure the prefix doesn't exceed
MODULE_NAME_LEN, as this is what param_sysfs_builtin() expects.

Later, commit 58f86cc89c33 ("VERIFY_OCTAL_PERMISSIONS: stricter checking
for sysfs perms.") removed this check, but there is no indication this was
intentional.

Since the check is still useful for param_sysfs_builtin() to function
properly, reintroduce it in __module_param_call(), but in a modernized form
using static_assert().

While here, clean up the __module_param_call() comments. In particular,
remove the comment "Default value instead of permissions?", which comes
from commit 9774a1f54f17 ("[PATCH] Compile-time check re world-writeable
module params"). This comment was related to the test variable
__param_perm_check_##name, which was removed in the previously mentioned
commit 58f86cc89c33.

Fixes: 58f86cc89c33 ("VERIFY_OCTAL_PERMISSIONS: stricter checking for sysfs perms.")
Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Link: https://lore.kernel.org/r/20250630143535.267745-4-petr.pavlu@suse.com
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
---
 include/linux/moduleparam.h | 5 ++---
 1 file changed, 2 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index bfb85fd13e1f..110e9d09de24 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -282,10 +282,9 @@ struct kparam_array
 #define __moduleparam_const const
 #endif
 
-/* This is the fundamental function for registering boot/module
-   parameters. */
+/* This is the fundamental function for registering boot/module parameters. */
 #define __module_param_call(prefix, name, ops, arg, perm, level, flags)	\
-	/* Default value instead of permissions? */			\
+	static_assert(sizeof(""prefix) - 1 <= MAX_PARAM_PREFIX_LEN);	\
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used __section("__param")					\
-- 
cgit v1.2.3


From 40a826bd6c82ae45cfd3a19cd2a60a10f56b74c0 Mon Sep 17 00:00:00 2001
From: Petr Pavlu <petr.pavlu@suse.com>
Date: Mon, 30 Jun 2025 16:32:36 +0200
Subject: module: Rename MAX_PARAM_PREFIX_LEN to __MODULE_NAME_LEN

The maximum module name length (MODULE_NAME_LEN) is somewhat confusingly
defined in terms of the maximum parameter prefix length
(MAX_PARAM_PREFIX_LEN), when in fact the dependency is in the opposite
direction.

This split originates from commit 730b69d22525 ("module: check kernel param
length at compile time, not runtime"). The code needed to use
MODULE_NAME_LEN in moduleparam.h, but because module.h requires
moduleparam.h, this created a circular dependency. It was resolved by
introducing MAX_PARAM_PREFIX_LEN in moduleparam.h and defining
MODULE_NAME_LEN in module.h in terms of MAX_PARAM_PREFIX_LEN.

Rename MAX_PARAM_PREFIX_LEN to __MODULE_NAME_LEN for clarity. This matches
the similar approach of defining MODULE_INFO in module.h and __MODULE_INFO
in moduleparam.h.

Signed-off-by: Petr Pavlu <petr.pavlu@suse.com>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Link: https://lore.kernel.org/r/20250630143535.267745-6-petr.pavlu@suse.com
Signed-off-by: Daniel Gomez <da.gomez@samsung.com>
---
 include/linux/module.h      |  2 +-
 include/linux/moduleparam.h | 12 ++++++++----
 2 files changed, 9 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/module.h b/include/linux/module.h
index 5fe812de2d84..313ecb8e5181 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -33,7 +33,7 @@
 #include <linux/percpu.h>
 #include <asm/module.h>
 
-#define MODULE_NAME_LEN MAX_PARAM_PREFIX_LEN
+#define MODULE_NAME_LEN __MODULE_NAME_LEN
 
 struct modversion_info {
 	unsigned long crc;
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index 110e9d09de24..a04a2bc4f51e 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -6,6 +6,13 @@
 #include <linux/stringify.h>
 #include <linux/kernel.h>
 
+/*
+ * The maximum module name length, including the NUL byte.
+ * Chosen so that structs with an unsigned long line up, specifically
+ * modversion_info.
+ */
+#define __MODULE_NAME_LEN (64 - sizeof(unsigned long))
+
 /* You can override this manually, but generally this should match the
    module name. */
 #ifdef MODULE
@@ -17,9 +24,6 @@
 #define __MODULE_INFO_PREFIX KBUILD_MODNAME "."
 #endif
 
-/* Chosen so that structs with an unsigned long line up. */
-#define MAX_PARAM_PREFIX_LEN (64 - sizeof(unsigned long))
-
 #define __MODULE_INFO(tag, name, info)					  \
 	static const char __UNIQUE_ID(name)[]				  \
 		__used __section(".modinfo") __aligned(1)		  \
@@ -284,7 +288,7 @@ struct kparam_array
 
 /* This is the fundamental function for registering boot/module parameters. */
 #define __module_param_call(prefix, name, ops, arg, perm, level, flags)	\
-	static_assert(sizeof(""prefix) - 1 <= MAX_PARAM_PREFIX_LEN);	\
+	static_assert(sizeof(""prefix) - 1 <= __MODULE_NAME_LEN);	\
 	static const char __param_str_##name[] = prefix #name;		\
 	static struct kernel_param __moduleparam_const __param_##name	\
 	__used __section("__param")					\
-- 
cgit v1.2.3


From b9c73524106e1c0c857006fb9ff2e5a510dc4021 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 29 Jul 2025 14:23:07 -0400
Subject: unwind_user/deferred: Add unwind cache

Cache the results of the unwind to ensure the unwind is only performed
once, even when called by multiple tracers.

The cache nr_entries gets cleared every time the task exits the kernel.
When a stacktrace is requested, nr_entries gets set to the number of
entries in the stacktrace. If another stacktrace is requested, if
nr_entries is not zero, then it contains the same stacktrace that would be
retrieved so it is not processed again and the entries is given to the
caller.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182405.319691167@kernel.org
Reviewed-by: Jens Remus <jremus@linux.ibm.com>
Reviewed-By: Indu Bhagat <indu.bhagat@oracle.com>
Co-developed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/entry-common.h          |  2 ++
 include/linux/unwind_deferred.h       |  8 ++++++++
 include/linux/unwind_deferred_types.h |  7 ++++++-
 kernel/unwind/deferred.c              | 31 ++++++++++++++++++++++++-------
 4 files changed, 40 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/entry-common.h b/include/linux/entry-common.h
index f94f3fdf15fc..8908b8eeb99b 100644
--- a/include/linux/entry-common.h
+++ b/include/linux/entry-common.h
@@ -12,6 +12,7 @@
 #include <linux/resume_user_mode.h>
 #include <linux/tick.h>
 #include <linux/kmsan.h>
+#include <linux/unwind_deferred.h>
 
 #include <asm/entry-common.h>
 #include <asm/syscall.h>
@@ -362,6 +363,7 @@ static __always_inline void exit_to_user_mode(void)
 	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
+	unwind_reset_info();
 	user_enter_irqoff();
 	arch_exit_to_user_mode();
 	lockdep_hardirqs_on(CALLER_ADDR0);
diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index a5f6e8f8a1a2..baacf4a1eb4c 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -12,6 +12,12 @@ void unwind_task_free(struct task_struct *task);
 
 int unwind_user_faultable(struct unwind_stacktrace *trace);
 
+static __always_inline void unwind_reset_info(void)
+{
+	if (unlikely(current->unwind_info.cache))
+		current->unwind_info.cache->nr_entries = 0;
+}
+
 #else /* !CONFIG_UNWIND_USER */
 
 static inline void unwind_task_init(struct task_struct *task) {}
@@ -19,6 +25,8 @@ static inline void unwind_task_free(struct task_struct *task) {}
 
 static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; }
 
+static inline void unwind_reset_info(void) {}
+
 #endif /* !CONFIG_UNWIND_USER */
 
 #endif /* _LINUX_UNWIND_USER_DEFERRED_H */
diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h
index aa32db574e43..db5b54b18828 100644
--- a/include/linux/unwind_deferred_types.h
+++ b/include/linux/unwind_deferred_types.h
@@ -2,8 +2,13 @@
 #ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H
 #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H
 
+struct unwind_cache {
+	unsigned int		nr_entries;
+	unsigned long		entries[];
+};
+
 struct unwind_task_info {
-	unsigned long		*entries;
+	struct unwind_cache	*cache;
 };
 
 #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index a0badbeb3cc1..96368a5aa522 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -4,10 +4,13 @@
  */
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sizes.h>
 #include <linux/slab.h>
 #include <linux/unwind_deferred.h>
 
-#define UNWIND_MAX_ENTRIES 512
+/* Make the cache fit in a 4K page */
+#define UNWIND_MAX_ENTRIES					\
+	((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long))
 
 /**
  * unwind_user_faultable - Produce a user stacktrace in faultable context
@@ -24,6 +27,7 @@
 int unwind_user_faultable(struct unwind_stacktrace *trace)
 {
 	struct unwind_task_info *info = &current->unwind_info;
+	struct unwind_cache *cache;
 
 	/* Should always be called from faultable context */
 	might_fault();
@@ -31,17 +35,30 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
 	if (current->flags & PF_EXITING)
 		return -EINVAL;
 
-	if (!info->entries) {
-		info->entries = kmalloc_array(UNWIND_MAX_ENTRIES, sizeof(long),
-					      GFP_KERNEL);
-		if (!info->entries)
+	if (!info->cache) {
+		info->cache = kzalloc(struct_size(cache, entries, UNWIND_MAX_ENTRIES),
+				      GFP_KERNEL);
+		if (!info->cache)
 			return -ENOMEM;
 	}
 
+	cache = info->cache;
+	trace->entries = cache->entries;
+
+	if (cache->nr_entries) {
+		/*
+		 * The user stack has already been previously unwound in this
+		 * entry context.  Skip the unwind and use the cache.
+		 */
+		trace->nr = cache->nr_entries;
+		return 0;
+	}
+
 	trace->nr = 0;
-	trace->entries = info->entries;
 	unwind_user(trace, UNWIND_MAX_ENTRIES);
 
+	cache->nr_entries = trace->nr;
+
 	return 0;
 }
 
@@ -56,5 +73,5 @@ void unwind_task_free(struct task_struct *task)
 {
 	struct unwind_task_info *info = &task->unwind_info;
 
-	kfree(info->entries);
+	kfree(info->cache);
 }
-- 
cgit v1.2.3


From 2dffa355f6c279e7d2e574abf9446c41a631c9e5 Mon Sep 17 00:00:00 2001
From: Josh Poimboeuf <jpoimboe@kernel.org>
Date: Tue, 29 Jul 2025 14:23:08 -0400
Subject: unwind_user/deferred: Add deferred unwinding interface

Add an interface for scheduling task work to unwind the user space stack
before returning to user space. This solves several problems for its
callers:

  - Ensure the unwind happens in task context even if the caller may be
    running in interrupt context.

  - Avoid duplicate unwinds, whether called multiple times by the same
    caller or by different callers.

  - Create a "context cookie" which allows trace post-processing to
    correlate kernel unwinds/traces with the user unwind.

A concept of a "cookie" is created to detect when the stacktrace is the
same. A cookie is generated the first time a user space stacktrace is
requested after the task enters the kernel. As the stacktrace is saved on
the task_struct while the task is in the kernel, if another request comes
in, if the cookie is still the same, it will use the saved stacktrace,
and not have to regenerate one.

The cookie is passed to the caller on request, and when the stacktrace is
generated upon returning to user space, it calls the requester's callback
with the cookie as well as the stacktrace. The cookie is cleared
when it goes back to user space. Note, this currently adds another
conditional to the unwind_reset_info() path that is always called
returning to user space, but future changes will put this back to a single
conditional.

A global list is created and protected by a global mutex that holds
tracers that register with the unwind infrastructure. The number of
registered tracers will be limited in future changes. Each perf program or
ftrace instance will register its own descriptor to use for deferred
unwind stack traces.

Note, in the function unwind_deferred_task_work() that gets called when
returning to user space, it uses a global mutex for synchronization which
will cause a big bottleneck. This will be replaced by SRCU, but that
change adds some complex synchronization that deservers its own commit.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Jens Remus <jremus@linux.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182405.488066537@kernel.org
Co-developed-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Josh Poimboeuf <jpoimboe@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/unwind_deferred.h       |  24 ++++++
 include/linux/unwind_deferred_types.h |  24 ++++++
 kernel/unwind/deferred.c              | 156 +++++++++++++++++++++++++++++++++-
 3 files changed, 203 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index baacf4a1eb4c..14efd8c027aa 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -2,9 +2,19 @@
 #ifndef _LINUX_UNWIND_USER_DEFERRED_H
 #define _LINUX_UNWIND_USER_DEFERRED_H
 
+#include <linux/task_work.h>
 #include <linux/unwind_user.h>
 #include <linux/unwind_deferred_types.h>
 
+struct unwind_work;
+
+typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stacktrace *trace, u64 cookie);
+
+struct unwind_work {
+	struct list_head		list;
+	unwind_callback_t		func;
+};
+
 #ifdef CONFIG_UNWIND_USER
 
 void unwind_task_init(struct task_struct *task);
@@ -12,8 +22,19 @@ void unwind_task_free(struct task_struct *task);
 
 int unwind_user_faultable(struct unwind_stacktrace *trace);
 
+int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func);
+int unwind_deferred_request(struct unwind_work *work, u64 *cookie);
+void unwind_deferred_cancel(struct unwind_work *work);
+
 static __always_inline void unwind_reset_info(void)
 {
+	if (unlikely(current->unwind_info.id.id))
+		current->unwind_info.id.id = 0;
+	/*
+	 * As unwind_user_faultable() can be called directly and
+	 * depends on nr_entries being cleared on exit to user,
+	 * this needs to be a separate conditional.
+	 */
 	if (unlikely(current->unwind_info.cache))
 		current->unwind_info.cache->nr_entries = 0;
 }
@@ -24,6 +45,9 @@ static inline void unwind_task_init(struct task_struct *task) {}
 static inline void unwind_task_free(struct task_struct *task) {}
 
 static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; }
+static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) { return -ENOSYS; }
+static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; }
+static inline void unwind_deferred_cancel(struct unwind_work *work) {}
 
 static inline void unwind_reset_info(void) {}
 
diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h
index db5b54b18828..104c477d5609 100644
--- a/include/linux/unwind_deferred_types.h
+++ b/include/linux/unwind_deferred_types.h
@@ -7,8 +7,32 @@ struct unwind_cache {
 	unsigned long		entries[];
 };
 
+/*
+ * The unwind_task_id is a unique identifier that maps to a user space
+ * stacktrace. It is generated the first time a deferred user space
+ * stacktrace is requested after a task has entered the kerenl and
+ * is cleared to zero when it exits. The mapped id will be a non-zero
+ * number.
+ *
+ * To simplify the generation of the 64 bit number, 32 bits will be
+ * the CPU it was generated on, and the other 32 bits will be a per
+ * cpu counter that gets incremented by two every time a new identifier
+ * is generated. The LSB will always be set to keep the value
+ * from being zero.
+ */
+union unwind_task_id {
+	struct {
+		u32		cpu;
+		u32		cnt;
+	};
+	u64			id;
+};
+
 struct unwind_task_info {
 	struct unwind_cache	*cache;
+	struct callback_head	work;
+	union unwind_task_id	id;
+	int			pending;
 };
 
 #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index 96368a5aa522..2cbae2ada309 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -2,16 +2,63 @@
 /*
  * Deferred user space unwinding
  */
+#include <linux/sched/task_stack.h>
+#include <linux/unwind_deferred.h>
+#include <linux/sched/clock.h>
+#include <linux/task_work.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
 #include <linux/sizes.h>
 #include <linux/slab.h>
-#include <linux/unwind_deferred.h>
+#include <linux/mm.h>
 
 /* Make the cache fit in a 4K page */
 #define UNWIND_MAX_ENTRIES					\
 	((SZ_4K - sizeof(struct unwind_cache)) / sizeof(long))
 
+/* Guards adding to and reading the list of callbacks */
+static DEFINE_MUTEX(callback_mutex);
+static LIST_HEAD(callbacks);
+
+/*
+ * This is a unique percpu identifier for a given task entry context.
+ * Conceptually, it's incremented every time the CPU enters the kernel from
+ * user space, so that each "entry context" on the CPU gets a unique ID.  In
+ * reality, as an optimization, it's only incremented on demand for the first
+ * deferred unwind request after a given entry-from-user.
+ *
+ * It's combined with the CPU id to make a systemwide-unique "context cookie".
+ */
+static DEFINE_PER_CPU(u32, unwind_ctx_ctr);
+
+/*
+ * The context cookie is a unique identifier that is assigned to a user
+ * space stacktrace. As the user space stacktrace remains the same while
+ * the task is in the kernel, the cookie is an identifier for the stacktrace.
+ * Although it is possible for the stacktrace to get another cookie if another
+ * request is made after the cookie was cleared and before reentering user
+ * space.
+ */
+static u64 get_cookie(struct unwind_task_info *info)
+{
+	u32 cnt = 1;
+	u32 old = 0;
+
+	if (info->id.cpu)
+		return info->id.id;
+
+	/* LSB is always set to ensure 0 is an invalid value */
+	cnt |= __this_cpu_read(unwind_ctx_ctr) + 2;
+	if (try_cmpxchg(&info->id.cnt, &old, cnt)) {
+		/* Update the per cpu counter */
+		__this_cpu_write(unwind_ctx_ctr, cnt);
+	}
+	/* Interrupts are disabled, the CPU will always be same */
+	info->id.cpu = smp_processor_id() + 1; /* Must be non zero */
+
+	return info->id.id;
+}
+
 /**
  * unwind_user_faultable - Produce a user stacktrace in faultable context
  * @trace: The descriptor that will store the user stacktrace
@@ -62,11 +109,117 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
 	return 0;
 }
 
+static void unwind_deferred_task_work(struct callback_head *head)
+{
+	struct unwind_task_info *info = container_of(head, struct unwind_task_info, work);
+	struct unwind_stacktrace trace;
+	struct unwind_work *work;
+	u64 cookie;
+
+	if (WARN_ON_ONCE(!info->pending))
+		return;
+
+	/* Allow work to come in again */
+	WRITE_ONCE(info->pending, 0);
+
+	/*
+	 * From here on out, the callback must always be called, even if it's
+	 * just an empty trace.
+	 */
+	trace.nr = 0;
+	trace.entries = NULL;
+
+	unwind_user_faultable(&trace);
+
+	cookie = info->id.id;
+
+	guard(mutex)(&callback_mutex);
+	list_for_each_entry(work, &callbacks, list) {
+		work->func(work, &trace, cookie);
+	}
+}
+
+/**
+ * unwind_deferred_request - Request a user stacktrace on task kernel exit
+ * @work: Unwind descriptor requesting the trace
+ * @cookie: The cookie of the first request made for this task
+ *
+ * Schedule a user space unwind to be done in task work before exiting the
+ * kernel.
+ *
+ * The returned @cookie output is the generated cookie of the very first
+ * request for a user space stacktrace for this task since it entered the
+ * kernel. It can be from a request by any caller of this infrastructure.
+ * Its value will also be passed to the callback function.  It can be
+ * used to stitch kernel and user stack traces together in post-processing.
+ *
+ * It's valid to call this function multiple times for the same @work within
+ * the same task entry context.  Each call will return the same cookie
+ * while the task hasn't left the kernel. If the callback is not pending
+ * because it has already been previously called for the same entry context,
+ * it will be called again with the same stack trace and cookie.
+ *
+ * Return: 1 if the the callback was already queued.
+ *         0 if the callback successfully was queued.
+ *         Negative if there's an error.
+ *         @cookie holds the cookie of the first request by any user
+ */
+int unwind_deferred_request(struct unwind_work *work, u64 *cookie)
+{
+	struct unwind_task_info *info = &current->unwind_info;
+	int ret;
+
+	*cookie = 0;
+
+	if (WARN_ON_ONCE(in_nmi()))
+		return -EINVAL;
+
+	if ((current->flags & (PF_KTHREAD | PF_EXITING)) ||
+	    !user_mode(task_pt_regs(current)))
+		return -EINVAL;
+
+	guard(irqsave)();
+
+	*cookie = get_cookie(info);
+
+	/* callback already pending? */
+	if (info->pending)
+		return 1;
+
+	/* The work has been claimed, now schedule it. */
+	ret = task_work_add(current, &info->work, TWA_RESUME);
+	if (WARN_ON_ONCE(ret))
+		return ret;
+
+	info->pending = 1;
+	return 0;
+}
+
+void unwind_deferred_cancel(struct unwind_work *work)
+{
+	if (!work)
+		return;
+
+	guard(mutex)(&callback_mutex);
+	list_del(&work->list);
+}
+
+int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func)
+{
+	memset(work, 0, sizeof(*work));
+
+	guard(mutex)(&callback_mutex);
+	list_add(&work->list, &callbacks);
+	work->func = func;
+	return 0;
+}
+
 void unwind_task_init(struct task_struct *task)
 {
 	struct unwind_task_info *info = &task->unwind_info;
 
 	memset(info, 0, sizeof(*info));
+	init_task_work(&info->work, unwind_deferred_task_work);
 }
 
 void unwind_task_free(struct task_struct *task)
@@ -74,4 +227,5 @@ void unwind_task_free(struct task_struct *task)
 	struct unwind_task_info *info = &task->unwind_info;
 
 	kfree(info->cache);
+	task_work_cancel(task, &info->work);
 }
-- 
cgit v1.2.3


From be3d526a5b34109cecf3bc23b96f0081ad600a5b Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 29 Jul 2025 14:23:10 -0400
Subject: unwind deferred: Use bitmask to determine which callbacks to call

In order to know which registered callback requested a stacktrace for when
the task goes back to user space, add a bitmask to keep track of all
registered tracers. The bitmask is the size of long, which means that on a
32 bit machine, it can have at most 32 registered tracers, and on 64 bit,
it can have at most 64 registered tracers. This should not be an issue as
there should not be more than 10 (unless BPF can abuse this?).

When a tracer registers with unwind_deferred_init() it will get a bit
number assigned to it. When a tracer requests a stacktrace, it will have
its bit set within the task_struct. When the task returns back to user
space, it will call the callbacks for all the registered tracers where
their bits are set in the task's mask.

When a tracer is removed by the unwind_deferred_cancel() all current tasks
will clear the associated bit, just in case another tracer gets registered
immediately afterward and then gets their callback called unexpectedly.

To prevent live locks from happening if an event that happens between the
task_work and when the task goes back to user space, triggers the deferred
unwind, have the unwind_mask get cleared on exit to user space and not
after the callback is made.

Move the pending bit from a value on the task_struct to bit zero of the
unwind_mask (saves space on the task_struct). This will allow modifying
the pending bit along with the work bits atomically.

Instead of clearing a work's bit after its callback is called, it is
delayed until exit. If the work is requested again, the task_work is not
queued again and the request will be notified that the task has already been
called by returning a positive number (the same as if it was already
pending).

The pending bit is cleared before calling the callback functions but the
current work bits remain. If one of the called works registers again, it
will not trigger a task_work if its bit is still present in the task's
unwind_mask.

If a new work requests a deferred unwind, then it will set both the
pending bit and its own bit. Note this will also cause any work that was
previously queued and had their callback already executed to be executed
again. Future work will remove these spurious callbacks.

The use of atomic_long bit operations were suggested by Peter Zijlstra:
Link: https://lore.kernel.org/all/20250715102912.GQ1613200@noisy.programming.kicks-ass.net/
The unwind_mask could not be converted to atomic_long_t do to atomic_long
not having all the bit operations needed by unwind_mask. Instead it
follows other use cases in the kernel and just typecasts the unwind_mask
to atomic_long_t when using the two atomic_long functions.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Jens Remus <jremus@linux.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182405.822789300@kernel.org
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/unwind_deferred.h       | 26 +++++++++--
 include/linux/unwind_deferred_types.h |  2 +-
 kernel/unwind/deferred.c              | 87 +++++++++++++++++++++++++++--------
 3 files changed, 92 insertions(+), 23 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index 14efd8c027aa..337ead927d4d 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -13,10 +13,19 @@ typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stackt
 struct unwind_work {
 	struct list_head		list;
 	unwind_callback_t		func;
+	int				bit;
 };
 
 #ifdef CONFIG_UNWIND_USER
 
+enum {
+	UNWIND_PENDING_BIT = 0,
+};
+
+enum {
+	UNWIND_PENDING		= BIT(UNWIND_PENDING_BIT),
+};
+
 void unwind_task_init(struct task_struct *task);
 void unwind_task_free(struct task_struct *task);
 
@@ -28,15 +37,26 @@ void unwind_deferred_cancel(struct unwind_work *work);
 
 static __always_inline void unwind_reset_info(void)
 {
-	if (unlikely(current->unwind_info.id.id))
+	struct unwind_task_info *info = &current->unwind_info;
+	unsigned long bits;
+
+	/* Was there any unwinding? */
+	if (unlikely(info->unwind_mask)) {
+		bits = info->unwind_mask;
+		do {
+			/* Is a task_work going to run again before going back */
+			if (bits & UNWIND_PENDING)
+				return;
+		} while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL));
 		current->unwind_info.id.id = 0;
+	}
 	/*
 	 * As unwind_user_faultable() can be called directly and
 	 * depends on nr_entries being cleared on exit to user,
 	 * this needs to be a separate conditional.
 	 */
-	if (unlikely(current->unwind_info.cache))
-		current->unwind_info.cache->nr_entries = 0;
+	if (unlikely(info->cache))
+		info->cache->nr_entries = 0;
 }
 
 #else /* !CONFIG_UNWIND_USER */
diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h
index 104c477d5609..5dc9cda141ff 100644
--- a/include/linux/unwind_deferred_types.h
+++ b/include/linux/unwind_deferred_types.h
@@ -29,10 +29,10 @@ union unwind_task_id {
 };
 
 struct unwind_task_info {
+	unsigned long		unwind_mask;
 	struct unwind_cache	*cache;
 	struct callback_head	work;
 	union unwind_task_id	id;
-	int			pending;
 };
 
 #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index c5ac087d2396..e19f02ef416d 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -45,6 +45,16 @@ static inline bool try_assign_cnt(struct unwind_task_info *info, u32 cnt)
 static DEFINE_MUTEX(callback_mutex);
 static LIST_HEAD(callbacks);
 
+#define RESERVED_BITS	(UNWIND_PENDING)
+
+/* Zero'd bits are available for assigning callback users */
+static unsigned long unwind_mask = RESERVED_BITS;
+
+static inline bool unwind_pending(struct unwind_task_info *info)
+{
+	return test_bit(UNWIND_PENDING_BIT, &info->unwind_mask);
+}
+
 /*
  * This is a unique percpu identifier for a given task entry context.
  * Conceptually, it's incremented every time the CPU enters the kernel from
@@ -138,14 +148,15 @@ static void unwind_deferred_task_work(struct callback_head *head)
 	struct unwind_task_info *info = container_of(head, struct unwind_task_info, work);
 	struct unwind_stacktrace trace;
 	struct unwind_work *work;
+	unsigned long bits;
 	u64 cookie;
 
-	if (WARN_ON_ONCE(!info->pending))
+	if (WARN_ON_ONCE(!unwind_pending(info)))
 		return;
 
-	/* Allow work to come in again */
-	WRITE_ONCE(info->pending, 0);
-
+	/* Clear pending bit but make sure to have the current bits */
+	bits = atomic_long_fetch_andnot(UNWIND_PENDING,
+				  (atomic_long_t *)&info->unwind_mask);
 	/*
 	 * From here on out, the callback must always be called, even if it's
 	 * just an empty trace.
@@ -159,7 +170,8 @@ static void unwind_deferred_task_work(struct callback_head *head)
 
 	guard(mutex)(&callback_mutex);
 	list_for_each_entry(work, &callbacks, list) {
-		work->func(work, &trace, cookie);
+		if (test_bit(work->bit, &bits))
+			work->func(work, &trace, cookie);
 	}
 }
 
@@ -183,15 +195,16 @@ static void unwind_deferred_task_work(struct callback_head *head)
  * because it has already been previously called for the same entry context,
  * it will be called again with the same stack trace and cookie.
  *
- * Return: 1 if the the callback was already queued.
- *         0 if the callback successfully was queued.
+ * Return: 0 if the callback successfully was queued.
+ *         1 if the callback is pending or was already executed.
  *         Negative if there's an error.
  *         @cookie holds the cookie of the first request by any user
  */
 int unwind_deferred_request(struct unwind_work *work, u64 *cookie)
 {
 	struct unwind_task_info *info = &current->unwind_info;
-	long pending;
+	unsigned long old, bits;
+	unsigned long bit = BIT(work->bit);
 	int ret;
 
 	*cookie = 0;
@@ -212,32 +225,59 @@ int unwind_deferred_request(struct unwind_work *work, u64 *cookie)
 
 	*cookie = get_cookie(info);
 
-	/* callback already pending? */
-	pending = READ_ONCE(info->pending);
-	if (pending)
-		return 1;
+	old = READ_ONCE(info->unwind_mask);
 
-	/* Claim the work unless an NMI just now swooped in to do so. */
-	if (!try_cmpxchg(&info->pending, &pending, 1))
+	/* Is this already queued or executed */
+	if (old & bit)
 		return 1;
 
+	/*
+	 * This work's bit hasn't been set yet. Now set it with the PENDING
+	 * bit and fetch the current value of unwind_mask. If ether the
+	 * work's bit or PENDING was already set, then this is already queued
+	 * to have a callback.
+	 */
+	bits = UNWIND_PENDING | bit;
+	old = atomic_long_fetch_or(bits, (atomic_long_t *)&info->unwind_mask);
+	if (old & bits) {
+		/*
+		 * If the work's bit was set, whatever set it had better
+		 * have also set pending and queued a callback.
+		 */
+		WARN_ON_ONCE(!(old & UNWIND_PENDING));
+		return old & bit;
+	}
+
 	/* The work has been claimed, now schedule it. */
 	ret = task_work_add(current, &info->work, TWA_RESUME);
-	if (WARN_ON_ONCE(ret)) {
-		WRITE_ONCE(info->pending, 0);
-		return ret;
-	}
 
-	return 0;
+	if (WARN_ON_ONCE(ret))
+		WRITE_ONCE(info->unwind_mask, 0);
+
+	return ret;
 }
 
 void unwind_deferred_cancel(struct unwind_work *work)
 {
+	struct task_struct *g, *t;
+
 	if (!work)
 		return;
 
+	/* No work should be using a reserved bit */
+	if (WARN_ON_ONCE(BIT(work->bit) & RESERVED_BITS))
+		return;
+
 	guard(mutex)(&callback_mutex);
 	list_del(&work->list);
+
+	__clear_bit(work->bit, &unwind_mask);
+
+	guard(rcu)();
+	/* Clear this bit from all threads */
+	for_each_process_thread(g, t) {
+		clear_bit(work->bit, &t->unwind_info.unwind_mask);
+	}
 }
 
 int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func)
@@ -245,6 +285,14 @@ int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func)
 	memset(work, 0, sizeof(*work));
 
 	guard(mutex)(&callback_mutex);
+
+	/* See if there's a bit in the mask available */
+	if (unwind_mask == ~0UL)
+		return -EBUSY;
+
+	work->bit = ffz(unwind_mask);
+	__set_bit(work->bit, &unwind_mask);
+
 	list_add(&work->list, &callbacks);
 	work->func = func;
 	return 0;
@@ -256,6 +304,7 @@ void unwind_task_init(struct task_struct *task)
 
 	memset(info, 0, sizeof(*info));
 	init_task_work(&info->work, unwind_deferred_task_work);
+	info->unwind_mask = 0;
 }
 
 void unwind_task_free(struct task_struct *task)
-- 
cgit v1.2.3


From 4c75133e745aa95636c9ccbab1603ed363dabcd4 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 29 Jul 2025 14:23:11 -0400
Subject: unwind deferred: Add unwind_completed mask to stop spurious callbacks

If there's more than one registered tracer to the unwind deferred
infrastructure, it is currently possible that one tracer could cause extra
callbacks to happen for another tracer if the former requests a deferred
stacktrace after the latter's callback was executed and before the task
went back to user space.

Here's an example of how this could occur:

  [Task enters kernel]
    tracer 1 request -> add cookie to its buffer
    tracer 1 request -> add cookie to its buffer
    <..>
    [ task work executes ]
    tracer 1 callback -> add trace + cookie to its buffer

    [tracer 2 requests and triggers the task work again]
    [ task work executes again ]
    tracer 1 callback -> add trace + cookie to its buffer
    tracer 2 callback -> add trace + cookie to its buffer
 [Task exits back to user space]

This is because the bit for tracer 1 gets set in the task's unwind_mask
when it did its request and does not get cleared until the task returns
back to user space. But if another tracer were to request another deferred
stacktrace, then the next task work will executed all tracer's callbacks
that have their bits set in the task's unwind_mask.

To fix this issue, add another mask called unwind_completed and place it
into the task's info->cache structure. The cache structure is allocated
on the first occurrence of a deferred stacktrace and this unwind_completed
mask is not needed until then. It's better to have it in the cache than to
permanently waste space in the task_struct.

After a tracer's callback is executed, it's bit gets set in this
unwind_completed mask. When the task_work enters, it will AND the task's
unwind_mask with the inverse of the unwind_completed which will eliminate
any work that already had its callback executed since the task entered the
kernel.

When the task leaves the kernel, it will reset this unwind_completed mask
just like it resets the other values as it enters user space.

Link: https://lore.kernel.org/all/20250716142609.47f0e4a5@batman.local.home/

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Jens Remus <jremus@linux.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182405.989222722@kernel.org
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/unwind_deferred.h       |  4 +++-
 include/linux/unwind_deferred_types.h |  1 +
 kernel/unwind/deferred.c              | 19 +++++++++++++++----
 3 files changed, 19 insertions(+), 5 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index 337ead927d4d..b9ec4c8515c7 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -55,8 +55,10 @@ static __always_inline void unwind_reset_info(void)
 	 * depends on nr_entries being cleared on exit to user,
 	 * this needs to be a separate conditional.
 	 */
-	if (unlikely(info->cache))
+	if (unlikely(info->cache)) {
 		info->cache->nr_entries = 0;
+		info->cache->unwind_completed = 0;
+	}
 }
 
 #else /* !CONFIG_UNWIND_USER */
diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h
index 5dc9cda141ff..33b62ac25c86 100644
--- a/include/linux/unwind_deferred_types.h
+++ b/include/linux/unwind_deferred_types.h
@@ -3,6 +3,7 @@
 #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H
 
 struct unwind_cache {
+	unsigned long		unwind_completed;
 	unsigned int		nr_entries;
 	unsigned long		entries[];
 };
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index e19f02ef416d..a3d26014a2e6 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -166,12 +166,18 @@ static void unwind_deferred_task_work(struct callback_head *head)
 
 	unwind_user_faultable(&trace);
 
+	if (info->cache)
+		bits &= ~(info->cache->unwind_completed);
+
 	cookie = info->id.id;
 
 	guard(mutex)(&callback_mutex);
 	list_for_each_entry(work, &callbacks, list) {
-		if (test_bit(work->bit, &bits))
+		if (test_bit(work->bit, &bits)) {
 			work->func(work, &trace, cookie);
+			if (info->cache)
+				info->cache->unwind_completed |= BIT(work->bit);
+		}
 	}
 }
 
@@ -260,23 +266,28 @@ int unwind_deferred_request(struct unwind_work *work, u64 *cookie)
 void unwind_deferred_cancel(struct unwind_work *work)
 {
 	struct task_struct *g, *t;
+	int bit;
 
 	if (!work)
 		return;
 
+	bit = work->bit;
+
 	/* No work should be using a reserved bit */
-	if (WARN_ON_ONCE(BIT(work->bit) & RESERVED_BITS))
+	if (WARN_ON_ONCE(BIT(bit) & RESERVED_BITS))
 		return;
 
 	guard(mutex)(&callback_mutex);
 	list_del(&work->list);
 
-	__clear_bit(work->bit, &unwind_mask);
+	__clear_bit(bit, &unwind_mask);
 
 	guard(rcu)();
 	/* Clear this bit from all threads */
 	for_each_process_thread(g, t) {
-		clear_bit(work->bit, &t->unwind_info.unwind_mask);
+		clear_bit(bit, &t->unwind_info.unwind_mask);
+		if (t->unwind_info.cache)
+			clear_bit(bit, &t->unwind_info.cache->unwind_completed);
 	}
 }
 
-- 
cgit v1.2.3


From 858fa8a3b083e862114bb6483b9fb50b3e2bc4c3 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 29 Jul 2025 14:23:12 -0400
Subject: unwind: Add USED bit to only have one conditional on way back to user
 space

On the way back to user space, the function unwind_reset_info() is called
unconditionally (but always inlined). It currently has two conditionals.
One that checks the unwind_mask which is set whenever a deferred trace is
called and is used to know that the mask needs to be cleared. The other
checks if the cache has been allocated, and if so, it resets the
nr_entries so that the unwinder knows it needs to do the work to get a new
user space stack trace again (it only does it once per entering the
kernel).

Use one of the bits in the unwind mask as a "USED" bit that gets set
whenever a trace is created. This will make it possible to only check the
unwind_mask in the unwind_reset_info() to know if it needs to do work or
not and eliminates a conditional that happens every time the task goes
back to user space.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Jens Remus <jremus@linux.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182406.155422551@kernel.org
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/unwind_deferred.h | 18 +++++++++---------
 kernel/unwind/deferred.c        |  5 ++++-
 2 files changed, 13 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index b9ec4c8515c7..2efbda01e959 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -20,10 +20,14 @@ struct unwind_work {
 
 enum {
 	UNWIND_PENDING_BIT = 0,
+	UNWIND_USED_BIT,
 };
 
 enum {
 	UNWIND_PENDING		= BIT(UNWIND_PENDING_BIT),
+
+	/* Set if the unwinding was used (directly or deferred) */
+	UNWIND_USED		= BIT(UNWIND_USED_BIT)
 };
 
 void unwind_task_init(struct task_struct *task);
@@ -49,15 +53,11 @@ static __always_inline void unwind_reset_info(void)
 				return;
 		} while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL));
 		current->unwind_info.id.id = 0;
-	}
-	/*
-	 * As unwind_user_faultable() can be called directly and
-	 * depends on nr_entries being cleared on exit to user,
-	 * this needs to be a separate conditional.
-	 */
-	if (unlikely(info->cache)) {
-		info->cache->nr_entries = 0;
-		info->cache->unwind_completed = 0;
+
+		if (unlikely(info->cache)) {
+			info->cache->nr_entries = 0;
+			info->cache->unwind_completed = 0;
+		}
 	}
 }
 
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index a3d26014a2e6..2311b725d691 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -45,7 +45,7 @@ static inline bool try_assign_cnt(struct unwind_task_info *info, u32 cnt)
 static DEFINE_MUTEX(callback_mutex);
 static LIST_HEAD(callbacks);
 
-#define RESERVED_BITS	(UNWIND_PENDING)
+#define RESERVED_BITS	(UNWIND_PENDING | UNWIND_USED)
 
 /* Zero'd bits are available for assigning callback users */
 static unsigned long unwind_mask = RESERVED_BITS;
@@ -140,6 +140,9 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
 
 	cache->nr_entries = trace->nr;
 
+	/* Clear nr_entries on way back to user space */
+	set_bit(UNWIND_USED_BIT, &info->unwind_mask);
+
 	return 0;
 }
 
-- 
cgit v1.2.3


From b3b9cb11aa034cfa9eb880bb9bb3d5aaf732e479 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Tue, 29 Jul 2025 14:23:14 -0400
Subject: unwind: Finish up unwind when a task exits

On do_exit() when a task is exiting, if a unwind is requested and the
deferred user stacktrace is deferred via the task_work, the task_work
callback is called after exit_mm() is called in do_exit(). This means that
the user stack trace will not be retrieved and an empty stack is created.

Instead, add a function unwind_deferred_task_exit() and call it just
before exit_mm() so that the unwinder can call the requested callbacks
with the user space stack.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: Jiri Olsa <jolsa@kernel.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Andrii Nakryiko <andrii@kernel.org>
Cc: Indu Bhagat <indu.bhagat@oracle.com>
Cc: "Jose E. Marchesi" <jemarch@gnu.org>
Cc: Beau Belgrave <beaub@linux.microsoft.com>
Cc: Jens Remus <jremus@linux.ibm.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Sam James <sam@gentoo.org>
Link: https://lore.kernel.org/20250729182406.504259474@kernel.org
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/unwind_deferred.h |  3 +++
 kernel/exit.c                   |  2 ++
 kernel/unwind/deferred.c        | 23 ++++++++++++++++++++---
 3 files changed, 25 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index 2efbda01e959..26122d00708a 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -39,6 +39,8 @@ int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func);
 int unwind_deferred_request(struct unwind_work *work, u64 *cookie);
 void unwind_deferred_cancel(struct unwind_work *work);
 
+void unwind_deferred_task_exit(struct task_struct *task);
+
 static __always_inline void unwind_reset_info(void)
 {
 	struct unwind_task_info *info = &current->unwind_info;
@@ -71,6 +73,7 @@ static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback
 static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; }
 static inline void unwind_deferred_cancel(struct unwind_work *work) {}
 
+static inline void unwind_deferred_task_exit(struct task_struct *task) {}
 static inline void unwind_reset_info(void) {}
 
 #endif /* !CONFIG_UNWIND_USER */
diff --git a/kernel/exit.c b/kernel/exit.c
index bb184a67ac73..1d8c8ac33c4f 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -68,6 +68,7 @@
 #include <linux/rethook.h>
 #include <linux/sysfs.h>
 #include <linux/user_events.h>
+#include <linux/unwind_deferred.h>
 #include <linux/uaccess.h>
 #include <linux/pidfs.h>
 
@@ -938,6 +939,7 @@ void __noreturn do_exit(long code)
 
 	tsk->exit_code = code;
 	taskstats_exit(tsk, group_dead);
+	unwind_deferred_task_exit(tsk);
 	trace_sched_process_exit(tsk, group_dead);
 
 	/*
diff --git a/kernel/unwind/deferred.c b/kernel/unwind/deferred.c
index a5ef1c1f915e..dc6040aae3ee 100644
--- a/kernel/unwind/deferred.c
+++ b/kernel/unwind/deferred.c
@@ -114,7 +114,7 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
 	/* Should always be called from faultable context */
 	might_fault();
 
-	if (current->flags & PF_EXITING)
+	if (!current->mm)
 		return -EINVAL;
 
 	if (!info->cache) {
@@ -147,9 +147,9 @@ int unwind_user_faultable(struct unwind_stacktrace *trace)
 	return 0;
 }
 
-static void unwind_deferred_task_work(struct callback_head *head)
+static void process_unwind_deferred(struct task_struct *task)
 {
-	struct unwind_task_info *info = container_of(head, struct unwind_task_info, work);
+	struct unwind_task_info *info = &task->unwind_info;
 	struct unwind_stacktrace trace;
 	struct unwind_work *work;
 	unsigned long bits;
@@ -186,6 +186,23 @@ static void unwind_deferred_task_work(struct callback_head *head)
 	}
 }
 
+static void unwind_deferred_task_work(struct callback_head *head)
+{
+	process_unwind_deferred(current);
+}
+
+void unwind_deferred_task_exit(struct task_struct *task)
+{
+	struct unwind_task_info *info = &current->unwind_info;
+
+	if (!unwind_pending(info))
+		return;
+
+	process_unwind_deferred(task);
+
+	task_work_cancel(task, &info->work);
+}
+
 /**
  * unwind_deferred_request - Request a user stacktrace on task kernel exit
  * @work: Unwind descriptor requesting the trace
-- 
cgit v1.2.3


From b0c85e99458af829c32c225b43f638443bff14e5 Mon Sep 17 00:00:00 2001
From: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Date: Mon, 23 Jun 2025 16:46:45 +0900
Subject: cpumask: Remove unnecessary cpumask_nth_andnot()

Commit 94f753143028("x86/resctrl: Optimize cpumask_any_housekeeping()")
switched the only user of cpumask_nth_andnot() to other cpumask
functions, but left the function cpumask_nth_andnot() unused.
This makes function find_nth_andnot_bit() unused as well. Delete them.

Signed-off-by: Shaopeng Tan <tan.shaopeng@jp.fujitsu.com>
Signed-off-by: Yury Norov [NVIDIA] <yury.norov@gmail.com>
---
 include/linux/cpumask.h | 16 ----------------
 include/linux/find.h    | 27 ---------------------------
 2 files changed, 43 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h
index 39b71b662da3..4bda089fbe5d 100644
--- a/include/linux/cpumask.h
+++ b/include/linux/cpumask.h
@@ -558,22 +558,6 @@ unsigned int cpumask_nth_and(unsigned int cpu, const struct cpumask *srcp1,
 				small_cpumask_bits, cpumask_check(cpu));
 }
 
-/**
- * cpumask_nth_andnot - get the Nth cpu set in 1st cpumask, and clear in 2nd.
- * @srcp1: the cpumask pointer
- * @srcp2: the cpumask pointer
- * @cpu: the Nth cpu to find, starting from 0
- *
- * Return: >= nr_cpu_ids if such cpu doesn't exist.
- */
-static __always_inline
-unsigned int cpumask_nth_andnot(unsigned int cpu, const struct cpumask *srcp1,
-							const struct cpumask *srcp2)
-{
-	return find_nth_andnot_bit(cpumask_bits(srcp1), cpumask_bits(srcp2),
-				small_cpumask_bits, cpumask_check(cpu));
-}
-
 /**
  * cpumask_nth_and_andnot - get the Nth cpu set in 1st and 2nd cpumask, and clear in 3rd.
  * @srcp1: the cpumask pointer
diff --git a/include/linux/find.h b/include/linux/find.h
index 98c61838002c..9d720ad92bc1 100644
--- a/include/linux/find.h
+++ b/include/linux/find.h
@@ -269,33 +269,6 @@ unsigned long find_nth_and_bit(const unsigned long *addr1, const unsigned long *
 	return __find_nth_and_bit(addr1, addr2, size, n);
 }
 
-/**
- * find_nth_andnot_bit - find N'th set bit in 2 memory regions,
- *			 flipping bits in 2nd region
- * @addr1: The 1st address to start the search at
- * @addr2: The 2nd address to start the search at
- * @size: The maximum number of bits to search
- * @n: The number of set bit, which position is needed, counting from 0
- *
- * Returns the bit number of the N'th set bit.
- * If no such, returns @size.
- */
-static __always_inline
-unsigned long find_nth_andnot_bit(const unsigned long *addr1, const unsigned long *addr2,
-				unsigned long size, unsigned long n)
-{
-	if (n >= size)
-		return size;
-
-	if (small_const_nbits(size)) {
-		unsigned long val =  *addr1 & (~*addr2) & GENMASK(size - 1, 0);
-
-		return val ? fns(val, n) : size;
-	}
-
-	return __find_nth_andnot_bit(addr1, addr2, size, n);
-}
-
 /**
  * find_nth_and_andnot_bit - find N'th set bit in 2 memory regions,
  *			     excluding those set in 3rd region
-- 
cgit v1.2.3


From 6d4471252ccc1722d25200fa9b6021ab4e1d6fde Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Mon, 9 Jun 2025 11:45:45 +0900
Subject: bits: split the definition of the asm and non-asm GENMASK*()

In an upcoming change, the non-asm GENMASK*() will all be unified to
depend on GENMASK_TYPE() which indirectly depend on sizeof(), something
not available in asm.

Instead of adding further complexity to GENMASK_TYPE() to make it work
for both asm and non asm, just split the definition of the two variants.

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Reviewed-by: Lucas De Marchi <lucas.demarchi@intel.com>
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 include/linux/bits.h | 13 +++++++------
 1 file changed, 7 insertions(+), 6 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bits.h b/include/linux/bits.h
index 7ad056219115..13dbc8adc70e 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -35,6 +35,11 @@
 
 #define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
 
+#define GENMASK(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
+#define GENMASK_ULL(h, l) \
+	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
+
 /*
  * Generate a mask for the specified type @t. Additional checks are made to
  * guarantee the value returned fits in that type, relying on
@@ -79,15 +84,11 @@
  * BUILD_BUG_ON_ZERO is not available in h files included from asm files,
  * disable the input check if that is the case.
  */
-#define GENMASK_INPUT_CHECK(h, l) 0
+#define GENMASK(h, l)		__GENMASK(h, l)
+#define GENMASK_ULL(h, l)	__GENMASK_ULL(h, l)
 
 #endif /* !defined(__ASSEMBLY__) */
 
-#define GENMASK(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
-#define GENMASK_ULL(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
-
 #if !defined(__ASSEMBLY__)
 /*
  * Missing asm support
-- 
cgit v1.2.3


From 104ea1c84b91c9f452e497ba51602b903711cdd5 Mon Sep 17 00:00:00 2001
From: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Date: Mon, 9 Jun 2025 11:45:46 +0900
Subject: bits: unify the non-asm GENMASK*()

The newly introduced GENMASK_TYPE() macro can also be used to generate
the pre-existing non-asm GENMASK*() variants.

Apply GENMASK_TYPE() to GENMASK(), GENMASK_ULL() and GENMASK_U128().

Signed-off-by: Vincent Mailhol <mailhol.vincent@wanadoo.fr>
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 include/linux/bits.h | 26 ++++----------------------
 1 file changed, 4 insertions(+), 22 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bits.h b/include/linux/bits.h
index 13dbc8adc70e..a40cc861b3a7 100644
--- a/include/linux/bits.h
+++ b/include/linux/bits.h
@@ -2,10 +2,8 @@
 #ifndef __LINUX_BITS_H
 #define __LINUX_BITS_H
 
-#include <linux/const.h>
 #include <vdso/bits.h>
 #include <uapi/linux/bits.h>
-#include <asm/bitsperlong.h>
 
 #define BIT_MASK(nr)		(UL(1) << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
@@ -35,11 +33,6 @@
 
 #define GENMASK_INPUT_CHECK(h, l) BUILD_BUG_ON_ZERO(const_true((l) > (h)))
 
-#define GENMASK(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK(h, l))
-#define GENMASK_ULL(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_ULL(h, l))
-
 /*
  * Generate a mask for the specified type @t. Additional checks are made to
  * guarantee the value returned fits in that type, relying on
@@ -55,10 +48,14 @@
 	     (type_max(t) << (l) &				\
 	      type_max(t) >> (BITS_PER_TYPE(t) - 1 - (h)))))
 
+#define GENMASK(h, l)		GENMASK_TYPE(unsigned long, h, l)
+#define GENMASK_ULL(h, l)	GENMASK_TYPE(unsigned long long, h, l)
+
 #define GENMASK_U8(h, l)	GENMASK_TYPE(u8, h, l)
 #define GENMASK_U16(h, l)	GENMASK_TYPE(u16, h, l)
 #define GENMASK_U32(h, l)	GENMASK_TYPE(u32, h, l)
 #define GENMASK_U64(h, l)	GENMASK_TYPE(u64, h, l)
+#define GENMASK_U128(h, l)	GENMASK_TYPE(u128, h, l)
 
 /*
  * Fixed-type variants of BIT(), with additional checks like GENMASK_TYPE(). The
@@ -89,19 +86,4 @@
 
 #endif /* !defined(__ASSEMBLY__) */
 
-#if !defined(__ASSEMBLY__)
-/*
- * Missing asm support
- *
- * __GENMASK_U128() depends on _BIT128() which would not work
- * in the asm code, as it shifts an 'unsigned __int128' data
- * type instead of direct representation of 128 bit constants
- * such as long and unsigned long. The fundamental problem is
- * that a 128 bit constant will get silently truncated by the
- * gcc compiler.
- */
-#define GENMASK_U128(h, l) \
-	(GENMASK_INPUT_CHECK(h, l) + __GENMASK_U128(h, l))
-#endif
-
 #endif	/* __LINUX_BITS_H */
-- 
cgit v1.2.3


From e2b02d382ae0cb90697e8529dfd3f93bf8c6905c Mon Sep 17 00:00:00 2001
From: Ben Horgan <ben.horgan@arm.com>
Date: Wed, 9 Jul 2025 10:38:08 +0100
Subject: bitfield: Ensure the return values of helper functions are checked

As type##_replace_bits() has no side effects it is only useful if its
return value is checked. Add __must_check to enforce this usage. To have
the bits replaced in-place typep##_replace_bits() can be used instead.

Although, type_##_get_bits() and type_##_encode_bits() are harder to misuse
they are still only useful if the return value is checked. For
consistency, also add __must_check to these.

Signed-off-by: Ben Horgan <ben.horgan@arm.com>
Signed-off-by: Yury Norov (NVIDIA) <yury.norov@gmail.com>
---
 include/linux/bitfield.h | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bitfield.h b/include/linux/bitfield.h
index 6d9a53db54b6..5355f8f806a9 100644
--- a/include/linux/bitfield.h
+++ b/include/linux/bitfield.h
@@ -189,14 +189,14 @@ static __always_inline u64 field_mask(u64 field)
 }
 #define field_max(field)	((typeof(field))field_mask(field))
 #define ____MAKE_OP(type,base,to,from)					\
-static __always_inline __##type type##_encode_bits(base v, base field)	\
+static __always_inline __##type __must_check type##_encode_bits(base v, base field)	\
 {									\
 	if (__builtin_constant_p(v) && (v & ~field_mask(field)))	\
 		__field_overflow();					\
 	return to((v & field_mask(field)) * field_multiplier(field));	\
 }									\
-static __always_inline __##type type##_replace_bits(__##type old,	\
-					base val, base field)		\
+static __always_inline __##type __must_check type##_replace_bits(__##type old,	\
+							base val, base field)	\
 {									\
 	return (old & ~to(field)) | type##_encode_bits(val, field);	\
 }									\
@@ -205,7 +205,7 @@ static __always_inline void type##p_replace_bits(__##type *p,		\
 {									\
 	*p = (*p & ~to(field)) | type##_encode_bits(val, field);	\
 }									\
-static __always_inline base type##_get_bits(__##type v, base field)	\
+static __always_inline base __must_check type##_get_bits(__##type v, base field)	\
 {									\
 	return (from(v) & field)/field_multiplier(field);		\
 }
-- 
cgit v1.2.3


From 12df58ad294253ac1d8df0c9bb9cf726397a671d Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 31 Jul 2025 01:47:30 +0200
Subject: bpf: Add cookie object to bpf maps

Add a cookie to BPF maps to uniquely identify BPF maps for the timespan
when the node is up. This is different to comparing a pointer or BPF map
id which could get rolled over and reused.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20250730234733.530041-1-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h  | 1 +
 kernel/bpf/syscall.c | 6 ++++++
 2 files changed, 7 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f9cd2164ed23..308530c8326b 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -310,6 +310,7 @@ struct bpf_map {
 	bool free_after_rcu_gp;
 	atomic64_t sleepable_refcnt;
 	s64 __percpu *elem_count;
+	u64 cookie; /* write-once */
 };
 
 static inline const char *btf_field_type_name(enum btf_field_type type)
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index e63039817af3..7a814e98d5f5 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -37,6 +37,7 @@
 #include <linux/trace_events.h>
 #include <linux/tracepoint.h>
 #include <linux/overflow.h>
+#include <linux/cookie.h>
 
 #include <net/netfilter/nf_bpf_link.h>
 #include <net/netkit.h>
@@ -53,6 +54,7 @@
 #define BPF_OBJ_FLAG_MASK   (BPF_F_RDONLY | BPF_F_WRONLY)
 
 DEFINE_PER_CPU(int, bpf_prog_active);
+DEFINE_COOKIE(bpf_map_cookie);
 static DEFINE_IDR(prog_idr);
 static DEFINE_SPINLOCK(prog_idr_lock);
 static DEFINE_IDR(map_idr);
@@ -1487,6 +1489,10 @@ static int map_create(union bpf_attr *attr, bool kernel)
 	if (err < 0)
 		goto free_map;
 
+	preempt_disable();
+	map->cookie = gen_cookie_next(&bpf_map_cookie);
+	preempt_enable();
+
 	atomic64_set(&map->refcnt, 1);
 	atomic64_set(&map->usercnt, 1);
 	mutex_init(&map->freeze_mutex);
-- 
cgit v1.2.3


From fd1c98f0ef5cbcec842209776505d9e70d8fcd53 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 31 Jul 2025 01:47:31 +0200
Subject: bpf: Move bpf map owner out of common struct

Given this is only relevant for BPF tail call maps, it is adding up space
and penalizing other map types. We also need to extend this with further
objects to track / compare to. Therefore, lets move this out into a separate
structure and dynamically allocate it only for BPF tail call maps.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20250730234733.530041-2-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h  | 36 ++++++++++++++++++++++++------------
 kernel/bpf/core.c    | 35 ++++++++++++++++++-----------------
 kernel/bpf/syscall.c | 13 +++++++------
 3 files changed, 49 insertions(+), 35 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 308530c8326b..a87646cc5398 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -260,6 +260,18 @@ struct bpf_list_node_kern {
 	void *owner;
 } __attribute__((aligned(8)));
 
+/* 'Ownership' of program-containing map is claimed by the first program
+ * that is going to use this map or by the first program which FD is
+ * stored in the map to make sure that all callers and callees have the
+ * same prog type, JITed flag and xdp_has_frags flag.
+ */
+struct bpf_map_owner {
+	enum bpf_prog_type type;
+	bool jited;
+	bool xdp_has_frags;
+	const struct btf_type *attach_func_proto;
+};
+
 struct bpf_map {
 	const struct bpf_map_ops *ops;
 	struct bpf_map *inner_map_meta;
@@ -292,18 +304,8 @@ struct bpf_map {
 		struct rcu_head rcu;
 	};
 	atomic64_t writecnt;
-	/* 'Ownership' of program-containing map is claimed by the first program
-	 * that is going to use this map or by the first program which FD is
-	 * stored in the map to make sure that all callers and callees have the
-	 * same prog type, JITed flag and xdp_has_frags flag.
-	 */
-	struct {
-		const struct btf_type *attach_func_proto;
-		spinlock_t lock;
-		enum bpf_prog_type type;
-		bool jited;
-		bool xdp_has_frags;
-	} owner;
+	spinlock_t owner_lock;
+	struct bpf_map_owner *owner;
 	bool bypass_spec_v1;
 	bool frozen; /* write-once; write-protected by freeze_mutex */
 	bool free_after_mult_rcu_gp;
@@ -2109,6 +2111,16 @@ static inline bool bpf_map_flags_access_ok(u32 access_flags)
 	       (BPF_F_RDONLY_PROG | BPF_F_WRONLY_PROG);
 }
 
+static inline struct bpf_map_owner *bpf_map_owner_alloc(struct bpf_map *map)
+{
+	return kzalloc(sizeof(*map->owner), GFP_ATOMIC);
+}
+
+static inline void bpf_map_owner_free(struct bpf_map *map)
+{
+	kfree(map->owner);
+}
+
 struct bpf_event_entry {
 	struct perf_event *event;
 	struct file *perf_file;
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 09dde5b00d0c..6e5b3a67e87f 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2377,28 +2377,29 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map,
 				      const struct bpf_prog *fp)
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(fp);
-	bool ret;
 	struct bpf_prog_aux *aux = fp->aux;
+	bool ret = false;
 
 	if (fp->kprobe_override)
-		return false;
+		return ret;
 
-	spin_lock(&map->owner.lock);
-	if (!map->owner.type) {
-		/* There's no owner yet where we could check for
-		 * compatibility.
-		 */
-		map->owner.type  = prog_type;
-		map->owner.jited = fp->jited;
-		map->owner.xdp_has_frags = aux->xdp_has_frags;
-		map->owner.attach_func_proto = aux->attach_func_proto;
+	spin_lock(&map->owner_lock);
+	/* There's no owner yet where we could check for compatibility. */
+	if (!map->owner) {
+		map->owner = bpf_map_owner_alloc(map);
+		if (!map->owner)
+			goto err;
+		map->owner->type  = prog_type;
+		map->owner->jited = fp->jited;
+		map->owner->xdp_has_frags = aux->xdp_has_frags;
+		map->owner->attach_func_proto = aux->attach_func_proto;
 		ret = true;
 	} else {
-		ret = map->owner.type  == prog_type &&
-		      map->owner.jited == fp->jited &&
-		      map->owner.xdp_has_frags == aux->xdp_has_frags;
+		ret = map->owner->type  == prog_type &&
+		      map->owner->jited == fp->jited &&
+		      map->owner->xdp_has_frags == aux->xdp_has_frags;
 		if (ret &&
-		    map->owner.attach_func_proto != aux->attach_func_proto) {
+		    map->owner->attach_func_proto != aux->attach_func_proto) {
 			switch (prog_type) {
 			case BPF_PROG_TYPE_TRACING:
 			case BPF_PROG_TYPE_LSM:
@@ -2411,8 +2412,8 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map,
 			}
 		}
 	}
-	spin_unlock(&map->owner.lock);
-
+err:
+	spin_unlock(&map->owner_lock);
 	return ret;
 }
 
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 7a814e98d5f5..0fbfa8532c39 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -887,6 +887,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 
 	security_bpf_map_free(map);
 	bpf_map_release_memcg(map);
+	bpf_map_owner_free(map);
 	bpf_map_free(map);
 }
 
@@ -981,12 +982,12 @@ static void bpf_map_show_fdinfo(struct seq_file *m, struct file *filp)
 	struct bpf_map *map = filp->private_data;
 	u32 type = 0, jited = 0;
 
-	if (map_type_contains_progs(map)) {
-		spin_lock(&map->owner.lock);
-		type  = map->owner.type;
-		jited = map->owner.jited;
-		spin_unlock(&map->owner.lock);
+	spin_lock(&map->owner_lock);
+	if (map->owner) {
+		type  = map->owner->type;
+		jited = map->owner->jited;
 	}
+	spin_unlock(&map->owner_lock);
 
 	seq_printf(m,
 		   "map_type:\t%u\n"
@@ -1496,7 +1497,7 @@ static int map_create(union bpf_attr *attr, bool kernel)
 	atomic64_set(&map->refcnt, 1);
 	atomic64_set(&map->usercnt, 1);
 	mutex_init(&map->freeze_mutex);
-	spin_lock_init(&map->owner.lock);
+	spin_lock_init(&map->owner_lock);
 
 	if (attr->btf_key_type_id || attr->btf_value_type_id ||
 	    /* Even the map's value is a kernel's struct,
-- 
cgit v1.2.3


From 9621e60f59eae87eb9ffe88d90f24f391a1ef0f0 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 31 Jul 2025 01:47:32 +0200
Subject: bpf: Move cgroup iterator helpers to bpf.h

Move them into bpf.h given we also need them in core code.

