1 files changed, 205 insertions, 85 deletions

diff --git a/drivers/gpu/drm/i915/i915_pmu.c b/drivers/gpu/drm/i915/i915_pmu.c
index 7ece883a7d95..a814583e19fd 100644
--- a/drivers/gpu/drm/i915/i915_pmu.c
+++ b/drivers/gpu/drm/i915/i915_pmu.c
@@ -10,6 +10,7 @@
 #include "gt/intel_engine_pm.h"
 #include "gt/intel_engine_regs.h"
 #include "gt/intel_engine_user.h"
+#include "gt/intel_gt.h"
 #include "gt/intel_gt_pm.h"
 #include "gt/intel_gt_regs.h"
 #include "gt/intel_rc6.h"
@@ -50,16 +51,26 @@ static u8 engine_event_instance(struct perf_event *event)
 	return (event->attr.config >> I915_PMU_SAMPLE_BITS) & 0xff;
 }
 
-static bool is_engine_config(u64 config)
+static bool is_engine_config(const u64 config)
 {
 	return config < __I915_PMU_OTHER(0);
 }
 
+static unsigned int config_gt_id(const u64 config)
+{
+	return config >> __I915_PMU_GT_SHIFT;
+}
+
+static u64 config_counter(const u64 config)
+{
+	return config & ~(~0ULL << __I915_PMU_GT_SHIFT);
+}
+
 static unsigned int other_bit(const u64 config)
 {
 	unsigned int val;
 
-	switch (config) {
+	switch (config_counter(config)) {
 	case I915_PMU_ACTUAL_FREQUENCY:
 		val =  __I915_PMU_ACTUAL_FREQUENCY_ENABLED;
 		break;
@@ -77,7 +88,9 @@ static unsigned int other_bit(const u64 config)
 		return -1;
 	}
 
-	return I915_ENGINE_SAMPLE_COUNT + val;
+	return I915_ENGINE_SAMPLE_COUNT +
+	       config_gt_id(config) * __I915_PMU_TRACKED_EVENT_COUNT +
+	       val;
 }
 
 static unsigned int config_bit(const u64 config)
@@ -88,9 +101,20 @@ static unsigned int config_bit(const u64 config)
 		return other_bit(config);
 }
 
-static u64 config_mask(u64 config)
+static u32 config_mask(const u64 config)
 {
-	return BIT_ULL(config_bit(config));
+	unsigned int bit = config_bit(config);
+
+	if (__builtin_constant_p(config))
+		BUILD_BUG_ON(bit >
+			     BITS_PER_TYPE(typeof_member(struct i915_pmu,
+							 enable)) - 1);
+	else
+		WARN_ON_ONCE(bit >
+			     BITS_PER_TYPE(typeof_member(struct i915_pmu,
+							 enable)) - 1);
+
+	return BIT(config_bit(config));
 }
 
 static bool is_engine_event(struct perf_event *event)
@@ -103,6 +127,18 @@ static unsigned int event_bit(struct perf_event *event)
 	return config_bit(event->attr.config);
 }
 
+static u32 frequency_enabled_mask(void)
+{
+	unsigned int i;
+	u32 mask = 0;
+
+	for (i = 0; i < I915_PMU_MAX_GTS; i++)
+		mask |= config_mask(__I915_PMU_ACTUAL_FREQUENCY(i)) |
+			config_mask(__I915_PMU_REQUESTED_FREQUENCY(i));
+
+	return mask;
+}
+
 static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active)
 {
 	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
@@ -119,9 +155,7 @@ static bool pmu_needs_timer(struct i915_pmu *pmu, bool gpu_active)
 	 * Mask out all the ones which do not need the timer, or in
 	 * other words keep all the ones that could need the timer.
 	 */
-	enable &= config_mask(I915_PMU_ACTUAL_FREQUENCY) |
-		  config_mask(I915_PMU_REQUESTED_FREQUENCY) |
-		  ENGINE_SAMPLE_MASK;
+	enable &= frequency_enabled_mask() | ENGINE_SAMPLE_MASK;
 
