diff mbox series

[01/21] drm/i915: Track all held rpm wakerefs

Message ID 20190110101152.15651-2-chris@chris-wilson.co.uk (mailing list archive)
State New, archived
Headers show
Series [01/21] drm/i915: Track all held rpm wakerefs | expand

Commit Message

Chris Wilson Jan. 10, 2019, 10:11 a.m. UTC
Everytime we take a wakeref, record the stack trace of where it was
taken; clearing the set if we ever drop back to no owners. For debugging
a rpm leak, we can look at all the current wakerefs and check if they
have a matching rpm_put.

v2: Use skip=0 for unwinding the stack as it appears our noinline
function doesn't appear on the stack (nor does save_stack_trace itself!)
v3: Allow rpm->debug_count to disappear between inspections and so
avoid calling krealloc(0) as that may return a ZERO_PTR not NULL! (Mika)
v4: Show who last acquire/released the runtime pm

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Jani Nikula <jani.nikula@intel.com>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Tested-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
---
 drivers/gpu/drm/i915/Kconfig.debug            |   3 +-
 drivers/gpu/drm/i915/i915_debugfs.c           |   6 +
 drivers/gpu/drm/i915/i915_drv.c               |   8 +-
 drivers/gpu/drm/i915/i915_drv.h               |  20 ++
 drivers/gpu/drm/i915/intel_drv.h              |  44 ++-
 drivers/gpu/drm/i915/intel_runtime_pm.c       | 315 ++++++++++++++++--
 .../gpu/drm/i915/selftests/mock_gem_device.c  |   8 +-
 7 files changed, 354 insertions(+), 50 deletions(-)
diff mbox series

Patch

diff --git a/drivers/gpu/drm/i915/Kconfig.debug b/drivers/gpu/drm/i915/Kconfig.debug
index 9e36ffb5eb7c..ad4d71161dda 100644
--- a/drivers/gpu/drm/i915/Kconfig.debug
+++ b/drivers/gpu/drm/i915/Kconfig.debug
@@ -21,11 +21,11 @@  config DRM_I915_DEBUG
         select DEBUG_FS
         select PREEMPT_COUNT
         select I2C_CHARDEV
+        select STACKDEPOT
         select DRM_DP_AUX_CHARDEV
         select X86_MSR # used by igt/pm_rpm
         select DRM_VGEM # used by igt/prime_vgem (dmabuf interop checks)
         select DRM_DEBUG_MM if DRM=y
-        select STACKDEPOT if DRM=y # for DRM_DEBUG_MM
 	select DRM_DEBUG_SELFTEST
 	select SW_SYNC # signaling validation framework (igt/syncobj*)
 	select DRM_I915_SW_FENCE_DEBUG_OBJECTS
@@ -173,6 +173,7 @@  config DRM_I915_DEBUG_RUNTIME_PM
 	bool "Enable extra state checking for runtime PM"
 	depends on DRM_I915
 	default n
+	select STACKDEPOT
 	help
 	  Choose this option to turn on extra state checking for the
 	  runtime PM functionality. This may introduce overhead during
diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index d460ef522d9c..56ec65ec5199 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -2702,6 +2702,12 @@  static int i915_runtime_pm_status(struct seq_file *m, void *unused)
 		   pci_power_name(pdev->current_state),
 		   pdev->current_state);
 
+	if (IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)) {
+		struct drm_printer p = drm_seq_file_printer(m);
+
+		print_intel_runtime_pm_wakeref(dev_priv, &p);
+	}
+
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_drv.c b/drivers/gpu/drm/i915/i915_drv.c
index 75652dc1e24c..5731f992cf44 100644
--- a/drivers/gpu/drm/i915/i915_drv.c
+++ b/drivers/gpu/drm/i915/i915_drv.c
@@ -905,6 +905,7 @@  static int i915_driver_init_early(struct drm_i915_private *dev_priv)
 	mutex_init(&dev_priv->pps_mutex);
 
 	i915_memcpy_init_early(dev_priv);
+	intel_runtime_pm_init_early(dev_priv);
 
 	ret = i915_workqueues_init(dev_priv);
 	if (ret < 0)
@@ -1807,8 +1808,7 @@  void i915_driver_unload(struct drm_device *dev)
 	i915_driver_cleanup_mmio(dev_priv);
 
 	enable_rpm_wakeref_asserts(dev_priv);
-
-	WARN_ON(atomic_read(&dev_priv->runtime_pm.wakeref_count));
+	intel_runtime_pm_cleanup(dev_priv);
 }
 