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20250730234733.530041-3-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf-cgroup.h |  5 -----
 include/linux/bpf.h        | 22 ++++++++++++++--------
 2 files changed, 14 insertions(+), 13 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
index 082ccd8ad96b..aedf573bdb42 100644
--- a/include/linux/bpf-cgroup.h
+++ b/include/linux/bpf-cgroup.h
@@ -77,9 +77,6 @@ to_cgroup_bpf_attach_type(enum bpf_attach_type attach_type)
 extern struct static_key_false cgroup_bpf_enabled_key[MAX_CGROUP_BPF_ATTACH_TYPE];
 #define cgroup_bpf_enabled(atype) static_branch_unlikely(&cgroup_bpf_enabled_key[atype])
 
-#define for_each_cgroup_storage_type(stype) \
-	for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++)
-
 struct bpf_cgroup_storage_map;
 
 struct bpf_storage_buffer {
@@ -510,8 +507,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
 #define BPF_CGROUP_RUN_PROG_SETSOCKOPT(sock, level, optname, optval, optlen, \
 				       kernel_optval) ({ 0; })
 
-#define for_each_cgroup_storage_type(stype) for (; false; )
-
 #endif /* CONFIG_CGROUP_BPF */
 
 #endif /* _BPF_CGROUP_H */
diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index a87646cc5398..02aa41e301a5 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -208,6 +208,20 @@ enum btf_field_type {
 	BPF_RES_SPIN_LOCK = (1 << 12),
 };
 
+enum bpf_cgroup_storage_type {
+	BPF_CGROUP_STORAGE_SHARED,
+	BPF_CGROUP_STORAGE_PERCPU,
+	__BPF_CGROUP_STORAGE_MAX
+#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
+};
+
+#ifdef CONFIG_CGROUP_BPF
+# define for_each_cgroup_storage_type(stype) \
+	for (stype = 0; stype < MAX_BPF_CGROUP_STORAGE_TYPE; stype++)
+#else
+# define for_each_cgroup_storage_type(stype) for (; false; )
+#endif /* CONFIG_CGROUP_BPF */
+
 typedef void (*btf_dtor_kfunc_t)(void *);
 
 struct btf_field_kptr {
@@ -1085,14 +1099,6 @@ struct bpf_prog_offload {
 	u32			jited_len;
 };
 
-enum bpf_cgroup_storage_type {
-	BPF_CGROUP_STORAGE_SHARED,
-	BPF_CGROUP_STORAGE_PERCPU,
-	__BPF_CGROUP_STORAGE_MAX
-};
-
-#define MAX_BPF_CGROUP_STORAGE_TYPE __BPF_CGROUP_STORAGE_MAX
-
 /* The longest tracepoint has 12 args.
  * See include/trace/bpf_probe.h
  */
-- 
cgit v1.2.3


From abad3d0bad72a52137e0c350c59542d75ae4f513 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Thu, 31 Jul 2025 01:47:33 +0200
Subject: bpf: Fix oob access in cgroup local storage

Lonial reported that an out-of-bounds access in cgroup local storage
can be crafted via tail calls. Given two programs each utilizing a
cgroup local storage with a different value size, and one program
doing a tail call into the other. The verifier will validate each of
the indivial programs just fine. However, in the runtime context
the bpf_cg_run_ctx holds an bpf_prog_array_item which contains the
BPF program as well as any cgroup local storage flavor the program
uses. Helpers such as bpf_get_local_storage() pick this up from the
runtime context:

  ctx = container_of(current->bpf_ctx, struct bpf_cg_run_ctx, run_ctx);
  storage = ctx->prog_item->cgroup_storage[stype];

  if (stype == BPF_CGROUP_STORAGE_SHARED)
    ptr = &READ_ONCE(storage->buf)->data[0];
  else
    ptr = this_cpu_ptr(storage->percpu_buf);

For the second program which was called from the originally attached
one, this means bpf_get_local_storage() will pick up the former
program's map, not its own. With mismatching sizes, this can result
in an unintended out-of-bounds access.

To fix this issue, we need to extend bpf_map_owner with an array of
storage_cookie[] to match on i) the exact maps from the original
program if the second program was using bpf_get_local_storage(), or
ii) allow the tail call combination if the second program was not
using any of the cgroup local storage maps.

Fixes: 7d9c3427894f ("bpf: Make cgroup storages shared between programs on the same cgroup")
Reported-by: Lonial Con <kongln9170@gmail.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/r/20250730234733.530041-4-daniel@iogearbox.net
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 include/linux/bpf.h |  1 +
 kernel/bpf/core.c   | 15 +++++++++++++++
 2 files changed, 16 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 02aa41e301a5..cc700925b802 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -283,6 +283,7 @@ struct bpf_map_owner {
 	enum bpf_prog_type type;
 	bool jited;
 	bool xdp_has_frags;
+	u64 storage_cookie[MAX_BPF_CGROUP_STORAGE_TYPE];
 	const struct btf_type *attach_func_proto;
 };
 
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c
index 6e5b3a67e87f..5d1650af899d 100644
--- a/kernel/bpf/core.c
+++ b/kernel/bpf/core.c
@@ -2378,7 +2378,9 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map,
 {
 	enum bpf_prog_type prog_type = resolve_prog_type(fp);
 	struct bpf_prog_aux *aux = fp->aux;
+	enum bpf_cgroup_storage_type i;
 	bool ret = false;
+	u64 cookie;
 
 	if (fp->kprobe_override)
 		return ret;
@@ -2393,11 +2395,24 @@ static bool __bpf_prog_map_compatible(struct bpf_map *map,
 		map->owner->jited = fp->jited;
 		map->owner->xdp_has_frags = aux->xdp_has_frags;
 		map->owner->attach_func_proto = aux->attach_func_proto;
+		for_each_cgroup_storage_type(i) {
+			map->owner->storage_cookie[i] =
+				aux->cgroup_storage[i] ?
+				aux->cgroup_storage[i]->cookie : 0;
+		}
 		ret = true;
 	} else {
 		ret = map->owner->type  == prog_type &&
 		      map->owner->jited == fp->jited &&
 		      map->owner->xdp_has_frags == aux->xdp_has_frags;
+		for_each_cgroup_storage_type(i) {
+			if (!ret)
+				break;
+			cookie = aux->cgroup_storage[i] ?
+				 aux->cgroup_storage[i]->cookie : 0;
+			ret = map->owner->storage_cookie[i] == cookie ||
+			      !cookie;
+		}
 		if (ret &&
 		    map->owner->attach_func_proto != aux->attach_func_proto) {
 			switch (prog_type) {
-- 
cgit v1.2.3


From e2ba58ccc9099514380c3300cbc0750b5055fc1c Mon Sep 17 00:00:00 2001
From: Guenter Roeck <linux@roeck-us.net>
Date: Wed, 30 Jul 2025 21:49:53 -0700
Subject: block: Fix default IO priority if there is no IO context

Upstream commit 53889bcaf536 ("block: make __get_task_ioprio() easier to
read") changes the IO priority returned to the caller if no IO context
is defined for the task. Prior to this commit, the returned IO priority
was determined by task_nice_ioclass() and task_nice_ioprio(). Now it is
always IOPRIO_DEFAULT, which translates to IOPRIO_CLASS_NONE with priority
0. However, task_nice_ioclass() returns IOPRIO_CLASS_IDLE, IOPRIO_CLASS_RT,
or IOPRIO_CLASS_BE depending on the task scheduling policy, and
task_nice_ioprio() returns a value determined by task_nice(). This causes
regressions in test code checking the IO priority and class of IO
operations on tasks with no IO context.

Fix the problem by returning the IO priority calculated from
task_nice_ioclass() and task_nice_ioprio() if no IO context is defined
to match earlier behavior.

Fixes: 53889bcaf536 ("block: make __get_task_ioprio() easier to read")
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Guenter Roeck <linux@roeck-us.net>
Reviewed-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Link: https://lore.kernel.org/r/20250731044953.1852690-1-linux@roeck-us.net
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/ioprio.h | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/ioprio.h b/include/linux/ioprio.h
index b25377b6ea98..5210e8371238 100644
--- a/include/linux/ioprio.h
+++ b/include/linux/ioprio.h
@@ -60,7 +60,8 @@ static inline int __get_task_ioprio(struct task_struct *p)
 	int prio;
 
 	if (!ioc)
-		return IOPRIO_DEFAULT;
+		return IOPRIO_PRIO_VALUE(task_nice_ioclass(p),
+					 task_nice_ioprio(p));
 
 	if (p != current)
 		lockdep_assert_held(&p->alloc_lock);
-- 
cgit v1.2.3


From 5ccaeedb489b41ce6cb857d0de488992746be282 Mon Sep 17 00:00:00 2001
From: Mark Rutland <mark.rutland@arm.com>
Date: Fri, 1 Aug 2025 00:10:06 +0000
Subject: cfi: add C CFI type macro

Currently x86 and riscv open-code 4 instances of the same logic to
define a u32 variable with the KCFI typeid of a given function.

Replace the duplicate logic with a common macro.

Signed-off-by: Mark Rutland <mark.rutland@arm.com>
Co-developed-by: Maxwell Bland <mbland@motorola.com>
Signed-off-by: Maxwell Bland <mbland@motorola.com>
Co-developed-by: Sami Tolvanen <samitolvanen@google.com>
Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Tested-by: Dao Huang <huangdao1@oppo.com>
Acked-by: Will Deacon <will@kernel.org>
Link: https://lore.kernel.org/r/20250801001004.1859976-6-samitolvanen@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/kernel/cfi.c       | 35 +++--------------------------------
 arch/x86/kernel/alternative.c | 31 +++----------------------------
 include/linux/cfi_types.h     | 23 +++++++++++++++++++++++
 3 files changed, 29 insertions(+), 60 deletions(-)

(limited to 'include/linux')

diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c
index 64bdd3e1ab8c..e7aec5f36dd5 100644
--- a/arch/riscv/kernel/cfi.c
+++ b/arch/riscv/kernel/cfi.c
@@ -4,6 +4,7 @@
  *
  * Copyright (C) 2023 Google LLC
  */
+#include <linux/cfi_types.h>
 #include <linux/cfi.h>
 #include <asm/insn.h>
 
@@ -82,41 +83,11 @@ struct bpf_insn;
 /* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
 extern unsigned int __bpf_prog_runX(const void *ctx,
 				    const struct bpf_insn *insn);
-
-/*
- * Force a reference to the external symbol so the compiler generates
- * __kcfi_typid.
- */
-__ADDRESSABLE(__bpf_prog_runX);
-
-/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
-asm (
-"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
-"	.type	cfi_bpf_hash,@object				\n"
-"	.globl	cfi_bpf_hash					\n"
-"	.p2align	2, 0x0					\n"
-"cfi_bpf_hash:							\n"
-"	.word	__kcfi_typeid___bpf_prog_runX			\n"
-"	.size	cfi_bpf_hash, 4					\n"
-"	.popsection						\n"
-);
+DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX);
 
 /* Must match bpf_callback_t */
 extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
-
-__ADDRESSABLE(__bpf_callback_fn);
-
-/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
-asm (
-"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
-"	.type	cfi_bpf_subprog_hash,@object			\n"
-"	.globl	cfi_bpf_subprog_hash				\n"
-"	.p2align	2, 0x0					\n"
-"cfi_bpf_subprog_hash:						\n"
-"	.word	__kcfi_typeid___bpf_callback_fn			\n"
-"	.size	cfi_bpf_subprog_hash, 4				\n"
-"	.popsection						\n"
-);
+DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn);
 
 u32 cfi_get_func_hash(void *func)
 {
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ea1d984166cd..a555665b4d9c 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -2,6 +2,7 @@
 #define pr_fmt(fmt) "SMP alternatives: " fmt
 
 #include <linux/mmu_context.h>
+#include <linux/cfi_types.h>
 #include <linux/perf_event.h>
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
@@ -1189,37 +1190,11 @@ struct bpf_insn;
 /* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
 extern unsigned int __bpf_prog_runX(const void *ctx,
 				    const struct bpf_insn *insn);
-
-KCFI_REFERENCE(__bpf_prog_runX);
-
-/* u32 __ro_after_init cfi_bpf_hash = __kcfi_typeid___bpf_prog_runX; */
-asm (
-"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
-"	.type	cfi_bpf_hash,@object				\n"
-"	.globl	cfi_bpf_hash					\n"
-"	.p2align	2, 0x0					\n"
-"cfi_bpf_hash:							\n"
-"	.long	__kcfi_typeid___bpf_prog_runX			\n"
-"	.size	cfi_bpf_hash, 4					\n"
-"	.popsection						\n"
-);
+DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX);
 
 /* Must match bpf_callback_t */
 extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
-
-KCFI_REFERENCE(__bpf_callback_fn);
-
-/* u32 __ro_after_init cfi_bpf_subprog_hash = __kcfi_typeid___bpf_callback_fn; */
-asm (
-"	.pushsection	.data..ro_after_init,\"aw\",@progbits	\n"
-"	.type	cfi_bpf_subprog_hash,@object			\n"
-"	.globl	cfi_bpf_subprog_hash				\n"
-"	.p2align	2, 0x0					\n"
-"cfi_bpf_subprog_hash:						\n"
-"	.long	__kcfi_typeid___bpf_callback_fn			\n"
-"	.size	cfi_bpf_subprog_hash, 4				\n"
-"	.popsection						\n"
-);
+DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn);
 
 u32 cfi_get_func_hash(void *func)
 {
diff --git a/include/linux/cfi_types.h b/include/linux/cfi_types.h
index 6b8713675765..685f7181780f 100644
--- a/include/linux/cfi_types.h
+++ b/include/linux/cfi_types.h
@@ -41,5 +41,28 @@
 	SYM_TYPED_START(name, SYM_L_GLOBAL, SYM_A_ALIGN)
 #endif
 
+#else /* __ASSEMBLY__ */
+
+#ifdef CONFIG_CFI_CLANG
+#define DEFINE_CFI_TYPE(name, func)						\
+	/*									\
+	 * Force a reference to the function so the compiler generates		\
+	 * __kcfi_typeid_<func>.						\
+	 */									\
+	__ADDRESSABLE(func);							\
+	/* u32 name __ro_after_init = __kcfi_typeid_<func> */			\
+	extern u32 name;							\
+	asm (									\
+	"	.pushsection	.data..ro_after_init,\"aw\",\%progbits	\n"	\
+	"	.type	" #name ",\%object				\n"	\
+	"	.globl	" #name "					\n"	\
+	"	.p2align	2, 0x0					\n"	\
+	#name ":							\n"	\
+	"	.4byte	__kcfi_typeid_" #func "				\n"	\
+	"	.size	" #name ", 4					\n"	\
+	"	.popsection						\n"	\
+	);
+#endif
+
 #endif /* __ASSEMBLY__ */
 #endif /* _LINUX_CFI_TYPES_H */
-- 
cgit v1.2.3


From f1befc82addda926c8301436123d041bf3249505 Mon Sep 17 00:00:00 2001
From: Sami Tolvanen <samitolvanen@google.com>
Date: Fri, 1 Aug 2025 00:10:07 +0000
Subject: cfi: Move BPF CFI types and helpers to generic code

Instead of duplicating the same code for each architecture, move
the CFI type hash variables for BPF function types and related
helper functions to generic CFI code, and allow architectures to
override the function definitions if needed.

Signed-off-by: Sami Tolvanen <samitolvanen@google.com>
Link: https://lore.kernel.org/r/20250801001004.1859976-7-samitolvanen@google.com
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
---
 arch/riscv/include/asm/cfi.h  | 16 ---------------
 arch/riscv/kernel/cfi.c       | 24 ----------------------
 arch/x86/include/asm/cfi.h    | 10 ++-------
 arch/x86/kernel/alternative.c | 12 -----------
 include/linux/cfi.h           | 47 +++++++++++++++++++++++++++++++++++--------
 kernel/cfi.c                  | 15 ++++++++++++++
 6 files changed, 56 insertions(+), 68 deletions(-)

(limited to 'include/linux')

diff --git a/arch/riscv/include/asm/cfi.h b/arch/riscv/include/asm/cfi.h
index fb9696d7a3f2..4508aaa7a2fd 100644
--- a/arch/riscv/include/asm/cfi.h
+++ b/arch/riscv/include/asm/cfi.h
@@ -14,27 +14,11 @@ struct pt_regs;
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
 #define __bpfcall
-static inline int cfi_get_offset(void)
-{
-	return 4;
-}
-
-#define cfi_get_offset cfi_get_offset
-extern u32 cfi_bpf_hash;
-extern u32 cfi_bpf_subprog_hash;
-extern u32 cfi_get_func_hash(void *func);
 #else
 static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
 	return BUG_TRAP_TYPE_NONE;
 }
-
-#define cfi_bpf_hash 0U
-#define cfi_bpf_subprog_hash 0U
-static inline u32 cfi_get_func_hash(void *func)
-{
-	return 0;
-}
 #endif /* CONFIG_CFI_CLANG */
 
 #endif /* _ASM_RISCV_CFI_H */
diff --git a/arch/riscv/kernel/cfi.c b/arch/riscv/kernel/cfi.c
index e7aec5f36dd5..6ec9dbd7292e 100644
--- a/arch/riscv/kernel/cfi.c
+++ b/arch/riscv/kernel/cfi.c
@@ -4,7 +4,6 @@
  *
  * Copyright (C) 2023 Google LLC
  */
-#include <linux/cfi_types.h>
 #include <linux/cfi.h>
 #include <asm/insn.h>
 
@@ -76,26 +75,3 @@ enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 
 	return report_cfi_failure(regs, regs->epc, &target, type);
 }
-
-#ifdef CONFIG_CFI_CLANG
-struct bpf_insn;
-
-/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
-extern unsigned int __bpf_prog_runX(const void *ctx,
-				    const struct bpf_insn *insn);
-DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX);
-
-/* Must match bpf_callback_t */
-extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
-DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn);
-
-u32 cfi_get_func_hash(void *func)
-{
-	u32 hash;
-
-	if (get_kernel_nofault(hash, func - cfi_get_offset()))
-		return 0;
-
-	return hash;
-}
-#endif
diff --git a/arch/x86/include/asm/cfi.h b/arch/x86/include/asm/cfi.h
index 3e51ba459154..1751f1eb95ef 100644
--- a/arch/x86/include/asm/cfi.h
+++ b/arch/x86/include/asm/cfi.h
@@ -116,8 +116,6 @@ struct pt_regs;
 #ifdef CONFIG_CFI_CLANG
 enum bug_trap_type handle_cfi_failure(struct pt_regs *regs);
 #define __bpfcall
-extern u32 cfi_bpf_hash;
-extern u32 cfi_bpf_subprog_hash;
 
 static inline int cfi_get_offset(void)
 {
@@ -135,6 +133,8 @@ static inline int cfi_get_offset(void)
 #define cfi_get_offset cfi_get_offset
 
 extern u32 cfi_get_func_hash(void *func);
+#define cfi_get_func_hash cfi_get_func_hash
+
 extern int cfi_get_func_arity(void *func);
 
 #ifdef CONFIG_FINEIBT
@@ -153,12 +153,6 @@ static inline enum bug_trap_type handle_cfi_failure(struct pt_regs *regs)
 {
 	return BUG_TRAP_TYPE_NONE;
 }
-#define cfi_bpf_hash 0U
-#define cfi_bpf_subprog_hash 0U
-static inline u32 cfi_get_func_hash(void *func)
-{
-	return 0;
-}
 static inline int cfi_get_func_arity(void *func)
 {
 	return 0;
diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index a555665b4d9c..9f6b7dab2d9a 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -2,7 +2,6 @@
 #define pr_fmt(fmt) "SMP alternatives: " fmt
 
 #include <linux/mmu_context.h>
-#include <linux/cfi_types.h>
 #include <linux/perf_event.h>
 #include <linux/vmalloc.h>
 #include <linux/memory.h>
@@ -1185,17 +1184,6 @@ bool cfi_bhi __ro_after_init = false;
 #endif
 
 #ifdef CONFIG_CFI_CLANG
-struct bpf_insn;
-
-/* Must match bpf_func_t / DEFINE_BPF_PROG_RUN() */
-extern unsigned int __bpf_prog_runX(const void *ctx,
-				    const struct bpf_insn *insn);
-DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX);
-
-/* Must match bpf_callback_t */
-extern u64 __bpf_callback_fn(u64, u64, u64, u64, u64);
-DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn);
-
 u32 cfi_get_func_hash(void *func)
 {
 	u32 hash;
diff --git a/include/linux/cfi.h b/include/linux/cfi.h
index 1db17ecbb86c..52a98886a455 100644
--- a/include/linux/cfi.h
+++ b/include/linux/cfi.h
@@ -11,16 +11,9 @@
 #include <linux/module.h>
 #include <asm/cfi.h>
 
+#ifdef CONFIG_CFI_CLANG
 extern bool cfi_warn;
 
-#ifndef cfi_get_offset
-static inline int cfi_get_offset(void)
-{
-	return 0;
-}
-#endif
-
-#ifdef CONFIG_CFI_CLANG
 enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
 				      unsigned long *target, u32 type);
 
@@ -29,6 +22,44 @@ static inline enum bug_trap_type report_cfi_failure_noaddr(struct pt_regs *regs,
 {
 	return report_cfi_failure(regs, addr, NULL, 0);
 }
+
+#ifndef cfi_get_offset
+/*
+ * Returns the CFI prefix offset. By default, the compiler emits only
+ * a 4-byte CFI type hash before the function. If an architecture
+ * uses -fpatchable-function-entry=N,M where M>0 to change the prefix
+ * offset, they must override this function.
+ */
+static inline int cfi_get_offset(void)
+{
+	return 4;
+}
+#endif
+
+#ifndef cfi_get_func_hash
+static inline u32 cfi_get_func_hash(void *func)
+{
+	u32 hash;
+
+	if (get_kernel_nofault(hash, func - cfi_get_offset()))
+		return 0;
+
+	return hash;
+}
+#endif
+
+/* CFI type hashes for BPF function types */
+extern u32 cfi_bpf_hash;
+extern u32 cfi_bpf_subprog_hash;
+
+#else /* CONFIG_CFI_CLANG */
+
+static inline int cfi_get_offset(void) { return 0; }
+static inline u32 cfi_get_func_hash(void *func) { return 0; }
+
+#define cfi_bpf_hash 0U
+#define cfi_bpf_subprog_hash 0U
+
 #endif /* CONFIG_CFI_CLANG */
 
 #ifdef CONFIG_ARCH_USES_CFI_TRAPS
diff --git a/kernel/cfi.c b/kernel/cfi.c
index 422fa4f958ae..4dad04ead06c 100644
--- a/kernel/cfi.c
+++ b/kernel/cfi.c
@@ -5,6 +5,8 @@
  * Copyright (C) 2022 Google LLC
  */
 
+#include <linux/bpf.h>
+#include <linux/cfi_types.h>
 #include <linux/cfi.h>
 
 bool cfi_warn __ro_after_init = IS_ENABLED(CONFIG_CFI_PERMISSIVE);
@@ -27,6 +29,19 @@ enum bug_trap_type report_cfi_failure(struct pt_regs *regs, unsigned long addr,
 	return BUG_TRAP_TYPE_BUG;
 }
 
+/*
+ * Declare two non-existent functions with types that match bpf_func_t and
+ * bpf_callback_t pointers, and use DEFINE_CFI_TYPE to define type hash
+ * variables for each function type. The cfi_bpf_* variables are used by
+ * arch-specific BPF JIT implementations to ensure indirectly callable JIT
+ * code has matching CFI type hashes.
+ */
+extern typeof(*(bpf_func_t)0) __bpf_prog_runX;
+DEFINE_CFI_TYPE(cfi_bpf_hash, __bpf_prog_runX);
+
+extern typeof(*(bpf_callback_t)0) __bpf_callback_fn;
+DEFINE_CFI_TYPE(cfi_bpf_subprog_hash, __bpf_callback_fn);
+
 #ifdef CONFIG_ARCH_USES_CFI_TRAPS
 static inline unsigned long trap_address(s32 *p)
 {
-- 
cgit v1.2.3


From 564a69ad90d15c782176e1a8c9e1c95661e1aed0 Mon Sep 17 00:00:00 2001
From: Viresh Kumar <viresh.kumar@linaro.org>
Date: Wed, 21 May 2025 17:03:46 +0530
Subject: virtio-mmio: Remove virtqueue list from mmio device

The MMIO transport implementation creates a list of virtqueues for a
virtio device, while the same is already available in the struct
virtio_device.

Don't create a duplicate list, and use the other one instead.

While at it, fix the virtio_device_for_each_vq() macro to accept an
argument like "&vm_dev->vdev" (which currently fails to build).

Signed-off-by: Viresh Kumar <viresh.kumar@linaro.org>
Message-Id: <3e56c6f74002987e22f364d883cbad177cd9ad9c.1747827066.git.viresh.kumar@linaro.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
---
 drivers/virtio/virtio_mmio.c | 52 +++-----------------------------------------
 include/linux/virtio.h       |  2 +-
 2 files changed, 4 insertions(+), 50 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/virtio/virtio_mmio.c b/drivers/virtio/virtio_mmio.c
index 5d78c2d572ab..b152a1eca05a 100644
--- a/drivers/virtio/virtio_mmio.c
+++ b/drivers/virtio/virtio_mmio.c
@@ -65,7 +65,6 @@
 #include <linux/platform_device.h>
 #include <linux/pm.h>
 #include <linux/slab.h>
-#include <linux/spinlock.h>
 #include <linux/virtio.h>
 #include <linux/virtio_config.h>
 #include <uapi/linux/virtio_mmio.h>
@@ -88,22 +87,8 @@ struct virtio_mmio_device {
 
 	void __iomem *base;
 	unsigned long version;
-
-	/* a list of queues so we can dispatch IRQs */
-	spinlock_t lock;
-	struct list_head virtqueues;
-};
-
-struct virtio_mmio_vq_info {
-	/* the actual virtqueue */
-	struct virtqueue *vq;
-
-	/* the list node for the virtqueues list */
-	struct list_head node;
 };
 
-
-
 /* Configuration interface */
 
 static u64 vm_get_features(struct virtio_device *vdev)
@@ -300,9 +285,8 @@ static bool vm_notify_with_data(struct virtqueue *vq)
 static irqreturn_t vm_interrupt(int irq, void *opaque)
 {
 	struct virtio_mmio_device *vm_dev = opaque;
-	struct virtio_mmio_vq_info *info;
+	struct virtqueue *vq;
 	unsigned long status;
-	unsigned long flags;
 	irqreturn_t ret = IRQ_NONE;
 
 	/* Read and acknowledge interrupts */
@@ -315,10 +299,8 @@ static irqreturn_t vm_interrupt(int irq, void *opaque)
 	}
 
 	if (likely(status & VIRTIO_MMIO_INT_VRING)) {
-		spin_lock_irqsave(&vm_dev->lock, flags);
-		list_for_each_entry(info, &vm_dev->virtqueues, node)
-			ret |= vring_interrupt(irq, info->vq);
-		spin_unlock_irqrestore(&vm_dev->lock, flags);
+		virtio_device_for_each_vq(&vm_dev->vdev, vq)
+			ret |= vring_interrupt(irq, vq);
 	}
 
 	return ret;
@@ -329,14 +311,8 @@ static irqreturn_t vm_interrupt(int irq, void *opaque)
 static void vm_del_vq(struct virtqueue *vq)
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vq->vdev);
-	struct virtio_mmio_vq_info *info = vq->priv;
-	unsigned long flags;
 	unsigned int index = vq->index;
 
-	spin_lock_irqsave(&vm_dev->lock, flags);
-	list_del(&info->node);
-	spin_unlock_irqrestore(&vm_dev->lock, flags);
-
 	/* Select and deactivate the queue */
 	writel(index, vm_dev->base + VIRTIO_MMIO_QUEUE_SEL);
 	if (vm_dev->version == 1) {
@@ -347,8 +323,6 @@ static void vm_del_vq(struct virtqueue *vq)
 	}
 
 	vring_del_virtqueue(vq);
-
-	kfree(info);
 }
 
 static void vm_del_vqs(struct virtio_device *vdev)
@@ -375,9 +349,7 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in
 {
 	struct virtio_mmio_device *vm_dev = to_virtio_mmio_device(vdev);
 	bool (*notify)(struct virtqueue *vq);
-	struct virtio_mmio_vq_info *info;
 	struct virtqueue *vq;
-	unsigned long flags;
 	unsigned int num;
 	int err;
 
@@ -399,13 +371,6 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in
 		goto error_available;
 	}
 
-	/* Allocate and fill out our active queue description */
-	info = kmalloc(sizeof(*info), GFP_KERNEL);
-	if (!info) {
-		err = -ENOMEM;
-		goto error_kmalloc;
-	}
-
 	num = readl(vm_dev->base + VIRTIO_MMIO_QUEUE_NUM_MAX);
 	if (num == 0) {
 		err = -ENOENT;
@@ -463,13 +428,6 @@ static struct virtqueue *vm_setup_vq(struct virtio_device *vdev, unsigned int in
 		writel(1, vm_dev->base + VIRTIO_MMIO_QUEUE_READY);
 	}
 
-	vq->priv = info;
-	info->vq = vq;
-
-	spin_lock_irqsave(&vm_dev->lock, flags);
-	list_add(&info->node, &vm_dev->virtqueues);
-	spin_unlock_irqrestore(&vm_dev->lock, flags);
-
 	return vq;
 
 error_bad_pfn:
@@ -481,8 +439,6 @@ error_new_virtqueue:
 		writel(0, vm_dev->base + VIRTIO_MMIO_QUEUE_READY);
 		WARN_ON(readl(vm_dev->base + VIRTIO_MMIO_QUEUE_READY));
 	}
-	kfree(info);
-error_kmalloc:
 error_available:
 	return ERR_PTR(err);
 }
@@ -627,8 +583,6 @@ static int virtio_mmio_probe(struct platform_device *pdev)
 	vm_dev->vdev.dev.release = virtio_mmio_release_dev;
 	vm_dev->vdev.config = &virtio_mmio_config_ops;
 	vm_dev->pdev = pdev;
-	INIT_LIST_HEAD(&vm_dev->virtqueues);
-	spin_lock_init(&vm_dev->lock);
 
 	vm_dev->base = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(vm_dev->base)) {
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index 64cb4b04be7a..8b745ce0cf5f 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -196,7 +196,7 @@ int virtio_device_reset_done(struct virtio_device *dev);
 size_t virtio_max_dma_size(const struct virtio_device *vdev);
 
 #define virtio_device_for_each_vq(vdev, vq) \
-	list_for_each_entry(vq, &vdev->vqs, list)
+	list_for_each_entry(vq, &(vdev)->vqs, list)
 
 /**
  * struct virtio_driver - operations for a virtio I/O driver
-- 
cgit v1.2.3


From 569c392e191361cd05fba1fd87ed02ef0d130ef7 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 17 Jun 2025 01:18:36 +0100
Subject: vhost: vringh: Remove unused iotlb functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The functions:
  vringh_abandon_iotlb()
  vringh_notify_disable_iotlb() and
  vringh_notify_enable_iotlb()

were added in 2020 by
commit 9ad9c49cfe97 ("vringh: IOTLB support")
but have remained unused.

Remove them.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Message-Id: <20250617001838.114457-2-linux@treblig.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
---
 drivers/vhost/vringh.c | 43 -------------------------------------------
 include/linux/vringh.h |  5 -----
 2 files changed, 48 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index bbce65452701..67a028d6fb5f 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -1534,23 +1534,6 @@ ssize_t vringh_iov_push_iotlb(struct vringh *vrh,
 }
 EXPORT_SYMBOL(vringh_iov_push_iotlb);
 
-/**
- * vringh_abandon_iotlb - we've decided not to handle the descriptor(s).
- * @vrh: the vring.
- * @num: the number of descriptors to put back (ie. num
- *	 vringh_get_iotlb() to undo).
- *
- * The next vringh_get_iotlb() will return the old descriptor(s) again.
- */
-void vringh_abandon_iotlb(struct vringh *vrh, unsigned int num)
-{
-	/* We only update vring_avail_event(vr) when we want to be notified,
-	 * so we haven't changed that yet.
-	 */
-	vrh->last_avail_idx -= num;
-}
-EXPORT_SYMBOL(vringh_abandon_iotlb);
-
 /**
  * vringh_complete_iotlb - we've finished with descriptor, publish it.
  * @vrh: the vring.
@@ -1571,32 +1554,6 @@ int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len)
 }
 EXPORT_SYMBOL(vringh_complete_iotlb);
 
-/**
- * vringh_notify_enable_iotlb - we want to know if something changes.
- * @vrh: the vring.
- *
- * This always enables notifications, but returns false if there are
- * now more buffers available in the vring.
- */
-bool vringh_notify_enable_iotlb(struct vringh *vrh)
-{
-	return __vringh_notify_enable(vrh, getu16_iotlb, putu16_iotlb);
-}
-EXPORT_SYMBOL(vringh_notify_enable_iotlb);
-
-/**
- * vringh_notify_disable_iotlb - don't tell us if something changes.
- * @vrh: the vring.
- *
- * This is our normal running state: we disable and then only enable when
- * we're going to sleep.
- */
-void vringh_notify_disable_iotlb(struct vringh *vrh)
-{
-	__vringh_notify_disable(vrh, putu16_iotlb);
-}
-EXPORT_SYMBOL(vringh_notify_disable_iotlb);
-
 /**
  * vringh_need_notify_iotlb - must we tell the other side about used buffers?
  * @vrh: the vring we've called vringh_complete_iotlb() on.
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
index c3a8117dabe8..af8bd2695a7b 100644
--- a/include/linux/vringh.h
+++ b/include/linux/vringh.h
@@ -319,13 +319,8 @@ ssize_t vringh_iov_push_iotlb(struct vringh *vrh,
 			      struct vringh_kiov *wiov,
 			      const void *src, size_t len);
 
-void vringh_abandon_iotlb(struct vringh *vrh, unsigned int num);
-
 int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len);
 
-bool vringh_notify_enable_iotlb(struct vringh *vrh);
-void vringh_notify_disable_iotlb(struct vringh *vrh);
-
 int vringh_need_notify_iotlb(struct vringh *vrh);
 
 #endif /* CONFIG_VHOST_IOTLB */
-- 
cgit v1.2.3


From 6e9ef6937c726b97d4a6d49332d06e999acc15f5 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Tue, 17 Jun 2025 01:18:37 +0100
Subject: vhost: vringh: Remove unused functions
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

The functions:
  vringh_abandon_kern()
  vringh_abandon_user()
  vringh_iov_pull_kern() and
  vringh_iov_push_kern()
were all added in 2013 by
commit f87d0fbb5798 ("vringh: host-side implementation of virtio rings.")
but have remained unused.

Remove them and the two helper functions they used.

Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Message-Id: <20250617001838.114457-3-linux@treblig.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Eugenio Pérez <eperezma@redhat.com>
Tested-by: Lei Yang <leiyang@redhat.com>
Reviewed-by: Simon Horman <horms@kernel.org>
---
 drivers/vhost/vringh.c | 75 --------------------------------------------------
 include/linux/vringh.h |  7 -----
 2 files changed, 82 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vringh.c b/drivers/vhost/vringh.c
index 67a028d6fb5f..9f27c3f6091b 100644
--- a/drivers/vhost/vringh.c
+++ b/drivers/vhost/vringh.c
@@ -779,22 +779,6 @@ ssize_t vringh_iov_push_user(struct vringh_iov *wiov,
 }
 EXPORT_SYMBOL(vringh_iov_push_user);
 
-/**
- * vringh_abandon_user - we've decided not to handle the descriptor(s).
- * @vrh: the vring.
- * @num: the number of descriptors to put back (ie. num
- *	 vringh_get_user() to undo).
- *
- * The next vringh_get_user() will return the old descriptor(s) again.
- */
-void vringh_abandon_user(struct vringh *vrh, unsigned int num)
-{
-	/* We only update vring_avail_event(vr) when we want to be notified,
-	 * so we haven't changed that yet. */
-	vrh->last_avail_idx -= num;
-}
-EXPORT_SYMBOL(vringh_abandon_user);
-
 /**
  * vringh_complete_user - we've finished with descriptor, publish it.
  * @vrh: the vring.
@@ -900,20 +884,6 @@ static inline int putused_kern(const struct vringh *vrh,
 	return 0;
 }
 
-static inline int xfer_kern(const struct vringh *vrh, void *src,
-			    void *dst, size_t len)
-{
-	memcpy(dst, src, len);
-	return 0;
-}
-
-static inline int kern_xfer(const struct vringh *vrh, void *dst,
-			    void *src, size_t len)
-{
-	memcpy(dst, src, len);
-	return 0;
-}
-
 /**
  * vringh_init_kern - initialize a vringh for a kernelspace vring.
  * @vrh: the vringh to initialize.
@@ -998,51 +968,6 @@ int vringh_getdesc_kern(struct vringh *vrh,
 }
 EXPORT_SYMBOL(vringh_getdesc_kern);
 
-/**
- * vringh_iov_pull_kern - copy bytes from vring_iov.
- * @riov: the riov as passed to vringh_getdesc_kern() (updated as we consume)
- * @dst: the place to copy.
- * @len: the maximum length to copy.
- *
- * Returns the bytes copied <= len or a negative errno.
- */
-ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len)
-{
-	return vringh_iov_xfer(NULL, riov, dst, len, xfer_kern);
-}
-EXPORT_SYMBOL(vringh_iov_pull_kern);
-
-/**
- * vringh_iov_push_kern - copy bytes into vring_iov.
- * @wiov: the wiov as passed to vringh_getdesc_kern() (updated as we consume)
- * @src: the place to copy from.
- * @len: the maximum length to copy.
- *
- * Returns the bytes copied <= len or a negative errno.
- */
-ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
-			     const void *src, size_t len)
-{
-	return vringh_iov_xfer(NULL, wiov, (void *)src, len, kern_xfer);
-}
-EXPORT_SYMBOL(vringh_iov_push_kern);
-
-/**
- * vringh_abandon_kern - we've decided not to handle the descriptor(s).
- * @vrh: the vring.
- * @num: the number of descriptors to put back (ie. num
- *	 vringh_get_kern() to undo).
- *
- * The next vringh_get_kern() will return the old descriptor(s) again.
- */
-void vringh_abandon_kern(struct vringh *vrh, unsigned int num)
-{
-	/* We only update vring_avail_event(vr) when we want to be notified,
-	 * so we haven't changed that yet. */
-	vrh->last_avail_idx -= num;
-}
-EXPORT_SYMBOL(vringh_abandon_kern);
-
 /**
  * vringh_complete_kern - we've finished with descriptor, publish it.
  * @vrh: the vring.
diff --git a/include/linux/vringh.h b/include/linux/vringh.h
index af8bd2695a7b..49e7cbc9697a 100644
--- a/include/linux/vringh.h
+++ b/include/linux/vringh.h
@@ -175,9 +175,6 @@ int vringh_complete_multi_user(struct vringh *vrh,
 			       const struct vring_used_elem used[],
 			       unsigned num_used);
 
-/* Pretend we've never seen descriptor (for easy error handling). */
-void vringh_abandon_user(struct vringh *vrh, unsigned int num);
-
 /* Do we need to fire the eventfd to notify the other side? */
 int vringh_need_notify_user(struct vringh *vrh);
 
@@ -235,10 +232,6 @@ int vringh_getdesc_kern(struct vringh *vrh,
 			u16 *head,
 			gfp_t gfp);
 
-ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len);
-ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
-			     const void *src, size_t len);
-void vringh_abandon_kern(struct vringh *vrh, unsigned int num);
 int vringh_complete_kern(struct vringh *vrh, u16 head, u32 len);
 
 bool vringh_notify_enable_kern(struct vringh *vrh);
-- 
cgit v1.2.3


From 87dbae5e36613a6020f3d64a2eaeac0a1e0e6dc6 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 17 Jul 2025 10:01:10 +0100
Subject: vsock/virtio: Move length check to callers of
 virtio_vsock_skb_rx_put()

virtio_vsock_skb_rx_put() only calls skb_put() if the length in the
packet header is not zero even though skb_put() handles this case
gracefully.

Remove the functionally redundant check from virtio_vsock_skb_rx_put()
and, on the assumption that this is a worthwhile optimisation for
handling credit messages, augment the existing length checks in
virtio_transport_rx_work() to elide the call for zero-length payloads.
Since the callers all have the length, extend virtio_vsock_skb_rx_put()
to take it as an additional parameter rather than fish it back out of
the packet header.

Note that the vhost code already has similar logic in
vhost_vsock_alloc_skb().

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Will Deacon <will@kernel.org>
Message-Id: <20250717090116.11987-4-will@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vsock.c            | 2 +-
 include/linux/virtio_vsock.h     | 9 ++-------
 net/vmw_vsock/virtio_transport.c | 4 +++-
 3 files changed, 6 insertions(+), 9 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 66a0f060770e..4c4a642945eb 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -375,7 +375,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
 		return NULL;
 	}
 
-	virtio_vsock_skb_rx_put(skb);
+	virtio_vsock_skb_rx_put(skb, payload_len);
 
 	nbytes = copy_from_iter(skb->data, payload_len, &iov_iter);
 	if (nbytes != payload_len) {
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 36fb3edfa403..97465f378ade 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -47,14 +47,9 @@ static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb)
 	VIRTIO_VSOCK_SKB_CB(skb)->tap_delivered = false;
 }
 
-static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb)
+static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len)
 {
-	u32 len;
-
-	len = le32_to_cpu(virtio_vsock_hdr(skb)->len);
-
-	if (len > 0)
-		skb_put(skb, len);
+	skb_put(skb, len);
 }
 
 static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask)
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index eb08a393413d..0166919f8705 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -656,7 +656,9 @@ static void virtio_transport_rx_work(struct work_struct *work)
 				continue;
 			}
 
-			virtio_vsock_skb_rx_put(skb);
+			if (payload_len)
+				virtio_vsock_skb_rx_put(skb, payload_len);
+
 			virtio_transport_deliver_tap_pkt(skb);
 			virtio_transport_recv_pkt(&virtio_transport, skb);
 		}
-- 
cgit v1.2.3


From 03a92f036a04fed2b00d69f5f46f1a486e70dc5c Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 17 Jul 2025 10:01:11 +0100
Subject: vsock/virtio: Resize receive buffers so that each SKB fits in a 4K
 page

When allocating receive buffers for the vsock virtio RX virtqueue, an
SKB is allocated with a 4140 data payload (the 44-byte packet header +
VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE). Even when factoring in the SKB
overhead, the resulting 8KiB allocation thanks to the rounding in
kmalloc_reserve() is wasteful (~3700 unusable bytes) and results in a
higher-order page allocation on systems with 4KiB pages just for the
sake of a few hundred bytes of packet data.

Limit the vsock virtio RX buffers to 4KiB per SKB, resulting in much
better memory utilisation and removing the need to allocate higher-order
pages entirely.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Will Deacon <will@kernel.org>
Message-Id: <20250717090116.11987-5-will@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 include/linux/virtio_vsock.h     | 7 ++++++-
 net/vmw_vsock/virtio_transport.c | 2 +-
 2 files changed, 7 insertions(+), 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 97465f378ade..879f1dfa7d3a 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -106,7 +106,12 @@ static inline size_t virtio_vsock_skb_len(struct sk_buff *skb)
 	return (size_t)(skb_end_pointer(skb) - skb->head);
 }
 
-#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE	(1024 * 4)
+/* Dimension the RX SKB so that the entire thing fits exactly into
+ * a single 4KiB page. This avoids wasting memory due to alloc_skb()
+ * rounding up to the next page order and also means that we
+ * don't leave higher-order pages sitting around in the RX queue.
+ */
+#define VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE	SKB_WITH_OVERHEAD(1024 * 4)
 #define VIRTIO_VSOCK_MAX_BUF_SIZE		0xFFFFFFFFUL
 #define VIRTIO_VSOCK_MAX_PKT_BUF_SIZE		(1024 * 64)
 
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 0166919f8705..39f346890f7f 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -307,7 +307,7 @@ out_rcu:
 
 static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
 {
-	int total_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM;
+	int total_len = VIRTIO_VSOCK_DEFAULT_RX_BUF_SIZE;
 	struct scatterlist pkt, *p;
 	struct virtqueue *vq;
 	struct sk_buff *skb;
-- 
cgit v1.2.3


From 2304c64a2866c58534560c63dc6e79d09b8f8d8d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 17 Jul 2025 10:01:12 +0100
Subject: vsock/virtio: Rename virtio_vsock_alloc_skb()

In preparation for nonlinear allocations for large SKBs, rename
virtio_vsock_alloc_skb() to virtio_vsock_alloc_linear_skb() to indicate
that it returns linear SKBs unconditionally and switch all callers over
to this new interface for now.

No functional change.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Will Deacon <will@kernel.org>
Message-Id: <20250717090116.11987-6-will@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vsock.c                   | 2 +-
 include/linux/virtio_vsock.h            | 3 ++-
 net/vmw_vsock/virtio_transport.c        | 2 +-
 net/vmw_vsock/virtio_transport_common.c | 2 +-
 4 files changed, 5 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 4c4a642945eb..1ad96613680e 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -348,7 +348,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
 		return NULL;
 
 	/* len contains both payload and hdr */
-	skb = virtio_vsock_alloc_skb(len, GFP_KERNEL);
+	skb = virtio_vsock_alloc_linear_skb(len, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 879f1dfa7d3a..4504ea29ff82 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -52,7 +52,8 @@ static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len)
 	skb_put(skb, len);
 }
 
-static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask)
+static inline struct sk_buff *
+virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask)
 {
 	struct sk_buff *skb;
 
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 39f346890f7f..80dcf6ac1e72 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -316,7 +316,7 @@ static void virtio_vsock_rx_fill(struct virtio_vsock *vsock)
 	vq = vsock->vqs[VSOCK_VQ_RX];
 
 	do {
-		skb = virtio_vsock_alloc_skb(total_len, GFP_KERNEL);
+		skb = virtio_vsock_alloc_linear_skb(total_len, GFP_KERNEL);
 		if (!skb)
 			break;
 
diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c
index 1b5d9896edae..c9eb7f7ac00d 100644
--- a/net/vmw_vsock/virtio_transport_common.c
+++ b/net/vmw_vsock/virtio_transport_common.c
@@ -261,7 +261,7 @@ static struct sk_buff *virtio_transport_alloc_skb(struct virtio_vsock_pkt_info *
 	if (!zcopy)
 		skb_len += payload_len;
 
-	skb = virtio_vsock_alloc_skb(skb_len, GFP_KERNEL);
+	skb = virtio_vsock_alloc_linear_skb(skb_len, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
-- 
cgit v1.2.3


From fac6b82e0f3eaca33c8c67ec401681b21143ae17 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 17 Jul 2025 10:01:13 +0100
Subject: vsock/virtio: Move SKB allocation lower-bound check to callers

virtio_vsock_alloc_linear_skb() checks that the requested size is at
least big enough for the packet header (VIRTIO_VSOCK_SKB_HEADROOM).

Of the three callers of virtio_vsock_alloc_linear_skb(), only
vhost_vsock_alloc_skb() can potentially pass a packet smaller than the
header size and, as it already has a check against the maximum packet
size, extend its bounds checking to consider the minimum packet size
and remove the check from virtio_vsock_alloc_linear_skb().

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Will Deacon <will@kernel.org>
Message-Id: <20250717090116.11987-7-will@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vsock.c        | 3 ++-
 include/linux/virtio_vsock.h | 3 ---
 2 files changed, 2 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 1ad96613680e..24b7547b05a6 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -344,7 +344,8 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
 
 	len = iov_length(vq->iov, out);
 
-	if (len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM)
+	if (len < VIRTIO_VSOCK_SKB_HEADROOM ||
+	    len > VIRTIO_VSOCK_MAX_PKT_BUF_SIZE + VIRTIO_VSOCK_SKB_HEADROOM)
 		return NULL;
 
 	/* len contains both payload and hdr */
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 4504ea29ff82..36dd0cd55368 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -57,9 +57,6 @@ virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask)
 {
 	struct sk_buff *skb;
 
-	if (size < VIRTIO_VSOCK_SKB_HEADROOM)
-		return NULL;
-
 	skb = alloc_skb(size, mask);
 	if (!skb)
 		return NULL;
-- 
cgit v1.2.3


From ab9aa2f3afc2713c14f6c4c6b90c9a0933b837f1 Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 17 Jul 2025 10:01:14 +0100
Subject: vhost/vsock: Allocate nonlinear SKBs for handling large receive
 buffers

When receiving a packet from a guest, vhost_vsock_handle_tx_kick()
calls vhost_vsock_alloc_linear_skb() to allocate and fill an SKB with
the receive data. Unfortunately, these are always linear allocations and
can therefore result in significant pressure on kmalloc() considering
that the maximum packet size (VIRTIO_VSOCK_MAX_PKT_BUF_SIZE +
VIRTIO_VSOCK_SKB_HEADROOM) is a little over 64KiB, resulting in a 128KiB
allocation for each packet.

Rework the vsock SKB allocation so that, for sizes with page order
greater than PAGE_ALLOC_COSTLY_ORDER, a nonlinear SKB is allocated
instead with the packet header in the SKB and the receive data in the
fragments. Finally, add a debug warning if virtio_vsock_skb_rx_put() is
ever called on an SKB with a non-zero length, as this would be
destructive for the nonlinear case.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Will Deacon <will@kernel.org>
Message-Id: <20250717090116.11987-8-will@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vsock.c        |  8 +++-----
 include/linux/virtio_vsock.h | 32 +++++++++++++++++++++++++++++---
 2 files changed, 32 insertions(+), 8 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 24b7547b05a6..0679a706ebc0 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -349,7 +349,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
 		return NULL;
 
 	/* len contains both payload and hdr */
-	skb = virtio_vsock_alloc_linear_skb(len, GFP_KERNEL);
+	skb = virtio_vsock_alloc_skb(len, GFP_KERNEL);
 	if (!skb)
 		return NULL;
 
@@ -378,10 +378,8 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
 
 	virtio_vsock_skb_rx_put(skb, payload_len);
 
-	nbytes = copy_from_iter(skb->data, payload_len, &iov_iter);
-	if (nbytes != payload_len) {
-		vq_err(vq, "Expected %zu byte payload, got %zu bytes\n",
-		       payload_len, nbytes);
+	if (skb_copy_datagram_from_iter(skb, 0, &iov_iter, payload_len)) {
+		vq_err(vq, "Failed to copy %zu byte payload\n", payload_len);
 		kfree_skb(skb);
 		return NULL;
 	}
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index 36dd0cd55368..fa5934ea9c81 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -49,22 +49,48 @@ static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb)
 
 static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len)
 {
-	skb_put(skb, len);
+	DEBUG_NET_WARN_ON_ONCE(skb->len);
+
+	if (skb_is_nonlinear(skb))
+		skb->len = len;
+	else
+		skb_put(skb, len);
 }
 
 static inline struct sk_buff *
-virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask)
+__virtio_vsock_alloc_skb_with_frags(unsigned int header_len,
+				    unsigned int data_len,
+				    gfp_t mask)
 {
 	struct sk_buff *skb;
+	int err;
 
-	skb = alloc_skb(size, mask);
+	skb = alloc_skb_with_frags(header_len, data_len,
+				   PAGE_ALLOC_COSTLY_ORDER, &err, mask);
 	if (!skb)
 		return NULL;
 
 	skb_reserve(skb, VIRTIO_VSOCK_SKB_HEADROOM);
+	skb->data_len = data_len;
 	return skb;
 }
 
+static inline struct sk_buff *
+virtio_vsock_alloc_linear_skb(unsigned int size, gfp_t mask)
+{
+	return __virtio_vsock_alloc_skb_with_frags(size, 0, mask);
+}
+
+static inline struct sk_buff *virtio_vsock_alloc_skb(unsigned int size, gfp_t mask)
+{
+	if (size <= SKB_WITH_OVERHEAD(PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		return virtio_vsock_alloc_linear_skb(size, mask);
+
+	size -= VIRTIO_VSOCK_SKB_HEADROOM;
+	return __virtio_vsock_alloc_skb_with_frags(VIRTIO_VSOCK_SKB_HEADROOM,
+						   size, mask);
+}
+
 static inline void
 virtio_vsock_skb_queue_head(struct sk_buff_head *list, struct sk_buff *skb)
 {
-- 
cgit v1.2.3


From 8ca76151d2c8219edea82f1925a2a25907ff6a9d Mon Sep 17 00:00:00 2001
From: Will Deacon <will@kernel.org>
Date: Thu, 17 Jul 2025 10:01:15 +0100
Subject: vsock/virtio: Rename virtio_vsock_skb_rx_put()

In preparation for using virtio_vsock_skb_rx_put() when populating SKBs
on the vsock TX path, rename virtio_vsock_skb_rx_put() to
virtio_vsock_skb_put().

No functional change.

Reviewed-by: Stefano Garzarella <sgarzare@redhat.com>
Signed-off-by: Will Deacon <will@kernel.org>
Message-Id: <20250717090116.11987-9-will@kernel.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
 drivers/vhost/vsock.c            | 2 +-
 include/linux/virtio_vsock.h     | 2 +-
 net/vmw_vsock/virtio_transport.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
index 0679a706ebc0..ae01457ea2cd 100644
--- a/drivers/vhost/vsock.c
+++ b/drivers/vhost/vsock.c
@@ -376,7 +376,7 @@ vhost_vsock_alloc_skb(struct vhost_virtqueue *vq,
 		return NULL;
 	}
 
-	virtio_vsock_skb_rx_put(skb, payload_len);
+	virtio_vsock_skb_put(skb, payload_len);
 
 	if (skb_copy_datagram_from_iter(skb, 0, &iov_iter, payload_len)) {
 		vq_err(vq, "Failed to copy %zu byte payload\n", payload_len);
diff --git a/include/linux/virtio_vsock.h b/include/linux/virtio_vsock.h
index fa5934ea9c81..0c67543a45c8 100644
--- a/include/linux/virtio_vsock.h
+++ b/include/linux/virtio_vsock.h
@@ -47,7 +47,7 @@ static inline void virtio_vsock_skb_clear_tap_delivered(struct sk_buff *skb)
 	VIRTIO_VSOCK_SKB_CB(skb)->tap_delivered = false;
 }
 
-static inline void virtio_vsock_skb_rx_put(struct sk_buff *skb, u32 len)
+static inline void virtio_vsock_skb_put(struct sk_buff *skb, u32 len)
 {
 	DEBUG_NET_WARN_ON_ONCE(skb->len);
 
diff --git a/net/vmw_vsock/virtio_transport.c b/net/vmw_vsock/virtio_transport.c
index 80dcf6ac1e72..b6569b0ca2bb 100644
--- a/net/vmw_vsock/virtio_transport.c
+++ b/net/vmw_vsock/virtio_transport.c
@@ -657,7 +657,7 @@ static void virtio_transport_rx_work(struct work_struct *work)
 			}
 
 			if (payload_len)
-				virtio_vsock_skb_rx_put(skb, payload_len);
+				virtio_vsock_skb_put(skb, payload_len);
 
 			virtio_transport_deliver_tap_pkt(skb);
 			virtio_transport_recv_pkt(&virtio_transport, skb);
-- 
cgit v1.2.3


From 788fa4b47cdcd9b3d8c2d02ac0b3cd2540305f18 Mon Sep 17 00:00:00 2001
From: Steven Rostedt <rostedt@goodmis.org>
Date: Fri, 1 Aug 2025 16:37:24 -0400
Subject: tracing: Add guard(ring_buffer_nest)

Some calls to the tracing ring buffer can happen when the ring buffer is
already being written to by the same context (for example, a
trace_printk() in between a ring_buffer_lock_reserve() and a
ring_buffer_unlock_commit()).

In order to not trigger the recursion detection, these functions use
ring_buffer_nest_start() and ring_buffer_nest_end(). Create a guard() for
these functions so that their use cases can be simplified and not need to
use goto for the release.

Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Link: https://lore.kernel.org/20250801203857.710501021@kernel.org
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
---
 include/linux/ring_buffer.h       |  3 ++
 kernel/trace/trace.c              | 69 ++++++++++++++++-----------------------
 kernel/trace/trace_events_synth.c |  6 ++--
 3 files changed, 34 insertions(+), 44 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/ring_buffer.h b/include/linux/ring_buffer.h
index cd7f0ae26615..8253cb69540c 100644
--- a/include/linux/ring_buffer.h
+++ b/include/linux/ring_buffer.h
@@ -144,6 +144,9 @@ int ring_buffer_write(struct trace_buffer *buffer,
 void ring_buffer_nest_start(struct trace_buffer *buffer);
 void ring_buffer_nest_end(struct trace_buffer *buffer);
 
+DEFINE_GUARD(ring_buffer_nest, struct trace_buffer *,
+	     ring_buffer_nest_start(_T), ring_buffer_nest_end(_T))
+
 struct ring_buffer_event *
 ring_buffer_peek(struct trace_buffer *buffer, int cpu, u64 *ts,
 		 unsigned long *lost_events);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 0ec9cab9a812..332487179e1d 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1160,13 +1160,11 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip,
 
 	trace_ctx = tracing_gen_ctx();
 	buffer = tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
+	guard(ring_buffer_nest)(buffer);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, alloc,
 					    trace_ctx);
-	if (!event) {
-		size = 0;
-		goto out;
-	}
+	if (!event)
+		return 0;
 
 	entry = ring_buffer_event_data(event);
 	entry->ip = ip;
@@ -1182,8 +1180,6 @@ int __trace_array_puts(struct trace_array *tr, unsigned long ip,
 
 	__buffer_unlock_commit(buffer, event);
 	ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL);
- out:
-	ring_buffer_nest_end(buffer);
 	return size;
 }
 EXPORT_SYMBOL_GPL(__trace_array_puts);
@@ -1213,7 +1209,6 @@ int __trace_bputs(unsigned long ip, const char *str)
 	struct bputs_entry *entry;
 	unsigned int trace_ctx;
 	int size = sizeof(struct bputs_entry);
-	int ret = 0;
 
 	if (!printk_binsafe(tr))
 		return __trace_puts(ip, str, strlen(str));
@@ -1227,11 +1222,11 @@ int __trace_bputs(unsigned long ip, const char *str)
 	trace_ctx = tracing_gen_ctx();
 	buffer = tr->array_buffer.buffer;
 
-	ring_buffer_nest_start(buffer);
+	guard(ring_buffer_nest)(buffer);
 	event = __trace_buffer_lock_reserve(buffer, TRACE_BPUTS, size,
 					    trace_ctx);
 	if (!event)
-		goto out;
+		return 0;
 
 	entry = ring_buffer_event_data(event);
 	entry->ip			= ip;
@@ -1240,10 +1235,7 @@ int __trace_bputs(unsigned long ip, const char *str)
 	__buffer_unlock_commit(buffer, event);
 	ftrace_trace_stack(tr, buffer, trace_ctx, 4, NULL);
 
-	ret = 1;
- out:
-	ring_buffer_nest_end(buffer);
-	return ret;
+	return 1;
 }
 EXPORT_SYMBOL_GPL(__trace_bputs);
 
@@ -3397,21 +3389,19 @@ int trace_vbprintk(unsigned long ip, const char *fmt, va_list args)
 
 	size = sizeof(*entry) + sizeof(u32) * len;
 	buffer = tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
-	event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
-					    trace_ctx);
-	if (!event)
-		goto out;
-	entry = ring_buffer_event_data(event);
-	entry->ip			= ip;
-	entry->fmt			= fmt;
-
-	memcpy(entry->buf, tbuffer, sizeof(u32) * len);
-	__buffer_unlock_commit(buffer, event);
-	ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
+	scoped_guard(ring_buffer_nest, buffer) {
+		event = __trace_buffer_lock_reserve(buffer, TRACE_BPRINT, size,
+						    trace_ctx);
+		if (!event)
+			goto out_put;
+		entry = ring_buffer_event_data(event);
+		entry->ip			= ip;
+		entry->fmt			= fmt;
 
-out:
-	ring_buffer_nest_end(buffer);
+		memcpy(entry->buf, tbuffer, sizeof(u32) * len);
+		__buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(tr, buffer, trace_ctx, 6, NULL);
+	}
 out_put:
 	put_trace_buf();
 
@@ -3452,20 +3442,19 @@ int __trace_array_vprintk(struct trace_buffer *buffer,
 	len = vscnprintf(tbuffer, TRACE_BUF_SIZE, fmt, args);
 
 	size = sizeof(*entry) + len + 1;
-	ring_buffer_nest_start(buffer);
-	event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
-					    trace_ctx);
-	if (!event)
-		goto out;
-	entry = ring_buffer_event_data(event);
-	entry->ip = ip;
-
-	memcpy(&entry->buf, tbuffer, len + 1);
-	__buffer_unlock_commit(buffer, event);
-	ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
+	scoped_guard(ring_buffer_nest, buffer) {
+		event = __trace_buffer_lock_reserve(buffer, TRACE_PRINT, size,
+						    trace_ctx);
+		if (!event)
+			goto out;
+		entry = ring_buffer_event_data(event);
+		entry->ip = ip;
 
+		memcpy(&entry->buf, tbuffer, len + 1);
+		__buffer_unlock_commit(buffer, event);
+		ftrace_trace_stack(printk_trace, buffer, trace_ctx, 6, NULL);
+	}
 out:
-	ring_buffer_nest_end(buffer);
 	put_trace_buf();
 
 out_nobuffer:
diff --git a/kernel/trace/trace_events_synth.c b/kernel/trace/trace_events_synth.c
index 33cfbd4ed76d..f24ee61f8884 100644
--- a/kernel/trace/trace_events_synth.c
+++ b/kernel/trace/trace_events_synth.c
@@ -536,12 +536,12 @@ static notrace void trace_event_raw_event_synth(void *__data,
 	 * is being performed within another event.
 	 */
 	buffer = trace_file->tr->array_buffer.buffer;
-	ring_buffer_nest_start(buffer);
+	guard(ring_buffer_nest)(buffer);
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
 					   sizeof(*entry) + fields_size);
 	if (!entry)
-		goto out;
+		return;
 
 	for (i = 0, n_u64 = 0; i < event->n_fields; i++) {
 		val_idx = var_ref_idx[i];
@@ -584,8 +584,6 @@ static notrace void trace_event_raw_event_synth(void *__data,
 	}
 
 	trace_event_buffer_commit(&fbuffer);
-out:
-	ring_buffer_nest_end(buffer);
 }
 
 static void free_synth_event_print_fmt(struct trace_event_call *call)
-- 
cgit v1.2.3


From d45cf1e7d7180256e17c9ce88e32e8061a7887fe Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Wed, 30 Jul 2025 13:17:38 +0000
Subject: ipv6: reject malicious packets in ipv6_gso_segment()

syzbot was able to craft a packet with very long IPv6 extension headers
leading to an overflow of skb->transport_header.

This 16bit field has a limited range.

Add skb_reset_transport_header_careful() helper and use it
from ipv6_gso_segment()

WARNING: CPU: 0 PID: 5871 at ./include/linux/skbuff.h:3032 skb_reset_transport_header include/linux/skbuff.h:3032 [inline]
WARNING: CPU: 0 PID: 5871 at ./include/linux/skbuff.h:3032 ipv6_gso_segment+0x15e2/0x21e0 net/ipv6/ip6_offload.c:151
Modules linked in:
CPU: 0 UID: 0 PID: 5871 Comm: syz-executor211 Not tainted 6.16.0-rc6-syzkaller-g7abc678e3084 #0 PREEMPT(full)
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 07/12/2025
 RIP: 0010:skb_reset_transport_header include/linux/skbuff.h:3032 [inline]
 RIP: 0010:ipv6_gso_segment+0x15e2/0x21e0 net/ipv6/ip6_offload.c:151
Call Trace:
 <TASK>
  skb_mac_gso_segment+0x31c/0x640 net/core/gso.c:53
  nsh_gso_segment+0x54a/0xe10 net/nsh/nsh.c:110
  skb_mac_gso_segment+0x31c/0x640 net/core/gso.c:53
  __skb_gso_segment+0x342/0x510 net/core/gso.c:124
  skb_gso_segment include/net/gso.h:83 [inline]
  validate_xmit_skb+0x857/0x11b0 net/core/dev.c:3950
  validate_xmit_skb_list+0x84/0x120 net/core/dev.c:4000
  sch_direct_xmit+0xd3/0x4b0 net/sched/sch_generic.c:329
  __dev_xmit_skb net/core/dev.c:4102 [inline]
  __dev_queue_xmit+0x17b6/0x3a70 net/core/dev.c:4679

Fixes: d1da932ed4ec ("ipv6: Separate ipv6 offload support")
Reported-by: syzbot+af43e647fd835acc02df@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/688a1a05.050a0220.5d226.0008.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Dawid Osuchowski <dawid.osuchowski@linux.intel.com>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20250730131738.3385939-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/linux/skbuff.h | 23 +++++++++++++++++++++++
 net/ipv6/ip6_offload.c |  4 +++-
 2 files changed, 26 insertions(+), 1 deletion(-)

(limited to 'include/linux')

diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index b8b06e71b73e..14b923ddb6df 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -3033,6 +3033,29 @@ static inline void skb_reset_transport_header(struct sk_buff *skb)
 	skb->transport_header = offset;
 }
 
+/**
+ * skb_reset_transport_header_careful - conditionally reset transport header
+ * @skb: buffer to alter
+ *
+ * Hardened version of skb_reset_transport_header().
+ *
+ * Returns: true if the operation was a success.
+ */
+static inline bool __must_check
+skb_reset_transport_header_careful(struct sk_buff *skb)
+{
+	long offset = skb->data - skb->head;
+
+	if (unlikely(offset != (typeof(skb->transport_header))offset))
+		return false;
+
+	if (unlikely(offset == (typeof(skb->transport_header))~0U))
+		return false;
+
+	skb->transport_header = offset;
+	return true;
+}
+
 static inline void skb_set_transport_header(struct sk_buff *skb,
 					    const int offset)
 {
diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c
index 9822163428b0..fce91183797a 100644
--- a/net/ipv6/ip6_offload.c
+++ b/net/ipv6/ip6_offload.c
@@ -148,7 +148,9 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb,
 
 	ops = rcu_dereference(inet6_offloads[proto]);
 	if (likely(ops && ops->callbacks.gso_segment)) {
-		skb_reset_transport_header(skb);
+		if (!skb_reset_transport_header_careful(skb))
+			goto out;
+
 		segs = ops->callbacks.gso_segment(skb, features);
 		if (!segs)
 			skb->network_header = skb_mac_header(skb) + nhoff - skb->head;
-- 
cgit v1.2.3


From 6c6d8f8ba7789c221a2e4c43a0ed982c7a41f428 Mon Sep 17 00:00:00 2001
From: "Dr. David Alan Gilbert" <linux@treblig.org>
Date: Wed, 16 Jul 2025 14:32:45 +0100
Subject: lib/xxhash: remove unused functions

xxh32_digest() and xxh32_update() were added in 2017 in the original
xxhash commit, but have remained unused.

Remove them.

Link: https://lkml.kernel.org/r/20250716133245.243363-1-linux@treblig.org
Signed-off-by: Dr. David Alan Gilbert <linux@treblig.org>
Reviewed-by: Christoph Hellwig <hch@lst.de>
Cc: Dave Gilbert <linux@treblig.org>
Cc: Nick Terrell <terrelln@fb.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/xxhash.h |  26 ------------
 lib/xxhash.c           | 107 -------------------------------------------------
 2 files changed, 133 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/xxhash.h b/include/linux/xxhash.h
index df42511438d0..27f57eca8cb1 100644
--- a/include/linux/xxhash.h
+++ b/include/linux/xxhash.h
@@ -177,32 +177,6 @@ struct xxh64_state {
  */
 void xxh32_reset(struct xxh32_state *state, uint32_t seed);
 
-/**
- * xxh32_update() - hash the data given and update the xxh32 state
- *
- * @state:  The xxh32 state to update.
- * @input:  The data to hash.
- * @length: The length of the data to hash.
- *
- * After calling xxh32_reset() call xxh32_update() as many times as necessary.
- *
- * Return:  Zero on success, otherwise an error code.
- */
-int xxh32_update(struct xxh32_state *state, const void *input, size_t length);
-
-/**
- * xxh32_digest() - produce the current xxh32 hash
- *
- * @state: Produce the current xxh32 hash of this state.
- *
- * A hash value can be produced at any time. It is still possible to continue
- * inserting input into the hash state after a call to xxh32_digest(), and
- * generate new hashes later on, by calling xxh32_digest() again.
- *
- * Return: The xxh32 hash stored in the state.
- */
-uint32_t xxh32_digest(const struct xxh32_state *state);
-
 /**
  * xxh64_reset() - reset the xxh64 state to start a new hashing operation
  *
diff --git a/lib/xxhash.c b/lib/xxhash.c
index b5bd567aa6b3..cf629766f376 100644
--- a/lib/xxhash.c
+++ b/lib/xxhash.c
@@ -267,113 +267,6 @@ void xxh64_reset(struct xxh64_state *statePtr, const uint64_t seed)
 }
 EXPORT_SYMBOL(xxh64_reset);
 
-int xxh32_update(struct xxh32_state *state, const void *input, const size_t len)
-{
-	const uint8_t *p = (const uint8_t *)input;
-	const uint8_t *const b_end = p + len;
-
-	if (input == NULL)
-		return -EINVAL;
-
-	state->total_len_32 += (uint32_t)len;
-	state->large_len |= (len >= 16) | (state->total_len_32 >= 16);
-
-	if (state->memsize + len < 16) { /* fill in tmp buffer */
-		memcpy((uint8_t *)(state->mem32) + state->memsize, input, len);
-		state->memsize += (uint32_t)len;
-		return 0;
-	}
-
-	if (state->memsize) { /* some data left from previous update */
-		const uint32_t *p32 = state->mem32;
-
-		memcpy((uint8_t *)(state->mem32) + state->memsize, input,
-			16 - state->memsize);
-
-		state->v1 = xxh32_round(state->v1, get_unaligned_le32(p32));
-		p32++;
-		state->v2 = xxh32_round(state->v2, get_unaligned_le32(p32));
-		p32++;
-		state->v3 = xxh32_round(state->v3, get_unaligned_le32(p32));
-		p32++;
-		state->v4 = xxh32_round(state->v4, get_unaligned_le32(p32));
-		p32++;
-
-		p += 16-state->memsize;
-		state->memsize = 0;
-	}
-
-	if (p <= b_end - 16) {
-		const uint8_t *const limit = b_end - 16;
-		uint32_t v1 = state->v1;
-		uint32_t v2 = state->v2;
-		uint32_t v3 = state->v3;
-		uint32_t v4 = state->v4;
-
-		do {
-			v1 = xxh32_round(v1, get_unaligned_le32(p));
-			p += 4;
-			v2 = xxh32_round(v2, get_unaligned_le32(p));
-			p += 4;
-			v3 = xxh32_round(v3, get_unaligned_le32(p));
-			p += 4;
-			v4 = xxh32_round(v4, get_unaligned_le32(p));
-			p += 4;
-		} while (p <= limit);
-
-		state->v1 = v1;
-		state->v2 = v2;
-		state->v3 = v3;
-		state->v4 = v4;
-	}
-
-	if (p < b_end) {
-		memcpy(state->mem32, p, (size_t)(b_end-p));
-		state->memsize = (uint32_t)(b_end-p);
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL(xxh32_update);
-
-uint32_t xxh32_digest(const struct xxh32_state *state)
-{
-	const uint8_t *p = (const uint8_t *)state->mem32;
-	const uint8_t *const b_end = (const uint8_t *)(state->mem32) +
-		state->memsize;
-	uint32_t h32;
-
-	if (state->large_len) {
-		h32 = xxh_rotl32(state->v1, 1) + xxh_rotl32(state->v2, 7) +
-			xxh_rotl32(state->v3, 12) + xxh_rotl32(state->v4, 18);
-	} else {
-		h32 = state->v3 /* == seed */ + PRIME32_5;
-	}
-
-	h32 += state->total_len_32;
-
-	while (p + 4 <= b_end) {
-		h32 += get_unaligned_le32(p) * PRIME32_3;
-		h32 = xxh_rotl32(h32, 17) * PRIME32_4;
-		p += 4;
-	}
-
-	while (p < b_end) {
-		h32 += (*p) * PRIME32_5;
-		h32 = xxh_rotl32(h32, 11) * PRIME32_1;
-		p++;
-	}
-
-	h32 ^= h32 >> 15;
-	h32 *= PRIME32_2;
-	h32 ^= h32 >> 13;
-	h32 *= PRIME32_3;
-	h32 ^= h32 >> 16;
-
-	return h32;
-}
-EXPORT_SYMBOL(xxh32_digest);
-
 int xxh64_update(struct xxh64_state *state, const void *input, const size_t len)
 {
 	const uint8_t *p = (const uint8_t *)input;
-- 
cgit v1.2.3


From 07d24902977e4704fab8472981e73a0ad6dfa1fd Mon Sep 17 00:00:00 2001
From: Alexander Graf <graf@amazon.com>
Date: Tue, 10 Jun 2025 08:53:27 +0000
Subject: kexec: enable CMA based contiguous allocation

When booting a new kernel with kexec_file, the kernel picks a target
location that the kernel should live at, then allocates random pages,
checks whether any of those patches magically happens to coincide with a
target address range and if so, uses them for that range.

For every page allocated this way, it then creates a page list that the
relocation code - code that executes while all CPUs are off and we are
just about to jump into the new kernel - copies to their final memory
location.  We can not put them there before, because chances are pretty
good that at least some page in the target range is already in use by the
currently running Linux environment.  Copying is happening from a single
CPU at RAM rate, which takes around 4-50 ms per 100 MiB.

All of this is inefficient and error prone.

To successfully kexec, we need to quiesce all devices of the outgoing
kernel so they don't scribble over the new kernel's memory.  We have seen
cases where that does not happen properly (*cough* GIC *cough*) and hence
the new kernel was corrupted.  This started a month long journey to root
cause failing kexecs to eventually see memory corruption, because the new
kernel was corrupted severely enough that it could not emit output to tell
us about the fact that it was corrupted.  By allocating memory for the
next kernel from a memory range that is guaranteed scribbling free, we can
boot the next kernel up to a point where it is at least able to detect
corruption and maybe even stop it before it becomes severe.  This
increases the chance for successful kexecs.

Since kexec got introduced, Linux has gained the CMA framework which can
perform physically contiguous memory mappings, while keeping that memory
available for movable memory when it is not needed for contiguous
allocations.  The default CMA allocator is for DMA allocations.

This patch adds logic to the kexec file loader to attempt to place the
target payload at a location allocated from CMA.  If successful, it uses
that memory range directly instead of creating copy instructions during
the hot phase.  To ensure that there is a safety net in case anything goes
wrong with the CMA allocation, it also adds a flag for user space to force
disable CMA allocations.

Using CMA allocations has two advantages:

  1) Faster by 4-50 ms per 100 MiB. There is no more need to copy in the
     hot phase.
  2) More robust. Even if by accident some page is still in use for DMA,
     the new kernel image will be safe from that access because it resides
     in a memory region that is considered allocated in the old kernel and
     has a chance to reinitialize that component.

Link: https://lkml.kernel.org/r/20250610085327.51817-1-graf@amazon.com
Signed-off-by: Alexander Graf <graf@amazon.com>
Acked-by: Baoquan He <bhe@redhat.com>
Reviewed-by: Pasha Tatashin <pasha.tatashin@soleen.com>
Cc: Zhongkun He <hezhongkun.hzk@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/riscv/kernel/kexec_elf.c |   1 +
 include/linux/kexec.h         |  10 +++++
 include/uapi/linux/kexec.h    |   1 +
 kernel/kexec.c                |   2 +-
 kernel/kexec_core.c           | 100 ++++++++++++++++++++++++++++++++++++++----
 kernel/kexec_file.c           |  51 ++++++++++++++++++++-
 kernel/kexec_internal.h       |   2 +-
 7 files changed, 156 insertions(+), 11 deletions(-)

(limited to 'include/linux')

diff --git a/arch/riscv/kernel/kexec_elf.c b/arch/riscv/kernel/kexec_elf.c
index f4755d49b89e..56444c7bd34e 100644
--- a/arch/riscv/kernel/kexec_elf.c
+++ b/arch/riscv/kernel/kexec_elf.c
@@ -95,6 +95,7 @@ static int elf_find_pbase(struct kimage *image, unsigned long kernel_len,
 	kbuf.buf_align = PMD_SIZE;
 	kbuf.mem = KEXEC_BUF_MEM_UNKNOWN;
 	kbuf.memsz = ALIGN(kernel_len, PAGE_SIZE);
+	kbuf.cma = NULL;
 	kbuf.top_down = false;
 	ret = arch_kexec_locate_mem_hole(&kbuf);
 	if (!ret) {
diff --git a/include/linux/kexec.h b/include/linux/kexec.h
index 03f85ad03025..1b10a5d84b68 100644
--- a/include/linux/kexec.h
+++ b/include/linux/kexec.h
@@ -79,6 +79,12 @@ extern note_buf_t __percpu *crash_notes;
 
 typedef unsigned long kimage_entry_t;
 
+/*
+ * This is a copy of the UAPI struct kexec_segment and must be identical
+ * to it because it gets copied straight from user space into kernel
+ * memory. Do not modify this structure unless you change the way segments
+ * get ingested from user space.
+ */
 struct kexec_segment {
 	/*
 	 * This pointer can point to user memory if kexec_load() system
@@ -172,6 +178,7 @@ int kexec_image_post_load_cleanup_default(struct kimage *image);
  * @buf_align:	Minimum alignment needed.
  * @buf_min:	The buffer can't be placed below this address.
  * @buf_max:	The buffer can't be placed above this address.
+ * @cma:	CMA page if the buffer is backed by CMA.
  * @top_down:	Allocate from top of memory.
  * @random:	Place the buffer at a random position.
  */
@@ -184,6 +191,7 @@ struct kexec_buf {
 	unsigned long buf_align;
 	unsigned long buf_min;
 	unsigned long buf_max;
+	struct page *cma;
 	bool top_down;
 #ifdef CONFIG_CRASH_DUMP
 	bool random;
@@ -340,6 +348,7 @@ struct kimage {
 
 	unsigned long nr_segments;
 	struct kexec_segment segment[KEXEC_SEGMENT_MAX];
+	struct page *segment_cma[KEXEC_SEGMENT_MAX];
 
 	struct list_head control_pages;
 	struct list_head dest_pages;
@@ -361,6 +370,7 @@ struct kimage {
 	 */
 	unsigned int hotplug_support:1;
 #endif
+	unsigned int no_cma:1;
 
 #ifdef ARCH_HAS_KIMAGE_ARCH
 	struct kimage_arch arch;
diff --git a/include/uapi/linux/kexec.h b/include/uapi/linux/kexec.h
index 5ae1741ea8ea..8958ebfcff94 100644
--- a/include/uapi/linux/kexec.h
+++ b/include/uapi/linux/kexec.h
@@ -27,6 +27,7 @@
 #define KEXEC_FILE_ON_CRASH	0x00000002
 #define KEXEC_FILE_NO_INITRAMFS	0x00000004
 #define KEXEC_FILE_DEBUG	0x00000008
+#define KEXEC_FILE_NO_CMA	0x00000010
 
 /* These values match the ELF architecture values.
  * Unless there is a good reason that should continue to be the case.
diff --git a/kernel/kexec.c b/kernel/kexec.c
index a6b3f96bb50c..28008e3d462e 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -152,7 +152,7 @@ static int do_kexec_load(unsigned long entry, unsigned long nr_segments,
 		goto out;
 
 	for (i = 0; i < nr_segments; i++) {
-		ret = kimage_load_segment(image, &image->segment[i]);
+		ret = kimage_load_segment(image, i);
 		if (ret)
 			goto out;
 	}
diff --git a/kernel/kexec_core.c b/kernel/kexec_core.c
index 3a9a9f240dbc..e390c0df6d55 100644
--- a/kernel/kexec_core.c
+++ b/kernel/kexec_core.c
@@ -40,6 +40,7 @@
 #include <linux/hugetlb.h>
 #include <linux/objtool.h>
 #include <linux/kmsg_dump.h>
+#include <linux/dma-map-ops.h>
 
 #include <asm/page.h>
 #include <asm/sections.h>
@@ -553,6 +554,24 @@ static void kimage_free_entry(kimage_entry_t entry)
 	kimage_free_pages(page);
 }
 
+static void kimage_free_cma(struct kimage *image)
+{
+	unsigned long i;
+
+	for (i = 0; i < image->nr_segments; i++) {
+		struct page *cma = image->segment_cma[i];
+		u32 nr_pages = image->segment[i].memsz >> PAGE_SHIFT;
+
+		if (!cma)
+			continue;
+
+		arch_kexec_pre_free_pages(page_address(cma), nr_pages);
+		dma_release_from_contiguous(NULL, cma, nr_pages);
+		image->segment_cma[i] = NULL;
+	}
+
+}
+
 void kimage_free(struct kimage *image)
 {
 	kimage_entry_t *ptr, entry;
@@ -591,6 +610,9 @@ void kimage_free(struct kimage *image)
 	/* Free the kexec control pages... */
 	kimage_free_page_list(&image->control_pages);
 
+	/* Free CMA allocations */
+	kimage_free_cma(image);
+
 	/*
 	 * Free up any temporary buffers allocated. This might hit if
 	 * error occurred much later after buffer allocation.
@@ -716,9 +738,69 @@ static struct page *kimage_alloc_page(struct kimage *image,
 	return page;
 }
 
-static int kimage_load_normal_segment(struct kimage *image,
-					 struct kexec_segment *segment)
+static int kimage_load_cma_segment(struct kimage *image, int idx)
+{
+	struct kexec_segment *segment = &image->segment[idx];
+	struct page *cma = image->segment_cma[idx];
+	char *ptr = page_address(cma);
+	unsigned long maddr;
+	size_t ubytes, mbytes;
+	int result = 0;
+	unsigned char __user *buf = NULL;
+	unsigned char *kbuf = NULL;
+
+	if (image->file_mode)
+		kbuf = segment->kbuf;
+	else
+		buf = segment->buf;
+	ubytes = segment->bufsz;
+	mbytes = segment->memsz;
+	maddr = segment->mem;
+
+	/* Then copy from source buffer to the CMA one */
+	while (mbytes) {
+		size_t uchunk, mchunk;
+
+		ptr += maddr & ~PAGE_MASK;
+		mchunk = min_t(size_t, mbytes,
+				PAGE_SIZE - (maddr & ~PAGE_MASK));
+		uchunk = min(ubytes, mchunk);
+
+		if (uchunk) {
+			/* For file based kexec, source pages are in kernel memory */
+			if (image->file_mode)
+				memcpy(ptr, kbuf, uchunk);
+			else
+				result = copy_from_user(ptr, buf, uchunk);
+			ubytes -= uchunk;
+			if (image->file_mode)
+				kbuf += uchunk;
+			else
+				buf += uchunk;
+		}
+
+		if (result) {
+			result = -EFAULT;
+			goto out;
+		}
+
+		ptr    += mchunk;
+		maddr  += mchunk;
+		mbytes -= mchunk;
+
+		cond_resched();
+	}
+
+	/* Clear any remainder */
+	memset(ptr, 0, mbytes);
+
+out:
+	return result;
+}
+
+static int kimage_load_normal_segment(struct kimage *image, int idx)
 {
+	struct kexec_segment *segment = &image->segment[idx];
 	unsigned long maddr;
 	size_t ubytes, mbytes;
 	int result;
@@ -733,6 +815,9 @@ static int kimage_load_normal_segment(struct kimage *image,
 	mbytes = segment->memsz;
 	maddr = segment->mem;
 
+	if (image->segment_cma[idx])
+		return kimage_load_cma_segment(image, idx);
+
 	result = kimage_set_destination(image, maddr);
 	if (result < 0)
 		goto out;
@@ -787,13 +872,13 @@ out:
 }
 
 #ifdef CONFIG_CRASH_DUMP
-static int kimage_load_crash_segment(struct kimage *image,
-					struct kexec_segment *segment)
+static int kimage_load_crash_segment(struct kimage *image, int idx)
 {
 	/* For crash dumps kernels we simply copy the data from
 	 * user space to it's destination.
 	 * We do things a page at a time for the sake of kmap.
 	 */
+	struct kexec_segment *segment = &image->segment[idx];
 	unsigned long maddr;
 	size_t ubytes, mbytes;
 	int result;
@@ -858,18 +943,17 @@ out:
 }
 #endif
 
-int kimage_load_segment(struct kimage *image,
-				struct kexec_segment *segment)
+int kimage_load_segment(struct kimage *image, int idx)
 {
 	int result = -ENOMEM;
 
 	switch (image->type) {
 	case KEXEC_TYPE_DEFAULT:
-		result = kimage_load_normal_segment(image, segment);
+		result = kimage_load_normal_segment(image, idx);
 		break;
 #ifdef CONFIG_CRASH_DUMP
 	case KEXEC_TYPE_CRASH:
-		result = kimage_load_crash_segment(image, segment);
+		result = kimage_load_crash_segment(image, idx);
 		break;
 #endif
 	}
diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
index 69fe76fd9233..41271eee0f99 100644
--- a/kernel/kexec_file.c
+++ b/kernel/kexec_file.c
@@ -26,6 +26,7 @@
 #include <linux/kernel_read_file.h>
 #include <linux/syscalls.h>
 #include <linux/vmalloc.h>
+#include <linux/dma-map-ops.h>
 #include "kexec_internal.h"
 
 #ifdef CONFIG_KEXEC_SIG
@@ -253,6 +254,8 @@ kimage_file_prepare_segments(struct kimage *image, int kernel_fd, int initrd_fd,
 		ret = 0;
 	}
 
+	image->no_cma = !!(flags & KEXEC_FILE_NO_CMA);
+
 	if (cmdline_len) {
 		image->cmdline_buf = memdup_user(cmdline_ptr, cmdline_len);
 		if (IS_ERR(image->cmdline_buf)) {
@@ -434,7 +437,7 @@ SYSCALL_DEFINE5(kexec_file_load, int, kernel_fd, int, initrd_fd,
 			      i, ksegment->buf, ksegment->bufsz, ksegment->mem,
 			      ksegment->memsz);
 
-		ret = kimage_load_segment(image, &image->segment[i]);
+		ret = kimage_load_segment(image, i);
 		if (ret)
 			goto out;
 	}
@@ -663,6 +666,43 @@ static int kexec_walk_resources(struct kexec_buf *kbuf,
 		return walk_system_ram_res(0, ULONG_MAX, kbuf, func);
 }
 
+static int kexec_alloc_contig(struct kexec_buf *kbuf)
+{
+	size_t nr_pages = kbuf->memsz >> PAGE_SHIFT;
+	unsigned long mem;
+	struct page *p;
+
+	/* User space disabled CMA allocations, bail out. */
+	if (kbuf->image->no_cma)
+		return -EPERM;
+
+	/* Skip CMA logic for crash kernel */
+	if (kbuf->image->type == KEXEC_TYPE_CRASH)
+		return -EPERM;
+
+	p = dma_alloc_from_contiguous(NULL, nr_pages, get_order(kbuf->buf_align), true);
+	if (!p)
+		return -ENOMEM;
+
+	pr_debug("allocated %zu DMA pages at 0x%lx", nr_pages, page_to_boot_pfn(p));
+
+	mem = page_to_boot_pfn(p) << PAGE_SHIFT;
+
+	if (kimage_is_destination_range(kbuf->image, mem, mem + kbuf->memsz)) {
+		/* Our region is already in use by a statically defined one. Bail out. */
+		pr_debug("CMA overlaps existing mem: 0x%lx+0x%lx\n", mem, kbuf->memsz);
+		dma_release_from_contiguous(NULL, p, nr_pages);
+		return -EBUSY;
+	}
+
+	kbuf->mem = page_to_boot_pfn(p) << PAGE_SHIFT;
+	kbuf->cma = p;
+
+	arch_kexec_post_alloc_pages(page_address(p), (int)nr_pages, 0);
+
+	return 0;
+}
+
 /**
  * kexec_locate_mem_hole - find free memory for the purgatory or the next kernel
  * @kbuf:	Parameters for the memory search.
@@ -687,6 +727,13 @@ int kexec_locate_mem_hole(struct kexec_buf *kbuf)
 	if (ret <= 0)
 		return ret;
 
+	/*
+	 * Try to find a free physically contiguous block of memory first. With that, we
+	 * can avoid any copying at kexec time.
+	 */
+	if (!kexec_alloc_contig(kbuf))
+		return 0;
+
 	if (!IS_ENABLED(CONFIG_ARCH_KEEP_MEMBLOCK))
 		ret = kexec_walk_resources(kbuf, locate_mem_hole_callback);
 	else
@@ -732,6 +779,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	/* Ensure minimum alignment needed for segments. */
 	kbuf->memsz = ALIGN(kbuf->memsz, PAGE_SIZE);
 	kbuf->buf_align = max(kbuf->buf_align, PAGE_SIZE);
+	kbuf->cma = NULL;
 
 	/* Walk the RAM ranges and allocate a suitable range for the buffer */
 	ret = arch_kexec_locate_mem_hole(kbuf);
@@ -744,6 +792,7 @@ int kexec_add_buffer(struct kexec_buf *kbuf)
 	ksegment->bufsz = kbuf->bufsz;
 	ksegment->mem = kbuf->mem;
 	ksegment->memsz = kbuf->memsz;
+	kbuf->image->segment_cma[kbuf->image->nr_segments] = kbuf->cma;
 	kbuf->image->nr_segments++;
 	return 0;
 }
diff --git a/kernel/kexec_internal.h b/kernel/kexec_internal.h
index 30a733a55a67..228bb88c018b 100644
--- a/kernel/kexec_internal.h
+++ b/kernel/kexec_internal.h
@@ -10,7 +10,7 @@ struct kimage *do_kimage_alloc_init(void);
 int sanity_check_segment_list(struct kimage *image);
 void kimage_free_page_list(struct list_head *list);
 void kimage_free(struct kimage *image);
-int kimage_load_segment(struct kimage *image, struct kexec_segment *segment);
+int kimage_load_segment(struct kimage *image, int idx);
 void kimage_terminate(struct kimage *image);
 int kimage_is_destination_range(struct kimage *image,
 				unsigned long start, unsigned long end);
-- 
cgit v1.2.3


From d171b10b2d7b067c16d79e1d069a23a34f088d23 Mon Sep 17 00:00:00 2001
From: Joanne Koong <joannelkoong@gmail.com>
Date: Tue, 22 Jul 2025 11:22:30 -0700
Subject: mm/page-flags: remove folio_start_writeback_keepwrite()

Commit cd57b77197a4 ("ext4: Convert ext4_bio_write_page() to use a folio)
removed set_page_writeback_keepwrite() which was the last/only caller of
folio_start_writeback_keepwrite().

Link: https://lkml.kernel.org/r/20250722182230.2114587-1-joannelkoong@gmail.com
Signed-off-by: Joanne Koong <joannelkoong@gmail.com>
Reviewed-by: Matthew Wilcox (Oracle) <willy@infradead.org>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/page-flags.h | 2 --
 1 file changed, 2 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 8e4d6eda8a8d..8d3fa3a91ce4 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -837,8 +837,6 @@ void set_page_writeback(struct page *page);
 
 #define folio_start_writeback(folio)			\
 	__folio_start_writeback(folio, false)
-#define folio_start_writeback_keepwrite(folio)	\
-	__folio_start_writeback(folio, true)
 
 static __always_inline bool folio_test_head(const struct folio *folio)
 {
-- 
cgit v1.2.3


From f225b34f1e6c81c50e48f6207ddb6d290be1b932 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Fri, 25 Jul 2025 09:29:41 +0100
Subject: mm/mseal: always define VM_SEALED

Patch series "mseal cleanups", v4.

Perform a number of cleanups to the mseal logic.  Firstly, VM_SEALED is
treated differently from every other VMA flag, it really doesn't make
sense to do this, so we start by making this consistent with everything
else.

Next we place the madvise logic where it belongs - in mm/madvise.c.  It
really makes no sense to abstract this elsewhere.  In doing so, we go to
great lengths to explain very clearly the previously very confusing logic
as to what sealed mappings are impacted here.

In doing so, we retain existing logic regarding treatment of madvise()
discard operations for a sealed, read-only MAP_PRIVATE file-backed
mapping.  This is something we likely need to revisit.

We then abstract out and explain the 'are there are any gaps in this range
in the mm?' check being performed as a prerequisite to mseal being
performed.

Finally, we simplify the actual mseal logic which is really quite
straightforward.

No functional change is intended.


This patch (of 4):

There is no reason to treat VM_SEALED in a special way, in each other case
in which a VMA flag is unavailable due to configuration, we simply assign
that flag to VM_NONE, so make VM_SEALED consistent with all other VMA
flags in this respect.

Additionally, use the next available bit for VM_SEALED, 42, rather than
arbitrarily putting it at 63 and update the declaration to match all other
VMA flags.

No functional change intended.

Link: https://lkml.kernel.org/r/cover.1753431105.git.lorenzo.stoakes@oracle.com
Link: https://lkml.kernel.org/r/aeb398a77029b6e7377cd944328bc9bbc3c90537.1753431105.git.lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reviewed-by: Pedro Falcato <pfalcato@suse.de>
Acked-by: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Kees Cook <kees@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mm.h               | 6 ++++--
 tools/testing/vma/vma_internal.h | 6 ++++--
 2 files changed, 8 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mm.h b/include/linux/mm.h
index 8e3a4c5b78ff..ceaa780a703a 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -414,8 +414,10 @@ extern unsigned int kobjsize(const void *objp);
 #endif
 
 #ifdef CONFIG_64BIT
-/* VM is sealed, in vm_flags */
-#define VM_SEALED	_BITUL(63)
+#define VM_SEALED_BIT	42
+#define VM_SEALED	BIT(VM_SEALED_BIT)
+#else
+#define VM_SEALED	VM_NONE
 #endif
 
 /* Bits set in the VMA until the stack is in its final location */
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 991022e9e0d3..0fe52fd6782b 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -108,8 +108,10 @@ extern unsigned long dac_mmap_min_addr;
 #define CAP_IPC_LOCK         14
 
 #ifdef CONFIG_64BIT
-/* VM is sealed, in vm_flags */
-#define VM_SEALED	_BITUL(63)
+#define VM_SEALED_BIT	42
+#define VM_SEALED	BIT(VM_SEALED_BIT)
+#else
+#define VM_SEALED	VM_NONE
 #endif
 
 #define FIRST_USER_ADDRESS	0UL
-- 
cgit v1.2.3


From 3dfde97800e06882960cc926d2c428f2128b7c70 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <david@redhat.com>
Date: Thu, 24 Jul 2025 10:52:59 +0530
Subject: mm: add get_and_clear_ptes() and clear_ptes()

Patch series "Optimizations for khugepaged", v4.

If the underlying folio mapped by the ptes is large, we can process those
ptes in a batch using folio_pte_batch().

For arm64 specifically, this results in a 16x reduction in the number of
ptep_get() calls, since on a contig block, ptep_get() on arm64 will
iterate through all 16 entries to collect a/d bits.  Next, ptep_clear()
will cause a TLBI for every contig block in the range via
contpte_try_unfold().  Instead, use clear_ptes() to only do the TLBI at
the first and last contig block of the range.

For split folios, there will be no pte batching; the batch size returned
by folio_pte_batch() will be 1.  For pagetable split folios, the ptes will
still point to the same large folio; for arm64, this results in the
optimization described above, and for other arches, a minor improvement is
expected due to a reduction in the number of function calls and batching
atomic operations.


This patch (of 3):

Let's add variants to be used where "full" does not apply -- which will
be the majority of cases in the future. "full" really only applies if
we are about to tear down a full MM.

Use get_and_clear_ptes() in existing code, clear_ptes() users will
be added next.

Link: https://lkml.kernel.org/r/20250724052301.23844-2-dev.jain@arm.com
Signed-off-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Dev Jain <dev.jain@arm.com>
Reviewed-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Barry Song <baohua@kernel.org>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Zi Yan <ziy@nvidia.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Mariano Pache <npache@redhat.com>
Cc: Ryan Roberts <ryan.roberts@arm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/arm64/mm/mmu.c     |  2 +-
 include/linux/pgtable.h | 45 +++++++++++++++++++++++++++++++++++++++++++++
 mm/mremap.c             |  2 +-
 mm/rmap.c               |  2 +-
 4 files changed, 48 insertions(+), 3 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index abd9725796e9..20a89ab97dc5 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -1528,7 +1528,7 @@ early_initcall(prevent_bootmem_remove_init);
 pte_t modify_prot_start_ptes(struct vm_area_struct *vma, unsigned long addr,
 			     pte_t *ptep, unsigned int nr)
 {
-	pte_t pte = get_and_clear_full_ptes(vma->vm_mm, addr, ptep, nr, /* full = */ 0);
+	pte_t pte = get_and_clear_ptes(vma->vm_mm, addr, ptep, nr);
 
 	if (alternative_has_cap_unlikely(ARM64_WORKAROUND_2645198)) {
 		/*
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index e3b99920be05..4c035637eeb7 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -736,6 +736,29 @@ static inline pte_t get_and_clear_full_ptes(struct mm_struct *mm,
 }
 #endif
 
+/**
+ * get_and_clear_ptes - Clear present PTEs that map consecutive pages of
+ *			the same folio, collecting dirty/accessed bits.
+ * @mm: Address space the pages are mapped into.
+ * @addr: Address the first page is mapped at.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries to clear.
+ *
+ * Use this instead of get_and_clear_full_ptes() if it is known that we don't
+ * need to clear the full mm, which is mostly the case.
+ *
+ * Note that PTE bits in the PTE range besides the PFN can differ. For example,
+ * some PTEs might be write-protected.
+ *
+ * Context: The caller holds the page table lock.  The PTEs map consecutive
+ * pages that belong to the same folio.  The PTEs are all in the same PMD.
+ */
+static inline pte_t get_and_clear_ptes(struct mm_struct *mm, unsigned long addr,
+		pte_t *ptep, unsigned int nr)
+{
+	return get_and_clear_full_ptes(mm, addr, ptep, nr, 0);
+}
+
 #ifndef clear_full_ptes
 /**
  * clear_full_ptes - Clear present PTEs that map consecutive pages of the same
@@ -768,6 +791,28 @@ static inline void clear_full_ptes(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 
+/**
+ * clear_ptes - Clear present PTEs that map consecutive pages of the same folio.
+ * @mm: Address space the pages are mapped into.
+ * @addr: Address the first page is mapped at.
+ * @ptep: Page table pointer for the first entry.
+ * @nr: Number of entries to clear.
+ *
+ * Use this instead of clear_full_ptes() if it is known that we don't need to
+ * clear the full mm, which is mostly the case.
+ *
+ * Note that PTE bits in the PTE range besides the PFN can differ. For example,
+ * some PTEs might be write-protected.
+ *
+ * Context: The caller holds the page table lock.  The PTEs map consecutive
+ * pages that belong to the same folio.  The PTEs are all in the same PMD.
+ */
+static inline void clear_ptes(struct mm_struct *mm, unsigned long addr,
+		pte_t *ptep, unsigned int nr)
+{
+	clear_full_ptes(mm, addr, ptep, nr, 0);
+}
+
 /*
  * If two threads concurrently fault at the same page, the thread that
  * won the race updates the PTE and its local TLB/Cache. The other thread
diff --git a/mm/mremap.c b/mm/mremap.c
index ac39845e9718..677a4d744df9 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -280,7 +280,7 @@ static int move_ptes(struct pagetable_move_control *pmc,
 							 old_pte, max_nr_ptes);
 			force_flush = true;
 		}
-		pte = get_and_clear_full_ptes(mm, old_addr, old_ptep, nr_ptes, 0);
+		pte = get_and_clear_ptes(mm, old_addr, old_ptep, nr_ptes);
 		pte = move_pte(pte, old_addr, new_addr);
 		pte = move_soft_dirty_pte(pte);
 
diff --git a/mm/rmap.c b/mm/rmap.c
index f93ce27132ab..568198e9efc2 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -2036,7 +2036,7 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			flush_cache_range(vma, address, end_addr);
 
 			/* Nuke the page table entry. */
-			pteval = get_and_clear_full_ptes(mm, address, pvmw.pte, nr_pages, 0);
+			pteval = get_and_clear_ptes(mm, address, pvmw.pte, nr_pages);
 			/*
 			 * We clear the PTE but do not flush so potentially
 			 * a remote CPU could still be writing to the folio.
-- 
cgit v1.2.3


From 9a4f90e246615d1f42a9b907deb9b4c0a418d996 Mon Sep 17 00:00:00 2001
From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Date: Fri, 25 Jul 2025 15:29:01 +0100
Subject: mm: remove mm/io-mapping.c

This is dead code, which was used from commit b739f125e4eb ("i915: use
io_mapping_map_user") but reverted a month later by commit 0e4fe0c9f2f9
("Revert "i915: use io_mapping_map_user"") back in 2021.

Since then nobody has used it, so remove it.

[akpm@linux-foundation.org: update Documentation/core-api/mm-api.rst, per Vlastimil]
Link: https://lkml.kernel.org/r/20250725142901.81502-1-lorenzo.stoakes@oracle.com
Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: David Hildenbrand <david@redhat.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Mike Rapoport <rppt@kernel.org>
Cc: Suren Baghdasaryan <surenb@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 Documentation/core-api/mm-api.rst |  1 -
 include/linux/io-mapping.h        |  3 ---
 mm/Kconfig                        |  4 ----
 mm/Makefile                       |  1 -
 mm/io-mapping.c                   | 30 ------------------------------
 5 files changed, 39 deletions(-)
 delete mode 100644 mm/io-mapping.c

(limited to 'include/linux')

diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst
index af8151db88b2..24970b91ac15 100644
--- a/Documentation/core-api/mm-api.rst
+++ b/Documentation/core-api/mm-api.rst
@@ -139,4 +139,3 @@ More Memory Management Functions
 .. kernel-doc:: mm/mmu_notifier.c
 .. kernel-doc:: mm/balloon_compaction.c
 .. kernel-doc:: mm/huge_memory.c
-.. kernel-doc:: mm/io-mapping.c
diff --git a/include/linux/io-mapping.h b/include/linux/io-mapping.h
index 7376c1df9c90..c16353cc6e3c 100644
--- a/include/linux/io-mapping.h
+++ b/include/linux/io-mapping.h
@@ -225,7 +225,4 @@ io_mapping_free(struct io_mapping *iomap)
 	kfree(iomap);
 }
 
-int io_mapping_map_user(struct io_mapping *iomap, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long pfn, unsigned long size);
-
 #endif /* _LINUX_IO_MAPPING_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index d5d4eca947a6..e443fe8cd6cf 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1242,10 +1242,6 @@ config KMAP_LOCAL
 config KMAP_LOCAL_NON_LINEAR_PTE_ARRAY
 	bool
 
-# struct io_mapping based helper.  Selected by drivers that need them
-config IO_MAPPING
-	bool
-
 config MEMFD_CREATE
 	bool "Enable memfd_create() system call" if EXPERT
 
diff --git a/mm/Makefile b/mm/Makefile
index 1a7a11d4933d..ef54aa615d9d 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -141,7 +141,6 @@ obj-$(CONFIG_MEMFD_CREATE) += memfd.o
 obj-$(CONFIG_MAPPING_DIRTY_HELPERS) += mapping_dirty_helpers.o
 obj-$(CONFIG_PTDUMP) += ptdump.o
 obj-$(CONFIG_PAGE_REPORTING) += page_reporting.o
-obj-$(CONFIG_IO_MAPPING) += io-mapping.o
 obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
 obj-$(CONFIG_GENERIC_IOREMAP) += ioremap.o
 obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
diff --git a/mm/io-mapping.c b/mm/io-mapping.c
deleted file mode 100644
index d3586e95c12c..000000000000
--- a/mm/io-mapping.c
+++ /dev/null
@@ -1,30 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0-only
-
-#include <linux/mm.h>
-#include <linux/io-mapping.h>
-
-/**
- * io_mapping_map_user - remap an I/O mapping to userspace
- * @iomap: the source io_mapping
- * @vma: user vma to map to
- * @addr: target user address to start at
- * @pfn: physical address of kernel memory
- * @size: size of map area
- *
- *  Note: this is only safe if the mm semaphore is held when called.
- */
-int io_mapping_map_user(struct io_mapping *iomap, struct vm_area_struct *vma,
-		unsigned long addr, unsigned long pfn, unsigned long size)
-{
-	vm_flags_t expected_flags = VM_PFNMAP | VM_DONTEXPAND | VM_DONTDUMP;
-
-	if (WARN_ON_ONCE((vma->vm_flags & expected_flags) != expected_flags))
-		return -EINVAL;
-
-	pgprot_t remap_prot = __pgprot((pgprot_val(iomap->prot) & _PAGE_CACHE_MASK) |
-				       (pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK));
-
-	/* We rely on prevalidation of the io-mapping to skip pfnmap tracking. */
-	return remap_pfn_range_notrack(vma, addr, pfn, size, remap_prot);
-}
-EXPORT_SYMBOL_GPL(io_mapping_map_user);
-- 
cgit v1.2.3


From a222439e1e273fa0f4e37ce17aeb109f3e91824f Mon Sep 17 00:00:00 2001
From: Jann Horn <jannh@google.com>
Date: Fri, 25 Jul 2025 14:16:24 +0200
Subject: mm/rmap: add anon_vma lifetime debug check

If an anon folio is mapped into userspace, its anon_vma must be alive,
otherwise rmap walks can hit UAF.

There have been syzkaller reports a few months ago[1][2] of UAF in rmap
walks that seems to indicate that there can be pages with elevated
mapcount whose anon_vma has already been freed, but I think we never
figured out what the cause is; and syzkaller only hit these UAFs when
memory pressure randomly caused reclaim to rmap-walk the affected pages,
so it of course didn't manage to create a reproducer.

Add a VM_WARN_ON_FOLIO() when we add/remove mappings of anonymous folios
to hopefully catch such issues more reliably.

[1] https://lore.kernel.org/r/67abaeaf.050a0220.110943.0041.GAE@google.com
[2] https://lore.kernel.org/r/67a76f33.050a0220.3d72c.0028.GAE@google.com

Link: https://lkml.kernel.org/r/20250725-anonvma-uaf-debug-v2-1-bc3c7e5ba5b1@google.com
Signed-off-by: Jann Horn <jannh@google.com>
Acked-by: David Hildenbrand <david@redhat.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Harry Yoo <harry.yoo@oracle.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/rmap.h | 22 ++++++++++++++++++++++
 1 file changed, 22 insertions(+)

(limited to 'include/linux')

diff --git a/include/linux/rmap.h b/include/linux/rmap.h
index 20803fcb49a7..6cd020eea37a 100644
--- a/include/linux/rmap.h
+++ b/include/linux/rmap.h
@@ -449,6 +449,28 @@ static inline void __folio_rmap_sanity_checks(const struct folio *folio,
 	default:
 		VM_WARN_ON_ONCE(true);
 	}
+
+	/*
+	 * Anon folios must have an associated live anon_vma as long as they're
+	 * mapped into userspace.
+	 * Note that the atomic_read() mainly does two things:
+	 *
+	 * 1. In KASAN builds with CONFIG_SLUB_RCU_DEBUG, it causes KASAN to
+	 *    check that the associated anon_vma has not yet been freed (subject
+	 *    to KASAN's usual limitations). This check will pass if the
+	 *    anon_vma's refcount has already dropped to 0 but an RCU grace
+	 *    period hasn't passed since then.
+	 * 2. If the anon_vma has not yet been freed, it checks that the
+	 *    anon_vma still has a nonzero refcount (as opposed to being in the
+	 *    middle of an RCU delay for getting freed).
+	 */
+	if (folio_test_anon(folio) && !folio_test_ksm(folio)) {
+		unsigned long mapping = (unsigned long)folio->mapping;
+		struct anon_vma *anon_vma;
+
+		anon_vma = (void *)(mapping - FOLIO_MAPPING_ANON);
+		VM_WARN_ON_FOLIO(atomic_read(&anon_vma->refcount) == 0, folio);
+	}
 }
 
 /*
-- 
cgit v1.2.3


From 9bbffee67ffd16360179327b57f3b1245579ef08 Mon Sep 17 00:00:00 2001
From: Suren Baghdasaryan <surenb@google.com>
Date: Mon, 28 Jul 2025 10:53:55 -0700
Subject: mm: fix a UAF when vma->mm is freed after vma->vm_refcnt got dropped

By inducing delays in the right places, Jann Horn created a reproducer for
a hard to hit UAF issue that became possible after VMAs were allowed to be
recycled by adding SLAB_TYPESAFE_BY_RCU to their cache.

Race description is borrowed from Jann's discovery report:
lock_vma_under_rcu() looks up a VMA locklessly with mas_walk() under
rcu_read_lock().  At that point, the VMA may be concurrently freed, and it
can be recycled by another process.  vma_start_read() then increments the
vma->vm_refcnt (if it is in an acceptable range), and if this succeeds,
vma_start_read() can return a recycled VMA.

In this scenario where the VMA has been recycled, lock_vma_under_rcu()
will then detect the mismatching ->vm_mm pointer and drop the VMA through
vma_end_read(), which calls vma_refcount_put().  vma_refcount_put() drops
the refcount and then calls rcuwait_wake_up() using a copy of vma->vm_mm.
This is wrong: It implicitly assumes that the caller is keeping the VMA's
mm alive, but in this scenario the caller has no relation to the VMA's mm,
so the rcuwait_wake_up() can cause UAF.

The diagram depicting the race:
T1         T2         T3
==         ==         ==
lock_vma_under_rcu
  mas_walk
          <VMA gets removed from mm>
                      mmap
                        <the same VMA is reallocated>
  vma_start_read
    __refcount_inc_not_zero_limited_acquire
                      munmap
                        __vma_enter_locked
                          refcount_add_not_zero
  vma_end_read
    vma_refcount_put
      __refcount_dec_and_test
                          rcuwait_wait_event
                            <finish operation>
      rcuwait_wake_up [UAF]

Note that rcuwait_wait_event() in T3 does not block because refcount was
already dropped by T1.  At this point T3 can exit and free the mm causing
UAF in T1.

To avoid this we move vma->vm_mm verification into vma_start_read() and
grab vma->vm_mm to stabilize it before vma_refcount_put() operation.

[surenb@google.com: v3]
  Link: https://lkml.kernel.org/r/20250729145709.2731370-1-surenb@google.com
Link: https://lkml.kernel.org/r/20250728175355.2282375-1-surenb@google.com
Fixes: 3104138517fc ("mm: make vma cache SLAB_TYPESAFE_BY_RCU")
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reported-by: Jann Horn <jannh@google.com>
Closes: https://lore.kernel.org/all/CAG48ez0-deFbVH=E3jbkWx=X3uVbd8nWeo6kbJPQ0KoUD+m2tA@mail.gmail.com/
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Jann Horn <jannh@google.com>
Cc: Liam Howlett <liam.howlett@oracle.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/mmap_lock.h | 30 ++++++++++++++++++++++++++++++
 mm/mmap_lock.c            | 10 +++-------
 2 files changed, 33 insertions(+), 7 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 1f4f44951abe..11a078de9150 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -12,6 +12,7 @@ extern int rcuwait_wake_up(struct rcuwait *w);
 #include <linux/tracepoint-defs.h>
 #include <linux/types.h>
 #include <linux/cleanup.h>
+#include <linux/sched/mm.h>
 
 #define MMAP_LOCK_INITIALIZER(name) \
 	.mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock),
@@ -154,6 +155,10 @@ static inline void vma_refcount_put(struct vm_area_struct *vma)
  * reused and attached to a different mm before we lock it.
  * Returns the vma on success, NULL on failure to lock and EAGAIN if vma got
  * detached.
+ *
+ * WARNING! The vma passed to this function cannot be used if the function
+ * fails to lock it because in certain cases RCU lock is dropped and then
+ * reacquired. Once RCU lock is dropped the vma can be concurently freed.
  */
 static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
 						    struct vm_area_struct *vma)
@@ -183,6 +188,31 @@ static inline struct vm_area_struct *vma_start_read(struct mm_struct *mm,
 	}
 
 	rwsem_acquire_read(&vma->vmlock_dep_map, 0, 1, _RET_IP_);
+
+	/*
+	 * If vma got attached to another mm from under us, that mm is not
+	 * stable and can be freed in the narrow window after vma->vm_refcnt
+	 * is dropped and before rcuwait_wake_up(mm) is called. Grab it before
+	 * releasing vma->vm_refcnt.
+	 */
+	if (unlikely(vma->vm_mm != mm)) {
+		/* Use a copy of vm_mm in case vma is freed after we drop vm_refcnt */
+		struct mm_struct *other_mm = vma->vm_mm;
+
+		/*
+		 * __mmdrop() is a heavy operation and we don't need RCU
+		 * protection here. Release RCU lock during these operations.
+		 * We reinstate the RCU read lock as the caller expects it to
+		 * be held when this function returns even on error.
+		 */
+		rcu_read_unlock();
+		mmgrab(other_mm);
+		vma_refcount_put(vma);
+		mmdrop(other_mm);
+		rcu_read_lock();
+		return NULL;
+	}
+
 	/*
 	 * Overflow of vm_lock_seq/mm_lock_seq might produce false locked result.
 	 * False unlocked result is impossible because we modify and check
diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
index 729fb7d0dd59..b006cec8e6fe 100644
--- a/mm/mmap_lock.c
+++ b/mm/mmap_lock.c
@@ -164,8 +164,7 @@ retry:
 	 */
 
 	/* Check if the vma we locked is the right one. */
-	if (unlikely(vma->vm_mm != mm ||
-		     address < vma->vm_start || address >= vma->vm_end))
+	if (unlikely(address < vma->vm_start || address >= vma->vm_end))
 		goto inval_end_read;
 
 	rcu_read_unlock();
@@ -236,11 +235,8 @@ retry:
 		goto fallback;
 	}
 
-	/*
-	 * Verify the vma we locked belongs to the same address space and it's
-	 * not behind of the last search position.
-	 */
-	if (unlikely(vma->vm_mm != mm || from_addr >= vma->vm_end))
+	/* Verify the vma is not behind the last search position. */
+	if (unlikely(from_addr >= vma->vm_end))
 		goto fallback_unlock;
 
 	/*
-- 
cgit v1.2.3


From fcd90ad31e29d0b403f3a074a64cd7f0876175dd Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 13 Jul 2025 10:17:23 +0300
Subject: execmem: drop unused execmem_update_copy()

Patch series "x86: enable EXECMEM_ROX_CACHE for ftrace and kprobes", v3.

These patches enable use of EXECMEM_ROX_CACHE for ftrace and kprobes
allocations on x86.

They also include some ground work in execmem.

Since the execmem model for caching large ROX pages changed from the
initial assumption that the memory that is allocated from ROX cache is
always ROX to the current state where memory can be temporarily made RW
and then restored to ROX, we can stop using text poking to update it.
This also saves the hassle of trying lock text_mutex in
execmem_cache_free() when kprobes already hold that mutex.


This patch (of 8):

The execmem_update_copy() that used text poking was required when memory
allocated from ROX cache was always read-only.  Since now its permissions
can be switched to read-write there is no need in a function that updates
memory with text poking.

Remove it.

Link: https://lkml.kernel.org/r/20250713071730.4117334-1-rppt@kernel.org
Link: https://lkml.kernel.org/r/20250713071730.4117334-2-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Daniel Gomez <da.gomez@samsung.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Petr Pavlu <petr.pavlu@suse.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 include/linux/execmem.h | 13 -------------
 mm/execmem.c            |  5 -----
 2 files changed, 18 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 3be35680a54f..734fbe83d98e 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -185,19 +185,6 @@ DEFINE_FREE(execmem, void *, if (_T) execmem_free(_T));
 struct vm_struct *execmem_vmap(size_t size);
 #endif
 
-/**
- * execmem_update_copy - copy an update to executable memory
- * @dst:  destination address to update
- * @src:  source address containing the data
- * @size: how many bytes of memory shold be copied
- *
- * Copy @size bytes from @src to @dst using text poking if the memory at
- * @dst is read-only.
- *
- * Return: a pointer to @dst or NULL on error
- */
-void *execmem_update_copy(void *dst, const void *src, size_t size);
-
 /**
  * execmem_is_rox - check if execmem is read-only
  * @type - the execmem type to check
diff --git a/mm/execmem.c b/mm/execmem.c
index 627e6cf64f4f..aac211bc88c5 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -399,11 +399,6 @@ void execmem_free(void *ptr)
 		vfree(ptr);
 }
 
-void *execmem_update_copy(void *dst, const void *src, size_t size)
-{
-	return text_poke_copy(dst, src, size);
-}
-
 bool execmem_is_rox(enum execmem_type type)
 {
 	return !!(execmem_info->ranges[type].flags & EXECMEM_ROX_CACHE);
-- 
cgit v1.2.3


From 838955f64ae7582f009a3538889bb9244f37ab26 Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 13 Jul 2025 10:17:24 +0300
Subject: execmem: introduce execmem_alloc_rw()

Some callers of execmem_alloc() require the memory to be temporarily
writable even when it is allocated from ROX cache.  These callers use
execemem_make_temp_rw() right after the call to execmem_alloc().

Wrap this sequence in execmem_alloc_rw() API.