 	/*
 	 * When the GPU is idle per-engine counters do not need to be
@@ -163,9 +197,37 @@ static inline s64 ktime_since_raw(const ktime_t kt)
 	return ktime_to_ns(ktime_sub(ktime_get_raw(), kt));
 }
 
+static unsigned int
+__sample_idx(struct i915_pmu *pmu, unsigned int gt_id, int sample)
+{
+	unsigned int idx = gt_id * __I915_NUM_PMU_SAMPLERS + sample;
+
+	GEM_BUG_ON(idx >= ARRAY_SIZE(pmu->sample));
+
+	return idx;
+}
+
+static u64 read_sample(struct i915_pmu *pmu, unsigned int gt_id, int sample)
+{
+	return pmu->sample[__sample_idx(pmu, gt_id, sample)].cur;
+}
+
+static void
+store_sample(struct i915_pmu *pmu, unsigned int gt_id, int sample, u64 val)
+{
+	pmu->sample[__sample_idx(pmu, gt_id, sample)].cur = val;
+}
+
+static void
+add_sample_mult(struct i915_pmu *pmu, unsigned int gt_id, int sample, u32 val, u32 mul)
+{
+	pmu->sample[__sample_idx(pmu, gt_id, sample)].cur += mul_u32_u32(val, mul);
+}
+
 static u64 get_rc6(struct intel_gt *gt)
 {
 	struct drm_i915_private *i915 = gt->i915;
+	const unsigned int gt_id = gt->info.id;
 	struct i915_pmu *pmu = &i915->pmu;
 	unsigned long flags;
 	bool awake = false;
@@ -180,7 +242,7 @@ static u64 get_rc6(struct intel_gt *gt)
 	spin_lock_irqsave(&pmu->lock, flags);
 
 	if (awake) {
-		pmu->sample[__I915_SAMPLE_RC6].cur = val;
+		store_sample(pmu, gt_id, __I915_SAMPLE_RC6, val);
 	} else {
 		/*
 		 * We think we are runtime suspended.
@@ -189,14 +251,14 @@ static u64 get_rc6(struct intel_gt *gt)
 		 * on top of the last known real value, as the approximated RC6
 		 * counter value.
 		 */
-		val = ktime_since_raw(pmu->sleep_last);
-		val += pmu->sample[__I915_SAMPLE_RC6].cur;
+		val = ktime_since_raw(pmu->sleep_last[gt_id]);
+		val += read_sample(pmu, gt_id, __I915_SAMPLE_RC6);
 	}
 
-	if (val < pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur)
-		val = pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur;
+	if (val < read_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED))
+		val = read_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED);
 	else
-		pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur = val;
+		store_sample(pmu, gt_id, __I915_SAMPLE_RC6_LAST_REPORTED, val);
 
 	spin_unlock_irqrestore(&pmu->lock, flags);
 
@@ -206,22 +268,29 @@ static u64 get_rc6(struct intel_gt *gt)
 static void init_rc6(struct i915_pmu *pmu)
 {
 	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
-	intel_wakeref_t wakeref;
+	struct intel_gt *gt;
+	unsigned int i;
 
-	with_intel_runtime_pm(to_gt(i915)->uncore->rpm, wakeref) {
-		pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(to_gt(i915));
-		pmu->sample[__I915_SAMPLE_RC6_LAST_REPORTED].cur =
-					pmu->sample[__I915_SAMPLE_RC6].cur;
-		pmu->sleep_last = ktime_get_raw();
+	for_each_gt(gt, i915, i) {
+		intel_wakeref_t wakeref;
+
+		with_intel_runtime_pm(gt->uncore->rpm, wakeref) {
+			u64 val = __get_rc6(gt);
+
+			store_sample(pmu, i, __I915_SAMPLE_RC6, val);
+			store_sample(pmu, i, __I915_SAMPLE_RC6_LAST_REPORTED,
+				     val);
+			pmu->sleep_last[i] = ktime_get_raw();
+		}
 	}
 }
 
