---
V1 -> V2: add another amdgpu_fence_ops which is for job-embedded fence.
V2 -> V3: use amdgpu_fence_driver_clear_job_fences abstract the job fence
clearing operation.
---
drivers/gpu/drm/amd/amdgpu/amdgpu_device.c | 11 +-
drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c | 126 ++++++++++++++-------
drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h | 4 +-
3 files changed, 90 insertions(+), 51 deletions(-)
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
index 5625f7736e37..fecf7a09e5a2 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
@@ -4456,7 +4456,7 @@ int amdgpu_device_mode1_reset(struct amdgpu_device *adev)
int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
struct amdgpu_reset_context *reset_context)
{
- int i, j, r = 0;
+ int i, r = 0;
struct amdgpu_job *job = NULL;
bool need_full_reset =
test_bit(AMDGPU_NEED_FULL_RESET, &reset_context->flags);
@@ -4478,15 +4478,8 @@ int amdgpu_device_pre_asic_reset(struct amdgpu_device *adev,
/*clear job fence from fence drv to avoid force_completion
*leave NULL and vm flush fence in fence drv */
- for (j = 0; j <= ring->fence_drv.num_fences_mask; j++) {
- struct dma_fence *old, **ptr;
+ amdgpu_fence_driver_clear_job_fences(ring);
- ptr = &ring->fence_drv.fences[j];
- old = rcu_dereference_protected(*ptr, 1);
- if (old && test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &old->flags)) {
- RCU_INIT_POINTER(*ptr, NULL);
- }
- }
/* after all hw jobs are reset, hw fence is meaningless, so force_completion */
amdgpu_fence_driver_force_completion(ring);
}
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
index 3b7e86ea7167..db41d16838b9 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_fence.c
@@ -77,11 +77,13 @@ void amdgpu_fence_slab_fini(void)
* 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)
+ if (__f->base.ops == &amdgpu_fence_ops ||
+ __f->base.ops == &amdgpu_job_fence_ops)
return __f;
return NULL;
@@ -158,19 +160,18 @@ int amdgpu_fence_emit(struct amdgpu_ring *ring, struct dma_fence **f, struct amd
}
seq = ++ring->fence_drv.sync_seq;
- if (job != NULL && job->job_run_counter) {
+ if (job && job->job_run_counter) {
/* reinit seq for resubmitted jobs */
fence->seqno = seq;
} else {
- dma_fence_init(fence, &amdgpu_fence_ops,
- &ring->fence_drv.lock,
- adev->fence_context + ring->idx,
- seq);
- }
-
- if (job != NULL) {
- /* mark this fence has a parent job */
- set_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &fence->flags);
+ if (job)
+ dma_fence_init(fence, &amdgpu_job_fence_ops,
+ &ring->fence_drv.lock,
+ adev->fence_context + ring->idx, seq);
+ else
+ 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,
@@ -620,6 +621,25 @@ void amdgpu_fence_driver_hw_init(struct amdgpu_device *adev)
}
}
+/**
+ * amdgpu_fence_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)
+ RCU_INIT_POINTER(*ptr, NULL);
+ }
+}
+
/**
* amdgpu_fence_driver_force_completion - force signal latest fence of ring
*
@@ -643,16 +663,14 @@ static const char *amdgpu_fence_get_driver_name(struct dma_fence *fence)
static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
{
- struct amdgpu_ring *ring;
+ return (const char *)to_amdgpu_fence(f)->ring->name;
+}
- if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
- struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+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);
- ring = to_amdgpu_ring(job->base.sched);
- } else {
- ring = to_amdgpu_fence(f)->ring;
- }
- return (const char *)ring->name;
+ return (const char *)to_amdgpu_ring(job->base.sched)->name;
}
/**
@@ -665,18 +683,25 @@ static const char *amdgpu_fence_get_timeline_name(struct dma_fence *f)
*/
static bool amdgpu_fence_enable_signaling(struct dma_fence *f)
{
- struct amdgpu_ring *ring;
+ if (!timer_pending(&to_amdgpu_fence(f)->ring->fence_drv.fallback_timer))
+ amdgpu_fence_schedule_fallback(to_amdgpu_fence(f)->ring);
- if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
- struct amdgpu_job *job = container_of(f, struct amdgpu_job, hw_fence);
+ return true;
+}
- ring = to_amdgpu_ring(job->base.sched);
- } else {
- ring = to_amdgpu_fence(f)->ring;
- }
+/**
+ * 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);
- if (!timer_pending(&ring->fence_drv.fallback_timer))
- amdgpu_fence_schedule_fallback(ring);
+ 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;
}
@@ -692,19 +717,23 @@ static void amdgpu_fence_free(struct rcu_head *rcu)
{
struct dma_fence *f = container_of(rcu, struct dma_fence, rcu);
- if (test_bit(AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT, &f->flags)) {
- /* free job if fence has a parent job */
- struct amdgpu_job *job;
-
- job = container_of(f, struct amdgpu_job, hw_fence);
- kfree(job);
- } else {
/* free fence_slab if it's separated fence*/
- struct amdgpu_fence *fence;
+ kmem_cache_free(amdgpu_fence_slab, to_amdgpu_fence(f));
+}
- fence = to_amdgpu_fence(f);
- kmem_cache_free(amdgpu_fence_slab, fence);
- }
+/**
+ * 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));
}
/**
@@ -720,6 +749,19 @@ 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,
@@ -727,6 +769,12 @@ 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
diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
index 4d380e79752c..fae7d185ad0d 100644
--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
+++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
@@ -53,9 +53,6 @@ enum amdgpu_ring_priority_level {
#define AMDGPU_FENCE_FLAG_INT (1 << 1)
#define AMDGPU_FENCE_FLAG_TC_WB_ONLY (1 << 2)
-/* fence flag bit to indicate the face is embedded in job*/
-#define AMDGPU_FENCE_FLAG_EMBED_IN_JOB_BIT (DMA_FENCE_FLAG_USER_BITS + 1)
-
#define to_amdgpu_ring(s) container_of((s), struct amdgpu_ring, sched)
#define AMDGPU_IB_POOL_SIZE (1024 * 1024)
@@ -114,6 +111,7 @@ struct amdgpu_fence_driver {
struct dma_fence **fences;
};
+void amdgpu_fence_driver_clear_job_fences(struct amdgpu_ring *ring);
void amdgpu_fence_driver_force_completion(struct amdgpu_ring *ring);
int amdgpu_fence_driver_init_ring(struct amdgpu_ring *ring,
