Merging upstream version 6.10.3.

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

7 files changed, 110 insertions, 118 deletions

diff --git a/drivers/gpu/drm/v3d/v3d_bo.c b/drivers/gpu/drm/v3d/v3d_bo.c
index a07ede668c..a165cbcdd2 100644
--- a/drivers/gpu/drm/v3d/v3d_bo.c
+++ b/drivers/gpu/drm/v3d/v3d_bo.c
@@ -21,6 +21,7 @@
 
 #include <linux/dma-buf.h>
 #include <linux/pfn_t.h>
+#include <linux/vmalloc.h>
 
 #include "v3d_drv.h"
 #include "uapi/drm/v3d_drm.h"
diff --git a/drivers/gpu/drm/v3d/v3d_drv.c b/drivers/gpu/drm/v3d/v3d_drv.c
index 3debf37e7d..28b7ddce77 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.c
+++ b/drivers/gpu/drm/v3d/v3d_drv.c
@@ -115,14 +115,13 @@ v3d_open(struct drm_device *dev, struct drm_file *file)
 	v3d_priv->v3d = v3d;
 
 	for (i = 0; i < V3D_MAX_QUEUES; i++) {
-		v3d_priv->enabled_ns[i] = 0;
-		v3d_priv->start_ns[i] = 0;
-		v3d_priv->jobs_sent[i] = 0;
-
 		sched = &v3d->queue[i].sched;
 		drm_sched_entity_init(&v3d_priv->sched_entity[i],
 				      DRM_SCHED_PRIORITY_NORMAL, &sched,
 				      1, NULL);
+
+		memset(&v3d_priv->stats[i], 0, sizeof(v3d_priv->stats[i]));
+		seqcount_init(&v3d_priv->stats[i].lock);
 	}
 
 	v3d_perfmon_open_file(v3d_priv);
@@ -144,6 +143,20 @@ v3d_postclose(struct drm_device *dev, struct drm_file *file)
 	kfree(v3d_priv);
 }
 
+void v3d_get_stats(const struct v3d_stats *stats, u64 timestamp,
+		   u64 *active_runtime, u64 *jobs_completed)
+{
+	unsigned int seq;
+
+	do {
+		seq = read_seqcount_begin(&stats->lock);
+		*active_runtime = stats->enabled_ns;
+		if (stats->start_ns)
+			*active_runtime += timestamp - stats->start_ns;
+		*jobs_completed = stats->jobs_completed;
+	} while (read_seqcount_retry(&stats->lock, seq));
+}
+
 static void v3d_show_fdinfo(struct drm_printer *p, struct drm_file *file)
 {
 	struct v3d_file_priv *file_priv = file->driver_priv;
@@ -151,20 +164,22 @@ static void v3d_show_fdinfo(struct drm_printer *p, struct drm_file *file)
 	enum v3d_queue queue;
 
 	for (queue = 0; queue < V3D_MAX_QUEUES; queue++) {
+		struct v3d_stats *stats = &file_priv->stats[queue];
+		u64 active_runtime, jobs_completed;
+
+		v3d_get_stats(stats, timestamp, &active_runtime, &jobs_completed);
+
 		/* Note that, in case of a GPU reset, the time spent during an
 		 * attempt of executing the job is not computed in the runtime.
 		 */
 		drm_printf(p, "drm-engine-%s: \t%llu ns\n",
-			   v3d_queue_to_string(queue),
-			   file_priv->start_ns[queue] ? file_priv->enabled_ns[queue]
-						      + timestamp - file_priv->start_ns[queue]
-						      : file_priv->enabled_ns[queue]);
+			   v3d_queue_to_string(queue), active_runtime);
 
 		/* Note that we only count jobs that completed. Therefore, jobs
 		 * that were resubmitted due to a GPU reset are not computed.
 		 */
 		drm_printf(p, "v3d-jobs-%s: \t%llu jobs\n",
-			   v3d_queue_to_string(queue), file_priv->jobs_sent[queue]);
+			   v3d_queue_to_string(queue), jobs_completed);
 	}
 }
 
diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
index 1950c723dd..a2c516fe6d 100644
--- a/drivers/gpu/drm/v3d/v3d_drv.h
+++ b/drivers/gpu/drm/v3d/v3d_drv.h
@@ -36,15 +36,27 @@ static inline char *v3d_queue_to_string(enum v3d_queue queue)
 	return "UNKNOWN";
 }
 