-static void park_rc6(struct drm_i915_private *i915)
+static void park_rc6(struct intel_gt *gt)
 {
-	struct i915_pmu *pmu = &i915->pmu;
+	struct i915_pmu *pmu = &gt->i915->pmu;
 
-	pmu->sample[__I915_SAMPLE_RC6].cur = __get_rc6(to_gt(i915));
-	pmu->sleep_last = ktime_get_raw();
+	store_sample(pmu, gt->info.id, __I915_SAMPLE_RC6, __get_rc6(gt));
+	pmu->sleep_last[gt->info.id] = ktime_get_raw();
 }
 
 static void __i915_pmu_maybe_start_timer(struct i915_pmu *pmu)
@@ -235,29 +304,31 @@ static void __i915_pmu_maybe_start_timer(struct i915_pmu *pmu)
 	}
 }
 
-void i915_pmu_gt_parked(struct drm_i915_private *i915)
+void i915_pmu_gt_parked(struct intel_gt *gt)
 {
-	struct i915_pmu *pmu = &i915->pmu;
+	struct i915_pmu *pmu = &gt->i915->pmu;
 
 	if (!pmu->base.event_init)
 		return;
 
 	spin_lock_irq(&pmu->lock);
 
-	park_rc6(i915);
+	park_rc6(gt);
 
 	/*
 	 * Signal sampling timer to stop if only engine events are enabled and
 	 * GPU went idle.
 	 */
-	pmu->timer_enabled = pmu_needs_timer(pmu, false);
+	pmu->unparked &= ~BIT(gt->info.id);
+	if (pmu->unparked == 0)
+		pmu->timer_enabled = pmu_needs_timer(pmu, false);
 
 	spin_unlock_irq(&pmu->lock);
 }
 
-void i915_pmu_gt_unparked(struct drm_i915_private *i915)
+void i915_pmu_gt_unparked(struct intel_gt *gt)
 {
-	struct i915_pmu *pmu = &i915->pmu;
+	struct i915_pmu *pmu = &gt->i915->pmu;
 
 	if (!pmu->base.event_init)
 		return;
@@ -267,7 +338,10 @@ void i915_pmu_gt_unparked(struct drm_i915_private *i915)
 	/*
 	 * Re-enable sampling timer when GPU goes active.
 	 */
-	__i915_pmu_maybe_start_timer(pmu);
+	if (pmu->unparked == 0)
+		__i915_pmu_maybe_start_timer(pmu);
+
+	pmu->unparked |= BIT(gt->info.id);
 
 	spin_unlock_irq(&pmu->lock);
 }
@@ -338,6 +412,9 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 		return;
 
 	for_each_engine(engine, gt, id) {
+		if (!engine->pmu.enable)
+			continue;
+
 		if (!intel_engine_pm_get_if_awake(engine))
 			continue;
 
@@ -353,34 +430,30 @@ engines_sample(struct intel_gt *gt, unsigned int period_ns)
 	}
 }
 
-static void
-add_sample_mult(struct i915_pmu_sample *sample, u32 val, u32 mul)
-{
-	sample->cur += mul_u32_u32(val, mul);
-}
-
-static bool frequency_sampling_enabled(struct i915_pmu *pmu)
+static bool
+frequency_sampling_enabled(struct i915_pmu *pmu, unsigned int gt)
 {
 	return pmu->enable &
-	       (config_mask(I915_PMU_ACTUAL_FREQUENCY) |
-		config_mask(I915_PMU_REQUESTED_FREQUENCY));
+	       (config_mask(__I915_PMU_ACTUAL_FREQUENCY(gt)) |
+		config_mask(__I915_PMU_REQUESTED_FREQUENCY(gt)));
 }
 
 static void
 frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 {
 	struct drm_i915_private *i915 = gt->i915;
+	const unsigned int gt_id = gt->info.id;
 	struct i915_pmu *pmu = &i915->pmu;
 	struct intel_rps *rps = &gt->rps;
 
