Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 446 insertions, 0 deletions

diff --git a/drivers/thermal/testing/zone.c b/drivers/thermal/testing/zone.c
new file mode 100644
index 000000000..6db26276d
--- /dev/null
+++ b/drivers/thermal/testing/zone.c
@@ -0,0 +1,446 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright 2024, Intel Corporation
+ *
+ * Author: Rafael J. Wysocki <rafael.j.wysocki@intel.com>
+ *
+ * Thermal zone tempalates handling for thermal core testing.
+ */
+
+#define pr_fmt(fmt) "thermal-testing: " fmt
+
+#include <linux/debugfs.h>
+#include <linux/idr.h>
+#include <linux/list.h>
+#include <linux/thermal.h>
+
+#include "thermal_testing.h"
+
+#define TT_MAX_FILE_NAME_LENGTH		16
+
+/**
+ * struct tt_thermal_zone - Testing thermal zone template
+ *
+ * Represents a template of a thermal zone that can be used for registering
+ * a test thermal zone with the thermal core.
+ *
+ * @list_node: Node in the list of all testing thermal zone templates.
+ * @trips: List of trip point templates for this thermal zone template.
+ * @d_tt_zone: Directory in debugfs representing this template.
+ * @tz: Test thermal zone based on this template, if present.
+ * @lock: Mutex for synchronizing changes of this template.
+ * @ida: IDA for trip point IDs.
+ * @id: The ID of this template for the debugfs interface.
+ * @temp: Temperature value.
+ * @tz_temp: Current thermal zone temperature (after registration).
+ * @num_trips: Number of trip points in the @trips list.
+ * @refcount: Reference counter for usage and removal synchronization.
+ */
+struct tt_thermal_zone {
+	struct list_head list_node;
+	struct list_head trips;
+	struct dentry *d_tt_zone;
+	struct thermal_zone_device *tz;
+	struct mutex lock;
+	struct ida ida;
+	int id;
+	int temp;
+	int tz_temp;
+	unsigned int num_trips;
+	unsigned int refcount;
+};
+
+DEFINE_GUARD(tt_zone, struct tt_thermal_zone *, mutex_lock(&_T->lock), mutex_unlock(&_T->lock))
+
+/**
+ * struct tt_trip - Testing trip point template
+ *
+ * Represents a template of a trip point to be used for populating a trip point
+ * during the registration of a thermal zone based on a given zone template.
+ *
+ * @list_node: Node in the list of all trip templates in the zone template.
+ * @trip: Trip point data to use for thernal zone registration.
+ * @id: The ID of this trip template for the debugfs interface.
+ */
+struct tt_trip {
+	struct list_head list_node;
+	struct thermal_trip trip;
+	int id;
+};
+
+/*
+ * It is both questionable and potentially problematic from the sychnronization
+ * perspective to attempt to manipulate debugfs from within a debugfs file
+ * "write" operation, so auxiliary work items are used for that.  The majority
+ * of zone-related command functions have a part that runs from a workqueue and
+ * make changes in debugs, among other things.
