1 files changed, 57 insertions, 140 deletions

diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index fd8cca241da6..c7843e336310 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -45,16 +45,11 @@
  * Cast helper
  */
 static const struct dma_fence_ops amdgpu_fence_ops;
-static const struct dma_fence_ops amdgpu_job_fence_ops;
 static inline struct amdgpu_fence *to_amdgpu_fence(struct dma_fence *f)
 {
 	struct amdgpu_fence *__f = container_of(f, struct amdgpu_fence, base);
 
-	if (__f->base.ops == &amdgpu_fence_ops ||
-	    __f->base.ops == &amdgpu_job_fence_ops)
-		return __f;
-
-	return NULL;
+	return __f;
 }
 
 /**
@@ -98,51 +93,32 @@ static u32 amdgpu_fence_read(struct amdgpu_ring *ring)
  * amdgpu_fence_emit - emit a fence on the requested ring
  *
  * @ring: ring the fence is associated with
- * @f: resulting fence object
  * @af: amdgpu fence input
  * @flags: flags to pass into the subordinate .emit_fence() call
  *
  * Emits a fence command on the requested ring (all asics).
  * Returns 0 on success, -ENOMEM on failure.
  */
-int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
-		      struct amdgpu_fence *af, unsigned int flags)
+int amdgpu_fence_emit(struct amdgpu_ring *ring, struct amdgpu_fence *af,
+		      unsigned int flags)
 {
 	struct amdgpu_device *adev = ring->adev;
 	struct dma_fence *fence;
-	struct amdgpu_fence *am_fence;
 	struct dma_fence __rcu **ptr;
 	uint32_t seq;
 	int r;
 
-	if (!af) {
-		/* create a separate hw fence */
-		am_fence = kzalloc(sizeof(*am_fence), GFP_KERNEL);
-		if (!am_fence)
-			return -ENOMEM;
-	} else {
-		am_fence = af;
-	}
-	fence = &am_fence->base;
-	am_fence->ring = ring;
+	fence = &af->base;
+	af->ring = ring;
 
 	seq = ++ring->fence_drv.sync_seq;
-	am_fence->seq = seq;
-	if (af) {
-		dma_fence_init(fence, &amdgpu_job_fence_ops,
-			       &ring->fence_drv.lock,
-			       adev->fence_context + ring->idx, seq);
-		/* Against remove in amdgpu_job_{free, free_cb} */
-		dma_fence_get(fence);
-	} else {
-		dma_fence_init(fence, &amdgpu_fence_ops,
-			       &ring->fence_drv.lock,
-			       adev->fence_context + ring->idx, seq);
-	}
+	dma_fence_init(fence, &amdgpu_fence_ops,
+		       &ring->fence_drv.lock,
+		       adev->fence_context + ring->idx, seq);
 
 	amdgpu_ring_emit_fence(ring, ring->fence_drv.gpu_addr,
 			       seq, flags | AMDGPU_FENCE_FLAG_INT);
-	amdgpu_fence_save_wptr(fence);
+	amdgpu_fence_save_wptr(af);
 	pm_runtime_get_noresume(adev_to_drm(adev)->dev);
 	ptr = &ring->fence_drv.fences[seq & ring->fence_drv.num_fences_mask];
 	if (unlikely(rcu_dereference_protected(*ptr, 1))) {
@@ -167,8 +143,6 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f,
 	 */
 	rcu_assign_pointer(*ptr, dma_fence_get(fence));
 
-	*f = fence;
-
 	return 0;
 }
 
@@ -276,7 +250,6 @@ bool amdgpu_fence_process(struct amdgpu_ring *ring)
 		drv->signalled_wptr = am_fence->wptr;
 		dma_fence_signal(fence);
 		dma_fence_put(fence);
-		pm_runtime_mark_last_busy(adev_to_drm(adev)->dev);
 		pm_runtime_put_autosuspend(adev_to_drm(adev)->dev);
 	} while (last_seq != seq);
 
