Backmerge tag 'v5.17-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux into drm-next

Daniel asked for this for some intel deps, so let's do it now.

Signed-off-by: Dave Airlie <airlied@redhat.com>

5 files changed, 120 insertions, 24 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
index 355a7b68fdac..54cae821513b 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_execbuffer.c
@@ -2507,9 +2507,14 @@ static int eb_pin_timeline(struct i915_execbuffer *eb, struct intel_context *ce,
 				      timeout) < 0) {
 			i915_request_put(rq);
 
-			tl = intel_context_timeline_lock(ce);
+			/*
+			 * Error path, cannot use intel_context_timeline_lock as
+			 * that is user interruptable and this clean up step
+			 * must be done.
+			 */
+			mutex_lock(&ce->timeline->mutex);
 			intel_context_exit(ce);
-			intel_context_timeline_unlock(tl);
+			mutex_unlock(&ce->timeline->mutex);
 
 			if (nonblock)
 				return -EWOULDBLOCK;
diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
index ee9612a3ee5e..e130c820ae4e 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm_move.c
@@ -427,11 +427,17 @@ __i915_ttm_move(struct ttm_buffer_object *bo,
 
 		if (!IS_ERR(fence))
 			goto out;
-	} else if (move_deps) {
-		int err = i915_deps_sync(move_deps, ctx);
+	} else {
+		int err = PTR_ERR(fence);
+
+		if (err == -EINTR || err == -ERESTARTSYS || err == -EAGAIN)
+			return fence;
 
-		if (err)
-			return ERR_PTR(err);
+		if (move_deps) {
+			err = i915_deps_sync(move_deps, ctx);
+			if (err)
+				return ERR_PTR(err);
+		}
 	}
 
 	/* Error intercept failed or no accelerated migration to start with */
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc.h b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
index f9240d4baa69..3aabe164c329 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc.h
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc.h
@@ -206,6 +206,11 @@ struct intel_guc {
 		 * context usage for overflows.
 		 */
 		struct delayed_work work;
+
+		/**
+		 * @shift: Right shift value for the gpm timestamp
+		 */
+		u32 shift;
 	} timestamp;
 
 #ifdef CONFIG_DRM_I915_SELFTEST
diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
index 0cb51c5bb765..04b8321fc758 100644
--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
@@ -1115,6 +1115,19 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start)
 	if (new_start == lower_32_bits(*prev_start))
 		return;
 
+	/*
+	 * When gt is unparked, we update the gt timestamp and start the ping
+	 * worker that updates the gt_stamp every POLL_TIME_CLKS. As long as gt
+	 * is unparked, all switched in contexts will have a start time that is
+	 * within +/- POLL_TIME_CLKS of the most recent gt_stamp.
+	 *
+	 * If neither gt_stamp nor new_start has rolled over, then the
+	 * gt_stamp_hi does not need to be adjusted, however if one of them has
+	 * rolled over, we need to adjust gt_stamp_hi accordingly.
+	 *
+	 * The below conditions address the cases of new_start rollover and
+	 * gt_stamp_last rollover respectively.
+	 */
 	if (new_start < gt_stamp_last &&
 	    (new_start - gt_stamp_last) <= POLL_TIME_CLKS)
 		gt_stamp_hi++;
@@ -1126,17 +1139,45 @@ __extend_last_switch(struct intel_guc *guc, u64 *prev_start, u32 new_start)
 	*prev_start = ((u64)gt_stamp_hi << 32) | new_start;
 }
 