 static void i915_driver_release(struct drm_device *dev)
@@ -2010,6 +2010,8 @@  static int i915_drm_suspend_late(struct drm_device *dev, bool hibernation)
 
 out:
 	enable_rpm_wakeref_asserts(dev_priv);
+	if (!dev_priv->uncore.user_forcewake.count)
+		intel_runtime_pm_cleanup(dev_priv);
 
 	return ret;
 }
@@ -2965,7 +2967,7 @@  static int intel_runtime_suspend(struct device *kdev)
 	}
 
 	enable_rpm_wakeref_asserts(dev_priv);
-	WARN_ON_ONCE(atomic_read(&dev_priv->runtime_pm.wakeref_count));
+	intel_runtime_pm_cleanup(dev_priv);
 
 	if (intel_uncore_arm_unclaimed_mmio_detection(dev_priv))
 		DRM_ERROR("Unclaimed access detected prior to suspending\n");
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 6f341822653c..525a26174fcf 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -45,6 +45,7 @@ 
 #include <linux/pm_qos.h>
 #include <linux/reservation.h>
 #include <linux/shmem_fs.h>
+#include <linux/stackdepot.h>
 
 #include <drm/intel-gtt.h>
 #include <drm/drm_legacy.h> /* for struct drm_dma_handle */
@@ -1156,6 +1157,25 @@  struct i915_runtime_pm {
 	atomic_t wakeref_count;
 	bool suspended;
 	bool irqs_enabled;
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+	/*
+	 * To aide detection of wakeref leaks and general misuse, we
+	 * track all wakeref holders. With manual markup (i.e. returning
+	 * a cookie to each rpm_get caller which they then supply to their
+	 * paired rpm_put) we can remove corresponding pairs of and keep
+	 * the array trimmed to active wakerefs.
+	 */
+	struct intel_runtime_pm_debug {
+		spinlock_t lock;
+
+		depot_stack_handle_t last_acquire;
+		depot_stack_handle_t last_release;
+
+		depot_stack_handle_t *owners;
+		unsigned long count;
+	} debug;
+#endif
 };
 
 enum intel_pipe_crc_source {
diff --git a/drivers/gpu/drm/i915/intel_drv.h b/drivers/gpu/drm/i915/intel_drv.h
index 1a11c2beb7f3..ac513fd70315 100644
--- a/drivers/gpu/drm/i915/intel_drv.h
+++ b/drivers/gpu/drm/i915/intel_drv.h
@@ -41,6 +41,8 @@ 
 #include <drm/drm_atomic.h>
 #include <media/cec-notifier.h>
 
+struct drm_printer;
+
 /**
  * __wait_for - magic wait macro
  *
@@ -2084,6 +2086,7 @@  bool intel_psr_enabled(struct intel_dp *intel_dp);
 void intel_init_quirks(struct drm_i915_private *dev_priv);
 
 /* intel_runtime_pm.c */
+void intel_runtime_pm_init_early(struct drm_i915_private *dev_priv);
 int intel_power_domains_init(struct drm_i915_private *);
 void intel_power_domains_cleanup(struct drm_i915_private *dev_priv);
 void intel_power_domains_init_hw(struct drm_i915_private *dev_priv, bool resume);
@@ -2106,6 +2109,7 @@  void bxt_display_core_init(struct drm_i915_private *dev_priv, bool resume);
 void bxt_display_core_uninit(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_enable(struct drm_i915_private *dev_priv);
 void intel_runtime_pm_disable(struct drm_i915_private *dev_priv);
+void intel_runtime_pm_cleanup(struct drm_i915_private *dev_priv);
 const char *
 intel_display_power_domain_str(enum intel_display_power_domain domain);
 
@@ -2123,23 +2127,23 @@  void icl_dbuf_slices_update(struct drm_i915_private *dev_priv,
 			    u8 req_slices);
 
 static inline void
-assert_rpm_device_not_suspended(struct drm_i915_private *dev_priv)
+assert_rpm_device_not_suspended(struct drm_i915_private *i915)
 {
-	WARN_ONCE(dev_priv->runtime_pm.suspended,
+	WARN_ONCE(i915->runtime_pm.suspended,
 		  "Device suspended during HW access\n");
 }
 
 static inline void
-assert_rpm_wakelock_held(struct drm_i915_private *dev_priv)
+assert_rpm_wakelock_held(struct drm_i915_private *i915)
 {
-	assert_rpm_device_not_suspended(dev_priv);
-	WARN_ONCE(!atomic_read(&dev_priv->runtime_pm.wakeref_count),
+	assert_rpm_device_not_suspended(i915);
+	WARN_ONCE(!atomic_read(&i915->runtime_pm.wakeref_count),
 		  "RPM wakelock ref not held during HW access");
 }
 