-	if (!frequency_sampling_enabled(pmu))
+	if (!frequency_sampling_enabled(pmu, gt_id))
 		return;
 
 	/* Report 0/0 (actual/requested) frequency while parked. */
 	if (!intel_gt_pm_get_if_awake(gt))
 		return;
 
-	if (pmu->enable & config_mask(I915_PMU_ACTUAL_FREQUENCY)) {
+	if (pmu->enable & config_mask(__I915_PMU_ACTUAL_FREQUENCY(gt_id))) {
 		u32 val;
 
 		/*
@@ -396,12 +469,12 @@ frequency_sample(struct intel_gt *gt, unsigned int period_ns)
 		if (!val)
 			val = intel_gpu_freq(rps, rps->cur_freq);
 
-		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_ACT],
+		add_sample_mult(pmu, gt_id, __I915_SAMPLE_FREQ_ACT,
 				val, period_ns / 1000);
 	}
 
-	if (pmu->enable & config_mask(I915_PMU_REQUESTED_FREQUENCY)) {
-		add_sample_mult(&pmu->sample[__I915_SAMPLE_FREQ_REQ],
+	if (pmu->enable & config_mask(__I915_PMU_REQUESTED_FREQUENCY(gt_id))) {
+		add_sample_mult(pmu, gt_id, __I915_SAMPLE_FREQ_REQ,
 				intel_rps_get_requested_frequency(rps),
 				period_ns / 1000);
 	}
@@ -414,8 +487,9 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 	struct drm_i915_private *i915 =
 		container_of(hrtimer, struct drm_i915_private, pmu.timer);
 	struct i915_pmu *pmu = &i915->pmu;
-	struct intel_gt *gt = to_gt(i915);
 	unsigned int period_ns;
+	struct intel_gt *gt;
+	unsigned int i;
 	ktime_t now;
 
 	if (!READ_ONCE(pmu->timer_enabled))
@@ -431,8 +505,14 @@ static enum hrtimer_restart i915_sample(struct hrtimer *hrtimer)
 	 * grabbing the forcewake. However the potential error from timer call-
 	 * back delay greatly dominates this so we keep it simple.
 	 */
-	engines_sample(gt, period_ns);
-	frequency_sample(gt, period_ns);
+
+	for_each_gt(gt, i915, i) {
+		if (!(pmu->unparked & BIT(i)))
+			continue;
+
+		engines_sample(gt, period_ns);
+		frequency_sample(gt, period_ns);
+	}
 
 	hrtimer_forward(hrtimer, now, ns_to_ktime(PERIOD));
 
@@ -473,7 +553,13 @@ config_status(struct drm_i915_private *i915, u64 config)
 {
 	struct intel_gt *gt = to_gt(i915);
 
