drm/amdgpu: make pipeline sync be in same place v2

v2: directly return for 'if' case.

Signed-off-by: Chunming Zhou <David1.Zhou@amd.com>
Reviewed-by: Christian König <christian.koenig@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
This commit is contained in:
Chunming Zhou 2017-05-11 14:52:48 -04:00 committed by Alex Deucher
parent df83d1ebc9
commit b9bf33d5ac
5 changed files with 34 additions and 8 deletions

View File

@ -1132,7 +1132,6 @@ struct amdgpu_job {
void *owner;
uint64_t fence_ctx; /* the fence_context this job uses */
bool vm_needs_flush;
bool need_pipeline_sync;
unsigned vm_id;
uint64_t vm_pd_addr;
uint32_t gds_base, gds_size;

View File

@ -121,7 +121,7 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
{
struct amdgpu_device *adev = ring->adev;
struct amdgpu_ib *ib = &ibs[0];
struct dma_fence *tmp;
struct dma_fence *tmp = NULL;
bool skip_preamble, need_ctx_switch;
unsigned patch_offset = ~0;
struct amdgpu_vm *vm;
@ -163,8 +163,8 @@ int amdgpu_ib_schedule(struct amdgpu_ring *ring, unsigned num_ibs,
}
if (ring->funcs->emit_pipeline_sync && job &&
(tmp = amdgpu_sync_get_fence(&job->sched_sync))) {
job->need_pipeline_sync = true;
((tmp = amdgpu_sync_get_fence(&job->sched_sync)) ||
amdgpu_vm_need_pipeline_sync(ring, job))) {
amdgpu_ring_emit_pipeline_sync(ring);
dma_fence_put(tmp);
}

View File

@ -57,7 +57,6 @@ int amdgpu_job_alloc(struct amdgpu_device *adev, unsigned num_ibs,
(*job)->vm = vm;
(*job)->ibs = (void *)&(*job)[1];
(*job)->num_ibs = num_ibs;
(*job)->need_pipeline_sync = false;
amdgpu_sync_create(&(*job)->sync);
amdgpu_sync_create(&(*job)->sched_sync);

View File

@ -694,6 +694,35 @@ static u64 amdgpu_vm_adjust_mc_addr(struct amdgpu_device *adev, u64 mc_addr)
return addr;
}
bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
struct amdgpu_job *job)
{
struct amdgpu_device *adev = ring->adev;
unsigned vmhub = ring->funcs->vmhub;
struct amdgpu_vm_id_manager *id_mgr = &adev->vm_manager.id_mgr[vmhub];
struct amdgpu_vm_id *id;
bool gds_switch_needed;
bool vm_flush_needed = job->vm_needs_flush ||
amdgpu_vm_ring_has_compute_vm_bug(ring);
if (job->vm_id == 0)
return false;
id = &id_mgr->ids[job->vm_id];
gds_switch_needed = ring->funcs->emit_gds_switch && (
id->gds_base != job->gds_base ||
id->gds_size != job->gds_size ||
id->gws_base != job->gws_base ||
id->gws_size != job->gws_size ||
id->oa_base != job->oa_base ||
id->oa_size != job->oa_size);
if (amdgpu_vm_had_gpu_reset(adev, id))
return true;
if (!vm_flush_needed && !gds_switch_needed)
return false;
return true;
}
/**
* amdgpu_vm_flush - hardware flush the vm
*
@ -732,9 +761,6 @@ int amdgpu_vm_flush(struct amdgpu_ring *ring, struct amdgpu_job *job)
if (ring->funcs->init_cond_exec)
patch_offset = amdgpu_ring_init_cond_exec(ring);
if (ring->funcs->emit_pipeline_sync && !job->need_pipeline_sync)
amdgpu_ring_emit_pipeline_sync(ring);
if (ring->funcs->emit_vm_flush && vm_flush_needed) {
u64 pd_addr = amdgpu_vm_adjust_mc_addr(adev, job->vm_pd_addr);
struct dma_fence *fence;

View File

@ -245,5 +245,7 @@ void amdgpu_vm_bo_rmv(struct amdgpu_device *adev,
struct amdgpu_bo_va *bo_va);
void amdgpu_vm_adjust_size(struct amdgpu_device *adev, uint64_t vm_size);
int amdgpu_vm_ioctl(struct drm_device *dev, void *data, struct drm_file *filp);
bool amdgpu_vm_need_pipeline_sync(struct amdgpu_ring *ring,
struct amdgpu_job *job);
#endif