 /**
  * disable_rpm_wakeref_asserts - disable the RPM assert checks
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function disable asserts that check if we hold an RPM wakelock
  * reference, while keeping the device-not-suspended checks still enabled.
@@ -2156,14 +2160,14 @@  assert_rpm_wakelock_held(struct drm_i915_private *dev_priv)
  * enable_rpm_wakeref_asserts().
  */
 static inline void
-disable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv)
+disable_rpm_wakeref_asserts(struct drm_i915_private *i915)
 {
-	atomic_inc(&dev_priv->runtime_pm.wakeref_count);
+	atomic_inc(&i915->runtime_pm.wakeref_count);
 }
 
 /**
  * enable_rpm_wakeref_asserts - re-enable the RPM assert checks
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function re-enables the RPM assert checks after disabling them with
  * disable_rpm_wakeref_asserts. It's meant to be used only in special
@@ -2173,15 +2177,25 @@  disable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv)
  * disable_rpm_wakeref_asserts().
  */
 static inline void
-enable_rpm_wakeref_asserts(struct drm_i915_private *dev_priv)
+enable_rpm_wakeref_asserts(struct drm_i915_private *i915)
 {
-	atomic_dec(&dev_priv->runtime_pm.wakeref_count);
+	atomic_dec(&i915->runtime_pm.wakeref_count);
 }
 
-void intel_runtime_pm_get(struct drm_i915_private *dev_priv);
-bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv);
-void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv);
-void intel_runtime_pm_put(struct drm_i915_private *dev_priv);
+void intel_runtime_pm_get(struct drm_i915_private *i915);
+bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915);
+void intel_runtime_pm_get_noresume(struct drm_i915_private *i915);
+void intel_runtime_pm_put(struct drm_i915_private *i915);
+
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+void print_intel_runtime_pm_wakeref(struct drm_i915_private *i915,
+				    struct drm_printer *p);
+#else
+static inline void print_intel_runtime_pm_wakeref(struct drm_i915_private *i915,
+						  struct drm_printer *p)
+{
+}
+#endif
 
 void chv_phy_powergate_lanes(struct intel_encoder *encoder,
 			     bool override, unsigned int mask);
diff --git a/drivers/gpu/drm/i915/intel_runtime_pm.c b/drivers/gpu/drm/i915/intel_runtime_pm.c
index 9e9501f82f06..a2f8d1fcf136 100644
--- a/drivers/gpu/drm/i915/intel_runtime_pm.c
+++ b/drivers/gpu/drm/i915/intel_runtime_pm.c
@@ -29,6 +29,8 @@ 
 #include <linux/pm_runtime.h>
 #include <linux/vgaarb.h>
 
+#include <drm/drm_print.h>
+
 #include "i915_drv.h"
 #include "intel_drv.h"
 