-static void guc_update_engine_gt_clks(struct intel_engine_cs *engine)
+/*
+ * GuC updates shared memory and KMD reads it. Since this is not synchronized,
+ * we run into a race where the value read is inconsistent. Sometimes the
+ * inconsistency is in reading the upper MSB bytes of the last_in value when
+ * this race occurs. 2 types of cases are seen - upper 8 bits are zero and upper
+ * 24 bits are zero. Since these are non-zero values, it is non-trivial to
+ * determine validity of these values. Instead we read the values multiple times
+ * until they are consistent. In test runs, 3 attempts results in consistent
+ * values. The upper bound is set to 6 attempts and may need to be tuned as per
+ * any new occurences.
+ */
+static void __get_engine_usage_record(struct intel_engine_cs *engine,
+				      u32 *last_in, u32 *id, u32 *total)
 {
 	struct guc_engine_usage_record *rec = intel_guc_engine_usage(engine);
+	int i = 0;
+
+	do {
+		*last_in = READ_ONCE(rec->last_switch_in_stamp);
+		*id = READ_ONCE(rec->current_context_index);
+		*total = READ_ONCE(rec->total_runtime);
+
+		if (READ_ONCE(rec->last_switch_in_stamp) == *last_in &&
+		    READ_ONCE(rec->current_context_index) == *id &&
+		    READ_ONCE(rec->total_runtime) == *total)
+			break;
+	} while (++i < 6);
+}
+
+static void guc_update_engine_gt_clks(struct intel_engine_cs *engine)
+{
 	struct intel_engine_guc_stats *stats = &engine->stats.guc;
 	struct intel_guc *guc = &engine->gt->uc.guc;
-	u32 last_switch = rec->last_switch_in_stamp;
-	u32 ctx_id = rec->current_context_index;
-	u32 total = rec->total_runtime;
+	u32 last_switch, ctx_id, total;
 
 	lockdep_assert_held(&guc->timestamp.lock);
 
+	__get_engine_usage_record(engine, &last_switch, &ctx_id, &total);
+
 	stats->running = ctx_id != ~0U && last_switch;
 	if (stats->running)
 		__extend_last_switch(guc, &stats->start_gt_clk, last_switch);
@@ -1151,23 +1192,51 @@ static void guc_update_engine_gt_clks(struct intel_engine_cs *engine)
 	}
 }
 
-static void guc_update_pm_timestamp(struct intel_guc *guc,
-				    struct intel_engine_cs *engine,
-				    ktime_t *now)
+static u32 gpm_timestamp_shift(struct intel_gt *gt)
+{
+	intel_wakeref_t wakeref;
+	u32 reg, shift;
+
+	with_intel_runtime_pm(gt->uncore->rpm, wakeref)
+		reg = intel_uncore_read(gt->uncore, RPM_CONFIG0);
+
+	shift = (reg & GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_MASK) >>
+		GEN10_RPM_CONFIG0_CTC_SHIFT_PARAMETER_SHIFT;
+
+	return 3 - shift;
+}
+
+static u64 gpm_timestamp(struct intel_gt *gt)
+{
+	u32 lo, hi, old_hi, loop = 0;
+
+	hi = intel_uncore_read(gt->uncore, MISC_STATUS1);
+	do {
+		lo = intel_uncore_read(gt->uncore, MISC_STATUS0);
+		old_hi = hi;
+		hi = intel_uncore_read(gt->uncore, MISC_STATUS1);
+	} while (old_hi != hi && loop++ < 2);
+
+	return ((u64)hi << 32) | lo;
+}
+
+static void guc_update_pm_timestamp(struct intel_guc *guc, ktime_t *now)
 {
-	u32 gt_stamp_now, gt_stamp_hi;
+	struct intel_gt *gt = guc_to_gt(guc);
+	u32 gt_stamp_lo, gt_stamp_hi;
+	u64 gpm_ts;
 
 	lockdep_assert_held(&guc->timestamp.lock);
 
 	gt_stamp_hi = upper_32_bits(guc->timestamp.gt_stamp);
-	gt_stamp_now = intel_uncore_read(engine->uncore,
-					 RING_TIMESTAMP(engine->mmio_base));
+	gpm_ts = gpm_timestamp(gt) >> guc->timestamp.shift;
+	gt_stamp_lo = lower_32_bits(gpm_ts);
 	*now = ktime_get();
 