+struct v3d_stats {
+	u64 start_ns;
+	u64 enabled_ns;
+	u64 jobs_completed;
+
+	/*
+	 * This seqcount is used to protect the access to the GPU stats
+	 * variables. It must be used as, while we are reading the stats,
+	 * IRQs can happen and the stats can be updated.
+	 */
+	seqcount_t lock;
+};
+
 struct v3d_queue_state {
 	struct drm_gpu_scheduler sched;
 
 	u64 fence_context;
 	u64 emit_seqno;
 
-	u64 start_ns;
-	u64 enabled_ns;
-	u64 jobs_sent;
+	/* Stores the GPU stats for this queue in the global context. */
+	struct v3d_stats stats;
 };
 
 /* Performance monitor object. The perform lifetime is controlled by userspace
@@ -188,11 +200,8 @@ struct v3d_file_priv {
 
 	struct drm_sched_entity sched_entity[V3D_MAX_QUEUES];
 
-	u64 start_ns[V3D_MAX_QUEUES];
-
-	u64 enabled_ns[V3D_MAX_QUEUES];
-
-	u64 jobs_sent[V3D_MAX_QUEUES];
+	/* Stores the GPU stats for a specific queue for this fd. */
+	struct v3d_stats stats[V3D_MAX_QUEUES];
 };
 
 struct v3d_bo {
@@ -508,6 +517,10 @@ struct drm_gem_object *v3d_prime_import_sg_table(struct drm_device *dev,
 /* v3d_debugfs.c */
 void v3d_debugfs_init(struct drm_minor *minor);
 
+/* v3d_drv.c */
+void v3d_get_stats(const struct v3d_stats *stats, u64 timestamp,
+		   u64 *active_runtime, u64 *jobs_completed);
+
 /* v3d_fence.c */
 extern const struct dma_fence_ops v3d_fence_ops;
 struct dma_fence *v3d_fence_create(struct v3d_dev *v3d, enum v3d_queue queue);
@@ -543,6 +556,7 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo);
 void v3d_mmu_remove_ptes(struct v3d_bo *bo);
 
 /* v3d_sched.c */
+void v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue);
 int v3d_sched_init(struct v3d_dev *v3d);
 void v3d_sched_fini(struct v3d_dev *v3d);
 
diff --git a/drivers/gpu/drm/v3d/v3d_gem.c b/drivers/gpu/drm/v3d/v3d_gem.c
index afc565078c..da8faf3b90 100644
--- a/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/drivers/gpu/drm/v3d/v3d_gem.c
@@ -247,10 +247,11 @@ v3d_gem_init(struct drm_device *dev)
 	int ret, i;
 
 	for (i = 0; i < V3D_MAX_QUEUES; i++) {
-		v3d->queue[i].fence_context = dma_fence_context_alloc(1);
-		v3d->queue[i].start_ns = 0;
-		v3d->queue[i].enabled_ns = 0;
-		v3d->queue[i].jobs_sent = 0;
+		struct v3d_queue_state *queue = &v3d->queue[i];
+
+		queue->fence_context = dma_fence_context_alloc(1);
+		memset(&queue->stats, 0, sizeof(queue->stats));
+		seqcount_init(&queue->stats.lock);
 	}
 
 	spin_lock_init(&v3d->mm_lock);
diff --git a/drivers/gpu/drm/v3d/v3d_irq.c b/drivers/gpu/drm/v3d/v3d_irq.c
index ce6b2fb341..d469bda52c 100644
--- a/drivers/gpu/drm/v3d/v3d_irq.c
+++ b/drivers/gpu/drm/v3d/v3d_irq.c
@@ -102,18 +102,8 @@ v3d_irq(int irq, void *arg)
 	if (intsts & V3D_INT_FLDONE) {
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->bin_job->base.irq_fence);
-		struct v3d_file_priv *file = v3d->bin_job->base.file->driver_priv;
-		u64 runtime = local_clock() - file->start_ns[V3D_BIN];
-
-		file->jobs_sent[V3D_BIN]++;
-		v3d->queue[V3D_BIN].jobs_sent++;
-
-		file->start_ns[V3D_BIN] = 0;
-		v3d->queue[V3D_BIN].start_ns = 0;
-
-		file->enabled_ns[V3D_BIN] += runtime;
-		v3d->queue[V3D_BIN].enabled_ns += runtime;
 