@@ -670,36 +643,6 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
 }
 
 /**
- * amdgpu_fence_driver_clear_job_fences - clear job embedded fences of ring
- *
- * @ring: fence of the ring to be cleared
- *
- */
-void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring)
-{
-	int i;
-	struct dma_fence *old, **ptr;
-
-	for (i = 0; i <= ring->fence_drv.num_fences_mask; i++) {
-		ptr = &ring->fence_drv.fences[i];
-		old = rcu_dereference_protected(*ptr, 1);
-		if (old && old->ops == &amdgpu_job_fence_ops) {
-			struct amdgpu_job *job;
-
-			/* For non-scheduler bad job, i.e. failed ib test, we need to signal
-			 * it right here or we won't be able to track them in fence_drv
-			 * and they will remain unsignaled during sa_bo free.
-			 */
-			job = container_of(old, struct amdgpu_job, hw_fence.base);
-			if (!job->base.s_fence && !dma_fence_is_signaled(old))
-				dma_fence_signal(old);
-			RCU_INIT_POINTER(*ptr, NULL);
-			dma_fence_put(old);
-		}
-	}
-}
-
-/**
  * amdgpu_fence_driver_set_error - set error code on fences
  * @ring: the ring which contains the fences
  * @error: the error code to set
@@ -755,21 +698,50 @@ void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring)
 /**
  * amdgpu_fence_driver_guilty_force_completion - force signal of specified sequence
  *
- * @fence: fence of the ring to signal
+ * @af: fence of the ring to signal
  *
  */
-void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *fence)
+void amdgpu_fence_driver_guilty_force_completion(struct amdgpu_fence *af)
 {
-	dma_fence_set_error(&fence->base, -ETIME);
-	amdgpu_fence_write(fence->ring, fence->seq);
-	amdgpu_fence_process(fence->ring);
+	struct dma_fence *unprocessed;
+	struct dma_fence __rcu **ptr;
+	struct amdgpu_fence *fence;
+	struct amdgpu_ring *ring = af->ring;
+	unsigned long flags;
+	u32 seq, last_seq;
+
+	last_seq = amdgpu_fence_read(ring) & ring->fence_drv.num_fences_mask;
+	seq = ring->fence_drv.sync_seq & ring->fence_drv.num_fences_mask;
+
+	/* mark all fences from the guilty context with an error */
+	spin_lock_irqsave(&ring->fence_drv.lock, flags);
+	do {
+		last_seq++;
+		last_seq &= ring->fence_drv.num_fences_mask;
+
+		ptr = &ring->fence_drv.fences[last_seq];
+		rcu_read_lock();
+		unprocessed = rcu_dereference(*ptr);
+
+		if (unprocessed && !dma_fence_is_signaled_locked(unprocessed)) {
+			fence = container_of(unprocessed, struct amdgpu_fence, base);
+
+			if (fence == af)
+				dma_fence_set_error(&fence->base, -ETIME);
+			else if (fence->context == af->context)
+				dma_fence_set_error(&fence->base, -ECANCELED);
+		}
+		rcu_read_unlock();
+	} while (last_seq != seq);
+	spin_unlock_irqrestore(&ring->fence_drv.lock, flags);
+	/* signal the guilty fence */
+	amdgpu_fence_write(ring, (u32)af->base.seqno);
+	amdgpu_fence_process(ring);
 }
 
-void amdgpu_fence_save_wptr(struct dma_fence *fence)
+void amdgpu_fence_save_wptr(struct amdgpu_fence *af)
 {
-	struct amdgpu_fence *am_fence = container_of(fence, struct amdgpu_fence, base);
-
-	am_fence->wptr = am_fence->ring->wptr;
+	af->wptr = af->ring->wptr;
 }
 
 static void amdgpu_ring_backup_unprocessed_command(struct amdgpu_ring *ring,
@@ -790,14 +762,19 @@ void amdgpu_ring_backup_unprocessed_commands(struct amdgpu_ring *ring,
 	struct dma_fence *unprocessed;
 	struct dma_fence __rcu **ptr;
 	struct amdgpu_fence *fence;
-	u64 wptr, i, seqno;
+	u64 wptr;
+	u32 seq, last_seq;
 
-	seqno = amdgpu_fence_read(ring);
+	last_seq = amdgpu_fence_read(ring) & ring->fence_drv.num_fences_mask;
+	seq = ring->fence_drv.sync_seq & ring->fence_drv.num_fences_mask;
 	wptr = ring->fence_drv.signalled_wptr;
 	ring->ring_backup_entries_to_copy = 0;
 