Link: https://lkml.kernel.org/r/20250713071730.4117334-3-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
Reviewed-by: Petr Pavlu <petr.pavlu@suse.com>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/kernel/alternative.c |  3 +--
 include/linux/execmem.h       | 38 ++++++++++++++++++++++----------------
 kernel/module/main.c          | 13 ++-----------
 mm/execmem.c                  | 27 ++++++++++++++++++++++++++-
 4 files changed, 51 insertions(+), 30 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/kernel/alternative.c b/arch/x86/kernel/alternative.c
index ea1d984166cd..526a5fef93ab 100644
--- a/arch/x86/kernel/alternative.c
+++ b/arch/x86/kernel/alternative.c
@@ -120,7 +120,7 @@ struct its_array its_pages;
 
 static void *__its_alloc(struct its_array *pages)
 {
-	void *page __free(execmem) = execmem_alloc(EXECMEM_MODULE_TEXT, PAGE_SIZE);
+	void *page __free(execmem) = execmem_alloc_rw(EXECMEM_MODULE_TEXT, PAGE_SIZE);
 	if (!page)
 		return NULL;
 
@@ -237,7 +237,6 @@ static void *its_alloc(void)
 	if (!page)
 		return NULL;
 
-	execmem_make_temp_rw(page, PAGE_SIZE);
 	if (pages == &its_pages)
 		set_memory_x((unsigned long)page, 1);
 
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 734fbe83d98e..8b61b05da7d5 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -67,21 +67,6 @@ enum execmem_range_flags {
  */
 void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable);
 
-/**
- * execmem_make_temp_rw - temporarily remap region with read-write
- *			  permissions
- * @ptr:	address of the region to remap
- * @size:	size of the region to remap
- *
- * Remaps a part of the cached large page in the ROX cache in the range
- * [@ptr, @ptr + @size) as writable and not executable. The caller must
- * have exclusive ownership of this range and ensure nothing will try to
- * execute code in this range.
- *
- * Return: 0 on success or negative error code on failure.
- */
-int execmem_make_temp_rw(void *ptr, size_t size);
-
 /**
  * execmem_restore_rox - restore read-only-execute permissions
  * @ptr:	address of the region to remap
@@ -95,7 +80,6 @@ int execmem_make_temp_rw(void *ptr, size_t size);
  */
 int execmem_restore_rox(void *ptr, size_t size);
 #else
-static inline int execmem_make_temp_rw(void *ptr, size_t size) { return 0; }
 static inline int execmem_restore_rox(void *ptr, size_t size) { return 0; }
 #endif
 
@@ -165,6 +149,28 @@ struct execmem_info *execmem_arch_setup(void);
  */
 void *execmem_alloc(enum execmem_type type, size_t size);
 
+/**
+ * execmem_alloc_rw - allocate writable executable memory
+ * @type: type of the allocation
+ * @size: how many bytes of memory are required
+ *
+ * Allocates memory that will contain executable code, either generated or
+ * loaded from kernel modules.
+ *
+ * Allocates memory that will contain data coupled with executable code,
+ * like data sections in kernel modules.
+ *
+ * Forces writable permissions on the allocated memory and the caller is
+ * responsible to manage the permissions afterwards.
+ *
+ * For architectures that use ROX cache the permissions will be set to R+W.
+ * For architectures that don't use ROX cache the default permissions for @type
+ * will be used as they must be writable.
+ *
+ * Return: a pointer to the allocated memory or %NULL
+ */
+void *execmem_alloc_rw(enum execmem_type type, size_t size);
+
 /**
  * execmem_free - free executable memory
  * @ptr: pointer to the memory that should be freed
diff --git a/kernel/module/main.c b/kernel/module/main.c
index 413ac6ea3702..d009326ef7bb 100644
--- a/kernel/module/main.c
+++ b/kernel/module/main.c
@@ -1292,20 +1292,11 @@ static int module_memory_alloc(struct module *mod, enum mod_mem_type type)
 	else
 		execmem_type = EXECMEM_MODULE_TEXT;
 
-	ptr = execmem_alloc(execmem_type, size);
+	ptr = execmem_alloc_rw(execmem_type, size);
 	if (!ptr)
 		return -ENOMEM;
 
-	if (execmem_is_rox(execmem_type)) {
-		int err = execmem_make_temp_rw(ptr, size);
-
-		if (err) {
-			execmem_free(ptr);
-			return -ENOMEM;
-		}
-
-		mod->mem[type].is_rox = true;
-	}
+	mod->mem[type].is_rox = execmem_is_rox(execmem_type);
 
 	/*
 	 * The pointer to these blocks of memory are stored on the module
diff --git a/mm/execmem.c b/mm/execmem.c
index aac211bc88c5..d0bf0123bce4 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -336,7 +336,7 @@ static bool execmem_cache_free(void *ptr)
 	return true;
 }
 
-int execmem_make_temp_rw(void *ptr, size_t size)
+static int execmem_force_rw(void *ptr, size_t size)
 {
 	unsigned int nr = PAGE_ALIGN(size) >> PAGE_SHIFT;
 	unsigned long addr = (unsigned long)ptr;
@@ -358,6 +358,16 @@ int execmem_restore_rox(void *ptr, size_t size)
 }
 
 #else /* CONFIG_ARCH_HAS_EXECMEM_ROX */
+/*
+ * when ROX cache is not used the permissions defined by architectures for
+ * execmem ranges that are updated before use (e.g. EXECMEM_MODULE_TEXT) must
+ * be writable anyway
+ */
+static inline int execmem_force_rw(void *ptr, size_t size)
+{
+	return 0;
+}
+
 static void *execmem_cache_alloc(struct execmem_range *range, size_t size)
 {
 	return NULL;
@@ -387,6 +397,21 @@ void *execmem_alloc(enum execmem_type type, size_t size)
 	return kasan_reset_tag(p);
 }
 
+void *execmem_alloc_rw(enum execmem_type type, size_t size)
+{
+	void *p __free(execmem) = execmem_alloc(type, size);
+	int err;
+
+	if (!p)
+		return NULL;
+
+	err = execmem_force_rw(p, size);
+	if (err)
+		return NULL;
+
+	return no_free_ptr(p);
+}
+
 void execmem_free(void *ptr)
 {
 	/*
-- 
cgit v1.2.3


From ab674b6871b049aab2e86d1d7375526368ed175a Mon Sep 17 00:00:00 2001
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Date: Sun, 13 Jul 2025 10:17:28 +0300
Subject: execmem: drop writable parameter from execmem_fill_trapping_insns()

After update of execmem_cache_free() that made memory writable before
updating it, there is no need to update read only memory, so the writable
parameter to execmem_fill_trapping_insns() is not needed.  Drop it.

Link: https://lkml.kernel.org/r/20250713071730.4117334-7-rppt@kernel.org
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Daniel Gomez <da.gomez@samsung.com>
Cc: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Cc: Petr Pavlu <petr.pavlu@suse.com>
Cc: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
---
 arch/x86/mm/init.c      | 8 ++------
 include/linux/execmem.h | 3 +--
 mm/execmem.c            | 4 ++--
 3 files changed, 5 insertions(+), 10 deletions(-)

(limited to 'include/linux')

diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 7456df985d96..dbc63f0d538f 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -1063,13 +1063,9 @@ unsigned long arch_max_swapfile_size(void)
 static struct execmem_info execmem_info __ro_after_init;
 
 #ifdef CONFIG_ARCH_HAS_EXECMEM_ROX
-void execmem_fill_trapping_insns(void *ptr, size_t size, bool writeable)
+void execmem_fill_trapping_insns(void *ptr, size_t size)
 {
-	/* fill memory with INT3 instructions */
-	if (writeable)
-		memset(ptr, INT3_INSN_OPCODE, size);
-	else
-		text_poke_set(ptr, INT3_INSN_OPCODE, size);
+	memset(ptr, INT3_INSN_OPCODE, size);
 }
 #endif
 
diff --git a/include/linux/execmem.h b/include/linux/execmem.h
index 8b61b05da7d5..7de229134e30 100644
--- a/include/linux/execmem.h
+++ b/include/linux/execmem.h
@@ -60,12 +60,11 @@ enum execmem_range_flags {
  *				 will trap
  * @ptr:	pointer to memory to fill
  * @size:	size of the range to fill
- * @writable:	is the memory poited by @ptr is writable or ROX
  *
  * A hook for architecures to fill execmem ranges with invalid instructions.
  * Architectures that use EXECMEM_ROX_CACHE must implement this.
  */
-void execmem_fill_trapping_insns(void *ptr, size_t size, bool writable);
+void execmem_fill_trapping_insns(void *ptr, size_t size);
 
 /**
  * execmem_restore_rox - restore read-only-execute permissions
diff --git a/mm/execmem.c b/mm/execmem.c
index 9abf76a63a79..1785d7f435e4 100644
--- a/mm/execmem.c
+++ b/mm/execmem.c
@@ -304,7 +304,7 @@ static int execmem_cache_populate(struct execmem_range *range, size_t size)
 		goto err_free_mem;
 
 	/* fill memory with instructions that will trap */
-	execmem_fill_trapping_insns(p, alloc_size, /* writable = */ true);
+	execmem_fill_trapping_insns(p, alloc_size);
 
 	err = set_memory_rox((unsigned long)p, vm->nr_pages);
 	if (err)
@@ -363,7 +363,7 @@ static int __execmem_cache_free(struct ma_state *mas, void *ptr, gfp_t gfp_mask)
 	if (err)
 		return err;
 
-	execmem_fill_trapping_insns(ptr, size, /* writable = */ true);
+	execmem_fill_trapping_insns(ptr, size);
 	execmem_restore_rox(ptr, size);
 
 	err = execmem_cache_add_locked(ptr, size, gfp_mask);
-- 
cgit v1.2.3


From bb5b0b4317c9516bdc5e9a4235e3b5f1a73b7e48 Mon Sep 17 00:00:00 2001
From: Joshua Kinard <kumba@gentoo.org>
Date: Mon, 21 Jul 2025 13:00:51 -0400
Subject: rtc: ds1685: Update Joshua Kinard's email address.

I am switching my address to a personal domain, so need to update the
driver's files and the entry in MAINTAINERS.

Signed-off-by: Joshua Kinard <kumba@gentoo.org>
Link: https://lore.kernel.org/r/20250721170051.32407-1-kumba@gentoo.org
Signed-off-by: Alexandre Belloni <alexandre.belloni@bootlin.com>
---
 MAINTAINERS                | 2 +-
 drivers/rtc/rtc-ds1685.c   | 4 ++--
 include/linux/rtc/ds1685.h | 2 +-
 3 files changed, 4 insertions(+), 4 deletions(-)

(limited to 'include/linux')

diff --git a/MAINTAINERS b/MAINTAINERS
index a92290fffa16..536befd32be8 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -6608,7 +6608,7 @@ S:	Supported
 F:	drivers/input/keyboard/dlink-dir685-touchkeys.c
 
 DALLAS/MAXIM DS1685-FAMILY REAL TIME CLOCK
-M:	Joshua Kinard <kumba@gentoo.org>
+M:	Joshua Kinard <linux@kumba.dev>
 S:	Maintained
 F:	drivers/rtc/rtc-ds1685.c
 F:	include/linux/rtc/ds1685.h
diff --git a/drivers/rtc/rtc-ds1685.c b/drivers/rtc/rtc-ds1685.c
index 38e25f63597a..97423f1d0361 100644
--- a/drivers/rtc/rtc-ds1685.c
+++ b/drivers/rtc/rtc-ds1685.c
@@ -3,7 +3,7 @@
  * An rtc driver for the Dallas/Maxim DS1685/DS1687 and related real-time
  * chips.
  *
- * Copyright (C) 2011-2014 Joshua Kinard <kumba@gentoo.org>.
+ * Copyright (C) 2011-2014 Joshua Kinard <linux@kumba.dev>.
  * Copyright (C) 2009 Matthias Fuchs <matthias.fuchs@esd-electronics.com>.
  *
  * References:
@@ -1436,7 +1436,7 @@ EXPORT_SYMBOL_GPL(ds1685_rtc_poweroff);
 /* ----------------------------------------------------------------------- */
 
 
-MODULE_AUTHOR("Joshua Kinard <kumba@gentoo.org>");
+MODULE_AUTHOR("Joshua Kinard <linux@kumba.dev>");
 MODULE_AUTHOR("Matthias Fuchs <matthias.fuchs@esd-electronics.com>");
 MODULE_DESCRIPTION("Dallas/Maxim DS1685/DS1687-series RTC driver");
 MODULE_LICENSE("GPL");
diff --git a/include/linux/rtc/ds1685.h b/include/linux/rtc/ds1685.h
index 5a41c3bbcbe3..01da4582db6d 100644
--- a/include/linux/rtc/ds1685.h
+++ b/include/linux/rtc/ds1685.h
@@ -8,7 +8,7 @@
  * include larger, battery-backed NV-SRAM, burst-mode access, and an RTC
  * write counter.
  *
- * Copyright (C) 2011-2014 Joshua Kinard <kumba@gentoo.org>.
+ * Copyright (C) 2011-2014 Joshua Kinard <linux@kumba.dev>.
  * Copyright (C) 2009 Matthias Fuchs <matthias.fuchs@esd-electronics.com>.
  *
  * References:
-- 
cgit v1.2.3


From 86624ba3b522b6512def25534341da93356c8da4 Mon Sep 17 00:00:00 2001
From: Jason Gunthorpe <jgg@nvidia.com>
Date: Mon, 14 Jul 2025 13:08:25 -0300
Subject: vfio/pci: Do vf_token checks for VFIO_DEVICE_BIND_IOMMUFD

This was missed during the initial implementation. The VFIO PCI encodes
the vf_token inside the device name when opening the device from the group
FD, something like:

  "0000:04:10.0 vf_token=bd8d9d2b-5a5f-4f5a-a211-f591514ba1f3"

This is used to control access to a VF unless there is co-ordination with
the owner of the PF.

Since we no longer have a device name in the cdev path, pass the token
directly through VFIO_DEVICE_BIND_IOMMUFD using an optional field
indicated by VFIO_DEVICE_BIND_FLAG_TOKEN.

Fixes: 5fcc26969a16 ("vfio: Add VFIO_DEVICE_BIND_IOMMUFD")
Tested-by: Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>
Reviewed-by: Yi Liu <yi.l.liu@intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/0-v3-bdd8716e85fe+3978a-vfio_token_jgg@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
---
 drivers/vfio/device_cdev.c                     | 38 ++++++++++++++++++++++++--
 drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c |  1 +
 drivers/vfio/pci/mlx5/main.c                   |  1 +
 drivers/vfio/pci/nvgrace-gpu/main.c            |  2 ++
 drivers/vfio/pci/pds/vfio_dev.c                |  1 +
 drivers/vfio/pci/qat/main.c                    |  1 +
 drivers/vfio/pci/vfio_pci.c                    |  1 +
 drivers/vfio/pci/vfio_pci_core.c               | 22 +++++++++------
 drivers/vfio/pci/virtio/main.c                 |  3 ++
 include/linux/vfio.h                           |  4 +++
 include/linux/vfio_pci_core.h                  |  2 ++
 include/uapi/linux/vfio.h                      | 12 +++++++-
 12 files changed, 76 insertions(+), 12 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c
index 281a8dc3ed49..480cac3a0c27 100644
--- a/drivers/vfio/device_cdev.c
+++ b/drivers/vfio/device_cdev.c
@@ -60,22 +60,50 @@ static void vfio_df_get_kvm_safe(struct vfio_device_file *df)
 	spin_unlock(&df->kvm_ref_lock);
 }
 
+static int vfio_df_check_token(struct vfio_device *device,
+			       const struct vfio_device_bind_iommufd *bind)
+{
+	uuid_t uuid;
+
+	if (!device->ops->match_token_uuid) {
+		if (bind->flags & VFIO_DEVICE_BIND_FLAG_TOKEN)
+			return -EINVAL;
+		return 0;
+	}
+
+	if (!(bind->flags & VFIO_DEVICE_BIND_FLAG_TOKEN))
+		return device->ops->match_token_uuid(device, NULL);
+
+	if (copy_from_user(&uuid, u64_to_user_ptr(bind->token_uuid_ptr),
+			   sizeof(uuid)))
+		return -EFAULT;
+	return device->ops->match_token_uuid(device, &uuid);
+}
+
 long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df,
 				struct vfio_device_bind_iommufd __user *arg)
 {
+	const u32 VALID_FLAGS = VFIO_DEVICE_BIND_FLAG_TOKEN;
 	struct vfio_device *device = df->device;
 	struct vfio_device_bind_iommufd bind;
 	unsigned long minsz;
+	u32 user_size;
 	int ret;
 
 	static_assert(__same_type(arg->out_devid, df->devid));
 
 	minsz = offsetofend(struct vfio_device_bind_iommufd, out_devid);
 
-	if (copy_from_user(&bind, arg, minsz))
-		return -EFAULT;
+	ret = get_user(user_size, &arg->argsz);
+	if (ret)
+		return ret;
+	if (user_size < minsz)
+		return -EINVAL;
+	ret = copy_struct_from_user(&bind, minsz, arg, user_size);
+	if (ret)
+		return ret;
 
-	if (bind.argsz < minsz || bind.flags || bind.iommufd < 0)
+	if (bind.iommufd < 0 || bind.flags & ~VALID_FLAGS)
 		return -EINVAL;
 
 	/* BIND_IOMMUFD only allowed for cdev fds */
@@ -93,6 +121,10 @@ long vfio_df_ioctl_bind_iommufd(struct vfio_device_file *df,
 		goto out_unlock;
 	}
 
+	ret = vfio_df_check_token(device, &bind);
+	if (ret)
+		goto out_unlock;
+
 	df->iommufd = iommufd_ctx_from_fd(bind.iommufd);
 	if (IS_ERR(df->iommufd)) {
 		ret = PTR_ERR(df->iommufd);
diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 2149f49aeec7..397f5e445136 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -1583,6 +1583,7 @@ static const struct vfio_device_ops hisi_acc_vfio_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index 93f894fe60d2..7ec47e736a8e 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -1372,6 +1372,7 @@ static const struct vfio_device_ops mlx5vf_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index e5ac39c4cc6b..d95761dcdd58 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -696,6 +696,7 @@ static const struct vfio_device_ops nvgrace_gpu_pci_ops = {
 	.mmap		= nvgrace_gpu_mmap,
 	.request	= vfio_pci_core_request,
 	.match		= vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd	= vfio_iommufd_physical_bind,
 	.unbind_iommufd	= vfio_iommufd_physical_unbind,
 	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
@@ -715,6 +716,7 @@ static const struct vfio_device_ops nvgrace_gpu_pci_core_ops = {
 	.mmap		= vfio_pci_core_mmap,
 	.request	= vfio_pci_core_request,
 	.match		= vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd	= vfio_iommufd_physical_bind,
 	.unbind_iommufd	= vfio_iommufd_physical_unbind,
 	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index f6e0253a8a14..f3ccb0008f67 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -201,6 +201,7 @@ static const struct vfio_device_ops pds_vfio_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/qat/main.c b/drivers/vfio/pci/qat/main.c
index 845ed15b6771..5cce6b0b8d2f 100644
--- a/drivers/vfio/pci/qat/main.c
+++ b/drivers/vfio/pci/qat/main.c
@@ -614,6 +614,7 @@ static const struct vfio_device_ops qat_vf_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 5ba39f7623bb..ac10f14417f2 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -138,6 +138,7 @@ static const struct vfio_device_ops vfio_pci_ops = {
 	.mmap		= vfio_pci_core_mmap,
 	.request	= vfio_pci_core_request,
 	.match		= vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd	= vfio_iommufd_physical_bind,
 	.unbind_iommufd	= vfio_iommufd_physical_unbind,
 	.attach_ioas	= vfio_iommufd_physical_attach_ioas,
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 261a6dc5a5fc..fad410cf91bc 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -1821,9 +1821,13 @@ void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count)
 }
 EXPORT_SYMBOL_GPL(vfio_pci_core_request);
 
-static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
-				      bool vf_token, uuid_t *uuid)
+int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev,
+				   const uuid_t *uuid)
+
 {
+	struct vfio_pci_core_device *vdev =
+		container_of(core_vdev, struct vfio_pci_core_device, vdev);
+
 	/*
 	 * There's always some degree of trust or collaboration between SR-IOV
 	 * PF and VFs, even if just that the PF hosts the SR-IOV capability and
@@ -1854,7 +1858,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 		bool match;
 
 		if (!pf_vdev) {
-			if (!vf_token)
+			if (!uuid)
 				return 0; /* PF is not vfio-pci, no VF token */
 
 			pci_info_ratelimited(vdev->pdev,
@@ -1862,7 +1866,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 			return -EINVAL;
 		}
 
-		if (!vf_token) {
+		if (!uuid) {
 			pci_info_ratelimited(vdev->pdev,
 				"VF token required to access device\n");
 			return -EACCES;
@@ -1880,7 +1884,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 	} else if (vdev->vf_token) {
 		mutex_lock(&vdev->vf_token->lock);
 		if (vdev->vf_token->users) {
-			if (!vf_token) {
+			if (!uuid) {
 				mutex_unlock(&vdev->vf_token->lock);
 				pci_info_ratelimited(vdev->pdev,
 					"VF token required to access device\n");
@@ -1893,12 +1897,12 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 					"Incorrect VF token provided for device\n");
 				return -EACCES;
 			}
-		} else if (vf_token) {
+		} else if (uuid) {
 			uuid_copy(&vdev->vf_token->uuid, uuid);
 		}
 
 		mutex_unlock(&vdev->vf_token->lock);
-	} else if (vf_token) {
+	} else if (uuid) {
 		pci_info_ratelimited(vdev->pdev,
 			"VF token incorrectly provided, not a PF or VF\n");
 		return -EINVAL;
@@ -1906,6 +1910,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_core_device *vdev,
 
 	return 0;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_core_match_token_uuid);
 
 #define VF_TOKEN_ARG "vf_token="
 
@@ -1952,7 +1957,8 @@ int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf)
 		}
 	}
 
-	ret = vfio_pci_validate_vf_token(vdev, vf_token, &uuid);
+	ret = core_vdev->ops->match_token_uuid(core_vdev,
+					       vf_token ? &uuid : NULL);
 	if (ret)
 		return ret;
 
diff --git a/drivers/vfio/pci/virtio/main.c b/drivers/vfio/pci/virtio/main.c
index 515fe1b9f94d..8084f3e36a9f 100644
--- a/drivers/vfio/pci/virtio/main.c
+++ b/drivers/vfio/pci/virtio/main.c
@@ -94,6 +94,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_lm_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
@@ -114,6 +115,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_tran_lm_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
@@ -134,6 +136,7 @@ static const struct vfio_device_ops virtiovf_vfio_pci_ops = {
 	.mmap = vfio_pci_core_mmap,
 	.request = vfio_pci_core_request,
 	.match = vfio_pci_core_match,
+	.match_token_uuid = vfio_pci_core_match_token_uuid,
 	.bind_iommufd = vfio_iommufd_physical_bind,
 	.unbind_iommufd = vfio_iommufd_physical_unbind,
 	.attach_ioas = vfio_iommufd_physical_attach_ioas,
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 707b00772ce1..eb563f538dee 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -105,6 +105,9 @@ struct vfio_device {
  * @match: Optional device name match callback (return: 0 for no-match, >0 for
  *         match, -errno for abort (ex. match with insufficient or incorrect
  *         additional args)
+ * @match_token_uuid: Optional device token match/validation. Return 0
+ *         if the uuid is valid for the device, -errno otherwise. uuid is NULL
+ *         if none was provided.
  * @dma_unmap: Called when userspace unmaps IOVA from the container
  *             this device is attached to.
  * @device_feature: Optional, fill in the VFIO_DEVICE_FEATURE ioctl
@@ -132,6 +135,7 @@ struct vfio_device_ops {
 	int	(*mmap)(struct vfio_device *vdev, struct vm_area_struct *vma);
 	void	(*request)(struct vfio_device *vdev, unsigned int count);
 	int	(*match)(struct vfio_device *vdev, char *buf);
+	int	(*match_token_uuid)(struct vfio_device *vdev, const uuid_t *uuid);
 	void	(*dma_unmap)(struct vfio_device *vdev, u64 iova, u64 length);
 	int	(*device_feature)(struct vfio_device *device, u32 flags,
 				  void __user *arg, size_t argsz);
diff --git a/include/linux/vfio_pci_core.h b/include/linux/vfio_pci_core.h
index fbb472dd99b3..f541044e42a2 100644
--- a/include/linux/vfio_pci_core.h
+++ b/include/linux/vfio_pci_core.h
@@ -122,6 +122,8 @@ ssize_t vfio_pci_core_write(struct vfio_device *core_vdev, const char __user *bu
 int vfio_pci_core_mmap(struct vfio_device *core_vdev, struct vm_area_struct *vma);
 void vfio_pci_core_request(struct vfio_device *core_vdev, unsigned int count);
 int vfio_pci_core_match(struct vfio_device *core_vdev, char *buf);
+int vfio_pci_core_match_token_uuid(struct vfio_device *core_vdev,
+				   const uuid_t *uuid);
 int vfio_pci_core_enable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_disable(struct vfio_pci_core_device *vdev);
 void vfio_pci_core_finish_enable(struct vfio_pci_core_device *vdev);
diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h
index 5764f315137f..75100bf009ba 100644
--- a/include/uapi/linux/vfio.h
+++ b/include/uapi/linux/vfio.h
@@ -905,10 +905,12 @@ struct vfio_device_feature {
  * VFIO_DEVICE_BIND_IOMMUFD - _IOR(VFIO_TYPE, VFIO_BASE + 18,
  *				   struct vfio_device_bind_iommufd)
  * @argsz:	 User filled size of this data.
- * @flags:	 Must be 0.
+ * @flags:	 Must be 0 or a bit flags of VFIO_DEVICE_BIND_*
  * @iommufd:	 iommufd to bind.
  * @out_devid:	 The device id generated by this bind. devid is a handle for
  *		 this device/iommufd bond and can be used in IOMMUFD commands.
+ * @token_uuid_ptr: Valid if VFIO_DEVICE_BIND_FLAG_TOKEN. Points to a 16 byte
+ *                  UUID in the same format as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN.
  *
  * Bind a vfio_device to the specified iommufd.
  *
@@ -917,13 +919,21 @@ struct vfio_device_feature {
  *
  * Unbind is automatically conducted when device fd is closed.
  *
+ * A token is sometimes required to open the device, unless this is known to be
+ * needed VFIO_DEVICE_BIND_FLAG_TOKEN should not be set and token_uuid_ptr is
+ * ignored. The only case today is a PF/VF relationship where the VF bind must
+ * be provided the same token as VFIO_DEVICE_FEATURE_PCI_VF_TOKEN provided to
+ * the PF.
+ *
  * Return: 0 on success, -errno on failure.
  */
 struct vfio_device_bind_iommufd {
 	__u32		argsz;
 	__u32		flags;
+#define VFIO_DEVICE_BIND_FLAG_TOKEN (1 << 0)
 	__s32		iommufd;
 	__u32		out_devid;
+	__aligned_u64	token_uuid_ptr;
 };
 
 #define VFIO_DEVICE_BIND_IOMMUFD	_IO(VFIO_TYPE, VFIO_BASE + 18)
-- 
cgit v1.2.3


From 397a46c9aa3343e8efe6847bdaa124945bab1de4 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Fri, 25 Jul 2025 09:46:50 +0200
Subject: gpio: remove legacy GPIO line value setter callbacks

With no more users of the legacy GPIO line value setters - .set() and
.set_multiple() - we can now remove them from the kernel.

Link: https://lore.kernel.org/r/20250725074651.14002-1-brgl@bgdev.pl
Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 drivers/gpio/gpiolib.c      | 27 ++++++---------------------
 include/linux/gpio/driver.h |  7 -------
 2 files changed, 6 insertions(+), 28 deletions(-)

(limited to 'include/linux')

diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index a93d2a9355e2..9ac4c23d656a 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -1037,11 +1037,6 @@ int gpiochip_add_data_with_key(struct gpio_chip *gc, void *data,
 	int base = 0;
 	int ret;
 
-	/* Only allow one set() and one set_multiple(). */
-	if ((gc->set && gc->set_rv) ||
-	    (gc->set_multiple && gc->set_multiple_rv))
-		return -EINVAL;
-
 	/*
 	 * First: allocate and populate the internal stat container, and
 	 * set up the struct device.
@@ -2891,19 +2886,14 @@ static int gpiochip_set(struct gpio_chip *gc, unsigned int offset, int value)
 
 	lockdep_assert_held(&gc->gpiodev->srcu);
 
-	if (WARN_ON(unlikely(!gc->set && !gc->set_rv)))
+	if (WARN_ON(unlikely(!gc->set_rv)))
 		return -EOPNOTSUPP;
 
-	if (gc->set_rv) {
-		ret = gc->set_rv(gc, offset, value);
-		if (ret > 0)
-			ret = -EBADE;
-
-		return ret;
-	}
+	ret = gc->set_rv(gc, offset, value);
+	if (ret > 0)
+		ret = -EBADE;
 
-	gc->set(gc, offset, value);
-	return 0;
+	return ret;
 }
 
 static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
@@ -2919,7 +2909,7 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 	 * output-only, but if there is then not even a .set() operation it
 	 * is pretty tricky to drive the output line.
 	 */
-	if (!guard.gc->set && !guard.gc->set_rv && !guard.gc->direction_output) {
+	if (!guard.gc->set_rv && !guard.gc->direction_output) {
 		gpiod_warn(desc,
 			   "%s: missing set() and direction_output() operations\n",
 			   __func__);
@@ -3673,11 +3663,6 @@ static int gpiochip_set_multiple(struct gpio_chip *gc,
 		return ret;
 	}
 
-	if (gc->set_multiple) {
-		gc->set_multiple(gc, mask, bits);
-		return 0;
-	}
-
 	/* set outputs if the corresponding mask bit is set */
 	for_each_set_bit(i, mask, gc->ngpio) {
 		ret = gpiochip_set(gc, i, test_bit(i, bits));
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 4b984e8f8fcd..90567dde7d8e 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -347,8 +347,6 @@ struct gpio_irq_chip {
  * @get: returns value for signal "offset", 0=low, 1=high, or negative error
  * @get_multiple: reads values for multiple signals defined by "mask" and
  *	stores them in "bits", returns 0 on success or negative error
- * @set: **DEPRECATED** - please use set_rv() instead
- * @set_multiple: **DEPRECATED** - please use set_multiple_rv() instead
  * @set_rv: assigns output value for signal "offset", returns 0 on success or
  *          negative error value
  * @set_multiple_rv: assigns output values for multiple signals defined by
@@ -445,11 +443,6 @@ struct gpio_chip {
 	int			(*get_multiple)(struct gpio_chip *gc,
 						unsigned long *mask,
 						unsigned long *bits);
-	void			(*set)(struct gpio_chip *gc,
-						unsigned int offset, int value);
-	void			(*set_multiple)(struct gpio_chip *gc,
-						unsigned long *mask,
-						unsigned long *bits);
 	int			(*set_rv)(struct gpio_chip *gc,
 					  unsigned int offset,
 					  int value);
-- 
cgit v1.2.3


From d9d87d90cc0b10cd56ae353f50b11417e7d21712 Mon Sep 17 00:00:00 2001
From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Date: Thu, 17 Jul 2025 15:21:26 +0200
Subject: treewide: rename GPIO set callbacks back to their original names

The conversion of all GPIO drivers to using the .set_rv() and
.set_multiple_rv() callbacks from struct gpio_chip (which - unlike their
predecessors - return an integer and allow the controller drivers to
indicate failures to users) is now complete and the legacy ones have
been removed. Rename the new callbacks back to their original names in
one sweeping change.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
---
 arch/arm/common/sa1111.c                           |  4 ++--
 arch/arm/common/scoop.c                            |  2 +-
 arch/arm/mach-s3c/gpio-samsung.c                   |  2 +-
 arch/arm/mach-sa1100/assabet.c                     |  2 +-
 arch/arm/mach-sa1100/neponset.c                    |  2 +-
 arch/arm/plat-orion/gpio.c                         |  2 +-
 arch/m68k/coldfire/gpio.c                          |  2 +-
 arch/mips/alchemy/common/gpiolib.c                 |  6 +++---
 arch/mips/bcm63xx/gpio.c                           |  2 +-
 arch/mips/kernel/gpio_txx9.c                       |  2 +-
 arch/mips/rb532/gpio.c                             |  2 +-
 arch/mips/txx9/generic/setup.c                     |  2 +-
 arch/powerpc/platforms/44x/gpio.c                  |  2 +-
 arch/powerpc/platforms/52xx/mpc52xx_gpt.c          |  2 +-
 arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c     |  2 +-
 arch/powerpc/platforms/8xx/cpm1.c                  |  4 ++--
 arch/powerpc/sysdev/cpm_common.c                   |  2 +-
 drivers/bcma/driver_gpio.c                         |  2 +-
 drivers/gpio/gpio-74x164.c                         |  4 ++--
 drivers/gpio/gpio-adnp.c                           |  2 +-
 drivers/gpio/gpio-adp5520.c                        |  2 +-
 drivers/gpio/gpio-adp5585.c                        |  2 +-
 drivers/gpio/gpio-aggregator.c                     |  4 ++--
 drivers/gpio/gpio-altera-a10sr.c                   |  2 +-
 drivers/gpio/gpio-altera.c                         |  2 +-
 drivers/gpio/gpio-amd-fch.c                        |  2 +-
 drivers/gpio/gpio-amd8111.c                        |  2 +-
 drivers/gpio/gpio-arizona.c                        |  2 +-
 drivers/gpio/gpio-aspeed-sgpio.c                   |  2 +-
 drivers/gpio/gpio-aspeed.c                         |  2 +-
 drivers/gpio/gpio-bcm-kona.c                       |  2 +-
 drivers/gpio/gpio-bd71815.c                        |  2 +-
 drivers/gpio/gpio-bd71828.c                        |  2 +-
 drivers/gpio/gpio-bd9571mwv.c                      |  2 +-
 drivers/gpio/gpio-bt8xx.c                          |  2 +-
 drivers/gpio/gpio-cgbc.c                           |  2 +-
 drivers/gpio/gpio-creg-snps.c                      |  2 +-
 drivers/gpio/gpio-cros-ec.c                        |  2 +-
 drivers/gpio/gpio-crystalcove.c                    |  2 +-
 drivers/gpio/gpio-cs5535.c                         |  2 +-
 drivers/gpio/gpio-da9052.c                         |  2 +-
 drivers/gpio/gpio-da9055.c                         |  2 +-
 drivers/gpio/gpio-davinci.c                        |  2 +-
 drivers/gpio/gpio-dln2.c                           |  2 +-
 drivers/gpio/gpio-eic-sprd.c                       |  2 +-
 drivers/gpio/gpio-em.c                             |  2 +-
 drivers/gpio/gpio-exar.c                           |  2 +-
 drivers/gpio/gpio-f7188x.c                         |  2 +-
 drivers/gpio/gpio-graniterapids.c                  |  2 +-
 drivers/gpio/gpio-gw-pld.c                         |  2 +-
 drivers/gpio/gpio-htc-egpio.c                      |  2 +-
 drivers/gpio/gpio-ich.c                            |  2 +-
 drivers/gpio/gpio-imx-scu.c                        |  2 +-
 drivers/gpio/gpio-it87.c                           |  2 +-
 drivers/gpio/gpio-janz-ttl.c                       |  2 +-
 drivers/gpio/gpio-kempld.c                         |  2 +-
 drivers/gpio/gpio-latch.c                          |  4 ++--
 drivers/gpio/gpio-ljca.c                           |  2 +-
 drivers/gpio/gpio-logicvc.c                        |  2 +-
 drivers/gpio/gpio-loongson-64bit.c                 |  2 +-
 drivers/gpio/gpio-loongson.c                       |  2 +-
 drivers/gpio/gpio-lp3943.c                         |  2 +-
 drivers/gpio/gpio-lp873x.c                         |  2 +-
 drivers/gpio/gpio-lp87565.c                        |  2 +-
 drivers/gpio/gpio-lpc18xx.c                        |  2 +-
 drivers/gpio/gpio-lpc32xx.c                        | 10 ++++-----
 drivers/gpio/gpio-macsmc.c                         |  2 +-
 drivers/gpio/gpio-madera.c                         |  2 +-
 drivers/gpio/gpio-max730x.c                        |  2 +-
 drivers/gpio/gpio-max732x.c                        |  4 ++--
 drivers/gpio/gpio-max77620.c                       |  2 +-
 drivers/gpio/gpio-max77650.c                       |  2 +-
 drivers/gpio/gpio-max77759.c                       |  2 +-
 drivers/gpio/gpio-mb86s7x.c                        |  2 +-
 drivers/gpio/gpio-mc33880.c                        |  2 +-
 drivers/gpio/gpio-ml-ioh.c                         |  2 +-
 drivers/gpio/gpio-mm-lantiq.c                      |  2 +-
 drivers/gpio/gpio-mmio.c                           | 24 +++++++++++-----------
 drivers/gpio/gpio-mockup.c                         |  4 ++--
 drivers/gpio/gpio-moxtet.c                         |  2 +-
 drivers/gpio/gpio-mpc5200.c                        |  4 ++--
 drivers/gpio/gpio-mpfs.c                           |  2 +-
 drivers/gpio/gpio-mpsse.c                          |  4 ++--
 drivers/gpio/gpio-msc313.c                         |  2 +-
 drivers/gpio/gpio-mvebu.c                          |  2 +-
 drivers/gpio/gpio-nomadik.c                        |  2 +-
 drivers/gpio/gpio-npcm-sgpio.c                     |  4 ++--
 drivers/gpio/gpio-octeon.c                         |  2 +-
 drivers/gpio/gpio-omap.c                           |  4 ++--
 drivers/gpio/gpio-palmas.c                         |  2 +-
 drivers/gpio/gpio-pca953x.c                        |  4 ++--
 drivers/gpio/gpio-pca9570.c                        |  2 +-
 drivers/gpio/gpio-pcf857x.c                        |  4 ++--
 drivers/gpio/gpio-pch.c                            |  2 +-
 drivers/gpio/gpio-pl061.c                          |  2 +-
 drivers/gpio/gpio-pxa.c                            |  2 +-
 drivers/gpio/gpio-raspberrypi-exp.c                |  2 +-
 drivers/gpio/gpio-rc5t583.c                        |  2 +-
 drivers/gpio/gpio-rcar.c                           |  4 ++--
 drivers/gpio/gpio-rdc321x.c                        |  2 +-
 drivers/gpio/gpio-reg.c                            |  6 +++---
 drivers/gpio/gpio-regmap.c                         |  4 ++--
 drivers/gpio/gpio-rockchip.c                       |  2 +-
 drivers/gpio/gpio-rtd.c                            |  2 +-
 drivers/gpio/gpio-sa1100.c                         |  2 +-
 drivers/gpio/gpio-sama5d2-piobu.c                  |  2 +-
 drivers/gpio/gpio-sch.c                            |  2 +-
 drivers/gpio/gpio-sch311x.c                        |  2 +-
 drivers/gpio/gpio-sim.c                            |  4 ++--
 drivers/gpio/gpio-siox.c                           |  2 +-
 drivers/gpio/gpio-spear-spics.c                    |  2 +-
 drivers/gpio/gpio-sprd.c                           |  2 +-
 drivers/gpio/gpio-stmpe.c                          |  2 +-
 drivers/gpio/gpio-stp-xway.c                       |  2 +-
 drivers/gpio/gpio-syscon.c                         |  4 ++--
 drivers/gpio/gpio-tangier.c                        |  2 +-
 drivers/gpio/gpio-tc3589x.c                        |  2 +-
 drivers/gpio/gpio-tegra.c                          |  2 +-
 drivers/gpio/gpio-tegra186.c                       |  2 +-
 drivers/gpio/gpio-thunderx.c                       |  4 ++--
 drivers/gpio/gpio-timberdale.c                     |  2 +-
 drivers/gpio/gpio-tpic2810.c                       |  4 ++--
 drivers/gpio/gpio-tps65086.c                       |  2 +-
 drivers/gpio/gpio-tps65218.c                       |  2 +-
 drivers/gpio/gpio-tps65219.c                       |  4 ++--
 drivers/gpio/gpio-tps6586x.c                       |  2 +-
 drivers/gpio/gpio-tps65910.c                       |  2 +-
 drivers/gpio/gpio-tps65912.c                       |  2 +-
 drivers/gpio/gpio-tps68470.c                       |  2 +-
 drivers/gpio/gpio-tqmx86.c                         |  2 +-
 drivers/gpio/gpio-ts4900.c                         |  2 +-
 drivers/gpio/gpio-ts5500.c                         |  2 +-
 drivers/gpio/gpio-twl4030.c                        |  2 +-
 drivers/gpio/gpio-twl6040.c                        |  2 +-
 drivers/gpio/gpio-uniphier.c                       |  4 ++--
 drivers/gpio/gpio-viperboard.c                     |  4 ++--
 drivers/gpio/gpio-virtio.c                         |  2 +-
 drivers/gpio/gpio-vx855.c                          |  2 +-
 drivers/gpio/gpio-wcd934x.c                        |  2 +-
 drivers/gpio/gpio-wcove.c                          |  2 +-
 drivers/gpio/gpio-winbond.c                        |  2 +-
 drivers/gpio/gpio-wm831x.c                         |  2 +-
 drivers/gpio/gpio-wm8350.c                         |  2 +-
 drivers/gpio/gpio-wm8994.c                         |  2 +-
 drivers/gpio/gpio-xgene.c                          |  2 +-
 drivers/gpio/gpio-xilinx.c                         |  4 ++--
 drivers/gpio/gpio-xlp.c                            |  2 +-
 drivers/gpio/gpio-xra1403.c                        |  2 +-
 drivers/gpio/gpio-xtensa.c                         |  2 +-
 drivers/gpio/gpio-zevio.c                          |  2 +-
 drivers/gpio/gpio-zynq.c                           |  2 +-
 drivers/gpio/gpio-zynqmp-modepin.c                 |  2 +-
 drivers/gpio/gpiolib.c                             | 10 ++++-----
 drivers/gpu/drm/bridge/ti-sn65dsi86.c              |  2 +-
 drivers/hid/hid-cp2112.c                           |  2 +-
 drivers/hid/hid-mcp2200.c                          |  4 ++--
 drivers/hid/hid-mcp2221.c                          |  2 +-
 drivers/hwmon/ltc2992.c                            |  4 ++--
 drivers/hwmon/pmbus/ucd9000.c                      |  2 +-
 drivers/i2c/muxes/i2c-mux-ltc4306.c                |  2 +-
 drivers/iio/adc/ad4130.c                           |  2 +-
 drivers/iio/adc/ad4170-4.c                         |  2 +-
 drivers/iio/adc/ad7768-1.c                         |  2 +-
 drivers/iio/adc/rohm-bd79124.c                     |  4 ++--
 drivers/iio/adc/ti-ads7950.c                       |  2 +-
 drivers/iio/addac/ad74115.c                        |  2 +-
 drivers/iio/addac/ad74413r.c                       |  4 ++--
 drivers/iio/dac/ad5592r-base.c                     |  2 +-
 drivers/input/keyboard/adp5588-keys.c              |  2 +-
 drivers/input/touchscreen/ad7879.c                 |  2 +-
 drivers/leds/blink/leds-lgm-sso.c                  |  2 +-
 drivers/leds/leds-pca9532.c                        |  2 +-
 drivers/leds/leds-pca955x.c                        |  2 +-
 drivers/leds/leds-tca6507.c                        |  2 +-
 drivers/media/dvb-frontends/cxd2820r_core.c        |  2 +-
 drivers/media/i2c/ds90ub913.c                      |  2 +-
 drivers/media/i2c/ds90ub953.c                      |  2 +-
 drivers/media/i2c/max9286.c                        |  2 +-
 drivers/media/i2c/max96717.c                       |  2 +-
 drivers/media/pci/solo6x10/solo6x10-gpio.c         |  2 +-
 drivers/mfd/sm501.c                                |  2 +-
 drivers/mfd/tps65010.c                             |  2 +-
 drivers/mfd/ucb1x00-core.c                         |  2 +-
 drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c    |  2 +-
 drivers/misc/ti_fpc202.c                           |  2 +-
 drivers/net/can/spi/mcp251x.c                      |  4 ++--
 drivers/net/dsa/mt7530.c                           |  2 +-
 drivers/net/dsa/vitesse-vsc73xx-core.c             |  2 +-
 drivers/net/phy/qcom/qca807x.c                     |  2 +-
 drivers/pinctrl/actions/pinctrl-owl.c              |  2 +-
 drivers/pinctrl/bcm/pinctrl-bcm2835.c              |  4 ++--
 drivers/pinctrl/bcm/pinctrl-iproc-gpio.c           |  2 +-
 drivers/pinctrl/bcm/pinctrl-nsp-gpio.c             |  2 +-
 drivers/pinctrl/cirrus/pinctrl-cs42l43.c           |  2 +-
 drivers/pinctrl/cirrus/pinctrl-lochnagar.c         |  2 +-
 drivers/pinctrl/intel/pinctrl-baytrail.c           |  2 +-
 drivers/pinctrl/intel/pinctrl-cherryview.c         |  2 +-
 drivers/pinctrl/intel/pinctrl-intel.c              |  2 +-
 drivers/pinctrl/intel/pinctrl-lynxpoint.c          |  2 +-
 drivers/pinctrl/mediatek/pinctrl-airoha.c          |  2 +-
 drivers/pinctrl/mediatek/pinctrl-moore.c           |  2 +-
 drivers/pinctrl/mediatek/pinctrl-mtk-common.c      |  2 +-
 drivers/pinctrl/mediatek/pinctrl-paris.c           |  2 +-
 drivers/pinctrl/meson/pinctrl-amlogic-a4.c         |  2 +-
 drivers/pinctrl/meson/pinctrl-meson.c              |  2 +-
 drivers/pinctrl/mvebu/pinctrl-armada-37xx.c        |  2 +-
 drivers/pinctrl/nomadik/pinctrl-abx500.c           |  2 +-
 drivers/pinctrl/nuvoton/pinctrl-ma35.c             |  2 +-
 drivers/pinctrl/pinctrl-amd.c                      |  2 +-
 drivers/pinctrl/pinctrl-amdisp.c                   |  2 +-
 drivers/pinctrl/pinctrl-apple-gpio.c               |  2 +-
 drivers/pinctrl/pinctrl-as3722.c                   |  2 +-
 drivers/pinctrl/pinctrl-at91-pio4.c                |  4 ++--
 drivers/pinctrl/pinctrl-at91.c                     |  4 ++--
 drivers/pinctrl/pinctrl-aw9523.c                   |  4 ++--
 drivers/pinctrl/pinctrl-axp209.c                   |  4 ++--
 drivers/pinctrl/pinctrl-cy8c95x0.c                 |  4 ++--
 drivers/pinctrl/pinctrl-da9062.c                   |  2 +-
 drivers/pinctrl/pinctrl-digicolor.c                |  2 +-
 drivers/pinctrl/pinctrl-ingenic.c                  |  2 +-
 drivers/pinctrl/pinctrl-keembay.c                  |  2 +-
 drivers/pinctrl/pinctrl-mcp23s08.c                 |  4 ++--
 drivers/pinctrl/pinctrl-microchip-sgpio.c          |  2 +-
 drivers/pinctrl/pinctrl-ocelot.c                   |  2 +-
 drivers/pinctrl/pinctrl-pic32.c                    |  2 +-
 drivers/pinctrl/pinctrl-pistachio.c                |  2 +-
 drivers/pinctrl/pinctrl-rk805.c                    |  2 +-
 drivers/pinctrl/pinctrl-rp1.c                      |  2 +-
 drivers/pinctrl/pinctrl-st.c                       |  2 +-
 drivers/pinctrl/pinctrl-stmfx.c                    |  2 +-
 drivers/pinctrl/pinctrl-sx150x.c                   |  4 ++--
 drivers/pinctrl/pinctrl-xway.c                     |  2 +-
 drivers/pinctrl/qcom/pinctrl-lpass-lpi.c           |  2 +-
 drivers/pinctrl/qcom/pinctrl-msm.c                 |  2 +-
 drivers/pinctrl/qcom/pinctrl-spmi-gpio.c           |  2 +-
 drivers/pinctrl/qcom/pinctrl-spmi-mpp.c            |  2 +-
 drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c           |  2 +-
 drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c            |  2 +-
 drivers/pinctrl/renesas/gpio.c                     |  2 +-
 drivers/pinctrl/renesas/pinctrl-rza1.c             |  2 +-
 drivers/pinctrl/renesas/pinctrl-rza2.c             |  2 +-
 drivers/pinctrl/renesas/pinctrl-rzg2l.c            |  2 +-
 drivers/pinctrl/renesas/pinctrl-rzv2m.c            |  2 +-
 drivers/pinctrl/samsung/pinctrl-samsung.c          |  2 +-
 drivers/pinctrl/spear/pinctrl-plgpio.c             |  2 +-
 drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c |  2 +-
 drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c |  2 +-
 drivers/pinctrl/stm32/pinctrl-stm32.c              |  2 +-
 drivers/pinctrl/sunplus/sppctl.c                   |  2 +-
 drivers/pinctrl/sunxi/pinctrl-sunxi.c              |  2 +-
 drivers/pinctrl/vt8500/pinctrl-wmt.c               |  2 +-
 drivers/platform/cznic/turris-omnia-mcu-gpio.c     |  4 ++--
 drivers/platform/x86/barco-p50-gpio.c              |  2 +-
 drivers/platform/x86/intel/int0002_vgpio.c         |  2 +-
 drivers/platform/x86/portwell-ec.c                 |  4 ++--
 drivers/platform/x86/silicom-platform.c            |  2 +-
 drivers/pwm/pwm-pca9685.c                          |  2 +-
 drivers/regulator/rpi-panel-attiny-regulator.c     |  2 +-
 drivers/soc/fsl/qe/gpio.c                          |  4 ++--
 drivers/soc/renesas/pwc-rzv2m.c                    |  2 +-
 drivers/spi/spi-xcomm.c                            |  2 +-
 drivers/ssb/driver_gpio.c                          |  4 ++--
 drivers/staging/greybus/gpio.c                     |  2 +-
 drivers/tty/serial/max310x.c                       |  2 +-
 drivers/tty/serial/sc16is7xx.c                     |  2 +-
 drivers/usb/serial/cp210x.c                        |  2 +-
 drivers/usb/serial/ftdi_sio.c                      |  4 ++--
 drivers/video/fbdev/via/via-gpio.c                 |  2 +-
 include/linux/gpio/driver.h                        | 19 ++++++++---------
 include/linux/gpio/generic.h                       |  4 ++--
 sound/hda/codecs/side-codecs/cirrus_scodec_test.c  |  2 +-
 sound/soc/codecs/idt821034.c                       |  2 +-
 sound/soc/codecs/peb2466.c                         |  2 +-
 sound/soc/codecs/rt5677.c                          |  2 +-
 sound/soc/codecs/tlv320adc3xxx.c                   |  2 +-
 sound/soc/codecs/wm5100.c                          |  2 +-
 sound/soc/codecs/wm8903.c                          |  2 +-
 sound/soc/codecs/wm8962.c                          |  2 +-
 sound/soc/codecs/wm8996.c                          |  2 +-
 sound/soc/codecs/zl38060.c                         |  2 +-
 sound/soc/soc-ac97.c                               |  2 +-
 sound/soc/ti/davinci-mcasp.c                       |  2 +-
 282 files changed, 355 insertions(+), 356 deletions(-)

(limited to 'include/linux')

diff --git a/arch/arm/common/sa1111.c b/arch/arm/common/sa1111.c
index d7e2ea27ce59..3389a70e4d49 100644
--- a/arch/arm/common/sa1111.c
+++ b/arch/arm/common/sa1111.c
@@ -617,8 +617,8 @@ static int sa1111_setup_gpios(struct sa1111 *sachip)
 	sachip->gc.direction_input = sa1111_gpio_direction_input;
 	sachip->gc.direction_output = sa1111_gpio_direction_output;
 	sachip->gc.get = sa1111_gpio_get;
-	sachip->gc.set_rv = sa1111_gpio_set;
-	sachip->gc.set_multiple_rv = sa1111_gpio_set_multiple;
+	sachip->gc.set = sa1111_gpio_set;
+	sachip->gc.set_multiple = sa1111_gpio_set_multiple;
 	sachip->gc.to_irq = sa1111_gpio_to_irq;
 	sachip->gc.base = -1;
 	sachip->gc.ngpio = 18;
diff --git a/arch/arm/common/scoop.c b/arch/arm/common/scoop.c
index 2d3ee76c8e17..dddb73c96826 100644
--- a/arch/arm/common/scoop.c
+++ b/arch/arm/common/scoop.c
@@ -218,7 +218,7 @@ static int scoop_probe(struct platform_device *pdev)
 		devptr->gpio.label = dev_name(&pdev->dev);
 		devptr->gpio.base = inf->gpio_base;
 		devptr->gpio.ngpio = 12; /* PA11 = 0, PA12 = 1, etc. up to PA22 = 11 */
-		devptr->gpio.set_rv = scoop_gpio_set;
+		devptr->gpio.set = scoop_gpio_set;
 		devptr->gpio.get = scoop_gpio_get;
 		devptr->gpio.direction_input = scoop_gpio_direction_input;
 		devptr->gpio.direction_output = scoop_gpio_direction_output;
diff --git a/arch/arm/mach-s3c/gpio-samsung.c b/arch/arm/mach-s3c/gpio-samsung.c
index 206a492fbaf5..81e198e5a6d3 100644
--- a/arch/arm/mach-s3c/gpio-samsung.c
+++ b/arch/arm/mach-s3c/gpio-samsung.c
@@ -517,7 +517,7 @@ static void __init samsung_gpiolib_add(struct samsung_gpio_chip *chip)
 	if (!gc->direction_output)
 		gc->direction_output = samsung_gpiolib_2bit_output;
 	if (!gc->set)
-		gc->set_rv = samsung_gpiolib_set;
+		gc->set = samsung_gpiolib_set;
 	if (!gc->get)
 		gc->get = samsung_gpiolib_get;
 
diff --git a/arch/arm/mach-sa1100/assabet.c b/arch/arm/mach-sa1100/assabet.c
index bad8aa661e9d..2b833aa0212b 100644
--- a/arch/arm/mach-sa1100/assabet.c
+++ b/arch/arm/mach-sa1100/assabet.c
@@ -80,7 +80,7 @@ void ASSABET_BCR_frob(unsigned int mask, unsigned int val)
 {
 	unsigned long m = mask, v = val;
 