@@ -49,6 +51,237 @@ 
  * present for a given platform.
  */
 
+#if IS_ENABLED(CONFIG_DRM_I915_DEBUG_RUNTIME_PM)
+
+#include <linux/sort.h>
+
+#define STACKDEPTH 8
+
+static void __print_depot_stack(depot_stack_handle_t stack,
+				char *buf, int sz, int indent)
+{
+	unsigned long entries[STACKDEPTH];
+	struct stack_trace trace = {
+		.entries = entries,
+		.max_entries = ARRAY_SIZE(entries),
+	};
+
+	depot_fetch_stack(stack, &trace);
+	snprint_stack_trace(buf, sz, &trace, indent);
+}
+
+static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+
+	spin_lock_init(&rpm->debug.lock);
+}
+
+static noinline void
+track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+	unsigned long entries[STACKDEPTH];
+	struct stack_trace trace = {
+		.entries = entries,
+		.max_entries = ARRAY_SIZE(entries),
+		.skip = 0 /* gcc is ignoring noinline for tail calls? */
+	};
+	unsigned long flags;
+	depot_stack_handle_t stack, *stacks;
+
+	if (!HAS_RUNTIME_PM(i915))
+		return;
+
+	save_stack_trace(&trace);
+	if (trace.nr_entries &&
+	    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
+		trace.nr_entries--;
+
+	stack = depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
+	if (!stack)
+		return;
+
+	spin_lock_irqsave(&rpm->debug.lock, flags);
+
+	if (!rpm->debug.count)
+		rpm->debug.last_acquire = stack;
+
+	stacks = krealloc(rpm->debug.owners,
+			  (rpm->debug.count + 1) * sizeof(*stacks),
+			  GFP_NOWAIT | __GFP_NOWARN);
+	if (stacks) {
+		stacks[rpm->debug.count++] = stack;
+		rpm->debug.owners = stacks;
+	}
+
+	spin_unlock_irqrestore(&rpm->debug.lock, flags);
+}
+
+static noinline void
+untrack_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+	depot_stack_handle_t *stacks;
+	unsigned long entries[STACKDEPTH];
+	struct stack_trace trace = {
+		.entries = entries,
+		.max_entries = ARRAY_SIZE(entries),
+		.skip = 1,
+	};
+	unsigned long flags;
+	depot_stack_handle_t stack;
+
+	if (!HAS_RUNTIME_PM(i915))
+		return;
+
+	save_stack_trace(&trace);
+	if (trace.nr_entries &&
+	    trace.entries[trace.nr_entries - 1] == ULONG_MAX)
+		trace.nr_entries--;
+
+	stack = depot_save_stack(&trace, GFP_NOWAIT | __GFP_NOWARN);
+
+	spin_lock_irqsave(&rpm->debug.lock, flags);
+	stacks = fetch_and_zero(&rpm->debug.owners);
+	rpm->debug.count = 0;
+	rpm->debug.last_release = stack;
+	spin_unlock_irqrestore(&rpm->debug.lock, flags);
+
+	kfree(stacks);
+}
+
+static int cmphandle(const void *_a, const void *_b)
+{
+	const depot_stack_handle_t * const a = _a, * const b = _b;
+
+	if (*a < *b)
+		return -1;
+	else if (*a > *b)
+		return 1;
+	else
+		return 0;
+}
+
+static void
+__print_intel_runtime_pm_wakeref(struct drm_printer *p,
+				 const struct intel_runtime_pm_debug *dbg)
+{
+	unsigned long i;
+	char *buf;
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		return;
+
+	if (dbg->last_acquire) {
+		__print_depot_stack(dbg->last_acquire, buf, PAGE_SIZE, 2);
+		drm_printf(p, "Wakeref last acquired:\n%s", buf);
+	}
+
+	if (dbg->last_release) {
+		__print_depot_stack(dbg->last_release, buf, PAGE_SIZE, 2);
+		drm_printf(p, "Wakeref last released:\n%s", buf);
+	}
+
+	drm_printf(p, "Wakeref count: %lu\n", dbg->count);
+
+	sort(dbg->owners, dbg->count, sizeof(*dbg->owners), cmphandle, NULL);
+
+	for (i = 0; i < dbg->count; i++) {
+		depot_stack_handle_t stack = dbg->owners[i];
+		unsigned long rep;
+
+		rep = 1;
+		while (i + 1 < dbg->count && dbg->owners[i + 1] == stack)
+			rep++, i++;
+		__print_depot_stack(stack, buf, PAGE_SIZE, 2);
+		drm_printf(p, "Wakeref x%lu taken at:\n%s", rep, buf);
+	}
+
+	kfree(buf);
+}
+
+static void show_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+	struct intel_runtime_pm_debug dbg;
+	struct drm_printer p;
+	unsigned long flags;
+
+	spin_lock_irqsave(&rpm->debug.lock, flags);
+
+	dbg = rpm->debug;
+
+	rpm->debug.owners = NULL;
+	rpm->debug.count = 0;
+
+	spin_unlock_irqrestore(&rpm->debug.lock, flags);
+	if (!dbg.count)
+		return;
+
+	p = drm_debug_printer("i915");
+	__print_intel_runtime_pm_wakeref(&p, &dbg);
+
+	kfree(dbg.owners);
+}
+
+void print_intel_runtime_pm_wakeref(struct drm_i915_private *i915,
+				    struct drm_printer *p)
+{
+	struct intel_runtime_pm_debug dbg = {};
+
+	do {
+		struct i915_runtime_pm *rpm = &i915->runtime_pm;
+		unsigned long alloc = dbg.count;
+		depot_stack_handle_t *s;
+
+		spin_lock_irq(&rpm->debug.lock);
+		dbg.count = rpm->debug.count;
+		if (dbg.count <= alloc) {
+			memcpy(dbg.owners,
+			       rpm->debug.owners,
+			       dbg.count * sizeof(*s));
+		}
+		dbg.last_acquire = rpm->debug.last_acquire;
+		dbg.last_release = rpm->debug.last_release;
+		spin_unlock_irq(&rpm->debug.lock);
+		if (dbg.count <= alloc)
+			break;
+
+		s = krealloc(dbg.owners, dbg.count * sizeof(*s), GFP_KERNEL);
+		if (!s)
+			goto out;
+
+		dbg.owners = s;
+	} while (1);
+
+	__print_intel_runtime_pm_wakeref(p, &dbg);
+
+out:
+	kfree(dbg.owners);
+}
+
+#else
+
+static void init_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+}
+
+static void track_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+}
+
+static void untrack_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+}
+
+static void show_intel_runtime_pm_wakeref(struct drm_i915_private *i915)
+{
+}
+
+#endif
+
 bool intel_display_power_well_is_enabled(struct drm_i915_private *dev_priv,
 					 enum i915_power_well_id power_well_id);
 
