i915 PMU and engine busy stats

index 0bb6e01121fc..8d6b096891a5 100644
@@ -1178,13 +1178,8 @@ static int i915_frequency_info(struct seq_file *m, void *unused)
 		rpdownei = I915_READ(GEN6_RP_CUR_DOWN_EI) & GEN6_CURIAVG_MASK;
 		rpcurdown = I915_READ(GEN6_RP_CUR_DOWN) & GEN6_CURBSYTAVG_MASK;
 		rpprevdown = I915_READ(GEN6_RP_PREV_DOWN) & GEN6_CURBSYTAVG_MASK;
-		if (INTEL_GEN(dev_priv) >= 9)
-			cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
-		else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-			cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
-		else
-			cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
-		cagf = intel_gpu_freq(dev_priv, cagf);
+		cagf = intel_gpu_freq(dev_priv,
+				      intel_get_cagf(dev_priv, rpstat));
 
 		intel_uncore_forcewake_put(dev_priv, FORCEWAKE_ALL);
 

index 6bbc4b83aa0a..0f5e336a67f4 100644
@@ -4187,6 +4187,8 @@ int intel_freq_opcode(struct drm_i915_private *dev_priv, int val);
 u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
 			   const i915_reg_t reg);
 
+u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat1);
+
 #define I915_READ8(reg)		dev_priv->uncore.funcs.mmio_readb(dev_priv, (reg), true)
 #define I915_WRITE8(reg, val)	dev_priv->uncore.funcs.mmio_writeb(dev_priv, (reg), (val), true)
 

index 791759f632e1..450ac7d343ad 100644
@@ -252,14 +252,9 @@ static ssize_t gt_act_freq_mhz_show(struct device *kdev,
 		freq = vlv_punit_read(dev_priv, PUNIT_REG_GPU_FREQ_STS);
 		ret = intel_gpu_freq(dev_priv, (freq >> 8) & 0xff);
 	} else {
-		u32 rpstat = I915_READ(GEN6_RPSTAT1);
-		if (INTEL_GEN(dev_priv) >= 9)
-			ret = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
-		else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
-			ret = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
-		else
-			ret = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
-		ret = intel_gpu_freq(dev_priv, ret);
+		ret = intel_gpu_freq(dev_priv,
+				     intel_get_cagf(dev_priv,
+						    I915_READ(GEN6_RPSTAT1)));
 	}
 	mutex_unlock(&dev_priv->pcu_lock);
 

index 2fcff9788b6f..a06ab60847eb 100644
@@ -9513,3 +9513,17 @@ u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
 	intel_runtime_pm_put(dev_priv);
 	return DIV_ROUND_UP_ULL(time_hw * units, div);
 }
+
+u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat)
+{
+	u32 cagf;
+
+	if (INTEL_GEN(dev_priv) >= 9)
+		cagf = (rpstat & GEN9_CAGF_MASK) >> GEN9_CAGF_SHIFT;
+	else if (IS_HASWELL(dev_priv) || IS_BROADWELL(dev_priv))
+		cagf = (rpstat & HSW_CAGF_MASK) >> HSW_CAGF_SHIFT;
+	else
+		cagf = (rpstat & GEN6_CAGF_MASK) >> GEN6_CAGF_SHIFT;
+
+	return  cagf;
+}

index f1e651703764..65060bdc7b81 100644
@@ -1215,6 +1215,7 @@ static void i915_driver_register(struct drm_i915_private *dev_priv)
 	struct drm_device *dev = &dev_priv->drm;
 
 	i915_gem_shrinker_init(dev_priv);
+	i915_pmu_register(dev_priv);
 
 	/*
 	 * Notify a valid surface after modesetting,

@@ -1269,6 +1270,7 @@ static void i915_driver_unregister(struct drm_i915_private *dev_priv)
 	intel_opregion_unregister(dev_priv);
 
 	i915_perf_unregister(dev_priv);
+	i915_pmu_unregister(dev_priv);
 
 	i915_teardown_sysfs(dev_priv);
 	i915_guc_log_unregister(dev_priv);

index 0f5e336a67f4..c577d811d560 100644
@@ -40,6 +40,7 @@
 #include <linux/hash.h>
 #include <linux/intel-iommu.h>
 #include <linux/kref.h>
+#include <linux/perf_event.h>
 #include <linux/pm_qos.h>
 #include <linux/reservation.h>
 #include <linux/shmem_fs.h>