-	assabet_bcr_gc->set_multiple_rv(assabet_bcr_gc, &m, &v);
+	assabet_bcr_gc->set_multiple(assabet_bcr_gc, &m, &v);
 }
 EXPORT_SYMBOL(ASSABET_BCR_frob);
 
diff --git a/arch/arm/mach-sa1100/neponset.c b/arch/arm/mach-sa1100/neponset.c
index 6516598c8a71..88fe79f0a4ed 100644
--- a/arch/arm/mach-sa1100/neponset.c
+++ b/arch/arm/mach-sa1100/neponset.c
@@ -126,7 +126,7 @@ void neponset_ncr_frob(unsigned int mask, unsigned int val)
 	unsigned long m = mask, v = val;
 
 	if (nep)
-		n->gpio[0]->set_multiple_rv(n->gpio[0], &m, &v);
+		n->gpio[0]->set_multiple(n->gpio[0], &m, &v);
 	else
 		WARN(1, "nep unset\n");
 }
diff --git a/arch/arm/plat-orion/gpio.c b/arch/arm/plat-orion/gpio.c
index 6f09f65e3d95..49e29b7894a3 100644
--- a/arch/arm/plat-orion/gpio.c
+++ b/arch/arm/plat-orion/gpio.c
@@ -540,7 +540,7 @@ void __init orion_gpio_init(int gpio_base, int ngpio,
 	ochip->chip.direction_input = orion_gpio_direction_input;
 	ochip->chip.get = orion_gpio_get;
 	ochip->chip.direction_output = orion_gpio_direction_output;
-	ochip->chip.set_rv = orion_gpio_set;
+	ochip->chip.set = orion_gpio_set;
 	ochip->chip.to_irq = orion_gpio_to_irq;
 	ochip->chip.base = gpio_base;
 	ochip->chip.ngpio = ngpio;
diff --git a/arch/m68k/coldfire/gpio.c b/arch/m68k/coldfire/gpio.c
index 30e5a4ed799d..e2f7af1facb2 100644
--- a/arch/m68k/coldfire/gpio.c
+++ b/arch/m68k/coldfire/gpio.c
@@ -160,7 +160,7 @@ static struct gpio_chip mcfgpio_chip = {
 	.direction_input	= mcfgpio_direction_input,
 	.direction_output	= mcfgpio_direction_output,
 	.get			= mcfgpio_get_value,
-	.set_rv			= mcfgpio_set_value,
+	.set			= mcfgpio_set_value,
 	.to_irq			= mcfgpio_to_irq,
 	.base			= 0,
 	.ngpio			= MCFGPIO_PIN_MAX,
diff --git a/arch/mips/alchemy/common/gpiolib.c b/arch/mips/alchemy/common/gpiolib.c
index 194034eba75f..e79e26ffac99 100644
--- a/arch/mips/alchemy/common/gpiolib.c
+++ b/arch/mips/alchemy/common/gpiolib.c
@@ -101,7 +101,7 @@ struct gpio_chip alchemy_gpio_chip[] = {
 		.direction_input	= gpio1_direction_input,
 		.direction_output	= gpio1_direction_output,
 		.get			= gpio1_get,
-		.set_rv			= gpio1_set,
+		.set			= gpio1_set,
 		.to_irq			= gpio1_to_irq,
 		.base			= ALCHEMY_GPIO1_BASE,
 		.ngpio			= ALCHEMY_GPIO1_NUM,
@@ -111,7 +111,7 @@ struct gpio_chip alchemy_gpio_chip[] = {
 		.direction_input	= gpio2_direction_input,
 		.direction_output	= gpio2_direction_output,
 		.get			= gpio2_get,
-		.set_rv			= gpio2_set,
+		.set			= gpio2_set,
 		.to_irq			= gpio2_to_irq,
 		.base			= ALCHEMY_GPIO2_BASE,
 		.ngpio			= ALCHEMY_GPIO2_NUM,
@@ -151,7 +151,7 @@ static struct gpio_chip au1300_gpiochip = {
 	.direction_input	= alchemy_gpic_dir_input,
 	.direction_output	= alchemy_gpic_dir_output,
 	.get			= alchemy_gpic_get,
-	.set_rv			= alchemy_gpic_set,
+	.set			= alchemy_gpic_set,
 	.to_irq			= alchemy_gpic_gpio_to_irq,
 	.base			= AU1300_GPIO_BASE,
 	.ngpio			= AU1300_GPIO_NUM,
diff --git a/arch/mips/bcm63xx/gpio.c b/arch/mips/bcm63xx/gpio.c
index e7a53cd0dec5..ff45a6989c3a 100644
--- a/arch/mips/bcm63xx/gpio.c
+++ b/arch/mips/bcm63xx/gpio.c
@@ -131,7 +131,7 @@ static struct gpio_chip bcm63xx_gpio_chip = {
 	.direction_input	= bcm63xx_gpio_direction_input,
 	.direction_output	= bcm63xx_gpio_direction_output,
 	.get			= bcm63xx_gpio_get,
-	.set_rv			= bcm63xx_gpio_set,
+	.set			= bcm63xx_gpio_set,
 	.base			= 0,
 };
 
diff --git a/arch/mips/kernel/gpio_txx9.c b/arch/mips/kernel/gpio_txx9.c
index 027fb57d0d79..96ac40d20c23 100644
--- a/arch/mips/kernel/gpio_txx9.c
+++ b/arch/mips/kernel/gpio_txx9.c
@@ -70,7 +70,7 @@ static int txx9_gpio_dir_out(struct gpio_chip *chip, unsigned int offset,
 
 static struct gpio_chip txx9_gpio_chip = {
 	.get = txx9_gpio_get,
-	.set_rv = txx9_gpio_set,
+	.set = txx9_gpio_set,
 	.direction_input = txx9_gpio_dir_in,
 	.direction_output = txx9_gpio_dir_out,
 	.label = "TXx9",
diff --git a/arch/mips/rb532/gpio.c b/arch/mips/rb532/gpio.c
index 0e47cd59b6cb..9aa5ef374465 100644
--- a/arch/mips/rb532/gpio.c
+++ b/arch/mips/rb532/gpio.c
@@ -164,7 +164,7 @@ static struct rb532_gpio_chip rb532_gpio_chip[] = {
 			.direction_input	= rb532_gpio_direction_input,
 			.direction_output	= rb532_gpio_direction_output,
 			.get			= rb532_gpio_get,
-			.set_rv			= rb532_gpio_set,
+			.set			= rb532_gpio_set,
 			.to_irq			= rb532_gpio_to_irq,
 			.base			= 0,
 			.ngpio			= 32,
diff --git a/arch/mips/txx9/generic/setup.c b/arch/mips/txx9/generic/setup.c
index 5a37e8b234a3..5dc867ea2c69 100644
--- a/arch/mips/txx9/generic/setup.c
+++ b/arch/mips/txx9/generic/setup.c
@@ -655,7 +655,7 @@ void __init txx9_iocled_init(unsigned long baseaddr,
 	if (!iocled->mmioaddr)
 		goto out_free;
 	iocled->chip.get = txx9_iocled_get;
-	iocled->chip.set_rv = txx9_iocled_set;
+	iocled->chip.set = txx9_iocled_set;
 	iocled->chip.direction_input = txx9_iocled_dir_in;
 	iocled->chip.direction_output = txx9_iocled_dir_out;
 	iocled->chip.label = "iocled";
diff --git a/arch/powerpc/platforms/44x/gpio.c b/arch/powerpc/platforms/44x/gpio.c
index d540e261d85a..08ab76582568 100644
--- a/arch/powerpc/platforms/44x/gpio.c
+++ b/arch/powerpc/platforms/44x/gpio.c
@@ -180,7 +180,7 @@ static int __init ppc4xx_add_gpiochips(void)
 		gc->direction_input = ppc4xx_gpio_dir_in;
 		gc->direction_output = ppc4xx_gpio_dir_out;
 		gc->get = ppc4xx_gpio_get;
-		gc->set_rv = ppc4xx_gpio_set;
+		gc->set = ppc4xx_gpio_set;
 
 		ret = of_mm_gpiochip_add_data(np, mm_gc, ppc4xx_gc);
 		if (ret)
diff --git a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
index bda707d848a6..7748b6641a3c 100644
--- a/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
+++ b/arch/powerpc/platforms/52xx/mpc52xx_gpt.c
@@ -336,7 +336,7 @@ static void mpc52xx_gpt_gpio_setup(struct mpc52xx_gpt_priv *gpt)
 	gpt->gc.direction_input  = mpc52xx_gpt_gpio_dir_in;
 	gpt->gc.direction_output = mpc52xx_gpt_gpio_dir_out;
 	gpt->gc.get = mpc52xx_gpt_gpio_get;
-	gpt->gc.set_rv = mpc52xx_gpt_gpio_set;
+	gpt->gc.set = mpc52xx_gpt_gpio_set;
 	gpt->gc.base = -1;
 	gpt->gc.parent = gpt->dev;
 
diff --git a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
index 6e37dfc6c5c9..cb7b9498f291 100644
--- a/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
+++ b/arch/powerpc/platforms/83xx/mcu_mpc8349emitx.c
@@ -126,7 +126,7 @@ static int mcu_gpiochip_add(struct mcu *mcu)
 	gc->can_sleep = 1;
 	gc->ngpio = MCU_NUM_GPIO;
 	gc->base = -1;
-	gc->set_rv = mcu_gpio_set;
+	gc->set = mcu_gpio_set;
 	gc->direction_output = mcu_gpio_dir_out;
 	gc->parent = dev;
 
diff --git a/arch/powerpc/platforms/8xx/cpm1.c b/arch/powerpc/platforms/8xx/cpm1.c
index 7462c221115c..7433be7d66ee 100644
--- a/arch/powerpc/platforms/8xx/cpm1.c
+++ b/arch/powerpc/platforms/8xx/cpm1.c
@@ -499,7 +499,7 @@ int cpm1_gpiochip_add16(struct device *dev)
 	gc->direction_input = cpm1_gpio16_dir_in;
 	gc->direction_output = cpm1_gpio16_dir_out;
 	gc->get = cpm1_gpio16_get;
-	gc->set_rv = cpm1_gpio16_set;
+	gc->set = cpm1_gpio16_set;
 	gc->to_irq = cpm1_gpio16_to_irq;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
@@ -622,7 +622,7 @@ int cpm1_gpiochip_add32(struct device *dev)
 	gc->direction_input = cpm1_gpio32_dir_in;
 	gc->direction_output = cpm1_gpio32_dir_out;
 	gc->get = cpm1_gpio32_get;
-	gc->set_rv = cpm1_gpio32_set;
+	gc->set = cpm1_gpio32_set;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
 
diff --git a/arch/powerpc/sysdev/cpm_common.c b/arch/powerpc/sysdev/cpm_common.c
index e22fc638dbc7..f469f6a9f6e0 100644
--- a/arch/powerpc/sysdev/cpm_common.c
+++ b/arch/powerpc/sysdev/cpm_common.c
@@ -210,7 +210,7 @@ int cpm2_gpiochip_add32(struct device *dev)
 	gc->direction_input = cpm2_gpio32_dir_in;
 	gc->direction_output = cpm2_gpio32_dir_out;
 	gc->get = cpm2_gpio32_get;
-	gc->set_rv = cpm2_gpio32_set;
+	gc->set = cpm2_gpio32_set;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
 
diff --git a/drivers/bcma/driver_gpio.c b/drivers/bcma/driver_gpio.c
index f021e27644e0..658c7e2ac8bf 100644
--- a/drivers/bcma/driver_gpio.c
+++ b/drivers/bcma/driver_gpio.c
@@ -186,7 +186,7 @@ int bcma_gpio_init(struct bcma_drv_cc *cc)
 	chip->request		= bcma_gpio_request;
 	chip->free		= bcma_gpio_free;
 	chip->get		= bcma_gpio_get_value;
-	chip->set_rv		= bcma_gpio_set_value;
+	chip->set		= bcma_gpio_set_value;
 	chip->direction_input	= bcma_gpio_direction_input;
 	chip->direction_output	= bcma_gpio_direction_output;
 	chip->parent		= bus->dev;
diff --git a/drivers/gpio/gpio-74x164.c b/drivers/gpio/gpio-74x164.c
index 4dd5c2c330bb..c226524efeba 100644
--- a/drivers/gpio/gpio-74x164.c
+++ b/drivers/gpio/gpio-74x164.c
@@ -141,8 +141,8 @@ static int gen_74x164_probe(struct spi_device *spi)
 	chip->gpio_chip.label = spi->modalias;
 	chip->gpio_chip.direction_output = gen_74x164_direction_output;
 	chip->gpio_chip.get = gen_74x164_get_value;
-	chip->gpio_chip.set_rv = gen_74x164_set_value;
-	chip->gpio_chip.set_multiple_rv = gen_74x164_set_multiple;
+	chip->gpio_chip.set = gen_74x164_set_value;
+	chip->gpio_chip.set_multiple = gen_74x164_set_multiple;
 	chip->gpio_chip.base = -1;
 	chip->gpio_chip.ngpio = GEN_74X164_NUMBER_GPIOS * chip->registers;
 	chip->gpio_chip.can_sleep = true;
diff --git a/drivers/gpio/gpio-adnp.c b/drivers/gpio/gpio-adnp.c
index dc2b941c3726..e5ac2d211013 100644
--- a/drivers/gpio/gpio-adnp.c
+++ b/drivers/gpio/gpio-adnp.c
@@ -430,7 +430,7 @@ static int adnp_gpio_setup(struct adnp *adnp, unsigned int num_gpios,
 	chip->direction_input = adnp_gpio_direction_input;
 	chip->direction_output = adnp_gpio_direction_output;
 	chip->get = adnp_gpio_get;
-	chip->set_rv = adnp_gpio_set;
+	chip->set = adnp_gpio_set;
 	chip->can_sleep = true;
 
 	if (IS_ENABLED(CONFIG_DEBUG_FS))
diff --git a/drivers/gpio/gpio-adp5520.c b/drivers/gpio/gpio-adp5520.c
index 57d12c10cbda..6305c8b7dc05 100644
--- a/drivers/gpio/gpio-adp5520.c
+++ b/drivers/gpio/gpio-adp5520.c
@@ -122,7 +122,7 @@ static int adp5520_gpio_probe(struct platform_device *pdev)
 	gc->direction_input  = adp5520_gpio_direction_input;
 	gc->direction_output = adp5520_gpio_direction_output;
 	gc->get = adp5520_gpio_get_value;
-	gc->set_rv = adp5520_gpio_set_value;
+	gc->set = adp5520_gpio_set_value;
 	gc->can_sleep = true;
 
 	gc->base = pdata->gpio_start;
diff --git a/drivers/gpio/gpio-adp5585.c b/drivers/gpio/gpio-adp5585.c
index b2c8836c5f84..0fd3cc26d017 100644
--- a/drivers/gpio/gpio-adp5585.c
+++ b/drivers/gpio/gpio-adp5585.c
@@ -428,7 +428,7 @@ static int adp5585_gpio_probe(struct platform_device *pdev)
 	gc->direction_input = adp5585_gpio_direction_input;
 	gc->direction_output = adp5585_gpio_direction_output;
 	gc->get = adp5585_gpio_get_value;
-	gc->set_rv = adp5585_gpio_set_value;
+	gc->set = adp5585_gpio_set_value;
 	gc->set_config = adp5585_gpio_set_config;
 	gc->request = adp5585_gpio_request;
 	gc->free = adp5585_gpio_free;
diff --git a/drivers/gpio/gpio-aggregator.c b/drivers/gpio/gpio-aggregator.c
index 6f941db02c04..af9d8b3a711d 100644
--- a/drivers/gpio/gpio-aggregator.c
+++ b/drivers/gpio/gpio-aggregator.c
@@ -534,8 +534,8 @@ static struct gpiochip_fwd *gpiochip_fwd_create(struct device *dev,
 	chip->direction_output = gpio_fwd_direction_output;
 	chip->get = gpio_fwd_get;
 	chip->get_multiple = gpio_fwd_get_multiple_locked;
-	chip->set_rv = gpio_fwd_set;
-	chip->set_multiple_rv = gpio_fwd_set_multiple_locked;
+	chip->set = gpio_fwd_set;
+	chip->set_multiple = gpio_fwd_set_multiple_locked;
 	chip->to_irq = gpio_fwd_to_irq;
 	chip->base = -1;
 	chip->ngpio = ngpios;
diff --git a/drivers/gpio/gpio-altera-a10sr.c b/drivers/gpio/gpio-altera-a10sr.c
index 77a674cf99e4..4524c18a87e7 100644
--- a/drivers/gpio/gpio-altera-a10sr.c
+++ b/drivers/gpio/gpio-altera-a10sr.c
@@ -69,7 +69,7 @@ static const struct gpio_chip altr_a10sr_gc = {
 	.label = "altr_a10sr_gpio",
 	.owner = THIS_MODULE,
 	.get = altr_a10sr_gpio_get,
-	.set_rv = altr_a10sr_gpio_set,
+	.set = altr_a10sr_gpio_set,
 	.direction_input = altr_a10sr_gpio_direction_input,
 	.direction_output = altr_a10sr_gpio_direction_output,
 	.can_sleep = true,
diff --git a/drivers/gpio/gpio-altera.c b/drivers/gpio/gpio-altera.c
index 1b28525726d7..9508d764cce4 100644
--- a/drivers/gpio/gpio-altera.c
+++ b/drivers/gpio/gpio-altera.c
@@ -259,7 +259,7 @@ static int altera_gpio_probe(struct platform_device *pdev)
 	altera_gc->gc.direction_input	= altera_gpio_direction_input;
 	altera_gc->gc.direction_output	= altera_gpio_direction_output;
 	altera_gc->gc.get		= altera_gpio_get;
-	altera_gc->gc.set_rv		= altera_gpio_set;
+	altera_gc->gc.set		= altera_gpio_set;
 	altera_gc->gc.owner		= THIS_MODULE;
 	altera_gc->gc.parent		= &pdev->dev;
 	altera_gc->gc.base		= -1;
diff --git a/drivers/gpio/gpio-amd-fch.c b/drivers/gpio/gpio-amd-fch.c
index f8d0cea46049..e6c6c3ec7656 100644
--- a/drivers/gpio/gpio-amd-fch.c
+++ b/drivers/gpio/gpio-amd-fch.c
@@ -165,7 +165,7 @@ static int amd_fch_gpio_probe(struct platform_device *pdev)
 	priv->gc.direction_output	= amd_fch_gpio_direction_output;
 	priv->gc.get_direction		= amd_fch_gpio_get_direction;
 	priv->gc.get			= amd_fch_gpio_get;
-	priv->gc.set_rv			= amd_fch_gpio_set;
+	priv->gc.set			= amd_fch_gpio_set;
 
 	spin_lock_init(&priv->lock);
 
diff --git a/drivers/gpio/gpio-amd8111.c b/drivers/gpio/gpio-amd8111.c
index 425d8472f744..15fd5e210d74 100644
--- a/drivers/gpio/gpio-amd8111.c
+++ b/drivers/gpio/gpio-amd8111.c
@@ -165,7 +165,7 @@ static struct amd_gpio gp = {
 		.ngpio		= 32,
 		.request	= amd_gpio_request,
 		.free		= amd_gpio_free,
-		.set_rv		= amd_gpio_set,
+		.set		= amd_gpio_set,
 		.get		= amd_gpio_get,
 		.direction_output = amd_gpio_dirout,
 		.direction_input = amd_gpio_dirin,
diff --git a/drivers/gpio/gpio-arizona.c b/drivers/gpio/gpio-arizona.c
index 89ffde693019..a7e98d395d8e 100644
--- a/drivers/gpio/gpio-arizona.c
+++ b/drivers/gpio/gpio-arizona.c
@@ -138,7 +138,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= arizona_gpio_direction_in,
 	.get			= arizona_gpio_get,
 	.direction_output	= arizona_gpio_direction_out,
-	.set_rv			= arizona_gpio_set,
+	.set			= arizona_gpio_set,
 	.can_sleep		= true,
 };
 
diff --git a/drivers/gpio/gpio-aspeed-sgpio.c b/drivers/gpio/gpio-aspeed-sgpio.c
index 00b31497ecff..7622f9e9f54a 100644
--- a/drivers/gpio/gpio-aspeed-sgpio.c
+++ b/drivers/gpio/gpio-aspeed-sgpio.c
@@ -596,7 +596,7 @@ static int __init aspeed_sgpio_probe(struct platform_device *pdev)
 	gpio->chip.request = NULL;
 	gpio->chip.free = NULL;
 	gpio->chip.get = aspeed_sgpio_get;
-	gpio->chip.set_rv = aspeed_sgpio_set;
+	gpio->chip.set = aspeed_sgpio_set;
 	gpio->chip.set_config = aspeed_sgpio_set_config;
 	gpio->chip.label = dev_name(&pdev->dev);
 	gpio->chip.base = -1;
diff --git a/drivers/gpio/gpio-aspeed.c b/drivers/gpio/gpio-aspeed.c
index 2d340a343a17..7953a9c4e36d 100644
--- a/drivers/gpio/gpio-aspeed.c
+++ b/drivers/gpio/gpio-aspeed.c
@@ -1352,7 +1352,7 @@ static int aspeed_gpio_probe(struct platform_device *pdev)
 	gpio->chip.request = aspeed_gpio_request;
 	gpio->chip.free = aspeed_gpio_free;
 	gpio->chip.get = aspeed_gpio_get;
-	gpio->chip.set_rv = aspeed_gpio_set;
+	gpio->chip.set = aspeed_gpio_set;
 	gpio->chip.set_config = aspeed_gpio_set_config;
 	gpio->chip.label = dev_name(&pdev->dev);
 	gpio->chip.base = -1;
diff --git a/drivers/gpio/gpio-bcm-kona.c b/drivers/gpio/gpio-bcm-kona.c
index 8f22cb36004d..208b71c59d58 100644
--- a/drivers/gpio/gpio-bcm-kona.c
+++ b/drivers/gpio/gpio-bcm-kona.c
@@ -339,7 +339,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input = bcm_kona_gpio_direction_input,
 	.get = bcm_kona_gpio_get,
 	.direction_output = bcm_kona_gpio_direction_output,
-	.set_rv = bcm_kona_gpio_set,
+	.set = bcm_kona_gpio_set,
 	.set_config = bcm_kona_gpio_set_config,
 	.to_irq = bcm_kona_gpio_to_irq,
 	.base = 0,
diff --git a/drivers/gpio/gpio-bd71815.c b/drivers/gpio/gpio-bd71815.c
index 36701500925e..afb18a5a9d79 100644
--- a/drivers/gpio/gpio-bd71815.c
+++ b/drivers/gpio/gpio-bd71815.c
@@ -85,7 +85,7 @@ static const struct gpio_chip bd71815gpo_chip = {
 	.owner			= THIS_MODULE,
 	.get			= bd71815gpo_get,
 	.get_direction		= bd71815gpo_direction_get,
-	.set_rv			= bd71815gpo_set,
+	.set			= bd71815gpo_set,
 	.set_config		= bd71815_gpio_set_config,
 	.can_sleep		= true,
 };
diff --git a/drivers/gpio/gpio-bd71828.c b/drivers/gpio/gpio-bd71828.c
index 4ba151e5cf25..e439dbfffc62 100644
--- a/drivers/gpio/gpio-bd71828.c
+++ b/drivers/gpio/gpio-bd71828.c
@@ -109,7 +109,7 @@ static int bd71828_probe(struct platform_device *pdev)
 	bdgpio->gpio.set_config = bd71828_gpio_set_config;
 	bdgpio->gpio.can_sleep = true;
 	bdgpio->gpio.get = bd71828_gpio_get;
-	bdgpio->gpio.set_rv = bd71828_gpio_set;
+	bdgpio->gpio.set = bd71828_gpio_set;
 	bdgpio->gpio.base = -1;
 
 	/*
diff --git a/drivers/gpio/gpio-bd9571mwv.c b/drivers/gpio/gpio-bd9571mwv.c
index 8df1361e3e84..7c95bb36511e 100644
--- a/drivers/gpio/gpio-bd9571mwv.c
+++ b/drivers/gpio/gpio-bd9571mwv.c
@@ -88,7 +88,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= bd9571mwv_gpio_direction_input,
 	.direction_output	= bd9571mwv_gpio_direction_output,
 	.get			= bd9571mwv_gpio_get,
-	.set_rv			= bd9571mwv_gpio_set,
+	.set			= bd9571mwv_gpio_set,
 	.base			= -1,
 	.ngpio			= 2,
 	.can_sleep		= true,
diff --git a/drivers/gpio/gpio-bt8xx.c b/drivers/gpio/gpio-bt8xx.c
index 7c9e81fea37a..05401da03ca3 100644
--- a/drivers/gpio/gpio-bt8xx.c
+++ b/drivers/gpio/gpio-bt8xx.c
@@ -145,7 +145,7 @@ static void bt8xxgpio_gpio_setup(struct bt8xxgpio *bg)
 	c->direction_input = bt8xxgpio_gpio_direction_input;
 	c->get = bt8xxgpio_gpio_get;
 	c->direction_output = bt8xxgpio_gpio_direction_output;
-	c->set_rv = bt8xxgpio_gpio_set;
+	c->set = bt8xxgpio_gpio_set;
 	c->dbg_show = NULL;
 	c->base = modparam_gpiobase;
 	c->ngpio = BT8XXGPIO_NR_GPIOS;
diff --git a/drivers/gpio/gpio-cgbc.c b/drivers/gpio/gpio-cgbc.c
index 1495bec62456..0efa1b61001a 100644
--- a/drivers/gpio/gpio-cgbc.c
+++ b/drivers/gpio/gpio-cgbc.c
@@ -171,7 +171,7 @@ static int cgbc_gpio_probe(struct platform_device *pdev)
 	chip->direction_output = cgbc_gpio_direction_output;
 	chip->get_direction = cgbc_gpio_get_direction;
 	chip->get = cgbc_gpio_get;
-	chip->set_rv = cgbc_gpio_set;
+	chip->set = cgbc_gpio_set;
 	chip->ngpio = CGBC_GPIO_NGPIO;
 
 	ret = devm_mutex_init(dev, &gpio->lock);
diff --git a/drivers/gpio/gpio-creg-snps.c b/drivers/gpio/gpio-creg-snps.c
index 8b49f02c7896..f8ea961fa1de 100644
--- a/drivers/gpio/gpio-creg-snps.c
+++ b/drivers/gpio/gpio-creg-snps.c
@@ -167,7 +167,7 @@ static int creg_gpio_probe(struct platform_device *pdev)
 	hcg->gc.label = dev_name(dev);
 	hcg->gc.base = -1;
 	hcg->gc.ngpio = ngpios;
-	hcg->gc.set_rv = creg_gpio_set;
+	hcg->gc.set = creg_gpio_set;
 	hcg->gc.direction_output = creg_gpio_dir_out;
 
 	ret = devm_gpiochip_add_data(dev, &hcg->gc, hcg);
diff --git a/drivers/gpio/gpio-cros-ec.c b/drivers/gpio/gpio-cros-ec.c
index 53cd5ff6247b..435483826c6e 100644
--- a/drivers/gpio/gpio-cros-ec.c
+++ b/drivers/gpio/gpio-cros-ec.c
@@ -188,7 +188,7 @@ static int cros_ec_gpio_probe(struct platform_device *pdev)
 	gc->can_sleep = true;
 	gc->label = dev_name(dev);
 	gc->base = -1;
-	gc->set_rv = cros_ec_gpio_set;
+	gc->set = cros_ec_gpio_set;
 	gc->get = cros_ec_gpio_get;
 	gc->get_direction = cros_ec_gpio_get_direction;
 
diff --git a/drivers/gpio/gpio-crystalcove.c b/drivers/gpio/gpio-crystalcove.c
index 8db7cca3a060..0fb5c06d0886 100644
--- a/drivers/gpio/gpio-crystalcove.c
+++ b/drivers/gpio/gpio-crystalcove.c
@@ -349,7 +349,7 @@ static int crystalcove_gpio_probe(struct platform_device *pdev)
 	cg->chip.direction_input = crystalcove_gpio_dir_in;
 	cg->chip.direction_output = crystalcove_gpio_dir_out;
 	cg->chip.get = crystalcove_gpio_get;
-	cg->chip.set_rv = crystalcove_gpio_set;
+	cg->chip.set = crystalcove_gpio_set;
 	cg->chip.base = -1;
 	cg->chip.ngpio = CRYSTALCOVE_VGPIO_NUM;
 	cg->chip.can_sleep = true;
diff --git a/drivers/gpio/gpio-cs5535.c b/drivers/gpio/gpio-cs5535.c
index 143d1f4173a6..8affe4e9f90e 100644
--- a/drivers/gpio/gpio-cs5535.c
+++ b/drivers/gpio/gpio-cs5535.c
@@ -296,7 +296,7 @@ static struct cs5535_gpio_chip cs5535_gpio_chip = {
 		.request = chip_gpio_request,
 
 		.get = chip_gpio_get,
-		.set_rv = chip_gpio_set,
+		.set = chip_gpio_set,
 
 		.direction_input = chip_direction_input,
 		.direction_output = chip_direction_output,
diff --git a/drivers/gpio/gpio-da9052.c b/drivers/gpio/gpio-da9052.c
index 6482c5b267db..495f0ee58505 100644
--- a/drivers/gpio/gpio-da9052.c
+++ b/drivers/gpio/gpio-da9052.c
@@ -172,7 +172,7 @@ static const struct gpio_chip reference_gp = {
 	.label = "da9052-gpio",
 	.owner = THIS_MODULE,
 	.get = da9052_gpio_get,
-	.set_rv = da9052_gpio_set,
+	.set = da9052_gpio_set,
 	.direction_input = da9052_gpio_direction_input,
 	.direction_output = da9052_gpio_direction_output,
 	.to_irq = da9052_gpio_to_irq,
diff --git a/drivers/gpio/gpio-da9055.c b/drivers/gpio/gpio-da9055.c
index 3d9d0c700100..a09bd6eb93cf 100644
--- a/drivers/gpio/gpio-da9055.c
+++ b/drivers/gpio/gpio-da9055.c
@@ -116,7 +116,7 @@ static const struct gpio_chip reference_gp = {
 	.label = "da9055-gpio",
 	.owner = THIS_MODULE,
 	.get = da9055_gpio_get,
-	.set_rv = da9055_gpio_set,
+	.set = da9055_gpio_set,
 	.direction_input = da9055_gpio_direction_input,
 	.direction_output = da9055_gpio_direction_output,
 	.to_irq = da9055_gpio_to_irq,
diff --git a/drivers/gpio/gpio-davinci.c b/drivers/gpio/gpio-davinci.c
index 8f3a36d0191d..538f27209ce7 100644
--- a/drivers/gpio/gpio-davinci.c
+++ b/drivers/gpio/gpio-davinci.c
@@ -202,7 +202,7 @@ static int davinci_gpio_probe(struct platform_device *pdev)
 	chips->chip.direction_input = davinci_direction_in;
 	chips->chip.get = davinci_gpio_get;
 	chips->chip.direction_output = davinci_direction_out;
-	chips->chip.set_rv = davinci_gpio_set;
+	chips->chip.set = davinci_gpio_set;
 
 	chips->chip.ngpio = ngpio;
 	chips->chip.base = -1;
diff --git a/drivers/gpio/gpio-dln2.c b/drivers/gpio/gpio-dln2.c
index 4bd3c47eaf93..4670ffd7ea7f 100644
--- a/drivers/gpio/gpio-dln2.c
+++ b/drivers/gpio/gpio-dln2.c
@@ -469,7 +469,7 @@ static int dln2_gpio_probe(struct platform_device *pdev)
 	dln2->gpio.base = -1;
 	dln2->gpio.ngpio = pins;
 	dln2->gpio.can_sleep = true;
-	dln2->gpio.set_rv = dln2_gpio_set;
+	dln2->gpio.set = dln2_gpio_set;
 	dln2->gpio.get = dln2_gpio_get;
 	dln2->gpio.request = dln2_gpio_request;
 	dln2->gpio.free = dln2_gpio_free;
diff --git a/drivers/gpio/gpio-eic-sprd.c b/drivers/gpio/gpio-eic-sprd.c
index f2973d0b7138..50fafeda8d7e 100644
--- a/drivers/gpio/gpio-eic-sprd.c
+++ b/drivers/gpio/gpio-eic-sprd.c
@@ -663,7 +663,7 @@ static int sprd_eic_probe(struct platform_device *pdev)
 		sprd_eic->chip.request = sprd_eic_request;
 		sprd_eic->chip.free = sprd_eic_free;
 		sprd_eic->chip.set_config = sprd_eic_set_config;
-		sprd_eic->chip.set_rv = sprd_eic_set;
+		sprd_eic->chip.set = sprd_eic_set;
 		fallthrough;
 	case SPRD_EIC_ASYNC:
 	case SPRD_EIC_SYNC:
diff --git a/drivers/gpio/gpio-em.c b/drivers/gpio/gpio-em.c
index 015f1ac32dd9..a214b0672726 100644
--- a/drivers/gpio/gpio-em.c
+++ b/drivers/gpio/gpio-em.c
@@ -306,7 +306,7 @@ static int em_gio_probe(struct platform_device *pdev)
 	gpio_chip->direction_input = em_gio_direction_input;
 	gpio_chip->get = em_gio_get;
 	gpio_chip->direction_output = em_gio_direction_output;
-	gpio_chip->set_rv = em_gio_set;
+	gpio_chip->set = em_gio_set;
 	gpio_chip->to_irq = em_gio_to_irq;
 	gpio_chip->request = pinctrl_gpio_request;
 	gpio_chip->free = em_gio_free;
diff --git a/drivers/gpio/gpio-exar.c b/drivers/gpio/gpio-exar.c
index beb98286d13e..9053662f1817 100644
--- a/drivers/gpio/gpio-exar.c
+++ b/drivers/gpio/gpio-exar.c
@@ -211,7 +211,7 @@ static int gpio_exar_probe(struct platform_device *pdev)
 	exar_gpio->gpio_chip.direction_input = exar_direction_input;
 	exar_gpio->gpio_chip.get_direction = exar_get_direction;
 	exar_gpio->gpio_chip.get = exar_get_value;
-	exar_gpio->gpio_chip.set_rv = exar_set_value;
+	exar_gpio->gpio_chip.set = exar_set_value;
 	exar_gpio->gpio_chip.base = -1;
 	exar_gpio->gpio_chip.ngpio = ngpios;
 	exar_gpio->index = index;
diff --git a/drivers/gpio/gpio-f7188x.c b/drivers/gpio/gpio-f7188x.c
index dfcd3634f279..4d5b927ad70f 100644
--- a/drivers/gpio/gpio-f7188x.c
+++ b/drivers/gpio/gpio-f7188x.c
@@ -173,7 +173,7 @@ static int f7188x_gpio_set_config(struct gpio_chip *chip, unsigned offset,
 			.direction_input  = f7188x_gpio_direction_in,	\
 			.get              = f7188x_gpio_get,		\
 			.direction_output = f7188x_gpio_direction_out,	\
-			.set_rv           = f7188x_gpio_set,		\
+			.set              = f7188x_gpio_set,		\
 			.set_config	  = f7188x_gpio_set_config,	\
 			.base             = -1,				\
 			.ngpio            = _ngpio,			\
diff --git a/drivers/gpio/gpio-graniterapids.c b/drivers/gpio/gpio-graniterapids.c
index f25283e5239d..121bf29a27f5 100644
--- a/drivers/gpio/gpio-graniterapids.c
+++ b/drivers/gpio/gpio-graniterapids.c
@@ -159,7 +159,7 @@ static const struct gpio_chip gnr_gpio_chip = {
 	.owner		  = THIS_MODULE,
 	.request	  = gnr_gpio_request,
 	.get		  = gnr_gpio_get,
-	.set_rv		  = gnr_gpio_set,
+	.set		  = gnr_gpio_set,
 	.get_direction    = gnr_gpio_get_direction,
 	.direction_input  = gnr_gpio_direction_input,
 	.direction_output = gnr_gpio_direction_output,
diff --git a/drivers/gpio/gpio-gw-pld.c b/drivers/gpio/gpio-gw-pld.c
index a40ba99a3aea..2e5d97b7363f 100644
--- a/drivers/gpio/gpio-gw-pld.c
+++ b/drivers/gpio/gpio-gw-pld.c
@@ -86,7 +86,7 @@ static int gw_pld_probe(struct i2c_client *client)
 	gw->chip.direction_input = gw_pld_input8;
 	gw->chip.get = gw_pld_get8;
 	gw->chip.direction_output = gw_pld_output8;
-	gw->chip.set_rv = gw_pld_set8;
+	gw->chip.set = gw_pld_set8;
 	gw->client = client;
 
 	/*
diff --git a/drivers/gpio/gpio-htc-egpio.c b/drivers/gpio/gpio-htc-egpio.c
index b1844a676c7c..2eaed83214d8 100644
--- a/drivers/gpio/gpio-htc-egpio.c
+++ b/drivers/gpio/gpio-htc-egpio.c
@@ -324,7 +324,7 @@ static int __init egpio_probe(struct platform_device *pdev)
 		chip->parent          = &pdev->dev;
 		chip->owner           = THIS_MODULE;
 		chip->get             = egpio_get;
-		chip->set_rv          = egpio_set;
+		chip->set             = egpio_set;
 		chip->direction_input = egpio_direction_input;
 		chip->direction_output = egpio_direction_output;
 		chip->get_direction   = egpio_get_direction;
diff --git a/drivers/gpio/gpio-ich.c b/drivers/gpio/gpio-ich.c
index 67089b2423d8..1802c9116ffe 100644
--- a/drivers/gpio/gpio-ich.c
+++ b/drivers/gpio/gpio-ich.c
@@ -273,7 +273,7 @@ static void ichx_gpiolib_setup(struct gpio_chip *chip)
 	chip->get = ichx_priv.desc->get ?
 		ichx_priv.desc->get : ichx_gpio_get;
 
-	chip->set_rv = ichx_gpio_set;
+	chip->set = ichx_gpio_set;
 	chip->get_direction = ichx_gpio_get_direction;
 	chip->direction_input = ichx_gpio_direction_input;
 	chip->direction_output = ichx_gpio_direction_output;
diff --git a/drivers/gpio/gpio-imx-scu.c b/drivers/gpio/gpio-imx-scu.c
index 1693dbf1b777..0a75afecf9f8 100644
--- a/drivers/gpio/gpio-imx-scu.c
+++ b/drivers/gpio/gpio-imx-scu.c
@@ -102,7 +102,7 @@ static int imx_scu_gpio_probe(struct platform_device *pdev)
 	gc->ngpio = ARRAY_SIZE(scu_rsrc_arr);
 	gc->label = dev_name(dev);
 	gc->get = imx_scu_gpio_get;
-	gc->set_rv = imx_scu_gpio_set;
+	gc->set = imx_scu_gpio_set;
 	gc->get_direction = imx_scu_gpio_get_direction;
 
 	platform_set_drvdata(pdev, priv);
diff --git a/drivers/gpio/gpio-it87.c b/drivers/gpio/gpio-it87.c
index d8184b527bac..5d677bcfccf2 100644
--- a/drivers/gpio/gpio-it87.c
+++ b/drivers/gpio/gpio-it87.c
@@ -267,7 +267,7 @@ static const struct gpio_chip it87_template_chip = {
 	.request		= it87_gpio_request,
 	.get			= it87_gpio_get,
 	.direction_input	= it87_gpio_direction_in,
-	.set_rv			= it87_gpio_set,
+	.set			= it87_gpio_set,
 	.direction_output	= it87_gpio_direction_out,
 	.base			= -1
 };
diff --git a/drivers/gpio/gpio-janz-ttl.c b/drivers/gpio/gpio-janz-ttl.c
index 9f548eda3888..b0c4a3346e7d 100644
--- a/drivers/gpio/gpio-janz-ttl.c
+++ b/drivers/gpio/gpio-janz-ttl.c
@@ -171,7 +171,7 @@ static int ttl_probe(struct platform_device *pdev)
 	gpio->parent = &pdev->dev;
 	gpio->label = pdev->name;
 	gpio->get = ttl_get_value;
-	gpio->set_rv = ttl_set_value;
+	gpio->set = ttl_set_value;
 	gpio->owner = THIS_MODULE;
 
 	/* request dynamic allocation */
diff --git a/drivers/gpio/gpio-kempld.c b/drivers/gpio/gpio-kempld.c
index e38e604baa22..923aad3ab4d4 100644
--- a/drivers/gpio/gpio-kempld.c
+++ b/drivers/gpio/gpio-kempld.c
@@ -169,7 +169,7 @@ static int kempld_gpio_probe(struct platform_device *pdev)
 	chip->direction_output = kempld_gpio_direction_output;
 	chip->get_direction = kempld_gpio_get_direction;
 	chip->get = kempld_gpio_get;
-	chip->set_rv = kempld_gpio_set;
+	chip->set = kempld_gpio_set;
 	chip->ngpio = kempld_gpio_pincount(pld);
 	if (chip->ngpio == 0) {
 		dev_err(dev, "No GPIO pins detected\n");
diff --git a/drivers/gpio/gpio-latch.c b/drivers/gpio/gpio-latch.c
index 3d0ff09284fb..c64aaa896766 100644
--- a/drivers/gpio/gpio-latch.c
+++ b/drivers/gpio/gpio-latch.c
@@ -166,11 +166,11 @@ static int gpio_latch_probe(struct platform_device *pdev)
 
 	if (gpio_latch_can_sleep(priv, n_latches)) {
 		priv->gc.can_sleep = true;
-		priv->gc.set_rv = gpio_latch_set_can_sleep;
+		priv->gc.set = gpio_latch_set_can_sleep;
 		mutex_init(&priv->mutex);
 	} else {
 		priv->gc.can_sleep = false;
-		priv->gc.set_rv = gpio_latch_set;
+		priv->gc.set = gpio_latch_set;
 		spin_lock_init(&priv->spinlock);
 	}
 
diff --git a/drivers/gpio/gpio-ljca.c b/drivers/gpio/gpio-ljca.c
index 61524a9ba765..3b4f8830c741 100644
--- a/drivers/gpio/gpio-ljca.c
+++ b/drivers/gpio/gpio-ljca.c
@@ -437,7 +437,7 @@ static int ljca_gpio_probe(struct auxiliary_device *auxdev,
 	ljca_gpio->gc.direction_output = ljca_gpio_direction_output;
 	ljca_gpio->gc.get_direction = ljca_gpio_get_direction;
 	ljca_gpio->gc.get = ljca_gpio_get_value;
-	ljca_gpio->gc.set_rv = ljca_gpio_set_value;
+	ljca_gpio->gc.set = ljca_gpio_set_value;
 	ljca_gpio->gc.set_config = ljca_gpio_set_config;
 	ljca_gpio->gc.init_valid_mask = ljca_gpio_init_valid_mask;
 	ljca_gpio->gc.can_sleep = true;
diff --git a/drivers/gpio/gpio-logicvc.c b/drivers/gpio/gpio-logicvc.c
index 19cd2847467c..cb9dbcc290ad 100644
--- a/drivers/gpio/gpio-logicvc.c
+++ b/drivers/gpio/gpio-logicvc.c
@@ -134,7 +134,7 @@ static int logicvc_gpio_probe(struct platform_device *pdev)
 	logicvc->chip.ngpio = LOGICVC_CTRL_GPIO_BITS +
 			      LOGICVC_POWER_CTRL_GPIO_BITS;
 	logicvc->chip.get = logicvc_gpio_get;
-	logicvc->chip.set_rv = logicvc_gpio_set;
+	logicvc->chip.set = logicvc_gpio_set;
 	logicvc->chip.direction_output = logicvc_gpio_direction_output;
 
 	return devm_gpiochip_add_data(dev, &logicvc->chip, logicvc);
diff --git a/drivers/gpio/gpio-loongson-64bit.c b/drivers/gpio/gpio-loongson-64bit.c
index add09971d26a..818c606fbc51 100644
--- a/drivers/gpio/gpio-loongson-64bit.c
+++ b/drivers/gpio/gpio-loongson-64bit.c
@@ -157,7 +157,7 @@ static int loongson_gpio_init(struct device *dev, struct loongson_gpio_chip *lgp
 		lgpio->chip.get = loongson_gpio_get;
 		lgpio->chip.get_direction = loongson_gpio_get_direction;
 		lgpio->chip.direction_output = loongson_gpio_direction_output;
-		lgpio->chip.set_rv = loongson_gpio_set;
+		lgpio->chip.set = loongson_gpio_set;
 		lgpio->chip.parent = dev;
 		spin_lock_init(&lgpio->lock);
 	}
diff --git a/drivers/gpio/gpio-loongson.c b/drivers/gpio/gpio-loongson.c
index 8f3668169ebf..f3e0559f969d 100644
--- a/drivers/gpio/gpio-loongson.c
+++ b/drivers/gpio/gpio-loongson.c
@@ -106,7 +106,7 @@ static int loongson_gpio_probe(struct platform_device *pdev)
 	gc->base = 0;
 	gc->ngpio = LOONGSON_N_GPIO;
 	gc->get = loongson_gpio_get_value;
-	gc->set_rv = loongson_gpio_set_value;
+	gc->set = loongson_gpio_set_value;
 	gc->direction_input = loongson_gpio_direction_input;
 	gc->direction_output = loongson_gpio_direction_output;
 
diff --git a/drivers/gpio/gpio-lp3943.c b/drivers/gpio/gpio-lp3943.c
index 52ab3ac4844c..e8e00daff7df 100644
--- a/drivers/gpio/gpio-lp3943.c
+++ b/drivers/gpio/gpio-lp3943.c
@@ -184,7 +184,7 @@ static const struct gpio_chip lp3943_gpio_chip = {
 	.direction_input	= lp3943_gpio_direction_input,
 	.get			= lp3943_gpio_get,
 	.direction_output	= lp3943_gpio_direction_output,
-	.set_rv			= lp3943_gpio_set,
+	.set			= lp3943_gpio_set,
 	.base			= -1,
 	.ngpio			= LP3943_MAX_GPIO,
 	.can_sleep		= 1,
diff --git a/drivers/gpio/gpio-lp873x.c b/drivers/gpio/gpio-lp873x.c
index 1908ed302e92..5376708a81bf 100644
--- a/drivers/gpio/gpio-lp873x.c
+++ b/drivers/gpio/gpio-lp873x.c
@@ -124,7 +124,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= lp873x_gpio_direction_input,
 	.direction_output	= lp873x_gpio_direction_output,
 	.get			= lp873x_gpio_get,
-	.set_rv			= lp873x_gpio_set,
+	.set			= lp873x_gpio_set,
 	.set_config		= lp873x_gpio_set_config,
 	.base			= -1,
 	.ngpio			= 2,
diff --git a/drivers/gpio/gpio-lp87565.c b/drivers/gpio/gpio-lp87565.c
index 8ea687d5d028..0f337c1283b2 100644
--- a/drivers/gpio/gpio-lp87565.c
+++ b/drivers/gpio/gpio-lp87565.c
@@ -139,7 +139,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= lp87565_gpio_direction_input,
 	.direction_output	= lp87565_gpio_direction_output,
 	.get			= lp87565_gpio_get,
-	.set_rv			= lp87565_gpio_set,
+	.set			= lp87565_gpio_set,
 	.set_config		= lp87565_gpio_set_config,
 	.base			= -1,
 	.ngpio			= 3,
diff --git a/drivers/gpio/gpio-lpc18xx.c b/drivers/gpio/gpio-lpc18xx.c
index 2dbfbf90176c..37a2342eb2e6 100644
--- a/drivers/gpio/gpio-lpc18xx.c
+++ b/drivers/gpio/gpio-lpc18xx.c
@@ -327,7 +327,7 @@ static const struct gpio_chip lpc18xx_chip = {
 	.free			= gpiochip_generic_free,
 	.direction_input	= lpc18xx_gpio_direction_input,
 	.direction_output	= lpc18xx_gpio_direction_output,
-	.set_rv			= lpc18xx_gpio_set,
+	.set			= lpc18xx_gpio_set,
 	.get			= lpc18xx_gpio_get,
 	.ngpio			= LPC18XX_MAX_PORTS * LPC18XX_PINS_PER_PORT,
 	.owner			= THIS_MODULE,
diff --git a/drivers/gpio/gpio-lpc32xx.c b/drivers/gpio/gpio-lpc32xx.c
index 6668b8bd9f1e..37fc54fc7385 100644
--- a/drivers/gpio/gpio-lpc32xx.c
+++ b/drivers/gpio/gpio-lpc32xx.c
@@ -407,7 +407,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = {
 			.direction_input	= lpc32xx_gpio_dir_input_p012,
 			.get			= lpc32xx_gpio_get_value_p012,
 			.direction_output	= lpc32xx_gpio_dir_output_p012,
-			.set_rv			= lpc32xx_gpio_set_value_p012,
+			.set			= lpc32xx_gpio_set_value_p012,
 			.request		= lpc32xx_gpio_request,
 			.to_irq			= lpc32xx_gpio_to_irq_p01,
 			.base			= LPC32XX_GPIO_P0_GRP,
@@ -423,7 +423,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = {
 			.direction_input	= lpc32xx_gpio_dir_input_p012,
 			.get			= lpc32xx_gpio_get_value_p012,
 			.direction_output	= lpc32xx_gpio_dir_output_p012,
-			.set_rv			= lpc32xx_gpio_set_value_p012,
+			.set			= lpc32xx_gpio_set_value_p012,
 			.request		= lpc32xx_gpio_request,
 			.to_irq			= lpc32xx_gpio_to_irq_p01,
 			.base			= LPC32XX_GPIO_P1_GRP,
@@ -439,7 +439,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = {
 			.direction_input	= lpc32xx_gpio_dir_input_p012,
 			.get			= lpc32xx_gpio_get_value_p012,
 			.direction_output	= lpc32xx_gpio_dir_output_p012,
-			.set_rv			= lpc32xx_gpio_set_value_p012,
+			.set			= lpc32xx_gpio_set_value_p012,
 			.request		= lpc32xx_gpio_request,
 			.base			= LPC32XX_GPIO_P2_GRP,
 			.ngpio			= LPC32XX_GPIO_P2_MAX,
@@ -454,7 +454,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = {
 			.direction_input	= lpc32xx_gpio_dir_input_p3,
 			.get			= lpc32xx_gpio_get_value_p3,
 			.direction_output	= lpc32xx_gpio_dir_output_p3,
-			.set_rv			= lpc32xx_gpio_set_value_p3,
+			.set			= lpc32xx_gpio_set_value_p3,
 			.request		= lpc32xx_gpio_request,
 			.to_irq			= lpc32xx_gpio_to_irq_gpio_p3,
 			.base			= LPC32XX_GPIO_P3_GRP,
@@ -482,7 +482,7 @@ static struct lpc32xx_gpio_chip lpc32xx_gpiochip[] = {
 		.chip = {
 			.label			= "gpo_p3",
 			.direction_output	= lpc32xx_gpio_dir_out_always,
-			.set_rv			= lpc32xx_gpo_set_value,
+			.set			= lpc32xx_gpo_set_value,
 			.get			= lpc32xx_gpo_get_value,
 			.request		= lpc32xx_gpio_request,
 			.base			= LPC32XX_GPO_P3_GRP,
diff --git a/drivers/gpio/gpio-macsmc.c b/drivers/gpio/gpio-macsmc.c
index 7570d9e89adf..30ef258e7655 100644
--- a/drivers/gpio/gpio-macsmc.c
+++ b/drivers/gpio/gpio-macsmc.c
@@ -261,7 +261,7 @@ static int macsmc_gpio_probe(struct platform_device *pdev)
 	smcgp->gc.label = "macsmc-pmu-gpio";
 	smcgp->gc.owner = THIS_MODULE;
 	smcgp->gc.get = macsmc_gpio_get;
-	smcgp->gc.set_rv = macsmc_gpio_set;
+	smcgp->gc.set = macsmc_gpio_set;
 	smcgp->gc.get_direction = macsmc_gpio_get_direction;
 	smcgp->gc.init_valid_mask = macsmc_gpio_init_valid_mask;
 	smcgp->gc.can_sleep = true;
diff --git a/drivers/gpio/gpio-madera.c b/drivers/gpio/gpio-madera.c
index e73e72d62bc8..551faf9655b2 100644
--- a/drivers/gpio/gpio-madera.c
+++ b/drivers/gpio/gpio-madera.c
@@ -109,7 +109,7 @@ static const struct gpio_chip madera_gpio_chip = {
 	.direction_input	= madera_gpio_direction_in,
 	.get			= madera_gpio_get,
 	.direction_output	= madera_gpio_direction_out,
-	.set_rv			= madera_gpio_set,
+	.set			= madera_gpio_set,
 	.set_config		= gpiochip_generic_config,
 	.can_sleep		= true,
 };
diff --git a/drivers/gpio/gpio-max730x.c b/drivers/gpio/gpio-max730x.c
index 75d414d8c992..84c7c2dca822 100644
--- a/drivers/gpio/gpio-max730x.c
+++ b/drivers/gpio/gpio-max730x.c
@@ -188,7 +188,7 @@ int __max730x_probe(struct max7301 *ts)
 	ts->chip.direction_input = max7301_direction_input;
 	ts->chip.get = max7301_get;
 	ts->chip.direction_output = max7301_direction_output;
-	ts->chip.set_rv = max7301_set;
+	ts->chip.set = max7301_set;
 
 	ts->chip.ngpio = PIN_NUMBER;
 	ts->chip.can_sleep = true;
diff --git a/drivers/gpio/gpio-max732x.c b/drivers/gpio/gpio-max732x.c
index d5ffedb086af..a61d670ceeda 100644
--- a/drivers/gpio/gpio-max732x.c
+++ b/drivers/gpio/gpio-max732x.c
@@ -585,8 +585,8 @@ static int max732x_setup_gpio(struct max732x_chip *chip,
 		gc->direction_input = max732x_gpio_direction_input;
 	if (chip->dir_output) {
 		gc->direction_output = max732x_gpio_direction_output;
-		gc->set_rv = max732x_gpio_set_value;
-		gc->set_multiple_rv = max732x_gpio_set_multiple;
+		gc->set = max732x_gpio_set_value;
+		gc->set_multiple = max732x_gpio_set_multiple;
 	}
 	gc->get = max732x_gpio_get_value;
 	gc->can_sleep = true;
diff --git a/drivers/gpio/gpio-max77620.c b/drivers/gpio/gpio-max77620.c
index af7af8e40afe..02eca400b307 100644
--- a/drivers/gpio/gpio-max77620.c
+++ b/drivers/gpio/gpio-max77620.c
@@ -311,7 +311,7 @@ static int max77620_gpio_probe(struct platform_device *pdev)
 	mgpio->gpio_chip.direction_input = max77620_gpio_dir_input;
 	mgpio->gpio_chip.get = max77620_gpio_get;
 	mgpio->gpio_chip.direction_output = max77620_gpio_dir_output;
-	mgpio->gpio_chip.set_rv = max77620_gpio_set;
+	mgpio->gpio_chip.set = max77620_gpio_set;
 	mgpio->gpio_chip.set_config = max77620_gpio_set_config;
 	mgpio->gpio_chip.ngpio = MAX77620_GPIO_NR;
 	mgpio->gpio_chip.can_sleep = 1;
diff --git a/drivers/gpio/gpio-max77650.c b/drivers/gpio/gpio-max77650.c
index a553e141059f..4540da4c1418 100644
--- a/drivers/gpio/gpio-max77650.c
+++ b/drivers/gpio/gpio-max77650.c
@@ -166,7 +166,7 @@ static int max77650_gpio_probe(struct platform_device *pdev)
 
 	chip->gc.direction_input = max77650_gpio_direction_input;
 	chip->gc.direction_output = max77650_gpio_direction_output;
-	chip->gc.set_rv = max77650_gpio_set_value;
+	chip->gc.set = max77650_gpio_set_value;
 	chip->gc.get = max77650_gpio_get_value;
 	chip->gc.get_direction = max77650_gpio_get_direction;
 	chip->gc.set_config = max77650_gpio_set_config;
diff --git a/drivers/gpio/gpio-max77759.c b/drivers/gpio/gpio-max77759.c
index 7fe8e6f697d0..5e48eb03e7b3 100644
--- a/drivers/gpio/gpio-max77759.c
+++ b/drivers/gpio/gpio-max77759.c
@@ -469,7 +469,7 @@ static int max77759_gpio_probe(struct platform_device *pdev)
 	chip->gc.direction_input = max77759_gpio_direction_input;
 	chip->gc.direction_output = max77759_gpio_direction_output;
 	chip->gc.get = max77759_gpio_get_value;
-	chip->gc.set_rv = max77759_gpio_set_value;
+	chip->gc.set = max77759_gpio_set_value;
 
 	girq = &chip->gc.irq;
 	gpio_irq_chip_set_chip(girq, &max77759_gpio_irq_chip);
diff --git a/drivers/gpio/gpio-mb86s7x.c b/drivers/gpio/gpio-mb86s7x.c
index 5ee2991ecdfd..581a71872eab 100644
--- a/drivers/gpio/gpio-mb86s7x.c
+++ b/drivers/gpio/gpio-mb86s7x.c
@@ -180,7 +180,7 @@ static int mb86s70_gpio_probe(struct platform_device *pdev)
 	gchip->gc.request = mb86s70_gpio_request;
 	gchip->gc.free = mb86s70_gpio_free;
 	gchip->gc.get = mb86s70_gpio_get;
-	gchip->gc.set_rv = mb86s70_gpio_set;
+	gchip->gc.set = mb86s70_gpio_set;
 	gchip->gc.to_irq = mb86s70_gpio_to_irq;
 	gchip->gc.label = dev_name(&pdev->dev);
 	gchip->gc.ngpio = 32;
diff --git a/drivers/gpio/gpio-mc33880.c b/drivers/gpio/gpio-mc33880.c
index e68956104161..9a40e9579e95 100644
--- a/drivers/gpio/gpio-mc33880.c
+++ b/drivers/gpio/gpio-mc33880.c
@@ -103,7 +103,7 @@ static int mc33880_probe(struct spi_device *spi)
 	mc->spi = spi;
 
 	mc->chip.label = DRIVER_NAME;
-	mc->chip.set_rv = mc33880_set;
+	mc->chip.set = mc33880_set;
 	mc->chip.base = pdata->base;
 	mc->chip.ngpio = PIN_NUMBER;
 	mc->chip.can_sleep = true;
diff --git a/drivers/gpio/gpio-ml-ioh.c b/drivers/gpio/gpio-ml-ioh.c
index 12cf36f9ca63..f6af81bf2b13 100644
--- a/drivers/gpio/gpio-ml-ioh.c
+++ b/drivers/gpio/gpio-ml-ioh.c
@@ -224,7 +224,7 @@ static void ioh_gpio_setup(struct ioh_gpio *chip, int num_port)
 	gpio->direction_input = ioh_gpio_direction_input;
 	gpio->get = ioh_gpio_get;
 	gpio->direction_output = ioh_gpio_direction_output;
-	gpio->set_rv = ioh_gpio_set;
+	gpio->set = ioh_gpio_set;
 	gpio->dbg_show = NULL;
 	gpio->base = -1;
 	gpio->ngpio = num_port;
diff --git a/drivers/gpio/gpio-mm-lantiq.c b/drivers/gpio/gpio-mm-lantiq.c
index 897a1e004681..8f1405733d98 100644
--- a/drivers/gpio/gpio-mm-lantiq.c
+++ b/drivers/gpio/gpio-mm-lantiq.c
@@ -111,7 +111,7 @@ static int ltq_mm_probe(struct platform_device *pdev)
 
 	chip->mmchip.gc.ngpio = 16;
 	chip->mmchip.gc.direction_output = ltq_mm_dir_out;
-	chip->mmchip.gc.set_rv = ltq_mm_set;
+	chip->mmchip.gc.set = ltq_mm_set;
 	chip->mmchip.save_regs = ltq_mm_save_regs;
 