@@ -3986,7 +4219,7 @@  static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
 
 /**
  * intel_runtime_pm_get - grab a runtime pm reference
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function grabs a device-level runtime pm reference (mostly used for GEM
  * code to ensure the GTT or GT is on) and ensures that it is powered up.
@@ -3994,22 +4227,24 @@  static void intel_power_domains_verify_state(struct drm_i915_private *dev_priv)
  * Any runtime pm reference obtained by this function must have a symmetric
  * call to intel_runtime_pm_put() to release the reference again.
  */
-void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_get(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 	int ret;
 
 	ret = pm_runtime_get_sync(kdev);
 	WARN_ONCE(ret < 0, "pm_runtime_get_sync() failed: %d\n", ret);
 
-	atomic_inc(&dev_priv->runtime_pm.wakeref_count);
-	assert_rpm_wakelock_held(dev_priv);
+	atomic_inc(&i915->runtime_pm.wakeref_count);
+	assert_rpm_wakelock_held(i915);
+
+	track_intel_runtime_pm_wakeref(i915);
 }
 
 /**
  * intel_runtime_pm_get_if_in_use - grab a runtime pm reference if device in use
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function grabs a device-level runtime pm reference if the device is
  * already in use and ensures that it is powered up. It is illegal to try
@@ -4020,10 +4255,10 @@  void intel_runtime_pm_get(struct drm_i915_private *dev_priv)
  *
  * Returns: True if the wakeref was acquired, or False otherwise.
  */
-bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
+bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *i915)
 {
 	if (IS_ENABLED(CONFIG_PM)) {
-		struct pci_dev *pdev = dev_priv->drm.pdev;
+		struct pci_dev *pdev = i915->drm.pdev;
 		struct device *kdev = &pdev->dev;
 
 		/*
@@ -4036,15 +4271,17 @@  bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
 			return false;
 	}
 
-	atomic_inc(&dev_priv->runtime_pm.wakeref_count);
-	assert_rpm_wakelock_held(dev_priv);
+	atomic_inc(&i915->runtime_pm.wakeref_count);
+	assert_rpm_wakelock_held(i915);
+
+	track_intel_runtime_pm_wakeref(i915);
 
 	return true;
 }
 
 /**
  * intel_runtime_pm_get_noresume - grab a runtime pm reference
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function grabs a device-level runtime pm reference (mostly used for GEM
  * code to ensure the GTT or GT is on).
@@ -4059,32 +4296,35 @@  bool intel_runtime_pm_get_if_in_use(struct drm_i915_private *dev_priv)
  * Any runtime pm reference obtained by this function must have a symmetric
  * call to intel_runtime_pm_put() to release the reference again.
  */
-void intel_runtime_pm_get_noresume(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_get_noresume(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
-	assert_rpm_wakelock_held(dev_priv);
+	assert_rpm_wakelock_held(i915);
 	pm_runtime_get_noresume(kdev);
 
-	atomic_inc(&dev_priv->runtime_pm.wakeref_count);
+	atomic_inc(&i915->runtime_pm.wakeref_count);
+
+	track_intel_runtime_pm_wakeref(i915);
 }
 