+		v3d_job_update_stats(&v3d->bin_job->base, V3D_BIN);
 		trace_v3d_bcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
 		status = IRQ_HANDLED;
@@ -122,18 +112,8 @@ v3d_irq(int irq, void *arg)
 	if (intsts & V3D_INT_FRDONE) {
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->render_job->base.irq_fence);
-		struct v3d_file_priv *file = v3d->render_job->base.file->driver_priv;
-		u64 runtime = local_clock() - file->start_ns[V3D_RENDER];
-
-		file->jobs_sent[V3D_RENDER]++;
-		v3d->queue[V3D_RENDER].jobs_sent++;
-
-		file->start_ns[V3D_RENDER] = 0;
-		v3d->queue[V3D_RENDER].start_ns = 0;
-
-		file->enabled_ns[V3D_RENDER] += runtime;
-		v3d->queue[V3D_RENDER].enabled_ns += runtime;
 
+		v3d_job_update_stats(&v3d->render_job->base, V3D_RENDER);
 		trace_v3d_rcl_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
 		status = IRQ_HANDLED;
@@ -142,18 +122,8 @@ v3d_irq(int irq, void *arg)
 	if (intsts & V3D_INT_CSDDONE(v3d->ver)) {
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->csd_job->base.irq_fence);
-		struct v3d_file_priv *file = v3d->csd_job->base.file->driver_priv;
-		u64 runtime = local_clock() - file->start_ns[V3D_CSD];
-
-		file->jobs_sent[V3D_CSD]++;
-		v3d->queue[V3D_CSD].jobs_sent++;
-
-		file->start_ns[V3D_CSD] = 0;
-		v3d->queue[V3D_CSD].start_ns = 0;
-
-		file->enabled_ns[V3D_CSD] += runtime;
-		v3d->queue[V3D_CSD].enabled_ns += runtime;
 
+		v3d_job_update_stats(&v3d->csd_job->base, V3D_CSD);
 		trace_v3d_csd_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
 		status = IRQ_HANDLED;
@@ -189,18 +159,8 @@ v3d_hub_irq(int irq, void *arg)
 	if (intsts & V3D_HUB_INT_TFUC) {
 		struct v3d_fence *fence =
 			to_v3d_fence(v3d->tfu_job->base.irq_fence);
-		struct v3d_file_priv *file = v3d->tfu_job->base.file->driver_priv;
-		u64 runtime = local_clock() - file->start_ns[V3D_TFU];
-
-		file->jobs_sent[V3D_TFU]++;
-		v3d->queue[V3D_TFU].jobs_sent++;
-
-		file->start_ns[V3D_TFU] = 0;
-		v3d->queue[V3D_TFU].start_ns = 0;
-
-		file->enabled_ns[V3D_TFU] += runtime;
-		v3d->queue[V3D_TFU].enabled_ns += runtime;
 
+		v3d_job_update_stats(&v3d->tfu_job->base, V3D_TFU);
 		trace_v3d_tfu_irq(&v3d->drm, fence->seqno);
 		dma_fence_signal(&fence->base);
 		status = IRQ_HANDLED;
diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
index 54015ad765..7cd8c335cd 100644
--- a/drivers/gpu/drm/v3d/v3d_sched.c
+++ b/drivers/gpu/drm/v3d/v3d_sched.c
@@ -105,11 +105,51 @@ v3d_switch_perfmon(struct v3d_dev *v3d, struct v3d_job *job)
 		v3d_perfmon_start(v3d, job->perfmon);
 }
 