 	/* store the shadow value if one was passed by the devicetree */
diff --git a/drivers/gpio/gpio-mmio.c b/drivers/gpio/gpio-mmio.c
index cf878c2ea6bf..021ad62778c2 100644
--- a/drivers/gpio/gpio-mmio.c
+++ b/drivers/gpio/gpio-mmio.c
@@ -367,7 +367,7 @@ static int bgpio_dir_out_err(struct gpio_chip *gc, unsigned int gpio,
 static int bgpio_simple_dir_out(struct gpio_chip *gc, unsigned int gpio,
 				int val)
 {
-	gc->set_rv(gc, gpio, val);
+	gc->set(gc, gpio, val);
 
 	return bgpio_dir_return(gc, gpio, true);
 }
@@ -432,14 +432,14 @@ static int bgpio_dir_out_dir_first(struct gpio_chip *gc, unsigned int gpio,
 				   int val)
 {
 	bgpio_dir_out(gc, gpio, val);
-	gc->set_rv(gc, gpio, val);
+	gc->set(gc, gpio, val);
 	return bgpio_dir_return(gc, gpio, true);
 }
 
 static int bgpio_dir_out_val_first(struct gpio_chip *gc, unsigned int gpio,
 				   int val)
 {
-	gc->set_rv(gc, gpio, val);
+	gc->set(gc, gpio, val);
 	bgpio_dir_out(gc, gpio, val);
 	return bgpio_dir_return(gc, gpio, true);
 }
@@ -528,18 +528,18 @@ static int bgpio_setup_io(struct gpio_chip *gc,
 	if (set && clr) {
 		gc->reg_set = set;
 		gc->reg_clr = clr;
-		gc->set_rv = bgpio_set_with_clear;
-		gc->set_multiple_rv = bgpio_set_multiple_with_clear;
+		gc->set = bgpio_set_with_clear;
+		gc->set_multiple = bgpio_set_multiple_with_clear;
 	} else if (set && !clr) {
 		gc->reg_set = set;
-		gc->set_rv = bgpio_set_set;
-		gc->set_multiple_rv = bgpio_set_multiple_set;
+		gc->set = bgpio_set_set;
+		gc->set_multiple = bgpio_set_multiple_set;
 	} else if (flags & BGPIOF_NO_OUTPUT) {
-		gc->set_rv = bgpio_set_none;
-		gc->set_multiple_rv = NULL;
+		gc->set = bgpio_set_none;
+		gc->set_multiple = NULL;
 	} else {
-		gc->set_rv = bgpio_set;
-		gc->set_multiple_rv = bgpio_set_multiple;
+		gc->set = bgpio_set;
+		gc->set_multiple = bgpio_set_multiple;
 	}
 
 	if (!(flags & BGPIOF_UNREADABLE_REG_SET) &&
@@ -676,7 +676,7 @@ int bgpio_init(struct gpio_chip *gc, struct device *dev,
 	}
 
 	gc->bgpio_data = gc->read_reg(gc->reg_dat);
-	if (gc->set_rv == bgpio_set_set &&
+	if (gc->set == bgpio_set_set &&
 			!(flags & BGPIOF_UNREADABLE_REG_SET))
 		gc->bgpio_data = gc->read_reg(gc->reg_set);
 
diff --git a/drivers/gpio/gpio-mockup.c b/drivers/gpio/gpio-mockup.c
index 266c0953d914..a7d69f3835c1 100644
--- a/drivers/gpio/gpio-mockup.c
+++ b/drivers/gpio/gpio-mockup.c
@@ -449,9 +449,9 @@ static int gpio_mockup_probe(struct platform_device *pdev)
 	gc->owner = THIS_MODULE;
 	gc->parent = dev;
 	gc->get = gpio_mockup_get;
-	gc->set_rv = gpio_mockup_set;
+	gc->set = gpio_mockup_set;
 	gc->get_multiple = gpio_mockup_get_multiple;
-	gc->set_multiple_rv = gpio_mockup_set_multiple;
+	gc->set_multiple = gpio_mockup_set_multiple;
 	gc->direction_output = gpio_mockup_dirout;
 	gc->direction_input = gpio_mockup_dirin;
 	gc->get_direction = gpio_mockup_get_direction;
diff --git a/drivers/gpio/gpio-moxtet.c b/drivers/gpio/gpio-moxtet.c
index 27dd9c3e7b77..4eb9f1a2779b 100644
--- a/drivers/gpio/gpio-moxtet.c
+++ b/drivers/gpio/gpio-moxtet.c
@@ -140,7 +140,7 @@ static int moxtet_gpio_probe(struct device *dev)
 	chip->gpio_chip.direction_input = moxtet_gpio_direction_input;
 	chip->gpio_chip.direction_output = moxtet_gpio_direction_output;
 	chip->gpio_chip.get = moxtet_gpio_get_value;
-	chip->gpio_chip.set_rv = moxtet_gpio_set_value;
+	chip->gpio_chip.set = moxtet_gpio_set_value;
 	chip->gpio_chip.base = -1;
 
 	chip->gpio_chip.ngpio = MOXTET_GPIO_NGPIOS;
diff --git a/drivers/gpio/gpio-mpc5200.c b/drivers/gpio/gpio-mpc5200.c
index 40d587176a75..dad0eca1ca2e 100644
--- a/drivers/gpio/gpio-mpc5200.c
+++ b/drivers/gpio/gpio-mpc5200.c
@@ -153,7 +153,7 @@ static int mpc52xx_wkup_gpiochip_probe(struct platform_device *ofdev)
 	gc->direction_input  = mpc52xx_wkup_gpio_dir_in;
 	gc->direction_output = mpc52xx_wkup_gpio_dir_out;
 	gc->get              = mpc52xx_wkup_gpio_get;
-	gc->set_rv           = mpc52xx_wkup_gpio_set;
+	gc->set              = mpc52xx_wkup_gpio_set;
 
 	ret = of_mm_gpiochip_add_data(ofdev->dev.of_node, &chip->mmchip, chip);
 	if (ret)
@@ -315,7 +315,7 @@ static int mpc52xx_simple_gpiochip_probe(struct platform_device *ofdev)
 	gc->direction_input  = mpc52xx_simple_gpio_dir_in;
 	gc->direction_output = mpc52xx_simple_gpio_dir_out;
 	gc->get              = mpc52xx_simple_gpio_get;
-	gc->set_rv           = mpc52xx_simple_gpio_set;
+	gc->set              = mpc52xx_simple_gpio_set;
 
 	ret = of_mm_gpiochip_add_data(ofdev->dev.of_node, &chip->mmchip, chip);
 	if (ret)
diff --git a/drivers/gpio/gpio-mpfs.c b/drivers/gpio/gpio-mpfs.c
index 3415cb7ebb0f..82d557a7e5d8 100644
--- a/drivers/gpio/gpio-mpfs.c
+++ b/drivers/gpio/gpio-mpfs.c
@@ -150,7 +150,7 @@ static int mpfs_gpio_probe(struct platform_device *pdev)
 	mpfs_gpio->gc.direction_output = mpfs_gpio_direction_output;
 	mpfs_gpio->gc.get_direction = mpfs_gpio_get_direction;
 	mpfs_gpio->gc.get = mpfs_gpio_get;
-	mpfs_gpio->gc.set_rv = mpfs_gpio_set;
+	mpfs_gpio->gc.set = mpfs_gpio_set;
 	mpfs_gpio->gc.base = -1;
 	mpfs_gpio->gc.ngpio = ngpios;
 	mpfs_gpio->gc.label = dev_name(dev);
diff --git a/drivers/gpio/gpio-mpsse.c b/drivers/gpio/gpio-mpsse.c
index b17de08e9e03..9f42bb30b4ec 100644
--- a/drivers/gpio/gpio-mpsse.c
+++ b/drivers/gpio/gpio-mpsse.c
@@ -448,9 +448,9 @@ static int gpio_mpsse_probe(struct usb_interface *interface,
 	priv->gpio.direction_input = gpio_mpsse_direction_input;
 	priv->gpio.direction_output = gpio_mpsse_direction_output;
 	priv->gpio.get = gpio_mpsse_gpio_get;
-	priv->gpio.set_rv = gpio_mpsse_gpio_set;
+	priv->gpio.set = gpio_mpsse_gpio_set;
 	priv->gpio.get_multiple = gpio_mpsse_get_multiple;
-	priv->gpio.set_multiple_rv = gpio_mpsse_set_multiple;
+	priv->gpio.set_multiple = gpio_mpsse_set_multiple;
 	priv->gpio.base = -1;
 	priv->gpio.ngpio = 16;
 	priv->gpio.offset = priv->intf_id * priv->gpio.ngpio;
diff --git a/drivers/gpio/gpio-msc313.c b/drivers/gpio/gpio-msc313.c
index 992339a89d19..b0cccd856840 100644
--- a/drivers/gpio/gpio-msc313.c
+++ b/drivers/gpio/gpio-msc313.c
@@ -658,7 +658,7 @@ static int msc313_gpio_probe(struct platform_device *pdev)
 	gpiochip->direction_input = msc313_gpio_direction_input;
 	gpiochip->direction_output = msc313_gpio_direction_output;
 	gpiochip->get = msc313_gpio_get;
-	gpiochip->set_rv = msc313_gpio_set;
+	gpiochip->set = msc313_gpio_set;
 	gpiochip->base = -1;
 	gpiochip->ngpio = gpio->gpio_data->num;
 	gpiochip->names = gpio->gpio_data->names;
diff --git a/drivers/gpio/gpio-mvebu.c b/drivers/gpio/gpio-mvebu.c
index 24792b8eb083..5e3f54cb8bc4 100644
--- a/drivers/gpio/gpio-mvebu.c
+++ b/drivers/gpio/gpio-mvebu.c
@@ -1168,7 +1168,7 @@ static int mvebu_gpio_probe(struct platform_device *pdev)
 	mvchip->chip.direction_input = mvebu_gpio_direction_input;
 	mvchip->chip.get = mvebu_gpio_get;
 	mvchip->chip.direction_output = mvebu_gpio_direction_output;
-	mvchip->chip.set_rv = mvebu_gpio_set;
+	mvchip->chip.set = mvebu_gpio_set;
 	if (have_irqs)
 		mvchip->chip.to_irq = mvebu_gpio_to_irq;
 	mvchip->chip.base = id * MVEBU_MAX_GPIO_PER_BANK;
diff --git a/drivers/gpio/gpio-nomadik.c b/drivers/gpio/gpio-nomadik.c
index 296d13845b30..bcf4b07dd458 100644
--- a/drivers/gpio/gpio-nomadik.c
+++ b/drivers/gpio/gpio-nomadik.c
@@ -674,7 +674,7 @@ static int nmk_gpio_probe(struct platform_device *pdev)
 	chip->direction_input = nmk_gpio_make_input;
 	chip->get = nmk_gpio_get_input;
 	chip->direction_output = nmk_gpio_make_output;
-	chip->set_rv = nmk_gpio_set_output;
+	chip->set = nmk_gpio_set_output;
 	chip->dbg_show = nmk_gpio_dbg_show;
 	chip->can_sleep = false;
 	chip->owner = THIS_MODULE;
diff --git a/drivers/gpio/gpio-npcm-sgpio.c b/drivers/gpio/gpio-npcm-sgpio.c
index 25b203a89e38..83c77a2c0623 100644
--- a/drivers/gpio/gpio-npcm-sgpio.c
+++ b/drivers/gpio/gpio-npcm-sgpio.c
@@ -211,7 +211,7 @@ static int npcm_sgpio_dir_in(struct gpio_chip *gc, unsigned int offset)
 
 static int npcm_sgpio_dir_out(struct gpio_chip *gc, unsigned int offset, int val)
 {
-	return gc->set_rv(gc, offset, val);
+	return gc->set(gc, offset, val);
 }
 
 static int npcm_sgpio_get_direction(struct gpio_chip *gc, unsigned int offset)
@@ -546,7 +546,7 @@ static int npcm_sgpio_probe(struct platform_device *pdev)
 	gpio->chip.direction_output = npcm_sgpio_dir_out;
 	gpio->chip.get_direction = npcm_sgpio_get_direction;
 	gpio->chip.get = npcm_sgpio_get;
-	gpio->chip.set_rv = npcm_sgpio_set;
+	gpio->chip.set = npcm_sgpio_set;
 	gpio->chip.label = dev_name(&pdev->dev);
 	gpio->chip.base = -1;
 
diff --git a/drivers/gpio/gpio-octeon.c b/drivers/gpio/gpio-octeon.c
index 24966161742a..777e20c608dc 100644
--- a/drivers/gpio/gpio-octeon.c
+++ b/drivers/gpio/gpio-octeon.c
@@ -108,7 +108,7 @@ static int octeon_gpio_probe(struct platform_device *pdev)
 	chip->direction_input = octeon_gpio_dir_in;
 	chip->get = octeon_gpio_get;
 	chip->direction_output = octeon_gpio_dir_out;
-	chip->set_rv = octeon_gpio_set;
+	chip->set = octeon_gpio_set;
 	err = devm_gpiochip_add_data(&pdev->dev, chip, gpio);
 	if (err)
 		return err;
diff --git a/drivers/gpio/gpio-omap.c b/drivers/gpio/gpio-omap.c
index ed5c88a5c520..a268c76bdca6 100644
--- a/drivers/gpio/gpio-omap.c
+++ b/drivers/gpio/gpio-omap.c
@@ -1046,8 +1046,8 @@ static int omap_gpio_chip_init(struct gpio_bank *bank, struct device *pm_dev)
 	bank->chip.get_multiple = omap_gpio_get_multiple;
 	bank->chip.direction_output = omap_gpio_output;
 	bank->chip.set_config = omap_gpio_set_config;
-	bank->chip.set_rv = omap_gpio_set;
-	bank->chip.set_multiple_rv = omap_gpio_set_multiple;
+	bank->chip.set = omap_gpio_set;
+	bank->chip.set_multiple = omap_gpio_set_multiple;
 	if (bank->is_mpuio) {
 		bank->chip.label = "mpuio";
 		if (bank->regs->wkup_en)
diff --git a/drivers/gpio/gpio-palmas.c b/drivers/gpio/gpio-palmas.c
index 9329d8ce8f59..e377f6dd4ccf 100644
--- a/drivers/gpio/gpio-palmas.c
+++ b/drivers/gpio/gpio-palmas.c
@@ -166,7 +166,7 @@ static int palmas_gpio_probe(struct platform_device *pdev)
 	palmas_gpio->gpio_chip.direction_input = palmas_gpio_input;
 	palmas_gpio->gpio_chip.direction_output = palmas_gpio_output;
 	palmas_gpio->gpio_chip.to_irq = palmas_gpio_to_irq;
-	palmas_gpio->gpio_chip.set_rv	= palmas_gpio_set;
+	palmas_gpio->gpio_chip.set	= palmas_gpio_set;
 	palmas_gpio->gpio_chip.get	= palmas_gpio_get;
 	palmas_gpio->gpio_chip.parent = &pdev->dev;
 
diff --git a/drivers/gpio/gpio-pca953x.c b/drivers/gpio/gpio-pca953x.c
index 69906a9af7e6..b46927f55038 100644
--- a/drivers/gpio/gpio-pca953x.c
+++ b/drivers/gpio/gpio-pca953x.c
@@ -789,10 +789,10 @@ static void pca953x_setup_gpio(struct pca953x_chip *chip, int gpios)
 	gc->direction_input  = pca953x_gpio_direction_input;
 	gc->direction_output = pca953x_gpio_direction_output;
 	gc->get = pca953x_gpio_get_value;
-	gc->set_rv = pca953x_gpio_set_value;
+	gc->set = pca953x_gpio_set_value;
 	gc->get_direction = pca953x_gpio_get_direction;
 	gc->get_multiple = pca953x_gpio_get_multiple;
-	gc->set_multiple_rv = pca953x_gpio_set_multiple;
+	gc->set_multiple = pca953x_gpio_set_multiple;
 	gc->set_config = pca953x_gpio_set_config;
 	gc->can_sleep = true;
 
diff --git a/drivers/gpio/gpio-pca9570.c b/drivers/gpio/gpio-pca9570.c
index a33246f20fd8..c5a1287079a0 100644
--- a/drivers/gpio/gpio-pca9570.c
+++ b/drivers/gpio/gpio-pca9570.c
@@ -126,7 +126,7 @@ static int pca9570_probe(struct i2c_client *client)
 	gpio->chip.owner = THIS_MODULE;
 	gpio->chip.get_direction = pca9570_get_direction;
 	gpio->chip.get = pca9570_get;
-	gpio->chip.set_rv = pca9570_set;
+	gpio->chip.set = pca9570_set;
 	gpio->chip.base = -1;
 	gpio->chip_data = device_get_match_data(&client->dev);
 	gpio->chip.ngpio = gpio->chip_data->ngpio;
diff --git a/drivers/gpio/gpio-pcf857x.c b/drivers/gpio/gpio-pcf857x.c
index a04203680333..3b9de8c3d924 100644
--- a/drivers/gpio/gpio-pcf857x.c
+++ b/drivers/gpio/gpio-pcf857x.c
@@ -295,8 +295,8 @@ static int pcf857x_probe(struct i2c_client *client)
 	gpio->chip.owner		= THIS_MODULE;
 	gpio->chip.get			= pcf857x_get;
 	gpio->chip.get_multiple		= pcf857x_get_multiple;
-	gpio->chip.set_rv		= pcf857x_set;
-	gpio->chip.set_multiple_rv	= pcf857x_set_multiple;
+	gpio->chip.set			= pcf857x_set;
+	gpio->chip.set_multiple		= pcf857x_set_multiple;
 	gpio->chip.direction_input	= pcf857x_input;
 	gpio->chip.direction_output	= pcf857x_output;
 	gpio->chip.ngpio		= (uintptr_t)i2c_get_match_data(client);
diff --git a/drivers/gpio/gpio-pch.c b/drivers/gpio/gpio-pch.c
index c6f313342ba0..9925687e05fb 100644
--- a/drivers/gpio/gpio-pch.c
+++ b/drivers/gpio/gpio-pch.c
@@ -219,7 +219,7 @@ static void pch_gpio_setup(struct pch_gpio *chip)
 	gpio->direction_input = pch_gpio_direction_input;
 	gpio->get = pch_gpio_get;
 	gpio->direction_output = pch_gpio_direction_output;
-	gpio->set_rv = pch_gpio_set;
+	gpio->set = pch_gpio_set;
 	gpio->base = -1;
 	gpio->ngpio = gpio_pins[chip->ioh];
 	gpio->can_sleep = false;
diff --git a/drivers/gpio/gpio-pl061.c b/drivers/gpio/gpio-pl061.c
index 98cfac4eac85..02e4ffcf5a6f 100644
--- a/drivers/gpio/gpio-pl061.c
+++ b/drivers/gpio/gpio-pl061.c
@@ -330,7 +330,7 @@ static int pl061_probe(struct amba_device *adev, const struct amba_id *id)
 	pl061->gc.direction_input = pl061_direction_input;
 	pl061->gc.direction_output = pl061_direction_output;
 	pl061->gc.get = pl061_get_value;
-	pl061->gc.set_rv = pl061_set_value;
+	pl061->gc.set = pl061_set_value;
 	pl061->gc.ngpio = PL061_GPIO_NR;
 	pl061->gc.label = dev_name(dev);
 	pl061->gc.parent = dev;
diff --git a/drivers/gpio/gpio-pxa.c b/drivers/gpio/gpio-pxa.c
index cbcdd416f8b9..fa22f3faa163 100644
--- a/drivers/gpio/gpio-pxa.c
+++ b/drivers/gpio/gpio-pxa.c
@@ -355,7 +355,7 @@ static int pxa_init_gpio_chip(struct pxa_gpio_chip *pchip, int ngpio, void __iom
 	pchip->chip.direction_input  = pxa_gpio_direction_input;
 	pchip->chip.direction_output = pxa_gpio_direction_output;
 	pchip->chip.get = pxa_gpio_get;
-	pchip->chip.set_rv = pxa_gpio_set;
+	pchip->chip.set = pxa_gpio_set;
 	pchip->chip.to_irq = pxa_gpio_to_irq;
 	pchip->chip.ngpio = ngpio;
 	pchip->chip.request = gpiochip_generic_request;
diff --git a/drivers/gpio/gpio-raspberrypi-exp.c b/drivers/gpio/gpio-raspberrypi-exp.c
index b4b607515a04..40413e06b69c 100644
--- a/drivers/gpio/gpio-raspberrypi-exp.c
+++ b/drivers/gpio/gpio-raspberrypi-exp.c
@@ -232,7 +232,7 @@ static int rpi_exp_gpio_probe(struct platform_device *pdev)
 	rpi_gpio->gc.direction_output = rpi_exp_gpio_dir_out;
 	rpi_gpio->gc.get_direction = rpi_exp_gpio_get_direction;
 	rpi_gpio->gc.get = rpi_exp_gpio_get;
-	rpi_gpio->gc.set_rv = rpi_exp_gpio_set;
+	rpi_gpio->gc.set = rpi_exp_gpio_set;
 	rpi_gpio->gc.can_sleep = true;
 
 	return devm_gpiochip_add_data(dev, &rpi_gpio->gc, rpi_gpio);
diff --git a/drivers/gpio/gpio-rc5t583.c b/drivers/gpio/gpio-rc5t583.c
index cf3e91d235df..5a69e4534591 100644
--- a/drivers/gpio/gpio-rc5t583.c
+++ b/drivers/gpio/gpio-rc5t583.c
@@ -118,7 +118,7 @@ static int rc5t583_gpio_probe(struct platform_device *pdev)
 	rc5t583_gpio->gpio_chip.free = rc5t583_gpio_free,
 	rc5t583_gpio->gpio_chip.direction_input = rc5t583_gpio_dir_input,
 	rc5t583_gpio->gpio_chip.direction_output = rc5t583_gpio_dir_output,
-	rc5t583_gpio->gpio_chip.set_rv = rc5t583_gpio_set,
+	rc5t583_gpio->gpio_chip.set = rc5t583_gpio_set,
 	rc5t583_gpio->gpio_chip.get = rc5t583_gpio_get,
 	rc5t583_gpio->gpio_chip.to_irq = rc5t583_gpio_to_irq,
 	rc5t583_gpio->gpio_chip.ngpio = RC5T583_MAX_GPIO,
diff --git a/drivers/gpio/gpio-rcar.c b/drivers/gpio/gpio-rcar.c
index cd31580effa9..86777e097fd8 100644
--- a/drivers/gpio/gpio-rcar.c
+++ b/drivers/gpio/gpio-rcar.c
@@ -535,8 +535,8 @@ static int gpio_rcar_probe(struct platform_device *pdev)
 	gpio_chip->get = gpio_rcar_get;
 	gpio_chip->get_multiple = gpio_rcar_get_multiple;
 	gpio_chip->direction_output = gpio_rcar_direction_output;
-	gpio_chip->set_rv = gpio_rcar_set;
-	gpio_chip->set_multiple_rv = gpio_rcar_set_multiple;
+	gpio_chip->set = gpio_rcar_set;
+	gpio_chip->set_multiple = gpio_rcar_set_multiple;
 	gpio_chip->label = name;
 	gpio_chip->parent = dev;
 	gpio_chip->owner = THIS_MODULE;
diff --git a/drivers/gpio/gpio-rdc321x.c b/drivers/gpio/gpio-rdc321x.c
index a75ed8021de5..ba62b81aa8ae 100644
--- a/drivers/gpio/gpio-rdc321x.c
+++ b/drivers/gpio/gpio-rdc321x.c
@@ -159,7 +159,7 @@ static int rdc321x_gpio_probe(struct platform_device *pdev)
 	rdc321x_gpio_dev->chip.direction_input = rdc_gpio_direction_input;
 	rdc321x_gpio_dev->chip.direction_output = rdc_gpio_config;
 	rdc321x_gpio_dev->chip.get = rdc_gpio_get_value;
-	rdc321x_gpio_dev->chip.set_rv = rdc_gpio_set_value;
+	rdc321x_gpio_dev->chip.set = rdc_gpio_set_value;
 	rdc321x_gpio_dev->chip.base = 0;
 	rdc321x_gpio_dev->chip.ngpio = pdata->max_gpios;
 
diff --git a/drivers/gpio/gpio-reg.c b/drivers/gpio/gpio-reg.c
index d8da99f97385..f2238196faf1 100644
--- a/drivers/gpio/gpio-reg.c
+++ b/drivers/gpio/gpio-reg.c
@@ -46,7 +46,7 @@ static int gpio_reg_direction_output(struct gpio_chip *gc, unsigned offset,
 	if (r->direction & BIT(offset))
 		return -ENOTSUPP;
 
-	gc->set_rv(gc, offset, value);
+	gc->set(gc, offset, value);
 	return 0;
 }
 
@@ -161,9 +161,9 @@ struct gpio_chip *gpio_reg_init(struct device *dev, void __iomem *reg,
 	r->gc.get_direction = gpio_reg_get_direction;
 	r->gc.direction_input = gpio_reg_direction_input;
 	r->gc.direction_output = gpio_reg_direction_output;
-	r->gc.set_rv = gpio_reg_set;
+	r->gc.set = gpio_reg_set;
 	r->gc.get = gpio_reg_get;
-	r->gc.set_multiple_rv = gpio_reg_set_multiple;
+	r->gc.set_multiple = gpio_reg_set_multiple;
 	if (irqs)
 		r->gc.to_irq = gpio_reg_to_irq;
 	r->gc.base = base;
diff --git a/drivers/gpio/gpio-regmap.c b/drivers/gpio/gpio-regmap.c
index 87c4225784cf..e8a32dfebdcb 100644
--- a/drivers/gpio/gpio-regmap.c
+++ b/drivers/gpio/gpio-regmap.c
@@ -260,9 +260,9 @@ struct gpio_regmap *gpio_regmap_register(const struct gpio_regmap_config *config
 	chip->free = gpiochip_generic_free;
 	chip->get = gpio_regmap_get;
 	if (gpio->reg_set_base && gpio->reg_clr_base)
-		chip->set_rv = gpio_regmap_set_with_clear;
+		chip->set = gpio_regmap_set_with_clear;
 	else if (gpio->reg_set_base)
-		chip->set_rv = gpio_regmap_set;
+		chip->set = gpio_regmap_set;
 
 	chip->get_direction = gpio_regmap_get_direction;
 	if (gpio->reg_dir_in_base || gpio->reg_dir_out_base) {
diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c
index ecd60ff9e1dd..bcfc323a8315 100644
--- a/drivers/gpio/gpio-rockchip.c
+++ b/drivers/gpio/gpio-rockchip.c
@@ -327,7 +327,7 @@ static int rockchip_gpio_to_irq(struct gpio_chip *gc, unsigned int offset)
 static const struct gpio_chip rockchip_gpiolib_chip = {
 	.request = gpiochip_generic_request,
 	.free = gpiochip_generic_free,
-	.set_rv = rockchip_gpio_set,
+	.set = rockchip_gpio_set,
 	.get = rockchip_gpio_get,
 	.get_direction	= rockchip_gpio_get_direction,
 	.direction_input = rockchip_gpio_direction_input,
diff --git a/drivers/gpio/gpio-rtd.c b/drivers/gpio/gpio-rtd.c
index 25bbd749b019..d46b40dd5283 100644
--- a/drivers/gpio/gpio-rtd.c
+++ b/drivers/gpio/gpio-rtd.c
@@ -565,7 +565,7 @@ static int rtd_gpio_probe(struct platform_device *pdev)
 	data->gpio_chip.get_direction = rtd_gpio_get_direction;
 	data->gpio_chip.direction_input = rtd_gpio_direction_input;
 	data->gpio_chip.direction_output = rtd_gpio_direction_output;
-	data->gpio_chip.set_rv = rtd_gpio_set;
+	data->gpio_chip.set = rtd_gpio_set;
 	data->gpio_chip.get = rtd_gpio_get;
 	data->gpio_chip.set_config = rtd_gpio_set_config;
 	data->gpio_chip.parent = dev;
diff --git a/drivers/gpio/gpio-sa1100.c b/drivers/gpio/gpio-sa1100.c
index e9d054d78ccb..7f6a62f5d1ee 100644
--- a/drivers/gpio/gpio-sa1100.c
+++ b/drivers/gpio/gpio-sa1100.c
@@ -99,7 +99,7 @@ static struct sa1100_gpio_chip sa1100_gpio_chip = {
 		.get_direction		= sa1100_get_direction,
 		.direction_input	= sa1100_direction_input,
 		.direction_output	= sa1100_direction_output,
-		.set_rv			= sa1100_gpio_set,
+		.set			= sa1100_gpio_set,
 		.get			= sa1100_gpio_get,
 		.to_irq			= sa1100_to_irq,
 		.base			= 0,
diff --git a/drivers/gpio/gpio-sama5d2-piobu.c b/drivers/gpio/gpio-sama5d2-piobu.c
index c31244cf5e89..5005688f6e67 100644
--- a/drivers/gpio/gpio-sama5d2-piobu.c
+++ b/drivers/gpio/gpio-sama5d2-piobu.c
@@ -196,7 +196,7 @@ static int sama5d2_piobu_probe(struct platform_device *pdev)
 	piobu->chip.direction_input = sama5d2_piobu_direction_input;
 	piobu->chip.direction_output = sama5d2_piobu_direction_output;
 	piobu->chip.get = sama5d2_piobu_get;
-	piobu->chip.set_rv = sama5d2_piobu_set;
+	piobu->chip.set = sama5d2_piobu_set;
 	piobu->chip.base = -1;
 	piobu->chip.ngpio = PIOBU_NUM;
 	piobu->chip.can_sleep = 0;
diff --git a/drivers/gpio/gpio-sch.c b/drivers/gpio/gpio-sch.c
index 833ffdd98d74..966d16a6d515 100644
--- a/drivers/gpio/gpio-sch.c
+++ b/drivers/gpio/gpio-sch.c
@@ -167,7 +167,7 @@ static const struct gpio_chip sch_gpio_chip = {
 	.direction_input	= sch_gpio_direction_in,
 	.get			= sch_gpio_get,
 	.direction_output	= sch_gpio_direction_out,
-	.set_rv			= sch_gpio_set,
+	.set			= sch_gpio_set,
 	.get_direction		= sch_gpio_get_direction,
 };
 
diff --git a/drivers/gpio/gpio-sch311x.c b/drivers/gpio/gpio-sch311x.c
index 44fb5fc21fb8..f95566998d30 100644
--- a/drivers/gpio/gpio-sch311x.c
+++ b/drivers/gpio/gpio-sch311x.c
@@ -297,7 +297,7 @@ static int sch311x_gpio_probe(struct platform_device *pdev)
 		block->chip.get_direction = sch311x_gpio_get_direction;
 		block->chip.set_config = sch311x_gpio_set_config;
 		block->chip.get = sch311x_gpio_get;
-		block->chip.set_rv = sch311x_gpio_set;
+		block->chip.set = sch311x_gpio_set;
 		block->chip.ngpio = 8;
 		block->chip.parent = &pdev->dev;
 		block->chip.base = sch311x_gpio_blocks[i].base;
diff --git a/drivers/gpio/gpio-sim.c b/drivers/gpio/gpio-sim.c
index 9503296422fd..050092583f79 100644
--- a/drivers/gpio/gpio-sim.c
+++ b/drivers/gpio/gpio-sim.c
@@ -486,9 +486,9 @@ static int gpio_sim_add_bank(struct fwnode_handle *swnode, struct device *dev)
 	gc->parent = dev;
 	gc->fwnode = swnode;
 	gc->get = gpio_sim_get;
-	gc->set_rv = gpio_sim_set;
+	gc->set = gpio_sim_set;
 	gc->get_multiple = gpio_sim_get_multiple;
-	gc->set_multiple_rv = gpio_sim_set_multiple;
+	gc->set_multiple = gpio_sim_set_multiple;
 	gc->direction_output = gpio_sim_direction_output;
 	gc->direction_input = gpio_sim_direction_input;
 	gc->get_direction = gpio_sim_get_direction;
diff --git a/drivers/gpio/gpio-siox.c b/drivers/gpio/gpio-siox.c
index 95355dda621b..958034b9f3f3 100644
--- a/drivers/gpio/gpio-siox.c
+++ b/drivers/gpio/gpio-siox.c
@@ -237,7 +237,7 @@ static int gpio_siox_probe(struct siox_device *sdevice)
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
 	gc->get = gpio_siox_get;
-	gc->set_rv = gpio_siox_set;
+	gc->set = gpio_siox_set;
 	gc->direction_input = gpio_siox_direction_input;
 	gc->direction_output = gpio_siox_direction_output;
 	gc->get_direction = gpio_siox_get_direction;
diff --git a/drivers/gpio/gpio-spear-spics.c b/drivers/gpio/gpio-spear-spics.c
index 55f0e8afa291..96a0e1211500 100644
--- a/drivers/gpio/gpio-spear-spics.c
+++ b/drivers/gpio/gpio-spear-spics.c
@@ -140,7 +140,7 @@ static int spics_gpio_probe(struct platform_device *pdev)
 	spics->chip.request = spics_request;
 	spics->chip.free = spics_free;
 	spics->chip.direction_output = spics_direction_output;
-	spics->chip.set_rv = spics_set_value;
+	spics->chip.set = spics_set_value;
 	spics->chip.label = dev_name(&pdev->dev);
 	spics->chip.parent = &pdev->dev;
 	spics->chip.owner = THIS_MODULE;
diff --git a/drivers/gpio/gpio-sprd.c b/drivers/gpio/gpio-sprd.c
index bbd5bf51c088..413bcd0a4240 100644
--- a/drivers/gpio/gpio-sprd.c
+++ b/drivers/gpio/gpio-sprd.c
@@ -245,7 +245,7 @@ static int sprd_gpio_probe(struct platform_device *pdev)
 	sprd_gpio->chip.request = sprd_gpio_request;
 	sprd_gpio->chip.free = sprd_gpio_free;
 	sprd_gpio->chip.get = sprd_gpio_get;
-	sprd_gpio->chip.set_rv = sprd_gpio_set;
+	sprd_gpio->chip.set = sprd_gpio_set;
 	sprd_gpio->chip.direction_input = sprd_gpio_direction_input;
 	sprd_gpio->chip.direction_output = sprd_gpio_direction_output;
 
diff --git a/drivers/gpio/gpio-stmpe.c b/drivers/gpio/gpio-stmpe.c
index 0a270156e0be..5dd4c21a8e60 100644
--- a/drivers/gpio/gpio-stmpe.c
+++ b/drivers/gpio/gpio-stmpe.c
@@ -136,7 +136,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= stmpe_gpio_direction_input,
 	.get			= stmpe_gpio_get,
 	.direction_output	= stmpe_gpio_direction_output,
-	.set_rv			= stmpe_gpio_set,
+	.set			= stmpe_gpio_set,
 	.request		= stmpe_gpio_request,
 	.can_sleep		= true,
 };
diff --git a/drivers/gpio/gpio-stp-xway.c b/drivers/gpio/gpio-stp-xway.c
index fdda8de6ca36..493c027afdd6 100644
--- a/drivers/gpio/gpio-stp-xway.c
+++ b/drivers/gpio/gpio-stp-xway.c
@@ -249,7 +249,7 @@ static int xway_stp_probe(struct platform_device *pdev)
 	chip->gc.label = "stp-xway";
 	chip->gc.direction_output = xway_stp_dir_out;
 	chip->gc.get = xway_stp_get;
-	chip->gc.set_rv = xway_stp_set;
+	chip->gc.set = xway_stp_set;
 	chip->gc.request = xway_stp_request;
 	chip->gc.base = -1;
 	chip->gc.owner = THIS_MODULE;
diff --git a/drivers/gpio/gpio-syscon.c b/drivers/gpio/gpio-syscon.c
index f86f78655c24..40064d4cf47f 100644
--- a/drivers/gpio/gpio-syscon.c
+++ b/drivers/gpio/gpio-syscon.c
@@ -115,7 +115,7 @@ static int syscon_gpio_dir_out(struct gpio_chip *chip, unsigned offset, int val)
 				   BIT(offs % SYSCON_REG_BITS));
 	}
 
-	return chip->set_rv(chip, offset, val);
+	return chip->set(chip, offset, val);
 }
 
 static const struct syscon_gpio_data clps711x_mctrl_gpio = {
@@ -251,7 +251,7 @@ static int syscon_gpio_probe(struct platform_device *pdev)
 	if (priv->data->flags & GPIO_SYSCON_FEAT_IN)
 		priv->chip.direction_input = syscon_gpio_dir_in;
 	if (priv->data->flags & GPIO_SYSCON_FEAT_OUT) {
-		priv->chip.set_rv = priv->data->set ? : syscon_gpio_set;
+		priv->chip.set = priv->data->set ? : syscon_gpio_set;
 		priv->chip.direction_output = syscon_gpio_dir_out;
 	}
 
diff --git a/drivers/gpio/gpio-tangier.c b/drivers/gpio/gpio-tangier.c
index ce17b98e0623..ba5a8ede8912 100644
--- a/drivers/gpio/gpio-tangier.c
+++ b/drivers/gpio/gpio-tangier.c
@@ -430,7 +430,7 @@ int devm_tng_gpio_probe(struct device *dev, struct tng_gpio *gpio)
 	gpio->chip.direction_input = tng_gpio_direction_input;
 	gpio->chip.direction_output = tng_gpio_direction_output;
 	gpio->chip.get = tng_gpio_get;
-	gpio->chip.set_rv = tng_gpio_set;
+	gpio->chip.set = tng_gpio_set;
 	gpio->chip.get_direction = tng_gpio_get_direction;
 	gpio->chip.set_config = tng_gpio_set_config;
 	gpio->chip.base = info->base;
diff --git a/drivers/gpio/gpio-tc3589x.c b/drivers/gpio/gpio-tc3589x.c
index 0bd32809fd68..90d048f9da08 100644
--- a/drivers/gpio/gpio-tc3589x.c
+++ b/drivers/gpio/gpio-tc3589x.c
@@ -149,7 +149,7 @@ static const struct gpio_chip template_chip = {
 	.label			= "tc3589x",
 	.owner			= THIS_MODULE,
 	.get			= tc3589x_gpio_get,
-	.set_rv			= tc3589x_gpio_set,
+	.set			= tc3589x_gpio_set,
 	.direction_output	= tc3589x_gpio_direction_output,
 	.direction_input	= tc3589x_gpio_direction_input,
 	.get_direction		= tc3589x_gpio_get_direction,
diff --git a/drivers/gpio/gpio-tegra.c b/drivers/gpio/gpio-tegra.c
index 126fd12550aa..15a5762a82c2 100644
--- a/drivers/gpio/gpio-tegra.c
+++ b/drivers/gpio/gpio-tegra.c
@@ -720,7 +720,7 @@ static int tegra_gpio_probe(struct platform_device *pdev)
 	tgi->gc.direction_input		= tegra_gpio_direction_input;
 	tgi->gc.get			= tegra_gpio_get;
 	tgi->gc.direction_output	= tegra_gpio_direction_output;
-	tgi->gc.set_rv			= tegra_gpio_set;
+	tgi->gc.set			= tegra_gpio_set;
 	tgi->gc.get_direction		= tegra_gpio_get_direction;
 	tgi->gc.base			= 0;
 	tgi->gc.ngpio			= tgi->bank_count * 32;
diff --git a/drivers/gpio/gpio-tegra186.c b/drivers/gpio/gpio-tegra186.c
index f902da15c419..5fd3ec3e2c53 100644
--- a/drivers/gpio/gpio-tegra186.c
+++ b/drivers/gpio/gpio-tegra186.c
@@ -891,7 +891,7 @@ static int tegra186_gpio_probe(struct platform_device *pdev)
 	gpio->gpio.direction_input = tegra186_gpio_direction_input;
 	gpio->gpio.direction_output = tegra186_gpio_direction_output;
 	gpio->gpio.get = tegra186_gpio_get;
-	gpio->gpio.set_rv = tegra186_gpio_set;
+	gpio->gpio.set = tegra186_gpio_set;
 	gpio->gpio.set_config = tegra186_gpio_set_config;
 	gpio->gpio.add_pin_ranges = tegra186_gpio_add_pin_ranges;
 	gpio->gpio.init_valid_mask = tegra186_init_valid_mask;
diff --git a/drivers/gpio/gpio-thunderx.c b/drivers/gpio/gpio-thunderx.c
index eb6a1f0279c0..be96853063ba 100644
--- a/drivers/gpio/gpio-thunderx.c
+++ b/drivers/gpio/gpio-thunderx.c
@@ -533,8 +533,8 @@ static int thunderx_gpio_probe(struct pci_dev *pdev,
 	chip->direction_input = thunderx_gpio_dir_in;
 	chip->get = thunderx_gpio_get;
 	chip->direction_output = thunderx_gpio_dir_out;
-	chip->set_rv = thunderx_gpio_set;
-	chip->set_multiple_rv = thunderx_gpio_set_multiple;
+	chip->set = thunderx_gpio_set;
+	chip->set_multiple = thunderx_gpio_set_multiple;
 	chip->set_config = thunderx_gpio_set_config;
 	girq = &chip->irq;
 	gpio_irq_chip_set_chip(girq, &thunderx_gpio_irq_chip);
diff --git a/drivers/gpio/gpio-timberdale.c b/drivers/gpio/gpio-timberdale.c
index fbb883089189..679e27f00ff6 100644
--- a/drivers/gpio/gpio-timberdale.c
+++ b/drivers/gpio/gpio-timberdale.c
@@ -253,7 +253,7 @@ static int timbgpio_probe(struct platform_device *pdev)
 	gc->direction_input = timbgpio_gpio_direction_input;
 	gc->get = timbgpio_gpio_get;
 	gc->direction_output = timbgpio_gpio_direction_output;
-	gc->set_rv = timbgpio_gpio_set;
+	gc->set = timbgpio_gpio_set;
 	gc->to_irq = (irq >= 0 && tgpio->irq_base > 0) ? timbgpio_to_irq : NULL;
 	gc->dbg_show = NULL;
 	gc->base = pdata->gpio_base;
diff --git a/drivers/gpio/gpio-tpic2810.c b/drivers/gpio/gpio-tpic2810.c
index d5b8568ab061..866ff2d436d5 100644
--- a/drivers/gpio/gpio-tpic2810.c
+++ b/drivers/gpio/gpio-tpic2810.c
@@ -80,8 +80,8 @@ static const struct gpio_chip template_chip = {
 	.owner			= THIS_MODULE,
 	.get_direction		= tpic2810_get_direction,
 	.direction_output	= tpic2810_direction_output,
-	.set_rv			= tpic2810_set,
-	.set_multiple_rv	= tpic2810_set_multiple,
+	.set			= tpic2810_set,
+	.set_multiple		= tpic2810_set_multiple,
 	.base			= -1,
 	.ngpio			= 8,
 	.can_sleep		= true,
diff --git a/drivers/gpio/gpio-tps65086.c b/drivers/gpio/gpio-tps65086.c
index 08fa061b73ef..84b17b83476f 100644
--- a/drivers/gpio/gpio-tps65086.c
+++ b/drivers/gpio/gpio-tps65086.c
@@ -69,7 +69,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= tps65086_gpio_direction_input,
 	.direction_output	= tps65086_gpio_direction_output,
 	.get			= tps65086_gpio_get,
-	.set_rv			= tps65086_gpio_set,
+	.set			= tps65086_gpio_set,
 	.base			= -1,
 	.ngpio			= 4,
 	.can_sleep		= true,
diff --git a/drivers/gpio/gpio-tps65218.c b/drivers/gpio/gpio-tps65218.c
index 49cd7754ed05..3b4c41f5ef55 100644
--- a/drivers/gpio/gpio-tps65218.c
+++ b/drivers/gpio/gpio-tps65218.c
@@ -169,7 +169,7 @@ static const struct gpio_chip template_chip = {
 	.request		= tps65218_gpio_request,
 	.direction_output	= tps65218_gpio_output,
 	.get			= tps65218_gpio_get,
-	.set_rv			= tps65218_gpio_set,
+	.set			= tps65218_gpio_set,
 	.set_config		= tps65218_gpio_set_config,
 	.can_sleep		= true,
 	.ngpio			= 3,
diff --git a/drivers/gpio/gpio-tps65219.c b/drivers/gpio/gpio-tps65219.c
index c0177088c54c..158f63bcf10c 100644
--- a/drivers/gpio/gpio-tps65219.c
+++ b/drivers/gpio/gpio-tps65219.c
@@ -203,7 +203,7 @@ static const struct gpio_chip tps65214_template_chip = {
 	.direction_input	= tps65219_gpio_direction_input,
 	.direction_output	= tps65219_gpio_direction_output,
 	.get			= tps65219_gpio_get,
-	.set_rv			= tps65219_gpio_set,
+	.set			= tps65219_gpio_set,
 	.base			= -1,
 	.ngpio			= 2,
 	.can_sleep		= true,
@@ -216,7 +216,7 @@ static const struct gpio_chip tps65219_template_chip = {
 	.direction_input	= tps65219_gpio_direction_input,
 	.direction_output	= tps65219_gpio_direction_output,
 	.get			= tps65219_gpio_get,
-	.set_rv			= tps65219_gpio_set,
+	.set			= tps65219_gpio_set,
 	.base			= -1,
 	.ngpio			= 3,
 	.can_sleep		= true,
diff --git a/drivers/gpio/gpio-tps6586x.c b/drivers/gpio/gpio-tps6586x.c
index f1ced092f38a..aaacbb54bf5d 100644
--- a/drivers/gpio/gpio-tps6586x.c
+++ b/drivers/gpio/gpio-tps6586x.c
@@ -98,7 +98,7 @@ static int tps6586x_gpio_probe(struct platform_device *pdev)
 
 	/* FIXME: add handling of GPIOs as dedicated inputs */
 	tps6586x_gpio->gpio_chip.direction_output = tps6586x_gpio_output;
-	tps6586x_gpio->gpio_chip.set_rv	= tps6586x_gpio_set;
+	tps6586x_gpio->gpio_chip.set	= tps6586x_gpio_set;
 	tps6586x_gpio->gpio_chip.get	= tps6586x_gpio_get;
 	tps6586x_gpio->gpio_chip.to_irq	= tps6586x_gpio_to_irq;
 
diff --git a/drivers/gpio/gpio-tps65910.c b/drivers/gpio/gpio-tps65910.c
index 3204f55394cf..25e9f41efe78 100644
--- a/drivers/gpio/gpio-tps65910.c
+++ b/drivers/gpio/gpio-tps65910.c
@@ -139,7 +139,7 @@ static int tps65910_gpio_probe(struct platform_device *pdev)
 	tps65910_gpio->gpio_chip.can_sleep = true;
 	tps65910_gpio->gpio_chip.direction_input = tps65910_gpio_input;
 	tps65910_gpio->gpio_chip.direction_output = tps65910_gpio_output;
-	tps65910_gpio->gpio_chip.set_rv	= tps65910_gpio_set;
+	tps65910_gpio->gpio_chip.set	= tps65910_gpio_set;
 	tps65910_gpio->gpio_chip.get	= tps65910_gpio_get;
 	tps65910_gpio->gpio_chip.parent = &pdev->dev;
 
diff --git a/drivers/gpio/gpio-tps65912.c b/drivers/gpio/gpio-tps65912.c
index d586ccfbfc56..7a2c5685c2fd 100644
--- a/drivers/gpio/gpio-tps65912.c
+++ b/drivers/gpio/gpio-tps65912.c
@@ -92,7 +92,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= tps65912_gpio_direction_input,
 	.direction_output	= tps65912_gpio_direction_output,
 	.get			= tps65912_gpio_get,
-	.set_rv			= tps65912_gpio_set,
+	.set			= tps65912_gpio_set,
 	.base			= -1,
 	.ngpio			= 5,
 	.can_sleep		= true,
diff --git a/drivers/gpio/gpio-tps68470.c b/drivers/gpio/gpio-tps68470.c
index 3b8805c854f7..d4fbdf90e190 100644
--- a/drivers/gpio/gpio-tps68470.c
+++ b/drivers/gpio/gpio-tps68470.c
@@ -142,7 +142,7 @@ static int tps68470_gpio_probe(struct platform_device *pdev)
 	tps68470_gpio->gc.direction_output = tps68470_gpio_output;
 	tps68470_gpio->gc.get = tps68470_gpio_get;
 	tps68470_gpio->gc.get_direction = tps68470_gpio_get_direction;
-	tps68470_gpio->gc.set_rv = tps68470_gpio_set;
+	tps68470_gpio->gc.set = tps68470_gpio_set;
 	tps68470_gpio->gc.can_sleep = true;
 	tps68470_gpio->gc.names = tps68470_names;
 	tps68470_gpio->gc.ngpio = TPS68470_N_GPIO;
diff --git a/drivers/gpio/gpio-tqmx86.c b/drivers/gpio/gpio-tqmx86.c
index 056799ecce6a..27dd09273292 100644
--- a/drivers/gpio/gpio-tqmx86.c
+++ b/drivers/gpio/gpio-tqmx86.c
@@ -370,7 +370,7 @@ static int tqmx86_gpio_probe(struct platform_device *pdev)
 	chip->direction_output = tqmx86_gpio_direction_output;
 	chip->get_direction = tqmx86_gpio_get_direction;
 	chip->get = tqmx86_gpio_get;
-	chip->set_rv = tqmx86_gpio_set;
+	chip->set = tqmx86_gpio_set;
 	chip->ngpio = TQMX86_NGPIO;
 	chip->parent = pdev->dev.parent;
 
diff --git a/drivers/gpio/gpio-ts4900.c b/drivers/gpio/gpio-ts4900.c
index 35dd2d09b4d4..d9ee8fc77ccd 100644
--- a/drivers/gpio/gpio-ts4900.c
+++ b/drivers/gpio/gpio-ts4900.c
@@ -119,7 +119,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= ts4900_gpio_direction_input,
 	.direction_output	= ts4900_gpio_direction_output,
 	.get			= ts4900_gpio_get,
-	.set_rv			= ts4900_gpio_set,
+	.set			= ts4900_gpio_set,
 	.base			= -1,
 	.can_sleep		= true,
 };
diff --git a/drivers/gpio/gpio-ts5500.c b/drivers/gpio/gpio-ts5500.c
index bb432ed73698..3c7f2efe10fd 100644
--- a/drivers/gpio/gpio-ts5500.c
+++ b/drivers/gpio/gpio-ts5500.c
@@ -340,7 +340,7 @@ static int ts5500_dio_probe(struct platform_device *pdev)
 	priv->gpio_chip.direction_input = ts5500_gpio_input;
 	priv->gpio_chip.direction_output = ts5500_gpio_output;
 	priv->gpio_chip.get = ts5500_gpio_get;
-	priv->gpio_chip.set_rv = ts5500_gpio_set;
+	priv->gpio_chip.set = ts5500_gpio_set;
 	priv->gpio_chip.to_irq = ts5500_gpio_to_irq;
 	priv->gpio_chip.base = -1;
 
diff --git a/drivers/gpio/gpio-twl4030.c b/drivers/gpio/gpio-twl4030.c
index e39e39e3ef85..a33dc7c7e7a0 100644
--- a/drivers/gpio/gpio-twl4030.c
+++ b/drivers/gpio/gpio-twl4030.c
@@ -419,7 +419,7 @@ static const struct gpio_chip template_chip = {
 	.direction_output	= twl_direction_out,
 	.get_direction		= twl_get_direction,
 	.get			= twl_get,
-	.set_rv			= twl_set,
+	.set			= twl_set,
 	.to_irq			= twl_to_irq,
 	.can_sleep		= true,
 };
diff --git a/drivers/gpio/gpio-twl6040.c b/drivers/gpio/gpio-twl6040.c
index b2196b62b528..4ec9bcd40439 100644
--- a/drivers/gpio/gpio-twl6040.c
+++ b/drivers/gpio/gpio-twl6040.c
@@ -69,7 +69,7 @@ static struct gpio_chip twl6040gpo_chip = {
 	.get			= twl6040gpo_get,
 	.direction_output	= twl6040gpo_direction_out,
 	.get_direction		= twl6040gpo_get_direction,
-	.set_rv			= twl6040gpo_set,
+	.set			= twl6040gpo_set,
 	.can_sleep		= true,
 };
 
diff --git a/drivers/gpio/gpio-uniphier.c b/drivers/gpio/gpio-uniphier.c
index 8939556f42b6..197bb1d22b3c 100644
--- a/drivers/gpio/gpio-uniphier.c
+++ b/drivers/gpio/gpio-uniphier.c
@@ -386,8 +386,8 @@ static int uniphier_gpio_probe(struct platform_device *pdev)
 	chip->direction_input = uniphier_gpio_direction_input;
 	chip->direction_output = uniphier_gpio_direction_output;
 	chip->get = uniphier_gpio_get;
-	chip->set_rv = uniphier_gpio_set;
-	chip->set_multiple_rv = uniphier_gpio_set_multiple;
+	chip->set = uniphier_gpio_set;
+	chip->set_multiple = uniphier_gpio_set_multiple;
 	chip->to_irq = uniphier_gpio_to_irq;
 	chip->base = -1;
 	chip->ngpio = ngpios;
diff --git a/drivers/gpio/gpio-viperboard.c b/drivers/gpio/gpio-viperboard.c
index e8e906b54d51..15e495c109d2 100644
--- a/drivers/gpio/gpio-viperboard.c
+++ b/drivers/gpio/gpio-viperboard.c
@@ -408,7 +408,7 @@ static int vprbrd_gpio_probe(struct platform_device *pdev)
 	vb_gpio->gpioa.base = -1;
 	vb_gpio->gpioa.ngpio = 16;
 	vb_gpio->gpioa.can_sleep = true;
-	vb_gpio->gpioa.set_rv = vprbrd_gpioa_set;
+	vb_gpio->gpioa.set = vprbrd_gpioa_set;
 	vb_gpio->gpioa.get = vprbrd_gpioa_get;
 	vb_gpio->gpioa.direction_input = vprbrd_gpioa_direction_input;
 	vb_gpio->gpioa.direction_output = vprbrd_gpioa_direction_output;
@@ -424,7 +424,7 @@ static int vprbrd_gpio_probe(struct platform_device *pdev)
 	vb_gpio->gpiob.base = -1;
 	vb_gpio->gpiob.ngpio = 16;
 	vb_gpio->gpiob.can_sleep = true;
-	vb_gpio->gpiob.set_rv = vprbrd_gpiob_set;
+	vb_gpio->gpiob.set = vprbrd_gpiob_set;
 	vb_gpio->gpiob.get = vprbrd_gpiob_get;
 	vb_gpio->gpiob.direction_input = vprbrd_gpiob_direction_input;
 	vb_gpio->gpiob.direction_output = vprbrd_gpiob_direction_output;
diff --git a/drivers/gpio/gpio-virtio.c b/drivers/gpio/gpio-virtio.c
index 07552611da98..17e040991e46 100644
--- a/drivers/gpio/gpio-virtio.c
+++ b/drivers/gpio/gpio-virtio.c
@@ -567,7 +567,7 @@ static int virtio_gpio_probe(struct virtio_device *vdev)
 	vgpio->gc.direction_input	= virtio_gpio_direction_input;
 	vgpio->gc.direction_output	= virtio_gpio_direction_output;
 	vgpio->gc.get			= virtio_gpio_get;
-	vgpio->gc.set_rv		= virtio_gpio_set;
+	vgpio->gc.set			= virtio_gpio_set;
 	vgpio->gc.ngpio			= ngpio;
 	vgpio->gc.base			= -1; /* Allocate base dynamically */
 	vgpio->gc.label			= dev_name(dev);
diff --git a/drivers/gpio/gpio-vx855.c b/drivers/gpio/gpio-vx855.c
index a3bceac7854c..84b3a973a503 100644
--- a/drivers/gpio/gpio-vx855.c
+++ b/drivers/gpio/gpio-vx855.c
@@ -216,7 +216,7 @@ static void vx855gpio_gpio_setup(struct vx855_gpio *vg)
 	c->direction_input = vx855gpio_direction_input;
 	c->direction_output = vx855gpio_direction_output;
 	c->get = vx855gpio_get;
-	c->set_rv = vx855gpio_set;
+	c->set = vx855gpio_set;
 	c->set_config = vx855gpio_set_config;
 	c->dbg_show = NULL;
 	c->base = 0;
diff --git a/drivers/gpio/gpio-wcd934x.c b/drivers/gpio/gpio-wcd934x.c
index c89da9a22016..4af504c23e6f 100644
--- a/drivers/gpio/gpio-wcd934x.c
+++ b/drivers/gpio/gpio-wcd934x.c
@@ -98,7 +98,7 @@ static int wcd_gpio_probe(struct platform_device *pdev)
 	chip->direction_output = wcd_gpio_direction_output;
 	chip->get_direction = wcd_gpio_get_direction;
 	chip->get = wcd_gpio_get;
-	chip->set_rv = wcd_gpio_set;
+	chip->set = wcd_gpio_set;
 	chip->parent = dev;
 	chip->base = -1;
 	chip->ngpio = WCD934X_NPINS;
diff --git a/drivers/gpio/gpio-wcove.c b/drivers/gpio/gpio-wcove.c
index f7df3d5fc71c..4a5e20e936a9 100644
--- a/drivers/gpio/gpio-wcove.c
+++ b/drivers/gpio/gpio-wcove.c
@@ -439,7 +439,7 @@ static int wcove_gpio_probe(struct platform_device *pdev)
 	wg->chip.direction_output = wcove_gpio_dir_out;
 	wg->chip.get_direction = wcove_gpio_get_direction;
 	wg->chip.get = wcove_gpio_get;
-	wg->chip.set_rv = wcove_gpio_set;
+	wg->chip.set = wcove_gpio_set;
 	wg->chip.set_config = wcove_gpio_set_config;
 	wg->chip.base = -1;
 	wg->chip.ngpio = WCOVE_VGPIO_NUM;
diff --git a/drivers/gpio/gpio-winbond.c b/drivers/gpio/gpio-winbond.c
index 421655b5d4c2..dcfda738fd69 100644
--- a/drivers/gpio/gpio-winbond.c
+++ b/drivers/gpio/gpio-winbond.c
@@ -494,7 +494,7 @@ static struct gpio_chip winbond_gpio_chip = {
 	.can_sleep		= true,
 	.get			= winbond_gpio_get,
 	.direction_input	= winbond_gpio_direction_in,
-	.set_rv			= winbond_gpio_set,
+	.set			= winbond_gpio_set,
 	.direction_output	= winbond_gpio_direction_out,
 };
 
diff --git a/drivers/gpio/gpio-wm831x.c b/drivers/gpio/gpio-wm831x.c
index ab58aa7c0b99..f03c0e808fab 100644
--- a/drivers/gpio/gpio-wm831x.c
+++ b/drivers/gpio/gpio-wm831x.c
@@ -253,7 +253,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= wm831x_gpio_direction_in,
 	.get			= wm831x_gpio_get,
 	.direction_output	= wm831x_gpio_direction_out,
-	.set_rv			= wm831x_gpio_set,
+	.set			= wm831x_gpio_set,
 	.to_irq			= wm831x_gpio_to_irq,
 	.set_config		= wm831x_set_config,
 	.dbg_show		= wm831x_gpio_dbg_show,
diff --git a/drivers/gpio/gpio-wm8350.c b/drivers/gpio/gpio-wm8350.c
index 9a7677f841fc..46923b23a72e 100644
--- a/drivers/gpio/gpio-wm8350.c
+++ b/drivers/gpio/gpio-wm8350.c
@@ -93,7 +93,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= wm8350_gpio_direction_in,
 	.get			= wm8350_gpio_get,
 	.direction_output	= wm8350_gpio_direction_out,
-	.set_rv			= wm8350_gpio_set,
+	.set			= wm8350_gpio_set,
 	.to_irq			= wm8350_gpio_to_irq,
 	.can_sleep		= true,
 };
diff --git a/drivers/gpio/gpio-wm8994.c b/drivers/gpio/gpio-wm8994.c
index ccc005628dd2..df47a27f508d 100644
--- a/drivers/gpio/gpio-wm8994.c
+++ b/drivers/gpio/gpio-wm8994.c
@@ -256,7 +256,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input	= wm8994_gpio_direction_in,
 	.get			= wm8994_gpio_get,
 	.direction_output	= wm8994_gpio_direction_out,
-	.set_rv			= wm8994_gpio_set,
+	.set			= wm8994_gpio_set,
 	.set_config		= wm8994_gpio_set_config,
 	.to_irq			= wm8994_gpio_to_irq,
 	.dbg_show		= wm8994_gpio_dbg_show,
diff --git a/drivers/gpio/gpio-xgene.c b/drivers/gpio/gpio-xgene.c
index 28f794e5eb26..4f627de3f56c 100644
--- a/drivers/gpio/gpio-xgene.c
+++ b/drivers/gpio/gpio-xgene.c
@@ -178,7 +178,7 @@ static int xgene_gpio_probe(struct platform_device *pdev)
 	gpio->chip.direction_input = xgene_gpio_dir_in;
 	gpio->chip.direction_output = xgene_gpio_dir_out;
 	gpio->chip.get = xgene_gpio_get;
-	gpio->chip.set_rv = xgene_gpio_set;
+	gpio->chip.set = xgene_gpio_set;
 	gpio->chip.label = dev_name(&pdev->dev);
 	gpio->chip.base = -1;
 
diff --git a/drivers/gpio/gpio-xilinx.c b/drivers/gpio/gpio-xilinx.c
index 36d91cacc2d9..83675ac81077 100644
--- a/drivers/gpio/gpio-xilinx.c
+++ b/drivers/gpio/gpio-xilinx.c
@@ -604,10 +604,10 @@ static int xgpio_probe(struct platform_device *pdev)
 	chip->gc.direction_input = xgpio_dir_in;
 	chip->gc.direction_output = xgpio_dir_out;
 	chip->gc.get = xgpio_get;
-	chip->gc.set_rv = xgpio_set;
+	chip->gc.set = xgpio_set;
 	chip->gc.request = xgpio_request;
 	chip->gc.free = xgpio_free;
-	chip->gc.set_multiple_rv = xgpio_set_multiple;
+	chip->gc.set_multiple = xgpio_set_multiple;
 
 	chip->gc.label = dev_name(dev);
 
diff --git a/drivers/gpio/gpio-xlp.c b/drivers/gpio/gpio-xlp.c
index bcd2dfec462d..aede6324387f 100644
--- a/drivers/gpio/gpio-xlp.c
+++ b/drivers/gpio/gpio-xlp.c
@@ -274,7 +274,7 @@ static int xlp_gpio_probe(struct platform_device *pdev)
 	gc->ngpio = 70;
 	gc->direction_output = xlp_gpio_dir_output;
 	gc->direction_input = xlp_gpio_dir_input;
-	gc->set_rv = xlp_gpio_set;
+	gc->set = xlp_gpio_set;
 	gc->get = xlp_gpio_get;
 
 	spin_lock_init(&priv->lock);
diff --git a/drivers/gpio/gpio-xra1403.c b/drivers/gpio/gpio-xra1403.c
index 70402c6b5407..faadcb4b0b2d 100644
--- a/drivers/gpio/gpio-xra1403.c
+++ b/drivers/gpio/gpio-xra1403.c
@@ -164,7 +164,7 @@ static int xra1403_probe(struct spi_device *spi)
 	xra->chip.direction_output = xra1403_direction_output;
 	xra->chip.get_direction = xra1403_get_direction;
 	xra->chip.get = xra1403_get;
-	xra->chip.set_rv = xra1403_set;
+	xra->chip.set = xra1403_set;
 
 	xra->chip.dbg_show = xra1403_dbg_show;
 
diff --git a/drivers/gpio/gpio-xtensa.c b/drivers/gpio/gpio-xtensa.c
index e7ff3c60324d..4418947a10e5 100644
--- a/drivers/gpio/gpio-xtensa.c
+++ b/drivers/gpio/gpio-xtensa.c
@@ -132,7 +132,7 @@ static struct gpio_chip expstate_chip = {
 	.ngpio		= 32,
 	.get_direction	= xtensa_expstate_get_direction,
 	.get		= xtensa_expstate_get_value,
-	.set_rv		= xtensa_expstate_set_value,
+	.set		= xtensa_expstate_set_value,
 };
 
 static int xtensa_gpio_probe(struct platform_device *pdev)
diff --git a/drivers/gpio/gpio-zevio.c b/drivers/gpio/gpio-zevio.c
index 0799f7976710..29375bea2289 100644
--- a/drivers/gpio/gpio-zevio.c
+++ b/drivers/gpio/gpio-zevio.c
@@ -161,7 +161,7 @@ static int zevio_gpio_to_irq(struct gpio_chip *chip, unsigned pin)
 static const struct gpio_chip zevio_gpio_chip = {
 	.direction_input	= zevio_gpio_direction_input,
 	.direction_output	= zevio_gpio_direction_output,
-	.set_rv			= zevio_gpio_set,
+	.set			= zevio_gpio_set,
 	.get			= zevio_gpio_get,
 	.to_irq			= zevio_gpio_to_irq,
 	.base			= 0,
diff --git a/drivers/gpio/gpio-zynq.c b/drivers/gpio/gpio-zynq.c
index b22b4e25c68d..0ffd76e8951f 100644
--- a/drivers/gpio/gpio-zynq.c
+++ b/drivers/gpio/gpio-zynq.c
@@ -932,7 +932,7 @@ static int zynq_gpio_probe(struct platform_device *pdev)
 	chip->owner = THIS_MODULE;
 	chip->parent = &pdev->dev;
 	chip->get = zynq_gpio_get_value;
-	chip->set_rv = zynq_gpio_set_value;
+	chip->set = zynq_gpio_set_value;
 	chip->request = zynq_gpio_request;
 	chip->free = zynq_gpio_free;
 	chip->direction_input = zynq_gpio_dir_in;
diff --git a/drivers/gpio/gpio-zynqmp-modepin.c b/drivers/gpio/gpio-zynqmp-modepin.c
index 6dc5d7acb89c..5e651482e985 100644
--- a/drivers/gpio/gpio-zynqmp-modepin.c
+++ b/drivers/gpio/gpio-zynqmp-modepin.c
@@ -130,7 +130,7 @@ static int modepin_gpio_probe(struct platform_device *pdev)
 	chip->owner = THIS_MODULE;
 	chip->parent = &pdev->dev;
 	chip->get = modepin_gpio_get_value;
-	chip->set_rv = modepin_gpio_set_value;
+	chip->set = modepin_gpio_set_value;
 	chip->direction_input = modepin_gpio_dir_in;
 	chip->direction_output = modepin_gpio_dir_out;
 	chip->label = dev_name(&pdev->dev);
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 9ac4c23d656a..0d2b470a252e 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -2886,10 +2886,10 @@ static int gpiochip_set(struct gpio_chip *gc, unsigned int offset, int value)
 
 	lockdep_assert_held(&gc->gpiodev->srcu);
 
-	if (WARN_ON(unlikely(!gc->set_rv)))
+	if (WARN_ON(unlikely(!gc->set)))
 		return -EOPNOTSUPP;
 
-	ret = gc->set_rv(gc, offset, value);
+	ret = gc->set(gc, offset, value);
 	if (ret > 0)
 		ret = -EBADE;
 
@@ -2909,7 +2909,7 @@ static int gpiod_direction_output_raw_commit(struct gpio_desc *desc, int value)
 	 * output-only, but if there is then not even a .set() operation it
 	 * is pretty tricky to drive the output line.
 	 */
-	if (!guard.gc->set_rv && !guard.gc->direction_output) {
+	if (!guard.gc->set && !guard.gc->direction_output) {
 		gpiod_warn(desc,
 			   "%s: missing set() and direction_output() operations\n",
 			   __func__);
@@ -3655,8 +3655,8 @@ static int gpiochip_set_multiple(struct gpio_chip *gc,
 
 	lockdep_assert_held(&gc->gpiodev->srcu);
 
