[PATCH v2 1/5] platform profile: Separate handler locking from sysfs lifetime

[Daniel Lezcano <daniel.lezcano@oss.qualcomm.com>]

Registration and removal currently hold profile_lock across
device_unregister() and sysfs_update_group(). These operations can remove
sysfs attributes and wait for their active callbacks to finish. The
profile read and write callbacks acquire profile_lock themselves, so a
concurrent access can deadlock:

  Removal/update path             Active sysfs callback
  -------------------             ---------------------
  acquire profile_lock            hold kernfs active reference
  remove a sysfs attribute         wait for profile_lock
  wait for its active references

The removal path cannot finish until the callback returns, and the
callback cannot return until the removal path releases profile_lock.
This applies both to per-provider device teardown and to updates of the
legacy aggregate attribute group.

Commit 041142d7d252 ("ACPI: platform-profile: Fix possible deadlock in
platform_profile_remove()") previously fixed this lock ordering by moving
sysfs_remove_group() outside profile_lock. Commit 55b1e68134bf ("ACPI:
platform_profile: Use guard(mutex) for register/unregister") reintroduced
the issue by extending the mutex guard over sysfs_remove_group(). Later,
commit 77be5cacb2c2 ("ACPI: platform_profile: Create class for ACPI
platform profile") replaced that teardown with device_unregister() and
sysfs_update_group(), still under the same mutex, extending the problem
to class-device teardown and aggregate attribute updates.

Simply dropping profile_lock around these operations is insufficient.
Aggregate operations currently discover providers through the class
device list. A provider being unregistered could therefore still be
selected for an aggregate read, write or cycle while its sysfs files are
being torn down. Concurrent registrations and removals would also race
when updating aggregate attribute visibility.

Introduce profile_registration_lock to serialize registration, removal
and aggregate sysfs updates. Sysfs callbacks never acquire this mutex.
Retain profile_lock for profile operations and use it to protect an
explicit list of handlers participating in the aggregate interface.

Add a handler to that list only after device_register() succeeds. On
removal, unlink it under profile_lock before calling device_unregister().
Acquiring profile_lock first waits for any aggregate operation already
using the handler to complete; unlinking prevents later aggregate
operations from finding it. Release profile_lock before draining sysfs
callbacks, allowing active per-provider callbacks to complete before the
device is released. Apply the same unlink-before-unregister ordering to
registration error cleanup.

Walk this list for aggregate reads, writes and profile cycling, and use
its emptiness to determine aggregate attribute visibility. The class
devices remain the per-provider userspace interface.

There can now be an interval between removing the last handler from the
list and removing the aggregate attributes. Explicitly reject choices
reads and writes during that interval: the intersection bitmap starts
with every bit set, so an empty traversal must not advertise all profiles
or report a successful write without updating a provider.

This separates aggregate membership from class device teardown while
preserving the existing class and ACPI sysfs interfaces.

Fixes: 55b1e68134bf ("ACPI: platform_profile: Use guard(mutex) for register/unregister")
Assisted-by: OpenCode:gpt-6.1-sol
Signed-off-by: Daniel Lezcano <daniel.lezcano@oss.qualcomm.com>
---
 drivers/acpi/platform_profile.c | 75 ++++++++++++++++++---------------
 1 file changed, 42 insertions(+), 33 deletions(-)

diff --git a/drivers/acpi/platform_profile.c b/drivers/acpi/platform_profile.c
index 79d2e92e5c28..f98ce4cda02c 100644
--- a/drivers/acpi/platform_profile.c
+++ b/drivers/acpi/platform_profile.c
@@ -8,6 +8,7 @@
 #include <linux/bits.h>
 #include <linux/cleanup.h>
 #include <linux/init.h>
+#include <linux/list.h>
 #include <linux/mutex.h>
 #include <linux/platform_profile.h>
 #include <linux/sysfs.h>
@@ -15,8 +16,12 @@
 #define to_pprof_handler(d)	(container_of(d, struct platform_profile_handler, dev))
 
 static DEFINE_MUTEX(profile_lock);
+/* Serialize registration and sysfs updates without blocking sysfs callbacks. */
+static DEFINE_MUTEX(profile_registration_lock);
+static LIST_HEAD(profile_handlers);
 
 struct platform_profile_handler {
+	struct list_head node;
 	const char *name;
 	struct device dev;
 	int minor;
@@ -44,6 +49,22 @@ static_assert(ARRAY_SIZE(profile_names) == PLATFORM_PROFILE_LAST);
 
 static DEFINE_IDA(platform_profile_ida);
 
+static int profile_walk_handlers(void *data,
+				 int (*fn)(struct device *dev, void *data))
+{
+	struct platform_profile_handler *handler;
+	int ret;
+
+	lockdep_assert_held(&profile_lock);
+	list_for_each_entry(handler, &profile_handlers, node) {
+		ret = fn(&handler->dev, data);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
 /**
  * _commmon_choices_show - Show the available profile choices
  * @choices: The available profile choices
@@ -306,20 +327,18 @@ static ssize_t platform_profile_choices_show(struct kobject *kobj,
 	int err;
 