+static void
+v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue)
+{
+	struct v3d_dev *v3d = job->v3d;
+	struct v3d_file_priv *file = job->file->driver_priv;
+	struct v3d_stats *global_stats = &v3d->queue[queue].stats;
+	struct v3d_stats *local_stats = &file->stats[queue];
+	u64 now = local_clock();
+
+	write_seqcount_begin(&local_stats->lock);
+	local_stats->start_ns = now;
+	write_seqcount_end(&local_stats->lock);
+
+	write_seqcount_begin(&global_stats->lock);
+	global_stats->start_ns = now;
+	write_seqcount_end(&global_stats->lock);
+}
+
+static void
+v3d_stats_update(struct v3d_stats *stats, u64 now)
+{
+	write_seqcount_begin(&stats->lock);
+	stats->enabled_ns += now - stats->start_ns;
+	stats->jobs_completed++;
+	stats->start_ns = 0;
+	write_seqcount_end(&stats->lock);
+}
+
+void
+v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
+{
+	struct v3d_dev *v3d = job->v3d;
+	struct v3d_file_priv *file = job->file->driver_priv;
+	struct v3d_stats *global_stats = &v3d->queue[queue].stats;
+	struct v3d_stats *local_stats = &file->stats[queue];
+	u64 now = local_clock();
+
+	v3d_stats_update(local_stats, now);
+	v3d_stats_update(global_stats, now);
+}
+
 static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_bin_job *job = to_bin_job(sched_job);
 	struct v3d_dev *v3d = job->base.v3d;
-	struct v3d_file_priv *file = job->base.file->driver_priv;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 	unsigned long irqflags;
@@ -141,9 +181,7 @@ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
 	trace_v3d_submit_cl(dev, false, to_v3d_fence(fence)->seqno,
 			    job->start, job->end);
 
-	file->start_ns[V3D_BIN] = local_clock();
-	v3d->queue[V3D_BIN].start_ns = file->start_ns[V3D_BIN];
-
+	v3d_job_start_stats(&job->base, V3D_BIN);
 	v3d_switch_perfmon(v3d, &job->base);
 
 	/* Set the current and end address of the control list.
@@ -168,7 +206,6 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_render_job *job = to_render_job(sched_job);
 	struct v3d_dev *v3d = job->base.v3d;
-	struct v3d_file_priv *file = job->base.file->driver_priv;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 
@@ -196,9 +233,7 @@ static struct dma_fence *v3d_render_job_run(struct drm_sched_job *sched_job)
 	trace_v3d_submit_cl(dev, true, to_v3d_fence(fence)->seqno,
 			    job->start, job->end);
 
-	file->start_ns[V3D_RENDER] = local_clock();
-	v3d->queue[V3D_RENDER].start_ns = file->start_ns[V3D_RENDER];
-
+	v3d_job_start_stats(&job->base, V3D_RENDER);
 	v3d_switch_perfmon(v3d, &job->base);
 
 	/* XXX: Set the QCFG */
@@ -217,7 +252,6 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_tfu_job *job = to_tfu_job(sched_job);
 	struct v3d_dev *v3d = job->base.v3d;
-	struct v3d_file_priv *file = job->base.file->driver_priv;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 
@@ -232,8 +266,7 @@ v3d_tfu_job_run(struct drm_sched_job *sched_job)
 
 	trace_v3d_submit_tfu(dev, to_v3d_fence(fence)->seqno);
 
-	file->start_ns[V3D_TFU] = local_clock();
-	v3d->queue[V3D_TFU].start_ns = file->start_ns[V3D_TFU];
+	v3d_job_start_stats(&job->base, V3D_TFU);
 
 	V3D_WRITE(V3D_TFU_IIA(v3d->ver), job->args.iia);
 	V3D_WRITE(V3D_TFU_IIS(v3d->ver), job->args.iis);
@@ -260,7 +293,6 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_csd_job *job = to_csd_job(sched_job);
 	struct v3d_dev *v3d = job->base.v3d;
-	struct v3d_file_priv *file = job->base.file->driver_priv;
 	struct drm_device *dev = &v3d->drm;
 	struct dma_fence *fence;
 	int i, csd_cfg0_reg, csd_cfg_reg_count;
@@ -279,9 +311,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
 
 	trace_v3d_submit_csd(dev, to_v3d_fence(fence)->seqno);
 
-	file->start_ns[V3D_CSD] = local_clock();
-	v3d->queue[V3D_CSD].start_ns = file->start_ns[V3D_CSD];
-
+	v3d_job_start_stats(&job->base, V3D_CSD);
 	v3d_switch_perfmon(v3d, &job->base);
 
 	csd_cfg0_reg = V3D_CSD_QUEUED_CFG0(v3d->ver);
@@ -530,8 +560,6 @@ v3d_cpu_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_cpu_job *job = to_cpu_job(sched_job);
 	struct v3d_dev *v3d = job->base.v3d;
-	struct v3d_file_priv *file = job->base.file->driver_priv;
-	u64 runtime;
 
 	v3d->cpu_job = job;
 