@@ -2272,6 +2273,8 @@ struct drm_i915_private {
 	struct i915_gem_context *kernel_context;
 	/* Context only to be used for injecting preemption commands */
 	struct i915_gem_context *preempt_context;
+	struct intel_engine_cs *engine_class[MAX_ENGINE_CLASS + 1]
+					    [MAX_ENGINE_INSTANCE + 1];
 	struct i915_vma *semaphore;
 
 	struct drm_dma_handle *status_page_dmah;

@@ -2742,6 +2745,8 @@ struct drm_i915_private {
 		int	irq;
 	} lpe_audio;
 
+	struct i915_pmu pmu;
+
 	/*
 	 * NOTE: This is the dri1/ums dungeon, don't add stuff here. Your patch
 	 * will be rejected. Instead look for a better place.

@@ -3988,6 +3993,15 @@ extern void i915_perf_fini(struct drm_i915_private *dev_priv);
 extern void i915_perf_register(struct drm_i915_private *dev_priv);
 extern void i915_perf_unregister(struct drm_i915_private *dev_priv);
 
+/* i915_pmu.c */
+#ifdef CONFIG_PERF_EVENTS
+void i915_pmu_register(struct drm_i915_private *i915);
+void i915_pmu_unregister(struct drm_i915_private *i915);
+#else
+static inline void i915_pmu_register(struct drm_i915_private *i915) {}
+static inline void i915_pmu_unregister(struct drm_i915_private *i915) {}
+#endif
+
 /* i915_suspend.c */
 extern int i915_save_state(struct drm_i915_private *dev_priv);
 extern int i915_restore_state(struct drm_i915_private *dev_priv);

659 lines not on this page · raw message

96 lines not on this page · raw message

index d2d0a83c09b6..41fe69943c02 100644
@@ -186,6 +186,9 @@ static inline bool i915_mmio_reg_valid(i915_reg_t reg)
 #define VIDEO_ENHANCEMENT_CLASS	2
 #define COPY_ENGINE_CLASS	3
 #define OTHER_CLASS		4
+#define MAX_ENGINE_CLASS	4
+
+#define MAX_ENGINE_INSTANCE    1
 
 /* PCI config space */
 

index a59b2a30ff5a..4c7d7ade99d8 100644
@@ -202,6 +202,15 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	GEM_BUG_ON(info->class >= ARRAY_SIZE(intel_engine_classes));
 	class_info = &intel_engine_classes[info->class];
 
+	if (GEM_WARN_ON(info->class > MAX_ENGINE_CLASS))
+		return -EINVAL;
+
+	if (GEM_WARN_ON(info->instance > MAX_ENGINE_INSTANCE))
+		return -EINVAL;
+
+	if (GEM_WARN_ON(dev_priv->engine_class[info->class][info->instance]))
+		return -EINVAL;
+
 	GEM_BUG_ON(dev_priv->engine[id]);
 	engine = kzalloc(sizeof(*engine), GFP_KERNEL);
 	if (!engine)

@@ -229,6 +238,7 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
+	dev_priv->engine_class[info->class][info->instance] = engine;
 	dev_priv->engine[id] = engine;
 	return 0;
 }

@@ -1776,6 +1786,31 @@ void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *m)
 	drm_printf(m, "\n");
 }
 
+static u8 user_class_map[I915_ENGINE_CLASS_MAX] = {
+	[I915_ENGINE_CLASS_OTHER] = OTHER_CLASS,
+	[I915_ENGINE_CLASS_RENDER] = RENDER_CLASS,
+	[I915_ENGINE_CLASS_COPY] = COPY_ENGINE_CLASS,
+	[I915_ENGINE_CLASS_VIDEO] = VIDEO_DECODE_CLASS,
+	[I915_ENGINE_CLASS_VIDEO_ENHANCE] = VIDEO_ENHANCEMENT_CLASS,
+};
+
+struct intel_engine_cs *
+intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
+{
+	if (class >= ARRAY_SIZE(user_class_map))
+		return NULL;
+
+	class = user_class_map[class];
+
+	if (WARN_ON_ONCE(class > MAX_ENGINE_CLASS))
+		return NULL;
+
+	if (instance > MAX_ENGINE_INSTANCE)
+		return NULL;
+
+	return i915->engine_class[class][instance];
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_engine.c"
 #endif

index 17186f067408..289bb25dd964 100644
@@ -5,6 +5,7 @@
 #include "i915_gem_batch_pool.h"
 #include "i915_gem_request.h"
 #include "i915_gem_timeline.h"
+#include "i915_pmu.h"
 #include "i915_selftest.h"
 
 struct drm_printer;