-	switch (config) {
+	unsigned int gt_id = config_gt_id(config);
+	unsigned int max_gt_id = HAS_EXTRA_GT_LIST(i915) ? 1 : 0;
+
+	if (gt_id > max_gt_id)
+		return -ENOENT;
+
+	switch (config_counter(config)) {
 	case I915_PMU_ACTUAL_FREQUENCY:
 		if (IS_VALLEYVIEW(i915) || IS_CHERRYVIEW(i915))
 			/* Requires a mutex for sampling! */
@@ -484,6 +570,8 @@ config_status(struct drm_i915_private *i915, u64 config)
 			return -ENODEV;
 		break;
 	case I915_PMU_INTERRUPTS:
+		if (gt_id)
+			return -ENOENT;
 		break;
 	case I915_PMU_RC6_RESIDENCY:
 		if (!gt->rc6.supported)
@@ -581,22 +669,27 @@ static u64 __i915_pmu_event_read(struct perf_event *event)
 			val = engine->pmu.sample[sample].cur;
 		}
 	} else {
-		switch (event->attr.config) {
+		const unsigned int gt_id = config_gt_id(event->attr.config);
+		const u64 config = config_counter(event->attr.config);
+
+		switch (config) {
 		case I915_PMU_ACTUAL_FREQUENCY:
 			val =
-			   div_u64(pmu->sample[__I915_SAMPLE_FREQ_ACT].cur,
+			   div_u64(read_sample(pmu, gt_id,
+					       __I915_SAMPLE_FREQ_ACT),
 				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_REQUESTED_FREQUENCY:
 			val =
-			   div_u64(pmu->sample[__I915_SAMPLE_FREQ_REQ].cur,
+			   div_u64(read_sample(pmu, gt_id,
+					       __I915_SAMPLE_FREQ_REQ),
 				   USEC_PER_SEC /* to MHz */);
 			break;
 		case I915_PMU_INTERRUPTS:
 			val = READ_ONCE(pmu->irq_count);
 			break;
 		case I915_PMU_RC6_RESIDENCY:
-			val = get_rc6(to_gt(i915));
+			val = get_rc6(i915->gt[gt_id]);
 			break;
 		case I915_PMU_SOFTWARE_GT_AWAKE_TIME:
 			val = ktime_to_ns(intel_gt_get_awake_time(to_gt(i915)));
@@ -633,11 +726,10 @@ static void i915_pmu_enable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
 		container_of(event->pmu, typeof(*i915), pmu.base);
+	const unsigned int bit = event_bit(event);
 	struct i915_pmu *pmu = &i915->pmu;
 	unsigned long flags;
-	unsigned int bit;
 
-	bit = event_bit(event);
 	if (bit == -1)
 		goto update;
 
@@ -651,7 +743,7 @@ static void i915_pmu_enable(struct perf_event *event)
 	GEM_BUG_ON(bit >= ARRAY_SIZE(pmu->enable_count));
 	GEM_BUG_ON(pmu->enable_count[bit] == ~0);
 
-	pmu->enable |= BIT_ULL(bit);
+	pmu->enable |= BIT(bit);
 	pmu->enable_count[bit]++;
 
 	/*
@@ -698,7 +790,7 @@ static void i915_pmu_disable(struct perf_event *event)
 {
 	struct drm_i915_private *i915 =
 		container_of(event->pmu, typeof(*i915), pmu.base);
-	unsigned int bit = event_bit(event);
+	const unsigned int bit = event_bit(event);
 	struct i915_pmu *pmu = &i915->pmu;
 	unsigned long flags;
 
@@ -734,7 +826,7 @@ static void i915_pmu_disable(struct perf_event *event)
 	 * bitmask when the last listener on an event goes away.
 	 */
 	if (--pmu->enable_count[bit] == 0) {
-		pmu->enable &= ~BIT_ULL(bit);
+		pmu->enable &= ~BIT(bit);
 		pmu->timer_enabled &= pmu_needs_timer(pmu, true);
 	}
 
@@ -848,11 +940,20 @@ static const struct attribute_group i915_pmu_cpumask_attr_group = {
 	.attrs = i915_cpumask_attrs,
 };
 
-#define __event(__config, __name, __unit) \
+#define __event(__counter, __name, __unit) \
 { \
-	.config = (__config), \
+	.counter = (__counter), \
 	.name = (__name), \
 	.unit = (__unit), \
+	.global = false, \
+}
+
+#define __global_event(__counter, __name, __unit) \
+{ \
+	.counter = (__counter), \
+	.name = (__name), \
+	.unit = (__unit), \
+	.global = true, \
 }
 