-	if (gt_stamp_now < lower_32_bits(guc->timestamp.gt_stamp))
+	if (gt_stamp_lo < lower_32_bits(guc->timestamp.gt_stamp))
 		gt_stamp_hi++;
 
-	guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_now;
+	guc->timestamp.gt_stamp = ((u64)gt_stamp_hi << 32) | gt_stamp_lo;
 }
 
 /*
@@ -1210,8 +1279,12 @@ static ktime_t guc_engine_busyness(struct intel_engine_cs *engine, ktime_t *now)
 	if (!in_reset && intel_gt_pm_get_if_awake(gt)) {
 		stats_saved = *stats;
 		gt_stamp_saved = guc->timestamp.gt_stamp;
+		/*
+		 * Update gt_clks, then gt timestamp to simplify the 'gt_stamp -
+		 * start_gt_clk' calculation below for active engines.
+		 */
 		guc_update_engine_gt_clks(engine);
-		guc_update_pm_timestamp(guc, engine, now);
+		guc_update_pm_timestamp(guc, now);
 		intel_gt_pm_put_async(gt);
 		if (i915_reset_count(gpu_error) != reset_count) {
 			*stats = stats_saved;
@@ -1243,8 +1316,8 @@ static void __reset_guc_busyness_stats(struct intel_guc *guc)
 
 	spin_lock_irqsave(&guc->timestamp.lock, flags);
 
+	guc_update_pm_timestamp(guc, &unused);
 	for_each_engine(engine, gt, id) {
-		guc_update_pm_timestamp(guc, engine, &unused);
 		guc_update_engine_gt_clks(engine);
 		engine->stats.guc.prev_total = 0;
 	}
@@ -1261,10 +1334,11 @@ static void __update_guc_busyness_stats(struct intel_guc *guc)
 	ktime_t unused;
 
 	spin_lock_irqsave(&guc->timestamp.lock, flags);
-	for_each_engine(engine, gt, id) {
-		guc_update_pm_timestamp(guc, engine, &unused);
+
+	guc_update_pm_timestamp(guc, &unused);
+	for_each_engine(engine, gt, id)
 		guc_update_engine_gt_clks(engine);
-	}
+
 	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
 }
 
@@ -1337,10 +1411,15 @@ void intel_guc_busyness_park(struct intel_gt *gt)
 void intel_guc_busyness_unpark(struct intel_gt *gt)
 {
 	struct intel_guc *guc = &gt->uc.guc;
+	unsigned long flags;
+	ktime_t unused;
 
 	if (!guc_submission_initialized(guc))
 		return;
 
+	spin_lock_irqsave(&guc->timestamp.lock, flags);
+	guc_update_pm_timestamp(guc, &unused);
+	spin_unlock_irqrestore(&guc->timestamp.lock, flags);
 	mod_delayed_work(system_highpri_wq, &guc->timestamp.work,
 			 guc->timestamp.ping_delay);
 }
@@ -1785,6 +1864,7 @@ int intel_guc_submission_init(struct intel_guc *guc)
 	spin_lock_init(&guc->timestamp.lock);
 	INIT_DELAYED_WORK(&guc->timestamp.work, guc_timestamp_ping);
 	guc->timestamp.ping_delay = (POLL_TIME_CLKS / gt->clock_frequency + 1) * HZ;
+	guc->timestamp.shift = gpm_timestamp_shift(gt);
 
 	return 0;
 }
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index ffce5bb8e939..102c7bb747f8 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -1524,7 +1524,7 @@ capture_engine(struct intel_engine_cs *engine,
 	struct i915_request *rq = NULL;
 	unsigned long flags;
 
-	ee = intel_engine_coredump_alloc(engine, GFP_KERNEL);
+	ee = intel_engine_coredump_alloc(engine, ALLOW_FAIL);
 	if (!ee)
 		return NULL;