@@ -337,6 +338,28 @@ struct intel_engine_cs {
 		I915_SELFTEST_DECLARE(bool mock : 1);
 	} breadcrumbs;
 
+	struct {
+		/**
+		 * @enable: Bitmask of enable sample events on this engine.
+		 *
+		 * Bits correspond to sample event types, for instance
+		 * I915_SAMPLE_QUEUED is bit 0 etc.
+		 */
+		u32 enable;
+		/**
+		 * @enable_count: Reference count for the enabled samplers.
+		 *
+		 * Index number corresponds to the bit number from @enable.
+		 */
+		unsigned int enable_count[I915_PMU_SAMPLE_BITS];
+		/**
+		 * @sample: Counter values for sampling events.
+		 *
+		 * Our internal timer stores the current counters in this field.
+		 */
+		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
+	} pmu;
+
 	/*
 	 * A pool of objects to use as shadow copies of client batch buffers
 	 * when the command parser is enabled. Prevents the client from

@@ -843,4 +866,7 @@ bool intel_engine_can_store_dword(struct intel_engine_cs *engine);
 
 void intel_engine_dump(struct intel_engine_cs *engine, struct drm_printer *p);
 
+struct intel_engine_cs *
+intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance);
+
 #endif /* _INTEL_RINGBUFFER_H_ */

54 lines not on this page · raw message

index c577d811d560..a8b565e1193e 100644
@@ -3997,9 +3997,13 @@ extern void i915_perf_unregister(struct drm_i915_private *dev_priv);
 #ifdef CONFIG_PERF_EVENTS
 void i915_pmu_register(struct drm_i915_private *i915);
 void i915_pmu_unregister(struct drm_i915_private *i915);
+void i915_pmu_gt_idle(struct drm_i915_private *i915);
+void i915_pmu_gt_active(struct drm_i915_private *i915);
 #else
 static inline void i915_pmu_register(struct drm_i915_private *i915) {}
 static inline void i915_pmu_unregister(struct drm_i915_private *i915) {}
+static inline void i915_pmu_gt_idle(struct drm_i915_private *i915) {}
+static inline void i915_pmu_gt_active(struct drm_i915_private *i915) {}
 #endif
 
 /* i915_suspend.c */

index f76890b74d00..100398b10a8b 100644
@@ -3269,6 +3269,7 @@ i915_gem_idle_work_handler(struct work_struct *work)
 
 	intel_engines_mark_idle(dev_priv);
 	i915_gem_timelines_mark_idle(dev_priv);
+	i915_pmu_gt_idle(dev_priv);
 
 	GEM_BUG_ON(!dev_priv->gt.awake);
 	dev_priv->gt.awake = false;

index d5f4023e5d63..fa9af1ed80bd 100644
@@ -258,6 +258,7 @@ static void mark_busy(struct drm_i915_private *i915)
 	i915_update_gfx_val(i915);
 	if (INTEL_GEN(i915) >= 6)
 		gen6_rps_busy(i915);
+	i915_pmu_gt_active(i915);
 
 	queue_delayed_work(i915->wq,
 			   &i915->gt.retire_work,

119 lines not on this page · raw message

index 0f884dd3496a..89be7eb4af1c 100644
@@ -83,6 +83,10 @@ struct i915_pmu {
 	 */
 	unsigned int enable_count[I915_PMU_MASK_BITS];
 	/**
+	 * @timer_enabled: Should the internal sampling timer be running.
+	 */
+	bool timer_enabled;
+	/**
 	 * @sample: Current and previous (raw) counters for sampling events.
 	 *
 	 * These counters are updated from the i915 PMU sampling timer.

index fbfcf88d7fe3..52a7c741762d 100644
@@ -400,6 +400,18 @@ execlists_context_status_change(struct drm_i915_gem_request *rq,
 				   status, rq);
 }
 
+static inline void
+execlists_context_schedule_in(struct drm_i915_gem_request *rq)
+{
+	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
+}
+
+static inline void
+execlists_context_schedule_out(struct drm_i915_gem_request *rq)
+{
+	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
+}
+
 static void
 execlists_update_context_pdps(struct i915_hw_ppgtt *ppgtt, u32 *reg_state)
 {

@@ -451,7 +463,7 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 		if (rq) {
 			GEM_BUG_ON(count > !n);
 			if (!count++)
-				execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
+				execlists_context_schedule_in(rq);
 			port_set(&port[n], port_pack(rq, count));
 			desc = execlists_update_context(rq);
 			GEM_DEBUG_EXEC(port[n].context_id = upper_32_bits(desc));