 /**
  * intel_runtime_pm_put - release a runtime pm reference
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function drops the device-level runtime pm reference obtained by
  * intel_runtime_pm_get() and might power down the corresponding
  * hardware block right away if this is the last reference.
  */
-void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_put(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
-	assert_rpm_wakelock_held(dev_priv);
-	atomic_dec(&dev_priv->runtime_pm.wakeref_count);
+	assert_rpm_wakelock_held(i915);
+	if (atomic_dec_and_test(&i915->runtime_pm.wakeref_count))
+		untrack_intel_runtime_pm_wakeref(i915);
 
 	pm_runtime_mark_last_busy(kdev);
 	pm_runtime_put_autosuspend(kdev);
@@ -4092,7 +4332,7 @@  void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
 
 /**
  * intel_runtime_pm_enable - enable runtime pm
- * @dev_priv: i915 device instance
+ * @i915: i915 device instance
  *
  * This function enables runtime pm at the end of the driver load sequence.
  *
@@ -4100,9 +4340,9 @@  void intel_runtime_pm_put(struct drm_i915_private *dev_priv)
  * subordinate display power domains. That is done by
  * intel_power_domains_enable().
  */
-void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_enable(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
 	/*
@@ -4124,7 +4364,7 @@  void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 	 * so the driver's own RPM reference tracking asserts also work on
 	 * platforms without RPM support.
 	 */
-	if (!HAS_RUNTIME_PM(dev_priv)) {
+	if (!HAS_RUNTIME_PM(i915)) {
 		int ret;
 
 		pm_runtime_dont_use_autosuspend(kdev);
@@ -4142,17 +4382,36 @@  void intel_runtime_pm_enable(struct drm_i915_private *dev_priv)
 	pm_runtime_put_autosuspend(kdev);
 }
 
-void intel_runtime_pm_disable(struct drm_i915_private *dev_priv)
+void intel_runtime_pm_disable(struct drm_i915_private *i915)
 {
-	struct pci_dev *pdev = dev_priv->drm.pdev;
+	struct pci_dev *pdev = i915->drm.pdev;
 	struct device *kdev = &pdev->dev;
 
 	/* Transfer rpm ownership back to core */
-	WARN(pm_runtime_get_sync(&dev_priv->drm.pdev->dev) < 0,
+	WARN(pm_runtime_get_sync(kdev) < 0,
 	     "Failed to pass rpm ownership back to core\n");
 
 	pm_runtime_dont_use_autosuspend(kdev);
 
-	if (!HAS_RUNTIME_PM(dev_priv))
+	if (!HAS_RUNTIME_PM(i915))
 		pm_runtime_put(kdev);
 }
+
+void intel_runtime_pm_cleanup(struct drm_i915_private *i915)
+{
+	struct i915_runtime_pm *rpm = &i915->runtime_pm;
+
+	if (WARN(atomic_read(&rpm->wakeref_count),
+		 "i915->runtime_pm.wakeref_count=%d on cleanup\n",
+		 atomic_read(&rpm->wakeref_count))) {
+		show_intel_runtime_pm_wakeref(i915);
+		atomic_set(&rpm->wakeref_count, 0);
+	}
+
+	untrack_intel_runtime_pm_wakeref(i915);
+}
+
+void intel_runtime_pm_init_early(struct drm_i915_private *i915)
+{
+	init_intel_runtime_pm_wakeref(i915);
+}
diff --git a/drivers/gpu/drm/i915/selftests/mock_gem_device.c b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
index baa3c38919de..082809569681 100644
--- a/drivers/gpu/drm/i915/selftests/mock_gem_device.c
+++ b/drivers/gpu/drm/i915/selftests/mock_gem_device.c
@@ -154,15 +154,17 @@  struct drm_i915_private *mock_gem_device(void)
 	pdev->dev.archdata.iommu = (void *)-1;
 #endif
 
+	i915 = (struct drm_i915_private *)(pdev + 1);
+	pci_set_drvdata(pdev, i915);
+
+	intel_runtime_pm_init_early(i915);
+
 	dev_pm_domain_set(&pdev->dev, &pm_domain);
 	pm_runtime_enable(&pdev->dev);
 	pm_runtime_dont_use_autosuspend(&pdev->dev);
 	if (pm_runtime_enabled(&pdev->dev))
 		WARN_ON(pm_runtime_get_sync(&pdev->dev));
 
-	i915 = (struct drm_i915_private *)(pdev + 1);
-	pci_set_drvdata(pdev, i915);
-
 	err = drm_dev_init(&i915->drm, &mock_driver, &pdev->dev);
 	if (err) {
 		pr_err("Failed to initialise mock GEM device: err=%d\n", err);