+ */
+struct tt_work {
+	struct work_struct work;
+	struct tt_thermal_zone *tt_zone;
+	struct tt_trip *tt_trip;
+};
+
+static inline struct tt_work *tt_work_of_work(struct work_struct *work)
+{
+	return container_of(work, struct tt_work, work);
+}
+
+static LIST_HEAD(tt_thermal_zones);
+static DEFINE_IDA(tt_thermal_zones_ida);
+static DEFINE_MUTEX(tt_thermal_zones_lock);
+
+static int tt_int_get(void *data, u64 *val)
+{
+	*val = *(int *)data;
+	return 0;
+}
+static int tt_int_set(void *data, u64 val)
+{
+	if ((int)val < THERMAL_TEMP_INVALID)
+		return -EINVAL;
+
+	*(int *)data = val;
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(tt_int_attr, tt_int_get, tt_int_set, "%lld\n");
+DEFINE_DEBUGFS_ATTRIBUTE(tt_unsigned_int_attr, tt_int_get, tt_int_set, "%llu\n");
+
+static int tt_zone_tz_temp_get(void *data, u64 *val)
+{
+	struct tt_thermal_zone *tt_zone = data;
+
+	guard(tt_zone)(tt_zone);
+
+	if (!tt_zone->tz)
+		return -EBUSY;
+
+	*val = tt_zone->tz_temp;
+
+	return 0;
+}
+static int tt_zone_tz_temp_set(void *data, u64 val)
+{
+	struct tt_thermal_zone *tt_zone = data;
+
+	guard(tt_zone)(tt_zone);
+
+	if (!tt_zone->tz)
+		return -EBUSY;
+
+	WRITE_ONCE(tt_zone->tz_temp, val);
+	thermal_zone_device_update(tt_zone->tz, THERMAL_EVENT_TEMP_SAMPLE);
+
+	return 0;
+}
+DEFINE_DEBUGFS_ATTRIBUTE_SIGNED(tt_zone_tz_temp_attr, tt_zone_tz_temp_get,
+				tt_zone_tz_temp_set, "%lld\n");
+
+static void tt_zone_free_trips(struct tt_thermal_zone *tt_zone)
+{
+	struct tt_trip *tt_trip, *aux;
+
+	list_for_each_entry_safe(tt_trip, aux, &tt_zone->trips, list_node) {
+		list_del(&tt_trip->list_node);
+		ida_free(&tt_zone->ida, tt_trip->id);
+		kfree(tt_trip);
+	}
+}
+
+static void tt_zone_free(struct tt_thermal_zone *tt_zone)
+{
+	tt_zone_free_trips(tt_zone);
+	ida_free(&tt_thermal_zones_ida, tt_zone->id);
+	ida_destroy(&tt_zone->ida);
+	kfree(tt_zone);
+}
+
+static void tt_add_tz_work_fn(struct work_struct *work)
+{
+	struct tt_work *tt_work = tt_work_of_work(work);
+	struct tt_thermal_zone *tt_zone = tt_work->tt_zone;
+	char f_name[TT_MAX_FILE_NAME_LENGTH];
+
+	kfree(tt_work);
+
+	snprintf(f_name, TT_MAX_FILE_NAME_LENGTH, "tz%d", tt_zone->id);
+	tt_zone->d_tt_zone = debugfs_create_dir(f_name, d_testing);
+	if (IS_ERR(tt_zone->d_tt_zone)) {
+		tt_zone_free(tt_zone);
+		return;
+	}
+
+	debugfs_create_file_unsafe("temp", 0600, tt_zone->d_tt_zone, tt_zone,
+				   &tt_zone_tz_temp_attr);
+
+	debugfs_create_file_unsafe("init_temp", 0600, tt_zone->d_tt_zone,
+				   &tt_zone->temp, &tt_int_attr);
+
+	guard(mutex)(&tt_thermal_zones_lock);
+
+	list_add_tail(&tt_zone->list_node, &tt_thermal_zones);
+}
+
+int tt_add_tz(void)
+{
+	int ret;
+
+	struct tt_thermal_zone *tt_zone __free(kfree) = kzalloc_obj(*tt_zone);
+	if (!tt_zone)
+		return -ENOMEM;
+
+	struct tt_work *tt_work __free(kfree) = kzalloc_obj(*tt_work);