@@ -879,8 +891,7 @@ static void intel_lrc_irq_handler(unsigned long data)
 			if (--count == 0) {
 				GEM_BUG_ON(status & GEN8_CTX_STATUS_PREEMPTED);
 				GEM_BUG_ON(!i915_gem_request_completed(rq));
-				execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
-
+				execlists_context_schedule_out(rq);
 				trace_i915_gem_request_out(rq);
 				rq->priotree.priority = INT_MAX;
 				i915_gem_request_put(rq);

index 4c7d7ade99d8..1dbe99373057 100644
@@ -236,6 +236,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
+	spin_lock_init(&engine->stats.lock);
+
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
 	dev_priv->engine_class[info->class][info->instance] = engine;

@@ -1811,6 +1813,91 @@ intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
 	return i915->engine_class[class][instance];
 }
 
+/**
+ * intel_enable_engine_stats() - Enable engine busy tracking on engine
+ * @engine: engine to enable stats collection
+ *
+ * Start collecting the engine busyness data for @engine.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+int intel_enable_engine_stats(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (!i915_modparams.enable_execlists)
+		return -ENODEV;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	if (engine->stats.enabled == ~0)
+		goto busy;
+	if (engine->stats.enabled++ == 0)
+		engine->stats.enabled_at = ktime_get();
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return 0;
+
+busy:
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return -EBUSY;
+}
+
+static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
+{
+	ktime_t total = engine->stats.total;
+
+	/*
+	 * If the engine is executing something at the moment
+	 * add it to the total.
+	 */
+	if (engine->stats.active)
+		total = ktime_add(total,
+				  ktime_sub(ktime_get(), engine->stats.start));
+
+	return total;
+}
+
+/**
+ * intel_engine_get_busy_time() - Return current accumulated engine busyness
+ * @engine: engine to report on
+ *
+ * Returns accumulated time @engine was busy since engine stats were enabled.
+ */
+ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
+{
+	ktime_t total;
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	total = __intel_engine_get_busy_time(engine);
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return total;
+}
+
+/**
+ * intel_disable_engine_stats() - Disable engine busy tracking on engine
+ * @engine: engine to disable stats collection
+ *
+ * Stops collecting the engine busyness data for @engine.
+ */
+void intel_disable_engine_stats(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (!i915_modparams.enable_execlists)
+		return;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	WARN_ON_ONCE(engine->stats.enabled == 0);
+	if (--engine->stats.enabled == 0) {
+		engine->stats.total = __intel_engine_get_busy_time(engine);
+		engine->stats.active = 0;
+	}
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_engine.c"
 #endif

index 52a7c741762d..145f2d9d0fe0 100644
@@ -404,11 +404,13 @@ static inline void
 execlists_context_schedule_in(struct drm_i915_gem_request *rq)
 {
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
+	intel_engine_context_in(rq->engine);
 }
 
 static inline void
 execlists_context_schedule_out(struct drm_i915_gem_request *rq)
 {
+	intel_engine_context_out(rq->engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
 }
 

102 lines not on this page · raw message

index 02ac8e1d415b..47d8ee347d2b 100644
@@ -237,6 +237,8 @@ intel_engine_setup(struct drm_i915_private *dev_priv,
 	/* Nothing to do here, execute in order of dependencies */
 	engine->schedule = NULL;
 
+	spin_lock_init(&engine->stats.lock);
+
 	ATOMIC_INIT_NOTIFIER_HEAD(&engine->context_status_notifier);
 
 	dev_priv->engine_class[info->class][info->instance] = engine;

@@ -1815,6 +1817,91 @@ intel_engine_lookup_user(struct drm_i915_private *i915, u8 class, u8 instance)
 	return i915->engine_class[class][instance];
 }
 