-	if (gc->set_multiple_rv) {
-		ret = gc->set_multiple_rv(gc, mask, bits);
+	if (gc->set_multiple) {
+		ret = gc->set_multiple(gc, mask, bits);
 		if (ret > 0)
 			ret = -EBADE;
 
diff --git a/drivers/gpu/drm/bridge/ti-sn65dsi86.c b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
index e3a8c0c0c945..464390372b34 100644
--- a/drivers/gpu/drm/bridge/ti-sn65dsi86.c
+++ b/drivers/gpu/drm/bridge/ti-sn65dsi86.c
@@ -1836,7 +1836,7 @@ static int ti_sn_gpio_probe(struct auxiliary_device *adev,
 	pdata->gchip.direction_input = ti_sn_bridge_gpio_direction_input;
 	pdata->gchip.direction_output = ti_sn_bridge_gpio_direction_output;
 	pdata->gchip.get = ti_sn_bridge_gpio_get;
-	pdata->gchip.set_rv = ti_sn_bridge_gpio_set;
+	pdata->gchip.set = ti_sn_bridge_gpio_set;
 	pdata->gchip.can_sleep = true;
 	pdata->gchip.names = ti_sn_bridge_gpio_names;
 	pdata->gchip.ngpio = SN_NUM_GPIOS;
diff --git a/drivers/hid/hid-cp2112.c b/drivers/hid/hid-cp2112.c
index 234fa82eab07..482f62a78c41 100644
--- a/drivers/hid/hid-cp2112.c
+++ b/drivers/hid/hid-cp2112.c
@@ -1288,7 +1288,7 @@ static int cp2112_probe(struct hid_device *hdev, const struct hid_device_id *id)
 	dev->gc.label			= "cp2112_gpio";
 	dev->gc.direction_input		= cp2112_gpio_direction_input;
 	dev->gc.direction_output	= cp2112_gpio_direction_output;
-	dev->gc.set_rv			= cp2112_gpio_set;
+	dev->gc.set			= cp2112_gpio_set;
 	dev->gc.get			= cp2112_gpio_get;
 	dev->gc.base			= -1;
 	dev->gc.ngpio			= CP2112_GPIO_MAX_GPIO;
diff --git a/drivers/hid/hid-mcp2200.c b/drivers/hid/hid-mcp2200.c
index e6ea0a2140eb..dafdd5b4a079 100644
--- a/drivers/hid/hid-mcp2200.c
+++ b/drivers/hid/hid-mcp2200.c
@@ -279,8 +279,8 @@ static const struct gpio_chip template_chip = {
 	.get_direction		= mcp_get_direction,
 	.direction_input	= mcp_direction_input,
 	.direction_output	= mcp_direction_output,
-	.set_rv			= mcp_set,
-	.set_multiple_rv	= mcp_set_multiple,
+	.set			= mcp_set,
+	.set_multiple		= mcp_set_multiple,
 	.get			= mcp_get,
 	.get_multiple		= mcp_get_multiple,
 	.base			= -1,
diff --git a/drivers/hid/hid-mcp2221.c b/drivers/hid/hid-mcp2221.c
index fcfe9370a887..475ac352df30 100644
--- a/drivers/hid/hid-mcp2221.c
+++ b/drivers/hid/hid-mcp2221.c
@@ -1298,7 +1298,7 @@ static int mcp2221_probe(struct hid_device *hdev,
 	mcp->gc->direction_input = mcp_gpio_direction_input;
 	mcp->gc->direction_output = mcp_gpio_direction_output;
 	mcp->gc->get_direction = mcp_gpio_get_direction;
-	mcp->gc->set_rv = mcp_gpio_set;
+	mcp->gc->set = mcp_gpio_set;
 	mcp->gc->get = mcp_gpio_get;
 	mcp->gc->ngpio = MCP_NGPIO;
 	mcp->gc->base = -1;
diff --git a/drivers/hwmon/ltc2992.c b/drivers/hwmon/ltc2992.c
index a07e2eb93c71..1fcd320d6161 100644
--- a/drivers/hwmon/ltc2992.c
+++ b/drivers/hwmon/ltc2992.c
@@ -339,8 +339,8 @@ static int ltc2992_config_gpio(struct ltc2992_state *st)
 	st->gc.ngpio = ARRAY_SIZE(st->gpio_names);
 	st->gc.get = ltc2992_gpio_get;
 	st->gc.get_multiple = ltc2992_gpio_get_multiple;
-	st->gc.set_rv = ltc2992_gpio_set;
-	st->gc.set_multiple_rv = ltc2992_gpio_set_multiple;
+	st->gc.set = ltc2992_gpio_set;
+	st->gc.set_multiple = ltc2992_gpio_set_multiple;
 
 	ret = devm_gpiochip_add_data(&st->client->dev, &st->gc, st);
 	if (ret)
diff --git a/drivers/hwmon/pmbus/ucd9000.c b/drivers/hwmon/pmbus/ucd9000.c
index 52d4000902d5..55e7af3a5f98 100644
--- a/drivers/hwmon/pmbus/ucd9000.c
+++ b/drivers/hwmon/pmbus/ucd9000.c
@@ -364,7 +364,7 @@ static void ucd9000_probe_gpio(struct i2c_client *client,
 	data->gpio.direction_input = ucd9000_gpio_direction_input;
 	data->gpio.direction_output = ucd9000_gpio_direction_output;
 	data->gpio.get = ucd9000_gpio_get;
-	data->gpio.set_rv = ucd9000_gpio_set;
+	data->gpio.set = ucd9000_gpio_set;
 	data->gpio.can_sleep = true;
 	data->gpio.base = -1;
 	data->gpio.parent = &client->dev;
diff --git a/drivers/i2c/muxes/i2c-mux-ltc4306.c b/drivers/i2c/muxes/i2c-mux-ltc4306.c
index c688af270a11..50fbc0d06e62 100644
--- a/drivers/i2c/muxes/i2c-mux-ltc4306.c
+++ b/drivers/i2c/muxes/i2c-mux-ltc4306.c
@@ -164,7 +164,7 @@ static int ltc4306_gpio_init(struct ltc4306 *data)
 	data->gpiochip.direction_input = ltc4306_gpio_direction_input;
 	data->gpiochip.direction_output = ltc4306_gpio_direction_output;
 	data->gpiochip.get = ltc4306_gpio_get;
-	data->gpiochip.set_rv = ltc4306_gpio_set;
+	data->gpiochip.set = ltc4306_gpio_set;
 	data->gpiochip.set_config = ltc4306_gpio_set_config;
 	data->gpiochip.owner = THIS_MODULE;
 
diff --git a/drivers/iio/adc/ad4130.c b/drivers/iio/adc/ad4130.c
index 6cf790ff3eb5..dcdb5778f7d6 100644
--- a/drivers/iio/adc/ad4130.c
+++ b/drivers/iio/adc/ad4130.c
@@ -2064,7 +2064,7 @@ static int ad4130_probe(struct spi_device *spi)
 	st->gc.can_sleep = true;
 	st->gc.init_valid_mask = ad4130_gpio_init_valid_mask;
 	st->gc.get_direction = ad4130_gpio_get_direction;
-	st->gc.set_rv = ad4130_gpio_set;
+	st->gc.set = ad4130_gpio_set;
 
 	ret = devm_gpiochip_add_data(dev, &st->gc, st);
 	if (ret)
diff --git a/drivers/iio/adc/ad4170-4.c b/drivers/iio/adc/ad4170-4.c
index 6cd84d6fb08b..efaed92191f1 100644
--- a/drivers/iio/adc/ad4170-4.c
+++ b/drivers/iio/adc/ad4170-4.c
@@ -1807,7 +1807,7 @@ static int ad4170_gpio_init(struct iio_dev *indio_dev)
 	st->gpiochip.direction_input = ad4170_gpio_direction_input;
 	st->gpiochip.direction_output = ad4170_gpio_direction_output;
 	st->gpiochip.get = ad4170_gpio_get;
-	st->gpiochip.set_rv = ad4170_gpio_set;
+	st->gpiochip.set = ad4170_gpio_set;
 	st->gpiochip.owner = THIS_MODULE;
 
 	return devm_gpiochip_add_data(&st->spi->dev, &st->gpiochip, indio_dev);
diff --git a/drivers/iio/adc/ad7768-1.c b/drivers/iio/adc/ad7768-1.c
index a2e061f0cb08..ca8fa91796ca 100644
--- a/drivers/iio/adc/ad7768-1.c
+++ b/drivers/iio/adc/ad7768-1.c
@@ -673,7 +673,7 @@ static int ad7768_gpio_init(struct iio_dev *indio_dev)
 		.direction_input = ad7768_gpio_direction_input,
 		.direction_output = ad7768_gpio_direction_output,
 		.get = ad7768_gpio_get,
-		.set_rv = ad7768_gpio_set,
+		.set = ad7768_gpio_set,
 		.owner = THIS_MODULE,
 	};
 
diff --git a/drivers/iio/adc/rohm-bd79124.c b/drivers/iio/adc/rohm-bd79124.c
index bb7c93ae4055..06c55c8da93f 100644
--- a/drivers/iio/adc/rohm-bd79124.c
+++ b/drivers/iio/adc/rohm-bd79124.c
@@ -246,8 +246,8 @@ static int bd79124_init_valid_mask(struct gpio_chip *gc,
 static const struct gpio_chip bd79124gpo_chip = {
 	.label			= "bd79124-gpo",
 	.get_direction		= bd79124gpo_direction_get,
-	.set_rv			= bd79124gpo_set,
-	.set_multiple_rv	= bd79124gpo_set_multiple,
+	.set			= bd79124gpo_set,
+	.set_multiple		= bd79124gpo_set_multiple,
 	.init_valid_mask	= bd79124_init_valid_mask,
 	.can_sleep		= true,
 	.ngpio			= 8,
diff --git a/drivers/iio/adc/ti-ads7950.c b/drivers/iio/adc/ti-ads7950.c
index 0356ccf23fea..bbe1ce577789 100644
--- a/drivers/iio/adc/ti-ads7950.c
+++ b/drivers/iio/adc/ti-ads7950.c
@@ -648,7 +648,7 @@ static int ti_ads7950_probe(struct spi_device *spi)
 	st->chip.direction_input = ti_ads7950_direction_input;
 	st->chip.direction_output = ti_ads7950_direction_output;
 	st->chip.get = ti_ads7950_get;
-	st->chip.set_rv = ti_ads7950_set;
+	st->chip.set = ti_ads7950_set;
 
 	ret = gpiochip_add_data(&st->chip, st);
 	if (ret) {
diff --git a/drivers/iio/addac/ad74115.c b/drivers/iio/addac/ad74115.c
index 4d8b64048e4f..f8b04d86b01f 100644
--- a/drivers/iio/addac/ad74115.c
+++ b/drivers/iio/addac/ad74115.c
@@ -1577,7 +1577,7 @@ static int ad74115_setup_gpio_chip(struct ad74115_state *st)
 		.direction_input = ad74115_gpio_direction_input,
 		.direction_output = ad74115_gpio_direction_output,
 		.get = ad74115_gpio_get,
-		.set_rv = ad74115_gpio_set,
+		.set = ad74115_gpio_set,
 	};
 
 	return devm_gpiochip_add_data(dev, &st->gc, st);
diff --git a/drivers/iio/addac/ad74413r.c b/drivers/iio/addac/ad74413r.c
index a0bb1dbcb7ad..a20b4d48c5f7 100644
--- a/drivers/iio/addac/ad74413r.c
+++ b/drivers/iio/addac/ad74413r.c
@@ -1425,8 +1425,8 @@ static int ad74413r_probe(struct spi_device *spi)
 		st->gpo_gpiochip.ngpio = st->num_gpo_gpios;
 		st->gpo_gpiochip.parent = st->dev;
 		st->gpo_gpiochip.can_sleep = true;
-		st->gpo_gpiochip.set_rv = ad74413r_gpio_set;
-		st->gpo_gpiochip.set_multiple_rv = ad74413r_gpio_set_multiple;
+		st->gpo_gpiochip.set = ad74413r_gpio_set;
+		st->gpo_gpiochip.set_multiple = ad74413r_gpio_set_multiple;
 		st->gpo_gpiochip.set_config = ad74413r_gpio_set_gpo_config;
 		st->gpo_gpiochip.get_direction =
 			ad74413r_gpio_get_gpo_direction;
diff --git a/drivers/iio/dac/ad5592r-base.c b/drivers/iio/dac/ad5592r-base.c
index 5f2cd51723f6..4720733d66b2 100644
--- a/drivers/iio/dac/ad5592r-base.c
+++ b/drivers/iio/dac/ad5592r-base.c
@@ -129,7 +129,7 @@ static int ad5592r_gpio_init(struct ad5592r_state *st)
 	st->gpiochip.direction_input = ad5592r_gpio_direction_input;
 	st->gpiochip.direction_output = ad5592r_gpio_direction_output;
 	st->gpiochip.get = ad5592r_gpio_get;
-	st->gpiochip.set_rv = ad5592r_gpio_set;
+	st->gpiochip.set = ad5592r_gpio_set;
 	st->gpiochip.request = ad5592r_gpio_request;
 	st->gpiochip.owner = THIS_MODULE;
 	st->gpiochip.names = ad5592r_gpio_names;
diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c
index 2b2aca08423a..414fbef4abf9 100644
--- a/drivers/input/keyboard/adp5588-keys.c
+++ b/drivers/input/keyboard/adp5588-keys.c
@@ -425,7 +425,7 @@ static int adp5588_gpio_add(struct adp5588_kpad *kpad)
 	kpad->gc.direction_input = adp5588_gpio_direction_input;
 	kpad->gc.direction_output = adp5588_gpio_direction_output;
 	kpad->gc.get = adp5588_gpio_get_value;
-	kpad->gc.set_rv = adp5588_gpio_set_value;
+	kpad->gc.set = adp5588_gpio_set_value;
 	kpad->gc.set_config = adp5588_gpio_set_config;
 	kpad->gc.can_sleep = 1;
 
diff --git a/drivers/input/touchscreen/ad7879.c b/drivers/input/touchscreen/ad7879.c
index d2a3a5e016b6..8b4f3e3660b8 100644
--- a/drivers/input/touchscreen/ad7879.c
+++ b/drivers/input/touchscreen/ad7879.c
@@ -475,7 +475,7 @@ static int ad7879_gpio_add(struct ad7879 *ts)
 	ts->gc.direction_input = ad7879_gpio_direction_input;
 	ts->gc.direction_output = ad7879_gpio_direction_output;
 	ts->gc.get = ad7879_gpio_get_value;
-	ts->gc.set_rv = ad7879_gpio_set_value;
+	ts->gc.set = ad7879_gpio_set_value;
 	ts->gc.can_sleep = 1;
 	ts->gc.base = -1;
 	ts->gc.ngpio = 1;
diff --git a/drivers/leds/blink/leds-lgm-sso.c b/drivers/leds/blink/leds-lgm-sso.c
index c9027f9c4bb7..8923d2df4704 100644
--- a/drivers/leds/blink/leds-lgm-sso.c
+++ b/drivers/leds/blink/leds-lgm-sso.c
@@ -471,7 +471,7 @@ static int sso_gpio_gc_init(struct device *dev, struct sso_led_priv *priv)
 	gc->get_direction       = sso_gpio_get_dir;
 	gc->direction_output    = sso_gpio_dir_out;
 	gc->get                 = sso_gpio_get;
-	gc->set_rv              = sso_gpio_set;
+	gc->set                 = sso_gpio_set;
 
 	gc->label               = "lgm-sso";
 	gc->base                = -1;
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 7d4c071a6cd0..0344189bb991 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -473,7 +473,7 @@ static int pca9532_configure(struct i2c_client *client,
 		data->gpio.label = "gpio-pca9532";
 		data->gpio.direction_input = pca9532_gpio_direction_input;
 		data->gpio.direction_output = pca9532_gpio_direction_output;
-		data->gpio.set_rv = pca9532_gpio_set_value;
+		data->gpio.set = pca9532_gpio_set_value;
 		data->gpio.get = pca9532_gpio_get_value;
 		data->gpio.request = pca9532_gpio_request_pin;
 		data->gpio.can_sleep = 1;
diff --git a/drivers/leds/leds-pca955x.c b/drivers/leds/leds-pca955x.c
index 70d109246088..2007fe6217ec 100644
--- a/drivers/leds/leds-pca955x.c
+++ b/drivers/leds/leds-pca955x.c
@@ -737,7 +737,7 @@ static int pca955x_probe(struct i2c_client *client)
 	pca955x->gpio.label = "gpio-pca955x";
 	pca955x->gpio.direction_input = pca955x_gpio_direction_input;
 	pca955x->gpio.direction_output = pca955x_gpio_direction_output;
-	pca955x->gpio.set_rv = pca955x_gpio_set_value;
+	pca955x->gpio.set = pca955x_gpio_set_value;
 	pca955x->gpio.get = pca955x_gpio_get_value;
 	pca955x->gpio.request = pca955x_gpio_request_pin;
 	pca955x->gpio.free = pca955x_gpio_free_pin;
diff --git a/drivers/leds/leds-tca6507.c b/drivers/leds/leds-tca6507.c
index 89c165c8ee9c..fd0e8bab9a4b 100644
--- a/drivers/leds/leds-tca6507.c
+++ b/drivers/leds/leds-tca6507.c
@@ -637,7 +637,7 @@ static int tca6507_probe_gpios(struct device *dev,
 	tca->gpio.base = -1;
 	tca->gpio.owner = THIS_MODULE;
 	tca->gpio.direction_output = tca6507_gpio_direction_output;
-	tca->gpio.set_rv = tca6507_gpio_set_value;
+	tca->gpio.set = tca6507_gpio_set_value;
 	tca->gpio.parent = dev;
 	err = devm_gpiochip_add_data(dev, &tca->gpio, tca);
 	if (err) {
diff --git a/drivers/media/dvb-frontends/cxd2820r_core.c b/drivers/media/dvb-frontends/cxd2820r_core.c
index a31a8a6a4946..5aa3d45a691a 100644
--- a/drivers/media/dvb-frontends/cxd2820r_core.c
+++ b/drivers/media/dvb-frontends/cxd2820r_core.c
@@ -651,7 +651,7 @@ static int cxd2820r_probe(struct i2c_client *client)
 		priv->gpio_chip.parent = &client->dev;
 		priv->gpio_chip.owner = THIS_MODULE;
 		priv->gpio_chip.direction_output = cxd2820r_gpio_direction_output;
-		priv->gpio_chip.set_rv = cxd2820r_gpio_set;
+		priv->gpio_chip.set = cxd2820r_gpio_set;
 		priv->gpio_chip.get = cxd2820r_gpio_get;
 		priv->gpio_chip.base = -1; /* Dynamic allocation */
 		priv->gpio_chip.ngpio = GPIO_COUNT;
diff --git a/drivers/media/i2c/ds90ub913.c b/drivers/media/i2c/ds90ub913.c
index bc74499b0a96..a80da2b4a8fa 100644
--- a/drivers/media/i2c/ds90ub913.c
+++ b/drivers/media/i2c/ds90ub913.c
@@ -235,7 +235,7 @@ static int ub913_gpiochip_probe(struct ub913_data *priv)
 	gc->ngpio = UB913_NUM_GPIOS;
 	gc->get_direction = ub913_gpio_get_direction;
 	gc->direction_output = ub913_gpio_direction_out;
-	gc->set_rv = ub913_gpio_set;
+	gc->set = ub913_gpio_set;
 	gc->of_xlate = ub913_gpio_of_xlate;
 	gc->of_gpio_n_cells = 2;
 
diff --git a/drivers/media/i2c/ds90ub953.c b/drivers/media/i2c/ds90ub953.c
index a865bfc89500..e3fc9d66970a 100644
--- a/drivers/media/i2c/ds90ub953.c
+++ b/drivers/media/i2c/ds90ub953.c
@@ -361,7 +361,7 @@ static int ub953_gpiochip_probe(struct ub953_data *priv)
 	gc->direction_input = ub953_gpio_direction_in;
 	gc->direction_output = ub953_gpio_direction_out;
 	gc->get = ub953_gpio_get;
-	gc->set_rv = ub953_gpio_set;
+	gc->set = ub953_gpio_set;
 	gc->of_xlate = ub953_gpio_of_xlate;
 	gc->of_gpio_n_cells = 2;
 
diff --git a/drivers/media/i2c/max9286.c b/drivers/media/i2c/max9286.c
index 1d0b5f56f989..7c0961688d61 100644
--- a/drivers/media/i2c/max9286.c
+++ b/drivers/media/i2c/max9286.c
@@ -1220,7 +1220,7 @@ static int max9286_register_gpio(struct max9286_priv *priv)
 	gpio->owner = THIS_MODULE;
 	gpio->ngpio = 2;
 	gpio->base = -1;
-	gpio->set_rv = max9286_gpiochip_set;
+	gpio->set = max9286_gpiochip_set;
 	gpio->get = max9286_gpiochip_get;
 	gpio->can_sleep = true;
 
diff --git a/drivers/media/i2c/max96717.c b/drivers/media/i2c/max96717.c
index 015e42fbe246..c8ae7890d9fa 100644
--- a/drivers/media/i2c/max96717.c
+++ b/drivers/media/i2c/max96717.c
@@ -355,7 +355,7 @@ static int max96717_gpiochip_probe(struct max96717_priv *priv)
 	gc->get_direction = max96717_gpio_get_direction;
 	gc->direction_input = max96717_gpio_direction_in;
 	gc->direction_output = max96717_gpio_direction_out;
-	gc->set_rv = max96717_gpiochip_set;
+	gc->set = max96717_gpiochip_set;
 	gc->get = max96717_gpiochip_get;
 
 	/* Disable GPIO forwarding */
diff --git a/drivers/media/pci/solo6x10/solo6x10-gpio.c b/drivers/media/pci/solo6x10/solo6x10-gpio.c
index b16a8453a62a..71848741c55c 100644
--- a/drivers/media/pci/solo6x10/solo6x10-gpio.c
+++ b/drivers/media/pci/solo6x10/solo6x10-gpio.c
@@ -158,7 +158,7 @@ int solo_gpio_init(struct solo_dev *solo_dev)
 
 	solo_dev->gpio_dev.get_direction = solo_gpiochip_get_direction;
 	solo_dev->gpio_dev.get = solo_gpiochip_get;
-	solo_dev->gpio_dev.set_rv = solo_gpiochip_set;
+	solo_dev->gpio_dev.set = solo_gpiochip_set;
 
 	ret = gpiochip_add_data(&solo_dev->gpio_dev, solo_dev);
 
diff --git a/drivers/mfd/sm501.c b/drivers/mfd/sm501.c
index a5f9241fa3f2..50bf3260f65d 100644
--- a/drivers/mfd/sm501.c
+++ b/drivers/mfd/sm501.c
@@ -965,7 +965,7 @@ static const struct gpio_chip gpio_chip_template = {
 	.ngpio			= 32,
 	.direction_input	= sm501_gpio_input,
 	.direction_output	= sm501_gpio_output,
-	.set_rv			= sm501_gpio_set,
+	.set			= sm501_gpio_set,
 	.get			= sm501_gpio_get,
 };
 
diff --git a/drivers/mfd/tps65010.c b/drivers/mfd/tps65010.c
index 03bd5cd66798..8a144ec52201 100644
--- a/drivers/mfd/tps65010.c
+++ b/drivers/mfd/tps65010.c
@@ -620,7 +620,7 @@ static int tps65010_probe(struct i2c_client *client)
 		tps->chip.parent = &client->dev;
 		tps->chip.owner = THIS_MODULE;
 
-		tps->chip.set_rv = tps65010_gpio_set;
+		tps->chip.set = tps65010_gpio_set;
 		tps->chip.direction_output = tps65010_output;
 
 		/* NOTE:  only partial support for inputs; nyet IRQs */
diff --git a/drivers/mfd/ucb1x00-core.c b/drivers/mfd/ucb1x00-core.c
index fd71ba29f6b5..4b450d78a65f 100644
--- a/drivers/mfd/ucb1x00-core.c
+++ b/drivers/mfd/ucb1x00-core.c
@@ -570,7 +570,7 @@ static int ucb1x00_probe(struct mcp *mcp)
 		ucb->gpio.owner = THIS_MODULE;
 		ucb->gpio.base = pdata->gpio_base;
 		ucb->gpio.ngpio = 10;
-		ucb->gpio.set_rv = ucb1x00_gpio_set;
+		ucb->gpio.set = ucb1x00_gpio_set;
 		ucb->gpio.get = ucb1x00_gpio_get;
 		ucb->gpio.direction_input = ucb1x00_gpio_direction_input;
 		ucb->gpio.direction_output = ucb1x00_gpio_direction_output;
diff --git a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
index ff8f4404d10f..8eddbaa1fccd 100644
--- a/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
+++ b/drivers/misc/mchp_pci1xxxx/mchp_pci1xxxx_gpio.c
@@ -438,7 +438,7 @@ static int pci1xxxx_gpio_setup(struct pci1xxxx_gpio *priv, int irq)
 	gchip->direction_output = pci1xxxx_gpio_direction_output;
 	gchip->get_direction = pci1xxxx_gpio_get_direction;
 	gchip->get = pci1xxxx_gpio_get;
-	gchip->set_rv = pci1xxxx_gpio_set;
+	gchip->set = pci1xxxx_gpio_set;
 	gchip->set_config = pci1xxxx_gpio_set_config;
 	gchip->dbg_show = NULL;
 	gchip->base = -1;
diff --git a/drivers/misc/ti_fpc202.c b/drivers/misc/ti_fpc202.c
index 0b1a6350c02b..7964e46c7448 100644
--- a/drivers/misc/ti_fpc202.c
+++ b/drivers/misc/ti_fpc202.c
@@ -333,7 +333,7 @@ static int fpc202_probe(struct i2c_client *client)
 	priv->gpio.base = -1;
 	priv->gpio.direction_input = fpc202_gpio_direction_input;
 	priv->gpio.direction_output = fpc202_gpio_direction_output;
-	priv->gpio.set_rv = fpc202_gpio_set;
+	priv->gpio.set = fpc202_gpio_set;
 	priv->gpio.get = fpc202_gpio_get;
 	priv->gpio.ngpio = FPC202_GPIO_COUNT;
 	priv->gpio.parent = dev;
diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
index 5a95877b7419..313e1d241f01 100644
--- a/drivers/net/can/spi/mcp251x.c
+++ b/drivers/net/can/spi/mcp251x.c
@@ -607,8 +607,8 @@ static int mcp251x_gpio_setup(struct mcp251x_priv *priv)
 	gpio->get_direction = mcp251x_gpio_get_direction;
 	gpio->get = mcp251x_gpio_get;
 	gpio->get_multiple = mcp251x_gpio_get_multiple;
-	gpio->set_rv = mcp251x_gpio_set;
-	gpio->set_multiple_rv = mcp251x_gpio_set_multiple;
+	gpio->set = mcp251x_gpio_set;
+	gpio->set_multiple = mcp251x_gpio_set_multiple;
 	gpio->base = -1;
 	gpio->ngpio = ARRAY_SIZE(mcp251x_gpio_names);
 	gpio->names = mcp251x_gpio_names;
diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c
index e5bed4237ff4..548b85befbf4 100644
--- a/drivers/net/dsa/mt7530.c
+++ b/drivers/net/dsa/mt7530.c
@@ -2187,7 +2187,7 @@ mt7530_setup_gpio(struct mt7530_priv *priv)
 	gc->direction_input = mt7530_gpio_direction_input;
 	gc->direction_output = mt7530_gpio_direction_output;
 	gc->get = mt7530_gpio_get;
-	gc->set_rv = mt7530_gpio_set;
+	gc->set = mt7530_gpio_set;
 	gc->base = -1;
 	gc->ngpio = 15;
 	gc->can_sleep = true;
diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
index 4f9687ab3b2b..9d31b8258268 100644
--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
+++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
@@ -2317,7 +2317,7 @@ static int vsc73xx_gpio_probe(struct vsc73xx *vsc)
 	vsc->gc.parent = vsc->dev;
 	vsc->gc.base = -1;
 	vsc->gc.get = vsc73xx_gpio_get;
-	vsc->gc.set_rv = vsc73xx_gpio_set;
+	vsc->gc.set = vsc73xx_gpio_set;
 	vsc->gc.direction_input = vsc73xx_gpio_direction_input;
 	vsc->gc.direction_output = vsc73xx_gpio_direction_output;
 	vsc->gc.get_direction = vsc73xx_gpio_get_direction;
diff --git a/drivers/net/phy/qcom/qca807x.c b/drivers/net/phy/qcom/qca807x.c
index 04e84ebb646c..070dc8c00835 100644
--- a/drivers/net/phy/qcom/qca807x.c
+++ b/drivers/net/phy/qcom/qca807x.c
@@ -427,7 +427,7 @@ static int qca807x_gpio(struct phy_device *phydev)
 	gc->get_direction = qca807x_gpio_get_direction;
 	gc->direction_output = qca807x_gpio_dir_out;
 	gc->get = qca807x_gpio_get;
-	gc->set_rv = qca807x_gpio_set;
+	gc->set = qca807x_gpio_set;
 
 	return devm_gpiochip_add_data(dev, gc, priv);
 }
diff --git a/drivers/pinctrl/actions/pinctrl-owl.c b/drivers/pinctrl/actions/pinctrl-owl.c
index 86f3d5c69e36..1f0ef4727ba7 100644
--- a/drivers/pinctrl/actions/pinctrl-owl.c
+++ b/drivers/pinctrl/actions/pinctrl-owl.c
@@ -962,7 +962,7 @@ int owl_pinctrl_probe(struct platform_device *pdev,
 	pctrl->chip.direction_input  = owl_gpio_direction_input;
 	pctrl->chip.direction_output = owl_gpio_direction_output;
 	pctrl->chip.get = owl_gpio_get;
-	pctrl->chip.set_rv = owl_gpio_set;
+	pctrl->chip.set = owl_gpio_set;
 	pctrl->chip.request = owl_gpio_request;
 	pctrl->chip.free = owl_gpio_free;
 
diff --git a/drivers/pinctrl/bcm/pinctrl-bcm2835.c b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
index 826827800474..7dbf079739bc 100644
--- a/drivers/pinctrl/bcm/pinctrl-bcm2835.c
+++ b/drivers/pinctrl/bcm/pinctrl-bcm2835.c
@@ -397,7 +397,7 @@ static const struct gpio_chip bcm2835_gpio_chip = {
 	.direction_output = bcm2835_gpio_direction_output,
 	.get_direction = bcm2835_gpio_get_direction,
 	.get = bcm2835_gpio_get,
-	.set_rv = bcm2835_gpio_set,
+	.set = bcm2835_gpio_set,
 	.set_config = gpiochip_generic_config,
 	.base = -1,
 	.ngpio = BCM2835_NUM_GPIOS,
@@ -414,7 +414,7 @@ static const struct gpio_chip bcm2711_gpio_chip = {
 	.direction_output = bcm2835_gpio_direction_output,
 	.get_direction = bcm2835_gpio_get_direction,
 	.get = bcm2835_gpio_get,
-	.set_rv = bcm2835_gpio_set,
+	.set = bcm2835_gpio_set,
 	.set_config = gpiochip_generic_config,
 	.base = -1,
 	.ngpio = BCM2711_NUM_GPIOS,
diff --git a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
index 1d08b8d4cdd7..8c353676f2af 100644
--- a/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-iproc-gpio.c
@@ -865,7 +865,7 @@ static int iproc_gpio_probe(struct platform_device *pdev)
 	gc->direction_input = iproc_gpio_direction_input;
 	gc->direction_output = iproc_gpio_direction_output;
 	gc->get_direction = iproc_gpio_get_direction;
-	gc->set_rv = iproc_gpio_set;
+	gc->set = iproc_gpio_set;
 	gc->get = iproc_gpio_get;
 
 	chip->pinmux_is_supported = of_property_read_bool(dev->of_node,
diff --git a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
index b08f8480ddc6..b425ecacd1b0 100644
--- a/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
+++ b/drivers/pinctrl/bcm/pinctrl-nsp-gpio.c
@@ -656,7 +656,7 @@ static int nsp_gpio_probe(struct platform_device *pdev)
 	gc->direction_input = nsp_gpio_direction_input;
 	gc->direction_output = nsp_gpio_direction_output;
 	gc->get_direction = nsp_gpio_get_direction;
-	gc->set_rv = nsp_gpio_set;
+	gc->set = nsp_gpio_set;
 	gc->get = nsp_gpio_get;
 
 	/* optional GPIO interrupt support */
diff --git a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
index 4e47710eb3d5..68abb6d6cecd 100644
--- a/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
+++ b/drivers/pinctrl/cirrus/pinctrl-cs42l43.c
@@ -555,7 +555,7 @@ static int cs42l43_pin_probe(struct platform_device *pdev)
 	priv->gpio_chip.direction_output = cs42l43_gpio_direction_out;
 	priv->gpio_chip.add_pin_ranges = cs42l43_gpio_add_pin_ranges;
 	priv->gpio_chip.get = cs42l43_gpio_get;
-	priv->gpio_chip.set_rv = cs42l43_gpio_set;
+	priv->gpio_chip.set = cs42l43_gpio_set;
 	priv->gpio_chip.label = dev_name(priv->dev);
 	priv->gpio_chip.parent = priv->dev;
 	priv->gpio_chip.can_sleep = true;
diff --git a/drivers/pinctrl/cirrus/pinctrl-lochnagar.c b/drivers/pinctrl/cirrus/pinctrl-lochnagar.c
index dcc0a2f3c7dd..ca6ae566082b 100644
--- a/drivers/pinctrl/cirrus/pinctrl-lochnagar.c
+++ b/drivers/pinctrl/cirrus/pinctrl-lochnagar.c
@@ -1161,7 +1161,7 @@ static int lochnagar_pin_probe(struct platform_device *pdev)
 	priv->gpio_chip.request = gpiochip_generic_request;
 	priv->gpio_chip.free = gpiochip_generic_free;
 	priv->gpio_chip.direction_output = lochnagar_gpio_direction_out;
-	priv->gpio_chip.set_rv = lochnagar_gpio_set;
+	priv->gpio_chip.set = lochnagar_gpio_set;
 	priv->gpio_chip.can_sleep = true;
 	priv->gpio_chip.parent = dev;
 	priv->gpio_chip.base = -1;
diff --git a/drivers/pinctrl/intel/pinctrl-baytrail.c b/drivers/pinctrl/intel/pinctrl-baytrail.c
index 6eb649f1ffd6..5fd107a00ef8 100644
--- a/drivers/pinctrl/intel/pinctrl-baytrail.c
+++ b/drivers/pinctrl/intel/pinctrl-baytrail.c
@@ -1231,7 +1231,7 @@ static const struct gpio_chip byt_gpio_chip = {
 	.direction_input	= byt_gpio_direction_input,
 	.direction_output	= byt_gpio_direction_output,
 	.get			= byt_gpio_get,
-	.set_rv			= byt_gpio_set,
+	.set			= byt_gpio_set,
 	.set_config		= gpiochip_generic_config,
 	.dbg_show		= byt_gpio_dbg_show,
 };
diff --git a/drivers/pinctrl/intel/pinctrl-cherryview.c b/drivers/pinctrl/intel/pinctrl-cherryview.c
index 769e8c4102a5..f81f7929cd3b 100644
--- a/drivers/pinctrl/intel/pinctrl-cherryview.c
+++ b/drivers/pinctrl/intel/pinctrl-cherryview.c
@@ -1168,7 +1168,7 @@ static const struct gpio_chip chv_gpio_chip = {
 	.direction_input = chv_gpio_direction_input,
 	.direction_output = chv_gpio_direction_output,
 	.get = chv_gpio_get,
-	.set_rv = chv_gpio_set,
+	.set = chv_gpio_set,
 };
 
 static void chv_gpio_irq_ack(struct irq_data *d)
diff --git a/drivers/pinctrl/intel/pinctrl-intel.c b/drivers/pinctrl/intel/pinctrl-intel.c
index f2ff71e5ea6f..d68cef4ec52a 100644
--- a/drivers/pinctrl/intel/pinctrl-intel.c
+++ b/drivers/pinctrl/intel/pinctrl-intel.c
@@ -1114,7 +1114,7 @@ static const struct gpio_chip intel_gpio_chip = {
 	.direction_input = intel_gpio_direction_input,
 	.direction_output = intel_gpio_direction_output,
 	.get = intel_gpio_get,
-	.set_rv = intel_gpio_set,
+	.set = intel_gpio_set,
 	.set_config = gpiochip_generic_config,
 };
 
diff --git a/drivers/pinctrl/intel/pinctrl-lynxpoint.c b/drivers/pinctrl/intel/pinctrl-lynxpoint.c
index 5d4a5dd493d1..3fb628309fb2 100644
--- a/drivers/pinctrl/intel/pinctrl-lynxpoint.c
+++ b/drivers/pinctrl/intel/pinctrl-lynxpoint.c
@@ -777,7 +777,7 @@ static int lp_gpio_probe(struct platform_device *pdev)
 	gc->direction_input = lp_gpio_direction_input;
 	gc->direction_output = lp_gpio_direction_output;
 	gc->get = lp_gpio_get;
-	gc->set_rv = lp_gpio_set;
+	gc->set = lp_gpio_set;
 	gc->set_config = gpiochip_generic_config;
 	gc->get_direction = lp_gpio_get_direction;
 	gc->base = -1;
diff --git a/drivers/pinctrl/mediatek/pinctrl-airoha.c b/drivers/pinctrl/mediatek/pinctrl-airoha.c
index 1737b88530c3..5f1ec9e0de21 100644
--- a/drivers/pinctrl/mediatek/pinctrl-airoha.c
+++ b/drivers/pinctrl/mediatek/pinctrl-airoha.c
@@ -2418,7 +2418,7 @@ static int airoha_pinctrl_add_gpiochip(struct airoha_pinctrl *pinctrl,
 	gc->free = gpiochip_generic_free;
 	gc->direction_input = pinctrl_gpio_direction_input;
 	gc->direction_output = airoha_gpio_direction_output;
-	gc->set_rv = airoha_gpio_set;
+	gc->set = airoha_gpio_set;
 	gc->get = airoha_gpio_get;
 	gc->base = -1;
 	gc->ngpio = AIROHA_NUM_PINS;
diff --git a/drivers/pinctrl/mediatek/pinctrl-moore.c b/drivers/pinctrl/mediatek/pinctrl-moore.c
index ba0d6f880c6e..6e4f6c07a509 100644
--- a/drivers/pinctrl/mediatek/pinctrl-moore.c
+++ b/drivers/pinctrl/mediatek/pinctrl-moore.c
@@ -569,7 +569,7 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw)
 	chip->direction_input	= pinctrl_gpio_direction_input;
 	chip->direction_output	= mtk_gpio_direction_output;
 	chip->get		= mtk_gpio_get;
-	chip->set_rv		= mtk_gpio_set;
+	chip->set		= mtk_gpio_set;
 	chip->to_irq		= mtk_gpio_to_irq;
 	chip->set_config	= mtk_gpio_set_config;
 	chip->base		= -1;
diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
index a4cb6d511fcd..d10306024111 100644
--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
+++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common.c
@@ -898,7 +898,7 @@ static const struct gpio_chip mtk_gpio_chip = {
 	.direction_input	= pinctrl_gpio_direction_input,
 	.direction_output	= mtk_gpio_direction_output,
 	.get			= mtk_gpio_get,
-	.set_rv			= mtk_gpio_set,
+	.set			= mtk_gpio_set,
 	.to_irq			= mtk_gpio_to_irq,
 	.set_config		= mtk_gpio_set_config,
 };
diff --git a/drivers/pinctrl/mediatek/pinctrl-paris.c b/drivers/pinctrl/mediatek/pinctrl-paris.c
index 89ef4e530fcc..3e714554789d 100644
--- a/drivers/pinctrl/mediatek/pinctrl-paris.c
+++ b/drivers/pinctrl/mediatek/pinctrl-paris.c
@@ -949,7 +949,7 @@ static int mtk_build_gpiochip(struct mtk_pinctrl *hw)
 	chip->direction_input	= mtk_gpio_direction_input;
 	chip->direction_output	= mtk_gpio_direction_output;
 	chip->get		= mtk_gpio_get;
-	chip->set_rv		= mtk_gpio_set;
+	chip->set		= mtk_gpio_set;
 	chip->to_irq		= mtk_gpio_to_irq;
 	chip->set_config	= mtk_gpio_set_config;
 	chip->base		= -1;
diff --git a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
index c8958222df8c..e34e984c2b38 100644
--- a/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
+++ b/drivers/pinctrl/meson/pinctrl-amlogic-a4.c
@@ -888,7 +888,7 @@ static const struct gpio_chip aml_gpio_template = {
 	.request		= gpiochip_generic_request,
 	.free			= gpiochip_generic_free,
 	.set_config		= gpiochip_generic_config,
-	.set_rv			= aml_gpio_set,
+	.set			= aml_gpio_set,
 	.get			= aml_gpio_get,
 	.direction_input	= aml_gpio_direction_input,
 	.direction_output	= aml_gpio_direction_output,
diff --git a/drivers/pinctrl/meson/pinctrl-meson.c b/drivers/pinctrl/meson/pinctrl-meson.c
index f5be61f2ede4..277e9c40490d 100644
--- a/drivers/pinctrl/meson/pinctrl-meson.c
+++ b/drivers/pinctrl/meson/pinctrl-meson.c
@@ -616,7 +616,7 @@ static int meson_gpiolib_register(struct meson_pinctrl *pc)
 	pc->chip.direction_input = meson_gpio_direction_input;
 	pc->chip.direction_output = meson_gpio_direction_output;
 	pc->chip.get = meson_gpio_get;
-	pc->chip.set_rv = meson_gpio_set;
+	pc->chip.set = meson_gpio_set;
 	pc->chip.base = -1;
 	pc->chip.ngpio = pc->data->num_pins;
 	pc->chip.can_sleep = false;
diff --git a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
index a6b106984e12..881df5e08f61 100644
--- a/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
+++ b/drivers/pinctrl/mvebu/pinctrl-armada-37xx.c
@@ -518,7 +518,7 @@ static const struct pinmux_ops armada_37xx_pmx_ops = {
 static const struct gpio_chip armada_37xx_gpiolib_chip = {
 	.request = gpiochip_generic_request,
 	.free = gpiochip_generic_free,
-	.set_rv = armada_37xx_gpio_set,
+	.set = armada_37xx_gpio_set,
 	.get = armada_37xx_gpio_get,
 	.get_direction	= armada_37xx_gpio_get_direction,
 	.direction_input = armada_37xx_gpio_direction_input,
diff --git a/drivers/pinctrl/nomadik/pinctrl-abx500.c b/drivers/pinctrl/nomadik/pinctrl-abx500.c
index 2f55f83127cf..7b5f94d8cb23 100644
--- a/drivers/pinctrl/nomadik/pinctrl-abx500.c
+++ b/drivers/pinctrl/nomadik/pinctrl-abx500.c
@@ -536,7 +536,7 @@ static const struct gpio_chip abx500gpio_chip = {
 	.direction_input	= abx500_gpio_direction_input,
 	.get			= abx500_gpio_get,
 	.direction_output	= abx500_gpio_direction_output,
-	.set_rv			= abx500_gpio_set,
+	.set			= abx500_gpio_set,
 	.to_irq			= abx500_gpio_to_irq,
 	.dbg_show		= abx500_gpio_dbg_show,
 };
diff --git a/drivers/pinctrl/nuvoton/pinctrl-ma35.c b/drivers/pinctrl/nuvoton/pinctrl-ma35.c
index da5220da5149..54652bfbe6ac 100644
--- a/drivers/pinctrl/nuvoton/pinctrl-ma35.c
+++ b/drivers/pinctrl/nuvoton/pinctrl-ma35.c
@@ -526,7 +526,7 @@ static int ma35_gpiolib_register(struct platform_device *pdev, struct ma35_pinct
 		bank->chip.direction_input = ma35_gpio_core_direction_in;
 		bank->chip.direction_output = ma35_gpio_core_direction_out;
 		bank->chip.get = ma35_gpio_core_get;
-		bank->chip.set_rv = ma35_gpio_core_set;
+		bank->chip.set = ma35_gpio_core_set;
 		bank->chip.base = -1;
 		bank->chip.ngpio = bank->nr_pins;
 		bank->chip.can_sleep = false;
diff --git a/drivers/pinctrl/pinctrl-amd.c b/drivers/pinctrl/pinctrl-amd.c
index b90ef3a26ae8..09a5425d54ba 100644
--- a/drivers/pinctrl/pinctrl-amd.c
+++ b/drivers/pinctrl/pinctrl-amd.c
@@ -1187,7 +1187,7 @@ static int amd_gpio_probe(struct platform_device *pdev)
 	gpio_dev->gc.direction_input	= amd_gpio_direction_input;
 	gpio_dev->gc.direction_output	= amd_gpio_direction_output;
 	gpio_dev->gc.get			= amd_gpio_get_value;
-	gpio_dev->gc.set_rv			= amd_gpio_set_value;
+	gpio_dev->gc.set			= amd_gpio_set_value;
 	gpio_dev->gc.set_config		= amd_gpio_set_config;
 	gpio_dev->gc.dbg_show		= amd_gpio_dbg_show;
 
diff --git a/drivers/pinctrl/pinctrl-amdisp.c b/drivers/pinctrl/pinctrl-amdisp.c
index 2e706bf8bcde..efbf40c776ea 100644
--- a/drivers/pinctrl/pinctrl-amdisp.c
+++ b/drivers/pinctrl/pinctrl-amdisp.c
@@ -151,7 +151,7 @@ static int amdisp_gpiochip_add(struct platform_device *pdev,
 	gc->direction_input	= amdisp_gpio_direction_input;
 	gc->direction_output	= amdisp_gpio_direction_output;
 	gc->get			= amdisp_gpio_get;
-	gc->set_rv		= amdisp_gpio_set;
+	gc->set			= amdisp_gpio_set;
 	gc->base		= -1;
 	gc->ngpio		= ARRAY_SIZE(amdisp_range_pins);
 
diff --git a/drivers/pinctrl/pinctrl-apple-gpio.c b/drivers/pinctrl/pinctrl-apple-gpio.c
index dcf3a921b4df..a09daa72bfe4 100644
--- a/drivers/pinctrl/pinctrl-apple-gpio.c
+++ b/drivers/pinctrl/pinctrl-apple-gpio.c
@@ -378,7 +378,7 @@ static int apple_gpio_register(struct apple_gpio_pinctrl *pctl)
 	pctl->gpio_chip.direction_input = apple_gpio_direction_input;
 	pctl->gpio_chip.direction_output = apple_gpio_direction_output;
 	pctl->gpio_chip.get = apple_gpio_get;
-	pctl->gpio_chip.set_rv = apple_gpio_set;
+	pctl->gpio_chip.set = apple_gpio_set;
 	pctl->gpio_chip.base = -1;
 	pctl->gpio_chip.ngpio = pctl->pinctrl_desc.npins;
 	pctl->gpio_chip.parent = pctl->dev;
diff --git a/drivers/pinctrl/pinctrl-as3722.c b/drivers/pinctrl/pinctrl-as3722.c
index 30ed758bbe9d..e713dea98aa8 100644
--- a/drivers/pinctrl/pinctrl-as3722.c
+++ b/drivers/pinctrl/pinctrl-as3722.c
@@ -529,7 +529,7 @@ static const struct gpio_chip as3722_gpio_chip = {
 	.request		= gpiochip_generic_request,
 	.free			= gpiochip_generic_free,
 	.get			= as3722_gpio_get,
-	.set_rv			= as3722_gpio_set,
+	.set			= as3722_gpio_set,
 	.direction_input	= pinctrl_gpio_direction_input,
 	.direction_output	= as3722_gpio_direction_output,
 	.to_irq			= as3722_gpio_to_irq,
diff --git a/drivers/pinctrl/pinctrl-at91-pio4.c b/drivers/pinctrl/pinctrl-at91-pio4.c
index 57f105ac962d..35ea3414cb96 100644
--- a/drivers/pinctrl/pinctrl-at91-pio4.c
+++ b/drivers/pinctrl/pinctrl-at91-pio4.c
@@ -442,8 +442,8 @@ static struct gpio_chip atmel_gpio_chip = {
 	.get                    = atmel_gpio_get,
 	.get_multiple           = atmel_gpio_get_multiple,
 	.direction_output       = atmel_gpio_direction_output,
-	.set_rv                 = atmel_gpio_set,
-	.set_multiple_rv        = atmel_gpio_set_multiple,
+	.set                    = atmel_gpio_set,
+	.set_multiple           = atmel_gpio_set_multiple,
 	.to_irq                 = atmel_gpio_to_irq,
 	.base                   = 0,
 };
diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
index 6c2727bd55bc..0a57ed51d4c9 100644
--- a/drivers/pinctrl/pinctrl-at91.c
+++ b/drivers/pinctrl/pinctrl-at91.c
@@ -1801,8 +1801,8 @@ static const struct gpio_chip at91_gpio_template = {
 	.direction_input	= at91_gpio_direction_input,
 	.get			= at91_gpio_get,
 	.direction_output	= at91_gpio_direction_output,
-	.set_rv			= at91_gpio_set,
-	.set_multiple_rv	= at91_gpio_set_multiple,
+	.set			= at91_gpio_set,
+	.set_multiple		= at91_gpio_set_multiple,
 	.dbg_show		= at91_gpio_dbg_show,
 	.can_sleep		= false,
 	.ngpio			= MAX_NB_GPIO_PER_BANK,
diff --git a/drivers/pinctrl/pinctrl-aw9523.c b/drivers/pinctrl/pinctrl-aw9523.c
index 9570ef346af6..890b83fddea3 100644
--- a/drivers/pinctrl/pinctrl-aw9523.c
+++ b/drivers/pinctrl/pinctrl-aw9523.c
@@ -785,8 +785,8 @@ static int aw9523_init_gpiochip(struct aw9523 *awi, unsigned int npins)
 	gc->direction_output = aw9523_direction_output;
 	gc->get = aw9523_gpio_get;
 	gc->get_multiple = aw9523_gpio_get_multiple;
-	gc->set_rv = aw9523_gpio_set;
-	gc->set_multiple_rv = aw9523_gpio_set_multiple;
+	gc->set = aw9523_gpio_set;
+	gc->set_multiple = aw9523_gpio_set_multiple;
 	gc->set_config = gpiochip_generic_config;
 	gc->parent = dev;
 	gc->owner = THIS_MODULE;
diff --git a/drivers/pinctrl/pinctrl-axp209.c b/drivers/pinctrl/pinctrl-axp209.c
index fff408b60c4a..2bd8487484a8 100644
--- a/drivers/pinctrl/pinctrl-axp209.c
+++ b/drivers/pinctrl/pinctrl-axp209.c
@@ -192,7 +192,7 @@ static int axp20x_gpio_get_direction(struct gpio_chip *chip,
 static int axp20x_gpio_output(struct gpio_chip *chip, unsigned int offset,
 			      int value)
 {
-	return chip->set_rv(chip, offset, value);
+	return chip->set(chip, offset, value);
 }
 
 static int axp20x_gpio_set(struct gpio_chip *chip, unsigned int offset,
@@ -463,7 +463,7 @@ static int axp20x_pctl_probe(struct platform_device *pdev)
 	pctl->chip.owner		= THIS_MODULE;
 	pctl->chip.get			= axp20x_gpio_get;
 	pctl->chip.get_direction	= axp20x_gpio_get_direction;
-	pctl->chip.set_rv		= axp20x_gpio_set;
+	pctl->chip.set			= axp20x_gpio_set;
 	pctl->chip.direction_input	= pinctrl_gpio_direction_input;
 	pctl->chip.direction_output	= axp20x_gpio_output;
 
diff --git a/drivers/pinctrl/pinctrl-cy8c95x0.c b/drivers/pinctrl/pinctrl-cy8c95x0.c
index 8a2fd632bdd4..cf7f80497fde 100644
--- a/drivers/pinctrl/pinctrl-cy8c95x0.c
+++ b/drivers/pinctrl/pinctrl-cy8c95x0.c
@@ -939,10 +939,10 @@ static int cy8c95x0_setup_gpiochip(struct cy8c95x0_pinctrl *chip)
 	gc->direction_input  = cy8c95x0_gpio_direction_input;
 	gc->direction_output = cy8c95x0_gpio_direction_output;
 	gc->get = cy8c95x0_gpio_get_value;
-	gc->set_rv = cy8c95x0_gpio_set_value;
+	gc->set = cy8c95x0_gpio_set_value;
 	gc->get_direction = cy8c95x0_gpio_get_direction;
 	gc->get_multiple = cy8c95x0_gpio_get_multiple;
-	gc->set_multiple_rv = cy8c95x0_gpio_set_multiple;
+	gc->set_multiple = cy8c95x0_gpio_set_multiple;
 	gc->set_config = gpiochip_generic_config;
 	gc->can_sleep = true;
 	gc->add_pin_ranges = cy8c95x0_add_pin_ranges;
diff --git a/drivers/pinctrl/pinctrl-da9062.c b/drivers/pinctrl/pinctrl-da9062.c
index 3295b09dfc3d..53298cbcc5cf 100644
--- a/drivers/pinctrl/pinctrl-da9062.c
+++ b/drivers/pinctrl/pinctrl-da9062.c
@@ -233,7 +233,7 @@ static int da9062_gpio_to_irq(struct gpio_chip *gc, unsigned int offset)
 static const struct gpio_chip reference_gc = {
 	.owner = THIS_MODULE,
 	.get = da9062_gpio_get,
-	.set_rv = da9062_gpio_set,
+	.set = da9062_gpio_set,
 	.get_direction = da9062_gpio_get_direction,
 	.direction_input = da9062_gpio_direction_input,
 	.direction_output = da9062_gpio_direction_output,
diff --git a/drivers/pinctrl/pinctrl-digicolor.c b/drivers/pinctrl/pinctrl-digicolor.c
index 1676cb3cc4c9..2e16f09aeb47 100644
--- a/drivers/pinctrl/pinctrl-digicolor.c
+++ b/drivers/pinctrl/pinctrl-digicolor.c
@@ -248,7 +248,7 @@ static int dc_gpiochip_add(struct dc_pinmap *pmap)
 	chip->direction_input	= dc_gpio_direction_input;
 	chip->direction_output	= dc_gpio_direction_output;
 	chip->get		= dc_gpio_get;
-	chip->set_rv		= dc_gpio_set;
+	chip->set		= dc_gpio_set;
 	chip->base		= -1;
 	chip->ngpio		= PINS_COUNT;
 
diff --git a/drivers/pinctrl/pinctrl-ingenic.c b/drivers/pinctrl/pinctrl-ingenic.c
index 79119cf20efc..2900513467fa 100644
--- a/drivers/pinctrl/pinctrl-ingenic.c
+++ b/drivers/pinctrl/pinctrl-ingenic.c
@@ -4451,7 +4451,7 @@ static int __init ingenic_gpio_probe(struct ingenic_pinctrl *jzpc,
 	jzgc->gc.fwnode = fwnode;
 	jzgc->gc.owner = THIS_MODULE;
 
-	jzgc->gc.set_rv = ingenic_gpio_set;
+	jzgc->gc.set = ingenic_gpio_set;
 	jzgc->gc.get = ingenic_gpio_get;
 	jzgc->gc.direction_input = pinctrl_gpio_direction_input;
 	jzgc->gc.direction_output = ingenic_gpio_direction_output;
diff --git a/drivers/pinctrl/pinctrl-keembay.c b/drivers/pinctrl/pinctrl-keembay.c
index 30e641571cfe..60cf017498b3 100644
--- a/drivers/pinctrl/pinctrl-keembay.c
+++ b/drivers/pinctrl/pinctrl-keembay.c
@@ -1481,7 +1481,7 @@ static int keembay_gpiochip_probe(struct keembay_pinctrl *kpc,
 	gc->direction_input	= keembay_gpio_set_direction_in;
 	gc->direction_output	= keembay_gpio_set_direction_out;
 	gc->get			= keembay_gpio_get;
-	gc->set_rv		= keembay_gpio_set;
+	gc->set			= keembay_gpio_set;
 	gc->set_config		= gpiochip_generic_config;
 	gc->base		= -1;
 	gc->ngpio		= kpc->npins;
diff --git a/drivers/pinctrl/pinctrl-mcp23s08.c b/drivers/pinctrl/pinctrl-mcp23s08.c
index c8027ef03ecc..a17fcaddf490 100644
--- a/drivers/pinctrl/pinctrl-mcp23s08.c
+++ b/drivers/pinctrl/pinctrl-mcp23s08.c
@@ -632,8 +632,8 @@ int mcp23s08_probe_one(struct mcp23s08 *mcp, struct device *dev,
 	mcp->chip.get = mcp23s08_get;
 	mcp->chip.get_multiple = mcp23s08_get_multiple;
 	mcp->chip.direction_output = mcp23s08_direction_output;
-	mcp->chip.set_rv = mcp23s08_set;
-	mcp->chip.set_multiple_rv = mcp23s08_set_multiple;
+	mcp->chip.set = mcp23s08_set;
+	mcp->chip.set_multiple = mcp23s08_set_multiple;
 
 	mcp->chip.base = base;
 	mcp->chip.can_sleep = true;
diff --git a/drivers/pinctrl/pinctrl-microchip-sgpio.c b/drivers/pinctrl/pinctrl-microchip-sgpio.c
index 88c2f14cfc6b..6191e5c13815 100644
--- a/drivers/pinctrl/pinctrl-microchip-sgpio.c
+++ b/drivers/pinctrl/pinctrl-microchip-sgpio.c
@@ -858,7 +858,7 @@ static int microchip_sgpio_register_bank(struct device *dev,
 	gc->direction_input	= microchip_sgpio_direction_input;
 	gc->direction_output	= microchip_sgpio_direction_output;
 	gc->get			= microchip_sgpio_get_value;
-	gc->set_rv		= microchip_sgpio_set_value;
+	gc->set			= microchip_sgpio_set_value;
 	gc->request		= gpiochip_generic_request;
 	gc->free		= gpiochip_generic_free;
 	gc->of_xlate		= microchip_sgpio_of_xlate;
diff --git a/drivers/pinctrl/pinctrl-ocelot.c b/drivers/pinctrl/pinctrl-ocelot.c
index fbb3d43746bb..b82bf83fed25 100644
--- a/drivers/pinctrl/pinctrl-ocelot.c
+++ b/drivers/pinctrl/pinctrl-ocelot.c
@@ -1997,7 +1997,7 @@ static int ocelot_gpio_direction_output(struct gpio_chip *chip,
 static const struct gpio_chip ocelot_gpiolib_chip = {
 	.request = gpiochip_generic_request,
 	.free = gpiochip_generic_free,
-	.set_rv = ocelot_gpio_set,
+	.set = ocelot_gpio_set,
 	.get = ocelot_gpio_get,
 	.get_direction = ocelot_gpio_get_direction,
 	.direction_input = pinctrl_gpio_direction_input,
diff --git a/drivers/pinctrl/pinctrl-pic32.c b/drivers/pinctrl/pinctrl-pic32.c
index 6d64cab97e81..37c2bf752154 100644
--- a/drivers/pinctrl/pinctrl-pic32.c
+++ b/drivers/pinctrl/pinctrl-pic32.c
@@ -2120,7 +2120,7 @@ static void pic32_gpio_irq_handler(struct irq_desc *desc)
 			.direction_input = pic32_gpio_direction_input,	\
 			.direction_output = pic32_gpio_direction_output, \
 			.get = pic32_gpio_get,				\
-			.set_rv = pic32_gpio_set,			\
+			.set = pic32_gpio_set,				\
 			.ngpio = _npins,				\
 			.base = GPIO_BANK_START(_bank),			\
 			.owner = THIS_MODULE,				\
diff --git a/drivers/pinctrl/pinctrl-pistachio.c b/drivers/pinctrl/pinctrl-pistachio.c
index 7f8b562c81c9..0b33b01dbaad 100644
--- a/drivers/pinctrl/pinctrl-pistachio.c
+++ b/drivers/pinctrl/pinctrl-pistachio.c
@@ -1331,7 +1331,7 @@ static void pistachio_gpio_irq_handler(struct irq_desc *desc)
 			.direction_input = pistachio_gpio_direction_input, \
 			.direction_output = pistachio_gpio_direction_output, \
 			.get = pistachio_gpio_get,			\
-			.set_rv = pistachio_gpio_set,			\
+			.set = pistachio_gpio_set,			\
 			.base = _pin_base,				\
 			.ngpio = _npins,				\
 		},							\
diff --git a/drivers/pinctrl/pinctrl-rk805.c b/drivers/pinctrl/pinctrl-rk805.c
index fc0e330b1d11..3acf770316c1 100644
--- a/drivers/pinctrl/pinctrl-rk805.c
+++ b/drivers/pinctrl/pinctrl-rk805.c
@@ -378,7 +378,7 @@ static const struct gpio_chip rk805_gpio_chip = {
 	.free			= gpiochip_generic_free,
 	.get_direction		= rk805_gpio_get_direction,
 	.get			= rk805_gpio_get,
-	.set_rv			= rk805_gpio_set,
+	.set			= rk805_gpio_set,
 	.direction_input	= pinctrl_gpio_direction_input,
 	.direction_output	= rk805_gpio_direction_output,
 	.can_sleep		= true,
diff --git a/drivers/pinctrl/pinctrl-rp1.c b/drivers/pinctrl/pinctrl-rp1.c
index 6080b57a5d87..dadafc935dbb 100644
--- a/drivers/pinctrl/pinctrl-rp1.c
+++ b/drivers/pinctrl/pinctrl-rp1.c
@@ -851,7 +851,7 @@ static const struct gpio_chip rp1_gpio_chip = {
 	.direction_output = rp1_gpio_direction_output,
 	.get_direction = rp1_gpio_get_direction,
 	.get = rp1_gpio_get,
-	.set_rv = rp1_gpio_set,
+	.set = rp1_gpio_set,
 	.base = -1,
 	.set_config = rp1_gpio_set_config,
 	.ngpio = RP1_NUM_GPIOS,
diff --git a/drivers/pinctrl/pinctrl-st.c b/drivers/pinctrl/pinctrl-st.c
index 574fe2cbfbec..d3cea3437d7f 100644
--- a/drivers/pinctrl/pinctrl-st.c
+++ b/drivers/pinctrl/pinctrl-st.c
@@ -1467,7 +1467,7 @@ static const struct gpio_chip st_gpio_template = {
 	.request		= gpiochip_generic_request,
 	.free			= gpiochip_generic_free,
 	.get			= st_gpio_get,
-	.set_rv			= st_gpio_set,
+	.set			= st_gpio_set,
 	.direction_input	= pinctrl_gpio_direction_input,
 	.direction_output	= st_gpio_direction_output,
 	.get_direction		= st_gpio_get_direction,
diff --git a/drivers/pinctrl/pinctrl-stmfx.c b/drivers/pinctrl/pinctrl-stmfx.c
index f4fdcaa043e6..c89b99003b71 100644
--- a/drivers/pinctrl/pinctrl-stmfx.c
+++ b/drivers/pinctrl/pinctrl-stmfx.c
@@ -697,7 +697,7 @@ static int stmfx_pinctrl_probe(struct platform_device *pdev)
 	pctl->gpio_chip.direction_input = stmfx_gpio_direction_input;
 	pctl->gpio_chip.direction_output = stmfx_gpio_direction_output;
 	pctl->gpio_chip.get = stmfx_gpio_get;
-	pctl->gpio_chip.set_rv = stmfx_gpio_set;
+	pctl->gpio_chip.set = stmfx_gpio_set;
 	pctl->gpio_chip.set_config = gpiochip_generic_config;
 	pctl->gpio_chip.base = -1;
 	pctl->gpio_chip.ngpio = pctl->pctl_desc.npins;
diff --git a/drivers/pinctrl/pinctrl-sx150x.c b/drivers/pinctrl/pinctrl-sx150x.c
index d3a12c1c0de2..53cf8168b274 100644
--- a/drivers/pinctrl/pinctrl-sx150x.c
+++ b/drivers/pinctrl/pinctrl-sx150x.c
@@ -1176,7 +1176,7 @@ static int sx150x_probe(struct i2c_client *client)
 	pctl->gpio.direction_input = sx150x_gpio_direction_input;
 	pctl->gpio.direction_output = sx150x_gpio_direction_output;
 	pctl->gpio.get = sx150x_gpio_get;
-	pctl->gpio.set_rv = sx150x_gpio_set;
+	pctl->gpio.set = sx150x_gpio_set;
 	pctl->gpio.set_config = gpiochip_generic_config;
 	pctl->gpio.parent = dev;
 	pctl->gpio.can_sleep = true;
@@ -1191,7 +1191,7 @@ static int sx150x_probe(struct i2c_client *client)
 	 * would require locking that is not in place at this time.
 	 */
 	if (pctl->data->model != SX150X_789)
-		pctl->gpio.set_multiple_rv = sx150x_gpio_set_multiple;
+		pctl->gpio.set_multiple = sx150x_gpio_set_multiple;
 