@@ -540,25 +568,13 @@ v3d_cpu_job_run(struct drm_sched_job *sched_job)
 		return NULL;
 	}
 
-	file->start_ns[V3D_CPU] = local_clock();
-	v3d->queue[V3D_CPU].start_ns = file->start_ns[V3D_CPU];
-
+	v3d_job_start_stats(&job->base, V3D_CPU);
 	trace_v3d_cpu_job_begin(&v3d->drm, job->job_type);
 
 	cpu_job_function[job->job_type](job);
 
 	trace_v3d_cpu_job_end(&v3d->drm, job->job_type);
-
-	runtime = local_clock() - file->start_ns[V3D_CPU];
-
-	file->enabled_ns[V3D_CPU] += runtime;
-	v3d->queue[V3D_CPU].enabled_ns += runtime;
-
-	file->jobs_sent[V3D_CPU]++;
-	v3d->queue[V3D_CPU].jobs_sent++;
-
-	file->start_ns[V3D_CPU] = 0;
-	v3d->queue[V3D_CPU].start_ns = 0;
+	v3d_job_update_stats(&job->base, V3D_CPU);
 
 	return NULL;
 }
@@ -568,24 +584,12 @@ v3d_cache_clean_job_run(struct drm_sched_job *sched_job)
 {
 	struct v3d_job *job = to_v3d_job(sched_job);
 	struct v3d_dev *v3d = job->v3d;
-	struct v3d_file_priv *file = job->file->driver_priv;
-	u64 runtime;
 
-	file->start_ns[V3D_CACHE_CLEAN] = local_clock();
-	v3d->queue[V3D_CACHE_CLEAN].start_ns = file->start_ns[V3D_CACHE_CLEAN];
+	v3d_job_start_stats(job, V3D_CACHE_CLEAN);
 
 	v3d_clean_caches(v3d);
 
-	runtime = local_clock() - file->start_ns[V3D_CACHE_CLEAN];
-
-	file->enabled_ns[V3D_CACHE_CLEAN] += runtime;
-	v3d->queue[V3D_CACHE_CLEAN].enabled_ns += runtime;
-
-	file->jobs_sent[V3D_CACHE_CLEAN]++;
-	v3d->queue[V3D_CACHE_CLEAN].jobs_sent++;
-
-	file->start_ns[V3D_CACHE_CLEAN] = 0;
-	v3d->queue[V3D_CACHE_CLEAN].start_ns = 0;
+	v3d_job_update_stats(job, V3D_CACHE_CLEAN);
 
 	return NULL;
 }
diff --git a/drivers/gpu/drm/v3d/v3d_sysfs.c b/drivers/gpu/drm/v3d/v3d_sysfs.c
index d106845ba8..d610e35596 100644
--- a/drivers/gpu/drm/v3d/v3d_sysfs.c
+++ b/drivers/gpu/drm/v3d/v3d_sysfs.c
@@ -15,16 +15,15 @@ gpu_stats_show(struct device *dev, struct device_attribute *attr, char *buf)
 	struct v3d_dev *v3d = to_v3d_dev(drm);
 	enum v3d_queue queue;
 	u64 timestamp = local_clock();
-	u64 active_runtime;
 	ssize_t len = 0;
 
 	len += sysfs_emit(buf, "queue\ttimestamp\tjobs\truntime\n");
 
 	for (queue = 0; queue < V3D_MAX_QUEUES; queue++) {
-		if (v3d->queue[queue].start_ns)
-			active_runtime = timestamp - v3d->queue[queue].start_ns;
-		else
-			active_runtime = 0;
+		struct v3d_stats *stats = &v3d->queue[queue].stats;
+		u64 active_runtime, jobs_completed;
+
+		v3d_get_stats(stats, timestamp, &active_runtime, &jobs_completed);
 
 		/* Each line will display the queue name, timestamp, the number
 		 * of jobs sent to that queue and the runtime, as can be seem here:
@@ -38,9 +37,7 @@ gpu_stats_show(struct device *dev, struct device_attribute *attr, char *buf)
 		 */
 		len += sysfs_emit_at(buf, len, "%s\t%llu\t%llu\t%llu\n",
 				     v3d_queue_to_string(queue),
-				     timestamp,
-				     v3d->queue[queue].jobs_sent,
-				     v3d->queue[queue].enabled_ns + active_runtime);
+				     timestamp, jobs_completed, active_runtime);
 	}
 
 	return len;