+/**
+ * intel_enable_engine_stats() - Enable engine busy tracking on engine
+ * @engine: engine to enable stats collection
+ *
+ * Start collecting the engine busyness data for @engine.
+ *
+ * Returns 0 on success or a negative error code.
+ */
+int intel_enable_engine_stats(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (!i915_modparams.enable_execlists)
+		return -ENODEV;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	if (engine->stats.enabled == ~0)
+		goto busy;
+	if (engine->stats.enabled++ == 0)
+		engine->stats.enabled_at = ktime_get();
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return 0;
+
+busy:
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return -EBUSY;
+}
+
+static ktime_t __intel_engine_get_busy_time(struct intel_engine_cs *engine)
+{
+	ktime_t total = engine->stats.total;
+
+	/*
+	 * If the engine is executing something at the moment
+	 * add it to the total.
+	 */
+	if (engine->stats.active)
+		total = ktime_add(total,
+				  ktime_sub(ktime_get(), engine->stats.start));
+
+	return total;
+}
+
+/**
+ * intel_engine_get_busy_time() - Return current accumulated engine busyness
+ * @engine: engine to report on
+ *
+ * Returns accumulated time @engine was busy since engine stats were enabled.
+ */
+ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
+{
+	ktime_t total;
+	unsigned long flags;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	total = __intel_engine_get_busy_time(engine);
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+
+	return total;
+}
+
+/**
+ * intel_disable_engine_stats() - Disable engine busy tracking on engine
+ * @engine: engine to disable stats collection
+ *
+ * Stops collecting the engine busyness data for @engine.
+ */
+void intel_disable_engine_stats(struct intel_engine_cs *engine)
+{
+	unsigned long flags;
+
+	if (!i915_modparams.enable_execlists)
+		return;
+
+	spin_lock_irqsave(&engine->stats.lock, flags);
+	WARN_ON_ONCE(engine->stats.enabled == 0);
+	if (--engine->stats.enabled == 0) {
+		engine->stats.total = __intel_engine_get_busy_time(engine);
+		engine->stats.active = 0;
+	}
+	spin_unlock_irqrestore(&engine->stats.lock, flags);
+}
+
 #if IS_ENABLED(CONFIG_DRM_I915_SELFTEST)
 #include "selftests/mock_engine.c"
 #endif

index 6713f4a2f581..8a7a9cc5f28d 100644
@@ -404,11 +404,13 @@ static inline void
 execlists_context_schedule_in(struct drm_i915_gem_request *rq)
 {
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_IN);
+	intel_engine_context_in(rq->engine);
 }
 
 static inline void
 execlists_context_schedule_out(struct drm_i915_gem_request *rq)
 {
+	intel_engine_context_out(rq->engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
 }
 

@@ -708,6 +710,7 @@ execlist_cancel_port_requests(struct intel_engine_execlists *execlists)
 	while (num_ports-- && port_isset(port)) {
 		struct drm_i915_gem_request *rq = port_request(port);
 
+		intel_engine_context_out(rq->engine);
 		execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_PREEMPTED);
 		i915_gem_request_put(rq);
 

102 lines not on this page · raw message

index bd394da47c7a..434895288094 100644
@@ -90,6 +90,11 @@ static unsigned int event_enabled_bit(struct perf_event *event)
 	return config_enabled_bit(event->attr.config);
 }
 
+static bool supports_busy_stats(void)
+{
+	return i915_modparams.enable_execlists;
+}
+
 static bool pmu_needs_timer(struct drm_i915_private *i915, bool gpu_active)
 {
 	u64 enable;

@@ -115,6 +120,12 @@ static bool pmu_needs_timer(struct drm_i915_private *i915, bool gpu_active)
 	 */
 	if (!gpu_active)
 		enable &= ~ENGINE_SAMPLE_MASK;
+	/*
+	 * Also there is software busyness tracking available we do not
+	 * need the timer for I915_SAMPLE_BUSY counter.
+	 */
+	else if (supports_busy_stats())
+		enable &= ~BIT(I915_SAMPLE_BUSY);
 
 	/*
 	 * If some bits remain it means we need the sampling timer running.

@@ -363,6 +374,9 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 
 		if (WARN_ON_ONCE(!engine)) {
 			/* Do nothing */
+		} else if (sample == I915_SAMPLE_BUSY &&
+			   engine->pmu.busy_stats) {
+			val = ktime_to_ns(intel_engine_get_busy_time(engine));
 		} else {
 			val = engine->pmu.sample[sample].cur;
 		}

@@ -399,6 +413,12 @@ static void i915_pmu_event_read(struct perf_event *event)
 	local64_add(new - prev, &event->count);
 }
 
+static bool engine_needs_busy_stats(struct intel_engine_cs *engine)
+{
+	return supports_busy_stats() &&
+	       (engine->pmu.enable & BIT(I915_SAMPLE_BUSY));
+}
+
 static void i915_pmu_enable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =

@@ -438,7 +458,21 @@ static void i915_pmu_enable(struct perf_event *event)
 