+	if (!tt_work)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&tt_zone->trips);
+	mutex_init(&tt_zone->lock);
+	ida_init(&tt_zone->ida);
+	tt_zone->temp = THERMAL_TEMP_INVALID;
+
+	ret = ida_alloc(&tt_thermal_zones_ida, GFP_KERNEL);
+	if (ret < 0)
+		return ret;
+
+	tt_zone->id = ret;
+
+	INIT_WORK(&tt_work->work, tt_add_tz_work_fn);
+	tt_work->tt_zone = no_free_ptr(tt_zone);
+	tt_queue_work(&(no_free_ptr(tt_work)->work));
+
+	return 0;
+}
+
+static void tt_del_tz_work_fn(struct work_struct *work)
+{
+	struct tt_work *tt_work = tt_work_of_work(work);
+	struct tt_thermal_zone *tt_zone = tt_work->tt_zone;
+
+	kfree(tt_work);
+
+	debugfs_remove(tt_zone->d_tt_zone);
+	tt_zone_free(tt_zone);
+}
+
+static void tt_zone_unregister_tz(struct tt_thermal_zone *tt_zone)
+{
+	guard(tt_zone)(tt_zone);
+
+	if (tt_zone->tz) {
+		thermal_zone_device_unregister(tt_zone->tz);
+		tt_zone->tz = NULL;
+	}
+}
+
+int tt_del_tz(const char *arg)
+{
+	struct tt_thermal_zone *tt_zone, *aux;
+	int ret;
+	int id;
+
+	ret = kstrtoint(arg, 10, &id);
+	if (ret < 0)
+		return ret;
+
+	struct tt_work *tt_work __free(kfree) = kzalloc_obj(*tt_work);
+	if (!tt_work)
+		return -ENOMEM;
+
+	guard(mutex)(&tt_thermal_zones_lock);
+
+	ret = -EINVAL;
+	list_for_each_entry_safe(tt_zone, aux, &tt_thermal_zones, list_node) {
+		if (tt_zone->id == id) {
+			if (tt_zone->refcount) {
+				ret = -EBUSY;
+			} else {
+				list_del(&tt_zone->list_node);
+				ret = 0;
+			}
+			break;
+		}
+	}
+
+	if (ret)
+		return ret;
+
+	tt_zone_unregister_tz(tt_zone);
+
+	INIT_WORK(&tt_work->work, tt_del_tz_work_fn);
+	tt_work->tt_zone = tt_zone;
+	tt_queue_work(&(no_free_ptr(tt_work)->work));
+
+	return 0;
+}
+
+static struct tt_thermal_zone *tt_get_tt_zone(const char *arg)
+{
+	struct tt_thermal_zone *tt_zone;
+	int ret, id;
+
+	ret = kstrtoint(arg, 10, &id);
+	if (ret < 0)
+		return ERR_PTR(ret);
+
+	guard(mutex)(&tt_thermal_zones_lock);
+
+	list_for_each_entry(tt_zone, &tt_thermal_zones, list_node) {
+		if (tt_zone->id == id) {
+			tt_zone->refcount++;
+			return tt_zone;
+		}
+	}
+
+	return ERR_PTR(-EINVAL);
+}
+
+static void tt_put_tt_zone(struct tt_thermal_zone *tt_zone)
+{
+	guard(mutex)(&tt_thermal_zones_lock);
+
+	tt_zone->refcount--;
+}
+
+DEFINE_FREE(put_tt_zone, struct tt_thermal_zone *,
+	    if (!IS_ERR_OR_NULL(_T)) tt_put_tt_zone(_T))
+
+static void tt_zone_add_trip_work_fn(struct work_struct *work)
+{
+	struct tt_work *tt_work = tt_work_of_work(work);
+	struct tt_thermal_zone *tt_zone = tt_work->tt_zone;
+	struct tt_trip *tt_trip = tt_work->tt_trip;
+	char d_name[TT_MAX_FILE_NAME_LENGTH];
+
+	kfree(tt_work);
+
+	snprintf(d_name, TT_MAX_FILE_NAME_LENGTH, "trip_%d_temp", tt_trip->id);
+	debugfs_create_file_unsafe(d_name, 0600, tt_zone->d_tt_zone,
+				   &tt_trip->trip.temperature, &tt_int_attr);
+
+	snprintf(d_name, TT_MAX_FILE_NAME_LENGTH, "trip_%d_hyst", tt_trip->id);