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
-		err = class_for_each_device(&platform_profile_class, NULL,
-					    &data, _aggregate_choices);
+		err = profile_walk_handlers(&data, _aggregate_choices);
 		if (err)
 			return err;
 		if (data.count == 1) {
-			err = class_for_each_device(&platform_profile_class, NULL,
-						    &data, _remove_hidden_choices);
+			err = profile_walk_handlers(&data, _remove_hidden_choices);
 			if (err)
 				return err;
 		}
 	}
 
 	/* no profile handler registered any more */
-	if (bitmap_empty(data.aggregate, PLATFORM_PROFILE_LAST))
+	if (!data.count || bitmap_empty(data.aggregate, PLATFORM_PROFILE_LAST))
 		return -EINVAL;
 
 	return _commmon_choices_show(data.aggregate, buf);
@@ -384,8 +403,7 @@ static ssize_t platform_profile_show(struct kobject *kobj,
 	int err;
 
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
-		err = class_for_each_device(&platform_profile_class, NULL,
-					    &profile, _aggregate_profiles);
+		err = profile_walk_handlers(&profile, _aggregate_profiles);
 		if (err)
 			return err;
 	}
@@ -423,15 +441,13 @@ static ssize_t platform_profile_store(struct kobject *kobj,
 		return -EINVAL;
 
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
-		ret = class_for_each_device(&platform_profile_class, NULL,
-					    &data, _aggregate_choices);
+		ret = profile_walk_handlers(&data, _aggregate_choices);
 		if (ret)
 			return ret;
-		if (!test_bit(i, data.aggregate))
+		if (!data.count || !test_bit(i, data.aggregate))
 			return -EOPNOTSUPP;
 
-		ret = class_for_each_device(&platform_profile_class, NULL, &i,
-					    _store_and_notify);
+		ret = profile_walk_handlers(&i, _store_and_notify);
 		if (ret)
 			return ret;
 	}
@@ -450,22 +466,11 @@ static struct attribute *platform_profile_attrs[] = {
 	NULL
 };
 
-static int profile_class_registered(struct device *dev, const void *data)
-{
-	return 1;
-}
-
 static umode_t profile_class_is_visible(struct kobject *kobj, struct attribute *attr, int idx)
 {
-	struct device *dev;
-
-	dev = class_find_device(&platform_profile_class, NULL, NULL, profile_class_registered);
-	if (!dev)
-		return 0;
-
-	put_device(dev);
+	guard(mutex)(&profile_lock);
 
-	return attr->mode;
+	return list_empty(&profile_handlers) ? 0 : attr->mode;
 }
 
 static const struct attribute_group platform_profile_group = {
@@ -502,8 +507,7 @@ int platform_profile_cycle(void)
 	int err;
 
 	scoped_cond_guard(mutex_intr, return -ERESTARTSYS, &profile_lock) {
-		err = class_for_each_device(&platform_profile_class, NULL,
-					    &profile, _aggregate_profiles);
+		err = profile_walk_handlers(&profile, _aggregate_profiles);
 		if (err)
 			return err;
 
@@ -512,8 +516,7 @@ int platform_profile_cycle(void)
 		    profile == PLATFORM_PROFILE_LAST)
 			return -EINVAL;
 
-		err = class_for_each_device(&platform_profile_class, NULL,
-					    &data, _aggregate_choices);
+		err = profile_walk_handlers(&data, _aggregate_choices);
 		if (err)
 			return err;
 
@@ -525,8 +528,7 @@ int platform_profile_cycle(void)
 					  PLATFORM_PROFILE_LAST,
 					  profile + 1);
 
-		err = class_for_each_device(&platform_profile_class, NULL, &next,
-					    _store_and_notify);
+		err = profile_walk_handlers(&next, _store_and_notify);
 
 		if (err)
 			return err;
@@ -583,7 +585,7 @@ struct device *platform_profile_register(struct device *dev, const char *name,
 		}
 	}
 
-	guard(mutex)(&profile_lock);
+	guard(mutex)(&profile_registration_lock);
 
 	/* create class interface for individual handler */
 	minor = ida_alloc(&platform_profile_ida, GFP_KERNEL);
@@ -604,6 +606,8 @@ struct device *platform_profile_register(struct device *dev, const char *name,
 		put_device(ppdev);
 		goto cleanup_ida;
 	}
+	scoped_guard(mutex, &profile_lock)
+		list_add_tail(&to_pprof_handler(ppdev)->node, &profile_handlers);
 
 	sysfs_notify(acpi_kobj, NULL, "platform_profile");
 
@@ -614,6 +618,8 @@ struct device *platform_profile_register(struct device *dev, const char *name,
 	return ppdev;
 
 cleanup_cur:
+	scoped_guard(mutex, &profile_lock)
+		list_del(&to_pprof_handler(ppdev)->node);
 	device_unregister(ppdev);
 
 cleanup_ida:
@@ -636,7 +642,10 @@ void platform_profile_remove(struct device *dev)
 
 	pprof = to_pprof_handler(dev);
 
-	guard(mutex)(&profile_lock);
+	guard(mutex)(&profile_registration_lock);
+
+	scoped_guard(mutex, &profile_lock)
+		list_del(&pprof->node);
 
 	ida_free(&platform_profile_ida, pprof->minor);
 	device_unregister(&pprof->dev);
-- 
2.43.0