 		GEM_BUG_ON(sample >= I915_PMU_SAMPLE_BITS);
 		GEM_BUG_ON(engine->pmu.enable_count[sample] == ~0);
-		engine->pmu.enable_count[sample]++;
+		if (engine->pmu.enable_count[sample]++ == 0) {
+			/*
+			 * Enable engine busy stats tracking if needed or
+			 * alternatively cancel the scheduled disable.
+			 *
+			 * If the delayed disable was pending, cancel it and
+			 * in this case do not enable since it already is.
+			 */
+			if (engine_needs_busy_stats(engine) &&
+			    !engine->pmu.busy_stats) {
+				engine->pmu.busy_stats = true;
+				if (!cancel_delayed_work(&engine->pmu.disable_busy_stats))
+					intel_enable_engine_stats(engine);
+			}
+		}
 	}
 
 	/*

@@ -474,8 +508,26 @@ static void i915_pmu_disable(struct perf_event *event)
 		 * Decrement the reference count and clear the enabled
 		 * bitmask when the last listener on an event goes away.
 		 */
-		if (--engine->pmu.enable_count[sample] == 0)
+		if (--engine->pmu.enable_count[sample] == 0) {
 			engine->pmu.enable &= ~BIT(sample);
+			if (!engine_needs_busy_stats(engine) &&
+			    engine->pmu.busy_stats) {
+				engine->pmu.busy_stats = false;
+				/*
+				 * We request a delayed disable to handle the
+				 * rapid on/off cycles on events, which can
+				 * happen when tools like perf stat start, in a
+				 * nicer way.
+				 *
+				 * In addition, this also helps with busy stats
+				 * accuracy with background CPU offline/online
+				 * migration events.
+				 */
+				queue_delayed_work(system_wq,
+						   &engine->pmu.disable_busy_stats,
+						   round_jiffies_up_relative(HZ));
+			}
+		}
 	}
 
 	GEM_BUG_ON(bit >= I915_PMU_MASK_BITS);

@@ -657,8 +709,18 @@ static int i915_pmu_cpu_offline(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
+static void __disable_busy_stats(struct work_struct *work)
+{
+	struct intel_engine_cs *engine =
+	       container_of(work, typeof(*engine), pmu.disable_busy_stats.work);
+
+	intel_disable_engine_stats(engine);
+}
+
 void i915_pmu_register(struct drm_i915_private *i915)
 {
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
 	int ret;
 
 	if (INTEL_GEN(i915) <= 2) {

@@ -693,6 +755,10 @@ void i915_pmu_register(struct drm_i915_private *i915)
 	i915->pmu.timer.function = i915_sample;
 	i915->pmu.enable = 0;
 
+	for_each_engine(engine, i915, id)
+		INIT_DELAYED_WORK(&engine->pmu.disable_busy_stats,
+				  __disable_busy_stats);
+
 	ret = perf_pmu_register(&i915->pmu.base, "i915", -1);
 	if (ret == 0)
 		return;

@@ -711,6 +777,9 @@ void i915_pmu_register(struct drm_i915_private *i915)
 
 void i915_pmu_unregister(struct drm_i915_private *i915)
 {
+	struct intel_engine_cs *engine;
+	enum intel_engine_id id;
+
 	if (!i915->pmu.base.event_init)
 		return;
 

@@ -722,6 +791,11 @@ void i915_pmu_unregister(struct drm_i915_private *i915)
 
 	hrtimer_cancel(&i915->pmu.timer);
 
+	for_each_engine(engine, i915, id) {
+		GEM_BUG_ON(engine->pmu.busy_stats);
+		flush_delayed_work(&engine->pmu.disable_busy_stats);
+	}
+
 	perf_pmu_unregister(&i915->pmu.base);
 	i915->pmu.base.event_init = NULL;
 }

index 850620699468..871dca7e82ba 100644
@@ -358,6 +358,20 @@ struct intel_engine_cs {
 		 * Our internal timer stores the current counters in this field.
 		 */
 		struct i915_pmu_sample sample[I915_ENGINE_SAMPLE_MAX];
+		/**
+		 * @busy_stats: Has enablement of engine stats tracking been
+		 * 		requested.
+		 */
+		bool busy_stats;
+		/**
+		 * @disable_busy_stats: Work item for busy stats disabling.
+		 *
+		 * Same as with @enable_busy_stats action, with the difference
+		 * that we delay it in case there are rapid enable-disable
+		 * actions, which can happen during tool startup (like perf
+		 * stat).
+		 */
+		struct delayed_work disable_busy_stats;
 	} pmu;
 