+	debugfs_create_file_unsafe(d_name, 0600, tt_zone->d_tt_zone,
+				   &tt_trip->trip.hysteresis, &tt_unsigned_int_attr);
+
+	tt_put_tt_zone(tt_zone);
+}
+
+int tt_zone_add_trip(const char *arg)
+{
+	int id;
+
+	struct tt_work *tt_work __free(kfree) = kzalloc_obj(*tt_work);
+	if (!tt_work)
+		return -ENOMEM;
+
+	struct tt_trip *tt_trip __free(kfree) = kzalloc_obj(*tt_trip);
+	if (!tt_trip)
+		return -ENOMEM;
+
+	struct tt_thermal_zone *tt_zone __free(put_tt_zone) = tt_get_tt_zone(arg);
+	if (IS_ERR(tt_zone))
+		return PTR_ERR(tt_zone);
+
+	id = ida_alloc(&tt_zone->ida, GFP_KERNEL);
+	if (id < 0)
+		return id;
+
+	tt_trip->trip.type = THERMAL_TRIP_ACTIVE;
+	tt_trip->trip.temperature = THERMAL_TEMP_INVALID;
+	tt_trip->trip.flags = THERMAL_TRIP_FLAG_RW;
+	tt_trip->id = id;
+
+	guard(tt_zone)(tt_zone);
+
+	list_add_tail(&tt_trip->list_node, &tt_zone->trips);
+	tt_zone->num_trips++;
+
+	INIT_WORK(&tt_work->work, tt_zone_add_trip_work_fn);
+	tt_work->tt_zone = no_free_ptr(tt_zone);
+	tt_work->tt_trip = no_free_ptr(tt_trip);
+	tt_queue_work(&(no_free_ptr(tt_work)->work));
+
+	return 0;
+}
+
+static int tt_zone_get_temp(struct thermal_zone_device *tz, int *temp)
+{
+	struct tt_thermal_zone *tt_zone = thermal_zone_device_priv(tz);
+
+	*temp = READ_ONCE(tt_zone->tz_temp);
+
+	if (*temp < THERMAL_TEMP_INVALID)
+		return -ENODATA;
+
+	return 0;
+}
+
+static const struct thermal_zone_device_ops tt_zone_ops = {
+	.get_temp = tt_zone_get_temp,
+};
+
+static int tt_zone_register_tz(struct tt_thermal_zone *tt_zone)
+{
+	struct thermal_zone_device *tz;
+	struct tt_trip *tt_trip;
+	int i;
+
+	guard(tt_zone)(tt_zone);
+
+	if (tt_zone->tz)
+		return -EINVAL;
+
+	struct thermal_trip *trips __free(kfree) = kzalloc_objs(*trips,
+								tt_zone->num_trips);
+	if (!trips)
+		return -ENOMEM;
+
+	i = 0;
+	list_for_each_entry(tt_trip, &tt_zone->trips, list_node)
+		trips[i++] = tt_trip->trip;
+
+	tt_zone->tz_temp = tt_zone->temp;
+
+	tz = thermal_zone_device_register_with_trips("test_tz", trips, i, tt_zone,
+						     &tt_zone_ops, NULL, 0, 0);
+	if (IS_ERR(tz))
+		return PTR_ERR(tz);
+
+	tt_zone->tz = tz;
+
+	thermal_zone_device_enable(tz);
+
+	return 0;
+}
+
+int tt_zone_reg(const char *arg)
+{
+	struct tt_thermal_zone *tt_zone __free(put_tt_zone) = tt_get_tt_zone(arg);
+	if (IS_ERR(tt_zone))
+		return PTR_ERR(tt_zone);
+
+	return tt_zone_register_tz(tt_zone);
+}
+
+int tt_zone_unreg(const char *arg)
+{
+	struct tt_thermal_zone *tt_zone __free(put_tt_zone) = tt_get_tt_zone(arg);
+	if (IS_ERR(tt_zone))
+		return PTR_ERR(tt_zone);
+
+	tt_zone_unregister_tz(tt_zone);
+
+	return 0;
+}
+
+void tt_zone_cleanup(void)
+{
+	struct tt_thermal_zone *tt_zone, *aux;
+
+	list_for_each_entry_safe(tt_zone, aux, &tt_thermal_zones, list_node) {
+		tt_zone_unregister_tz(tt_zone);
+
+		list_del(&tt_zone->list_node);
+
+		tt_zone_free(tt_zone);
+	}
+}