 #define __engine_event(__sample, __name) \
@@ -891,15 +992,16 @@ create_event_attributes(struct i915_pmu *pmu)
 {
 	struct drm_i915_private *i915 = container_of(pmu, typeof(*i915), pmu);
 	static const struct {
-		u64 config;
+		unsigned int counter;
 		const char *name;
 		const char *unit;
+		bool global;
 	} events[] = {
-		__event(I915_PMU_ACTUAL_FREQUENCY, "actual-frequency", "M"),
-		__event(I915_PMU_REQUESTED_FREQUENCY, "requested-frequency", "M"),
-		__event(I915_PMU_INTERRUPTS, "interrupts", NULL),
-		__event(I915_PMU_RC6_RESIDENCY, "rc6-residency", "ns"),
-		__event(I915_PMU_SOFTWARE_GT_AWAKE_TIME, "software-gt-awake-time", "ns"),
+		__event(0, "actual-frequency", "M"),
+		__event(1, "requested-frequency", "M"),
+		__global_event(2, "interrupts", NULL),
+		__event(3, "rc6-residency", "ns"),
+		__event(4, "software-gt-awake-time", "ns"),
 	};
 	static const struct {
 		enum drm_i915_pmu_engine_sample sample;
@@ -914,12 +1016,17 @@ create_event_attributes(struct i915_pmu *pmu)
 	struct i915_ext_attribute *i915_attr = NULL, *i915_iter;
 	struct attribute **attr = NULL, **attr_iter;
 	struct intel_engine_cs *engine;
-	unsigned int i;
+	struct intel_gt *gt;
+	unsigned int i, j;
 
 	/* Count how many counters we will be exposing. */
-	for (i = 0; i < ARRAY_SIZE(events); i++) {
-		if (!config_status(i915, events[i].config))
-			count++;
+	for_each_gt(gt, i915, j) {
+		for (i = 0; i < ARRAY_SIZE(events); i++) {
+			u64 config = ___I915_PMU_OTHER(j, events[i].counter);
+
+			if (!config_status(i915, config))
+				count++;
+		}
 	}
 
 	for_each_uabi_engine(engine, i915) {
@@ -949,26 +1056,39 @@ create_event_attributes(struct i915_pmu *pmu)
 	attr_iter = attr;
 
 	/* Initialize supported non-engine counters. */
-	for (i = 0; i < ARRAY_SIZE(events); i++) {
-		char *str;
-
-		if (config_status(i915, events[i].config))
-			continue;
-
-		str = kstrdup(events[i].name, GFP_KERNEL);
-		if (!str)
-			goto err;
+	for_each_gt(gt, i915, j) {
+		for (i = 0; i < ARRAY_SIZE(events); i++) {
+			u64 config = ___I915_PMU_OTHER(j, events[i].counter);
+			char *str;
 
-		*attr_iter++ = &i915_iter->attr.attr;
-		i915_iter = add_i915_attr(i915_iter, str, events[i].config);
+			if (config_status(i915, config))
+				continue;
 
-		if (events[i].unit) {
-			str = kasprintf(GFP_KERNEL, "%s.unit", events[i].name);
+			if (events[i].global || !HAS_EXTRA_GT_LIST(i915))
+				str = kstrdup(events[i].name, GFP_KERNEL);
+			else
+				str = kasprintf(GFP_KERNEL, "%s-gt%u",
+						events[i].name, j);
 			if (!str)
 				goto err;
 
-			*attr_iter++ = &pmu_iter->attr.attr;
-			pmu_iter = add_pmu_attr(pmu_iter, str, events[i].unit);
+			*attr_iter++ = &i915_iter->attr.attr;
+			i915_iter = add_i915_attr(i915_iter, str, config);
+
+			if (events[i].unit) {
+				if (events[i].global || !HAS_EXTRA_GT_LIST(i915))
+					str = kasprintf(GFP_KERNEL, "%s.unit",
+							events[i].name);
+				else
+					str = kasprintf(GFP_KERNEL, "%s-gt%u.unit",
+							events[i].name, j);
+				if (!str)
+					goto err;
+
+				*attr_iter++ = &pmu_iter->attr.attr;
+				pmu_iter = add_pmu_attr(pmu_iter, str,
+							events[i].unit);
+			}
 		}
 	}