 	/*

index 434895288094..97d489565cd1 100644
@@ -277,6 +277,22 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 	return HRTIMER_RESTART;
 }
 
+static u64 count_interrupts(struct drm_i915_private *i915)
+{
+	/* open-coded kstat_irqs() */
+	struct irq_desc *desc = irq_to_desc(i915->drm.pdev->irq);
+	u64 sum = 0;
+	int cpu;
+
+	if (!desc || !desc->kstat_irqs)
+		return 0;
+
+	for_each_possible_cpu(cpu)
+		sum += *per_cpu_ptr(desc->kstat_irqs, cpu);
+
+	return sum;
+}
+
 static void i915_pmu_event_destroy(struct perf_event *event)
 {
 	WARN_ON(event->parent);

@@ -343,6 +359,8 @@ static int i915_pmu_event_init(struct perf_event *event)
 			if (INTEL_GEN(i915) < 6)
 				ret = -ENODEV;
 			break;
+		case I915_PMU_INTERRUPTS:
+			break;
 		default:
 			ret = -ENOENT;
 			break;

@@ -392,6 +410,9 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 			   div_u64(i915->pmu.sample[__I915_SAMPLE_FREQ_REQ].cur,
 				   FREQUENCY);
 			break;
+		case I915_PMU_INTERRUPTS:
+			val = count_interrupts(i915);
+			break;
 		}
 	}
 

@@ -646,6 +667,8 @@ static struct attribute *i915_pmu_events_attrs[] = {
 	I915_EVENT(actual-frequency,    I915_PMU_ACTUAL_FREQUENCY,    "MHz"),
 	I915_EVENT(requested-frequency, I915_PMU_REQUESTED_FREQUENCY, "MHz"),
 
+	I915_EVENT_ATTR(interrupts, I915_PMU_INTERRUPTS),
+
 	NULL,
 };
 

index d35af9ff635c..8aceb7f57e0c 100644
@@ -132,7 +132,9 @@ enum drm_i915_pmu_engine_sample {
 #define I915_PMU_ACTUAL_FREQUENCY	__I915_PMU_OTHER(0)
 #define I915_PMU_REQUESTED_FREQUENCY	__I915_PMU_OTHER(1)
 
-#define I915_PMU_LAST I915_PMU_REQUESTED_FREQUENCY
+#define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
+
+#define I915_PMU_LAST I915_PMU_INTERRUPTS
 
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */

index a8b565e1193e..57d08ec5b6a3 100644
@@ -4202,11 +4202,17 @@ void vlv_phy_reset_lanes(struct intel_encoder *encoder);
 
 int intel_gpu_freq(struct drm_i915_private *dev_priv, int val);
 int intel_freq_opcode(struct drm_i915_private *dev_priv, int val);
-u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
+u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
 			   const i915_reg_t reg);
 
 u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat1);
 
+static inline u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
+					 const i915_reg_t reg)
+{
+	return DIV_ROUND_UP_ULL(intel_rc6_residency_ns(dev_priv, reg), 1000);
+}
+
 #define I915_READ8(reg)		dev_priv->uncore.funcs.mmio_readb(dev_priv, (reg), true)
 #define I915_WRITE8(reg, val)	dev_priv->uncore.funcs.mmio_writeb(dev_priv, (reg), (val), true)
 

index 450ac7d343ad..c290cb600eea 100644
@@ -42,8 +42,13 @@ static inline struct drm_i915_private *kdev_minor_to_i915(struct device *kdev)
 static u32 calc_residency(struct drm_i915_private *dev_priv,
 			  i915_reg_t reg)
 {
-	return DIV_ROUND_CLOSEST_ULL(intel_rc6_residency_us(dev_priv, reg),
-				     1000);
+	u64 res;
+
+	intel_runtime_pm_get(dev_priv);
+	res = intel_rc6_residency_us(dev_priv, reg);
+	intel_runtime_pm_put(dev_priv);
+
+	return DIV_ROUND_CLOSEST_ULL(res, 1000);
 }
 
 static ssize_t

index a06ab60847eb..4787937757b8 100644
@@ -9482,36 +9482,35 @@ static u64 vlv_residency_raw(struct drm_i915_private *dev_priv,
 	return lower | (u64)upper << 8;
 }
 
-u64 intel_rc6_residency_us(struct drm_i915_private *dev_priv,
+u64 intel_rc6_residency_ns(struct drm_i915_private *dev_priv,
 			   const i915_reg_t reg)
 {
-	u64 time_hw, units, div;
+	u64 time_hw;
+	u32 mul, div;
 
 	if (!intel_rc6_enabled())
 		return 0;
 