 	/* Add Interrupt support if an irq is specified */
 	if (client->irq > 0) {
diff --git a/drivers/pinctrl/pinctrl-xway.c b/drivers/pinctrl/pinctrl-xway.c
index 53c6c22ff24d..3d4ad61d0da9 100644
--- a/drivers/pinctrl/pinctrl-xway.c
+++ b/drivers/pinctrl/pinctrl-xway.c
@@ -1354,7 +1354,7 @@ static struct gpio_chip xway_chip = {
 	.direction_input = xway_gpio_dir_in,
 	.direction_output = xway_gpio_dir_out,
 	.get = xway_gpio_get,
-	.set_rv = xway_gpio_set,
+	.set = xway_gpio_set,
 	.request = gpiochip_generic_request,
 	.free = gpiochip_generic_free,
 	.to_irq = xway_gpio_to_irq,
diff --git a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
index 57fefeb603f0..54c77e0b96e9 100644
--- a/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
+++ b/drivers/pinctrl/qcom/pinctrl-lpass-lpi.c
@@ -398,7 +398,7 @@ static const struct gpio_chip lpi_gpio_template = {
 	.direction_input	= lpi_gpio_direction_input,
 	.direction_output	= lpi_gpio_direction_output,
 	.get			= lpi_gpio_get,
-	.set_rv			= lpi_gpio_set,
+	.set			= lpi_gpio_set,
 	.request		= gpiochip_generic_request,
 	.free			= gpiochip_generic_free,
 	.dbg_show		= lpi_gpio_dbg_show,
diff --git a/drivers/pinctrl/qcom/pinctrl-msm.c b/drivers/pinctrl/qcom/pinctrl-msm.c
index f713c80d7f3e..83eb075b6bfa 100644
--- a/drivers/pinctrl/qcom/pinctrl-msm.c
+++ b/drivers/pinctrl/qcom/pinctrl-msm.c
@@ -792,7 +792,7 @@ static const struct gpio_chip msm_gpio_template = {
 	.direction_output = msm_gpio_direction_output,
 	.get_direction    = msm_gpio_get_direction,
 	.get              = msm_gpio_get,
-	.set_rv           = msm_gpio_set,
+	.set              = msm_gpio_set,
 	.request          = gpiochip_generic_request,
 	.free             = gpiochip_generic_free,
 	.dbg_show         = msm_gpio_dbg_show,
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
index 606becc160eb..b7b15874e488 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-gpio.c
@@ -802,7 +802,7 @@ static const struct gpio_chip pmic_gpio_gpio_template = {
 	.direction_input	= pmic_gpio_direction_input,
 	.direction_output	= pmic_gpio_direction_output,
 	.get			= pmic_gpio_get,
-	.set_rv			= pmic_gpio_set,
+	.set			= pmic_gpio_set,
 	.request		= gpiochip_generic_request,
 	.free			= gpiochip_generic_free,
 	.of_xlate		= pmic_gpio_of_xlate,
diff --git a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
index ba9084978f90..22d76b1013a3 100644
--- a/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-spmi-mpp.c
@@ -638,7 +638,7 @@ static const struct gpio_chip pmic_mpp_gpio_template = {
 	.direction_input	= pmic_mpp_direction_input,
 	.direction_output	= pmic_mpp_direction_output,
 	.get			= pmic_mpp_get,
-	.set_rv			= pmic_mpp_set,
+	.set			= pmic_mpp_set,
 	.request		= gpiochip_generic_request,
 	.free			= gpiochip_generic_free,
 	.of_xlate		= pmic_mpp_of_xlate,
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
index 3a8014ebf064..fb37b1c1acb4 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-gpio.c
@@ -597,7 +597,7 @@ static const struct gpio_chip pm8xxx_gpio_template = {
 	.direction_input = pm8xxx_gpio_direction_input,
 	.direction_output = pm8xxx_gpio_direction_output,
 	.get = pm8xxx_gpio_get,
-	.set_rv = pm8xxx_gpio_set,
+	.set = pm8xxx_gpio_set,
 	.of_xlate = pm8xxx_gpio_of_xlate,
 	.dbg_show = pm8xxx_gpio_dbg_show,
 	.owner = THIS_MODULE,
diff --git a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
index 087c37d304fc..6103849af042 100644
--- a/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
+++ b/drivers/pinctrl/qcom/pinctrl-ssbi-mpp.c
@@ -634,7 +634,7 @@ static const struct gpio_chip pm8xxx_mpp_template = {
 	.direction_input = pm8xxx_mpp_direction_input,
 	.direction_output = pm8xxx_mpp_direction_output,
 	.get = pm8xxx_mpp_get,
-	.set_rv = pm8xxx_mpp_set,
+	.set = pm8xxx_mpp_set,
 	.of_xlate = pm8xxx_mpp_of_xlate,
 	.dbg_show = pm8xxx_mpp_dbg_show,
 	.owner = THIS_MODULE,
diff --git a/drivers/pinctrl/renesas/gpio.c b/drivers/pinctrl/renesas/gpio.c
index 8efbdc1b0078..2293af642849 100644
--- a/drivers/pinctrl/renesas/gpio.c
+++ b/drivers/pinctrl/renesas/gpio.c
@@ -234,7 +234,7 @@ static int gpio_pin_setup(struct sh_pfc_chip *chip)
 	gc->direction_input = gpio_pin_direction_input;
 	gc->get = gpio_pin_get;
 	gc->direction_output = gpio_pin_direction_output;
-	gc->set_rv = gpio_pin_set;
+	gc->set = gpio_pin_set;
 	gc->to_irq = gpio_pin_to_irq;
 
 	gc->label = pfc->info->name;
diff --git a/drivers/pinctrl/renesas/pinctrl-rza1.c b/drivers/pinctrl/renesas/pinctrl-rza1.c
index 3d8492c91710..23812116ef42 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza1.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza1.c
@@ -846,7 +846,7 @@ static const struct gpio_chip rza1_gpiochip_template = {
 	.direction_input	= rza1_gpio_direction_input,
 	.direction_output	= rza1_gpio_direction_output,
 	.get			= rza1_gpio_get,
-	.set_rv			= rza1_gpio_set,
+	.set			= rza1_gpio_set,
 };
 /* ----------------------------------------------------------------------------
  * pinctrl operations
diff --git a/drivers/pinctrl/renesas/pinctrl-rza2.c b/drivers/pinctrl/renesas/pinctrl-rza2.c
index 7a0b268d3eb9..b78b5b4ec5af 100644
--- a/drivers/pinctrl/renesas/pinctrl-rza2.c
+++ b/drivers/pinctrl/renesas/pinctrl-rza2.c
@@ -237,7 +237,7 @@ static struct gpio_chip chip = {
 	.direction_input = rza2_chip_direction_input,
 	.direction_output = rza2_chip_direction_output,
 	.get = rza2_chip_get,
-	.set_rv = rza2_chip_set,
+	.set = rza2_chip_set,
 };
 
 static int rza2_gpio_register(struct rza2_pinctrl_priv *priv)
diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
index 2a10ae0bf5bd..c52263c2a7b0 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
@@ -2795,7 +2795,7 @@ static int rzg2l_gpio_register(struct rzg2l_pinctrl *pctrl)
 	chip->direction_input = rzg2l_gpio_direction_input;
 	chip->direction_output = rzg2l_gpio_direction_output;
 	chip->get = rzg2l_gpio_get;
-	chip->set_rv = rzg2l_gpio_set;
+	chip->set = rzg2l_gpio_set;
 	chip->label = name;
 	chip->parent = pctrl->dev;
 	chip->owner = THIS_MODULE;
diff --git a/drivers/pinctrl/renesas/pinctrl-rzv2m.c b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
index a17b68b4c466..daaa986d994d 100644
--- a/drivers/pinctrl/renesas/pinctrl-rzv2m.c
+++ b/drivers/pinctrl/renesas/pinctrl-rzv2m.c
@@ -957,7 +957,7 @@ static int rzv2m_gpio_register(struct rzv2m_pinctrl *pctrl)
 	chip->direction_input = rzv2m_gpio_direction_input;
 	chip->direction_output = rzv2m_gpio_direction_output;
 	chip->get = rzv2m_gpio_get;
-	chip->set_rv = rzv2m_gpio_set;
+	chip->set = rzv2m_gpio_set;
 	chip->label = name;
 	chip->parent = pctrl->dev;
 	chip->owner = THIS_MODULE;
diff --git a/drivers/pinctrl/samsung/pinctrl-samsung.c b/drivers/pinctrl/samsung/pinctrl-samsung.c
index fe1ac82b9d79..24745e1d78ce 100644
--- a/drivers/pinctrl/samsung/pinctrl-samsung.c
+++ b/drivers/pinctrl/samsung/pinctrl-samsung.c
@@ -1067,7 +1067,7 @@ static int samsung_gpio_set_config(struct gpio_chip *gc, unsigned int offset,
 static const struct gpio_chip samsung_gpiolib_chip = {
 	.request = gpiochip_generic_request,
 	.free = gpiochip_generic_free,
-	.set_rv = samsung_gpio_set,
+	.set = samsung_gpio_set,
 	.get = samsung_gpio_get,
 	.direction_input = samsung_gpio_direction_input,
 	.direction_output = samsung_gpio_direction_output,
diff --git a/drivers/pinctrl/spear/pinctrl-plgpio.c b/drivers/pinctrl/spear/pinctrl-plgpio.c
index e8234d2156da..1ec22010a3f9 100644
--- a/drivers/pinctrl/spear/pinctrl-plgpio.c
+++ b/drivers/pinctrl/spear/pinctrl-plgpio.c
@@ -582,7 +582,7 @@ static int plgpio_probe(struct platform_device *pdev)
 	plgpio->chip.direction_input = plgpio_direction_input;
 	plgpio->chip.direction_output = plgpio_direction_output;
 	plgpio->chip.get = plgpio_get_value;
-	plgpio->chip.set_rv = plgpio_set_value;
+	plgpio->chip.set = plgpio_set_value;
 	plgpio->chip.label = dev_name(&pdev->dev);
 	plgpio->chip.parent = &pdev->dev;
 	plgpio->chip.owner = THIS_MODULE;
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
index b729ca4de422..7fa13f282b85 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7100.c
@@ -1302,7 +1302,7 @@ static int starfive_probe(struct platform_device *pdev)
 	sfp->gc.direction_input = starfive_gpio_direction_input;
 	sfp->gc.direction_output = starfive_gpio_direction_output;
 	sfp->gc.get = starfive_gpio_get;
-	sfp->gc.set_rv = starfive_gpio_set;
+	sfp->gc.set = starfive_gpio_set;
 	sfp->gc.set_config = starfive_gpio_set_config;
 	sfp->gc.add_pin_ranges = starfive_gpio_add_pin_ranges;
 	sfp->gc.base = -1;
diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
index 082bb1c6cea9..05e3af75b09f 100644
--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
+++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
@@ -935,7 +935,7 @@ int jh7110_pinctrl_probe(struct platform_device *pdev)
 	sfp->gc.direction_input = jh7110_gpio_direction_input;
 	sfp->gc.direction_output = jh7110_gpio_direction_output;
 	sfp->gc.get = jh7110_gpio_get;
-	sfp->gc.set_rv = jh7110_gpio_set;
+	sfp->gc.set = jh7110_gpio_set;
 	sfp->gc.set_config = jh7110_gpio_set_config;
 	sfp->gc.add_pin_ranges = jh7110_gpio_add_pin_ranges;
 	sfp->gc.base = info->gc_base;
diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c
index f47c4e6f12b4..823c8fe758e2 100644
--- a/drivers/pinctrl/stm32/pinctrl-stm32.c
+++ b/drivers/pinctrl/stm32/pinctrl-stm32.c
@@ -433,7 +433,7 @@ static const struct gpio_chip stm32_gpio_template = {
 	.request		= stm32_gpio_request,
 	.free			= stm32_gpio_free,
 	.get			= stm32_gpio_get,
-	.set_rv			= stm32_gpio_set,
+	.set			= stm32_gpio_set,
 	.direction_input	= pinctrl_gpio_direction_input,
 	.direction_output	= stm32_gpio_direction_output,
 	.to_irq			= stm32_gpio_to_irq,
diff --git a/drivers/pinctrl/sunplus/sppctl.c b/drivers/pinctrl/sunplus/sppctl.c
index 3c3357f80889..3e924aa86cc2 100644
--- a/drivers/pinctrl/sunplus/sppctl.c
+++ b/drivers/pinctrl/sunplus/sppctl.c
@@ -547,7 +547,7 @@ static int sppctl_gpio_new(struct platform_device *pdev, struct sppctl_pdata *pc
 	gchip->direction_input  = sppctl_gpio_direction_input;
 	gchip->direction_output = sppctl_gpio_direction_output;
 	gchip->get              = sppctl_gpio_get;
-	gchip->set_rv           = sppctl_gpio_set;
+	gchip->set              = sppctl_gpio_set;
 	gchip->set_config       = sppctl_gpio_set_config;
 	gchip->dbg_show         = IS_ENABLED(CONFIG_DEBUG_FS) ?
 				  sppctl_gpio_dbg_show : NULL;
diff --git a/drivers/pinctrl/sunxi/pinctrl-sunxi.c b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
index 0db8429a013f..0fb057a07dcc 100644
--- a/drivers/pinctrl/sunxi/pinctrl-sunxi.c
+++ b/drivers/pinctrl/sunxi/pinctrl-sunxi.c
@@ -1604,7 +1604,7 @@ int sunxi_pinctrl_init_with_flags(struct platform_device *pdev,
 	pctl->chip->direction_input = sunxi_pinctrl_gpio_direction_input;
 	pctl->chip->direction_output = sunxi_pinctrl_gpio_direction_output;
 	pctl->chip->get = sunxi_pinctrl_gpio_get;
-	pctl->chip->set_rv = sunxi_pinctrl_gpio_set;
+	pctl->chip->set = sunxi_pinctrl_gpio_set;
 	pctl->chip->of_xlate = sunxi_pinctrl_gpio_of_xlate;
 	pctl->chip->to_irq = sunxi_pinctrl_gpio_to_irq;
 	pctl->chip->of_gpio_n_cells = 3;
diff --git a/drivers/pinctrl/vt8500/pinctrl-wmt.c b/drivers/pinctrl/vt8500/pinctrl-wmt.c
index 767c6808a463..7213a8d4bf09 100644
--- a/drivers/pinctrl/vt8500/pinctrl-wmt.c
+++ b/drivers/pinctrl/vt8500/pinctrl-wmt.c
@@ -549,7 +549,7 @@ static const struct gpio_chip wmt_gpio_chip = {
 	.direction_input = pinctrl_gpio_direction_input,
 	.direction_output = wmt_gpio_direction_output,
 	.get = wmt_gpio_get_value,
-	.set_rv = wmt_gpio_set_value,
+	.set = wmt_gpio_set_value,
 	.can_sleep = false,
 };
 
diff --git a/drivers/platform/cznic/turris-omnia-mcu-gpio.c b/drivers/platform/cznic/turris-omnia-mcu-gpio.c
index 77184c8b42ea..7f0ada4fa606 100644
--- a/drivers/platform/cznic/turris-omnia-mcu-gpio.c
+++ b/drivers/platform/cznic/turris-omnia-mcu-gpio.c
@@ -1024,8 +1024,8 @@ int omnia_mcu_register_gpiochip(struct omnia_mcu *mcu)
 	mcu->gc.direction_output = omnia_gpio_direction_output;
 	mcu->gc.get = omnia_gpio_get;
 	mcu->gc.get_multiple = omnia_gpio_get_multiple;
-	mcu->gc.set_rv = omnia_gpio_set;
-	mcu->gc.set_multiple_rv = omnia_gpio_set_multiple;
+	mcu->gc.set = omnia_gpio_set;
+	mcu->gc.set_multiple = omnia_gpio_set_multiple;
 	mcu->gc.init_valid_mask = omnia_gpio_init_valid_mask;
 	mcu->gc.can_sleep = true;
 	mcu->gc.names = omnia_mcu_gpio_names;
diff --git a/drivers/platform/x86/barco-p50-gpio.c b/drivers/platform/x86/barco-p50-gpio.c
index bb3393bbfb89..28012eebdb10 100644
--- a/drivers/platform/x86/barco-p50-gpio.c
+++ b/drivers/platform/x86/barco-p50-gpio.c
@@ -316,7 +316,7 @@ static int p50_gpio_probe(struct platform_device *pdev)
 	p50->gc.base = -1;
 	p50->gc.get_direction = p50_gpio_get_direction;
 	p50->gc.get = p50_gpio_get;
-	p50->gc.set_rv = p50_gpio_set;
+	p50->gc.set = p50_gpio_set;
 
 
 	/* reset mbox */
diff --git a/drivers/platform/x86/intel/int0002_vgpio.c b/drivers/platform/x86/intel/int0002_vgpio.c
index 9bc24ed19c64..6f5629dc3f8d 100644
--- a/drivers/platform/x86/intel/int0002_vgpio.c
+++ b/drivers/platform/x86/intel/int0002_vgpio.c
@@ -193,7 +193,7 @@ static int int0002_probe(struct platform_device *pdev)
 	chip->parent = dev;
 	chip->owner = THIS_MODULE;
 	chip->get = int0002_gpio_get;
-	chip->set_rv = int0002_gpio_set;
+	chip->set = int0002_gpio_set;
 	chip->direction_input = int0002_gpio_get;
 	chip->direction_output = int0002_gpio_direction_output;
 	chip->base = -1;
diff --git a/drivers/platform/x86/portwell-ec.c b/drivers/platform/x86/portwell-ec.c
index 3e019c51913e..322f296e9315 100644
--- a/drivers/platform/x86/portwell-ec.c
+++ b/drivers/platform/x86/portwell-ec.c
@@ -86,7 +86,7 @@ static int pwec_gpio_get(struct gpio_chip *chip, unsigned int offset)
 	return pwec_read(PORTWELL_GPIO_VAL_REG) & BIT(offset) ? 1 : 0;
 }
 
-static int pwec_gpio_set_rv(struct gpio_chip *chip, unsigned int offset, int val)
+static int pwec_gpio_set(struct gpio_chip *chip, unsigned int offset, int val)
 {
 	u8 tmp = pwec_read(PORTWELL_GPIO_VAL_REG);
 
@@ -130,7 +130,7 @@ static struct gpio_chip pwec_gpio_chip = {
 	.direction_input = pwec_gpio_direction_input,
 	.direction_output = pwec_gpio_direction_output,
 	.get = pwec_gpio_get,
-	.set_rv = pwec_gpio_set_rv,
+	.set = pwec_gpio_set,
 	.base = -1,
 	.ngpio = PORTWELL_GPIO_PINS,
 };
diff --git a/drivers/platform/x86/silicom-platform.c b/drivers/platform/x86/silicom-platform.c
index 63b5da410ed5..266f7bc5e416 100644
--- a/drivers/platform/x86/silicom-platform.c
+++ b/drivers/platform/x86/silicom-platform.c
@@ -466,7 +466,7 @@ static struct gpio_chip silicom_gpio_chip = {
 	.direction_input = silicom_gpio_direction_input,
 	.direction_output = silicom_gpio_direction_output,
 	.get = silicom_gpio_get,
-	.set_rv = silicom_gpio_set,
+	.set = silicom_gpio_set,
 	.base = -1,
 	.ngpio = ARRAY_SIZE(plat_0222_gpio_channels),
 	.names = plat_0222_gpio_names,
diff --git a/drivers/pwm/pwm-pca9685.c b/drivers/pwm/pwm-pca9685.c
index eb03ccd5b688..9ce75704a15f 100644
--- a/drivers/pwm/pwm-pca9685.c
+++ b/drivers/pwm/pwm-pca9685.c
@@ -323,7 +323,7 @@ static int pca9685_pwm_gpio_probe(struct pwm_chip *chip)
 	pca->gpio.direction_input = pca9685_pwm_gpio_direction_input;
 	pca->gpio.direction_output = pca9685_pwm_gpio_direction_output;
 	pca->gpio.get = pca9685_pwm_gpio_get;
-	pca->gpio.set_rv = pca9685_pwm_gpio_set;
+	pca->gpio.set = pca9685_pwm_gpio_set;
 	pca->gpio.base = -1;
 	pca->gpio.ngpio = PCA9685_MAXCHAN;
 	pca->gpio.can_sleep = true;
diff --git a/drivers/regulator/rpi-panel-attiny-regulator.c b/drivers/regulator/rpi-panel-attiny-regulator.c
index 58dbf8bffa5d..3020839b9ef1 100644
--- a/drivers/regulator/rpi-panel-attiny-regulator.c
+++ b/drivers/regulator/rpi-panel-attiny-regulator.c
@@ -351,7 +351,7 @@ static int attiny_i2c_probe(struct i2c_client *i2c)
 	state->gc.base = -1;
 	state->gc.ngpio = NUM_GPIO;
 
-	state->gc.set_rv = attiny_gpio_set;
+	state->gc.set = attiny_gpio_set;
 	state->gc.get_direction = attiny_gpio_get_direction;
 	state->gc.can_sleep = true;
 
diff --git a/drivers/soc/fsl/qe/gpio.c b/drivers/soc/fsl/qe/gpio.c
index 710a3a03758b..8df1e8fa86a5 100644
--- a/drivers/soc/fsl/qe/gpio.c
+++ b/drivers/soc/fsl/qe/gpio.c
@@ -321,8 +321,8 @@ static int __init qe_add_gpiochips(void)
 		gc->direction_input = qe_gpio_dir_in;
 		gc->direction_output = qe_gpio_dir_out;
 		gc->get = qe_gpio_get;
-		gc->set_rv = qe_gpio_set;
-		gc->set_multiple_rv = qe_gpio_set_multiple;
+		gc->set = qe_gpio_set;
+		gc->set_multiple = qe_gpio_set_multiple;
 
 		ret = of_mm_gpiochip_add_data(np, mm_gc, qe_gc);
 		if (ret)
diff --git a/drivers/soc/renesas/pwc-rzv2m.c b/drivers/soc/renesas/pwc-rzv2m.c
index 4dbcb3d4a90c..6209168b3734 100644
--- a/drivers/soc/renesas/pwc-rzv2m.c
+++ b/drivers/soc/renesas/pwc-rzv2m.c
@@ -64,7 +64,7 @@ static const struct gpio_chip rzv2m_pwc_gc = {
 	.label = "gpio_rzv2m_pwc",
 	.owner = THIS_MODULE,
 	.get = rzv2m_pwc_gpio_get,
-	.set_rv = rzv2m_pwc_gpio_set,
+	.set = rzv2m_pwc_gpio_set,
 	.direction_output = rzv2m_pwc_gpio_direction_output,
 	.can_sleep = false,
 	.ngpio = 2,
diff --git a/drivers/spi/spi-xcomm.c b/drivers/spi/spi-xcomm.c
index 1a40c4866ce1..33b78c537520 100644
--- a/drivers/spi/spi-xcomm.c
+++ b/drivers/spi/spi-xcomm.c
@@ -70,7 +70,7 @@ static int spi_xcomm_gpio_add(struct spi_xcomm *spi_xcomm)
 		return 0;
 
 	spi_xcomm->gc.get_direction = spi_xcomm_gpio_get_direction;
-	spi_xcomm->gc.set_rv = spi_xcomm_gpio_set_value;
+	spi_xcomm->gc.set = spi_xcomm_gpio_set_value;
 	spi_xcomm->gc.can_sleep = 1;
 	spi_xcomm->gc.base = -1;
 	spi_xcomm->gc.ngpio = 1;
diff --git a/drivers/ssb/driver_gpio.c b/drivers/ssb/driver_gpio.c
index e1f5f0a9c8a2..905657c925bc 100644
--- a/drivers/ssb/driver_gpio.c
+++ b/drivers/ssb/driver_gpio.c
@@ -225,7 +225,7 @@ static int ssb_gpio_chipco_init(struct ssb_bus *bus)
 	chip->request		= ssb_gpio_chipco_request;
 	chip->free		= ssb_gpio_chipco_free;
 	chip->get		= ssb_gpio_chipco_get_value;
-	chip->set_rv		= ssb_gpio_chipco_set_value;
+	chip->set		= ssb_gpio_chipco_set_value;
 	chip->direction_input	= ssb_gpio_chipco_direction_input;
 	chip->direction_output	= ssb_gpio_chipco_direction_output;
 #if IS_ENABLED(CONFIG_SSB_EMBEDDED)
@@ -422,7 +422,7 @@ static int ssb_gpio_extif_init(struct ssb_bus *bus)
 	chip->label		= "ssb_extif_gpio";
 	chip->owner		= THIS_MODULE;
 	chip->get		= ssb_gpio_extif_get_value;
-	chip->set_rv		= ssb_gpio_extif_set_value;
+	chip->set		= ssb_gpio_extif_set_value;
 	chip->direction_input	= ssb_gpio_extif_direction_input;
 	chip->direction_output	= ssb_gpio_extif_direction_output;
 #if IS_ENABLED(CONFIG_SSB_EMBEDDED)
diff --git a/drivers/staging/greybus/gpio.c b/drivers/staging/greybus/gpio.c
index 1280530c8987..ac62b932e6a4 100644
--- a/drivers/staging/greybus/gpio.c
+++ b/drivers/staging/greybus/gpio.c
@@ -551,7 +551,7 @@ static int gb_gpio_probe(struct gbphy_device *gbphy_dev,
 	gpio->direction_input = gb_gpio_direction_input;
 	gpio->direction_output = gb_gpio_direction_output;
 	gpio->get = gb_gpio_get;
-	gpio->set_rv = gb_gpio_set;
+	gpio->set = gb_gpio_set;
 	gpio->set_config = gb_gpio_set_config;
 	gpio->base = -1;		/* Allocate base dynamically */
 	gpio->ngpio = ggc->line_max + 1;
diff --git a/drivers/tty/serial/max310x.c b/drivers/tty/serial/max310x.c
index 541c790c0109..ce260e9949c3 100644
--- a/drivers/tty/serial/max310x.c
+++ b/drivers/tty/serial/max310x.c
@@ -1414,7 +1414,7 @@ static int max310x_probe(struct device *dev, const struct max310x_devtype *devty
 	s->gpio.direction_input	= max310x_gpio_direction_input;
 	s->gpio.get		= max310x_gpio_get;
 	s->gpio.direction_output= max310x_gpio_direction_output;
-	s->gpio.set_rv		= max310x_gpio_set;
+	s->gpio.set		= max310x_gpio_set;
 	s->gpio.set_config	= max310x_gpio_set_config;
 	s->gpio.base		= -1;
 	s->gpio.ngpio		= devtype->nr * 4;
diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
index 5ea8aadb6e69..3f38fba8f6ea 100644
--- a/drivers/tty/serial/sc16is7xx.c
+++ b/drivers/tty/serial/sc16is7xx.c
@@ -1425,7 +1425,7 @@ static int sc16is7xx_setup_gpio_chip(struct sc16is7xx_port *s)
 	s->gpio.direction_input	 = sc16is7xx_gpio_direction_input;
 	s->gpio.get		 = sc16is7xx_gpio_get;
 	s->gpio.direction_output = sc16is7xx_gpio_direction_output;
-	s->gpio.set_rv		 = sc16is7xx_gpio_set;
+	s->gpio.set		 = sc16is7xx_gpio_set;
 	s->gpio.base		 = -1;
 	s->gpio.ngpio		 = s->devtype->nr_gpio;
 	s->gpio.can_sleep	 = 1;
diff --git a/drivers/usb/serial/cp210x.c b/drivers/usb/serial/cp210x.c
index cfa1d68c7919..36b25418b214 100644
--- a/drivers/usb/serial/cp210x.c
+++ b/drivers/usb/serial/cp210x.c
@@ -1962,7 +1962,7 @@ static int cp210x_gpio_init(struct usb_serial *serial)
 	priv->gc.direction_input = cp210x_gpio_direction_input;
 	priv->gc.direction_output = cp210x_gpio_direction_output;
 	priv->gc.get = cp210x_gpio_get;
-	priv->gc.set_rv = cp210x_gpio_set;
+	priv->gc.set = cp210x_gpio_set;
 	priv->gc.set_config = cp210x_gpio_set_config;
 	priv->gc.init_valid_mask = cp210x_gpio_init_valid_mask;
 	priv->gc.owner = THIS_MODULE;
diff --git a/drivers/usb/serial/ftdi_sio.c b/drivers/usb/serial/ftdi_sio.c
index 7737285a84ba..49666c33b41f 100644
--- a/drivers/usb/serial/ftdi_sio.c
+++ b/drivers/usb/serial/ftdi_sio.c
@@ -2150,9 +2150,9 @@ static int ftdi_gpio_init(struct usb_serial_port *port)
 	priv->gc.direction_output = ftdi_gpio_direction_output;
 	priv->gc.init_valid_mask = ftdi_gpio_init_valid_mask;
 	priv->gc.get = ftdi_gpio_get;
-	priv->gc.set_rv = ftdi_gpio_set;
+	priv->gc.set = ftdi_gpio_set;
 	priv->gc.get_multiple = ftdi_gpio_get_multiple;
-	priv->gc.set_multiple_rv = ftdi_gpio_set_multiple;
+	priv->gc.set_multiple = ftdi_gpio_set_multiple;
 	priv->gc.owner = THIS_MODULE;
 	priv->gc.parent = &serial->interface->dev;
 	priv->gc.base = -1;
diff --git a/drivers/video/fbdev/via/via-gpio.c b/drivers/video/fbdev/via/via-gpio.c
index 72302384bf77..45c0a4a6f85c 100644
--- a/drivers/video/fbdev/via/via-gpio.c
+++ b/drivers/video/fbdev/via/via-gpio.c
@@ -145,7 +145,7 @@ static struct viafb_gpio_cfg viafb_gpio_config = {
 		.label = "VIAFB onboard GPIO",
 		.owner = THIS_MODULE,
 		.direction_output = via_gpio_dir_out,
-		.set_rv = via_gpio_set,
+		.set = via_gpio_set,
 		.direction_input = via_gpio_dir_input,
 		.get = via_gpio_get,
 		.base = -1,
diff --git a/include/linux/gpio/driver.h b/include/linux/gpio/driver.h
index 90567dde7d8e..667f8fd58a79 100644
--- a/include/linux/gpio/driver.h
+++ b/include/linux/gpio/driver.h
@@ -347,10 +347,10 @@ struct gpio_irq_chip {
  * @get: returns value for signal "offset", 0=low, 1=high, or negative error
  * @get_multiple: reads values for multiple signals defined by "mask" and
  *	stores them in "bits", returns 0 on success or negative error
- * @set_rv: assigns output value for signal "offset", returns 0 on success or
- *          negative error value
- * @set_multiple_rv: assigns output values for multiple signals defined by
- *                   "mask", returns 0 on success or negative error value
+ * @set: assigns output value for signal "offset", returns 0 on success or
+ *       negative error value
+ * @set_multiple: assigns output values for multiple signals defined by
+ *                "mask", returns 0 on success or negative error value
  * @set_config: optional hook for all kinds of settings. Uses the same
  *	packed config format as generic pinconf. Must return 0 on success and
  *	a negative error number on failure.
@@ -443,12 +443,11 @@ struct gpio_chip {
 	int			(*get_multiple)(struct gpio_chip *gc,
 						unsigned long *mask,
 						unsigned long *bits);
-	int			(*set_rv)(struct gpio_chip *gc,
-					  unsigned int offset,
-					  int value);
-	int			(*set_multiple_rv)(struct gpio_chip *gc,
-						   unsigned long *mask,
-						   unsigned long *bits);
+	int			(*set)(struct gpio_chip *gc,
+				       unsigned int offset, int value);
+	int			(*set_multiple)(struct gpio_chip *gc,
+						unsigned long *mask,
+						unsigned long *bits);
 	int			(*set_config)(struct gpio_chip *gc,
 					      unsigned int offset,
 					      unsigned long config);
diff --git a/include/linux/gpio/generic.h b/include/linux/gpio/generic.h
index b511acd58ab0..f3a8db4598bb 100644
--- a/include/linux/gpio/generic.h
+++ b/include/linux/gpio/generic.h
@@ -88,10 +88,10 @@ static inline int
 gpio_generic_chip_set(struct gpio_generic_chip *chip, unsigned int offset,
 		      int value)
 {
-	if (WARN_ON(!chip->gc.set_rv))
+	if (WARN_ON(!chip->gc.set))
 		return -EOPNOTSUPP;
 
-	return chip->gc.set_rv(&chip->gc, offset, value);
+	return chip->gc.set(&chip->gc, offset, value);
 }
 
 #define gpio_generic_chip_lock(gen_gc) \
diff --git a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c
index 93b9cbf1f08a..9ba14c09c07f 100644
--- a/sound/hda/codecs/side-codecs/cirrus_scodec_test.c
+++ b/sound/hda/codecs/side-codecs/cirrus_scodec_test.c
@@ -86,7 +86,7 @@ static const struct gpio_chip cirrus_scodec_test_gpio_chip = {
 	.direction_input	= cirrus_scodec_test_gpio_direction_in,
 	.get			= cirrus_scodec_test_gpio_get,
 	.direction_output	= cirrus_scodec_test_gpio_direction_out,
-	.set_rv			= cirrus_scodec_test_gpio_set,
+	.set			= cirrus_scodec_test_gpio_set,
 	.set_config		= cirrus_scodec_test_gpio_set_config,
 	.base			= -1,
 	.ngpio			= 32,
diff --git a/sound/soc/codecs/idt821034.c b/sound/soc/codecs/idt821034.c
index 55e90604bbaa..6738cf21983b 100644
--- a/sound/soc/codecs/idt821034.c
+++ b/sound/soc/codecs/idt821034.c
@@ -1117,7 +1117,7 @@ static int idt821034_gpio_init(struct idt821034 *idt821034)
 	idt821034->gpio_chip.direction_input = idt821034_chip_direction_input;
 	idt821034->gpio_chip.direction_output = idt821034_chip_direction_output;
 	idt821034->gpio_chip.get = idt821034_chip_gpio_get;
-	idt821034->gpio_chip.set_rv = idt821034_chip_gpio_set;
+	idt821034->gpio_chip.set = idt821034_chip_gpio_set;
 	idt821034->gpio_chip.can_sleep = true;
 
 	return devm_gpiochip_add_data(&idt821034->spi->dev, &idt821034->gpio_chip,
diff --git a/sound/soc/codecs/peb2466.c b/sound/soc/codecs/peb2466.c
index b8905c03445e..c0c5b3c3e98b 100644
--- a/sound/soc/codecs/peb2466.c
+++ b/sound/soc/codecs/peb2466.c
@@ -1945,7 +1945,7 @@ static int peb2466_gpio_init(struct peb2466 *peb2466)
 	peb2466->gpio.gpio_chip.direction_input = peb2466_chip_direction_input;
 	peb2466->gpio.gpio_chip.direction_output = peb2466_chip_direction_output;
 	peb2466->gpio.gpio_chip.get = peb2466_chip_gpio_get;
-	peb2466->gpio.gpio_chip.set_rv = peb2466_chip_gpio_set;
+	peb2466->gpio.gpio_chip.set = peb2466_chip_gpio_set;
 	peb2466->gpio.gpio_chip.can_sleep = true;
 
 	return devm_gpiochip_add_data(&peb2466->spi->dev, &peb2466->gpio.gpio_chip,
diff --git a/sound/soc/codecs/rt5677.c b/sound/soc/codecs/rt5677.c
index 69a0fb8d7f77..6b6c690a9e45 100644
--- a/sound/soc/codecs/rt5677.c
+++ b/sound/soc/codecs/rt5677.c
@@ -4835,7 +4835,7 @@ static const struct gpio_chip rt5677_template_chip = {
 	.label			= RT5677_DRV_NAME,
 	.owner			= THIS_MODULE,
 	.direction_output	= rt5677_gpio_direction_out,
-	.set_rv			= rt5677_gpio_set,
+	.set			= rt5677_gpio_set,
 	.direction_input	= rt5677_gpio_direction_in,
 	.get			= rt5677_gpio_get,
 	.to_irq			= rt5677_to_irq,
diff --git a/sound/soc/codecs/tlv320adc3xxx.c b/sound/soc/codecs/tlv320adc3xxx.c
index 1035ba17dc5d..258fbcaf345a 100644
--- a/sound/soc/codecs/tlv320adc3xxx.c
+++ b/sound/soc/codecs/tlv320adc3xxx.c
@@ -1052,7 +1052,7 @@ static const struct gpio_chip adc3xxx_gpio_chip = {
 	.owner			= THIS_MODULE,
 	.request		= adc3xxx_gpio_request,
 	.direction_output	= adc3xxx_gpio_direction_out,
-	.set_rv			= adc3xxx_gpio_set,
+	.set			= adc3xxx_gpio_set,
 	.get			= adc3xxx_gpio_get,
 	.can_sleep		= 1,
 };
diff --git a/sound/soc/codecs/wm5100.c b/sound/soc/codecs/wm5100.c
index fb5ed4ba7f60..2d0a20f2fd8c 100644
--- a/sound/soc/codecs/wm5100.c
+++ b/sound/soc/codecs/wm5100.c
@@ -2290,7 +2290,7 @@ static const struct gpio_chip wm5100_template_chip = {
 	.label			= "wm5100",
 	.owner			= THIS_MODULE,
 	.direction_output	= wm5100_gpio_direction_out,
-	.set_rv			= wm5100_gpio_set,
+	.set			= wm5100_gpio_set,
 	.direction_input	= wm5100_gpio_direction_in,
 	.get			= wm5100_gpio_get,
 	.can_sleep		= 1,
diff --git a/sound/soc/codecs/wm8903.c b/sound/soc/codecs/wm8903.c
index 2ed9f493d507..f7d726e3052c 100644
--- a/sound/soc/codecs/wm8903.c
+++ b/sound/soc/codecs/wm8903.c
@@ -1843,7 +1843,7 @@ static const struct gpio_chip wm8903_template_chip = {
 	.direction_input	= wm8903_gpio_direction_in,
 	.get			= wm8903_gpio_get,
 	.direction_output	= wm8903_gpio_direction_out,
-	.set_rv			= wm8903_gpio_set,
+	.set			= wm8903_gpio_set,
 	.can_sleep		= 1,
 };
 
diff --git a/sound/soc/codecs/wm8962.c b/sound/soc/codecs/wm8962.c
index d69aa8b15629..7bf6b88c056c 100644
--- a/sound/soc/codecs/wm8962.c
+++ b/sound/soc/codecs/wm8962.c
@@ -3442,7 +3442,7 @@ static const struct gpio_chip wm8962_template_chip = {
 	.owner			= THIS_MODULE,
 	.request		= wm8962_gpio_request,
 	.direction_output	= wm8962_gpio_direction_out,
-	.set_rv			= wm8962_gpio_set,
+	.set			= wm8962_gpio_set,
 	.can_sleep		= 1,
 };
 
diff --git a/sound/soc/codecs/wm8996.c b/sound/soc/codecs/wm8996.c
index e364d0da9044..459b39998307 100644
--- a/sound/soc/codecs/wm8996.c
+++ b/sound/soc/codecs/wm8996.c
@@ -2186,7 +2186,7 @@ static const struct gpio_chip wm8996_template_chip = {
 	.label			= "wm8996",
 	.owner			= THIS_MODULE,
 	.direction_output	= wm8996_gpio_direction_out,
-	.set_rv			= wm8996_gpio_set,
+	.set			= wm8996_gpio_set,
 	.direction_input	= wm8996_gpio_direction_in,
 	.get			= wm8996_gpio_get,
 	.can_sleep		= 1,
diff --git a/sound/soc/codecs/zl38060.c b/sound/soc/codecs/zl38060.c
index 180d45a349ac..7de4014e626d 100644
--- a/sound/soc/codecs/zl38060.c
+++ b/sound/soc/codecs/zl38060.c
@@ -440,7 +440,7 @@ static const struct gpio_chip template_chip = {
 	.direction_input = chip_direction_input,
 	.direction_output = chip_direction_output,
 	.get = chip_gpio_get,
-	.set_rv = chip_gpio_set,
+	.set = chip_gpio_set,
 
 	.can_sleep = true,
 };
diff --git a/sound/soc/soc-ac97.c b/sound/soc/soc-ac97.c
index 29790807d785..37486d6a438e 100644
--- a/sound/soc/soc-ac97.c
+++ b/sound/soc/soc-ac97.c
@@ -125,7 +125,7 @@ static const struct gpio_chip snd_soc_ac97_gpio_chip = {
 	.direction_input	= snd_soc_ac97_gpio_direction_in,
 	.get			= snd_soc_ac97_gpio_get,
 	.direction_output	= snd_soc_ac97_gpio_direction_out,
-	.set_rv			= snd_soc_ac97_gpio_set,
+	.set			= snd_soc_ac97_gpio_set,
 	.can_sleep		= 1,
 };
 
diff --git a/sound/soc/ti/davinci-mcasp.c b/sound/soc/ti/davinci-mcasp.c
index caf1887cc9d1..621a9d5f9377 100644
--- a/sound/soc/ti/davinci-mcasp.c
+++ b/sound/soc/ti/davinci-mcasp.c
@@ -2218,7 +2218,7 @@ static const struct gpio_chip davinci_mcasp_template_chip = {
 	.request		= davinci_mcasp_gpio_request,
 	.free			= davinci_mcasp_gpio_free,
 	.direction_output	= davinci_mcasp_gpio_direction_out,
-	.set_rv			= davinci_mcasp_gpio_set,
+	.set			= davinci_mcasp_gpio_set,
 	.direction_input	= davinci_mcasp_gpio_direction_in,
 	.get			= davinci_mcasp_gpio_get,
 	.get_direction		= davinci_mcasp_gpio_get_direction,
-- 
cgit v1.2.3


From 42e6c6ce03fd3e41e39a0f93f9b1a1d9fa664338 Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Thu, 7 Aug 2025 11:24:12 +0800
Subject: lib/sbitmap: convert shallow_depth from one word to the whole sbitmap

Currently elevators will record internal 'async_depth' to throttle
asynchronous requests, and they both calculate shallow_dpeth based on
sb->shift, with the respect that sb->shift is the available tags in one
word.

However, sb->shift is not the availbale tags in the last word, see
__map_depth:

if (index == sb->map_nr - 1)
  return sb->depth - (index << sb->shift);

For consequence, if the last word is used, more tags can be get than
expected, for example, assume nr_requests=256 and there are four words,
in the worst case if user set nr_requests=32, then the first word is
the last word, and still use bits per word, which is 64, to calculate
async_depth is wrong.

One the ohter hand, due to cgroup qos, bfq can allow only one request
to be allocated, and set shallow_dpeth=1 will still allow the number
of words request to be allocated.

Fix this problems by using shallow_depth to the whole sbitmap instead
of per word, also change kyber, mq-deadline and bfq to follow this,
a new helper __map_depth_with_shallow() is introduced to calculate
available bits in each word.

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Link: https://lore.kernel.org/r/20250807032413.1469456-2-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 block/bfq-iosched.c     | 35 ++++++++++++++-----------------
 block/bfq-iosched.h     |  3 +--
 block/kyber-iosched.c   |  9 ++------
 block/mq-deadline.c     | 16 +-------------
 include/linux/sbitmap.h |  6 +++---
 lib/sbitmap.c           | 56 +++++++++++++++++++++++++------------------------
 6 files changed, 52 insertions(+), 73 deletions(-)

(limited to 'include/linux')

diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
index aca9886c9ee3..3bf76902f07f 100644
--- a/block/bfq-iosched.c
+++ b/block/bfq-iosched.c
@@ -694,17 +694,13 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 {
 	struct bfq_data *bfqd = data->q->elevator->elevator_data;
 	struct bfq_io_cq *bic = bfq_bic_lookup(data->q);
-	int depth;
-	unsigned limit = data->q->nr_requests;
-	unsigned int act_idx;
+	unsigned int limit, act_idx;
 
 	/* Sync reads have full depth available */
-	if (op_is_sync(opf) && !op_is_write(opf)) {
-		depth = 0;
-	} else {
-		depth = bfqd->word_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)];
-		limit = (limit * depth) >> bfqd->full_depth_shift;
-	}
+	if (op_is_sync(opf) && !op_is_write(opf))
+		limit = data->q->nr_requests;
+	else
+		limit = bfqd->async_depths[!!bfqd->wr_busy_queues][op_is_sync(opf)];
 
 	for (act_idx = 0; bic && act_idx < bfqd->num_actuators; act_idx++) {
 		/* Fast path to check if bfqq is already allocated. */
@@ -718,14 +714,16 @@ static void bfq_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 		 * available requests and thus starve other entities.
 		 */
 		if (bfqq_request_over_limit(bfqd, bic, opf, act_idx, limit)) {
-			depth = 1;
+			limit = 1;
 			break;
 		}
 	}
+
 	bfq_log(bfqd, "[%s] wr_busy %d sync %d depth %u",
-		__func__, bfqd->wr_busy_queues, op_is_sync(opf), depth);
-	if (depth)
-		data->shallow_depth = depth;
+		__func__, bfqd->wr_busy_queues, op_is_sync(opf), limit);
+
+	if (limit < data->q->nr_requests)
+		data->shallow_depth = limit;
 }
 
 static struct bfq_queue *
@@ -7114,9 +7112,8 @@ void bfq_put_async_queues(struct bfq_data *bfqd, struct bfq_group *bfqg)
  */
 static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
 {
-	unsigned int depth = 1U << bt->sb.shift;
+	unsigned int nr_requests = bfqd->queue->nr_requests;
 
-	bfqd->full_depth_shift = bt->sb.shift;
 	/*
 	 * In-word depths if no bfq_queue is being weight-raised:
 	 * leaving 25% of tags only for sync reads.
@@ -7128,13 +7125,13 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
 	 * limit 'something'.
 	 */
 	/* no more than 50% of tags for async I/O */
-	bfqd->word_depths[0][0] = max(depth >> 1, 1U);
+	bfqd->async_depths[0][0] = max(nr_requests >> 1, 1U);
 	/*
 	 * no more than 75% of tags for sync writes (25% extra tags
 	 * w.r.t. async I/O, to prevent async I/O from starving sync
 	 * writes)
 	 */
-	bfqd->word_depths[0][1] = max((depth * 3) >> 2, 1U);
+	bfqd->async_depths[0][1] = max((nr_requests * 3) >> 2, 1U);
 
 	/*
 	 * In-word depths in case some bfq_queue is being weight-
@@ -7144,9 +7141,9 @@ static void bfq_update_depths(struct bfq_data *bfqd, struct sbitmap_queue *bt)
 	 * shortage.
 	 */
 	/* no more than ~18% of tags for async I/O */
-	bfqd->word_depths[1][0] = max((depth * 3) >> 4, 1U);
+	bfqd->async_depths[1][0] = max((nr_requests * 3) >> 4, 1U);
 	/* no more than ~37% of tags for sync writes (~20% extra tags) */
-	bfqd->word_depths[1][1] = max((depth * 6) >> 4, 1U);
+	bfqd->async_depths[1][1] = max((nr_requests * 6) >> 4, 1U);
 }
 
 static void bfq_depth_updated(struct blk_mq_hw_ctx *hctx)
diff --git a/block/bfq-iosched.h b/block/bfq-iosched.h
index 0b4704932d72..34a498e6b2a5 100644
--- a/block/bfq-iosched.h
+++ b/block/bfq-iosched.h
@@ -813,8 +813,7 @@ struct bfq_data {
 	 * Depth limits used in bfq_limit_depth (see comments on the
 	 * function)
 	 */
-	unsigned int word_depths[2][2];
-	unsigned int full_depth_shift;
+	unsigned int async_depths[2][2];
 
 	/*
 	 * Number of independent actuators. This is equal to 1 in
diff --git a/block/kyber-iosched.c b/block/kyber-iosched.c
index 7b6832cb3a8d..70cbc7b2deb4 100644
--- a/block/kyber-iosched.c
+++ b/block/kyber-iosched.c
@@ -157,10 +157,7 @@ struct kyber_queue_data {
 	 */
 	struct sbitmap_queue domain_tokens[KYBER_NUM_DOMAINS];
 
-	/*
-	 * Async request percentage, converted to per-word depth for
-	 * sbitmap_get_shallow().
-	 */
+	/* Number of allowed async requests. */
 	unsigned int async_depth;
 
 	struct kyber_cpu_latency __percpu *cpu_latency;
@@ -447,10 +444,8 @@ static void kyber_depth_updated(struct blk_mq_hw_ctx *hctx)
 {
 	struct kyber_queue_data *kqd = hctx->queue->elevator->elevator_data;
 	struct blk_mq_tags *tags = hctx->sched_tags;
-	unsigned int shift = tags->bitmap_tags.sb.shift;
-
-	kqd->async_depth = (1U << shift) * KYBER_ASYNC_PERCENT / 100U;
 
+	kqd->async_depth = hctx->queue->nr_requests * KYBER_ASYNC_PERCENT / 100U;
 	sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, kqd->async_depth);
 }
 
diff --git a/block/mq-deadline.c b/block/mq-deadline.c
index 7b6caf30e00a..b9b7cdf1d3c9 100644
--- a/block/mq-deadline.c
+++ b/block/mq-deadline.c
@@ -487,20 +487,6 @@ unlock:
 	return rq;
 }
 
-/*
- * 'depth' is a number in the range 1..INT_MAX representing a number of
- * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since
- * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow().
- * Values larger than q->nr_requests have the same effect as q->nr_requests.
- */
-static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth)
-{
-	struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags;
-	const unsigned int nrr = hctx->queue->nr_requests;
-
-	return ((qdepth << bt->sb.shift) + nrr - 1) / nrr;
-}
-
 /*
  * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
  * function is used by __blk_mq_get_tag().
@@ -517,7 +503,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
 	 * Throttle asynchronous requests and writes such that these requests
 	 * do not block the allocation of synchronous requests.
 	 */
-	data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth);
+	data->shallow_depth = dd->async_depth;
 }
 
 /* Called by blk_mq_update_nr_requests(). */
diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 189140bf11fc..4adf4b364fcd 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -213,12 +213,12 @@ int sbitmap_get(struct sbitmap *sb);
  * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
  * limiting the depth used from each word.
  * @sb: Bitmap to allocate from.
- * @shallow_depth: The maximum number of bits to allocate from a single word.
+ * @shallow_depth: The maximum number of bits to allocate from the bitmap.
  *
  * This rather specific operation allows for having multiple users with
  * different allocation limits. E.g., there can be a high-priority class that
  * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
- * with a @shallow_depth of (1 << (@sb->shift - 1)). Then, the low-priority
+ * with a @shallow_depth of (sb->depth >> 1). Then, the low-priority
  * class can only allocate half of the total bits in the bitmap, preventing it
  * from starving out the high-priority class.
  *
@@ -478,7 +478,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
  * sbitmap_queue, limiting the depth used from each word, with preemption
  * already disabled.
  * @sbq: Bitmap queue to allocate from.
- * @shallow_depth: The maximum number of bits to allocate from a single word.
+ * @shallow_depth: The maximum number of bits to allocate from the queue.
  * See sbitmap_get_shallow().
  *
  * If you call this, make sure to call sbitmap_queue_min_shallow_depth() after
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index d3412984170c..c07e3cd82e29 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -208,8 +208,28 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map,
 	return nr;
 }
 
+static unsigned int __map_depth_with_shallow(const struct sbitmap *sb,
+					     int index,
+					     unsigned int shallow_depth)
+{
+	u64 shallow_word_depth;
+	unsigned int word_depth, reminder;
+
+	word_depth = __map_depth(sb, index);
+	if (shallow_depth >= sb->depth)
+		return word_depth;
+
+	shallow_word_depth = word_depth * shallow_depth;
+	reminder = do_div(shallow_word_depth, sb->depth);
+
+	if (reminder >= (index + 1) * word_depth)
+		shallow_word_depth++;
+
+	return (unsigned int)shallow_word_depth;
+}
+
 static int sbitmap_find_bit(struct sbitmap *sb,
-			    unsigned int depth,
+			    unsigned int shallow_depth,
 			    unsigned int index,
 			    unsigned int alloc_hint,
 			    bool wrap)
@@ -218,12 +238,12 @@ static int sbitmap_find_bit(struct sbitmap *sb,
 	int nr = -1;
 
 	for (i = 0; i < sb->map_nr; i++) {
-		nr = sbitmap_find_bit_in_word(&sb->map[index],
-					      min_t(unsigned int,
-						    __map_depth(sb, index),
-						    depth),
-					      alloc_hint, wrap);
+		unsigned int depth = __map_depth_with_shallow(sb, index,
+							      shallow_depth);
 
+		if (depth)
+			nr = sbitmap_find_bit_in_word(&sb->map[index], depth,
+						      alloc_hint, wrap);
 		if (nr != -1) {
 			nr += index << sb->shift;
 			break;
@@ -406,27 +426,9 @@ EXPORT_SYMBOL_GPL(sbitmap_bitmap_show);
 static unsigned int sbq_calc_wake_batch(struct sbitmap_queue *sbq,
 					unsigned int depth)
 {
-	unsigned int wake_batch;
-	unsigned int shallow_depth;
-
-	/*
-	 * Each full word of the bitmap has bits_per_word bits, and there might
-	 * be a partial word. There are depth / bits_per_word full words and
-	 * depth % bits_per_word bits left over. In bitwise arithmetic:
-	 *
-	 * bits_per_word = 1 << shift
-	 * depth / bits_per_word = depth >> shift
-	 * depth % bits_per_word = depth & ((1 << shift) - 1)
-	 *
-	 * Each word can be limited to sbq->min_shallow_depth bits.
-	 */
-	shallow_depth = min(1U << sbq->sb.shift, sbq->min_shallow_depth);
-	depth = ((depth >> sbq->sb.shift) * shallow_depth +
-		 min(depth & ((1U << sbq->sb.shift) - 1), shallow_depth));
-	wake_batch = clamp_t(unsigned int, depth / SBQ_WAIT_QUEUES, 1,
-			     SBQ_WAKE_BATCH);
-
-	return wake_batch;
+	return clamp_t(unsigned int,
+		       min(depth, sbq->min_shallow_depth) / SBQ_WAIT_QUEUES,
+		       1, SBQ_WAKE_BATCH);
 }
 
 int sbitmap_queue_init_node(struct sbitmap_queue *sbq, unsigned int depth,
-- 
cgit v1.2.3


From 45fa9f97e65231a9fd4f9429489cb74c10ccd0fd Mon Sep 17 00:00:00 2001
From: Yu Kuai <yukuai3@huawei.com>
Date: Thu, 7 Aug 2025 11:24:13 +0800
Subject: lib/sbitmap: make sbitmap_get_shallow() internal

Because it's only used in sbitmap.c

Signed-off-by: Yu Kuai <yukuai3@huawei.com>
Reviewed-by: Damien Le Moal <dlemoal@kernel.org>
Reviewed-by: Jan Kara <jack@suse.cz>
Reviewed-by: Bart Van Assche <bvanassche@acm.org>
Link: https://lore.kernel.org/r/20250807032413.1469456-3-yukuai1@huaweicloud.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
---
 include/linux/sbitmap.h | 17 -----------------
 lib/sbitmap.c           | 18 ++++++++++++++++--
 2 files changed, 16 insertions(+), 19 deletions(-)

(limited to 'include/linux')

diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
index 4adf4b364fcd..ffb9907c7070 100644
--- a/include/linux/sbitmap.h
+++ b/include/linux/sbitmap.h
@@ -209,23 +209,6 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth);
  */
 int sbitmap_get(struct sbitmap *sb);
 
-/**
- * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
- * limiting the depth used from each word.
- * @sb: Bitmap to allocate from.
- * @shallow_depth: The maximum number of bits to allocate from the bitmap.
- *
- * This rather specific operation allows for having multiple users with
- * different allocation limits. E.g., there can be a high-priority class that
- * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
- * with a @shallow_depth of (sb->depth >> 1). Then, the low-priority
- * class can only allocate half of the total bits in the bitmap, preventing it
- * from starving out the high-priority class.
- *
- * Return: Non-negative allocated bit number if successful, -1 otherwise.
- */
-int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth);
-
 /**
  * sbitmap_any_bit_set() - Check for a set bit in a &struct sbitmap.
  * @sb: Bitmap to check.
diff --git a/lib/sbitmap.c b/lib/sbitmap.c
index c07e3cd82e29..4d188d05db15 100644
--- a/lib/sbitmap.c
+++ b/lib/sbitmap.c
@@ -307,7 +307,22 @@ static int __sbitmap_get_shallow(struct sbitmap *sb,
 	return sbitmap_find_bit(sb, shallow_depth, index, alloc_hint, true);
 }
 
-int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth)
+/**
+ * sbitmap_get_shallow() - Try to allocate a free bit from a &struct sbitmap,
+ * limiting the depth used from each word.
+ * @sb: Bitmap to allocate from.
+ * @shallow_depth: The maximum number of bits to allocate from the bitmap.
+ *
+ * This rather specific operation allows for having multiple users with
+ * different allocation limits. E.g., there can be a high-priority class that
+ * uses sbitmap_get() and a low-priority class that uses sbitmap_get_shallow()
+ * with a @shallow_depth of (sb->depth >> 1). Then, the low-priority
+ * class can only allocate half of the total bits in the bitmap, preventing it
+ * from starving out the high-priority class.
+ *
+ * Return: Non-negative allocated bit number if successful, -1 otherwise.
+ */
+static int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth)
 {
 	int nr;
 	unsigned int hint, depth;
@@ -322,7 +337,6 @@ int sbitmap_get_shallow(struct sbitmap *sb, unsigned long shallow_depth)
 
 	return nr;
 }
-EXPORT_SYMBOL_GPL(sbitmap_get_shallow);
 
 bool sbitmap_any_bit_set(const struct sbitmap *sb)
 {
-- 
cgit v1.2.3