-	for (i = seqno + 1; i <= ring->fence_drv.sync_seq; ++i) {
-		ptr = &ring->fence_drv.fences[i & ring->fence_drv.num_fences_mask];
+	do {
+		last_seq++;
+		last_seq &= ring->fence_drv.num_fences_mask;
+
+		ptr = &ring->fence_drv.fences[last_seq];
 		rcu_read_lock();
 		unprocessed = rcu_dereference(*ptr);
 
@@ -813,7 +790,7 @@ void amdgpu_ring_backup_unprocessed_commands(struct amdgpu_ring *ring,
 			wptr = fence->wptr;
 		}
 		rcu_read_unlock();
-	}
+	} while (last_seq != seq);
 }
 
 /*
@@ -830,13 +807,6 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
 	return (const char *)to_amdgpu_fence(f)->ring->name;
 }
 
-static const char *amdgpu_job_fence_get_timeline_name(struct dma_fence *f)
-{
-	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base);
-
-	return (const char *)to_amdgpu_ring(job->base.sched)->name;
-}
-
 /**
  * amdgpu_fence_enable_signaling - enable signalling on fence
  * @f: fence
@@ -854,23 +824,6 @@ static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
 }
 
 /**
- * amdgpu_job_fence_enable_signaling - enable signalling on job fence
- * @f: fence
- *
- * This is the simliar function with amdgpu_fence_enable_signaling above, it
- * only handles the job embedded fence.
- */
-static bool amdgpu_job_fence_enable_signaling(struct dma_fence *f)
-{
-	struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence.base);
-
-	if (!timer_pending(&to_amdgpu_ring(job->base.sched)->fence_drv.fallback_timer))
-		amdgpu_fence_schedule_fallback(to_amdgpu_ring(job->base.sched));
-
-	return true;
-}
-
-/**
  * amdgpu_fence_free - free up the fence memory
  *
  * @rcu: RCU callback head
@@ -886,21 +839,6 @@ static void amdgpu_fence_free(struct rcu_head *rcu)
 }
 
 /**
- * amdgpu_job_fence_free - free up the job with embedded fence
- *
- * @rcu: RCU callback head
- *
- * Free up the job with embedded fence after the RCU grace period.
- */
-static void amdgpu_job_fence_free(struct rcu_head *rcu)
-{
-	struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
-
-	/* free job if fence has a parent job */
-	kfree(container_of(f, struct amdgpu_job, hw_fence.base));
-}
-
-/**
  * amdgpu_fence_release - callback that fence can be freed
  *
  * @f: fence
@@ -913,19 +851,6 @@ static void amdgpu_fence_release(struct dma_fence *f)
 	call_rcu(&f->rcu, amdgpu_fence_free);
 }
 
-/**
- * amdgpu_job_fence_release - callback that job embedded fence can be freed
- *
- * @f: fence
- *
- * This is the simliar function with amdgpu_fence_release above, it
- * only handles the job embedded fence.
- */
-static void amdgpu_job_fence_release(struct dma_fence *f)
-{
-	call_rcu(&f->rcu, amdgpu_job_fence_free);
-}
-
 static const struct dma_fence_ops amdgpu_fence_ops = {
 	.get_driver_name = amdgpu_fence_get_driver_name,
 	.get_timeline_name = amdgpu_fence_get_timeline_name,
@@ -933,13 +858,6 @@ static const struct dma_fence_ops amdgpu_fence_ops = {
 	.release = amdgpu_fence_release,
 };
 
-static const struct dma_fence_ops amdgpu_job_fence_ops = {
-	.get_driver_name = amdgpu_fence_get_driver_name,
-	.get_timeline_name = amdgpu_job_fence_get_timeline_name,
-	.enable_signaling = amdgpu_job_fence_enable_signaling,
-	.release = amdgpu_job_fence_release,
-};
-
 /*
  * Fence debugfs
  */
@@ -1009,7 +927,6 @@ static int gpu_recover_get(void *data, u64 *val)
 
 	*val = atomic_read(&adev->reset_domain->reset_res);
 
-	pm_runtime_mark_last_busy(dev->dev);
 	pm_runtime_put_autosuspend(dev->dev);
 
 	return 0;