-	intel_runtime_pm_get(dev_priv);
-
 	/* On VLV and CHV, residency time is in CZ units rather than 1.28us */
 	if (IS_VALLEYVIEW(dev_priv) || IS_CHERRYVIEW(dev_priv)) {
-		units = 1000;
+		mul = 1000000;
 		div = dev_priv->czclk_freq;
-
 		time_hw = vlv_residency_raw(dev_priv, reg);
-	} else if (IS_GEN9_LP(dev_priv)) {
-		units = 1000;
-		div = 1200;		/* 833.33ns */
 
-		time_hw = I915_READ(reg);
 	} else {
-		units = 128000; /* 1.28us */
-		div = 100000;
+		/* 833.33ns units on Gen9LP, 1.28us elsewhere. */
+		if (IS_GEN9_LP(dev_priv)) {
+			mul = 10000;
+			div = 12;
+		} else {
+			mul = 1280;
+			div = 1;
+		}
 
 		time_hw = I915_READ(reg);
 	}
 
-	intel_runtime_pm_put(dev_priv);
-	return DIV_ROUND_UP_ULL(time_hw * units, div);
+	return DIV_ROUND_UP_ULL(time_hw * mul, div);
 }
 
 u32 intel_get_cagf(struct drm_i915_private *dev_priv, u32 rpstat)

index 97d489565cd1..5d2c83a41b53 100644
@@ -361,6 +361,15 @@ static int i915_pmu_event_init(struct perf_event *event)
 			break;
 		case I915_PMU_INTERRUPTS:
 			break;
+		case I915_PMU_RC6_RESIDENCY:
+			if (!HAS_RC6(i915))
+				ret = -ENODEV;
+			break;
+		case I915_PMU_RC6p_RESIDENCY:
+		case I915_PMU_RC6pp_RESIDENCY:
+			if (!HAS_RC6p(i915))
+				ret = -ENODEV;
+			break;
 		default:
 			ret = -ENOENT;
 			break;

@@ -413,6 +422,24 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 		case I915_PMU_INTERRUPTS:
 			val = count_interrupts(i915);
 			break;
+		case I915_PMU_RC6_RESIDENCY:
+			intel_runtime_pm_get(i915);
+			val = intel_rc6_residency_ns(i915,
+						     IS_VALLEYVIEW(i915) ?
+						     VLV_GT_RENDER_RC6 :
+						     GEN6_GT_GFX_RC6);
+			intel_runtime_pm_put(i915);
+			break;
+		case I915_PMU_RC6p_RESIDENCY:
+			intel_runtime_pm_get(i915);
+			val = intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6p);
+			intel_runtime_pm_put(i915);
+			break;
+		case I915_PMU_RC6pp_RESIDENCY:
+			intel_runtime_pm_get(i915);
+			val = intel_rc6_residency_ns(i915, GEN6_GT_GFX_RC6pp);
+			intel_runtime_pm_put(i915);
+			break;
 		}
 	}
 

@@ -669,6 +696,10 @@ static struct attribute *i915_pmu_events_attrs[] = {
 
 	I915_EVENT_ATTR(interrupts, I915_PMU_INTERRUPTS),
 
+	I915_EVENT(rc6-residency,   I915_PMU_RC6_RESIDENCY,   "ns"),
+	I915_EVENT(rc6p-residency,  I915_PMU_RC6p_RESIDENCY,  "ns"),
+	I915_EVENT(rc6pp-residency, I915_PMU_RC6pp_RESIDENCY, "ns"),
+
 	NULL,
 };
 

index 8aceb7f57e0c..709f28fc0970 100644
@@ -134,7 +134,11 @@ enum drm_i915_pmu_engine_sample {
 
 #define I915_PMU_INTERRUPTS		__I915_PMU_OTHER(2)
 
-#define I915_PMU_LAST I915_PMU_INTERRUPTS
+#define I915_PMU_RC6_RESIDENCY		__I915_PMU_OTHER(3)
+#define I915_PMU_RC6p_RESIDENCY		__I915_PMU_OTHER(4)
+#define I915_PMU_RC6pp_RESIDENCY	__I915_PMU_OTHER(5)
+
+#define I915_PMU_LAST I915_PMU_RC6pp_RESIDENCY
 
 /* Each region is a minimum of 16k, and there are at most 255 of them.
  */